| 189 89 190 189 191 173 173 175 175 175 73 175 74 109 56 109 175 173 175 129 71 71 71 71 71 8 174 188 174 34 34 187 51 51 51 51 51 51 51 51 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 | /* * Copyright (C) 2014 Red Hat * Author: Rob Clark <robdclark@gmail.com> * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the "Software"), * to deal in the Software without restriction, including without limitation * the rights to use, copy, modify, merge, publish, distribute, sublicense, * and/or sell copies of the Software, and to permit persons to whom the * Software is furnished to do so, subject to the following conditions: * * The above copyright notice and this permission notice shall be included in * all copies or substantial portions of the Software. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR * OTHER DEALINGS IN THE SOFTWARE. */ #include <drm/drm_atomic.h> #include <drm/drm_crtc.h> #include <drm/drm_device.h> #include <drm/drm_modeset_lock.h> #include <drm/drm_print.h> /** * DOC: kms locking * * As KMS moves toward more fine grained locking, and atomic ioctl where * userspace can indirectly control locking order, it becomes necessary * to use &ww_mutex and acquire-contexts to avoid deadlocks. But because * the locking is more distributed around the driver code, we want a bit * of extra utility/tracking out of our acquire-ctx. This is provided * by &struct drm_modeset_lock and &struct drm_modeset_acquire_ctx. * * For basic principles of &ww_mutex, see: Documentation/locking/ww-mutex-design.rst * * The basic usage pattern is to:: * * drm_modeset_acquire_init(ctx, DRM_MODESET_ACQUIRE_INTERRUPTIBLE) * retry: * foreach (lock in random_ordered_set_of_locks) { * ret = drm_modeset_lock(lock, ctx) * if (ret == -EDEADLK) { * ret = drm_modeset_backoff(ctx); * if (!ret) * goto retry; * } * if (ret) * goto out; * } * ... do stuff ... * out: * drm_modeset_drop_locks(ctx); * drm_modeset_acquire_fini(ctx); * * For convenience this control flow is implemented in * DRM_MODESET_LOCK_ALL_BEGIN() and DRM_MODESET_LOCK_ALL_END() for the case * where all modeset locks need to be taken through drm_modeset_lock_all_ctx(). * * If all that is needed is a single modeset lock, then the &struct * drm_modeset_acquire_ctx is not needed and the locking can be simplified * by passing a NULL instead of ctx in the drm_modeset_lock() call or * calling drm_modeset_lock_single_interruptible(). To unlock afterwards * call drm_modeset_unlock(). * * On top of these per-object locks using &ww_mutex there's also an overall * &drm_mode_config.mutex, for protecting everything else. Mostly this means * probe state of connectors, and preventing hotplug add/removal of connectors. * * Finally there's a bunch of dedicated locks to protect drm core internal * lists and lookup data structures. */ static DEFINE_WW_CLASS(crtc_ww_class); #if IS_ENABLED(CONFIG_DRM_DEBUG_MODESET_LOCK) static noinline depot_stack_handle_t __drm_stack_depot_save(void) { unsigned long entries[8]; unsigned int n; n = stack_trace_save(entries, ARRAY_SIZE(entries), 1); return stack_depot_save(entries, n, GFP_NOWAIT | __GFP_NOWARN); } static void __drm_stack_depot_print(depot_stack_handle_t stack_depot) { struct drm_printer p = drm_dbg_printer(NULL, DRM_UT_KMS, "drm_modeset_lock"); unsigned long *entries; unsigned int nr_entries; char *buf; buf = kmalloc(PAGE_SIZE, GFP_NOWAIT | __GFP_NOWARN); if (!buf) return; nr_entries = stack_depot_fetch(stack_depot, &entries); stack_trace_snprint(buf, PAGE_SIZE, entries, nr_entries, 2); drm_printf(&p, "attempting to lock a contended lock without backoff:\n%s", buf); kfree(buf); } static void __drm_stack_depot_init(void) { stack_depot_init(); } #else /* CONFIG_DRM_DEBUG_MODESET_LOCK */ static depot_stack_handle_t __drm_stack_depot_save(void) { return 0; } static void __drm_stack_depot_print(depot_stack_handle_t stack_depot) { } static void __drm_stack_depot_init(void) { } #endif /* CONFIG_DRM_DEBUG_MODESET_LOCK */ /** * drm_modeset_lock_all - take all modeset locks * @dev: DRM device * * This function takes all modeset locks, suitable where a more fine-grained * scheme isn't (yet) implemented. Locks must be dropped by calling the * drm_modeset_unlock_all() function. * * This function is deprecated. It allocates a lock acquisition context and * stores it in &drm_device.mode_config. This facilitate conversion of * existing code because it removes the need to manually deal with the * acquisition context, but it is also brittle because the context is global * and care must be taken not to nest calls. New code should use the * drm_modeset_lock_all_ctx() function and pass in the context explicitly. */ void drm_modeset_lock_all(struct drm_device *dev) { struct drm_mode_config *config = &dev->mode_config; struct drm_modeset_acquire_ctx *ctx; int ret; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL | __GFP_NOFAIL); if (WARN_ON(!ctx)) return; mutex_lock(&config->mutex); drm_modeset_acquire_init(ctx, 0); retry: ret = drm_modeset_lock_all_ctx(dev, ctx); if (ret < 0) { if (ret == -EDEADLK) { drm_modeset_backoff(ctx); goto retry; } drm_modeset_acquire_fini(ctx); kfree(ctx); return; } ww_acquire_done(&ctx->ww_ctx); WARN_ON(config->acquire_ctx); /* * We hold the locks now, so it is safe to stash the acquisition * context for drm_modeset_unlock_all(). */ config->acquire_ctx = ctx; drm_warn_on_modeset_not_all_locked(dev); } EXPORT_SYMBOL(drm_modeset_lock_all); /** * drm_modeset_unlock_all - drop all modeset locks * @dev: DRM device * * This function drops all modeset locks taken by a previous call to the * drm_modeset_lock_all() function. * * This function is deprecated. It uses the lock acquisition context stored * in &drm_device.mode_config. This facilitates conversion of existing * code because it removes the need to manually deal with the acquisition * context, but it is also brittle because the context is global and care must * be taken not to nest calls. New code should pass the acquisition context * directly to the drm_modeset_drop_locks() function. */ void drm_modeset_unlock_all(struct drm_device *dev) { struct drm_mode_config *config = &dev->mode_config; struct drm_modeset_acquire_ctx *ctx = config->acquire_ctx; if (WARN_ON(!ctx)) return; config->acquire_ctx = NULL; drm_modeset_drop_locks(ctx); drm_modeset_acquire_fini(ctx); kfree(ctx); mutex_unlock(&dev->mode_config.mutex); } EXPORT_SYMBOL(drm_modeset_unlock_all); /** * drm_warn_on_modeset_not_all_locked - check that all modeset locks are locked * @dev: device * * Useful as a debug assert. */ void drm_warn_on_modeset_not_all_locked(struct drm_device *dev) { struct drm_crtc *crtc; /* Locking is currently fubar in the panic handler. */ if (oops_in_progress) return; drm_for_each_crtc(crtc, dev) WARN_ON(!drm_modeset_is_locked(&crtc->mutex)); WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex)); WARN_ON(!mutex_is_locked(&dev->mode_config.mutex)); } EXPORT_SYMBOL(drm_warn_on_modeset_not_all_locked); /** * drm_modeset_acquire_init - initialize acquire context * @ctx: the acquire context * @flags: 0 or %DRM_MODESET_ACQUIRE_INTERRUPTIBLE * * When passing %DRM_MODESET_ACQUIRE_INTERRUPTIBLE to @flags, * all calls to drm_modeset_lock() will perform an interruptible * wait. */ void drm_modeset_acquire_init(struct drm_modeset_acquire_ctx *ctx, uint32_t flags) { memset(ctx, 0, sizeof(*ctx)); ww_acquire_init(&ctx->ww_ctx, &crtc_ww_class); INIT_LIST_HEAD(&ctx->locked); if (flags & DRM_MODESET_ACQUIRE_INTERRUPTIBLE) ctx->interruptible = true; } EXPORT_SYMBOL(drm_modeset_acquire_init); /** * drm_modeset_acquire_fini - cleanup acquire context * @ctx: the acquire context */ void drm_modeset_acquire_fini(struct drm_modeset_acquire_ctx *ctx) { ww_acquire_fini(&ctx->ww_ctx); } EXPORT_SYMBOL(drm_modeset_acquire_fini); /** * drm_modeset_drop_locks - drop all locks * @ctx: the acquire context * * Drop all locks currently held against this acquire context. */ void drm_modeset_drop_locks(struct drm_modeset_acquire_ctx *ctx) { if (WARN_ON(ctx->contended)) __drm_stack_depot_print(ctx->stack_depot); while (!list_empty(&ctx->locked)) { struct drm_modeset_lock *lock; lock = list_first_entry(&ctx->locked, struct drm_modeset_lock, head); drm_modeset_unlock(lock); } } EXPORT_SYMBOL(drm_modeset_drop_locks); static inline int modeset_lock(struct drm_modeset_lock *lock, struct drm_modeset_acquire_ctx *ctx, bool interruptible, bool slow) { int ret; if (WARN_ON(ctx->contended)) __drm_stack_depot_print(ctx->stack_depot); if (ctx->trylock_only) { lockdep_assert_held(&ctx->ww_ctx); if (!ww_mutex_trylock(&lock->mutex, NULL)) return -EBUSY; else return 0; } else if (interruptible && slow) { ret = ww_mutex_lock_slow_interruptible(&lock->mutex, &ctx->ww_ctx); } else if (interruptible) { ret = ww_mutex_lock_interruptible(&lock->mutex, &ctx->ww_ctx); } else if (slow) { ww_mutex_lock_slow(&lock->mutex, &ctx->ww_ctx); ret = 0; } else { ret = ww_mutex_lock(&lock->mutex, &ctx->ww_ctx); } if (!ret) { WARN_ON(!list_empty(&lock->head)); list_add(&lock->head, &ctx->locked); } else if (ret == -EALREADY) { /* we already hold the lock.. this is fine. For atomic * we will need to be able to drm_modeset_lock() things * without having to keep track of what is already locked * or not. */ ret = 0; } else if (ret == -EDEADLK) { ctx->contended = lock; ctx->stack_depot = __drm_stack_depot_save(); } return ret; } /** * drm_modeset_backoff - deadlock avoidance backoff * @ctx: the acquire context * * If deadlock is detected (ie. drm_modeset_lock() returns -EDEADLK), * you must call this function to drop all currently held locks and * block until the contended lock becomes available. * * This function returns 0 on success, or -ERESTARTSYS if this context * is initialized with %DRM_MODESET_ACQUIRE_INTERRUPTIBLE and the * wait has been interrupted. */ int drm_modeset_backoff(struct drm_modeset_acquire_ctx *ctx) { struct drm_modeset_lock *contended = ctx->contended; ctx->contended = NULL; ctx->stack_depot = 0; if (WARN_ON(!contended)) return 0; drm_modeset_drop_locks(ctx); return modeset_lock(contended, ctx, ctx->interruptible, true); } EXPORT_SYMBOL(drm_modeset_backoff); /** * drm_modeset_lock_init - initialize lock * @lock: lock to init */ void drm_modeset_lock_init(struct drm_modeset_lock *lock) { ww_mutex_init(&lock->mutex, &crtc_ww_class); INIT_LIST_HEAD(&lock->head); __drm_stack_depot_init(); } EXPORT_SYMBOL(drm_modeset_lock_init); /** * drm_modeset_lock - take modeset lock * @lock: lock to take * @ctx: acquire ctx * * If @ctx is not NULL, then its ww acquire context is used and the * lock will be tracked by the context and can be released by calling * drm_modeset_drop_locks(). If -EDEADLK is returned, this means a * deadlock scenario has been detected and it is an error to attempt * to take any more locks without first calling drm_modeset_backoff(). * * If the @ctx is not NULL and initialized with * %DRM_MODESET_ACQUIRE_INTERRUPTIBLE, this function will fail with * -ERESTARTSYS when interrupted. * * If @ctx is NULL then the function call behaves like a normal, * uninterruptible non-nesting mutex_lock() call. */ int drm_modeset_lock(struct drm_modeset_lock *lock, struct drm_modeset_acquire_ctx *ctx) { if (ctx) return modeset_lock(lock, ctx, ctx->interruptible, false); ww_mutex_lock(&lock->mutex, NULL); return 0; } EXPORT_SYMBOL(drm_modeset_lock); /** * drm_modeset_lock_single_interruptible - take a single modeset lock * @lock: lock to take * * This function behaves as drm_modeset_lock() with a NULL context, * but performs interruptible waits. * * This function returns 0 on success, or -ERESTARTSYS when interrupted. */ int drm_modeset_lock_single_interruptible(struct drm_modeset_lock *lock) { return ww_mutex_lock_interruptible(&lock->mutex, NULL); } EXPORT_SYMBOL(drm_modeset_lock_single_interruptible); /** * drm_modeset_unlock - drop modeset lock * @lock: lock to release */ void drm_modeset_unlock(struct drm_modeset_lock *lock) { list_del_init(&lock->head); ww_mutex_unlock(&lock->mutex); } EXPORT_SYMBOL(drm_modeset_unlock); /** * drm_modeset_lock_all_ctx - take all modeset locks * @dev: DRM device * @ctx: lock acquisition context * * This function takes all modeset locks, suitable where a more fine-grained * scheme isn't (yet) implemented. * * Unlike drm_modeset_lock_all(), it doesn't take the &drm_mode_config.mutex * since that lock isn't required for modeset state changes. Callers which * need to grab that lock too need to do so outside of the acquire context * @ctx. * * Locks acquired with this function should be released by calling the * drm_modeset_drop_locks() function on @ctx. * * See also: DRM_MODESET_LOCK_ALL_BEGIN() and DRM_MODESET_LOCK_ALL_END() * * Returns: 0 on success or a negative error-code on failure. */ int drm_modeset_lock_all_ctx(struct drm_device *dev, struct drm_modeset_acquire_ctx *ctx) { struct drm_private_obj *privobj; struct drm_crtc *crtc; struct drm_plane *plane; int ret; ret = drm_modeset_lock(&dev->mode_config.connection_mutex, ctx); if (ret) return ret; drm_for_each_crtc(crtc, dev) { ret = drm_modeset_lock(&crtc->mutex, ctx); if (ret) return ret; } drm_for_each_plane(plane, dev) { ret = drm_modeset_lock(&plane->mutex, ctx); if (ret) return ret; } drm_for_each_privobj(privobj, dev) { ret = drm_modeset_lock(&privobj->lock, ctx); if (ret) return ret; } return 0; } EXPORT_SYMBOL(drm_modeset_lock_all_ctx); |
| 10 5 5 5 2 1 1 1 1 1 1 1 5 5 5 5 5 5 5 1142 1 1139 1142 6 5 5 5 5 1 1 1 1 1 1 1 1 1 17 17 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 | // SPDX-License-Identifier: GPL-2.0-only /* * CAIF Interface registration. * Copyright (C) ST-Ericsson AB 2010 * Author: Sjur Brendeland * * Borrowed heavily from file: pn_dev.c. Thanks to Remi Denis-Courmont * and Sakari Ailus <sakari.ailus@nokia.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ":%s(): " fmt, __func__ #include <linux/kernel.h> #include <linux/if_arp.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/mutex.h> #include <linux/module.h> #include <linux/spinlock.h> #include <net/netns/generic.h> #include <net/net_namespace.h> #include <net/pkt_sched.h> #include <net/caif/caif_device.h> #include <net/caif/caif_layer.h> #include <net/caif/caif_dev.h> #include <net/caif/cfpkt.h> #include <net/caif/cfcnfg.h> #include <net/caif/cfserl.h> MODULE_DESCRIPTION("ST-Ericsson CAIF modem protocol support"); MODULE_LICENSE("GPL"); /* Used for local tracking of the CAIF net devices */ struct caif_device_entry { struct cflayer layer; struct list_head list; struct net_device *netdev; int __percpu *pcpu_refcnt; spinlock_t flow_lock; struct sk_buff *xoff_skb; void (*xoff_skb_dtor)(struct sk_buff *skb); bool xoff; }; struct caif_device_entry_list { struct list_head list; /* Protects simulanous deletes in list */ struct mutex lock; }; struct caif_net { struct cfcnfg *cfg; struct caif_device_entry_list caifdevs; }; static unsigned int caif_net_id; static int q_high = 50; /* Percent */ struct cfcnfg *get_cfcnfg(struct net *net) { struct caif_net *caifn; caifn = net_generic(net, caif_net_id); return caifn->cfg; } EXPORT_SYMBOL(get_cfcnfg); static struct caif_device_entry_list *caif_device_list(struct net *net) { struct caif_net *caifn; caifn = net_generic(net, caif_net_id); return &caifn->caifdevs; } static void caifd_put(struct caif_device_entry *e) { this_cpu_dec(*e->pcpu_refcnt); } static void caifd_hold(struct caif_device_entry *e) { this_cpu_inc(*e->pcpu_refcnt); } static int caifd_refcnt_read(struct caif_device_entry *e) { int i, refcnt = 0; for_each_possible_cpu(i) refcnt += *per_cpu_ptr(e->pcpu_refcnt, i); return refcnt; } /* Allocate new CAIF device. */ static struct caif_device_entry *caif_device_alloc(struct net_device *dev) { struct caif_device_entry *caifd; caifd = kzalloc(sizeof(*caifd), GFP_KERNEL); if (!caifd) return NULL; caifd->pcpu_refcnt = alloc_percpu(int); if (!caifd->pcpu_refcnt) { kfree(caifd); return NULL; } caifd->netdev = dev; dev_hold(dev); return caifd; } static struct caif_device_entry *caif_get(struct net_device *dev) { struct caif_device_entry_list *caifdevs = caif_device_list(dev_net(dev)); struct caif_device_entry *caifd; list_for_each_entry_rcu(caifd, &caifdevs->list, list, lockdep_rtnl_is_held()) { if (caifd->netdev == dev) return caifd; } return NULL; } static void caif_flow_cb(struct sk_buff *skb) { struct caif_device_entry *caifd; void (*dtor)(struct sk_buff *skb) = NULL; bool send_xoff; WARN_ON(skb->dev == NULL); rcu_read_lock(); caifd = caif_get(skb->dev); WARN_ON(caifd == NULL); if (!caifd) { rcu_read_unlock(); return; } caifd_hold(caifd); rcu_read_unlock(); spin_lock_bh(&caifd->flow_lock); send_xoff = caifd->xoff; caifd->xoff = false; dtor = caifd->xoff_skb_dtor; if (WARN_ON(caifd->xoff_skb != skb)) skb = NULL; caifd->xoff_skb = NULL; caifd->xoff_skb_dtor = NULL; spin_unlock_bh(&caifd->flow_lock); if (dtor && skb) dtor(skb); if (send_xoff) caifd->layer.up-> ctrlcmd(caifd->layer.up, _CAIF_CTRLCMD_PHYIF_FLOW_ON_IND, caifd->layer.id); caifd_put(caifd); } static int transmit(struct cflayer *layer, struct cfpkt *pkt) { int err, high = 0, qlen = 0; struct caif_device_entry *caifd = container_of(layer, struct caif_device_entry, layer); struct sk_buff *skb; struct netdev_queue *txq; rcu_read_lock_bh(); skb = cfpkt_tonative(pkt); skb->dev = caifd->netdev; skb_reset_network_header(skb); skb->protocol = htons(ETH_P_CAIF); /* Check if we need to handle xoff */ if (likely(caifd->netdev->priv_flags & IFF_NO_QUEUE)) goto noxoff; if (unlikely(caifd->xoff)) goto noxoff; if (likely(!netif_queue_stopped(caifd->netdev))) { struct Qdisc *sch; /* If we run with a TX queue, check if the queue is too long*/ txq = netdev_get_tx_queue(skb->dev, 0); sch = rcu_dereference_bh(txq->qdisc); if (likely(qdisc_is_empty(sch))) goto noxoff; /* can check for explicit qdisc len value only !NOLOCK, * always set flow off otherwise */ high = (caifd->netdev->tx_queue_len * q_high) / 100; if (!(sch->flags & TCQ_F_NOLOCK) && likely(sch->q.qlen < high)) goto noxoff; } /* Hold lock while accessing xoff */ spin_lock_bh(&caifd->flow_lock); if (caifd->xoff) { spin_unlock_bh(&caifd->flow_lock); goto noxoff; } /* * Handle flow off, we do this by temporary hi-jacking this * skb's destructor function, and replace it with our own * flow-on callback. The callback will set flow-on and call * the original destructor. */ pr_debug("queue has stopped(%d) or is full (%d > %d)\n", netif_queue_stopped(caifd->netdev), qlen, high); caifd->xoff = true; caifd->xoff_skb = skb; caifd->xoff_skb_dtor = skb->destructor; skb->destructor = caif_flow_cb; spin_unlock_bh(&caifd->flow_lock); caifd->layer.up->ctrlcmd(caifd->layer.up, _CAIF_CTRLCMD_PHYIF_FLOW_OFF_IND, caifd->layer.id); noxoff: rcu_read_unlock_bh(); err = dev_queue_xmit(skb); if (err > 0) err = -EIO; return err; } /* * Stuff received packets into the CAIF stack. * On error, returns non-zero and releases the skb. */ static int receive(struct sk_buff *skb, struct net_device *dev, struct packet_type *pkttype, struct net_device *orig_dev) { struct cfpkt *pkt; struct caif_device_entry *caifd; int err; pkt = cfpkt_fromnative(CAIF_DIR_IN, skb); rcu_read_lock(); caifd = caif_get(dev); if (!caifd || !caifd->layer.up || !caifd->layer.up->receive || !netif_oper_up(caifd->netdev)) { rcu_read_unlock(); kfree_skb(skb); return NET_RX_DROP; } /* Hold reference to netdevice while using CAIF stack */ caifd_hold(caifd); rcu_read_unlock(); err = caifd->layer.up->receive(caifd->layer.up, pkt); /* For -EILSEQ the packet is not freed so free it now */ if (err == -EILSEQ) cfpkt_destroy(pkt); /* Release reference to stack upwards */ caifd_put(caifd); if (err != 0) err = NET_RX_DROP; return err; } static struct packet_type caif_packet_type __read_mostly = { .type = cpu_to_be16(ETH_P_CAIF), .func = receive, }; static void dev_flowctrl(struct net_device *dev, int on) { struct caif_device_entry *caifd; rcu_read_lock(); caifd = caif_get(dev); if (!caifd || !caifd->layer.up || !caifd->layer.up->ctrlcmd) { rcu_read_unlock(); return; } caifd_hold(caifd); rcu_read_unlock(); caifd->layer.up->ctrlcmd(caifd->layer.up, on ? _CAIF_CTRLCMD_PHYIF_FLOW_ON_IND : _CAIF_CTRLCMD_PHYIF_FLOW_OFF_IND, caifd->layer.id); caifd_put(caifd); } int caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev, struct cflayer *link_support, int head_room, struct cflayer **layer, int (**rcv_func)(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *)) { struct caif_device_entry *caifd; enum cfcnfg_phy_preference pref; struct cfcnfg *cfg = get_cfcnfg(dev_net(dev)); struct caif_device_entry_list *caifdevs; int res; caifdevs = caif_device_list(dev_net(dev)); caifd = caif_device_alloc(dev); if (!caifd) return -ENOMEM; *layer = &caifd->layer; spin_lock_init(&caifd->flow_lock); switch (caifdev->link_select) { case CAIF_LINK_HIGH_BANDW: pref = CFPHYPREF_HIGH_BW; break; case CAIF_LINK_LOW_LATENCY: pref = CFPHYPREF_LOW_LAT; break; default: pref = CFPHYPREF_HIGH_BW; break; } mutex_lock(&caifdevs->lock); list_add_rcu(&caifd->list, &caifdevs->list); strscpy(caifd->layer.name, dev->name, sizeof(caifd->layer.name)); caifd->layer.transmit = transmit; res = cfcnfg_add_phy_layer(cfg, dev, &caifd->layer, pref, link_support, caifdev->use_fcs, head_room); mutex_unlock(&caifdevs->lock); if (rcv_func) *rcv_func = receive; return res; } EXPORT_SYMBOL(caif_enroll_dev); /* notify Caif of device events */ static int caif_device_notify(struct notifier_block *me, unsigned long what, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct caif_device_entry *caifd = NULL; struct caif_dev_common *caifdev; struct cfcnfg *cfg; struct cflayer *layer, *link_support; int head_room = 0; struct caif_device_entry_list *caifdevs; int res; cfg = get_cfcnfg(dev_net(dev)); caifdevs = caif_device_list(dev_net(dev)); caifd = caif_get(dev); if (caifd == NULL && dev->type != ARPHRD_CAIF) return 0; switch (what) { case NETDEV_REGISTER: if (caifd != NULL) break; caifdev = netdev_priv(dev); link_support = NULL; if (caifdev->use_frag) { head_room = 1; link_support = cfserl_create(dev->ifindex, caifdev->use_stx); if (!link_support) { pr_warn("Out of memory\n"); break; } } res = caif_enroll_dev(dev, caifdev, link_support, head_room, &layer, NULL); if (res) cfserl_release(link_support); caifdev->flowctrl = dev_flowctrl; break; case NETDEV_UP: rcu_read_lock(); caifd = caif_get(dev); if (caifd == NULL) { rcu_read_unlock(); break; } caifd->xoff = false; cfcnfg_set_phy_state(cfg, &caifd->layer, true); rcu_read_unlock(); break; case NETDEV_DOWN: rcu_read_lock(); caifd = caif_get(dev); if (!caifd || !caifd->layer.up || !caifd->layer.up->ctrlcmd) { rcu_read_unlock(); return -EINVAL; } cfcnfg_set_phy_state(cfg, &caifd->layer, false); caifd_hold(caifd); rcu_read_unlock(); caifd->layer.up->ctrlcmd(caifd->layer.up, _CAIF_CTRLCMD_PHYIF_DOWN_IND, caifd->layer.id); spin_lock_bh(&caifd->flow_lock); /* * Replace our xoff-destructor with original destructor. * We trust that skb->destructor *always* is called before * the skb reference is invalid. The hijacked SKB destructor * takes the flow_lock so manipulating the skb->destructor here * should be safe. */ if (caifd->xoff_skb_dtor != NULL && caifd->xoff_skb != NULL) caifd->xoff_skb->destructor = caifd->xoff_skb_dtor; caifd->xoff = false; caifd->xoff_skb_dtor = NULL; caifd->xoff_skb = NULL; spin_unlock_bh(&caifd->flow_lock); caifd_put(caifd); break; case NETDEV_UNREGISTER: mutex_lock(&caifdevs->lock); caifd = caif_get(dev); if (caifd == NULL) { mutex_unlock(&caifdevs->lock); break; } list_del_rcu(&caifd->list); /* * NETDEV_UNREGISTER is called repeatedly until all reference * counts for the net-device are released. If references to * caifd is taken, simply ignore NETDEV_UNREGISTER and wait for * the next call to NETDEV_UNREGISTER. * * If any packets are in flight down the CAIF Stack, * cfcnfg_del_phy_layer will return nonzero. * If no packets are in flight, the CAIF Stack associated * with the net-device un-registering is freed. */ if (caifd_refcnt_read(caifd) != 0 || cfcnfg_del_phy_layer(cfg, &caifd->layer) != 0) { pr_info("Wait for device inuse\n"); /* Enrole device if CAIF Stack is still in use */ list_add_rcu(&caifd->list, &caifdevs->list); mutex_unlock(&caifdevs->lock); break; } synchronize_rcu(); dev_put(caifd->netdev); free_percpu(caifd->pcpu_refcnt); kfree(caifd); mutex_unlock(&caifdevs->lock); break; } return 0; } static struct notifier_block caif_device_notifier = { .notifier_call = caif_device_notify, .priority = 0, }; /* Per-namespace Caif devices handling */ static int caif_init_net(struct net *net) { struct caif_net *caifn = net_generic(net, caif_net_id); INIT_LIST_HEAD(&caifn->caifdevs.list); mutex_init(&caifn->caifdevs.lock); caifn->cfg = cfcnfg_create(); if (!caifn->cfg) return -ENOMEM; return 0; } static void caif_exit_net(struct net *net) { struct caif_device_entry *caifd, *tmp; struct caif_device_entry_list *caifdevs = caif_device_list(net); struct cfcnfg *cfg = get_cfcnfg(net); rtnl_lock(); mutex_lock(&caifdevs->lock); list_for_each_entry_safe(caifd, tmp, &caifdevs->list, list) { int i = 0; list_del_rcu(&caifd->list); cfcnfg_set_phy_state(cfg, &caifd->layer, false); while (i < 10 && (caifd_refcnt_read(caifd) != 0 || cfcnfg_del_phy_layer(cfg, &caifd->layer) != 0)) { pr_info("Wait for device inuse\n"); msleep(250); i++; } synchronize_rcu(); dev_put(caifd->netdev); free_percpu(caifd->pcpu_refcnt); kfree(caifd); } cfcnfg_remove(cfg); mutex_unlock(&caifdevs->lock); rtnl_unlock(); } static struct pernet_operations caif_net_ops = { .init = caif_init_net, .exit = caif_exit_net, .id = &caif_net_id, .size = sizeof(struct caif_net), }; /* Initialize Caif devices list */ static int __init caif_device_init(void) { int result; result = register_pernet_subsys(&caif_net_ops); if (result) return result; register_netdevice_notifier(&caif_device_notifier); dev_add_pack(&caif_packet_type); return result; } static void __exit caif_device_exit(void) { unregister_netdevice_notifier(&caif_device_notifier); dev_remove_pack(&caif_packet_type); unregister_pernet_subsys(&caif_net_ops); } module_init(caif_device_init); module_exit(caif_device_exit); |
| 92 92 92 65 54 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 | // SPDX-License-Identifier: GPL-2.0+ /* * Serial core port device driver * * Copyright (C) 2023 Texas Instruments Incorporated - https://www.ti.com/ * Author: Tony Lindgren <tony@atomide.com> */ #include <linux/device.h> #include <linux/module.h> #include <linux/of.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> #include <linux/pnp.h> #include <linux/property.h> #include <linux/serial_core.h> #include <linux/spinlock.h> #include "serial_base.h" #define SERIAL_PORT_AUTOSUSPEND_DELAY_MS 500 /* Only considers pending TX for now. Caller must take care of locking */ static int __serial_port_busy(struct uart_port *port) { return !uart_tx_stopped(port) && !kfifo_is_empty(&port->state->port.xmit_fifo); } static int serial_port_runtime_resume(struct device *dev) { struct serial_port_device *port_dev = to_serial_base_port_device(dev); struct uart_port *port; unsigned long flags; port = port_dev->port; if (port->flags & UPF_DEAD) goto out; /* Flush any pending TX for the port */ uart_port_lock_irqsave(port, &flags); if (!port_dev->tx_enabled) goto unlock; if (__serial_port_busy(port)) port->ops->start_tx(port); unlock: uart_port_unlock_irqrestore(port, flags); out: pm_runtime_mark_last_busy(dev); return 0; } static int serial_port_runtime_suspend(struct device *dev) { struct serial_port_device *port_dev = to_serial_base_port_device(dev); struct uart_port *port = port_dev->port; unsigned long flags; bool busy; if (port->flags & UPF_DEAD) return 0; /* * Nothing to do on pm_runtime_force_suspend(), see * DEFINE_RUNTIME_DEV_PM_OPS. */ if (!pm_runtime_enabled(dev)) return 0; uart_port_lock_irqsave(port, &flags); if (!port_dev->tx_enabled) { uart_port_unlock_irqrestore(port, flags); return 0; } busy = __serial_port_busy(port); if (busy) port->ops->start_tx(port); uart_port_unlock_irqrestore(port, flags); if (busy) pm_runtime_mark_last_busy(dev); return busy ? -EBUSY : 0; } static void serial_base_port_set_tx(struct uart_port *port, struct serial_port_device *port_dev, bool enabled) { unsigned long flags; uart_port_lock_irqsave(port, &flags); port_dev->tx_enabled = enabled; uart_port_unlock_irqrestore(port, flags); } void serial_base_port_startup(struct uart_port *port) { struct serial_port_device *port_dev = port->port_dev; serial_base_port_set_tx(port, port_dev, true); } void serial_base_port_shutdown(struct uart_port *port) { struct serial_port_device *port_dev = port->port_dev; serial_base_port_set_tx(port, port_dev, false); } static DEFINE_RUNTIME_DEV_PM_OPS(serial_port_pm, serial_port_runtime_suspend, serial_port_runtime_resume, NULL); static int serial_port_probe(struct device *dev) { pm_runtime_enable(dev); pm_runtime_set_autosuspend_delay(dev, SERIAL_PORT_AUTOSUSPEND_DELAY_MS); pm_runtime_use_autosuspend(dev); return 0; } static int serial_port_remove(struct device *dev) { pm_runtime_dont_use_autosuspend(dev); pm_runtime_disable(dev); return 0; } /* * Serial core port device init functions. Note that the physical serial * port device driver may not have completed probe at this point. */ int uart_add_one_port(struct uart_driver *drv, struct uart_port *port) { return serial_ctrl_register_port(drv, port); } EXPORT_SYMBOL(uart_add_one_port); void uart_remove_one_port(struct uart_driver *drv, struct uart_port *port) { serial_ctrl_unregister_port(drv, port); } EXPORT_SYMBOL(uart_remove_one_port); /** * __uart_read_properties - read firmware properties of the given UART port * @port: corresponding port * @use_defaults: apply defaults (when %true) or validate the values (when %false) * * The following device properties are supported: * - clock-frequency (optional) * - fifo-size (optional) * - no-loopback-test (optional) * - reg-shift (defaults may apply) * - reg-offset (value may be validated) * - reg-io-width (defaults may apply or value may be validated) * - interrupts (OF only) * - serial [alias ID] (OF only) * * If the port->dev is of struct platform_device type the interrupt line * will be retrieved via platform_get_irq() call against that device. * Otherwise it will be assigned by fwnode_irq_get() call. In both cases * the index 0 of the resource is used. * * The caller is responsible to initialize the following fields of the @port * ->dev (must be valid) * ->flags * ->iobase * ->mapbase * ->mapsize * ->regshift (if @use_defaults is false) * before calling this function. Alternatively the above mentioned fields * may be zeroed, in such case the only ones, that have associated properties * found, will be set to the respective values. * * If no error happened, the ->irq, ->mapbase, ->mapsize will be altered. * The ->iotype is always altered. * * When @use_defaults is true and the respective property is not found * the following values will be applied: * ->regshift = 0 * In this case IRQ must be provided, otherwise an error will be returned. * * When @use_defaults is false and the respective property is found * the following values will be validated: * - reg-io-width (->iotype) * - reg-offset (->mapsize against ->mapbase) * * Returns: 0 on success or negative errno on failure */ static int __uart_read_properties(struct uart_port *port, bool use_defaults) { struct device *dev = port->dev; u32 value; int ret; /* Read optional UART functional clock frequency */ device_property_read_u32(dev, "clock-frequency", &port->uartclk); /* Read the registers alignment (default: 8-bit) */ ret = device_property_read_u32(dev, "reg-shift", &value); if (ret) port->regshift = use_defaults ? 0 : port->regshift; else port->regshift = value; /* Read the registers I/O access type (default: MMIO 8-bit) */ ret = device_property_read_u32(dev, "reg-io-width", &value); if (ret) { port->iotype = port->iobase ? UPIO_PORT : UPIO_MEM; } else { switch (value) { case 1: port->iotype = UPIO_MEM; break; case 2: port->iotype = UPIO_MEM16; break; case 4: port->iotype = device_is_big_endian(dev) ? UPIO_MEM32BE : UPIO_MEM32; break; default: port->iotype = UPIO_UNKNOWN; break; } } if (!use_defaults && port->iotype == UPIO_UNKNOWN) { dev_err(dev, "Unsupported reg-io-width (%u)\n", value); return -EINVAL; } /* Read the address mapping base offset (default: no offset) */ ret = device_property_read_u32(dev, "reg-offset", &value); if (ret) value = 0; /* Check for shifted address mapping overflow */ if (!use_defaults && port->mapsize < value) { dev_err(dev, "reg-offset %u exceeds region size %pa\n", value, &port->mapsize); return -EINVAL; } port->mapbase += value; port->mapsize -= value; /* Read optional FIFO size */ device_property_read_u32(dev, "fifo-size", &port->fifosize); if (device_property_read_bool(dev, "no-loopback-test")) port->flags |= UPF_SKIP_TEST; /* Get index of serial line, if found in DT aliases */ ret = of_alias_get_id(dev_of_node(dev), "serial"); if (ret >= 0) port->line = ret; if (dev_is_platform(dev)) ret = platform_get_irq(to_platform_device(dev), 0); else if (dev_is_pnp(dev)) { ret = pnp_irq(to_pnp_dev(dev), 0); if (ret < 0) ret = -ENXIO; } else ret = fwnode_irq_get(dev_fwnode(dev), 0); if (ret == -EPROBE_DEFER) return ret; if (ret > 0) port->irq = ret; else if (use_defaults) /* By default IRQ support is mandatory */ return ret; else port->irq = 0; port->flags |= UPF_SHARE_IRQ; return 0; } int uart_read_port_properties(struct uart_port *port) { return __uart_read_properties(port, true); } EXPORT_SYMBOL_GPL(uart_read_port_properties); int uart_read_and_validate_port_properties(struct uart_port *port) { return __uart_read_properties(port, false); } EXPORT_SYMBOL_GPL(uart_read_and_validate_port_properties); static struct device_driver serial_port_driver = { .name = "port", .suppress_bind_attrs = true, .probe = serial_port_probe, .remove = serial_port_remove, .pm = pm_ptr(&serial_port_pm), }; int serial_base_port_init(void) { return serial_base_driver_register(&serial_port_driver); } void serial_base_port_exit(void) { serial_base_driver_unregister(&serial_port_driver); } MODULE_AUTHOR("Tony Lindgren <tony@atomide.com>"); MODULE_DESCRIPTION("Serial controller port driver"); MODULE_LICENSE("GPL"); |
| 44 75 251 201 295 111 60 60 59 118 65 64 69 67 71 60 60 60 60 60 60 60 60 60 59 144 144 144 143 118 65 143 123 107 32 29 76 44 143 60 60 60 27 60 144 72 144 59 27 59 60 60 27 60 60 60 60 60 60 60 27 60 60 60 59 60 60 60 60 27 19 19 27 27 27 27 27 27 27 27 27 60 19 19 19 19 19 19 19 19 19 19 19 44 44 44 44 44 44 192 193 193 192 193 192 239 238 239 229 228 229 229 238 239 239 239 239 60 60 60 239 229 19 19 19 229 44 239 70 17 17 1 68 13 14 208 209 206 208 207 207 209 264 265 265 265 264 264 263 263 165 165 3 3 3 3 3 3 3 3 3 3 3 3 3 69 134 108 69 38 38 38 38 38 69 69 69 108 108 108 6 68 67 66 65 68 65 6 70 2 2 256 2 165 165 163 162 73 97 67 65 64 94 63 63 63 63 63 63 63 7 1 6 6 6 6 6 6 2 56 47 93 89 89 89 87 53 86 4 88 163 1118 1000 1003 1006 2 998 1178 1184 1178 21 1186 1183 1186 1179 1179 1182 1188 1175 252 1122 353 330 447 578 340 342 17 17 17 317 1015 53 1014 1010 1007 1005 1012 1017 1010 24 997 997 1006 994 1002 988 995 26 90 97 97 90 68 90 89 88 36 6 202 202 109 29 110 110 111 109 107 106 95 107 106 107 107 105 101 106 89 105 91 105 98 106 96 1 97 90 97 41 41 41 41 41 40 41 41 41 41 41 41 41 41 41 23 19 23 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 159 159 158 158 159 158 158 159 157 159 159 159 158 159 158 159 45 158 1 159 158 12 12 158 159 2 2 2 2 2 2 2 2 2 2 2 2 2 2 19 14 7 14 14 14 14 7 4 2 3 2 9 9 9 9 7 9 10 7 14 14 7 14 2 14 14 14 7 14 14 62 62 61 62 11 11 11 11 11 11 11 11 11 11 11 11 10 11 3 11 11 11 11 11 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 10 4 10 11 11 3 4 4 4 4 4 4 4 4 4 4 4 4 7 7 3 7 6 7 7 7 7 7 7 6 6 1 1 6 6 6 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 1 7 7 6 5 5 1 6 6 1 6 5 1 5 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 6 17 17 17 17 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * * Robert Olsson <robert.olsson@its.uu.se> Uppsala Universitet * & Swedish University of Agricultural Sciences. * * Jens Laas <jens.laas@data.slu.se> Swedish University of * Agricultural Sciences. * * Hans Liss <hans.liss@its.uu.se> Uppsala Universitet * * This work is based on the LPC-trie which is originally described in: * * An experimental study of compression methods for dynamic tries * Stefan Nilsson and Matti Tikkanen. Algorithmica, 33(1):19-33, 2002. * https://www.csc.kth.se/~snilsson/software/dyntrie2/ * * IP-address lookup using LC-tries. Stefan Nilsson and Gunnar Karlsson * IEEE Journal on Selected Areas in Communications, 17(6):1083-1092, June 1999 * * Code from fib_hash has been reused which includes the following header: * * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * IPv4 FIB: lookup engine and maintenance routines. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * * Substantial contributions to this work comes from: * * David S. Miller, <davem@davemloft.net> * Stephen Hemminger <shemminger@osdl.org> * Paul E. McKenney <paulmck@us.ibm.com> * Patrick McHardy <kaber@trash.net> */ #include <linux/cache.h> #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/errno.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/inetdevice.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/proc_fs.h> #include <linux/rcupdate.h> #include <linux/rcupdate_wait.h> #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/init.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/export.h> #include <linux/vmalloc.h> #include <linux/notifier.h> #include <net/net_namespace.h> #include <net/inet_dscp.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> #include <net/tcp.h> #include <net/sock.h> #include <net/ip_fib.h> #include <net/fib_notifier.h> #include <trace/events/fib.h> #include "fib_lookup.h" static int call_fib_entry_notifier(struct notifier_block *nb, enum fib_event_type event_type, u32 dst, int dst_len, struct fib_alias *fa, struct netlink_ext_ack *extack) { struct fib_entry_notifier_info info = { .info.extack = extack, .dst = dst, .dst_len = dst_len, .fi = fa->fa_info, .dscp = fa->fa_dscp, .type = fa->fa_type, .tb_id = fa->tb_id, }; return call_fib4_notifier(nb, event_type, &info.info); } static int call_fib_entry_notifiers(struct net *net, enum fib_event_type event_type, u32 dst, int dst_len, struct fib_alias *fa, struct netlink_ext_ack *extack) { struct fib_entry_notifier_info info = { .info.extack = extack, .dst = dst, .dst_len = dst_len, .fi = fa->fa_info, .dscp = fa->fa_dscp, .type = fa->fa_type, .tb_id = fa->tb_id, }; return call_fib4_notifiers(net, event_type, &info.info); } #define MAX_STAT_DEPTH 32 #define KEYLENGTH (8*sizeof(t_key)) #define KEY_MAX ((t_key)~0) typedef unsigned int t_key; #define IS_TRIE(n) ((n)->pos >= KEYLENGTH) #define IS_TNODE(n) ((n)->bits) #define IS_LEAF(n) (!(n)->bits) struct key_vector { t_key key; unsigned char pos; /* 2log(KEYLENGTH) bits needed */ unsigned char bits; /* 2log(KEYLENGTH) bits needed */ unsigned char slen; union { /* This list pointer if valid if (pos | bits) == 0 (LEAF) */ struct hlist_head leaf; /* This array is valid if (pos | bits) > 0 (TNODE) */ DECLARE_FLEX_ARRAY(struct key_vector __rcu *, tnode); }; }; struct tnode { struct rcu_head rcu; t_key empty_children; /* KEYLENGTH bits needed */ t_key full_children; /* KEYLENGTH bits needed */ struct key_vector __rcu *parent; struct key_vector kv[1]; #define tn_bits kv[0].bits }; #define TNODE_SIZE(n) offsetof(struct tnode, kv[0].tnode[n]) #define LEAF_SIZE TNODE_SIZE(1) #ifdef CONFIG_IP_FIB_TRIE_STATS struct trie_use_stats { unsigned int gets; unsigned int backtrack; unsigned int semantic_match_passed; unsigned int semantic_match_miss; unsigned int null_node_hit; unsigned int resize_node_skipped; }; #endif struct trie_stat { unsigned int totdepth; unsigned int maxdepth; unsigned int tnodes; unsigned int leaves; unsigned int nullpointers; unsigned int prefixes; unsigned int nodesizes[MAX_STAT_DEPTH]; }; struct trie { struct key_vector kv[1]; #ifdef CONFIG_IP_FIB_TRIE_STATS struct trie_use_stats __percpu *stats; #endif }; static struct key_vector *resize(struct trie *t, struct key_vector *tn); static unsigned int tnode_free_size; /* * synchronize_rcu after call_rcu for outstanding dirty memory; it should be * especially useful before resizing the root node with PREEMPT_NONE configs; * the value was obtained experimentally, aiming to avoid visible slowdown. */ unsigned int sysctl_fib_sync_mem = 512 * 1024; unsigned int sysctl_fib_sync_mem_min = 64 * 1024; unsigned int sysctl_fib_sync_mem_max = 64 * 1024 * 1024; static struct kmem_cache *fn_alias_kmem __ro_after_init; static struct kmem_cache *trie_leaf_kmem __ro_after_init; static inline struct tnode *tn_info(struct key_vector *kv) { return container_of(kv, struct tnode, kv[0]); } /* caller must hold RTNL */ #define node_parent(tn) rtnl_dereference(tn_info(tn)->parent) #define get_child(tn, i) rtnl_dereference((tn)->tnode[i]) /* caller must hold RCU read lock or RTNL */ #define node_parent_rcu(tn) rcu_dereference_rtnl(tn_info(tn)->parent) #define get_child_rcu(tn, i) rcu_dereference_rtnl((tn)->tnode[i]) /* wrapper for rcu_assign_pointer */ static inline void node_set_parent(struct key_vector *n, struct key_vector *tp) { if (n) rcu_assign_pointer(tn_info(n)->parent, tp); } #define NODE_INIT_PARENT(n, p) RCU_INIT_POINTER(tn_info(n)->parent, p) /* This provides us with the number of children in this node, in the case of a * leaf this will return 0 meaning none of the children are accessible. */ static inline unsigned long child_length(const struct key_vector *tn) { return (1ul << tn->bits) & ~(1ul); } #define get_cindex(key, kv) (((key) ^ (kv)->key) >> (kv)->pos) static inline unsigned long get_index(t_key key, struct key_vector *kv) { unsigned long index = key ^ kv->key; if ((BITS_PER_LONG <= KEYLENGTH) && (KEYLENGTH == kv->pos)) return 0; return index >> kv->pos; } /* To understand this stuff, an understanding of keys and all their bits is * necessary. Every node in the trie has a key associated with it, but not * all of the bits in that key are significant. * * Consider a node 'n' and its parent 'tp'. * * If n is a leaf, every bit in its key is significant. Its presence is * necessitated by path compression, since during a tree traversal (when * searching for a leaf - unless we are doing an insertion) we will completely * ignore all skipped bits we encounter. Thus we need to verify, at the end of * a potentially successful search, that we have indeed been walking the * correct key path. * * Note that we can never "miss" the correct key in the tree if present by * following the wrong path. Path compression ensures that segments of the key * that are the same for all keys with a given prefix are skipped, but the * skipped part *is* identical for each node in the subtrie below the skipped * bit! trie_insert() in this implementation takes care of that. * * if n is an internal node - a 'tnode' here, the various parts of its key * have many different meanings. * * Example: * _________________________________________________________________ * | i | i | i | i | i | i | i | N | N | N | S | S | S | S | S | C | * ----------------------------------------------------------------- * 31 30 29 28 27 26 25 24 23 22 21 20 19 18 17 16 * * _________________________________________________________________ * | C | C | C | u | u | u | u | u | u | u | u | u | u | u | u | u | * ----------------------------------------------------------------- * 15 14 13 12 11 10 9 8 7 6 5 4 3 2 1 0 * * tp->pos = 22 * tp->bits = 3 * n->pos = 13 * n->bits = 4 * * First, let's just ignore the bits that come before the parent tp, that is * the bits from (tp->pos + tp->bits) to 31. They are *known* but at this * point we do not use them for anything. * * The bits from (tp->pos) to (tp->pos + tp->bits - 1) - "N", above - are the * index into the parent's child array. That is, they will be used to find * 'n' among tp's children. * * The bits from (n->pos + n->bits) to (tp->pos - 1) - "S" - are skipped bits * for the node n. * * All the bits we have seen so far are significant to the node n. The rest * of the bits are really not needed or indeed known in n->key. * * The bits from (n->pos) to (n->pos + n->bits - 1) - "C" - are the index into * n's child array, and will of course be different for each child. * * The rest of the bits, from 0 to (n->pos -1) - "u" - are completely unknown * at this point. */ static const int halve_threshold = 25; static const int inflate_threshold = 50; static const int halve_threshold_root = 15; static const int inflate_threshold_root = 30; static inline void alias_free_mem_rcu(struct fib_alias *fa) { kfree_rcu(fa, rcu); } #define TNODE_VMALLOC_MAX \ ilog2((SIZE_MAX - TNODE_SIZE(0)) / sizeof(struct key_vector *)) static void __node_free_rcu(struct rcu_head *head) { struct tnode *n = container_of(head, struct tnode, rcu); if (!n->tn_bits) kmem_cache_free(trie_leaf_kmem, n); else kvfree(n); } #define node_free(n) call_rcu(&tn_info(n)->rcu, __node_free_rcu) static struct tnode *tnode_alloc(int bits) { size_t size; /* verify bits is within bounds */ if (bits > TNODE_VMALLOC_MAX) return NULL; /* determine size and verify it is non-zero and didn't overflow */ size = TNODE_SIZE(1ul << bits); if (size <= PAGE_SIZE) return kzalloc(size, GFP_KERNEL); else return vzalloc(size); } static inline void empty_child_inc(struct key_vector *n) { tn_info(n)->empty_children++; if (!tn_info(n)->empty_children) tn_info(n)->full_children++; } static inline void empty_child_dec(struct key_vector *n) { if (!tn_info(n)->empty_children) tn_info(n)->full_children--; tn_info(n)->empty_children--; } static struct key_vector *leaf_new(t_key key, struct fib_alias *fa) { struct key_vector *l; struct tnode *kv; kv = kmem_cache_alloc(trie_leaf_kmem, GFP_KERNEL); if (!kv) return NULL; /* initialize key vector */ l = kv->kv; l->key = key; l->pos = 0; l->bits = 0; l->slen = fa->fa_slen; /* link leaf to fib alias */ INIT_HLIST_HEAD(&l->leaf); hlist_add_head(&fa->fa_list, &l->leaf); return l; } static struct key_vector *tnode_new(t_key key, int pos, int bits) { unsigned int shift = pos + bits; struct key_vector *tn; struct tnode *tnode; /* verify bits and pos their msb bits clear and values are valid */ BUG_ON(!bits || (shift > KEYLENGTH)); tnode = tnode_alloc(bits); if (!tnode) return NULL; pr_debug("AT %p s=%zu %zu\n", tnode, TNODE_SIZE(0), sizeof(struct key_vector *) << bits); if (bits == KEYLENGTH) tnode->full_children = 1; else tnode->empty_children = 1ul << bits; tn = tnode->kv; tn->key = (shift < KEYLENGTH) ? (key >> shift) << shift : 0; tn->pos = pos; tn->bits = bits; tn->slen = pos; return tn; } /* Check whether a tnode 'n' is "full", i.e. it is an internal node * and no bits are skipped. See discussion in dyntree paper p. 6 */ static inline int tnode_full(struct key_vector *tn, struct key_vector *n) { return n && ((n->pos + n->bits) == tn->pos) && IS_TNODE(n); } /* Add a child at position i overwriting the old value. * Update the value of full_children and empty_children. */ static void put_child(struct key_vector *tn, unsigned long i, struct key_vector *n) { struct key_vector *chi = get_child(tn, i); int isfull, wasfull; BUG_ON(i >= child_length(tn)); /* update emptyChildren, overflow into fullChildren */ if (!n && chi) empty_child_inc(tn); if (n && !chi) empty_child_dec(tn); /* update fullChildren */ wasfull = tnode_full(tn, chi); isfull = tnode_full(tn, n); if (wasfull && !isfull) tn_info(tn)->full_children--; else if (!wasfull && isfull) tn_info(tn)->full_children++; if (n && (tn->slen < n->slen)) tn->slen = n->slen; rcu_assign_pointer(tn->tnode[i], n); } static void update_children(struct key_vector *tn) { unsigned long i; /* update all of the child parent pointers */ for (i = child_length(tn); i;) { struct key_vector *inode = get_child(tn, --i); if (!inode) continue; /* Either update the children of a tnode that * already belongs to us or update the child * to point to ourselves. */ if (node_parent(inode) == tn) update_children(inode); else node_set_parent(inode, tn); } } static inline void put_child_root(struct key_vector *tp, t_key key, struct key_vector *n) { if (IS_TRIE(tp)) rcu_assign_pointer(tp->tnode[0], n); else put_child(tp, get_index(key, tp), n); } static inline void tnode_free_init(struct key_vector *tn) { tn_info(tn)->rcu.next = NULL; } static inline void tnode_free_append(struct key_vector *tn, struct key_vector *n) { tn_info(n)->rcu.next = tn_info(tn)->rcu.next; tn_info(tn)->rcu.next = &tn_info(n)->rcu; } static void tnode_free(struct key_vector *tn) { struct callback_head *head = &tn_info(tn)->rcu; while (head) { head = head->next; tnode_free_size += TNODE_SIZE(1ul << tn->bits); node_free(tn); tn = container_of(head, struct tnode, rcu)->kv; } if (tnode_free_size >= READ_ONCE(sysctl_fib_sync_mem)) { tnode_free_size = 0; synchronize_net(); } } static struct key_vector *replace(struct trie *t, struct key_vector *oldtnode, struct key_vector *tn) { struct key_vector *tp = node_parent(oldtnode); unsigned long i; /* setup the parent pointer out of and back into this node */ NODE_INIT_PARENT(tn, tp); put_child_root(tp, tn->key, tn); /* update all of the child parent pointers */ update_children(tn); /* all pointers should be clean so we are done */ tnode_free(oldtnode); /* resize children now that oldtnode is freed */ for (i = child_length(tn); i;) { struct key_vector *inode = get_child(tn, --i); /* resize child node */ if (tnode_full(tn, inode)) tn = resize(t, inode); } return tp; } static struct key_vector *inflate(struct trie *t, struct key_vector *oldtnode) { struct key_vector *tn; unsigned long i; t_key m; pr_debug("In inflate\n"); tn = tnode_new(oldtnode->key, oldtnode->pos - 1, oldtnode->bits + 1); if (!tn) goto notnode; /* prepare oldtnode to be freed */ tnode_free_init(oldtnode); /* Assemble all of the pointers in our cluster, in this case that * represents all of the pointers out of our allocated nodes that * point to existing tnodes and the links between our allocated * nodes. */ for (i = child_length(oldtnode), m = 1u << tn->pos; i;) { struct key_vector *inode = get_child(oldtnode, --i); struct key_vector *node0, *node1; unsigned long j, k; /* An empty child */ if (!inode) continue; /* A leaf or an internal node with skipped bits */ if (!tnode_full(oldtnode, inode)) { put_child(tn, get_index(inode->key, tn), inode); continue; } /* drop the node in the old tnode free list */ tnode_free_append(oldtnode, inode); /* An internal node with two children */ if (inode->bits == 1) { put_child(tn, 2 * i + 1, get_child(inode, 1)); put_child(tn, 2 * i, get_child(inode, 0)); continue; } /* We will replace this node 'inode' with two new * ones, 'node0' and 'node1', each with half of the * original children. The two new nodes will have * a position one bit further down the key and this * means that the "significant" part of their keys * (see the discussion near the top of this file) * will differ by one bit, which will be "0" in * node0's key and "1" in node1's key. Since we are * moving the key position by one step, the bit that * we are moving away from - the bit at position * (tn->pos) - is the one that will differ between * node0 and node1. So... we synthesize that bit in the * two new keys. */ node1 = tnode_new(inode->key | m, inode->pos, inode->bits - 1); if (!node1) goto nomem; node0 = tnode_new(inode->key, inode->pos, inode->bits - 1); tnode_free_append(tn, node1); if (!node0) goto nomem; tnode_free_append(tn, node0); /* populate child pointers in new nodes */ for (k = child_length(inode), j = k / 2; j;) { put_child(node1, --j, get_child(inode, --k)); put_child(node0, j, get_child(inode, j)); put_child(node1, --j, get_child(inode, --k)); put_child(node0, j, get_child(inode, j)); } /* link new nodes to parent */ NODE_INIT_PARENT(node1, tn); NODE_INIT_PARENT(node0, tn); /* link parent to nodes */ put_child(tn, 2 * i + 1, node1); put_child(tn, 2 * i, node0); } /* setup the parent pointers into and out of this node */ return replace(t, oldtnode, tn); nomem: /* all pointers should be clean so we are done */ tnode_free(tn); notnode: return NULL; } static struct key_vector *halve(struct trie *t, struct key_vector *oldtnode) { struct key_vector *tn; unsigned long i; pr_debug("In halve\n"); tn = tnode_new(oldtnode->key, oldtnode->pos + 1, oldtnode->bits - 1); if (!tn) goto notnode; /* prepare oldtnode to be freed */ tnode_free_init(oldtnode); /* Assemble all of the pointers in our cluster, in this case that * represents all of the pointers out of our allocated nodes that * point to existing tnodes and the links between our allocated * nodes. */ for (i = child_length(oldtnode); i;) { struct key_vector *node1 = get_child(oldtnode, --i); struct key_vector *node0 = get_child(oldtnode, --i); struct key_vector *inode; /* At least one of the children is empty */ if (!node1 || !node0) { put_child(tn, i / 2, node1 ? : node0); continue; } /* Two nonempty children */ inode = tnode_new(node0->key, oldtnode->pos, 1); if (!inode) goto nomem; tnode_free_append(tn, inode); /* initialize pointers out of node */ put_child(inode, 1, node1); put_child(inode, 0, node0); NODE_INIT_PARENT(inode, tn); /* link parent to node */ put_child(tn, i / 2, inode); } /* setup the parent pointers into and out of this node */ return replace(t, oldtnode, tn); nomem: /* all pointers should be clean so we are done */ tnode_free(tn); notnode: return NULL; } static struct key_vector *collapse(struct trie *t, struct key_vector *oldtnode) { struct key_vector *n, *tp; unsigned long i; /* scan the tnode looking for that one child that might still exist */ for (n = NULL, i = child_length(oldtnode); !n && i;) n = get_child(oldtnode, --i); /* compress one level */ tp = node_parent(oldtnode); put_child_root(tp, oldtnode->key, n); node_set_parent(n, tp); /* drop dead node */ node_free(oldtnode); return tp; } static unsigned char update_suffix(struct key_vector *tn) { unsigned char slen = tn->pos; unsigned long stride, i; unsigned char slen_max; /* only vector 0 can have a suffix length greater than or equal to * tn->pos + tn->bits, the second highest node will have a suffix * length at most of tn->pos + tn->bits - 1 */ slen_max = min_t(unsigned char, tn->pos + tn->bits - 1, tn->slen); /* search though the list of children looking for nodes that might * have a suffix greater than the one we currently have. This is * why we start with a stride of 2 since a stride of 1 would * represent the nodes with suffix length equal to tn->pos */ for (i = 0, stride = 0x2ul ; i < child_length(tn); i += stride) { struct key_vector *n = get_child(tn, i); if (!n || (n->slen <= slen)) continue; /* update stride and slen based on new value */ stride <<= (n->slen - slen); slen = n->slen; i &= ~(stride - 1); /* stop searching if we have hit the maximum possible value */ if (slen >= slen_max) break; } tn->slen = slen; return slen; } /* From "Implementing a dynamic compressed trie" by Stefan Nilsson of * the Helsinki University of Technology and Matti Tikkanen of Nokia * Telecommunications, page 6: * "A node is doubled if the ratio of non-empty children to all * children in the *doubled* node is at least 'high'." * * 'high' in this instance is the variable 'inflate_threshold'. It * is expressed as a percentage, so we multiply it with * child_length() and instead of multiplying by 2 (since the * child array will be doubled by inflate()) and multiplying * the left-hand side by 100 (to handle the percentage thing) we * multiply the left-hand side by 50. * * The left-hand side may look a bit weird: child_length(tn) * - tn->empty_children is of course the number of non-null children * in the current node. tn->full_children is the number of "full" * children, that is non-null tnodes with a skip value of 0. * All of those will be doubled in the resulting inflated tnode, so * we just count them one extra time here. * * A clearer way to write this would be: * * to_be_doubled = tn->full_children; * not_to_be_doubled = child_length(tn) - tn->empty_children - * tn->full_children; * * new_child_length = child_length(tn) * 2; * * new_fill_factor = 100 * (not_to_be_doubled + 2*to_be_doubled) / * new_child_length; * if (new_fill_factor >= inflate_threshold) * * ...and so on, tho it would mess up the while () loop. * * anyway, * 100 * (not_to_be_doubled + 2*to_be_doubled) / new_child_length >= * inflate_threshold * * avoid a division: * 100 * (not_to_be_doubled + 2*to_be_doubled) >= * inflate_threshold * new_child_length * * expand not_to_be_doubled and to_be_doubled, and shorten: * 100 * (child_length(tn) - tn->empty_children + * tn->full_children) >= inflate_threshold * new_child_length * * expand new_child_length: * 100 * (child_length(tn) - tn->empty_children + * tn->full_children) >= * inflate_threshold * child_length(tn) * 2 * * shorten again: * 50 * (tn->full_children + child_length(tn) - * tn->empty_children) >= inflate_threshold * * child_length(tn) * */ static inline bool should_inflate(struct key_vector *tp, struct key_vector *tn) { unsigned long used = child_length(tn); unsigned long threshold = used; /* Keep root node larger */ threshold *= IS_TRIE(tp) ? inflate_threshold_root : inflate_threshold; used -= tn_info(tn)->empty_children; used += tn_info(tn)->full_children; /* if bits == KEYLENGTH then pos = 0, and will fail below */ return (used > 1) && tn->pos && ((50 * used) >= threshold); } static inline bool should_halve(struct key_vector *tp, struct key_vector *tn) { unsigned long used = child_length(tn); unsigned long threshold = used; /* Keep root node larger */ threshold *= IS_TRIE(tp) ? halve_threshold_root : halve_threshold; used -= tn_info(tn)->empty_children; /* if bits == KEYLENGTH then used = 100% on wrap, and will fail below */ return (used > 1) && (tn->bits > 1) && ((100 * used) < threshold); } static inline bool should_collapse(struct key_vector *tn) { unsigned long used = child_length(tn); used -= tn_info(tn)->empty_children; /* account for bits == KEYLENGTH case */ if ((tn->bits == KEYLENGTH) && tn_info(tn)->full_children) used -= KEY_MAX; /* One child or none, time to drop us from the trie */ return used < 2; } #define MAX_WORK 10 static struct key_vector *resize(struct trie *t, struct key_vector *tn) { #ifdef CONFIG_IP_FIB_TRIE_STATS struct trie_use_stats __percpu *stats = t->stats; #endif struct key_vector *tp = node_parent(tn); unsigned long cindex = get_index(tn->key, tp); int max_work = MAX_WORK; pr_debug("In tnode_resize %p inflate_threshold=%d threshold=%d\n", tn, inflate_threshold, halve_threshold); /* track the tnode via the pointer from the parent instead of * doing it ourselves. This way we can let RCU fully do its * thing without us interfering */ BUG_ON(tn != get_child(tp, cindex)); /* Double as long as the resulting node has a number of * nonempty nodes that are above the threshold. */ while (should_inflate(tp, tn) && max_work) { tp = inflate(t, tn); if (!tp) { #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->resize_node_skipped); #endif break; } max_work--; tn = get_child(tp, cindex); } /* update parent in case inflate failed */ tp = node_parent(tn); /* Return if at least one inflate is run */ if (max_work != MAX_WORK) return tp; /* Halve as long as the number of empty children in this * node is above threshold. */ while (should_halve(tp, tn) && max_work) { tp = halve(t, tn); if (!tp) { #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->resize_node_skipped); #endif break; } max_work--; tn = get_child(tp, cindex); } /* Only one child remains */ if (should_collapse(tn)) return collapse(t, tn); /* update parent in case halve failed */ return node_parent(tn); } static void node_pull_suffix(struct key_vector *tn, unsigned char slen) { unsigned char node_slen = tn->slen; while ((node_slen > tn->pos) && (node_slen > slen)) { slen = update_suffix(tn); if (node_slen == slen) break; tn = node_parent(tn); node_slen = tn->slen; } } static void node_push_suffix(struct key_vector *tn, unsigned char slen) { while (tn->slen < slen) { tn->slen = slen; tn = node_parent(tn); } } /* rcu_read_lock needs to be hold by caller from readside */ static struct key_vector *fib_find_node(struct trie *t, struct key_vector **tp, u32 key) { struct key_vector *pn, *n = t->kv; unsigned long index = 0; do { pn = n; n = get_child_rcu(n, index); if (!n) break; index = get_cindex(key, n); /* This bit of code is a bit tricky but it combines multiple * checks into a single check. The prefix consists of the * prefix plus zeros for the bits in the cindex. The index * is the difference between the key and this value. From * this we can actually derive several pieces of data. * if (index >= (1ul << bits)) * we have a mismatch in skip bits and failed * else * we know the value is cindex * * This check is safe even if bits == KEYLENGTH due to the * fact that we can only allocate a node with 32 bits if a * long is greater than 32 bits. */ if (index >= (1ul << n->bits)) { n = NULL; break; } /* keep searching until we find a perfect match leaf or NULL */ } while (IS_TNODE(n)); *tp = pn; return n; } /* Return the first fib alias matching DSCP with * priority less than or equal to PRIO. * If 'find_first' is set, return the first matching * fib alias, regardless of DSCP and priority. */ static struct fib_alias *fib_find_alias(struct hlist_head *fah, u8 slen, dscp_t dscp, u32 prio, u32 tb_id, bool find_first) { struct fib_alias *fa; if (!fah) return NULL; hlist_for_each_entry(fa, fah, fa_list) { /* Avoid Sparse warning when using dscp_t in inequalities */ u8 __fa_dscp = inet_dscp_to_dsfield(fa->fa_dscp); u8 __dscp = inet_dscp_to_dsfield(dscp); if (fa->fa_slen < slen) continue; if (fa->fa_slen != slen) break; if (fa->tb_id > tb_id) continue; if (fa->tb_id != tb_id) break; if (find_first) return fa; if (__fa_dscp > __dscp) continue; if (fa->fa_info->fib_priority >= prio || __fa_dscp < __dscp) return fa; } return NULL; } static struct fib_alias * fib_find_matching_alias(struct net *net, const struct fib_rt_info *fri) { u8 slen = KEYLENGTH - fri->dst_len; struct key_vector *l, *tp; struct fib_table *tb; struct fib_alias *fa; struct trie *t; tb = fib_get_table(net, fri->tb_id); if (!tb) return NULL; t = (struct trie *)tb->tb_data; l = fib_find_node(t, &tp, be32_to_cpu(fri->dst)); if (!l) return NULL; hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { if (fa->fa_slen == slen && fa->tb_id == fri->tb_id && fa->fa_dscp == fri->dscp && fa->fa_info == fri->fi && fa->fa_type == fri->type) return fa; } return NULL; } void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri) { u8 fib_notify_on_flag_change; struct fib_alias *fa_match; struct sk_buff *skb; int err; rcu_read_lock(); fa_match = fib_find_matching_alias(net, fri); if (!fa_match) goto out; /* These are paired with the WRITE_ONCE() happening in this function. * The reason is that we are only protected by RCU at this point. */ if (READ_ONCE(fa_match->offload) == fri->offload && READ_ONCE(fa_match->trap) == fri->trap && READ_ONCE(fa_match->offload_failed) == fri->offload_failed) goto out; WRITE_ONCE(fa_match->offload, fri->offload); WRITE_ONCE(fa_match->trap, fri->trap); fib_notify_on_flag_change = READ_ONCE(net->ipv4.sysctl_fib_notify_on_flag_change); /* 2 means send notifications only if offload_failed was changed. */ if (fib_notify_on_flag_change == 2 && READ_ONCE(fa_match->offload_failed) == fri->offload_failed) goto out; WRITE_ONCE(fa_match->offload_failed, fri->offload_failed); if (!fib_notify_on_flag_change) goto out; skb = nlmsg_new(fib_nlmsg_size(fa_match->fa_info), GFP_ATOMIC); if (!skb) { err = -ENOBUFS; goto errout; } err = fib_dump_info(skb, 0, 0, RTM_NEWROUTE, fri, 0); if (err < 0) { /* -EMSGSIZE implies BUG in fib_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_IPV4_ROUTE, NULL, GFP_ATOMIC); goto out; errout: rtnl_set_sk_err(net, RTNLGRP_IPV4_ROUTE, err); out: rcu_read_unlock(); } EXPORT_SYMBOL_GPL(fib_alias_hw_flags_set); static void trie_rebalance(struct trie *t, struct key_vector *tn) { while (!IS_TRIE(tn)) tn = resize(t, tn); } static int fib_insert_node(struct trie *t, struct key_vector *tp, struct fib_alias *new, t_key key) { struct key_vector *n, *l; l = leaf_new(key, new); if (!l) goto noleaf; /* retrieve child from parent node */ n = get_child(tp, get_index(key, tp)); /* Case 2: n is a LEAF or a TNODE and the key doesn't match. * * Add a new tnode here * first tnode need some special handling * leaves us in position for handling as case 3 */ if (n) { struct key_vector *tn; tn = tnode_new(key, __fls(key ^ n->key), 1); if (!tn) goto notnode; /* initialize routes out of node */ NODE_INIT_PARENT(tn, tp); put_child(tn, get_index(key, tn) ^ 1, n); /* start adding routes into the node */ put_child_root(tp, key, tn); node_set_parent(n, tn); /* parent now has a NULL spot where the leaf can go */ tp = tn; } /* Case 3: n is NULL, and will just insert a new leaf */ node_push_suffix(tp, new->fa_slen); NODE_INIT_PARENT(l, tp); put_child_root(tp, key, l); trie_rebalance(t, tp); return 0; notnode: node_free(l); noleaf: return -ENOMEM; } static int fib_insert_alias(struct trie *t, struct key_vector *tp, struct key_vector *l, struct fib_alias *new, struct fib_alias *fa, t_key key) { if (!l) return fib_insert_node(t, tp, new, key); if (fa) { hlist_add_before_rcu(&new->fa_list, &fa->fa_list); } else { struct fib_alias *last; hlist_for_each_entry(last, &l->leaf, fa_list) { if (new->fa_slen < last->fa_slen) break; if ((new->fa_slen == last->fa_slen) && (new->tb_id > last->tb_id)) break; fa = last; } if (fa) hlist_add_behind_rcu(&new->fa_list, &fa->fa_list); else hlist_add_head_rcu(&new->fa_list, &l->leaf); } /* if we added to the tail node then we need to update slen */ if (l->slen < new->fa_slen) { l->slen = new->fa_slen; node_push_suffix(tp, new->fa_slen); } return 0; } static bool fib_valid_key_len(u32 key, u8 plen, struct netlink_ext_ack *extack) { if (plen > KEYLENGTH) { NL_SET_ERR_MSG(extack, "Invalid prefix length"); return false; } if ((plen < KEYLENGTH) && (key << plen)) { NL_SET_ERR_MSG(extack, "Invalid prefix for given prefix length"); return false; } return true; } static void fib_remove_alias(struct trie *t, struct key_vector *tp, struct key_vector *l, struct fib_alias *old); /* Caller must hold RTNL. */ int fib_table_insert(struct net *net, struct fib_table *tb, struct fib_config *cfg, struct netlink_ext_ack *extack) { struct trie *t = (struct trie *)tb->tb_data; struct fib_alias *fa, *new_fa; struct key_vector *l, *tp; u16 nlflags = NLM_F_EXCL; struct fib_info *fi; u8 plen = cfg->fc_dst_len; u8 slen = KEYLENGTH - plen; dscp_t dscp; u32 key; int err; key = ntohl(cfg->fc_dst); if (!fib_valid_key_len(key, plen, extack)) return -EINVAL; pr_debug("Insert table=%u %08x/%d\n", tb->tb_id, key, plen); fi = fib_create_info(cfg, extack); if (IS_ERR(fi)) { err = PTR_ERR(fi); goto err; } dscp = cfg->fc_dscp; l = fib_find_node(t, &tp, key); fa = l ? fib_find_alias(&l->leaf, slen, dscp, fi->fib_priority, tb->tb_id, false) : NULL; /* Now fa, if non-NULL, points to the first fib alias * with the same keys [prefix,dscp,priority], if such key already * exists or to the node before which we will insert new one. * * If fa is NULL, we will need to allocate a new one and * insert to the tail of the section matching the suffix length * of the new alias. */ if (fa && fa->fa_dscp == dscp && fa->fa_info->fib_priority == fi->fib_priority) { struct fib_alias *fa_first, *fa_match; err = -EEXIST; if (cfg->fc_nlflags & NLM_F_EXCL) goto out; nlflags &= ~NLM_F_EXCL; /* We have 2 goals: * 1. Find exact match for type, scope, fib_info to avoid * duplicate routes * 2. Find next 'fa' (or head), NLM_F_APPEND inserts before it */ fa_match = NULL; fa_first = fa; hlist_for_each_entry_from(fa, fa_list) { if ((fa->fa_slen != slen) || (fa->tb_id != tb->tb_id) || (fa->fa_dscp != dscp)) break; if (fa->fa_info->fib_priority != fi->fib_priority) break; if (fa->fa_type == cfg->fc_type && fa->fa_info == fi) { fa_match = fa; break; } } if (cfg->fc_nlflags & NLM_F_REPLACE) { struct fib_info *fi_drop; u8 state; nlflags |= NLM_F_REPLACE; fa = fa_first; if (fa_match) { if (fa == fa_match) err = 0; goto out; } err = -ENOBUFS; new_fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL); if (!new_fa) goto out; fi_drop = fa->fa_info; new_fa->fa_dscp = fa->fa_dscp; new_fa->fa_info = fi; new_fa->fa_type = cfg->fc_type; state = fa->fa_state; new_fa->fa_state = state & ~FA_S_ACCESSED; new_fa->fa_slen = fa->fa_slen; new_fa->tb_id = tb->tb_id; new_fa->fa_default = -1; new_fa->offload = 0; new_fa->trap = 0; new_fa->offload_failed = 0; hlist_replace_rcu(&fa->fa_list, &new_fa->fa_list); if (fib_find_alias(&l->leaf, fa->fa_slen, 0, 0, tb->tb_id, true) == new_fa) { enum fib_event_type fib_event; fib_event = FIB_EVENT_ENTRY_REPLACE; err = call_fib_entry_notifiers(net, fib_event, key, plen, new_fa, extack); if (err) { hlist_replace_rcu(&new_fa->fa_list, &fa->fa_list); goto out_free_new_fa; } } rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id, &cfg->fc_nlinfo, nlflags); alias_free_mem_rcu(fa); fib_release_info(fi_drop); if (state & FA_S_ACCESSED) rt_cache_flush(cfg->fc_nlinfo.nl_net); goto succeeded; } /* Error if we find a perfect match which * uses the same scope, type, and nexthop * information. */ if (fa_match) goto out; if (cfg->fc_nlflags & NLM_F_APPEND) nlflags |= NLM_F_APPEND; else fa = fa_first; } err = -ENOENT; if (!(cfg->fc_nlflags & NLM_F_CREATE)) goto out; nlflags |= NLM_F_CREATE; err = -ENOBUFS; new_fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL); if (!new_fa) goto out; new_fa->fa_info = fi; new_fa->fa_dscp = dscp; new_fa->fa_type = cfg->fc_type; new_fa->fa_state = 0; new_fa->fa_slen = slen; new_fa->tb_id = tb->tb_id; new_fa->fa_default = -1; new_fa->offload = 0; new_fa->trap = 0; new_fa->offload_failed = 0; /* Insert new entry to the list. */ err = fib_insert_alias(t, tp, l, new_fa, fa, key); if (err) goto out_free_new_fa; /* The alias was already inserted, so the node must exist. */ l = l ? l : fib_find_node(t, &tp, key); if (WARN_ON_ONCE(!l)) { err = -ENOENT; goto out_free_new_fa; } if (fib_find_alias(&l->leaf, new_fa->fa_slen, 0, 0, tb->tb_id, true) == new_fa) { enum fib_event_type fib_event; fib_event = FIB_EVENT_ENTRY_REPLACE; err = call_fib_entry_notifiers(net, fib_event, key, plen, new_fa, extack); if (err) goto out_remove_new_fa; } if (!plen) tb->tb_num_default++; rt_cache_flush(cfg->fc_nlinfo.nl_net); rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, new_fa->tb_id, &cfg->fc_nlinfo, nlflags); succeeded: return 0; out_remove_new_fa: fib_remove_alias(t, tp, l, new_fa); out_free_new_fa: kmem_cache_free(fn_alias_kmem, new_fa); out: fib_release_info(fi); err: return err; } static inline t_key prefix_mismatch(t_key key, struct key_vector *n) { t_key prefix = n->key; return (key ^ prefix) & (prefix | -prefix); } bool fib_lookup_good_nhc(const struct fib_nh_common *nhc, int fib_flags, const struct flowi4 *flp) { if (nhc->nhc_flags & RTNH_F_DEAD) return false; if (ip_ignore_linkdown(nhc->nhc_dev) && nhc->nhc_flags & RTNH_F_LINKDOWN && !(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE)) return false; if (flp->flowi4_oif && flp->flowi4_oif != nhc->nhc_oif) return false; return true; } /* should be called with rcu_read_lock */ int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, struct fib_result *res, int fib_flags) { struct trie *t = (struct trie *) tb->tb_data; #ifdef CONFIG_IP_FIB_TRIE_STATS struct trie_use_stats __percpu *stats = t->stats; #endif const t_key key = ntohl(flp->daddr); struct key_vector *n, *pn; struct fib_alias *fa; unsigned long index; t_key cindex; pn = t->kv; cindex = 0; n = get_child_rcu(pn, cindex); if (!n) { trace_fib_table_lookup(tb->tb_id, flp, NULL, -EAGAIN); return -EAGAIN; } #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->gets); #endif /* Step 1: Travel to the longest prefix match in the trie */ for (;;) { index = get_cindex(key, n); /* This bit of code is a bit tricky but it combines multiple * checks into a single check. The prefix consists of the * prefix plus zeros for the "bits" in the prefix. The index * is the difference between the key and this value. From * this we can actually derive several pieces of data. * if (index >= (1ul << bits)) * we have a mismatch in skip bits and failed * else * we know the value is cindex * * This check is safe even if bits == KEYLENGTH due to the * fact that we can only allocate a node with 32 bits if a * long is greater than 32 bits. */ if (index >= (1ul << n->bits)) break; /* we have found a leaf. Prefixes have already been compared */ if (IS_LEAF(n)) goto found; /* only record pn and cindex if we are going to be chopping * bits later. Otherwise we are just wasting cycles. */ if (n->slen > n->pos) { pn = n; cindex = index; } n = get_child_rcu(n, index); if (unlikely(!n)) goto backtrace; } /* Step 2: Sort out leaves and begin backtracing for longest prefix */ for (;;) { /* record the pointer where our next node pointer is stored */ struct key_vector __rcu **cptr = n->tnode; /* This test verifies that none of the bits that differ * between the key and the prefix exist in the region of * the lsb and higher in the prefix. */ if (unlikely(prefix_mismatch(key, n)) || (n->slen == n->pos)) goto backtrace; /* exit out and process leaf */ if (unlikely(IS_LEAF(n))) break; /* Don't bother recording parent info. Since we are in * prefix match mode we will have to come back to wherever * we started this traversal anyway */ while ((n = rcu_dereference(*cptr)) == NULL) { backtrace: #ifdef CONFIG_IP_FIB_TRIE_STATS if (!n) this_cpu_inc(stats->null_node_hit); #endif /* If we are at cindex 0 there are no more bits for * us to strip at this level so we must ascend back * up one level to see if there are any more bits to * be stripped there. */ while (!cindex) { t_key pkey = pn->key; /* If we don't have a parent then there is * nothing for us to do as we do not have any * further nodes to parse. */ if (IS_TRIE(pn)) { trace_fib_table_lookup(tb->tb_id, flp, NULL, -EAGAIN); return -EAGAIN; } #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->backtrack); #endif /* Get Child's index */ pn = node_parent_rcu(pn); cindex = get_index(pkey, pn); } /* strip the least significant bit from the cindex */ cindex &= cindex - 1; /* grab pointer for next child node */ cptr = &pn->tnode[cindex]; } } found: /* this line carries forward the xor from earlier in the function */ index = key ^ n->key; /* Step 3: Process the leaf, if that fails fall back to backtracing */ hlist_for_each_entry_rcu(fa, &n->leaf, fa_list) { struct fib_info *fi = fa->fa_info; struct fib_nh_common *nhc; int nhsel, err; if ((BITS_PER_LONG > KEYLENGTH) || (fa->fa_slen < KEYLENGTH)) { if (index >= (1ul << fa->fa_slen)) continue; } if (fa->fa_dscp && !fib_dscp_masked_match(fa->fa_dscp, flp)) continue; /* Paired with WRITE_ONCE() in fib_release_info() */ if (READ_ONCE(fi->fib_dead)) continue; if (fa->fa_info->fib_scope < flp->flowi4_scope) continue; fib_alias_accessed(fa); err = fib_props[fa->fa_type].error; if (unlikely(err < 0)) { out_reject: #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->semantic_match_passed); #endif trace_fib_table_lookup(tb->tb_id, flp, NULL, err); return err; } if (fi->fib_flags & RTNH_F_DEAD) continue; if (unlikely(fi->nh)) { if (nexthop_is_blackhole(fi->nh)) { err = fib_props[RTN_BLACKHOLE].error; goto out_reject; } nhc = nexthop_get_nhc_lookup(fi->nh, fib_flags, flp, &nhsel); if (nhc) goto set_result; goto miss; } for (nhsel = 0; nhsel < fib_info_num_path(fi); nhsel++) { nhc = fib_info_nhc(fi, nhsel); if (!fib_lookup_good_nhc(nhc, fib_flags, flp)) continue; set_result: if (!(fib_flags & FIB_LOOKUP_NOREF)) refcount_inc(&fi->fib_clntref); res->prefix = htonl(n->key); res->prefixlen = KEYLENGTH - fa->fa_slen; res->nh_sel = nhsel; res->nhc = nhc; res->type = fa->fa_type; res->scope = fi->fib_scope; res->dscp = fa->fa_dscp; res->fi = fi; res->table = tb; res->fa_head = &n->leaf; #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->semantic_match_passed); #endif trace_fib_table_lookup(tb->tb_id, flp, nhc, err); return err; } } miss: #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->semantic_match_miss); #endif goto backtrace; } EXPORT_SYMBOL_GPL(fib_table_lookup); static void fib_remove_alias(struct trie *t, struct key_vector *tp, struct key_vector *l, struct fib_alias *old) { /* record the location of the previous list_info entry */ struct hlist_node **pprev = old->fa_list.pprev; struct fib_alias *fa = hlist_entry(pprev, typeof(*fa), fa_list.next); /* remove the fib_alias from the list */ hlist_del_rcu(&old->fa_list); /* if we emptied the list this leaf will be freed and we can sort * out parent suffix lengths as a part of trie_rebalance */ if (hlist_empty(&l->leaf)) { if (tp->slen == l->slen) node_pull_suffix(tp, tp->pos); put_child_root(tp, l->key, NULL); node_free(l); trie_rebalance(t, tp); return; } /* only access fa if it is pointing at the last valid hlist_node */ if (*pprev) return; /* update the trie with the latest suffix length */ l->slen = fa->fa_slen; node_pull_suffix(tp, fa->fa_slen); } static void fib_notify_alias_delete(struct net *net, u32 key, struct hlist_head *fah, struct fib_alias *fa_to_delete, struct netlink_ext_ack *extack) { struct fib_alias *fa_next, *fa_to_notify; u32 tb_id = fa_to_delete->tb_id; u8 slen = fa_to_delete->fa_slen; enum fib_event_type fib_event; /* Do not notify if we do not care about the route. */ if (fib_find_alias(fah, slen, 0, 0, tb_id, true) != fa_to_delete) return; /* Determine if the route should be replaced by the next route in the * list. */ fa_next = hlist_entry_safe(fa_to_delete->fa_list.next, struct fib_alias, fa_list); if (fa_next && fa_next->fa_slen == slen && fa_next->tb_id == tb_id) { fib_event = FIB_EVENT_ENTRY_REPLACE; fa_to_notify = fa_next; } else { fib_event = FIB_EVENT_ENTRY_DEL; fa_to_notify = fa_to_delete; } call_fib_entry_notifiers(net, fib_event, key, KEYLENGTH - slen, fa_to_notify, extack); } /* Caller must hold RTNL. */ int fib_table_delete(struct net *net, struct fib_table *tb, struct fib_config *cfg, struct netlink_ext_ack *extack) { struct trie *t = (struct trie *) tb->tb_data; struct fib_alias *fa, *fa_to_delete; struct key_vector *l, *tp; u8 plen = cfg->fc_dst_len; u8 slen = KEYLENGTH - plen; dscp_t dscp; u32 key; key = ntohl(cfg->fc_dst); if (!fib_valid_key_len(key, plen, extack)) return -EINVAL; l = fib_find_node(t, &tp, key); if (!l) return -ESRCH; dscp = cfg->fc_dscp; fa = fib_find_alias(&l->leaf, slen, dscp, 0, tb->tb_id, false); if (!fa) return -ESRCH; pr_debug("Deleting %08x/%d dsfield=0x%02x t=%p\n", key, plen, inet_dscp_to_dsfield(dscp), t); fa_to_delete = NULL; hlist_for_each_entry_from(fa, fa_list) { struct fib_info *fi = fa->fa_info; if ((fa->fa_slen != slen) || (fa->tb_id != tb->tb_id) || (fa->fa_dscp != dscp)) break; if ((!cfg->fc_type || fa->fa_type == cfg->fc_type) && (cfg->fc_scope == RT_SCOPE_NOWHERE || fa->fa_info->fib_scope == cfg->fc_scope) && (!cfg->fc_prefsrc || fi->fib_prefsrc == cfg->fc_prefsrc) && (!cfg->fc_protocol || fi->fib_protocol == cfg->fc_protocol) && fib_nh_match(net, cfg, fi, extack) == 0 && fib_metrics_match(cfg, fi)) { fa_to_delete = fa; break; } } if (!fa_to_delete) return -ESRCH; fib_notify_alias_delete(net, key, &l->leaf, fa_to_delete, extack); rtmsg_fib(RTM_DELROUTE, htonl(key), fa_to_delete, plen, tb->tb_id, &cfg->fc_nlinfo, 0); if (!plen) tb->tb_num_default--; fib_remove_alias(t, tp, l, fa_to_delete); if (fa_to_delete->fa_state & FA_S_ACCESSED) rt_cache_flush(cfg->fc_nlinfo.nl_net); fib_release_info(fa_to_delete->fa_info); alias_free_mem_rcu(fa_to_delete); return 0; } /* Scan for the next leaf starting at the provided key value */ static struct key_vector *leaf_walk_rcu(struct key_vector **tn, t_key key) { struct key_vector *pn, *n = *tn; unsigned long cindex; /* this loop is meant to try and find the key in the trie */ do { /* record parent and next child index */ pn = n; cindex = (key > pn->key) ? get_index(key, pn) : 0; if (cindex >> pn->bits) break; /* descend into the next child */ n = get_child_rcu(pn, cindex++); if (!n) break; /* guarantee forward progress on the keys */ if (IS_LEAF(n) && (n->key >= key)) goto found; } while (IS_TNODE(n)); /* this loop will search for the next leaf with a greater key */ while (!IS_TRIE(pn)) { /* if we exhausted the parent node we will need to climb */ if (cindex >= (1ul << pn->bits)) { t_key pkey = pn->key; pn = node_parent_rcu(pn); cindex = get_index(pkey, pn) + 1; continue; } /* grab the next available node */ n = get_child_rcu(pn, cindex++); if (!n) continue; /* no need to compare keys since we bumped the index */ if (IS_LEAF(n)) goto found; /* Rescan start scanning in new node */ pn = n; cindex = 0; } *tn = pn; return NULL; /* Root of trie */ found: /* if we are at the limit for keys just return NULL for the tnode */ *tn = pn; return n; } static void fib_trie_free(struct fib_table *tb) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *pn = t->kv; unsigned long cindex = 1; struct hlist_node *tmp; struct fib_alias *fa; /* walk trie in reverse order and free everything */ for (;;) { struct key_vector *n; if (!(cindex--)) { t_key pkey = pn->key; if (IS_TRIE(pn)) break; n = pn; pn = node_parent(pn); /* drop emptied tnode */ put_child_root(pn, n->key, NULL); node_free(n); cindex = get_index(pkey, pn); continue; } /* grab the next available node */ n = get_child(pn, cindex); if (!n) continue; if (IS_TNODE(n)) { /* record pn and cindex for leaf walking */ pn = n; cindex = 1ul << n->bits; continue; } hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) { hlist_del_rcu(&fa->fa_list); alias_free_mem_rcu(fa); } put_child_root(pn, n->key, NULL); node_free(n); } #ifdef CONFIG_IP_FIB_TRIE_STATS free_percpu(t->stats); #endif kfree(tb); } struct fib_table *fib_trie_unmerge(struct fib_table *oldtb) { struct trie *ot = (struct trie *)oldtb->tb_data; struct key_vector *l, *tp = ot->kv; struct fib_table *local_tb; struct fib_alias *fa; struct trie *lt; t_key key = 0; if (oldtb->tb_data == oldtb->__data) return oldtb; local_tb = fib_trie_table(RT_TABLE_LOCAL, NULL); if (!local_tb) return NULL; lt = (struct trie *)local_tb->tb_data; while ((l = leaf_walk_rcu(&tp, key)) != NULL) { struct key_vector *local_l = NULL, *local_tp; hlist_for_each_entry(fa, &l->leaf, fa_list) { struct fib_alias *new_fa; if (local_tb->tb_id != fa->tb_id) continue; /* clone fa for new local table */ new_fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL); if (!new_fa) goto out; memcpy(new_fa, fa, sizeof(*fa)); /* insert clone into table */ if (!local_l) local_l = fib_find_node(lt, &local_tp, l->key); if (fib_insert_alias(lt, local_tp, local_l, new_fa, NULL, l->key)) { kmem_cache_free(fn_alias_kmem, new_fa); goto out; } } /* stop loop if key wrapped back to 0 */ key = l->key + 1; if (key < l->key) break; } return local_tb; out: fib_trie_free(local_tb); return NULL; } /* Caller must hold RTNL */ void fib_table_flush_external(struct fib_table *tb) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *pn = t->kv; unsigned long cindex = 1; struct hlist_node *tmp; struct fib_alias *fa; /* walk trie in reverse order */ for (;;) { unsigned char slen = 0; struct key_vector *n; if (!(cindex--)) { t_key pkey = pn->key; /* cannot resize the trie vector */ if (IS_TRIE(pn)) break; /* update the suffix to address pulled leaves */ if (pn->slen > pn->pos) update_suffix(pn); /* resize completed node */ pn = resize(t, pn); cindex = get_index(pkey, pn); continue; } /* grab the next available node */ n = get_child(pn, cindex); if (!n) continue; if (IS_TNODE(n)) { /* record pn and cindex for leaf walking */ pn = n; cindex = 1ul << n->bits; continue; } hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) { /* if alias was cloned to local then we just * need to remove the local copy from main */ if (tb->tb_id != fa->tb_id) { hlist_del_rcu(&fa->fa_list); alias_free_mem_rcu(fa); continue; } /* record local slen */ slen = fa->fa_slen; } /* update leaf slen */ n->slen = slen; if (hlist_empty(&n->leaf)) { put_child_root(pn, n->key, NULL); node_free(n); } } } /* Caller must hold RTNL. */ int fib_table_flush(struct net *net, struct fib_table *tb, bool flush_all) { struct trie *t = (struct trie *)tb->tb_data; struct nl_info info = { .nl_net = net }; struct key_vector *pn = t->kv; unsigned long cindex = 1; struct hlist_node *tmp; struct fib_alias *fa; int found = 0; /* walk trie in reverse order */ for (;;) { unsigned char slen = 0; struct key_vector *n; if (!(cindex--)) { t_key pkey = pn->key; /* cannot resize the trie vector */ if (IS_TRIE(pn)) break; /* update the suffix to address pulled leaves */ if (pn->slen > pn->pos) update_suffix(pn); /* resize completed node */ pn = resize(t, pn); cindex = get_index(pkey, pn); continue; } /* grab the next available node */ n = get_child(pn, cindex); if (!n) continue; if (IS_TNODE(n)) { /* record pn and cindex for leaf walking */ pn = n; cindex = 1ul << n->bits; continue; } hlist_for_each_entry_safe(fa, tmp, &n->leaf, fa_list) { struct fib_info *fi = fa->fa_info; if (!fi || tb->tb_id != fa->tb_id || (!(fi->fib_flags & RTNH_F_DEAD) && !fib_props[fa->fa_type].error)) { slen = fa->fa_slen; continue; } /* Do not flush error routes if network namespace is * not being dismantled */ if (!flush_all && fib_props[fa->fa_type].error) { slen = fa->fa_slen; continue; } fib_notify_alias_delete(net, n->key, &n->leaf, fa, NULL); if (fi->pfsrc_removed) rtmsg_fib(RTM_DELROUTE, htonl(n->key), fa, KEYLENGTH - fa->fa_slen, tb->tb_id, &info, 0); hlist_del_rcu(&fa->fa_list); fib_release_info(fa->fa_info); alias_free_mem_rcu(fa); found++; } /* update leaf slen */ n->slen = slen; if (hlist_empty(&n->leaf)) { put_child_root(pn, n->key, NULL); node_free(n); } } pr_debug("trie_flush found=%d\n", found); return found; } /* derived from fib_trie_free */ static void __fib_info_notify_update(struct net *net, struct fib_table *tb, struct nl_info *info) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *pn = t->kv; unsigned long cindex = 1; struct fib_alias *fa; for (;;) { struct key_vector *n; if (!(cindex--)) { t_key pkey = pn->key; if (IS_TRIE(pn)) break; pn = node_parent(pn); cindex = get_index(pkey, pn); continue; } /* grab the next available node */ n = get_child(pn, cindex); if (!n) continue; if (IS_TNODE(n)) { /* record pn and cindex for leaf walking */ pn = n; cindex = 1ul << n->bits; continue; } hlist_for_each_entry(fa, &n->leaf, fa_list) { struct fib_info *fi = fa->fa_info; if (!fi || !fi->nh_updated || fa->tb_id != tb->tb_id) continue; rtmsg_fib(RTM_NEWROUTE, htonl(n->key), fa, KEYLENGTH - fa->fa_slen, tb->tb_id, info, NLM_F_REPLACE); } } } void fib_info_notify_update(struct net *net, struct nl_info *info) { unsigned int h; for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct fib_table *tb; hlist_for_each_entry_rcu(tb, head, tb_hlist, lockdep_rtnl_is_held()) __fib_info_notify_update(net, tb, info); } } static int fib_leaf_notify(struct key_vector *l, struct fib_table *tb, struct notifier_block *nb, struct netlink_ext_ack *extack) { struct fib_alias *fa; int last_slen = -1; int err; hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { struct fib_info *fi = fa->fa_info; if (!fi) continue; /* local and main table can share the same trie, * so don't notify twice for the same entry. */ if (tb->tb_id != fa->tb_id) continue; if (fa->fa_slen == last_slen) continue; last_slen = fa->fa_slen; err = call_fib_entry_notifier(nb, FIB_EVENT_ENTRY_REPLACE, l->key, KEYLENGTH - fa->fa_slen, fa, extack); if (err) return err; } return 0; } static int fib_table_notify(struct fib_table *tb, struct notifier_block *nb, struct netlink_ext_ack *extack) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *l, *tp = t->kv; t_key key = 0; int err; while ((l = leaf_walk_rcu(&tp, key)) != NULL) { err = fib_leaf_notify(l, tb, nb, extack); if (err) return err; key = l->key + 1; /* stop in case of wrap around */ if (key < l->key) break; } return 0; } int fib_notify(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { unsigned int h; int err; for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct fib_table *tb; hlist_for_each_entry_rcu(tb, head, tb_hlist) { err = fib_table_notify(tb, nb, extack); if (err) return err; } } return 0; } static void __trie_free_rcu(struct rcu_head *head) { struct fib_table *tb = container_of(head, struct fib_table, rcu); #ifdef CONFIG_IP_FIB_TRIE_STATS struct trie *t = (struct trie *)tb->tb_data; if (tb->tb_data == tb->__data) free_percpu(t->stats); #endif /* CONFIG_IP_FIB_TRIE_STATS */ kfree(tb); } void fib_free_table(struct fib_table *tb) { call_rcu(&tb->rcu, __trie_free_rcu); } static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb, struct sk_buff *skb, struct netlink_callback *cb, struct fib_dump_filter *filter) { unsigned int flags = NLM_F_MULTI; __be32 xkey = htonl(l->key); int i, s_i, i_fa, s_fa, err; struct fib_alias *fa; if (filter->filter_set || !filter->dump_exceptions || !filter->dump_routes) flags |= NLM_F_DUMP_FILTERED; s_i = cb->args[4]; s_fa = cb->args[5]; i = 0; /* rcu_read_lock is hold by caller */ hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { struct fib_info *fi = fa->fa_info; if (i < s_i) goto next; i_fa = 0; if (tb->tb_id != fa->tb_id) goto next; if (filter->filter_set) { if (filter->rt_type && fa->fa_type != filter->rt_type) goto next; if ((filter->protocol && fi->fib_protocol != filter->protocol)) goto next; if (filter->dev && !fib_info_nh_uses_dev(fi, filter->dev)) goto next; } if (filter->dump_routes) { if (!s_fa) { struct fib_rt_info fri; fri.fi = fi; fri.tb_id = tb->tb_id; fri.dst = xkey; fri.dst_len = KEYLENGTH - fa->fa_slen; fri.dscp = fa->fa_dscp; fri.type = fa->fa_type; fri.offload = READ_ONCE(fa->offload); fri.trap = READ_ONCE(fa->trap); fri.offload_failed = READ_ONCE(fa->offload_failed); err = fib_dump_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWROUTE, &fri, flags); if (err < 0) goto stop; } i_fa++; } if (filter->dump_exceptions) { err = fib_dump_info_fnhe(skb, cb, tb->tb_id, fi, &i_fa, s_fa, flags); if (err < 0) goto stop; } next: i++; } cb->args[4] = i; return skb->len; stop: cb->args[4] = i; cb->args[5] = i_fa; return err; } /* rcu_read_lock needs to be hold by caller from readside */ int fib_table_dump(struct fib_table *tb, struct sk_buff *skb, struct netlink_callback *cb, struct fib_dump_filter *filter) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *l, *tp = t->kv; /* Dump starting at last key. * Note: 0.0.0.0/0 (ie default) is first key. */ int count = cb->args[2]; t_key key = cb->args[3]; /* First time here, count and key are both always 0. Count > 0 * and key == 0 means the dump has wrapped around and we are done. */ if (count && !key) return 0; while ((l = leaf_walk_rcu(&tp, key)) != NULL) { int err; err = fn_trie_dump_leaf(l, tb, skb, cb, filter); if (err < 0) { cb->args[3] = key; cb->args[2] = count; return err; } ++count; key = l->key + 1; memset(&cb->args[4], 0, sizeof(cb->args) - 4*sizeof(cb->args[0])); /* stop loop if key wrapped back to 0 */ if (key < l->key) break; } cb->args[3] = key; cb->args[2] = count; return 0; } void __init fib_trie_init(void) { fn_alias_kmem = kmem_cache_create("ip_fib_alias", sizeof(struct fib_alias), 0, SLAB_PANIC | SLAB_ACCOUNT, NULL); trie_leaf_kmem = kmem_cache_create("ip_fib_trie", LEAF_SIZE, 0, SLAB_PANIC | SLAB_ACCOUNT, NULL); } struct fib_table *fib_trie_table(u32 id, struct fib_table *alias) { struct fib_table *tb; struct trie *t; size_t sz = sizeof(*tb); if (!alias) sz += sizeof(struct trie); tb = kzalloc(sz, GFP_KERNEL); if (!tb) return NULL; tb->tb_id = id; tb->tb_num_default = 0; tb->tb_data = (alias ? alias->__data : tb->__data); if (alias) return tb; t = (struct trie *) tb->tb_data; t->kv[0].pos = KEYLENGTH; t->kv[0].slen = KEYLENGTH; #ifdef CONFIG_IP_FIB_TRIE_STATS t->stats = alloc_percpu(struct trie_use_stats); if (!t->stats) { kfree(tb); tb = NULL; } #endif return tb; } #ifdef CONFIG_PROC_FS /* Depth first Trie walk iterator */ struct fib_trie_iter { struct seq_net_private p; struct fib_table *tb; struct key_vector *tnode; unsigned int index; unsigned int depth; }; static struct key_vector *fib_trie_get_next(struct fib_trie_iter *iter) { unsigned long cindex = iter->index; struct key_vector *pn = iter->tnode; t_key pkey; pr_debug("get_next iter={node=%p index=%d depth=%d}\n", iter->tnode, iter->index, iter->depth); while (!IS_TRIE(pn)) { while (cindex < child_length(pn)) { struct key_vector *n = get_child_rcu(pn, cindex++); if (!n) continue; if (IS_LEAF(n)) { iter->tnode = pn; iter->index = cindex; } else { /* push down one level */ iter->tnode = n; iter->index = 0; ++iter->depth; } return n; } /* Current node exhausted, pop back up */ pkey = pn->key; pn = node_parent_rcu(pn); cindex = get_index(pkey, pn) + 1; --iter->depth; } /* record root node so further searches know we are done */ iter->tnode = pn; iter->index = 0; return NULL; } static struct key_vector *fib_trie_get_first(struct fib_trie_iter *iter, struct trie *t) { struct key_vector *n, *pn; if (!t) return NULL; pn = t->kv; n = rcu_dereference(pn->tnode[0]); if (!n) return NULL; if (IS_TNODE(n)) { iter->tnode = n; iter->index = 0; iter->depth = 1; } else { iter->tnode = pn; iter->index = 0; iter->depth = 0; } return n; } static void trie_collect_stats(struct trie *t, struct trie_stat *s) { struct key_vector *n; struct fib_trie_iter iter; memset(s, 0, sizeof(*s)); rcu_read_lock(); for (n = fib_trie_get_first(&iter, t); n; n = fib_trie_get_next(&iter)) { if (IS_LEAF(n)) { struct fib_alias *fa; s->leaves++; s->totdepth += iter.depth; if (iter.depth > s->maxdepth) s->maxdepth = iter.depth; hlist_for_each_entry_rcu(fa, &n->leaf, fa_list) ++s->prefixes; } else { s->tnodes++; if (n->bits < MAX_STAT_DEPTH) s->nodesizes[n->bits]++; s->nullpointers += tn_info(n)->empty_children; } } rcu_read_unlock(); } /* * This outputs /proc/net/fib_triestats */ static void trie_show_stats(struct seq_file *seq, struct trie_stat *stat) { unsigned int i, max, pointers, bytes, avdepth; if (stat->leaves) avdepth = stat->totdepth*100 / stat->leaves; else avdepth = 0; seq_printf(seq, "\tAver depth: %u.%02d\n", avdepth / 100, avdepth % 100); seq_printf(seq, "\tMax depth: %u\n", stat->maxdepth); seq_printf(seq, "\tLeaves: %u\n", stat->leaves); bytes = LEAF_SIZE * stat->leaves; seq_printf(seq, "\tPrefixes: %u\n", stat->prefixes); bytes += sizeof(struct fib_alias) * stat->prefixes; seq_printf(seq, "\tInternal nodes: %u\n\t", stat->tnodes); bytes += TNODE_SIZE(0) * stat->tnodes; max = MAX_STAT_DEPTH; while (max > 0 && stat->nodesizes[max-1] == 0) max--; pointers = 0; for (i = 1; i < max; i++) if (stat->nodesizes[i] != 0) { seq_printf(seq, " %u: %u", i, stat->nodesizes[i]); pointers += (1<<i) * stat->nodesizes[i]; } seq_putc(seq, '\n'); seq_printf(seq, "\tPointers: %u\n", pointers); bytes += sizeof(struct key_vector *) * pointers; seq_printf(seq, "Null ptrs: %u\n", stat->nullpointers); seq_printf(seq, "Total size: %u kB\n", (bytes + 1023) / 1024); } #ifdef CONFIG_IP_FIB_TRIE_STATS static void trie_show_usage(struct seq_file *seq, const struct trie_use_stats __percpu *stats) { struct trie_use_stats s = { 0 }; int cpu; /* loop through all of the CPUs and gather up the stats */ for_each_possible_cpu(cpu) { const struct trie_use_stats *pcpu = per_cpu_ptr(stats, cpu); s.gets += pcpu->gets; s.backtrack += pcpu->backtrack; s.semantic_match_passed += pcpu->semantic_match_passed; s.semantic_match_miss += pcpu->semantic_match_miss; s.null_node_hit += pcpu->null_node_hit; s.resize_node_skipped += pcpu->resize_node_skipped; } seq_printf(seq, "\nCounters:\n---------\n"); seq_printf(seq, "gets = %u\n", s.gets); seq_printf(seq, "backtracks = %u\n", s.backtrack); seq_printf(seq, "semantic match passed = %u\n", s.semantic_match_passed); seq_printf(seq, "semantic match miss = %u\n", s.semantic_match_miss); seq_printf(seq, "null node hit= %u\n", s.null_node_hit); seq_printf(seq, "skipped node resize = %u\n\n", s.resize_node_skipped); } #endif /* CONFIG_IP_FIB_TRIE_STATS */ static void fib_table_print(struct seq_file *seq, struct fib_table *tb) { if (tb->tb_id == RT_TABLE_LOCAL) seq_puts(seq, "Local:\n"); else if (tb->tb_id == RT_TABLE_MAIN) seq_puts(seq, "Main:\n"); else seq_printf(seq, "Id %d:\n", tb->tb_id); } static int fib_triestat_seq_show(struct seq_file *seq, void *v) { struct net *net = seq->private; unsigned int h; seq_printf(seq, "Basic info: size of leaf:" " %zd bytes, size of tnode: %zd bytes.\n", LEAF_SIZE, TNODE_SIZE(0)); rcu_read_lock(); for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct fib_table *tb; hlist_for_each_entry_rcu(tb, head, tb_hlist) { struct trie *t = (struct trie *) tb->tb_data; struct trie_stat stat; if (!t) continue; fib_table_print(seq, tb); trie_collect_stats(t, &stat); trie_show_stats(seq, &stat); #ifdef CONFIG_IP_FIB_TRIE_STATS trie_show_usage(seq, t->stats); #endif } cond_resched_rcu(); } rcu_read_unlock(); return 0; } static struct key_vector *fib_trie_get_idx(struct seq_file *seq, loff_t pos) { struct fib_trie_iter *iter = seq->private; struct net *net = seq_file_net(seq); loff_t idx = 0; unsigned int h; for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct fib_table *tb; hlist_for_each_entry_rcu(tb, head, tb_hlist) { struct key_vector *n; for (n = fib_trie_get_first(iter, (struct trie *) tb->tb_data); n; n = fib_trie_get_next(iter)) if (pos == idx++) { iter->tb = tb; return n; } } } return NULL; } static void *fib_trie_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { rcu_read_lock(); return fib_trie_get_idx(seq, *pos); } static void *fib_trie_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct fib_trie_iter *iter = seq->private; struct net *net = seq_file_net(seq); struct fib_table *tb = iter->tb; struct hlist_node *tb_node; unsigned int h; struct key_vector *n; ++*pos; /* next node in same table */ n = fib_trie_get_next(iter); if (n) return n; /* walk rest of this hash chain */ h = tb->tb_id & (FIB_TABLE_HASHSZ - 1); while ((tb_node = rcu_dereference(hlist_next_rcu(&tb->tb_hlist)))) { tb = hlist_entry(tb_node, struct fib_table, tb_hlist); n = fib_trie_get_first(iter, (struct trie *) tb->tb_data); if (n) goto found; } /* new hash chain */ while (++h < FIB_TABLE_HASHSZ) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; hlist_for_each_entry_rcu(tb, head, tb_hlist) { n = fib_trie_get_first(iter, (struct trie *) tb->tb_data); if (n) goto found; } } return NULL; found: iter->tb = tb; return n; } static void fib_trie_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static void seq_indent(struct seq_file *seq, int n) { while (n-- > 0) seq_puts(seq, " "); } static inline const char *rtn_scope(char *buf, size_t len, enum rt_scope_t s) { switch (s) { case RT_SCOPE_UNIVERSE: return "universe"; case RT_SCOPE_SITE: return "site"; case RT_SCOPE_LINK: return "link"; case RT_SCOPE_HOST: return "host"; case RT_SCOPE_NOWHERE: return "nowhere"; default: snprintf(buf, len, "scope=%d", s); return buf; } } static const char *const rtn_type_names[__RTN_MAX] = { [RTN_UNSPEC] = "UNSPEC", [RTN_UNICAST] = "UNICAST", [RTN_LOCAL] = "LOCAL", [RTN_BROADCAST] = "BROADCAST", [RTN_ANYCAST] = "ANYCAST", [RTN_MULTICAST] = "MULTICAST", [RTN_BLACKHOLE] = "BLACKHOLE", [RTN_UNREACHABLE] = "UNREACHABLE", [RTN_PROHIBIT] = "PROHIBIT", [RTN_THROW] = "THROW", [RTN_NAT] = "NAT", [RTN_XRESOLVE] = "XRESOLVE", }; static inline const char *rtn_type(char *buf, size_t len, unsigned int t) { if (t < __RTN_MAX && rtn_type_names[t]) return rtn_type_names[t]; snprintf(buf, len, "type %u", t); return buf; } /* Pretty print the trie */ static int fib_trie_seq_show(struct seq_file *seq, void *v) { const struct fib_trie_iter *iter = seq->private; struct key_vector *n = v; if (IS_TRIE(node_parent_rcu(n))) fib_table_print(seq, iter->tb); if (IS_TNODE(n)) { __be32 prf = htonl(n->key); seq_indent(seq, iter->depth-1); seq_printf(seq, " +-- %pI4/%zu %u %u %u\n", &prf, KEYLENGTH - n->pos - n->bits, n->bits, tn_info(n)->full_children, tn_info(n)->empty_children); } else { __be32 val = htonl(n->key); struct fib_alias *fa; seq_indent(seq, iter->depth); seq_printf(seq, " |-- %pI4\n", &val); hlist_for_each_entry_rcu(fa, &n->leaf, fa_list) { char buf1[32], buf2[32]; seq_indent(seq, iter->depth + 1); seq_printf(seq, " /%zu %s %s", KEYLENGTH - fa->fa_slen, rtn_scope(buf1, sizeof(buf1), fa->fa_info->fib_scope), rtn_type(buf2, sizeof(buf2), fa->fa_type)); if (fa->fa_dscp) seq_printf(seq, " tos=%d", inet_dscp_to_dsfield(fa->fa_dscp)); seq_putc(seq, '\n'); } } return 0; } static const struct seq_operations fib_trie_seq_ops = { .start = fib_trie_seq_start, .next = fib_trie_seq_next, .stop = fib_trie_seq_stop, .show = fib_trie_seq_show, }; struct fib_route_iter { struct seq_net_private p; struct fib_table *main_tb; struct key_vector *tnode; loff_t pos; t_key key; }; static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter, loff_t pos) { struct key_vector *l, **tp = &iter->tnode; t_key key; /* use cached location of previously found key */ if (iter->pos > 0 && pos >= iter->pos) { key = iter->key; } else { iter->pos = 1; key = 0; } pos -= iter->pos; while ((l = leaf_walk_rcu(tp, key)) && (pos-- > 0)) { key = l->key + 1; iter->pos++; l = NULL; /* handle unlikely case of a key wrap */ if (!key) break; } if (l) iter->key = l->key; /* remember it */ else iter->pos = 0; /* forget it */ return l; } static void *fib_route_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { struct fib_route_iter *iter = seq->private; struct fib_table *tb; struct trie *t; rcu_read_lock(); tb = fib_get_table(seq_file_net(seq), RT_TABLE_MAIN); if (!tb) return NULL; iter->main_tb = tb; t = (struct trie *)tb->tb_data; iter->tnode = t->kv; if (*pos != 0) return fib_route_get_idx(iter, *pos); iter->pos = 0; iter->key = KEY_MAX; return SEQ_START_TOKEN; } static void *fib_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct fib_route_iter *iter = seq->private; struct key_vector *l = NULL; t_key key = iter->key + 1; ++*pos; /* only allow key of 0 for start of sequence */ if ((v == SEQ_START_TOKEN) || key) l = leaf_walk_rcu(&iter->tnode, key); if (l) { iter->key = l->key; iter->pos++; } else { iter->pos = 0; } return l; } static void fib_route_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static unsigned int fib_flag_trans(int type, __be32 mask, struct fib_info *fi) { unsigned int flags = 0; if (type == RTN_UNREACHABLE || type == RTN_PROHIBIT) flags = RTF_REJECT; if (fi) { const struct fib_nh_common *nhc = fib_info_nhc(fi, 0); if (nhc->nhc_gw.ipv4) flags |= RTF_GATEWAY; } if (mask == htonl(0xFFFFFFFF)) flags |= RTF_HOST; flags |= RTF_UP; return flags; } /* * This outputs /proc/net/route. * The format of the file is not supposed to be changed * and needs to be same as fib_hash output to avoid breaking * legacy utilities */ static int fib_route_seq_show(struct seq_file *seq, void *v) { struct fib_route_iter *iter = seq->private; struct fib_table *tb = iter->main_tb; struct fib_alias *fa; struct key_vector *l = v; __be32 prefix; if (v == SEQ_START_TOKEN) { seq_printf(seq, "%-127s\n", "Iface\tDestination\tGateway " "\tFlags\tRefCnt\tUse\tMetric\tMask\t\tMTU" "\tWindow\tIRTT"); return 0; } prefix = htonl(l->key); hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { struct fib_info *fi = fa->fa_info; __be32 mask = inet_make_mask(KEYLENGTH - fa->fa_slen); unsigned int flags = fib_flag_trans(fa->fa_type, mask, fi); if ((fa->fa_type == RTN_BROADCAST) || (fa->fa_type == RTN_MULTICAST)) continue; if (fa->tb_id != tb->tb_id) continue; seq_setwidth(seq, 127); if (fi) { struct fib_nh_common *nhc = fib_info_nhc(fi, 0); __be32 gw = 0; if (nhc->nhc_gw_family == AF_INET) gw = nhc->nhc_gw.ipv4; seq_printf(seq, "%s\t%08X\t%08X\t%04X\t%d\t%u\t" "%u\t%08X\t%d\t%u\t%u", nhc->nhc_dev ? nhc->nhc_dev->name : "*", prefix, gw, flags, 0, 0, fi->fib_priority, mask, (fi->fib_advmss ? fi->fib_advmss + 40 : 0), fi->fib_window, fi->fib_rtt >> 3); } else { seq_printf(seq, "*\t%08X\t%08X\t%04X\t%d\t%u\t" "%u\t%08X\t%d\t%u\t%u", prefix, 0, flags, 0, 0, 0, mask, 0, 0, 0); } seq_pad(seq, '\n'); } return 0; } static const struct seq_operations fib_route_seq_ops = { .start = fib_route_seq_start, .next = fib_route_seq_next, .stop = fib_route_seq_stop, .show = fib_route_seq_show, }; int __net_init fib_proc_init(struct net *net) { if (!proc_create_net("fib_trie", 0444, net->proc_net, &fib_trie_seq_ops, sizeof(struct fib_trie_iter))) goto out1; if (!proc_create_net_single("fib_triestat", 0444, net->proc_net, fib_triestat_seq_show, NULL)) goto out2; if (!proc_create_net("route", 0444, net->proc_net, &fib_route_seq_ops, sizeof(struct fib_route_iter))) goto out3; return 0; out3: remove_proc_entry("fib_triestat", net->proc_net); out2: remove_proc_entry("fib_trie", net->proc_net); out1: return -ENOMEM; } void __net_exit fib_proc_exit(struct net *net) { remove_proc_entry("fib_trie", net->proc_net); remove_proc_entry("fib_triestat", net->proc_net); remove_proc_entry("route", net->proc_net); } #endif /* CONFIG_PROC_FS */ |
| 1 1 1 5 3 3 1 2 2 2 2 2 5 5 4 1 1 1 4 3 644 45 45 24 644 249 17 17 249 9 9 9 9 9 9 8 4 4 4 4 2 2 4 1 1 1 1 2 2 4 4 4 4 4 4 4 1 1 1 4 4 11 10 9 4 4 4 7 4 2 4 11 11 3 3 2 2 3 3 2 2 1 1 1 2 1 3 17 1146 250 1144 645 387 17 17 397 394 397 396 103 395 2 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Shared Memory Communications over RDMA (SMC-R) and RoCE * * Generic netlink support functions to configure an SMC-R PNET table * * Copyright IBM Corp. 2016 * * Author(s): Thomas Richter <tmricht@linux.vnet.ibm.com> */ #include <linux/module.h> #include <linux/list.h> #include <linux/ctype.h> #include <linux/mutex.h> #include <net/netlink.h> #include <net/genetlink.h> #include <uapi/linux/if.h> #include <uapi/linux/smc.h> #include <rdma/ib_verbs.h> #include <net/netns/generic.h> #include "smc_netns.h" #include "smc_pnet.h" #include "smc_ib.h" #include "smc_ism.h" #include "smc_core.h" static struct net_device *__pnet_find_base_ndev(struct net_device *ndev); static struct net_device *pnet_find_base_ndev(struct net_device *ndev); static const struct nla_policy smc_pnet_policy[SMC_PNETID_MAX + 1] = { [SMC_PNETID_NAME] = { .type = NLA_NUL_STRING, .len = SMC_MAX_PNETID_LEN }, [SMC_PNETID_ETHNAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 }, [SMC_PNETID_IBNAME] = { .type = NLA_NUL_STRING, .len = IB_DEVICE_NAME_MAX - 1 }, [SMC_PNETID_IBPORT] = { .type = NLA_U8 } }; static struct genl_family smc_pnet_nl_family; enum smc_pnet_nametype { SMC_PNET_ETH = 1, SMC_PNET_IB = 2, }; /* pnet entry stored in pnet table */ struct smc_pnetentry { struct list_head list; char pnet_name[SMC_MAX_PNETID_LEN + 1]; enum smc_pnet_nametype type; union { struct { char eth_name[IFNAMSIZ + 1]; struct net_device *ndev; netdevice_tracker dev_tracker; }; struct { char ib_name[IB_DEVICE_NAME_MAX + 1]; u8 ib_port; }; }; }; /* Check if the pnetid is set */ bool smc_pnet_is_pnetid_set(u8 *pnetid) { if (pnetid[0] == 0 || pnetid[0] == _S) return false; return true; } /* Check if two given pnetids match */ static bool smc_pnet_match(u8 *pnetid1, u8 *pnetid2) { int i; for (i = 0; i < SMC_MAX_PNETID_LEN; i++) { if ((pnetid1[i] == 0 || pnetid1[i] == _S) && (pnetid2[i] == 0 || pnetid2[i] == _S)) break; if (pnetid1[i] != pnetid2[i]) return false; } return true; } /* Remove a pnetid from the pnet table. */ static int smc_pnet_remove_by_pnetid(struct net *net, char *pnet_name) { struct smc_pnetentry *pnetelem, *tmp_pe; struct smc_pnettable *pnettable; struct smc_ib_device *ibdev; struct smcd_dev *smcd; struct smc_net *sn; int rc = -ENOENT; int ibport; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; /* remove table entry */ mutex_lock(&pnettable->lock); list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist, list) { if (!pnet_name || smc_pnet_match(pnetelem->pnet_name, pnet_name)) { list_del(&pnetelem->list); if (pnetelem->type == SMC_PNET_ETH && pnetelem->ndev) { netdev_put(pnetelem->ndev, &pnetelem->dev_tracker); pr_warn_ratelimited("smc: net device %s " "erased user defined " "pnetid %.16s\n", pnetelem->eth_name, pnetelem->pnet_name); } kfree(pnetelem); rc = 0; } } mutex_unlock(&pnettable->lock); /* if this is not the initial namespace, stop here */ if (net != &init_net) return rc; /* remove ib devices */ mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { for (ibport = 0; ibport < SMC_MAX_PORTS; ibport++) { if (ibdev->pnetid_by_user[ibport] && (!pnet_name || smc_pnet_match(pnet_name, ibdev->pnetid[ibport]))) { pr_warn_ratelimited("smc: ib device %s ibport " "%d erased user defined " "pnetid %.16s\n", ibdev->ibdev->name, ibport + 1, ibdev->pnetid[ibport]); memset(ibdev->pnetid[ibport], 0, SMC_MAX_PNETID_LEN); ibdev->pnetid_by_user[ibport] = false; rc = 0; } } } mutex_unlock(&smc_ib_devices.mutex); /* remove smcd devices */ mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(smcd, &smcd_dev_list.list, list) { if (smcd->pnetid_by_user && (!pnet_name || smc_pnet_match(pnet_name, smcd->pnetid))) { pr_warn_ratelimited("smc: smcd device %s " "erased user defined pnetid " "%.16s\n", dev_name(smcd->ops->get_dev(smcd)), smcd->pnetid); memset(smcd->pnetid, 0, SMC_MAX_PNETID_LEN); smcd->pnetid_by_user = false; rc = 0; } } mutex_unlock(&smcd_dev_list.mutex); return rc; } /* Add the reference to a given network device to the pnet table. */ static int smc_pnet_add_by_ndev(struct net_device *ndev) { struct smc_pnetentry *pnetelem, *tmp_pe; struct smc_pnettable *pnettable; struct net *net = dev_net(ndev); struct smc_net *sn; int rc = -ENOENT; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; mutex_lock(&pnettable->lock); list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist, list) { if (pnetelem->type == SMC_PNET_ETH && !pnetelem->ndev && !strncmp(pnetelem->eth_name, ndev->name, IFNAMSIZ)) { netdev_hold(ndev, &pnetelem->dev_tracker, GFP_ATOMIC); pnetelem->ndev = ndev; rc = 0; pr_warn_ratelimited("smc: adding net device %s with " "user defined pnetid %.16s\n", pnetelem->eth_name, pnetelem->pnet_name); break; } } mutex_unlock(&pnettable->lock); return rc; } /* Remove the reference to a given network device from the pnet table. */ static int smc_pnet_remove_by_ndev(struct net_device *ndev) { struct smc_pnetentry *pnetelem, *tmp_pe; struct smc_pnettable *pnettable; struct net *net = dev_net(ndev); struct smc_net *sn; int rc = -ENOENT; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; mutex_lock(&pnettable->lock); list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist, list) { if (pnetelem->type == SMC_PNET_ETH && pnetelem->ndev == ndev) { netdev_put(pnetelem->ndev, &pnetelem->dev_tracker); pnetelem->ndev = NULL; rc = 0; pr_warn_ratelimited("smc: removing net device %s with " "user defined pnetid %.16s\n", pnetelem->eth_name, pnetelem->pnet_name); break; } } mutex_unlock(&pnettable->lock); return rc; } /* Apply pnetid to ib device when no pnetid is set. */ static bool smc_pnet_apply_ib(struct smc_ib_device *ib_dev, u8 ib_port, char *pnet_name) { bool applied = false; mutex_lock(&smc_ib_devices.mutex); if (!smc_pnet_is_pnetid_set(ib_dev->pnetid[ib_port - 1])) { memcpy(ib_dev->pnetid[ib_port - 1], pnet_name, SMC_MAX_PNETID_LEN); ib_dev->pnetid_by_user[ib_port - 1] = true; applied = true; } mutex_unlock(&smc_ib_devices.mutex); return applied; } /* Apply pnetid to smcd device when no pnetid is set. */ static bool smc_pnet_apply_smcd(struct smcd_dev *smcd_dev, char *pnet_name) { bool applied = false; mutex_lock(&smcd_dev_list.mutex); if (!smc_pnet_is_pnetid_set(smcd_dev->pnetid)) { memcpy(smcd_dev->pnetid, pnet_name, SMC_MAX_PNETID_LEN); smcd_dev->pnetid_by_user = true; applied = true; } mutex_unlock(&smcd_dev_list.mutex); return applied; } /* The limit for pnetid is 16 characters. * Valid characters should be (single-byte character set) a-z, A-Z, 0-9. * Lower case letters are converted to upper case. * Interior blanks should not be used. */ static bool smc_pnetid_valid(const char *pnet_name, char *pnetid) { char *bf = skip_spaces(pnet_name); size_t len = strlen(bf); char *end = bf + len; if (!len) return false; while (--end >= bf && isspace(*end)) ; if (end - bf >= SMC_MAX_PNETID_LEN) return false; while (bf <= end) { if (!isalnum(*bf)) return false; *pnetid++ = islower(*bf) ? toupper(*bf) : *bf; bf++; } *pnetid = '\0'; return true; } /* Find an infiniband device by a given name. The device might not exist. */ static struct smc_ib_device *smc_pnet_find_ib(char *ib_name) { struct smc_ib_device *ibdev; mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { if (!strncmp(ibdev->ibdev->name, ib_name, sizeof(ibdev->ibdev->name)) || (ibdev->ibdev->dev.parent && !strncmp(dev_name(ibdev->ibdev->dev.parent), ib_name, IB_DEVICE_NAME_MAX - 1))) { goto out; } } ibdev = NULL; out: mutex_unlock(&smc_ib_devices.mutex); return ibdev; } /* Find an smcd device by a given name. The device might not exist. */ static struct smcd_dev *smc_pnet_find_smcd(char *smcd_name) { struct smcd_dev *smcd_dev; mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(smcd_dev, &smcd_dev_list.list, list) { if (!strncmp(dev_name(smcd_dev->ops->get_dev(smcd_dev)), smcd_name, IB_DEVICE_NAME_MAX - 1)) goto out; } smcd_dev = NULL; out: mutex_unlock(&smcd_dev_list.mutex); return smcd_dev; } static int smc_pnet_add_eth(struct smc_pnettable *pnettable, struct net *net, char *eth_name, char *pnet_name) { struct smc_pnetentry *tmp_pe, *new_pe; struct net_device *ndev, *base_ndev; u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; bool new_netdev; int rc; /* check if (base) netdev already has a pnetid. If there is one, we do * not want to add a pnet table entry */ rc = -EEXIST; ndev = dev_get_by_name(net, eth_name); /* dev_hold() */ if (ndev) { base_ndev = pnet_find_base_ndev(ndev); if (!smc_pnetid_by_dev_port(base_ndev->dev.parent, base_ndev->dev_port, ndev_pnetid)) goto out_put; } /* add a new netdev entry to the pnet table if there isn't one */ rc = -ENOMEM; new_pe = kzalloc(sizeof(*new_pe), GFP_KERNEL); if (!new_pe) goto out_put; new_pe->type = SMC_PNET_ETH; memcpy(new_pe->pnet_name, pnet_name, SMC_MAX_PNETID_LEN); strncpy(new_pe->eth_name, eth_name, IFNAMSIZ); rc = -EEXIST; new_netdev = true; mutex_lock(&pnettable->lock); list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) { if (tmp_pe->type == SMC_PNET_ETH && !strncmp(tmp_pe->eth_name, eth_name, IFNAMSIZ)) { new_netdev = false; break; } } if (new_netdev) { if (ndev) { new_pe->ndev = ndev; netdev_tracker_alloc(ndev, &new_pe->dev_tracker, GFP_ATOMIC); } list_add_tail(&new_pe->list, &pnettable->pnetlist); mutex_unlock(&pnettable->lock); } else { mutex_unlock(&pnettable->lock); kfree(new_pe); goto out_put; } if (ndev) pr_warn_ratelimited("smc: net device %s " "applied user defined pnetid %.16s\n", new_pe->eth_name, new_pe->pnet_name); return 0; out_put: dev_put(ndev); return rc; } static int smc_pnet_add_ib(struct smc_pnettable *pnettable, char *ib_name, u8 ib_port, char *pnet_name) { struct smc_pnetentry *tmp_pe, *new_pe; struct smc_ib_device *ib_dev; bool smcddev_applied = true; bool ibdev_applied = true; struct smcd_dev *smcd; struct device *dev; bool new_ibdev; /* try to apply the pnetid to active devices */ ib_dev = smc_pnet_find_ib(ib_name); if (ib_dev) { ibdev_applied = smc_pnet_apply_ib(ib_dev, ib_port, pnet_name); if (ibdev_applied) pr_warn_ratelimited("smc: ib device %s ibport %d " "applied user defined pnetid " "%.16s\n", ib_dev->ibdev->name, ib_port, ib_dev->pnetid[ib_port - 1]); } smcd = smc_pnet_find_smcd(ib_name); if (smcd) { smcddev_applied = smc_pnet_apply_smcd(smcd, pnet_name); if (smcddev_applied) { dev = smcd->ops->get_dev(smcd); pr_warn_ratelimited("smc: smcd device %s " "applied user defined pnetid " "%.16s\n", dev_name(dev), smcd->pnetid); } } /* Apply fails when a device has a hardware-defined pnetid set, do not * add a pnet table entry in that case. */ if (!ibdev_applied || !smcddev_applied) return -EEXIST; /* add a new ib entry to the pnet table if there isn't one */ new_pe = kzalloc(sizeof(*new_pe), GFP_KERNEL); if (!new_pe) return -ENOMEM; new_pe->type = SMC_PNET_IB; memcpy(new_pe->pnet_name, pnet_name, SMC_MAX_PNETID_LEN); strncpy(new_pe->ib_name, ib_name, IB_DEVICE_NAME_MAX); new_pe->ib_port = ib_port; new_ibdev = true; mutex_lock(&pnettable->lock); list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) { if (tmp_pe->type == SMC_PNET_IB && !strncmp(tmp_pe->ib_name, ib_name, IB_DEVICE_NAME_MAX)) { new_ibdev = false; break; } } if (new_ibdev) { list_add_tail(&new_pe->list, &pnettable->pnetlist); mutex_unlock(&pnettable->lock); } else { mutex_unlock(&pnettable->lock); kfree(new_pe); } return (new_ibdev) ? 0 : -EEXIST; } /* Append a pnetid to the end of the pnet table if not already on this list. */ static int smc_pnet_enter(struct net *net, struct nlattr *tb[]) { char pnet_name[SMC_MAX_PNETID_LEN + 1]; struct smc_pnettable *pnettable; bool new_netdev = false; bool new_ibdev = false; struct smc_net *sn; u8 ibport = 1; char *string; int rc; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; rc = -EINVAL; if (!tb[SMC_PNETID_NAME]) goto error; string = (char *)nla_data(tb[SMC_PNETID_NAME]); if (!smc_pnetid_valid(string, pnet_name)) goto error; if (tb[SMC_PNETID_ETHNAME]) { string = (char *)nla_data(tb[SMC_PNETID_ETHNAME]); rc = smc_pnet_add_eth(pnettable, net, string, pnet_name); if (!rc) new_netdev = true; else if (rc != -EEXIST) goto error; } /* if this is not the initial namespace, stop here */ if (net != &init_net) return new_netdev ? 0 : -EEXIST; rc = -EINVAL; if (tb[SMC_PNETID_IBNAME]) { string = (char *)nla_data(tb[SMC_PNETID_IBNAME]); string = strim(string); if (tb[SMC_PNETID_IBPORT]) { ibport = nla_get_u8(tb[SMC_PNETID_IBPORT]); if (ibport < 1 || ibport > SMC_MAX_PORTS) goto error; } rc = smc_pnet_add_ib(pnettable, string, ibport, pnet_name); if (!rc) new_ibdev = true; else if (rc != -EEXIST) goto error; } return (new_netdev || new_ibdev) ? 0 : -EEXIST; error: return rc; } /* Convert an smc_pnetentry to a netlink attribute sequence */ static int smc_pnet_set_nla(struct sk_buff *msg, struct smc_pnetentry *pnetelem) { if (nla_put_string(msg, SMC_PNETID_NAME, pnetelem->pnet_name)) return -1; if (pnetelem->type == SMC_PNET_ETH) { if (nla_put_string(msg, SMC_PNETID_ETHNAME, pnetelem->eth_name)) return -1; } else { if (nla_put_string(msg, SMC_PNETID_ETHNAME, "n/a")) return -1; } if (pnetelem->type == SMC_PNET_IB) { if (nla_put_string(msg, SMC_PNETID_IBNAME, pnetelem->ib_name) || nla_put_u8(msg, SMC_PNETID_IBPORT, pnetelem->ib_port)) return -1; } else { if (nla_put_string(msg, SMC_PNETID_IBNAME, "n/a") || nla_put_u8(msg, SMC_PNETID_IBPORT, 0xff)) return -1; } return 0; } static int smc_pnet_add(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); return smc_pnet_enter(net, info->attrs); } static int smc_pnet_del(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); if (!info->attrs[SMC_PNETID_NAME]) return -EINVAL; return smc_pnet_remove_by_pnetid(net, (char *)nla_data(info->attrs[SMC_PNETID_NAME])); } static int smc_pnet_dump_start(struct netlink_callback *cb) { cb->args[0] = 0; return 0; } static int smc_pnet_dumpinfo(struct sk_buff *skb, u32 portid, u32 seq, u32 flags, struct smc_pnetentry *pnetelem) { void *hdr; hdr = genlmsg_put(skb, portid, seq, &smc_pnet_nl_family, flags, SMC_PNETID_GET); if (!hdr) return -ENOMEM; if (smc_pnet_set_nla(skb, pnetelem) < 0) { genlmsg_cancel(skb, hdr); return -EMSGSIZE; } genlmsg_end(skb, hdr); return 0; } static int _smc_pnet_dump(struct net *net, struct sk_buff *skb, u32 portid, u32 seq, u8 *pnetid, int start_idx) { struct smc_pnettable *pnettable; struct smc_pnetentry *pnetelem; struct smc_net *sn; int idx = 0; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; /* dump pnettable entries */ mutex_lock(&pnettable->lock); list_for_each_entry(pnetelem, &pnettable->pnetlist, list) { if (pnetid && !smc_pnet_match(pnetelem->pnet_name, pnetid)) continue; if (idx++ < start_idx) continue; /* if this is not the initial namespace, dump only netdev */ if (net != &init_net && pnetelem->type != SMC_PNET_ETH) continue; if (smc_pnet_dumpinfo(skb, portid, seq, NLM_F_MULTI, pnetelem)) { --idx; break; } } mutex_unlock(&pnettable->lock); return idx; } static int smc_pnet_dump(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); int idx; idx = _smc_pnet_dump(net, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NULL, cb->args[0]); cb->args[0] = idx; return skb->len; } /* Retrieve one PNETID entry */ static int smc_pnet_get(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct sk_buff *msg; void *hdr; if (!info->attrs[SMC_PNETID_NAME]) return -EINVAL; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; _smc_pnet_dump(net, msg, info->snd_portid, info->snd_seq, nla_data(info->attrs[SMC_PNETID_NAME]), 0); /* finish multi part message and send it */ hdr = nlmsg_put(msg, info->snd_portid, info->snd_seq, NLMSG_DONE, 0, NLM_F_MULTI); if (!hdr) { nlmsg_free(msg); return -EMSGSIZE; } return genlmsg_reply(msg, info); } /* Remove and delete all pnetids from pnet table. */ static int smc_pnet_flush(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); smc_pnet_remove_by_pnetid(net, NULL); return 0; } /* SMC_PNETID generic netlink operation definition */ static const struct genl_ops smc_pnet_ops[] = { { .cmd = SMC_PNETID_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, /* can be retrieved by unprivileged users */ .doit = smc_pnet_get, .dumpit = smc_pnet_dump, .start = smc_pnet_dump_start }, { .cmd = SMC_PNETID_ADD, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = smc_pnet_add }, { .cmd = SMC_PNETID_DEL, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = smc_pnet_del }, { .cmd = SMC_PNETID_FLUSH, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .flags = GENL_ADMIN_PERM, .doit = smc_pnet_flush } }; /* SMC_PNETID family definition */ static struct genl_family smc_pnet_nl_family __ro_after_init = { .hdrsize = 0, .name = SMCR_GENL_FAMILY_NAME, .version = SMCR_GENL_FAMILY_VERSION, .maxattr = SMC_PNETID_MAX, .policy = smc_pnet_policy, .netnsok = true, .module = THIS_MODULE, .ops = smc_pnet_ops, .n_ops = ARRAY_SIZE(smc_pnet_ops), .resv_start_op = SMC_PNETID_FLUSH + 1, }; bool smc_pnet_is_ndev_pnetid(struct net *net, u8 *pnetid) { struct smc_net *sn = net_generic(net, smc_net_id); struct smc_pnetids_ndev_entry *pe; bool rc = false; read_lock(&sn->pnetids_ndev.lock); list_for_each_entry(pe, &sn->pnetids_ndev.list, list) { if (smc_pnet_match(pnetid, pe->pnetid)) { rc = true; goto unlock; } } unlock: read_unlock(&sn->pnetids_ndev.lock); return rc; } static int smc_pnet_add_pnetid(struct net *net, u8 *pnetid) { struct smc_net *sn = net_generic(net, smc_net_id); struct smc_pnetids_ndev_entry *pe, *pi; pe = kzalloc(sizeof(*pe), GFP_KERNEL); if (!pe) return -ENOMEM; write_lock(&sn->pnetids_ndev.lock); list_for_each_entry(pi, &sn->pnetids_ndev.list, list) { if (smc_pnet_match(pnetid, pi->pnetid)) { refcount_inc(&pi->refcnt); kfree(pe); goto unlock; } } refcount_set(&pe->refcnt, 1); memcpy(pe->pnetid, pnetid, SMC_MAX_PNETID_LEN); list_add_tail(&pe->list, &sn->pnetids_ndev.list); unlock: write_unlock(&sn->pnetids_ndev.lock); return 0; } static void smc_pnet_remove_pnetid(struct net *net, u8 *pnetid) { struct smc_net *sn = net_generic(net, smc_net_id); struct smc_pnetids_ndev_entry *pe, *pe2; write_lock(&sn->pnetids_ndev.lock); list_for_each_entry_safe(pe, pe2, &sn->pnetids_ndev.list, list) { if (smc_pnet_match(pnetid, pe->pnetid)) { if (refcount_dec_and_test(&pe->refcnt)) { list_del(&pe->list); kfree(pe); } break; } } write_unlock(&sn->pnetids_ndev.lock); } static void smc_pnet_add_base_pnetid(struct net *net, struct net_device *dev, u8 *ndev_pnetid) { struct net_device *base_dev; base_dev = __pnet_find_base_ndev(dev); if (base_dev->flags & IFF_UP && !smc_pnetid_by_dev_port(base_dev->dev.parent, base_dev->dev_port, ndev_pnetid)) { /* add to PNETIDs list */ smc_pnet_add_pnetid(net, ndev_pnetid); } } /* create initial list of netdevice pnetids */ static void smc_pnet_create_pnetids_list(struct net *net) { u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; struct net_device *dev; /* Newly created netns do not have devices. * Do not even acquire rtnl. */ if (list_empty(&net->dev_base_head)) return; /* Note: This might not be needed, because smc_pnet_netdev_event() * is also calling smc_pnet_add_base_pnetid() when handling * NETDEV_UP event. */ rtnl_lock(); for_each_netdev(net, dev) smc_pnet_add_base_pnetid(net, dev, ndev_pnetid); rtnl_unlock(); } /* clean up list of netdevice pnetids */ static void smc_pnet_destroy_pnetids_list(struct net *net) { struct smc_net *sn = net_generic(net, smc_net_id); struct smc_pnetids_ndev_entry *pe, *temp_pe; write_lock(&sn->pnetids_ndev.lock); list_for_each_entry_safe(pe, temp_pe, &sn->pnetids_ndev.list, list) { list_del(&pe->list); kfree(pe); } write_unlock(&sn->pnetids_ndev.lock); } static int smc_pnet_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(event_dev); u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; switch (event) { case NETDEV_REBOOT: case NETDEV_UNREGISTER: smc_pnet_remove_by_ndev(event_dev); smc_ib_ndev_change(event_dev, event); return NOTIFY_OK; case NETDEV_REGISTER: smc_pnet_add_by_ndev(event_dev); smc_ib_ndev_change(event_dev, event); return NOTIFY_OK; case NETDEV_UP: smc_pnet_add_base_pnetid(net, event_dev, ndev_pnetid); return NOTIFY_OK; case NETDEV_DOWN: event_dev = __pnet_find_base_ndev(event_dev); if (!smc_pnetid_by_dev_port(event_dev->dev.parent, event_dev->dev_port, ndev_pnetid)) { /* remove from PNETIDs list */ smc_pnet_remove_pnetid(net, ndev_pnetid); } return NOTIFY_OK; default: return NOTIFY_DONE; } } static struct notifier_block smc_netdev_notifier = { .notifier_call = smc_pnet_netdev_event }; /* init network namespace */ int smc_pnet_net_init(struct net *net) { struct smc_net *sn = net_generic(net, smc_net_id); struct smc_pnettable *pnettable = &sn->pnettable; struct smc_pnetids_ndev *pnetids_ndev = &sn->pnetids_ndev; INIT_LIST_HEAD(&pnettable->pnetlist); mutex_init(&pnettable->lock); INIT_LIST_HEAD(&pnetids_ndev->list); rwlock_init(&pnetids_ndev->lock); smc_pnet_create_pnetids_list(net); return 0; } int __init smc_pnet_init(void) { int rc; rc = genl_register_family(&smc_pnet_nl_family); if (rc) return rc; rc = register_netdevice_notifier(&smc_netdev_notifier); if (rc) genl_unregister_family(&smc_pnet_nl_family); return rc; } /* exit network namespace */ void smc_pnet_net_exit(struct net *net) { /* flush pnet table */ smc_pnet_remove_by_pnetid(net, NULL); smc_pnet_destroy_pnetids_list(net); } void smc_pnet_exit(void) { unregister_netdevice_notifier(&smc_netdev_notifier); genl_unregister_family(&smc_pnet_nl_family); } static struct net_device *__pnet_find_base_ndev(struct net_device *ndev) { int i, nest_lvl; ASSERT_RTNL(); nest_lvl = ndev->lower_level; for (i = 0; i < nest_lvl; i++) { struct list_head *lower = &ndev->adj_list.lower; if (list_empty(lower)) break; lower = lower->next; ndev = netdev_lower_get_next(ndev, &lower); } return ndev; } /* Determine one base device for stacked net devices. * If the lower device level contains more than one devices * (for instance with bonding slaves), just the first device * is used to reach a base device. */ static struct net_device *pnet_find_base_ndev(struct net_device *ndev) { rtnl_lock(); ndev = __pnet_find_base_ndev(ndev); rtnl_unlock(); return ndev; } static int smc_pnet_find_ndev_pnetid_by_table(struct net_device *ndev, u8 *pnetid) { struct smc_pnettable *pnettable; struct net *net = dev_net(ndev); struct smc_pnetentry *pnetelem; struct smc_net *sn; int rc = -ENOENT; /* get pnettable for namespace */ sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; mutex_lock(&pnettable->lock); list_for_each_entry(pnetelem, &pnettable->pnetlist, list) { if (pnetelem->type == SMC_PNET_ETH && ndev == pnetelem->ndev) { /* get pnetid of netdev device */ memcpy(pnetid, pnetelem->pnet_name, SMC_MAX_PNETID_LEN); rc = 0; break; } } mutex_unlock(&pnettable->lock); return rc; } static int smc_pnet_determine_gid(struct smc_ib_device *ibdev, int i, struct smc_init_info *ini) { if (!ini->check_smcrv2 && !smc_ib_determine_gid(ibdev, i, ini->vlan_id, ini->ib_gid, NULL, NULL)) { ini->ib_dev = ibdev; ini->ib_port = i; return 0; } if (ini->check_smcrv2 && !smc_ib_determine_gid(ibdev, i, ini->vlan_id, ini->smcrv2.ib_gid_v2, NULL, &ini->smcrv2)) { ini->smcrv2.ib_dev_v2 = ibdev; ini->smcrv2.ib_port_v2 = i; return 0; } return -ENODEV; } /* find a roce device for the given pnetid */ static void _smc_pnet_find_roce_by_pnetid(u8 *pnet_id, struct smc_init_info *ini, struct smc_ib_device *known_dev, struct net *net) { struct smc_ib_device *ibdev; int i; mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { if (ibdev == known_dev || !rdma_dev_access_netns(ibdev->ibdev, net)) continue; for (i = 1; i <= SMC_MAX_PORTS; i++) { if (!rdma_is_port_valid(ibdev->ibdev, i)) continue; if (smc_pnet_match(ibdev->pnetid[i - 1], pnet_id) && smc_ib_port_active(ibdev, i) && !test_bit(i - 1, ibdev->ports_going_away)) { if (!smc_pnet_determine_gid(ibdev, i, ini)) goto out; } } } out: mutex_unlock(&smc_ib_devices.mutex); } /* find alternate roce device with same pnet_id, vlan_id and net namespace */ void smc_pnet_find_alt_roce(struct smc_link_group *lgr, struct smc_init_info *ini, struct smc_ib_device *known_dev) { struct net *net = lgr->net; _smc_pnet_find_roce_by_pnetid(lgr->pnet_id, ini, known_dev, net); } /* if handshake network device belongs to a roce device, return its * IB device and port */ static void smc_pnet_find_rdma_dev(struct net_device *netdev, struct smc_init_info *ini) { struct net *net = dev_net(netdev); struct smc_ib_device *ibdev; mutex_lock(&smc_ib_devices.mutex); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { struct net_device *ndev; int i; /* check rdma net namespace */ if (!rdma_dev_access_netns(ibdev->ibdev, net)) continue; for (i = 1; i <= SMC_MAX_PORTS; i++) { if (!rdma_is_port_valid(ibdev->ibdev, i)) continue; ndev = ib_device_get_netdev(ibdev->ibdev, i); if (!ndev) continue; dev_put(ndev); if (netdev == ndev && smc_ib_port_active(ibdev, i) && !test_bit(i - 1, ibdev->ports_going_away)) { if (!smc_pnet_determine_gid(ibdev, i, ini)) break; } } } mutex_unlock(&smc_ib_devices.mutex); } /* Determine the corresponding IB device port based on the hardware PNETID. * Searching stops at the first matching active IB device port with vlan_id * configured. * If nothing found, check pnetid table. * If nothing found, try to use handshake device */ static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev, struct smc_init_info *ini) { u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; struct net *net; ndev = pnet_find_base_ndev(ndev); net = dev_net(ndev); if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port, ndev_pnetid) && smc_pnet_find_ndev_pnetid_by_table(ndev, ndev_pnetid)) { smc_pnet_find_rdma_dev(ndev, ini); return; /* pnetid could not be determined */ } _smc_pnet_find_roce_by_pnetid(ndev_pnetid, ini, NULL, net); } static void smc_pnet_find_ism_by_pnetid(struct net_device *ndev, struct smc_init_info *ini) { u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; struct smcd_dev *ismdev; ndev = pnet_find_base_ndev(ndev); if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port, ndev_pnetid) && smc_pnet_find_ndev_pnetid_by_table(ndev, ndev_pnetid)) return; /* pnetid could not be determined */ mutex_lock(&smcd_dev_list.mutex); list_for_each_entry(ismdev, &smcd_dev_list.list, list) { if (smc_pnet_match(ismdev->pnetid, ndev_pnetid) && !ismdev->going_away && (!ini->ism_peer_gid[0].gid || !smc_ism_cantalk(&ini->ism_peer_gid[0], ini->vlan_id, ismdev))) { ini->ism_dev[0] = ismdev; break; } } mutex_unlock(&smcd_dev_list.mutex); } /* PNET table analysis for a given sock: * determine ib_device and port belonging to used internal TCP socket * ethernet interface. */ void smc_pnet_find_roce_resource(struct sock *sk, struct smc_init_info *ini) { struct dst_entry *dst = sk_dst_get(sk); if (!dst) goto out; if (!dst->dev) goto out_rel; smc_pnet_find_roce_by_pnetid(dst->dev, ini); out_rel: dst_release(dst); out: return; } void smc_pnet_find_ism_resource(struct sock *sk, struct smc_init_info *ini) { struct dst_entry *dst = sk_dst_get(sk); ini->ism_dev[0] = NULL; if (!dst) goto out; if (!dst->dev) goto out_rel; smc_pnet_find_ism_by_pnetid(dst->dev, ini); out_rel: dst_release(dst); out: return; } /* Lookup and apply a pnet table entry to the given ib device. */ int smc_pnetid_by_table_ib(struct smc_ib_device *smcibdev, u8 ib_port) { char *ib_name = smcibdev->ibdev->name; struct smc_pnettable *pnettable; struct smc_pnetentry *tmp_pe; struct smc_net *sn; int rc = -ENOENT; /* get pnettable for init namespace */ sn = net_generic(&init_net, smc_net_id); pnettable = &sn->pnettable; mutex_lock(&pnettable->lock); list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) { if (tmp_pe->type == SMC_PNET_IB && !strncmp(tmp_pe->ib_name, ib_name, IB_DEVICE_NAME_MAX) && tmp_pe->ib_port == ib_port) { smc_pnet_apply_ib(smcibdev, ib_port, tmp_pe->pnet_name); rc = 0; break; } } mutex_unlock(&pnettable->lock); return rc; } /* Lookup and apply a pnet table entry to the given smcd device. */ int smc_pnetid_by_table_smcd(struct smcd_dev *smcddev) { const char *ib_name = dev_name(smcddev->ops->get_dev(smcddev)); struct smc_pnettable *pnettable; struct smc_pnetentry *tmp_pe; struct smc_net *sn; int rc = -ENOENT; /* get pnettable for init namespace */ sn = net_generic(&init_net, smc_net_id); pnettable = &sn->pnettable; mutex_lock(&pnettable->lock); list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) { if (tmp_pe->type == SMC_PNET_IB && !strncmp(tmp_pe->ib_name, ib_name, IB_DEVICE_NAME_MAX)) { smc_pnet_apply_smcd(smcddev, tmp_pe->pnet_name); rc = 0; break; } } mutex_unlock(&pnettable->lock); return rc; } |
| 4 4 3 1 2 1 1 4 1 7 4 3 1 1 1 7 1 4 3 3 1 2 4 9 8 7 3 4 2 2 9 6 6 6 1 5 2 3 6 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 | // 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/io_uring.h> #include <uapi/linux/io_uring.h> #include "../fs/internal.h" #include "io_uring.h" #include "fs.h" struct io_rename { struct file *file; int old_dfd; int new_dfd; struct filename *oldpath; struct filename *newpath; int flags; }; struct io_unlink { struct file *file; int dfd; int flags; struct filename *filename; }; struct io_mkdir { struct file *file; int dfd; umode_t mode; struct filename *filename; }; struct io_link { struct file *file; int old_dfd; int new_dfd; struct filename *oldpath; struct filename *newpath; int flags; }; int io_renameat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_rename *ren = io_kiocb_to_cmd(req, struct io_rename); const char __user *oldf, *newf; if (sqe->buf_index || sqe->splice_fd_in) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; ren->old_dfd = READ_ONCE(sqe->fd); oldf = u64_to_user_ptr(READ_ONCE(sqe->addr)); newf = u64_to_user_ptr(READ_ONCE(sqe->addr2)); ren->new_dfd = READ_ONCE(sqe->len); ren->flags = READ_ONCE(sqe->rename_flags); ren->oldpath = getname(oldf); if (IS_ERR(ren->oldpath)) return PTR_ERR(ren->oldpath); ren->newpath = getname(newf); if (IS_ERR(ren->newpath)) { putname(ren->oldpath); return PTR_ERR(ren->newpath); } req->flags |= REQ_F_NEED_CLEANUP; req->flags |= REQ_F_FORCE_ASYNC; return 0; } int io_renameat(struct io_kiocb *req, unsigned int issue_flags) { struct io_rename *ren = io_kiocb_to_cmd(req, struct io_rename); int ret; WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK); ret = do_renameat2(ren->old_dfd, ren->oldpath, ren->new_dfd, ren->newpath, ren->flags); req->flags &= ~REQ_F_NEED_CLEANUP; io_req_set_res(req, ret, 0); return IOU_OK; } void io_renameat_cleanup(struct io_kiocb *req) { struct io_rename *ren = io_kiocb_to_cmd(req, struct io_rename); putname(ren->oldpath); putname(ren->newpath); } int io_unlinkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_unlink *un = io_kiocb_to_cmd(req, struct io_unlink); const char __user *fname; if (sqe->off || sqe->len || sqe->buf_index || sqe->splice_fd_in) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; un->dfd = READ_ONCE(sqe->fd); un->flags = READ_ONCE(sqe->unlink_flags); if (un->flags & ~AT_REMOVEDIR) return -EINVAL; fname = u64_to_user_ptr(READ_ONCE(sqe->addr)); un->filename = getname(fname); if (IS_ERR(un->filename)) return PTR_ERR(un->filename); req->flags |= REQ_F_NEED_CLEANUP; req->flags |= REQ_F_FORCE_ASYNC; return 0; } int io_unlinkat(struct io_kiocb *req, unsigned int issue_flags) { struct io_unlink *un = io_kiocb_to_cmd(req, struct io_unlink); int ret; WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK); if (un->flags & AT_REMOVEDIR) ret = do_rmdir(un->dfd, un->filename); else ret = do_unlinkat(un->dfd, un->filename); req->flags &= ~REQ_F_NEED_CLEANUP; io_req_set_res(req, ret, 0); return IOU_OK; } void io_unlinkat_cleanup(struct io_kiocb *req) { struct io_unlink *ul = io_kiocb_to_cmd(req, struct io_unlink); putname(ul->filename); } int io_mkdirat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_mkdir *mkd = io_kiocb_to_cmd(req, struct io_mkdir); const char __user *fname; if (sqe->off || sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; mkd->dfd = READ_ONCE(sqe->fd); mkd->mode = READ_ONCE(sqe->len); fname = u64_to_user_ptr(READ_ONCE(sqe->addr)); mkd->filename = getname(fname); if (IS_ERR(mkd->filename)) return PTR_ERR(mkd->filename); req->flags |= REQ_F_NEED_CLEANUP; req->flags |= REQ_F_FORCE_ASYNC; return 0; } int io_mkdirat(struct io_kiocb *req, unsigned int issue_flags) { struct io_mkdir *mkd = io_kiocb_to_cmd(req, struct io_mkdir); int ret; WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK); ret = do_mkdirat(mkd->dfd, mkd->filename, mkd->mode); req->flags &= ~REQ_F_NEED_CLEANUP; io_req_set_res(req, ret, 0); return IOU_OK; } void io_mkdirat_cleanup(struct io_kiocb *req) { struct io_mkdir *md = io_kiocb_to_cmd(req, struct io_mkdir); putname(md->filename); } int io_symlinkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_link *sl = io_kiocb_to_cmd(req, struct io_link); const char __user *oldpath, *newpath; if (sqe->len || sqe->rw_flags || sqe->buf_index || sqe->splice_fd_in) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; sl->new_dfd = READ_ONCE(sqe->fd); oldpath = u64_to_user_ptr(READ_ONCE(sqe->addr)); newpath = u64_to_user_ptr(READ_ONCE(sqe->addr2)); sl->oldpath = getname(oldpath); if (IS_ERR(sl->oldpath)) return PTR_ERR(sl->oldpath); sl->newpath = getname(newpath); if (IS_ERR(sl->newpath)) { putname(sl->oldpath); return PTR_ERR(sl->newpath); } req->flags |= REQ_F_NEED_CLEANUP; req->flags |= REQ_F_FORCE_ASYNC; return 0; } int io_symlinkat(struct io_kiocb *req, unsigned int issue_flags) { struct io_link *sl = io_kiocb_to_cmd(req, struct io_link); int ret; WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK); ret = do_symlinkat(sl->oldpath, sl->new_dfd, sl->newpath); req->flags &= ~REQ_F_NEED_CLEANUP; io_req_set_res(req, ret, 0); return IOU_OK; } int io_linkat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_link *lnk = io_kiocb_to_cmd(req, struct io_link); const char __user *oldf, *newf; if (sqe->buf_index || sqe->splice_fd_in) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) return -EBADF; lnk->old_dfd = READ_ONCE(sqe->fd); lnk->new_dfd = READ_ONCE(sqe->len); oldf = u64_to_user_ptr(READ_ONCE(sqe->addr)); newf = u64_to_user_ptr(READ_ONCE(sqe->addr2)); lnk->flags = READ_ONCE(sqe->hardlink_flags); lnk->oldpath = getname_uflags(oldf, lnk->flags); if (IS_ERR(lnk->oldpath)) return PTR_ERR(lnk->oldpath); lnk->newpath = getname(newf); if (IS_ERR(lnk->newpath)) { putname(lnk->oldpath); return PTR_ERR(lnk->newpath); } req->flags |= REQ_F_NEED_CLEANUP; req->flags |= REQ_F_FORCE_ASYNC; return 0; } int io_linkat(struct io_kiocb *req, unsigned int issue_flags) { struct io_link *lnk = io_kiocb_to_cmd(req, struct io_link); int ret; WARN_ON_ONCE(issue_flags & IO_URING_F_NONBLOCK); ret = do_linkat(lnk->old_dfd, lnk->oldpath, lnk->new_dfd, lnk->newpath, lnk->flags); req->flags &= ~REQ_F_NEED_CLEANUP; io_req_set_res(req, ret, 0); return IOU_OK; } void io_link_cleanup(struct io_kiocb *req) { struct io_link *sl = io_kiocb_to_cmd(req, struct io_link); putname(sl->oldpath); putname(sl->newpath); } |
| 5 364 364 154 357 355 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2013 Red Hat, Inc. and Parallels Inc. All rights reserved. * Authors: David Chinner and Glauber Costa * * Generic LRU infrastructure */ #ifndef _LRU_LIST_H #define _LRU_LIST_H #include <linux/list.h> #include <linux/nodemask.h> #include <linux/shrinker.h> #include <linux/xarray.h> struct mem_cgroup; /* list_lru_walk_cb has to always return one of those */ enum lru_status { LRU_REMOVED, /* item removed from list */ LRU_REMOVED_RETRY, /* item removed, but lock has been dropped and reacquired */ LRU_ROTATE, /* item referenced, give another pass */ LRU_SKIP, /* item cannot be locked, skip */ LRU_RETRY, /* item not freeable. May drop the lock internally, but has to return locked. */ LRU_STOP, /* stop lru list walking. May drop the lock internally, but has to return locked. */ }; struct list_lru_one { struct list_head list; /* may become negative during memcg reparenting */ long nr_items; /* protects all fields above */ spinlock_t lock; }; struct list_lru_memcg { struct rcu_head rcu; /* array of per cgroup per node lists, indexed by node id */ struct list_lru_one node[]; }; struct list_lru_node { /* global list, used for the root cgroup in cgroup aware lrus */ struct list_lru_one lru; atomic_long_t nr_items; } ____cacheline_aligned_in_smp; struct list_lru { struct list_lru_node *node; #ifdef CONFIG_MEMCG struct list_head list; int shrinker_id; bool memcg_aware; struct xarray xa; #endif #ifdef CONFIG_LOCKDEP struct lock_class_key *key; #endif }; void list_lru_destroy(struct list_lru *lru); int __list_lru_init(struct list_lru *lru, bool memcg_aware, struct shrinker *shrinker); #define list_lru_init(lru) \ __list_lru_init((lru), false, NULL) #define list_lru_init_memcg(lru, shrinker) \ __list_lru_init((lru), true, shrinker) static inline int list_lru_init_memcg_key(struct list_lru *lru, struct shrinker *shrinker, struct lock_class_key *key) { #ifdef CONFIG_LOCKDEP lru->key = key; #endif return list_lru_init_memcg(lru, shrinker); } int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru, gfp_t gfp); void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *parent); /** * list_lru_add: add an element to the lru list's tail * @lru: the lru pointer * @item: the item to be added. * @nid: the node id of the sublist to add the item to. * @memcg: the cgroup of the sublist to add the item to. * * If the element is already part of a list, this function returns doing * nothing. This means that it is not necessary to keep state about whether or * not the element already belongs in the list. That said, this logic only * works if the item is in *this* list. If the item might be in some other * list, then you cannot rely on this check and you must remove it from the * other list before trying to insert it. * * The lru list consists of many sublists internally; the @nid and @memcg * parameters are used to determine which sublist to insert the item into. * It's important to use the right value of @nid and @memcg when deleting the * item, since it might otherwise get deleted from the wrong sublist. * * This also applies when attempting to insert the item multiple times - if * the item is currently in one sublist and you call list_lru_add() again, you * must pass the right @nid and @memcg parameters so that the same sublist is * used. * * You must ensure that the memcg is not freed during this call (e.g., with * rcu or by taking a css refcnt). * * Return: true if the list was updated, false otherwise */ bool list_lru_add(struct list_lru *lru, struct list_head *item, int nid, struct mem_cgroup *memcg); /** * list_lru_add_obj: add an element to the lru list's tail * @lru: the lru pointer * @item: the item to be added. * * This function is similar to list_lru_add(), but the NUMA node and the * memcg of the sublist is determined by @item list_head. This assumption is * valid for slab objects LRU such as dentries, inodes, etc. * * Return: true if the list was updated, false otherwise */ bool list_lru_add_obj(struct list_lru *lru, struct list_head *item); /** * list_lru_del: delete an element from the lru list * @lru: the lru pointer * @item: the item to be deleted. * @nid: the node id of the sublist to delete the item from. * @memcg: the cgroup of the sublist to delete the item from. * * This function works analogously as list_lru_add() in terms of list * manipulation. * * The comments in list_lru_add() about an element already being in a list are * also valid for list_lru_del(), that is, you can delete an item that has * already been removed or never been added. However, if the item is in a * list, it must be in *this* list, and you must pass the right value of @nid * and @memcg so that the right sublist is used. * * You must ensure that the memcg is not freed during this call (e.g., with * rcu or by taking a css refcnt). When a memcg is deleted, list_lru entries * are automatically moved to the parent memcg. This is done in a race-free * way, so during deletion of an memcg both the old and new memcg will resolve * to the same sublist internally. * * Return: true if the list was updated, false otherwise */ bool list_lru_del(struct list_lru *lru, struct list_head *item, int nid, struct mem_cgroup *memcg); /** * list_lru_del_obj: delete an element from the lru list * @lru: the lru pointer * @item: the item to be deleted. * * This function is similar to list_lru_del(), but the NUMA node and the * memcg of the sublist is determined by @item list_head. This assumption is * valid for slab objects LRU such as dentries, inodes, etc. * * Return: true if the list was updated, false otherwise. */ bool list_lru_del_obj(struct list_lru *lru, struct list_head *item); /** * list_lru_count_one: return the number of objects currently held by @lru * @lru: the lru pointer. * @nid: the node id to count from. * @memcg: the cgroup to count from. * * There is no guarantee that the list is not updated while the count is being * computed. Callers that want such a guarantee need to provide an outer lock. * * Return: 0 for empty lists, otherwise the number of objects * currently held by @lru. */ unsigned long list_lru_count_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg); unsigned long list_lru_count_node(struct list_lru *lru, int nid); static inline unsigned long list_lru_shrink_count(struct list_lru *lru, struct shrink_control *sc) { return list_lru_count_one(lru, sc->nid, sc->memcg); } static inline unsigned long list_lru_count(struct list_lru *lru) { long count = 0; int nid; for_each_node_state(nid, N_NORMAL_MEMORY) count += list_lru_count_node(lru, nid); return count; } void list_lru_isolate(struct list_lru_one *list, struct list_head *item); void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item, struct list_head *head); typedef enum lru_status (*list_lru_walk_cb)(struct list_head *item, struct list_lru_one *list, void *cb_arg); /** * list_lru_walk_one: walk a @lru, isolating and disposing freeable items. * @lru: the lru pointer. * @nid: the node id to scan from. * @memcg: the cgroup to scan from. * @isolate: callback function that is responsible for deciding what to do with * the item currently being scanned * @cb_arg: opaque type that will be passed to @isolate * @nr_to_walk: how many items to scan. * * This function will scan all elements in a particular @lru, calling the * @isolate callback for each of those items, along with the current list * spinlock and a caller-provided opaque. The @isolate callback can choose to * drop the lock internally, but *must* return with the lock held. The callback * will return an enum lru_status telling the @lru infrastructure what to * do with the object being scanned. * * Please note that @nr_to_walk does not mean how many objects will be freed, * just how many objects will be scanned. * * Return: the number of objects effectively removed from the LRU. */ unsigned long list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk); /** * list_lru_walk_one_irq: walk a @lru, isolating and disposing freeable items. * @lru: the lru pointer. * @nid: the node id to scan from. * @memcg: the cgroup to scan from. * @isolate: callback function that is responsible for deciding what to do with * the item currently being scanned * @cb_arg: opaque type that will be passed to @isolate * @nr_to_walk: how many items to scan. * * Same as list_lru_walk_one() except that the spinlock is acquired with * spin_lock_irq(). */ unsigned long list_lru_walk_one_irq(struct list_lru *lru, int nid, struct mem_cgroup *memcg, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk); unsigned long list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate, void *cb_arg, unsigned long *nr_to_walk); static inline unsigned long list_lru_shrink_walk(struct list_lru *lru, struct shrink_control *sc, list_lru_walk_cb isolate, void *cb_arg) { return list_lru_walk_one(lru, sc->nid, sc->memcg, isolate, cb_arg, &sc->nr_to_scan); } static inline unsigned long list_lru_shrink_walk_irq(struct list_lru *lru, struct shrink_control *sc, list_lru_walk_cb isolate, void *cb_arg) { return list_lru_walk_one_irq(lru, sc->nid, sc->memcg, isolate, cb_arg, &sc->nr_to_scan); } static inline unsigned long list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate, void *cb_arg, unsigned long nr_to_walk) { long isolated = 0; int nid; for_each_node_state(nid, N_NORMAL_MEMORY) { isolated += list_lru_walk_node(lru, nid, isolate, cb_arg, &nr_to_walk); if (nr_to_walk <= 0) break; } return isolated; } #endif /* _LRU_LIST_H */ |
| 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 2 2 2 1 1 2 2 2 2 2 2 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 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 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 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 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 1 1 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 1 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 108 108 108 107 6 6 6 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2011, 2012 STRATO. All rights reserved. */ #include <linux/blkdev.h> #include <linux/ratelimit.h> #include <linux/sched/mm.h> #include <crypto/hash.h> #include "ctree.h" #include "discard.h" #include "volumes.h" #include "disk-io.h" #include "ordered-data.h" #include "transaction.h" #include "backref.h" #include "extent_io.h" #include "dev-replace.h" #include "raid56.h" #include "block-group.h" #include "zoned.h" #include "fs.h" #include "accessors.h" #include "file-item.h" #include "scrub.h" #include "raid-stripe-tree.h" /* * This is only the first step towards a full-features scrub. It reads all * extent and super block and verifies the checksums. In case a bad checksum * is found or the extent cannot be read, good data will be written back if * any can be found. * * Future enhancements: * - In case an unrepairable extent is encountered, track which files are * affected and report them * - track and record media errors, throw out bad devices * - add a mode to also read unallocated space */ struct scrub_ctx; /* * The following value only influences the performance. * * This determines how many stripes would be submitted in one go, * which is 512KiB (BTRFS_STRIPE_LEN * SCRUB_STRIPES_PER_GROUP). */ #define SCRUB_STRIPES_PER_GROUP 8 /* * How many groups we have for each sctx. * * This would be 8M per device, the same value as the old scrub in-flight bios * size limit. */ #define SCRUB_GROUPS_PER_SCTX 16 #define SCRUB_TOTAL_STRIPES (SCRUB_GROUPS_PER_SCTX * SCRUB_STRIPES_PER_GROUP) /* * The following value times PAGE_SIZE needs to be large enough to match the * largest node/leaf/sector size that shall be supported. */ #define SCRUB_MAX_SECTORS_PER_BLOCK (BTRFS_MAX_METADATA_BLOCKSIZE / SZ_4K) /* Represent one sector and its needed info to verify the content. */ struct scrub_sector_verification { bool is_metadata; union { /* * Csum pointer for data csum verification. Should point to a * sector csum inside scrub_stripe::csums. * * NULL if this data sector has no csum. */ u8 *csum; /* * Extra info for metadata verification. All sectors inside a * tree block share the same generation. */ u64 generation; }; }; enum scrub_stripe_flags { /* Set when @mirror_num, @dev, @physical and @logical are set. */ SCRUB_STRIPE_FLAG_INITIALIZED, /* Set when the read-repair is finished. */ SCRUB_STRIPE_FLAG_REPAIR_DONE, /* * Set for data stripes if it's triggered from P/Q stripe. * During such scrub, we should not report errors in data stripes, nor * update the accounting. */ SCRUB_STRIPE_FLAG_NO_REPORT, }; #define SCRUB_STRIPE_PAGES (BTRFS_STRIPE_LEN / PAGE_SIZE) /* * Represent one contiguous range with a length of BTRFS_STRIPE_LEN. */ struct scrub_stripe { struct scrub_ctx *sctx; struct btrfs_block_group *bg; struct page *pages[SCRUB_STRIPE_PAGES]; struct scrub_sector_verification *sectors; struct btrfs_device *dev; u64 logical; u64 physical; u16 mirror_num; /* Should be BTRFS_STRIPE_LEN / sectorsize. */ u16 nr_sectors; /* * How many data/meta extents are in this stripe. Only for scrub status * reporting purposes. */ u16 nr_data_extents; u16 nr_meta_extents; atomic_t pending_io; wait_queue_head_t io_wait; wait_queue_head_t repair_wait; /* * Indicate the states of the stripe. Bits are defined in * scrub_stripe_flags enum. */ unsigned long state; /* Indicate which sectors are covered by extent items. */ unsigned long extent_sector_bitmap; /* * The errors hit during the initial read of the stripe. * * Would be utilized for error reporting and repair. * * The remaining init_nr_* records the number of errors hit, only used * by error reporting. */ unsigned long init_error_bitmap; unsigned int init_nr_io_errors; unsigned int init_nr_csum_errors; unsigned int init_nr_meta_errors; /* * The following error bitmaps are all for the current status. * Every time we submit a new read, these bitmaps may be updated. * * error_bitmap = io_error_bitmap | csum_error_bitmap | meta_error_bitmap; * * IO and csum errors can happen for both metadata and data. */ unsigned long error_bitmap; unsigned long io_error_bitmap; unsigned long csum_error_bitmap; unsigned long meta_error_bitmap; /* For writeback (repair or replace) error reporting. */ unsigned long write_error_bitmap; /* Writeback can be concurrent, thus we need to protect the bitmap. */ spinlock_t write_error_lock; /* * Checksum for the whole stripe if this stripe is inside a data block * group. */ u8 *csums; struct work_struct work; }; struct scrub_ctx { struct scrub_stripe stripes[SCRUB_TOTAL_STRIPES]; struct scrub_stripe *raid56_data_stripes; struct btrfs_fs_info *fs_info; struct btrfs_path extent_path; struct btrfs_path csum_path; int first_free; int cur_stripe; atomic_t cancel_req; int readonly; /* State of IO submission throttling affecting the associated device */ ktime_t throttle_deadline; u64 throttle_sent; int is_dev_replace; u64 write_pointer; struct mutex wr_lock; struct btrfs_device *wr_tgtdev; /* * statistics */ struct btrfs_scrub_progress stat; spinlock_t stat_lock; /* * Use a ref counter to avoid use-after-free issues. Scrub workers * decrement bios_in_flight and workers_pending and then do a wakeup * on the list_wait wait queue. We must ensure the main scrub task * doesn't free the scrub context before or while the workers are * doing the wakeup() call. */ refcount_t refs; }; struct scrub_warning { struct btrfs_path *path; u64 extent_item_size; const char *errstr; u64 physical; u64 logical; struct btrfs_device *dev; }; static void release_scrub_stripe(struct scrub_stripe *stripe) { if (!stripe) return; for (int i = 0; i < SCRUB_STRIPE_PAGES; i++) { if (stripe->pages[i]) __free_page(stripe->pages[i]); stripe->pages[i] = NULL; } kfree(stripe->sectors); kfree(stripe->csums); stripe->sectors = NULL; stripe->csums = NULL; stripe->sctx = NULL; stripe->state = 0; } static int init_scrub_stripe(struct btrfs_fs_info *fs_info, struct scrub_stripe *stripe) { int ret; memset(stripe, 0, sizeof(*stripe)); stripe->nr_sectors = BTRFS_STRIPE_LEN >> fs_info->sectorsize_bits; stripe->state = 0; init_waitqueue_head(&stripe->io_wait); init_waitqueue_head(&stripe->repair_wait); atomic_set(&stripe->pending_io, 0); spin_lock_init(&stripe->write_error_lock); ret = btrfs_alloc_page_array(SCRUB_STRIPE_PAGES, stripe->pages, false); if (ret < 0) goto error; stripe->sectors = kcalloc(stripe->nr_sectors, sizeof(struct scrub_sector_verification), GFP_KERNEL); if (!stripe->sectors) goto error; stripe->csums = kcalloc(BTRFS_STRIPE_LEN >> fs_info->sectorsize_bits, fs_info->csum_size, GFP_KERNEL); if (!stripe->csums) goto error; return 0; error: release_scrub_stripe(stripe); return -ENOMEM; } static void wait_scrub_stripe_io(struct scrub_stripe *stripe) { wait_event(stripe->io_wait, atomic_read(&stripe->pending_io) == 0); } static void scrub_put_ctx(struct scrub_ctx *sctx); static void __scrub_blocked_if_needed(struct btrfs_fs_info *fs_info) { while (atomic_read(&fs_info->scrub_pause_req)) { mutex_unlock(&fs_info->scrub_lock); wait_event(fs_info->scrub_pause_wait, atomic_read(&fs_info->scrub_pause_req) == 0); mutex_lock(&fs_info->scrub_lock); } } static void scrub_pause_on(struct btrfs_fs_info *fs_info) { atomic_inc(&fs_info->scrubs_paused); wake_up(&fs_info->scrub_pause_wait); } static void scrub_pause_off(struct btrfs_fs_info *fs_info) { mutex_lock(&fs_info->scrub_lock); __scrub_blocked_if_needed(fs_info); atomic_dec(&fs_info->scrubs_paused); mutex_unlock(&fs_info->scrub_lock); wake_up(&fs_info->scrub_pause_wait); } static void scrub_blocked_if_needed(struct btrfs_fs_info *fs_info) { scrub_pause_on(fs_info); scrub_pause_off(fs_info); } static noinline_for_stack void scrub_free_ctx(struct scrub_ctx *sctx) { int i; if (!sctx) return; for (i = 0; i < SCRUB_TOTAL_STRIPES; i++) release_scrub_stripe(&sctx->stripes[i]); kvfree(sctx); } static void scrub_put_ctx(struct scrub_ctx *sctx) { if (refcount_dec_and_test(&sctx->refs)) scrub_free_ctx(sctx); } static noinline_for_stack struct scrub_ctx *scrub_setup_ctx( struct btrfs_fs_info *fs_info, int is_dev_replace) { struct scrub_ctx *sctx; int i; /* Since sctx has inline 128 stripes, it can go beyond 64K easily. Use * kvzalloc(). */ sctx = kvzalloc(sizeof(*sctx), GFP_KERNEL); if (!sctx) goto nomem; refcount_set(&sctx->refs, 1); sctx->is_dev_replace = is_dev_replace; sctx->fs_info = fs_info; sctx->extent_path.search_commit_root = 1; sctx->extent_path.skip_locking = 1; sctx->csum_path.search_commit_root = 1; sctx->csum_path.skip_locking = 1; for (i = 0; i < SCRUB_TOTAL_STRIPES; i++) { int ret; ret = init_scrub_stripe(fs_info, &sctx->stripes[i]); if (ret < 0) goto nomem; sctx->stripes[i].sctx = sctx; } sctx->first_free = 0; atomic_set(&sctx->cancel_req, 0); spin_lock_init(&sctx->stat_lock); sctx->throttle_deadline = 0; mutex_init(&sctx->wr_lock); if (is_dev_replace) { WARN_ON(!fs_info->dev_replace.tgtdev); sctx->wr_tgtdev = fs_info->dev_replace.tgtdev; } return sctx; nomem: scrub_free_ctx(sctx); return ERR_PTR(-ENOMEM); } static int scrub_print_warning_inode(u64 inum, u64 offset, u64 num_bytes, u64 root, void *warn_ctx) { u32 nlink; int ret; int i; unsigned nofs_flag; struct extent_buffer *eb; struct btrfs_inode_item *inode_item; struct scrub_warning *swarn = warn_ctx; struct btrfs_fs_info *fs_info = swarn->dev->fs_info; struct inode_fs_paths *ipath = NULL; struct btrfs_root *local_root; struct btrfs_key key; local_root = btrfs_get_fs_root(fs_info, root, true); if (IS_ERR(local_root)) { ret = PTR_ERR(local_root); goto err; } /* * this makes the path point to (inum INODE_ITEM ioff) */ key.objectid = inum; key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; ret = btrfs_search_slot(NULL, local_root, &key, swarn->path, 0, 0); if (ret) { btrfs_put_root(local_root); btrfs_release_path(swarn->path); goto err; } eb = swarn->path->nodes[0]; inode_item = btrfs_item_ptr(eb, swarn->path->slots[0], struct btrfs_inode_item); nlink = btrfs_inode_nlink(eb, inode_item); btrfs_release_path(swarn->path); /* * init_path might indirectly call vmalloc, or use GFP_KERNEL. Scrub * uses GFP_NOFS in this context, so we keep it consistent but it does * not seem to be strictly necessary. */ nofs_flag = memalloc_nofs_save(); ipath = init_ipath(4096, local_root, swarn->path); memalloc_nofs_restore(nofs_flag); if (IS_ERR(ipath)) { btrfs_put_root(local_root); ret = PTR_ERR(ipath); ipath = NULL; goto err; } ret = paths_from_inode(inum, ipath); if (ret < 0) goto err; /* * we deliberately ignore the bit ipath might have been too small to * hold all of the paths here */ for (i = 0; i < ipath->fspath->elem_cnt; ++i) btrfs_warn_in_rcu(fs_info, "%s at logical %llu on dev %s, physical %llu, root %llu, inode %llu, offset %llu, length %u, links %u (path: %s)", swarn->errstr, swarn->logical, btrfs_dev_name(swarn->dev), swarn->physical, root, inum, offset, fs_info->sectorsize, nlink, (char *)(unsigned long)ipath->fspath->val[i]); btrfs_put_root(local_root); free_ipath(ipath); return 0; err: btrfs_warn_in_rcu(fs_info, "%s at logical %llu on dev %s, physical %llu, root %llu, inode %llu, offset %llu: path resolving failed with ret=%d", swarn->errstr, swarn->logical, btrfs_dev_name(swarn->dev), swarn->physical, root, inum, offset, ret); free_ipath(ipath); return 0; } static void scrub_print_common_warning(const char *errstr, struct btrfs_device *dev, bool is_super, u64 logical, u64 physical) { struct btrfs_fs_info *fs_info = dev->fs_info; struct btrfs_path *path; struct btrfs_key found_key; struct extent_buffer *eb; struct btrfs_extent_item *ei; struct scrub_warning swarn; u64 flags = 0; u32 item_size; int ret; /* Super block error, no need to search extent tree. */ if (is_super) { btrfs_warn_in_rcu(fs_info, "%s on device %s, physical %llu", errstr, btrfs_dev_name(dev), physical); return; } path = btrfs_alloc_path(); if (!path) return; swarn.physical = physical; swarn.logical = logical; swarn.errstr = errstr; swarn.dev = NULL; ret = extent_from_logical(fs_info, swarn.logical, path, &found_key, &flags); if (ret < 0) goto out; swarn.extent_item_size = found_key.offset; eb = path->nodes[0]; ei = btrfs_item_ptr(eb, path->slots[0], struct btrfs_extent_item); item_size = btrfs_item_size(eb, path->slots[0]); if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) { unsigned long ptr = 0; u8 ref_level; u64 ref_root; while (true) { ret = tree_backref_for_extent(&ptr, eb, &found_key, ei, item_size, &ref_root, &ref_level); if (ret < 0) { btrfs_warn(fs_info, "failed to resolve tree backref for logical %llu: %d", swarn.logical, ret); break; } if (ret > 0) break; btrfs_warn_in_rcu(fs_info, "%s at logical %llu on dev %s, physical %llu: metadata %s (level %d) in tree %llu", errstr, swarn.logical, btrfs_dev_name(dev), swarn.physical, (ref_level ? "node" : "leaf"), ref_level, ref_root); } btrfs_release_path(path); } else { struct btrfs_backref_walk_ctx ctx = { 0 }; btrfs_release_path(path); ctx.bytenr = found_key.objectid; ctx.extent_item_pos = swarn.logical - found_key.objectid; ctx.fs_info = fs_info; swarn.path = path; swarn.dev = dev; iterate_extent_inodes(&ctx, true, scrub_print_warning_inode, &swarn); } out: btrfs_free_path(path); } static int fill_writer_pointer_gap(struct scrub_ctx *sctx, u64 physical) { int ret = 0; u64 length; if (!btrfs_is_zoned(sctx->fs_info)) return 0; if (!btrfs_dev_is_sequential(sctx->wr_tgtdev, physical)) return 0; if (sctx->write_pointer < physical) { length = physical - sctx->write_pointer; ret = btrfs_zoned_issue_zeroout(sctx->wr_tgtdev, sctx->write_pointer, length); if (!ret) sctx->write_pointer = physical; } return ret; } static struct page *scrub_stripe_get_page(struct scrub_stripe *stripe, int sector_nr) { struct btrfs_fs_info *fs_info = stripe->bg->fs_info; int page_index = (sector_nr << fs_info->sectorsize_bits) >> PAGE_SHIFT; return stripe->pages[page_index]; } static unsigned int scrub_stripe_get_page_offset(struct scrub_stripe *stripe, int sector_nr) { struct btrfs_fs_info *fs_info = stripe->bg->fs_info; return offset_in_page(sector_nr << fs_info->sectorsize_bits); } static void scrub_verify_one_metadata(struct scrub_stripe *stripe, int sector_nr) { struct btrfs_fs_info *fs_info = stripe->bg->fs_info; const u32 sectors_per_tree = fs_info->nodesize >> fs_info->sectorsize_bits; const u64 logical = stripe->logical + (sector_nr << fs_info->sectorsize_bits); const struct page *first_page = scrub_stripe_get_page(stripe, sector_nr); const unsigned int first_off = scrub_stripe_get_page_offset(stripe, sector_nr); SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); u8 on_disk_csum[BTRFS_CSUM_SIZE]; u8 calculated_csum[BTRFS_CSUM_SIZE]; struct btrfs_header *header; /* * Here we don't have a good way to attach the pages (and subpages) * to a dummy extent buffer, thus we have to directly grab the members * from pages. */ header = (struct btrfs_header *)(page_address(first_page) + first_off); memcpy(on_disk_csum, header->csum, fs_info->csum_size); if (logical != btrfs_stack_header_bytenr(header)) { bitmap_set(&stripe->csum_error_bitmap, sector_nr, sectors_per_tree); bitmap_set(&stripe->error_bitmap, sector_nr, sectors_per_tree); btrfs_warn_rl(fs_info, "tree block %llu mirror %u has bad bytenr, has %llu want %llu", logical, stripe->mirror_num, btrfs_stack_header_bytenr(header), logical); return; } if (memcmp(header->fsid, fs_info->fs_devices->metadata_uuid, BTRFS_FSID_SIZE) != 0) { bitmap_set(&stripe->meta_error_bitmap, sector_nr, sectors_per_tree); bitmap_set(&stripe->error_bitmap, sector_nr, sectors_per_tree); btrfs_warn_rl(fs_info, "tree block %llu mirror %u has bad fsid, has %pU want %pU", logical, stripe->mirror_num, header->fsid, fs_info->fs_devices->fsid); return; } if (memcmp(header->chunk_tree_uuid, fs_info->chunk_tree_uuid, BTRFS_UUID_SIZE) != 0) { bitmap_set(&stripe->meta_error_bitmap, sector_nr, sectors_per_tree); bitmap_set(&stripe->error_bitmap, sector_nr, sectors_per_tree); btrfs_warn_rl(fs_info, "tree block %llu mirror %u has bad chunk tree uuid, has %pU want %pU", logical, stripe->mirror_num, header->chunk_tree_uuid, fs_info->chunk_tree_uuid); return; } /* Now check tree block csum. */ shash->tfm = fs_info->csum_shash; crypto_shash_init(shash); crypto_shash_update(shash, page_address(first_page) + first_off + BTRFS_CSUM_SIZE, fs_info->sectorsize - BTRFS_CSUM_SIZE); for (int i = sector_nr + 1; i < sector_nr + sectors_per_tree; i++) { struct page *page = scrub_stripe_get_page(stripe, i); unsigned int page_off = scrub_stripe_get_page_offset(stripe, i); crypto_shash_update(shash, page_address(page) + page_off, fs_info->sectorsize); } crypto_shash_final(shash, calculated_csum); if (memcmp(calculated_csum, on_disk_csum, fs_info->csum_size) != 0) { bitmap_set(&stripe->meta_error_bitmap, sector_nr, sectors_per_tree); bitmap_set(&stripe->error_bitmap, sector_nr, sectors_per_tree); btrfs_warn_rl(fs_info, "tree block %llu mirror %u has bad csum, has " CSUM_FMT " want " CSUM_FMT, logical, stripe->mirror_num, CSUM_FMT_VALUE(fs_info->csum_size, on_disk_csum), CSUM_FMT_VALUE(fs_info->csum_size, calculated_csum)); return; } if (stripe->sectors[sector_nr].generation != btrfs_stack_header_generation(header)) { bitmap_set(&stripe->meta_error_bitmap, sector_nr, sectors_per_tree); bitmap_set(&stripe->error_bitmap, sector_nr, sectors_per_tree); btrfs_warn_rl(fs_info, "tree block %llu mirror %u has bad generation, has %llu want %llu", logical, stripe->mirror_num, btrfs_stack_header_generation(header), stripe->sectors[sector_nr].generation); return; } bitmap_clear(&stripe->error_bitmap, sector_nr, sectors_per_tree); bitmap_clear(&stripe->csum_error_bitmap, sector_nr, sectors_per_tree); bitmap_clear(&stripe->meta_error_bitmap, sector_nr, sectors_per_tree); } static void scrub_verify_one_sector(struct scrub_stripe *stripe, int sector_nr) { struct btrfs_fs_info *fs_info = stripe->bg->fs_info; struct scrub_sector_verification *sector = &stripe->sectors[sector_nr]; const u32 sectors_per_tree = fs_info->nodesize >> fs_info->sectorsize_bits; struct page *page = scrub_stripe_get_page(stripe, sector_nr); unsigned int pgoff = scrub_stripe_get_page_offset(stripe, sector_nr); u8 csum_buf[BTRFS_CSUM_SIZE]; int ret; ASSERT(sector_nr >= 0 && sector_nr < stripe->nr_sectors); /* Sector not utilized, skip it. */ if (!test_bit(sector_nr, &stripe->extent_sector_bitmap)) return; /* IO error, no need to check. */ if (test_bit(sector_nr, &stripe->io_error_bitmap)) return; /* Metadata, verify the full tree block. */ if (sector->is_metadata) { /* * Check if the tree block crosses the stripe boundary. If * crossed the boundary, we cannot verify it but only give a * warning. * * This can only happen on a very old filesystem where chunks * are not ensured to be stripe aligned. */ if (unlikely(sector_nr + sectors_per_tree > stripe->nr_sectors)) { btrfs_warn_rl(fs_info, "tree block at %llu crosses stripe boundary %llu", stripe->logical + (sector_nr << fs_info->sectorsize_bits), stripe->logical); return; } scrub_verify_one_metadata(stripe, sector_nr); return; } /* * Data is easier, we just verify the data csum (if we have it). For * cases without csum, we have no other choice but to trust it. */ if (!sector->csum) { clear_bit(sector_nr, &stripe->error_bitmap); return; } ret = btrfs_check_sector_csum(fs_info, page, pgoff, csum_buf, sector->csum); if (ret < 0) { set_bit(sector_nr, &stripe->csum_error_bitmap); set_bit(sector_nr, &stripe->error_bitmap); } else { clear_bit(sector_nr, &stripe->csum_error_bitmap); clear_bit(sector_nr, &stripe->error_bitmap); } } /* Verify specified sectors of a stripe. */ static void scrub_verify_one_stripe(struct scrub_stripe *stripe, unsigned long bitmap) { struct btrfs_fs_info *fs_info = stripe->bg->fs_info; const u32 sectors_per_tree = fs_info->nodesize >> fs_info->sectorsize_bits; int sector_nr; for_each_set_bit(sector_nr, &bitmap, stripe->nr_sectors) { scrub_verify_one_sector(stripe, sector_nr); if (stripe->sectors[sector_nr].is_metadata) sector_nr += sectors_per_tree - 1; } } static int calc_sector_number(struct scrub_stripe *stripe, struct bio_vec *first_bvec) { int i; for (i = 0; i < stripe->nr_sectors; i++) { if (scrub_stripe_get_page(stripe, i) == first_bvec->bv_page && scrub_stripe_get_page_offset(stripe, i) == first_bvec->bv_offset) break; } ASSERT(i < stripe->nr_sectors); return i; } /* * Repair read is different to the regular read: * * - Only reads the failed sectors * - May have extra blocksize limits */ static void scrub_repair_read_endio(struct btrfs_bio *bbio) { struct scrub_stripe *stripe = bbio->private; struct btrfs_fs_info *fs_info = stripe->bg->fs_info; struct bio_vec *bvec; int sector_nr = calc_sector_number(stripe, bio_first_bvec_all(&bbio->bio)); u32 bio_size = 0; int i; ASSERT(sector_nr < stripe->nr_sectors); bio_for_each_bvec_all(bvec, &bbio->bio, i) bio_size += bvec->bv_len; if (bbio->bio.bi_status) { bitmap_set(&stripe->io_error_bitmap, sector_nr, bio_size >> fs_info->sectorsize_bits); bitmap_set(&stripe->error_bitmap, sector_nr, bio_size >> fs_info->sectorsize_bits); } else { bitmap_clear(&stripe->io_error_bitmap, sector_nr, bio_size >> fs_info->sectorsize_bits); } bio_put(&bbio->bio); if (atomic_dec_and_test(&stripe->pending_io)) wake_up(&stripe->io_wait); } static int calc_next_mirror(int mirror, int num_copies) { ASSERT(mirror <= num_copies); return (mirror + 1 > num_copies) ? 1 : mirror + 1; } static void scrub_stripe_submit_repair_read(struct scrub_stripe *stripe, int mirror, int blocksize, bool wait) { struct btrfs_fs_info *fs_info = stripe->bg->fs_info; struct btrfs_bio *bbio = NULL; const unsigned long old_error_bitmap = stripe->error_bitmap; int i; ASSERT(stripe->mirror_num >= 1); ASSERT(atomic_read(&stripe->pending_io) == 0); for_each_set_bit(i, &old_error_bitmap, stripe->nr_sectors) { struct page *page; int pgoff; int ret; page = scrub_stripe_get_page(stripe, i); pgoff = scrub_stripe_get_page_offset(stripe, i); /* The current sector cannot be merged, submit the bio. */ if (bbio && ((i > 0 && !test_bit(i - 1, &stripe->error_bitmap)) || bbio->bio.bi_iter.bi_size >= blocksize)) { ASSERT(bbio->bio.bi_iter.bi_size); atomic_inc(&stripe->pending_io); btrfs_submit_bbio(bbio, mirror); if (wait) wait_scrub_stripe_io(stripe); bbio = NULL; } if (!bbio) { bbio = btrfs_bio_alloc(stripe->nr_sectors, REQ_OP_READ, fs_info, scrub_repair_read_endio, stripe); bbio->bio.bi_iter.bi_sector = (stripe->logical + (i << fs_info->sectorsize_bits)) >> SECTOR_SHIFT; } ret = bio_add_page(&bbio->bio, page, fs_info->sectorsize, pgoff); ASSERT(ret == fs_info->sectorsize); } if (bbio) { ASSERT(bbio->bio.bi_iter.bi_size); atomic_inc(&stripe->pending_io); btrfs_submit_bbio(bbio, mirror); if (wait) wait_scrub_stripe_io(stripe); } } static void scrub_stripe_report_errors(struct scrub_ctx *sctx, struct scrub_stripe *stripe) { static DEFINE_RATELIMIT_STATE(rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); struct btrfs_fs_info *fs_info = sctx->fs_info; struct btrfs_device *dev = NULL; u64 physical = 0; int nr_data_sectors = 0; int nr_meta_sectors = 0; int nr_nodatacsum_sectors = 0; int nr_repaired_sectors = 0; int sector_nr; if (test_bit(SCRUB_STRIPE_FLAG_NO_REPORT, &stripe->state)) return; /* * Init needed infos for error reporting. * * Although our scrub_stripe infrastructure is mostly based on btrfs_submit_bio() * thus no need for dev/physical, error reporting still needs dev and physical. */ if (!bitmap_empty(&stripe->init_error_bitmap, stripe->nr_sectors)) { u64 mapped_len = fs_info->sectorsize; struct btrfs_io_context *bioc = NULL; int stripe_index = stripe->mirror_num - 1; int ret; /* For scrub, our mirror_num should always start at 1. */ ASSERT(stripe->mirror_num >= 1); ret = btrfs_map_block(fs_info, BTRFS_MAP_GET_READ_MIRRORS, stripe->logical, &mapped_len, &bioc, NULL, NULL); /* * If we failed, dev will be NULL, and later detailed reports * will just be skipped. */ if (ret < 0) goto skip; physical = bioc->stripes[stripe_index].physical; dev = bioc->stripes[stripe_index].dev; btrfs_put_bioc(bioc); } skip: for_each_set_bit(sector_nr, &stripe->extent_sector_bitmap, stripe->nr_sectors) { bool repaired = false; if (stripe->sectors[sector_nr].is_metadata) { nr_meta_sectors++; } else { nr_data_sectors++; if (!stripe->sectors[sector_nr].csum) nr_nodatacsum_sectors++; } if (test_bit(sector_nr, &stripe->init_error_bitmap) && !test_bit(sector_nr, &stripe->error_bitmap)) { nr_repaired_sectors++; repaired = true; } /* Good sector from the beginning, nothing need to be done. */ if (!test_bit(sector_nr, &stripe->init_error_bitmap)) continue; /* * Report error for the corrupted sectors. If repaired, just * output the message of repaired message. */ if (repaired) { if (dev) { btrfs_err_rl_in_rcu(fs_info, "fixed up error at logical %llu on dev %s physical %llu", stripe->logical, btrfs_dev_name(dev), physical); } else { btrfs_err_rl_in_rcu(fs_info, "fixed up error at logical %llu on mirror %u", stripe->logical, stripe->mirror_num); } continue; } /* The remaining are all for unrepaired. */ if (dev) { btrfs_err_rl_in_rcu(fs_info, "unable to fixup (regular) error at logical %llu on dev %s physical %llu", stripe->logical, btrfs_dev_name(dev), physical); } else { btrfs_err_rl_in_rcu(fs_info, "unable to fixup (regular) error at logical %llu on mirror %u", stripe->logical, stripe->mirror_num); } if (test_bit(sector_nr, &stripe->io_error_bitmap)) if (__ratelimit(&rs) && dev) scrub_print_common_warning("i/o error", dev, false, stripe->logical, physical); if (test_bit(sector_nr, &stripe->csum_error_bitmap)) if (__ratelimit(&rs) && dev) scrub_print_common_warning("checksum error", dev, false, stripe->logical, physical); if (test_bit(sector_nr, &stripe->meta_error_bitmap)) if (__ratelimit(&rs) && dev) scrub_print_common_warning("header error", dev, false, stripe->logical, physical); } spin_lock(&sctx->stat_lock); sctx->stat.data_extents_scrubbed += stripe->nr_data_extents; sctx->stat.tree_extents_scrubbed += stripe->nr_meta_extents; sctx->stat.data_bytes_scrubbed += nr_data_sectors << fs_info->sectorsize_bits; sctx->stat.tree_bytes_scrubbed += nr_meta_sectors << fs_info->sectorsize_bits; sctx->stat.no_csum += nr_nodatacsum_sectors; sctx->stat.read_errors += stripe->init_nr_io_errors; sctx->stat.csum_errors += stripe->init_nr_csum_errors; sctx->stat.verify_errors += stripe->init_nr_meta_errors; sctx->stat.uncorrectable_errors += bitmap_weight(&stripe->error_bitmap, stripe->nr_sectors); sctx->stat.corrected_errors += nr_repaired_sectors; spin_unlock(&sctx->stat_lock); } static void scrub_write_sectors(struct scrub_ctx *sctx, struct scrub_stripe *stripe, unsigned long write_bitmap, bool dev_replace); /* * The main entrance for all read related scrub work, including: * * - Wait for the initial read to finish * - Verify and locate any bad sectors * - Go through the remaining mirrors and try to read as large blocksize as * possible * - Go through all mirrors (including the failed mirror) sector-by-sector * - Submit writeback for repaired sectors * * Writeback for dev-replace does not happen here, it needs extra * synchronization for zoned devices. */ static void scrub_stripe_read_repair_worker(struct work_struct *work) { struct scrub_stripe *stripe = container_of(work, struct scrub_stripe, work); struct scrub_ctx *sctx = stripe->sctx; struct btrfs_fs_info *fs_info = sctx->fs_info; int num_copies = btrfs_num_copies(fs_info, stripe->bg->start, stripe->bg->length); unsigned long repaired; int mirror; int i; ASSERT(stripe->mirror_num > 0); wait_scrub_stripe_io(stripe); scrub_verify_one_stripe(stripe, stripe->extent_sector_bitmap); /* Save the initial failed bitmap for later repair and report usage. */ stripe->init_error_bitmap = stripe->error_bitmap; stripe->init_nr_io_errors = bitmap_weight(&stripe->io_error_bitmap, stripe->nr_sectors); stripe->init_nr_csum_errors = bitmap_weight(&stripe->csum_error_bitmap, stripe->nr_sectors); stripe->init_nr_meta_errors = bitmap_weight(&stripe->meta_error_bitmap, stripe->nr_sectors); if (bitmap_empty(&stripe->init_error_bitmap, stripe->nr_sectors)) goto out; /* * Try all remaining mirrors. * * Here we still try to read as large block as possible, as this is * faster and we have extra safety nets to rely on. */ for (mirror = calc_next_mirror(stripe->mirror_num, num_copies); mirror != stripe->mirror_num; mirror = calc_next_mirror(mirror, num_copies)) { const unsigned long old_error_bitmap = stripe->error_bitmap; scrub_stripe_submit_repair_read(stripe, mirror, BTRFS_STRIPE_LEN, false); wait_scrub_stripe_io(stripe); scrub_verify_one_stripe(stripe, old_error_bitmap); if (bitmap_empty(&stripe->error_bitmap, stripe->nr_sectors)) goto out; } /* * Last safety net, try re-checking all mirrors, including the failed * one, sector-by-sector. * * As if one sector failed the drive's internal csum, the whole read * containing the offending sector would be marked as error. * Thus here we do sector-by-sector read. * * This can be slow, thus we only try it as the last resort. */ for (i = 0, mirror = stripe->mirror_num; i < num_copies; i++, mirror = calc_next_mirror(mirror, num_copies)) { const unsigned long old_error_bitmap = stripe->error_bitmap; scrub_stripe_submit_repair_read(stripe, mirror, fs_info->sectorsize, true); wait_scrub_stripe_io(stripe); scrub_verify_one_stripe(stripe, old_error_bitmap); if (bitmap_empty(&stripe->error_bitmap, stripe->nr_sectors)) goto out; } out: /* * Submit the repaired sectors. For zoned case, we cannot do repair * in-place, but queue the bg to be relocated. */ bitmap_andnot(&repaired, &stripe->init_error_bitmap, &stripe->error_bitmap, stripe->nr_sectors); if (!sctx->readonly && !bitmap_empty(&repaired, stripe->nr_sectors)) { if (btrfs_is_zoned(fs_info)) { btrfs_repair_one_zone(fs_info, sctx->stripes[0].bg->start); } else { scrub_write_sectors(sctx, stripe, repaired, false); wait_scrub_stripe_io(stripe); } } scrub_stripe_report_errors(sctx, stripe); set_bit(SCRUB_STRIPE_FLAG_REPAIR_DONE, &stripe->state); wake_up(&stripe->repair_wait); } static void scrub_read_endio(struct btrfs_bio *bbio) { struct scrub_stripe *stripe = bbio->private; struct bio_vec *bvec; int sector_nr = calc_sector_number(stripe, bio_first_bvec_all(&bbio->bio)); int num_sectors; u32 bio_size = 0; int i; ASSERT(sector_nr < stripe->nr_sectors); bio_for_each_bvec_all(bvec, &bbio->bio, i) bio_size += bvec->bv_len; num_sectors = bio_size >> stripe->bg->fs_info->sectorsize_bits; if (bbio->bio.bi_status) { bitmap_set(&stripe->io_error_bitmap, sector_nr, num_sectors); bitmap_set(&stripe->error_bitmap, sector_nr, num_sectors); } else { bitmap_clear(&stripe->io_error_bitmap, sector_nr, num_sectors); } bio_put(&bbio->bio); if (atomic_dec_and_test(&stripe->pending_io)) { wake_up(&stripe->io_wait); INIT_WORK(&stripe->work, scrub_stripe_read_repair_worker); queue_work(stripe->bg->fs_info->scrub_workers, &stripe->work); } } static void scrub_write_endio(struct btrfs_bio *bbio) { struct scrub_stripe *stripe = bbio->private; struct btrfs_fs_info *fs_info = stripe->bg->fs_info; struct bio_vec *bvec; int sector_nr = calc_sector_number(stripe, bio_first_bvec_all(&bbio->bio)); u32 bio_size = 0; int i; bio_for_each_bvec_all(bvec, &bbio->bio, i) bio_size += bvec->bv_len; if (bbio->bio.bi_status) { unsigned long flags; spin_lock_irqsave(&stripe->write_error_lock, flags); bitmap_set(&stripe->write_error_bitmap, sector_nr, bio_size >> fs_info->sectorsize_bits); spin_unlock_irqrestore(&stripe->write_error_lock, flags); } bio_put(&bbio->bio); if (atomic_dec_and_test(&stripe->pending_io)) wake_up(&stripe->io_wait); } static void scrub_submit_write_bio(struct scrub_ctx *sctx, struct scrub_stripe *stripe, struct btrfs_bio *bbio, bool dev_replace) { struct btrfs_fs_info *fs_info = sctx->fs_info; u32 bio_len = bbio->bio.bi_iter.bi_size; u32 bio_off = (bbio->bio.bi_iter.bi_sector << SECTOR_SHIFT) - stripe->logical; fill_writer_pointer_gap(sctx, stripe->physical + bio_off); atomic_inc(&stripe->pending_io); btrfs_submit_repair_write(bbio, stripe->mirror_num, dev_replace); if (!btrfs_is_zoned(fs_info)) return; /* * For zoned writeback, queue depth must be 1, thus we must wait for * the write to finish before the next write. */ wait_scrub_stripe_io(stripe); /* * And also need to update the write pointer if write finished * successfully. */ if (!test_bit(bio_off >> fs_info->sectorsize_bits, &stripe->write_error_bitmap)) sctx->write_pointer += bio_len; } /* * Submit the write bio(s) for the sectors specified by @write_bitmap. * * Here we utilize btrfs_submit_repair_write(), which has some extra benefits: * * - Only needs logical bytenr and mirror_num * Just like the scrub read path * * - Would only result in writes to the specified mirror * Unlike the regular writeback path, which would write back to all stripes * * - Handle dev-replace and read-repair writeback differently */ static void scrub_write_sectors(struct scrub_ctx *sctx, struct scrub_stripe *stripe, unsigned long write_bitmap, bool dev_replace) { struct btrfs_fs_info *fs_info = stripe->bg->fs_info; struct btrfs_bio *bbio = NULL; int sector_nr; for_each_set_bit(sector_nr, &write_bitmap, stripe->nr_sectors) { struct page *page = scrub_stripe_get_page(stripe, sector_nr); unsigned int pgoff = scrub_stripe_get_page_offset(stripe, sector_nr); int ret; /* We should only writeback sectors covered by an extent. */ ASSERT(test_bit(sector_nr, &stripe->extent_sector_bitmap)); /* Cannot merge with previous sector, submit the current one. */ if (bbio && sector_nr && !test_bit(sector_nr - 1, &write_bitmap)) { scrub_submit_write_bio(sctx, stripe, bbio, dev_replace); bbio = NULL; } if (!bbio) { bbio = btrfs_bio_alloc(stripe->nr_sectors, REQ_OP_WRITE, fs_info, scrub_write_endio, stripe); bbio->bio.bi_iter.bi_sector = (stripe->logical + (sector_nr << fs_info->sectorsize_bits)) >> SECTOR_SHIFT; } ret = bio_add_page(&bbio->bio, page, fs_info->sectorsize, pgoff); ASSERT(ret == fs_info->sectorsize); } if (bbio) scrub_submit_write_bio(sctx, stripe, bbio, dev_replace); } /* * Throttling of IO submission, bandwidth-limit based, the timeslice is 1 * second. Limit can be set via /sys/fs/UUID/devinfo/devid/scrub_speed_max. */ static void scrub_throttle_dev_io(struct scrub_ctx *sctx, struct btrfs_device *device, unsigned int bio_size) { const int time_slice = 1000; s64 delta; ktime_t now; u32 div; u64 bwlimit; bwlimit = READ_ONCE(device->scrub_speed_max); if (bwlimit == 0) return; /* * Slice is divided into intervals when the IO is submitted, adjust by * bwlimit and maximum of 64 intervals. */ div = max_t(u32, 1, (u32)(bwlimit / (16 * 1024 * 1024))); div = min_t(u32, 64, div); /* Start new epoch, set deadline */ now = ktime_get(); if (sctx->throttle_deadline == 0) { sctx->throttle_deadline = ktime_add_ms(now, time_slice / div); sctx->throttle_sent = 0; } /* Still in the time to send? */ if (ktime_before(now, sctx->throttle_deadline)) { /* If current bio is within the limit, send it */ sctx->throttle_sent += bio_size; if (sctx->throttle_sent <= div_u64(bwlimit, div)) return; /* We're over the limit, sleep until the rest of the slice */ delta = ktime_ms_delta(sctx->throttle_deadline, now); } else { /* New request after deadline, start new epoch */ delta = 0; } if (delta) { long timeout; timeout = div_u64(delta * HZ, 1000); schedule_timeout_interruptible(timeout); } /* Next call will start the deadline period */ sctx->throttle_deadline = 0; } /* * Given a physical address, this will calculate it's * logical offset. if this is a parity stripe, it will return * the most left data stripe's logical offset. * * return 0 if it is a data stripe, 1 means parity stripe. */ static int get_raid56_logic_offset(u64 physical, int num, struct btrfs_chunk_map *map, u64 *offset, u64 *stripe_start) { int i; int j = 0; u64 last_offset; const int data_stripes = nr_data_stripes(map); last_offset = (physical - map->stripes[num].physical) * data_stripes; if (stripe_start) *stripe_start = last_offset; *offset = last_offset; for (i = 0; i < data_stripes; i++) { u32 stripe_nr; u32 stripe_index; u32 rot; *offset = last_offset + btrfs_stripe_nr_to_offset(i); stripe_nr = (u32)(*offset >> BTRFS_STRIPE_LEN_SHIFT) / data_stripes; /* Work out the disk rotation on this stripe-set */ rot = stripe_nr % map->num_stripes; /* calculate which stripe this data locates */ rot += i; stripe_index = rot % map->num_stripes; if (stripe_index == num) return 0; if (stripe_index < num) j++; } *offset = last_offset + btrfs_stripe_nr_to_offset(j); return 1; } /* * Return 0 if the extent item range covers any byte of the range. * Return <0 if the extent item is before @search_start. * Return >0 if the extent item is after @start_start + @search_len. */ static int compare_extent_item_range(struct btrfs_path *path, u64 search_start, u64 search_len) { struct btrfs_fs_info *fs_info = path->nodes[0]->fs_info; u64 len; struct btrfs_key key; btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); ASSERT(key.type == BTRFS_EXTENT_ITEM_KEY || key.type == BTRFS_METADATA_ITEM_KEY); if (key.type == BTRFS_METADATA_ITEM_KEY) len = fs_info->nodesize; else len = key.offset; if (key.objectid + len <= search_start) return -1; if (key.objectid >= search_start + search_len) return 1; return 0; } /* * Locate one extent item which covers any byte in range * [@search_start, @search_start + @search_length) * * If the path is not initialized, we will initialize the search by doing * a btrfs_search_slot(). * If the path is already initialized, we will use the path as the initial * slot, to avoid duplicated btrfs_search_slot() calls. * * NOTE: If an extent item starts before @search_start, we will still * return the extent item. This is for data extent crossing stripe boundary. * * Return 0 if we found such extent item, and @path will point to the extent item. * Return >0 if no such extent item can be found, and @path will be released. * Return <0 if hit fatal error, and @path will be released. */ static int find_first_extent_item(struct btrfs_root *extent_root, struct btrfs_path *path, u64 search_start, u64 search_len) { struct btrfs_fs_info *fs_info = extent_root->fs_info; struct btrfs_key key; int ret; /* Continue using the existing path */ if (path->nodes[0]) goto search_forward; if (btrfs_fs_incompat(fs_info, SKINNY_METADATA)) key.type = BTRFS_METADATA_ITEM_KEY; else key.type = BTRFS_EXTENT_ITEM_KEY; key.objectid = search_start; key.offset = (u64)-1; ret = btrfs_search_slot(NULL, extent_root, &key, path, 0, 0); if (ret < 0) return ret; if (ret == 0) { /* * Key with offset -1 found, there would have to exist an extent * item with such offset, but this is out of the valid range. */ btrfs_release_path(path); return -EUCLEAN; } /* * Here we intentionally pass 0 as @min_objectid, as there could be * an extent item starting before @search_start. */ ret = btrfs_previous_extent_item(extent_root, path, 0); if (ret < 0) return ret; /* * No matter whether we have found an extent item, the next loop will * properly do every check on the key. */ search_forward: while (true) { btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.objectid >= search_start + search_len) break; if (key.type != BTRFS_METADATA_ITEM_KEY && key.type != BTRFS_EXTENT_ITEM_KEY) goto next; ret = compare_extent_item_range(path, search_start, search_len); if (ret == 0) return ret; if (ret > 0) break; next: ret = btrfs_next_item(extent_root, path); if (ret) { /* Either no more items or a fatal error. */ btrfs_release_path(path); return ret; } } btrfs_release_path(path); return 1; } static void get_extent_info(struct btrfs_path *path, u64 *extent_start_ret, u64 *size_ret, u64 *flags_ret, u64 *generation_ret) { struct btrfs_key key; struct btrfs_extent_item *ei; btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); ASSERT(key.type == BTRFS_METADATA_ITEM_KEY || key.type == BTRFS_EXTENT_ITEM_KEY); *extent_start_ret = key.objectid; if (key.type == BTRFS_METADATA_ITEM_KEY) *size_ret = path->nodes[0]->fs_info->nodesize; else *size_ret = key.offset; ei = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_extent_item); *flags_ret = btrfs_extent_flags(path->nodes[0], ei); *generation_ret = btrfs_extent_generation(path->nodes[0], ei); } static int sync_write_pointer_for_zoned(struct scrub_ctx *sctx, u64 logical, u64 physical, u64 physical_end) { struct btrfs_fs_info *fs_info = sctx->fs_info; int ret = 0; if (!btrfs_is_zoned(fs_info)) return 0; mutex_lock(&sctx->wr_lock); if (sctx->write_pointer < physical_end) { ret = btrfs_sync_zone_write_pointer(sctx->wr_tgtdev, logical, physical, sctx->write_pointer); if (ret) btrfs_err(fs_info, "zoned: failed to recover write pointer"); } mutex_unlock(&sctx->wr_lock); btrfs_dev_clear_zone_empty(sctx->wr_tgtdev, physical); return ret; } static void fill_one_extent_info(struct btrfs_fs_info *fs_info, struct scrub_stripe *stripe, u64 extent_start, u64 extent_len, u64 extent_flags, u64 extent_gen) { for (u64 cur_logical = max(stripe->logical, extent_start); cur_logical < min(stripe->logical + BTRFS_STRIPE_LEN, extent_start + extent_len); cur_logical += fs_info->sectorsize) { const int nr_sector = (cur_logical - stripe->logical) >> fs_info->sectorsize_bits; struct scrub_sector_verification *sector = &stripe->sectors[nr_sector]; set_bit(nr_sector, &stripe->extent_sector_bitmap); if (extent_flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) { sector->is_metadata = true; sector->generation = extent_gen; } } } static void scrub_stripe_reset_bitmaps(struct scrub_stripe *stripe) { stripe->extent_sector_bitmap = 0; stripe->init_error_bitmap = 0; stripe->init_nr_io_errors = 0; stripe->init_nr_csum_errors = 0; stripe->init_nr_meta_errors = 0; stripe->error_bitmap = 0; stripe->io_error_bitmap = 0; stripe->csum_error_bitmap = 0; stripe->meta_error_bitmap = 0; } /* * Locate one stripe which has at least one extent in its range. * * Return 0 if found such stripe, and store its info into @stripe. * Return >0 if there is no such stripe in the specified range. * Return <0 for error. */ static int scrub_find_fill_first_stripe(struct btrfs_block_group *bg, struct btrfs_path *extent_path, struct btrfs_path *csum_path, struct btrfs_device *dev, u64 physical, int mirror_num, u64 logical_start, u32 logical_len, struct scrub_stripe *stripe) { struct btrfs_fs_info *fs_info = bg->fs_info; struct btrfs_root *extent_root = btrfs_extent_root(fs_info, bg->start); struct btrfs_root *csum_root = btrfs_csum_root(fs_info, bg->start); const u64 logical_end = logical_start + logical_len; u64 cur_logical = logical_start; u64 stripe_end; u64 extent_start; u64 extent_len; u64 extent_flags; u64 extent_gen; int ret; if (unlikely(!extent_root)) { btrfs_err(fs_info, "no valid extent root for scrub"); return -EUCLEAN; } memset(stripe->sectors, 0, sizeof(struct scrub_sector_verification) * stripe->nr_sectors); scrub_stripe_reset_bitmaps(stripe); /* The range must be inside the bg. */ ASSERT(logical_start >= bg->start && logical_end <= bg->start + bg->length); ret = find_first_extent_item(extent_root, extent_path, logical_start, logical_len); /* Either error or not found. */ if (ret) goto out; get_extent_info(extent_path, &extent_start, &extent_len, &extent_flags, &extent_gen); if (extent_flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) stripe->nr_meta_extents++; if (extent_flags & BTRFS_EXTENT_FLAG_DATA) stripe->nr_data_extents++; cur_logical = max(extent_start, cur_logical); /* * Round down to stripe boundary. * * The extra calculation against bg->start is to handle block groups * whose logical bytenr is not BTRFS_STRIPE_LEN aligned. */ stripe->logical = round_down(cur_logical - bg->start, BTRFS_STRIPE_LEN) + bg->start; stripe->physical = physical + stripe->logical - logical_start; stripe->dev = dev; stripe->bg = bg; stripe->mirror_num = mirror_num; stripe_end = stripe->logical + BTRFS_STRIPE_LEN - 1; /* Fill the first extent info into stripe->sectors[] array. */ fill_one_extent_info(fs_info, stripe, extent_start, extent_len, extent_flags, extent_gen); cur_logical = extent_start + extent_len; /* Fill the extent info for the remaining sectors. */ while (cur_logical <= stripe_end) { ret = find_first_extent_item(extent_root, extent_path, cur_logical, stripe_end - cur_logical + 1); if (ret < 0) goto out; if (ret > 0) { ret = 0; break; } get_extent_info(extent_path, &extent_start, &extent_len, &extent_flags, &extent_gen); if (extent_flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) stripe->nr_meta_extents++; if (extent_flags & BTRFS_EXTENT_FLAG_DATA) stripe->nr_data_extents++; fill_one_extent_info(fs_info, stripe, extent_start, extent_len, extent_flags, extent_gen); cur_logical = extent_start + extent_len; } /* Now fill the data csum. */ if (bg->flags & BTRFS_BLOCK_GROUP_DATA) { int sector_nr; unsigned long csum_bitmap = 0; /* Csum space should have already been allocated. */ ASSERT(stripe->csums); /* * Our csum bitmap should be large enough, as BTRFS_STRIPE_LEN * should contain at most 16 sectors. */ ASSERT(BITS_PER_LONG >= BTRFS_STRIPE_LEN >> fs_info->sectorsize_bits); ret = btrfs_lookup_csums_bitmap(csum_root, csum_path, stripe->logical, stripe_end, stripe->csums, &csum_bitmap); if (ret < 0) goto out; if (ret > 0) ret = 0; for_each_set_bit(sector_nr, &csum_bitmap, stripe->nr_sectors) { stripe->sectors[sector_nr].csum = stripe->csums + sector_nr * fs_info->csum_size; } } set_bit(SCRUB_STRIPE_FLAG_INITIALIZED, &stripe->state); out: return ret; } static void scrub_reset_stripe(struct scrub_stripe *stripe) { scrub_stripe_reset_bitmaps(stripe); stripe->nr_meta_extents = 0; stripe->nr_data_extents = 0; stripe->state = 0; for (int i = 0; i < stripe->nr_sectors; i++) { stripe->sectors[i].is_metadata = false; stripe->sectors[i].csum = NULL; stripe->sectors[i].generation = 0; } } static u32 stripe_length(const struct scrub_stripe *stripe) { ASSERT(stripe->bg); return min(BTRFS_STRIPE_LEN, stripe->bg->start + stripe->bg->length - stripe->logical); } static void scrub_submit_extent_sector_read(struct scrub_stripe *stripe) { struct btrfs_fs_info *fs_info = stripe->bg->fs_info; struct btrfs_bio *bbio = NULL; unsigned int nr_sectors = stripe_length(stripe) >> fs_info->sectorsize_bits; u64 stripe_len = BTRFS_STRIPE_LEN; int mirror = stripe->mirror_num; int i; atomic_inc(&stripe->pending_io); for_each_set_bit(i, &stripe->extent_sector_bitmap, stripe->nr_sectors) { struct page *page = scrub_stripe_get_page(stripe, i); unsigned int pgoff = scrub_stripe_get_page_offset(stripe, i); /* We're beyond the chunk boundary, no need to read anymore. */ if (i >= nr_sectors) break; /* The current sector cannot be merged, submit the bio. */ if (bbio && ((i > 0 && !test_bit(i - 1, &stripe->extent_sector_bitmap)) || bbio->bio.bi_iter.bi_size >= stripe_len)) { ASSERT(bbio->bio.bi_iter.bi_size); atomic_inc(&stripe->pending_io); btrfs_submit_bbio(bbio, mirror); bbio = NULL; } if (!bbio) { struct btrfs_io_stripe io_stripe = {}; struct btrfs_io_context *bioc = NULL; const u64 logical = stripe->logical + (i << fs_info->sectorsize_bits); int err; io_stripe.rst_search_commit_root = true; stripe_len = (nr_sectors - i) << fs_info->sectorsize_bits; /* * For RST cases, we need to manually split the bbio to * follow the RST boundary. */ err = btrfs_map_block(fs_info, BTRFS_MAP_READ, logical, &stripe_len, &bioc, &io_stripe, &mirror); btrfs_put_bioc(bioc); if (err < 0) { if (err != -ENODATA) { /* * Earlier btrfs_get_raid_extent_offset() * returned -ENODATA, which means there's * no entry for the corresponding range * in the stripe tree. But if it's in * the extent tree, then it's a preallocated * extent and not an error. */ set_bit(i, &stripe->io_error_bitmap); set_bit(i, &stripe->error_bitmap); } continue; } bbio = btrfs_bio_alloc(stripe->nr_sectors, REQ_OP_READ, fs_info, scrub_read_endio, stripe); bbio->bio.bi_iter.bi_sector = logical >> SECTOR_SHIFT; } __bio_add_page(&bbio->bio, page, fs_info->sectorsize, pgoff); } if (bbio) { ASSERT(bbio->bio.bi_iter.bi_size); atomic_inc(&stripe->pending_io); btrfs_submit_bbio(bbio, mirror); } if (atomic_dec_and_test(&stripe->pending_io)) { wake_up(&stripe->io_wait); INIT_WORK(&stripe->work, scrub_stripe_read_repair_worker); queue_work(stripe->bg->fs_info->scrub_workers, &stripe->work); } } static void scrub_submit_initial_read(struct scrub_ctx *sctx, struct scrub_stripe *stripe) { struct btrfs_fs_info *fs_info = sctx->fs_info; struct btrfs_bio *bbio; unsigned int nr_sectors = stripe_length(stripe) >> fs_info->sectorsize_bits; int mirror = stripe->mirror_num; ASSERT(stripe->bg); ASSERT(stripe->mirror_num > 0); ASSERT(test_bit(SCRUB_STRIPE_FLAG_INITIALIZED, &stripe->state)); if (btrfs_need_stripe_tree_update(fs_info, stripe->bg->flags)) { scrub_submit_extent_sector_read(stripe); return; } bbio = btrfs_bio_alloc(SCRUB_STRIPE_PAGES, REQ_OP_READ, fs_info, scrub_read_endio, stripe); bbio->bio.bi_iter.bi_sector = stripe->logical >> SECTOR_SHIFT; /* Read the whole range inside the chunk boundary. */ for (unsigned int cur = 0; cur < nr_sectors; cur++) { struct page *page = scrub_stripe_get_page(stripe, cur); unsigned int pgoff = scrub_stripe_get_page_offset(stripe, cur); int ret; ret = bio_add_page(&bbio->bio, page, fs_info->sectorsize, pgoff); /* We should have allocated enough bio vectors. */ ASSERT(ret == fs_info->sectorsize); } atomic_inc(&stripe->pending_io); /* * For dev-replace, either user asks to avoid the source dev, or * the device is missing, we try the next mirror instead. */ if (sctx->is_dev_replace && (fs_info->dev_replace.cont_reading_from_srcdev_mode == BTRFS_DEV_REPLACE_ITEM_CONT_READING_FROM_SRCDEV_MODE_AVOID || !stripe->dev->bdev)) { int num_copies = btrfs_num_copies(fs_info, stripe->bg->start, stripe->bg->length); mirror = calc_next_mirror(mirror, num_copies); } btrfs_submit_bbio(bbio, mirror); } static bool stripe_has_metadata_error(struct scrub_stripe *stripe) { int i; for_each_set_bit(i, &stripe->error_bitmap, stripe->nr_sectors) { if (stripe->sectors[i].is_metadata) { struct btrfs_fs_info *fs_info = stripe->bg->fs_info; btrfs_err(fs_info, "stripe %llu has unrepaired metadata sector at %llu", stripe->logical, stripe->logical + (i << fs_info->sectorsize_bits)); return true; } } return false; } static void submit_initial_group_read(struct scrub_ctx *sctx, unsigned int first_slot, unsigned int nr_stripes) { struct blk_plug plug; ASSERT(first_slot < SCRUB_TOTAL_STRIPES); ASSERT(first_slot + nr_stripes <= SCRUB_TOTAL_STRIPES); scrub_throttle_dev_io(sctx, sctx->stripes[0].dev, btrfs_stripe_nr_to_offset(nr_stripes)); blk_start_plug(&plug); for (int i = 0; i < nr_stripes; i++) { struct scrub_stripe *stripe = &sctx->stripes[first_slot + i]; /* Those stripes should be initialized. */ ASSERT(test_bit(SCRUB_STRIPE_FLAG_INITIALIZED, &stripe->state)); scrub_submit_initial_read(sctx, stripe); } blk_finish_plug(&plug); } static int flush_scrub_stripes(struct scrub_ctx *sctx) { struct btrfs_fs_info *fs_info = sctx->fs_info; struct scrub_stripe *stripe; const int nr_stripes = sctx->cur_stripe; int ret = 0; if (!nr_stripes) return 0; ASSERT(test_bit(SCRUB_STRIPE_FLAG_INITIALIZED, &sctx->stripes[0].state)); /* Submit the stripes which are populated but not submitted. */ if (nr_stripes % SCRUB_STRIPES_PER_GROUP) { const int first_slot = round_down(nr_stripes, SCRUB_STRIPES_PER_GROUP); submit_initial_group_read(sctx, first_slot, nr_stripes - first_slot); } for (int i = 0; i < nr_stripes; i++) { stripe = &sctx->stripes[i]; wait_event(stripe->repair_wait, test_bit(SCRUB_STRIPE_FLAG_REPAIR_DONE, &stripe->state)); } /* Submit for dev-replace. */ if (sctx->is_dev_replace) { /* * For dev-replace, if we know there is something wrong with * metadata, we should immediately abort. */ for (int i = 0; i < nr_stripes; i++) { if (stripe_has_metadata_error(&sctx->stripes[i])) { ret = -EIO; goto out; } } for (int i = 0; i < nr_stripes; i++) { unsigned long good; stripe = &sctx->stripes[i]; ASSERT(stripe->dev == fs_info->dev_replace.srcdev); bitmap_andnot(&good, &stripe->extent_sector_bitmap, &stripe->error_bitmap, stripe->nr_sectors); scrub_write_sectors(sctx, stripe, good, true); } } /* Wait for the above writebacks to finish. */ for (int i = 0; i < nr_stripes; i++) { stripe = &sctx->stripes[i]; wait_scrub_stripe_io(stripe); spin_lock(&sctx->stat_lock); sctx->stat.last_physical = stripe->physical + stripe_length(stripe); spin_unlock(&sctx->stat_lock); scrub_reset_stripe(stripe); } out: sctx->cur_stripe = 0; return ret; } static void raid56_scrub_wait_endio(struct bio *bio) { complete(bio->bi_private); } static int queue_scrub_stripe(struct scrub_ctx *sctx, struct btrfs_block_group *bg, struct btrfs_device *dev, int mirror_num, u64 logical, u32 length, u64 physical, u64 *found_logical_ret) { struct scrub_stripe *stripe; int ret; /* * There should always be one slot left, as caller filling the last * slot should flush them all. */ ASSERT(sctx->cur_stripe < SCRUB_TOTAL_STRIPES); /* @found_logical_ret must be specified. */ ASSERT(found_logical_ret); stripe = &sctx->stripes[sctx->cur_stripe]; scrub_reset_stripe(stripe); ret = scrub_find_fill_first_stripe(bg, &sctx->extent_path, &sctx->csum_path, dev, physical, mirror_num, logical, length, stripe); /* Either >0 as no more extents or <0 for error. */ if (ret) return ret; *found_logical_ret = stripe->logical; sctx->cur_stripe++; /* We filled one group, submit it. */ if (sctx->cur_stripe % SCRUB_STRIPES_PER_GROUP == 0) { const int first_slot = sctx->cur_stripe - SCRUB_STRIPES_PER_GROUP; submit_initial_group_read(sctx, first_slot, SCRUB_STRIPES_PER_GROUP); } /* Last slot used, flush them all. */ if (sctx->cur_stripe == SCRUB_TOTAL_STRIPES) return flush_scrub_stripes(sctx); return 0; } static int scrub_raid56_parity_stripe(struct scrub_ctx *sctx, struct btrfs_device *scrub_dev, struct btrfs_block_group *bg, struct btrfs_chunk_map *map, u64 full_stripe_start) { DECLARE_COMPLETION_ONSTACK(io_done); struct btrfs_fs_info *fs_info = sctx->fs_info; struct btrfs_raid_bio *rbio; struct btrfs_io_context *bioc = NULL; struct btrfs_path extent_path = { 0 }; struct btrfs_path csum_path = { 0 }; struct bio *bio; struct scrub_stripe *stripe; bool all_empty = true; const int data_stripes = nr_data_stripes(map); unsigned long extent_bitmap = 0; u64 length = btrfs_stripe_nr_to_offset(data_stripes); int ret; ASSERT(sctx->raid56_data_stripes); /* * For data stripe search, we cannot reuse the same extent/csum paths, * as the data stripe bytenr may be smaller than previous extent. Thus * we have to use our own extent/csum paths. */ extent_path.search_commit_root = 1; extent_path.skip_locking = 1; csum_path.search_commit_root = 1; csum_path.skip_locking = 1; for (int i = 0; i < data_stripes; i++) { int stripe_index; int rot; u64 physical; stripe = &sctx->raid56_data_stripes[i]; rot = div_u64(full_stripe_start - bg->start, data_stripes) >> BTRFS_STRIPE_LEN_SHIFT; stripe_index = (i + rot) % map->num_stripes; physical = map->stripes[stripe_index].physical + btrfs_stripe_nr_to_offset(rot); scrub_reset_stripe(stripe); set_bit(SCRUB_STRIPE_FLAG_NO_REPORT, &stripe->state); ret = scrub_find_fill_first_stripe(bg, &extent_path, &csum_path, map->stripes[stripe_index].dev, physical, 1, full_stripe_start + btrfs_stripe_nr_to_offset(i), BTRFS_STRIPE_LEN, stripe); if (ret < 0) goto out; /* * No extent in this data stripe, need to manually mark them * initialized to make later read submission happy. */ if (ret > 0) { stripe->logical = full_stripe_start + btrfs_stripe_nr_to_offset(i); stripe->dev = map->stripes[stripe_index].dev; stripe->mirror_num = 1; set_bit(SCRUB_STRIPE_FLAG_INITIALIZED, &stripe->state); } } /* Check if all data stripes are empty. */ for (int i = 0; i < data_stripes; i++) { stripe = &sctx->raid56_data_stripes[i]; if (!bitmap_empty(&stripe->extent_sector_bitmap, stripe->nr_sectors)) { all_empty = false; break; } } if (all_empty) { ret = 0; goto out; } for (int i = 0; i < data_stripes; i++) { stripe = &sctx->raid56_data_stripes[i]; scrub_submit_initial_read(sctx, stripe); } for (int i = 0; i < data_stripes; i++) { stripe = &sctx->raid56_data_stripes[i]; wait_event(stripe->repair_wait, test_bit(SCRUB_STRIPE_FLAG_REPAIR_DONE, &stripe->state)); } /* For now, no zoned support for RAID56. */ ASSERT(!btrfs_is_zoned(sctx->fs_info)); /* * Now all data stripes are properly verified. Check if we have any * unrepaired, if so abort immediately or we could further corrupt the * P/Q stripes. * * During the loop, also populate extent_bitmap. */ for (int i = 0; i < data_stripes; i++) { unsigned long error; stripe = &sctx->raid56_data_stripes[i]; /* * We should only check the errors where there is an extent. * As we may hit an empty data stripe while it's missing. */ bitmap_and(&error, &stripe->error_bitmap, &stripe->extent_sector_bitmap, stripe->nr_sectors); if (!bitmap_empty(&error, stripe->nr_sectors)) { btrfs_err(fs_info, "unrepaired sectors detected, full stripe %llu data stripe %u errors %*pbl", full_stripe_start, i, stripe->nr_sectors, &error); ret = -EIO; goto out; } bitmap_or(&extent_bitmap, &extent_bitmap, &stripe->extent_sector_bitmap, stripe->nr_sectors); } /* Now we can check and regenerate the P/Q stripe. */ bio = bio_alloc(NULL, 1, REQ_OP_READ, GFP_NOFS); bio->bi_iter.bi_sector = full_stripe_start >> SECTOR_SHIFT; bio->bi_private = &io_done; bio->bi_end_io = raid56_scrub_wait_endio; btrfs_bio_counter_inc_blocked(fs_info); ret = btrfs_map_block(fs_info, BTRFS_MAP_WRITE, full_stripe_start, &length, &bioc, NULL, NULL); if (ret < 0) { btrfs_put_bioc(bioc); btrfs_bio_counter_dec(fs_info); goto out; } rbio = raid56_parity_alloc_scrub_rbio(bio, bioc, scrub_dev, &extent_bitmap, BTRFS_STRIPE_LEN >> fs_info->sectorsize_bits); btrfs_put_bioc(bioc); if (!rbio) { ret = -ENOMEM; btrfs_bio_counter_dec(fs_info); goto out; } /* Use the recovered stripes as cache to avoid read them from disk again. */ for (int i = 0; i < data_stripes; i++) { stripe = &sctx->raid56_data_stripes[i]; raid56_parity_cache_data_pages(rbio, stripe->pages, full_stripe_start + (i << BTRFS_STRIPE_LEN_SHIFT)); } raid56_parity_submit_scrub_rbio(rbio); wait_for_completion_io(&io_done); ret = blk_status_to_errno(bio->bi_status); bio_put(bio); btrfs_bio_counter_dec(fs_info); btrfs_release_path(&extent_path); btrfs_release_path(&csum_path); out: return ret; } /* * Scrub one range which can only has simple mirror based profile. * (Including all range in SINGLE/DUP/RAID1/RAID1C*, and each stripe in * RAID0/RAID10). * * Since we may need to handle a subset of block group, we need @logical_start * and @logical_length parameter. */ static int scrub_simple_mirror(struct scrub_ctx *sctx, struct btrfs_block_group *bg, u64 logical_start, u64 logical_length, struct btrfs_device *device, u64 physical, int mirror_num) { struct btrfs_fs_info *fs_info = sctx->fs_info; const u64 logical_end = logical_start + logical_length; u64 cur_logical = logical_start; int ret = 0; /* The range must be inside the bg */ ASSERT(logical_start >= bg->start && logical_end <= bg->start + bg->length); /* Go through each extent items inside the logical range */ while (cur_logical < logical_end) { u64 found_logical = U64_MAX; u64 cur_physical = physical + cur_logical - logical_start; /* Canceled? */ if (atomic_read(&fs_info->scrub_cancel_req) || atomic_read(&sctx->cancel_req)) { ret = -ECANCELED; break; } /* Paused? */ if (atomic_read(&fs_info->scrub_pause_req)) { /* Push queued extents */ scrub_blocked_if_needed(fs_info); } /* Block group removed? */ spin_lock(&bg->lock); if (test_bit(BLOCK_GROUP_FLAG_REMOVED, &bg->runtime_flags)) { spin_unlock(&bg->lock); ret = 0; break; } spin_unlock(&bg->lock); ret = queue_scrub_stripe(sctx, bg, device, mirror_num, cur_logical, logical_end - cur_logical, cur_physical, &found_logical); if (ret > 0) { /* No more extent, just update the accounting */ spin_lock(&sctx->stat_lock); sctx->stat.last_physical = physical + logical_length; spin_unlock(&sctx->stat_lock); ret = 0; break; } if (ret < 0) break; /* queue_scrub_stripe() returned 0, @found_logical must be updated. */ ASSERT(found_logical != U64_MAX); cur_logical = found_logical + BTRFS_STRIPE_LEN; /* Don't hold CPU for too long time */ cond_resched(); } return ret; } /* Calculate the full stripe length for simple stripe based profiles */ static u64 simple_stripe_full_stripe_len(const struct btrfs_chunk_map *map) { ASSERT(map->type & (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID10)); return btrfs_stripe_nr_to_offset(map->num_stripes / map->sub_stripes); } /* Get the logical bytenr for the stripe */ static u64 simple_stripe_get_logical(struct btrfs_chunk_map *map, struct btrfs_block_group *bg, int stripe_index) { ASSERT(map->type & (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID10)); ASSERT(stripe_index < map->num_stripes); /* * (stripe_index / sub_stripes) gives how many data stripes we need to * skip. */ return btrfs_stripe_nr_to_offset(stripe_index / map->sub_stripes) + bg->start; } /* Get the mirror number for the stripe */ static int simple_stripe_mirror_num(struct btrfs_chunk_map *map, int stripe_index) { ASSERT(map->type & (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID10)); ASSERT(stripe_index < map->num_stripes); /* For RAID0, it's fixed to 1, for RAID10 it's 0,1,0,1... */ return stripe_index % map->sub_stripes + 1; } static int scrub_simple_stripe(struct scrub_ctx *sctx, struct btrfs_block_group *bg, struct btrfs_chunk_map *map, struct btrfs_device *device, int stripe_index) { const u64 logical_increment = simple_stripe_full_stripe_len(map); const u64 orig_logical = simple_stripe_get_logical(map, bg, stripe_index); const u64 orig_physical = map->stripes[stripe_index].physical; const int mirror_num = simple_stripe_mirror_num(map, stripe_index); u64 cur_logical = orig_logical; u64 cur_physical = orig_physical; int ret = 0; while (cur_logical < bg->start + bg->length) { /* * Inside each stripe, RAID0 is just SINGLE, and RAID10 is * just RAID1, so we can reuse scrub_simple_mirror() to scrub * this stripe. */ ret = scrub_simple_mirror(sctx, bg, cur_logical, BTRFS_STRIPE_LEN, device, cur_physical, mirror_num); if (ret) return ret; /* Skip to next stripe which belongs to the target device */ cur_logical += logical_increment; /* For physical offset, we just go to next stripe */ cur_physical += BTRFS_STRIPE_LEN; } return ret; } static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, struct btrfs_block_group *bg, struct btrfs_chunk_map *map, struct btrfs_device *scrub_dev, int stripe_index) { struct btrfs_fs_info *fs_info = sctx->fs_info; const u64 profile = map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK; const u64 chunk_logical = bg->start; int ret; int ret2; u64 physical = map->stripes[stripe_index].physical; const u64 dev_stripe_len = btrfs_calc_stripe_length(map); const u64 physical_end = physical + dev_stripe_len; u64 logical; u64 logic_end; /* The logical increment after finishing one stripe */ u64 increment; /* Offset inside the chunk */ u64 offset; u64 stripe_logical; /* Extent_path should be released by now. */ ASSERT(sctx->extent_path.nodes[0] == NULL); scrub_blocked_if_needed(fs_info); if (sctx->is_dev_replace && btrfs_dev_is_sequential(sctx->wr_tgtdev, physical)) { mutex_lock(&sctx->wr_lock); sctx->write_pointer = physical; mutex_unlock(&sctx->wr_lock); } /* Prepare the extra data stripes used by RAID56. */ if (profile & BTRFS_BLOCK_GROUP_RAID56_MASK) { ASSERT(sctx->raid56_data_stripes == NULL); sctx->raid56_data_stripes = kcalloc(nr_data_stripes(map), sizeof(struct scrub_stripe), GFP_KERNEL); if (!sctx->raid56_data_stripes) { ret = -ENOMEM; goto out; } for (int i = 0; i < nr_data_stripes(map); i++) { ret = init_scrub_stripe(fs_info, &sctx->raid56_data_stripes[i]); if (ret < 0) goto out; sctx->raid56_data_stripes[i].bg = bg; sctx->raid56_data_stripes[i].sctx = sctx; } } /* * There used to be a big double loop to handle all profiles using the * same routine, which grows larger and more gross over time. * * So here we handle each profile differently, so simpler profiles * have simpler scrubbing function. */ if (!(profile & (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID10 | BTRFS_BLOCK_GROUP_RAID56_MASK))) { /* * Above check rules out all complex profile, the remaining * profiles are SINGLE|DUP|RAID1|RAID1C*, which is simple * mirrored duplication without stripe. * * Only @physical and @mirror_num needs to calculated using * @stripe_index. */ ret = scrub_simple_mirror(sctx, bg, bg->start, bg->length, scrub_dev, map->stripes[stripe_index].physical, stripe_index + 1); offset = 0; goto out; } if (profile & (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID10)) { ret = scrub_simple_stripe(sctx, bg, map, scrub_dev, stripe_index); offset = btrfs_stripe_nr_to_offset(stripe_index / map->sub_stripes); goto out; } /* Only RAID56 goes through the old code */ ASSERT(map->type & BTRFS_BLOCK_GROUP_RAID56_MASK); ret = 0; /* Calculate the logical end of the stripe */ get_raid56_logic_offset(physical_end, stripe_index, map, &logic_end, NULL); logic_end += chunk_logical; /* Initialize @offset in case we need to go to out: label */ get_raid56_logic_offset(physical, stripe_index, map, &offset, NULL); increment = btrfs_stripe_nr_to_offset(nr_data_stripes(map)); /* * Due to the rotation, for RAID56 it's better to iterate each stripe * using their physical offset. */ while (physical < physical_end) { ret = get_raid56_logic_offset(physical, stripe_index, map, &logical, &stripe_logical); logical += chunk_logical; if (ret) { /* it is parity strip */ stripe_logical += chunk_logical; ret = scrub_raid56_parity_stripe(sctx, scrub_dev, bg, map, stripe_logical); spin_lock(&sctx->stat_lock); sctx->stat.last_physical = min(physical + BTRFS_STRIPE_LEN, physical_end); spin_unlock(&sctx->stat_lock); if (ret) goto out; goto next; } /* * Now we're at a data stripe, scrub each extents in the range. * * At this stage, if we ignore the repair part, inside each data * stripe it is no different than SINGLE profile. * We can reuse scrub_simple_mirror() here, as the repair part * is still based on @mirror_num. */ ret = scrub_simple_mirror(sctx, bg, logical, BTRFS_STRIPE_LEN, scrub_dev, physical, 1); if (ret < 0) goto out; next: logical += increment; physical += BTRFS_STRIPE_LEN; spin_lock(&sctx->stat_lock); sctx->stat.last_physical = physical; spin_unlock(&sctx->stat_lock); } out: ret2 = flush_scrub_stripes(sctx); if (!ret) ret = ret2; btrfs_release_path(&sctx->extent_path); btrfs_release_path(&sctx->csum_path); if (sctx->raid56_data_stripes) { for (int i = 0; i < nr_data_stripes(map); i++) release_scrub_stripe(&sctx->raid56_data_stripes[i]); kfree(sctx->raid56_data_stripes); sctx->raid56_data_stripes = NULL; } if (sctx->is_dev_replace && ret >= 0) { int ret2; ret2 = sync_write_pointer_for_zoned(sctx, chunk_logical + offset, map->stripes[stripe_index].physical, physical_end); if (ret2) ret = ret2; } return ret < 0 ? ret : 0; } static noinline_for_stack int scrub_chunk(struct scrub_ctx *sctx, struct btrfs_block_group *bg, struct btrfs_device *scrub_dev, u64 dev_offset, u64 dev_extent_len) { struct btrfs_fs_info *fs_info = sctx->fs_info; struct btrfs_chunk_map *map; int i; int ret = 0; map = btrfs_find_chunk_map(fs_info, bg->start, bg->length); if (!map) { /* * Might have been an unused block group deleted by the cleaner * kthread or relocation. */ spin_lock(&bg->lock); if (!test_bit(BLOCK_GROUP_FLAG_REMOVED, &bg->runtime_flags)) ret = -EINVAL; spin_unlock(&bg->lock); return ret; } if (map->start != bg->start) goto out; if (map->chunk_len < dev_extent_len) goto out; for (i = 0; i < map->num_stripes; ++i) { if (map->stripes[i].dev->bdev == scrub_dev->bdev && map->stripes[i].physical == dev_offset) { ret = scrub_stripe(sctx, bg, map, scrub_dev, i); if (ret) goto out; } } out: btrfs_free_chunk_map(map); return ret; } static int finish_extent_writes_for_zoned(struct btrfs_root *root, struct btrfs_block_group *cache) { struct btrfs_fs_info *fs_info = cache->fs_info; if (!btrfs_is_zoned(fs_info)) return 0; btrfs_wait_block_group_reservations(cache); btrfs_wait_nocow_writers(cache); btrfs_wait_ordered_roots(fs_info, U64_MAX, cache); return btrfs_commit_current_transaction(root); } static noinline_for_stack int scrub_enumerate_chunks(struct scrub_ctx *sctx, struct btrfs_device *scrub_dev, u64 start, u64 end) { struct btrfs_dev_extent *dev_extent = NULL; struct btrfs_path *path; struct btrfs_fs_info *fs_info = sctx->fs_info; struct btrfs_root *root = fs_info->dev_root; u64 chunk_offset; int ret = 0; int ro_set; int slot; struct extent_buffer *l; struct btrfs_key key; struct btrfs_key found_key; struct btrfs_block_group *cache; struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace; path = btrfs_alloc_path(); if (!path) return -ENOMEM; path->reada = READA_FORWARD; path->search_commit_root = 1; path->skip_locking = 1; key.objectid = scrub_dev->devid; key.offset = 0ull; key.type = BTRFS_DEV_EXTENT_KEY; while (1) { u64 dev_extent_len; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) break; if (ret > 0) { if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) { ret = btrfs_next_leaf(root, path); if (ret < 0) break; if (ret > 0) { ret = 0; break; } } else { ret = 0; } } l = path->nodes[0]; slot = path->slots[0]; btrfs_item_key_to_cpu(l, &found_key, slot); if (found_key.objectid != scrub_dev->devid) break; if (found_key.type != BTRFS_DEV_EXTENT_KEY) break; if (found_key.offset >= end) break; if (found_key.offset < key.offset) break; dev_extent = btrfs_item_ptr(l, slot, struct btrfs_dev_extent); dev_extent_len = btrfs_dev_extent_length(l, dev_extent); if (found_key.offset + dev_extent_len <= start) goto skip; chunk_offset = btrfs_dev_extent_chunk_offset(l, dev_extent); /* * get a reference on the corresponding block group to prevent * the chunk from going away while we scrub it */ cache = btrfs_lookup_block_group(fs_info, chunk_offset); /* some chunks are removed but not committed to disk yet, * continue scrubbing */ if (!cache) goto skip; ASSERT(cache->start <= chunk_offset); /* * We are using the commit root to search for device extents, so * that means we could have found a device extent item from a * block group that was deleted in the current transaction. The * logical start offset of the deleted block group, stored at * @chunk_offset, might be part of the logical address range of * a new block group (which uses different physical extents). * In this case btrfs_lookup_block_group() has returned the new * block group, and its start address is less than @chunk_offset. * * We skip such new block groups, because it's pointless to * process them, as we won't find their extents because we search * for them using the commit root of the extent tree. For a device * replace it's also fine to skip it, we won't miss copying them * to the target device because we have the write duplication * setup through the regular write path (by btrfs_map_block()), * and we have committed a transaction when we started the device * replace, right after setting up the device replace state. */ if (cache->start < chunk_offset) { btrfs_put_block_group(cache); goto skip; } if (sctx->is_dev_replace && btrfs_is_zoned(fs_info)) { if (!test_bit(BLOCK_GROUP_FLAG_TO_COPY, &cache->runtime_flags)) { btrfs_put_block_group(cache); goto skip; } } /* * Make sure that while we are scrubbing the corresponding block * group doesn't get its logical address and its device extents * reused for another block group, which can possibly be of a * different type and different profile. We do this to prevent * false error detections and crashes due to bogus attempts to * repair extents. */ spin_lock(&cache->lock); if (test_bit(BLOCK_GROUP_FLAG_REMOVED, &cache->runtime_flags)) { spin_unlock(&cache->lock); btrfs_put_block_group(cache); goto skip; } btrfs_freeze_block_group(cache); spin_unlock(&cache->lock); /* * we need call btrfs_inc_block_group_ro() with scrubs_paused, * to avoid deadlock caused by: * btrfs_inc_block_group_ro() * -> btrfs_wait_for_commit() * -> btrfs_commit_transaction() * -> btrfs_scrub_pause() */ scrub_pause_on(fs_info); /* * Don't do chunk preallocation for scrub. * * This is especially important for SYSTEM bgs, or we can hit * -EFBIG from btrfs_finish_chunk_alloc() like: * 1. The only SYSTEM bg is marked RO. * Since SYSTEM bg is small, that's pretty common. * 2. New SYSTEM bg will be allocated * Due to regular version will allocate new chunk. * 3. New SYSTEM bg is empty and will get cleaned up * Before cleanup really happens, it's marked RO again. * 4. Empty SYSTEM bg get scrubbed * We go back to 2. * * This can easily boost the amount of SYSTEM chunks if cleaner * thread can't be triggered fast enough, and use up all space * of btrfs_super_block::sys_chunk_array * * While for dev replace, we need to try our best to mark block * group RO, to prevent race between: * - Write duplication * Contains latest data * - Scrub copy * Contains data from commit tree * * If target block group is not marked RO, nocow writes can * be overwritten by scrub copy, causing data corruption. * So for dev-replace, it's not allowed to continue if a block * group is not RO. */ ret = btrfs_inc_block_group_ro(cache, sctx->is_dev_replace); if (!ret && sctx->is_dev_replace) { ret = finish_extent_writes_for_zoned(root, cache); if (ret) { btrfs_dec_block_group_ro(cache); scrub_pause_off(fs_info); btrfs_put_block_group(cache); break; } } if (ret == 0) { ro_set = 1; } else if (ret == -ENOSPC && !sctx->is_dev_replace && !(cache->flags & BTRFS_BLOCK_GROUP_RAID56_MASK)) { /* * btrfs_inc_block_group_ro return -ENOSPC when it * failed in creating new chunk for metadata. * It is not a problem for scrub, because * metadata are always cowed, and our scrub paused * commit_transactions. * * For RAID56 chunks, we have to mark them read-only * for scrub, as later we would use our own cache * out of RAID56 realm. * Thus we want the RAID56 bg to be marked RO to * prevent RMW from screwing up out cache. */ ro_set = 0; } else if (ret == -ETXTBSY) { btrfs_warn(fs_info, "skipping scrub of block group %llu due to active swapfile", cache->start); scrub_pause_off(fs_info); ret = 0; goto skip_unfreeze; } else { btrfs_warn(fs_info, "failed setting block group ro: %d", ret); btrfs_unfreeze_block_group(cache); btrfs_put_block_group(cache); scrub_pause_off(fs_info); break; } /* * Now the target block is marked RO, wait for nocow writes to * finish before dev-replace. * COW is fine, as COW never overwrites extents in commit tree. */ if (sctx->is_dev_replace) { btrfs_wait_nocow_writers(cache); btrfs_wait_ordered_roots(fs_info, U64_MAX, cache); } scrub_pause_off(fs_info); down_write(&dev_replace->rwsem); dev_replace->cursor_right = found_key.offset + dev_extent_len; dev_replace->cursor_left = found_key.offset; dev_replace->item_needs_writeback = 1; up_write(&dev_replace->rwsem); ret = scrub_chunk(sctx, cache, scrub_dev, found_key.offset, dev_extent_len); if (sctx->is_dev_replace && !btrfs_finish_block_group_to_copy(dev_replace->srcdev, cache, found_key.offset)) ro_set = 0; down_write(&dev_replace->rwsem); dev_replace->cursor_left = dev_replace->cursor_right; dev_replace->item_needs_writeback = 1; up_write(&dev_replace->rwsem); if (ro_set) btrfs_dec_block_group_ro(cache); /* * We might have prevented the cleaner kthread from deleting * this block group if it was already unused because we raced * and set it to RO mode first. So add it back to the unused * list, otherwise it might not ever be deleted unless a manual * balance is triggered or it becomes used and unused again. */ spin_lock(&cache->lock); if (!test_bit(BLOCK_GROUP_FLAG_REMOVED, &cache->runtime_flags) && !cache->ro && cache->reserved == 0 && cache->used == 0) { spin_unlock(&cache->lock); if (btrfs_test_opt(fs_info, DISCARD_ASYNC)) btrfs_discard_queue_work(&fs_info->discard_ctl, cache); else btrfs_mark_bg_unused(cache); } else { spin_unlock(&cache->lock); } skip_unfreeze: btrfs_unfreeze_block_group(cache); btrfs_put_block_group(cache); if (ret) break; if (sctx->is_dev_replace && atomic64_read(&dev_replace->num_write_errors) > 0) { ret = -EIO; break; } if (sctx->stat.malloc_errors > 0) { ret = -ENOMEM; break; } skip: key.offset = found_key.offset + dev_extent_len; btrfs_release_path(path); } btrfs_free_path(path); return ret; } static int scrub_one_super(struct scrub_ctx *sctx, struct btrfs_device *dev, struct page *page, u64 physical, u64 generation) { struct btrfs_fs_info *fs_info = sctx->fs_info; struct bio_vec bvec; struct bio bio; struct btrfs_super_block *sb = page_address(page); int ret; bio_init(&bio, dev->bdev, &bvec, 1, REQ_OP_READ); bio.bi_iter.bi_sector = physical >> SECTOR_SHIFT; __bio_add_page(&bio, page, BTRFS_SUPER_INFO_SIZE, 0); ret = submit_bio_wait(&bio); bio_uninit(&bio); if (ret < 0) return ret; ret = btrfs_check_super_csum(fs_info, sb); if (ret != 0) { btrfs_err_rl(fs_info, "super block at physical %llu devid %llu has bad csum", physical, dev->devid); return -EIO; } if (btrfs_super_generation(sb) != generation) { btrfs_err_rl(fs_info, "super block at physical %llu devid %llu has bad generation %llu expect %llu", physical, dev->devid, btrfs_super_generation(sb), generation); return -EUCLEAN; } return btrfs_validate_super(fs_info, sb, -1); } static noinline_for_stack int scrub_supers(struct scrub_ctx *sctx, struct btrfs_device *scrub_dev) { int i; u64 bytenr; u64 gen; int ret = 0; struct page *page; struct btrfs_fs_info *fs_info = sctx->fs_info; if (BTRFS_FS_ERROR(fs_info)) return -EROFS; page = alloc_page(GFP_KERNEL); if (!page) { spin_lock(&sctx->stat_lock); sctx->stat.malloc_errors++; spin_unlock(&sctx->stat_lock); return -ENOMEM; } /* Seed devices of a new filesystem has their own generation. */ if (scrub_dev->fs_devices != fs_info->fs_devices) gen = scrub_dev->generation; else gen = btrfs_get_last_trans_committed(fs_info); for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) { ret = btrfs_sb_log_location(scrub_dev, i, 0, &bytenr); if (ret == -ENOENT) break; if (ret) { spin_lock(&sctx->stat_lock); sctx->stat.super_errors++; spin_unlock(&sctx->stat_lock); continue; } if (bytenr + BTRFS_SUPER_INFO_SIZE > scrub_dev->commit_total_bytes) break; if (!btrfs_check_super_location(scrub_dev, bytenr)) continue; ret = scrub_one_super(sctx, scrub_dev, page, bytenr, gen); if (ret) { spin_lock(&sctx->stat_lock); sctx->stat.super_errors++; spin_unlock(&sctx->stat_lock); } } __free_page(page); return 0; } static void scrub_workers_put(struct btrfs_fs_info *fs_info) { if (refcount_dec_and_mutex_lock(&fs_info->scrub_workers_refcnt, &fs_info->scrub_lock)) { struct workqueue_struct *scrub_workers = fs_info->scrub_workers; fs_info->scrub_workers = NULL; mutex_unlock(&fs_info->scrub_lock); if (scrub_workers) destroy_workqueue(scrub_workers); } } /* * get a reference count on fs_info->scrub_workers. start worker if necessary */ static noinline_for_stack int scrub_workers_get(struct btrfs_fs_info *fs_info) { struct workqueue_struct *scrub_workers = NULL; unsigned int flags = WQ_FREEZABLE | WQ_UNBOUND; int max_active = fs_info->thread_pool_size; int ret = -ENOMEM; if (refcount_inc_not_zero(&fs_info->scrub_workers_refcnt)) return 0; scrub_workers = alloc_workqueue("btrfs-scrub", flags, max_active); if (!scrub_workers) return -ENOMEM; mutex_lock(&fs_info->scrub_lock); if (refcount_read(&fs_info->scrub_workers_refcnt) == 0) { ASSERT(fs_info->scrub_workers == NULL); fs_info->scrub_workers = scrub_workers; refcount_set(&fs_info->scrub_workers_refcnt, 1); mutex_unlock(&fs_info->scrub_lock); return 0; } /* Other thread raced in and created the workers for us */ refcount_inc(&fs_info->scrub_workers_refcnt); mutex_unlock(&fs_info->scrub_lock); ret = 0; destroy_workqueue(scrub_workers); return ret; } int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start, u64 end, struct btrfs_scrub_progress *progress, int readonly, int is_dev_replace) { struct btrfs_dev_lookup_args args = { .devid = devid }; struct scrub_ctx *sctx; int ret; struct btrfs_device *dev; unsigned int nofs_flag; bool need_commit = false; if (btrfs_fs_closing(fs_info)) return -EAGAIN; /* At mount time we have ensured nodesize is in the range of [4K, 64K]. */ ASSERT(fs_info->nodesize <= BTRFS_STRIPE_LEN); /* * SCRUB_MAX_SECTORS_PER_BLOCK is calculated using the largest possible * value (max nodesize / min sectorsize), thus nodesize should always * be fine. */ ASSERT(fs_info->nodesize <= SCRUB_MAX_SECTORS_PER_BLOCK << fs_info->sectorsize_bits); /* Allocate outside of device_list_mutex */ sctx = scrub_setup_ctx(fs_info, is_dev_replace); if (IS_ERR(sctx)) return PTR_ERR(sctx); ret = scrub_workers_get(fs_info); if (ret) goto out_free_ctx; mutex_lock(&fs_info->fs_devices->device_list_mutex); dev = btrfs_find_device(fs_info->fs_devices, &args); if (!dev || (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state) && !is_dev_replace)) { mutex_unlock(&fs_info->fs_devices->device_list_mutex); ret = -ENODEV; goto out; } if (!is_dev_replace && !readonly && !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) { mutex_unlock(&fs_info->fs_devices->device_list_mutex); btrfs_err_in_rcu(fs_info, "scrub on devid %llu: filesystem on %s is not writable", devid, btrfs_dev_name(dev)); ret = -EROFS; goto out; } mutex_lock(&fs_info->scrub_lock); if (!test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &dev->dev_state) || test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &dev->dev_state)) { mutex_unlock(&fs_info->scrub_lock); mutex_unlock(&fs_info->fs_devices->device_list_mutex); ret = -EIO; goto out; } down_read(&fs_info->dev_replace.rwsem); if (dev->scrub_ctx || (!is_dev_replace && btrfs_dev_replace_is_ongoing(&fs_info->dev_replace))) { up_read(&fs_info->dev_replace.rwsem); mutex_unlock(&fs_info->scrub_lock); mutex_unlock(&fs_info->fs_devices->device_list_mutex); ret = -EINPROGRESS; goto out; } up_read(&fs_info->dev_replace.rwsem); sctx->readonly = readonly; dev->scrub_ctx = sctx; mutex_unlock(&fs_info->fs_devices->device_list_mutex); /* * checking @scrub_pause_req here, we can avoid * race between committing transaction and scrubbing. */ __scrub_blocked_if_needed(fs_info); atomic_inc(&fs_info->scrubs_running); mutex_unlock(&fs_info->scrub_lock); /* * In order to avoid deadlock with reclaim when there is a transaction * trying to pause scrub, make sure we use GFP_NOFS for all the * allocations done at btrfs_scrub_sectors() and scrub_sectors_for_parity() * invoked by our callees. The pausing request is done when the * transaction commit starts, and it blocks the transaction until scrub * is paused (done at specific points at scrub_stripe() or right above * before incrementing fs_info->scrubs_running). */ nofs_flag = memalloc_nofs_save(); if (!is_dev_replace) { u64 old_super_errors; spin_lock(&sctx->stat_lock); old_super_errors = sctx->stat.super_errors; spin_unlock(&sctx->stat_lock); btrfs_info(fs_info, "scrub: started on devid %llu", devid); /* * by holding device list mutex, we can * kick off writing super in log tree sync. */ mutex_lock(&fs_info->fs_devices->device_list_mutex); ret = scrub_supers(sctx, dev); mutex_unlock(&fs_info->fs_devices->device_list_mutex); spin_lock(&sctx->stat_lock); /* * Super block errors found, but we can not commit transaction * at current context, since btrfs_commit_transaction() needs * to pause the current running scrub (hold by ourselves). */ if (sctx->stat.super_errors > old_super_errors && !sctx->readonly) need_commit = true; spin_unlock(&sctx->stat_lock); } if (!ret) ret = scrub_enumerate_chunks(sctx, dev, start, end); memalloc_nofs_restore(nofs_flag); atomic_dec(&fs_info->scrubs_running); wake_up(&fs_info->scrub_pause_wait); if (progress) memcpy(progress, &sctx->stat, sizeof(*progress)); if (!is_dev_replace) btrfs_info(fs_info, "scrub: %s on devid %llu with status: %d", ret ? "not finished" : "finished", devid, ret); mutex_lock(&fs_info->scrub_lock); dev->scrub_ctx = NULL; mutex_unlock(&fs_info->scrub_lock); scrub_workers_put(fs_info); scrub_put_ctx(sctx); /* * We found some super block errors before, now try to force a * transaction commit, as scrub has finished. */ if (need_commit) { struct btrfs_trans_handle *trans; trans = btrfs_start_transaction(fs_info->tree_root, 0); if (IS_ERR(trans)) { ret = PTR_ERR(trans); btrfs_err(fs_info, "scrub: failed to start transaction to fix super block errors: %d", ret); return ret; } ret = btrfs_commit_transaction(trans); if (ret < 0) btrfs_err(fs_info, "scrub: failed to commit transaction to fix super block errors: %d", ret); } return ret; out: scrub_workers_put(fs_info); out_free_ctx: scrub_free_ctx(sctx); return ret; } void btrfs_scrub_pause(struct btrfs_fs_info *fs_info) { mutex_lock(&fs_info->scrub_lock); atomic_inc(&fs_info->scrub_pause_req); while (atomic_read(&fs_info->scrubs_paused) != atomic_read(&fs_info->scrubs_running)) { mutex_unlock(&fs_info->scrub_lock); wait_event(fs_info->scrub_pause_wait, atomic_read(&fs_info->scrubs_paused) == atomic_read(&fs_info->scrubs_running)); mutex_lock(&fs_info->scrub_lock); } mutex_unlock(&fs_info->scrub_lock); } void btrfs_scrub_continue(struct btrfs_fs_info *fs_info) { atomic_dec(&fs_info->scrub_pause_req); wake_up(&fs_info->scrub_pause_wait); } int btrfs_scrub_cancel(struct btrfs_fs_info *fs_info) { mutex_lock(&fs_info->scrub_lock); if (!atomic_read(&fs_info->scrubs_running)) { mutex_unlock(&fs_info->scrub_lock); return -ENOTCONN; } atomic_inc(&fs_info->scrub_cancel_req); while (atomic_read(&fs_info->scrubs_running)) { mutex_unlock(&fs_info->scrub_lock); wait_event(fs_info->scrub_pause_wait, atomic_read(&fs_info->scrubs_running) == 0); mutex_lock(&fs_info->scrub_lock); } atomic_dec(&fs_info->scrub_cancel_req); mutex_unlock(&fs_info->scrub_lock); return 0; } int btrfs_scrub_cancel_dev(struct btrfs_device *dev) { struct btrfs_fs_info *fs_info = dev->fs_info; struct scrub_ctx *sctx; mutex_lock(&fs_info->scrub_lock); sctx = dev->scrub_ctx; if (!sctx) { mutex_unlock(&fs_info->scrub_lock); return -ENOTCONN; } atomic_inc(&sctx->cancel_req); while (dev->scrub_ctx) { mutex_unlock(&fs_info->scrub_lock); wait_event(fs_info->scrub_pause_wait, dev->scrub_ctx == NULL); mutex_lock(&fs_info->scrub_lock); } mutex_unlock(&fs_info->scrub_lock); return 0; } int btrfs_scrub_progress(struct btrfs_fs_info *fs_info, u64 devid, struct btrfs_scrub_progress *progress) { struct btrfs_dev_lookup_args args = { .devid = devid }; struct btrfs_device *dev; struct scrub_ctx *sctx = NULL; mutex_lock(&fs_info->fs_devices->device_list_mutex); dev = btrfs_find_device(fs_info->fs_devices, &args); if (dev) sctx = dev->scrub_ctx; if (sctx) memcpy(progress, &sctx->stat, sizeof(*progress)); mutex_unlock(&fs_info->fs_devices->device_list_mutex); return dev ? (sctx ? 0 : -ENOTCONN) : -ENODEV; } |
| 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 | // SPDX-License-Identifier: GPL-2.0+ /* * HID driver for Topre REALFORCE Keyboards * * Copyright (c) 2022 Harry Stern <harry@harrystern.net> * * Based on the hid-macally driver */ #include <linux/hid.h> #include <linux/module.h> #include "hid-ids.h" MODULE_AUTHOR("Harry Stern <harry@harrystern.net>"); MODULE_DESCRIPTION("REALFORCE R2 Keyboard driver"); MODULE_LICENSE("GPL"); /* * Fix the REALFORCE R2's non-boot interface's report descriptor to match the * events it's actually sending. It claims to send array events but is instead * sending variable events. */ static const __u8 *topre_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { if (*rsize >= 119 && rdesc[69] == 0x29 && rdesc[70] == 0xe7 && rdesc[71] == 0x81 && rdesc[72] == 0x00) { hid_info(hdev, "fixing up Topre REALFORCE keyboard report descriptor\n"); rdesc[72] = 0x02; } else if (*rsize >= 106 && rdesc[28] == 0x29 && rdesc[29] == 0xe7 && rdesc[30] == 0x81 && rdesc[31] == 0x00) { hid_info(hdev, "fixing up Topre REALFORCE keyboard report descriptor\n"); rdesc[31] = 0x02; } return rdesc; } static const struct hid_device_id topre_id_table[] = { { HID_USB_DEVICE(USB_VENDOR_ID_TOPRE, USB_DEVICE_ID_TOPRE_REALFORCE_R2_108) }, { HID_USB_DEVICE(USB_VENDOR_ID_TOPRE, USB_DEVICE_ID_TOPRE_REALFORCE_R2_87) }, { HID_USB_DEVICE(USB_VENDOR_ID_TOPRE, USB_DEVICE_ID_TOPRE_REALFORCE_R3S_87) }, { } }; MODULE_DEVICE_TABLE(hid, topre_id_table); static struct hid_driver topre_driver = { .name = "topre", .id_table = topre_id_table, .report_fixup = topre_report_fixup, }; module_hid_driver(topre_driver); |
| 10 10 10 7 10 1 10 10 8 8 8 8 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Cryptographic API. * * RIPEMD-160 - RACE Integrity Primitives Evaluation Message Digest. * * Based on the reference implementation by Antoon Bosselaers, ESAT-COSIC * * Copyright (c) 2008 Adrian-Ken Rueegsegger <ken@codelabs.ch> */ #include <crypto/internal/hash.h> #include <linux/init.h> #include <linux/module.h> #include <linux/mm.h> #include <linux/types.h> #include <asm/byteorder.h> #include "ripemd.h" struct rmd160_ctx { u64 byte_count; u32 state[5]; __le32 buffer[16]; }; #define K1 RMD_K1 #define K2 RMD_K2 #define K3 RMD_K3 #define K4 RMD_K4 #define K5 RMD_K5 #define KK1 RMD_K6 #define KK2 RMD_K7 #define KK3 RMD_K8 #define KK4 RMD_K9 #define KK5 RMD_K1 #define F1(x, y, z) (x ^ y ^ z) /* XOR */ #define F2(x, y, z) (z ^ (x & (y ^ z))) /* x ? y : z */ #define F3(x, y, z) ((x | ~y) ^ z) #define F4(x, y, z) (y ^ (z & (x ^ y))) /* z ? x : y */ #define F5(x, y, z) (x ^ (y | ~z)) #define ROUND(a, b, c, d, e, f, k, x, s) { \ (a) += f((b), (c), (d)) + le32_to_cpup(&(x)) + (k); \ (a) = rol32((a), (s)) + (e); \ (c) = rol32((c), 10); \ } static void rmd160_transform(u32 *state, const __le32 *in) { u32 aa, bb, cc, dd, ee, aaa, bbb, ccc, ddd, eee; /* Initialize left lane */ aa = state[0]; bb = state[1]; cc = state[2]; dd = state[3]; ee = state[4]; /* Initialize right lane */ aaa = state[0]; bbb = state[1]; ccc = state[2]; ddd = state[3]; eee = state[4]; /* round 1: left lane */ ROUND(aa, bb, cc, dd, ee, F1, K1, in[0], 11); ROUND(ee, aa, bb, cc, dd, F1, K1, in[1], 14); ROUND(dd, ee, aa, bb, cc, F1, K1, in[2], 15); ROUND(cc, dd, ee, aa, bb, F1, K1, in[3], 12); ROUND(bb, cc, dd, ee, aa, F1, K1, in[4], 5); ROUND(aa, bb, cc, dd, ee, F1, K1, in[5], 8); ROUND(ee, aa, bb, cc, dd, F1, K1, in[6], 7); ROUND(dd, ee, aa, bb, cc, F1, K1, in[7], 9); ROUND(cc, dd, ee, aa, bb, F1, K1, in[8], 11); ROUND(bb, cc, dd, ee, aa, F1, K1, in[9], 13); ROUND(aa, bb, cc, dd, ee, F1, K1, in[10], 14); ROUND(ee, aa, bb, cc, dd, F1, K1, in[11], 15); ROUND(dd, ee, aa, bb, cc, F1, K1, in[12], 6); ROUND(cc, dd, ee, aa, bb, F1, K1, in[13], 7); ROUND(bb, cc, dd, ee, aa, F1, K1, in[14], 9); ROUND(aa, bb, cc, dd, ee, F1, K1, in[15], 8); /* round 2: left lane" */ ROUND(ee, aa, bb, cc, dd, F2, K2, in[7], 7); ROUND(dd, ee, aa, bb, cc, F2, K2, in[4], 6); ROUND(cc, dd, ee, aa, bb, F2, K2, in[13], 8); ROUND(bb, cc, dd, ee, aa, F2, K2, in[1], 13); ROUND(aa, bb, cc, dd, ee, F2, K2, in[10], 11); ROUND(ee, aa, bb, cc, dd, F2, K2, in[6], 9); ROUND(dd, ee, aa, bb, cc, F2, K2, in[15], 7); ROUND(cc, dd, ee, aa, bb, F2, K2, in[3], 15); ROUND(bb, cc, dd, ee, aa, F2, K2, in[12], 7); ROUND(aa, bb, cc, dd, ee, F2, K2, in[0], 12); ROUND(ee, aa, bb, cc, dd, F2, K2, in[9], 15); ROUND(dd, ee, aa, bb, cc, F2, K2, in[5], 9); ROUND(cc, dd, ee, aa, bb, F2, K2, in[2], 11); ROUND(bb, cc, dd, ee, aa, F2, K2, in[14], 7); ROUND(aa, bb, cc, dd, ee, F2, K2, in[11], 13); ROUND(ee, aa, bb, cc, dd, F2, K2, in[8], 12); /* round 3: left lane" */ ROUND(dd, ee, aa, bb, cc, F3, K3, in[3], 11); ROUND(cc, dd, ee, aa, bb, F3, K3, in[10], 13); ROUND(bb, cc, dd, ee, aa, F3, K3, in[14], 6); ROUND(aa, bb, cc, dd, ee, F3, K3, in[4], 7); ROUND(ee, aa, bb, cc, dd, F3, K3, in[9], 14); ROUND(dd, ee, aa, bb, cc, F3, K3, in[15], 9); ROUND(cc, dd, ee, aa, bb, F3, K3, in[8], 13); ROUND(bb, cc, dd, ee, aa, F3, K3, in[1], 15); ROUND(aa, bb, cc, dd, ee, F3, K3, in[2], 14); ROUND(ee, aa, bb, cc, dd, F3, K3, in[7], 8); ROUND(dd, ee, aa, bb, cc, F3, K3, in[0], 13); ROUND(cc, dd, ee, aa, bb, F3, K3, in[6], 6); ROUND(bb, cc, dd, ee, aa, F3, K3, in[13], 5); ROUND(aa, bb, cc, dd, ee, F3, K3, in[11], 12); ROUND(ee, aa, bb, cc, dd, F3, K3, in[5], 7); ROUND(dd, ee, aa, bb, cc, F3, K3, in[12], 5); /* round 4: left lane" */ ROUND(cc, dd, ee, aa, bb, F4, K4, in[1], 11); ROUND(bb, cc, dd, ee, aa, F4, K4, in[9], 12); ROUND(aa, bb, cc, dd, ee, F4, K4, in[11], 14); ROUND(ee, aa, bb, cc, dd, F4, K4, in[10], 15); ROUND(dd, ee, aa, bb, cc, F4, K4, in[0], 14); ROUND(cc, dd, ee, aa, bb, F4, K4, in[8], 15); ROUND(bb, cc, dd, ee, aa, F4, K4, in[12], 9); ROUND(aa, bb, cc, dd, ee, F4, K4, in[4], 8); ROUND(ee, aa, bb, cc, dd, F4, K4, in[13], 9); ROUND(dd, ee, aa, bb, cc, F4, K4, in[3], 14); ROUND(cc, dd, ee, aa, bb, F4, K4, in[7], 5); ROUND(bb, cc, dd, ee, aa, F4, K4, in[15], 6); ROUND(aa, bb, cc, dd, ee, F4, K4, in[14], 8); ROUND(ee, aa, bb, cc, dd, F4, K4, in[5], 6); ROUND(dd, ee, aa, bb, cc, F4, K4, in[6], 5); ROUND(cc, dd, ee, aa, bb, F4, K4, in[2], 12); /* round 5: left lane" */ ROUND(bb, cc, dd, ee, aa, F5, K5, in[4], 9); ROUND(aa, bb, cc, dd, ee, F5, K5, in[0], 15); ROUND(ee, aa, bb, cc, dd, F5, K5, in[5], 5); ROUND(dd, ee, aa, bb, cc, F5, K5, in[9], 11); ROUND(cc, dd, ee, aa, bb, F5, K5, in[7], 6); ROUND(bb, cc, dd, ee, aa, F5, K5, in[12], 8); ROUND(aa, bb, cc, dd, ee, F5, K5, in[2], 13); ROUND(ee, aa, bb, cc, dd, F5, K5, in[10], 12); ROUND(dd, ee, aa, bb, cc, F5, K5, in[14], 5); ROUND(cc, dd, ee, aa, bb, F5, K5, in[1], 12); ROUND(bb, cc, dd, ee, aa, F5, K5, in[3], 13); ROUND(aa, bb, cc, dd, ee, F5, K5, in[8], 14); ROUND(ee, aa, bb, cc, dd, F5, K5, in[11], 11); ROUND(dd, ee, aa, bb, cc, F5, K5, in[6], 8); ROUND(cc, dd, ee, aa, bb, F5, K5, in[15], 5); ROUND(bb, cc, dd, ee, aa, F5, K5, in[13], 6); /* round 1: right lane */ ROUND(aaa, bbb, ccc, ddd, eee, F5, KK1, in[5], 8); ROUND(eee, aaa, bbb, ccc, ddd, F5, KK1, in[14], 9); ROUND(ddd, eee, aaa, bbb, ccc, F5, KK1, in[7], 9); ROUND(ccc, ddd, eee, aaa, bbb, F5, KK1, in[0], 11); ROUND(bbb, ccc, ddd, eee, aaa, F5, KK1, in[9], 13); ROUND(aaa, bbb, ccc, ddd, eee, F5, KK1, in[2], 15); ROUND(eee, aaa, bbb, ccc, ddd, F5, KK1, in[11], 15); ROUND(ddd, eee, aaa, bbb, ccc, F5, KK1, in[4], 5); ROUND(ccc, ddd, eee, aaa, bbb, F5, KK1, in[13], 7); ROUND(bbb, ccc, ddd, eee, aaa, F5, KK1, in[6], 7); ROUND(aaa, bbb, ccc, ddd, eee, F5, KK1, in[15], 8); ROUND(eee, aaa, bbb, ccc, ddd, F5, KK1, in[8], 11); ROUND(ddd, eee, aaa, bbb, ccc, F5, KK1, in[1], 14); ROUND(ccc, ddd, eee, aaa, bbb, F5, KK1, in[10], 14); ROUND(bbb, ccc, ddd, eee, aaa, F5, KK1, in[3], 12); ROUND(aaa, bbb, ccc, ddd, eee, F5, KK1, in[12], 6); /* round 2: right lane */ ROUND(eee, aaa, bbb, ccc, ddd, F4, KK2, in[6], 9); ROUND(ddd, eee, aaa, bbb, ccc, F4, KK2, in[11], 13); ROUND(ccc, ddd, eee, aaa, bbb, F4, KK2, in[3], 15); ROUND(bbb, ccc, ddd, eee, aaa, F4, KK2, in[7], 7); ROUND(aaa, bbb, ccc, ddd, eee, F4, KK2, in[0], 12); ROUND(eee, aaa, bbb, ccc, ddd, F4, KK2, in[13], 8); ROUND(ddd, eee, aaa, bbb, ccc, F4, KK2, in[5], 9); ROUND(ccc, ddd, eee, aaa, bbb, F4, KK2, in[10], 11); ROUND(bbb, ccc, ddd, eee, aaa, F4, KK2, in[14], 7); ROUND(aaa, bbb, ccc, ddd, eee, F4, KK2, in[15], 7); ROUND(eee, aaa, bbb, ccc, ddd, F4, KK2, in[8], 12); ROUND(ddd, eee, aaa, bbb, ccc, F4, KK2, in[12], 7); ROUND(ccc, ddd, eee, aaa, bbb, F4, KK2, in[4], 6); ROUND(bbb, ccc, ddd, eee, aaa, F4, KK2, in[9], 15); ROUND(aaa, bbb, ccc, ddd, eee, F4, KK2, in[1], 13); ROUND(eee, aaa, bbb, ccc, ddd, F4, KK2, in[2], 11); /* round 3: right lane */ ROUND(ddd, eee, aaa, bbb, ccc, F3, KK3, in[15], 9); ROUND(ccc, ddd, eee, aaa, bbb, F3, KK3, in[5], 7); ROUND(bbb, ccc, ddd, eee, aaa, F3, KK3, in[1], 15); ROUND(aaa, bbb, ccc, ddd, eee, F3, KK3, in[3], 11); ROUND(eee, aaa, bbb, ccc, ddd, F3, KK3, in[7], 8); ROUND(ddd, eee, aaa, bbb, ccc, F3, KK3, in[14], 6); ROUND(ccc, ddd, eee, aaa, bbb, F3, KK3, in[6], 6); ROUND(bbb, ccc, ddd, eee, aaa, F3, KK3, in[9], 14); ROUND(aaa, bbb, ccc, ddd, eee, F3, KK3, in[11], 12); ROUND(eee, aaa, bbb, ccc, ddd, F3, KK3, in[8], 13); ROUND(ddd, eee, aaa, bbb, ccc, F3, KK3, in[12], 5); ROUND(ccc, ddd, eee, aaa, bbb, F3, KK3, in[2], 14); ROUND(bbb, ccc, ddd, eee, aaa, F3, KK3, in[10], 13); ROUND(aaa, bbb, ccc, ddd, eee, F3, KK3, in[0], 13); ROUND(eee, aaa, bbb, ccc, ddd, F3, KK3, in[4], 7); ROUND(ddd, eee, aaa, bbb, ccc, F3, KK3, in[13], 5); /* round 4: right lane */ ROUND(ccc, ddd, eee, aaa, bbb, F2, KK4, in[8], 15); ROUND(bbb, ccc, ddd, eee, aaa, F2, KK4, in[6], 5); ROUND(aaa, bbb, ccc, ddd, eee, F2, KK4, in[4], 8); ROUND(eee, aaa, bbb, ccc, ddd, F2, KK4, in[1], 11); ROUND(ddd, eee, aaa, bbb, ccc, F2, KK4, in[3], 14); ROUND(ccc, ddd, eee, aaa, bbb, F2, KK4, in[11], 14); ROUND(bbb, ccc, ddd, eee, aaa, F2, KK4, in[15], 6); ROUND(aaa, bbb, ccc, ddd, eee, F2, KK4, in[0], 14); ROUND(eee, aaa, bbb, ccc, ddd, F2, KK4, in[5], 6); ROUND(ddd, eee, aaa, bbb, ccc, F2, KK4, in[12], 9); ROUND(ccc, ddd, eee, aaa, bbb, F2, KK4, in[2], 12); ROUND(bbb, ccc, ddd, eee, aaa, F2, KK4, in[13], 9); ROUND(aaa, bbb, ccc, ddd, eee, F2, KK4, in[9], 12); ROUND(eee, aaa, bbb, ccc, ddd, F2, KK4, in[7], 5); ROUND(ddd, eee, aaa, bbb, ccc, F2, KK4, in[10], 15); ROUND(ccc, ddd, eee, aaa, bbb, F2, KK4, in[14], 8); /* round 5: right lane */ ROUND(bbb, ccc, ddd, eee, aaa, F1, KK5, in[12], 8); ROUND(aaa, bbb, ccc, ddd, eee, F1, KK5, in[15], 5); ROUND(eee, aaa, bbb, ccc, ddd, F1, KK5, in[10], 12); ROUND(ddd, eee, aaa, bbb, ccc, F1, KK5, in[4], 9); ROUND(ccc, ddd, eee, aaa, bbb, F1, KK5, in[1], 12); ROUND(bbb, ccc, ddd, eee, aaa, F1, KK5, in[5], 5); ROUND(aaa, bbb, ccc, ddd, eee, F1, KK5, in[8], 14); ROUND(eee, aaa, bbb, ccc, ddd, F1, KK5, in[7], 6); ROUND(ddd, eee, aaa, bbb, ccc, F1, KK5, in[6], 8); ROUND(ccc, ddd, eee, aaa, bbb, F1, KK5, in[2], 13); ROUND(bbb, ccc, ddd, eee, aaa, F1, KK5, in[13], 6); ROUND(aaa, bbb, ccc, ddd, eee, F1, KK5, in[14], 5); ROUND(eee, aaa, bbb, ccc, ddd, F1, KK5, in[0], 15); ROUND(ddd, eee, aaa, bbb, ccc, F1, KK5, in[3], 13); ROUND(ccc, ddd, eee, aaa, bbb, F1, KK5, in[9], 11); ROUND(bbb, ccc, ddd, eee, aaa, F1, KK5, in[11], 11); /* combine results */ ddd += cc + state[1]; /* final result for state[0] */ state[1] = state[2] + dd + eee; state[2] = state[3] + ee + aaa; state[3] = state[4] + aa + bbb; state[4] = state[0] + bb + ccc; state[0] = ddd; } static int rmd160_init(struct shash_desc *desc) { struct rmd160_ctx *rctx = shash_desc_ctx(desc); rctx->byte_count = 0; rctx->state[0] = RMD_H0; rctx->state[1] = RMD_H1; rctx->state[2] = RMD_H2; rctx->state[3] = RMD_H3; rctx->state[4] = RMD_H4; memset(rctx->buffer, 0, sizeof(rctx->buffer)); return 0; } static int rmd160_update(struct shash_desc *desc, const u8 *data, unsigned int len) { struct rmd160_ctx *rctx = shash_desc_ctx(desc); const u32 avail = sizeof(rctx->buffer) - (rctx->byte_count & 0x3f); rctx->byte_count += len; /* Enough space in buffer? If so copy and we're done */ if (avail > len) { memcpy((char *)rctx->buffer + (sizeof(rctx->buffer) - avail), data, len); goto out; } memcpy((char *)rctx->buffer + (sizeof(rctx->buffer) - avail), data, avail); rmd160_transform(rctx->state, rctx->buffer); data += avail; len -= avail; while (len >= sizeof(rctx->buffer)) { memcpy(rctx->buffer, data, sizeof(rctx->buffer)); rmd160_transform(rctx->state, rctx->buffer); data += sizeof(rctx->buffer); len -= sizeof(rctx->buffer); } memcpy(rctx->buffer, data, len); out: return 0; } /* Add padding and return the message digest. */ static int rmd160_final(struct shash_desc *desc, u8 *out) { struct rmd160_ctx *rctx = shash_desc_ctx(desc); u32 i, index, padlen; __le64 bits; __le32 *dst = (__le32 *)out; static const u8 padding[64] = { 0x80, }; bits = cpu_to_le64(rctx->byte_count << 3); /* Pad out to 56 mod 64 */ index = rctx->byte_count & 0x3f; padlen = (index < 56) ? (56 - index) : ((64+56) - index); rmd160_update(desc, padding, padlen); /* Append length */ rmd160_update(desc, (const u8 *)&bits, sizeof(bits)); /* Store state in digest */ for (i = 0; i < 5; i++) dst[i] = cpu_to_le32p(&rctx->state[i]); /* Wipe context */ memset(rctx, 0, sizeof(*rctx)); return 0; } static struct shash_alg alg = { .digestsize = RMD160_DIGEST_SIZE, .init = rmd160_init, .update = rmd160_update, .final = rmd160_final, .descsize = sizeof(struct rmd160_ctx), .base = { .cra_name = "rmd160", .cra_driver_name = "rmd160-generic", .cra_blocksize = RMD160_BLOCK_SIZE, .cra_module = THIS_MODULE, } }; static int __init rmd160_mod_init(void) { return crypto_register_shash(&alg); } static void __exit rmd160_mod_fini(void) { crypto_unregister_shash(&alg); } subsys_initcall(rmd160_mod_init); module_exit(rmd160_mod_fini); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Adrian-Ken Rueegsegger <ken@codelabs.ch>"); MODULE_DESCRIPTION("RIPEMD-160 Message Digest"); MODULE_ALIAS_CRYPTO("rmd160"); |
| 4 4 4 4 4 4 4 4 4 5 5 5 5 5 5 5 4 4 4 4 4 4 4 4 4 4 4 4 5 5 5 5 6 6 6 6 6 6 6 6 6 6 6 6 6 6 5 5 4 4 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) International Business Machines Corp., 2006 * Copyright (c) Nokia Corporation, 2006, 2007 * * Author: Artem Bityutskiy (Битюцкий Артём) */ /* * This file includes volume table manipulation code. The volume table is an * on-flash table containing volume meta-data like name, number of reserved * physical eraseblocks, type, etc. The volume table is stored in the so-called * "layout volume". * * The layout volume is an internal volume which is organized as follows. It * consists of two logical eraseblocks - LEB 0 and LEB 1. Each logical * eraseblock stores one volume table copy, i.e. LEB 0 and LEB 1 duplicate each * other. This redundancy guarantees robustness to unclean reboots. The volume * table is basically an array of volume table records. Each record contains * full information about the volume and protected by a CRC checksum. Note, * nowadays we use the atomic LEB change operation when updating the volume * table, so we do not really need 2 LEBs anymore, but we preserve the older * design for the backward compatibility reasons. * * When the volume table is changed, it is first changed in RAM. Then LEB 0 is * erased, and the updated volume table is written back to LEB 0. Then same for * LEB 1. This scheme guarantees recoverability from unclean reboots. * * In this UBI implementation the on-flash volume table does not contain any * information about how much data static volumes contain. * * But it would still be beneficial to store this information in the volume * table. For example, suppose we have a static volume X, and all its physical * eraseblocks became bad for some reasons. Suppose we are attaching the * corresponding MTD device, for some reason we find no logical eraseblocks * corresponding to the volume X. According to the volume table volume X does * exist. So we don't know whether it is just empty or all its physical * eraseblocks went bad. So we cannot alarm the user properly. * * The volume table also stores so-called "update marker", which is used for * volume updates. Before updating the volume, the update marker is set, and * after the update operation is finished, the update marker is cleared. So if * the update operation was interrupted (e.g. by an unclean reboot) - the * update marker is still there and we know that the volume's contents is * damaged. */ #include <linux/crc32.h> #include <linux/err.h> #include <linux/slab.h> #include <asm/div64.h> #include "ubi.h" static void self_vtbl_check(const struct ubi_device *ubi); /* Empty volume table record */ static struct ubi_vtbl_record empty_vtbl_record; /** * ubi_update_layout_vol - helper for updatting layout volumes on flash * @ubi: UBI device description object */ static int ubi_update_layout_vol(struct ubi_device *ubi) { struct ubi_volume *layout_vol; int i, err; layout_vol = ubi->volumes[vol_id2idx(ubi, UBI_LAYOUT_VOLUME_ID)]; for (i = 0; i < UBI_LAYOUT_VOLUME_EBS; i++) { err = ubi_eba_atomic_leb_change(ubi, layout_vol, i, ubi->vtbl, ubi->vtbl_size); if (err) return err; } return 0; } /** * ubi_change_vtbl_record - change volume table record. * @ubi: UBI device description object * @idx: table index to change * @vtbl_rec: new volume table record * * This function changes volume table record @idx. If @vtbl_rec is %NULL, empty * volume table record is written. The caller does not have to calculate CRC of * the record as it is done by this function. Returns zero in case of success * and a negative error code in case of failure. */ int ubi_change_vtbl_record(struct ubi_device *ubi, int idx, struct ubi_vtbl_record *vtbl_rec) { int err; uint32_t crc; ubi_assert(idx >= 0 && idx < ubi->vtbl_slots); if (!vtbl_rec) vtbl_rec = &empty_vtbl_record; else { crc = crc32(UBI_CRC32_INIT, vtbl_rec, UBI_VTBL_RECORD_SIZE_CRC); vtbl_rec->crc = cpu_to_be32(crc); } memcpy(&ubi->vtbl[idx], vtbl_rec, sizeof(struct ubi_vtbl_record)); err = ubi_update_layout_vol(ubi); self_vtbl_check(ubi); return err ? err : 0; } /** * ubi_vtbl_rename_volumes - rename UBI volumes in the volume table. * @ubi: UBI device description object * @rename_list: list of &struct ubi_rename_entry objects * * This function re-names multiple volumes specified in @req in the volume * table. Returns zero in case of success and a negative error code in case of * failure. */ int ubi_vtbl_rename_volumes(struct ubi_device *ubi, struct list_head *rename_list) { struct ubi_rename_entry *re; list_for_each_entry(re, rename_list, list) { uint32_t crc; struct ubi_volume *vol = re->desc->vol; struct ubi_vtbl_record *vtbl_rec = &ubi->vtbl[vol->vol_id]; if (re->remove) { memcpy(vtbl_rec, &empty_vtbl_record, sizeof(struct ubi_vtbl_record)); continue; } vtbl_rec->name_len = cpu_to_be16(re->new_name_len); memcpy(vtbl_rec->name, re->new_name, re->new_name_len); memset(vtbl_rec->name + re->new_name_len, 0, UBI_VOL_NAME_MAX + 1 - re->new_name_len); crc = crc32(UBI_CRC32_INIT, vtbl_rec, UBI_VTBL_RECORD_SIZE_CRC); vtbl_rec->crc = cpu_to_be32(crc); } return ubi_update_layout_vol(ubi); } /** * vtbl_check - check if volume table is not corrupted and sensible. * @ubi: UBI device description object * @vtbl: volume table * * This function returns zero if @vtbl is all right, %1 if CRC is incorrect, * and %-EINVAL if it contains inconsistent data. */ static int vtbl_check(const struct ubi_device *ubi, const struct ubi_vtbl_record *vtbl) { int i, n, reserved_pebs, alignment, data_pad, vol_type, name_len; int upd_marker, err; uint32_t crc; const char *name; for (i = 0; i < ubi->vtbl_slots; i++) { cond_resched(); reserved_pebs = be32_to_cpu(vtbl[i].reserved_pebs); alignment = be32_to_cpu(vtbl[i].alignment); data_pad = be32_to_cpu(vtbl[i].data_pad); upd_marker = vtbl[i].upd_marker; vol_type = vtbl[i].vol_type; name_len = be16_to_cpu(vtbl[i].name_len); name = &vtbl[i].name[0]; crc = crc32(UBI_CRC32_INIT, &vtbl[i], UBI_VTBL_RECORD_SIZE_CRC); if (be32_to_cpu(vtbl[i].crc) != crc) { ubi_err(ubi, "bad CRC at record %u: %#08x, not %#08x", i, crc, be32_to_cpu(vtbl[i].crc)); ubi_dump_vtbl_record(&vtbl[i], i); return 1; } if (reserved_pebs == 0) { if (memcmp(&vtbl[i], &empty_vtbl_record, UBI_VTBL_RECORD_SIZE)) { err = 2; goto bad; } continue; } if (reserved_pebs < 0 || alignment < 0 || data_pad < 0 || name_len < 0) { err = 3; goto bad; } if (alignment > ubi->leb_size || alignment == 0) { err = 4; goto bad; } n = alignment & (ubi->min_io_size - 1); if (alignment != 1 && n) { err = 5; goto bad; } n = ubi->leb_size % alignment; if (data_pad != n) { ubi_err(ubi, "bad data_pad, has to be %d", n); err = 6; goto bad; } if (vol_type != UBI_VID_DYNAMIC && vol_type != UBI_VID_STATIC) { err = 7; goto bad; } if (upd_marker != 0 && upd_marker != 1) { err = 8; goto bad; } if (reserved_pebs > ubi->good_peb_count) { ubi_err(ubi, "too large reserved_pebs %d, good PEBs %d", reserved_pebs, ubi->good_peb_count); err = 9; goto bad; } if (name_len > UBI_VOL_NAME_MAX) { err = 10; goto bad; } if (name[0] == '\0') { err = 11; goto bad; } if (name_len != strnlen(name, name_len + 1)) { err = 12; goto bad; } } /* Checks that all names are unique */ for (i = 0; i < ubi->vtbl_slots - 1; i++) { for (n = i + 1; n < ubi->vtbl_slots; n++) { int len1 = be16_to_cpu(vtbl[i].name_len); int len2 = be16_to_cpu(vtbl[n].name_len); if (len1 > 0 && len1 == len2 && !strncmp(vtbl[i].name, vtbl[n].name, len1)) { ubi_err(ubi, "volumes %d and %d have the same name \"%s\"", i, n, vtbl[i].name); ubi_dump_vtbl_record(&vtbl[i], i); ubi_dump_vtbl_record(&vtbl[n], n); return -EINVAL; } } } return 0; bad: ubi_err(ubi, "volume table check failed: record %d, error %d", i, err); ubi_dump_vtbl_record(&vtbl[i], i); return -EINVAL; } /** * create_vtbl - create a copy of volume table. * @ubi: UBI device description object * @ai: attaching information * @copy: number of the volume table copy * @vtbl: contents of the volume table * * This function returns zero in case of success and a negative error code in * case of failure. */ static int create_vtbl(struct ubi_device *ubi, struct ubi_attach_info *ai, int copy, void *vtbl) { int err, tries = 0; struct ubi_vid_io_buf *vidb; struct ubi_vid_hdr *vid_hdr; struct ubi_ainf_peb *new_aeb; dbg_gen("create volume table (copy #%d)", copy + 1); vidb = ubi_alloc_vid_buf(ubi, GFP_KERNEL); if (!vidb) return -ENOMEM; vid_hdr = ubi_get_vid_hdr(vidb); retry: new_aeb = ubi_early_get_peb(ubi, ai); if (IS_ERR(new_aeb)) { err = PTR_ERR(new_aeb); goto out_free; } vid_hdr->vol_type = UBI_LAYOUT_VOLUME_TYPE; vid_hdr->vol_id = cpu_to_be32(UBI_LAYOUT_VOLUME_ID); vid_hdr->compat = UBI_LAYOUT_VOLUME_COMPAT; vid_hdr->data_size = vid_hdr->used_ebs = vid_hdr->data_pad = cpu_to_be32(0); vid_hdr->lnum = cpu_to_be32(copy); vid_hdr->sqnum = cpu_to_be64(++ai->max_sqnum); /* The EC header is already there, write the VID header */ err = ubi_io_write_vid_hdr(ubi, new_aeb->pnum, vidb); if (err) goto write_error; /* Write the layout volume contents */ err = ubi_io_write_data(ubi, vtbl, new_aeb->pnum, 0, ubi->vtbl_size); if (err) goto write_error; /* * And add it to the attaching information. Don't delete the old version * of this LEB as it will be deleted and freed in 'ubi_add_to_av()'. */ err = ubi_add_to_av(ubi, ai, new_aeb->pnum, new_aeb->ec, vid_hdr, 0); ubi_free_aeb(ai, new_aeb); ubi_free_vid_buf(vidb); return err; write_error: if (err == -EIO && ++tries <= 5) { /* * Probably this physical eraseblock went bad, try to pick * another one. */ list_add(&new_aeb->u.list, &ai->erase); goto retry; } ubi_free_aeb(ai, new_aeb); out_free: ubi_free_vid_buf(vidb); return err; } /** * process_lvol - process the layout volume. * @ubi: UBI device description object * @ai: attaching information * @av: layout volume attaching information * * This function is responsible for reading the layout volume, ensuring it is * not corrupted, and recovering from corruptions if needed. Returns volume * table in case of success and a negative error code in case of failure. */ static struct ubi_vtbl_record *process_lvol(struct ubi_device *ubi, struct ubi_attach_info *ai, struct ubi_ainf_volume *av) { int err; struct rb_node *rb; struct ubi_ainf_peb *aeb; struct ubi_vtbl_record *leb[UBI_LAYOUT_VOLUME_EBS] = { NULL, NULL }; int leb_corrupted[UBI_LAYOUT_VOLUME_EBS] = {1, 1}; /* * UBI goes through the following steps when it changes the layout * volume: * a. erase LEB 0; * b. write new data to LEB 0; * c. erase LEB 1; * d. write new data to LEB 1. * * Before the change, both LEBs contain the same data. * * Due to unclean reboots, the contents of LEB 0 may be lost, but there * should LEB 1. So it is OK if LEB 0 is corrupted while LEB 1 is not. * Similarly, LEB 1 may be lost, but there should be LEB 0. And * finally, unclean reboots may result in a situation when neither LEB * 0 nor LEB 1 are corrupted, but they are different. In this case, LEB * 0 contains more recent information. * * So the plan is to first check LEB 0. Then * a. if LEB 0 is OK, it must be containing the most recent data; then * we compare it with LEB 1, and if they are different, we copy LEB * 0 to LEB 1; * b. if LEB 0 is corrupted, but LEB 1 has to be OK, and we copy LEB 1 * to LEB 0. */ dbg_gen("check layout volume"); /* Read both LEB 0 and LEB 1 into memory */ ubi_rb_for_each_entry(rb, aeb, &av->root, u.rb) { leb[aeb->lnum] = vzalloc(ubi->vtbl_size); if (!leb[aeb->lnum]) { err = -ENOMEM; goto out_free; } err = ubi_io_read_data(ubi, leb[aeb->lnum], aeb->pnum, 0, ubi->vtbl_size); if (err == UBI_IO_BITFLIPS || mtd_is_eccerr(err)) /* * Scrub the PEB later. Note, -EBADMSG indicates an * uncorrectable ECC error, but we have our own CRC and * the data will be checked later. If the data is OK, * the PEB will be scrubbed (because we set * aeb->scrub). If the data is not OK, the contents of * the PEB will be recovered from the second copy, and * aeb->scrub will be cleared in * 'ubi_add_to_av()'. */ aeb->scrub = 1; else if (err) goto out_free; } err = -EINVAL; if (leb[0]) { leb_corrupted[0] = vtbl_check(ubi, leb[0]); if (leb_corrupted[0] < 0) goto out_free; } if (!leb_corrupted[0]) { /* LEB 0 is OK */ if (leb[1]) leb_corrupted[1] = memcmp(leb[0], leb[1], ubi->vtbl_size); if (leb_corrupted[1]) { ubi_warn(ubi, "volume table copy #2 is corrupted"); err = create_vtbl(ubi, ai, 1, leb[0]); if (err) goto out_free; ubi_msg(ubi, "volume table was restored"); } /* Both LEB 1 and LEB 2 are OK and consistent */ vfree(leb[1]); return leb[0]; } else { /* LEB 0 is corrupted or does not exist */ if (leb[1]) { leb_corrupted[1] = vtbl_check(ubi, leb[1]); if (leb_corrupted[1] < 0) goto out_free; } if (leb_corrupted[1]) { /* Both LEB 0 and LEB 1 are corrupted */ ubi_err(ubi, "both volume tables are corrupted"); goto out_free; } ubi_warn(ubi, "volume table copy #1 is corrupted"); err = create_vtbl(ubi, ai, 0, leb[1]); if (err) goto out_free; ubi_msg(ubi, "volume table was restored"); vfree(leb[0]); return leb[1]; } out_free: vfree(leb[0]); vfree(leb[1]); return ERR_PTR(err); } /** * create_empty_lvol - create empty layout volume. * @ubi: UBI device description object * @ai: attaching information * * This function returns volume table contents in case of success and a * negative error code in case of failure. */ static struct ubi_vtbl_record *create_empty_lvol(struct ubi_device *ubi, struct ubi_attach_info *ai) { int i; struct ubi_vtbl_record *vtbl; vtbl = vzalloc(ubi->vtbl_size); if (!vtbl) return ERR_PTR(-ENOMEM); for (i = 0; i < ubi->vtbl_slots; i++) memcpy(&vtbl[i], &empty_vtbl_record, UBI_VTBL_RECORD_SIZE); for (i = 0; i < UBI_LAYOUT_VOLUME_EBS; i++) { int err; err = create_vtbl(ubi, ai, i, vtbl); if (err) { vfree(vtbl); return ERR_PTR(err); } } return vtbl; } /** * init_volumes - initialize volume information for existing volumes. * @ubi: UBI device description object * @ai: scanning information * @vtbl: volume table * * This function allocates volume description objects for existing volumes. * Returns zero in case of success and a negative error code in case of * failure. */ static int init_volumes(struct ubi_device *ubi, const struct ubi_attach_info *ai, const struct ubi_vtbl_record *vtbl) { int i, err, reserved_pebs = 0; struct ubi_ainf_volume *av; struct ubi_volume *vol; for (i = 0; i < ubi->vtbl_slots; i++) { cond_resched(); if (be32_to_cpu(vtbl[i].reserved_pebs) == 0) continue; /* Empty record */ vol = kzalloc(sizeof(struct ubi_volume), GFP_KERNEL); if (!vol) return -ENOMEM; vol->reserved_pebs = be32_to_cpu(vtbl[i].reserved_pebs); vol->alignment = be32_to_cpu(vtbl[i].alignment); vol->data_pad = be32_to_cpu(vtbl[i].data_pad); vol->upd_marker = vtbl[i].upd_marker; vol->vol_type = vtbl[i].vol_type == UBI_VID_DYNAMIC ? UBI_DYNAMIC_VOLUME : UBI_STATIC_VOLUME; vol->name_len = be16_to_cpu(vtbl[i].name_len); vol->usable_leb_size = ubi->leb_size - vol->data_pad; memcpy(vol->name, vtbl[i].name, vol->name_len); vol->name[vol->name_len] = '\0'; vol->vol_id = i; if (vtbl[i].flags & UBI_VTBL_SKIP_CRC_CHECK_FLG) vol->skip_check = 1; if (vtbl[i].flags & UBI_VTBL_AUTORESIZE_FLG) { /* Auto re-size flag may be set only for one volume */ if (ubi->autoresize_vol_id != -1) { ubi_err(ubi, "more than one auto-resize volume (%d and %d)", ubi->autoresize_vol_id, i); kfree(vol); return -EINVAL; } ubi->autoresize_vol_id = i; } ubi_assert(!ubi->volumes[i]); ubi->volumes[i] = vol; ubi->vol_count += 1; vol->ubi = ubi; reserved_pebs += vol->reserved_pebs; /* * We use ubi->peb_count and not vol->reserved_pebs because * we want to keep the code simple. Otherwise we'd have to * resize/check the bitmap upon volume resize too. * Allocating a few bytes more does not hurt. */ err = ubi_fastmap_init_checkmap(vol, ubi->peb_count); if (err) return err; /* * In case of dynamic volume UBI knows nothing about how many * data is stored there. So assume the whole volume is used. */ if (vol->vol_type == UBI_DYNAMIC_VOLUME) { vol->used_ebs = vol->reserved_pebs; vol->last_eb_bytes = vol->usable_leb_size; vol->used_bytes = (long long)vol->used_ebs * vol->usable_leb_size; continue; } /* Static volumes only */ av = ubi_find_av(ai, i); if (!av || !av->leb_count) { /* * No eraseblocks belonging to this volume found. We * don't actually know whether this static volume is * completely corrupted or just contains no data. And * we cannot know this as long as data size is not * stored on flash. So we just assume the volume is * empty. FIXME: this should be handled. */ continue; } if (av->leb_count != av->used_ebs) { /* * We found a static volume which misses several * eraseblocks. Treat it as corrupted. */ ubi_warn(ubi, "static volume %d misses %d LEBs - corrupted", av->vol_id, av->used_ebs - av->leb_count); vol->corrupted = 1; continue; } vol->used_ebs = av->used_ebs; vol->used_bytes = (long long)(vol->used_ebs - 1) * vol->usable_leb_size; vol->used_bytes += av->last_data_size; vol->last_eb_bytes = av->last_data_size; } /* And add the layout volume */ vol = kzalloc(sizeof(struct ubi_volume), GFP_KERNEL); if (!vol) return -ENOMEM; vol->reserved_pebs = UBI_LAYOUT_VOLUME_EBS; vol->alignment = UBI_LAYOUT_VOLUME_ALIGN; vol->vol_type = UBI_DYNAMIC_VOLUME; vol->name_len = sizeof(UBI_LAYOUT_VOLUME_NAME) - 1; memcpy(vol->name, UBI_LAYOUT_VOLUME_NAME, vol->name_len + 1); vol->usable_leb_size = ubi->leb_size; vol->used_ebs = vol->reserved_pebs; vol->last_eb_bytes = vol->reserved_pebs; vol->used_bytes = (long long)vol->used_ebs * (ubi->leb_size - vol->data_pad); vol->vol_id = UBI_LAYOUT_VOLUME_ID; vol->ref_count = 1; ubi_assert(!ubi->volumes[i]); ubi->volumes[vol_id2idx(ubi, vol->vol_id)] = vol; reserved_pebs += vol->reserved_pebs; ubi->vol_count += 1; vol->ubi = ubi; err = ubi_fastmap_init_checkmap(vol, UBI_LAYOUT_VOLUME_EBS); if (err) return err; if (reserved_pebs > ubi->avail_pebs) { ubi_err(ubi, "not enough PEBs, required %d, available %d", reserved_pebs, ubi->avail_pebs); if (ubi->corr_peb_count) ubi_err(ubi, "%d PEBs are corrupted and not used", ubi->corr_peb_count); return -ENOSPC; } ubi->rsvd_pebs += reserved_pebs; ubi->avail_pebs -= reserved_pebs; return 0; } /** * check_av - check volume attaching information. * @vol: UBI volume description object * @av: volume attaching information * * This function returns zero if the volume attaching information is consistent * to the data read from the volume tabla, and %-EINVAL if not. */ static int check_av(const struct ubi_volume *vol, const struct ubi_ainf_volume *av) { int err; if (av->highest_lnum >= vol->reserved_pebs) { err = 1; goto bad; } if (av->leb_count > vol->reserved_pebs) { err = 2; goto bad; } if (av->vol_type != vol->vol_type) { err = 3; goto bad; } if (av->used_ebs > vol->reserved_pebs) { err = 4; goto bad; } if (av->data_pad != vol->data_pad) { err = 5; goto bad; } return 0; bad: ubi_err(vol->ubi, "bad attaching information, error %d", err); ubi_dump_av(av); ubi_dump_vol_info(vol); return -EINVAL; } /** * check_attaching_info - check that attaching information. * @ubi: UBI device description object * @ai: attaching information * * Even though we protect on-flash data by CRC checksums, we still don't trust * the media. This function ensures that attaching information is consistent to * the information read from the volume table. Returns zero if the attaching * information is OK and %-EINVAL if it is not. */ static int check_attaching_info(const struct ubi_device *ubi, struct ubi_attach_info *ai) { int err, i; struct ubi_ainf_volume *av; struct ubi_volume *vol; if (ai->vols_found > UBI_INT_VOL_COUNT + ubi->vtbl_slots) { ubi_err(ubi, "found %d volumes while attaching, maximum is %d + %d", ai->vols_found, UBI_INT_VOL_COUNT, ubi->vtbl_slots); return -EINVAL; } if (ai->highest_vol_id >= ubi->vtbl_slots + UBI_INT_VOL_COUNT && ai->highest_vol_id < UBI_INTERNAL_VOL_START) { ubi_err(ubi, "too large volume ID %d found", ai->highest_vol_id); return -EINVAL; } for (i = 0; i < ubi->vtbl_slots + UBI_INT_VOL_COUNT; i++) { cond_resched(); av = ubi_find_av(ai, i); vol = ubi->volumes[i]; if (!vol) { if (av) ubi_remove_av(ai, av); continue; } if (vol->reserved_pebs == 0) { ubi_assert(i < ubi->vtbl_slots); if (!av) continue; /* * During attaching we found a volume which does not * exist according to the information in the volume * table. This must have happened due to an unclean * reboot while the volume was being removed. Discard * these eraseblocks. */ ubi_msg(ubi, "finish volume %d removal", av->vol_id); ubi_remove_av(ai, av); } else if (av) { err = check_av(vol, av); if (err) return err; } } return 0; } /** * ubi_read_volume_table - read the volume table. * @ubi: UBI device description object * @ai: attaching information * * This function reads volume table, checks it, recover from errors if needed, * or creates it if needed. Returns zero in case of success and a negative * error code in case of failure. */ int ubi_read_volume_table(struct ubi_device *ubi, struct ubi_attach_info *ai) { int err; struct ubi_ainf_volume *av; empty_vtbl_record.crc = cpu_to_be32(0xf116c36b); /* * The number of supported volumes is limited by the eraseblock size * and by the UBI_MAX_VOLUMES constant. */ if (ubi->leb_size < UBI_VTBL_RECORD_SIZE) { ubi_err(ubi, "LEB size too small for a volume record"); return -EINVAL; } ubi->vtbl_slots = ubi->leb_size / UBI_VTBL_RECORD_SIZE; if (ubi->vtbl_slots > UBI_MAX_VOLUMES) ubi->vtbl_slots = UBI_MAX_VOLUMES; ubi->vtbl_size = ubi->vtbl_slots * UBI_VTBL_RECORD_SIZE; ubi->vtbl_size = ALIGN(ubi->vtbl_size, ubi->min_io_size); av = ubi_find_av(ai, UBI_LAYOUT_VOLUME_ID); if (!av) { /* * No logical eraseblocks belonging to the layout volume were * found. This could mean that the flash is just empty. In * this case we create empty layout volume. * * But if flash is not empty this must be a corruption or the * MTD device just contains garbage. */ if (ai->is_empty) { ubi->vtbl = create_empty_lvol(ubi, ai); if (IS_ERR(ubi->vtbl)) return PTR_ERR(ubi->vtbl); } else { ubi_err(ubi, "the layout volume was not found"); return -EINVAL; } } else { if (av->leb_count > UBI_LAYOUT_VOLUME_EBS) { /* This must not happen with proper UBI images */ ubi_err(ubi, "too many LEBs (%d) in layout volume", av->leb_count); return -EINVAL; } ubi->vtbl = process_lvol(ubi, ai, av); if (IS_ERR(ubi->vtbl)) return PTR_ERR(ubi->vtbl); } ubi->avail_pebs = ubi->good_peb_count - ubi->corr_peb_count; /* * The layout volume is OK, initialize the corresponding in-RAM data * structures. */ err = init_volumes(ubi, ai, ubi->vtbl); if (err) goto out_free; /* * Make sure that the attaching information is consistent to the * information stored in the volume table. */ err = check_attaching_info(ubi, ai); if (err) goto out_free; return 0; out_free: vfree(ubi->vtbl); ubi_free_all_volumes(ubi); return err; } /** * self_vtbl_check - check volume table. * @ubi: UBI device description object */ static void self_vtbl_check(const struct ubi_device *ubi) { if (!ubi_dbg_chk_gen(ubi)) return; if (vtbl_check(ubi, ubi->vtbl)) { ubi_err(ubi, "self-check failed"); BUG(); } } |
| 2 2 2 2 2 2 2 2 2 2 2 5 39 39 39 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/if_bridge.h> #include <linux/in.h> #include <linux/list.h> #include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/rhashtable.h> #include <linux/rhashtable-types.h> #include <linux/rtnetlink.h> #include <linux/skbuff.h> #include <linux/types.h> #include <net/netlink.h> #include <net/vxlan.h> #include "vxlan_private.h" struct vxlan_mdb_entry_key { union vxlan_addr src; union vxlan_addr dst; __be32 vni; }; struct vxlan_mdb_entry { struct rhash_head rhnode; struct list_head remotes; struct vxlan_mdb_entry_key key; struct hlist_node mdb_node; struct rcu_head rcu; }; #define VXLAN_MDB_REMOTE_F_BLOCKED BIT(0) struct vxlan_mdb_remote { struct list_head list; struct vxlan_rdst __rcu *rd; u8 flags; u8 filter_mode; u8 rt_protocol; struct hlist_head src_list; struct rcu_head rcu; }; #define VXLAN_SGRP_F_DELETE BIT(0) struct vxlan_mdb_src_entry { struct hlist_node node; union vxlan_addr addr; u8 flags; }; struct vxlan_mdb_dump_ctx { long reserved; long entry_idx; long remote_idx; }; struct vxlan_mdb_config_src_entry { union vxlan_addr addr; struct list_head node; }; struct vxlan_mdb_config { struct vxlan_dev *vxlan; struct vxlan_mdb_entry_key group; struct list_head src_list; union vxlan_addr remote_ip; u32 remote_ifindex; __be32 remote_vni; __be16 remote_port; u16 nlflags; u8 flags; u8 filter_mode; u8 rt_protocol; }; struct vxlan_mdb_flush_desc { union vxlan_addr remote_ip; __be32 src_vni; __be32 remote_vni; __be16 remote_port; u8 rt_protocol; }; static const struct rhashtable_params vxlan_mdb_rht_params = { .head_offset = offsetof(struct vxlan_mdb_entry, rhnode), .key_offset = offsetof(struct vxlan_mdb_entry, key), .key_len = sizeof(struct vxlan_mdb_entry_key), .automatic_shrinking = true, }; static int __vxlan_mdb_add(const struct vxlan_mdb_config *cfg, struct netlink_ext_ack *extack); static int __vxlan_mdb_del(const struct vxlan_mdb_config *cfg, struct netlink_ext_ack *extack); static void vxlan_br_mdb_entry_fill(const struct vxlan_dev *vxlan, const struct vxlan_mdb_entry *mdb_entry, const struct vxlan_mdb_remote *remote, struct br_mdb_entry *e) { const union vxlan_addr *dst = &mdb_entry->key.dst; memset(e, 0, sizeof(*e)); e->ifindex = vxlan->dev->ifindex; e->state = MDB_PERMANENT; if (remote->flags & VXLAN_MDB_REMOTE_F_BLOCKED) e->flags |= MDB_FLAGS_BLOCKED; switch (dst->sa.sa_family) { case AF_INET: e->addr.u.ip4 = dst->sin.sin_addr.s_addr; e->addr.proto = htons(ETH_P_IP); break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: e->addr.u.ip6 = dst->sin6.sin6_addr; e->addr.proto = htons(ETH_P_IPV6); break; #endif } } static int vxlan_mdb_entry_info_fill_srcs(struct sk_buff *skb, const struct vxlan_mdb_remote *remote) { struct vxlan_mdb_src_entry *ent; struct nlattr *nest; if (hlist_empty(&remote->src_list)) return 0; nest = nla_nest_start(skb, MDBA_MDB_EATTR_SRC_LIST); if (!nest) return -EMSGSIZE; hlist_for_each_entry(ent, &remote->src_list, node) { struct nlattr *nest_ent; nest_ent = nla_nest_start(skb, MDBA_MDB_SRCLIST_ENTRY); if (!nest_ent) goto out_cancel_err; if (vxlan_nla_put_addr(skb, MDBA_MDB_SRCATTR_ADDRESS, &ent->addr) || nla_put_u32(skb, MDBA_MDB_SRCATTR_TIMER, 0)) goto out_cancel_err; nla_nest_end(skb, nest_ent); } nla_nest_end(skb, nest); return 0; out_cancel_err: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static int vxlan_mdb_entry_info_fill(const struct vxlan_dev *vxlan, struct sk_buff *skb, const struct vxlan_mdb_entry *mdb_entry, const struct vxlan_mdb_remote *remote) { struct vxlan_rdst *rd = rtnl_dereference(remote->rd); struct br_mdb_entry e; struct nlattr *nest; nest = nla_nest_start_noflag(skb, MDBA_MDB_ENTRY_INFO); if (!nest) return -EMSGSIZE; vxlan_br_mdb_entry_fill(vxlan, mdb_entry, remote, &e); if (nla_put_nohdr(skb, sizeof(e), &e) || nla_put_u32(skb, MDBA_MDB_EATTR_TIMER, 0)) goto nest_err; if (!vxlan_addr_any(&mdb_entry->key.src) && vxlan_nla_put_addr(skb, MDBA_MDB_EATTR_SOURCE, &mdb_entry->key.src)) goto nest_err; if (nla_put_u8(skb, MDBA_MDB_EATTR_RTPROT, remote->rt_protocol) || nla_put_u8(skb, MDBA_MDB_EATTR_GROUP_MODE, remote->filter_mode) || vxlan_mdb_entry_info_fill_srcs(skb, remote) || vxlan_nla_put_addr(skb, MDBA_MDB_EATTR_DST, &rd->remote_ip)) goto nest_err; if (rd->remote_port && rd->remote_port != vxlan->cfg.dst_port && nla_put_u16(skb, MDBA_MDB_EATTR_DST_PORT, be16_to_cpu(rd->remote_port))) goto nest_err; if (rd->remote_vni != vxlan->default_dst.remote_vni && nla_put_u32(skb, MDBA_MDB_EATTR_VNI, be32_to_cpu(rd->remote_vni))) goto nest_err; if (rd->remote_ifindex && nla_put_u32(skb, MDBA_MDB_EATTR_IFINDEX, rd->remote_ifindex)) goto nest_err; if ((vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) && mdb_entry->key.vni && nla_put_u32(skb, MDBA_MDB_EATTR_SRC_VNI, be32_to_cpu(mdb_entry->key.vni))) goto nest_err; nla_nest_end(skb, nest); return 0; nest_err: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static int vxlan_mdb_entry_fill(const struct vxlan_dev *vxlan, struct sk_buff *skb, struct vxlan_mdb_dump_ctx *ctx, const struct vxlan_mdb_entry *mdb_entry) { int remote_idx = 0, s_remote_idx = ctx->remote_idx; struct vxlan_mdb_remote *remote; struct nlattr *nest; int err = 0; nest = nla_nest_start_noflag(skb, MDBA_MDB_ENTRY); if (!nest) return -EMSGSIZE; list_for_each_entry(remote, &mdb_entry->remotes, list) { if (remote_idx < s_remote_idx) goto skip; err = vxlan_mdb_entry_info_fill(vxlan, skb, mdb_entry, remote); if (err) break; skip: remote_idx++; } ctx->remote_idx = err ? remote_idx : 0; nla_nest_end(skb, nest); return err; } static int vxlan_mdb_fill(const struct vxlan_dev *vxlan, struct sk_buff *skb, struct vxlan_mdb_dump_ctx *ctx) { int entry_idx = 0, s_entry_idx = ctx->entry_idx; struct vxlan_mdb_entry *mdb_entry; struct nlattr *nest; int err = 0; nest = nla_nest_start_noflag(skb, MDBA_MDB); if (!nest) return -EMSGSIZE; hlist_for_each_entry(mdb_entry, &vxlan->mdb_list, mdb_node) { if (entry_idx < s_entry_idx) goto skip; err = vxlan_mdb_entry_fill(vxlan, skb, ctx, mdb_entry); if (err) break; skip: entry_idx++; } ctx->entry_idx = err ? entry_idx : 0; nla_nest_end(skb, nest); return err; } int vxlan_mdb_dump(struct net_device *dev, struct sk_buff *skb, struct netlink_callback *cb) { struct vxlan_mdb_dump_ctx *ctx = (void *)cb->ctx; struct vxlan_dev *vxlan = netdev_priv(dev); struct br_port_msg *bpm; struct nlmsghdr *nlh; int err; ASSERT_RTNL(); NL_ASSERT_CTX_FITS(struct vxlan_mdb_dump_ctx); nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWMDB, sizeof(*bpm), NLM_F_MULTI); if (!nlh) return -EMSGSIZE; bpm = nlmsg_data(nlh); memset(bpm, 0, sizeof(*bpm)); bpm->family = AF_BRIDGE; bpm->ifindex = dev->ifindex; err = vxlan_mdb_fill(vxlan, skb, ctx); nlmsg_end(skb, nlh); cb->seq = vxlan->mdb_seq; nl_dump_check_consistent(cb, nlh); return err; } static const struct nla_policy vxlan_mdbe_src_list_entry_pol[MDBE_SRCATTR_MAX + 1] = { [MDBE_SRCATTR_ADDRESS] = NLA_POLICY_RANGE(NLA_BINARY, sizeof(struct in_addr), sizeof(struct in6_addr)), }; static const struct nla_policy vxlan_mdbe_src_list_pol[MDBE_SRC_LIST_MAX + 1] = { [MDBE_SRC_LIST_ENTRY] = NLA_POLICY_NESTED(vxlan_mdbe_src_list_entry_pol), }; static const struct netlink_range_validation vni_range = { .max = VXLAN_N_VID - 1, }; static const struct nla_policy vxlan_mdbe_attrs_pol[MDBE_ATTR_MAX + 1] = { [MDBE_ATTR_SOURCE] = NLA_POLICY_RANGE(NLA_BINARY, sizeof(struct in_addr), sizeof(struct in6_addr)), [MDBE_ATTR_GROUP_MODE] = NLA_POLICY_RANGE(NLA_U8, MCAST_EXCLUDE, MCAST_INCLUDE), [MDBE_ATTR_SRC_LIST] = NLA_POLICY_NESTED(vxlan_mdbe_src_list_pol), [MDBE_ATTR_RTPROT] = NLA_POLICY_MIN(NLA_U8, RTPROT_STATIC), [MDBE_ATTR_DST] = NLA_POLICY_RANGE(NLA_BINARY, sizeof(struct in_addr), sizeof(struct in6_addr)), [MDBE_ATTR_DST_PORT] = { .type = NLA_U16 }, [MDBE_ATTR_VNI] = NLA_POLICY_FULL_RANGE(NLA_U32, &vni_range), [MDBE_ATTR_IFINDEX] = NLA_POLICY_MIN(NLA_S32, 1), [MDBE_ATTR_SRC_VNI] = NLA_POLICY_FULL_RANGE(NLA_U32, &vni_range), }; static bool vxlan_mdb_is_valid_source(const struct nlattr *attr, __be16 proto, struct netlink_ext_ack *extack) { switch (proto) { case htons(ETH_P_IP): if (nla_len(attr) != sizeof(struct in_addr)) { NL_SET_ERR_MSG_MOD(extack, "IPv4 invalid source address length"); return false; } if (ipv4_is_multicast(nla_get_in_addr(attr))) { NL_SET_ERR_MSG_MOD(extack, "IPv4 multicast source address is not allowed"); return false; } break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): { struct in6_addr src; if (nla_len(attr) != sizeof(struct in6_addr)) { NL_SET_ERR_MSG_MOD(extack, "IPv6 invalid source address length"); return false; } src = nla_get_in6_addr(attr); if (ipv6_addr_is_multicast(&src)) { NL_SET_ERR_MSG_MOD(extack, "IPv6 multicast source address is not allowed"); return false; } break; } #endif default: NL_SET_ERR_MSG_MOD(extack, "Invalid protocol used with source address"); return false; } return true; } static void vxlan_mdb_group_set(struct vxlan_mdb_entry_key *group, const struct br_mdb_entry *entry, const struct nlattr *source_attr) { switch (entry->addr.proto) { case htons(ETH_P_IP): group->dst.sa.sa_family = AF_INET; group->dst.sin.sin_addr.s_addr = entry->addr.u.ip4; break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): group->dst.sa.sa_family = AF_INET6; group->dst.sin6.sin6_addr = entry->addr.u.ip6; break; #endif } if (source_attr) vxlan_nla_get_addr(&group->src, source_attr); } static bool vxlan_mdb_is_star_g(const struct vxlan_mdb_entry_key *group) { return !vxlan_addr_any(&group->dst) && vxlan_addr_any(&group->src); } static bool vxlan_mdb_is_sg(const struct vxlan_mdb_entry_key *group) { return !vxlan_addr_any(&group->dst) && !vxlan_addr_any(&group->src); } static int vxlan_mdb_config_src_entry_init(struct vxlan_mdb_config *cfg, __be16 proto, const struct nlattr *src_entry, struct netlink_ext_ack *extack) { struct nlattr *tb[MDBE_SRCATTR_MAX + 1]; struct vxlan_mdb_config_src_entry *src; int err; err = nla_parse_nested(tb, MDBE_SRCATTR_MAX, src_entry, vxlan_mdbe_src_list_entry_pol, extack); if (err) return err; if (NL_REQ_ATTR_CHECK(extack, src_entry, tb, MDBE_SRCATTR_ADDRESS)) return -EINVAL; if (!vxlan_mdb_is_valid_source(tb[MDBE_SRCATTR_ADDRESS], proto, extack)) return -EINVAL; src = kzalloc(sizeof(*src), GFP_KERNEL); if (!src) return -ENOMEM; err = vxlan_nla_get_addr(&src->addr, tb[MDBE_SRCATTR_ADDRESS]); if (err) goto err_free_src; list_add_tail(&src->node, &cfg->src_list); return 0; err_free_src: kfree(src); return err; } static void vxlan_mdb_config_src_entry_fini(struct vxlan_mdb_config_src_entry *src) { list_del(&src->node); kfree(src); } static int vxlan_mdb_config_src_list_init(struct vxlan_mdb_config *cfg, __be16 proto, const struct nlattr *src_list, struct netlink_ext_ack *extack) { struct vxlan_mdb_config_src_entry *src, *tmp; struct nlattr *src_entry; int rem, err; nla_for_each_nested(src_entry, src_list, rem) { err = vxlan_mdb_config_src_entry_init(cfg, proto, src_entry, extack); if (err) goto err_src_entry_init; } return 0; err_src_entry_init: list_for_each_entry_safe_reverse(src, tmp, &cfg->src_list, node) vxlan_mdb_config_src_entry_fini(src); return err; } static void vxlan_mdb_config_src_list_fini(struct vxlan_mdb_config *cfg) { struct vxlan_mdb_config_src_entry *src, *tmp; list_for_each_entry_safe_reverse(src, tmp, &cfg->src_list, node) vxlan_mdb_config_src_entry_fini(src); } static int vxlan_mdb_config_attrs_init(struct vxlan_mdb_config *cfg, const struct br_mdb_entry *entry, const struct nlattr *set_attrs, struct netlink_ext_ack *extack) { struct nlattr *mdbe_attrs[MDBE_ATTR_MAX + 1]; int err; err = nla_parse_nested(mdbe_attrs, MDBE_ATTR_MAX, set_attrs, vxlan_mdbe_attrs_pol, extack); if (err) return err; if (NL_REQ_ATTR_CHECK(extack, set_attrs, mdbe_attrs, MDBE_ATTR_DST)) { NL_SET_ERR_MSG_MOD(extack, "Missing remote destination IP address"); return -EINVAL; } if (mdbe_attrs[MDBE_ATTR_SOURCE] && !vxlan_mdb_is_valid_source(mdbe_attrs[MDBE_ATTR_SOURCE], entry->addr.proto, extack)) return -EINVAL; vxlan_mdb_group_set(&cfg->group, entry, mdbe_attrs[MDBE_ATTR_SOURCE]); /* rtnetlink code only validates that IPv4 group address is * multicast. */ if (!vxlan_addr_is_multicast(&cfg->group.dst) && !vxlan_addr_any(&cfg->group.dst)) { NL_SET_ERR_MSG_MOD(extack, "Group address is not multicast"); return -EINVAL; } if (vxlan_addr_any(&cfg->group.dst) && mdbe_attrs[MDBE_ATTR_SOURCE]) { NL_SET_ERR_MSG_MOD(extack, "Source cannot be specified for the all-zeros entry"); return -EINVAL; } if (vxlan_mdb_is_sg(&cfg->group)) cfg->filter_mode = MCAST_INCLUDE; if (mdbe_attrs[MDBE_ATTR_GROUP_MODE]) { if (!vxlan_mdb_is_star_g(&cfg->group)) { NL_SET_ERR_MSG_MOD(extack, "Filter mode can only be set for (*, G) entries"); return -EINVAL; } cfg->filter_mode = nla_get_u8(mdbe_attrs[MDBE_ATTR_GROUP_MODE]); } if (mdbe_attrs[MDBE_ATTR_SRC_LIST]) { if (!vxlan_mdb_is_star_g(&cfg->group)) { NL_SET_ERR_MSG_MOD(extack, "Source list can only be set for (*, G) entries"); return -EINVAL; } if (!mdbe_attrs[MDBE_ATTR_GROUP_MODE]) { NL_SET_ERR_MSG_MOD(extack, "Source list cannot be set without filter mode"); return -EINVAL; } err = vxlan_mdb_config_src_list_init(cfg, entry->addr.proto, mdbe_attrs[MDBE_ATTR_SRC_LIST], extack); if (err) return err; } if (vxlan_mdb_is_star_g(&cfg->group) && list_empty(&cfg->src_list) && cfg->filter_mode == MCAST_INCLUDE) { NL_SET_ERR_MSG_MOD(extack, "Cannot add (*, G) INCLUDE with an empty source list"); return -EINVAL; } if (mdbe_attrs[MDBE_ATTR_RTPROT]) cfg->rt_protocol = nla_get_u8(mdbe_attrs[MDBE_ATTR_RTPROT]); err = vxlan_nla_get_addr(&cfg->remote_ip, mdbe_attrs[MDBE_ATTR_DST]); if (err) { NL_SET_ERR_MSG_MOD(extack, "Invalid remote destination address"); goto err_src_list_fini; } if (mdbe_attrs[MDBE_ATTR_DST_PORT]) cfg->remote_port = cpu_to_be16(nla_get_u16(mdbe_attrs[MDBE_ATTR_DST_PORT])); if (mdbe_attrs[MDBE_ATTR_VNI]) cfg->remote_vni = cpu_to_be32(nla_get_u32(mdbe_attrs[MDBE_ATTR_VNI])); if (mdbe_attrs[MDBE_ATTR_IFINDEX]) { cfg->remote_ifindex = nla_get_s32(mdbe_attrs[MDBE_ATTR_IFINDEX]); if (!__dev_get_by_index(cfg->vxlan->net, cfg->remote_ifindex)) { NL_SET_ERR_MSG_MOD(extack, "Outgoing interface not found"); err = -EINVAL; goto err_src_list_fini; } } if (mdbe_attrs[MDBE_ATTR_SRC_VNI]) cfg->group.vni = cpu_to_be32(nla_get_u32(mdbe_attrs[MDBE_ATTR_SRC_VNI])); return 0; err_src_list_fini: vxlan_mdb_config_src_list_fini(cfg); return err; } static int vxlan_mdb_config_init(struct vxlan_mdb_config *cfg, struct net_device *dev, struct nlattr *tb[], u16 nlmsg_flags, struct netlink_ext_ack *extack) { struct br_mdb_entry *entry = nla_data(tb[MDBA_SET_ENTRY]); struct vxlan_dev *vxlan = netdev_priv(dev); memset(cfg, 0, sizeof(*cfg)); cfg->vxlan = vxlan; cfg->group.vni = vxlan->default_dst.remote_vni; INIT_LIST_HEAD(&cfg->src_list); cfg->nlflags = nlmsg_flags; cfg->filter_mode = MCAST_EXCLUDE; cfg->rt_protocol = RTPROT_STATIC; cfg->remote_vni = vxlan->default_dst.remote_vni; cfg->remote_port = vxlan->cfg.dst_port; if (entry->ifindex != dev->ifindex) { NL_SET_ERR_MSG_MOD(extack, "Port net device must be the VXLAN net device"); return -EINVAL; } /* State is not part of the entry key and can be ignored on deletion * requests. */ if ((nlmsg_flags & (NLM_F_CREATE | NLM_F_REPLACE)) && entry->state != MDB_PERMANENT) { NL_SET_ERR_MSG_MOD(extack, "MDB entry must be permanent"); return -EINVAL; } if (entry->flags) { NL_SET_ERR_MSG_MOD(extack, "Invalid MDB entry flags"); return -EINVAL; } if (entry->vid) { NL_SET_ERR_MSG_MOD(extack, "VID must not be specified"); return -EINVAL; } if (entry->addr.proto != htons(ETH_P_IP) && entry->addr.proto != htons(ETH_P_IPV6)) { NL_SET_ERR_MSG_MOD(extack, "Group address must be an IPv4 / IPv6 address"); return -EINVAL; } if (NL_REQ_ATTR_CHECK(extack, NULL, tb, MDBA_SET_ENTRY_ATTRS)) { NL_SET_ERR_MSG_MOD(extack, "Missing MDBA_SET_ENTRY_ATTRS attribute"); return -EINVAL; } return vxlan_mdb_config_attrs_init(cfg, entry, tb[MDBA_SET_ENTRY_ATTRS], extack); } static void vxlan_mdb_config_fini(struct vxlan_mdb_config *cfg) { vxlan_mdb_config_src_list_fini(cfg); } static struct vxlan_mdb_entry * vxlan_mdb_entry_lookup(struct vxlan_dev *vxlan, const struct vxlan_mdb_entry_key *group) { return rhashtable_lookup_fast(&vxlan->mdb_tbl, group, vxlan_mdb_rht_params); } static struct vxlan_mdb_remote * vxlan_mdb_remote_lookup(const struct vxlan_mdb_entry *mdb_entry, const union vxlan_addr *addr) { struct vxlan_mdb_remote *remote; list_for_each_entry(remote, &mdb_entry->remotes, list) { struct vxlan_rdst *rd = rtnl_dereference(remote->rd); if (vxlan_addr_equal(addr, &rd->remote_ip)) return remote; } return NULL; } static void vxlan_mdb_rdst_free(struct rcu_head *head) { struct vxlan_rdst *rd = container_of(head, struct vxlan_rdst, rcu); dst_cache_destroy(&rd->dst_cache); kfree(rd); } static int vxlan_mdb_remote_rdst_init(const struct vxlan_mdb_config *cfg, struct vxlan_mdb_remote *remote) { struct vxlan_rdst *rd; int err; rd = kzalloc(sizeof(*rd), GFP_KERNEL); if (!rd) return -ENOMEM; err = dst_cache_init(&rd->dst_cache, GFP_KERNEL); if (err) goto err_free_rdst; rd->remote_ip = cfg->remote_ip; rd->remote_port = cfg->remote_port; rd->remote_vni = cfg->remote_vni; rd->remote_ifindex = cfg->remote_ifindex; rcu_assign_pointer(remote->rd, rd); return 0; err_free_rdst: kfree(rd); return err; } static void vxlan_mdb_remote_rdst_fini(struct vxlan_rdst *rd) { call_rcu(&rd->rcu, vxlan_mdb_rdst_free); } static int vxlan_mdb_remote_init(const struct vxlan_mdb_config *cfg, struct vxlan_mdb_remote *remote) { int err; err = vxlan_mdb_remote_rdst_init(cfg, remote); if (err) return err; remote->flags = cfg->flags; remote->filter_mode = cfg->filter_mode; remote->rt_protocol = cfg->rt_protocol; INIT_HLIST_HEAD(&remote->src_list); return 0; } static void vxlan_mdb_remote_fini(struct vxlan_dev *vxlan, struct vxlan_mdb_remote *remote) { WARN_ON_ONCE(!hlist_empty(&remote->src_list)); vxlan_mdb_remote_rdst_fini(rtnl_dereference(remote->rd)); } static struct vxlan_mdb_src_entry * vxlan_mdb_remote_src_entry_lookup(const struct vxlan_mdb_remote *remote, const union vxlan_addr *addr) { struct vxlan_mdb_src_entry *ent; hlist_for_each_entry(ent, &remote->src_list, node) { if (vxlan_addr_equal(&ent->addr, addr)) return ent; } return NULL; } static struct vxlan_mdb_src_entry * vxlan_mdb_remote_src_entry_add(struct vxlan_mdb_remote *remote, const union vxlan_addr *addr) { struct vxlan_mdb_src_entry *ent; ent = kzalloc(sizeof(*ent), GFP_KERNEL); if (!ent) return NULL; ent->addr = *addr; hlist_add_head(&ent->node, &remote->src_list); return ent; } static void vxlan_mdb_remote_src_entry_del(struct vxlan_mdb_src_entry *ent) { hlist_del(&ent->node); kfree(ent); } static int vxlan_mdb_remote_src_fwd_add(const struct vxlan_mdb_config *cfg, const union vxlan_addr *addr, struct netlink_ext_ack *extack) { struct vxlan_mdb_config sg_cfg; memset(&sg_cfg, 0, sizeof(sg_cfg)); sg_cfg.vxlan = cfg->vxlan; sg_cfg.group.src = *addr; sg_cfg.group.dst = cfg->group.dst; sg_cfg.group.vni = cfg->group.vni; INIT_LIST_HEAD(&sg_cfg.src_list); sg_cfg.remote_ip = cfg->remote_ip; sg_cfg.remote_ifindex = cfg->remote_ifindex; sg_cfg.remote_vni = cfg->remote_vni; sg_cfg.remote_port = cfg->remote_port; sg_cfg.nlflags = cfg->nlflags; sg_cfg.filter_mode = MCAST_INCLUDE; if (cfg->filter_mode == MCAST_EXCLUDE) sg_cfg.flags = VXLAN_MDB_REMOTE_F_BLOCKED; sg_cfg.rt_protocol = cfg->rt_protocol; return __vxlan_mdb_add(&sg_cfg, extack); } static void vxlan_mdb_remote_src_fwd_del(struct vxlan_dev *vxlan, const struct vxlan_mdb_entry_key *group, const struct vxlan_mdb_remote *remote, const union vxlan_addr *addr) { struct vxlan_rdst *rd = rtnl_dereference(remote->rd); struct vxlan_mdb_config sg_cfg; memset(&sg_cfg, 0, sizeof(sg_cfg)); sg_cfg.vxlan = vxlan; sg_cfg.group.src = *addr; sg_cfg.group.dst = group->dst; sg_cfg.group.vni = group->vni; INIT_LIST_HEAD(&sg_cfg.src_list); sg_cfg.remote_ip = rd->remote_ip; __vxlan_mdb_del(&sg_cfg, NULL); } static int vxlan_mdb_remote_src_add(const struct vxlan_mdb_config *cfg, struct vxlan_mdb_remote *remote, const struct vxlan_mdb_config_src_entry *src, struct netlink_ext_ack *extack) { struct vxlan_mdb_src_entry *ent; int err; ent = vxlan_mdb_remote_src_entry_lookup(remote, &src->addr); if (!ent) { ent = vxlan_mdb_remote_src_entry_add(remote, &src->addr); if (!ent) return -ENOMEM; } else if (!(cfg->nlflags & NLM_F_REPLACE)) { NL_SET_ERR_MSG_MOD(extack, "Source entry already exists"); return -EEXIST; } err = vxlan_mdb_remote_src_fwd_add(cfg, &ent->addr, extack); if (err) goto err_src_del; /* Clear flags in case source entry was marked for deletion as part of * replace flow. */ ent->flags = 0; return 0; err_src_del: vxlan_mdb_remote_src_entry_del(ent); return err; } static void vxlan_mdb_remote_src_del(struct vxlan_dev *vxlan, const struct vxlan_mdb_entry_key *group, const struct vxlan_mdb_remote *remote, struct vxlan_mdb_src_entry *ent) { vxlan_mdb_remote_src_fwd_del(vxlan, group, remote, &ent->addr); vxlan_mdb_remote_src_entry_del(ent); } static int vxlan_mdb_remote_srcs_add(const struct vxlan_mdb_config *cfg, struct vxlan_mdb_remote *remote, struct netlink_ext_ack *extack) { struct vxlan_mdb_config_src_entry *src; struct vxlan_mdb_src_entry *ent; struct hlist_node *tmp; int err; list_for_each_entry(src, &cfg->src_list, node) { err = vxlan_mdb_remote_src_add(cfg, remote, src, extack); if (err) goto err_src_del; } return 0; err_src_del: hlist_for_each_entry_safe(ent, tmp, &remote->src_list, node) vxlan_mdb_remote_src_del(cfg->vxlan, &cfg->group, remote, ent); return err; } static void vxlan_mdb_remote_srcs_del(struct vxlan_dev *vxlan, const struct vxlan_mdb_entry_key *group, struct vxlan_mdb_remote *remote) { struct vxlan_mdb_src_entry *ent; struct hlist_node *tmp; hlist_for_each_entry_safe(ent, tmp, &remote->src_list, node) vxlan_mdb_remote_src_del(vxlan, group, remote, ent); } static size_t vxlan_mdb_nlmsg_src_list_size(const struct vxlan_mdb_entry_key *group, const struct vxlan_mdb_remote *remote) { struct vxlan_mdb_src_entry *ent; size_t nlmsg_size; if (hlist_empty(&remote->src_list)) return 0; /* MDBA_MDB_EATTR_SRC_LIST */ nlmsg_size = nla_total_size(0); hlist_for_each_entry(ent, &remote->src_list, node) { /* MDBA_MDB_SRCLIST_ENTRY */ nlmsg_size += nla_total_size(0) + /* MDBA_MDB_SRCATTR_ADDRESS */ nla_total_size(vxlan_addr_size(&group->dst)) + /* MDBA_MDB_SRCATTR_TIMER */ nla_total_size(sizeof(u8)); } return nlmsg_size; } static size_t vxlan_mdb_nlmsg_remote_size(const struct vxlan_dev *vxlan, const struct vxlan_mdb_entry *mdb_entry, const struct vxlan_mdb_remote *remote) { const struct vxlan_mdb_entry_key *group = &mdb_entry->key; struct vxlan_rdst *rd = rtnl_dereference(remote->rd); size_t nlmsg_size; /* MDBA_MDB_ENTRY_INFO */ nlmsg_size = nla_total_size(sizeof(struct br_mdb_entry)) + /* MDBA_MDB_EATTR_TIMER */ nla_total_size(sizeof(u32)); /* MDBA_MDB_EATTR_SOURCE */ if (vxlan_mdb_is_sg(group)) nlmsg_size += nla_total_size(vxlan_addr_size(&group->dst)); /* MDBA_MDB_EATTR_RTPROT */ nlmsg_size += nla_total_size(sizeof(u8)); /* MDBA_MDB_EATTR_SRC_LIST */ nlmsg_size += vxlan_mdb_nlmsg_src_list_size(group, remote); /* MDBA_MDB_EATTR_GROUP_MODE */ nlmsg_size += nla_total_size(sizeof(u8)); /* MDBA_MDB_EATTR_DST */ nlmsg_size += nla_total_size(vxlan_addr_size(&rd->remote_ip)); /* MDBA_MDB_EATTR_DST_PORT */ if (rd->remote_port && rd->remote_port != vxlan->cfg.dst_port) nlmsg_size += nla_total_size(sizeof(u16)); /* MDBA_MDB_EATTR_VNI */ if (rd->remote_vni != vxlan->default_dst.remote_vni) nlmsg_size += nla_total_size(sizeof(u32)); /* MDBA_MDB_EATTR_IFINDEX */ if (rd->remote_ifindex) nlmsg_size += nla_total_size(sizeof(u32)); /* MDBA_MDB_EATTR_SRC_VNI */ if ((vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) && group->vni) nlmsg_size += nla_total_size(sizeof(u32)); return nlmsg_size; } static size_t vxlan_mdb_nlmsg_size(const struct vxlan_dev *vxlan, const struct vxlan_mdb_entry *mdb_entry, const struct vxlan_mdb_remote *remote) { return NLMSG_ALIGN(sizeof(struct br_port_msg)) + /* MDBA_MDB */ nla_total_size(0) + /* MDBA_MDB_ENTRY */ nla_total_size(0) + /* Remote entry */ vxlan_mdb_nlmsg_remote_size(vxlan, mdb_entry, remote); } static int vxlan_mdb_nlmsg_fill(const struct vxlan_dev *vxlan, struct sk_buff *skb, const struct vxlan_mdb_entry *mdb_entry, const struct vxlan_mdb_remote *remote, int type) { struct nlattr *mdb_nest, *mdb_entry_nest; struct br_port_msg *bpm; struct nlmsghdr *nlh; nlh = nlmsg_put(skb, 0, 0, type, sizeof(*bpm), 0); if (!nlh) return -EMSGSIZE; bpm = nlmsg_data(nlh); memset(bpm, 0, sizeof(*bpm)); bpm->family = AF_BRIDGE; bpm->ifindex = vxlan->dev->ifindex; mdb_nest = nla_nest_start_noflag(skb, MDBA_MDB); if (!mdb_nest) goto cancel; mdb_entry_nest = nla_nest_start_noflag(skb, MDBA_MDB_ENTRY); if (!mdb_entry_nest) goto cancel; if (vxlan_mdb_entry_info_fill(vxlan, skb, mdb_entry, remote)) goto cancel; nla_nest_end(skb, mdb_entry_nest); nla_nest_end(skb, mdb_nest); nlmsg_end(skb, nlh); return 0; cancel: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static void vxlan_mdb_remote_notify(const struct vxlan_dev *vxlan, const struct vxlan_mdb_entry *mdb_entry, const struct vxlan_mdb_remote *remote, int type) { struct net *net = dev_net(vxlan->dev); struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(vxlan_mdb_nlmsg_size(vxlan, mdb_entry, remote), GFP_KERNEL); if (!skb) goto errout; err = vxlan_mdb_nlmsg_fill(vxlan, skb, mdb_entry, remote, type); if (err) { kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_MDB, NULL, GFP_KERNEL); return; errout: rtnl_set_sk_err(net, RTNLGRP_MDB, err); } static int vxlan_mdb_remote_srcs_replace(const struct vxlan_mdb_config *cfg, const struct vxlan_mdb_entry *mdb_entry, struct vxlan_mdb_remote *remote, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = cfg->vxlan; struct vxlan_mdb_src_entry *ent; struct hlist_node *tmp; int err; hlist_for_each_entry(ent, &remote->src_list, node) ent->flags |= VXLAN_SGRP_F_DELETE; err = vxlan_mdb_remote_srcs_add(cfg, remote, extack); if (err) goto err_clear_delete; hlist_for_each_entry_safe(ent, tmp, &remote->src_list, node) { if (ent->flags & VXLAN_SGRP_F_DELETE) vxlan_mdb_remote_src_del(vxlan, &mdb_entry->key, remote, ent); } return 0; err_clear_delete: hlist_for_each_entry(ent, &remote->src_list, node) ent->flags &= ~VXLAN_SGRP_F_DELETE; return err; } static int vxlan_mdb_remote_replace(const struct vxlan_mdb_config *cfg, const struct vxlan_mdb_entry *mdb_entry, struct vxlan_mdb_remote *remote, struct netlink_ext_ack *extack) { struct vxlan_rdst *new_rd, *old_rd = rtnl_dereference(remote->rd); struct vxlan_dev *vxlan = cfg->vxlan; int err; err = vxlan_mdb_remote_rdst_init(cfg, remote); if (err) return err; new_rd = rtnl_dereference(remote->rd); err = vxlan_mdb_remote_srcs_replace(cfg, mdb_entry, remote, extack); if (err) goto err_rdst_reset; WRITE_ONCE(remote->flags, cfg->flags); WRITE_ONCE(remote->filter_mode, cfg->filter_mode); remote->rt_protocol = cfg->rt_protocol; vxlan_mdb_remote_notify(vxlan, mdb_entry, remote, RTM_NEWMDB); vxlan_mdb_remote_rdst_fini(old_rd); return 0; err_rdst_reset: rcu_assign_pointer(remote->rd, old_rd); vxlan_mdb_remote_rdst_fini(new_rd); return err; } static int vxlan_mdb_remote_add(const struct vxlan_mdb_config *cfg, struct vxlan_mdb_entry *mdb_entry, struct netlink_ext_ack *extack) { struct vxlan_mdb_remote *remote; int err; remote = vxlan_mdb_remote_lookup(mdb_entry, &cfg->remote_ip); if (remote) { if (!(cfg->nlflags & NLM_F_REPLACE)) { NL_SET_ERR_MSG_MOD(extack, "Replace not specified and MDB remote entry already exists"); return -EEXIST; } return vxlan_mdb_remote_replace(cfg, mdb_entry, remote, extack); } if (!(cfg->nlflags & NLM_F_CREATE)) { NL_SET_ERR_MSG_MOD(extack, "Create not specified and entry does not exist"); return -ENOENT; } remote = kzalloc(sizeof(*remote), GFP_KERNEL); if (!remote) return -ENOMEM; err = vxlan_mdb_remote_init(cfg, remote); if (err) { NL_SET_ERR_MSG_MOD(extack, "Failed to initialize remote MDB entry"); goto err_free_remote; } err = vxlan_mdb_remote_srcs_add(cfg, remote, extack); if (err) goto err_remote_fini; list_add_rcu(&remote->list, &mdb_entry->remotes); vxlan_mdb_remote_notify(cfg->vxlan, mdb_entry, remote, RTM_NEWMDB); return 0; err_remote_fini: vxlan_mdb_remote_fini(cfg->vxlan, remote); err_free_remote: kfree(remote); return err; } static void vxlan_mdb_remote_del(struct vxlan_dev *vxlan, struct vxlan_mdb_entry *mdb_entry, struct vxlan_mdb_remote *remote) { vxlan_mdb_remote_notify(vxlan, mdb_entry, remote, RTM_DELMDB); list_del_rcu(&remote->list); vxlan_mdb_remote_srcs_del(vxlan, &mdb_entry->key, remote); vxlan_mdb_remote_fini(vxlan, remote); kfree_rcu(remote, rcu); } static struct vxlan_mdb_entry * vxlan_mdb_entry_get(struct vxlan_dev *vxlan, const struct vxlan_mdb_entry_key *group) { struct vxlan_mdb_entry *mdb_entry; int err; mdb_entry = vxlan_mdb_entry_lookup(vxlan, group); if (mdb_entry) return mdb_entry; mdb_entry = kzalloc(sizeof(*mdb_entry), GFP_KERNEL); if (!mdb_entry) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&mdb_entry->remotes); memcpy(&mdb_entry->key, group, sizeof(mdb_entry->key)); hlist_add_head(&mdb_entry->mdb_node, &vxlan->mdb_list); err = rhashtable_lookup_insert_fast(&vxlan->mdb_tbl, &mdb_entry->rhnode, vxlan_mdb_rht_params); if (err) goto err_free_entry; if (hlist_is_singular_node(&mdb_entry->mdb_node, &vxlan->mdb_list)) vxlan->cfg.flags |= VXLAN_F_MDB; return mdb_entry; err_free_entry: hlist_del(&mdb_entry->mdb_node); kfree(mdb_entry); return ERR_PTR(err); } static void vxlan_mdb_entry_put(struct vxlan_dev *vxlan, struct vxlan_mdb_entry *mdb_entry) { if (!list_empty(&mdb_entry->remotes)) return; if (hlist_is_singular_node(&mdb_entry->mdb_node, &vxlan->mdb_list)) vxlan->cfg.flags &= ~VXLAN_F_MDB; rhashtable_remove_fast(&vxlan->mdb_tbl, &mdb_entry->rhnode, vxlan_mdb_rht_params); hlist_del(&mdb_entry->mdb_node); kfree_rcu(mdb_entry, rcu); } static int __vxlan_mdb_add(const struct vxlan_mdb_config *cfg, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = cfg->vxlan; struct vxlan_mdb_entry *mdb_entry; int err; mdb_entry = vxlan_mdb_entry_get(vxlan, &cfg->group); if (IS_ERR(mdb_entry)) return PTR_ERR(mdb_entry); err = vxlan_mdb_remote_add(cfg, mdb_entry, extack); if (err) goto err_entry_put; vxlan->mdb_seq++; return 0; err_entry_put: vxlan_mdb_entry_put(vxlan, mdb_entry); return err; } static int __vxlan_mdb_del(const struct vxlan_mdb_config *cfg, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = cfg->vxlan; struct vxlan_mdb_entry *mdb_entry; struct vxlan_mdb_remote *remote; mdb_entry = vxlan_mdb_entry_lookup(vxlan, &cfg->group); if (!mdb_entry) { NL_SET_ERR_MSG_MOD(extack, "Did not find MDB entry"); return -ENOENT; } remote = vxlan_mdb_remote_lookup(mdb_entry, &cfg->remote_ip); if (!remote) { NL_SET_ERR_MSG_MOD(extack, "Did not find MDB remote entry"); return -ENOENT; } vxlan_mdb_remote_del(vxlan, mdb_entry, remote); vxlan_mdb_entry_put(vxlan, mdb_entry); vxlan->mdb_seq++; return 0; } int vxlan_mdb_add(struct net_device *dev, struct nlattr *tb[], u16 nlmsg_flags, struct netlink_ext_ack *extack) { struct vxlan_mdb_config cfg; int err; ASSERT_RTNL(); err = vxlan_mdb_config_init(&cfg, dev, tb, nlmsg_flags, extack); if (err) return err; err = __vxlan_mdb_add(&cfg, extack); vxlan_mdb_config_fini(&cfg); return err; } int vxlan_mdb_del(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct vxlan_mdb_config cfg; int err; ASSERT_RTNL(); err = vxlan_mdb_config_init(&cfg, dev, tb, 0, extack); if (err) return err; err = __vxlan_mdb_del(&cfg, extack); vxlan_mdb_config_fini(&cfg); return err; } static const struct nla_policy vxlan_mdbe_attrs_del_bulk_pol[MDBE_ATTR_MAX + 1] = { [MDBE_ATTR_RTPROT] = NLA_POLICY_MIN(NLA_U8, RTPROT_STATIC), [MDBE_ATTR_DST] = NLA_POLICY_RANGE(NLA_BINARY, sizeof(struct in_addr), sizeof(struct in6_addr)), [MDBE_ATTR_DST_PORT] = { .type = NLA_U16 }, [MDBE_ATTR_VNI] = NLA_POLICY_FULL_RANGE(NLA_U32, &vni_range), [MDBE_ATTR_SRC_VNI] = NLA_POLICY_FULL_RANGE(NLA_U32, &vni_range), [MDBE_ATTR_STATE_MASK] = NLA_POLICY_MASK(NLA_U8, MDB_PERMANENT), }; static int vxlan_mdb_flush_desc_init(struct vxlan_dev *vxlan, struct vxlan_mdb_flush_desc *desc, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct br_mdb_entry *entry = nla_data(tb[MDBA_SET_ENTRY]); struct nlattr *mdbe_attrs[MDBE_ATTR_MAX + 1]; int err; if (entry->ifindex && entry->ifindex != vxlan->dev->ifindex) { NL_SET_ERR_MSG_MOD(extack, "Invalid port net device"); return -EINVAL; } if (entry->vid) { NL_SET_ERR_MSG_MOD(extack, "VID must not be specified"); return -EINVAL; } if (!tb[MDBA_SET_ENTRY_ATTRS]) return 0; err = nla_parse_nested(mdbe_attrs, MDBE_ATTR_MAX, tb[MDBA_SET_ENTRY_ATTRS], vxlan_mdbe_attrs_del_bulk_pol, extack); if (err) return err; if (mdbe_attrs[MDBE_ATTR_STATE_MASK]) { u8 state_mask = nla_get_u8(mdbe_attrs[MDBE_ATTR_STATE_MASK]); if ((state_mask & MDB_PERMANENT) && !(entry->state & MDB_PERMANENT)) { NL_SET_ERR_MSG_MOD(extack, "Only permanent MDB entries are supported"); return -EINVAL; } } if (mdbe_attrs[MDBE_ATTR_RTPROT]) desc->rt_protocol = nla_get_u8(mdbe_attrs[MDBE_ATTR_RTPROT]); if (mdbe_attrs[MDBE_ATTR_DST]) vxlan_nla_get_addr(&desc->remote_ip, mdbe_attrs[MDBE_ATTR_DST]); if (mdbe_attrs[MDBE_ATTR_DST_PORT]) desc->remote_port = cpu_to_be16(nla_get_u16(mdbe_attrs[MDBE_ATTR_DST_PORT])); if (mdbe_attrs[MDBE_ATTR_VNI]) desc->remote_vni = cpu_to_be32(nla_get_u32(mdbe_attrs[MDBE_ATTR_VNI])); if (mdbe_attrs[MDBE_ATTR_SRC_VNI]) desc->src_vni = cpu_to_be32(nla_get_u32(mdbe_attrs[MDBE_ATTR_SRC_VNI])); return 0; } static void vxlan_mdb_remotes_flush(struct vxlan_dev *vxlan, struct vxlan_mdb_entry *mdb_entry, const struct vxlan_mdb_flush_desc *desc) { struct vxlan_mdb_remote *remote, *tmp; list_for_each_entry_safe(remote, tmp, &mdb_entry->remotes, list) { struct vxlan_rdst *rd = rtnl_dereference(remote->rd); __be32 remote_vni; if (desc->remote_ip.sa.sa_family && !vxlan_addr_equal(&desc->remote_ip, &rd->remote_ip)) continue; /* Encapsulation is performed with source VNI if remote VNI * is not set. */ remote_vni = rd->remote_vni ? : mdb_entry->key.vni; if (desc->remote_vni && desc->remote_vni != remote_vni) continue; if (desc->remote_port && desc->remote_port != rd->remote_port) continue; if (desc->rt_protocol && desc->rt_protocol != remote->rt_protocol) continue; vxlan_mdb_remote_del(vxlan, mdb_entry, remote); } } static void vxlan_mdb_flush(struct vxlan_dev *vxlan, const struct vxlan_mdb_flush_desc *desc) { struct vxlan_mdb_entry *mdb_entry; struct hlist_node *tmp; /* The removal of an entry cannot trigger the removal of another entry * since entries are always added to the head of the list. */ hlist_for_each_entry_safe(mdb_entry, tmp, &vxlan->mdb_list, mdb_node) { if (desc->src_vni && desc->src_vni != mdb_entry->key.vni) continue; vxlan_mdb_remotes_flush(vxlan, mdb_entry, desc); /* Entry will only be removed if its remotes list is empty. */ vxlan_mdb_entry_put(vxlan, mdb_entry); } } int vxlan_mdb_del_bulk(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_mdb_flush_desc desc = {}; int err; ASSERT_RTNL(); err = vxlan_mdb_flush_desc_init(vxlan, &desc, tb, extack); if (err) return err; vxlan_mdb_flush(vxlan, &desc); return 0; } static const struct nla_policy vxlan_mdbe_attrs_get_pol[MDBE_ATTR_MAX + 1] = { [MDBE_ATTR_SOURCE] = NLA_POLICY_RANGE(NLA_BINARY, sizeof(struct in_addr), sizeof(struct in6_addr)), [MDBE_ATTR_SRC_VNI] = NLA_POLICY_FULL_RANGE(NLA_U32, &vni_range), }; static int vxlan_mdb_get_parse(struct net_device *dev, struct nlattr *tb[], struct vxlan_mdb_entry_key *group, struct netlink_ext_ack *extack) { struct br_mdb_entry *entry = nla_data(tb[MDBA_GET_ENTRY]); struct nlattr *mdbe_attrs[MDBE_ATTR_MAX + 1]; struct vxlan_dev *vxlan = netdev_priv(dev); int err; memset(group, 0, sizeof(*group)); group->vni = vxlan->default_dst.remote_vni; if (!tb[MDBA_GET_ENTRY_ATTRS]) { vxlan_mdb_group_set(group, entry, NULL); return 0; } err = nla_parse_nested(mdbe_attrs, MDBE_ATTR_MAX, tb[MDBA_GET_ENTRY_ATTRS], vxlan_mdbe_attrs_get_pol, extack); if (err) return err; if (mdbe_attrs[MDBE_ATTR_SOURCE] && !vxlan_mdb_is_valid_source(mdbe_attrs[MDBE_ATTR_SOURCE], entry->addr.proto, extack)) return -EINVAL; vxlan_mdb_group_set(group, entry, mdbe_attrs[MDBE_ATTR_SOURCE]); if (mdbe_attrs[MDBE_ATTR_SRC_VNI]) group->vni = cpu_to_be32(nla_get_u32(mdbe_attrs[MDBE_ATTR_SRC_VNI])); return 0; } static struct sk_buff * vxlan_mdb_get_reply_alloc(const struct vxlan_dev *vxlan, const struct vxlan_mdb_entry *mdb_entry) { struct vxlan_mdb_remote *remote; size_t nlmsg_size; nlmsg_size = NLMSG_ALIGN(sizeof(struct br_port_msg)) + /* MDBA_MDB */ nla_total_size(0) + /* MDBA_MDB_ENTRY */ nla_total_size(0); list_for_each_entry(remote, &mdb_entry->remotes, list) nlmsg_size += vxlan_mdb_nlmsg_remote_size(vxlan, mdb_entry, remote); return nlmsg_new(nlmsg_size, GFP_KERNEL); } static int vxlan_mdb_get_reply_fill(const struct vxlan_dev *vxlan, struct sk_buff *skb, const struct vxlan_mdb_entry *mdb_entry, u32 portid, u32 seq) { struct nlattr *mdb_nest, *mdb_entry_nest; struct vxlan_mdb_remote *remote; struct br_port_msg *bpm; struct nlmsghdr *nlh; int err; nlh = nlmsg_put(skb, portid, seq, RTM_NEWMDB, sizeof(*bpm), 0); if (!nlh) return -EMSGSIZE; bpm = nlmsg_data(nlh); memset(bpm, 0, sizeof(*bpm)); bpm->family = AF_BRIDGE; bpm->ifindex = vxlan->dev->ifindex; mdb_nest = nla_nest_start_noflag(skb, MDBA_MDB); if (!mdb_nest) { err = -EMSGSIZE; goto cancel; } mdb_entry_nest = nla_nest_start_noflag(skb, MDBA_MDB_ENTRY); if (!mdb_entry_nest) { err = -EMSGSIZE; goto cancel; } list_for_each_entry(remote, &mdb_entry->remotes, list) { err = vxlan_mdb_entry_info_fill(vxlan, skb, mdb_entry, remote); if (err) goto cancel; } nla_nest_end(skb, mdb_entry_nest); nla_nest_end(skb, mdb_nest); nlmsg_end(skb, nlh); return 0; cancel: nlmsg_cancel(skb, nlh); return err; } int vxlan_mdb_get(struct net_device *dev, struct nlattr *tb[], u32 portid, u32 seq, struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_mdb_entry *mdb_entry; struct vxlan_mdb_entry_key group; struct sk_buff *skb; int err; ASSERT_RTNL(); err = vxlan_mdb_get_parse(dev, tb, &group, extack); if (err) return err; mdb_entry = vxlan_mdb_entry_lookup(vxlan, &group); if (!mdb_entry) { NL_SET_ERR_MSG_MOD(extack, "MDB entry not found"); return -ENOENT; } skb = vxlan_mdb_get_reply_alloc(vxlan, mdb_entry); if (!skb) return -ENOMEM; err = vxlan_mdb_get_reply_fill(vxlan, skb, mdb_entry, portid, seq); if (err) { NL_SET_ERR_MSG_MOD(extack, "Failed to fill MDB get reply"); goto free; } return rtnl_unicast(skb, dev_net(dev), portid); free: kfree_skb(skb); return err; } struct vxlan_mdb_entry *vxlan_mdb_entry_skb_get(struct vxlan_dev *vxlan, struct sk_buff *skb, __be32 src_vni) { struct vxlan_mdb_entry *mdb_entry; struct vxlan_mdb_entry_key group; if (!is_multicast_ether_addr(eth_hdr(skb)->h_dest) || is_broadcast_ether_addr(eth_hdr(skb)->h_dest)) return NULL; /* When not in collect metadata mode, 'src_vni' is zero, but MDB * entries are stored with the VNI of the VXLAN device. */ if (!(vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA)) src_vni = vxlan->default_dst.remote_vni; memset(&group, 0, sizeof(group)); group.vni = src_vni; switch (skb->protocol) { case htons(ETH_P_IP): if (!pskb_may_pull(skb, sizeof(struct iphdr))) return NULL; group.dst.sa.sa_family = AF_INET; group.dst.sin.sin_addr.s_addr = ip_hdr(skb)->daddr; group.src.sa.sa_family = AF_INET; group.src.sin.sin_addr.s_addr = ip_hdr(skb)->saddr; break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) return NULL; group.dst.sa.sa_family = AF_INET6; group.dst.sin6.sin6_addr = ipv6_hdr(skb)->daddr; group.src.sa.sa_family = AF_INET6; group.src.sin6.sin6_addr = ipv6_hdr(skb)->saddr; break; #endif default: return NULL; } mdb_entry = vxlan_mdb_entry_lookup(vxlan, &group); if (mdb_entry) return mdb_entry; memset(&group.src, 0, sizeof(group.src)); mdb_entry = vxlan_mdb_entry_lookup(vxlan, &group); if (mdb_entry) return mdb_entry; /* No (S, G) or (*, G) found. Look up the all-zeros entry, but only if * the destination IP address is not link-local multicast since we want * to transmit such traffic together with broadcast and unknown unicast * traffic. */ switch (skb->protocol) { case htons(ETH_P_IP): if (ipv4_is_local_multicast(group.dst.sin.sin_addr.s_addr)) return NULL; group.dst.sin.sin_addr.s_addr = 0; break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): if (ipv6_addr_type(&group.dst.sin6.sin6_addr) & IPV6_ADDR_LINKLOCAL) return NULL; memset(&group.dst.sin6.sin6_addr, 0, sizeof(group.dst.sin6.sin6_addr)); break; #endif default: return NULL; } return vxlan_mdb_entry_lookup(vxlan, &group); } netdev_tx_t vxlan_mdb_xmit(struct vxlan_dev *vxlan, const struct vxlan_mdb_entry *mdb_entry, struct sk_buff *skb) { struct vxlan_mdb_remote *remote, *fremote = NULL; __be32 src_vni = mdb_entry->key.vni; list_for_each_entry_rcu(remote, &mdb_entry->remotes, list) { struct sk_buff *skb1; if ((vxlan_mdb_is_star_g(&mdb_entry->key) && READ_ONCE(remote->filter_mode) == MCAST_INCLUDE) || (READ_ONCE(remote->flags) & VXLAN_MDB_REMOTE_F_BLOCKED)) continue; if (!fremote) { fremote = remote; continue; } skb1 = skb_clone(skb, GFP_ATOMIC); if (skb1) vxlan_xmit_one(skb1, vxlan->dev, src_vni, rcu_dereference(remote->rd), false); } if (fremote) vxlan_xmit_one(skb, vxlan->dev, src_vni, rcu_dereference(fremote->rd), false); else kfree_skb_reason(skb, SKB_DROP_REASON_NO_TX_TARGET); return NETDEV_TX_OK; } static void vxlan_mdb_check_empty(void *ptr, void *arg) { WARN_ON_ONCE(1); } int vxlan_mdb_init(struct vxlan_dev *vxlan) { int err; err = rhashtable_init(&vxlan->mdb_tbl, &vxlan_mdb_rht_params); if (err) return err; INIT_HLIST_HEAD(&vxlan->mdb_list); return 0; } void vxlan_mdb_fini(struct vxlan_dev *vxlan) { struct vxlan_mdb_flush_desc desc = {}; vxlan_mdb_flush(vxlan, &desc); WARN_ON_ONCE(vxlan->cfg.flags & VXLAN_F_MDB); rhashtable_free_and_destroy(&vxlan->mdb_tbl, vxlan_mdb_check_empty, NULL); } |
| 49 49 39 39 1857 1854 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 | // SPDX-License-Identifier: GPL-2.0+ /* * A wrapper for multiple PHYs which passes all phy_* function calls to * multiple (actual) PHY devices. This is comes handy when initializing * all PHYs on a HCD and to keep them all in the same state. * * Copyright (C) 2018 Martin Blumenstingl <martin.blumenstingl@googlemail.com> */ #include <linux/device.h> #include <linux/list.h> #include <linux/phy/phy.h> #include <linux/of.h> #include "phy.h" struct usb_phy_roothub { struct phy *phy; struct list_head list; }; /* Allocate the roothub_entry by specific name of phy */ static int usb_phy_roothub_add_phy_by_name(struct device *dev, const char *name, struct list_head *list) { struct usb_phy_roothub *roothub_entry; struct phy *phy; phy = devm_of_phy_get(dev, dev->of_node, name); if (IS_ERR(phy)) return PTR_ERR(phy); roothub_entry = devm_kzalloc(dev, sizeof(*roothub_entry), GFP_KERNEL); if (!roothub_entry) return -ENOMEM; INIT_LIST_HEAD(&roothub_entry->list); roothub_entry->phy = phy; list_add_tail(&roothub_entry->list, list); return 0; } static int usb_phy_roothub_add_phy(struct device *dev, int index, struct list_head *list) { struct usb_phy_roothub *roothub_entry; struct phy *phy; phy = devm_of_phy_get_by_index(dev, dev->of_node, index); if (IS_ERR(phy)) { if (PTR_ERR(phy) == -ENODEV) return 0; else return PTR_ERR(phy); } roothub_entry = devm_kzalloc(dev, sizeof(*roothub_entry), GFP_KERNEL); if (!roothub_entry) return -ENOMEM; INIT_LIST_HEAD(&roothub_entry->list); roothub_entry->phy = phy; list_add_tail(&roothub_entry->list, list); return 0; } struct usb_phy_roothub *usb_phy_roothub_alloc(struct device *dev) { struct usb_phy_roothub *phy_roothub; int i, num_phys, err; if (!IS_ENABLED(CONFIG_GENERIC_PHY)) return NULL; num_phys = of_count_phandle_with_args(dev->of_node, "phys", "#phy-cells"); if (num_phys <= 0) return NULL; phy_roothub = devm_kzalloc(dev, sizeof(*phy_roothub), GFP_KERNEL); if (!phy_roothub) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&phy_roothub->list); if (!usb_phy_roothub_add_phy_by_name(dev, "usb2-phy", &phy_roothub->list)) return phy_roothub; for (i = 0; i < num_phys; i++) { err = usb_phy_roothub_add_phy(dev, i, &phy_roothub->list); if (err) return ERR_PTR(err); } return phy_roothub; } EXPORT_SYMBOL_GPL(usb_phy_roothub_alloc); /** * usb_phy_roothub_alloc_usb3_phy - alloc the roothub * @dev: the device of the host controller * * Allocate the usb phy roothub if the host use a generic usb3-phy. * * Return: On success, a pointer to the usb_phy_roothub. Otherwise, * %NULL if no use usb3 phy or %-ENOMEM if out of memory. */ struct usb_phy_roothub *usb_phy_roothub_alloc_usb3_phy(struct device *dev) { struct usb_phy_roothub *phy_roothub; int num_phys; if (!IS_ENABLED(CONFIG_GENERIC_PHY)) return NULL; num_phys = of_count_phandle_with_args(dev->of_node, "phys", "#phy-cells"); if (num_phys <= 0) return NULL; phy_roothub = devm_kzalloc(dev, sizeof(*phy_roothub), GFP_KERNEL); if (!phy_roothub) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&phy_roothub->list); if (!usb_phy_roothub_add_phy_by_name(dev, "usb3-phy", &phy_roothub->list)) return phy_roothub; return NULL; } EXPORT_SYMBOL_GPL(usb_phy_roothub_alloc_usb3_phy); int usb_phy_roothub_init(struct usb_phy_roothub *phy_roothub) { struct usb_phy_roothub *roothub_entry; struct list_head *head; int err; if (!phy_roothub) return 0; head = &phy_roothub->list; list_for_each_entry(roothub_entry, head, list) { err = phy_init(roothub_entry->phy); if (err) goto err_exit_phys; } return 0; err_exit_phys: list_for_each_entry_continue_reverse(roothub_entry, head, list) phy_exit(roothub_entry->phy); return err; } EXPORT_SYMBOL_GPL(usb_phy_roothub_init); int usb_phy_roothub_exit(struct usb_phy_roothub *phy_roothub) { struct usb_phy_roothub *roothub_entry; struct list_head *head; int err, ret = 0; if (!phy_roothub) return 0; head = &phy_roothub->list; list_for_each_entry(roothub_entry, head, list) { err = phy_exit(roothub_entry->phy); if (err) ret = err; } return ret; } EXPORT_SYMBOL_GPL(usb_phy_roothub_exit); int usb_phy_roothub_set_mode(struct usb_phy_roothub *phy_roothub, enum phy_mode mode) { struct usb_phy_roothub *roothub_entry; struct list_head *head; int err; if (!phy_roothub) return 0; head = &phy_roothub->list; list_for_each_entry(roothub_entry, head, list) { err = phy_set_mode(roothub_entry->phy, mode); if (err) goto err_out; } return 0; err_out: list_for_each_entry_continue_reverse(roothub_entry, head, list) phy_power_off(roothub_entry->phy); return err; } EXPORT_SYMBOL_GPL(usb_phy_roothub_set_mode); int usb_phy_roothub_calibrate(struct usb_phy_roothub *phy_roothub) { struct usb_phy_roothub *roothub_entry; struct list_head *head; int err; if (!phy_roothub) return 0; head = &phy_roothub->list; list_for_each_entry(roothub_entry, head, list) { err = phy_calibrate(roothub_entry->phy); if (err) return err; } return 0; } EXPORT_SYMBOL_GPL(usb_phy_roothub_calibrate); /** * usb_phy_roothub_notify_connect() - connect notification * @phy_roothub: the phy of roothub, if the host use a generic phy. * @port: the port index for connect * * If the phy needs to get connection status, the callback can be used. * Returns: %0 if successful, a negative error code otherwise */ int usb_phy_roothub_notify_connect(struct usb_phy_roothub *phy_roothub, int port) { struct usb_phy_roothub *roothub_entry; struct list_head *head; int err; if (!phy_roothub) return 0; head = &phy_roothub->list; list_for_each_entry(roothub_entry, head, list) { err = phy_notify_connect(roothub_entry->phy, port); if (err) return err; } return 0; } EXPORT_SYMBOL_GPL(usb_phy_roothub_notify_connect); /** * usb_phy_roothub_notify_disconnect() - disconnect notification * @phy_roothub: the phy of roothub, if the host use a generic phy. * @port: the port index for disconnect * * If the phy needs to get connection status, the callback can be used. * Returns: %0 if successful, a negative error code otherwise */ int usb_phy_roothub_notify_disconnect(struct usb_phy_roothub *phy_roothub, int port) { struct usb_phy_roothub *roothub_entry; struct list_head *head; int err; if (!phy_roothub) return 0; head = &phy_roothub->list; list_for_each_entry(roothub_entry, head, list) { err = phy_notify_disconnect(roothub_entry->phy, port); if (err) return err; } return 0; } EXPORT_SYMBOL_GPL(usb_phy_roothub_notify_disconnect); int usb_phy_roothub_power_on(struct usb_phy_roothub *phy_roothub) { struct usb_phy_roothub *roothub_entry; struct list_head *head; int err; if (!phy_roothub) return 0; head = &phy_roothub->list; list_for_each_entry(roothub_entry, head, list) { err = phy_power_on(roothub_entry->phy); if (err) goto err_out; } return 0; err_out: list_for_each_entry_continue_reverse(roothub_entry, head, list) phy_power_off(roothub_entry->phy); return err; } EXPORT_SYMBOL_GPL(usb_phy_roothub_power_on); void usb_phy_roothub_power_off(struct usb_phy_roothub *phy_roothub) { struct usb_phy_roothub *roothub_entry; if (!phy_roothub) return; list_for_each_entry_reverse(roothub_entry, &phy_roothub->list, list) phy_power_off(roothub_entry->phy); } EXPORT_SYMBOL_GPL(usb_phy_roothub_power_off); int usb_phy_roothub_suspend(struct device *controller_dev, struct usb_phy_roothub *phy_roothub) { usb_phy_roothub_power_off(phy_roothub); /* keep the PHYs initialized so the device can wake up the system */ if (device_may_wakeup(controller_dev)) return 0; return usb_phy_roothub_exit(phy_roothub); } EXPORT_SYMBOL_GPL(usb_phy_roothub_suspend); int usb_phy_roothub_resume(struct device *controller_dev, struct usb_phy_roothub *phy_roothub) { int err; /* if the device can't wake up the system _exit was called */ if (!device_may_wakeup(controller_dev)) { err = usb_phy_roothub_init(phy_roothub); if (err) return err; } err = usb_phy_roothub_power_on(phy_roothub); /* undo _init if _power_on failed */ if (err && !device_may_wakeup(controller_dev)) usb_phy_roothub_exit(phy_roothub); return err; } EXPORT_SYMBOL_GPL(usb_phy_roothub_resume); |
| 7 60 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Handle firewalling core * Linux ethernet bridge * * Authors: * Lennert Buytenhek <buytenh@gnu.org> * Bart De Schuymer <bdschuym@pandora.be> * * Lennert dedicates this file to Kerstin Wurdinger. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/in_route.h> #include <linux/inetdevice.h> #include <net/route.h> #include "br_private.h" #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif static void fake_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh) { } static void fake_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb) { } static u32 *fake_cow_metrics(struct dst_entry *dst, unsigned long old) { return NULL; } static struct neighbour *fake_neigh_lookup(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr) { return NULL; } static unsigned int fake_mtu(const struct dst_entry *dst) { return dst->dev->mtu; } static struct dst_ops fake_dst_ops = { .family = AF_INET, .update_pmtu = fake_update_pmtu, .redirect = fake_redirect, .cow_metrics = fake_cow_metrics, .neigh_lookup = fake_neigh_lookup, .mtu = fake_mtu, }; /* * Initialize bogus route table used to keep netfilter happy. * Currently, we fill in the PMTU entry because netfilter * refragmentation needs it, and the rt_flags entry because * ipt_REJECT needs it. Future netfilter modules might * require us to fill additional fields. */ static const u32 br_dst_default_metrics[RTAX_MAX] = { [RTAX_MTU - 1] = 1500, }; void br_netfilter_rtable_init(struct net_bridge *br) { struct rtable *rt = &br->fake_rtable; rcuref_init(&rt->dst.__rcuref, 1); rt->dst.dev = br->dev; dst_init_metrics(&rt->dst, br_dst_default_metrics, true); rt->dst.flags = DST_NOXFRM | DST_FAKE_RTABLE; rt->dst.ops = &fake_dst_ops; } int __init br_nf_core_init(void) { return dst_entries_init(&fake_dst_ops); } void br_nf_core_fini(void) { dst_entries_destroy(&fake_dst_ops); } |
| 15 14 3 2 15 11 3 2 8 2 2 2 8 8 7 1 6 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 | // SPDX-License-Identifier: GPL-2.0-only /* * VMware VMCI Driver * * Copyright (C) 2012 VMware, Inc. All rights reserved. */ #include <linux/vmw_vmci_defs.h> #include <linux/vmw_vmci_api.h> #include "vmci_context.h" #include "vmci_driver.h" #include "vmci_route.h" /* * Make a routing decision for the given source and destination handles. * This will try to determine the route using the handles and the available * devices. Will set the source context if it is invalid. */ int vmci_route(struct vmci_handle *src, const struct vmci_handle *dst, bool from_guest, enum vmci_route *route) { bool has_host_device = vmci_host_code_active(); bool has_guest_device = vmci_guest_code_active(); *route = VMCI_ROUTE_NONE; /* * "from_guest" is only ever set to true by * IOCTL_VMCI_DATAGRAM_SEND (or by the vmkernel equivalent), * which comes from the VMX, so we know it is coming from a * guest. * * To avoid inconsistencies, test these once. We will test * them again when we do the actual send to ensure that we do * not touch a non-existent device. */ /* Must have a valid destination context. */ if (VMCI_INVALID_ID == dst->context) return VMCI_ERROR_INVALID_ARGS; /* Anywhere to hypervisor. */ if (VMCI_HYPERVISOR_CONTEXT_ID == dst->context) { /* * If this message already came from a guest then we * cannot send it to the hypervisor. It must come * from a local client. */ if (from_guest) return VMCI_ERROR_DST_UNREACHABLE; /* * We must be acting as a guest in order to send to * the hypervisor. */ if (!has_guest_device) return VMCI_ERROR_DEVICE_NOT_FOUND; /* And we cannot send if the source is the host context. */ if (VMCI_HOST_CONTEXT_ID == src->context) return VMCI_ERROR_INVALID_ARGS; /* * If the client passed the ANON source handle then * respect it (both context and resource are invalid). * However, if they passed only an invalid context, * then they probably mean ANY, in which case we * should set the real context here before passing it * down. */ if (VMCI_INVALID_ID == src->context && VMCI_INVALID_ID != src->resource) src->context = vmci_get_context_id(); /* Send from local client down to the hypervisor. */ *route = VMCI_ROUTE_AS_GUEST; return VMCI_SUCCESS; } /* Anywhere to local client on host. */ if (VMCI_HOST_CONTEXT_ID == dst->context) { /* * If it is not from a guest but we are acting as a * guest, then we need to send it down to the host. * Note that if we are also acting as a host then this * will prevent us from sending from local client to * local client, but we accept that restriction as a * way to remove any ambiguity from the host context. */ if (src->context == VMCI_HYPERVISOR_CONTEXT_ID) { /* * If the hypervisor is the source, this is * host local communication. The hypervisor * may send vmci event datagrams to the host * itself, but it will never send datagrams to * an "outer host" through the guest device. */ if (has_host_device) { *route = VMCI_ROUTE_AS_HOST; return VMCI_SUCCESS; } else { return VMCI_ERROR_DEVICE_NOT_FOUND; } } if (!from_guest && has_guest_device) { /* If no source context then use the current. */ if (VMCI_INVALID_ID == src->context) src->context = vmci_get_context_id(); /* Send it from local client down to the host. */ *route = VMCI_ROUTE_AS_GUEST; return VMCI_SUCCESS; } /* * Otherwise we already received it from a guest and * it is destined for a local client on this host, or * it is from another local client on this host. We * must be acting as a host to service it. */ if (!has_host_device) return VMCI_ERROR_DEVICE_NOT_FOUND; if (VMCI_INVALID_ID == src->context) { /* * If it came from a guest then it must have a * valid context. Otherwise we can use the * host context. */ if (from_guest) return VMCI_ERROR_INVALID_ARGS; src->context = VMCI_HOST_CONTEXT_ID; } /* Route to local client. */ *route = VMCI_ROUTE_AS_HOST; return VMCI_SUCCESS; } /* * If we are acting as a host then this might be destined for * a guest. */ if (has_host_device) { /* It will have a context if it is meant for a guest. */ if (vmci_ctx_exists(dst->context)) { if (VMCI_INVALID_ID == src->context) { /* * If it came from a guest then it * must have a valid context. * Otherwise we can use the host * context. */ if (from_guest) return VMCI_ERROR_INVALID_ARGS; src->context = VMCI_HOST_CONTEXT_ID; } else if (VMCI_CONTEXT_IS_VM(src->context) && src->context != dst->context) { /* * VM to VM communication is not * allowed. Since we catch all * communication destined for the host * above, this must be destined for a * VM since there is a valid context. */ return VMCI_ERROR_DST_UNREACHABLE; } /* Pass it up to the guest. */ *route = VMCI_ROUTE_AS_HOST; return VMCI_SUCCESS; } else if (!has_guest_device) { /* * The host is attempting to reach a CID * without an active context, and we can't * send it down, since we have no guest * device. */ return VMCI_ERROR_DST_UNREACHABLE; } } /* * We must be a guest trying to send to another guest, which means * we need to send it down to the host. We do not filter out VM to * VM communication here, since we want to be able to use the guest * driver on older versions that do support VM to VM communication. */ if (!has_guest_device) { /* * Ending up here means we have neither guest nor host * device. */ return VMCI_ERROR_DEVICE_NOT_FOUND; } /* If no source context then use the current context. */ if (VMCI_INVALID_ID == src->context) src->context = vmci_get_context_id(); /* * Send it from local client down to the host, which will * route it to the other guest for us. */ *route = VMCI_ROUTE_AS_GUEST; return VMCI_SUCCESS; } |
| 2 1 1 1 1 1 1 2 2 2 2 3 2 3 3 1 1 1 1 1 1 1 1 1 1 3 1 1 1 1 1 3 3 3 3 3 3 3 3 3 3 2 3 1 2 2 1 1 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 3 3 3 3 3 2 2 2 1 2 3 3 3 3 2 2 1 1 2 2 2 2 2 1 2 2 2 2 2 2 2 2 1 1 2 1 1 1 1 1 1 3 1 3 3 3 3 3 3 3 3 3 3 3 3 2 2 3 2 2 2 3 1 1 2 2 2 2 2 2 2 2 2 2 2 2 2 2 1 1 1 2 2 3 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 2 2 1 1 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 1 1 2 2 2 2 1 1 2 2 2 2 2 2 1 1 1 1 1 1 1 2 2 2 2 1 1 1 2 2 2 2 4 2 2 2 2 2 2 2 2 2 7 7 7 5 5 5 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2011 STRATO. All rights reserved. */ #include <linux/mm.h> #include <linux/rbtree.h> #include <trace/events/btrfs.h> #include "ctree.h" #include "disk-io.h" #include "backref.h" #include "ulist.h" #include "transaction.h" #include "delayed-ref.h" #include "locking.h" #include "misc.h" #include "tree-mod-log.h" #include "fs.h" #include "accessors.h" #include "extent-tree.h" #include "relocation.h" #include "tree-checker.h" /* Just arbitrary numbers so we can be sure one of these happened. */ #define BACKREF_FOUND_SHARED 6 #define BACKREF_FOUND_NOT_SHARED 7 struct extent_inode_elem { u64 inum; u64 offset; u64 num_bytes; struct extent_inode_elem *next; }; static int check_extent_in_eb(struct btrfs_backref_walk_ctx *ctx, const struct btrfs_key *key, const struct extent_buffer *eb, const struct btrfs_file_extent_item *fi, struct extent_inode_elem **eie) { const u64 data_len = btrfs_file_extent_num_bytes(eb, fi); u64 offset = key->offset; struct extent_inode_elem *e; const u64 *root_ids; int root_count; bool cached; if (!ctx->ignore_extent_item_pos && !btrfs_file_extent_compression(eb, fi) && !btrfs_file_extent_encryption(eb, fi) && !btrfs_file_extent_other_encoding(eb, fi)) { u64 data_offset; data_offset = btrfs_file_extent_offset(eb, fi); if (ctx->extent_item_pos < data_offset || ctx->extent_item_pos >= data_offset + data_len) return 1; offset += ctx->extent_item_pos - data_offset; } if (!ctx->indirect_ref_iterator || !ctx->cache_lookup) goto add_inode_elem; cached = ctx->cache_lookup(eb->start, ctx->user_ctx, &root_ids, &root_count); if (!cached) goto add_inode_elem; for (int i = 0; i < root_count; i++) { int ret; ret = ctx->indirect_ref_iterator(key->objectid, offset, data_len, root_ids[i], ctx->user_ctx); if (ret) return ret; } add_inode_elem: e = kmalloc(sizeof(*e), GFP_NOFS); if (!e) return -ENOMEM; e->next = *eie; e->inum = key->objectid; e->offset = offset; e->num_bytes = data_len; *eie = e; return 0; } static void free_inode_elem_list(struct extent_inode_elem *eie) { struct extent_inode_elem *eie_next; for (; eie; eie = eie_next) { eie_next = eie->next; kfree(eie); } } static int find_extent_in_eb(struct btrfs_backref_walk_ctx *ctx, const struct extent_buffer *eb, struct extent_inode_elem **eie) { u64 disk_byte; struct btrfs_key key; struct btrfs_file_extent_item *fi; int slot; int nritems; int extent_type; int ret; /* * from the shared data ref, we only have the leaf but we need * the key. thus, we must look into all items and see that we * find one (some) with a reference to our extent item. */ nritems = btrfs_header_nritems(eb); for (slot = 0; slot < nritems; ++slot) { btrfs_item_key_to_cpu(eb, &key, slot); if (key.type != BTRFS_EXTENT_DATA_KEY) continue; fi = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item); extent_type = btrfs_file_extent_type(eb, fi); if (extent_type == BTRFS_FILE_EXTENT_INLINE) continue; /* don't skip BTRFS_FILE_EXTENT_PREALLOC, we can handle that */ disk_byte = btrfs_file_extent_disk_bytenr(eb, fi); if (disk_byte != ctx->bytenr) continue; ret = check_extent_in_eb(ctx, &key, eb, fi, eie); if (ret == BTRFS_ITERATE_EXTENT_INODES_STOP || ret < 0) return ret; } return 0; } struct preftree { struct rb_root_cached root; unsigned int count; }; #define PREFTREE_INIT { .root = RB_ROOT_CACHED, .count = 0 } struct preftrees { struct preftree direct; /* BTRFS_SHARED_[DATA|BLOCK]_REF_KEY */ struct preftree indirect; /* BTRFS_[TREE_BLOCK|EXTENT_DATA]_REF_KEY */ struct preftree indirect_missing_keys; }; /* * Checks for a shared extent during backref search. * * The share_count tracks prelim_refs (direct and indirect) having a * ref->count >0: * - incremented when a ref->count transitions to >0 * - decremented when a ref->count transitions to <1 */ struct share_check { struct btrfs_backref_share_check_ctx *ctx; struct btrfs_root *root; u64 inum; u64 data_bytenr; u64 data_extent_gen; /* * Counts number of inodes that refer to an extent (different inodes in * the same root or different roots) that we could find. The sharedness * check typically stops once this counter gets greater than 1, so it * may not reflect the total number of inodes. */ int share_count; /* * The number of times we found our inode refers to the data extent we * are determining the sharedness. In other words, how many file extent * items we could find for our inode that point to our target data * extent. The value we get here after finishing the extent sharedness * check may be smaller than reality, but if it ends up being greater * than 1, then we know for sure the inode has multiple file extent * items that point to our inode, and we can safely assume it's useful * to cache the sharedness check result. */ int self_ref_count; bool have_delayed_delete_refs; }; static inline int extent_is_shared(struct share_check *sc) { return (sc && sc->share_count > 1) ? BACKREF_FOUND_SHARED : 0; } static struct kmem_cache *btrfs_prelim_ref_cache; int __init btrfs_prelim_ref_init(void) { btrfs_prelim_ref_cache = kmem_cache_create("btrfs_prelim_ref", sizeof(struct prelim_ref), 0, 0, NULL); if (!btrfs_prelim_ref_cache) return -ENOMEM; return 0; } void __cold btrfs_prelim_ref_exit(void) { kmem_cache_destroy(btrfs_prelim_ref_cache); } static void free_pref(struct prelim_ref *ref) { kmem_cache_free(btrfs_prelim_ref_cache, ref); } /* * Return 0 when both refs are for the same block (and can be merged). * A -1 return indicates ref1 is a 'lower' block than ref2, while 1 * indicates a 'higher' block. */ static int prelim_ref_compare(const struct prelim_ref *ref1, const struct prelim_ref *ref2) { if (ref1->level < ref2->level) return -1; if (ref1->level > ref2->level) return 1; if (ref1->root_id < ref2->root_id) return -1; if (ref1->root_id > ref2->root_id) return 1; if (ref1->key_for_search.type < ref2->key_for_search.type) return -1; if (ref1->key_for_search.type > ref2->key_for_search.type) return 1; if (ref1->key_for_search.objectid < ref2->key_for_search.objectid) return -1; if (ref1->key_for_search.objectid > ref2->key_for_search.objectid) return 1; if (ref1->key_for_search.offset < ref2->key_for_search.offset) return -1; if (ref1->key_for_search.offset > ref2->key_for_search.offset) return 1; if (ref1->parent < ref2->parent) return -1; if (ref1->parent > ref2->parent) return 1; return 0; } static int prelim_ref_rb_add_cmp(const struct rb_node *new, const struct rb_node *exist) { const struct prelim_ref *ref_new = rb_entry(new, struct prelim_ref, rbnode); const struct prelim_ref *ref_exist = rb_entry(exist, struct prelim_ref, rbnode); /* * prelim_ref_compare() expects the first parameter as the existing one, * different from the rb_find_add_cached() order. */ return prelim_ref_compare(ref_exist, ref_new); } static void update_share_count(struct share_check *sc, int oldcount, int newcount, const struct prelim_ref *newref) { if ((!sc) || (oldcount == 0 && newcount < 1)) return; if (oldcount > 0 && newcount < 1) sc->share_count--; else if (oldcount < 1 && newcount > 0) sc->share_count++; if (newref->root_id == btrfs_root_id(sc->root) && newref->wanted_disk_byte == sc->data_bytenr && newref->key_for_search.objectid == sc->inum) sc->self_ref_count += newref->count; } /* * Add @newref to the @root rbtree, merging identical refs. * * Callers should assume that newref has been freed after calling. */ static void prelim_ref_insert(const struct btrfs_fs_info *fs_info, struct preftree *preftree, struct prelim_ref *newref, struct share_check *sc) { struct rb_root_cached *root; struct rb_node *exist; root = &preftree->root; exist = rb_find_add_cached(&newref->rbnode, root, prelim_ref_rb_add_cmp); if (exist) { struct prelim_ref *ref = rb_entry(exist, struct prelim_ref, rbnode); /* Identical refs, merge them and free @newref */ struct extent_inode_elem *eie = ref->inode_list; while (eie && eie->next) eie = eie->next; if (!eie) ref->inode_list = newref->inode_list; else eie->next = newref->inode_list; trace_btrfs_prelim_ref_merge(fs_info, ref, newref, preftree->count); /* * A delayed ref can have newref->count < 0. * The ref->count is updated to follow any * BTRFS_[ADD|DROP]_DELAYED_REF actions. */ update_share_count(sc, ref->count, ref->count + newref->count, newref); ref->count += newref->count; free_pref(newref); return; } update_share_count(sc, 0, newref->count, newref); preftree->count++; trace_btrfs_prelim_ref_insert(fs_info, newref, NULL, preftree->count); } /* * Release the entire tree. We don't care about internal consistency so * just free everything and then reset the tree root. */ static void prelim_release(struct preftree *preftree) { struct prelim_ref *ref, *next_ref; rbtree_postorder_for_each_entry_safe(ref, next_ref, &preftree->root.rb_root, rbnode) { free_inode_elem_list(ref->inode_list); free_pref(ref); } preftree->root = RB_ROOT_CACHED; preftree->count = 0; } /* * the rules for all callers of this function are: * - obtaining the parent is the goal * - if you add a key, you must know that it is a correct key * - if you cannot add the parent or a correct key, then we will look into the * block later to set a correct key * * delayed refs * ============ * backref type | shared | indirect | shared | indirect * information | tree | tree | data | data * --------------------+--------+----------+--------+---------- * parent logical | y | - | - | - * key to resolve | - | y | y | y * tree block logical | - | - | - | - * root for resolving | y | y | y | y * * - column 1: we've the parent -> done * - column 2, 3, 4: we use the key to find the parent * * on disk refs (inline or keyed) * ============================== * backref type | shared | indirect | shared | indirect * information | tree | tree | data | data * --------------------+--------+----------+--------+---------- * parent logical | y | - | y | - * key to resolve | - | - | - | y * tree block logical | y | y | y | y * root for resolving | - | y | y | y * * - column 1, 3: we've the parent -> done * - column 2: we take the first key from the block to find the parent * (see add_missing_keys) * - column 4: we use the key to find the parent * * additional information that's available but not required to find the parent * block might help in merging entries to gain some speed. */ static int add_prelim_ref(const struct btrfs_fs_info *fs_info, struct preftree *preftree, u64 root_id, const struct btrfs_key *key, int level, u64 parent, u64 wanted_disk_byte, int count, struct share_check *sc, gfp_t gfp_mask) { struct prelim_ref *ref; if (root_id == BTRFS_DATA_RELOC_TREE_OBJECTID) return 0; ref = kmem_cache_alloc(btrfs_prelim_ref_cache, gfp_mask); if (!ref) return -ENOMEM; ref->root_id = root_id; if (key) ref->key_for_search = *key; else memset(&ref->key_for_search, 0, sizeof(ref->key_for_search)); ref->inode_list = NULL; ref->level = level; ref->count = count; ref->parent = parent; ref->wanted_disk_byte = wanted_disk_byte; prelim_ref_insert(fs_info, preftree, ref, sc); return extent_is_shared(sc); } /* direct refs use root == 0, key == NULL */ static int add_direct_ref(const struct btrfs_fs_info *fs_info, struct preftrees *preftrees, int level, u64 parent, u64 wanted_disk_byte, int count, struct share_check *sc, gfp_t gfp_mask) { return add_prelim_ref(fs_info, &preftrees->direct, 0, NULL, level, parent, wanted_disk_byte, count, sc, gfp_mask); } /* indirect refs use parent == 0 */ static int add_indirect_ref(const struct btrfs_fs_info *fs_info, struct preftrees *preftrees, u64 root_id, const struct btrfs_key *key, int level, u64 wanted_disk_byte, int count, struct share_check *sc, gfp_t gfp_mask) { struct preftree *tree = &preftrees->indirect; if (!key) tree = &preftrees->indirect_missing_keys; return add_prelim_ref(fs_info, tree, root_id, key, level, 0, wanted_disk_byte, count, sc, gfp_mask); } static int is_shared_data_backref(struct preftrees *preftrees, u64 bytenr) { struct rb_node **p = &preftrees->direct.root.rb_root.rb_node; struct rb_node *parent = NULL; struct prelim_ref *ref = NULL; struct prelim_ref target = {}; int result; target.parent = bytenr; while (*p) { parent = *p; ref = rb_entry(parent, struct prelim_ref, rbnode); result = prelim_ref_compare(ref, &target); if (result < 0) p = &(*p)->rb_left; else if (result > 0) p = &(*p)->rb_right; else return 1; } return 0; } static int add_all_parents(struct btrfs_backref_walk_ctx *ctx, struct btrfs_root *root, struct btrfs_path *path, struct ulist *parents, struct preftrees *preftrees, struct prelim_ref *ref, int level) { int ret = 0; int slot; struct extent_buffer *eb; struct btrfs_key key; struct btrfs_key *key_for_search = &ref->key_for_search; struct btrfs_file_extent_item *fi; struct extent_inode_elem *eie = NULL, *old = NULL; u64 disk_byte; u64 wanted_disk_byte = ref->wanted_disk_byte; u64 count = 0; u64 data_offset; u8 type; if (level != 0) { eb = path->nodes[level]; ret = ulist_add(parents, eb->start, 0, GFP_NOFS); if (ret < 0) return ret; return 0; } /* * 1. We normally enter this function with the path already pointing to * the first item to check. But sometimes, we may enter it with * slot == nritems. * 2. We are searching for normal backref but bytenr of this leaf * matches shared data backref * 3. The leaf owner is not equal to the root we are searching * * For these cases, go to the next leaf before we continue. */ eb = path->nodes[0]; if (path->slots[0] >= btrfs_header_nritems(eb) || is_shared_data_backref(preftrees, eb->start) || ref->root_id != btrfs_header_owner(eb)) { if (ctx->time_seq == BTRFS_SEQ_LAST) ret = btrfs_next_leaf(root, path); else ret = btrfs_next_old_leaf(root, path, ctx->time_seq); } while (!ret && count < ref->count) { eb = path->nodes[0]; slot = path->slots[0]; btrfs_item_key_to_cpu(eb, &key, slot); if (key.objectid != key_for_search->objectid || key.type != BTRFS_EXTENT_DATA_KEY) break; /* * We are searching for normal backref but bytenr of this leaf * matches shared data backref, OR * the leaf owner is not equal to the root we are searching for */ if (slot == 0 && (is_shared_data_backref(preftrees, eb->start) || ref->root_id != btrfs_header_owner(eb))) { if (ctx->time_seq == BTRFS_SEQ_LAST) ret = btrfs_next_leaf(root, path); else ret = btrfs_next_old_leaf(root, path, ctx->time_seq); continue; } fi = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item); type = btrfs_file_extent_type(eb, fi); if (type == BTRFS_FILE_EXTENT_INLINE) goto next; disk_byte = btrfs_file_extent_disk_bytenr(eb, fi); data_offset = btrfs_file_extent_offset(eb, fi); if (disk_byte == wanted_disk_byte) { eie = NULL; old = NULL; if (ref->key_for_search.offset == key.offset - data_offset) count++; else goto next; if (!ctx->skip_inode_ref_list) { ret = check_extent_in_eb(ctx, &key, eb, fi, &eie); if (ret == BTRFS_ITERATE_EXTENT_INODES_STOP || ret < 0) break; } if (ret > 0) goto next; ret = ulist_add_merge_ptr(parents, eb->start, eie, (void **)&old, GFP_NOFS); if (ret < 0) break; if (!ret && !ctx->skip_inode_ref_list) { while (old->next) old = old->next; old->next = eie; } eie = NULL; } next: if (ctx->time_seq == BTRFS_SEQ_LAST) ret = btrfs_next_item(root, path); else ret = btrfs_next_old_item(root, path, ctx->time_seq); } if (ret == BTRFS_ITERATE_EXTENT_INODES_STOP || ret < 0) free_inode_elem_list(eie); else if (ret > 0) ret = 0; return ret; } /* * resolve an indirect backref in the form (root_id, key, level) * to a logical address */ static int resolve_indirect_ref(struct btrfs_backref_walk_ctx *ctx, struct btrfs_path *path, struct preftrees *preftrees, struct prelim_ref *ref, struct ulist *parents) { struct btrfs_root *root; struct extent_buffer *eb; int ret = 0; int root_level; int level = ref->level; struct btrfs_key search_key = ref->key_for_search; /* * If we're search_commit_root we could possibly be holding locks on * other tree nodes. This happens when qgroups does backref walks when * adding new delayed refs. To deal with this we need to look in cache * for the root, and if we don't find it then we need to search the * tree_root's commit root, thus the btrfs_get_fs_root_commit_root usage * here. */ if (path->search_commit_root) root = btrfs_get_fs_root_commit_root(ctx->fs_info, path, ref->root_id); else root = btrfs_get_fs_root(ctx->fs_info, ref->root_id, false); if (IS_ERR(root)) { ret = PTR_ERR(root); goto out_free; } if (!path->search_commit_root && test_bit(BTRFS_ROOT_DELETING, &root->state)) { ret = -ENOENT; goto out; } if (btrfs_is_testing(ctx->fs_info)) { ret = -ENOENT; goto out; } if (path->search_commit_root) root_level = btrfs_header_level(root->commit_root); else if (ctx->time_seq == BTRFS_SEQ_LAST) root_level = btrfs_header_level(root->node); else root_level = btrfs_old_root_level(root, ctx->time_seq); if (root_level + 1 == level) goto out; /* * We can often find data backrefs with an offset that is too large * (>= LLONG_MAX, maximum allowed file offset) due to underflows when * subtracting a file's offset with the data offset of its * corresponding extent data item. This can happen for example in the * clone ioctl. * * So if we detect such case we set the search key's offset to zero to * make sure we will find the matching file extent item at * add_all_parents(), otherwise we will miss it because the offset * taken form the backref is much larger then the offset of the file * extent item. This can make us scan a very large number of file * extent items, but at least it will not make us miss any. * * This is an ugly workaround for a behaviour that should have never * existed, but it does and a fix for the clone ioctl would touch a lot * of places, cause backwards incompatibility and would not fix the * problem for extents cloned with older kernels. */ if (search_key.type == BTRFS_EXTENT_DATA_KEY && search_key.offset >= LLONG_MAX) search_key.offset = 0; path->lowest_level = level; if (ctx->time_seq == BTRFS_SEQ_LAST) ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0); else ret = btrfs_search_old_slot(root, &search_key, path, ctx->time_seq); btrfs_debug(ctx->fs_info, "search slot in root %llu (level %d, ref count %d) returned %d for key (%llu %u %llu)", ref->root_id, level, ref->count, ret, ref->key_for_search.objectid, ref->key_for_search.type, ref->key_for_search.offset); if (ret < 0) goto out; eb = path->nodes[level]; while (!eb) { if (WARN_ON(!level)) { ret = 1; goto out; } level--; eb = path->nodes[level]; } ret = add_all_parents(ctx, root, path, parents, preftrees, ref, level); out: btrfs_put_root(root); out_free: path->lowest_level = 0; btrfs_release_path(path); return ret; } static struct extent_inode_elem * unode_aux_to_inode_list(struct ulist_node *node) { if (!node) return NULL; return (struct extent_inode_elem *)(uintptr_t)node->aux; } static void free_leaf_list(struct ulist *ulist) { struct ulist_node *node; struct ulist_iterator uiter; ULIST_ITER_INIT(&uiter); while ((node = ulist_next(ulist, &uiter))) free_inode_elem_list(unode_aux_to_inode_list(node)); ulist_free(ulist); } /* * We maintain three separate rbtrees: one for direct refs, one for * indirect refs which have a key, and one for indirect refs which do not * have a key. Each tree does merge on insertion. * * Once all of the references are located, we iterate over the tree of * indirect refs with missing keys. An appropriate key is located and * the ref is moved onto the tree for indirect refs. After all missing * keys are thus located, we iterate over the indirect ref tree, resolve * each reference, and then insert the resolved reference onto the * direct tree (merging there too). * * New backrefs (i.e., for parent nodes) are added to the appropriate * rbtree as they are encountered. The new backrefs are subsequently * resolved as above. */ static int resolve_indirect_refs(struct btrfs_backref_walk_ctx *ctx, struct btrfs_path *path, struct preftrees *preftrees, struct share_check *sc) { int err; int ret = 0; struct ulist *parents; struct ulist_node *node; struct ulist_iterator uiter; struct rb_node *rnode; parents = ulist_alloc(GFP_NOFS); if (!parents) return -ENOMEM; /* * We could trade memory usage for performance here by iterating * the tree, allocating new refs for each insertion, and then * freeing the entire indirect tree when we're done. In some test * cases, the tree can grow quite large (~200k objects). */ while ((rnode = rb_first_cached(&preftrees->indirect.root))) { struct prelim_ref *ref; ref = rb_entry(rnode, struct prelim_ref, rbnode); if (WARN(ref->parent, "BUG: direct ref found in indirect tree")) { ret = -EINVAL; goto out; } rb_erase_cached(&ref->rbnode, &preftrees->indirect.root); preftrees->indirect.count--; if (ref->count == 0) { free_pref(ref); continue; } if (sc && ref->root_id != btrfs_root_id(sc->root)) { free_pref(ref); ret = BACKREF_FOUND_SHARED; goto out; } err = resolve_indirect_ref(ctx, path, preftrees, ref, parents); /* * we can only tolerate ENOENT,otherwise,we should catch error * and return directly. */ if (err == -ENOENT) { prelim_ref_insert(ctx->fs_info, &preftrees->direct, ref, NULL); continue; } else if (err) { free_pref(ref); ret = err; goto out; } /* we put the first parent into the ref at hand */ ULIST_ITER_INIT(&uiter); node = ulist_next(parents, &uiter); ref->parent = node ? node->val : 0; ref->inode_list = unode_aux_to_inode_list(node); /* Add a prelim_ref(s) for any other parent(s). */ while ((node = ulist_next(parents, &uiter))) { struct prelim_ref *new_ref; new_ref = kmem_cache_alloc(btrfs_prelim_ref_cache, GFP_NOFS); if (!new_ref) { free_pref(ref); ret = -ENOMEM; goto out; } memcpy(new_ref, ref, sizeof(*ref)); new_ref->parent = node->val; new_ref->inode_list = unode_aux_to_inode_list(node); prelim_ref_insert(ctx->fs_info, &preftrees->direct, new_ref, NULL); } /* * Now it's a direct ref, put it in the direct tree. We must * do this last because the ref could be merged/freed here. */ prelim_ref_insert(ctx->fs_info, &preftrees->direct, ref, NULL); ulist_reinit(parents); cond_resched(); } out: /* * We may have inode lists attached to refs in the parents ulist, so we * must free them before freeing the ulist and its refs. */ free_leaf_list(parents); return ret; } /* * read tree blocks and add keys where required. */ static int add_missing_keys(struct btrfs_fs_info *fs_info, struct preftrees *preftrees, bool lock) { struct prelim_ref *ref; struct extent_buffer *eb; struct preftree *tree = &preftrees->indirect_missing_keys; struct rb_node *node; while ((node = rb_first_cached(&tree->root))) { struct btrfs_tree_parent_check check = { 0 }; ref = rb_entry(node, struct prelim_ref, rbnode); rb_erase_cached(node, &tree->root); BUG_ON(ref->parent); /* should not be a direct ref */ BUG_ON(ref->key_for_search.type); BUG_ON(!ref->wanted_disk_byte); check.level = ref->level - 1; check.owner_root = ref->root_id; eb = read_tree_block(fs_info, ref->wanted_disk_byte, &check); if (IS_ERR(eb)) { free_pref(ref); return PTR_ERR(eb); } if (!extent_buffer_uptodate(eb)) { free_pref(ref); free_extent_buffer(eb); return -EIO; } if (lock) btrfs_tree_read_lock(eb); if (btrfs_header_level(eb) == 0) btrfs_item_key_to_cpu(eb, &ref->key_for_search, 0); else btrfs_node_key_to_cpu(eb, &ref->key_for_search, 0); if (lock) btrfs_tree_read_unlock(eb); free_extent_buffer(eb); prelim_ref_insert(fs_info, &preftrees->indirect, ref, NULL); cond_resched(); } return 0; } /* * add all currently queued delayed refs from this head whose seq nr is * smaller or equal that seq to the list */ static int add_delayed_refs(const struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_head *head, u64 seq, struct preftrees *preftrees, struct share_check *sc) { struct btrfs_delayed_ref_node *node; struct btrfs_key key; struct rb_node *n; int count; int ret = 0; spin_lock(&head->lock); for (n = rb_first_cached(&head->ref_tree); n; n = rb_next(n)) { node = rb_entry(n, struct btrfs_delayed_ref_node, ref_node); if (node->seq > seq) continue; switch (node->action) { case BTRFS_ADD_DELAYED_EXTENT: case BTRFS_UPDATE_DELAYED_HEAD: WARN_ON(1); continue; case BTRFS_ADD_DELAYED_REF: count = node->ref_mod; break; case BTRFS_DROP_DELAYED_REF: count = node->ref_mod * -1; break; default: BUG(); } switch (node->type) { case BTRFS_TREE_BLOCK_REF_KEY: { /* NORMAL INDIRECT METADATA backref */ struct btrfs_key *key_ptr = NULL; /* The owner of a tree block ref is the level. */ int level = btrfs_delayed_ref_owner(node); if (head->extent_op && head->extent_op->update_key) { btrfs_disk_key_to_cpu(&key, &head->extent_op->key); key_ptr = &key; } ret = add_indirect_ref(fs_info, preftrees, node->ref_root, key_ptr, level + 1, node->bytenr, count, sc, GFP_ATOMIC); break; } case BTRFS_SHARED_BLOCK_REF_KEY: { /* * SHARED DIRECT METADATA backref * * The owner of a tree block ref is the level. */ int level = btrfs_delayed_ref_owner(node); ret = add_direct_ref(fs_info, preftrees, level + 1, node->parent, node->bytenr, count, sc, GFP_ATOMIC); break; } case BTRFS_EXTENT_DATA_REF_KEY: { /* NORMAL INDIRECT DATA backref */ key.objectid = btrfs_delayed_ref_owner(node); key.type = BTRFS_EXTENT_DATA_KEY; key.offset = btrfs_delayed_ref_offset(node); /* * If we have a share check context and a reference for * another inode, we can't exit immediately. This is * because even if this is a BTRFS_ADD_DELAYED_REF * reference we may find next a BTRFS_DROP_DELAYED_REF * which cancels out this ADD reference. * * If this is a DROP reference and there was no previous * ADD reference, then we need to signal that when we * process references from the extent tree (through * add_inline_refs() and add_keyed_refs()), we should * not exit early if we find a reference for another * inode, because one of the delayed DROP references * may cancel that reference in the extent tree. */ if (sc && count < 0) sc->have_delayed_delete_refs = true; ret = add_indirect_ref(fs_info, preftrees, node->ref_root, &key, 0, node->bytenr, count, sc, GFP_ATOMIC); break; } case BTRFS_SHARED_DATA_REF_KEY: { /* SHARED DIRECT FULL backref */ ret = add_direct_ref(fs_info, preftrees, 0, node->parent, node->bytenr, count, sc, GFP_ATOMIC); break; } default: WARN_ON(1); } /* * We must ignore BACKREF_FOUND_SHARED until all delayed * refs have been checked. */ if (ret && (ret != BACKREF_FOUND_SHARED)) break; } if (!ret) ret = extent_is_shared(sc); spin_unlock(&head->lock); return ret; } /* * add all inline backrefs for bytenr to the list * * Returns 0 on success, <0 on error, or BACKREF_FOUND_SHARED. */ static int add_inline_refs(struct btrfs_backref_walk_ctx *ctx, struct btrfs_path *path, int *info_level, struct preftrees *preftrees, struct share_check *sc) { int ret = 0; int slot; struct extent_buffer *leaf; struct btrfs_key key; struct btrfs_key found_key; unsigned long ptr; unsigned long end; struct btrfs_extent_item *ei; u64 flags; u64 item_size; /* * enumerate all inline refs */ leaf = path->nodes[0]; slot = path->slots[0]; item_size = btrfs_item_size(leaf, slot); ei = btrfs_item_ptr(leaf, slot, struct btrfs_extent_item); if (ctx->check_extent_item) { ret = ctx->check_extent_item(ctx->bytenr, ei, leaf, ctx->user_ctx); if (ret) return ret; } flags = btrfs_extent_flags(leaf, ei); btrfs_item_key_to_cpu(leaf, &found_key, slot); ptr = (unsigned long)(ei + 1); end = (unsigned long)ei + item_size; if (found_key.type == BTRFS_EXTENT_ITEM_KEY && flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) { struct btrfs_tree_block_info *info; info = (struct btrfs_tree_block_info *)ptr; *info_level = btrfs_tree_block_level(leaf, info); ptr += sizeof(struct btrfs_tree_block_info); BUG_ON(ptr > end); } else if (found_key.type == BTRFS_METADATA_ITEM_KEY) { *info_level = found_key.offset; } else { BUG_ON(!(flags & BTRFS_EXTENT_FLAG_DATA)); } while (ptr < end) { struct btrfs_extent_inline_ref *iref; u64 offset; int type; iref = (struct btrfs_extent_inline_ref *)ptr; type = btrfs_get_extent_inline_ref_type(leaf, iref, BTRFS_REF_TYPE_ANY); if (type == BTRFS_REF_TYPE_INVALID) return -EUCLEAN; offset = btrfs_extent_inline_ref_offset(leaf, iref); switch (type) { case BTRFS_SHARED_BLOCK_REF_KEY: ret = add_direct_ref(ctx->fs_info, preftrees, *info_level + 1, offset, ctx->bytenr, 1, NULL, GFP_NOFS); break; case BTRFS_SHARED_DATA_REF_KEY: { struct btrfs_shared_data_ref *sdref; int count; sdref = (struct btrfs_shared_data_ref *)(iref + 1); count = btrfs_shared_data_ref_count(leaf, sdref); ret = add_direct_ref(ctx->fs_info, preftrees, 0, offset, ctx->bytenr, count, sc, GFP_NOFS); break; } case BTRFS_TREE_BLOCK_REF_KEY: ret = add_indirect_ref(ctx->fs_info, preftrees, offset, NULL, *info_level + 1, ctx->bytenr, 1, NULL, GFP_NOFS); break; case BTRFS_EXTENT_DATA_REF_KEY: { struct btrfs_extent_data_ref *dref; int count; u64 root; dref = (struct btrfs_extent_data_ref *)(&iref->offset); count = btrfs_extent_data_ref_count(leaf, dref); key.objectid = btrfs_extent_data_ref_objectid(leaf, dref); key.type = BTRFS_EXTENT_DATA_KEY; key.offset = btrfs_extent_data_ref_offset(leaf, dref); if (sc && key.objectid != sc->inum && !sc->have_delayed_delete_refs) { ret = BACKREF_FOUND_SHARED; break; } root = btrfs_extent_data_ref_root(leaf, dref); if (!ctx->skip_data_ref || !ctx->skip_data_ref(root, key.objectid, key.offset, ctx->user_ctx)) ret = add_indirect_ref(ctx->fs_info, preftrees, root, &key, 0, ctx->bytenr, count, sc, GFP_NOFS); break; } case BTRFS_EXTENT_OWNER_REF_KEY: ASSERT(btrfs_fs_incompat(ctx->fs_info, SIMPLE_QUOTA)); break; default: WARN_ON(1); } if (ret) return ret; ptr += btrfs_extent_inline_ref_size(type); } return 0; } /* * add all non-inline backrefs for bytenr to the list * * Returns 0 on success, <0 on error, or BACKREF_FOUND_SHARED. */ static int add_keyed_refs(struct btrfs_backref_walk_ctx *ctx, struct btrfs_root *extent_root, struct btrfs_path *path, int info_level, struct preftrees *preftrees, struct share_check *sc) { struct btrfs_fs_info *fs_info = extent_root->fs_info; int ret; int slot; struct extent_buffer *leaf; struct btrfs_key key; while (1) { ret = btrfs_next_item(extent_root, path); if (ret < 0) break; if (ret) { ret = 0; break; } slot = path->slots[0]; leaf = path->nodes[0]; btrfs_item_key_to_cpu(leaf, &key, slot); if (key.objectid != ctx->bytenr) break; if (key.type < BTRFS_TREE_BLOCK_REF_KEY) continue; if (key.type > BTRFS_SHARED_DATA_REF_KEY) break; switch (key.type) { case BTRFS_SHARED_BLOCK_REF_KEY: /* SHARED DIRECT METADATA backref */ ret = add_direct_ref(fs_info, preftrees, info_level + 1, key.offset, ctx->bytenr, 1, NULL, GFP_NOFS); break; case BTRFS_SHARED_DATA_REF_KEY: { /* SHARED DIRECT FULL backref */ struct btrfs_shared_data_ref *sdref; int count; sdref = btrfs_item_ptr(leaf, slot, struct btrfs_shared_data_ref); count = btrfs_shared_data_ref_count(leaf, sdref); ret = add_direct_ref(fs_info, preftrees, 0, key.offset, ctx->bytenr, count, sc, GFP_NOFS); break; } case BTRFS_TREE_BLOCK_REF_KEY: /* NORMAL INDIRECT METADATA backref */ ret = add_indirect_ref(fs_info, preftrees, key.offset, NULL, info_level + 1, ctx->bytenr, 1, NULL, GFP_NOFS); break; case BTRFS_EXTENT_DATA_REF_KEY: { /* NORMAL INDIRECT DATA backref */ struct btrfs_extent_data_ref *dref; int count; u64 root; dref = btrfs_item_ptr(leaf, slot, struct btrfs_extent_data_ref); count = btrfs_extent_data_ref_count(leaf, dref); key.objectid = btrfs_extent_data_ref_objectid(leaf, dref); key.type = BTRFS_EXTENT_DATA_KEY; key.offset = btrfs_extent_data_ref_offset(leaf, dref); if (sc && key.objectid != sc->inum && !sc->have_delayed_delete_refs) { ret = BACKREF_FOUND_SHARED; break; } root = btrfs_extent_data_ref_root(leaf, dref); if (!ctx->skip_data_ref || !ctx->skip_data_ref(root, key.objectid, key.offset, ctx->user_ctx)) ret = add_indirect_ref(fs_info, preftrees, root, &key, 0, ctx->bytenr, count, sc, GFP_NOFS); break; } default: WARN_ON(1); } if (ret) return ret; } return ret; } /* * The caller has joined a transaction or is holding a read lock on the * fs_info->commit_root_sem semaphore, so no need to worry about the root's last * snapshot field changing while updating or checking the cache. */ static bool lookup_backref_shared_cache(struct btrfs_backref_share_check_ctx *ctx, struct btrfs_root *root, u64 bytenr, int level, bool *is_shared) { const struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_backref_shared_cache_entry *entry; if (!current->journal_info) lockdep_assert_held(&fs_info->commit_root_sem); if (!ctx->use_path_cache) return false; if (WARN_ON_ONCE(level >= BTRFS_MAX_LEVEL)) return false; /* * Level -1 is used for the data extent, which is not reliable to cache * because its reference count can increase or decrease without us * realizing. We cache results only for extent buffers that lead from * the root node down to the leaf with the file extent item. */ ASSERT(level >= 0); entry = &ctx->path_cache_entries[level]; /* Unused cache entry or being used for some other extent buffer. */ if (entry->bytenr != bytenr) return false; /* * We cached a false result, but the last snapshot generation of the * root changed, so we now have a snapshot. Don't trust the result. */ if (!entry->is_shared && entry->gen != btrfs_root_last_snapshot(&root->root_item)) return false; /* * If we cached a true result and the last generation used for dropping * a root changed, we can not trust the result, because the dropped root * could be a snapshot sharing this extent buffer. */ if (entry->is_shared && entry->gen != btrfs_get_last_root_drop_gen(fs_info)) return false; *is_shared = entry->is_shared; /* * If the node at this level is shared, than all nodes below are also * shared. Currently some of the nodes below may be marked as not shared * because we have just switched from one leaf to another, and switched * also other nodes above the leaf and below the current level, so mark * them as shared. */ if (*is_shared) { for (int i = 0; i < level; i++) { ctx->path_cache_entries[i].is_shared = true; ctx->path_cache_entries[i].gen = entry->gen; } } return true; } /* * The caller has joined a transaction or is holding a read lock on the * fs_info->commit_root_sem semaphore, so no need to worry about the root's last * snapshot field changing while updating or checking the cache. */ static void store_backref_shared_cache(struct btrfs_backref_share_check_ctx *ctx, struct btrfs_root *root, u64 bytenr, int level, bool is_shared) { const struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_backref_shared_cache_entry *entry; u64 gen; if (!current->journal_info) lockdep_assert_held(&fs_info->commit_root_sem); if (!ctx->use_path_cache) return; if (WARN_ON_ONCE(level >= BTRFS_MAX_LEVEL)) return; /* * Level -1 is used for the data extent, which is not reliable to cache * because its reference count can increase or decrease without us * realizing. We cache results only for extent buffers that lead from * the root node down to the leaf with the file extent item. */ ASSERT(level >= 0); if (is_shared) gen = btrfs_get_last_root_drop_gen(fs_info); else gen = btrfs_root_last_snapshot(&root->root_item); entry = &ctx->path_cache_entries[level]; entry->bytenr = bytenr; entry->is_shared = is_shared; entry->gen = gen; /* * If we found an extent buffer is shared, set the cache result for all * extent buffers below it to true. As nodes in the path are COWed, * their sharedness is moved to their children, and if a leaf is COWed, * then the sharedness of a data extent becomes direct, the refcount of * data extent is increased in the extent item at the extent tree. */ if (is_shared) { for (int i = 0; i < level; i++) { entry = &ctx->path_cache_entries[i]; entry->is_shared = is_shared; entry->gen = gen; } } } /* * this adds all existing backrefs (inline backrefs, backrefs and delayed * refs) for the given bytenr to the refs list, merges duplicates and resolves * indirect refs to their parent bytenr. * When roots are found, they're added to the roots list * * @ctx: Backref walking context object, must be not NULL. * @sc: If !NULL, then immediately return BACKREF_FOUND_SHARED when a * shared extent is detected. * * Otherwise this returns 0 for success and <0 for an error. * * FIXME some caching might speed things up */ static int find_parent_nodes(struct btrfs_backref_walk_ctx *ctx, struct share_check *sc) { struct btrfs_root *root = btrfs_extent_root(ctx->fs_info, ctx->bytenr); struct btrfs_key key; struct btrfs_path *path; struct btrfs_delayed_ref_root *delayed_refs = NULL; struct btrfs_delayed_ref_head *head; int info_level = 0; int ret; struct prelim_ref *ref; struct rb_node *node; struct extent_inode_elem *eie = NULL; struct preftrees preftrees = { .direct = PREFTREE_INIT, .indirect = PREFTREE_INIT, .indirect_missing_keys = PREFTREE_INIT }; /* Roots ulist is not needed when using a sharedness check context. */ if (sc) ASSERT(ctx->roots == NULL); key.objectid = ctx->bytenr; key.offset = (u64)-1; if (btrfs_fs_incompat(ctx->fs_info, SKINNY_METADATA)) key.type = BTRFS_METADATA_ITEM_KEY; else key.type = BTRFS_EXTENT_ITEM_KEY; path = btrfs_alloc_path(); if (!path) return -ENOMEM; if (!ctx->trans) { path->search_commit_root = 1; path->skip_locking = 1; } if (ctx->time_seq == BTRFS_SEQ_LAST) path->skip_locking = 1; again: head = NULL; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) goto out; if (ret == 0) { /* * Key with offset -1 found, there would have to exist an extent * item with such offset, but this is out of the valid range. */ ret = -EUCLEAN; goto out; } if (ctx->trans && likely(ctx->trans->type != __TRANS_DUMMY) && ctx->time_seq != BTRFS_SEQ_LAST) { /* * We have a specific time_seq we care about and trans which * means we have the path lock, we need to grab the ref head and * lock it so we have a consistent view of the refs at the given * time. */ delayed_refs = &ctx->trans->transaction->delayed_refs; spin_lock(&delayed_refs->lock); head = btrfs_find_delayed_ref_head(ctx->fs_info, delayed_refs, ctx->bytenr); if (head) { if (!mutex_trylock(&head->mutex)) { refcount_inc(&head->refs); spin_unlock(&delayed_refs->lock); btrfs_release_path(path); /* * Mutex was contended, block until it's * released and try again */ mutex_lock(&head->mutex); mutex_unlock(&head->mutex); btrfs_put_delayed_ref_head(head); goto again; } spin_unlock(&delayed_refs->lock); ret = add_delayed_refs(ctx->fs_info, head, ctx->time_seq, &preftrees, sc); mutex_unlock(&head->mutex); if (ret) goto out; } else { spin_unlock(&delayed_refs->lock); } } if (path->slots[0]) { struct extent_buffer *leaf; int slot; path->slots[0]--; leaf = path->nodes[0]; slot = path->slots[0]; btrfs_item_key_to_cpu(leaf, &key, slot); if (key.objectid == ctx->bytenr && (key.type == BTRFS_EXTENT_ITEM_KEY || key.type == BTRFS_METADATA_ITEM_KEY)) { ret = add_inline_refs(ctx, path, &info_level, &preftrees, sc); if (ret) goto out; ret = add_keyed_refs(ctx, root, path, info_level, &preftrees, sc); if (ret) goto out; } } /* * If we have a share context and we reached here, it means the extent * is not directly shared (no multiple reference items for it), * otherwise we would have exited earlier with a return value of * BACKREF_FOUND_SHARED after processing delayed references or while * processing inline or keyed references from the extent tree. * The extent may however be indirectly shared through shared subtrees * as a result from creating snapshots, so we determine below what is * its parent node, in case we are dealing with a metadata extent, or * what's the leaf (or leaves), from a fs tree, that has a file extent * item pointing to it in case we are dealing with a data extent. */ ASSERT(extent_is_shared(sc) == 0); /* * If we are here for a data extent and we have a share_check structure * it means the data extent is not directly shared (does not have * multiple reference items), so we have to check if a path in the fs * tree (going from the root node down to the leaf that has the file * extent item pointing to the data extent) is shared, that is, if any * of the extent buffers in the path is referenced by other trees. */ if (sc && ctx->bytenr == sc->data_bytenr) { /* * If our data extent is from a generation more recent than the * last generation used to snapshot the root, then we know that * it can not be shared through subtrees, so we can skip * resolving indirect references, there's no point in * determining the extent buffers for the path from the fs tree * root node down to the leaf that has the file extent item that * points to the data extent. */ if (sc->data_extent_gen > btrfs_root_last_snapshot(&sc->root->root_item)) { ret = BACKREF_FOUND_NOT_SHARED; goto out; } /* * If we are only determining if a data extent is shared or not * and the corresponding file extent item is located in the same * leaf as the previous file extent item, we can skip resolving * indirect references for a data extent, since the fs tree path * is the same (same leaf, so same path). We skip as long as the * cached result for the leaf is valid and only if there's only * one file extent item pointing to the data extent, because in * the case of multiple file extent items, they may be located * in different leaves and therefore we have multiple paths. */ if (sc->ctx->curr_leaf_bytenr == sc->ctx->prev_leaf_bytenr && sc->self_ref_count == 1) { bool cached; bool is_shared; cached = lookup_backref_shared_cache(sc->ctx, sc->root, sc->ctx->curr_leaf_bytenr, 0, &is_shared); if (cached) { if (is_shared) ret = BACKREF_FOUND_SHARED; else ret = BACKREF_FOUND_NOT_SHARED; goto out; } } } btrfs_release_path(path); ret = add_missing_keys(ctx->fs_info, &preftrees, path->skip_locking == 0); if (ret) goto out; WARN_ON(!RB_EMPTY_ROOT(&preftrees.indirect_missing_keys.root.rb_root)); ret = resolve_indirect_refs(ctx, path, &preftrees, sc); if (ret) goto out; WARN_ON(!RB_EMPTY_ROOT(&preftrees.indirect.root.rb_root)); /* * This walks the tree of merged and resolved refs. Tree blocks are * read in as needed. Unique entries are added to the ulist, and * the list of found roots is updated. * * We release the entire tree in one go before returning. */ node = rb_first_cached(&preftrees.direct.root); while (node) { ref = rb_entry(node, struct prelim_ref, rbnode); node = rb_next(&ref->rbnode); /* * ref->count < 0 can happen here if there are delayed * refs with a node->action of BTRFS_DROP_DELAYED_REF. * prelim_ref_insert() relies on this when merging * identical refs to keep the overall count correct. * prelim_ref_insert() will merge only those refs * which compare identically. Any refs having * e.g. different offsets would not be merged, * and would retain their original ref->count < 0. */ if (ctx->roots && ref->count && ref->root_id && ref->parent == 0) { /* no parent == root of tree */ ret = ulist_add(ctx->roots, ref->root_id, 0, GFP_NOFS); if (ret < 0) goto out; } if (ref->count && ref->parent) { if (!ctx->skip_inode_ref_list && !ref->inode_list && ref->level == 0) { struct btrfs_tree_parent_check check = { 0 }; struct extent_buffer *eb; check.level = ref->level; eb = read_tree_block(ctx->fs_info, ref->parent, &check); if (IS_ERR(eb)) { ret = PTR_ERR(eb); goto out; } if (!extent_buffer_uptodate(eb)) { free_extent_buffer(eb); ret = -EIO; goto out; } if (!path->skip_locking) btrfs_tree_read_lock(eb); ret = find_extent_in_eb(ctx, eb, &eie); if (!path->skip_locking) btrfs_tree_read_unlock(eb); free_extent_buffer(eb); if (ret == BTRFS_ITERATE_EXTENT_INODES_STOP || ret < 0) goto out; ref->inode_list = eie; /* * We transferred the list ownership to the ref, * so set to NULL to avoid a double free in case * an error happens after this. */ eie = NULL; } ret = ulist_add_merge_ptr(ctx->refs, ref->parent, ref->inode_list, (void **)&eie, GFP_NOFS); if (ret < 0) goto out; if (!ret && !ctx->skip_inode_ref_list) { /* * We've recorded that parent, so we must extend * its inode list here. * * However if there was corruption we may not * have found an eie, return an error in this * case. */ ASSERT(eie); if (!eie) { ret = -EUCLEAN; goto out; } while (eie->next) eie = eie->next; eie->next = ref->inode_list; } eie = NULL; /* * We have transferred the inode list ownership from * this ref to the ref we added to the 'refs' ulist. * So set this ref's inode list to NULL to avoid * use-after-free when our caller uses it or double * frees in case an error happens before we return. */ ref->inode_list = NULL; } cond_resched(); } out: btrfs_free_path(path); prelim_release(&preftrees.direct); prelim_release(&preftrees.indirect); prelim_release(&preftrees.indirect_missing_keys); if (ret == BTRFS_ITERATE_EXTENT_INODES_STOP || ret < 0) free_inode_elem_list(eie); return ret; } /* * Finds all leaves with a reference to the specified combination of * @ctx->bytenr and @ctx->extent_item_pos. The bytenr of the found leaves are * added to the ulist at @ctx->refs, and that ulist is allocated by this * function. The caller should free the ulist with free_leaf_list() if * @ctx->ignore_extent_item_pos is false, otherwise a fimple ulist_free() is * enough. * * Returns 0 on success and < 0 on error. On error @ctx->refs is not allocated. */ int btrfs_find_all_leafs(struct btrfs_backref_walk_ctx *ctx) { int ret; ASSERT(ctx->refs == NULL); ctx->refs = ulist_alloc(GFP_NOFS); if (!ctx->refs) return -ENOMEM; ret = find_parent_nodes(ctx, NULL); if (ret == BTRFS_ITERATE_EXTENT_INODES_STOP || (ret < 0 && ret != -ENOENT)) { free_leaf_list(ctx->refs); ctx->refs = NULL; return ret; } return 0; } /* * Walk all backrefs for a given extent to find all roots that reference this * extent. Walking a backref means finding all extents that reference this * extent and in turn walk the backrefs of those, too. Naturally this is a * recursive process, but here it is implemented in an iterative fashion: We * find all referencing extents for the extent in question and put them on a * list. In turn, we find all referencing extents for those, further appending * to the list. The way we iterate the list allows adding more elements after * the current while iterating. The process stops when we reach the end of the * list. * * Found roots are added to @ctx->roots, which is allocated by this function if * it points to NULL, in which case the caller is responsible for freeing it * after it's not needed anymore. * This function requires @ctx->refs to be NULL, as it uses it for allocating a * ulist to do temporary work, and frees it before returning. * * Returns 0 on success, < 0 on error. */ static int btrfs_find_all_roots_safe(struct btrfs_backref_walk_ctx *ctx) { const u64 orig_bytenr = ctx->bytenr; const bool orig_skip_inode_ref_list = ctx->skip_inode_ref_list; bool roots_ulist_allocated = false; struct ulist_iterator uiter; int ret = 0; ASSERT(ctx->refs == NULL); ctx->refs = ulist_alloc(GFP_NOFS); if (!ctx->refs) return -ENOMEM; if (!ctx->roots) { ctx->roots = ulist_alloc(GFP_NOFS); if (!ctx->roots) { ulist_free(ctx->refs); ctx->refs = NULL; return -ENOMEM; } roots_ulist_allocated = true; } ctx->skip_inode_ref_list = true; ULIST_ITER_INIT(&uiter); while (1) { struct ulist_node *node; ret = find_parent_nodes(ctx, NULL); if (ret < 0 && ret != -ENOENT) { if (roots_ulist_allocated) { ulist_free(ctx->roots); ctx->roots = NULL; } break; } ret = 0; node = ulist_next(ctx->refs, &uiter); if (!node) break; ctx->bytenr = node->val; cond_resched(); } ulist_free(ctx->refs); ctx->refs = NULL; ctx->bytenr = orig_bytenr; ctx->skip_inode_ref_list = orig_skip_inode_ref_list; return ret; } int btrfs_find_all_roots(struct btrfs_backref_walk_ctx *ctx, bool skip_commit_root_sem) { int ret; if (!ctx->trans && !skip_commit_root_sem) down_read(&ctx->fs_info->commit_root_sem); ret = btrfs_find_all_roots_safe(ctx); if (!ctx->trans && !skip_commit_root_sem) up_read(&ctx->fs_info->commit_root_sem); return ret; } struct btrfs_backref_share_check_ctx *btrfs_alloc_backref_share_check_ctx(void) { struct btrfs_backref_share_check_ctx *ctx; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) return NULL; ulist_init(&ctx->refs); return ctx; } void btrfs_free_backref_share_ctx(struct btrfs_backref_share_check_ctx *ctx) { if (!ctx) return; ulist_release(&ctx->refs); kfree(ctx); } /* * Check if a data extent is shared or not. * * @inode: The inode whose extent we are checking. * @bytenr: Logical bytenr of the extent we are checking. * @extent_gen: Generation of the extent (file extent item) or 0 if it is * not known. * @ctx: A backref sharedness check context. * * btrfs_is_data_extent_shared uses the backref walking code but will short * circuit as soon as it finds a root or inode that doesn't match the * one passed in. This provides a significant performance benefit for * callers (such as fiemap) which want to know whether the extent is * shared but do not need a ref count. * * This attempts to attach to the running transaction in order to account for * delayed refs, but continues on even when no running transaction exists. * * Return: 0 if extent is not shared, 1 if it is shared, < 0 on error. */ int btrfs_is_data_extent_shared(struct btrfs_inode *inode, u64 bytenr, u64 extent_gen, struct btrfs_backref_share_check_ctx *ctx) { struct btrfs_backref_walk_ctx walk_ctx = { 0 }; struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_trans_handle *trans; struct ulist_iterator uiter; struct ulist_node *node; struct btrfs_seq_list elem = BTRFS_SEQ_LIST_INIT(elem); int ret = 0; struct share_check shared = { .ctx = ctx, .root = root, .inum = btrfs_ino(inode), .data_bytenr = bytenr, .data_extent_gen = extent_gen, .share_count = 0, .self_ref_count = 0, .have_delayed_delete_refs = false, }; int level; bool leaf_cached; bool leaf_is_shared; for (int i = 0; i < BTRFS_BACKREF_CTX_PREV_EXTENTS_SIZE; i++) { if (ctx->prev_extents_cache[i].bytenr == bytenr) return ctx->prev_extents_cache[i].is_shared; } ulist_init(&ctx->refs); trans = btrfs_join_transaction_nostart(root); if (IS_ERR(trans)) { if (PTR_ERR(trans) != -ENOENT && PTR_ERR(trans) != -EROFS) { ret = PTR_ERR(trans); goto out; } trans = NULL; down_read(&fs_info->commit_root_sem); } else { btrfs_get_tree_mod_seq(fs_info, &elem); walk_ctx.time_seq = elem.seq; } ctx->use_path_cache = true; /* * We may have previously determined that the current leaf is shared. * If it is, then we have a data extent that is shared due to a shared * subtree (caused by snapshotting) and we don't need to check for data * backrefs. If the leaf is not shared, then we must do backref walking * to determine if the data extent is shared through reflinks. */ leaf_cached = lookup_backref_shared_cache(ctx, root, ctx->curr_leaf_bytenr, 0, &leaf_is_shared); if (leaf_cached && leaf_is_shared) { ret = 1; goto out_trans; } walk_ctx.skip_inode_ref_list = true; walk_ctx.trans = trans; walk_ctx.fs_info = fs_info; walk_ctx.refs = &ctx->refs; /* -1 means we are in the bytenr of the data extent. */ level = -1; ULIST_ITER_INIT(&uiter); while (1) { const unsigned long prev_ref_count = ctx->refs.nnodes; walk_ctx.bytenr = bytenr; ret = find_parent_nodes(&walk_ctx, &shared); if (ret == BACKREF_FOUND_SHARED || ret == BACKREF_FOUND_NOT_SHARED) { /* If shared must return 1, otherwise return 0. */ ret = (ret == BACKREF_FOUND_SHARED) ? 1 : 0; if (level >= 0) store_backref_shared_cache(ctx, root, bytenr, level, ret == 1); break; } if (ret < 0 && ret != -ENOENT) break; ret = 0; /* * More than one extent buffer (bytenr) may have been added to * the ctx->refs ulist, in which case we have to check multiple * tree paths in case the first one is not shared, so we can not * use the path cache which is made for a single path. Multiple * extent buffers at the current level happen when: * * 1) level -1, the data extent: If our data extent was not * directly shared (without multiple reference items), then * it might have a single reference item with a count > 1 for * the same offset, which means there are 2 (or more) file * extent items that point to the data extent - this happens * when a file extent item needs to be split and then one * item gets moved to another leaf due to a b+tree leaf split * when inserting some item. In this case the file extent * items may be located in different leaves and therefore * some of the leaves may be referenced through shared * subtrees while others are not. Since our extent buffer * cache only works for a single path (by far the most common * case and simpler to deal with), we can not use it if we * have multiple leaves (which implies multiple paths). * * 2) level >= 0, a tree node/leaf: We can have a mix of direct * and indirect references on a b+tree node/leaf, so we have * to check multiple paths, and the extent buffer (the * current bytenr) may be shared or not. One example is * during relocation as we may get a shared tree block ref * (direct ref) and a non-shared tree block ref (indirect * ref) for the same node/leaf. */ if ((ctx->refs.nnodes - prev_ref_count) > 1) ctx->use_path_cache = false; if (level >= 0) store_backref_shared_cache(ctx, root, bytenr, level, false); node = ulist_next(&ctx->refs, &uiter); if (!node) break; bytenr = node->val; if (ctx->use_path_cache) { bool is_shared; bool cached; level++; cached = lookup_backref_shared_cache(ctx, root, bytenr, level, &is_shared); if (cached) { ret = (is_shared ? 1 : 0); break; } } shared.share_count = 0; shared.have_delayed_delete_refs = false; cond_resched(); } /* * If the path cache is disabled, then it means at some tree level we * got multiple parents due to a mix of direct and indirect backrefs or * multiple leaves with file extent items pointing to the same data * extent. We have to invalidate the cache and cache only the sharedness * result for the levels where we got only one node/reference. */ if (!ctx->use_path_cache) { int i = 0; level--; if (ret >= 0 && level >= 0) { bytenr = ctx->path_cache_entries[level].bytenr; ctx->use_path_cache = true; store_backref_shared_cache(ctx, root, bytenr, level, ret); i = level + 1; } for ( ; i < BTRFS_MAX_LEVEL; i++) ctx->path_cache_entries[i].bytenr = 0; } /* * Cache the sharedness result for the data extent if we know our inode * has more than 1 file extent item that refers to the data extent. */ if (ret >= 0 && shared.self_ref_count > 1) { int slot = ctx->prev_extents_cache_slot; ctx->prev_extents_cache[slot].bytenr = shared.data_bytenr; ctx->prev_extents_cache[slot].is_shared = (ret == 1); slot = (slot + 1) % BTRFS_BACKREF_CTX_PREV_EXTENTS_SIZE; ctx->prev_extents_cache_slot = slot; } out_trans: if (trans) { btrfs_put_tree_mod_seq(fs_info, &elem); btrfs_end_transaction(trans); } else { up_read(&fs_info->commit_root_sem); } out: ulist_release(&ctx->refs); ctx->prev_leaf_bytenr = ctx->curr_leaf_bytenr; return ret; } int btrfs_find_one_extref(struct btrfs_root *root, u64 inode_objectid, u64 start_off, struct btrfs_path *path, struct btrfs_inode_extref **ret_extref, u64 *found_off) { int ret, slot; struct btrfs_key key; struct btrfs_key found_key; struct btrfs_inode_extref *extref; const struct extent_buffer *leaf; unsigned long ptr; key.objectid = inode_objectid; key.type = BTRFS_INODE_EXTREF_KEY; key.offset = start_off; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) return ret; while (1) { leaf = path->nodes[0]; slot = path->slots[0]; if (slot >= btrfs_header_nritems(leaf)) { /* * If the item at offset is not found, * btrfs_search_slot will point us to the slot * where it should be inserted. In our case * that will be the slot directly before the * next INODE_REF_KEY_V2 item. In the case * that we're pointing to the last slot in a * leaf, we must move one leaf over. */ ret = btrfs_next_leaf(root, path); if (ret) { if (ret >= 1) ret = -ENOENT; break; } continue; } btrfs_item_key_to_cpu(leaf, &found_key, slot); /* * Check that we're still looking at an extended ref key for * this particular objectid. If we have different * objectid or type then there are no more to be found * in the tree and we can exit. */ ret = -ENOENT; if (found_key.objectid != inode_objectid) break; if (found_key.type != BTRFS_INODE_EXTREF_KEY) break; ret = 0; ptr = btrfs_item_ptr_offset(leaf, path->slots[0]); extref = (struct btrfs_inode_extref *)ptr; *ret_extref = extref; if (found_off) *found_off = found_key.offset; break; } return ret; } /* * this iterates to turn a name (from iref/extref) into a full filesystem path. * Elements of the path are separated by '/' and the path is guaranteed to be * 0-terminated. the path is only given within the current file system. * Therefore, it never starts with a '/'. the caller is responsible to provide * "size" bytes in "dest". the dest buffer will be filled backwards. finally, * the start point of the resulting string is returned. this pointer is within * dest, normally. * in case the path buffer would overflow, the pointer is decremented further * as if output was written to the buffer, though no more output is actually * generated. that way, the caller can determine how much space would be * required for the path to fit into the buffer. in that case, the returned * value will be smaller than dest. callers must check this! */ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path, u32 name_len, unsigned long name_off, struct extent_buffer *eb_in, u64 parent, char *dest, u32 size) { int slot; u64 next_inum; int ret; s64 bytes_left = ((s64)size) - 1; struct extent_buffer *eb = eb_in; struct btrfs_key found_key; struct btrfs_inode_ref *iref; if (bytes_left >= 0) dest[bytes_left] = '\0'; while (1) { bytes_left -= name_len; if (bytes_left >= 0) read_extent_buffer(eb, dest + bytes_left, name_off, name_len); if (eb != eb_in) { if (!path->skip_locking) btrfs_tree_read_unlock(eb); free_extent_buffer(eb); } ret = btrfs_find_item(fs_root, path, parent, 0, BTRFS_INODE_REF_KEY, &found_key); if (ret > 0) ret = -ENOENT; if (ret) break; next_inum = found_key.offset; /* regular exit ahead */ if (parent == next_inum) break; slot = path->slots[0]; eb = path->nodes[0]; /* make sure we can use eb after releasing the path */ if (eb != eb_in) { path->nodes[0] = NULL; path->locks[0] = 0; } btrfs_release_path(path); iref = btrfs_item_ptr(eb, slot, struct btrfs_inode_ref); name_len = btrfs_inode_ref_name_len(eb, iref); name_off = (unsigned long)(iref + 1); parent = next_inum; --bytes_left; if (bytes_left >= 0) dest[bytes_left] = '/'; } btrfs_release_path(path); if (ret) return ERR_PTR(ret); return dest + bytes_left; } /* * this makes the path point to (logical EXTENT_ITEM *) * returns BTRFS_EXTENT_FLAG_DATA for data, BTRFS_EXTENT_FLAG_TREE_BLOCK for * tree blocks and <0 on error. */ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical, struct btrfs_path *path, struct btrfs_key *found_key, u64 *flags_ret) { struct btrfs_root *extent_root = btrfs_extent_root(fs_info, logical); int ret; u64 flags; u64 size = 0; u32 item_size; const struct extent_buffer *eb; struct btrfs_extent_item *ei; struct btrfs_key key; if (btrfs_fs_incompat(fs_info, SKINNY_METADATA)) key.type = BTRFS_METADATA_ITEM_KEY; else key.type = BTRFS_EXTENT_ITEM_KEY; key.objectid = logical; key.offset = (u64)-1; ret = btrfs_search_slot(NULL, extent_root, &key, path, 0, 0); if (ret < 0) return ret; if (ret == 0) { /* * Key with offset -1 found, there would have to exist an extent * item with such offset, but this is out of the valid range. */ return -EUCLEAN; } ret = btrfs_previous_extent_item(extent_root, path, 0); if (ret) { if (ret > 0) ret = -ENOENT; return ret; } btrfs_item_key_to_cpu(path->nodes[0], found_key, path->slots[0]); if (found_key->type == BTRFS_METADATA_ITEM_KEY) size = fs_info->nodesize; else if (found_key->type == BTRFS_EXTENT_ITEM_KEY) size = found_key->offset; if (found_key->objectid > logical || found_key->objectid + size <= logical) { btrfs_debug(fs_info, "logical %llu is not within any extent", logical); return -ENOENT; } eb = path->nodes[0]; item_size = btrfs_item_size(eb, path->slots[0]); ei = btrfs_item_ptr(eb, path->slots[0], struct btrfs_extent_item); flags = btrfs_extent_flags(eb, ei); btrfs_debug(fs_info, "logical %llu is at position %llu within the extent (%llu EXTENT_ITEM %llu) flags %#llx size %u", logical, logical - found_key->objectid, found_key->objectid, found_key->offset, flags, item_size); WARN_ON(!flags_ret); if (flags_ret) { if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) *flags_ret = BTRFS_EXTENT_FLAG_TREE_BLOCK; else if (flags & BTRFS_EXTENT_FLAG_DATA) *flags_ret = BTRFS_EXTENT_FLAG_DATA; else BUG(); return 0; } return -EIO; } /* * helper function to iterate extent inline refs. ptr must point to a 0 value * for the first call and may be modified. it is used to track state. * if more refs exist, 0 is returned and the next call to * get_extent_inline_ref must pass the modified ptr parameter to get the * next ref. after the last ref was processed, 1 is returned. * returns <0 on error */ static int get_extent_inline_ref(unsigned long *ptr, const struct extent_buffer *eb, const struct btrfs_key *key, const struct btrfs_extent_item *ei, u32 item_size, struct btrfs_extent_inline_ref **out_eiref, int *out_type) { unsigned long end; u64 flags; struct btrfs_tree_block_info *info; if (!*ptr) { /* first call */ flags = btrfs_extent_flags(eb, ei); if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) { if (key->type == BTRFS_METADATA_ITEM_KEY) { /* a skinny metadata extent */ *out_eiref = (struct btrfs_extent_inline_ref *)(ei + 1); } else { WARN_ON(key->type != BTRFS_EXTENT_ITEM_KEY); info = (struct btrfs_tree_block_info *)(ei + 1); *out_eiref = (struct btrfs_extent_inline_ref *)(info + 1); } } else { *out_eiref = (struct btrfs_extent_inline_ref *)(ei + 1); } *ptr = (unsigned long)*out_eiref; if ((unsigned long)(*ptr) >= (unsigned long)ei + item_size) return -ENOENT; } end = (unsigned long)ei + item_size; *out_eiref = (struct btrfs_extent_inline_ref *)(*ptr); *out_type = btrfs_get_extent_inline_ref_type(eb, *out_eiref, BTRFS_REF_TYPE_ANY); if (*out_type == BTRFS_REF_TYPE_INVALID) return -EUCLEAN; *ptr += btrfs_extent_inline_ref_size(*out_type); WARN_ON(*ptr > end); if (*ptr == end) return 1; /* last */ return 0; } /* * reads the tree block backref for an extent. tree level and root are returned * through out_level and out_root. ptr must point to a 0 value for the first * call and may be modified (see get_extent_inline_ref comment). * returns 0 if data was provided, 1 if there was no more data to provide or * <0 on error. */ int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb, struct btrfs_key *key, struct btrfs_extent_item *ei, u32 item_size, u64 *out_root, u8 *out_level) { int ret; int type; struct btrfs_extent_inline_ref *eiref; if (*ptr == (unsigned long)-1) return 1; while (1) { ret = get_extent_inline_ref(ptr, eb, key, ei, item_size, &eiref, &type); if (ret < 0) return ret; if (type == BTRFS_TREE_BLOCK_REF_KEY || type == BTRFS_SHARED_BLOCK_REF_KEY) break; if (ret == 1) return 1; } /* we can treat both ref types equally here */ *out_root = btrfs_extent_inline_ref_offset(eb, eiref); if (key->type == BTRFS_EXTENT_ITEM_KEY) { struct btrfs_tree_block_info *info; info = (struct btrfs_tree_block_info *)(ei + 1); *out_level = btrfs_tree_block_level(eb, info); } else { ASSERT(key->type == BTRFS_METADATA_ITEM_KEY); *out_level = (u8)key->offset; } if (ret == 1) *ptr = (unsigned long)-1; return 0; } static int iterate_leaf_refs(struct btrfs_fs_info *fs_info, struct extent_inode_elem *inode_list, u64 root, u64 extent_item_objectid, iterate_extent_inodes_t *iterate, void *ctx) { struct extent_inode_elem *eie; int ret = 0; for (eie = inode_list; eie; eie = eie->next) { btrfs_debug(fs_info, "ref for %llu resolved, key (%llu EXTEND_DATA %llu), root %llu", extent_item_objectid, eie->inum, eie->offset, root); ret = iterate(eie->inum, eie->offset, eie->num_bytes, root, ctx); if (ret) { btrfs_debug(fs_info, "stopping iteration for %llu due to ret=%d", extent_item_objectid, ret); break; } } return ret; } /* * calls iterate() for every inode that references the extent identified by * the given parameters. * when the iterator function returns a non-zero value, iteration stops. */ int iterate_extent_inodes(struct btrfs_backref_walk_ctx *ctx, bool search_commit_root, iterate_extent_inodes_t *iterate, void *user_ctx) { int ret; struct ulist *refs; struct ulist_node *ref_node; struct btrfs_seq_list seq_elem = BTRFS_SEQ_LIST_INIT(seq_elem); struct ulist_iterator ref_uiter; btrfs_debug(ctx->fs_info, "resolving all inodes for extent %llu", ctx->bytenr); ASSERT(ctx->trans == NULL); ASSERT(ctx->roots == NULL); if (!search_commit_root) { struct btrfs_trans_handle *trans; trans = btrfs_attach_transaction(ctx->fs_info->tree_root); if (IS_ERR(trans)) { if (PTR_ERR(trans) != -ENOENT && PTR_ERR(trans) != -EROFS) return PTR_ERR(trans); trans = NULL; } ctx->trans = trans; } if (ctx->trans) { btrfs_get_tree_mod_seq(ctx->fs_info, &seq_elem); ctx->time_seq = seq_elem.seq; } else { down_read(&ctx->fs_info->commit_root_sem); } ret = btrfs_find_all_leafs(ctx); if (ret) goto out; refs = ctx->refs; ctx->refs = NULL; ULIST_ITER_INIT(&ref_uiter); while (!ret && (ref_node = ulist_next(refs, &ref_uiter))) { const u64 leaf_bytenr = ref_node->val; struct ulist_node *root_node; struct ulist_iterator root_uiter; struct extent_inode_elem *inode_list; inode_list = (struct extent_inode_elem *)(uintptr_t)ref_node->aux; if (ctx->cache_lookup) { const u64 *root_ids; int root_count; bool cached; cached = ctx->cache_lookup(leaf_bytenr, ctx->user_ctx, &root_ids, &root_count); if (cached) { for (int i = 0; i < root_count; i++) { ret = iterate_leaf_refs(ctx->fs_info, inode_list, root_ids[i], leaf_bytenr, iterate, user_ctx); if (ret) break; } continue; } } if (!ctx->roots) { ctx->roots = ulist_alloc(GFP_NOFS); if (!ctx->roots) { ret = -ENOMEM; break; } } ctx->bytenr = leaf_bytenr; ret = btrfs_find_all_roots_safe(ctx); if (ret) break; if (ctx->cache_store) ctx->cache_store(leaf_bytenr, ctx->roots, ctx->user_ctx); ULIST_ITER_INIT(&root_uiter); while (!ret && (root_node = ulist_next(ctx->roots, &root_uiter))) { btrfs_debug(ctx->fs_info, "root %llu references leaf %llu, data list %#llx", root_node->val, ref_node->val, ref_node->aux); ret = iterate_leaf_refs(ctx->fs_info, inode_list, root_node->val, ctx->bytenr, iterate, user_ctx); } ulist_reinit(ctx->roots); } free_leaf_list(refs); out: if (ctx->trans) { btrfs_put_tree_mod_seq(ctx->fs_info, &seq_elem); btrfs_end_transaction(ctx->trans); ctx->trans = NULL; } else { up_read(&ctx->fs_info->commit_root_sem); } ulist_free(ctx->roots); ctx->roots = NULL; if (ret == BTRFS_ITERATE_EXTENT_INODES_STOP) ret = 0; return ret; } static int build_ino_list(u64 inum, u64 offset, u64 num_bytes, u64 root, void *ctx) { struct btrfs_data_container *inodes = ctx; const size_t c = 3 * sizeof(u64); if (inodes->bytes_left >= c) { inodes->bytes_left -= c; inodes->val[inodes->elem_cnt] = inum; inodes->val[inodes->elem_cnt + 1] = offset; inodes->val[inodes->elem_cnt + 2] = root; inodes->elem_cnt += 3; } else { inodes->bytes_missing += c - inodes->bytes_left; inodes->bytes_left = 0; inodes->elem_missed += 3; } return 0; } int iterate_inodes_from_logical(u64 logical, struct btrfs_fs_info *fs_info, struct btrfs_path *path, void *ctx, bool ignore_offset) { struct btrfs_backref_walk_ctx walk_ctx = { 0 }; int ret; u64 flags = 0; struct btrfs_key found_key; int search_commit_root = path->search_commit_root; ret = extent_from_logical(fs_info, logical, path, &found_key, &flags); btrfs_release_path(path); if (ret < 0) return ret; if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) return -EINVAL; walk_ctx.bytenr = found_key.objectid; if (ignore_offset) walk_ctx.ignore_extent_item_pos = true; else walk_ctx.extent_item_pos = logical - found_key.objectid; walk_ctx.fs_info = fs_info; return iterate_extent_inodes(&walk_ctx, search_commit_root, build_ino_list, ctx); } static int inode_to_path(u64 inum, u32 name_len, unsigned long name_off, struct extent_buffer *eb, struct inode_fs_paths *ipath); static int iterate_inode_refs(u64 inum, struct inode_fs_paths *ipath) { int ret = 0; int slot; u32 cur; u32 len; u32 name_len; u64 parent = 0; int found = 0; struct btrfs_root *fs_root = ipath->fs_root; struct btrfs_path *path = ipath->btrfs_path; struct extent_buffer *eb; struct btrfs_inode_ref *iref; struct btrfs_key found_key; while (!ret) { ret = btrfs_find_item(fs_root, path, inum, parent ? parent + 1 : 0, BTRFS_INODE_REF_KEY, &found_key); if (ret < 0) break; if (ret) { ret = found ? 0 : -ENOENT; break; } ++found; parent = found_key.offset; slot = path->slots[0]; eb = btrfs_clone_extent_buffer(path->nodes[0]); if (!eb) { ret = -ENOMEM; break; } btrfs_release_path(path); iref = btrfs_item_ptr(eb, slot, struct btrfs_inode_ref); for (cur = 0; cur < btrfs_item_size(eb, slot); cur += len) { name_len = btrfs_inode_ref_name_len(eb, iref); /* path must be released before calling iterate()! */ btrfs_debug(fs_root->fs_info, "following ref at offset %u for inode %llu in tree %llu", cur, found_key.objectid, btrfs_root_id(fs_root)); ret = inode_to_path(parent, name_len, (unsigned long)(iref + 1), eb, ipath); if (ret) break; len = sizeof(*iref) + name_len; iref = (struct btrfs_inode_ref *)((char *)iref + len); } free_extent_buffer(eb); } btrfs_release_path(path); return ret; } static int iterate_inode_extrefs(u64 inum, struct inode_fs_paths *ipath) { int ret; int slot; u64 offset = 0; u64 parent; int found = 0; struct btrfs_root *fs_root = ipath->fs_root; struct btrfs_path *path = ipath->btrfs_path; struct extent_buffer *eb; struct btrfs_inode_extref *extref; u32 item_size; u32 cur_offset; unsigned long ptr; while (1) { ret = btrfs_find_one_extref(fs_root, inum, offset, path, &extref, &offset); if (ret < 0) break; if (ret) { ret = found ? 0 : -ENOENT; break; } ++found; slot = path->slots[0]; eb = btrfs_clone_extent_buffer(path->nodes[0]); if (!eb) { ret = -ENOMEM; break; } btrfs_release_path(path); item_size = btrfs_item_size(eb, slot); ptr = btrfs_item_ptr_offset(eb, slot); cur_offset = 0; while (cur_offset < item_size) { u32 name_len; extref = (struct btrfs_inode_extref *)(ptr + cur_offset); parent = btrfs_inode_extref_parent(eb, extref); name_len = btrfs_inode_extref_name_len(eb, extref); ret = inode_to_path(parent, name_len, (unsigned long)&extref->name, eb, ipath); if (ret) break; cur_offset += btrfs_inode_extref_name_len(eb, extref); cur_offset += sizeof(*extref); } free_extent_buffer(eb); offset++; } btrfs_release_path(path); return ret; } /* * returns 0 if the path could be dumped (probably truncated) * returns <0 in case of an error */ static int inode_to_path(u64 inum, u32 name_len, unsigned long name_off, struct extent_buffer *eb, struct inode_fs_paths *ipath) { char *fspath; char *fspath_min; int i = ipath->fspath->elem_cnt; const int s_ptr = sizeof(char *); u32 bytes_left; bytes_left = ipath->fspath->bytes_left > s_ptr ? ipath->fspath->bytes_left - s_ptr : 0; fspath_min = (char *)ipath->fspath->val + (i + 1) * s_ptr; fspath = btrfs_ref_to_path(ipath->fs_root, ipath->btrfs_path, name_len, name_off, eb, inum, fspath_min, bytes_left); if (IS_ERR(fspath)) return PTR_ERR(fspath); if (fspath > fspath_min) { ipath->fspath->val[i] = (u64)(unsigned long)fspath; ++ipath->fspath->elem_cnt; ipath->fspath->bytes_left = fspath - fspath_min; } else { ++ipath->fspath->elem_missed; ipath->fspath->bytes_missing += fspath_min - fspath; ipath->fspath->bytes_left = 0; } return 0; } /* * this dumps all file system paths to the inode into the ipath struct, provided * is has been created large enough. each path is zero-terminated and accessed * from ipath->fspath->val[i]. * when it returns, there are ipath->fspath->elem_cnt number of paths available * in ipath->fspath->val[]. when the allocated space wasn't sufficient, the * number of missed paths is recorded in ipath->fspath->elem_missed, otherwise, * it's zero. ipath->fspath->bytes_missing holds the number of bytes that would * have been needed to return all paths. */ int paths_from_inode(u64 inum, struct inode_fs_paths *ipath) { int ret; int found_refs = 0; ret = iterate_inode_refs(inum, ipath); if (!ret) ++found_refs; else if (ret != -ENOENT) return ret; ret = iterate_inode_extrefs(inum, ipath); if (ret == -ENOENT && found_refs) return 0; return ret; } struct btrfs_data_container *init_data_container(u32 total_bytes) { struct btrfs_data_container *data; size_t alloc_bytes; alloc_bytes = max_t(size_t, total_bytes, sizeof(*data)); data = kvzalloc(alloc_bytes, GFP_KERNEL); if (!data) return ERR_PTR(-ENOMEM); if (total_bytes >= sizeof(*data)) data->bytes_left = total_bytes - sizeof(*data); else data->bytes_missing = sizeof(*data) - total_bytes; return data; } /* * allocates space to return multiple file system paths for an inode. * total_bytes to allocate are passed, note that space usable for actual path * information will be total_bytes - sizeof(struct inode_fs_paths). * the returned pointer must be freed with free_ipath() in the end. */ struct inode_fs_paths *init_ipath(s32 total_bytes, struct btrfs_root *fs_root, struct btrfs_path *path) { struct inode_fs_paths *ifp; struct btrfs_data_container *fspath; fspath = init_data_container(total_bytes); if (IS_ERR(fspath)) return ERR_CAST(fspath); ifp = kmalloc(sizeof(*ifp), GFP_KERNEL); if (!ifp) { kvfree(fspath); return ERR_PTR(-ENOMEM); } ifp->btrfs_path = path; ifp->fspath = fspath; ifp->fs_root = fs_root; return ifp; } void free_ipath(struct inode_fs_paths *ipath) { if (!ipath) return; kvfree(ipath->fspath); kfree(ipath); } struct btrfs_backref_iter *btrfs_backref_iter_alloc(struct btrfs_fs_info *fs_info) { struct btrfs_backref_iter *ret; ret = kzalloc(sizeof(*ret), GFP_NOFS); if (!ret) return NULL; ret->path = btrfs_alloc_path(); if (!ret->path) { kfree(ret); return NULL; } /* Current backref iterator only supports iteration in commit root */ ret->path->search_commit_root = 1; ret->path->skip_locking = 1; ret->fs_info = fs_info; return ret; } static void btrfs_backref_iter_release(struct btrfs_backref_iter *iter) { iter->bytenr = 0; iter->item_ptr = 0; iter->cur_ptr = 0; iter->end_ptr = 0; btrfs_release_path(iter->path); memset(&iter->cur_key, 0, sizeof(iter->cur_key)); } int btrfs_backref_iter_start(struct btrfs_backref_iter *iter, u64 bytenr) { struct btrfs_fs_info *fs_info = iter->fs_info; struct btrfs_root *extent_root = btrfs_extent_root(fs_info, bytenr); struct btrfs_path *path = iter->path; struct btrfs_extent_item *ei; struct btrfs_key key; int ret; key.objectid = bytenr; key.type = BTRFS_METADATA_ITEM_KEY; key.offset = (u64)-1; iter->bytenr = bytenr; ret = btrfs_search_slot(NULL, extent_root, &key, path, 0, 0); if (ret < 0) return ret; if (ret == 0) { /* * Key with offset -1 found, there would have to exist an extent * item with such offset, but this is out of the valid range. */ ret = -EUCLEAN; goto release; } if (path->slots[0] == 0) { WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG)); ret = -EUCLEAN; goto release; } path->slots[0]--; btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if ((key.type != BTRFS_EXTENT_ITEM_KEY && key.type != BTRFS_METADATA_ITEM_KEY) || key.objectid != bytenr) { ret = -ENOENT; goto release; } memcpy(&iter->cur_key, &key, sizeof(key)); iter->item_ptr = (u32)btrfs_item_ptr_offset(path->nodes[0], path->slots[0]); iter->end_ptr = (u32)(iter->item_ptr + btrfs_item_size(path->nodes[0], path->slots[0])); ei = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_extent_item); /* * Only support iteration on tree backref yet. * * This is an extra precaution for non skinny-metadata, where * EXTENT_ITEM is also used for tree blocks, that we can only use * extent flags to determine if it's a tree block. */ if (btrfs_extent_flags(path->nodes[0], ei) & BTRFS_EXTENT_FLAG_DATA) { ret = -ENOTSUPP; goto release; } iter->cur_ptr = (u32)(iter->item_ptr + sizeof(*ei)); /* If there is no inline backref, go search for keyed backref */ if (iter->cur_ptr >= iter->end_ptr) { ret = btrfs_next_item(extent_root, path); /* No inline nor keyed ref */ if (ret > 0) { ret = -ENOENT; goto release; } if (ret < 0) goto release; btrfs_item_key_to_cpu(path->nodes[0], &iter->cur_key, path->slots[0]); if (iter->cur_key.objectid != bytenr || (iter->cur_key.type != BTRFS_SHARED_BLOCK_REF_KEY && iter->cur_key.type != BTRFS_TREE_BLOCK_REF_KEY)) { ret = -ENOENT; goto release; } iter->cur_ptr = (u32)btrfs_item_ptr_offset(path->nodes[0], path->slots[0]); iter->item_ptr = iter->cur_ptr; iter->end_ptr = (u32)(iter->item_ptr + btrfs_item_size( path->nodes[0], path->slots[0])); } return 0; release: btrfs_backref_iter_release(iter); return ret; } static bool btrfs_backref_iter_is_inline_ref(struct btrfs_backref_iter *iter) { if (iter->cur_key.type == BTRFS_EXTENT_ITEM_KEY || iter->cur_key.type == BTRFS_METADATA_ITEM_KEY) return true; return false; } /* * Go to the next backref item of current bytenr, can be either inlined or * keyed. * * Caller needs to check whether it's inline ref or not by iter->cur_key. * * Return 0 if we get next backref without problem. * Return >0 if there is no extra backref for this bytenr. * Return <0 if there is something wrong happened. */ int btrfs_backref_iter_next(struct btrfs_backref_iter *iter) { struct extent_buffer *eb = iter->path->nodes[0]; struct btrfs_root *extent_root; struct btrfs_path *path = iter->path; struct btrfs_extent_inline_ref *iref; int ret; u32 size; if (btrfs_backref_iter_is_inline_ref(iter)) { /* We're still inside the inline refs */ ASSERT(iter->cur_ptr < iter->end_ptr); if (btrfs_backref_has_tree_block_info(iter)) { /* First tree block info */ size = sizeof(struct btrfs_tree_block_info); } else { /* Use inline ref type to determine the size */ int type; iref = (struct btrfs_extent_inline_ref *) ((unsigned long)iter->cur_ptr); type = btrfs_extent_inline_ref_type(eb, iref); size = btrfs_extent_inline_ref_size(type); } iter->cur_ptr += size; if (iter->cur_ptr < iter->end_ptr) return 0; /* All inline items iterated, fall through */ } /* We're at keyed items, there is no inline item, go to the next one */ extent_root = btrfs_extent_root(iter->fs_info, iter->bytenr); ret = btrfs_next_item(extent_root, iter->path); if (ret) return ret; btrfs_item_key_to_cpu(path->nodes[0], &iter->cur_key, path->slots[0]); if (iter->cur_key.objectid != iter->bytenr || (iter->cur_key.type != BTRFS_TREE_BLOCK_REF_KEY && iter->cur_key.type != BTRFS_SHARED_BLOCK_REF_KEY)) return 1; iter->item_ptr = (u32)btrfs_item_ptr_offset(path->nodes[0], path->slots[0]); iter->cur_ptr = iter->item_ptr; iter->end_ptr = iter->item_ptr + (u32)btrfs_item_size(path->nodes[0], path->slots[0]); return 0; } void btrfs_backref_init_cache(struct btrfs_fs_info *fs_info, struct btrfs_backref_cache *cache, bool is_reloc) { int i; cache->rb_root = RB_ROOT; for (i = 0; i < BTRFS_MAX_LEVEL; i++) INIT_LIST_HEAD(&cache->pending[i]); INIT_LIST_HEAD(&cache->pending_edge); INIT_LIST_HEAD(&cache->useless_node); cache->fs_info = fs_info; cache->is_reloc = is_reloc; } struct btrfs_backref_node *btrfs_backref_alloc_node( struct btrfs_backref_cache *cache, u64 bytenr, int level) { struct btrfs_backref_node *node; ASSERT(level >= 0 && level < BTRFS_MAX_LEVEL); node = kzalloc(sizeof(*node), GFP_NOFS); if (!node) return node; INIT_LIST_HEAD(&node->list); INIT_LIST_HEAD(&node->upper); INIT_LIST_HEAD(&node->lower); RB_CLEAR_NODE(&node->rb_node); cache->nr_nodes++; node->level = level; node->bytenr = bytenr; return node; } void btrfs_backref_free_node(struct btrfs_backref_cache *cache, struct btrfs_backref_node *node) { if (node) { ASSERT(list_empty(&node->list)); ASSERT(list_empty(&node->lower)); ASSERT(node->eb == NULL); cache->nr_nodes--; btrfs_put_root(node->root); kfree(node); } } struct btrfs_backref_edge *btrfs_backref_alloc_edge( struct btrfs_backref_cache *cache) { struct btrfs_backref_edge *edge; edge = kzalloc(sizeof(*edge), GFP_NOFS); if (edge) cache->nr_edges++; return edge; } void btrfs_backref_free_edge(struct btrfs_backref_cache *cache, struct btrfs_backref_edge *edge) { if (edge) { cache->nr_edges--; kfree(edge); } } void btrfs_backref_unlock_node_buffer(struct btrfs_backref_node *node) { if (node->locked) { btrfs_tree_unlock(node->eb); node->locked = 0; } } void btrfs_backref_drop_node_buffer(struct btrfs_backref_node *node) { if (node->eb) { btrfs_backref_unlock_node_buffer(node); free_extent_buffer(node->eb); node->eb = NULL; } } /* * Drop the backref node from cache without cleaning up its children * edges. * * This can only be called on node without parent edges. * The children edges are still kept as is. */ void btrfs_backref_drop_node(struct btrfs_backref_cache *tree, struct btrfs_backref_node *node) { ASSERT(list_empty(&node->upper)); btrfs_backref_drop_node_buffer(node); list_del_init(&node->list); list_del_init(&node->lower); if (!RB_EMPTY_NODE(&node->rb_node)) rb_erase(&node->rb_node, &tree->rb_root); btrfs_backref_free_node(tree, node); } /* * Drop the backref node from cache, also cleaning up all its * upper edges and any uncached nodes in the path. * * This cleanup happens bottom up, thus the node should either * be the lowest node in the cache or a detached node. */ void btrfs_backref_cleanup_node(struct btrfs_backref_cache *cache, struct btrfs_backref_node *node) { struct btrfs_backref_edge *edge; if (!node) return; while (!list_empty(&node->upper)) { edge = list_entry(node->upper.next, struct btrfs_backref_edge, list[LOWER]); list_del(&edge->list[LOWER]); list_del(&edge->list[UPPER]); btrfs_backref_free_edge(cache, edge); } btrfs_backref_drop_node(cache, node); } /* * Release all nodes/edges from current cache */ void btrfs_backref_release_cache(struct btrfs_backref_cache *cache) { struct btrfs_backref_node *node; while ((node = rb_entry_safe(rb_first(&cache->rb_root), struct btrfs_backref_node, rb_node))) btrfs_backref_cleanup_node(cache, node); ASSERT(list_empty(&cache->pending_edge)); ASSERT(list_empty(&cache->useless_node)); ASSERT(!cache->nr_nodes); ASSERT(!cache->nr_edges); } void btrfs_backref_link_edge(struct btrfs_backref_edge *edge, struct btrfs_backref_node *lower, struct btrfs_backref_node *upper, int link_which) { ASSERT(upper && lower && upper->level == lower->level + 1); edge->node[LOWER] = lower; edge->node[UPPER] = upper; if (link_which & LINK_LOWER) list_add_tail(&edge->list[LOWER], &lower->upper); if (link_which & LINK_UPPER) list_add_tail(&edge->list[UPPER], &upper->lower); } /* * Handle direct tree backref * * Direct tree backref means, the backref item shows its parent bytenr * directly. This is for SHARED_BLOCK_REF backref (keyed or inlined). * * @ref_key: The converted backref key. * For keyed backref, it's the item key. * For inlined backref, objectid is the bytenr, * type is btrfs_inline_ref_type, offset is * btrfs_inline_ref_offset. */ static int handle_direct_tree_backref(struct btrfs_backref_cache *cache, struct btrfs_key *ref_key, struct btrfs_backref_node *cur) { struct btrfs_backref_edge *edge; struct btrfs_backref_node *upper; struct rb_node *rb_node; ASSERT(ref_key->type == BTRFS_SHARED_BLOCK_REF_KEY); /* Only reloc root uses backref pointing to itself */ if (ref_key->objectid == ref_key->offset) { struct btrfs_root *root; cur->is_reloc_root = 1; /* Only reloc backref cache cares about a specific root */ if (cache->is_reloc) { root = find_reloc_root(cache->fs_info, cur->bytenr); if (!root) return -ENOENT; cur->root = root; } else { /* * For generic purpose backref cache, reloc root node * is useless. */ list_add(&cur->list, &cache->useless_node); } return 0; } edge = btrfs_backref_alloc_edge(cache); if (!edge) return -ENOMEM; rb_node = rb_simple_search(&cache->rb_root, ref_key->offset); if (!rb_node) { /* Parent node not yet cached */ upper = btrfs_backref_alloc_node(cache, ref_key->offset, cur->level + 1); if (!upper) { btrfs_backref_free_edge(cache, edge); return -ENOMEM; } /* * Backrefs for the upper level block isn't cached, add the * block to pending list */ list_add_tail(&edge->list[UPPER], &cache->pending_edge); } else { /* Parent node already cached */ upper = rb_entry(rb_node, struct btrfs_backref_node, rb_node); ASSERT(upper->checked); INIT_LIST_HEAD(&edge->list[UPPER]); } btrfs_backref_link_edge(edge, cur, upper, LINK_LOWER); return 0; } /* * Handle indirect tree backref * * Indirect tree backref means, we only know which tree the node belongs to. * We still need to do a tree search to find out the parents. This is for * TREE_BLOCK_REF backref (keyed or inlined). * * @trans: Transaction handle. * @ref_key: The same as @ref_key in handle_direct_tree_backref() * @tree_key: The first key of this tree block. * @path: A clean (released) path, to avoid allocating path every time * the function get called. */ static int handle_indirect_tree_backref(struct btrfs_trans_handle *trans, struct btrfs_backref_cache *cache, struct btrfs_path *path, struct btrfs_key *ref_key, struct btrfs_key *tree_key, struct btrfs_backref_node *cur) { struct btrfs_fs_info *fs_info = cache->fs_info; struct btrfs_backref_node *upper; struct btrfs_backref_node *lower; struct btrfs_backref_edge *edge; struct extent_buffer *eb; struct btrfs_root *root; struct rb_node *rb_node; int level; bool need_check = true; int ret; root = btrfs_get_fs_root(fs_info, ref_key->offset, false); if (IS_ERR(root)) return PTR_ERR(root); /* We shouldn't be using backref cache for non-shareable roots. */ if (unlikely(!test_bit(BTRFS_ROOT_SHAREABLE, &root->state))) { btrfs_put_root(root); return -EUCLEAN; } if (btrfs_root_level(&root->root_item) == cur->level) { /* Tree root */ ASSERT(btrfs_root_bytenr(&root->root_item) == cur->bytenr); /* * For reloc backref cache, we may ignore reloc root. But for * general purpose backref cache, we can't rely on * btrfs_should_ignore_reloc_root() as it may conflict with * current running relocation and lead to missing root. * * For general purpose backref cache, reloc root detection is * completely relying on direct backref (key->offset is parent * bytenr), thus only do such check for reloc cache. */ if (btrfs_should_ignore_reloc_root(root) && cache->is_reloc) { btrfs_put_root(root); list_add(&cur->list, &cache->useless_node); } else { cur->root = root; } return 0; } level = cur->level + 1; /* Search the tree to find parent blocks referring to the block */ path->search_commit_root = 1; path->skip_locking = 1; path->lowest_level = level; ret = btrfs_search_slot(NULL, root, tree_key, path, 0, 0); path->lowest_level = 0; if (ret < 0) { btrfs_put_root(root); return ret; } if (ret > 0 && path->slots[level] > 0) path->slots[level]--; eb = path->nodes[level]; if (btrfs_node_blockptr(eb, path->slots[level]) != cur->bytenr) { btrfs_err(fs_info, "couldn't find block (%llu) (level %d) in tree (%llu) with key (%llu %u %llu)", cur->bytenr, level - 1, btrfs_root_id(root), tree_key->objectid, tree_key->type, tree_key->offset); btrfs_put_root(root); ret = -ENOENT; goto out; } lower = cur; /* Add all nodes and edges in the path */ for (; level < BTRFS_MAX_LEVEL; level++) { if (!path->nodes[level]) { ASSERT(btrfs_root_bytenr(&root->root_item) == lower->bytenr); /* Same as previous should_ignore_reloc_root() call */ if (btrfs_should_ignore_reloc_root(root) && cache->is_reloc) { btrfs_put_root(root); list_add(&lower->list, &cache->useless_node); } else { lower->root = root; } break; } edge = btrfs_backref_alloc_edge(cache); if (!edge) { btrfs_put_root(root); ret = -ENOMEM; goto out; } eb = path->nodes[level]; rb_node = rb_simple_search(&cache->rb_root, eb->start); if (!rb_node) { upper = btrfs_backref_alloc_node(cache, eb->start, lower->level + 1); if (!upper) { btrfs_put_root(root); btrfs_backref_free_edge(cache, edge); ret = -ENOMEM; goto out; } upper->owner = btrfs_header_owner(eb); /* We shouldn't be using backref cache for non shareable roots. */ if (unlikely(!test_bit(BTRFS_ROOT_SHAREABLE, &root->state))) { btrfs_put_root(root); btrfs_backref_free_edge(cache, edge); btrfs_backref_free_node(cache, upper); ret = -EUCLEAN; goto out; } /* * If we know the block isn't shared we can avoid * checking its backrefs. */ if (btrfs_block_can_be_shared(trans, root, eb)) upper->checked = 0; else upper->checked = 1; /* * Add the block to pending list if we need to check its * backrefs, we only do this once while walking up a * tree as we will catch anything else later on. */ if (!upper->checked && need_check) { need_check = false; list_add_tail(&edge->list[UPPER], &cache->pending_edge); } else { if (upper->checked) need_check = true; INIT_LIST_HEAD(&edge->list[UPPER]); } } else { upper = rb_entry(rb_node, struct btrfs_backref_node, rb_node); ASSERT(upper->checked); INIT_LIST_HEAD(&edge->list[UPPER]); if (!upper->owner) upper->owner = btrfs_header_owner(eb); } btrfs_backref_link_edge(edge, lower, upper, LINK_LOWER); if (rb_node) { btrfs_put_root(root); break; } lower = upper; upper = NULL; } out: btrfs_release_path(path); return ret; } /* * Add backref node @cur into @cache. * * NOTE: Even if the function returned 0, @cur is not yet cached as its upper * links aren't yet bi-directional. Needs to finish such links. * Use btrfs_backref_finish_upper_links() to finish such linkage. * * @trans: Transaction handle. * @path: Released path for indirect tree backref lookup * @iter: Released backref iter for extent tree search * @node_key: The first key of the tree block */ int btrfs_backref_add_tree_node(struct btrfs_trans_handle *trans, struct btrfs_backref_cache *cache, struct btrfs_path *path, struct btrfs_backref_iter *iter, struct btrfs_key *node_key, struct btrfs_backref_node *cur) { struct btrfs_backref_edge *edge; struct btrfs_backref_node *exist; int ret; ret = btrfs_backref_iter_start(iter, cur->bytenr); if (ret < 0) return ret; /* * We skip the first btrfs_tree_block_info, as we don't use the key * stored in it, but fetch it from the tree block */ if (btrfs_backref_has_tree_block_info(iter)) { ret = btrfs_backref_iter_next(iter); if (ret < 0) goto out; /* No extra backref? This means the tree block is corrupted */ if (ret > 0) { ret = -EUCLEAN; goto out; } } WARN_ON(cur->checked); if (!list_empty(&cur->upper)) { /* * The backref was added previously when processing backref of * type BTRFS_TREE_BLOCK_REF_KEY */ ASSERT(list_is_singular(&cur->upper)); edge = list_entry(cur->upper.next, struct btrfs_backref_edge, list[LOWER]); ASSERT(list_empty(&edge->list[UPPER])); exist = edge->node[UPPER]; /* * Add the upper level block to pending list if we need check * its backrefs */ if (!exist->checked) list_add_tail(&edge->list[UPPER], &cache->pending_edge); } else { exist = NULL; } for (; ret == 0; ret = btrfs_backref_iter_next(iter)) { struct extent_buffer *eb; struct btrfs_key key; int type; cond_resched(); eb = iter->path->nodes[0]; key.objectid = iter->bytenr; if (btrfs_backref_iter_is_inline_ref(iter)) { struct btrfs_extent_inline_ref *iref; /* Update key for inline backref */ iref = (struct btrfs_extent_inline_ref *) ((unsigned long)iter->cur_ptr); type = btrfs_get_extent_inline_ref_type(eb, iref, BTRFS_REF_TYPE_BLOCK); if (type == BTRFS_REF_TYPE_INVALID) { ret = -EUCLEAN; goto out; } key.type = type; key.offset = btrfs_extent_inline_ref_offset(eb, iref); } else { key.type = iter->cur_key.type; key.offset = iter->cur_key.offset; } /* * Parent node found and matches current inline ref, no need to * rebuild this node for this inline ref */ if (exist && ((key.type == BTRFS_TREE_BLOCK_REF_KEY && exist->owner == key.offset) || (key.type == BTRFS_SHARED_BLOCK_REF_KEY && exist->bytenr == key.offset))) { exist = NULL; continue; } /* SHARED_BLOCK_REF means key.offset is the parent bytenr */ if (key.type == BTRFS_SHARED_BLOCK_REF_KEY) { ret = handle_direct_tree_backref(cache, &key, cur); if (ret < 0) goto out; } else if (key.type == BTRFS_TREE_BLOCK_REF_KEY) { /* * key.type == BTRFS_TREE_BLOCK_REF_KEY, inline ref * offset means the root objectid. We need to search * the tree to get its parent bytenr. */ ret = handle_indirect_tree_backref(trans, cache, path, &key, node_key, cur); if (ret < 0) goto out; } /* * Unrecognized tree backref items (if it can pass tree-checker) * would be ignored. */ } ret = 0; cur->checked = 1; WARN_ON(exist); out: btrfs_backref_iter_release(iter); return ret; } /* * Finish the upwards linkage created by btrfs_backref_add_tree_node() */ int btrfs_backref_finish_upper_links(struct btrfs_backref_cache *cache, struct btrfs_backref_node *start) { struct list_head *useless_node = &cache->useless_node; struct btrfs_backref_edge *edge; struct rb_node *rb_node; LIST_HEAD(pending_edge); ASSERT(start->checked); rb_node = rb_simple_insert(&cache->rb_root, start->bytenr, &start->rb_node); if (rb_node) btrfs_backref_panic(cache->fs_info, start->bytenr, -EEXIST); /* * Use breadth first search to iterate all related edges. * * The starting points are all the edges of this node */ list_for_each_entry(edge, &start->upper, list[LOWER]) list_add_tail(&edge->list[UPPER], &pending_edge); while (!list_empty(&pending_edge)) { struct btrfs_backref_node *upper; struct btrfs_backref_node *lower; edge = list_first_entry(&pending_edge, struct btrfs_backref_edge, list[UPPER]); list_del_init(&edge->list[UPPER]); upper = edge->node[UPPER]; lower = edge->node[LOWER]; /* Parent is detached, no need to keep any edges */ if (upper->detached) { list_del(&edge->list[LOWER]); btrfs_backref_free_edge(cache, edge); /* Lower node is orphan, queue for cleanup */ if (list_empty(&lower->upper)) list_add(&lower->list, useless_node); continue; } /* * All new nodes added in current build_backref_tree() haven't * been linked to the cache rb tree. * So if we have upper->rb_node populated, this means a cache * hit. We only need to link the edge, as @upper and all its * parents have already been linked. */ if (!RB_EMPTY_NODE(&upper->rb_node)) { list_add_tail(&edge->list[UPPER], &upper->lower); continue; } /* Sanity check, we shouldn't have any unchecked nodes */ if (!upper->checked) { ASSERT(0); return -EUCLEAN; } rb_node = rb_simple_insert(&cache->rb_root, upper->bytenr, &upper->rb_node); if (unlikely(rb_node)) { btrfs_backref_panic(cache->fs_info, upper->bytenr, -EEXIST); return -EUCLEAN; } list_add_tail(&edge->list[UPPER], &upper->lower); /* * Also queue all the parent edges of this uncached node * to finish the upper linkage */ list_for_each_entry(edge, &upper->upper, list[LOWER]) list_add_tail(&edge->list[UPPER], &pending_edge); } return 0; } void btrfs_backref_error_cleanup(struct btrfs_backref_cache *cache, struct btrfs_backref_node *node) { struct btrfs_backref_node *lower; struct btrfs_backref_node *upper; struct btrfs_backref_edge *edge; while (!list_empty(&cache->useless_node)) { lower = list_first_entry(&cache->useless_node, struct btrfs_backref_node, list); list_del_init(&lower->list); } while (!list_empty(&cache->pending_edge)) { edge = list_first_entry(&cache->pending_edge, struct btrfs_backref_edge, list[UPPER]); list_del(&edge->list[UPPER]); list_del(&edge->list[LOWER]); lower = edge->node[LOWER]; upper = edge->node[UPPER]; btrfs_backref_free_edge(cache, edge); /* * Lower is no longer linked to any upper backref nodes and * isn't in the cache, we can free it ourselves. */ if (list_empty(&lower->upper) && RB_EMPTY_NODE(&lower->rb_node)) list_add(&lower->list, &cache->useless_node); if (!RB_EMPTY_NODE(&upper->rb_node)) continue; /* Add this guy's upper edges to the list to process */ list_for_each_entry(edge, &upper->upper, list[LOWER]) list_add_tail(&edge->list[UPPER], &cache->pending_edge); if (list_empty(&upper->upper)) list_add(&upper->list, &cache->useless_node); } while (!list_empty(&cache->useless_node)) { lower = list_first_entry(&cache->useless_node, struct btrfs_backref_node, list); list_del_init(&lower->list); if (lower == node) node = NULL; btrfs_backref_drop_node(cache, lower); } btrfs_backref_cleanup_node(cache, node); ASSERT(list_empty(&cache->useless_node) && list_empty(&cache->pending_edge)); } |
| 169 1136 1139 1136 73 1134 39 1111 1137 1136 10 10 10 10 242 12 229 230 231 164 166 165 167 166 167 167 166 296 299 299 300 243 167 300 31 242 243 154 182 154 154 154 153 39 39 149 148 148 149 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 | // SPDX-License-Identifier: GPL-2.0-only #define pr_fmt(fmt) "%s: " fmt, __func__ #include <linux/kernel.h> #include <linux/sched.h> #include <linux/wait.h> #include <linux/slab.h> #include <linux/mm.h> #include <linux/percpu-refcount.h> /* * Initially, a percpu refcount is just a set of percpu counters. Initially, we * don't try to detect the ref hitting 0 - which means that get/put can just * increment or decrement the local counter. Note that the counter on a * particular cpu can (and will) wrap - this is fine, when we go to shutdown the * percpu counters will all sum to the correct value * * (More precisely: because modular arithmetic is commutative the sum of all the * percpu_count vars will be equal to what it would have been if all the gets * and puts were done to a single integer, even if some of the percpu integers * overflow or underflow). * * The real trick to implementing percpu refcounts is shutdown. We can't detect * the ref hitting 0 on every put - this would require global synchronization * and defeat the whole purpose of using percpu refs. * * What we do is require the user to keep track of the initial refcount; we know * the ref can't hit 0 before the user drops the initial ref, so as long as we * convert to non percpu mode before the initial ref is dropped everything * works. * * Converting to non percpu mode is done with some RCUish stuff in * percpu_ref_kill. Additionally, we need a bias value so that the * atomic_long_t can't hit 0 before we've added up all the percpu refs. */ #define PERCPU_COUNT_BIAS (1LU << (BITS_PER_LONG - 1)) static DEFINE_SPINLOCK(percpu_ref_switch_lock); static DECLARE_WAIT_QUEUE_HEAD(percpu_ref_switch_waitq); static unsigned long __percpu *percpu_count_ptr(struct percpu_ref *ref) { return (unsigned long __percpu *) (ref->percpu_count_ptr & ~__PERCPU_REF_ATOMIC_DEAD); } /** * percpu_ref_init - initialize a percpu refcount * @ref: percpu_ref to initialize * @release: function which will be called when refcount hits 0 * @flags: PERCPU_REF_INIT_* flags * @gfp: allocation mask to use * * Initializes @ref. @ref starts out in percpu mode with a refcount of 1 unless * @flags contains PERCPU_REF_INIT_ATOMIC or PERCPU_REF_INIT_DEAD. These flags * change the start state to atomic with the latter setting the initial refcount * to 0. See the definitions of PERCPU_REF_INIT_* flags for flag behaviors. * * Note that @release must not sleep - it may potentially be called from RCU * callback context by percpu_ref_kill(). */ int percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release, unsigned int flags, gfp_t gfp) { size_t align = max_t(size_t, 1 << __PERCPU_REF_FLAG_BITS, __alignof__(unsigned long)); unsigned long start_count = 0; struct percpu_ref_data *data; ref->percpu_count_ptr = (unsigned long) __alloc_percpu_gfp(sizeof(unsigned long), align, gfp); if (!ref->percpu_count_ptr) return -ENOMEM; data = kzalloc(sizeof(*ref->data), gfp); if (!data) { free_percpu((void __percpu *)ref->percpu_count_ptr); ref->percpu_count_ptr = 0; return -ENOMEM; } data->force_atomic = flags & PERCPU_REF_INIT_ATOMIC; data->allow_reinit = flags & PERCPU_REF_ALLOW_REINIT; if (flags & (PERCPU_REF_INIT_ATOMIC | PERCPU_REF_INIT_DEAD)) { ref->percpu_count_ptr |= __PERCPU_REF_ATOMIC; data->allow_reinit = true; } else { start_count += PERCPU_COUNT_BIAS; } if (flags & PERCPU_REF_INIT_DEAD) ref->percpu_count_ptr |= __PERCPU_REF_DEAD; else start_count++; atomic_long_set(&data->count, start_count); data->release = release; data->confirm_switch = NULL; data->ref = ref; ref->data = data; return 0; } EXPORT_SYMBOL_GPL(percpu_ref_init); static void __percpu_ref_exit(struct percpu_ref *ref) { unsigned long __percpu *percpu_count = percpu_count_ptr(ref); if (percpu_count) { /* non-NULL confirm_switch indicates switching in progress */ WARN_ON_ONCE(ref->data && ref->data->confirm_switch); free_percpu(percpu_count); ref->percpu_count_ptr = __PERCPU_REF_ATOMIC_DEAD; } } /** * percpu_ref_exit - undo percpu_ref_init() * @ref: percpu_ref to exit * * This function exits @ref. The caller is responsible for ensuring that * @ref is no longer in active use. The usual places to invoke this * function from are the @ref->release() callback or in init failure path * where percpu_ref_init() succeeded but other parts of the initialization * of the embedding object failed. */ void percpu_ref_exit(struct percpu_ref *ref) { struct percpu_ref_data *data = ref->data; unsigned long flags; __percpu_ref_exit(ref); if (!data) return; spin_lock_irqsave(&percpu_ref_switch_lock, flags); ref->percpu_count_ptr |= atomic_long_read(&ref->data->count) << __PERCPU_REF_FLAG_BITS; ref->data = NULL; spin_unlock_irqrestore(&percpu_ref_switch_lock, flags); kfree(data); } EXPORT_SYMBOL_GPL(percpu_ref_exit); static void percpu_ref_call_confirm_rcu(struct rcu_head *rcu) { struct percpu_ref_data *data = container_of(rcu, struct percpu_ref_data, rcu); struct percpu_ref *ref = data->ref; data->confirm_switch(ref); data->confirm_switch = NULL; wake_up_all(&percpu_ref_switch_waitq); if (!data->allow_reinit) __percpu_ref_exit(ref); /* drop ref from percpu_ref_switch_to_atomic() */ percpu_ref_put(ref); } static void percpu_ref_switch_to_atomic_rcu(struct rcu_head *rcu) { struct percpu_ref_data *data = container_of(rcu, struct percpu_ref_data, rcu); struct percpu_ref *ref = data->ref; unsigned long __percpu *percpu_count = percpu_count_ptr(ref); static atomic_t underflows; unsigned long count = 0; int cpu; for_each_possible_cpu(cpu) count += *per_cpu_ptr(percpu_count, cpu); pr_debug("global %lu percpu %lu\n", atomic_long_read(&data->count), count); /* * It's crucial that we sum the percpu counters _before_ adding the sum * to &ref->count; since gets could be happening on one cpu while puts * happen on another, adding a single cpu's count could cause * @ref->count to hit 0 before we've got a consistent value - but the * sum of all the counts will be consistent and correct. * * Subtracting the bias value then has to happen _after_ adding count to * &ref->count; we need the bias value to prevent &ref->count from * reaching 0 before we add the percpu counts. But doing it at the same * time is equivalent and saves us atomic operations: */ atomic_long_add((long)count - PERCPU_COUNT_BIAS, &data->count); if (WARN_ONCE(atomic_long_read(&data->count) <= 0, "percpu ref (%ps) <= 0 (%ld) after switching to atomic", data->release, atomic_long_read(&data->count)) && atomic_inc_return(&underflows) < 4) { pr_err("%s(): percpu_ref underflow", __func__); mem_dump_obj(data); } /* @ref is viewed as dead on all CPUs, send out switch confirmation */ percpu_ref_call_confirm_rcu(rcu); } static void percpu_ref_noop_confirm_switch(struct percpu_ref *ref) { } static void __percpu_ref_switch_to_atomic(struct percpu_ref *ref, percpu_ref_func_t *confirm_switch) { if (ref->percpu_count_ptr & __PERCPU_REF_ATOMIC) { if (confirm_switch) confirm_switch(ref); return; } /* switching from percpu to atomic */ ref->percpu_count_ptr |= __PERCPU_REF_ATOMIC; /* * Non-NULL ->confirm_switch is used to indicate that switching is * in progress. Use noop one if unspecified. */ ref->data->confirm_switch = confirm_switch ?: percpu_ref_noop_confirm_switch; percpu_ref_get(ref); /* put after confirmation */ call_rcu_hurry(&ref->data->rcu, percpu_ref_switch_to_atomic_rcu); } static void __percpu_ref_switch_to_percpu(struct percpu_ref *ref) { unsigned long __percpu *percpu_count = percpu_count_ptr(ref); int cpu; BUG_ON(!percpu_count); if (!(ref->percpu_count_ptr & __PERCPU_REF_ATOMIC)) return; if (WARN_ON_ONCE(!ref->data->allow_reinit)) return; atomic_long_add(PERCPU_COUNT_BIAS, &ref->data->count); /* * Restore per-cpu operation. smp_store_release() is paired * with READ_ONCE() in __ref_is_percpu() and guarantees that the * zeroing is visible to all percpu accesses which can see the * following __PERCPU_REF_ATOMIC clearing. */ for_each_possible_cpu(cpu) *per_cpu_ptr(percpu_count, cpu) = 0; smp_store_release(&ref->percpu_count_ptr, ref->percpu_count_ptr & ~__PERCPU_REF_ATOMIC); } static void __percpu_ref_switch_mode(struct percpu_ref *ref, percpu_ref_func_t *confirm_switch) { struct percpu_ref_data *data = ref->data; lockdep_assert_held(&percpu_ref_switch_lock); /* * If the previous ATOMIC switching hasn't finished yet, wait for * its completion. If the caller ensures that ATOMIC switching * isn't in progress, this function can be called from any context. */ wait_event_lock_irq(percpu_ref_switch_waitq, !data->confirm_switch, percpu_ref_switch_lock); if (data->force_atomic || percpu_ref_is_dying(ref)) __percpu_ref_switch_to_atomic(ref, confirm_switch); else __percpu_ref_switch_to_percpu(ref); } /** * percpu_ref_switch_to_atomic - switch a percpu_ref to atomic mode * @ref: percpu_ref to switch to atomic mode * @confirm_switch: optional confirmation callback * * There's no reason to use this function for the usual reference counting. * Use percpu_ref_kill[_and_confirm](). * * Schedule switching of @ref to atomic mode. All its percpu counts will * be collected to the main atomic counter. On completion, when all CPUs * are guaraneed to be in atomic mode, @confirm_switch, which may not * block, is invoked. This function may be invoked concurrently with all * the get/put operations and can safely be mixed with kill and reinit * operations. Note that @ref will stay in atomic mode across kill/reinit * cycles until percpu_ref_switch_to_percpu() is called. * * This function may block if @ref is in the process of switching to atomic * mode. If the caller ensures that @ref is not in the process of * switching to atomic mode, this function can be called from any context. */ void percpu_ref_switch_to_atomic(struct percpu_ref *ref, percpu_ref_func_t *confirm_switch) { unsigned long flags; spin_lock_irqsave(&percpu_ref_switch_lock, flags); ref->data->force_atomic = true; __percpu_ref_switch_mode(ref, confirm_switch); spin_unlock_irqrestore(&percpu_ref_switch_lock, flags); } EXPORT_SYMBOL_GPL(percpu_ref_switch_to_atomic); /** * percpu_ref_switch_to_atomic_sync - switch a percpu_ref to atomic mode * @ref: percpu_ref to switch to atomic mode * * Schedule switching the ref to atomic mode, and wait for the * switch to complete. Caller must ensure that no other thread * will switch back to percpu mode. */ void percpu_ref_switch_to_atomic_sync(struct percpu_ref *ref) { percpu_ref_switch_to_atomic(ref, NULL); wait_event(percpu_ref_switch_waitq, !ref->data->confirm_switch); } EXPORT_SYMBOL_GPL(percpu_ref_switch_to_atomic_sync); /** * percpu_ref_switch_to_percpu - switch a percpu_ref to percpu mode * @ref: percpu_ref to switch to percpu mode * * There's no reason to use this function for the usual reference counting. * To re-use an expired ref, use percpu_ref_reinit(). * * Switch @ref to percpu mode. This function may be invoked concurrently * with all the get/put operations and can safely be mixed with kill and * reinit operations. This function reverses the sticky atomic state set * by PERCPU_REF_INIT_ATOMIC or percpu_ref_switch_to_atomic(). If @ref is * dying or dead, the actual switching takes place on the following * percpu_ref_reinit(). * * This function may block if @ref is in the process of switching to atomic * mode. If the caller ensures that @ref is not in the process of * switching to atomic mode, this function can be called from any context. */ void percpu_ref_switch_to_percpu(struct percpu_ref *ref) { unsigned long flags; spin_lock_irqsave(&percpu_ref_switch_lock, flags); ref->data->force_atomic = false; __percpu_ref_switch_mode(ref, NULL); spin_unlock_irqrestore(&percpu_ref_switch_lock, flags); } EXPORT_SYMBOL_GPL(percpu_ref_switch_to_percpu); /** * percpu_ref_kill_and_confirm - drop the initial ref and schedule confirmation * @ref: percpu_ref to kill * @confirm_kill: optional confirmation callback * * Equivalent to percpu_ref_kill() but also schedules kill confirmation if * @confirm_kill is not NULL. @confirm_kill, which may not block, will be * called after @ref is seen as dead from all CPUs at which point all * further invocations of percpu_ref_tryget_live() will fail. See * percpu_ref_tryget_live() for details. * * This function normally doesn't block and can be called from any context * but it may block if @confirm_kill is specified and @ref is in the * process of switching to atomic mode by percpu_ref_switch_to_atomic(). * * There are no implied RCU grace periods between kill and release. */ void percpu_ref_kill_and_confirm(struct percpu_ref *ref, percpu_ref_func_t *confirm_kill) { unsigned long flags; spin_lock_irqsave(&percpu_ref_switch_lock, flags); WARN_ONCE(percpu_ref_is_dying(ref), "%s called more than once on %ps!", __func__, ref->data->release); ref->percpu_count_ptr |= __PERCPU_REF_DEAD; __percpu_ref_switch_mode(ref, confirm_kill); percpu_ref_put(ref); spin_unlock_irqrestore(&percpu_ref_switch_lock, flags); } EXPORT_SYMBOL_GPL(percpu_ref_kill_and_confirm); /** * percpu_ref_is_zero - test whether a percpu refcount reached zero * @ref: percpu_ref to test * * Returns %true if @ref reached zero. * * This function is safe to call as long as @ref is between init and exit. */ bool percpu_ref_is_zero(struct percpu_ref *ref) { unsigned long __percpu *percpu_count; unsigned long count, flags; if (__ref_is_percpu(ref, &percpu_count)) return false; /* protect us from being destroyed */ spin_lock_irqsave(&percpu_ref_switch_lock, flags); if (ref->data) count = atomic_long_read(&ref->data->count); else count = ref->percpu_count_ptr >> __PERCPU_REF_FLAG_BITS; spin_unlock_irqrestore(&percpu_ref_switch_lock, flags); return count == 0; } EXPORT_SYMBOL_GPL(percpu_ref_is_zero); /** * percpu_ref_reinit - re-initialize a percpu refcount * @ref: perpcu_ref to re-initialize * * Re-initialize @ref so that it's in the same state as when it finished * percpu_ref_init() ignoring %PERCPU_REF_INIT_DEAD. @ref must have been * initialized successfully and reached 0 but not exited. * * Note that percpu_ref_tryget[_live]() are safe to perform on @ref while * this function is in progress. */ void percpu_ref_reinit(struct percpu_ref *ref) { WARN_ON_ONCE(!percpu_ref_is_zero(ref)); percpu_ref_resurrect(ref); } EXPORT_SYMBOL_GPL(percpu_ref_reinit); /** * percpu_ref_resurrect - modify a percpu refcount from dead to live * @ref: perpcu_ref to resurrect * * Modify @ref so that it's in the same state as before percpu_ref_kill() was * called. @ref must be dead but must not yet have exited. * * If @ref->release() frees @ref then the caller is responsible for * guaranteeing that @ref->release() does not get called while this * function is in progress. * * Note that percpu_ref_tryget[_live]() are safe to perform on @ref while * this function is in progress. */ void percpu_ref_resurrect(struct percpu_ref *ref) { unsigned long __percpu *percpu_count; unsigned long flags; spin_lock_irqsave(&percpu_ref_switch_lock, flags); WARN_ON_ONCE(!percpu_ref_is_dying(ref)); WARN_ON_ONCE(__ref_is_percpu(ref, &percpu_count)); ref->percpu_count_ptr &= ~__PERCPU_REF_DEAD; percpu_ref_get(ref); __percpu_ref_switch_mode(ref, NULL); spin_unlock_irqrestore(&percpu_ref_switch_lock, flags); } EXPORT_SYMBOL_GPL(percpu_ref_resurrect); |
| 2 2 1 1 1 1 2 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 | // SPDX-License-Identifier: GPL-2.0-or-later /* * * Digianswer Bluetooth USB driver * * Copyright (C) 2004-2007 Marcel Holtmann <marcel@holtmann.org> */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/sched.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/usb.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include "h4_recv.h" #define VERSION "0.11" static const struct usb_device_id bpa10x_table[] = { /* Tektronix BPA 100/105 (Digianswer) */ { USB_DEVICE(0x08fd, 0x0002) }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, bpa10x_table); struct bpa10x_data { struct hci_dev *hdev; struct usb_device *udev; struct usb_anchor tx_anchor; struct usb_anchor rx_anchor; struct sk_buff *rx_skb[2]; }; static void bpa10x_tx_complete(struct urb *urb) { struct sk_buff *skb = urb->context; struct hci_dev *hdev = (struct hci_dev *) skb->dev; BT_DBG("%s urb %p status %d count %d", hdev->name, urb, urb->status, urb->actual_length); if (!test_bit(HCI_RUNNING, &hdev->flags)) goto done; if (!urb->status) hdev->stat.byte_tx += urb->transfer_buffer_length; else hdev->stat.err_tx++; done: kfree(urb->setup_packet); kfree_skb(skb); } #define HCI_VENDOR_HDR_SIZE 5 #define HCI_RECV_VENDOR \ .type = HCI_VENDOR_PKT, \ .hlen = HCI_VENDOR_HDR_SIZE, \ .loff = 3, \ .lsize = 2, \ .maxlen = HCI_MAX_FRAME_SIZE static const struct h4_recv_pkt bpa10x_recv_pkts[] = { { H4_RECV_ACL, .recv = hci_recv_frame }, { H4_RECV_SCO, .recv = hci_recv_frame }, { H4_RECV_EVENT, .recv = hci_recv_frame }, { HCI_RECV_VENDOR, .recv = hci_recv_diag }, }; static void bpa10x_rx_complete(struct urb *urb) { struct hci_dev *hdev = urb->context; struct bpa10x_data *data = hci_get_drvdata(hdev); int err; BT_DBG("%s urb %p status %d count %d", hdev->name, urb, urb->status, urb->actual_length); if (!test_bit(HCI_RUNNING, &hdev->flags)) return; if (urb->status == 0) { bool idx = usb_pipebulk(urb->pipe); data->rx_skb[idx] = h4_recv_buf(hdev, data->rx_skb[idx], urb->transfer_buffer, urb->actual_length, bpa10x_recv_pkts, ARRAY_SIZE(bpa10x_recv_pkts)); if (IS_ERR(data->rx_skb[idx])) { bt_dev_err(hdev, "corrupted event packet"); hdev->stat.err_rx++; data->rx_skb[idx] = NULL; } } usb_anchor_urb(urb, &data->rx_anchor); err = usb_submit_urb(urb, GFP_ATOMIC); if (err < 0) { bt_dev_err(hdev, "urb %p failed to resubmit (%d)", urb, -err); usb_unanchor_urb(urb); } } static inline int bpa10x_submit_intr_urb(struct hci_dev *hdev) { struct bpa10x_data *data = hci_get_drvdata(hdev); struct urb *urb; unsigned char *buf; unsigned int pipe; int err, size = 16; BT_DBG("%s", hdev->name); urb = usb_alloc_urb(0, GFP_KERNEL); if (!urb) return -ENOMEM; buf = kmalloc(size, GFP_KERNEL); if (!buf) { usb_free_urb(urb); return -ENOMEM; } pipe = usb_rcvintpipe(data->udev, 0x81); usb_fill_int_urb(urb, data->udev, pipe, buf, size, bpa10x_rx_complete, hdev, 1); urb->transfer_flags |= URB_FREE_BUFFER; usb_anchor_urb(urb, &data->rx_anchor); err = usb_submit_urb(urb, GFP_KERNEL); if (err < 0) { bt_dev_err(hdev, "urb %p submission failed (%d)", urb, -err); usb_unanchor_urb(urb); } usb_free_urb(urb); return err; } static inline int bpa10x_submit_bulk_urb(struct hci_dev *hdev) { struct bpa10x_data *data = hci_get_drvdata(hdev); struct urb *urb; unsigned char *buf; unsigned int pipe; int err, size = 64; BT_DBG("%s", hdev->name); urb = usb_alloc_urb(0, GFP_KERNEL); if (!urb) return -ENOMEM; buf = kmalloc(size, GFP_KERNEL); if (!buf) { usb_free_urb(urb); return -ENOMEM; } pipe = usb_rcvbulkpipe(data->udev, 0x82); usb_fill_bulk_urb(urb, data->udev, pipe, buf, size, bpa10x_rx_complete, hdev); urb->transfer_flags |= URB_FREE_BUFFER; usb_anchor_urb(urb, &data->rx_anchor); err = usb_submit_urb(urb, GFP_KERNEL); if (err < 0) { bt_dev_err(hdev, "urb %p submission failed (%d)", urb, -err); usb_unanchor_urb(urb); } usb_free_urb(urb); return err; } static int bpa10x_open(struct hci_dev *hdev) { struct bpa10x_data *data = hci_get_drvdata(hdev); int err; BT_DBG("%s", hdev->name); err = bpa10x_submit_intr_urb(hdev); if (err < 0) goto error; err = bpa10x_submit_bulk_urb(hdev); if (err < 0) goto error; return 0; error: usb_kill_anchored_urbs(&data->rx_anchor); return err; } static int bpa10x_close(struct hci_dev *hdev) { struct bpa10x_data *data = hci_get_drvdata(hdev); BT_DBG("%s", hdev->name); usb_kill_anchored_urbs(&data->rx_anchor); return 0; } static int bpa10x_flush(struct hci_dev *hdev) { struct bpa10x_data *data = hci_get_drvdata(hdev); BT_DBG("%s", hdev->name); usb_kill_anchored_urbs(&data->tx_anchor); return 0; } static int bpa10x_setup(struct hci_dev *hdev) { static const u8 req[] = { 0x07 }; struct sk_buff *skb; BT_DBG("%s", hdev->name); /* Read revision string */ skb = __hci_cmd_sync(hdev, 0xfc0e, sizeof(req), req, HCI_INIT_TIMEOUT); if (IS_ERR(skb)) return PTR_ERR(skb); bt_dev_info(hdev, "%s", (char *)(skb->data + 1)); hci_set_fw_info(hdev, "%s", skb->data + 1); kfree_skb(skb); return 0; } static int bpa10x_send_frame(struct hci_dev *hdev, struct sk_buff *skb) { struct bpa10x_data *data = hci_get_drvdata(hdev); struct usb_ctrlrequest *dr; struct urb *urb; unsigned int pipe; int err; BT_DBG("%s", hdev->name); skb->dev = (void *) hdev; urb = usb_alloc_urb(0, GFP_KERNEL); if (!urb) return -ENOMEM; /* Prepend skb with frame type */ *(u8 *)skb_push(skb, 1) = hci_skb_pkt_type(skb); switch (hci_skb_pkt_type(skb)) { case HCI_COMMAND_PKT: dr = kmalloc(sizeof(*dr), GFP_KERNEL); if (!dr) { usb_free_urb(urb); return -ENOMEM; } dr->bRequestType = USB_TYPE_VENDOR; dr->bRequest = 0; dr->wIndex = 0; dr->wValue = 0; dr->wLength = __cpu_to_le16(skb->len); pipe = usb_sndctrlpipe(data->udev, 0x00); usb_fill_control_urb(urb, data->udev, pipe, (void *) dr, skb->data, skb->len, bpa10x_tx_complete, skb); hdev->stat.cmd_tx++; break; case HCI_ACLDATA_PKT: pipe = usb_sndbulkpipe(data->udev, 0x02); usb_fill_bulk_urb(urb, data->udev, pipe, skb->data, skb->len, bpa10x_tx_complete, skb); hdev->stat.acl_tx++; break; case HCI_SCODATA_PKT: pipe = usb_sndbulkpipe(data->udev, 0x02); usb_fill_bulk_urb(urb, data->udev, pipe, skb->data, skb->len, bpa10x_tx_complete, skb); hdev->stat.sco_tx++; break; default: usb_free_urb(urb); return -EILSEQ; } usb_anchor_urb(urb, &data->tx_anchor); err = usb_submit_urb(urb, GFP_KERNEL); if (err < 0) { bt_dev_err(hdev, "urb %p submission failed", urb); kfree(urb->setup_packet); usb_unanchor_urb(urb); } usb_free_urb(urb); return err; } static int bpa10x_set_diag(struct hci_dev *hdev, bool enable) { const u8 req[] = { 0x00, enable }; struct sk_buff *skb; BT_DBG("%s", hdev->name); if (!test_bit(HCI_RUNNING, &hdev->flags)) return -ENETDOWN; /* Enable sniffer operation */ skb = __hci_cmd_sync(hdev, 0xfc0e, sizeof(req), req, HCI_INIT_TIMEOUT); if (IS_ERR(skb)) return PTR_ERR(skb); kfree_skb(skb); return 0; } static int bpa10x_probe(struct usb_interface *intf, const struct usb_device_id *id) { struct bpa10x_data *data; struct hci_dev *hdev; int err; BT_DBG("intf %p id %p", intf, id); if (intf->cur_altsetting->desc.bInterfaceNumber != 0) return -ENODEV; data = devm_kzalloc(&intf->dev, sizeof(*data), GFP_KERNEL); if (!data) return -ENOMEM; data->udev = interface_to_usbdev(intf); init_usb_anchor(&data->tx_anchor); init_usb_anchor(&data->rx_anchor); hdev = hci_alloc_dev(); if (!hdev) return -ENOMEM; hdev->bus = HCI_USB; hci_set_drvdata(hdev, data); data->hdev = hdev; SET_HCIDEV_DEV(hdev, &intf->dev); hdev->open = bpa10x_open; hdev->close = bpa10x_close; hdev->flush = bpa10x_flush; hdev->setup = bpa10x_setup; hdev->send = bpa10x_send_frame; hdev->set_diag = bpa10x_set_diag; set_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks); err = hci_register_dev(hdev); if (err < 0) { hci_free_dev(hdev); return err; } usb_set_intfdata(intf, data); return 0; } static void bpa10x_disconnect(struct usb_interface *intf) { struct bpa10x_data *data = usb_get_intfdata(intf); BT_DBG("intf %p", intf); if (!data) return; usb_set_intfdata(intf, NULL); hci_unregister_dev(data->hdev); hci_free_dev(data->hdev); kfree_skb(data->rx_skb[0]); kfree_skb(data->rx_skb[1]); } static struct usb_driver bpa10x_driver = { .name = "bpa10x", .probe = bpa10x_probe, .disconnect = bpa10x_disconnect, .id_table = bpa10x_table, .disable_hub_initiated_lpm = 1, }; module_usb_driver(bpa10x_driver); MODULE_AUTHOR("Marcel Holtmann <marcel@holtmann.org>"); MODULE_DESCRIPTION("Digianswer Bluetooth USB driver ver " VERSION); MODULE_VERSION(VERSION); MODULE_LICENSE("GPL"); |
| 2 2 1 2 2 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 | // SPDX-License-Identifier: GPL-2.0-or-later /* * HID driver for Holtek gaming mice * Copyright (c) 2013 Christian Ohm * Heavily inspired by various other HID drivers that adjust the report * descriptor. */ /* */ #include <linux/hid.h> #include <linux/module.h> #include <linux/usb.h> #include "hid-ids.h" /* * The report descriptor of some Holtek based gaming mice specifies an * excessively large number of consumer usages (2^15), which is more than * HID_MAX_USAGES. This prevents proper parsing of the report descriptor. * * This driver fixes the report descriptor for: * - USB ID 04d9:a067, sold as Sharkoon Drakonia and Perixx MX-2000 * - USB ID 04d9:a04a, sold as Tracer Sniper TRM-503, NOVA Gaming Slider X200 * and Zalman ZM-GM1 * - USB ID 04d9:a081, sold as SHARKOON DarkGlider Gaming mouse * - USB ID 04d9:a072, sold as LEETGION Hellion Gaming Mouse * - USB ID 04d9:a0c2, sold as ETEKCITY Scroll T-140 Gaming Mouse */ static const __u8 *holtek_mouse_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { struct usb_interface *intf = to_usb_interface(hdev->dev.parent); if (intf->cur_altsetting->desc.bInterfaceNumber == 1) { /* Change usage maximum and logical maximum from 0x7fff to * 0x2fff, so they don't exceed HID_MAX_USAGES */ switch (hdev->product) { case USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A067: case USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A072: case USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A0C2: if (*rsize >= 122 && rdesc[115] == 0xff && rdesc[116] == 0x7f && rdesc[120] == 0xff && rdesc[121] == 0x7f) { hid_info(hdev, "Fixing up report descriptor\n"); rdesc[116] = rdesc[121] = 0x2f; } break; case USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A04A: case USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A070: case USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A081: if (*rsize >= 113 && rdesc[106] == 0xff && rdesc[107] == 0x7f && rdesc[111] == 0xff && rdesc[112] == 0x7f) { hid_info(hdev, "Fixing up report descriptor\n"); rdesc[107] = rdesc[112] = 0x2f; } break; } } return rdesc; } static int holtek_mouse_probe(struct hid_device *hdev, const struct hid_device_id *id) { int ret; if (!hid_is_usb(hdev)) return -EINVAL; ret = hid_parse(hdev); if (ret) { hid_err(hdev, "hid parse failed: %d\n", ret); return ret; } ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT); if (ret) { hid_err(hdev, "hw start failed: %d\n", ret); return ret; } return 0; } static const struct hid_device_id holtek_mouse_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT, USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A067) }, { HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT, USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A070) }, { HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT, USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A04A) }, { HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT, USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A072) }, { HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT, USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A081) }, { HID_USB_DEVICE(USB_VENDOR_ID_HOLTEK_ALT, USB_DEVICE_ID_HOLTEK_ALT_MOUSE_A0C2) }, { } }; MODULE_DEVICE_TABLE(hid, holtek_mouse_devices); static struct hid_driver holtek_mouse_driver = { .name = "holtek_mouse", .id_table = holtek_mouse_devices, .report_fixup = holtek_mouse_report_fixup, .probe = holtek_mouse_probe, }; module_hid_driver(holtek_mouse_driver); MODULE_DESCRIPTION("HID driver for Holtek gaming mice"); MODULE_LICENSE("GPL"); |
| 5 5 5 5 5 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 | // SPDX-License-Identifier: GPL-2.0-or-later /* * HID Driver for ELAN Touchpad * * Currently only supports touchpad found on HP Pavilion X2 10 * * Copyright (c) 2016 Alexandrov Stanislav <neko@nya.ai> */ #include <linux/hid.h> #include <linux/input/mt.h> #include <linux/leds.h> #include <linux/module.h> #include <linux/usb.h> #include "hid-ids.h" #define ELAN_MT_I2C 0x5d #define ELAN_SINGLE_FINGER 0x81 #define ELAN_MT_FIRST_FINGER 0x82 #define ELAN_MT_SECOND_FINGER 0x83 #define ELAN_INPUT_REPORT_SIZE 8 #define ELAN_I2C_REPORT_SIZE 32 #define ELAN_FINGER_DATA_LEN 5 #define ELAN_MAX_FINGERS 5 #define ELAN_MAX_PRESSURE 255 #define ELAN_TP_USB_INTF 1 #define ELAN_FEATURE_REPORT 0x0d #define ELAN_FEATURE_SIZE 5 #define ELAN_PARAM_MAX_X 6 #define ELAN_PARAM_MAX_Y 7 #define ELAN_PARAM_RES 8 #define ELAN_MUTE_LED_REPORT 0xBC #define ELAN_LED_REPORT_SIZE 8 #define ELAN_HAS_LED BIT(0) struct elan_drvdata { struct input_dev *input; u8 prev_report[ELAN_INPUT_REPORT_SIZE]; struct led_classdev mute_led; u8 mute_led_state; u16 max_x; u16 max_y; u16 res_x; u16 res_y; }; static int is_not_elan_touchpad(struct hid_device *hdev) { if (hid_is_usb(hdev)) { struct usb_interface *intf = to_usb_interface(hdev->dev.parent); return (intf->altsetting->desc.bInterfaceNumber != ELAN_TP_USB_INTF); } return 0; } static int elan_input_mapping(struct hid_device *hdev, struct hid_input *hi, struct hid_field *field, struct hid_usage *usage, unsigned long **bit, int *max) { if (is_not_elan_touchpad(hdev)) return 0; if (field->report->id == ELAN_SINGLE_FINGER || field->report->id == ELAN_MT_FIRST_FINGER || field->report->id == ELAN_MT_SECOND_FINGER || field->report->id == ELAN_MT_I2C) return -1; return 0; } static int elan_get_device_param(struct hid_device *hdev, unsigned char *dmabuf, unsigned char param) { int ret; dmabuf[0] = ELAN_FEATURE_REPORT; dmabuf[1] = 0x05; dmabuf[2] = 0x03; dmabuf[3] = param; dmabuf[4] = 0x01; ret = hid_hw_raw_request(hdev, ELAN_FEATURE_REPORT, dmabuf, ELAN_FEATURE_SIZE, HID_FEATURE_REPORT, HID_REQ_SET_REPORT); if (ret != ELAN_FEATURE_SIZE) { hid_err(hdev, "Set report error for parm %d: %d\n", param, ret); return ret; } ret = hid_hw_raw_request(hdev, ELAN_FEATURE_REPORT, dmabuf, ELAN_FEATURE_SIZE, HID_FEATURE_REPORT, HID_REQ_GET_REPORT); if (ret != ELAN_FEATURE_SIZE) { hid_err(hdev, "Get report error for parm %d: %d\n", param, ret); return ret; } return 0; } static unsigned int elan_convert_res(char val) { /* * (value from firmware) * 10 + 790 = dpi * dpi * 10 / 254 = dots/mm */ return (val * 10 + 790) * 10 / 254; } static int elan_get_device_params(struct hid_device *hdev) { struct elan_drvdata *drvdata = hid_get_drvdata(hdev); unsigned char *dmabuf; int ret; dmabuf = kmalloc(ELAN_FEATURE_SIZE, GFP_KERNEL); if (!dmabuf) return -ENOMEM; ret = elan_get_device_param(hdev, dmabuf, ELAN_PARAM_MAX_X); if (ret) goto err; drvdata->max_x = (dmabuf[4] << 8) | dmabuf[3]; ret = elan_get_device_param(hdev, dmabuf, ELAN_PARAM_MAX_Y); if (ret) goto err; drvdata->max_y = (dmabuf[4] << 8) | dmabuf[3]; ret = elan_get_device_param(hdev, dmabuf, ELAN_PARAM_RES); if (ret) goto err; drvdata->res_x = elan_convert_res(dmabuf[3]); drvdata->res_y = elan_convert_res(dmabuf[4]); err: kfree(dmabuf); return ret; } static int elan_input_configured(struct hid_device *hdev, struct hid_input *hi) { int ret; struct input_dev *input; struct elan_drvdata *drvdata = hid_get_drvdata(hdev); if (is_not_elan_touchpad(hdev)) return 0; ret = elan_get_device_params(hdev); if (ret) return ret; input = devm_input_allocate_device(&hdev->dev); if (!input) return -ENOMEM; input->name = "Elan Touchpad"; input->phys = hdev->phys; input->uniq = hdev->uniq; input->id.bustype = hdev->bus; input->id.vendor = hdev->vendor; input->id.product = hdev->product; input->id.version = hdev->version; input->dev.parent = &hdev->dev; input_set_abs_params(input, ABS_MT_POSITION_X, 0, drvdata->max_x, 0, 0); input_set_abs_params(input, ABS_MT_POSITION_Y, 0, drvdata->max_y, 0, 0); input_set_abs_params(input, ABS_MT_PRESSURE, 0, ELAN_MAX_PRESSURE, 0, 0); __set_bit(BTN_LEFT, input->keybit); __set_bit(INPUT_PROP_BUTTONPAD, input->propbit); ret = input_mt_init_slots(input, ELAN_MAX_FINGERS, INPUT_MT_POINTER); if (ret) { hid_err(hdev, "Failed to init elan MT slots: %d\n", ret); return ret; } input_abs_set_res(input, ABS_X, drvdata->res_x); input_abs_set_res(input, ABS_Y, drvdata->res_y); ret = input_register_device(input); if (ret) { hid_err(hdev, "Failed to register elan input device: %d\n", ret); input_mt_destroy_slots(input); return ret; } drvdata->input = input; return 0; } static void elan_report_mt_slot(struct elan_drvdata *drvdata, u8 *data, unsigned int slot_num) { struct input_dev *input = drvdata->input; int x, y, p; bool active = !!data; input_mt_slot(input, slot_num); input_mt_report_slot_state(input, MT_TOOL_FINGER, active); if (active) { x = ((data[0] & 0xF0) << 4) | data[1]; y = drvdata->max_y - (((data[0] & 0x07) << 8) | data[2]); p = data[4]; input_report_abs(input, ABS_MT_POSITION_X, x); input_report_abs(input, ABS_MT_POSITION_Y, y); input_report_abs(input, ABS_MT_PRESSURE, p); } } static void elan_usb_report_input(struct elan_drvdata *drvdata, u8 *data) { int i; struct input_dev *input = drvdata->input; /* * There is 3 types of reports: for single touch, * for multitouch - first finger and for multitouch - second finger * * packet structure for ELAN_SINGLE_FINGER and ELAN_MT_FIRST_FINGER: * * byte 1: 1 0 0 0 0 0 0 1 // 0x81 or 0x82 * byte 2: 0 0 0 0 0 0 0 0 // looks like unused * byte 3: f5 f4 f3 f2 f1 0 0 L * byte 4: x12 x11 x10 x9 0? y11 y10 y9 * byte 5: x8 x7 x6 x5 x4 x3 x2 x1 * byte 6: y8 y7 y6 y5 y4 y3 y2 y1 * byte 7: sy4 sy3 sy2 sy1 sx4 sx3 sx2 sx1 * byte 8: p8 p7 p6 p5 p4 p3 p2 p1 * * packet structure for ELAN_MT_SECOND_FINGER: * * byte 1: 1 0 0 0 0 0 1 1 // 0x83 * byte 2: x12 x11 x10 x9 0 y11 y10 y9 * byte 3: x8 x7 x6 x5 x4 x3 x2 x1 * byte 4: y8 y7 y6 y5 y4 y3 y2 y1 * byte 5: sy4 sy3 sy2 sy1 sx4 sx3 sx2 sx1 * byte 6: p8 p7 p6 p5 p4 p3 p2 p1 * byte 7: 0 0 0 0 0 0 0 0 * byte 8: 0 0 0 0 0 0 0 0 * * f5-f1: finger touch bits * L: clickpad button * sy / sx: finger width / height expressed in traces, the total number * of traces can be queried by doing a HID_REQ_SET_REPORT * { 0x0d, 0x05, 0x03, 0x05, 0x01 } followed by a GET, in the * returned buf, buf[3]=no-x-traces, buf[4]=no-y-traces. * p: pressure */ if (data[0] == ELAN_SINGLE_FINGER) { for (i = 0; i < ELAN_MAX_FINGERS; i++) { if (data[2] & BIT(i + 3)) elan_report_mt_slot(drvdata, data + 3, i); else elan_report_mt_slot(drvdata, NULL, i); } input_report_key(input, BTN_LEFT, data[2] & 0x01); } /* * When touched with two fingers Elan touchpad will emit two HID reports * first is ELAN_MT_FIRST_FINGER and second is ELAN_MT_SECOND_FINGER * we will save ELAN_MT_FIRST_FINGER report and wait for * ELAN_MT_SECOND_FINGER to finish multitouch */ if (data[0] == ELAN_MT_FIRST_FINGER) { memcpy(drvdata->prev_report, data, sizeof(drvdata->prev_report)); return; } if (data[0] == ELAN_MT_SECOND_FINGER) { int first = 0; u8 *prev_report = drvdata->prev_report; if (prev_report[0] != ELAN_MT_FIRST_FINGER) return; for (i = 0; i < ELAN_MAX_FINGERS; i++) { if (prev_report[2] & BIT(i + 3)) { if (!first) { first = 1; elan_report_mt_slot(drvdata, prev_report + 3, i); } else { elan_report_mt_slot(drvdata, data + 1, i); } } else { elan_report_mt_slot(drvdata, NULL, i); } } input_report_key(input, BTN_LEFT, prev_report[2] & 0x01); } input_mt_sync_frame(input); input_sync(input); } static void elan_i2c_report_input(struct elan_drvdata *drvdata, u8 *data) { struct input_dev *input = drvdata->input; u8 *finger_data; int i; /* * Elan MT touchpads in i2c mode send finger data in the same format * as in USB mode, but then with all fingers in a single packet. * * packet structure for ELAN_MT_I2C: * * byte 1: 1 0 0 1 1 1 0 1 // 0x5d * byte 2: f5 f4 f3 f2 f1 0 0 L * byte 3: x12 x11 x10 x9 0? y11 y10 y9 * byte 4: x8 x7 x6 x5 x4 x3 x2 x1 * byte 5: y8 y7 y6 y5 y4 y3 y2 y1 * byte 6: sy4 sy3 sy2 sy1 sx4 sx3 sx2 sx1 * byte 7: p8 p7 p6 p5 p4 p3 p2 p1 * byte 8-12: Same as byte 3-7 for second finger down * byte 13-17: Same as byte 3-7 for third finger down * byte 18-22: Same as byte 3-7 for fourth finger down * byte 23-27: Same as byte 3-7 for fifth finger down */ finger_data = data + 2; for (i = 0; i < ELAN_MAX_FINGERS; i++) { if (data[1] & BIT(i + 3)) { elan_report_mt_slot(drvdata, finger_data, i); finger_data += ELAN_FINGER_DATA_LEN; } else { elan_report_mt_slot(drvdata, NULL, i); } } input_report_key(input, BTN_LEFT, data[1] & 0x01); input_mt_sync_frame(input); input_sync(input); } static int elan_raw_event(struct hid_device *hdev, struct hid_report *report, u8 *data, int size) { struct elan_drvdata *drvdata = hid_get_drvdata(hdev); if (is_not_elan_touchpad(hdev)) return 0; if (data[0] == ELAN_SINGLE_FINGER || data[0] == ELAN_MT_FIRST_FINGER || data[0] == ELAN_MT_SECOND_FINGER) { if (size == ELAN_INPUT_REPORT_SIZE) { elan_usb_report_input(drvdata, data); return 1; } } if (data[0] == ELAN_MT_I2C && size == ELAN_I2C_REPORT_SIZE) { elan_i2c_report_input(drvdata, data); return 1; } return 0; } static int elan_start_multitouch(struct hid_device *hdev) { int ret; /* * This byte sequence will enable multitouch mode and disable * mouse emulation */ static const unsigned char buf[] = { 0x0D, 0x00, 0x03, 0x21, 0x00 }; unsigned char *dmabuf = kmemdup(buf, sizeof(buf), GFP_KERNEL); if (!dmabuf) return -ENOMEM; ret = hid_hw_raw_request(hdev, dmabuf[0], dmabuf, sizeof(buf), HID_FEATURE_REPORT, HID_REQ_SET_REPORT); kfree(dmabuf); if (ret != sizeof(buf)) { hid_err(hdev, "Failed to start multitouch: %d\n", ret); return ret; } return 0; } static int elan_mute_led_set_brigtness(struct led_classdev *led_cdev, enum led_brightness value) { int ret; u8 led_state; struct device *dev = led_cdev->dev->parent; struct hid_device *hdev = to_hid_device(dev); struct elan_drvdata *drvdata = hid_get_drvdata(hdev); unsigned char *dmabuf = kzalloc(ELAN_LED_REPORT_SIZE, GFP_KERNEL); if (!dmabuf) return -ENOMEM; led_state = !!value; dmabuf[0] = ELAN_MUTE_LED_REPORT; dmabuf[1] = 0x02; dmabuf[2] = led_state; ret = hid_hw_raw_request(hdev, dmabuf[0], dmabuf, ELAN_LED_REPORT_SIZE, HID_FEATURE_REPORT, HID_REQ_SET_REPORT); kfree(dmabuf); if (ret != ELAN_LED_REPORT_SIZE) { if (ret != -ENODEV) hid_err(hdev, "Failed to set mute led brightness: %d\n", ret); return ret < 0 ? ret : -EIO; } drvdata->mute_led_state = led_state; return 0; } static int elan_init_mute_led(struct hid_device *hdev) { struct elan_drvdata *drvdata = hid_get_drvdata(hdev); struct led_classdev *mute_led = &drvdata->mute_led; mute_led->name = "elan:red:mute"; mute_led->default_trigger = "audio-mute"; mute_led->brightness_set_blocking = elan_mute_led_set_brigtness; mute_led->max_brightness = LED_ON; mute_led->flags = LED_HW_PLUGGABLE; mute_led->dev = &hdev->dev; return devm_led_classdev_register(&hdev->dev, mute_led); } static int elan_probe(struct hid_device *hdev, const struct hid_device_id *id) { int ret; struct elan_drvdata *drvdata; drvdata = devm_kzalloc(&hdev->dev, sizeof(*drvdata), GFP_KERNEL); if (!drvdata) return -ENOMEM; hid_set_drvdata(hdev, drvdata); ret = hid_parse(hdev); if (ret) { hid_err(hdev, "Hid Parse failed\n"); return ret; } ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT); if (ret) { hid_err(hdev, "Hid hw start failed\n"); return ret; } if (is_not_elan_touchpad(hdev)) return 0; if (!drvdata->input) { hid_err(hdev, "Input device is not registered\n"); ret = -ENAVAIL; goto err; } ret = elan_start_multitouch(hdev); if (ret) goto err; if (id->driver_data & ELAN_HAS_LED) { ret = elan_init_mute_led(hdev); if (ret) goto err; } return 0; err: hid_hw_stop(hdev); return ret; } static const struct hid_device_id elan_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_ELAN, USB_DEVICE_ID_HP_X2), .driver_data = ELAN_HAS_LED }, { HID_USB_DEVICE(USB_VENDOR_ID_ELAN, USB_DEVICE_ID_HP_X2_10_COVER), .driver_data = ELAN_HAS_LED }, { HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, USB_DEVICE_ID_TOSHIBA_CLICK_L9W) }, { } }; MODULE_DEVICE_TABLE(hid, elan_devices); static struct hid_driver elan_driver = { .name = "elan", .id_table = elan_devices, .input_mapping = elan_input_mapping, .input_configured = elan_input_configured, .raw_event = elan_raw_event, .probe = elan_probe, }; module_hid_driver(elan_driver); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Alexandrov Stanislav"); MODULE_DESCRIPTION("Driver for HID ELAN Touchpads"); |
| 38 38 38 38 38 38 38 38 38 38 451 417 452 9 459 9 9 4 4 4 4 4 4 4 3 3 3 4 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/ipc/namespace.c * Copyright (C) 2006 Pavel Emelyanov <xemul@openvz.org> OpenVZ, SWsoft Inc. */ #include <linux/ipc.h> #include <linux/msg.h> #include <linux/ipc_namespace.h> #include <linux/rcupdate.h> #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/cred.h> #include <linux/fs.h> #include <linux/mount.h> #include <linux/user_namespace.h> #include <linux/proc_ns.h> #include <linux/sched/task.h> #include "util.h" /* * The work queue is used to avoid the cost of synchronize_rcu in kern_unmount. */ static void free_ipc(struct work_struct *unused); static DECLARE_WORK(free_ipc_work, free_ipc); static struct ucounts *inc_ipc_namespaces(struct user_namespace *ns) { return inc_ucount(ns, current_euid(), UCOUNT_IPC_NAMESPACES); } static void dec_ipc_namespaces(struct ucounts *ucounts) { dec_ucount(ucounts, UCOUNT_IPC_NAMESPACES); } static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns, struct ipc_namespace *old_ns) { struct ipc_namespace *ns; struct ucounts *ucounts; int err; err = -ENOSPC; again: ucounts = inc_ipc_namespaces(user_ns); if (!ucounts) { /* * IPC namespaces are freed asynchronously, by free_ipc_work. * If frees were pending, flush_work will wait, and * return true. Fail the allocation if no frees are pending. */ if (flush_work(&free_ipc_work)) goto again; goto fail; } err = -ENOMEM; ns = kzalloc(sizeof(struct ipc_namespace), GFP_KERNEL_ACCOUNT); if (ns == NULL) goto fail_dec; err = ns_alloc_inum(&ns->ns); if (err) goto fail_free; ns->ns.ops = &ipcns_operations; refcount_set(&ns->ns.count, 1); ns->user_ns = get_user_ns(user_ns); ns->ucounts = ucounts; err = mq_init_ns(ns); if (err) goto fail_put; err = -ENOMEM; if (!setup_mq_sysctls(ns)) goto fail_put; if (!setup_ipc_sysctls(ns)) goto fail_mq; err = msg_init_ns(ns); if (err) goto fail_ipc; sem_init_ns(ns); shm_init_ns(ns); return ns; fail_ipc: retire_ipc_sysctls(ns); fail_mq: retire_mq_sysctls(ns); fail_put: put_user_ns(ns->user_ns); ns_free_inum(&ns->ns); fail_free: kfree(ns); fail_dec: dec_ipc_namespaces(ucounts); fail: return ERR_PTR(err); } struct ipc_namespace *copy_ipcs(unsigned long flags, struct user_namespace *user_ns, struct ipc_namespace *ns) { if (!(flags & CLONE_NEWIPC)) return get_ipc_ns(ns); return create_ipc_ns(user_ns, ns); } /* * free_ipcs - free all ipcs of one type * @ns: the namespace to remove the ipcs from * @ids: the table of ipcs to free * @free: the function called to free each individual ipc * * Called for each kind of ipc when an ipc_namespace exits. */ void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids, void (*free)(struct ipc_namespace *, struct kern_ipc_perm *)) { struct kern_ipc_perm *perm; int next_id; int total, in_use; down_write(&ids->rwsem); in_use = ids->in_use; for (total = 0, next_id = 0; total < in_use; next_id++) { perm = idr_find(&ids->ipcs_idr, next_id); if (perm == NULL) continue; rcu_read_lock(); ipc_lock_object(perm); free(ns, perm); total++; } up_write(&ids->rwsem); } static void free_ipc_ns(struct ipc_namespace *ns) { /* * Caller needs to wait for an RCU grace period to have passed * after making the mount point inaccessible to new accesses. */ mntput(ns->mq_mnt); sem_exit_ns(ns); msg_exit_ns(ns); shm_exit_ns(ns); retire_mq_sysctls(ns); retire_ipc_sysctls(ns); dec_ipc_namespaces(ns->ucounts); put_user_ns(ns->user_ns); ns_free_inum(&ns->ns); kfree(ns); } static LLIST_HEAD(free_ipc_list); static void free_ipc(struct work_struct *unused) { struct llist_node *node = llist_del_all(&free_ipc_list); struct ipc_namespace *n, *t; llist_for_each_entry_safe(n, t, node, mnt_llist) mnt_make_shortterm(n->mq_mnt); /* Wait for any last users to have gone away. */ synchronize_rcu(); llist_for_each_entry_safe(n, t, node, mnt_llist) free_ipc_ns(n); } /* * put_ipc_ns - drop a reference to an ipc namespace. * @ns: the namespace to put * * If this is the last task in the namespace exiting, and * it is dropping the refcount to 0, then it can race with * a task in another ipc namespace but in a mounts namespace * which has this ipcns's mqueuefs mounted, doing some action * with one of the mqueuefs files. That can raise the refcount. * So dropping the refcount, and raising the refcount when * accessing it through the VFS, are protected with mq_lock. * * (Clearly, a task raising the refcount on its own ipc_ns * needn't take mq_lock since it can't race with the last task * in the ipcns exiting). */ void put_ipc_ns(struct ipc_namespace *ns) { if (refcount_dec_and_lock(&ns->ns.count, &mq_lock)) { mq_clear_sbinfo(ns); spin_unlock(&mq_lock); if (llist_add(&ns->mnt_llist, &free_ipc_list)) schedule_work(&free_ipc_work); } } static inline struct ipc_namespace *to_ipc_ns(struct ns_common *ns) { return container_of(ns, struct ipc_namespace, ns); } static struct ns_common *ipcns_get(struct task_struct *task) { struct ipc_namespace *ns = NULL; struct nsproxy *nsproxy; task_lock(task); nsproxy = task->nsproxy; if (nsproxy) ns = get_ipc_ns(nsproxy->ipc_ns); task_unlock(task); return ns ? &ns->ns : NULL; } static void ipcns_put(struct ns_common *ns) { return put_ipc_ns(to_ipc_ns(ns)); } static int ipcns_install(struct nsset *nsset, struct ns_common *new) { struct nsproxy *nsproxy = nsset->nsproxy; struct ipc_namespace *ns = to_ipc_ns(new); if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN) || !ns_capable(nsset->cred->user_ns, CAP_SYS_ADMIN)) return -EPERM; put_ipc_ns(nsproxy->ipc_ns); nsproxy->ipc_ns = get_ipc_ns(ns); return 0; } static struct user_namespace *ipcns_owner(struct ns_common *ns) { return to_ipc_ns(ns)->user_ns; } const struct proc_ns_operations ipcns_operations = { .name = "ipc", .type = CLONE_NEWIPC, .get = ipcns_get, .put = ipcns_put, .install = ipcns_install, .owner = ipcns_owner, }; |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Nano River Technologies viperboard IIO ADC driver * * (C) 2012 by Lemonage GmbH * Author: Lars Poeschel <poeschel@lemonage.de> * All rights reserved. */ #include <linux/kernel.h> #include <linux/errno.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/mutex.h> #include <linux/platform_device.h> #include <linux/usb.h> #include <linux/iio/iio.h> #include <linux/mfd/viperboard.h> #define VPRBRD_ADC_CMD_GET 0x00 struct vprbrd_adc_msg { u8 cmd; u8 chan; u8 val; } __packed; struct vprbrd_adc { struct vprbrd *vb; }; #define VPRBRD_ADC_CHANNEL(_index) { \ .type = IIO_VOLTAGE, \ .indexed = 1, \ .channel = _index, \ .info_mask_separate = BIT(IIO_CHAN_INFO_RAW), \ } static struct iio_chan_spec const vprbrd_adc_iio_channels[] = { VPRBRD_ADC_CHANNEL(0), VPRBRD_ADC_CHANNEL(1), VPRBRD_ADC_CHANNEL(2), VPRBRD_ADC_CHANNEL(3), }; static int vprbrd_iio_read_raw(struct iio_dev *iio_dev, struct iio_chan_spec const *chan, int *val, int *val2, long info) { int ret, error = 0; struct vprbrd_adc *adc = iio_priv(iio_dev); struct vprbrd *vb = adc->vb; struct vprbrd_adc_msg *admsg = (struct vprbrd_adc_msg *)vb->buf; switch (info) { case IIO_CHAN_INFO_RAW: mutex_lock(&vb->lock); admsg->cmd = VPRBRD_ADC_CMD_GET; admsg->chan = chan->channel; admsg->val = 0x00; ret = usb_control_msg(vb->usb_dev, usb_sndctrlpipe(vb->usb_dev, 0), VPRBRD_USB_REQUEST_ADC, VPRBRD_USB_TYPE_OUT, 0x0000, 0x0000, admsg, sizeof(struct vprbrd_adc_msg), VPRBRD_USB_TIMEOUT_MS); if (ret != sizeof(struct vprbrd_adc_msg)) { dev_err(&iio_dev->dev, "usb send error on adc read\n"); error = -EREMOTEIO; } ret = usb_control_msg(vb->usb_dev, usb_rcvctrlpipe(vb->usb_dev, 0), VPRBRD_USB_REQUEST_ADC, VPRBRD_USB_TYPE_IN, 0x0000, 0x0000, admsg, sizeof(struct vprbrd_adc_msg), VPRBRD_USB_TIMEOUT_MS); *val = admsg->val; mutex_unlock(&vb->lock); if (ret != sizeof(struct vprbrd_adc_msg)) { dev_err(&iio_dev->dev, "usb recv error on adc read\n"); error = -EREMOTEIO; } if (error) goto error; return IIO_VAL_INT; default: error = -EINVAL; break; } error: return error; } static const struct iio_info vprbrd_adc_iio_info = { .read_raw = &vprbrd_iio_read_raw, }; static int vprbrd_adc_probe(struct platform_device *pdev) { struct vprbrd *vb = dev_get_drvdata(pdev->dev.parent); struct vprbrd_adc *adc; struct iio_dev *indio_dev; int ret; /* registering iio */ indio_dev = devm_iio_device_alloc(&pdev->dev, sizeof(*adc)); if (!indio_dev) { dev_err(&pdev->dev, "failed allocating iio device\n"); return -ENOMEM; } adc = iio_priv(indio_dev); adc->vb = vb; indio_dev->name = "viperboard adc"; indio_dev->info = &vprbrd_adc_iio_info; indio_dev->modes = INDIO_DIRECT_MODE; indio_dev->channels = vprbrd_adc_iio_channels; indio_dev->num_channels = ARRAY_SIZE(vprbrd_adc_iio_channels); ret = devm_iio_device_register(&pdev->dev, indio_dev); if (ret) { dev_err(&pdev->dev, "could not register iio (adc)"); return ret; } return 0; } static struct platform_driver vprbrd_adc_driver = { .driver = { .name = "viperboard-adc", }, .probe = vprbrd_adc_probe, }; module_platform_driver(vprbrd_adc_driver); MODULE_AUTHOR("Lars Poeschel <poeschel@lemonage.de>"); MODULE_DESCRIPTION("IIO ADC driver for Nano River Techs Viperboard"); MODULE_LICENSE("GPL"); MODULE_ALIAS("platform:viperboard-adc"); |
| 3 2 1 3 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2013 Patrick McHardy <kaber@trash.net> */ #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_SYNPROXY.h> #include <net/netfilter/nf_synproxy.h> static unsigned int synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_synproxy_info *info = par->targinfo; struct net *net = xt_net(par); struct synproxy_net *snet = synproxy_pernet(net); struct synproxy_options opts = {}; struct tcphdr *th, _th; if (nf_ip_checksum(skb, xt_hooknum(par), par->thoff, IPPROTO_TCP)) return NF_DROP; th = skb_header_pointer(skb, par->thoff, sizeof(_th), &_th); if (th == NULL) return NF_DROP; if (!synproxy_parse_options(skb, par->thoff, th, &opts)) return NF_DROP; if (th->syn && !(th->ack || th->fin || th->rst)) { /* Initial SYN from client */ this_cpu_inc(snet->stats->syn_received); if (th->ece && th->cwr) opts.options |= XT_SYNPROXY_OPT_ECN; opts.options &= info->options; opts.mss_encode = opts.mss_option; opts.mss_option = info->mss; if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) synproxy_init_timestamp_cookie(info, &opts); else opts.options &= ~(XT_SYNPROXY_OPT_WSCALE | XT_SYNPROXY_OPT_SACK_PERM | XT_SYNPROXY_OPT_ECN); synproxy_send_client_synack(net, skb, th, &opts); consume_skb(skb); return NF_STOLEN; } else if (th->ack && !(th->fin || th->rst || th->syn)) { /* ACK from client */ if (synproxy_recv_client_ack(net, skb, th, &opts, ntohl(th->seq))) { consume_skb(skb); return NF_STOLEN; } else { return NF_DROP; } } return XT_CONTINUE; } static int synproxy_tg4_check(const struct xt_tgchk_param *par) { struct synproxy_net *snet = synproxy_pernet(par->net); const struct ipt_entry *e = par->entryinfo; int err; if (e->ip.proto != IPPROTO_TCP || e->ip.invflags & XT_INV_PROTO) return -EINVAL; err = nf_ct_netns_get(par->net, par->family); if (err) return err; err = nf_synproxy_ipv4_init(snet, par->net); if (err) { nf_ct_netns_put(par->net, par->family); return err; } return err; } static void synproxy_tg4_destroy(const struct xt_tgdtor_param *par) { struct synproxy_net *snet = synproxy_pernet(par->net); nf_synproxy_ipv4_fini(snet, par->net); nf_ct_netns_put(par->net, par->family); } static struct xt_target synproxy_tg4_reg __read_mostly = { .name = "SYNPROXY", .family = NFPROTO_IPV4, .hooks = (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD), .target = synproxy_tg4, .targetsize = sizeof(struct xt_synproxy_info), .checkentry = synproxy_tg4_check, .destroy = synproxy_tg4_destroy, .me = THIS_MODULE, }; static int __init synproxy_tg4_init(void) { return xt_register_target(&synproxy_tg4_reg); } static void __exit synproxy_tg4_exit(void) { xt_unregister_target(&synproxy_tg4_reg); } module_init(synproxy_tg4_init); module_exit(synproxy_tg4_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_DESCRIPTION("Intercept TCP connections and establish them using syncookies"); |
| 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef BTRFS_DEFRAG_H #define BTRFS_DEFRAG_H #include <linux/types.h> #include <linux/compiler_types.h> struct inode; struct file_ra_state; struct btrfs_fs_info; struct btrfs_root; struct btrfs_trans_handle; struct btrfs_ioctl_defrag_range_args; int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra, struct btrfs_ioctl_defrag_range_args *range, u64 newer_than, unsigned long max_to_defrag); int __init btrfs_auto_defrag_init(void); void __cold btrfs_auto_defrag_exit(void); void btrfs_add_inode_defrag(struct btrfs_inode *inode, u32 extent_thresh); int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info); void btrfs_cleanup_defrag_inodes(struct btrfs_fs_info *fs_info); int btrfs_defrag_root(struct btrfs_root *root); static inline int btrfs_defrag_cancelled(struct btrfs_fs_info *fs_info) { return signal_pending(current); } #endif |
| 163 163 164 6 6 6 6 6 6 7 6 6 6 7 6 6 5 5 6 5 14 14 14 6 6 6 6 6 6 13 11 11 13 11 13 180 181 182 180 182 181 164 164 163 164 164 164 164 180 181 181 180 181 181 180 180 180 11 11 10 10 10 10 10 10 10 10 11 10 2 10 7 7 7 7 6 10 9 10 10 8 10 182 182 182 182 181 167 167 181 181 181 181 180 164 165 25 165 165 165 165 165 181 181 182 182 182 182 163 164 164 181 182 182 182 164 182 161 182 181 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Information interface for ALSA driver * Copyright (c) by Jaroslav Kysela <perex@perex.cz> */ #include <linux/init.h> #include <linux/time.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/module.h> #include <sound/core.h> #include <sound/minors.h> #include <sound/info.h> #include <linux/utsname.h> #include <linux/proc_fs.h> #include <linux/mutex.h> int snd_info_check_reserved_words(const char *str) { static const char * const reserved[] = { "version", "meminfo", "memdebug", "detect", "devices", "oss", "cards", "timers", "synth", "pcm", "seq", NULL }; const char * const *xstr = reserved; while (*xstr) { if (!strcmp(*xstr, str)) return 0; xstr++; } if (!strncmp(str, "card", 4)) return 0; return 1; } static DEFINE_MUTEX(info_mutex); struct snd_info_private_data { struct snd_info_buffer *rbuffer; struct snd_info_buffer *wbuffer; struct snd_info_entry *entry; void *file_private_data; }; static int snd_info_version_init(void); static void snd_info_clear_entries(struct snd_info_entry *entry); /* */ static struct snd_info_entry *snd_proc_root; struct snd_info_entry *snd_seq_root; EXPORT_SYMBOL(snd_seq_root); #ifdef CONFIG_SND_OSSEMUL struct snd_info_entry *snd_oss_root; #endif static int alloc_info_private(struct snd_info_entry *entry, struct snd_info_private_data **ret) { struct snd_info_private_data *data; if (!entry || !entry->p) return -ENODEV; if (!try_module_get(entry->module)) return -EFAULT; data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) { module_put(entry->module); return -ENOMEM; } data->entry = entry; *ret = data; return 0; } static bool valid_pos(loff_t pos, size_t count) { if (pos < 0 || (long) pos != pos || (ssize_t) count < 0) return false; if ((unsigned long) pos + (unsigned long) count < (unsigned long) pos) return false; return true; } /* * file ops for binary proc files */ static loff_t snd_info_entry_llseek(struct file *file, loff_t offset, int orig) { struct snd_info_private_data *data; struct snd_info_entry *entry; loff_t size; data = file->private_data; entry = data->entry; guard(mutex)(&entry->access); if (entry->c.ops->llseek) return entry->c.ops->llseek(entry, data->file_private_data, file, offset, orig); size = entry->size; switch (orig) { case SEEK_SET: break; case SEEK_CUR: offset += file->f_pos; break; case SEEK_END: if (!size) return -EINVAL; offset += size; break; default: return -EINVAL; } if (offset < 0) return -EINVAL; if (size && offset > size) offset = size; file->f_pos = offset; return offset; } static ssize_t snd_info_entry_read(struct file *file, char __user *buffer, size_t count, loff_t * offset) { struct snd_info_private_data *data = file->private_data; struct snd_info_entry *entry = data->entry; size_t size; loff_t pos; pos = *offset; if (!valid_pos(pos, count)) return -EIO; if (pos >= entry->size) return 0; size = entry->size - pos; size = min(count, size); size = entry->c.ops->read(entry, data->file_private_data, file, buffer, size, pos); if ((ssize_t) size > 0) *offset = pos + size; return size; } static ssize_t snd_info_entry_write(struct file *file, const char __user *buffer, size_t count, loff_t * offset) { struct snd_info_private_data *data = file->private_data; struct snd_info_entry *entry = data->entry; ssize_t size = 0; loff_t pos; pos = *offset; if (!valid_pos(pos, count)) return -EIO; if (count > 0) { size_t maxsize = entry->size - pos; count = min(count, maxsize); size = entry->c.ops->write(entry, data->file_private_data, file, buffer, count, pos); } if (size > 0) *offset = pos + size; return size; } static __poll_t snd_info_entry_poll(struct file *file, poll_table *wait) { struct snd_info_private_data *data = file->private_data; struct snd_info_entry *entry = data->entry; __poll_t mask = 0; if (entry->c.ops->poll) return entry->c.ops->poll(entry, data->file_private_data, file, wait); if (entry->c.ops->read) mask |= EPOLLIN | EPOLLRDNORM; if (entry->c.ops->write) mask |= EPOLLOUT | EPOLLWRNORM; return mask; } static long snd_info_entry_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct snd_info_private_data *data = file->private_data; struct snd_info_entry *entry = data->entry; if (!entry->c.ops->ioctl) return -ENOTTY; return entry->c.ops->ioctl(entry, data->file_private_data, file, cmd, arg); } static int snd_info_entry_mmap(struct file *file, struct vm_area_struct *vma) { struct inode *inode = file_inode(file); struct snd_info_private_data *data; struct snd_info_entry *entry; data = file->private_data; if (data == NULL) return 0; entry = data->entry; if (!entry->c.ops->mmap) return -ENXIO; return entry->c.ops->mmap(entry, data->file_private_data, inode, file, vma); } static int snd_info_entry_open(struct inode *inode, struct file *file) { struct snd_info_entry *entry = pde_data(inode); struct snd_info_private_data *data; int mode, err; guard(mutex)(&info_mutex); err = alloc_info_private(entry, &data); if (err < 0) return err; mode = file->f_flags & O_ACCMODE; if (((mode == O_RDONLY || mode == O_RDWR) && !entry->c.ops->read) || ((mode == O_WRONLY || mode == O_RDWR) && !entry->c.ops->write)) { err = -ENODEV; goto error; } if (entry->c.ops->open) { err = entry->c.ops->open(entry, mode, &data->file_private_data); if (err < 0) goto error; } file->private_data = data; return 0; error: kfree(data); module_put(entry->module); return err; } static int snd_info_entry_release(struct inode *inode, struct file *file) { struct snd_info_private_data *data = file->private_data; struct snd_info_entry *entry = data->entry; if (entry->c.ops->release) entry->c.ops->release(entry, file->f_flags & O_ACCMODE, data->file_private_data); module_put(entry->module); kfree(data); return 0; } static const struct proc_ops snd_info_entry_operations = { .proc_lseek = snd_info_entry_llseek, .proc_read = snd_info_entry_read, .proc_write = snd_info_entry_write, .proc_poll = snd_info_entry_poll, .proc_ioctl = snd_info_entry_ioctl, .proc_mmap = snd_info_entry_mmap, .proc_open = snd_info_entry_open, .proc_release = snd_info_entry_release, }; /* * file ops for text proc files */ static ssize_t snd_info_text_entry_write(struct file *file, const char __user *buffer, size_t count, loff_t *offset) { struct seq_file *m = file->private_data; struct snd_info_private_data *data = m->private; struct snd_info_entry *entry = data->entry; struct snd_info_buffer *buf; loff_t pos; size_t next; if (!entry->c.text.write) return -EIO; pos = *offset; if (!valid_pos(pos, count)) return -EIO; next = pos + count; /* don't handle too large text inputs */ if (next > 16 * 1024) return -EIO; guard(mutex)(&entry->access); buf = data->wbuffer; if (!buf) { data->wbuffer = buf = kzalloc(sizeof(*buf), GFP_KERNEL); if (!buf) return -ENOMEM; } if (next > buf->len) { char *nbuf = kvzalloc(PAGE_ALIGN(next), GFP_KERNEL); if (!nbuf) return -ENOMEM; kvfree(buf->buffer); buf->buffer = nbuf; buf->len = PAGE_ALIGN(next); } if (copy_from_user(buf->buffer + pos, buffer, count)) return -EFAULT; buf->size = next; *offset = next; return count; } static int snd_info_seq_show(struct seq_file *seq, void *p) { struct snd_info_private_data *data = seq->private; struct snd_info_entry *entry = data->entry; if (!entry->c.text.read) { return -EIO; } else { data->rbuffer->buffer = (char *)seq; /* XXX hack! */ entry->c.text.read(entry, data->rbuffer); } return 0; } static int snd_info_text_entry_open(struct inode *inode, struct file *file) { struct snd_info_entry *entry = pde_data(inode); struct snd_info_private_data *data; int err; guard(mutex)(&info_mutex); err = alloc_info_private(entry, &data); if (err < 0) return err; data->rbuffer = kzalloc(sizeof(*data->rbuffer), GFP_KERNEL); if (!data->rbuffer) { err = -ENOMEM; goto error; } if (entry->size) err = single_open_size(file, snd_info_seq_show, data, entry->size); else err = single_open(file, snd_info_seq_show, data); if (err < 0) goto error; return 0; error: kfree(data->rbuffer); kfree(data); module_put(entry->module); return err; } static int snd_info_text_entry_release(struct inode *inode, struct file *file) { struct seq_file *m = file->private_data; struct snd_info_private_data *data = m->private; struct snd_info_entry *entry = data->entry; if (data->wbuffer && entry->c.text.write) entry->c.text.write(entry, data->wbuffer); single_release(inode, file); kfree(data->rbuffer); if (data->wbuffer) { kvfree(data->wbuffer->buffer); kfree(data->wbuffer); } module_put(entry->module); kfree(data); return 0; } static const struct proc_ops snd_info_text_entry_ops = { .proc_open = snd_info_text_entry_open, .proc_release = snd_info_text_entry_release, .proc_write = snd_info_text_entry_write, .proc_lseek = seq_lseek, .proc_read = seq_read, }; static struct snd_info_entry *create_subdir(struct module *mod, const char *name) { struct snd_info_entry *entry; entry = snd_info_create_module_entry(mod, name, NULL); if (!entry) return NULL; entry->mode = S_IFDIR | 0555; if (snd_info_register(entry) < 0) { snd_info_free_entry(entry); return NULL; } return entry; } static struct snd_info_entry * snd_info_create_entry(const char *name, struct snd_info_entry *parent, struct module *module); int __init snd_info_init(void) { snd_proc_root = snd_info_create_entry("asound", NULL, THIS_MODULE); if (!snd_proc_root) return -ENOMEM; snd_proc_root->mode = S_IFDIR | 0555; snd_proc_root->p = proc_mkdir("asound", NULL); if (!snd_proc_root->p) goto error; #ifdef CONFIG_SND_OSSEMUL snd_oss_root = create_subdir(THIS_MODULE, "oss"); if (!snd_oss_root) goto error; #endif #if IS_ENABLED(CONFIG_SND_SEQUENCER) snd_seq_root = create_subdir(THIS_MODULE, "seq"); if (!snd_seq_root) goto error; #endif if (snd_info_version_init() < 0 || snd_minor_info_init() < 0 || snd_minor_info_oss_init() < 0 || snd_card_info_init() < 0 || snd_info_minor_register() < 0) goto error; return 0; error: snd_info_free_entry(snd_proc_root); return -ENOMEM; } int __exit snd_info_done(void) { snd_info_free_entry(snd_proc_root); return 0; } static void snd_card_id_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { struct snd_card *card = entry->private_data; snd_iprintf(buffer, "%s\n", card->id); } /* * create a card proc file * called from init.c */ int snd_info_card_create(struct snd_card *card) { char str[8]; struct snd_info_entry *entry; if (snd_BUG_ON(!card)) return -ENXIO; sprintf(str, "card%i", card->number); entry = create_subdir(card->module, str); if (!entry) return -ENOMEM; card->proc_root = entry; return snd_card_ro_proc_new(card, "id", card, snd_card_id_read); } /* * register the card proc file * called from init.c * can be called multiple times for reinitialization */ int snd_info_card_register(struct snd_card *card) { struct proc_dir_entry *p; int err; if (snd_BUG_ON(!card)) return -ENXIO; err = snd_info_register(card->proc_root); if (err < 0) return err; if (!strcmp(card->id, card->proc_root->name)) return 0; if (card->proc_root_link) return 0; p = proc_symlink(card->id, snd_proc_root->p, card->proc_root->name); if (!p) return -ENOMEM; card->proc_root_link = p; return 0; } /* * called on card->id change */ void snd_info_card_id_change(struct snd_card *card) { guard(mutex)(&info_mutex); if (card->proc_root_link) { proc_remove(card->proc_root_link); card->proc_root_link = NULL; } if (strcmp(card->id, card->proc_root->name)) card->proc_root_link = proc_symlink(card->id, snd_proc_root->p, card->proc_root->name); } /* * de-register the card proc file * called from init.c */ void snd_info_card_disconnect(struct snd_card *card) { if (!card) return; proc_remove(card->proc_root_link); if (card->proc_root) proc_remove(card->proc_root->p); guard(mutex)(&info_mutex); if (card->proc_root) snd_info_clear_entries(card->proc_root); card->proc_root_link = NULL; card->proc_root = NULL; } /* * release the card proc file resources * called from init.c */ int snd_info_card_free(struct snd_card *card) { if (!card) return 0; snd_info_free_entry(card->proc_root); card->proc_root = NULL; return 0; } /** * snd_info_get_line - read one line from the procfs buffer * @buffer: the procfs buffer * @line: the buffer to store * @len: the max. buffer size * * Reads one line from the buffer and stores the string. * * Return: Zero if successful, or 1 if error or EOF. */ int snd_info_get_line(struct snd_info_buffer *buffer, char *line, int len) { int c; if (snd_BUG_ON(!buffer)) return 1; if (!buffer->buffer) return 1; if (len <= 0 || buffer->stop || buffer->error) return 1; while (!buffer->stop) { c = buffer->buffer[buffer->curr++]; if (buffer->curr >= buffer->size) buffer->stop = 1; if (c == '\n') break; if (len > 1) { len--; *line++ = c; } } *line = '\0'; return 0; } EXPORT_SYMBOL(snd_info_get_line); /** * snd_info_get_str - parse a string token * @dest: the buffer to store the string token * @src: the original string * @len: the max. length of token - 1 * * Parses the original string and copy a token to the given * string buffer. * * Return: The updated pointer of the original string so that * it can be used for the next call. */ const char *snd_info_get_str(char *dest, const char *src, int len) { int c; while (*src == ' ' || *src == '\t') src++; if (*src == '"' || *src == '\'') { c = *src++; while (--len > 0 && *src && *src != c) { *dest++ = *src++; } if (*src == c) src++; } else { while (--len > 0 && *src && *src != ' ' && *src != '\t') { *dest++ = *src++; } } *dest = 0; while (*src == ' ' || *src == '\t') src++; return src; } EXPORT_SYMBOL(snd_info_get_str); /* * snd_info_create_entry - create an info entry * @name: the proc file name * @parent: the parent directory * * Creates an info entry with the given file name and initializes as * the default state. * * Usually called from other functions such as * snd_info_create_card_entry(). * * Return: The pointer of the new instance, or %NULL on failure. */ static struct snd_info_entry * snd_info_create_entry(const char *name, struct snd_info_entry *parent, struct module *module) { struct snd_info_entry *entry; entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (entry == NULL) return NULL; entry->name = kstrdup(name, GFP_KERNEL); if (entry->name == NULL) { kfree(entry); return NULL; } entry->mode = S_IFREG | 0444; entry->content = SNDRV_INFO_CONTENT_TEXT; mutex_init(&entry->access); INIT_LIST_HEAD(&entry->children); INIT_LIST_HEAD(&entry->list); entry->parent = parent; entry->module = module; if (parent) { guard(mutex)(&parent->access); list_add_tail(&entry->list, &parent->children); } return entry; } /** * snd_info_create_module_entry - create an info entry for the given module * @module: the module pointer * @name: the file name * @parent: the parent directory * * Creates a new info entry and assigns it to the given module. * * Return: The pointer of the new instance, or %NULL on failure. */ struct snd_info_entry *snd_info_create_module_entry(struct module * module, const char *name, struct snd_info_entry *parent) { if (!parent) parent = snd_proc_root; return snd_info_create_entry(name, parent, module); } EXPORT_SYMBOL(snd_info_create_module_entry); /** * snd_info_create_card_entry - create an info entry for the given card * @card: the card instance * @name: the file name * @parent: the parent directory * * Creates a new info entry and assigns it to the given card. * * Return: The pointer of the new instance, or %NULL on failure. */ struct snd_info_entry *snd_info_create_card_entry(struct snd_card *card, const char *name, struct snd_info_entry * parent) { if (!parent) parent = card->proc_root; return snd_info_create_entry(name, parent, card->module); } EXPORT_SYMBOL(snd_info_create_card_entry); static void snd_info_clear_entries(struct snd_info_entry *entry) { struct snd_info_entry *p; if (!entry->p) return; list_for_each_entry(p, &entry->children, list) snd_info_clear_entries(p); entry->p = NULL; } /** * snd_info_free_entry - release the info entry * @entry: the info entry * * Releases the info entry. */ void snd_info_free_entry(struct snd_info_entry * entry) { struct snd_info_entry *p, *n; if (!entry) return; if (entry->p) { proc_remove(entry->p); guard(mutex)(&info_mutex); snd_info_clear_entries(entry); } /* free all children at first */ list_for_each_entry_safe(p, n, &entry->children, list) snd_info_free_entry(p); p = entry->parent; if (p) { guard(mutex)(&p->access); list_del(&entry->list); } kfree(entry->name); if (entry->private_free) entry->private_free(entry); kfree(entry); } EXPORT_SYMBOL(snd_info_free_entry); static int __snd_info_register(struct snd_info_entry *entry) { struct proc_dir_entry *root, *p = NULL; if (snd_BUG_ON(!entry)) return -ENXIO; root = entry->parent == NULL ? snd_proc_root->p : entry->parent->p; guard(mutex)(&info_mutex); if (entry->p || !root) return 0; if (S_ISDIR(entry->mode)) { p = proc_mkdir_mode(entry->name, entry->mode, root); if (!p) return -ENOMEM; } else { const struct proc_ops *ops; if (entry->content == SNDRV_INFO_CONTENT_DATA) ops = &snd_info_entry_operations; else ops = &snd_info_text_entry_ops; p = proc_create_data(entry->name, entry->mode, root, ops, entry); if (!p) return -ENOMEM; proc_set_size(p, entry->size); } entry->p = p; return 0; } /** * snd_info_register - register the info entry * @entry: the info entry * * Registers the proc info entry. * The all children entries are registered recursively. * * Return: Zero if successful, or a negative error code on failure. */ int snd_info_register(struct snd_info_entry *entry) { struct snd_info_entry *p; int err; if (!entry->p) { err = __snd_info_register(entry); if (err < 0) return err; } list_for_each_entry(p, &entry->children, list) { err = snd_info_register(p); if (err < 0) return err; } return 0; } EXPORT_SYMBOL(snd_info_register); /** * snd_card_rw_proc_new - Create a read/write text proc file entry for the card * @card: the card instance * @name: the file name * @private_data: the arbitrary private data * @read: the read callback * @write: the write callback, NULL for read-only * * This proc file entry will be registered via snd_card_register() call, and * it will be removed automatically at the card removal, too. * * Return: zero if successful, or a negative error code */ int snd_card_rw_proc_new(struct snd_card *card, const char *name, void *private_data, void (*read)(struct snd_info_entry *, struct snd_info_buffer *), void (*write)(struct snd_info_entry *entry, struct snd_info_buffer *buffer)) { struct snd_info_entry *entry; entry = snd_info_create_card_entry(card, name, card->proc_root); if (!entry) return -ENOMEM; snd_info_set_text_ops(entry, private_data, read); if (write) { entry->mode |= 0200; entry->c.text.write = write; } return 0; } EXPORT_SYMBOL_GPL(snd_card_rw_proc_new); /* */ static void snd_info_version_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { snd_iprintf(buffer, "Advanced Linux Sound Architecture Driver Version k%s.\n", init_utsname()->release); } static int __init snd_info_version_init(void) { struct snd_info_entry *entry; entry = snd_info_create_module_entry(THIS_MODULE, "version", NULL); if (entry == NULL) return -ENOMEM; entry->c.text.read = snd_info_version_read; return snd_info_register(entry); /* freed in error path */ } |
| 8 8 8 8 8 5 8 1 1 1 7 2 2 2 5 1 1 1 4 6 4 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (c) 2008, Intel Corporation. * * Author: Alexander Duyck <alexander.h.duyck@intel.com> */ #ifndef __NET_TC_SKBEDIT_H #define __NET_TC_SKBEDIT_H #include <net/act_api.h> #include <linux/tc_act/tc_skbedit.h> struct tcf_skbedit_params { u32 flags; u32 priority; u32 mark; u32 mask; u16 queue_mapping; u16 mapping_mod; u16 ptype; struct rcu_head rcu; }; struct tcf_skbedit { struct tc_action common; struct tcf_skbedit_params __rcu *params; }; #define to_skbedit(a) ((struct tcf_skbedit *)a) /* Return true iff action is the one identified by FLAG. */ static inline bool is_tcf_skbedit_with_flag(const struct tc_action *a, u32 flag) { #ifdef CONFIG_NET_CLS_ACT u32 flags; if (a->ops && a->ops->id == TCA_ID_SKBEDIT) { rcu_read_lock(); flags = rcu_dereference(to_skbedit(a)->params)->flags; rcu_read_unlock(); return flags == flag; } #endif return false; } /* Return true iff action is mark */ static inline bool is_tcf_skbedit_mark(const struct tc_action *a) { return is_tcf_skbedit_with_flag(a, SKBEDIT_F_MARK); } static inline u32 tcf_skbedit_mark(const struct tc_action *a) { u32 mark; rcu_read_lock(); mark = rcu_dereference(to_skbedit(a)->params)->mark; rcu_read_unlock(); return mark; } /* Return true iff action is ptype */ static inline bool is_tcf_skbedit_ptype(const struct tc_action *a) { return is_tcf_skbedit_with_flag(a, SKBEDIT_F_PTYPE); } static inline u32 tcf_skbedit_ptype(const struct tc_action *a) { u16 ptype; rcu_read_lock(); ptype = rcu_dereference(to_skbedit(a)->params)->ptype; rcu_read_unlock(); return ptype; } /* Return true iff action is priority */ static inline bool is_tcf_skbedit_priority(const struct tc_action *a) { return is_tcf_skbedit_with_flag(a, SKBEDIT_F_PRIORITY); } static inline u32 tcf_skbedit_priority(const struct tc_action *a) { u32 priority; rcu_read_lock(); priority = rcu_dereference(to_skbedit(a)->params)->priority; rcu_read_unlock(); return priority; } static inline u16 tcf_skbedit_rx_queue_mapping(const struct tc_action *a) { u16 rx_queue; rcu_read_lock(); rx_queue = rcu_dereference(to_skbedit(a)->params)->queue_mapping; rcu_read_unlock(); return rx_queue; } /* Return true iff action is queue_mapping */ static inline bool is_tcf_skbedit_queue_mapping(const struct tc_action *a) { return is_tcf_skbedit_with_flag(a, SKBEDIT_F_QUEUE_MAPPING); } /* Return true if action is on ingress traffic */ static inline bool is_tcf_skbedit_ingress(u32 flags) { return flags & TCA_ACT_FLAGS_AT_INGRESS; } static inline bool is_tcf_skbedit_tx_queue_mapping(const struct tc_action *a) { return is_tcf_skbedit_queue_mapping(a) && !is_tcf_skbedit_ingress(a->tcfa_flags); } static inline bool is_tcf_skbedit_rx_queue_mapping(const struct tc_action *a) { return is_tcf_skbedit_queue_mapping(a) && is_tcf_skbedit_ingress(a->tcfa_flags); } /* Return true iff action is inheritdsfield */ static inline bool is_tcf_skbedit_inheritdsfield(const struct tc_action *a) { return is_tcf_skbedit_with_flag(a, SKBEDIT_F_INHERITDSFIELD); } #endif /* __NET_TC_SKBEDIT_H */ |
| 67 67 67 67 67 44 23 67 74 74 73 24 73 24 23 74 2 2 1 74 74 30 16 16 16 16 16 16 16 16 15 31 8 8 8 8 4 30 1 9 16 6 6 10 10 1 16 16 9 16 1 16 16 19 8 7 13 19 19 2 1 19 16 16 16 16 16 15 6 6 10 16 16 3 13 6 21 21 21 363 364 26 364 64 61 61 43 43 18 61 61 63 75 73 76 74 76 19 6 20 7 20 1 1 1 1 217 89 75 217 13 8 13 1 4 9 2 8 8 218 376 376 28 11 375 9 9 9 365 367 366 366 363 366 3 364 364 23 23 343 343 374 217 61 217 217 215 69 217 61 217 217 217 217 217 2 1 217 217 216 217 217 3 3 3 3 216 215 6 6 1 6 217 1 1 217 217 218 218 5 218 2 2 217 18 16 5 18 6 6 21 13 13 116 402 402 392 386 392 16 384 385 49 337 252 386 25 361 19 19 20 386 359 386 386 386 385 386 386 383 386 386 400 45 26 45 45 343 343 76 2 2 2 2 2 2 2 2 2 2 15 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * USB HID support for Linux * * Copyright (c) 1999 Andreas Gal * Copyright (c) 2000-2005 Vojtech Pavlik <vojtech@suse.cz> * Copyright (c) 2005 Michael Haboustak <mike-@cinci.rr.com> for Concept2, Inc * Copyright (c) 2007-2008 Oliver Neukum * Copyright (c) 2006-2010 Jiri Kosina */ /* */ #include <linux/module.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/mm.h> #include <linux/mutex.h> #include <linux/property.h> #include <linux/spinlock.h> #include <linux/unaligned.h> #include <asm/byteorder.h> #include <linux/input.h> #include <linux/wait.h> #include <linux/workqueue.h> #include <linux/string.h> #include <linux/usb.h> #include <linux/hid.h> #include <linux/hiddev.h> #include <linux/hid-debug.h> #include <linux/hidraw.h> #include "usbhid.h" /* * Version Information */ #define DRIVER_DESC "USB HID core driver" /* * Module parameters. */ static unsigned int hid_mousepoll_interval; module_param_named(mousepoll, hid_mousepoll_interval, uint, 0644); MODULE_PARM_DESC(mousepoll, "Polling interval of mice"); static unsigned int hid_jspoll_interval; module_param_named(jspoll, hid_jspoll_interval, uint, 0644); MODULE_PARM_DESC(jspoll, "Polling interval of joysticks"); static unsigned int hid_kbpoll_interval; module_param_named(kbpoll, hid_kbpoll_interval, uint, 0644); MODULE_PARM_DESC(kbpoll, "Polling interval of keyboards"); static unsigned int ignoreled; module_param_named(ignoreled, ignoreled, uint, 0644); MODULE_PARM_DESC(ignoreled, "Autosuspend with active leds"); /* Quirks specified at module load time */ static char *quirks_param[MAX_USBHID_BOOT_QUIRKS]; module_param_array_named(quirks, quirks_param, charp, NULL, 0444); MODULE_PARM_DESC(quirks, "Add/modify USB HID quirks by specifying " " quirks=vendorID:productID:quirks" " where vendorID, productID, and quirks are all in" " 0x-prefixed hex"); /* * Input submission and I/O error handler. */ static void hid_io_error(struct hid_device *hid); static int hid_submit_out(struct hid_device *hid); static int hid_submit_ctrl(struct hid_device *hid); static void hid_cancel_delayed_stuff(struct usbhid_device *usbhid); /* Start up the input URB */ static int hid_start_in(struct hid_device *hid) { unsigned long flags; int rc = 0; struct usbhid_device *usbhid = hid->driver_data; spin_lock_irqsave(&usbhid->lock, flags); if (test_bit(HID_IN_POLLING, &usbhid->iofl) && !test_bit(HID_DISCONNECTED, &usbhid->iofl) && !test_bit(HID_SUSPENDED, &usbhid->iofl) && !test_and_set_bit(HID_IN_RUNNING, &usbhid->iofl)) { rc = usb_submit_urb(usbhid->urbin, GFP_ATOMIC); if (rc != 0) { clear_bit(HID_IN_RUNNING, &usbhid->iofl); if (rc == -ENOSPC) set_bit(HID_NO_BANDWIDTH, &usbhid->iofl); } else { clear_bit(HID_NO_BANDWIDTH, &usbhid->iofl); } } spin_unlock_irqrestore(&usbhid->lock, flags); return rc; } /* I/O retry timer routine */ static void hid_retry_timeout(struct timer_list *t) { struct usbhid_device *usbhid = from_timer(usbhid, t, io_retry); struct hid_device *hid = usbhid->hid; dev_dbg(&usbhid->intf->dev, "retrying intr urb\n"); if (hid_start_in(hid)) hid_io_error(hid); } /* Workqueue routine to reset the device or clear a halt */ static void hid_reset(struct work_struct *work) { struct usbhid_device *usbhid = container_of(work, struct usbhid_device, reset_work); struct hid_device *hid = usbhid->hid; int rc; if (test_bit(HID_CLEAR_HALT, &usbhid->iofl)) { dev_dbg(&usbhid->intf->dev, "clear halt\n"); rc = usb_clear_halt(hid_to_usb_dev(hid), usbhid->urbin->pipe); clear_bit(HID_CLEAR_HALT, &usbhid->iofl); if (rc == 0) { hid_start_in(hid); } else { dev_dbg(&usbhid->intf->dev, "clear-halt failed: %d\n", rc); set_bit(HID_RESET_PENDING, &usbhid->iofl); } } if (test_bit(HID_RESET_PENDING, &usbhid->iofl)) { dev_dbg(&usbhid->intf->dev, "resetting device\n"); usb_queue_reset_device(usbhid->intf); } } /* Main I/O error handler */ static void hid_io_error(struct hid_device *hid) { unsigned long flags; struct usbhid_device *usbhid = hid->driver_data; spin_lock_irqsave(&usbhid->lock, flags); /* Stop when disconnected */ if (test_bit(HID_DISCONNECTED, &usbhid->iofl)) goto done; /* If it has been a while since the last error, we'll assume * this a brand new error and reset the retry timeout. */ if (time_after(jiffies, usbhid->stop_retry + HZ/2)) usbhid->retry_delay = 0; /* When an error occurs, retry at increasing intervals */ if (usbhid->retry_delay == 0) { usbhid->retry_delay = 13; /* Then 26, 52, 104, 104, ... */ usbhid->stop_retry = jiffies + msecs_to_jiffies(1000); } else if (usbhid->retry_delay < 100) usbhid->retry_delay *= 2; if (time_after(jiffies, usbhid->stop_retry)) { /* Retries failed, so do a port reset unless we lack bandwidth*/ if (!test_bit(HID_NO_BANDWIDTH, &usbhid->iofl) && !test_and_set_bit(HID_RESET_PENDING, &usbhid->iofl)) { schedule_work(&usbhid->reset_work); goto done; } } mod_timer(&usbhid->io_retry, jiffies + msecs_to_jiffies(usbhid->retry_delay)); done: spin_unlock_irqrestore(&usbhid->lock, flags); } static void usbhid_mark_busy(struct usbhid_device *usbhid) { struct usb_interface *intf = usbhid->intf; usb_mark_last_busy(interface_to_usbdev(intf)); } static int usbhid_restart_out_queue(struct usbhid_device *usbhid) { struct hid_device *hid = usb_get_intfdata(usbhid->intf); int kicked; int r; if (!hid || test_bit(HID_RESET_PENDING, &usbhid->iofl) || test_bit(HID_SUSPENDED, &usbhid->iofl)) return 0; if ((kicked = (usbhid->outhead != usbhid->outtail))) { hid_dbg(hid, "Kicking head %d tail %d", usbhid->outhead, usbhid->outtail); /* Try to wake up from autosuspend... */ r = usb_autopm_get_interface_async(usbhid->intf); if (r < 0) return r; /* * If still suspended, don't submit. Submission will * occur if/when resume drains the queue. */ if (test_bit(HID_SUSPENDED, &usbhid->iofl)) { usb_autopm_put_interface_no_suspend(usbhid->intf); return r; } /* Asynchronously flush queue. */ set_bit(HID_OUT_RUNNING, &usbhid->iofl); if (hid_submit_out(hid)) { clear_bit(HID_OUT_RUNNING, &usbhid->iofl); usb_autopm_put_interface_async(usbhid->intf); } wake_up(&usbhid->wait); } return kicked; } static int usbhid_restart_ctrl_queue(struct usbhid_device *usbhid) { struct hid_device *hid = usb_get_intfdata(usbhid->intf); int kicked; int r; WARN_ON(hid == NULL); if (!hid || test_bit(HID_RESET_PENDING, &usbhid->iofl) || test_bit(HID_SUSPENDED, &usbhid->iofl)) return 0; if ((kicked = (usbhid->ctrlhead != usbhid->ctrltail))) { hid_dbg(hid, "Kicking head %d tail %d", usbhid->ctrlhead, usbhid->ctrltail); /* Try to wake up from autosuspend... */ r = usb_autopm_get_interface_async(usbhid->intf); if (r < 0) return r; /* * If still suspended, don't submit. Submission will * occur if/when resume drains the queue. */ if (test_bit(HID_SUSPENDED, &usbhid->iofl)) { usb_autopm_put_interface_no_suspend(usbhid->intf); return r; } /* Asynchronously flush queue. */ set_bit(HID_CTRL_RUNNING, &usbhid->iofl); if (hid_submit_ctrl(hid)) { clear_bit(HID_CTRL_RUNNING, &usbhid->iofl); usb_autopm_put_interface_async(usbhid->intf); } wake_up(&usbhid->wait); } return kicked; } /* * Input interrupt completion handler. */ static void hid_irq_in(struct urb *urb) { struct hid_device *hid = urb->context; struct usbhid_device *usbhid = hid->driver_data; int status; switch (urb->status) { case 0: /* success */ usbhid->retry_delay = 0; if (!test_bit(HID_OPENED, &usbhid->iofl)) break; usbhid_mark_busy(usbhid); if (!test_bit(HID_RESUME_RUNNING, &usbhid->iofl)) { hid_input_report(urb->context, HID_INPUT_REPORT, urb->transfer_buffer, urb->actual_length, 1); /* * autosuspend refused while keys are pressed * because most keyboards don't wake up when * a key is released */ if (hid_check_keys_pressed(hid)) set_bit(HID_KEYS_PRESSED, &usbhid->iofl); else clear_bit(HID_KEYS_PRESSED, &usbhid->iofl); } break; case -EPIPE: /* stall */ usbhid_mark_busy(usbhid); clear_bit(HID_IN_RUNNING, &usbhid->iofl); set_bit(HID_CLEAR_HALT, &usbhid->iofl); schedule_work(&usbhid->reset_work); return; case -ECONNRESET: /* unlink */ case -ENOENT: case -ESHUTDOWN: /* unplug */ clear_bit(HID_IN_RUNNING, &usbhid->iofl); return; case -EILSEQ: /* protocol error or unplug */ case -EPROTO: /* protocol error or unplug */ case -ETIME: /* protocol error or unplug */ case -ETIMEDOUT: /* Should never happen, but... */ usbhid_mark_busy(usbhid); clear_bit(HID_IN_RUNNING, &usbhid->iofl); hid_io_error(hid); return; default: /* error */ hid_warn(urb->dev, "input irq status %d received\n", urb->status); } status = usb_submit_urb(urb, GFP_ATOMIC); if (status) { clear_bit(HID_IN_RUNNING, &usbhid->iofl); if (status != -EPERM) { hid_err(hid, "can't resubmit intr, %s-%s/input%d, status %d\n", hid_to_usb_dev(hid)->bus->bus_name, hid_to_usb_dev(hid)->devpath, usbhid->ifnum, status); hid_io_error(hid); } } } static int hid_submit_out(struct hid_device *hid) { struct hid_report *report; char *raw_report; struct usbhid_device *usbhid = hid->driver_data; int r; report = usbhid->out[usbhid->outtail].report; raw_report = usbhid->out[usbhid->outtail].raw_report; usbhid->urbout->transfer_buffer_length = hid_report_len(report); usbhid->urbout->dev = hid_to_usb_dev(hid); if (raw_report) { memcpy(usbhid->outbuf, raw_report, usbhid->urbout->transfer_buffer_length); kfree(raw_report); usbhid->out[usbhid->outtail].raw_report = NULL; } dbg_hid("submitting out urb\n"); r = usb_submit_urb(usbhid->urbout, GFP_ATOMIC); if (r < 0) { hid_err(hid, "usb_submit_urb(out) failed: %d\n", r); return r; } usbhid->last_out = jiffies; return 0; } static int hid_submit_ctrl(struct hid_device *hid) { struct hid_report *report; unsigned char dir; char *raw_report; int len, r; struct usbhid_device *usbhid = hid->driver_data; report = usbhid->ctrl[usbhid->ctrltail].report; raw_report = usbhid->ctrl[usbhid->ctrltail].raw_report; dir = usbhid->ctrl[usbhid->ctrltail].dir; len = hid_report_len(report); if (dir == USB_DIR_OUT) { usbhid->urbctrl->pipe = usb_sndctrlpipe(hid_to_usb_dev(hid), 0); if (raw_report) { memcpy(usbhid->ctrlbuf, raw_report, len); kfree(raw_report); usbhid->ctrl[usbhid->ctrltail].raw_report = NULL; } } else { int maxpacket; usbhid->urbctrl->pipe = usb_rcvctrlpipe(hid_to_usb_dev(hid), 0); maxpacket = usb_maxpacket(hid_to_usb_dev(hid), usbhid->urbctrl->pipe); len += (len == 0); /* Don't allow 0-length reports */ len = round_up(len, maxpacket); if (len > usbhid->bufsize) len = usbhid->bufsize; } usbhid->urbctrl->transfer_buffer_length = len; usbhid->urbctrl->dev = hid_to_usb_dev(hid); usbhid->cr->bRequestType = USB_TYPE_CLASS | USB_RECIP_INTERFACE | dir; usbhid->cr->bRequest = (dir == USB_DIR_OUT) ? HID_REQ_SET_REPORT : HID_REQ_GET_REPORT; usbhid->cr->wValue = cpu_to_le16(((report->type + 1) << 8) | report->id); usbhid->cr->wIndex = cpu_to_le16(usbhid->ifnum); usbhid->cr->wLength = cpu_to_le16(len); dbg_hid("submitting ctrl urb: %s wValue=0x%04x wIndex=0x%04x wLength=%u\n", usbhid->cr->bRequest == HID_REQ_SET_REPORT ? "Set_Report" : "Get_Report", usbhid->cr->wValue, usbhid->cr->wIndex, usbhid->cr->wLength); r = usb_submit_urb(usbhid->urbctrl, GFP_ATOMIC); if (r < 0) { hid_err(hid, "usb_submit_urb(ctrl) failed: %d\n", r); return r; } usbhid->last_ctrl = jiffies; return 0; } /* * Output interrupt completion handler. */ static void hid_irq_out(struct urb *urb) { struct hid_device *hid = urb->context; struct usbhid_device *usbhid = hid->driver_data; unsigned long flags; int unplug = 0; switch (urb->status) { case 0: /* success */ break; case -ESHUTDOWN: /* unplug */ unplug = 1; break; case -EILSEQ: /* protocol error or unplug */ case -EPROTO: /* protocol error or unplug */ case -ECONNRESET: /* unlink */ case -ENOENT: break; default: /* error */ hid_warn(urb->dev, "output irq status %d received\n", urb->status); } spin_lock_irqsave(&usbhid->lock, flags); if (unplug) { usbhid->outtail = usbhid->outhead; } else { usbhid->outtail = (usbhid->outtail + 1) & (HID_OUTPUT_FIFO_SIZE - 1); if (usbhid->outhead != usbhid->outtail && hid_submit_out(hid) == 0) { /* Successfully submitted next urb in queue */ spin_unlock_irqrestore(&usbhid->lock, flags); return; } } clear_bit(HID_OUT_RUNNING, &usbhid->iofl); spin_unlock_irqrestore(&usbhid->lock, flags); usb_autopm_put_interface_async(usbhid->intf); wake_up(&usbhid->wait); } /* * Control pipe completion handler. */ static void hid_ctrl(struct urb *urb) { struct hid_device *hid = urb->context; struct usbhid_device *usbhid = hid->driver_data; unsigned long flags; int unplug = 0, status = urb->status; switch (status) { case 0: /* success */ if (usbhid->ctrl[usbhid->ctrltail].dir == USB_DIR_IN) hid_input_report(urb->context, usbhid->ctrl[usbhid->ctrltail].report->type, urb->transfer_buffer, urb->actual_length, 0); break; case -ESHUTDOWN: /* unplug */ unplug = 1; break; case -EILSEQ: /* protocol error or unplug */ case -EPROTO: /* protocol error or unplug */ case -ECONNRESET: /* unlink */ case -ENOENT: case -EPIPE: /* report not available */ break; default: /* error */ hid_warn(urb->dev, "ctrl urb status %d received\n", status); } spin_lock_irqsave(&usbhid->lock, flags); if (unplug) { usbhid->ctrltail = usbhid->ctrlhead; } else if (usbhid->ctrlhead != usbhid->ctrltail) { usbhid->ctrltail = (usbhid->ctrltail + 1) & (HID_CONTROL_FIFO_SIZE - 1); if (usbhid->ctrlhead != usbhid->ctrltail && hid_submit_ctrl(hid) == 0) { /* Successfully submitted next urb in queue */ spin_unlock_irqrestore(&usbhid->lock, flags); return; } } clear_bit(HID_CTRL_RUNNING, &usbhid->iofl); spin_unlock_irqrestore(&usbhid->lock, flags); usb_autopm_put_interface_async(usbhid->intf); wake_up(&usbhid->wait); } static void __usbhid_submit_report(struct hid_device *hid, struct hid_report *report, unsigned char dir) { int head; struct usbhid_device *usbhid = hid->driver_data; if (((hid->quirks & HID_QUIRK_NOGET) && dir == USB_DIR_IN) || test_bit(HID_DISCONNECTED, &usbhid->iofl)) return; if (usbhid->urbout && dir == USB_DIR_OUT && report->type == HID_OUTPUT_REPORT) { if ((head = (usbhid->outhead + 1) & (HID_OUTPUT_FIFO_SIZE - 1)) == usbhid->outtail) { hid_warn(hid, "output queue full\n"); return; } usbhid->out[usbhid->outhead].raw_report = hid_alloc_report_buf(report, GFP_ATOMIC); if (!usbhid->out[usbhid->outhead].raw_report) { hid_warn(hid, "output queueing failed\n"); return; } hid_output_report(report, usbhid->out[usbhid->outhead].raw_report); usbhid->out[usbhid->outhead].report = report; usbhid->outhead = head; /* If the queue isn't running, restart it */ if (!test_bit(HID_OUT_RUNNING, &usbhid->iofl)) { usbhid_restart_out_queue(usbhid); /* Otherwise see if an earlier request has timed out */ } else if (time_after(jiffies, usbhid->last_out + HZ * 5)) { /* Prevent autosuspend following the unlink */ usb_autopm_get_interface_no_resume(usbhid->intf); /* * Prevent resubmission in case the URB completes * before we can unlink it. We don't want to cancel * the wrong transfer! */ usb_block_urb(usbhid->urbout); /* Drop lock to avoid deadlock if the callback runs */ spin_unlock(&usbhid->lock); usb_unlink_urb(usbhid->urbout); spin_lock(&usbhid->lock); usb_unblock_urb(usbhid->urbout); /* Unlink might have stopped the queue */ if (!test_bit(HID_OUT_RUNNING, &usbhid->iofl)) usbhid_restart_out_queue(usbhid); /* Now we can allow autosuspend again */ usb_autopm_put_interface_async(usbhid->intf); } return; } if ((head = (usbhid->ctrlhead + 1) & (HID_CONTROL_FIFO_SIZE - 1)) == usbhid->ctrltail) { hid_warn(hid, "control queue full\n"); return; } if (dir == USB_DIR_OUT) { usbhid->ctrl[usbhid->ctrlhead].raw_report = hid_alloc_report_buf(report, GFP_ATOMIC); if (!usbhid->ctrl[usbhid->ctrlhead].raw_report) { hid_warn(hid, "control queueing failed\n"); return; } hid_output_report(report, usbhid->ctrl[usbhid->ctrlhead].raw_report); } usbhid->ctrl[usbhid->ctrlhead].report = report; usbhid->ctrl[usbhid->ctrlhead].dir = dir; usbhid->ctrlhead = head; /* If the queue isn't running, restart it */ if (!test_bit(HID_CTRL_RUNNING, &usbhid->iofl)) { usbhid_restart_ctrl_queue(usbhid); /* Otherwise see if an earlier request has timed out */ } else if (time_after(jiffies, usbhid->last_ctrl + HZ * 5)) { /* Prevent autosuspend following the unlink */ usb_autopm_get_interface_no_resume(usbhid->intf); /* * Prevent resubmission in case the URB completes * before we can unlink it. We don't want to cancel * the wrong transfer! */ usb_block_urb(usbhid->urbctrl); /* Drop lock to avoid deadlock if the callback runs */ spin_unlock(&usbhid->lock); usb_unlink_urb(usbhid->urbctrl); spin_lock(&usbhid->lock); usb_unblock_urb(usbhid->urbctrl); /* Unlink might have stopped the queue */ if (!test_bit(HID_CTRL_RUNNING, &usbhid->iofl)) usbhid_restart_ctrl_queue(usbhid); /* Now we can allow autosuspend again */ usb_autopm_put_interface_async(usbhid->intf); } } static void usbhid_submit_report(struct hid_device *hid, struct hid_report *report, unsigned char dir) { struct usbhid_device *usbhid = hid->driver_data; unsigned long flags; spin_lock_irqsave(&usbhid->lock, flags); __usbhid_submit_report(hid, report, dir); spin_unlock_irqrestore(&usbhid->lock, flags); } static int usbhid_wait_io(struct hid_device *hid) { struct usbhid_device *usbhid = hid->driver_data; if (!wait_event_timeout(usbhid->wait, (!test_bit(HID_CTRL_RUNNING, &usbhid->iofl) && !test_bit(HID_OUT_RUNNING, &usbhid->iofl)), 10*HZ)) { dbg_hid("timeout waiting for ctrl or out queue to clear\n"); return -1; } return 0; } static int hid_set_idle(struct usb_device *dev, int ifnum, int report, int idle) { return usb_control_msg(dev, usb_sndctrlpipe(dev, 0), HID_REQ_SET_IDLE, USB_TYPE_CLASS | USB_RECIP_INTERFACE, (idle << 8) | report, ifnum, NULL, 0, USB_CTRL_SET_TIMEOUT); } static int hid_get_class_descriptor(struct usb_device *dev, int ifnum, unsigned char type, void *buf, int size) { int result, retries = 4; memset(buf, 0, size); do { result = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), USB_REQ_GET_DESCRIPTOR, USB_RECIP_INTERFACE | USB_DIR_IN, (type << 8), ifnum, buf, size, USB_CTRL_GET_TIMEOUT); retries--; } while (result < size && retries); return result; } static int usbhid_open(struct hid_device *hid) { struct usbhid_device *usbhid = hid->driver_data; int res; mutex_lock(&usbhid->mutex); set_bit(HID_OPENED, &usbhid->iofl); if (hid->quirks & HID_QUIRK_ALWAYS_POLL) { res = 0; goto Done; } res = usb_autopm_get_interface(usbhid->intf); /* the device must be awake to reliably request remote wakeup */ if (res < 0) { clear_bit(HID_OPENED, &usbhid->iofl); res = -EIO; goto Done; } usbhid->intf->needs_remote_wakeup = 1; set_bit(HID_RESUME_RUNNING, &usbhid->iofl); set_bit(HID_IN_POLLING, &usbhid->iofl); res = hid_start_in(hid); if (res) { if (res != -ENOSPC) { hid_io_error(hid); res = 0; } else { /* no use opening if resources are insufficient */ res = -EBUSY; clear_bit(HID_OPENED, &usbhid->iofl); clear_bit(HID_IN_POLLING, &usbhid->iofl); usbhid->intf->needs_remote_wakeup = 0; } } usb_autopm_put_interface(usbhid->intf); /* * In case events are generated while nobody was listening, * some are released when the device is re-opened. * Wait 50 msec for the queue to empty before allowing events * to go through hid. */ if (res == 0) msleep(50); clear_bit(HID_RESUME_RUNNING, &usbhid->iofl); Done: mutex_unlock(&usbhid->mutex); return res; } static void usbhid_close(struct hid_device *hid) { struct usbhid_device *usbhid = hid->driver_data; mutex_lock(&usbhid->mutex); /* * Make sure we don't restart data acquisition due to * a resumption we no longer care about by avoiding racing * with hid_start_in(). */ spin_lock_irq(&usbhid->lock); clear_bit(HID_OPENED, &usbhid->iofl); if (!(hid->quirks & HID_QUIRK_ALWAYS_POLL)) clear_bit(HID_IN_POLLING, &usbhid->iofl); spin_unlock_irq(&usbhid->lock); if (!(hid->quirks & HID_QUIRK_ALWAYS_POLL)) { hid_cancel_delayed_stuff(usbhid); usb_kill_urb(usbhid->urbin); usbhid->intf->needs_remote_wakeup = 0; } mutex_unlock(&usbhid->mutex); } /* * Initialize all reports */ void usbhid_init_reports(struct hid_device *hid) { struct hid_report *report; struct usbhid_device *usbhid = hid->driver_data; struct hid_report_enum *report_enum; int err, ret; report_enum = &hid->report_enum[HID_INPUT_REPORT]; list_for_each_entry(report, &report_enum->report_list, list) usbhid_submit_report(hid, report, USB_DIR_IN); report_enum = &hid->report_enum[HID_FEATURE_REPORT]; list_for_each_entry(report, &report_enum->report_list, list) usbhid_submit_report(hid, report, USB_DIR_IN); err = 0; ret = usbhid_wait_io(hid); while (ret) { err |= ret; if (test_bit(HID_CTRL_RUNNING, &usbhid->iofl)) usb_kill_urb(usbhid->urbctrl); if (test_bit(HID_OUT_RUNNING, &usbhid->iofl)) usb_kill_urb(usbhid->urbout); ret = usbhid_wait_io(hid); } if (err) hid_warn(hid, "timeout initializing reports\n"); } /* * Reset LEDs which BIOS might have left on. For now, just NumLock (0x01). */ static int hid_find_field_early(struct hid_device *hid, unsigned int page, unsigned int hid_code, struct hid_field **pfield) { struct hid_report *report; struct hid_field *field; struct hid_usage *usage; int i, j; list_for_each_entry(report, &hid->report_enum[HID_OUTPUT_REPORT].report_list, list) { for (i = 0; i < report->maxfield; i++) { field = report->field[i]; for (j = 0; j < field->maxusage; j++) { usage = &field->usage[j]; if ((usage->hid & HID_USAGE_PAGE) == page && (usage->hid & 0xFFFF) == hid_code) { *pfield = field; return j; } } } } return -1; } static void usbhid_set_leds(struct hid_device *hid) { struct hid_field *field; int offset; if ((offset = hid_find_field_early(hid, HID_UP_LED, 0x01, &field)) != -1) { hid_set_field(field, offset, 0); usbhid_submit_report(hid, field->report, USB_DIR_OUT); } } /* * Traverse the supplied list of reports and find the longest */ static void hid_find_max_report(struct hid_device *hid, unsigned int type, unsigned int *max) { struct hid_report *report; unsigned int size; list_for_each_entry(report, &hid->report_enum[type].report_list, list) { size = ((report->size - 1) >> 3) + 1 + hid->report_enum[type].numbered; if (*max < size) *max = size; } } static int hid_alloc_buffers(struct usb_device *dev, struct hid_device *hid) { struct usbhid_device *usbhid = hid->driver_data; usbhid->inbuf = usb_alloc_coherent(dev, usbhid->bufsize, GFP_KERNEL, &usbhid->inbuf_dma); usbhid->outbuf = usb_alloc_coherent(dev, usbhid->bufsize, GFP_KERNEL, &usbhid->outbuf_dma); usbhid->cr = kmalloc(sizeof(*usbhid->cr), GFP_KERNEL); usbhid->ctrlbuf = usb_alloc_coherent(dev, usbhid->bufsize, GFP_KERNEL, &usbhid->ctrlbuf_dma); if (!usbhid->inbuf || !usbhid->outbuf || !usbhid->cr || !usbhid->ctrlbuf) return -1; return 0; } static int usbhid_get_raw_report(struct hid_device *hid, unsigned char report_number, __u8 *buf, size_t count, unsigned char report_type) { struct usbhid_device *usbhid = hid->driver_data; struct usb_device *dev = hid_to_usb_dev(hid); struct usb_interface *intf = usbhid->intf; struct usb_host_interface *interface = intf->cur_altsetting; int skipped_report_id = 0; int ret; /* Byte 0 is the report number. Report data starts at byte 1.*/ buf[0] = report_number; if (report_number == 0x0) { /* Offset the return buffer by 1, so that the report ID will remain in byte 0. */ buf++; count--; skipped_report_id = 1; } ret = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), HID_REQ_GET_REPORT, USB_DIR_IN | USB_TYPE_CLASS | USB_RECIP_INTERFACE, ((report_type + 1) << 8) | report_number, interface->desc.bInterfaceNumber, buf, count, USB_CTRL_SET_TIMEOUT); /* count also the report id */ if (ret > 0 && skipped_report_id) ret++; return ret; } static int usbhid_set_raw_report(struct hid_device *hid, unsigned int reportnum, __u8 *buf, size_t count, unsigned char rtype) { struct usbhid_device *usbhid = hid->driver_data; struct usb_device *dev = hid_to_usb_dev(hid); struct usb_interface *intf = usbhid->intf; struct usb_host_interface *interface = intf->cur_altsetting; int ret, skipped_report_id = 0; /* Byte 0 is the report number. Report data starts at byte 1.*/ if ((rtype == HID_OUTPUT_REPORT) && (hid->quirks & HID_QUIRK_SKIP_OUTPUT_REPORT_ID)) buf[0] = 0; else buf[0] = reportnum; if (buf[0] == 0x0) { /* Don't send the Report ID */ buf++; count--; skipped_report_id = 1; } ret = usb_control_msg(dev, usb_sndctrlpipe(dev, 0), HID_REQ_SET_REPORT, USB_DIR_OUT | USB_TYPE_CLASS | USB_RECIP_INTERFACE, ((rtype + 1) << 8) | reportnum, interface->desc.bInterfaceNumber, buf, count, USB_CTRL_SET_TIMEOUT); /* count also the report id, if this was a numbered report. */ if (ret > 0 && skipped_report_id) ret++; return ret; } static int usbhid_output_report(struct hid_device *hid, __u8 *buf, size_t count) { struct usbhid_device *usbhid = hid->driver_data; struct usb_device *dev = hid_to_usb_dev(hid); int actual_length, skipped_report_id = 0, ret; if (!usbhid->urbout) return -ENOSYS; if (buf[0] == 0x0) { /* Don't send the Report ID */ buf++; count--; skipped_report_id = 1; } ret = usb_interrupt_msg(dev, usbhid->urbout->pipe, buf, count, &actual_length, USB_CTRL_SET_TIMEOUT); /* return the number of bytes transferred */ if (ret == 0) { ret = actual_length; /* count also the report id */ if (skipped_report_id) ret++; } return ret; } static void hid_free_buffers(struct usb_device *dev, struct hid_device *hid) { struct usbhid_device *usbhid = hid->driver_data; usb_free_coherent(dev, usbhid->bufsize, usbhid->inbuf, usbhid->inbuf_dma); usb_free_coherent(dev, usbhid->bufsize, usbhid->outbuf, usbhid->outbuf_dma); kfree(usbhid->cr); usb_free_coherent(dev, usbhid->bufsize, usbhid->ctrlbuf, usbhid->ctrlbuf_dma); } static int usbhid_parse(struct hid_device *hid) { struct usb_interface *intf = to_usb_interface(hid->dev.parent); struct usb_host_interface *interface = intf->cur_altsetting; struct usb_device *dev = interface_to_usbdev (intf); struct hid_descriptor *hdesc; u32 quirks = 0; unsigned int rsize = 0; char *rdesc; int ret, n; int num_descriptors; size_t offset = offsetof(struct hid_descriptor, desc); quirks = hid_lookup_quirk(hid); if (quirks & HID_QUIRK_IGNORE) return -ENODEV; /* Many keyboards and mice don't like to be polled for reports, * so we will always set the HID_QUIRK_NOGET flag for them. */ if (interface->desc.bInterfaceSubClass == USB_INTERFACE_SUBCLASS_BOOT) { if (interface->desc.bInterfaceProtocol == USB_INTERFACE_PROTOCOL_KEYBOARD || interface->desc.bInterfaceProtocol == USB_INTERFACE_PROTOCOL_MOUSE) quirks |= HID_QUIRK_NOGET; } if (usb_get_extra_descriptor(interface, HID_DT_HID, &hdesc) && (!interface->desc.bNumEndpoints || usb_get_extra_descriptor(&interface->endpoint[0], HID_DT_HID, &hdesc))) { dbg_hid("class descriptor not present\n"); return -ENODEV; } if (hdesc->bLength < sizeof(struct hid_descriptor)) { dbg_hid("hid descriptor is too short\n"); return -EINVAL; } hid->version = le16_to_cpu(hdesc->bcdHID); hid->country = hdesc->bCountryCode; num_descriptors = min_t(int, hdesc->bNumDescriptors, (hdesc->bLength - offset) / sizeof(struct hid_class_descriptor)); for (n = 0; n < num_descriptors; n++) if (hdesc->desc[n].bDescriptorType == HID_DT_REPORT) rsize = le16_to_cpu(hdesc->desc[n].wDescriptorLength); if (!rsize || rsize > HID_MAX_DESCRIPTOR_SIZE) { dbg_hid("weird size of report descriptor (%u)\n", rsize); return -EINVAL; } rdesc = kmalloc(rsize, GFP_KERNEL); if (!rdesc) return -ENOMEM; hid_set_idle(dev, interface->desc.bInterfaceNumber, 0, 0); ret = hid_get_class_descriptor(dev, interface->desc.bInterfaceNumber, HID_DT_REPORT, rdesc, rsize); if (ret < 0) { dbg_hid("reading report descriptor failed\n"); kfree(rdesc); goto err; } ret = hid_parse_report(hid, rdesc, rsize); kfree(rdesc); if (ret) { dbg_hid("parsing report descriptor failed\n"); goto err; } hid->quirks |= quirks; return 0; err: return ret; } static int usbhid_start(struct hid_device *hid) { struct usb_interface *intf = to_usb_interface(hid->dev.parent); struct usb_host_interface *interface = intf->cur_altsetting; struct usb_device *dev = interface_to_usbdev(intf); struct usbhid_device *usbhid = hid->driver_data; unsigned int n, insize = 0; int ret; mutex_lock(&usbhid->mutex); clear_bit(HID_DISCONNECTED, &usbhid->iofl); usbhid->bufsize = HID_MIN_BUFFER_SIZE; hid_find_max_report(hid, HID_INPUT_REPORT, &usbhid->bufsize); hid_find_max_report(hid, HID_OUTPUT_REPORT, &usbhid->bufsize); hid_find_max_report(hid, HID_FEATURE_REPORT, &usbhid->bufsize); if (usbhid->bufsize > HID_MAX_BUFFER_SIZE) usbhid->bufsize = HID_MAX_BUFFER_SIZE; hid_find_max_report(hid, HID_INPUT_REPORT, &insize); if (insize > HID_MAX_BUFFER_SIZE) insize = HID_MAX_BUFFER_SIZE; if (hid_alloc_buffers(dev, hid)) { ret = -ENOMEM; goto fail; } for (n = 0; n < interface->desc.bNumEndpoints; n++) { struct usb_endpoint_descriptor *endpoint; int pipe; int interval; endpoint = &interface->endpoint[n].desc; if (!usb_endpoint_xfer_int(endpoint)) continue; interval = endpoint->bInterval; /* Some vendors give fullspeed interval on highspeed devices */ if (hid->quirks & HID_QUIRK_FULLSPEED_INTERVAL && dev->speed == USB_SPEED_HIGH) { interval = fls(endpoint->bInterval*8); pr_info("%s: Fixing fullspeed to highspeed interval: %d -> %d\n", hid->name, endpoint->bInterval, interval); } /* Change the polling interval of mice, joysticks * and keyboards. */ switch (hid->collection->usage) { case HID_GD_MOUSE: if (hid_mousepoll_interval > 0) interval = hid_mousepoll_interval; break; case HID_GD_JOYSTICK: if (hid_jspoll_interval > 0) interval = hid_jspoll_interval; break; case HID_GD_KEYBOARD: if (hid_kbpoll_interval > 0) interval = hid_kbpoll_interval; break; } ret = -ENOMEM; if (usb_endpoint_dir_in(endpoint)) { if (usbhid->urbin) continue; if (!(usbhid->urbin = usb_alloc_urb(0, GFP_KERNEL))) goto fail; pipe = usb_rcvintpipe(dev, endpoint->bEndpointAddress); usb_fill_int_urb(usbhid->urbin, dev, pipe, usbhid->inbuf, insize, hid_irq_in, hid, interval); usbhid->urbin->transfer_dma = usbhid->inbuf_dma; usbhid->urbin->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; } else { if (usbhid->urbout) continue; if (!(usbhid->urbout = usb_alloc_urb(0, GFP_KERNEL))) goto fail; pipe = usb_sndintpipe(dev, endpoint->bEndpointAddress); usb_fill_int_urb(usbhid->urbout, dev, pipe, usbhid->outbuf, 0, hid_irq_out, hid, interval); usbhid->urbout->transfer_dma = usbhid->outbuf_dma; usbhid->urbout->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; } } usbhid->urbctrl = usb_alloc_urb(0, GFP_KERNEL); if (!usbhid->urbctrl) { ret = -ENOMEM; goto fail; } usb_fill_control_urb(usbhid->urbctrl, dev, 0, (void *) usbhid->cr, usbhid->ctrlbuf, 1, hid_ctrl, hid); usbhid->urbctrl->transfer_dma = usbhid->ctrlbuf_dma; usbhid->urbctrl->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; set_bit(HID_STARTED, &usbhid->iofl); if (hid->quirks & HID_QUIRK_ALWAYS_POLL) { ret = usb_autopm_get_interface(usbhid->intf); if (ret) goto fail; set_bit(HID_IN_POLLING, &usbhid->iofl); usbhid->intf->needs_remote_wakeup = 1; ret = hid_start_in(hid); if (ret) { dev_err(&hid->dev, "failed to start in urb: %d\n", ret); } usb_autopm_put_interface(usbhid->intf); } /* Some keyboards don't work until their LEDs have been set. * Since BIOSes do set the LEDs, it must be safe for any device * that supports the keyboard boot protocol. * In addition, enable remote wakeup by default for all keyboard * devices supporting the boot protocol. */ if (interface->desc.bInterfaceSubClass == USB_INTERFACE_SUBCLASS_BOOT && interface->desc.bInterfaceProtocol == USB_INTERFACE_PROTOCOL_KEYBOARD) { usbhid_set_leds(hid); device_set_wakeup_enable(&dev->dev, 1); } mutex_unlock(&usbhid->mutex); return 0; fail: usb_free_urb(usbhid->urbin); usb_free_urb(usbhid->urbout); usb_free_urb(usbhid->urbctrl); usbhid->urbin = NULL; usbhid->urbout = NULL; usbhid->urbctrl = NULL; hid_free_buffers(dev, hid); mutex_unlock(&usbhid->mutex); return ret; } static void usbhid_stop(struct hid_device *hid) { struct usbhid_device *usbhid = hid->driver_data; if (WARN_ON(!usbhid)) return; if (hid->quirks & HID_QUIRK_ALWAYS_POLL) { clear_bit(HID_IN_POLLING, &usbhid->iofl); usbhid->intf->needs_remote_wakeup = 0; } mutex_lock(&usbhid->mutex); clear_bit(HID_STARTED, &usbhid->iofl); spin_lock_irq(&usbhid->lock); /* Sync with error and led handlers */ set_bit(HID_DISCONNECTED, &usbhid->iofl); while (usbhid->ctrltail != usbhid->ctrlhead) { if (usbhid->ctrl[usbhid->ctrltail].dir == USB_DIR_OUT) { kfree(usbhid->ctrl[usbhid->ctrltail].raw_report); usbhid->ctrl[usbhid->ctrltail].raw_report = NULL; } usbhid->ctrltail = (usbhid->ctrltail + 1) & (HID_CONTROL_FIFO_SIZE - 1); } spin_unlock_irq(&usbhid->lock); usb_kill_urb(usbhid->urbin); usb_kill_urb(usbhid->urbout); usb_kill_urb(usbhid->urbctrl); hid_cancel_delayed_stuff(usbhid); hid->claimed = 0; usb_free_urb(usbhid->urbin); usb_free_urb(usbhid->urbctrl); usb_free_urb(usbhid->urbout); usbhid->urbin = NULL; /* don't mess up next start */ usbhid->urbctrl = NULL; usbhid->urbout = NULL; hid_free_buffers(hid_to_usb_dev(hid), hid); mutex_unlock(&usbhid->mutex); } static int usbhid_power(struct hid_device *hid, int lvl) { struct usbhid_device *usbhid = hid->driver_data; int r = 0; switch (lvl) { case PM_HINT_FULLON: r = usb_autopm_get_interface(usbhid->intf); break; case PM_HINT_NORMAL: usb_autopm_put_interface(usbhid->intf); break; } return r; } static void usbhid_request(struct hid_device *hid, struct hid_report *rep, int reqtype) { switch (reqtype) { case HID_REQ_GET_REPORT: usbhid_submit_report(hid, rep, USB_DIR_IN); break; case HID_REQ_SET_REPORT: usbhid_submit_report(hid, rep, USB_DIR_OUT); break; } } static int usbhid_raw_request(struct hid_device *hid, unsigned char reportnum, __u8 *buf, size_t len, unsigned char rtype, int reqtype) { switch (reqtype) { case HID_REQ_GET_REPORT: return usbhid_get_raw_report(hid, reportnum, buf, len, rtype); case HID_REQ_SET_REPORT: return usbhid_set_raw_report(hid, reportnum, buf, len, rtype); default: return -EIO; } } static int usbhid_idle(struct hid_device *hid, int report, int idle, int reqtype) { struct usb_device *dev = hid_to_usb_dev(hid); struct usb_interface *intf = to_usb_interface(hid->dev.parent); struct usb_host_interface *interface = intf->cur_altsetting; int ifnum = interface->desc.bInterfaceNumber; if (reqtype != HID_REQ_SET_IDLE) return -EINVAL; return hid_set_idle(dev, ifnum, report, idle); } static bool usbhid_may_wakeup(struct hid_device *hid) { struct usb_device *dev = hid_to_usb_dev(hid); return device_may_wakeup(&dev->dev); } static const struct hid_ll_driver usb_hid_driver = { .parse = usbhid_parse, .start = usbhid_start, .stop = usbhid_stop, .open = usbhid_open, .close = usbhid_close, .power = usbhid_power, .request = usbhid_request, .wait = usbhid_wait_io, .raw_request = usbhid_raw_request, .output_report = usbhid_output_report, .idle = usbhid_idle, .may_wakeup = usbhid_may_wakeup, }; bool hid_is_usb(const struct hid_device *hdev) { return hdev->ll_driver == &usb_hid_driver; } EXPORT_SYMBOL_GPL(hid_is_usb); static int usbhid_probe(struct usb_interface *intf, const struct usb_device_id *id) { struct usb_host_interface *interface = intf->cur_altsetting; struct usb_device *dev = interface_to_usbdev(intf); struct usbhid_device *usbhid; struct hid_device *hid; unsigned int n, has_in = 0; size_t len; int ret; dbg_hid("HID probe called for ifnum %d\n", intf->altsetting->desc.bInterfaceNumber); for (n = 0; n < interface->desc.bNumEndpoints; n++) if (usb_endpoint_is_int_in(&interface->endpoint[n].desc)) has_in++; if (!has_in) { hid_err(intf, "couldn't find an input interrupt endpoint\n"); return -ENODEV; } hid = hid_allocate_device(); if (IS_ERR(hid)) return PTR_ERR(hid); usb_set_intfdata(intf, hid); hid->ll_driver = &usb_hid_driver; hid->ff_init = hid_pidff_init; #ifdef CONFIG_USB_HIDDEV hid->hiddev_connect = hiddev_connect; hid->hiddev_disconnect = hiddev_disconnect; hid->hiddev_hid_event = hiddev_hid_event; hid->hiddev_report_event = hiddev_report_event; #endif hid->dev.parent = &intf->dev; device_set_node(&hid->dev, dev_fwnode(&intf->dev)); hid->bus = BUS_USB; hid->vendor = le16_to_cpu(dev->descriptor.idVendor); hid->product = le16_to_cpu(dev->descriptor.idProduct); hid->version = le16_to_cpu(dev->descriptor.bcdDevice); hid->name[0] = 0; if (intf->cur_altsetting->desc.bInterfaceProtocol == USB_INTERFACE_PROTOCOL_MOUSE) hid->type = HID_TYPE_USBMOUSE; else if (intf->cur_altsetting->desc.bInterfaceProtocol == 0) hid->type = HID_TYPE_USBNONE; if (dev->manufacturer) strscpy(hid->name, dev->manufacturer, sizeof(hid->name)); if (dev->product) { if (dev->manufacturer) strlcat(hid->name, " ", sizeof(hid->name)); strlcat(hid->name, dev->product, sizeof(hid->name)); } if (!strlen(hid->name)) snprintf(hid->name, sizeof(hid->name), "HID %04x:%04x", le16_to_cpu(dev->descriptor.idVendor), le16_to_cpu(dev->descriptor.idProduct)); usb_make_path(dev, hid->phys, sizeof(hid->phys)); strlcat(hid->phys, "/input", sizeof(hid->phys)); len = strlen(hid->phys); if (len < sizeof(hid->phys) - 1) snprintf(hid->phys + len, sizeof(hid->phys) - len, "%d", intf->altsetting[0].desc.bInterfaceNumber); if (usb_string(dev, dev->descriptor.iSerialNumber, hid->uniq, 64) <= 0) hid->uniq[0] = 0; usbhid = kzalloc(sizeof(*usbhid), GFP_KERNEL); if (usbhid == NULL) { ret = -ENOMEM; goto err; } hid->driver_data = usbhid; usbhid->hid = hid; usbhid->intf = intf; usbhid->ifnum = interface->desc.bInterfaceNumber; init_waitqueue_head(&usbhid->wait); INIT_WORK(&usbhid->reset_work, hid_reset); timer_setup(&usbhid->io_retry, hid_retry_timeout, 0); spin_lock_init(&usbhid->lock); mutex_init(&usbhid->mutex); ret = hid_add_device(hid); if (ret) { if (ret != -ENODEV) hid_err(intf, "can't add hid device: %d\n", ret); goto err_free; } return 0; err_free: kfree(usbhid); err: hid_destroy_device(hid); return ret; } static void usbhid_disconnect(struct usb_interface *intf) { struct hid_device *hid = usb_get_intfdata(intf); struct usbhid_device *usbhid; if (WARN_ON(!hid)) return; usbhid = hid->driver_data; spin_lock_irq(&usbhid->lock); /* Sync with error and led handlers */ set_bit(HID_DISCONNECTED, &usbhid->iofl); spin_unlock_irq(&usbhid->lock); hid_destroy_device(hid); kfree(usbhid); } static void hid_cancel_delayed_stuff(struct usbhid_device *usbhid) { del_timer_sync(&usbhid->io_retry); cancel_work_sync(&usbhid->reset_work); } static void hid_cease_io(struct usbhid_device *usbhid) { del_timer_sync(&usbhid->io_retry); usb_kill_urb(usbhid->urbin); usb_kill_urb(usbhid->urbctrl); usb_kill_urb(usbhid->urbout); } static void hid_restart_io(struct hid_device *hid) { struct usbhid_device *usbhid = hid->driver_data; int clear_halt = test_bit(HID_CLEAR_HALT, &usbhid->iofl); int reset_pending = test_bit(HID_RESET_PENDING, &usbhid->iofl); spin_lock_irq(&usbhid->lock); clear_bit(HID_SUSPENDED, &usbhid->iofl); usbhid_mark_busy(usbhid); if (clear_halt || reset_pending) schedule_work(&usbhid->reset_work); usbhid->retry_delay = 0; spin_unlock_irq(&usbhid->lock); if (reset_pending || !test_bit(HID_STARTED, &usbhid->iofl)) return; if (!clear_halt) { if (hid_start_in(hid) < 0) hid_io_error(hid); } spin_lock_irq(&usbhid->lock); if (usbhid->urbout && !test_bit(HID_OUT_RUNNING, &usbhid->iofl)) usbhid_restart_out_queue(usbhid); if (!test_bit(HID_CTRL_RUNNING, &usbhid->iofl)) usbhid_restart_ctrl_queue(usbhid); spin_unlock_irq(&usbhid->lock); } /* Treat USB reset pretty much the same as suspend/resume */ static int hid_pre_reset(struct usb_interface *intf) { struct hid_device *hid = usb_get_intfdata(intf); struct usbhid_device *usbhid = hid->driver_data; spin_lock_irq(&usbhid->lock); set_bit(HID_RESET_PENDING, &usbhid->iofl); spin_unlock_irq(&usbhid->lock); hid_cease_io(usbhid); return 0; } /* Same routine used for post_reset and reset_resume */ static int hid_post_reset(struct usb_interface *intf) { struct usb_device *dev = interface_to_usbdev (intf); struct hid_device *hid = usb_get_intfdata(intf); struct usbhid_device *usbhid = hid->driver_data; struct usb_host_interface *interface = intf->cur_altsetting; int status; char *rdesc; /* Fetch and examine the HID report descriptor. If this * has changed, then rebind. Since usbcore's check of the * configuration descriptors passed, we already know that * the size of the HID report descriptor has not changed. */ rdesc = kmalloc(hid->dev_rsize, GFP_KERNEL); if (!rdesc) return -ENOMEM; status = hid_get_class_descriptor(dev, interface->desc.bInterfaceNumber, HID_DT_REPORT, rdesc, hid->dev_rsize); if (status < 0) { dbg_hid("reading report descriptor failed (post_reset)\n"); kfree(rdesc); return status; } status = memcmp(rdesc, hid->dev_rdesc, hid->dev_rsize); kfree(rdesc); if (status != 0) { dbg_hid("report descriptor changed\n"); return -EPERM; } /* No need to do another reset or clear a halted endpoint */ spin_lock_irq(&usbhid->lock); clear_bit(HID_RESET_PENDING, &usbhid->iofl); clear_bit(HID_CLEAR_HALT, &usbhid->iofl); spin_unlock_irq(&usbhid->lock); hid_set_idle(dev, intf->cur_altsetting->desc.bInterfaceNumber, 0, 0); hid_restart_io(hid); return 0; } static int hid_resume_common(struct hid_device *hid, bool driver_suspended) { int status = 0; hid_restart_io(hid); if (driver_suspended) status = hid_driver_resume(hid); return status; } static int hid_suspend(struct usb_interface *intf, pm_message_t message) { struct hid_device *hid = usb_get_intfdata(intf); struct usbhid_device *usbhid = hid->driver_data; int status = 0; bool driver_suspended = false; unsigned int ledcount; if (PMSG_IS_AUTO(message)) { ledcount = hidinput_count_leds(hid); spin_lock_irq(&usbhid->lock); /* Sync with error handler */ if (!test_bit(HID_RESET_PENDING, &usbhid->iofl) && !test_bit(HID_CLEAR_HALT, &usbhid->iofl) && !test_bit(HID_OUT_RUNNING, &usbhid->iofl) && !test_bit(HID_CTRL_RUNNING, &usbhid->iofl) && !test_bit(HID_KEYS_PRESSED, &usbhid->iofl) && (!ledcount || ignoreled)) { set_bit(HID_SUSPENDED, &usbhid->iofl); spin_unlock_irq(&usbhid->lock); status = hid_driver_suspend(hid, message); if (status < 0) goto failed; driver_suspended = true; } else { usbhid_mark_busy(usbhid); spin_unlock_irq(&usbhid->lock); return -EBUSY; } } else { /* TODO: resume() might need to handle suspend failure */ status = hid_driver_suspend(hid, message); driver_suspended = true; spin_lock_irq(&usbhid->lock); set_bit(HID_SUSPENDED, &usbhid->iofl); spin_unlock_irq(&usbhid->lock); if (usbhid_wait_io(hid) < 0) status = -EIO; } hid_cancel_delayed_stuff(usbhid); hid_cease_io(usbhid); if (PMSG_IS_AUTO(message) && test_bit(HID_KEYS_PRESSED, &usbhid->iofl)) { /* lost race against keypresses */ status = -EBUSY; goto failed; } dev_dbg(&intf->dev, "suspend\n"); return status; failed: hid_resume_common(hid, driver_suspended); return status; } static int hid_resume(struct usb_interface *intf) { struct hid_device *hid = usb_get_intfdata (intf); int status; status = hid_resume_common(hid, true); dev_dbg(&intf->dev, "resume status %d\n", status); return 0; } static int hid_reset_resume(struct usb_interface *intf) { struct hid_device *hid = usb_get_intfdata(intf); int status; status = hid_post_reset(intf); if (status >= 0) { int ret = hid_driver_reset_resume(hid); if (ret < 0) status = ret; } return status; } static const struct usb_device_id hid_usb_ids[] = { { .match_flags = USB_DEVICE_ID_MATCH_INT_CLASS, .bInterfaceClass = USB_INTERFACE_CLASS_HID }, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE (usb, hid_usb_ids); static struct usb_driver hid_driver = { .name = "usbhid", .probe = usbhid_probe, .disconnect = usbhid_disconnect, .suspend = pm_ptr(hid_suspend), .resume = pm_ptr(hid_resume), .reset_resume = pm_ptr(hid_reset_resume), .pre_reset = hid_pre_reset, .post_reset = hid_post_reset, .id_table = hid_usb_ids, .supports_autosuspend = 1, }; struct usb_interface *usbhid_find_interface(int minor) { return usb_find_interface(&hid_driver, minor); } static int __init hid_init(void) { int retval; retval = hid_quirks_init(quirks_param, BUS_USB, MAX_USBHID_BOOT_QUIRKS); if (retval) goto usbhid_quirks_init_fail; retval = usb_register(&hid_driver); if (retval) goto usb_register_fail; pr_info(KBUILD_MODNAME ": " DRIVER_DESC "\n"); return 0; usb_register_fail: hid_quirks_exit(BUS_USB); usbhid_quirks_init_fail: return retval; } static void __exit hid_exit(void) { usb_deregister(&hid_driver); hid_quirks_exit(BUS_USB); } module_init(hid_init); module_exit(hid_exit); MODULE_AUTHOR("Andreas Gal"); MODULE_AUTHOR("Vojtech Pavlik"); MODULE_AUTHOR("Jiri Kosina"); MODULE_DESCRIPTION(DRIVER_DESC); MODULE_LICENSE("GPL"); |
| 4 4 4 21 22 9 22 22 22 22 22 15 14 22 22 22 4 4 4 4 4 4 20 1 19 20 20 4 17 20 20 19 20 20 15 21 2 20 20 21 21 21 22 22 22 21 22 3 3 8 8 13 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. */ #include <linux/spinlock.h> #include <linux/completion.h> #include <linux/buffer_head.h> #include <linux/gfs2_ondisk.h> #include <linux/bio.h> #include <linux/posix_acl.h> #include <linux/security.h> #include "gfs2.h" #include "incore.h" #include "bmap.h" #include "glock.h" #include "glops.h" #include "inode.h" #include "log.h" #include "meta_io.h" #include "recovery.h" #include "rgrp.h" #include "util.h" #include "trans.h" #include "dir.h" #include "lops.h" struct workqueue_struct *gfs2_freeze_wq; extern struct workqueue_struct *gfs2_control_wq; static void gfs2_ail_error(struct gfs2_glock *gl, const struct buffer_head *bh) { struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; fs_err(sdp, "AIL buffer %p: blocknr %llu state 0x%08lx mapping %p page " "state 0x%lx\n", bh, (unsigned long long)bh->b_blocknr, bh->b_state, bh->b_folio->mapping, bh->b_folio->flags); fs_err(sdp, "AIL glock %u:%llu mapping %p\n", gl->gl_name.ln_type, gl->gl_name.ln_number, gfs2_glock2aspace(gl)); gfs2_lm(sdp, "AIL error\n"); gfs2_withdraw_delayed(sdp); } /** * __gfs2_ail_flush - remove all buffers for a given lock from the AIL * @gl: the glock * @fsync: set when called from fsync (not all buffers will be clean) * @nr_revokes: Number of buffers to revoke * * None of the buffers should be dirty, locked, or pinned. */ static void __gfs2_ail_flush(struct gfs2_glock *gl, bool fsync, unsigned int nr_revokes) { struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; struct list_head *head = &gl->gl_ail_list; struct gfs2_bufdata *bd, *tmp; struct buffer_head *bh; const unsigned long b_state = (1UL << BH_Dirty)|(1UL << BH_Pinned)|(1UL << BH_Lock); gfs2_log_lock(sdp); spin_lock(&sdp->sd_ail_lock); list_for_each_entry_safe_reverse(bd, tmp, head, bd_ail_gl_list) { if (nr_revokes == 0) break; bh = bd->bd_bh; if (bh->b_state & b_state) { if (fsync) continue; gfs2_ail_error(gl, bh); } gfs2_trans_add_revoke(sdp, bd); nr_revokes--; } GLOCK_BUG_ON(gl, !fsync && atomic_read(&gl->gl_ail_count)); spin_unlock(&sdp->sd_ail_lock); gfs2_log_unlock(sdp); if (gfs2_withdrawing(sdp)) gfs2_withdraw(sdp); } static int gfs2_ail_empty_gl(struct gfs2_glock *gl) { struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; struct gfs2_trans tr; unsigned int revokes; int ret = 0; revokes = atomic_read(&gl->gl_ail_count); if (!revokes) { bool have_revokes; bool log_in_flight; /* * We have nothing on the ail, but there could be revokes on * the sdp revoke queue, in which case, we still want to flush * the log and wait for it to finish. * * If the sdp revoke list is empty too, we might still have an * io outstanding for writing revokes, so we should wait for * it before returning. * * If none of these conditions are true, our revokes are all * flushed and we can return. */ gfs2_log_lock(sdp); have_revokes = !list_empty(&sdp->sd_log_revokes); log_in_flight = atomic_read(&sdp->sd_log_in_flight); gfs2_log_unlock(sdp); if (have_revokes) goto flush; if (log_in_flight) log_flush_wait(sdp); return 0; } memset(&tr, 0, sizeof(tr)); set_bit(TR_ONSTACK, &tr.tr_flags); ret = __gfs2_trans_begin(&tr, sdp, 0, revokes, _RET_IP_); if (ret) { fs_err(sdp, "Transaction error %d: Unable to write revokes.", ret); goto flush; } __gfs2_ail_flush(gl, 0, revokes); gfs2_trans_end(sdp); flush: if (!ret) gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_NORMAL | GFS2_LFC_AIL_EMPTY_GL); return ret; } void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync) { struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; unsigned int revokes = atomic_read(&gl->gl_ail_count); int ret; if (!revokes) return; ret = gfs2_trans_begin(sdp, 0, revokes); if (ret) return; __gfs2_ail_flush(gl, fsync, revokes); gfs2_trans_end(sdp); gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_NORMAL | GFS2_LFC_AIL_FLUSH); } /** * gfs2_rgrp_metasync - sync out the metadata of a resource group * @gl: the glock protecting the resource group * */ static int gfs2_rgrp_metasync(struct gfs2_glock *gl) { struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; struct address_space *metamapping = &sdp->sd_aspace; struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl); const unsigned bsize = sdp->sd_sb.sb_bsize; loff_t start = (rgd->rd_addr * bsize) & PAGE_MASK; loff_t end = PAGE_ALIGN((rgd->rd_addr + rgd->rd_length) * bsize) - 1; int error; filemap_fdatawrite_range(metamapping, start, end); error = filemap_fdatawait_range(metamapping, start, end); WARN_ON_ONCE(error && !gfs2_withdrawing_or_withdrawn(sdp)); mapping_set_error(metamapping, error); if (error) gfs2_io_error(sdp); return error; } /** * rgrp_go_sync - sync out the metadata for this glock * @gl: the glock * * Called when demoting or unlocking an EX glock. We must flush * to disk all dirty buffers/pages relating to this glock, and must not * return to caller to demote/unlock the glock until I/O is complete. */ static int rgrp_go_sync(struct gfs2_glock *gl) { struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl); int error; if (!rgd || !test_and_clear_bit(GLF_DIRTY, &gl->gl_flags)) return 0; GLOCK_BUG_ON(gl, gl->gl_state != LM_ST_EXCLUSIVE); gfs2_log_flush(sdp, gl, GFS2_LOG_HEAD_FLUSH_NORMAL | GFS2_LFC_RGRP_GO_SYNC); error = gfs2_rgrp_metasync(gl); if (!error) error = gfs2_ail_empty_gl(gl); gfs2_free_clones(rgd); return error; } /** * rgrp_go_inval - invalidate the metadata for this glock * @gl: the glock * @flags: * * We never used LM_ST_DEFERRED with resource groups, so that we * should always see the metadata flag set here. * */ static void rgrp_go_inval(struct gfs2_glock *gl, int flags) { struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; struct address_space *mapping = &sdp->sd_aspace; struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl); const unsigned bsize = sdp->sd_sb.sb_bsize; loff_t start, end; if (!rgd) return; start = (rgd->rd_addr * bsize) & PAGE_MASK; end = PAGE_ALIGN((rgd->rd_addr + rgd->rd_length) * bsize) - 1; gfs2_rgrp_brelse(rgd); WARN_ON_ONCE(!(flags & DIO_METADATA)); truncate_inode_pages_range(mapping, start, end); } static void gfs2_rgrp_go_dump(struct seq_file *seq, const struct gfs2_glock *gl, const char *fs_id_buf) { struct gfs2_rgrpd *rgd = gl->gl_object; if (rgd) gfs2_rgrp_dump(seq, rgd, fs_id_buf); } static struct gfs2_inode *gfs2_glock2inode(struct gfs2_glock *gl) { struct gfs2_inode *ip; spin_lock(&gl->gl_lockref.lock); ip = gl->gl_object; if (ip) set_bit(GIF_GLOP_PENDING, &ip->i_flags); spin_unlock(&gl->gl_lockref.lock); return ip; } struct gfs2_rgrpd *gfs2_glock2rgrp(struct gfs2_glock *gl) { struct gfs2_rgrpd *rgd; spin_lock(&gl->gl_lockref.lock); rgd = gl->gl_object; spin_unlock(&gl->gl_lockref.lock); return rgd; } static void gfs2_clear_glop_pending(struct gfs2_inode *ip) { if (!ip) return; clear_bit_unlock(GIF_GLOP_PENDING, &ip->i_flags); wake_up_bit(&ip->i_flags, GIF_GLOP_PENDING); } /** * gfs2_inode_metasync - sync out the metadata of an inode * @gl: the glock protecting the inode * */ int gfs2_inode_metasync(struct gfs2_glock *gl) { struct address_space *metamapping = gfs2_glock2aspace(gl); int error; filemap_fdatawrite(metamapping); error = filemap_fdatawait(metamapping); if (error) gfs2_io_error(gl->gl_name.ln_sbd); return error; } /** * inode_go_sync - Sync the dirty metadata of an inode * @gl: the glock protecting the inode * */ static int inode_go_sync(struct gfs2_glock *gl) { struct gfs2_inode *ip = gfs2_glock2inode(gl); int isreg = ip && S_ISREG(ip->i_inode.i_mode); struct address_space *metamapping = gfs2_glock2aspace(gl); int error = 0, ret; if (isreg) { if (test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags)) unmap_shared_mapping_range(ip->i_inode.i_mapping, 0, 0); inode_dio_wait(&ip->i_inode); } if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags)) goto out; GLOCK_BUG_ON(gl, gl->gl_state != LM_ST_EXCLUSIVE); gfs2_log_flush(gl->gl_name.ln_sbd, gl, GFS2_LOG_HEAD_FLUSH_NORMAL | GFS2_LFC_INODE_GO_SYNC); filemap_fdatawrite(metamapping); if (isreg) { struct address_space *mapping = ip->i_inode.i_mapping; filemap_fdatawrite(mapping); error = filemap_fdatawait(mapping); mapping_set_error(mapping, error); } ret = gfs2_inode_metasync(gl); if (!error) error = ret; ret = gfs2_ail_empty_gl(gl); if (!error) error = ret; /* * Writeback of the data mapping may cause the dirty flag to be set * so we have to clear it again here. */ smp_mb__before_atomic(); clear_bit(GLF_DIRTY, &gl->gl_flags); out: gfs2_clear_glop_pending(ip); return error; } /** * inode_go_inval - prepare a inode glock to be released * @gl: the glock * @flags: * * Normally we invalidate everything, but if we are moving into * LM_ST_DEFERRED from LM_ST_SHARED or LM_ST_EXCLUSIVE then we * can keep hold of the metadata, since it won't have changed. * */ static void inode_go_inval(struct gfs2_glock *gl, int flags) { struct gfs2_inode *ip = gfs2_glock2inode(gl); if (flags & DIO_METADATA) { struct address_space *mapping = gfs2_glock2aspace(gl); truncate_inode_pages(mapping, 0); if (ip) { set_bit(GLF_INSTANTIATE_NEEDED, &gl->gl_flags); forget_all_cached_acls(&ip->i_inode); security_inode_invalidate_secctx(&ip->i_inode); gfs2_dir_hash_inval(ip); } } if (ip == GFS2_I(gl->gl_name.ln_sbd->sd_rindex)) { gfs2_log_flush(gl->gl_name.ln_sbd, NULL, GFS2_LOG_HEAD_FLUSH_NORMAL | GFS2_LFC_INODE_GO_INVAL); gl->gl_name.ln_sbd->sd_rindex_uptodate = 0; } if (ip && S_ISREG(ip->i_inode.i_mode)) truncate_inode_pages(ip->i_inode.i_mapping, 0); gfs2_clear_glop_pending(ip); } static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf) { struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode); const struct gfs2_dinode *str = buf; struct timespec64 atime, iatime; u16 height, depth; umode_t mode = be32_to_cpu(str->di_mode); struct inode *inode = &ip->i_inode; bool is_new = inode->i_state & I_NEW; if (unlikely(ip->i_no_addr != be64_to_cpu(str->di_num.no_addr))) { gfs2_consist_inode(ip); return -EIO; } if (unlikely(!is_new && inode_wrong_type(inode, mode))) { gfs2_consist_inode(ip); return -EIO; } ip->i_no_formal_ino = be64_to_cpu(str->di_num.no_formal_ino); inode->i_mode = mode; if (is_new) { inode->i_rdev = 0; switch (mode & S_IFMT) { case S_IFBLK: case S_IFCHR: inode->i_rdev = MKDEV(be32_to_cpu(str->di_major), be32_to_cpu(str->di_minor)); break; } } i_uid_write(inode, be32_to_cpu(str->di_uid)); i_gid_write(inode, be32_to_cpu(str->di_gid)); set_nlink(inode, be32_to_cpu(str->di_nlink)); i_size_write(inode, be64_to_cpu(str->di_size)); gfs2_set_inode_blocks(inode, be64_to_cpu(str->di_blocks)); atime.tv_sec = be64_to_cpu(str->di_atime); atime.tv_nsec = be32_to_cpu(str->di_atime_nsec); iatime = inode_get_atime(inode); if (timespec64_compare(&iatime, &atime) < 0) inode_set_atime_to_ts(inode, atime); inode_set_mtime(inode, be64_to_cpu(str->di_mtime), be32_to_cpu(str->di_mtime_nsec)); inode_set_ctime(inode, be64_to_cpu(str->di_ctime), be32_to_cpu(str->di_ctime_nsec)); ip->i_goal = be64_to_cpu(str->di_goal_meta); ip->i_generation = be64_to_cpu(str->di_generation); ip->i_diskflags = be32_to_cpu(str->di_flags); ip->i_eattr = be64_to_cpu(str->di_eattr); /* i_diskflags and i_eattr must be set before gfs2_set_inode_flags() */ gfs2_set_inode_flags(inode); height = be16_to_cpu(str->di_height); if (unlikely(height > sdp->sd_max_height)) { gfs2_consist_inode(ip); return -EIO; } ip->i_height = (u8)height; depth = be16_to_cpu(str->di_depth); if (unlikely(depth > GFS2_DIR_MAX_DEPTH)) { gfs2_consist_inode(ip); return -EIO; } ip->i_depth = (u8)depth; ip->i_entries = be32_to_cpu(str->di_entries); if (gfs2_is_stuffed(ip) && inode->i_size > gfs2_max_stuffed_size(ip)) { gfs2_consist_inode(ip); return -EIO; } if (S_ISREG(inode->i_mode)) gfs2_set_aops(inode); return 0; } /** * gfs2_inode_refresh - Refresh the incore copy of the dinode * @ip: The GFS2 inode * * Returns: errno */ static int gfs2_inode_refresh(struct gfs2_inode *ip) { struct buffer_head *dibh; int error; error = gfs2_meta_inode_buffer(ip, &dibh); if (error) return error; error = gfs2_dinode_in(ip, dibh->b_data); brelse(dibh); return error; } /** * inode_go_instantiate - read in an inode if necessary * @gl: The glock * * Returns: errno */ static int inode_go_instantiate(struct gfs2_glock *gl) { struct gfs2_inode *ip = gl->gl_object; struct gfs2_glock *io_gl; int error; if (!ip) /* no inode to populate - read it in later */ return 0; error = gfs2_inode_refresh(ip); if (error) return error; io_gl = ip->i_iopen_gh.gh_gl; io_gl->gl_no_formal_ino = ip->i_no_formal_ino; return 0; } static int inode_go_held(struct gfs2_holder *gh) { struct gfs2_glock *gl = gh->gh_gl; struct gfs2_inode *ip = gl->gl_object; int error = 0; if (!ip) /* no inode to populate - read it in later */ return 0; if (gh->gh_state != LM_ST_DEFERRED) inode_dio_wait(&ip->i_inode); if ((ip->i_diskflags & GFS2_DIF_TRUNC_IN_PROG) && (gl->gl_state == LM_ST_EXCLUSIVE) && (gh->gh_state == LM_ST_EXCLUSIVE)) error = gfs2_truncatei_resume(ip); return error; } /** * inode_go_dump - print information about an inode * @seq: The iterator * @gl: The glock * @fs_id_buf: file system id (may be empty) * */ static void inode_go_dump(struct seq_file *seq, const struct gfs2_glock *gl, const char *fs_id_buf) { struct gfs2_inode *ip = gl->gl_object; const struct inode *inode = &ip->i_inode; if (ip == NULL) return; gfs2_print_dbg(seq, "%s I: n:%llu/%llu t:%u f:0x%02lx d:0x%08x s:%llu " "p:%lu\n", fs_id_buf, (unsigned long long)ip->i_no_formal_ino, (unsigned long long)ip->i_no_addr, IF2DT(inode->i_mode), ip->i_flags, (unsigned int)ip->i_diskflags, (unsigned long long)i_size_read(inode), inode->i_data.nrpages); } /** * freeze_go_callback - A cluster node is requesting a freeze * @gl: the glock * @remote: true if this came from a different cluster node */ static void freeze_go_callback(struct gfs2_glock *gl, bool remote) { struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; struct super_block *sb = sdp->sd_vfs; if (!remote || (gl->gl_state != LM_ST_SHARED && gl->gl_state != LM_ST_UNLOCKED) || gl->gl_demote_state != LM_ST_UNLOCKED) return; /* * Try to get an active super block reference to prevent racing with * unmount (see super_trylock_shared()). But note that unmount isn't * the only place where a write lock on s_umount is taken, and we can * fail here because of things like remount as well. */ if (down_read_trylock(&sb->s_umount)) { atomic_inc(&sb->s_active); up_read(&sb->s_umount); if (!queue_work(gfs2_freeze_wq, &sdp->sd_freeze_work)) deactivate_super(sb); } } /** * freeze_go_xmote_bh - After promoting/demoting the freeze glock * @gl: the glock */ static int freeze_go_xmote_bh(struct gfs2_glock *gl) { struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; struct gfs2_inode *ip = GFS2_I(sdp->sd_jdesc->jd_inode); struct gfs2_glock *j_gl = ip->i_gl; struct gfs2_log_header_host head; int error; if (test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) { j_gl->gl_ops->go_inval(j_gl, DIO_METADATA); error = gfs2_find_jhead(sdp->sd_jdesc, &head, false); if (gfs2_assert_withdraw_delayed(sdp, !error)) return error; if (gfs2_assert_withdraw_delayed(sdp, head.lh_flags & GFS2_LOG_HEAD_UNMOUNT)) return -EIO; sdp->sd_log_sequence = head.lh_sequence + 1; gfs2_log_pointers_init(sdp, head.lh_blkno); } return 0; } /** * iopen_go_callback - schedule the dcache entry for the inode to be deleted * @gl: the glock * @remote: true if this came from a different cluster node * * gl_lockref.lock lock is held while calling this */ static void iopen_go_callback(struct gfs2_glock *gl, bool remote) { struct gfs2_inode *ip = gl->gl_object; struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; if (!remote || sb_rdonly(sdp->sd_vfs) || test_bit(SDF_KILL, &sdp->sd_flags)) return; if (gl->gl_demote_state == LM_ST_UNLOCKED && gl->gl_state == LM_ST_SHARED && ip) { gl->gl_lockref.count++; if (!gfs2_queue_try_to_evict(gl)) gl->gl_lockref.count--; } } /** * inode_go_unlocked - wake up anyone waiting for dlm's unlock ast * @gl: glock being unlocked * * For now, this is only used for the journal inode glock. In withdraw * situations, we need to wait for the glock to be unlocked so that we know * other nodes may proceed with recovery / journal replay. */ static void inode_go_unlocked(struct gfs2_glock *gl) { /* Note that we cannot reference gl_object because it's already set * to NULL by this point in its lifecycle. */ if (!test_bit(GLF_UNLOCKED, &gl->gl_flags)) return; clear_bit_unlock(GLF_UNLOCKED, &gl->gl_flags); wake_up_bit(&gl->gl_flags, GLF_UNLOCKED); } /** * nondisk_go_callback - used to signal when a node did a withdraw * @gl: the nondisk glock * @remote: true if this came from a different cluster node * */ static void nondisk_go_callback(struct gfs2_glock *gl, bool remote) { struct gfs2_sbd *sdp = gl->gl_name.ln_sbd; /* Ignore the callback unless it's from another node, and it's the live lock. */ if (!remote || gl->gl_name.ln_number != GFS2_LIVE_LOCK) return; /* First order of business is to cancel the demote request. We don't * really want to demote a nondisk glock. At best it's just to inform * us of another node's withdraw. We'll keep it in SH mode. */ clear_bit(GLF_DEMOTE, &gl->gl_flags); clear_bit(GLF_PENDING_DEMOTE, &gl->gl_flags); /* Ignore the unlock if we're withdrawn, unmounting, or in recovery. */ if (test_bit(SDF_NORECOVERY, &sdp->sd_flags) || test_bit(SDF_WITHDRAWN, &sdp->sd_flags) || test_bit(SDF_REMOTE_WITHDRAW, &sdp->sd_flags)) return; /* We only care when a node wants us to unlock, because that means * they want a journal recovered. */ if (gl->gl_demote_state != LM_ST_UNLOCKED) return; if (sdp->sd_args.ar_spectator) { fs_warn(sdp, "Spectator node cannot recover journals.\n"); return; } fs_warn(sdp, "Some node has withdrawn; checking for recovery.\n"); set_bit(SDF_REMOTE_WITHDRAW, &sdp->sd_flags); /* * We can't call remote_withdraw directly here or gfs2_recover_journal * because this is called from the glock unlock function and the * remote_withdraw needs to enqueue and dequeue the same "live" glock * we were called from. So we queue it to the control work queue in * lock_dlm. */ queue_delayed_work(gfs2_control_wq, &sdp->sd_control_work, 0); } const struct gfs2_glock_operations gfs2_meta_glops = { .go_type = LM_TYPE_META, .go_flags = GLOF_NONDISK, }; const struct gfs2_glock_operations gfs2_inode_glops = { .go_sync = inode_go_sync, .go_inval = inode_go_inval, .go_instantiate = inode_go_instantiate, .go_held = inode_go_held, .go_dump = inode_go_dump, .go_type = LM_TYPE_INODE, .go_flags = GLOF_ASPACE | GLOF_LVB, .go_unlocked = inode_go_unlocked, }; const struct gfs2_glock_operations gfs2_rgrp_glops = { .go_sync = rgrp_go_sync, .go_inval = rgrp_go_inval, .go_instantiate = gfs2_rgrp_go_instantiate, .go_dump = gfs2_rgrp_go_dump, .go_type = LM_TYPE_RGRP, .go_flags = GLOF_LVB, }; const struct gfs2_glock_operations gfs2_freeze_glops = { .go_xmote_bh = freeze_go_xmote_bh, .go_callback = freeze_go_callback, .go_type = LM_TYPE_NONDISK, .go_flags = GLOF_NONDISK, }; const struct gfs2_glock_operations gfs2_iopen_glops = { .go_type = LM_TYPE_IOPEN, .go_callback = iopen_go_callback, .go_dump = inode_go_dump, .go_flags = GLOF_NONDISK, .go_subclass = 1, }; const struct gfs2_glock_operations gfs2_flock_glops = { .go_type = LM_TYPE_FLOCK, .go_flags = GLOF_NONDISK, }; const struct gfs2_glock_operations gfs2_nondisk_glops = { .go_type = LM_TYPE_NONDISK, .go_flags = GLOF_NONDISK, .go_callback = nondisk_go_callback, }; const struct gfs2_glock_operations gfs2_quota_glops = { .go_type = LM_TYPE_QUOTA, .go_flags = GLOF_LVB | GLOF_NONDISK, }; const struct gfs2_glock_operations gfs2_journal_glops = { .go_type = LM_TYPE_JOURNAL, .go_flags = GLOF_NONDISK, }; const struct gfs2_glock_operations *gfs2_glops_list[] = { [LM_TYPE_META] = &gfs2_meta_glops, [LM_TYPE_INODE] = &gfs2_inode_glops, [LM_TYPE_RGRP] = &gfs2_rgrp_glops, [LM_TYPE_IOPEN] = &gfs2_iopen_glops, [LM_TYPE_FLOCK] = &gfs2_flock_glops, [LM_TYPE_NONDISK] = &gfs2_nondisk_glops, [LM_TYPE_QUOTA] = &gfs2_quota_glops, [LM_TYPE_JOURNAL] = &gfs2_journal_glops, }; |
| 97 97 94 100 61 100 102 83 54 102 42 42 38 7 37 1 35 36 36 36 36 36 36 36 36 36 37 35 37 34 37 37 60 31 31 31 18 18 99 97 85 85 82 23 80 79 79 81 79 50 49 80 63 63 25 79 84 84 40 40 40 40 39 27 39 38 39 40 40 16 16 15 16 16 45 44 44 28 3 28 28 25 45 40 40 63 59 51 51 36 51 50 64 3 29 26 32 34 15 7 15 2 13 12 51 16 16 12 16 15 4 2 4 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * OSS compatible sequencer driver * * MIDI device handlers * * Copyright (C) 1998,99 Takashi Iwai <tiwai@suse.de> */ #include <sound/asoundef.h> #include "seq_oss_midi.h" #include "seq_oss_readq.h" #include "seq_oss_timer.h" #include "seq_oss_event.h" #include <sound/seq_midi_event.h> #include "../seq_lock.h" #include <linux/init.h> #include <linux/slab.h> #include <linux/nospec.h> /* * constants */ #define SNDRV_SEQ_OSS_MAX_MIDI_NAME 30 /* * definition of midi device record */ struct seq_oss_midi { int seq_device; /* device number */ int client; /* sequencer client number */ int port; /* sequencer port number */ unsigned int flags; /* port capability */ int opened; /* flag for opening */ unsigned char name[SNDRV_SEQ_OSS_MAX_MIDI_NAME]; struct snd_midi_event *coder; /* MIDI event coder */ struct seq_oss_devinfo *devinfo; /* assigned OSSseq device */ snd_use_lock_t use_lock; struct mutex open_mutex; }; /* * midi device table */ static int max_midi_devs; static struct seq_oss_midi *midi_devs[SNDRV_SEQ_OSS_MAX_MIDI_DEVS]; static DEFINE_SPINLOCK(register_lock); /* * prototypes */ static struct seq_oss_midi *get_mdev(int dev); static struct seq_oss_midi *get_mididev(struct seq_oss_devinfo *dp, int dev); static int send_synth_event(struct seq_oss_devinfo *dp, struct snd_seq_event *ev, int dev); static int send_midi_event(struct seq_oss_devinfo *dp, struct snd_seq_event *ev, struct seq_oss_midi *mdev); /* * look up the existing ports * this looks a very exhausting job. */ int snd_seq_oss_midi_lookup_ports(int client) { struct snd_seq_client_info *clinfo __free(kfree) = NULL; struct snd_seq_port_info *pinfo __free(kfree) = NULL; clinfo = kzalloc(sizeof(*clinfo), GFP_KERNEL); pinfo = kzalloc(sizeof(*pinfo), GFP_KERNEL); if (!clinfo || !pinfo) return -ENOMEM; clinfo->client = -1; while (snd_seq_kernel_client_ctl(client, SNDRV_SEQ_IOCTL_QUERY_NEXT_CLIENT, clinfo) == 0) { if (clinfo->client == client) continue; /* ignore myself */ pinfo->addr.client = clinfo->client; pinfo->addr.port = -1; while (snd_seq_kernel_client_ctl(client, SNDRV_SEQ_IOCTL_QUERY_NEXT_PORT, pinfo) == 0) snd_seq_oss_midi_check_new_port(pinfo); } return 0; } /* */ static struct seq_oss_midi * get_mdev(int dev) { struct seq_oss_midi *mdev; unsigned long flags; spin_lock_irqsave(®ister_lock, flags); mdev = midi_devs[dev]; if (mdev) snd_use_lock_use(&mdev->use_lock); spin_unlock_irqrestore(®ister_lock, flags); return mdev; } /* * look for the identical slot */ static struct seq_oss_midi * find_slot(int client, int port) { int i; struct seq_oss_midi *mdev; unsigned long flags; spin_lock_irqsave(®ister_lock, flags); for (i = 0; i < max_midi_devs; i++) { mdev = midi_devs[i]; if (mdev && mdev->client == client && mdev->port == port) { /* found! */ snd_use_lock_use(&mdev->use_lock); spin_unlock_irqrestore(®ister_lock, flags); return mdev; } } spin_unlock_irqrestore(®ister_lock, flags); return NULL; } #define PERM_WRITE (SNDRV_SEQ_PORT_CAP_WRITE|SNDRV_SEQ_PORT_CAP_SUBS_WRITE) #define PERM_READ (SNDRV_SEQ_PORT_CAP_READ|SNDRV_SEQ_PORT_CAP_SUBS_READ) /* * register a new port if it doesn't exist yet */ int snd_seq_oss_midi_check_new_port(struct snd_seq_port_info *pinfo) { int i; struct seq_oss_midi *mdev; unsigned long flags; /* the port must include generic midi */ if (! (pinfo->type & SNDRV_SEQ_PORT_TYPE_MIDI_GENERIC)) return 0; /* either read or write subscribable */ if ((pinfo->capability & PERM_WRITE) != PERM_WRITE && (pinfo->capability & PERM_READ) != PERM_READ) return 0; /* * look for the identical slot */ mdev = find_slot(pinfo->addr.client, pinfo->addr.port); if (mdev) { /* already exists */ snd_use_lock_free(&mdev->use_lock); return 0; } /* * allocate midi info record */ mdev = kzalloc(sizeof(*mdev), GFP_KERNEL); if (!mdev) return -ENOMEM; /* copy the port information */ mdev->client = pinfo->addr.client; mdev->port = pinfo->addr.port; mdev->flags = pinfo->capability; mdev->opened = 0; snd_use_lock_init(&mdev->use_lock); mutex_init(&mdev->open_mutex); /* copy and truncate the name of synth device */ strscpy(mdev->name, pinfo->name, sizeof(mdev->name)); /* create MIDI coder */ if (snd_midi_event_new(MAX_MIDI_EVENT_BUF, &mdev->coder) < 0) { pr_err("ALSA: seq_oss: can't malloc midi coder\n"); kfree(mdev); return -ENOMEM; } /* OSS sequencer adds running status to all sequences */ snd_midi_event_no_status(mdev->coder, 1); /* * look for en empty slot */ spin_lock_irqsave(®ister_lock, flags); for (i = 0; i < max_midi_devs; i++) { if (midi_devs[i] == NULL) break; } if (i >= max_midi_devs) { if (max_midi_devs >= SNDRV_SEQ_OSS_MAX_MIDI_DEVS) { spin_unlock_irqrestore(®ister_lock, flags); snd_midi_event_free(mdev->coder); kfree(mdev); return -ENOMEM; } max_midi_devs++; } mdev->seq_device = i; midi_devs[mdev->seq_device] = mdev; spin_unlock_irqrestore(®ister_lock, flags); return 0; } /* * release the midi device if it was registered */ int snd_seq_oss_midi_check_exit_port(int client, int port) { struct seq_oss_midi *mdev; unsigned long flags; int index; mdev = find_slot(client, port); if (mdev) { spin_lock_irqsave(®ister_lock, flags); midi_devs[mdev->seq_device] = NULL; spin_unlock_irqrestore(®ister_lock, flags); snd_use_lock_free(&mdev->use_lock); snd_use_lock_sync(&mdev->use_lock); snd_midi_event_free(mdev->coder); kfree(mdev); } spin_lock_irqsave(®ister_lock, flags); for (index = max_midi_devs - 1; index >= 0; index--) { if (midi_devs[index]) break; } max_midi_devs = index + 1; spin_unlock_irqrestore(®ister_lock, flags); return 0; } /* * release the midi device if it was registered */ void snd_seq_oss_midi_clear_all(void) { int i; struct seq_oss_midi *mdev; unsigned long flags; spin_lock_irqsave(®ister_lock, flags); for (i = 0; i < max_midi_devs; i++) { mdev = midi_devs[i]; if (mdev) { snd_midi_event_free(mdev->coder); kfree(mdev); midi_devs[i] = NULL; } } max_midi_devs = 0; spin_unlock_irqrestore(®ister_lock, flags); } /* * set up midi tables */ void snd_seq_oss_midi_setup(struct seq_oss_devinfo *dp) { spin_lock_irq(®ister_lock); dp->max_mididev = max_midi_devs; spin_unlock_irq(®ister_lock); } /* * clean up midi tables */ void snd_seq_oss_midi_cleanup(struct seq_oss_devinfo *dp) { int i; for (i = 0; i < dp->max_mididev; i++) snd_seq_oss_midi_close(dp, i); dp->max_mididev = 0; } /* * open all midi devices. ignore errors. */ void snd_seq_oss_midi_open_all(struct seq_oss_devinfo *dp, int file_mode) { int i; for (i = 0; i < dp->max_mididev; i++) snd_seq_oss_midi_open(dp, i, file_mode); } /* * get the midi device information */ static struct seq_oss_midi * get_mididev(struct seq_oss_devinfo *dp, int dev) { if (dev < 0 || dev >= dp->max_mididev) return NULL; dev = array_index_nospec(dev, dp->max_mididev); return get_mdev(dev); } /* * open the midi device if not opened yet */ int snd_seq_oss_midi_open(struct seq_oss_devinfo *dp, int dev, int fmode) { int perm; struct seq_oss_midi *mdev; struct snd_seq_port_subscribe subs; int err; mdev = get_mididev(dp, dev); if (!mdev) return -ENODEV; mutex_lock(&mdev->open_mutex); /* already used? */ if (mdev->opened && mdev->devinfo != dp) { err = -EBUSY; goto unlock; } perm = 0; if (is_write_mode(fmode)) perm |= PERM_WRITE; if (is_read_mode(fmode)) perm |= PERM_READ; perm &= mdev->flags; if (perm == 0) { err = -ENXIO; goto unlock; } /* already opened? */ if ((mdev->opened & perm) == perm) { err = 0; goto unlock; } perm &= ~mdev->opened; memset(&subs, 0, sizeof(subs)); if (perm & PERM_WRITE) { subs.sender = dp->addr; subs.dest.client = mdev->client; subs.dest.port = mdev->port; if (snd_seq_kernel_client_ctl(dp->cseq, SNDRV_SEQ_IOCTL_SUBSCRIBE_PORT, &subs) >= 0) mdev->opened |= PERM_WRITE; } if (perm & PERM_READ) { subs.sender.client = mdev->client; subs.sender.port = mdev->port; subs.dest = dp->addr; subs.flags = SNDRV_SEQ_PORT_SUBS_TIMESTAMP; subs.queue = dp->queue; /* queue for timestamps */ if (snd_seq_kernel_client_ctl(dp->cseq, SNDRV_SEQ_IOCTL_SUBSCRIBE_PORT, &subs) >= 0) mdev->opened |= PERM_READ; } if (! mdev->opened) { err = -ENXIO; goto unlock; } mdev->devinfo = dp; err = 0; unlock: mutex_unlock(&mdev->open_mutex); snd_use_lock_free(&mdev->use_lock); return err; } /* * close the midi device if already opened */ int snd_seq_oss_midi_close(struct seq_oss_devinfo *dp, int dev) { struct seq_oss_midi *mdev; struct snd_seq_port_subscribe subs; mdev = get_mididev(dp, dev); if (!mdev) return -ENODEV; mutex_lock(&mdev->open_mutex); if (!mdev->opened || mdev->devinfo != dp) goto unlock; memset(&subs, 0, sizeof(subs)); if (mdev->opened & PERM_WRITE) { subs.sender = dp->addr; subs.dest.client = mdev->client; subs.dest.port = mdev->port; snd_seq_kernel_client_ctl(dp->cseq, SNDRV_SEQ_IOCTL_UNSUBSCRIBE_PORT, &subs); } if (mdev->opened & PERM_READ) { subs.sender.client = mdev->client; subs.sender.port = mdev->port; subs.dest = dp->addr; snd_seq_kernel_client_ctl(dp->cseq, SNDRV_SEQ_IOCTL_UNSUBSCRIBE_PORT, &subs); } mdev->opened = 0; mdev->devinfo = NULL; unlock: mutex_unlock(&mdev->open_mutex); snd_use_lock_free(&mdev->use_lock); return 0; } /* * change seq capability flags to file mode flags */ int snd_seq_oss_midi_filemode(struct seq_oss_devinfo *dp, int dev) { struct seq_oss_midi *mdev; int mode; mdev = get_mididev(dp, dev); if (!mdev) return 0; mode = 0; if (mdev->opened & PERM_WRITE) mode |= SNDRV_SEQ_OSS_FILE_WRITE; if (mdev->opened & PERM_READ) mode |= SNDRV_SEQ_OSS_FILE_READ; snd_use_lock_free(&mdev->use_lock); return mode; } /* * reset the midi device and close it: * so far, only close the device. */ void snd_seq_oss_midi_reset(struct seq_oss_devinfo *dp, int dev) { struct seq_oss_midi *mdev; mdev = get_mididev(dp, dev); if (!mdev) return; if (! mdev->opened) { snd_use_lock_free(&mdev->use_lock); return; } if (mdev->opened & PERM_WRITE) { struct snd_seq_event ev; int c; memset(&ev, 0, sizeof(ev)); ev.dest.client = mdev->client; ev.dest.port = mdev->port; ev.queue = dp->queue; ev.source.port = dp->port; if (dp->seq_mode == SNDRV_SEQ_OSS_MODE_SYNTH) { ev.type = SNDRV_SEQ_EVENT_SENSING; snd_seq_oss_dispatch(dp, &ev, 0, 0); } for (c = 0; c < 16; c++) { ev.type = SNDRV_SEQ_EVENT_CONTROLLER; ev.data.control.channel = c; ev.data.control.param = MIDI_CTL_ALL_NOTES_OFF; snd_seq_oss_dispatch(dp, &ev, 0, 0); if (dp->seq_mode == SNDRV_SEQ_OSS_MODE_MUSIC) { ev.data.control.param = MIDI_CTL_RESET_CONTROLLERS; snd_seq_oss_dispatch(dp, &ev, 0, 0); ev.type = SNDRV_SEQ_EVENT_PITCHBEND; ev.data.control.value = 0; snd_seq_oss_dispatch(dp, &ev, 0, 0); } } } // snd_seq_oss_midi_close(dp, dev); snd_use_lock_free(&mdev->use_lock); } /* * get client/port of the specified MIDI device */ void snd_seq_oss_midi_get_addr(struct seq_oss_devinfo *dp, int dev, struct snd_seq_addr *addr) { struct seq_oss_midi *mdev; mdev = get_mididev(dp, dev); if (!mdev) return; addr->client = mdev->client; addr->port = mdev->port; snd_use_lock_free(&mdev->use_lock); } /* * input callback - this can be atomic */ int snd_seq_oss_midi_input(struct snd_seq_event *ev, int direct, void *private_data) { struct seq_oss_devinfo *dp = (struct seq_oss_devinfo *)private_data; struct seq_oss_midi *mdev; int rc; if (dp->readq == NULL) return 0; mdev = find_slot(ev->source.client, ev->source.port); if (!mdev) return 0; if (! (mdev->opened & PERM_READ)) { snd_use_lock_free(&mdev->use_lock); return 0; } if (dp->seq_mode == SNDRV_SEQ_OSS_MODE_MUSIC) rc = send_synth_event(dp, ev, mdev->seq_device); else rc = send_midi_event(dp, ev, mdev); snd_use_lock_free(&mdev->use_lock); return rc; } /* * convert ALSA sequencer event to OSS synth event */ static int send_synth_event(struct seq_oss_devinfo *dp, struct snd_seq_event *ev, int dev) { union evrec ossev; memset(&ossev, 0, sizeof(ossev)); switch (ev->type) { case SNDRV_SEQ_EVENT_NOTEON: ossev.v.cmd = MIDI_NOTEON; break; case SNDRV_SEQ_EVENT_NOTEOFF: ossev.v.cmd = MIDI_NOTEOFF; break; case SNDRV_SEQ_EVENT_KEYPRESS: ossev.v.cmd = MIDI_KEY_PRESSURE; break; case SNDRV_SEQ_EVENT_CONTROLLER: ossev.l.cmd = MIDI_CTL_CHANGE; break; case SNDRV_SEQ_EVENT_PGMCHANGE: ossev.l.cmd = MIDI_PGM_CHANGE; break; case SNDRV_SEQ_EVENT_CHANPRESS: ossev.l.cmd = MIDI_CHN_PRESSURE; break; case SNDRV_SEQ_EVENT_PITCHBEND: ossev.l.cmd = MIDI_PITCH_BEND; break; default: return 0; /* not supported */ } ossev.v.dev = dev; switch (ev->type) { case SNDRV_SEQ_EVENT_NOTEON: case SNDRV_SEQ_EVENT_NOTEOFF: case SNDRV_SEQ_EVENT_KEYPRESS: ossev.v.code = EV_CHN_VOICE; ossev.v.note = ev->data.note.note; ossev.v.parm = ev->data.note.velocity; ossev.v.chn = ev->data.note.channel; break; case SNDRV_SEQ_EVENT_CONTROLLER: case SNDRV_SEQ_EVENT_PGMCHANGE: case SNDRV_SEQ_EVENT_CHANPRESS: ossev.l.code = EV_CHN_COMMON; ossev.l.p1 = ev->data.control.param; ossev.l.val = ev->data.control.value; ossev.l.chn = ev->data.control.channel; break; case SNDRV_SEQ_EVENT_PITCHBEND: ossev.l.code = EV_CHN_COMMON; ossev.l.val = ev->data.control.value + 8192; ossev.l.chn = ev->data.control.channel; break; } snd_seq_oss_readq_put_timestamp(dp->readq, ev->time.tick, dp->seq_mode); snd_seq_oss_readq_put_event(dp->readq, &ossev); return 0; } /* * decode event and send MIDI bytes to read queue */ static int send_midi_event(struct seq_oss_devinfo *dp, struct snd_seq_event *ev, struct seq_oss_midi *mdev) { char msg[32]; int len; snd_seq_oss_readq_put_timestamp(dp->readq, ev->time.tick, dp->seq_mode); if (!dp->timer->running) len = snd_seq_oss_timer_start(dp->timer); if (ev->type == SNDRV_SEQ_EVENT_SYSEX) { snd_seq_oss_readq_sysex(dp->readq, mdev->seq_device, ev); snd_midi_event_reset_decode(mdev->coder); } else { len = snd_midi_event_decode(mdev->coder, msg, sizeof(msg), ev); if (len > 0) snd_seq_oss_readq_puts(dp->readq, mdev->seq_device, msg, len); } return 0; } /* * dump midi data * return 0 : enqueued * non-zero : invalid - ignored */ int snd_seq_oss_midi_putc(struct seq_oss_devinfo *dp, int dev, unsigned char c, struct snd_seq_event *ev) { struct seq_oss_midi *mdev; mdev = get_mididev(dp, dev); if (!mdev) return -ENODEV; if (snd_midi_event_encode_byte(mdev->coder, c, ev)) { snd_seq_oss_fill_addr(dp, ev, mdev->client, mdev->port); snd_use_lock_free(&mdev->use_lock); return 0; } snd_use_lock_free(&mdev->use_lock); return -EINVAL; } /* * create OSS compatible midi_info record */ int snd_seq_oss_midi_make_info(struct seq_oss_devinfo *dp, int dev, struct midi_info *inf) { struct seq_oss_midi *mdev; mdev = get_mididev(dp, dev); if (!mdev) return -ENXIO; inf->device = dev; inf->dev_type = 0; /* FIXME: ?? */ inf->capabilities = 0; /* FIXME: ?? */ strscpy(inf->name, mdev->name, sizeof(inf->name)); snd_use_lock_free(&mdev->use_lock); return 0; } #ifdef CONFIG_SND_PROC_FS /* * proc interface */ static char * capmode_str(int val) { val &= PERM_READ|PERM_WRITE; if (val == (PERM_READ|PERM_WRITE)) return "read/write"; else if (val == PERM_READ) return "read"; else if (val == PERM_WRITE) return "write"; else return "none"; } void snd_seq_oss_midi_info_read(struct snd_info_buffer *buf) { int i; struct seq_oss_midi *mdev; snd_iprintf(buf, "\nNumber of MIDI devices: %d\n", max_midi_devs); for (i = 0; i < max_midi_devs; i++) { snd_iprintf(buf, "\nmidi %d: ", i); mdev = get_mdev(i); if (mdev == NULL) { snd_iprintf(buf, "*empty*\n"); continue; } snd_iprintf(buf, "[%s] ALSA port %d:%d\n", mdev->name, mdev->client, mdev->port); snd_iprintf(buf, " capability %s / opened %s\n", capmode_str(mdev->flags), capmode_str(mdev->opened)); snd_use_lock_free(&mdev->use_lock); } } #endif /* CONFIG_SND_PROC_FS */ |
| 435 459 456 457 463 464 461 463 457 439 457 459 459 433 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 | /* * kmod - the kernel module loader * * Copyright (C) 2023 Luis Chamberlain <mcgrof@kernel.org> */ #include <linux/module.h> #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/binfmts.h> #include <linux/syscalls.h> #include <linux/unistd.h> #include <linux/kmod.h> #include <linux/slab.h> #include <linux/completion.h> #include <linux/cred.h> #include <linux/file.h> #include <linux/workqueue.h> #include <linux/security.h> #include <linux/mount.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/resource.h> #include <linux/notifier.h> #include <linux/suspend.h> #include <linux/rwsem.h> #include <linux/ptrace.h> #include <linux/async.h> #include <linux/uaccess.h> #include <trace/events/module.h> #include "internal.h" /* * Assuming: * * threads = div64_u64((u64) totalram_pages * (u64) PAGE_SIZE, * (u64) THREAD_SIZE * 8UL); * * If you need less than 50 threads would mean we're dealing with systems * smaller than 3200 pages. This assumes you are capable of having ~13M memory, * and this would only be an upper limit, after which the OOM killer would take * effect. Systems like these are very unlikely if modules are enabled. */ #define MAX_KMOD_CONCURRENT 50 static DEFINE_SEMAPHORE(kmod_concurrent_max, MAX_KMOD_CONCURRENT); /* * This is a restriction on having *all* MAX_KMOD_CONCURRENT threads * running at the same time without returning. When this happens we * believe you've somehow ended up with a recursive module dependency * creating a loop. * * We have no option but to fail. * * Userspace should proactively try to detect and prevent these. */ #define MAX_KMOD_ALL_BUSY_TIMEOUT 5 /* modprobe_path is set via /proc/sys. */ char modprobe_path[KMOD_PATH_LEN] = CONFIG_MODPROBE_PATH; static void free_modprobe_argv(struct subprocess_info *info) { kfree(info->argv[3]); /* check call_modprobe() */ kfree(info->argv); } static int call_modprobe(char *orig_module_name, int wait) { struct subprocess_info *info; static char *envp[] = { "HOME=/", "TERM=linux", "PATH=/sbin:/usr/sbin:/bin:/usr/bin", NULL }; char *module_name; int ret; char **argv = kmalloc(sizeof(char *[5]), GFP_KERNEL); if (!argv) goto out; module_name = kstrdup(orig_module_name, GFP_KERNEL); if (!module_name) goto free_argv; argv[0] = modprobe_path; argv[1] = "-q"; argv[2] = "--"; argv[3] = module_name; /* check free_modprobe_argv() */ argv[4] = NULL; info = call_usermodehelper_setup(modprobe_path, argv, envp, GFP_KERNEL, NULL, free_modprobe_argv, NULL); if (!info) goto free_module_name; ret = call_usermodehelper_exec(info, wait | UMH_KILLABLE); kmod_dup_request_announce(orig_module_name, ret); return ret; free_module_name: kfree(module_name); free_argv: kfree(argv); out: kmod_dup_request_announce(orig_module_name, -ENOMEM); return -ENOMEM; } /** * __request_module - try to load a kernel module * @wait: wait (or not) for the operation to complete * @fmt: printf style format string for the name of the module * @...: arguments as specified in the format string * * Load a module using the user mode module loader. The function returns * zero on success or a negative errno code or positive exit code from * "modprobe" on failure. Note that a successful module load does not mean * the module did not then unload and exit on an error of its own. Callers * must check that the service they requested is now available not blindly * invoke it. * * If module auto-loading support is disabled then this function * simply returns -ENOENT. */ int __request_module(bool wait, const char *fmt, ...) { va_list args; char module_name[MODULE_NAME_LEN]; int ret, dup_ret; /* * We don't allow synchronous module loading from async. Module * init may invoke async_synchronize_full() which will end up * waiting for this task which already is waiting for the module * loading to complete, leading to a deadlock. */ WARN_ON_ONCE(wait && current_is_async()); if (!modprobe_path[0]) return -ENOENT; va_start(args, fmt); ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args); va_end(args); if (ret >= MODULE_NAME_LEN) return -ENAMETOOLONG; ret = security_kernel_module_request(module_name); if (ret) return ret; ret = down_timeout(&kmod_concurrent_max, MAX_KMOD_ALL_BUSY_TIMEOUT * HZ); if (ret) { pr_warn_ratelimited("request_module: modprobe %s cannot be processed, kmod busy with %d threads for more than %d seconds now", module_name, MAX_KMOD_CONCURRENT, MAX_KMOD_ALL_BUSY_TIMEOUT); return ret; } trace_module_request(module_name, wait, _RET_IP_); if (kmod_dup_request_exists_wait(module_name, wait, &dup_ret)) { ret = dup_ret; goto out; } ret = call_modprobe(module_name, wait ? UMH_WAIT_PROC : UMH_WAIT_EXEC); out: up(&kmod_concurrent_max); return ret; } EXPORT_SYMBOL(__request_module); |
| 17 2 17 2 19 19 19 19 19 19 19 19 18 19 19 19 11 11 10 11 11 9 2 2 2 2 2 2 2 17 17 17 16 17 16 16 17 11 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 | /* * Non-physical true random number generator based on timing jitter -- * Linux Kernel Crypto API specific code * * Copyright Stephan Mueller <smueller@chronox.de>, 2015 - 2023 * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, and the entire permission notice in its entirety, * including the disclaimer of warranties. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. The name of the author may not be used to endorse or promote * products derived from this software without specific prior * written permission. * * ALTERNATIVELY, this product may be distributed under the terms of * the GNU General Public License, in which case the provisions of the GPL2 are * required INSTEAD OF the above restrictions. (This clause is * necessary due to a potential bad interaction between the GPL and * the restrictions contained in a BSD-style copyright.) * * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE, ALL OF * WHICH ARE HEREBY DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT * OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE * USE OF THIS SOFTWARE, EVEN IF NOT ADVISED OF THE POSSIBILITY OF SUCH * DAMAGE. */ #include <crypto/hash.h> #include <crypto/sha3.h> #include <linux/fips.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/time.h> #include <crypto/internal/rng.h> #include "jitterentropy.h" #define JENT_CONDITIONING_HASH "sha3-256-generic" /*************************************************************************** * Helper function ***************************************************************************/ void *jent_kvzalloc(unsigned int len) { return kvzalloc(len, GFP_KERNEL); } void jent_kvzfree(void *ptr, unsigned int len) { kvfree_sensitive(ptr, len); } void *jent_zalloc(unsigned int len) { return kzalloc(len, GFP_KERNEL); } void jent_zfree(void *ptr) { kfree_sensitive(ptr); } /* * Obtain a high-resolution time stamp value. The time stamp is used to measure * the execution time of a given code path and its variations. Hence, the time * stamp must have a sufficiently high resolution. * * Note, if the function returns zero because a given architecture does not * implement a high-resolution time stamp, the RNG code's runtime test * will detect it and will not produce output. */ void jent_get_nstime(__u64 *out) { __u64 tmp = 0; tmp = random_get_entropy(); /* * If random_get_entropy does not return a value, i.e. it is not * implemented for a given architecture, use a clock source. * hoping that there are timers we can work with. */ if (tmp == 0) tmp = ktime_get_ns(); *out = tmp; jent_raw_hires_entropy_store(tmp); } int jent_hash_time(void *hash_state, __u64 time, u8 *addtl, unsigned int addtl_len, __u64 hash_loop_cnt, unsigned int stuck) { struct shash_desc *hash_state_desc = (struct shash_desc *)hash_state; SHASH_DESC_ON_STACK(desc, hash_state_desc->tfm); u8 intermediary[SHA3_256_DIGEST_SIZE]; __u64 j = 0; int ret; desc->tfm = hash_state_desc->tfm; if (sizeof(intermediary) != crypto_shash_digestsize(desc->tfm)) { pr_warn_ratelimited("Unexpected digest size\n"); return -EINVAL; } /* * This loop fills a buffer which is injected into the entropy pool. * The main reason for this loop is to execute something over which we * can perform a timing measurement. The injection of the resulting * data into the pool is performed to ensure the result is used and * the compiler cannot optimize the loop away in case the result is not * used at all. Yet that data is considered "additional information" * considering the terminology from SP800-90A without any entropy. * * Note, it does not matter which or how much data you inject, we are * interested in one Keccack1600 compression operation performed with * the crypto_shash_final. */ for (j = 0; j < hash_loop_cnt; j++) { ret = crypto_shash_init(desc) ?: crypto_shash_update(desc, intermediary, sizeof(intermediary)) ?: crypto_shash_finup(desc, addtl, addtl_len, intermediary); if (ret) goto err; } /* * Inject the data from the previous loop into the pool. This data is * not considered to contain any entropy, but it stirs the pool a bit. */ ret = crypto_shash_update(desc, intermediary, sizeof(intermediary)); if (ret) goto err; /* * Insert the time stamp into the hash context representing the pool. * * If the time stamp is stuck, do not finally insert the value into the * entropy pool. Although this operation should not do any harm even * when the time stamp has no entropy, SP800-90B requires that any * conditioning operation to have an identical amount of input data * according to section 3.1.5. */ if (!stuck) { ret = crypto_shash_update(hash_state_desc, (u8 *)&time, sizeof(__u64)); } err: shash_desc_zero(desc); memzero_explicit(intermediary, sizeof(intermediary)); return ret; } int jent_read_random_block(void *hash_state, char *dst, unsigned int dst_len) { struct shash_desc *hash_state_desc = (struct shash_desc *)hash_state; u8 jent_block[SHA3_256_DIGEST_SIZE]; /* Obtain data from entropy pool and re-initialize it */ int ret = crypto_shash_final(hash_state_desc, jent_block) ?: crypto_shash_init(hash_state_desc) ?: crypto_shash_update(hash_state_desc, jent_block, sizeof(jent_block)); if (!ret && dst_len) memcpy(dst, jent_block, dst_len); memzero_explicit(jent_block, sizeof(jent_block)); return ret; } /*************************************************************************** * Kernel crypto API interface ***************************************************************************/ struct jitterentropy { spinlock_t jent_lock; struct rand_data *entropy_collector; struct crypto_shash *tfm; struct shash_desc *sdesc; }; static void jent_kcapi_cleanup(struct crypto_tfm *tfm) { struct jitterentropy *rng = crypto_tfm_ctx(tfm); spin_lock(&rng->jent_lock); if (rng->sdesc) { shash_desc_zero(rng->sdesc); kfree(rng->sdesc); } rng->sdesc = NULL; if (rng->tfm) crypto_free_shash(rng->tfm); rng->tfm = NULL; if (rng->entropy_collector) jent_entropy_collector_free(rng->entropy_collector); rng->entropy_collector = NULL; spin_unlock(&rng->jent_lock); } static int jent_kcapi_init(struct crypto_tfm *tfm) { struct jitterentropy *rng = crypto_tfm_ctx(tfm); struct crypto_shash *hash; struct shash_desc *sdesc; int size, ret = 0; spin_lock_init(&rng->jent_lock); /* * Use SHA3-256 as conditioner. We allocate only the generic * implementation as we are not interested in high-performance. The * execution time of the SHA3 operation is measured and adds to the * Jitter RNG's unpredictable behavior. If we have a slower hash * implementation, the execution timing variations are larger. When * using a fast implementation, we would need to call it more often * as its variations are lower. */ hash = crypto_alloc_shash(JENT_CONDITIONING_HASH, 0, 0); if (IS_ERR(hash)) { pr_err("Cannot allocate conditioning digest\n"); return PTR_ERR(hash); } rng->tfm = hash; size = sizeof(struct shash_desc) + crypto_shash_descsize(hash); sdesc = kmalloc(size, GFP_KERNEL); if (!sdesc) { ret = -ENOMEM; goto err; } sdesc->tfm = hash; crypto_shash_init(sdesc); rng->sdesc = sdesc; rng->entropy_collector = jent_entropy_collector_alloc(CONFIG_CRYPTO_JITTERENTROPY_OSR, 0, sdesc); if (!rng->entropy_collector) { ret = -ENOMEM; goto err; } spin_lock_init(&rng->jent_lock); return 0; err: jent_kcapi_cleanup(tfm); return ret; } static int jent_kcapi_random(struct crypto_rng *tfm, const u8 *src, unsigned int slen, u8 *rdata, unsigned int dlen) { struct jitterentropy *rng = crypto_rng_ctx(tfm); int ret = 0; spin_lock(&rng->jent_lock); ret = jent_read_entropy(rng->entropy_collector, rdata, dlen); if (ret == -3) { /* Handle permanent health test error */ /* * If the kernel was booted with fips=1, it implies that * the entire kernel acts as a FIPS 140 module. In this case * an SP800-90B permanent health test error is treated as * a FIPS module error. */ if (fips_enabled) panic("Jitter RNG permanent health test failure\n"); pr_err("Jitter RNG permanent health test failure\n"); ret = -EFAULT; } else if (ret == -2) { /* Handle intermittent health test error */ pr_warn_ratelimited("Reset Jitter RNG due to intermittent health test failure\n"); ret = -EAGAIN; } else if (ret == -1) { /* Handle other errors */ ret = -EINVAL; } spin_unlock(&rng->jent_lock); return ret; } static int jent_kcapi_reset(struct crypto_rng *tfm, const u8 *seed, unsigned int slen) { return 0; } static struct rng_alg jent_alg = { .generate = jent_kcapi_random, .seed = jent_kcapi_reset, .seedsize = 0, .base = { .cra_name = "jitterentropy_rng", .cra_driver_name = "jitterentropy_rng", .cra_priority = 100, .cra_ctxsize = sizeof(struct jitterentropy), .cra_module = THIS_MODULE, .cra_init = jent_kcapi_init, .cra_exit = jent_kcapi_cleanup, } }; static int __init jent_mod_init(void) { SHASH_DESC_ON_STACK(desc, tfm); struct crypto_shash *tfm; int ret = 0; jent_testing_init(); tfm = crypto_alloc_shash(JENT_CONDITIONING_HASH, 0, 0); if (IS_ERR(tfm)) { jent_testing_exit(); return PTR_ERR(tfm); } desc->tfm = tfm; crypto_shash_init(desc); ret = jent_entropy_init(CONFIG_CRYPTO_JITTERENTROPY_OSR, 0, desc, NULL); shash_desc_zero(desc); crypto_free_shash(tfm); if (ret) { /* Handle permanent health test error */ if (fips_enabled) panic("jitterentropy: Initialization failed with host not compliant with requirements: %d\n", ret); jent_testing_exit(); pr_info("jitterentropy: Initialization failed with host not compliant with requirements: %d\n", ret); return -EFAULT; } return crypto_register_rng(&jent_alg); } static void __exit jent_mod_exit(void) { jent_testing_exit(); crypto_unregister_rng(&jent_alg); } module_init(jent_mod_init); module_exit(jent_mod_exit); MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Stephan Mueller <smueller@chronox.de>"); MODULE_DESCRIPTION("Non-physical True Random Number Generator based on CPU Jitter"); MODULE_ALIAS_CRYPTO("jitterentropy_rng"); |
| 17 117 30 26 17 10 20 15 14 13 13 10 30 30 24 6 20 23 19 20 20 10 9 10 10 4 7 3 7 7 7 7 7 7 7 7 7 5 7 4 9 9 9 9 8 9 99 100 107 102 15 15 15 15 14 14 14 9 4 4 7 2 9 4 9 8 8 8 8 8 8 8 74 74 3 74 74 3 11 11 11 8 8 7 4 4 4 1 4 4 4 4 4 3 3 3 14 14 1 13 14 14 13 1 7 24 19 14 13 13 13 13 13 13 14 13 1 13 14 14 14 9 8 8 1 8 14 11 11 7 11 1 10 11 3 9 9 14 13 13 13 7 13 13 13 13 4 13 2 2 2 2 2 1 1 1 2 12 11 12 12 12 12 12 12 12 12 12 12 11 11 11 12 12 2 3 26 6 2 37 24 1 24 24 24 20 24 14 14 5 1 1 1 1 24 17 17 17 24 12 24 11 24 12 24 22 2 24 24 1 1 24 3 3 3 3 3 3 2 1 1 3 2 2 2 3 5 5 5 2 5 5 1 7 7 7 6 7 47 44 45 16 45 14 1 36 12 1 35 2 10 23 33 47 47 40 1 39 21 41 47 13 20 14 14 14 14 5 14 14 14 20 20 20 20 25 24 1 23 1 22 1 21 21 3 1 20 5 20 6 2 4 4 1 4 1 2 4 1 7 1 1 4 4 4 4 3 4 3 4 1 4 1 4 4 4 4 4 4 4 4 4 4 4 4 4 4 12 10 4 6 4 4 3 3 4 2 4 2 4 4 4 3 3 3 3 3 3 3 1 3 1 3 3 3 8 5 3 3 3 3 3 5 5 5 8 8 5 8 8 5 8 3 2 2 2 2 2 2 2 3 4 1 1 1 1 1 2 2 3 2 1 4 1 4 2 2 4 1 1 1 1 1 1 2 2 3 3 3 2 3 2 3 3 3 13 13 11 6 1 10 10 5 5 4 7 7 3 3 3 14 5 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 3 3 3 33 33 2 2 2 2 2 1 1 1 2 61 61 3 3 3 1 2 1 3 17 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* Multipath TCP * * Copyright (c) 2020, Red Hat, Inc. */ #define pr_fmt(fmt) "MPTCP: " fmt #include <linux/inet.h> #include <linux/kernel.h> #include <net/inet_common.h> #include <net/netns/generic.h> #include <net/mptcp.h> #include "protocol.h" #include "mib.h" #include "mptcp_pm_gen.h" static int pm_nl_pernet_id; struct mptcp_pm_add_entry { struct list_head list; struct mptcp_addr_info addr; u8 retrans_times; struct timer_list add_timer; struct mptcp_sock *sock; }; struct pm_nl_pernet { /* protects pernet updates */ spinlock_t lock; struct list_head local_addr_list; unsigned int addrs; unsigned int stale_loss_cnt; unsigned int add_addr_signal_max; unsigned int add_addr_accept_max; unsigned int local_addr_max; unsigned int subflows_max; unsigned int next_id; DECLARE_BITMAP(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1); }; #define MPTCP_PM_ADDR_MAX 8 #define ADD_ADDR_RETRANS_MAX 3 static struct pm_nl_pernet *pm_nl_get_pernet(const struct net *net) { return net_generic(net, pm_nl_pernet_id); } static struct pm_nl_pernet * pm_nl_get_pernet_from_msk(const struct mptcp_sock *msk) { return pm_nl_get_pernet(sock_net((struct sock *)msk)); } bool mptcp_addresses_equal(const struct mptcp_addr_info *a, const struct mptcp_addr_info *b, bool use_port) { bool addr_equals = false; if (a->family == b->family) { if (a->family == AF_INET) addr_equals = a->addr.s_addr == b->addr.s_addr; #if IS_ENABLED(CONFIG_MPTCP_IPV6) else addr_equals = !ipv6_addr_cmp(&a->addr6, &b->addr6); } else if (a->family == AF_INET) { if (ipv6_addr_v4mapped(&b->addr6)) addr_equals = a->addr.s_addr == b->addr6.s6_addr32[3]; } else if (b->family == AF_INET) { if (ipv6_addr_v4mapped(&a->addr6)) addr_equals = a->addr6.s6_addr32[3] == b->addr.s_addr; #endif } if (!addr_equals) return false; if (!use_port) return true; return a->port == b->port; } void mptcp_local_address(const struct sock_common *skc, struct mptcp_addr_info *addr) { addr->family = skc->skc_family; addr->port = htons(skc->skc_num); if (addr->family == AF_INET) addr->addr.s_addr = skc->skc_rcv_saddr; #if IS_ENABLED(CONFIG_MPTCP_IPV6) else if (addr->family == AF_INET6) addr->addr6 = skc->skc_v6_rcv_saddr; #endif } static void remote_address(const struct sock_common *skc, struct mptcp_addr_info *addr) { addr->family = skc->skc_family; addr->port = skc->skc_dport; if (addr->family == AF_INET) addr->addr.s_addr = skc->skc_daddr; #if IS_ENABLED(CONFIG_MPTCP_IPV6) else if (addr->family == AF_INET6) addr->addr6 = skc->skc_v6_daddr; #endif } bool mptcp_lookup_subflow_by_saddr(const struct list_head *list, const struct mptcp_addr_info *saddr) { struct mptcp_subflow_context *subflow; struct mptcp_addr_info cur; struct sock_common *skc; list_for_each_entry(subflow, list, node) { skc = (struct sock_common *)mptcp_subflow_tcp_sock(subflow); mptcp_local_address(skc, &cur); if (mptcp_addresses_equal(&cur, saddr, saddr->port)) return true; } return false; } static bool lookup_subflow_by_daddr(const struct list_head *list, const struct mptcp_addr_info *daddr) { struct mptcp_subflow_context *subflow; struct mptcp_addr_info cur; list_for_each_entry(subflow, list, node) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); if (!((1 << inet_sk_state_load(ssk)) & (TCPF_ESTABLISHED | TCPF_SYN_SENT | TCPF_SYN_RECV))) continue; remote_address((struct sock_common *)ssk, &cur); if (mptcp_addresses_equal(&cur, daddr, daddr->port)) return true; } return false; } static bool select_local_address(const struct pm_nl_pernet *pernet, const struct mptcp_sock *msk, struct mptcp_pm_local *new_local) { struct mptcp_pm_addr_entry *entry; bool found = false; msk_owned_by_me(msk); rcu_read_lock(); list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) { if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW)) continue; if (!test_bit(entry->addr.id, msk->pm.id_avail_bitmap)) continue; new_local->addr = entry->addr; new_local->flags = entry->flags; new_local->ifindex = entry->ifindex; found = true; break; } rcu_read_unlock(); return found; } static bool select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk, struct mptcp_pm_local *new_local) { struct mptcp_pm_addr_entry *entry; bool found = false; rcu_read_lock(); /* do not keep any additional per socket state, just signal * the address list in order. * Note: removal from the local address list during the msk life-cycle * can lead to additional addresses not being announced. */ list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) { if (!test_bit(entry->addr.id, msk->pm.id_avail_bitmap)) continue; if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) continue; new_local->addr = entry->addr; new_local->flags = entry->flags; new_local->ifindex = entry->ifindex; found = true; break; } rcu_read_unlock(); return found; } unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk) { const struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk); return READ_ONCE(pernet->add_addr_signal_max); } EXPORT_SYMBOL_GPL(mptcp_pm_get_add_addr_signal_max); unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk) { struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk); return READ_ONCE(pernet->add_addr_accept_max); } EXPORT_SYMBOL_GPL(mptcp_pm_get_add_addr_accept_max); unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk) { struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk); return READ_ONCE(pernet->subflows_max); } EXPORT_SYMBOL_GPL(mptcp_pm_get_subflows_max); unsigned int mptcp_pm_get_local_addr_max(const struct mptcp_sock *msk) { struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk); return READ_ONCE(pernet->local_addr_max); } EXPORT_SYMBOL_GPL(mptcp_pm_get_local_addr_max); bool mptcp_pm_nl_check_work_pending(struct mptcp_sock *msk) { struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk); if (msk->pm.subflows == mptcp_pm_get_subflows_max(msk) || (find_next_and_bit(pernet->id_bitmap, msk->pm.id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1, 0) == MPTCP_PM_MAX_ADDR_ID + 1)) { WRITE_ONCE(msk->pm.work_pending, false); return false; } return true; } struct mptcp_pm_add_entry * mptcp_lookup_anno_list_by_saddr(const struct mptcp_sock *msk, const struct mptcp_addr_info *addr) { struct mptcp_pm_add_entry *entry; lockdep_assert_held(&msk->pm.lock); list_for_each_entry(entry, &msk->pm.anno_list, list) { if (mptcp_addresses_equal(&entry->addr, addr, true)) return entry; } return NULL; } bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk) { struct mptcp_pm_add_entry *entry; struct mptcp_addr_info saddr; bool ret = false; mptcp_local_address((struct sock_common *)sk, &saddr); spin_lock_bh(&msk->pm.lock); list_for_each_entry(entry, &msk->pm.anno_list, list) { if (mptcp_addresses_equal(&entry->addr, &saddr, true)) { ret = true; goto out; } } out: spin_unlock_bh(&msk->pm.lock); return ret; } static void mptcp_pm_add_timer(struct timer_list *timer) { struct mptcp_pm_add_entry *entry = from_timer(entry, timer, add_timer); struct mptcp_sock *msk = entry->sock; struct sock *sk = (struct sock *)msk; pr_debug("msk=%p\n", msk); if (!msk) return; if (inet_sk_state_load(sk) == TCP_CLOSE) return; if (!entry->addr.id) return; if (mptcp_pm_should_add_signal_addr(msk)) { sk_reset_timer(sk, timer, jiffies + TCP_RTO_MAX / 8); goto out; } spin_lock_bh(&msk->pm.lock); if (!mptcp_pm_should_add_signal_addr(msk)) { pr_debug("retransmit ADD_ADDR id=%d\n", entry->addr.id); mptcp_pm_announce_addr(msk, &entry->addr, false); mptcp_pm_add_addr_send_ack(msk); entry->retrans_times++; } if (entry->retrans_times < ADD_ADDR_RETRANS_MAX) sk_reset_timer(sk, timer, jiffies + mptcp_get_add_addr_timeout(sock_net(sk))); spin_unlock_bh(&msk->pm.lock); if (entry->retrans_times == ADD_ADDR_RETRANS_MAX) mptcp_pm_subflow_established(msk); out: __sock_put(sk); } struct mptcp_pm_add_entry * mptcp_pm_del_add_timer(struct mptcp_sock *msk, const struct mptcp_addr_info *addr, bool check_id) { struct mptcp_pm_add_entry *entry; struct sock *sk = (struct sock *)msk; struct timer_list *add_timer = NULL; spin_lock_bh(&msk->pm.lock); entry = mptcp_lookup_anno_list_by_saddr(msk, addr); if (entry && (!check_id || entry->addr.id == addr->id)) { entry->retrans_times = ADD_ADDR_RETRANS_MAX; add_timer = &entry->add_timer; } if (!check_id && entry) list_del(&entry->list); spin_unlock_bh(&msk->pm.lock); /* no lock, because sk_stop_timer_sync() is calling del_timer_sync() */ if (add_timer) sk_stop_timer_sync(sk, add_timer); return entry; } bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk, const struct mptcp_addr_info *addr) { struct mptcp_pm_add_entry *add_entry = NULL; struct sock *sk = (struct sock *)msk; struct net *net = sock_net(sk); lockdep_assert_held(&msk->pm.lock); add_entry = mptcp_lookup_anno_list_by_saddr(msk, addr); if (add_entry) { if (WARN_ON_ONCE(mptcp_pm_is_kernel(msk))) return false; sk_reset_timer(sk, &add_entry->add_timer, jiffies + mptcp_get_add_addr_timeout(net)); return true; } add_entry = kmalloc(sizeof(*add_entry), GFP_ATOMIC); if (!add_entry) return false; list_add(&add_entry->list, &msk->pm.anno_list); add_entry->addr = *addr; add_entry->sock = msk; add_entry->retrans_times = 0; timer_setup(&add_entry->add_timer, mptcp_pm_add_timer, 0); sk_reset_timer(sk, &add_entry->add_timer, jiffies + mptcp_get_add_addr_timeout(net)); return true; } void mptcp_pm_free_anno_list(struct mptcp_sock *msk) { struct mptcp_pm_add_entry *entry, *tmp; struct sock *sk = (struct sock *)msk; LIST_HEAD(free_list); pr_debug("msk=%p\n", msk); spin_lock_bh(&msk->pm.lock); list_splice_init(&msk->pm.anno_list, &free_list); spin_unlock_bh(&msk->pm.lock); list_for_each_entry_safe(entry, tmp, &free_list, list) { sk_stop_timer_sync(sk, &entry->add_timer); kfree(entry); } } /* Fill all the remote addresses into the array addrs[], * and return the array size. */ static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk, struct mptcp_addr_info *local, bool fullmesh, struct mptcp_addr_info *addrs) { bool deny_id0 = READ_ONCE(msk->pm.remote_deny_join_id0); struct sock *sk = (struct sock *)msk, *ssk; struct mptcp_subflow_context *subflow; struct mptcp_addr_info remote = { 0 }; unsigned int subflows_max; int i = 0; subflows_max = mptcp_pm_get_subflows_max(msk); remote_address((struct sock_common *)sk, &remote); /* Non-fullmesh endpoint, fill in the single entry * corresponding to the primary MPC subflow remote address */ if (!fullmesh) { if (deny_id0) return 0; if (!mptcp_pm_addr_families_match(sk, local, &remote)) return 0; msk->pm.subflows++; addrs[i++] = remote; } else { DECLARE_BITMAP(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1); /* Forbid creation of new subflows matching existing * ones, possibly already created by incoming ADD_ADDR */ bitmap_zero(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1); mptcp_for_each_subflow(msk, subflow) if (READ_ONCE(subflow->local_id) == local->id) __set_bit(subflow->remote_id, unavail_id); mptcp_for_each_subflow(msk, subflow) { ssk = mptcp_subflow_tcp_sock(subflow); remote_address((struct sock_common *)ssk, &addrs[i]); addrs[i].id = READ_ONCE(subflow->remote_id); if (deny_id0 && !addrs[i].id) continue; if (test_bit(addrs[i].id, unavail_id)) continue; if (!mptcp_pm_addr_families_match(sk, local, &addrs[i])) continue; if (msk->pm.subflows < subflows_max) { /* forbid creating multiple address towards * this id */ __set_bit(addrs[i].id, unavail_id); msk->pm.subflows++; i++; } } } return i; } static void __mptcp_pm_send_ack(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, bool prio, bool backup) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow; pr_debug("send ack for %s\n", prio ? "mp_prio" : (mptcp_pm_should_add_signal(msk) ? "add_addr" : "rm_addr")); slow = lock_sock_fast(ssk); if (prio) { subflow->send_mp_prio = 1; subflow->request_bkup = backup; } __mptcp_subflow_send_ack(ssk); unlock_sock_fast(ssk, slow); } static void mptcp_pm_send_ack(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, bool prio, bool backup) { spin_unlock_bh(&msk->pm.lock); __mptcp_pm_send_ack(msk, subflow, prio, backup); spin_lock_bh(&msk->pm.lock); } static struct mptcp_pm_addr_entry * __lookup_addr_by_id(struct pm_nl_pernet *pernet, unsigned int id) { struct mptcp_pm_addr_entry *entry; list_for_each_entry_rcu(entry, &pernet->local_addr_list, list, lockdep_is_held(&pernet->lock)) { if (entry->addr.id == id) return entry; } return NULL; } static struct mptcp_pm_addr_entry * __lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info) { struct mptcp_pm_addr_entry *entry; list_for_each_entry_rcu(entry, &pernet->local_addr_list, list, lockdep_is_held(&pernet->lock)) { if (mptcp_addresses_equal(&entry->addr, info, entry->addr.port)) return entry; } return NULL; } static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) { struct sock *sk = (struct sock *)msk; unsigned int add_addr_signal_max; bool signal_and_subflow = false; unsigned int local_addr_max; struct pm_nl_pernet *pernet; struct mptcp_pm_local local; unsigned int subflows_max; pernet = pm_nl_get_pernet(sock_net(sk)); add_addr_signal_max = mptcp_pm_get_add_addr_signal_max(msk); local_addr_max = mptcp_pm_get_local_addr_max(msk); subflows_max = mptcp_pm_get_subflows_max(msk); /* do lazy endpoint usage accounting for the MPC subflows */ if (unlikely(!(msk->pm.status & BIT(MPTCP_PM_MPC_ENDPOINT_ACCOUNTED))) && msk->first) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(msk->first); struct mptcp_pm_addr_entry *entry; struct mptcp_addr_info mpc_addr; bool backup = false; mptcp_local_address((struct sock_common *)msk->first, &mpc_addr); rcu_read_lock(); entry = __lookup_addr(pernet, &mpc_addr); if (entry) { __clear_bit(entry->addr.id, msk->pm.id_avail_bitmap); msk->mpc_endpoint_id = entry->addr.id; backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP); } rcu_read_unlock(); if (backup) mptcp_pm_send_ack(msk, subflow, true, backup); msk->pm.status |= BIT(MPTCP_PM_MPC_ENDPOINT_ACCOUNTED); } pr_debug("local %d:%d signal %d:%d subflows %d:%d\n", msk->pm.local_addr_used, local_addr_max, msk->pm.add_addr_signaled, add_addr_signal_max, msk->pm.subflows, subflows_max); /* check first for announce */ if (msk->pm.add_addr_signaled < add_addr_signal_max) { /* due to racing events on both ends we can reach here while * previous add address is still running: if we invoke now * mptcp_pm_announce_addr(), that will fail and the * corresponding id will be marked as used. * Instead let the PM machinery reschedule us when the * current address announce will be completed. */ if (msk->pm.addr_signal & BIT(MPTCP_ADD_ADDR_SIGNAL)) return; if (!select_signal_address(pernet, msk, &local)) goto subflow; /* If the alloc fails, we are on memory pressure, not worth * continuing, and trying to create subflows. */ if (!mptcp_pm_alloc_anno_list(msk, &local.addr)) return; __clear_bit(local.addr.id, msk->pm.id_avail_bitmap); msk->pm.add_addr_signaled++; /* Special case for ID0: set the correct ID */ if (local.addr.id == msk->mpc_endpoint_id) local.addr.id = 0; mptcp_pm_announce_addr(msk, &local.addr, false); mptcp_pm_nl_addr_send_ack(msk); if (local.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) signal_and_subflow = true; } subflow: /* check if should create a new subflow */ while (msk->pm.local_addr_used < local_addr_max && msk->pm.subflows < subflows_max) { struct mptcp_addr_info addrs[MPTCP_PM_ADDR_MAX]; bool fullmesh; int i, nr; if (signal_and_subflow) signal_and_subflow = false; else if (!select_local_address(pernet, msk, &local)) break; fullmesh = !!(local.flags & MPTCP_PM_ADDR_FLAG_FULLMESH); __clear_bit(local.addr.id, msk->pm.id_avail_bitmap); /* Special case for ID0: set the correct ID */ if (local.addr.id == msk->mpc_endpoint_id) local.addr.id = 0; else /* local_addr_used is not decr for ID 0 */ msk->pm.local_addr_used++; nr = fill_remote_addresses_vec(msk, &local.addr, fullmesh, addrs); if (nr == 0) continue; spin_unlock_bh(&msk->pm.lock); for (i = 0; i < nr; i++) __mptcp_subflow_connect(sk, &local, &addrs[i]); spin_lock_bh(&msk->pm.lock); } mptcp_pm_nl_check_work_pending(msk); } static void mptcp_pm_nl_fully_established(struct mptcp_sock *msk) { mptcp_pm_create_subflow_or_signal_addr(msk); } static void mptcp_pm_nl_subflow_established(struct mptcp_sock *msk) { mptcp_pm_create_subflow_or_signal_addr(msk); } /* Fill all the local addresses into the array addrs[], * and return the array size. */ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk, struct mptcp_addr_info *remote, struct mptcp_pm_local *locals) { struct sock *sk = (struct sock *)msk; struct mptcp_pm_addr_entry *entry; struct mptcp_addr_info mpc_addr; struct pm_nl_pernet *pernet; unsigned int subflows_max; int i = 0; pernet = pm_nl_get_pernet_from_msk(msk); subflows_max = mptcp_pm_get_subflows_max(msk); mptcp_local_address((struct sock_common *)msk, &mpc_addr); rcu_read_lock(); list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) { if (!(entry->flags & MPTCP_PM_ADDR_FLAG_FULLMESH)) continue; if (!mptcp_pm_addr_families_match(sk, &entry->addr, remote)) continue; if (msk->pm.subflows < subflows_max) { locals[i].addr = entry->addr; locals[i].flags = entry->flags; locals[i].ifindex = entry->ifindex; /* Special case for ID0: set the correct ID */ if (mptcp_addresses_equal(&locals[i].addr, &mpc_addr, locals[i].addr.port)) locals[i].addr.id = 0; msk->pm.subflows++; i++; } } rcu_read_unlock(); /* If the array is empty, fill in the single * 'IPADDRANY' local address */ if (!i) { memset(&locals[i], 0, sizeof(locals[i])); locals[i].addr.family = #if IS_ENABLED(CONFIG_MPTCP_IPV6) remote->family == AF_INET6 && ipv6_addr_v4mapped(&remote->addr6) ? AF_INET : #endif remote->family; if (!mptcp_pm_addr_families_match(sk, &locals[i].addr, remote)) return 0; msk->pm.subflows++; i++; } return i; } static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) { struct mptcp_pm_local locals[MPTCP_PM_ADDR_MAX]; struct sock *sk = (struct sock *)msk; unsigned int add_addr_accept_max; struct mptcp_addr_info remote; unsigned int subflows_max; bool sf_created = false; int i, nr; add_addr_accept_max = mptcp_pm_get_add_addr_accept_max(msk); subflows_max = mptcp_pm_get_subflows_max(msk); pr_debug("accepted %d:%d remote family %d\n", msk->pm.add_addr_accepted, add_addr_accept_max, msk->pm.remote.family); remote = msk->pm.remote; mptcp_pm_announce_addr(msk, &remote, true); mptcp_pm_nl_addr_send_ack(msk); if (lookup_subflow_by_daddr(&msk->conn_list, &remote)) return; /* pick id 0 port, if none is provided the remote address */ if (!remote.port) remote.port = sk->sk_dport; /* connect to the specified remote address, using whatever * local address the routing configuration will pick. */ nr = fill_local_addresses_vec(msk, &remote, locals); if (nr == 0) return; spin_unlock_bh(&msk->pm.lock); for (i = 0; i < nr; i++) if (__mptcp_subflow_connect(sk, &locals[i], &remote) == 0) sf_created = true; spin_lock_bh(&msk->pm.lock); if (sf_created) { /* add_addr_accepted is not decr for ID 0 */ if (remote.id) msk->pm.add_addr_accepted++; if (msk->pm.add_addr_accepted >= add_addr_accept_max || msk->pm.subflows >= subflows_max) WRITE_ONCE(msk->pm.accept_addr, false); } } bool mptcp_pm_nl_is_init_remote_addr(struct mptcp_sock *msk, const struct mptcp_addr_info *remote) { struct mptcp_addr_info mpc_remote; remote_address((struct sock_common *)msk, &mpc_remote); return mptcp_addresses_equal(&mpc_remote, remote, remote->port); } void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow, *alt = NULL; msk_owned_by_me(msk); lockdep_assert_held(&msk->pm.lock); if (!mptcp_pm_should_add_signal(msk) && !mptcp_pm_should_rm_signal(msk)) return; mptcp_for_each_subflow(msk, subflow) { if (__mptcp_subflow_active(subflow)) { if (!subflow->stale) { mptcp_pm_send_ack(msk, subflow, false, false); return; } if (!alt) alt = subflow; } } if (alt) mptcp_pm_send_ack(msk, alt, false, false); } int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, struct mptcp_addr_info *addr, struct mptcp_addr_info *rem, u8 bkup) { struct mptcp_subflow_context *subflow; pr_debug("bkup=%d\n", bkup); mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); struct mptcp_addr_info local, remote; mptcp_local_address((struct sock_common *)ssk, &local); if (!mptcp_addresses_equal(&local, addr, addr->port)) continue; if (rem && rem->family != AF_UNSPEC) { remote_address((struct sock_common *)ssk, &remote); if (!mptcp_addresses_equal(&remote, rem, rem->port)) continue; } __mptcp_pm_send_ack(msk, subflow, true, bkup); return 0; } return -EINVAL; } static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list, enum linux_mptcp_mib_field rm_type) { struct mptcp_subflow_context *subflow, *tmp; struct sock *sk = (struct sock *)msk; u8 i; pr_debug("%s rm_list_nr %d\n", rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow", rm_list->nr); msk_owned_by_me(msk); if (sk->sk_state == TCP_LISTEN) return; if (!rm_list->nr) return; if (list_empty(&msk->conn_list)) return; for (i = 0; i < rm_list->nr; i++) { u8 rm_id = rm_list->ids[i]; bool removed = false; mptcp_for_each_subflow_safe(msk, subflow, tmp) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); u8 remote_id = READ_ONCE(subflow->remote_id); int how = RCV_SHUTDOWN | SEND_SHUTDOWN; u8 id = subflow_get_local_id(subflow); if ((1 << inet_sk_state_load(ssk)) & (TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | TCPF_CLOSING | TCPF_CLOSE)) continue; if (rm_type == MPTCP_MIB_RMADDR && remote_id != rm_id) continue; if (rm_type == MPTCP_MIB_RMSUBFLOW && id != rm_id) continue; pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u mpc_id=%u\n", rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow", i, rm_id, id, remote_id, msk->mpc_endpoint_id); spin_unlock_bh(&msk->pm.lock); mptcp_subflow_shutdown(sk, ssk, how); removed |= subflow->request_join; /* the following takes care of updating the subflows counter */ mptcp_close_ssk(sk, ssk, subflow); spin_lock_bh(&msk->pm.lock); if (rm_type == MPTCP_MIB_RMSUBFLOW) __MPTCP_INC_STATS(sock_net(sk), rm_type); } if (rm_type == MPTCP_MIB_RMADDR) __MPTCP_INC_STATS(sock_net(sk), rm_type); if (!removed) continue; if (!mptcp_pm_is_kernel(msk)) continue; if (rm_type == MPTCP_MIB_RMADDR && rm_id && !WARN_ON_ONCE(msk->pm.add_addr_accepted == 0)) { /* Note: if the subflow has been closed before, this * add_addr_accepted counter will not be decremented. */ if (--msk->pm.add_addr_accepted < mptcp_pm_get_add_addr_accept_max(msk)) WRITE_ONCE(msk->pm.accept_addr, true); } } } static void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk) { mptcp_pm_nl_rm_addr_or_subflow(msk, &msk->pm.rm_list_rx, MPTCP_MIB_RMADDR); } static void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list) { mptcp_pm_nl_rm_addr_or_subflow(msk, rm_list, MPTCP_MIB_RMSUBFLOW); } void mptcp_pm_nl_work(struct mptcp_sock *msk) { struct mptcp_pm_data *pm = &msk->pm; msk_owned_by_me(msk); if (!(pm->status & MPTCP_PM_WORK_MASK)) return; spin_lock_bh(&msk->pm.lock); pr_debug("msk=%p status=%x\n", msk, pm->status); if (pm->status & BIT(MPTCP_PM_ADD_ADDR_RECEIVED)) { pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_RECEIVED); mptcp_pm_nl_add_addr_received(msk); } if (pm->status & BIT(MPTCP_PM_ADD_ADDR_SEND_ACK)) { pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_SEND_ACK); mptcp_pm_nl_addr_send_ack(msk); } if (pm->status & BIT(MPTCP_PM_RM_ADDR_RECEIVED)) { pm->status &= ~BIT(MPTCP_PM_RM_ADDR_RECEIVED); mptcp_pm_nl_rm_addr_received(msk); } if (pm->status & BIT(MPTCP_PM_ESTABLISHED)) { pm->status &= ~BIT(MPTCP_PM_ESTABLISHED); mptcp_pm_nl_fully_established(msk); } if (pm->status & BIT(MPTCP_PM_SUBFLOW_ESTABLISHED)) { pm->status &= ~BIT(MPTCP_PM_SUBFLOW_ESTABLISHED); mptcp_pm_nl_subflow_established(msk); } spin_unlock_bh(&msk->pm.lock); } static bool address_use_port(struct mptcp_pm_addr_entry *entry) { return (entry->flags & (MPTCP_PM_ADDR_FLAG_SIGNAL | MPTCP_PM_ADDR_FLAG_SUBFLOW)) == MPTCP_PM_ADDR_FLAG_SIGNAL; } /* caller must ensure the RCU grace period is already elapsed */ static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry) { if (entry->lsk) sock_release(entry->lsk); kfree(entry); } static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, struct mptcp_pm_addr_entry *entry, bool needs_id, bool replace) { struct mptcp_pm_addr_entry *cur, *del_entry = NULL; unsigned int addr_max; int ret = -EINVAL; spin_lock_bh(&pernet->lock); /* to keep the code simple, don't do IDR-like allocation for address ID, * just bail when we exceed limits */ if (pernet->next_id == MPTCP_PM_MAX_ADDR_ID) pernet->next_id = 1; if (pernet->addrs >= MPTCP_PM_ADDR_MAX) { ret = -ERANGE; goto out; } if (test_bit(entry->addr.id, pernet->id_bitmap)) { ret = -EBUSY; goto out; } /* do not insert duplicate address, differentiate on port only * singled addresses */ if (!address_use_port(entry)) entry->addr.port = 0; list_for_each_entry(cur, &pernet->local_addr_list, list) { if (mptcp_addresses_equal(&cur->addr, &entry->addr, cur->addr.port || entry->addr.port)) { /* allow replacing the exiting endpoint only if such * endpoint is an implicit one and the user-space * did not provide an endpoint id */ if (!(cur->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT)) { ret = -EEXIST; goto out; } if (entry->addr.id) goto out; /* allow callers that only need to look up the local * addr's id to skip replacement. This allows them to * avoid calling synchronize_rcu in the packet recv * path. */ if (!replace) { kfree(entry); ret = cur->addr.id; goto out; } pernet->addrs--; entry->addr.id = cur->addr.id; list_del_rcu(&cur->list); del_entry = cur; break; } } if (!entry->addr.id && needs_id) { find_next: entry->addr.id = find_next_zero_bit(pernet->id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1, pernet->next_id); if (!entry->addr.id && pernet->next_id != 1) { pernet->next_id = 1; goto find_next; } } if (!entry->addr.id && needs_id) goto out; __set_bit(entry->addr.id, pernet->id_bitmap); if (entry->addr.id > pernet->next_id) pernet->next_id = entry->addr.id; if (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL) { addr_max = pernet->add_addr_signal_max; WRITE_ONCE(pernet->add_addr_signal_max, addr_max + 1); } if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) { addr_max = pernet->local_addr_max; WRITE_ONCE(pernet->local_addr_max, addr_max + 1); } pernet->addrs++; if (!entry->addr.port) list_add_tail_rcu(&entry->list, &pernet->local_addr_list); else list_add_rcu(&entry->list, &pernet->local_addr_list); ret = entry->addr.id; out: spin_unlock_bh(&pernet->lock); /* just replaced an existing entry, free it */ if (del_entry) { synchronize_rcu(); __mptcp_pm_release_addr_entry(del_entry); } return ret; } static struct lock_class_key mptcp_slock_keys[2]; static struct lock_class_key mptcp_keys[2]; static int mptcp_pm_nl_create_listen_socket(struct sock *sk, struct mptcp_pm_addr_entry *entry) { bool is_ipv6 = sk->sk_family == AF_INET6; int addrlen = sizeof(struct sockaddr_in); struct sockaddr_storage addr; struct sock *newsk, *ssk; int backlog = 1024; int err; err = sock_create_kern(sock_net(sk), entry->addr.family, SOCK_STREAM, IPPROTO_MPTCP, &entry->lsk); if (err) return err; newsk = entry->lsk->sk; if (!newsk) return -EINVAL; /* The subflow socket lock is acquired in a nested to the msk one * in several places, even by the TCP stack, and this msk is a kernel * socket: lockdep complains. Instead of propagating the _nested * modifiers in several places, re-init the lock class for the msk * socket to an mptcp specific one. */ sock_lock_init_class_and_name(newsk, is_ipv6 ? "mlock-AF_INET6" : "mlock-AF_INET", &mptcp_slock_keys[is_ipv6], is_ipv6 ? "msk_lock-AF_INET6" : "msk_lock-AF_INET", &mptcp_keys[is_ipv6]); lock_sock(newsk); ssk = __mptcp_nmpc_sk(mptcp_sk(newsk)); release_sock(newsk); if (IS_ERR(ssk)) return PTR_ERR(ssk); mptcp_info2sockaddr(&entry->addr, &addr, entry->addr.family); #if IS_ENABLED(CONFIG_MPTCP_IPV6) if (entry->addr.family == AF_INET6) addrlen = sizeof(struct sockaddr_in6); #endif if (ssk->sk_family == AF_INET) err = inet_bind_sk(ssk, (struct sockaddr *)&addr, addrlen); #if IS_ENABLED(CONFIG_MPTCP_IPV6) else if (ssk->sk_family == AF_INET6) err = inet6_bind_sk(ssk, (struct sockaddr *)&addr, addrlen); #endif if (err) return err; /* We don't use mptcp_set_state() here because it needs to be called * under the msk socket lock. For the moment, that will not bring * anything more than only calling inet_sk_state_store(), because the * old status is known (TCP_CLOSE). */ inet_sk_state_store(newsk, TCP_LISTEN); lock_sock(ssk); WRITE_ONCE(mptcp_subflow_ctx(ssk)->pm_listener, true); err = __inet_listen_sk(ssk, backlog); if (!err) mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CREATED); release_sock(ssk); return err; } int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc) { struct mptcp_pm_addr_entry *entry; struct pm_nl_pernet *pernet; int ret; pernet = pm_nl_get_pernet_from_msk(msk); rcu_read_lock(); entry = __lookup_addr(pernet, skc); ret = entry ? entry->addr.id : -1; rcu_read_unlock(); if (ret >= 0) return ret; /* address not found, add to local list */ entry = kmalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) return -ENOMEM; entry->addr = *skc; entry->addr.id = 0; entry->addr.port = 0; entry->ifindex = 0; entry->flags = MPTCP_PM_ADDR_FLAG_IMPLICIT; entry->lsk = NULL; ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, true, false); if (ret < 0) kfree(entry); return ret; } bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc) { struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk); struct mptcp_pm_addr_entry *entry; bool backup; rcu_read_lock(); entry = __lookup_addr(pernet, skc); backup = entry && !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP); rcu_read_unlock(); return backup; } #define MPTCP_PM_CMD_GRP_OFFSET 0 #define MPTCP_PM_EV_GRP_OFFSET 1 static const struct genl_multicast_group mptcp_pm_mcgrps[] = { [MPTCP_PM_CMD_GRP_OFFSET] = { .name = MPTCP_PM_CMD_GRP_NAME, }, [MPTCP_PM_EV_GRP_OFFSET] = { .name = MPTCP_PM_EV_GRP_NAME, .flags = GENL_MCAST_CAP_NET_ADMIN, }, }; void mptcp_pm_nl_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk) { struct mptcp_subflow_context *iter, *subflow = mptcp_subflow_ctx(ssk); struct sock *sk = (struct sock *)msk; unsigned int active_max_loss_cnt; struct net *net = sock_net(sk); unsigned int stale_loss_cnt; bool slow; stale_loss_cnt = mptcp_stale_loss_cnt(net); if (subflow->stale || !stale_loss_cnt || subflow->stale_count <= stale_loss_cnt) return; /* look for another available subflow not in loss state */ active_max_loss_cnt = max_t(int, stale_loss_cnt - 1, 1); mptcp_for_each_subflow(msk, iter) { if (iter != subflow && mptcp_subflow_active(iter) && iter->stale_count < active_max_loss_cnt) { /* we have some alternatives, try to mark this subflow as idle ...*/ slow = lock_sock_fast(ssk); if (!tcp_rtx_and_write_queues_empty(ssk)) { subflow->stale = 1; __mptcp_retransmit_pending_data(sk); MPTCP_INC_STATS(net, MPTCP_MIB_SUBFLOWSTALE); } unlock_sock_fast(ssk, slow); /* always try to push the pending data regardless of re-injections: * we can possibly use backup subflows now, and subflow selection * is cheap under the msk socket lock */ __mptcp_push_pending(sk, 0); return; } } } static int mptcp_pm_family_to_addr(int family) { #if IS_ENABLED(CONFIG_MPTCP_IPV6) if (family == AF_INET6) return MPTCP_PM_ADDR_ATTR_ADDR6; #endif return MPTCP_PM_ADDR_ATTR_ADDR4; } static int mptcp_pm_parse_pm_addr_attr(struct nlattr *tb[], const struct nlattr *attr, struct genl_info *info, struct mptcp_addr_info *addr, bool require_family) { int err, addr_addr; if (!attr) { GENL_SET_ERR_MSG(info, "missing address info"); return -EINVAL; } /* no validation needed - was already done via nested policy */ err = nla_parse_nested_deprecated(tb, MPTCP_PM_ADDR_ATTR_MAX, attr, mptcp_pm_address_nl_policy, info->extack); if (err) return err; if (tb[MPTCP_PM_ADDR_ATTR_ID]) addr->id = nla_get_u8(tb[MPTCP_PM_ADDR_ATTR_ID]); if (!tb[MPTCP_PM_ADDR_ATTR_FAMILY]) { if (!require_family) return 0; NL_SET_ERR_MSG_ATTR(info->extack, attr, "missing family"); return -EINVAL; } addr->family = nla_get_u16(tb[MPTCP_PM_ADDR_ATTR_FAMILY]); if (addr->family != AF_INET #if IS_ENABLED(CONFIG_MPTCP_IPV6) && addr->family != AF_INET6 #endif ) { NL_SET_ERR_MSG_ATTR(info->extack, attr, "unknown address family"); return -EINVAL; } addr_addr = mptcp_pm_family_to_addr(addr->family); if (!tb[addr_addr]) { NL_SET_ERR_MSG_ATTR(info->extack, attr, "missing address data"); return -EINVAL; } #if IS_ENABLED(CONFIG_MPTCP_IPV6) if (addr->family == AF_INET6) addr->addr6 = nla_get_in6_addr(tb[addr_addr]); else #endif addr->addr.s_addr = nla_get_in_addr(tb[addr_addr]); if (tb[MPTCP_PM_ADDR_ATTR_PORT]) addr->port = htons(nla_get_u16(tb[MPTCP_PM_ADDR_ATTR_PORT])); return 0; } int mptcp_pm_parse_addr(struct nlattr *attr, struct genl_info *info, struct mptcp_addr_info *addr) { struct nlattr *tb[MPTCP_PM_ADDR_ATTR_MAX + 1]; memset(addr, 0, sizeof(*addr)); return mptcp_pm_parse_pm_addr_attr(tb, attr, info, addr, true); } int mptcp_pm_parse_entry(struct nlattr *attr, struct genl_info *info, bool require_family, struct mptcp_pm_addr_entry *entry) { struct nlattr *tb[MPTCP_PM_ADDR_ATTR_MAX + 1]; int err; memset(entry, 0, sizeof(*entry)); err = mptcp_pm_parse_pm_addr_attr(tb, attr, info, &entry->addr, require_family); if (err) return err; if (tb[MPTCP_PM_ADDR_ATTR_IF_IDX]) { u32 val = nla_get_s32(tb[MPTCP_PM_ADDR_ATTR_IF_IDX]); entry->ifindex = val; } if (tb[MPTCP_PM_ADDR_ATTR_FLAGS]) entry->flags = nla_get_u32(tb[MPTCP_PM_ADDR_ATTR_FLAGS]); if (tb[MPTCP_PM_ADDR_ATTR_PORT]) entry->addr.port = htons(nla_get_u16(tb[MPTCP_PM_ADDR_ATTR_PORT])); return 0; } static struct pm_nl_pernet *genl_info_pm_nl(struct genl_info *info) { return pm_nl_get_pernet(genl_info_net(info)); } static int mptcp_nl_add_subflow_or_signal_addr(struct net *net, struct mptcp_addr_info *addr) { struct mptcp_sock *msk; long s_slot = 0, s_num = 0; while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) { struct sock *sk = (struct sock *)msk; struct mptcp_addr_info mpc_addr; if (!READ_ONCE(msk->fully_established) || mptcp_pm_is_userspace(msk)) goto next; /* if the endp linked to the init sf is re-added with a != ID */ mptcp_local_address((struct sock_common *)msk, &mpc_addr); lock_sock(sk); spin_lock_bh(&msk->pm.lock); if (mptcp_addresses_equal(addr, &mpc_addr, addr->port)) msk->mpc_endpoint_id = addr->id; mptcp_pm_create_subflow_or_signal_addr(msk); spin_unlock_bh(&msk->pm.lock); release_sock(sk); next: sock_put(sk); cond_resched(); } return 0; } static bool mptcp_pm_has_addr_attr_id(const struct nlattr *attr, struct genl_info *info) { struct nlattr *tb[MPTCP_PM_ADDR_ATTR_MAX + 1]; if (!nla_parse_nested_deprecated(tb, MPTCP_PM_ADDR_ATTR_MAX, attr, mptcp_pm_address_nl_policy, info->extack) && tb[MPTCP_PM_ADDR_ATTR_ID]) return true; return false; } int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR]; struct pm_nl_pernet *pernet = genl_info_pm_nl(info); struct mptcp_pm_addr_entry addr, *entry; int ret; ret = mptcp_pm_parse_entry(attr, info, true, &addr); if (ret < 0) return ret; if (addr.addr.port && !address_use_port(&addr)) { GENL_SET_ERR_MSG(info, "flags must have signal and not subflow when using port"); return -EINVAL; } if (addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL && addr.flags & MPTCP_PM_ADDR_FLAG_FULLMESH) { GENL_SET_ERR_MSG(info, "flags mustn't have both signal and fullmesh"); return -EINVAL; } if (addr.flags & MPTCP_PM_ADDR_FLAG_IMPLICIT) { GENL_SET_ERR_MSG(info, "can't create IMPLICIT endpoint"); return -EINVAL; } entry = kzalloc(sizeof(*entry), GFP_KERNEL_ACCOUNT); if (!entry) { GENL_SET_ERR_MSG(info, "can't allocate addr"); return -ENOMEM; } *entry = addr; if (entry->addr.port) { ret = mptcp_pm_nl_create_listen_socket(skb->sk, entry); if (ret) { GENL_SET_ERR_MSG_FMT(info, "create listen socket error: %d", ret); goto out_free; } } ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, !mptcp_pm_has_addr_attr_id(attr, info), true); if (ret < 0) { GENL_SET_ERR_MSG_FMT(info, "too many addresses or duplicate one: %d", ret); goto out_free; } mptcp_nl_add_subflow_or_signal_addr(sock_net(skb->sk), &entry->addr); return 0; out_free: __mptcp_pm_release_addr_entry(entry); return ret; } bool mptcp_remove_anno_list_by_saddr(struct mptcp_sock *msk, const struct mptcp_addr_info *addr) { struct mptcp_pm_add_entry *entry; entry = mptcp_pm_del_add_timer(msk, addr, false); if (entry) { kfree(entry); return true; } return false; } static u8 mptcp_endp_get_local_id(struct mptcp_sock *msk, const struct mptcp_addr_info *addr) { return msk->mpc_endpoint_id == addr->id ? 0 : addr->id; } static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk, const struct mptcp_addr_info *addr, bool force) { struct mptcp_rm_list list = { .nr = 0 }; bool ret; list.ids[list.nr++] = mptcp_endp_get_local_id(msk, addr); ret = mptcp_remove_anno_list_by_saddr(msk, addr); if (ret || force) { spin_lock_bh(&msk->pm.lock); if (ret) { __set_bit(addr->id, msk->pm.id_avail_bitmap); msk->pm.add_addr_signaled--; } mptcp_pm_remove_addr(msk, &list); spin_unlock_bh(&msk->pm.lock); } return ret; } static void __mark_subflow_endp_available(struct mptcp_sock *msk, u8 id) { /* If it was marked as used, and not ID 0, decrement local_addr_used */ if (!__test_and_set_bit(id ? : msk->mpc_endpoint_id, msk->pm.id_avail_bitmap) && id && !WARN_ON_ONCE(msk->pm.local_addr_used == 0)) msk->pm.local_addr_used--; } static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net, const struct mptcp_pm_addr_entry *entry) { const struct mptcp_addr_info *addr = &entry->addr; struct mptcp_rm_list list = { .nr = 1 }; long s_slot = 0, s_num = 0; struct mptcp_sock *msk; pr_debug("remove_id=%d\n", addr->id); while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) { struct sock *sk = (struct sock *)msk; bool remove_subflow; if (mptcp_pm_is_userspace(msk)) goto next; lock_sock(sk); remove_subflow = mptcp_lookup_subflow_by_saddr(&msk->conn_list, addr); mptcp_pm_remove_anno_addr(msk, addr, remove_subflow && !(entry->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT)); list.ids[0] = mptcp_endp_get_local_id(msk, addr); if (remove_subflow) { spin_lock_bh(&msk->pm.lock); mptcp_pm_nl_rm_subflow_received(msk, &list); spin_unlock_bh(&msk->pm.lock); } if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) { spin_lock_bh(&msk->pm.lock); __mark_subflow_endp_available(msk, list.ids[0]); spin_unlock_bh(&msk->pm.lock); } if (msk->mpc_endpoint_id == entry->addr.id) msk->mpc_endpoint_id = 0; release_sock(sk); next: sock_put(sk); cond_resched(); } return 0; } static int mptcp_nl_remove_id_zero_address(struct net *net, struct mptcp_addr_info *addr) { struct mptcp_rm_list list = { .nr = 0 }; long s_slot = 0, s_num = 0; struct mptcp_sock *msk; list.ids[list.nr++] = 0; while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) { struct sock *sk = (struct sock *)msk; struct mptcp_addr_info msk_local; if (list_empty(&msk->conn_list) || mptcp_pm_is_userspace(msk)) goto next; mptcp_local_address((struct sock_common *)msk, &msk_local); if (!mptcp_addresses_equal(&msk_local, addr, addr->port)) goto next; lock_sock(sk); spin_lock_bh(&msk->pm.lock); mptcp_pm_remove_addr(msk, &list); mptcp_pm_nl_rm_subflow_received(msk, &list); __mark_subflow_endp_available(msk, 0); spin_unlock_bh(&msk->pm.lock); release_sock(sk); next: sock_put(sk); cond_resched(); } return 0; } int mptcp_pm_nl_del_addr_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR]; struct pm_nl_pernet *pernet = genl_info_pm_nl(info); struct mptcp_pm_addr_entry addr, *entry; unsigned int addr_max; int ret; ret = mptcp_pm_parse_entry(attr, info, false, &addr); if (ret < 0) return ret; /* the zero id address is special: the first address used by the msk * always gets such an id, so different subflows can have different zero * id addresses. Additionally zero id is not accounted for in id_bitmap. * Let's use an 'mptcp_rm_list' instead of the common remove code. */ if (addr.addr.id == 0) return mptcp_nl_remove_id_zero_address(sock_net(skb->sk), &addr.addr); spin_lock_bh(&pernet->lock); entry = __lookup_addr_by_id(pernet, addr.addr.id); if (!entry) { GENL_SET_ERR_MSG(info, "address not found"); spin_unlock_bh(&pernet->lock); return -EINVAL; } if (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL) { addr_max = pernet->add_addr_signal_max; WRITE_ONCE(pernet->add_addr_signal_max, addr_max - 1); } if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) { addr_max = pernet->local_addr_max; WRITE_ONCE(pernet->local_addr_max, addr_max - 1); } pernet->addrs--; list_del_rcu(&entry->list); __clear_bit(entry->addr.id, pernet->id_bitmap); spin_unlock_bh(&pernet->lock); mptcp_nl_remove_subflow_and_signal_addr(sock_net(skb->sk), entry); synchronize_rcu(); __mptcp_pm_release_addr_entry(entry); return ret; } static void mptcp_pm_flush_addrs_and_subflows(struct mptcp_sock *msk, struct list_head *rm_list) { struct mptcp_rm_list alist = { .nr = 0 }, slist = { .nr = 0 }; struct mptcp_pm_addr_entry *entry; list_for_each_entry(entry, rm_list, list) { if (slist.nr < MPTCP_RM_IDS_MAX && mptcp_lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) slist.ids[slist.nr++] = mptcp_endp_get_local_id(msk, &entry->addr); if (alist.nr < MPTCP_RM_IDS_MAX && mptcp_remove_anno_list_by_saddr(msk, &entry->addr)) alist.ids[alist.nr++] = mptcp_endp_get_local_id(msk, &entry->addr); } spin_lock_bh(&msk->pm.lock); if (alist.nr) { msk->pm.add_addr_signaled -= alist.nr; mptcp_pm_remove_addr(msk, &alist); } if (slist.nr) mptcp_pm_nl_rm_subflow_received(msk, &slist); /* Reset counters: maybe some subflows have been removed before */ bitmap_fill(msk->pm.id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1); msk->pm.local_addr_used = 0; spin_unlock_bh(&msk->pm.lock); } static void mptcp_nl_flush_addrs_list(struct net *net, struct list_head *rm_list) { long s_slot = 0, s_num = 0; struct mptcp_sock *msk; if (list_empty(rm_list)) return; while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) { struct sock *sk = (struct sock *)msk; if (!mptcp_pm_is_userspace(msk)) { lock_sock(sk); mptcp_pm_flush_addrs_and_subflows(msk, rm_list); release_sock(sk); } sock_put(sk); cond_resched(); } } /* caller must ensure the RCU grace period is already elapsed */ static void __flush_addrs(struct list_head *list) { while (!list_empty(list)) { struct mptcp_pm_addr_entry *cur; cur = list_entry(list->next, struct mptcp_pm_addr_entry, list); list_del_rcu(&cur->list); __mptcp_pm_release_addr_entry(cur); } } static void __reset_counters(struct pm_nl_pernet *pernet) { WRITE_ONCE(pernet->add_addr_signal_max, 0); WRITE_ONCE(pernet->add_addr_accept_max, 0); WRITE_ONCE(pernet->local_addr_max, 0); pernet->addrs = 0; } int mptcp_pm_nl_flush_addrs_doit(struct sk_buff *skb, struct genl_info *info) { struct pm_nl_pernet *pernet = genl_info_pm_nl(info); LIST_HEAD(free_list); spin_lock_bh(&pernet->lock); list_splice_init(&pernet->local_addr_list, &free_list); __reset_counters(pernet); pernet->next_id = 1; bitmap_zero(pernet->id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1); spin_unlock_bh(&pernet->lock); mptcp_nl_flush_addrs_list(sock_net(skb->sk), &free_list); synchronize_rcu(); __flush_addrs(&free_list); return 0; } int mptcp_nl_fill_addr(struct sk_buff *skb, struct mptcp_pm_addr_entry *entry) { struct mptcp_addr_info *addr = &entry->addr; struct nlattr *attr; attr = nla_nest_start(skb, MPTCP_PM_ATTR_ADDR); if (!attr) return -EMSGSIZE; if (nla_put_u16(skb, MPTCP_PM_ADDR_ATTR_FAMILY, addr->family)) goto nla_put_failure; if (nla_put_u16(skb, MPTCP_PM_ADDR_ATTR_PORT, ntohs(addr->port))) goto nla_put_failure; if (nla_put_u8(skb, MPTCP_PM_ADDR_ATTR_ID, addr->id)) goto nla_put_failure; if (nla_put_u32(skb, MPTCP_PM_ADDR_ATTR_FLAGS, entry->flags)) goto nla_put_failure; if (entry->ifindex && nla_put_s32(skb, MPTCP_PM_ADDR_ATTR_IF_IDX, entry->ifindex)) goto nla_put_failure; if (addr->family == AF_INET && nla_put_in_addr(skb, MPTCP_PM_ADDR_ATTR_ADDR4, addr->addr.s_addr)) goto nla_put_failure; #if IS_ENABLED(CONFIG_MPTCP_IPV6) else if (addr->family == AF_INET6 && nla_put_in6_addr(skb, MPTCP_PM_ADDR_ATTR_ADDR6, &addr->addr6)) goto nla_put_failure; #endif nla_nest_end(skb, attr); return 0; nla_put_failure: nla_nest_cancel(skb, attr); return -EMSGSIZE; } int mptcp_pm_nl_get_addr(struct sk_buff *skb, struct genl_info *info) { struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR]; struct pm_nl_pernet *pernet = genl_info_pm_nl(info); struct mptcp_pm_addr_entry addr, *entry; struct sk_buff *msg; void *reply; int ret; ret = mptcp_pm_parse_entry(attr, info, false, &addr); if (ret < 0) return ret; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; reply = genlmsg_put_reply(msg, info, &mptcp_genl_family, 0, info->genlhdr->cmd); if (!reply) { GENL_SET_ERR_MSG(info, "not enough space in Netlink message"); ret = -EMSGSIZE; goto fail; } rcu_read_lock(); entry = __lookup_addr_by_id(pernet, addr.addr.id); if (!entry) { GENL_SET_ERR_MSG(info, "address not found"); ret = -EINVAL; goto unlock_fail; } ret = mptcp_nl_fill_addr(msg, entry); if (ret) goto unlock_fail; genlmsg_end(msg, reply); ret = genlmsg_reply(msg, info); rcu_read_unlock(); return ret; unlock_fail: rcu_read_unlock(); fail: nlmsg_free(msg); return ret; } int mptcp_pm_nl_get_addr_doit(struct sk_buff *skb, struct genl_info *info) { return mptcp_pm_get_addr(skb, info); } int mptcp_pm_nl_dump_addr(struct sk_buff *msg, struct netlink_callback *cb) { struct net *net = sock_net(msg->sk); struct mptcp_pm_addr_entry *entry; struct pm_nl_pernet *pernet; int id = cb->args[0]; void *hdr; int i; pernet = pm_nl_get_pernet(net); rcu_read_lock(); for (i = id; i < MPTCP_PM_MAX_ADDR_ID + 1; i++) { if (test_bit(i, pernet->id_bitmap)) { entry = __lookup_addr_by_id(pernet, i); if (!entry) break; if (entry->addr.id <= id) continue; hdr = genlmsg_put(msg, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &mptcp_genl_family, NLM_F_MULTI, MPTCP_PM_CMD_GET_ADDR); if (!hdr) break; if (mptcp_nl_fill_addr(msg, entry) < 0) { genlmsg_cancel(msg, hdr); break; } id = entry->addr.id; genlmsg_end(msg, hdr); } } rcu_read_unlock(); cb->args[0] = id; return msg->len; } int mptcp_pm_nl_get_addr_dumpit(struct sk_buff *msg, struct netlink_callback *cb) { return mptcp_pm_dump_addr(msg, cb); } static int parse_limit(struct genl_info *info, int id, unsigned int *limit) { struct nlattr *attr = info->attrs[id]; if (!attr) return 0; *limit = nla_get_u32(attr); if (*limit > MPTCP_PM_ADDR_MAX) { GENL_SET_ERR_MSG(info, "limit greater than maximum"); return -EINVAL; } return 0; } int mptcp_pm_nl_set_limits_doit(struct sk_buff *skb, struct genl_info *info) { struct pm_nl_pernet *pernet = genl_info_pm_nl(info); unsigned int rcv_addrs, subflows; int ret; spin_lock_bh(&pernet->lock); rcv_addrs = pernet->add_addr_accept_max; ret = parse_limit(info, MPTCP_PM_ATTR_RCV_ADD_ADDRS, &rcv_addrs); if (ret) goto unlock; subflows = pernet->subflows_max; ret = parse_limit(info, MPTCP_PM_ATTR_SUBFLOWS, &subflows); if (ret) goto unlock; WRITE_ONCE(pernet->add_addr_accept_max, rcv_addrs); WRITE_ONCE(pernet->subflows_max, subflows); unlock: spin_unlock_bh(&pernet->lock); return ret; } int mptcp_pm_nl_get_limits_doit(struct sk_buff *skb, struct genl_info *info) { struct pm_nl_pernet *pernet = genl_info_pm_nl(info); struct sk_buff *msg; void *reply; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; reply = genlmsg_put_reply(msg, info, &mptcp_genl_family, 0, MPTCP_PM_CMD_GET_LIMITS); if (!reply) goto fail; if (nla_put_u32(msg, MPTCP_PM_ATTR_RCV_ADD_ADDRS, READ_ONCE(pernet->add_addr_accept_max))) goto fail; if (nla_put_u32(msg, MPTCP_PM_ATTR_SUBFLOWS, READ_ONCE(pernet->subflows_max))) goto fail; genlmsg_end(msg, reply); return genlmsg_reply(msg, info); fail: GENL_SET_ERR_MSG(info, "not enough space in Netlink message"); nlmsg_free(msg); return -EMSGSIZE; } static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk, struct mptcp_addr_info *addr) { struct mptcp_rm_list list = { .nr = 0 }; list.ids[list.nr++] = mptcp_endp_get_local_id(msk, addr); spin_lock_bh(&msk->pm.lock); mptcp_pm_nl_rm_subflow_received(msk, &list); __mark_subflow_endp_available(msk, list.ids[0]); mptcp_pm_create_subflow_or_signal_addr(msk); spin_unlock_bh(&msk->pm.lock); } static int mptcp_nl_set_flags(struct net *net, struct mptcp_addr_info *addr, u8 bkup, u8 changed) { long s_slot = 0, s_num = 0; struct mptcp_sock *msk; int ret = -EINVAL; while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) { struct sock *sk = (struct sock *)msk; if (list_empty(&msk->conn_list) || mptcp_pm_is_userspace(msk)) goto next; lock_sock(sk); if (changed & MPTCP_PM_ADDR_FLAG_BACKUP) ret = mptcp_pm_nl_mp_prio_send_ack(msk, addr, NULL, bkup); if (changed & MPTCP_PM_ADDR_FLAG_FULLMESH) mptcp_pm_nl_fullmesh(msk, addr); release_sock(sk); next: sock_put(sk); cond_resched(); } return ret; } int mptcp_pm_nl_set_flags(struct sk_buff *skb, struct genl_info *info) { struct mptcp_pm_addr_entry addr = { .addr = { .family = AF_UNSPEC }, }; struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; u8 changed, mask = MPTCP_PM_ADDR_FLAG_BACKUP | MPTCP_PM_ADDR_FLAG_FULLMESH; struct net *net = sock_net(skb->sk); struct mptcp_pm_addr_entry *entry; struct pm_nl_pernet *pernet; u8 lookup_by_id = 0; u8 bkup = 0; int ret; pernet = pm_nl_get_pernet(net); ret = mptcp_pm_parse_entry(attr, info, false, &addr); if (ret < 0) return ret; if (addr.addr.family == AF_UNSPEC) { lookup_by_id = 1; if (!addr.addr.id) { GENL_SET_ERR_MSG(info, "missing required inputs"); return -EOPNOTSUPP; } } if (addr.flags & MPTCP_PM_ADDR_FLAG_BACKUP) bkup = 1; spin_lock_bh(&pernet->lock); entry = lookup_by_id ? __lookup_addr_by_id(pernet, addr.addr.id) : __lookup_addr(pernet, &addr.addr); if (!entry) { spin_unlock_bh(&pernet->lock); GENL_SET_ERR_MSG(info, "address not found"); return -EINVAL; } if ((addr.flags & MPTCP_PM_ADDR_FLAG_FULLMESH) && (entry->flags & (MPTCP_PM_ADDR_FLAG_SIGNAL | MPTCP_PM_ADDR_FLAG_IMPLICIT))) { spin_unlock_bh(&pernet->lock); GENL_SET_ERR_MSG(info, "invalid addr flags"); return -EINVAL; } changed = (addr.flags ^ entry->flags) & mask; entry->flags = (entry->flags & ~mask) | (addr.flags & mask); addr = *entry; spin_unlock_bh(&pernet->lock); mptcp_nl_set_flags(net, &addr.addr, bkup, changed); return 0; } int mptcp_pm_nl_set_flags_doit(struct sk_buff *skb, struct genl_info *info) { return mptcp_pm_set_flags(skb, info); } static void mptcp_nl_mcast_send(struct net *net, struct sk_buff *nlskb, gfp_t gfp) { genlmsg_multicast_netns(&mptcp_genl_family, net, nlskb, 0, MPTCP_PM_EV_GRP_OFFSET, gfp); } bool mptcp_userspace_pm_active(const struct mptcp_sock *msk) { return genl_has_listeners(&mptcp_genl_family, sock_net((const struct sock *)msk), MPTCP_PM_EV_GRP_OFFSET); } static int mptcp_event_add_subflow(struct sk_buff *skb, const struct sock *ssk) { const struct inet_sock *issk = inet_sk(ssk); const struct mptcp_subflow_context *sf; if (nla_put_u16(skb, MPTCP_ATTR_FAMILY, ssk->sk_family)) return -EMSGSIZE; switch (ssk->sk_family) { case AF_INET: if (nla_put_in_addr(skb, MPTCP_ATTR_SADDR4, issk->inet_saddr)) return -EMSGSIZE; if (nla_put_in_addr(skb, MPTCP_ATTR_DADDR4, issk->inet_daddr)) return -EMSGSIZE; break; #if IS_ENABLED(CONFIG_MPTCP_IPV6) case AF_INET6: { const struct ipv6_pinfo *np = inet6_sk(ssk); if (nla_put_in6_addr(skb, MPTCP_ATTR_SADDR6, &np->saddr)) return -EMSGSIZE; if (nla_put_in6_addr(skb, MPTCP_ATTR_DADDR6, &ssk->sk_v6_daddr)) return -EMSGSIZE; break; } #endif default: WARN_ON_ONCE(1); return -EMSGSIZE; } if (nla_put_be16(skb, MPTCP_ATTR_SPORT, issk->inet_sport)) return -EMSGSIZE; if (nla_put_be16(skb, MPTCP_ATTR_DPORT, issk->inet_dport)) return -EMSGSIZE; sf = mptcp_subflow_ctx(ssk); if (WARN_ON_ONCE(!sf)) return -EINVAL; if (nla_put_u8(skb, MPTCP_ATTR_LOC_ID, subflow_get_local_id(sf))) return -EMSGSIZE; if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, sf->remote_id)) return -EMSGSIZE; return 0; } static int mptcp_event_put_token_and_ssk(struct sk_buff *skb, const struct mptcp_sock *msk, const struct sock *ssk) { const struct sock *sk = (const struct sock *)msk; const struct mptcp_subflow_context *sf; u8 sk_err; if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, READ_ONCE(msk->token))) return -EMSGSIZE; if (mptcp_event_add_subflow(skb, ssk)) return -EMSGSIZE; sf = mptcp_subflow_ctx(ssk); if (WARN_ON_ONCE(!sf)) return -EINVAL; if (nla_put_u8(skb, MPTCP_ATTR_BACKUP, sf->backup)) return -EMSGSIZE; if (ssk->sk_bound_dev_if && nla_put_s32(skb, MPTCP_ATTR_IF_IDX, ssk->sk_bound_dev_if)) return -EMSGSIZE; sk_err = READ_ONCE(ssk->sk_err); if (sk_err && sk->sk_state == TCP_ESTABLISHED && nla_put_u8(skb, MPTCP_ATTR_ERROR, sk_err)) return -EMSGSIZE; return 0; } static int mptcp_event_sub_established(struct sk_buff *skb, const struct mptcp_sock *msk, const struct sock *ssk) { return mptcp_event_put_token_and_ssk(skb, msk, ssk); } static int mptcp_event_sub_closed(struct sk_buff *skb, const struct mptcp_sock *msk, const struct sock *ssk) { const struct mptcp_subflow_context *sf; if (mptcp_event_put_token_and_ssk(skb, msk, ssk)) return -EMSGSIZE; sf = mptcp_subflow_ctx(ssk); if (!sf->reset_seen) return 0; if (nla_put_u32(skb, MPTCP_ATTR_RESET_REASON, sf->reset_reason)) return -EMSGSIZE; if (nla_put_u32(skb, MPTCP_ATTR_RESET_FLAGS, sf->reset_transient)) return -EMSGSIZE; return 0; } static int mptcp_event_created(struct sk_buff *skb, const struct mptcp_sock *msk, const struct sock *ssk) { int err = nla_put_u32(skb, MPTCP_ATTR_TOKEN, READ_ONCE(msk->token)); if (err) return err; if (nla_put_u8(skb, MPTCP_ATTR_SERVER_SIDE, READ_ONCE(msk->pm.server_side))) return -EMSGSIZE; return mptcp_event_add_subflow(skb, ssk); } void mptcp_event_addr_removed(const struct mptcp_sock *msk, uint8_t id) { struct net *net = sock_net((const struct sock *)msk); struct nlmsghdr *nlh; struct sk_buff *skb; if (!genl_has_listeners(&mptcp_genl_family, net, MPTCP_PM_EV_GRP_OFFSET)) return; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!skb) return; nlh = genlmsg_put(skb, 0, 0, &mptcp_genl_family, 0, MPTCP_EVENT_REMOVED); if (!nlh) goto nla_put_failure; if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, READ_ONCE(msk->token))) goto nla_put_failure; if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, id)) goto nla_put_failure; genlmsg_end(skb, nlh); mptcp_nl_mcast_send(net, skb, GFP_ATOMIC); return; nla_put_failure: nlmsg_free(skb); } void mptcp_event_addr_announced(const struct sock *ssk, const struct mptcp_addr_info *info) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); struct net *net = sock_net(ssk); struct nlmsghdr *nlh; struct sk_buff *skb; if (!genl_has_listeners(&mptcp_genl_family, net, MPTCP_PM_EV_GRP_OFFSET)) return; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!skb) return; nlh = genlmsg_put(skb, 0, 0, &mptcp_genl_family, 0, MPTCP_EVENT_ANNOUNCED); if (!nlh) goto nla_put_failure; if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, READ_ONCE(msk->token))) goto nla_put_failure; if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, info->id)) goto nla_put_failure; if (nla_put_be16(skb, MPTCP_ATTR_DPORT, info->port == 0 ? inet_sk(ssk)->inet_dport : info->port)) goto nla_put_failure; switch (info->family) { case AF_INET: if (nla_put_in_addr(skb, MPTCP_ATTR_DADDR4, info->addr.s_addr)) goto nla_put_failure; break; #if IS_ENABLED(CONFIG_MPTCP_IPV6) case AF_INET6: if (nla_put_in6_addr(skb, MPTCP_ATTR_DADDR6, &info->addr6)) goto nla_put_failure; break; #endif default: WARN_ON_ONCE(1); goto nla_put_failure; } genlmsg_end(skb, nlh); mptcp_nl_mcast_send(net, skb, GFP_ATOMIC); return; nla_put_failure: nlmsg_free(skb); } void mptcp_event_pm_listener(const struct sock *ssk, enum mptcp_event_type event) { const struct inet_sock *issk = inet_sk(ssk); struct net *net = sock_net(ssk); struct nlmsghdr *nlh; struct sk_buff *skb; if (!genl_has_listeners(&mptcp_genl_family, net, MPTCP_PM_EV_GRP_OFFSET)) return; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb) return; nlh = genlmsg_put(skb, 0, 0, &mptcp_genl_family, 0, event); if (!nlh) goto nla_put_failure; if (nla_put_u16(skb, MPTCP_ATTR_FAMILY, ssk->sk_family)) goto nla_put_failure; if (nla_put_be16(skb, MPTCP_ATTR_SPORT, issk->inet_sport)) goto nla_put_failure; switch (ssk->sk_family) { case AF_INET: if (nla_put_in_addr(skb, MPTCP_ATTR_SADDR4, issk->inet_saddr)) goto nla_put_failure; break; #if IS_ENABLED(CONFIG_MPTCP_IPV6) case AF_INET6: { const struct ipv6_pinfo *np = inet6_sk(ssk); if (nla_put_in6_addr(skb, MPTCP_ATTR_SADDR6, &np->saddr)) goto nla_put_failure; break; } #endif default: WARN_ON_ONCE(1); goto nla_put_failure; } genlmsg_end(skb, nlh); mptcp_nl_mcast_send(net, skb, GFP_KERNEL); return; nla_put_failure: nlmsg_free(skb); } void mptcp_event(enum mptcp_event_type type, const struct mptcp_sock *msk, const struct sock *ssk, gfp_t gfp) { struct net *net = sock_net((const struct sock *)msk); struct nlmsghdr *nlh; struct sk_buff *skb; if (!genl_has_listeners(&mptcp_genl_family, net, MPTCP_PM_EV_GRP_OFFSET)) return; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); if (!skb) return; nlh = genlmsg_put(skb, 0, 0, &mptcp_genl_family, 0, type); if (!nlh) goto nla_put_failure; switch (type) { case MPTCP_EVENT_UNSPEC: WARN_ON_ONCE(1); break; case MPTCP_EVENT_CREATED: case MPTCP_EVENT_ESTABLISHED: if (mptcp_event_created(skb, msk, ssk) < 0) goto nla_put_failure; break; case MPTCP_EVENT_CLOSED: if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, READ_ONCE(msk->token)) < 0) goto nla_put_failure; break; case MPTCP_EVENT_ANNOUNCED: case MPTCP_EVENT_REMOVED: /* call mptcp_event_addr_announced()/removed instead */ WARN_ON_ONCE(1); break; case MPTCP_EVENT_SUB_ESTABLISHED: case MPTCP_EVENT_SUB_PRIORITY: if (mptcp_event_sub_established(skb, msk, ssk) < 0) goto nla_put_failure; break; case MPTCP_EVENT_SUB_CLOSED: if (mptcp_event_sub_closed(skb, msk, ssk) < 0) goto nla_put_failure; break; case MPTCP_EVENT_LISTENER_CREATED: case MPTCP_EVENT_LISTENER_CLOSED: break; } genlmsg_end(skb, nlh); mptcp_nl_mcast_send(net, skb, gfp); return; nla_put_failure: nlmsg_free(skb); } struct genl_family mptcp_genl_family __ro_after_init = { .name = MPTCP_PM_NAME, .version = MPTCP_PM_VER, .netnsok = true, .module = THIS_MODULE, .ops = mptcp_pm_nl_ops, .n_ops = ARRAY_SIZE(mptcp_pm_nl_ops), .resv_start_op = MPTCP_PM_CMD_SUBFLOW_DESTROY + 1, .mcgrps = mptcp_pm_mcgrps, .n_mcgrps = ARRAY_SIZE(mptcp_pm_mcgrps), }; static int __net_init pm_nl_init_net(struct net *net) { struct pm_nl_pernet *pernet = pm_nl_get_pernet(net); INIT_LIST_HEAD_RCU(&pernet->local_addr_list); /* Cit. 2 subflows ought to be enough for anybody. */ pernet->subflows_max = 2; pernet->next_id = 1; pernet->stale_loss_cnt = 4; spin_lock_init(&pernet->lock); /* No need to initialize other pernet fields, the struct is zeroed at * allocation time. */ return 0; } static void __net_exit pm_nl_exit_net(struct list_head *net_list) { struct net *net; list_for_each_entry(net, net_list, exit_list) { struct pm_nl_pernet *pernet = pm_nl_get_pernet(net); /* net is removed from namespace list, can't race with * other modifiers, also netns core already waited for a * RCU grace period. */ __flush_addrs(&pernet->local_addr_list); } } static struct pernet_operations mptcp_pm_pernet_ops = { .init = pm_nl_init_net, .exit_batch = pm_nl_exit_net, .id = &pm_nl_pernet_id, .size = sizeof(struct pm_nl_pernet), }; void __init mptcp_pm_nl_init(void) { if (register_pernet_subsys(&mptcp_pm_pernet_ops) < 0) panic("Failed to register MPTCP PM pernet subsystem.\n"); if (genl_register_family(&mptcp_genl_family)) panic("Failed to register MPTCP PM netlink family\n"); } |
| 10 11 12 10 10 10 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 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * NILFS Segment buffer prototypes and definitions * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * * Written by Ryusuke Konishi. * */ #ifndef _NILFS_SEGBUF_H #define _NILFS_SEGBUF_H #include <linux/fs.h> #include <linux/buffer_head.h> #include <linux/bio.h> #include <linux/completion.h> /** * struct nilfs_segsum_info - On-memory segment summary * @flags: Flags * @nfinfo: Number of file information structures * @nblocks: Number of blocks included in the partial segment * @nsumblk: Number of summary blocks * @sumbytes: Byte count of segment summary * @nfileblk: Total number of file blocks * @seg_seq: Segment sequence number * @cno: Checkpoint number * @ctime: Creation time * @next: Block number of the next full segment */ struct nilfs_segsum_info { unsigned int flags; unsigned long nfinfo; unsigned long nblocks; unsigned long nsumblk; unsigned long sumbytes; unsigned long nfileblk; u64 seg_seq; __u64 cno; time64_t ctime; sector_t next; }; /** * struct nilfs_segment_buffer - Segment buffer * @sb_super: back pointer to a superblock struct * @sb_list: List head to chain this structure * @sb_sum: On-memory segment summary * @sb_segnum: Index number of the full segment * @sb_nextnum: Index number of the next full segment * @sb_fseg_start: Start block number of the full segment * @sb_fseg_end: End block number of the full segment * @sb_pseg_start: Disk block number of partial segment * @sb_rest_blocks: Number of residual blocks in the current segment * @sb_segsum_buffers: List of buffers for segment summaries * @sb_payload_buffers: List of buffers for segment payload * @sb_super_root: Pointer to buffer storing a super root block (if exists) * @sb_nbio: Number of flying bio requests * @sb_err: I/O error status * @sb_bio_event: Completion event of log writing */ struct nilfs_segment_buffer { struct super_block *sb_super; struct list_head sb_list; /* Segment information */ struct nilfs_segsum_info sb_sum; __u64 sb_segnum; __u64 sb_nextnum; sector_t sb_fseg_start, sb_fseg_end; sector_t sb_pseg_start; unsigned int sb_rest_blocks; /* Buffers */ struct list_head sb_segsum_buffers; struct list_head sb_payload_buffers; /* including super root */ struct buffer_head *sb_super_root; /* io status */ int sb_nbio; atomic_t sb_err; struct completion sb_bio_event; }; #define NILFS_LIST_SEGBUF(head) \ list_entry((head), struct nilfs_segment_buffer, sb_list) #define NILFS_NEXT_SEGBUF(segbuf) NILFS_LIST_SEGBUF((segbuf)->sb_list.next) #define NILFS_PREV_SEGBUF(segbuf) NILFS_LIST_SEGBUF((segbuf)->sb_list.prev) #define NILFS_LAST_SEGBUF(head) NILFS_LIST_SEGBUF((head)->prev) #define NILFS_FIRST_SEGBUF(head) NILFS_LIST_SEGBUF((head)->next) #define NILFS_SEGBUF_IS_LAST(segbuf, head) ((segbuf)->sb_list.next == (head)) #define nilfs_for_each_segbuf_before(s, t, h) \ for ((s) = NILFS_FIRST_SEGBUF(h); (s) != (t); \ (s) = NILFS_NEXT_SEGBUF(s)) #define NILFS_SEGBUF_FIRST_BH(head) \ (list_entry((head)->next, struct buffer_head, b_assoc_buffers)) #define NILFS_SEGBUF_NEXT_BH(bh) \ (list_entry((bh)->b_assoc_buffers.next, struct buffer_head, \ b_assoc_buffers)) #define NILFS_SEGBUF_BH_IS_LAST(bh, head) ((bh)->b_assoc_buffers.next == head) extern struct kmem_cache *nilfs_segbuf_cachep; struct nilfs_segment_buffer *nilfs_segbuf_new(struct super_block *); void nilfs_segbuf_free(struct nilfs_segment_buffer *); void nilfs_segbuf_map(struct nilfs_segment_buffer *, __u64, unsigned long, struct the_nilfs *); void nilfs_segbuf_map_cont(struct nilfs_segment_buffer *segbuf, struct nilfs_segment_buffer *prev); void nilfs_segbuf_set_next_segnum(struct nilfs_segment_buffer *, __u64, struct the_nilfs *); int nilfs_segbuf_reset(struct nilfs_segment_buffer *, unsigned int, time64_t, __u64); int nilfs_segbuf_extend_segsum(struct nilfs_segment_buffer *); int nilfs_segbuf_extend_payload(struct nilfs_segment_buffer *, struct buffer_head **); void nilfs_segbuf_fill_in_segsum(struct nilfs_segment_buffer *); static inline int nilfs_segbuf_simplex(struct nilfs_segment_buffer *segbuf) { unsigned int flags = segbuf->sb_sum.flags; return (flags & (NILFS_SS_LOGBGN | NILFS_SS_LOGEND)) == (NILFS_SS_LOGBGN | NILFS_SS_LOGEND); } static inline int nilfs_segbuf_empty(struct nilfs_segment_buffer *segbuf) { return segbuf->sb_sum.nblocks == segbuf->sb_sum.nsumblk; } static inline void nilfs_segbuf_add_segsum_buffer(struct nilfs_segment_buffer *segbuf, struct buffer_head *bh) { list_add_tail(&bh->b_assoc_buffers, &segbuf->sb_segsum_buffers); segbuf->sb_sum.nblocks++; segbuf->sb_sum.nsumblk++; } static inline void nilfs_segbuf_add_payload_buffer(struct nilfs_segment_buffer *segbuf, struct buffer_head *bh) { list_add_tail(&bh->b_assoc_buffers, &segbuf->sb_payload_buffers); segbuf->sb_sum.nblocks++; } static inline void nilfs_segbuf_add_file_buffer(struct nilfs_segment_buffer *segbuf, struct buffer_head *bh) { get_bh(bh); nilfs_segbuf_add_payload_buffer(segbuf, bh); segbuf->sb_sum.nfileblk++; } void nilfs_clear_logs(struct list_head *logs); void nilfs_truncate_logs(struct list_head *logs, struct nilfs_segment_buffer *last); int nilfs_write_logs(struct list_head *logs, struct the_nilfs *nilfs); int nilfs_wait_on_logs(struct list_head *logs); void nilfs_add_checksums_on_logs(struct list_head *logs, u32 seed); static inline void nilfs_destroy_logs(struct list_head *logs) { nilfs_truncate_logs(logs, NULL); } #endif /* _NILFS_SEGBUF_H */ |
| 4136 4123 4124 37 36 31 340 317 22 40 316 40 275 41 175 14 1 1 247 5 245 243 232 56 177 16 162 147 28 134 4 130 2 128 10 118 8 110 101 100 96 9 91 91 91 91 41 161 59 2 56 55 2 54 2 51 52 2 51 7 42 2 41 3 39 37 6 33 33 33 9 23 33 8 24 17 17 17 33 58 60 365 364 365 3 360 332 364 363 3 106 354 357 233 232 45 47 45 233 233 186 54 187 49 49 49 49 49 48 5 5 5 5 5 5 8 8 8 8 8 8 132 132 132 132 132 130 7 7 85 17 13 13 9 9 56 9 89 54 48 30 42 45 182 45 45 45 45 3 42 54 49 6 49 213 124 7 20 20 3 18 1 3 2 2 4 1 2 14 14 14 14 14 9 8 7 7 12 12 5 12 7 3 53 53 16 16 16 16 235 2 235 7 480 491 483 7 1847 1850 14 8 12 1839 1853 1 8 7 12 1 16 16 15 9 15 15 11 6 9 38 480 484 485 5 4 478 481 457 484 479 28 25 480 476 470 312 431 431 3 3 428 425 169 63 425 91 322 315 289 86 67 19 19 19 6 233 233 233 232 233 2 463 89 172 483 2 14 10 7 14 9 7 2 8 2 2 2 2 36 15 223 15 52 45 52 52 51 1 51 50 3 47 1 45 5 4 39 13 45 45 208 188 196 211 210 206 199 203 200 1 201 194 197 188 107 193 196 203 56 55 55 52 51 51 49 46 3 43 4 39 36 39 39 21 44 50 59 108 56 1 55 54 1 51 51 4 48 47 48 51 29 52 50 11 10 1 8 11 8 8 8 8 7 7 7 7 7 5 8 8 61 58 2 58 59 32 57 57 57 58 56 56 53 29 28 19 16 19 1 17 18 14 17 16 17 16 16 16 16 16 12 12 12 12 12 16 16 11 11 11 12 22 21 32 20 7 18 18 17 15 3 2 2 12 1 10 10 3 7 6 6 6 6 6 9 5 10 10 18 13 13 12 7 7 6 5 5 6 1606 1617 1615 1614 1089 1062 1061 35 35 551 591 587 39 2 36 551 35 35 35 957 35 33 936 47 1 30 30 30 1 1065 1064 1065 1510 23 23 109 1516 1597 1555 1527 1518 1508 62 73 1694 39 19 27 21 7 6 6 7 1668 38 48 76 33 27 26 9 60 1501 1501 1696 1694 1696 1694 2 2 1691 1695 1686 12 1685 1503 1501 1684 17 9 1 1 1671 1 1 1678 1 4 2 1662 6 21 1664 1668 1668 1652 1626 1624 21 1618 4 13 1613 1 1620 1614 1616 1592 1062 1061 1 1060 556 1665 84 116 1670 11 9 1 8 8 8 7 427 427 103 52 52 20 20 21 13 27 8 27 27 53 32 53 32 53 26 7 19 27 27 5 21 53 53 53 52 3 3 3 3 3 3 3 403 410 403 403 402 404 409 387 2 2 2 35 30 25 13 22 4 1 3 3 2 7 6 7 2 1 1 329 328 327 327 324 324 324 1 323 2 329 321 3 344 344 328 748 130 190 15 12 11 11 10 1 191 9 1 69 67 65 4 4 28 58 56 56 56 54 13 42 40 39 52 49 1 51 16 6 17 17 11 11 50 36 37 15 14 9 21 20 20 5 4 8 14 12 13 38 37 36 35 16 4 10 4 928 922 890 923 912 920 918 915 10 9 7 6 6 10 6 8 6 4 4 3 4 4 4 2 6 5 4 4 3 2 2 2 1 3 3 3 3 2 6 9 9 9 1 9 5 1 8 9 9 6 6 3 7 31 30 29 34 3 35 34 34 3 2 3 3 32 33 4 1 28 28 8 9 9 25 1 22 6 6 18 24 3 2 1 1 1 1 1 1 24 1 9 8 2 2 6 1 20 2 5 3 17 1 2 2 20 5 20 19 2 1 1 20 1 3 1 1 20 1 3 3 2 1 1 1 1 20 1 3 2 1 2 1 21 21 5 5 1 5 5 1 3 5 12 18 11 12 12 12 7 7 63 65 64 35 29 6 23 6 17 18 258 256 3 3 253 1 250 7 7 7 6 6 6 6 5 5 2 3 3 3 3 6 3 16 16 16 16 16 16 11 11 11 7 6 6 1 7 116 117 112 110 82 110 109 106 82 17 69 61 28 23 58 56 144 3 143 5 141 131 14 2 2 23 17 17 9 63 2 65 2 63 63 139 83 15 16 14 15 14 1 14 8 1 5 12 10 1 8 11 8 9 8 83 7 7 21 4 6 7 6 4 4 5 3 4 4 4 2 1 36 36 36 36 38 37 37 36 7 6 5 1 9 9 8 1 7 2 5 3 3 1 4 4 1 4 7 8 7 7 4124 3896 4133 4148 4117 4111 486 53 210 54 109 14 1690 11 8 57 37 38 933 5 2 2 4 6 65 1084 259 8 16 34 28 18 67 12 403 16 4 1 38 7 98 9 8 4118 2 2 11 27 10 3 3 2 4 42 4 4 3 39 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 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 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com */ #include <linux/bpf.h> #include <linux/bpf-cgroup.h> #include <linux/bpf_trace.h> #include <linux/bpf_lirc.h> #include <linux/bpf_verifier.h> #include <linux/bsearch.h> #include <linux/btf.h> #include <linux/syscalls.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/vmalloc.h> #include <linux/mmzone.h> #include <linux/anon_inodes.h> #include <linux/fdtable.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/license.h> #include <linux/filter.h> #include <linux/kernel.h> #include <linux/idr.h> #include <linux/cred.h> #include <linux/timekeeping.h> #include <linux/ctype.h> #include <linux/nospec.h> #include <linux/audit.h> #include <uapi/linux/btf.h> #include <linux/pgtable.h> #include <linux/bpf_lsm.h> #include <linux/poll.h> #include <linux/sort.h> #include <linux/bpf-netns.h> #include <linux/rcupdate_trace.h> #include <linux/memcontrol.h> #include <linux/trace_events.h> #include <linux/tracepoint.h> #include <net/netfilter/nf_bpf_link.h> #include <net/netkit.h> #include <net/tcx.h> #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \ (map)->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) #define IS_FD_PROG_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY) #define IS_FD_HASH(map) ((map)->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) #define IS_FD_MAP(map) (IS_FD_ARRAY(map) || IS_FD_PROG_ARRAY(map) || \ IS_FD_HASH(map)) #define BPF_OBJ_FLAG_MASK (BPF_F_RDONLY | BPF_F_WRONLY) DEFINE_PER_CPU(int, bpf_prog_active); static DEFINE_IDR(prog_idr); static DEFINE_SPINLOCK(prog_idr_lock); static DEFINE_IDR(map_idr); static DEFINE_SPINLOCK(map_idr_lock); static DEFINE_IDR(link_idr); static DEFINE_SPINLOCK(link_idr_lock); int sysctl_unprivileged_bpf_disabled __read_mostly = IS_BUILTIN(CONFIG_BPF_UNPRIV_DEFAULT_OFF) ? 2 : 0; static const struct bpf_map_ops * const bpf_map_types[] = { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) #define BPF_MAP_TYPE(_id, _ops) \ [_id] = &_ops, #define BPF_LINK_TYPE(_id, _name) #include <linux/bpf_types.h> #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE }; /* * If we're handed a bigger struct than we know of, ensure all the unknown bits * are 0 - i.e. new user-space does not rely on any kernel feature extensions * we don't know about yet. * * There is a ToCToU between this function call and the following * copy_from_user() call. However, this is not a concern since this function is * meant to be a future-proofing of bits. */ int bpf_check_uarg_tail_zero(bpfptr_t uaddr, size_t expected_size, size_t actual_size) { int res; if (unlikely(actual_size > PAGE_SIZE)) /* silly large */ return -E2BIG; if (actual_size <= expected_size) return 0; if (uaddr.is_kernel) res = memchr_inv(uaddr.kernel + expected_size, 0, actual_size - expected_size) == NULL; else res = check_zeroed_user(uaddr.user + expected_size, actual_size - expected_size); if (res < 0) return res; return res ? 0 : -E2BIG; } const struct bpf_map_ops bpf_map_offload_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc = bpf_map_offload_map_alloc, .map_free = bpf_map_offload_map_free, .map_check_btf = map_check_no_btf, .map_mem_usage = bpf_map_offload_map_mem_usage, }; static void bpf_map_write_active_inc(struct bpf_map *map) { atomic64_inc(&map->writecnt); } static void bpf_map_write_active_dec(struct bpf_map *map) { atomic64_dec(&map->writecnt); } bool bpf_map_write_active(const struct bpf_map *map) { return atomic64_read(&map->writecnt) != 0; } static u32 bpf_map_value_size(const struct bpf_map *map) { if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY || map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) return round_up(map->value_size, 8) * num_possible_cpus(); else if (IS_FD_MAP(map)) return sizeof(u32); else return map->value_size; } static void maybe_wait_bpf_programs(struct bpf_map *map) { /* Wait for any running non-sleepable BPF programs to complete so that * userspace, when we return to it, knows that all non-sleepable * programs that could be running use the new map value. For sleepable * BPF programs, synchronize_rcu_tasks_trace() should be used to wait * for the completions of these programs, but considering the waiting * time can be very long and userspace may think it will hang forever, * so don't handle sleepable BPF programs now. */ if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS || map->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) synchronize_rcu(); } static void unpin_uptr_kaddr(void *kaddr) { if (kaddr) unpin_user_page(virt_to_page(kaddr)); } static void __bpf_obj_unpin_uptrs(struct btf_record *rec, u32 cnt, void *obj) { const struct btf_field *field; void **uptr_addr; int i; for (i = 0, field = rec->fields; i < cnt; i++, field++) { if (field->type != BPF_UPTR) continue; uptr_addr = obj + field->offset; unpin_uptr_kaddr(*uptr_addr); } } static void bpf_obj_unpin_uptrs(struct btf_record *rec, void *obj) { if (!btf_record_has_field(rec, BPF_UPTR)) return; __bpf_obj_unpin_uptrs(rec, rec->cnt, obj); } static int bpf_obj_pin_uptrs(struct btf_record *rec, void *obj) { const struct btf_field *field; const struct btf_type *t; unsigned long start, end; struct page *page; void **uptr_addr; int i, err; if (!btf_record_has_field(rec, BPF_UPTR)) return 0; for (i = 0, field = rec->fields; i < rec->cnt; i++, field++) { if (field->type != BPF_UPTR) continue; uptr_addr = obj + field->offset; start = *(unsigned long *)uptr_addr; if (!start) continue; t = btf_type_by_id(field->kptr.btf, field->kptr.btf_id); /* t->size was checked for zero before */ if (check_add_overflow(start, t->size - 1, &end)) { err = -EFAULT; goto unpin_all; } /* The uptr's struct cannot span across two pages */ if ((start & PAGE_MASK) != (end & PAGE_MASK)) { err = -EOPNOTSUPP; goto unpin_all; } err = pin_user_pages_fast(start, 1, FOLL_LONGTERM | FOLL_WRITE, &page); if (err != 1) goto unpin_all; if (PageHighMem(page)) { err = -EOPNOTSUPP; unpin_user_page(page); goto unpin_all; } *uptr_addr = page_address(page) + offset_in_page(start); } return 0; unpin_all: __bpf_obj_unpin_uptrs(rec, i, obj); return err; } static int bpf_map_update_value(struct bpf_map *map, struct file *map_file, void *key, void *value, __u64 flags) { int err; /* Need to create a kthread, thus must support schedule */ if (bpf_map_is_offloaded(map)) { return bpf_map_offload_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_CPUMAP || map->map_type == BPF_MAP_TYPE_ARENA || map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { return map->ops->map_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_SOCKHASH || map->map_type == BPF_MAP_TYPE_SOCKMAP) { return sock_map_update_elem_sys(map, key, value, flags); } else if (IS_FD_PROG_ARRAY(map)) { return bpf_fd_array_map_update_elem(map, map_file, key, value, flags); } bpf_disable_instrumentation(); if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { err = bpf_percpu_hash_update(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_update(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { err = bpf_percpu_cgroup_storage_update(map, key, value, flags); } else if (IS_FD_ARRAY(map)) { err = bpf_fd_array_map_update_elem(map, map_file, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_HASH_OF_MAPS) { err = bpf_fd_htab_map_update_elem(map, map_file, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { /* rcu_read_lock() is not needed */ err = bpf_fd_reuseport_array_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_QUEUE || map->map_type == BPF_MAP_TYPE_STACK || map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { err = map->ops->map_push_elem(map, value, flags); } else { err = bpf_obj_pin_uptrs(map->record, value); if (!err) { rcu_read_lock(); err = map->ops->map_update_elem(map, key, value, flags); rcu_read_unlock(); if (err) bpf_obj_unpin_uptrs(map->record, value); } } bpf_enable_instrumentation(); return err; } static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, __u64 flags) { void *ptr; int err; if (bpf_map_is_offloaded(map)) return bpf_map_offload_lookup_elem(map, key, value); bpf_disable_instrumentation(); if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { err = bpf_percpu_hash_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE) { err = bpf_percpu_cgroup_storage_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_STACK_TRACE) { err = bpf_stackmap_copy(map, key, value); } else if (IS_FD_ARRAY(map) || IS_FD_PROG_ARRAY(map)) { err = bpf_fd_array_map_lookup_elem(map, key, value); } else if (IS_FD_HASH(map)) { err = bpf_fd_htab_map_lookup_elem(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { err = bpf_fd_reuseport_array_lookup_elem(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_QUEUE || map->map_type == BPF_MAP_TYPE_STACK || map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { err = map->ops->map_peek_elem(map, value); } else if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { /* struct_ops map requires directly updating "value" */ err = bpf_struct_ops_map_sys_lookup_elem(map, key, value); } else { rcu_read_lock(); if (map->ops->map_lookup_elem_sys_only) ptr = map->ops->map_lookup_elem_sys_only(map, key); else ptr = map->ops->map_lookup_elem(map, key); if (IS_ERR(ptr)) { err = PTR_ERR(ptr); } else if (!ptr) { err = -ENOENT; } else { err = 0; if (flags & BPF_F_LOCK) /* lock 'ptr' and copy everything but lock */ copy_map_value_locked(map, value, ptr, true); else copy_map_value(map, value, ptr); /* mask lock and timer, since value wasn't zero inited */ check_and_init_map_value(map, value); } rcu_read_unlock(); } bpf_enable_instrumentation(); return err; } /* Please, do not use this function outside from the map creation path * (e.g. in map update path) without taking care of setting the active * memory cgroup (see at bpf_map_kmalloc_node() for example). */ static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable) { /* We really just want to fail instead of triggering OOM killer * under memory pressure, therefore we set __GFP_NORETRY to kmalloc, * which is used for lower order allocation requests. * * It has been observed that higher order allocation requests done by * vmalloc with __GFP_NORETRY being set might fail due to not trying * to reclaim memory from the page cache, thus we set * __GFP_RETRY_MAYFAIL to avoid such situations. */ gfp_t gfp = bpf_memcg_flags(__GFP_NOWARN | __GFP_ZERO); unsigned int flags = 0; unsigned long align = 1; void *area; if (size >= SIZE_MAX) return NULL; /* kmalloc()'ed memory can't be mmap()'ed */ if (mmapable) { BUG_ON(!PAGE_ALIGNED(size)); align = SHMLBA; flags = VM_USERMAP; } else if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) { area = kmalloc_node(size, gfp | GFP_USER | __GFP_NORETRY, numa_node); if (area != NULL) return area; } return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END, gfp | GFP_KERNEL | __GFP_RETRY_MAYFAIL, PAGE_KERNEL, flags, numa_node, __builtin_return_address(0)); } void *bpf_map_area_alloc(u64 size, int numa_node) { return __bpf_map_area_alloc(size, numa_node, false); } void *bpf_map_area_mmapable_alloc(u64 size, int numa_node) { return __bpf_map_area_alloc(size, numa_node, true); } void bpf_map_area_free(void *area) { kvfree(area); } static u32 bpf_map_flags_retain_permanent(u32 flags) { /* Some map creation flags are not tied to the map object but * rather to the map fd instead, so they have no meaning upon * map object inspection since multiple file descriptors with * different (access) properties can exist here. Thus, given * this has zero meaning for the map itself, lets clear these * from here. */ return flags & ~(BPF_F_RDONLY | BPF_F_WRONLY); } void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr) { map->map_type = attr->map_type; map->key_size = attr->key_size; map->value_size = attr->value_size; map->max_entries = attr->max_entries; map->map_flags = bpf_map_flags_retain_permanent(attr->map_flags); map->numa_node = bpf_map_attr_numa_node(attr); map->map_extra = attr->map_extra; } static int bpf_map_alloc_id(struct bpf_map *map) { int id; idr_preload(GFP_KERNEL); spin_lock_bh(&map_idr_lock); id = idr_alloc_cyclic(&map_idr, map, 1, INT_MAX, GFP_ATOMIC); if (id > 0) map->id = id; spin_unlock_bh(&map_idr_lock); idr_preload_end(); if (WARN_ON_ONCE(!id)) return -ENOSPC; return id > 0 ? 0 : id; } void bpf_map_free_id(struct bpf_map *map) { unsigned long flags; /* Offloaded maps are removed from the IDR store when their device * disappears - even if someone holds an fd to them they are unusable, * the memory is gone, all ops will fail; they are simply waiting for * refcnt to drop to be freed. */ if (!map->id) return; spin_lock_irqsave(&map_idr_lock, flags); idr_remove(&map_idr, map->id); map->id = 0; spin_unlock_irqrestore(&map_idr_lock, flags); } #ifdef CONFIG_MEMCG static void bpf_map_save_memcg(struct bpf_map *map) { /* Currently if a map is created by a process belonging to the root * memory cgroup, get_obj_cgroup_from_current() will return NULL. * So we have to check map->objcg for being NULL each time it's * being used. */ if (memcg_bpf_enabled()) map->objcg = get_obj_cgroup_from_current(); } static void bpf_map_release_memcg(struct bpf_map *map) { if (map->objcg) obj_cgroup_put(map->objcg); } static struct mem_cgroup *bpf_map_get_memcg(const struct bpf_map *map) { if (map->objcg) return get_mem_cgroup_from_objcg(map->objcg); return root_mem_cgroup; } void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, int node) { struct mem_cgroup *memcg, *old_memcg; void *ptr; memcg = bpf_map_get_memcg(map); old_memcg = set_active_memcg(memcg); ptr = kmalloc_node(size, flags | __GFP_ACCOUNT, node); set_active_memcg(old_memcg); mem_cgroup_put(memcg); return ptr; } void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags) { struct mem_cgroup *memcg, *old_memcg; void *ptr; memcg = bpf_map_get_memcg(map); old_memcg = set_active_memcg(memcg); ptr = kzalloc(size, flags | __GFP_ACCOUNT); set_active_memcg(old_memcg); mem_cgroup_put(memcg); return ptr; } void *bpf_map_kvcalloc(struct bpf_map *map, size_t n, size_t size, gfp_t flags) { struct mem_cgroup *memcg, *old_memcg; void *ptr; memcg = bpf_map_get_memcg(map); old_memcg = set_active_memcg(memcg); ptr = kvcalloc(n, size, flags | __GFP_ACCOUNT); set_active_memcg(old_memcg); mem_cgroup_put(memcg); return ptr; } void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align, gfp_t flags) { struct mem_cgroup *memcg, *old_memcg; void __percpu *ptr; memcg = bpf_map_get_memcg(map); old_memcg = set_active_memcg(memcg); ptr = __alloc_percpu_gfp(size, align, flags | __GFP_ACCOUNT); set_active_memcg(old_memcg); mem_cgroup_put(memcg); return ptr; } #else static void bpf_map_save_memcg(struct bpf_map *map) { } static void bpf_map_release_memcg(struct bpf_map *map) { } #endif int bpf_map_alloc_pages(const struct bpf_map *map, gfp_t gfp, int nid, unsigned long nr_pages, struct page **pages) { unsigned long i, j; struct page *pg; int ret = 0; #ifdef CONFIG_MEMCG struct mem_cgroup *memcg, *old_memcg; memcg = bpf_map_get_memcg(map); old_memcg = set_active_memcg(memcg); #endif for (i = 0; i < nr_pages; i++) { pg = alloc_pages_node(nid, gfp | __GFP_ACCOUNT, 0); if (pg) { pages[i] = pg; continue; } for (j = 0; j < i; j++) __free_page(pages[j]); ret = -ENOMEM; break; } #ifdef CONFIG_MEMCG set_active_memcg(old_memcg); mem_cgroup_put(memcg); #endif return ret; } static int btf_field_cmp(const void *a, const void *b) { const struct btf_field *f1 = a, *f2 = b; if (f1->offset < f2->offset) return -1; else if (f1->offset > f2->offset) return 1; return 0; } struct btf_field *btf_record_find(const struct btf_record *rec, u32 offset, u32 field_mask) { struct btf_field *field; if (IS_ERR_OR_NULL(rec) || !(rec->field_mask & field_mask)) return NULL; field = bsearch(&offset, rec->fields, rec->cnt, sizeof(rec->fields[0]), btf_field_cmp); if (!field || !(field->type & field_mask)) return NULL; return field; } void btf_record_free(struct btf_record *rec) { int i; if (IS_ERR_OR_NULL(rec)) return; for (i = 0; i < rec->cnt; i++) { switch (rec->fields[i].type) { case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: case BPF_UPTR: if (rec->fields[i].kptr.module) module_put(rec->fields[i].kptr.module); if (btf_is_kernel(rec->fields[i].kptr.btf)) btf_put(rec->fields[i].kptr.btf); break; case BPF_LIST_HEAD: case BPF_LIST_NODE: case BPF_RB_ROOT: case BPF_RB_NODE: case BPF_SPIN_LOCK: case BPF_TIMER: case BPF_REFCOUNT: case BPF_WORKQUEUE: /* Nothing to release */ break; default: WARN_ON_ONCE(1); continue; } } kfree(rec); } void bpf_map_free_record(struct bpf_map *map) { btf_record_free(map->record); map->record = NULL; } struct btf_record *btf_record_dup(const struct btf_record *rec) { const struct btf_field *fields; struct btf_record *new_rec; int ret, size, i; if (IS_ERR_OR_NULL(rec)) return NULL; size = offsetof(struct btf_record, fields[rec->cnt]); new_rec = kmemdup(rec, size, GFP_KERNEL | __GFP_NOWARN); if (!new_rec) return ERR_PTR(-ENOMEM); /* Do a deep copy of the btf_record */ fields = rec->fields; new_rec->cnt = 0; for (i = 0; i < rec->cnt; i++) { switch (fields[i].type) { case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: case BPF_UPTR: if (btf_is_kernel(fields[i].kptr.btf)) btf_get(fields[i].kptr.btf); if (fields[i].kptr.module && !try_module_get(fields[i].kptr.module)) { ret = -ENXIO; goto free; } break; case BPF_LIST_HEAD: case BPF_LIST_NODE: case BPF_RB_ROOT: case BPF_RB_NODE: case BPF_SPIN_LOCK: case BPF_TIMER: case BPF_REFCOUNT: case BPF_WORKQUEUE: /* Nothing to acquire */ break; default: ret = -EFAULT; WARN_ON_ONCE(1); goto free; } new_rec->cnt++; } return new_rec; free: btf_record_free(new_rec); return ERR_PTR(ret); } bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *rec_b) { bool a_has_fields = !IS_ERR_OR_NULL(rec_a), b_has_fields = !IS_ERR_OR_NULL(rec_b); int size; if (!a_has_fields && !b_has_fields) return true; if (a_has_fields != b_has_fields) return false; if (rec_a->cnt != rec_b->cnt) return false; size = offsetof(struct btf_record, fields[rec_a->cnt]); /* btf_parse_fields uses kzalloc to allocate a btf_record, so unused * members are zeroed out. So memcmp is safe to do without worrying * about padding/unused fields. * * While spin_lock, timer, and kptr have no relation to map BTF, * list_head metadata is specific to map BTF, the btf and value_rec * members in particular. btf is the map BTF, while value_rec points to * btf_record in that map BTF. * * So while by default, we don't rely on the map BTF (which the records * were parsed from) matching for both records, which is not backwards * compatible, in case list_head is part of it, we implicitly rely on * that by way of depending on memcmp succeeding for it. */ return !memcmp(rec_a, rec_b, size); } void bpf_obj_free_timer(const struct btf_record *rec, void *obj) { if (WARN_ON_ONCE(!btf_record_has_field(rec, BPF_TIMER))) return; bpf_timer_cancel_and_free(obj + rec->timer_off); } void bpf_obj_free_workqueue(const struct btf_record *rec, void *obj) { if (WARN_ON_ONCE(!btf_record_has_field(rec, BPF_WORKQUEUE))) return; bpf_wq_cancel_and_free(obj + rec->wq_off); } void bpf_obj_free_fields(const struct btf_record *rec, void *obj) { const struct btf_field *fields; int i; if (IS_ERR_OR_NULL(rec)) return; fields = rec->fields; for (i = 0; i < rec->cnt; i++) { struct btf_struct_meta *pointee_struct_meta; const struct btf_field *field = &fields[i]; void *field_ptr = obj + field->offset; void *xchgd_field; switch (fields[i].type) { case BPF_SPIN_LOCK: break; case BPF_TIMER: bpf_timer_cancel_and_free(field_ptr); break; case BPF_WORKQUEUE: bpf_wq_cancel_and_free(field_ptr); break; case BPF_KPTR_UNREF: WRITE_ONCE(*(u64 *)field_ptr, 0); break; case BPF_KPTR_REF: case BPF_KPTR_PERCPU: xchgd_field = (void *)xchg((unsigned long *)field_ptr, 0); if (!xchgd_field) break; if (!btf_is_kernel(field->kptr.btf)) { pointee_struct_meta = btf_find_struct_meta(field->kptr.btf, field->kptr.btf_id); __bpf_obj_drop_impl(xchgd_field, pointee_struct_meta ? pointee_struct_meta->record : NULL, fields[i].type == BPF_KPTR_PERCPU); } else { field->kptr.dtor(xchgd_field); } break; case BPF_UPTR: /* The caller ensured that no one is using the uptr */ unpin_uptr_kaddr(*(void **)field_ptr); break; case BPF_LIST_HEAD: if (WARN_ON_ONCE(rec->spin_lock_off < 0)) continue; bpf_list_head_free(field, field_ptr, obj + rec->spin_lock_off); break; case BPF_RB_ROOT: if (WARN_ON_ONCE(rec->spin_lock_off < 0)) continue; bpf_rb_root_free(field, field_ptr, obj + rec->spin_lock_off); break; case BPF_LIST_NODE: case BPF_RB_NODE: case BPF_REFCOUNT: break; default: WARN_ON_ONCE(1); continue; } } } static void bpf_map_free(struct bpf_map *map) { struct btf_record *rec = map->record; struct btf *btf = map->btf; /* implementation dependent freeing. Disabling migration to simplify * the free of values or special fields allocated from bpf memory * allocator. */ migrate_disable(); map->ops->map_free(map); migrate_enable(); /* Delay freeing of btf_record for maps, as map_free * callback usually needs access to them. It is better to do it here * than require each callback to do the free itself manually. * * Note that the btf_record stashed in map->inner_map_meta->record was * already freed using the map_free callback for map in map case which * eventually calls bpf_map_free_meta, since inner_map_meta is only a * template bpf_map struct used during verification. */ btf_record_free(rec); /* Delay freeing of btf for maps, as map_free callback may need * struct_meta info which will be freed with btf_put(). */ btf_put(btf); } /* called from workqueue */ static void bpf_map_free_deferred(struct work_struct *work) { struct bpf_map *map = container_of(work, struct bpf_map, work); security_bpf_map_free(map); bpf_map_release_memcg(map); bpf_map_free(map); } static void bpf_map_put_uref(struct bpf_map *map) { if (atomic64_dec_and_test(&map->usercnt)) { if (map->ops->map_release_uref) map->ops->map_release_uref(map); } } static void bpf_map_free_in_work(struct bpf_map *map) { INIT_WORK(&map->work, bpf_map_free_deferred); /* Avoid spawning kworkers, since they all might contend * for the same mutex like slab_mutex. */ queue_work(system_unbound_wq, &map->work); } static void bpf_map_free_rcu_gp(struct rcu_head *rcu) { bpf_map_free_in_work(container_of(rcu, struct bpf_map, rcu)); } static void bpf_map_free_mult_rcu_gp(struct rcu_head *rcu) { if (rcu_trace_implies_rcu_gp()) bpf_map_free_rcu_gp(rcu); else call_rcu(rcu, bpf_map_free_rcu_gp); } /* decrement map refcnt and schedule it for freeing via workqueue * (underlying map implementation ops->map_free() might sleep) */ void bpf_map_put(struct bpf_map *map) { if (atomic64_dec_and_test(&map->refcnt)) { /* bpf_map_free_id() must be called first */ bpf_map_free_id(map); WARN_ON_ONCE(atomic64_read(&map->sleepable_refcnt)); if (READ_ONCE(map->free_after_mult_rcu_gp)) call_rcu_tasks_trace(&map->rcu, bpf_map_free_mult_rcu_gp); else if (READ_ONCE(map->free_after_rcu_gp)) call_rcu(&map->rcu, bpf_map_free_rcu_gp); else bpf_map_free_in_work(map); } } EXPORT_SYMBOL_GPL(bpf_map_put); void bpf_map_put_with_uref(struct bpf_map *map) { bpf_map_put_uref(map); bpf_map_put(map); } static int bpf_map_release(struct inode *inode, struct file *filp) { struct bpf_map *map = filp->private_data; if (map->ops->map_release) map->ops->map_release(map, filp); bpf_map_put_with_uref(map); return 0; } static fmode_t map_get_sys_perms(struct bpf_map *map, struct fd f) { fmode_t mode = fd_file(f)->f_mode; /* Our file permissions may have been overridden by global * map permissions facing syscall side. */ if (READ_ONCE(map->frozen)) mode &= ~FMODE_CAN_WRITE; return mode; } #ifdef CONFIG_PROC_FS /* Show the memory usage of a bpf map */ static u64 bpf_map_memory_usage(const struct bpf_map *map) { return map->ops->map_mem_usage(map); } static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) { struct bpf_map *map = filp->private_data; u32 type = 0, jited = 0; if (map_type_contains_progs(map)) { spin_lock(&map->owner.lock); type = map->owner.type; jited = map->owner.jited; spin_unlock(&map->owner.lock); } seq_printf(m, "map_type:\t%u\n" "key_size:\t%u\n" "value_size:\t%u\n" "max_entries:\t%u\n" "map_flags:\t%#x\n" "map_extra:\t%#llx\n" "memlock:\t%llu\n" "map_id:\t%u\n" "frozen:\t%u\n", map->map_type, map->key_size, map->value_size, map->max_entries, map->map_flags, (unsigned long long)map->map_extra, bpf_map_memory_usage(map), map->id, READ_ONCE(map->frozen)); if (type) { seq_printf(m, "owner_prog_type:\t%u\n", type); seq_printf(m, "owner_jited:\t%u\n", jited); } } #endif static ssize_t bpf_dummy_read(struct file *filp, char __user *buf, size_t siz, loff_t *ppos) { /* We need this handler such that alloc_file() enables * f_mode with FMODE_CAN_READ. */ return -EINVAL; } static ssize_t bpf_dummy_write(struct file *filp, const char __user *buf, size_t siz, loff_t *ppos) { /* We need this handler such that alloc_file() enables * f_mode with FMODE_CAN_WRITE. */ return -EINVAL; } /* called for any extra memory-mapped regions (except initial) */ static void bpf_map_mmap_open(struct vm_area_struct *vma) { struct bpf_map *map = vma->vm_file->private_data; if (vma->vm_flags & VM_MAYWRITE) bpf_map_write_active_inc(map); } /* called for all unmapped memory region (including initial) */ static void bpf_map_mmap_close(struct vm_area_struct *vma) { struct bpf_map *map = vma->vm_file->private_data; if (vma->vm_flags & VM_MAYWRITE) bpf_map_write_active_dec(map); } static const struct vm_operations_struct bpf_map_default_vmops = { .open = bpf_map_mmap_open, .close = bpf_map_mmap_close, }; static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) { struct bpf_map *map = filp->private_data; int err = 0; if (!map->ops->map_mmap || !IS_ERR_OR_NULL(map->record)) return -ENOTSUPP; if (!(vma->vm_flags & VM_SHARED)) return -EINVAL; mutex_lock(&map->freeze_mutex); if (vma->vm_flags & VM_WRITE) { if (map->frozen) { err = -EPERM; goto out; } /* map is meant to be read-only, so do not allow mapping as * writable, because it's possible to leak a writable page * reference and allows user-space to still modify it after * freezing, while verifier will assume contents do not change */ if (map->map_flags & BPF_F_RDONLY_PROG) { err = -EACCES; goto out; } bpf_map_write_active_inc(map); } out: mutex_unlock(&map->freeze_mutex); if (err) return err; /* set default open/close callbacks */ vma->vm_ops = &bpf_map_default_vmops; vma->vm_private_data = map; vm_flags_clear(vma, VM_MAYEXEC); /* If mapping is read-only, then disallow potentially re-mapping with * PROT_WRITE by dropping VM_MAYWRITE flag. This VM_MAYWRITE clearing * means that as far as BPF map's memory-mapped VMAs are concerned, * VM_WRITE and VM_MAYWRITE and equivalent, if one of them is set, * both should be set, so we can forget about VM_MAYWRITE and always * check just VM_WRITE */ if (!(vma->vm_flags & VM_WRITE)) vm_flags_clear(vma, VM_MAYWRITE); err = map->ops->map_mmap(map, vma); if (err) { if (vma->vm_flags & VM_WRITE) bpf_map_write_active_dec(map); } return err; } static __poll_t bpf_map_poll(struct file *filp, struct poll_table_struct *pts) { struct bpf_map *map = filp->private_data; if (map->ops->map_poll) return map->ops->map_poll(map, filp, pts); return EPOLLERR; } static unsigned long bpf_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct bpf_map *map = filp->private_data; if (map->ops->map_get_unmapped_area) return map->ops->map_get_unmapped_area(filp, addr, len, pgoff, flags); #ifdef CONFIG_MMU return mm_get_unmapped_area(current->mm, filp, addr, len, pgoff, flags); #else return addr; #endif } const struct file_operations bpf_map_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_map_show_fdinfo, #endif .release = bpf_map_release, .read = bpf_dummy_read, .write = bpf_dummy_write, .mmap = bpf_map_mmap, .poll = bpf_map_poll, .get_unmapped_area = bpf_get_unmapped_area, }; int bpf_map_new_fd(struct bpf_map *map, int flags) { int ret; ret = security_bpf_map(map, OPEN_FMODE(flags)); if (ret < 0) return ret; return anon_inode_getfd("bpf-map", &bpf_map_fops, map, flags | O_CLOEXEC); } int bpf_get_file_flag(int flags) { if ((flags & BPF_F_RDONLY) && (flags & BPF_F_WRONLY)) return -EINVAL; if (flags & BPF_F_RDONLY) return O_RDONLY; if (flags & BPF_F_WRONLY) return O_WRONLY; return O_RDWR; } /* helper macro to check that unused fields 'union bpf_attr' are zero */ #define CHECK_ATTR(CMD) \ memchr_inv((void *) &attr->CMD##_LAST_FIELD + \ sizeof(attr->CMD##_LAST_FIELD), 0, \ sizeof(*attr) - \ offsetof(union bpf_attr, CMD##_LAST_FIELD) - \ sizeof(attr->CMD##_LAST_FIELD)) != NULL /* dst and src must have at least "size" number of bytes. * Return strlen on success and < 0 on error. */ int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size) { const char *end = src + size; const char *orig_src = src; memset(dst, 0, size); /* Copy all isalnum(), '_' and '.' chars. */ while (src < end && *src) { if (!isalnum(*src) && *src != '_' && *src != '.') return -EINVAL; *dst++ = *src++; } /* No '\0' found in "size" number of bytes */ if (src == end) return -EINVAL; return src - orig_src; } int map_check_no_btf(const struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) { return -ENOTSUPP; } static int map_check_btf(struct bpf_map *map, struct bpf_token *token, const struct btf *btf, u32 btf_key_id, u32 btf_value_id) { const struct btf_type *key_type, *value_type; u32 key_size, value_size; int ret = 0; /* Some maps allow key to be unspecified. */ if (btf_key_id) { key_type = btf_type_id_size(btf, &btf_key_id, &key_size); if (!key_type || key_size != map->key_size) return -EINVAL; } else { key_type = btf_type_by_id(btf, 0); if (!map->ops->map_check_btf) return -EINVAL; } value_type = btf_type_id_size(btf, &btf_value_id, &value_size); if (!value_type || value_size != map->value_size) return -EINVAL; map->record = btf_parse_fields(btf, value_type, BPF_SPIN_LOCK | BPF_TIMER | BPF_KPTR | BPF_LIST_HEAD | BPF_RB_ROOT | BPF_REFCOUNT | BPF_WORKQUEUE | BPF_UPTR, map->value_size); if (!IS_ERR_OR_NULL(map->record)) { int i; if (!bpf_token_capable(token, CAP_BPF)) { ret = -EPERM; goto free_map_tab; } if (map->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG)) { ret = -EACCES; goto free_map_tab; } for (i = 0; i < sizeof(map->record->field_mask) * 8; i++) { switch (map->record->field_mask & (1 << i)) { case 0: continue; case BPF_SPIN_LOCK: if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_ARRAY && map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE && map->map_type != BPF_MAP_TYPE_SK_STORAGE && map->map_type != BPF_MAP_TYPE_INODE_STORAGE && map->map_type != BPF_MAP_TYPE_TASK_STORAGE && map->map_type != BPF_MAP_TYPE_CGRP_STORAGE) { ret = -EOPNOTSUPP; goto free_map_tab; } break; case BPF_TIMER: case BPF_WORKQUEUE: if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_LRU_HASH && map->map_type != BPF_MAP_TYPE_ARRAY) { ret = -EOPNOTSUPP; goto free_map_tab; } break; case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: case BPF_REFCOUNT: if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_PERCPU_HASH && map->map_type != BPF_MAP_TYPE_LRU_HASH && map->map_type != BPF_MAP_TYPE_LRU_PERCPU_HASH && map->map_type != BPF_MAP_TYPE_ARRAY && map->map_type != BPF_MAP_TYPE_PERCPU_ARRAY && map->map_type != BPF_MAP_TYPE_SK_STORAGE && map->map_type != BPF_MAP_TYPE_INODE_STORAGE && map->map_type != BPF_MAP_TYPE_TASK_STORAGE && map->map_type != BPF_MAP_TYPE_CGRP_STORAGE) { ret = -EOPNOTSUPP; goto free_map_tab; } break; case BPF_UPTR: if (map->map_type != BPF_MAP_TYPE_TASK_STORAGE) { ret = -EOPNOTSUPP; goto free_map_tab; } break; case BPF_LIST_HEAD: case BPF_RB_ROOT: if (map->map_type != BPF_MAP_TYPE_HASH && map->map_type != BPF_MAP_TYPE_LRU_HASH && map->map_type != BPF_MAP_TYPE_ARRAY) { ret = -EOPNOTSUPP; goto free_map_tab; } break; default: /* Fail if map_type checks are missing for a field type */ ret = -EOPNOTSUPP; goto free_map_tab; } } } ret = btf_check_and_fixup_fields(btf, map->record); if (ret < 0) goto free_map_tab; if (map->ops->map_check_btf) { ret = map->ops->map_check_btf(map, btf, key_type, value_type); if (ret < 0) goto free_map_tab; } return ret; free_map_tab: bpf_map_free_record(map); return ret; } static bool bpf_net_capable(void) { return capable(CAP_NET_ADMIN) || capable(CAP_SYS_ADMIN); } #define BPF_MAP_CREATE_LAST_FIELD map_token_fd /* called via syscall */ static int map_create(union bpf_attr *attr) { const struct bpf_map_ops *ops; struct bpf_token *token = NULL; int numa_node = bpf_map_attr_numa_node(attr); u32 map_type = attr->map_type; struct bpf_map *map; bool token_flag; int f_flags; int err; err = CHECK_ATTR(BPF_MAP_CREATE); if (err) return -EINVAL; /* check BPF_F_TOKEN_FD flag, remember if it's set, and then clear it * to avoid per-map type checks tripping on unknown flag */ token_flag = attr->map_flags & BPF_F_TOKEN_FD; attr->map_flags &= ~BPF_F_TOKEN_FD; if (attr->btf_vmlinux_value_type_id) { if (attr->map_type != BPF_MAP_TYPE_STRUCT_OPS || attr->btf_key_type_id || attr->btf_value_type_id) return -EINVAL; } else if (attr->btf_key_type_id && !attr->btf_value_type_id) { return -EINVAL; } if (attr->map_type != BPF_MAP_TYPE_BLOOM_FILTER && attr->map_type != BPF_MAP_TYPE_ARENA && attr->map_extra != 0) return -EINVAL; f_flags = bpf_get_file_flag(attr->map_flags); if (f_flags < 0) return f_flags; if (numa_node != NUMA_NO_NODE && ((unsigned int)numa_node >= nr_node_ids || !node_online(numa_node))) return -EINVAL; /* find map type and init map: hashtable vs rbtree vs bloom vs ... */ map_type = attr->map_type; if (map_type >= ARRAY_SIZE(bpf_map_types)) return -EINVAL; map_type = array_index_nospec(map_type, ARRAY_SIZE(bpf_map_types)); ops = bpf_map_types[map_type]; if (!ops) return -EINVAL; if (ops->map_alloc_check) { err = ops->map_alloc_check(attr); if (err) return err; } if (attr->map_ifindex) ops = &bpf_map_offload_ops; if (!ops->map_mem_usage) return -EINVAL; if (token_flag) { token = bpf_token_get_from_fd(attr->map_token_fd); if (IS_ERR(token)) return PTR_ERR(token); /* if current token doesn't grant map creation permissions, * then we can't use this token, so ignore it and rely on * system-wide capabilities checks */ if (!bpf_token_allow_cmd(token, BPF_MAP_CREATE) || !bpf_token_allow_map_type(token, attr->map_type)) { bpf_token_put(token); token = NULL; } } err = -EPERM; /* Intent here is for unprivileged_bpf_disabled to block BPF map * creation for unprivileged users; other actions depend * on fd availability and access to bpffs, so are dependent on * object creation success. Even with unprivileged BPF disabled, * capability checks are still carried out. */ if (sysctl_unprivileged_bpf_disabled && !bpf_token_capable(token, CAP_BPF)) goto put_token; /* check privileged map type permissions */ switch (map_type) { case BPF_MAP_TYPE_ARRAY: case BPF_MAP_TYPE_PERCPU_ARRAY: case BPF_MAP_TYPE_PROG_ARRAY: case BPF_MAP_TYPE_PERF_EVENT_ARRAY: case BPF_MAP_TYPE_CGROUP_ARRAY: case BPF_MAP_TYPE_ARRAY_OF_MAPS: case BPF_MAP_TYPE_HASH: case BPF_MAP_TYPE_PERCPU_HASH: case BPF_MAP_TYPE_HASH_OF_MAPS: case BPF_MAP_TYPE_RINGBUF: case BPF_MAP_TYPE_USER_RINGBUF: case BPF_MAP_TYPE_CGROUP_STORAGE: case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE: /* unprivileged */ break; case BPF_MAP_TYPE_SK_STORAGE: case BPF_MAP_TYPE_INODE_STORAGE: case BPF_MAP_TYPE_TASK_STORAGE: case BPF_MAP_TYPE_CGRP_STORAGE: case BPF_MAP_TYPE_BLOOM_FILTER: case BPF_MAP_TYPE_LPM_TRIE: case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY: case BPF_MAP_TYPE_STACK_TRACE: case BPF_MAP_TYPE_QUEUE: case BPF_MAP_TYPE_STACK: case BPF_MAP_TYPE_LRU_HASH: case BPF_MAP_TYPE_LRU_PERCPU_HASH: case BPF_MAP_TYPE_STRUCT_OPS: case BPF_MAP_TYPE_CPUMAP: case BPF_MAP_TYPE_ARENA: if (!bpf_token_capable(token, CAP_BPF)) goto put_token; break; case BPF_MAP_TYPE_SOCKMAP: case BPF_MAP_TYPE_SOCKHASH: case BPF_MAP_TYPE_DEVMAP: case BPF_MAP_TYPE_DEVMAP_HASH: case BPF_MAP_TYPE_XSKMAP: if (!bpf_token_capable(token, CAP_NET_ADMIN)) goto put_token; break; default: WARN(1, "unsupported map type %d", map_type); goto put_token; } map = ops->map_alloc(attr); if (IS_ERR(map)) { err = PTR_ERR(map); goto put_token; } map->ops = ops; map->map_type = map_type; err = bpf_obj_name_cpy(map->name, attr->map_name, sizeof(attr->map_name)); if (err < 0) goto free_map; atomic64_set(&map->refcnt, 1); atomic64_set(&map->usercnt, 1); mutex_init(&map->freeze_mutex); spin_lock_init(&map->owner.lock); if (attr->btf_key_type_id || attr->btf_value_type_id || /* Even the map's value is a kernel's struct, * the bpf_prog.o must have BTF to begin with * to figure out the corresponding kernel's * counter part. Thus, attr->btf_fd has * to be valid also. */ attr->btf_vmlinux_value_type_id) { struct btf *btf; btf = btf_get_by_fd(attr->btf_fd); if (IS_ERR(btf)) { err = PTR_ERR(btf); goto free_map; } if (btf_is_kernel(btf)) { btf_put(btf); err = -EACCES; goto free_map; } map->btf = btf; if (attr->btf_value_type_id) { err = map_check_btf(map, token, btf, attr->btf_key_type_id, attr->btf_value_type_id); if (err) goto free_map; } map->btf_key_type_id = attr->btf_key_type_id; map->btf_value_type_id = attr->btf_value_type_id; map->btf_vmlinux_value_type_id = attr->btf_vmlinux_value_type_id; } err = security_bpf_map_create(map, attr, token); if (err) goto free_map_sec; err = bpf_map_alloc_id(map); if (err) goto free_map_sec; bpf_map_save_memcg(map); bpf_token_put(token); err = bpf_map_new_fd(map, f_flags); if (err < 0) { /* failed to allocate fd. * bpf_map_put_with_uref() is needed because the above * bpf_map_alloc_id() has published the map * to the userspace and the userspace may * have refcnt-ed it through BPF_MAP_GET_FD_BY_ID. */ bpf_map_put_with_uref(map); return err; } return err; free_map_sec: security_bpf_map_free(map); free_map: bpf_map_free(map); put_token: bpf_token_put(token); return err; } void bpf_map_inc(struct bpf_map *map) { atomic64_inc(&map->refcnt); } EXPORT_SYMBOL_GPL(bpf_map_inc); void bpf_map_inc_with_uref(struct bpf_map *map) { atomic64_inc(&map->refcnt); atomic64_inc(&map->usercnt); } EXPORT_SYMBOL_GPL(bpf_map_inc_with_uref); struct bpf_map *bpf_map_get(u32 ufd) { CLASS(fd, f)(ufd); struct bpf_map *map = __bpf_map_get(f); if (!IS_ERR(map)) bpf_map_inc(map); return map; } EXPORT_SYMBOL(bpf_map_get); struct bpf_map *bpf_map_get_with_uref(u32 ufd) { CLASS(fd, f)(ufd); struct bpf_map *map = __bpf_map_get(f); if (!IS_ERR(map)) bpf_map_inc_with_uref(map); return map; } /* map_idr_lock should have been held or the map should have been * protected by rcu read lock. */ struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, bool uref) { int refold; refold = atomic64_fetch_add_unless(&map->refcnt, 1, 0); if (!refold) return ERR_PTR(-ENOENT); if (uref) atomic64_inc(&map->usercnt); return map; } struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map) { spin_lock_bh(&map_idr_lock); map = __bpf_map_inc_not_zero(map, false); spin_unlock_bh(&map_idr_lock); return map; } EXPORT_SYMBOL_GPL(bpf_map_inc_not_zero); int __weak bpf_stackmap_copy(struct bpf_map *map, void *key, void *value) { return -ENOTSUPP; } static void *__bpf_copy_key(void __user *ukey, u64 key_size) { if (key_size) return vmemdup_user(ukey, key_size); if (ukey) return ERR_PTR(-EINVAL); return NULL; } static void *___bpf_copy_key(bpfptr_t ukey, u64 key_size) { if (key_size) return kvmemdup_bpfptr(ukey, key_size); if (!bpfptr_is_null(ukey)) return ERR_PTR(-EINVAL); return NULL; } /* last field in 'union bpf_attr' used by this command */ #define BPF_MAP_LOOKUP_ELEM_LAST_FIELD flags static int map_lookup_elem(union bpf_attr *attr) { void __user *ukey = u64_to_user_ptr(attr->key); void __user *uvalue = u64_to_user_ptr(attr->value); struct bpf_map *map; void *key, *value; u32 value_size; int err; if (CHECK_ATTR(BPF_MAP_LOOKUP_ELEM)) return -EINVAL; if (attr->flags & ~BPF_F_LOCK) return -EINVAL; CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) return -EPERM; if ((attr->flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK)) return -EINVAL; key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) return PTR_ERR(key); value_size = bpf_map_value_size(map); err = -ENOMEM; value = kvmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) goto free_key; if (map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { if (copy_from_user(value, uvalue, value_size)) err = -EFAULT; else err = bpf_map_copy_value(map, key, value, attr->flags); goto free_value; } err = bpf_map_copy_value(map, key, value, attr->flags); if (err) goto free_value; err = -EFAULT; if (copy_to_user(uvalue, value, value_size) != 0) goto free_value; err = 0; free_value: kvfree(value); free_key: kvfree(key); return err; } #define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags static int map_update_elem(union bpf_attr *attr, bpfptr_t uattr) { bpfptr_t ukey = make_bpfptr(attr->key, uattr.is_kernel); bpfptr_t uvalue = make_bpfptr(attr->value, uattr.is_kernel); struct bpf_map *map; void *key, *value; u32 value_size; int err; if (CHECK_ATTR(BPF_MAP_UPDATE_ELEM)) return -EINVAL; CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } if ((attr->flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK)) { err = -EINVAL; goto err_put; } key = ___bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; } value_size = bpf_map_value_size(map); value = kvmemdup_bpfptr(uvalue, value_size); if (IS_ERR(value)) { err = PTR_ERR(value); goto free_key; } err = bpf_map_update_value(map, fd_file(f), key, value, attr->flags); if (!err) maybe_wait_bpf_programs(map); kvfree(value); free_key: kvfree(key); err_put: bpf_map_write_active_dec(map); return err; } #define BPF_MAP_DELETE_ELEM_LAST_FIELD key static int map_delete_elem(union bpf_attr *attr, bpfptr_t uattr) { bpfptr_t ukey = make_bpfptr(attr->key, uattr.is_kernel); struct bpf_map *map; void *key; int err; if (CHECK_ATTR(BPF_MAP_DELETE_ELEM)) return -EINVAL; CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } key = ___bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; } if (bpf_map_is_offloaded(map)) { err = bpf_map_offload_delete_elem(map, key); goto out; } else if (IS_FD_PROG_ARRAY(map) || map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { /* These maps require sleepable context */ err = map->ops->map_delete_elem(map, key); goto out; } bpf_disable_instrumentation(); rcu_read_lock(); err = map->ops->map_delete_elem(map, key); rcu_read_unlock(); bpf_enable_instrumentation(); if (!err) maybe_wait_bpf_programs(map); out: kvfree(key); err_put: bpf_map_write_active_dec(map); return err; } /* last field in 'union bpf_attr' used by this command */ #define BPF_MAP_GET_NEXT_KEY_LAST_FIELD next_key static int map_get_next_key(union bpf_attr *attr) { void __user *ukey = u64_to_user_ptr(attr->key); void __user *unext_key = u64_to_user_ptr(attr->next_key); struct bpf_map *map; void *key, *next_key; int err; if (CHECK_ATTR(BPF_MAP_GET_NEXT_KEY)) return -EINVAL; CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) return -EPERM; if (ukey) { key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) return PTR_ERR(key); } else { key = NULL; } err = -ENOMEM; next_key = kvmalloc(map->key_size, GFP_USER); if (!next_key) goto free_key; if (bpf_map_is_offloaded(map)) { err = bpf_map_offload_get_next_key(map, key, next_key); goto out; } rcu_read_lock(); err = map->ops->map_get_next_key(map, key, next_key); rcu_read_unlock(); out: if (err) goto free_next_key; err = -EFAULT; if (copy_to_user(unext_key, next_key, map->key_size) != 0) goto free_next_key; err = 0; free_next_key: kvfree(next_key); free_key: kvfree(key); return err; } int generic_map_delete_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr) { void __user *keys = u64_to_user_ptr(attr->batch.keys); u32 cp, max_count; int err = 0; void *key; if (attr->batch.elem_flags & ~BPF_F_LOCK) return -EINVAL; if ((attr->batch.elem_flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK)) { return -EINVAL; } max_count = attr->batch.count; if (!max_count) return 0; if (put_user(0, &uattr->batch.count)) return -EFAULT; key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); if (!key) return -ENOMEM; for (cp = 0; cp < max_count; cp++) { err = -EFAULT; if (copy_from_user(key, keys + cp * map->key_size, map->key_size)) break; if (bpf_map_is_offloaded(map)) { err = bpf_map_offload_delete_elem(map, key); break; } bpf_disable_instrumentation(); rcu_read_lock(); err = map->ops->map_delete_elem(map, key); rcu_read_unlock(); bpf_enable_instrumentation(); if (err) break; cond_resched(); } if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp))) err = -EFAULT; kvfree(key); return err; } int generic_map_update_batch(struct bpf_map *map, struct file *map_file, const union bpf_attr *attr, union bpf_attr __user *uattr) { void __user *values = u64_to_user_ptr(attr->batch.values); void __user *keys = u64_to_user_ptr(attr->batch.keys); u32 value_size, cp, max_count; void *key, *value; int err = 0; if (attr->batch.elem_flags & ~BPF_F_LOCK) return -EINVAL; if ((attr->batch.elem_flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK)) { return -EINVAL; } value_size = bpf_map_value_size(map); max_count = attr->batch.count; if (!max_count) return 0; if (put_user(0, &uattr->batch.count)) return -EFAULT; key = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); if (!key) return -ENOMEM; value = kvmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) { kvfree(key); return -ENOMEM; } for (cp = 0; cp < max_count; cp++) { err = -EFAULT; if (copy_from_user(key, keys + cp * map->key_size, map->key_size) || copy_from_user(value, values + cp * value_size, value_size)) break; err = bpf_map_update_value(map, map_file, key, value, attr->batch.elem_flags); if (err) break; cond_resched(); } if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp))) err = -EFAULT; kvfree(value); kvfree(key); return err; } int generic_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr) { void __user *uobatch = u64_to_user_ptr(attr->batch.out_batch); void __user *ubatch = u64_to_user_ptr(attr->batch.in_batch); void __user *values = u64_to_user_ptr(attr->batch.values); void __user *keys = u64_to_user_ptr(attr->batch.keys); void *buf, *buf_prevkey, *prev_key, *key, *value; u32 value_size, cp, max_count; int err; if (attr->batch.elem_flags & ~BPF_F_LOCK) return -EINVAL; if ((attr->batch.elem_flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK)) return -EINVAL; value_size = bpf_map_value_size(map); max_count = attr->batch.count; if (!max_count) return 0; if (put_user(0, &uattr->batch.count)) return -EFAULT; buf_prevkey = kvmalloc(map->key_size, GFP_USER | __GFP_NOWARN); if (!buf_prevkey) return -ENOMEM; buf = kvmalloc(map->key_size + value_size, GFP_USER | __GFP_NOWARN); if (!buf) { kvfree(buf_prevkey); return -ENOMEM; } err = -EFAULT; prev_key = NULL; if (ubatch && copy_from_user(buf_prevkey, ubatch, map->key_size)) goto free_buf; key = buf; value = key + map->key_size; if (ubatch) prev_key = buf_prevkey; for (cp = 0; cp < max_count;) { rcu_read_lock(); err = map->ops->map_get_next_key(map, prev_key, key); rcu_read_unlock(); if (err) break; err = bpf_map_copy_value(map, key, value, attr->batch.elem_flags); if (err == -ENOENT) goto next_key; if (err) goto free_buf; if (copy_to_user(keys + cp * map->key_size, key, map->key_size)) { err = -EFAULT; goto free_buf; } if (copy_to_user(values + cp * value_size, value, value_size)) { err = -EFAULT; goto free_buf; } cp++; next_key: if (!prev_key) prev_key = buf_prevkey; swap(prev_key, key); cond_resched(); } if (err == -EFAULT) goto free_buf; if ((copy_to_user(&uattr->batch.count, &cp, sizeof(cp)) || (cp && copy_to_user(uobatch, prev_key, map->key_size)))) err = -EFAULT; free_buf: kvfree(buf_prevkey); kvfree(buf); return err; } #define BPF_MAP_LOOKUP_AND_DELETE_ELEM_LAST_FIELD flags static int map_lookup_and_delete_elem(union bpf_attr *attr) { void __user *ukey = u64_to_user_ptr(attr->key); void __user *uvalue = u64_to_user_ptr(attr->value); struct bpf_map *map; void *key, *value; u32 value_size; int err; if (CHECK_ATTR(BPF_MAP_LOOKUP_AND_DELETE_ELEM)) return -EINVAL; if (attr->flags & ~BPF_F_LOCK) return -EINVAL; CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); bpf_map_write_active_inc(map); if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ) || !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } if (attr->flags && (map->map_type == BPF_MAP_TYPE_QUEUE || map->map_type == BPF_MAP_TYPE_STACK)) { err = -EINVAL; goto err_put; } if ((attr->flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK)) { err = -EINVAL; goto err_put; } key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); goto err_put; } value_size = bpf_map_value_size(map); err = -ENOMEM; value = kvmalloc(value_size, GFP_USER | __GFP_NOWARN); if (!value) goto free_key; err = -ENOTSUPP; if (map->map_type == BPF_MAP_TYPE_QUEUE || map->map_type == BPF_MAP_TYPE_STACK) { err = map->ops->map_pop_elem(map, value); } else if (map->map_type == BPF_MAP_TYPE_HASH || map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { if (!bpf_map_is_offloaded(map)) { bpf_disable_instrumentation(); rcu_read_lock(); err = map->ops->map_lookup_and_delete_elem(map, key, value, attr->flags); rcu_read_unlock(); bpf_enable_instrumentation(); } } if (err) goto free_value; if (copy_to_user(uvalue, value, value_size) != 0) { err = -EFAULT; goto free_value; } err = 0; free_value: kvfree(value); free_key: kvfree(key); err_put: bpf_map_write_active_dec(map); return err; } #define BPF_MAP_FREEZE_LAST_FIELD map_fd static int map_freeze(const union bpf_attr *attr) { int err = 0; struct bpf_map *map; if (CHECK_ATTR(BPF_MAP_FREEZE)) return -EINVAL; CLASS(fd, f)(attr->map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS || !IS_ERR_OR_NULL(map->record)) return -ENOTSUPP; if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) return -EPERM; mutex_lock(&map->freeze_mutex); if (bpf_map_write_active(map)) { err = -EBUSY; goto err_put; } if (READ_ONCE(map->frozen)) { err = -EBUSY; goto err_put; } WRITE_ONCE(map->frozen, true); err_put: mutex_unlock(&map->freeze_mutex); return err; } static const struct bpf_prog_ops * const bpf_prog_types[] = { #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ [_id] = & _name ## _prog_ops, #define BPF_MAP_TYPE(_id, _ops) #define BPF_LINK_TYPE(_id, _name) #include <linux/bpf_types.h> #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE }; static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog) { const struct bpf_prog_ops *ops; if (type >= ARRAY_SIZE(bpf_prog_types)) return -EINVAL; type = array_index_nospec(type, ARRAY_SIZE(bpf_prog_types)); ops = bpf_prog_types[type]; if (!ops) return -EINVAL; if (!bpf_prog_is_offloaded(prog->aux)) prog->aux->ops = ops; else prog->aux->ops = &bpf_offload_prog_ops; prog->type = type; return 0; } enum bpf_audit { BPF_AUDIT_LOAD, BPF_AUDIT_UNLOAD, BPF_AUDIT_MAX, }; static const char * const bpf_audit_str[BPF_AUDIT_MAX] = { [BPF_AUDIT_LOAD] = "LOAD", [BPF_AUDIT_UNLOAD] = "UNLOAD", }; static void bpf_audit_prog(const struct bpf_prog *prog, unsigned int op) { struct audit_context *ctx = NULL; struct audit_buffer *ab; if (WARN_ON_ONCE(op >= BPF_AUDIT_MAX)) return; if (audit_enabled == AUDIT_OFF) return; if (!in_irq() && !irqs_disabled()) ctx = audit_context(); ab = audit_log_start(ctx, GFP_ATOMIC, AUDIT_BPF); if (unlikely(!ab)) return; audit_log_format(ab, "prog-id=%u op=%s", prog->aux->id, bpf_audit_str[op]); audit_log_end(ab); } static int bpf_prog_alloc_id(struct bpf_prog *prog) { int id; idr_preload(GFP_KERNEL); spin_lock_bh(&prog_idr_lock); id = idr_alloc_cyclic(&prog_idr, prog, 1, INT_MAX, GFP_ATOMIC); if (id > 0) prog->aux->id = id; spin_unlock_bh(&prog_idr_lock); idr_preload_end(); /* id is in [1, INT_MAX) */ if (WARN_ON_ONCE(!id)) return -ENOSPC; return id > 0 ? 0 : id; } void bpf_prog_free_id(struct bpf_prog *prog) { unsigned long flags; /* cBPF to eBPF migrations are currently not in the idr store. * Offloaded programs are removed from the store when their device * disappears - even if someone grabs an fd to them they are unusable, * simply waiting for refcnt to drop to be freed. */ if (!prog->aux->id) return; spin_lock_irqsave(&prog_idr_lock, flags); idr_remove(&prog_idr, prog->aux->id); prog->aux->id = 0; spin_unlock_irqrestore(&prog_idr_lock, flags); } static void __bpf_prog_put_rcu(struct rcu_head *rcu) { struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu); kvfree(aux->func_info); kfree(aux->func_info_aux); free_uid(aux->user); security_bpf_prog_free(aux->prog); bpf_prog_free(aux->prog); } static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred) { bpf_prog_kallsyms_del_all(prog); btf_put(prog->aux->btf); module_put(prog->aux->mod); kvfree(prog->aux->jited_linfo); kvfree(prog->aux->linfo); kfree(prog->aux->kfunc_tab); if (prog->aux->attach_btf) btf_put(prog->aux->attach_btf); if (deferred) { if (prog->sleepable) call_rcu_tasks_trace(&prog->aux->rcu, __bpf_prog_put_rcu); else call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu); } else { __bpf_prog_put_rcu(&prog->aux->rcu); } } static void bpf_prog_put_deferred(struct work_struct *work) { struct bpf_prog_aux *aux; struct bpf_prog *prog; aux = container_of(work, struct bpf_prog_aux, work); prog = aux->prog; perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0); bpf_audit_prog(prog, BPF_AUDIT_UNLOAD); bpf_prog_free_id(prog); __bpf_prog_put_noref(prog, true); } static void __bpf_prog_put(struct bpf_prog *prog) { struct bpf_prog_aux *aux = prog->aux; if (atomic64_dec_and_test(&aux->refcnt)) { if (in_irq() || irqs_disabled()) { INIT_WORK(&aux->work, bpf_prog_put_deferred); schedule_work(&aux->work); } else { bpf_prog_put_deferred(&aux->work); } } } void bpf_prog_put(struct bpf_prog *prog) { __bpf_prog_put(prog); } EXPORT_SYMBOL_GPL(bpf_prog_put); static int bpf_prog_release(struct inode *inode, struct file *filp) { struct bpf_prog *prog = filp->private_data; bpf_prog_put(prog); return 0; } struct bpf_prog_kstats { u64 nsecs; u64 cnt; u64 misses; }; void notrace bpf_prog_inc_misses_counter(struct bpf_prog *prog) { struct bpf_prog_stats *stats; unsigned int flags; stats = this_cpu_ptr(prog->stats); flags = u64_stats_update_begin_irqsave(&stats->syncp); u64_stats_inc(&stats->misses); u64_stats_update_end_irqrestore(&stats->syncp, flags); } static void bpf_prog_get_stats(const struct bpf_prog *prog, struct bpf_prog_kstats *stats) { u64 nsecs = 0, cnt = 0, misses = 0; int cpu; for_each_possible_cpu(cpu) { const struct bpf_prog_stats *st; unsigned int start; u64 tnsecs, tcnt, tmisses; st = per_cpu_ptr(prog->stats, cpu); do { start = u64_stats_fetch_begin(&st->syncp); tnsecs = u64_stats_read(&st->nsecs); tcnt = u64_stats_read(&st->cnt); tmisses = u64_stats_read(&st->misses); } while (u64_stats_fetch_retry(&st->syncp, start)); nsecs += tnsecs; cnt += tcnt; misses += tmisses; } stats->nsecs = nsecs; stats->cnt = cnt; stats->misses = misses; } #ifdef CONFIG_PROC_FS static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) { const struct bpf_prog *prog = filp->private_data; char prog_tag[sizeof(prog->tag) * 2 + 1] = { }; struct bpf_prog_kstats stats; bpf_prog_get_stats(prog, &stats); bin2hex(prog_tag, prog->tag, sizeof(prog->tag)); seq_printf(m, "prog_type:\t%u\n" "prog_jited:\t%u\n" "prog_tag:\t%s\n" "memlock:\t%llu\n" "prog_id:\t%u\n" "run_time_ns:\t%llu\n" "run_cnt:\t%llu\n" "recursion_misses:\t%llu\n" "verified_insns:\t%u\n", prog->type, prog->jited, prog_tag, prog->pages * 1ULL << PAGE_SHIFT, prog->aux->id, stats.nsecs, stats.cnt, stats.misses, prog->aux->verified_insns); } #endif const struct file_operations bpf_prog_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_prog_show_fdinfo, #endif .release = bpf_prog_release, .read = bpf_dummy_read, .write = bpf_dummy_write, }; int bpf_prog_new_fd(struct bpf_prog *prog) { int ret; ret = security_bpf_prog(prog); if (ret < 0) return ret; return anon_inode_getfd("bpf-prog", &bpf_prog_fops, prog, O_RDWR | O_CLOEXEC); } void bpf_prog_add(struct bpf_prog *prog, int i) { atomic64_add(i, &prog->aux->refcnt); } EXPORT_SYMBOL_GPL(bpf_prog_add); void bpf_prog_sub(struct bpf_prog *prog, int i) { /* Only to be used for undoing previous bpf_prog_add() in some * error path. We still know that another entity in our call * path holds a reference to the program, thus atomic_sub() can * be safely used in such cases! */ WARN_ON(atomic64_sub_return(i, &prog->aux->refcnt) == 0); } EXPORT_SYMBOL_GPL(bpf_prog_sub); void bpf_prog_inc(struct bpf_prog *prog) { atomic64_inc(&prog->aux->refcnt); } EXPORT_SYMBOL_GPL(bpf_prog_inc); /* prog_idr_lock should have been held */ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog) { int refold; refold = atomic64_fetch_add_unless(&prog->aux->refcnt, 1, 0); if (!refold) return ERR_PTR(-ENOENT); return prog; } EXPORT_SYMBOL_GPL(bpf_prog_inc_not_zero); bool bpf_prog_get_ok(struct bpf_prog *prog, enum bpf_prog_type *attach_type, bool attach_drv) { /* not an attachment, just a refcount inc, always allow */ if (!attach_type) return true; if (prog->type != *attach_type) return false; if (bpf_prog_is_offloaded(prog->aux) && !attach_drv) return false; return true; } static struct bpf_prog *__bpf_prog_get(u32 ufd, enum bpf_prog_type *attach_type, bool attach_drv) { CLASS(fd, f)(ufd); struct bpf_prog *prog; if (fd_empty(f)) return ERR_PTR(-EBADF); if (fd_file(f)->f_op != &bpf_prog_fops) return ERR_PTR(-EINVAL); prog = fd_file(f)->private_data; if (!bpf_prog_get_ok(prog, attach_type, attach_drv)) return ERR_PTR(-EINVAL); bpf_prog_inc(prog); return prog; } struct bpf_prog *bpf_prog_get(u32 ufd) { return __bpf_prog_get(ufd, NULL, false); } struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, bool attach_drv) { return __bpf_prog_get(ufd, &type, attach_drv); } EXPORT_SYMBOL_GPL(bpf_prog_get_type_dev); /* Initially all BPF programs could be loaded w/o specifying * expected_attach_type. Later for some of them specifying expected_attach_type * at load time became required so that program could be validated properly. * Programs of types that are allowed to be loaded both w/ and w/o (for * backward compatibility) expected_attach_type, should have the default attach * type assigned to expected_attach_type for the latter case, so that it can be * validated later at attach time. * * bpf_prog_load_fixup_attach_type() sets expected_attach_type in @attr if * prog type requires it but has some attach types that have to be backward * compatible. */ static void bpf_prog_load_fixup_attach_type(union bpf_attr *attr) { switch (attr->prog_type) { case BPF_PROG_TYPE_CGROUP_SOCK: /* Unfortunately BPF_ATTACH_TYPE_UNSPEC enumeration doesn't * exist so checking for non-zero is the way to go here. */ if (!attr->expected_attach_type) attr->expected_attach_type = BPF_CGROUP_INET_SOCK_CREATE; break; case BPF_PROG_TYPE_SK_REUSEPORT: if (!attr->expected_attach_type) attr->expected_attach_type = BPF_SK_REUSEPORT_SELECT; break; } } static int bpf_prog_load_check_attach(enum bpf_prog_type prog_type, enum bpf_attach_type expected_attach_type, struct btf *attach_btf, u32 btf_id, struct bpf_prog *dst_prog) { if (btf_id) { if (btf_id > BTF_MAX_TYPE) return -EINVAL; if (!attach_btf && !dst_prog) return -EINVAL; switch (prog_type) { case BPF_PROG_TYPE_TRACING: case BPF_PROG_TYPE_LSM: case BPF_PROG_TYPE_STRUCT_OPS: case BPF_PROG_TYPE_EXT: break; default: return -EINVAL; } } if (attach_btf && (!btf_id || dst_prog)) return -EINVAL; if (dst_prog && prog_type != BPF_PROG_TYPE_TRACING && prog_type != BPF_PROG_TYPE_EXT) return -EINVAL; switch (prog_type) { case BPF_PROG_TYPE_CGROUP_SOCK: switch (expected_attach_type) { case BPF_CGROUP_INET_SOCK_CREATE: case BPF_CGROUP_INET_SOCK_RELEASE: case BPF_CGROUP_INET4_POST_BIND: case BPF_CGROUP_INET6_POST_BIND: return 0; default: return -EINVAL; } case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: switch (expected_attach_type) { case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UNIX_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: case BPF_CGROUP_UNIX_RECVMSG: return 0; default: return -EINVAL; } case BPF_PROG_TYPE_CGROUP_SKB: switch (expected_attach_type) { case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: return 0; default: return -EINVAL; } case BPF_PROG_TYPE_CGROUP_SOCKOPT: switch (expected_attach_type) { case BPF_CGROUP_SETSOCKOPT: case BPF_CGROUP_GETSOCKOPT: return 0; default: return -EINVAL; } case BPF_PROG_TYPE_SK_LOOKUP: if (expected_attach_type == BPF_SK_LOOKUP) return 0; return -EINVAL; case BPF_PROG_TYPE_SK_REUSEPORT: switch (expected_attach_type) { case BPF_SK_REUSEPORT_SELECT: case BPF_SK_REUSEPORT_SELECT_OR_MIGRATE: return 0; default: return -EINVAL; } case BPF_PROG_TYPE_NETFILTER: if (expected_attach_type == BPF_NETFILTER) return 0; return -EINVAL; case BPF_PROG_TYPE_SYSCALL: case BPF_PROG_TYPE_EXT: if (expected_attach_type) return -EINVAL; fallthrough; default: return 0; } } static bool is_net_admin_prog_type(enum bpf_prog_type prog_type) { switch (prog_type) { case BPF_PROG_TYPE_SCHED_CLS: case BPF_PROG_TYPE_SCHED_ACT: case BPF_PROG_TYPE_XDP: case BPF_PROG_TYPE_LWT_IN: case BPF_PROG_TYPE_LWT_OUT: case BPF_PROG_TYPE_LWT_XMIT: case BPF_PROG_TYPE_LWT_SEG6LOCAL: case BPF_PROG_TYPE_SK_SKB: case BPF_PROG_TYPE_SK_MSG: case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: case BPF_PROG_TYPE_CGROUP_SOCKOPT: case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_SOCK_OPS: case BPF_PROG_TYPE_EXT: /* extends any prog */ case BPF_PROG_TYPE_NETFILTER: return true; case BPF_PROG_TYPE_CGROUP_SKB: /* always unpriv */ case BPF_PROG_TYPE_SK_REUSEPORT: /* equivalent to SOCKET_FILTER. need CAP_BPF only */ default: return false; } } static bool is_perfmon_prog_type(enum bpf_prog_type prog_type) { switch (prog_type) { case BPF_PROG_TYPE_KPROBE: case BPF_PROG_TYPE_TRACEPOINT: case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_RAW_TRACEPOINT: case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: case BPF_PROG_TYPE_TRACING: case BPF_PROG_TYPE_LSM: case BPF_PROG_TYPE_STRUCT_OPS: /* has access to struct sock */ case BPF_PROG_TYPE_EXT: /* extends any prog */ return true; default: return false; } } /* last field in 'union bpf_attr' used by this command */ #define BPF_PROG_LOAD_LAST_FIELD fd_array_cnt static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) { enum bpf_prog_type type = attr->prog_type; struct bpf_prog *prog, *dst_prog = NULL; struct btf *attach_btf = NULL; struct bpf_token *token = NULL; bool bpf_cap; int err; char license[128]; if (CHECK_ATTR(BPF_PROG_LOAD)) return -EINVAL; if (attr->prog_flags & ~(BPF_F_STRICT_ALIGNMENT | BPF_F_ANY_ALIGNMENT | BPF_F_TEST_STATE_FREQ | BPF_F_SLEEPABLE | BPF_F_TEST_RND_HI32 | BPF_F_XDP_HAS_FRAGS | BPF_F_XDP_DEV_BOUND_ONLY | BPF_F_TEST_REG_INVARIANTS | BPF_F_TOKEN_FD)) return -EINVAL; bpf_prog_load_fixup_attach_type(attr); if (attr->prog_flags & BPF_F_TOKEN_FD) { token = bpf_token_get_from_fd(attr->prog_token_fd); if (IS_ERR(token)) return PTR_ERR(token); /* if current token doesn't grant prog loading permissions, * then we can't use this token, so ignore it and rely on * system-wide capabilities checks */ if (!bpf_token_allow_cmd(token, BPF_PROG_LOAD) || !bpf_token_allow_prog_type(token, attr->prog_type, attr->expected_attach_type)) { bpf_token_put(token); token = NULL; } } bpf_cap = bpf_token_capable(token, CAP_BPF); err = -EPERM; if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && (attr->prog_flags & BPF_F_ANY_ALIGNMENT) && !bpf_cap) goto put_token; /* Intent here is for unprivileged_bpf_disabled to block BPF program * creation for unprivileged users; other actions depend * on fd availability and access to bpffs, so are dependent on * object creation success. Even with unprivileged BPF disabled, * capability checks are still carried out for these * and other operations. */ if (sysctl_unprivileged_bpf_disabled && !bpf_cap) goto put_token; if (attr->insn_cnt == 0 || attr->insn_cnt > (bpf_cap ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) { err = -E2BIG; goto put_token; } if (type != BPF_PROG_TYPE_SOCKET_FILTER && type != BPF_PROG_TYPE_CGROUP_SKB && !bpf_cap) goto put_token; if (is_net_admin_prog_type(type) && !bpf_token_capable(token, CAP_NET_ADMIN)) goto put_token; if (is_perfmon_prog_type(type) && !bpf_token_capable(token, CAP_PERFMON)) goto put_token; /* attach_prog_fd/attach_btf_obj_fd can specify fd of either bpf_prog * or btf, we need to check which one it is */ if (attr->attach_prog_fd) { dst_prog = bpf_prog_get(attr->attach_prog_fd); if (IS_ERR(dst_prog)) { dst_prog = NULL; attach_btf = btf_get_by_fd(attr->attach_btf_obj_fd); if (IS_ERR(attach_btf)) { err = -EINVAL; goto put_token; } if (!btf_is_kernel(attach_btf)) { /* attaching through specifying bpf_prog's BTF * objects directly might be supported eventually */ btf_put(attach_btf); err = -ENOTSUPP; goto put_token; } } } else if (attr->attach_btf_id) { /* fall back to vmlinux BTF, if BTF type ID is specified */ attach_btf = bpf_get_btf_vmlinux(); if (IS_ERR(attach_btf)) { err = PTR_ERR(attach_btf); goto put_token; } if (!attach_btf) { err = -EINVAL; goto put_token; } btf_get(attach_btf); } if (bpf_prog_load_check_attach(type, attr->expected_attach_type, attach_btf, attr->attach_btf_id, dst_prog)) { if (dst_prog) bpf_prog_put(dst_prog); if (attach_btf) btf_put(attach_btf); err = -EINVAL; goto put_token; } /* plain bpf_prog allocation */ prog = bpf_prog_alloc(bpf_prog_size(attr->insn_cnt), GFP_USER); if (!prog) { if (dst_prog) bpf_prog_put(dst_prog); if (attach_btf) btf_put(attach_btf); err = -EINVAL; goto put_token; } prog->expected_attach_type = attr->expected_attach_type; prog->sleepable = !!(attr->prog_flags & BPF_F_SLEEPABLE); prog->aux->attach_btf = attach_btf; prog->aux->attach_btf_id = attr->attach_btf_id; prog->aux->dst_prog = dst_prog; prog->aux->dev_bound = !!attr->prog_ifindex; prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS; /* move token into prog->aux, reuse taken refcnt */ prog->aux->token = token; token = NULL; prog->aux->user = get_current_user(); prog->len = attr->insn_cnt; err = -EFAULT; if (copy_from_bpfptr(prog->insns, make_bpfptr(attr->insns, uattr.is_kernel), bpf_prog_insn_size(prog)) != 0) goto free_prog; /* copy eBPF program license from user space */ if (strncpy_from_bpfptr(license, make_bpfptr(attr->license, uattr.is_kernel), sizeof(license) - 1) < 0) goto free_prog; license[sizeof(license) - 1] = 0; /* eBPF programs must be GPL compatible to use GPL-ed functions */ prog->gpl_compatible = license_is_gpl_compatible(license) ? 1 : 0; prog->orig_prog = NULL; prog->jited = 0; atomic64_set(&prog->aux->refcnt, 1); if (bpf_prog_is_dev_bound(prog->aux)) { err = bpf_prog_dev_bound_init(prog, attr); if (err) goto free_prog; } if (type == BPF_PROG_TYPE_EXT && dst_prog && bpf_prog_is_dev_bound(dst_prog->aux)) { err = bpf_prog_dev_bound_inherit(prog, dst_prog); if (err) goto free_prog; } /* * Bookkeeping for managing the program attachment chain. * * It might be tempting to set attach_tracing_prog flag at the attachment * time, but this will not prevent from loading bunch of tracing prog * first, then attach them one to another. * * The flag attach_tracing_prog is set for the whole program lifecycle, and * doesn't have to be cleared in bpf_tracing_link_release, since tracing * programs cannot change attachment target. */ if (type == BPF_PROG_TYPE_TRACING && dst_prog && dst_prog->type == BPF_PROG_TYPE_TRACING) { prog->aux->attach_tracing_prog = true; } /* find program type: socket_filter vs tracing_filter */ err = find_prog_type(type, prog); if (err < 0) goto free_prog; prog->aux->load_time = ktime_get_boottime_ns(); err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name, sizeof(attr->prog_name)); if (err < 0) goto free_prog; err = security_bpf_prog_load(prog, attr, token); if (err) goto free_prog_sec; /* run eBPF verifier */ err = bpf_check(&prog, attr, uattr, uattr_size); if (err < 0) goto free_used_maps; prog = bpf_prog_select_runtime(prog, &err); if (err < 0) goto free_used_maps; err = bpf_prog_alloc_id(prog); if (err) goto free_used_maps; /* Upon success of bpf_prog_alloc_id(), the BPF prog is * effectively publicly exposed. However, retrieving via * bpf_prog_get_fd_by_id() will take another reference, * therefore it cannot be gone underneath us. * * Only for the time /after/ successful bpf_prog_new_fd() * and before returning to userspace, we might just hold * one reference and any parallel close on that fd could * rip everything out. Hence, below notifications must * happen before bpf_prog_new_fd(). * * Also, any failure handling from this point onwards must * be using bpf_prog_put() given the program is exposed. */ bpf_prog_kallsyms_add(prog); perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_LOAD, 0); bpf_audit_prog(prog, BPF_AUDIT_LOAD); err = bpf_prog_new_fd(prog); if (err < 0) bpf_prog_put(prog); return err; free_used_maps: /* In case we have subprogs, we need to wait for a grace * period before we can tear down JIT memory since symbols * are already exposed under kallsyms. */ __bpf_prog_put_noref(prog, prog->aux->real_func_cnt); return err; free_prog_sec: security_bpf_prog_free(prog); free_prog: free_uid(prog->aux->user); if (prog->aux->attach_btf) btf_put(prog->aux->attach_btf); bpf_prog_free(prog); put_token: bpf_token_put(token); return err; } #define BPF_OBJ_LAST_FIELD path_fd static int bpf_obj_pin(const union bpf_attr *attr) { int path_fd; if (CHECK_ATTR(BPF_OBJ) || attr->file_flags & ~BPF_F_PATH_FD) return -EINVAL; /* path_fd has to be accompanied by BPF_F_PATH_FD flag */ if (!(attr->file_flags & BPF_F_PATH_FD) && attr->path_fd) return -EINVAL; path_fd = attr->file_flags & BPF_F_PATH_FD ? attr->path_fd : AT_FDCWD; return bpf_obj_pin_user(attr->bpf_fd, path_fd, u64_to_user_ptr(attr->pathname)); } static int bpf_obj_get(const union bpf_attr *attr) { int path_fd; if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0 || attr->file_flags & ~(BPF_OBJ_FLAG_MASK | BPF_F_PATH_FD)) return -EINVAL; /* path_fd has to be accompanied by BPF_F_PATH_FD flag */ if (!(attr->file_flags & BPF_F_PATH_FD) && attr->path_fd) return -EINVAL; path_fd = attr->file_flags & BPF_F_PATH_FD ? attr->path_fd : AT_FDCWD; return bpf_obj_get_user(path_fd, u64_to_user_ptr(attr->pathname), attr->file_flags); } /* bpf_link_init_sleepable() allows to specify whether BPF link itself has * "sleepable" semantics, which normally would mean that BPF link's attach * hook can dereference link or link's underlying program for some time after * detachment due to RCU Tasks Trace-based lifetime protection scheme. * BPF program itself can be non-sleepable, yet, because it's transitively * reachable through BPF link, its freeing has to be delayed until after RCU * Tasks Trace GP. */ void bpf_link_init_sleepable(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog, bool sleepable) { WARN_ON(ops->dealloc && ops->dealloc_deferred); atomic64_set(&link->refcnt, 1); link->type = type; link->sleepable = sleepable; link->id = 0; link->ops = ops; link->prog = prog; } void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog) { bpf_link_init_sleepable(link, type, ops, prog, false); } static void bpf_link_free_id(int id) { if (!id) return; spin_lock_bh(&link_idr_lock); idr_remove(&link_idr, id); spin_unlock_bh(&link_idr_lock); } /* Clean up bpf_link and corresponding anon_inode file and FD. After * anon_inode is created, bpf_link can't be just kfree()'d due to deferred * anon_inode's release() call. This helper marks bpf_link as * defunct, releases anon_inode file and puts reserved FD. bpf_prog's refcnt * is not decremented, it's the responsibility of a calling code that failed * to complete bpf_link initialization. * This helper eventually calls link's dealloc callback, but does not call * link's release callback. */ void bpf_link_cleanup(struct bpf_link_primer *primer) { primer->link->prog = NULL; bpf_link_free_id(primer->id); fput(primer->file); put_unused_fd(primer->fd); } void bpf_link_inc(struct bpf_link *link) { atomic64_inc(&link->refcnt); } static void bpf_link_dealloc(struct bpf_link *link) { /* now that we know that bpf_link itself can't be reached, put underlying BPF program */ if (link->prog) bpf_prog_put(link->prog); /* free bpf_link and its containing memory */ if (link->ops->dealloc_deferred) link->ops->dealloc_deferred(link); else link->ops->dealloc(link); } static void bpf_link_defer_dealloc_rcu_gp(struct rcu_head *rcu) { struct bpf_link *link = container_of(rcu, struct bpf_link, rcu); bpf_link_dealloc(link); } static void bpf_link_defer_dealloc_mult_rcu_gp(struct rcu_head *rcu) { if (rcu_trace_implies_rcu_gp()) bpf_link_defer_dealloc_rcu_gp(rcu); else call_rcu(rcu, bpf_link_defer_dealloc_rcu_gp); } /* bpf_link_free is guaranteed to be called from process context */ static void bpf_link_free(struct bpf_link *link) { const struct bpf_link_ops *ops = link->ops; bpf_link_free_id(link->id); /* detach BPF program, clean up used resources */ if (link->prog) ops->release(link); if (ops->dealloc_deferred) { /* Schedule BPF link deallocation, which will only then * trigger putting BPF program refcount. * If underlying BPF program is sleepable or BPF link's target * attach hookpoint is sleepable or otherwise requires RCU GPs * to ensure link and its underlying BPF program is not * reachable anymore, we need to first wait for RCU tasks * trace sync, and then go through "classic" RCU grace period */ if (link->sleepable || (link->prog && link->prog->sleepable)) call_rcu_tasks_trace(&link->rcu, bpf_link_defer_dealloc_mult_rcu_gp); else call_rcu(&link->rcu, bpf_link_defer_dealloc_rcu_gp); } else if (ops->dealloc) { bpf_link_dealloc(link); } } static void bpf_link_put_deferred(struct work_struct *work) { struct bpf_link *link = container_of(work, struct bpf_link, work); bpf_link_free(link); } /* bpf_link_put might be called from atomic context. It needs to be called * from sleepable context in order to acquire sleeping locks during the process. */ void bpf_link_put(struct bpf_link *link) { if (!atomic64_dec_and_test(&link->refcnt)) return; INIT_WORK(&link->work, bpf_link_put_deferred); schedule_work(&link->work); } EXPORT_SYMBOL(bpf_link_put); static void bpf_link_put_direct(struct bpf_link *link) { if (!atomic64_dec_and_test(&link->refcnt)) return; bpf_link_free(link); } static int bpf_link_release(struct inode *inode, struct file *filp) { struct bpf_link *link = filp->private_data; bpf_link_put_direct(link); return 0; } #ifdef CONFIG_PROC_FS #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) #define BPF_MAP_TYPE(_id, _ops) #define BPF_LINK_TYPE(_id, _name) [_id] = #_name, static const char *bpf_link_type_strs[] = { [BPF_LINK_TYPE_UNSPEC] = "<invalid>", #include <linux/bpf_types.h> }; #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE static void bpf_link_show_fdinfo(struct seq_file *m, struct file *filp) { const struct bpf_link *link = filp->private_data; const struct bpf_prog *prog = link->prog; enum bpf_link_type type = link->type; char prog_tag[sizeof(prog->tag) * 2 + 1] = { }; if (type < ARRAY_SIZE(bpf_link_type_strs) && bpf_link_type_strs[type]) { seq_printf(m, "link_type:\t%s\n", bpf_link_type_strs[type]); } else { WARN_ONCE(1, "missing BPF_LINK_TYPE(...) for link type %u\n", type); seq_printf(m, "link_type:\t<%u>\n", type); } seq_printf(m, "link_id:\t%u\n", link->id); if (prog) { bin2hex(prog_tag, prog->tag, sizeof(prog->tag)); seq_printf(m, "prog_tag:\t%s\n" "prog_id:\t%u\n", prog_tag, prog->aux->id); } if (link->ops->show_fdinfo) link->ops->show_fdinfo(link, m); } #endif static __poll_t bpf_link_poll(struct file *file, struct poll_table_struct *pts) { struct bpf_link *link = file->private_data; return link->ops->poll(file, pts); } static const struct file_operations bpf_link_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_link_show_fdinfo, #endif .release = bpf_link_release, .read = bpf_dummy_read, .write = bpf_dummy_write, }; static const struct file_operations bpf_link_fops_poll = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_link_show_fdinfo, #endif .release = bpf_link_release, .read = bpf_dummy_read, .write = bpf_dummy_write, .poll = bpf_link_poll, }; static int bpf_link_alloc_id(struct bpf_link *link) { int id; idr_preload(GFP_KERNEL); spin_lock_bh(&link_idr_lock); id = idr_alloc_cyclic(&link_idr, link, 1, INT_MAX, GFP_ATOMIC); spin_unlock_bh(&link_idr_lock); idr_preload_end(); return id; } /* Prepare bpf_link to be exposed to user-space by allocating anon_inode file, * reserving unused FD and allocating ID from link_idr. This is to be paired * with bpf_link_settle() to install FD and ID and expose bpf_link to * user-space, if bpf_link is successfully attached. If not, bpf_link and * pre-allocated resources are to be freed with bpf_cleanup() call. All the * transient state is passed around in struct bpf_link_primer. * This is preferred way to create and initialize bpf_link, especially when * there are complicated and expensive operations in between creating bpf_link * itself and attaching it to BPF hook. By using bpf_link_prime() and * bpf_link_settle() kernel code using bpf_link doesn't have to perform * expensive (and potentially failing) roll back operations in a rare case * that file, FD, or ID can't be allocated. */ int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer) { struct file *file; int fd, id; fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) return fd; id = bpf_link_alloc_id(link); if (id < 0) { put_unused_fd(fd); return id; } file = anon_inode_getfile("bpf_link", link->ops->poll ? &bpf_link_fops_poll : &bpf_link_fops, link, O_CLOEXEC); if (IS_ERR(file)) { bpf_link_free_id(id); put_unused_fd(fd); return PTR_ERR(file); } primer->link = link; primer->file = file; primer->fd = fd; primer->id = id; return 0; } int bpf_link_settle(struct bpf_link_primer *primer) { /* make bpf_link fetchable by ID */ spin_lock_bh(&link_idr_lock); primer->link->id = primer->id; spin_unlock_bh(&link_idr_lock); /* make bpf_link fetchable by FD */ fd_install(primer->fd, primer->file); /* pass through installed FD */ return primer->fd; } int bpf_link_new_fd(struct bpf_link *link) { return anon_inode_getfd("bpf-link", link->ops->poll ? &bpf_link_fops_poll : &bpf_link_fops, link, O_CLOEXEC); } struct bpf_link *bpf_link_get_from_fd(u32 ufd) { CLASS(fd, f)(ufd); struct bpf_link *link; if (fd_empty(f)) return ERR_PTR(-EBADF); if (fd_file(f)->f_op != &bpf_link_fops && fd_file(f)->f_op != &bpf_link_fops_poll) return ERR_PTR(-EINVAL); link = fd_file(f)->private_data; bpf_link_inc(link); return link; } EXPORT_SYMBOL(bpf_link_get_from_fd); static void bpf_tracing_link_release(struct bpf_link *link) { struct bpf_tracing_link *tr_link = container_of(link, struct bpf_tracing_link, link.link); WARN_ON_ONCE(bpf_trampoline_unlink_prog(&tr_link->link, tr_link->trampoline, tr_link->tgt_prog)); bpf_trampoline_put(tr_link->trampoline); /* tgt_prog is NULL if target is a kernel function */ if (tr_link->tgt_prog) bpf_prog_put(tr_link->tgt_prog); } static void bpf_tracing_link_dealloc(struct bpf_link *link) { struct bpf_tracing_link *tr_link = container_of(link, struct bpf_tracing_link, link.link); kfree(tr_link); } static void bpf_tracing_link_show_fdinfo(const struct bpf_link *link, struct seq_file *seq) { struct bpf_tracing_link *tr_link = container_of(link, struct bpf_tracing_link, link.link); u32 target_btf_id, target_obj_id; bpf_trampoline_unpack_key(tr_link->trampoline->key, &target_obj_id, &target_btf_id); seq_printf(seq, "attach_type:\t%d\n" "target_obj_id:\t%u\n" "target_btf_id:\t%u\n", tr_link->attach_type, target_obj_id, target_btf_id); } static int bpf_tracing_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { struct bpf_tracing_link *tr_link = container_of(link, struct bpf_tracing_link, link.link); info->tracing.attach_type = tr_link->attach_type; bpf_trampoline_unpack_key(tr_link->trampoline->key, &info->tracing.target_obj_id, &info->tracing.target_btf_id); return 0; } static const struct bpf_link_ops bpf_tracing_link_lops = { .release = bpf_tracing_link_release, .dealloc = bpf_tracing_link_dealloc, .show_fdinfo = bpf_tracing_link_show_fdinfo, .fill_link_info = bpf_tracing_link_fill_link_info, }; static int bpf_tracing_prog_attach(struct bpf_prog *prog, int tgt_prog_fd, u32 btf_id, u64 bpf_cookie) { struct bpf_link_primer link_primer; struct bpf_prog *tgt_prog = NULL; struct bpf_trampoline *tr = NULL; struct bpf_tracing_link *link; u64 key = 0; int err; switch (prog->type) { case BPF_PROG_TYPE_TRACING: if (prog->expected_attach_type != BPF_TRACE_FENTRY && prog->expected_attach_type != BPF_TRACE_FEXIT && prog->expected_attach_type != BPF_MODIFY_RETURN) { err = -EINVAL; goto out_put_prog; } break; case BPF_PROG_TYPE_EXT: if (prog->expected_attach_type != 0) { err = -EINVAL; goto out_put_prog; } break; case BPF_PROG_TYPE_LSM: if (prog->expected_attach_type != BPF_LSM_MAC) { err = -EINVAL; goto out_put_prog; } break; default: err = -EINVAL; goto out_put_prog; } if (!!tgt_prog_fd != !!btf_id) { err = -EINVAL; goto out_put_prog; } if (tgt_prog_fd) { /* * For now we only allow new targets for BPF_PROG_TYPE_EXT. If this * part would be changed to implement the same for * BPF_PROG_TYPE_TRACING, do not forget to update the way how * attach_tracing_prog flag is set. */ if (prog->type != BPF_PROG_TYPE_EXT) { err = -EINVAL; goto out_put_prog; } tgt_prog = bpf_prog_get(tgt_prog_fd); if (IS_ERR(tgt_prog)) { err = PTR_ERR(tgt_prog); tgt_prog = NULL; goto out_put_prog; } key = bpf_trampoline_compute_key(tgt_prog, NULL, btf_id); } link = kzalloc(sizeof(*link), GFP_USER); if (!link) { err = -ENOMEM; goto out_put_prog; } bpf_link_init(&link->link.link, BPF_LINK_TYPE_TRACING, &bpf_tracing_link_lops, prog); link->attach_type = prog->expected_attach_type; link->link.cookie = bpf_cookie; mutex_lock(&prog->aux->dst_mutex); /* There are a few possible cases here: * * - if prog->aux->dst_trampoline is set, the program was just loaded * and not yet attached to anything, so we can use the values stored * in prog->aux * * - if prog->aux->dst_trampoline is NULL, the program has already been * attached to a target and its initial target was cleared (below) * * - if tgt_prog != NULL, the caller specified tgt_prog_fd + * target_btf_id using the link_create API. * * - if tgt_prog == NULL when this function was called using the old * raw_tracepoint_open API, and we need a target from prog->aux * * - if prog->aux->dst_trampoline and tgt_prog is NULL, the program * was detached and is going for re-attachment. * * - if prog->aux->dst_trampoline is NULL and tgt_prog and prog->aux->attach_btf * are NULL, then program was already attached and user did not provide * tgt_prog_fd so we have no way to find out or create trampoline */ if (!prog->aux->dst_trampoline && !tgt_prog) { /* * Allow re-attach for TRACING and LSM programs. If it's * currently linked, bpf_trampoline_link_prog will fail. * EXT programs need to specify tgt_prog_fd, so they * re-attach in separate code path. */ if (prog->type != BPF_PROG_TYPE_TRACING && prog->type != BPF_PROG_TYPE_LSM) { err = -EINVAL; goto out_unlock; } /* We can allow re-attach only if we have valid attach_btf. */ if (!prog->aux->attach_btf) { err = -EINVAL; goto out_unlock; } btf_id = prog->aux->attach_btf_id; key = bpf_trampoline_compute_key(NULL, prog->aux->attach_btf, btf_id); } if (!prog->aux->dst_trampoline || (key && key != prog->aux->dst_trampoline->key)) { /* If there is no saved target, or the specified target is * different from the destination specified at load time, we * need a new trampoline and a check for compatibility */ struct bpf_attach_target_info tgt_info = {}; err = bpf_check_attach_target(NULL, prog, tgt_prog, btf_id, &tgt_info); if (err) goto out_unlock; if (tgt_info.tgt_mod) { module_put(prog->aux->mod); prog->aux->mod = tgt_info.tgt_mod; } tr = bpf_trampoline_get(key, &tgt_info); if (!tr) { err = -ENOMEM; goto out_unlock; } } else { /* The caller didn't specify a target, or the target was the * same as the destination supplied during program load. This * means we can reuse the trampoline and reference from program * load time, and there is no need to allocate a new one. This * can only happen once for any program, as the saved values in * prog->aux are cleared below. */ tr = prog->aux->dst_trampoline; tgt_prog = prog->aux->dst_prog; } err = bpf_link_prime(&link->link.link, &link_primer); if (err) goto out_unlock; err = bpf_trampoline_link_prog(&link->link, tr, tgt_prog); if (err) { bpf_link_cleanup(&link_primer); link = NULL; goto out_unlock; } link->tgt_prog = tgt_prog; link->trampoline = tr; /* Always clear the trampoline and target prog from prog->aux to make * sure the original attach destination is not kept alive after a * program is (re-)attached to another target. */ if (prog->aux->dst_prog && (tgt_prog_fd || tr != prog->aux->dst_trampoline)) /* got extra prog ref from syscall, or attaching to different prog */ bpf_prog_put(prog->aux->dst_prog); if (prog->aux->dst_trampoline && tr != prog->aux->dst_trampoline) /* we allocated a new trampoline, so free the old one */ bpf_trampoline_put(prog->aux->dst_trampoline); prog->aux->dst_prog = NULL; prog->aux->dst_trampoline = NULL; mutex_unlock(&prog->aux->dst_mutex); return bpf_link_settle(&link_primer); out_unlock: if (tr && tr != prog->aux->dst_trampoline) bpf_trampoline_put(tr); mutex_unlock(&prog->aux->dst_mutex); kfree(link); out_put_prog: if (tgt_prog_fd && tgt_prog) bpf_prog_put(tgt_prog); return err; } static void bpf_raw_tp_link_release(struct bpf_link *link) { struct bpf_raw_tp_link *raw_tp = container_of(link, struct bpf_raw_tp_link, link); bpf_probe_unregister(raw_tp->btp, raw_tp); bpf_put_raw_tracepoint(raw_tp->btp); } static void bpf_raw_tp_link_dealloc(struct bpf_link *link) { struct bpf_raw_tp_link *raw_tp = container_of(link, struct bpf_raw_tp_link, link); kfree(raw_tp); } static void bpf_raw_tp_link_show_fdinfo(const struct bpf_link *link, struct seq_file *seq) { struct bpf_raw_tp_link *raw_tp_link = container_of(link, struct bpf_raw_tp_link, link); seq_printf(seq, "tp_name:\t%s\n", raw_tp_link->btp->tp->name); } static int bpf_copy_to_user(char __user *ubuf, const char *buf, u32 ulen, u32 len) { if (ulen >= len + 1) { if (copy_to_user(ubuf, buf, len + 1)) return -EFAULT; } else { char zero = '\0'; if (copy_to_user(ubuf, buf, ulen - 1)) return -EFAULT; if (put_user(zero, ubuf + ulen - 1)) return -EFAULT; return -ENOSPC; } return 0; } static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { struct bpf_raw_tp_link *raw_tp_link = container_of(link, struct bpf_raw_tp_link, link); char __user *ubuf = u64_to_user_ptr(info->raw_tracepoint.tp_name); const char *tp_name = raw_tp_link->btp->tp->name; u32 ulen = info->raw_tracepoint.tp_name_len; size_t tp_len = strlen(tp_name); if (!ulen ^ !ubuf) return -EINVAL; info->raw_tracepoint.tp_name_len = tp_len + 1; if (!ubuf) return 0; return bpf_copy_to_user(ubuf, tp_name, ulen, tp_len); } static const struct bpf_link_ops bpf_raw_tp_link_lops = { .release = bpf_raw_tp_link_release, .dealloc_deferred = bpf_raw_tp_link_dealloc, .show_fdinfo = bpf_raw_tp_link_show_fdinfo, .fill_link_info = bpf_raw_tp_link_fill_link_info, }; #ifdef CONFIG_PERF_EVENTS struct bpf_perf_link { struct bpf_link link; struct file *perf_file; }; static void bpf_perf_link_release(struct bpf_link *link) { struct bpf_perf_link *perf_link = container_of(link, struct bpf_perf_link, link); struct perf_event *event = perf_link->perf_file->private_data; perf_event_free_bpf_prog(event); fput(perf_link->perf_file); } static void bpf_perf_link_dealloc(struct bpf_link *link) { struct bpf_perf_link *perf_link = container_of(link, struct bpf_perf_link, link); kfree(perf_link); } static int bpf_perf_link_fill_common(const struct perf_event *event, char __user *uname, u32 *ulenp, u64 *probe_offset, u64 *probe_addr, u32 *fd_type, unsigned long *missed) { const char *buf; u32 prog_id, ulen; size_t len; int err; ulen = *ulenp; if (!ulen ^ !uname) return -EINVAL; err = bpf_get_perf_event_info(event, &prog_id, fd_type, &buf, probe_offset, probe_addr, missed); if (err) return err; if (buf) { len = strlen(buf); *ulenp = len + 1; } else { *ulenp = 1; } if (!uname) return 0; if (buf) { err = bpf_copy_to_user(uname, buf, ulen, len); if (err) return err; } else { char zero = '\0'; if (put_user(zero, uname)) return -EFAULT; } return 0; } #ifdef CONFIG_KPROBE_EVENTS static int bpf_perf_link_fill_kprobe(const struct perf_event *event, struct bpf_link_info *info) { unsigned long missed; char __user *uname; u64 addr, offset; u32 ulen, type; int err; uname = u64_to_user_ptr(info->perf_event.kprobe.func_name); ulen = info->perf_event.kprobe.name_len; err = bpf_perf_link_fill_common(event, uname, &ulen, &offset, &addr, &type, &missed); if (err) return err; if (type == BPF_FD_TYPE_KRETPROBE) info->perf_event.type = BPF_PERF_EVENT_KRETPROBE; else info->perf_event.type = BPF_PERF_EVENT_KPROBE; info->perf_event.kprobe.name_len = ulen; info->perf_event.kprobe.offset = offset; info->perf_event.kprobe.missed = missed; if (!kallsyms_show_value(current_cred())) addr = 0; info->perf_event.kprobe.addr = addr; info->perf_event.kprobe.cookie = event->bpf_cookie; return 0; } #endif #ifdef CONFIG_UPROBE_EVENTS static int bpf_perf_link_fill_uprobe(const struct perf_event *event, struct bpf_link_info *info) { char __user *uname; u64 addr, offset; u32 ulen, type; int err; uname = u64_to_user_ptr(info->perf_event.uprobe.file_name); ulen = info->perf_event.uprobe.name_len; err = bpf_perf_link_fill_common(event, uname, &ulen, &offset, &addr, &type, NULL); if (err) return err; if (type == BPF_FD_TYPE_URETPROBE) info->perf_event.type = BPF_PERF_EVENT_URETPROBE; else info->perf_event.type = BPF_PERF_EVENT_UPROBE; info->perf_event.uprobe.name_len = ulen; info->perf_event.uprobe.offset = offset; info->perf_event.uprobe.cookie = event->bpf_cookie; return 0; } #endif static int bpf_perf_link_fill_probe(const struct perf_event *event, struct bpf_link_info *info) { #ifdef CONFIG_KPROBE_EVENTS if (event->tp_event->flags & TRACE_EVENT_FL_KPROBE) return bpf_perf_link_fill_kprobe(event, info); #endif #ifdef CONFIG_UPROBE_EVENTS if (event->tp_event->flags & TRACE_EVENT_FL_UPROBE) return bpf_perf_link_fill_uprobe(event, info); #endif return -EOPNOTSUPP; } static int bpf_perf_link_fill_tracepoint(const struct perf_event *event, struct bpf_link_info *info) { char __user *uname; u32 ulen; int err; uname = u64_to_user_ptr(info->perf_event.tracepoint.tp_name); ulen = info->perf_event.tracepoint.name_len; err = bpf_perf_link_fill_common(event, uname, &ulen, NULL, NULL, NULL, NULL); if (err) return err; info->perf_event.type = BPF_PERF_EVENT_TRACEPOINT; info->perf_event.tracepoint.name_len = ulen; info->perf_event.tracepoint.cookie = event->bpf_cookie; return 0; } static int bpf_perf_link_fill_perf_event(const struct perf_event *event, struct bpf_link_info *info) { info->perf_event.event.type = event->attr.type; info->perf_event.event.config = event->attr.config; info->perf_event.event.cookie = event->bpf_cookie; info->perf_event.type = BPF_PERF_EVENT_EVENT; return 0; } static int bpf_perf_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { struct bpf_perf_link *perf_link; const struct perf_event *event; perf_link = container_of(link, struct bpf_perf_link, link); event = perf_get_event(perf_link->perf_file); if (IS_ERR(event)) return PTR_ERR(event); switch (event->prog->type) { case BPF_PROG_TYPE_PERF_EVENT: return bpf_perf_link_fill_perf_event(event, info); case BPF_PROG_TYPE_TRACEPOINT: return bpf_perf_link_fill_tracepoint(event, info); case BPF_PROG_TYPE_KPROBE: return bpf_perf_link_fill_probe(event, info); default: return -EOPNOTSUPP; } } static const struct bpf_link_ops bpf_perf_link_lops = { .release = bpf_perf_link_release, .dealloc = bpf_perf_link_dealloc, .fill_link_info = bpf_perf_link_fill_link_info, }; static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { struct bpf_link_primer link_primer; struct bpf_perf_link *link; struct perf_event *event; struct file *perf_file; int err; if (attr->link_create.flags) return -EINVAL; perf_file = perf_event_get(attr->link_create.target_fd); if (IS_ERR(perf_file)) return PTR_ERR(perf_file); link = kzalloc(sizeof(*link), GFP_USER); if (!link) { err = -ENOMEM; goto out_put_file; } bpf_link_init(&link->link, BPF_LINK_TYPE_PERF_EVENT, &bpf_perf_link_lops, prog); link->perf_file = perf_file; err = bpf_link_prime(&link->link, &link_primer); if (err) { kfree(link); goto out_put_file; } event = perf_file->private_data; err = perf_event_set_bpf_prog(event, prog, attr->link_create.perf_event.bpf_cookie); if (err) { bpf_link_cleanup(&link_primer); goto out_put_file; } /* perf_event_set_bpf_prog() doesn't take its own refcnt on prog */ bpf_prog_inc(prog); return bpf_link_settle(&link_primer); out_put_file: fput(perf_file); return err; } #else static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { return -EOPNOTSUPP; } #endif /* CONFIG_PERF_EVENTS */ static int bpf_raw_tp_link_attach(struct bpf_prog *prog, const char __user *user_tp_name, u64 cookie) { struct bpf_link_primer link_primer; struct bpf_raw_tp_link *link; struct bpf_raw_event_map *btp; const char *tp_name; char buf[128]; int err; switch (prog->type) { case BPF_PROG_TYPE_TRACING: case BPF_PROG_TYPE_EXT: case BPF_PROG_TYPE_LSM: if (user_tp_name) /* The attach point for this category of programs * should be specified via btf_id during program load. */ return -EINVAL; if (prog->type == BPF_PROG_TYPE_TRACING && prog->expected_attach_type == BPF_TRACE_RAW_TP) { tp_name = prog->aux->attach_func_name; break; } return bpf_tracing_prog_attach(prog, 0, 0, 0); case BPF_PROG_TYPE_RAW_TRACEPOINT: case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: if (strncpy_from_user(buf, user_tp_name, sizeof(buf) - 1) < 0) return -EFAULT; buf[sizeof(buf) - 1] = 0; tp_name = buf; break; default: return -EINVAL; } btp = bpf_get_raw_tracepoint(tp_name); if (!btp) return -ENOENT; link = kzalloc(sizeof(*link), GFP_USER); if (!link) { err = -ENOMEM; goto out_put_btp; } bpf_link_init_sleepable(&link->link, BPF_LINK_TYPE_RAW_TRACEPOINT, &bpf_raw_tp_link_lops, prog, tracepoint_is_faultable(btp->tp)); link->btp = btp; link->cookie = cookie; err = bpf_link_prime(&link->link, &link_primer); if (err) { kfree(link); goto out_put_btp; } err = bpf_probe_register(link->btp, link); if (err) { bpf_link_cleanup(&link_primer); goto out_put_btp; } return bpf_link_settle(&link_primer); out_put_btp: bpf_put_raw_tracepoint(btp); return err; } #define BPF_RAW_TRACEPOINT_OPEN_LAST_FIELD raw_tracepoint.cookie static int bpf_raw_tracepoint_open(const union bpf_attr *attr) { struct bpf_prog *prog; void __user *tp_name; __u64 cookie; int fd; if (CHECK_ATTR(BPF_RAW_TRACEPOINT_OPEN)) return -EINVAL; prog = bpf_prog_get(attr->raw_tracepoint.prog_fd); if (IS_ERR(prog)) return PTR_ERR(prog); tp_name = u64_to_user_ptr(attr->raw_tracepoint.name); cookie = attr->raw_tracepoint.cookie; fd = bpf_raw_tp_link_attach(prog, tp_name, cookie); if (fd < 0) bpf_prog_put(prog); return fd; } static enum bpf_prog_type attach_type_to_prog_type(enum bpf_attach_type attach_type) { switch (attach_type) { case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: return BPF_PROG_TYPE_CGROUP_SKB; case BPF_CGROUP_INET_SOCK_CREATE: case BPF_CGROUP_INET_SOCK_RELEASE: case BPF_CGROUP_INET4_POST_BIND: case BPF_CGROUP_INET6_POST_BIND: return BPF_PROG_TYPE_CGROUP_SOCK; case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UNIX_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: case BPF_CGROUP_UNIX_RECVMSG: return BPF_PROG_TYPE_CGROUP_SOCK_ADDR; case BPF_CGROUP_SOCK_OPS: return BPF_PROG_TYPE_SOCK_OPS; case BPF_CGROUP_DEVICE: return BPF_PROG_TYPE_CGROUP_DEVICE; case BPF_SK_MSG_VERDICT: return BPF_PROG_TYPE_SK_MSG; case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: case BPF_SK_SKB_VERDICT: return BPF_PROG_TYPE_SK_SKB; case BPF_LIRC_MODE2: return BPF_PROG_TYPE_LIRC_MODE2; case BPF_FLOW_DISSECTOR: return BPF_PROG_TYPE_FLOW_DISSECTOR; case BPF_CGROUP_SYSCTL: return BPF_PROG_TYPE_CGROUP_SYSCTL; case BPF_CGROUP_GETSOCKOPT: case BPF_CGROUP_SETSOCKOPT: return BPF_PROG_TYPE_CGROUP_SOCKOPT; case BPF_TRACE_ITER: case BPF_TRACE_RAW_TP: case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: case BPF_MODIFY_RETURN: return BPF_PROG_TYPE_TRACING; case BPF_LSM_MAC: return BPF_PROG_TYPE_LSM; case BPF_SK_LOOKUP: return BPF_PROG_TYPE_SK_LOOKUP; case BPF_XDP: return BPF_PROG_TYPE_XDP; case BPF_LSM_CGROUP: return BPF_PROG_TYPE_LSM; case BPF_TCX_INGRESS: case BPF_TCX_EGRESS: case BPF_NETKIT_PRIMARY: case BPF_NETKIT_PEER: return BPF_PROG_TYPE_SCHED_CLS; default: return BPF_PROG_TYPE_UNSPEC; } } static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, enum bpf_attach_type attach_type) { enum bpf_prog_type ptype; switch (prog->type) { case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: case BPF_PROG_TYPE_CGROUP_SOCKOPT: case BPF_PROG_TYPE_SK_LOOKUP: return attach_type == prog->expected_attach_type ? 0 : -EINVAL; case BPF_PROG_TYPE_CGROUP_SKB: if (!bpf_token_capable(prog->aux->token, CAP_NET_ADMIN)) /* cg-skb progs can be loaded by unpriv user. * check permissions at attach time. */ return -EPERM; ptype = attach_type_to_prog_type(attach_type); if (prog->type != ptype) return -EINVAL; return prog->enforce_expected_attach_type && prog->expected_attach_type != attach_type ? -EINVAL : 0; case BPF_PROG_TYPE_EXT: return 0; case BPF_PROG_TYPE_NETFILTER: if (attach_type != BPF_NETFILTER) return -EINVAL; return 0; case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_TRACEPOINT: if (attach_type != BPF_PERF_EVENT) return -EINVAL; return 0; case BPF_PROG_TYPE_KPROBE: if (prog->expected_attach_type == BPF_TRACE_KPROBE_MULTI && attach_type != BPF_TRACE_KPROBE_MULTI) return -EINVAL; if (prog->expected_attach_type == BPF_TRACE_KPROBE_SESSION && attach_type != BPF_TRACE_KPROBE_SESSION) return -EINVAL; if (prog->expected_attach_type == BPF_TRACE_UPROBE_MULTI && attach_type != BPF_TRACE_UPROBE_MULTI) return -EINVAL; if (prog->expected_attach_type == BPF_TRACE_UPROBE_SESSION && attach_type != BPF_TRACE_UPROBE_SESSION) return -EINVAL; if (attach_type != BPF_PERF_EVENT && attach_type != BPF_TRACE_KPROBE_MULTI && attach_type != BPF_TRACE_KPROBE_SESSION && attach_type != BPF_TRACE_UPROBE_MULTI && attach_type != BPF_TRACE_UPROBE_SESSION) return -EINVAL; return 0; case BPF_PROG_TYPE_SCHED_CLS: if (attach_type != BPF_TCX_INGRESS && attach_type != BPF_TCX_EGRESS && attach_type != BPF_NETKIT_PRIMARY && attach_type != BPF_NETKIT_PEER) return -EINVAL; return 0; default: ptype = attach_type_to_prog_type(attach_type); if (ptype == BPF_PROG_TYPE_UNSPEC || ptype != prog->type) return -EINVAL; return 0; } } #define BPF_PROG_ATTACH_LAST_FIELD expected_revision #define BPF_F_ATTACH_MASK_BASE \ (BPF_F_ALLOW_OVERRIDE | \ BPF_F_ALLOW_MULTI | \ BPF_F_REPLACE) #define BPF_F_ATTACH_MASK_MPROG \ (BPF_F_REPLACE | \ BPF_F_BEFORE | \ BPF_F_AFTER | \ BPF_F_ID | \ BPF_F_LINK) static int bpf_prog_attach(const union bpf_attr *attr) { enum bpf_prog_type ptype; struct bpf_prog *prog; int ret; if (CHECK_ATTR(BPF_PROG_ATTACH)) return -EINVAL; ptype = attach_type_to_prog_type(attr->attach_type); if (ptype == BPF_PROG_TYPE_UNSPEC) return -EINVAL; if (bpf_mprog_supported(ptype)) { if (attr->attach_flags & ~BPF_F_ATTACH_MASK_MPROG) return -EINVAL; } else { if (attr->attach_flags & ~BPF_F_ATTACH_MASK_BASE) return -EINVAL; if (attr->relative_fd || attr->expected_revision) return -EINVAL; } prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); if (IS_ERR(prog)) return PTR_ERR(prog); if (bpf_prog_attach_check_attach_type(prog, attr->attach_type)) { bpf_prog_put(prog); return -EINVAL; } switch (ptype) { case BPF_PROG_TYPE_SK_SKB: case BPF_PROG_TYPE_SK_MSG: ret = sock_map_get_from_fd(attr, prog); break; case BPF_PROG_TYPE_LIRC_MODE2: ret = lirc_prog_attach(attr, prog); break; case BPF_PROG_TYPE_FLOW_DISSECTOR: ret = netns_bpf_prog_attach(attr, prog); break; case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SKB: case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: case BPF_PROG_TYPE_CGROUP_SOCKOPT: case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_SOCK_OPS: case BPF_PROG_TYPE_LSM: if (ptype == BPF_PROG_TYPE_LSM && prog->expected_attach_type != BPF_LSM_CGROUP) ret = -EINVAL; else ret = cgroup_bpf_prog_attach(attr, ptype, prog); break; case BPF_PROG_TYPE_SCHED_CLS: if (attr->attach_type == BPF_TCX_INGRESS || attr->attach_type == BPF_TCX_EGRESS) ret = tcx_prog_attach(attr, prog); else ret = netkit_prog_attach(attr, prog); break; default: ret = -EINVAL; } if (ret) bpf_prog_put(prog); return ret; } #define BPF_PROG_DETACH_LAST_FIELD expected_revision static int bpf_prog_detach(const union bpf_attr *attr) { struct bpf_prog *prog = NULL; enum bpf_prog_type ptype; int ret; if (CHECK_ATTR(BPF_PROG_DETACH)) return -EINVAL; ptype = attach_type_to_prog_type(attr->attach_type); if (bpf_mprog_supported(ptype)) { if (ptype == BPF_PROG_TYPE_UNSPEC) return -EINVAL; if (attr->attach_flags & ~BPF_F_ATTACH_MASK_MPROG) return -EINVAL; if (attr->attach_bpf_fd) { prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); if (IS_ERR(prog)) return PTR_ERR(prog); } } else if (attr->attach_flags || attr->relative_fd || attr->expected_revision) { return -EINVAL; } switch (ptype) { case BPF_PROG_TYPE_SK_MSG: case BPF_PROG_TYPE_SK_SKB: ret = sock_map_prog_detach(attr, ptype); break; case BPF_PROG_TYPE_LIRC_MODE2: ret = lirc_prog_detach(attr); break; case BPF_PROG_TYPE_FLOW_DISSECTOR: ret = netns_bpf_prog_detach(attr, ptype); break; case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SKB: case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: case BPF_PROG_TYPE_CGROUP_SOCKOPT: case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_SOCK_OPS: case BPF_PROG_TYPE_LSM: ret = cgroup_bpf_prog_detach(attr, ptype); break; case BPF_PROG_TYPE_SCHED_CLS: if (attr->attach_type == BPF_TCX_INGRESS || attr->attach_type == BPF_TCX_EGRESS) ret = tcx_prog_detach(attr, prog); else ret = netkit_prog_detach(attr, prog); break; default: ret = -EINVAL; } if (prog) bpf_prog_put(prog); return ret; } #define BPF_PROG_QUERY_LAST_FIELD query.revision static int bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { if (!bpf_net_capable()) return -EPERM; if (CHECK_ATTR(BPF_PROG_QUERY)) return -EINVAL; if (attr->query.query_flags & ~BPF_F_QUERY_EFFECTIVE) return -EINVAL; switch (attr->query.attach_type) { case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: case BPF_CGROUP_INET_SOCK_CREATE: case BPF_CGROUP_INET_SOCK_RELEASE: case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_POST_BIND: case BPF_CGROUP_INET6_POST_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UNIX_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_SOCK_OPS: case BPF_CGROUP_DEVICE: case BPF_CGROUP_SYSCTL: case BPF_CGROUP_GETSOCKOPT: case BPF_CGROUP_SETSOCKOPT: case BPF_LSM_CGROUP: return cgroup_bpf_prog_query(attr, uattr); case BPF_LIRC_MODE2: return lirc_prog_query(attr, uattr); case BPF_FLOW_DISSECTOR: case BPF_SK_LOOKUP: return netns_bpf_prog_query(attr, uattr); case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: case BPF_SK_MSG_VERDICT: case BPF_SK_SKB_VERDICT: return sock_map_bpf_prog_query(attr, uattr); case BPF_TCX_INGRESS: case BPF_TCX_EGRESS: return tcx_prog_query(attr, uattr); case BPF_NETKIT_PRIMARY: case BPF_NETKIT_PEER: return netkit_prog_query(attr, uattr); default: return -EINVAL; } } #define BPF_PROG_TEST_RUN_LAST_FIELD test.batch_size static int bpf_prog_test_run(const union bpf_attr *attr, union bpf_attr __user *uattr) { struct bpf_prog *prog; int ret = -ENOTSUPP; if (CHECK_ATTR(BPF_PROG_TEST_RUN)) return -EINVAL; if ((attr->test.ctx_size_in && !attr->test.ctx_in) || (!attr->test.ctx_size_in && attr->test.ctx_in)) return -EINVAL; if ((attr->test.ctx_size_out && !attr->test.ctx_out) || (!attr->test.ctx_size_out && attr->test.ctx_out)) return -EINVAL; prog = bpf_prog_get(attr->test.prog_fd); if (IS_ERR(prog)) return PTR_ERR(prog); if (prog->aux->ops->test_run) ret = prog->aux->ops->test_run(prog, attr, uattr); bpf_prog_put(prog); return ret; } #define BPF_OBJ_GET_NEXT_ID_LAST_FIELD next_id static int bpf_obj_get_next_id(const union bpf_attr *attr, union bpf_attr __user *uattr, struct idr *idr, spinlock_t *lock) { u32 next_id = attr->start_id; int err = 0; if (CHECK_ATTR(BPF_OBJ_GET_NEXT_ID) || next_id >= INT_MAX) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; next_id++; spin_lock_bh(lock); if (!idr_get_next(idr, &next_id)) err = -ENOENT; spin_unlock_bh(lock); if (!err) err = put_user(next_id, &uattr->next_id); return err; } struct bpf_map *bpf_map_get_curr_or_next(u32 *id) { struct bpf_map *map; spin_lock_bh(&map_idr_lock); again: map = idr_get_next(&map_idr, id); if (map) { map = __bpf_map_inc_not_zero(map, false); if (IS_ERR(map)) { (*id)++; goto again; } } spin_unlock_bh(&map_idr_lock); return map; } struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id) { struct bpf_prog *prog; spin_lock_bh(&prog_idr_lock); again: prog = idr_get_next(&prog_idr, id); if (prog) { prog = bpf_prog_inc_not_zero(prog); if (IS_ERR(prog)) { (*id)++; goto again; } } spin_unlock_bh(&prog_idr_lock); return prog; } #define BPF_PROG_GET_FD_BY_ID_LAST_FIELD prog_id struct bpf_prog *bpf_prog_by_id(u32 id) { struct bpf_prog *prog; if (!id) return ERR_PTR(-ENOENT); spin_lock_bh(&prog_idr_lock); prog = idr_find(&prog_idr, id); if (prog) prog = bpf_prog_inc_not_zero(prog); else prog = ERR_PTR(-ENOENT); spin_unlock_bh(&prog_idr_lock); return prog; } static int bpf_prog_get_fd_by_id(const union bpf_attr *attr) { struct bpf_prog *prog; u32 id = attr->prog_id; int fd; if (CHECK_ATTR(BPF_PROG_GET_FD_BY_ID)) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; prog = bpf_prog_by_id(id); if (IS_ERR(prog)) return PTR_ERR(prog); fd = bpf_prog_new_fd(prog); if (fd < 0) bpf_prog_put(prog); return fd; } #define BPF_MAP_GET_FD_BY_ID_LAST_FIELD open_flags static int bpf_map_get_fd_by_id(const union bpf_attr *attr) { struct bpf_map *map; u32 id = attr->map_id; int f_flags; int fd; if (CHECK_ATTR(BPF_MAP_GET_FD_BY_ID) || attr->open_flags & ~BPF_OBJ_FLAG_MASK) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; f_flags = bpf_get_file_flag(attr->open_flags); if (f_flags < 0) return f_flags; spin_lock_bh(&map_idr_lock); map = idr_find(&map_idr, id); if (map) map = __bpf_map_inc_not_zero(map, true); else map = ERR_PTR(-ENOENT); spin_unlock_bh(&map_idr_lock); if (IS_ERR(map)) return PTR_ERR(map); fd = bpf_map_new_fd(map, f_flags); if (fd < 0) bpf_map_put_with_uref(map); return fd; } static const struct bpf_map *bpf_map_from_imm(const struct bpf_prog *prog, unsigned long addr, u32 *off, u32 *type) { const struct bpf_map *map; int i; mutex_lock(&prog->aux->used_maps_mutex); for (i = 0, *off = 0; i < prog->aux->used_map_cnt; i++) { map = prog->aux->used_maps[i]; if (map == (void *)addr) { *type = BPF_PSEUDO_MAP_FD; goto out; } if (!map->ops->map_direct_value_meta) continue; if (!map->ops->map_direct_value_meta(map, addr, off)) { *type = BPF_PSEUDO_MAP_VALUE; goto out; } } map = NULL; out: mutex_unlock(&prog->aux->used_maps_mutex); return map; } static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog, const struct cred *f_cred) { const struct bpf_map *map; struct bpf_insn *insns; u32 off, type; u64 imm; u8 code; int i; insns = kmemdup(prog->insnsi, bpf_prog_insn_size(prog), GFP_USER); if (!insns) return insns; for (i = 0; i < prog->len; i++) { code = insns[i].code; if (code == (BPF_JMP | BPF_TAIL_CALL)) { insns[i].code = BPF_JMP | BPF_CALL; insns[i].imm = BPF_FUNC_tail_call; /* fall-through */ } if (code == (BPF_JMP | BPF_CALL) || code == (BPF_JMP | BPF_CALL_ARGS)) { if (code == (BPF_JMP | BPF_CALL_ARGS)) insns[i].code = BPF_JMP | BPF_CALL; if (!bpf_dump_raw_ok(f_cred)) insns[i].imm = 0; continue; } if (BPF_CLASS(code) == BPF_LDX && BPF_MODE(code) == BPF_PROBE_MEM) { insns[i].code = BPF_LDX | BPF_SIZE(code) | BPF_MEM; continue; } if ((BPF_CLASS(code) == BPF_LDX || BPF_CLASS(code) == BPF_STX || BPF_CLASS(code) == BPF_ST) && BPF_MODE(code) == BPF_PROBE_MEM32) { insns[i].code = BPF_CLASS(code) | BPF_SIZE(code) | BPF_MEM; continue; } if (code != (BPF_LD | BPF_IMM | BPF_DW)) continue; imm = ((u64)insns[i + 1].imm << 32) | (u32)insns[i].imm; map = bpf_map_from_imm(prog, imm, &off, &type); if (map) { insns[i].src_reg = type; insns[i].imm = map->id; insns[i + 1].imm = off; continue; } } return insns; } static int set_info_rec_size(struct bpf_prog_info *info) { /* * Ensure info.*_rec_size is the same as kernel expected size * * or * * Only allow zero *_rec_size if both _rec_size and _cnt are * zero. In this case, the kernel will set the expected * _rec_size back to the info. */ if ((info->nr_func_info || info->func_info_rec_size) && info->func_info_rec_size != sizeof(struct bpf_func_info)) return -EINVAL; if ((info->nr_line_info || info->line_info_rec_size) && info->line_info_rec_size != sizeof(struct bpf_line_info)) return -EINVAL; if ((info->nr_jited_line_info || info->jited_line_info_rec_size) && info->jited_line_info_rec_size != sizeof(__u64)) return -EINVAL; info->func_info_rec_size = sizeof(struct bpf_func_info); info->line_info_rec_size = sizeof(struct bpf_line_info); info->jited_line_info_rec_size = sizeof(__u64); return 0; } static int bpf_prog_get_info_by_fd(struct file *file, struct bpf_prog *prog, const union bpf_attr *attr, union bpf_attr __user *uattr) { struct bpf_prog_info __user *uinfo = u64_to_user_ptr(attr->info.info); struct btf *attach_btf = bpf_prog_get_target_btf(prog); struct bpf_prog_info info; u32 info_len = attr->info.info_len; struct bpf_prog_kstats stats; char __user *uinsns; u32 ulen; int err; err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); memset(&info, 0, sizeof(info)); if (copy_from_user(&info, uinfo, info_len)) return -EFAULT; info.type = prog->type; info.id = prog->aux->id; info.load_time = prog->aux->load_time; info.created_by_uid = from_kuid_munged(current_user_ns(), prog->aux->user->uid); info.gpl_compatible = prog->gpl_compatible; memcpy(info.tag, prog->tag, sizeof(prog->tag)); memcpy(info.name, prog->aux->name, sizeof(prog->aux->name)); mutex_lock(&prog->aux->used_maps_mutex); ulen = info.nr_map_ids; info.nr_map_ids = prog->aux->used_map_cnt; ulen = min_t(u32, info.nr_map_ids, ulen); if (ulen) { u32 __user *user_map_ids = u64_to_user_ptr(info.map_ids); u32 i; for (i = 0; i < ulen; i++) if (put_user(prog->aux->used_maps[i]->id, &user_map_ids[i])) { mutex_unlock(&prog->aux->used_maps_mutex); return -EFAULT; } } mutex_unlock(&prog->aux->used_maps_mutex); err = set_info_rec_size(&info); if (err) return err; bpf_prog_get_stats(prog, &stats); info.run_time_ns = stats.nsecs; info.run_cnt = stats.cnt; info.recursion_misses = stats.misses; info.verified_insns = prog->aux->verified_insns; if (!bpf_capable()) { info.jited_prog_len = 0; info.xlated_prog_len = 0; info.nr_jited_ksyms = 0; info.nr_jited_func_lens = 0; info.nr_func_info = 0; info.nr_line_info = 0; info.nr_jited_line_info = 0; goto done; } ulen = info.xlated_prog_len; info.xlated_prog_len = bpf_prog_insn_size(prog); if (info.xlated_prog_len && ulen) { struct bpf_insn *insns_sanitized; bool fault; if (prog->blinded && !bpf_dump_raw_ok(file->f_cred)) { info.xlated_prog_insns = 0; goto done; } insns_sanitized = bpf_insn_prepare_dump(prog, file->f_cred); if (!insns_sanitized) return -ENOMEM; uinsns = u64_to_user_ptr(info.xlated_prog_insns); ulen = min_t(u32, info.xlated_prog_len, ulen); fault = copy_to_user(uinsns, insns_sanitized, ulen); kfree(insns_sanitized); if (fault) return -EFAULT; } if (bpf_prog_is_offloaded(prog->aux)) { err = bpf_prog_offload_info_fill(&info, prog); if (err) return err; goto done; } /* NOTE: the following code is supposed to be skipped for offload. * bpf_prog_offload_info_fill() is the place to fill similar fields * for offload. */ ulen = info.jited_prog_len; if (prog->aux->func_cnt) { u32 i; info.jited_prog_len = 0; for (i = 0; i < prog->aux->func_cnt; i++) info.jited_prog_len += prog->aux->func[i]->jited_len; } else { info.jited_prog_len = prog->jited_len; } if (info.jited_prog_len && ulen) { if (bpf_dump_raw_ok(file->f_cred)) { uinsns = u64_to_user_ptr(info.jited_prog_insns); ulen = min_t(u32, info.jited_prog_len, ulen); /* for multi-function programs, copy the JITed * instructions for all the functions */ if (prog->aux->func_cnt) { u32 len, free, i; u8 *img; free = ulen; for (i = 0; i < prog->aux->func_cnt; i++) { len = prog->aux->func[i]->jited_len; len = min_t(u32, len, free); img = (u8 *) prog->aux->func[i]->bpf_func; if (copy_to_user(uinsns, img, len)) return -EFAULT; uinsns += len; free -= len; if (!free) break; } } else { if (copy_to_user(uinsns, prog->bpf_func, ulen)) return -EFAULT; } } else { info.jited_prog_insns = 0; } } ulen = info.nr_jited_ksyms; info.nr_jited_ksyms = prog->aux->func_cnt ? : 1; if (ulen) { if (bpf_dump_raw_ok(file->f_cred)) { unsigned long ksym_addr; u64 __user *user_ksyms; u32 i; /* copy the address of the kernel symbol * corresponding to each function */ ulen = min_t(u32, info.nr_jited_ksyms, ulen); user_ksyms = u64_to_user_ptr(info.jited_ksyms); if (prog->aux->func_cnt) { for (i = 0; i < ulen; i++) { ksym_addr = (unsigned long) prog->aux->func[i]->bpf_func; if (put_user((u64) ksym_addr, &user_ksyms[i])) return -EFAULT; } } else { ksym_addr = (unsigned long) prog->bpf_func; if (put_user((u64) ksym_addr, &user_ksyms[0])) return -EFAULT; } } else { info.jited_ksyms = 0; } } ulen = info.nr_jited_func_lens; info.nr_jited_func_lens = prog->aux->func_cnt ? : 1; if (ulen) { if (bpf_dump_raw_ok(file->f_cred)) { u32 __user *user_lens; u32 func_len, i; /* copy the JITed image lengths for each function */ ulen = min_t(u32, info.nr_jited_func_lens, ulen); user_lens = u64_to_user_ptr(info.jited_func_lens); if (prog->aux->func_cnt) { for (i = 0; i < ulen; i++) { func_len = prog->aux->func[i]->jited_len; if (put_user(func_len, &user_lens[i])) return -EFAULT; } } else { func_len = prog->jited_len; if (put_user(func_len, &user_lens[0])) return -EFAULT; } } else { info.jited_func_lens = 0; } } if (prog->aux->btf) info.btf_id = btf_obj_id(prog->aux->btf); info.attach_btf_id = prog->aux->attach_btf_id; if (attach_btf) info.attach_btf_obj_id = btf_obj_id(attach_btf); ulen = info.nr_func_info; info.nr_func_info = prog->aux->func_info_cnt; if (info.nr_func_info && ulen) { char __user *user_finfo; user_finfo = u64_to_user_ptr(info.func_info); ulen = min_t(u32, info.nr_func_info, ulen); if (copy_to_user(user_finfo, prog->aux->func_info, info.func_info_rec_size * ulen)) return -EFAULT; } ulen = info.nr_line_info; info.nr_line_info = prog->aux->nr_linfo; if (info.nr_line_info && ulen) { __u8 __user *user_linfo; user_linfo = u64_to_user_ptr(info.line_info); ulen = min_t(u32, info.nr_line_info, ulen); if (copy_to_user(user_linfo, prog->aux->linfo, info.line_info_rec_size * ulen)) return -EFAULT; } ulen = info.nr_jited_line_info; if (prog->aux->jited_linfo) info.nr_jited_line_info = prog->aux->nr_linfo; else info.nr_jited_line_info = 0; if (info.nr_jited_line_info && ulen) { if (bpf_dump_raw_ok(file->f_cred)) { unsigned long line_addr; __u64 __user *user_linfo; u32 i; user_linfo = u64_to_user_ptr(info.jited_line_info); ulen = min_t(u32, info.nr_jited_line_info, ulen); for (i = 0; i < ulen; i++) { line_addr = (unsigned long)prog->aux->jited_linfo[i]; if (put_user((__u64)line_addr, &user_linfo[i])) return -EFAULT; } } else { info.jited_line_info = 0; } } ulen = info.nr_prog_tags; info.nr_prog_tags = prog->aux->func_cnt ? : 1; if (ulen) { __u8 __user (*user_prog_tags)[BPF_TAG_SIZE]; u32 i; user_prog_tags = u64_to_user_ptr(info.prog_tags); ulen = min_t(u32, info.nr_prog_tags, ulen); if (prog->aux->func_cnt) { for (i = 0; i < ulen; i++) { if (copy_to_user(user_prog_tags[i], prog->aux->func[i]->tag, BPF_TAG_SIZE)) return -EFAULT; } } else { if (copy_to_user(user_prog_tags[0], prog->tag, BPF_TAG_SIZE)) return -EFAULT; } } done: if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) return -EFAULT; return 0; } static int bpf_map_get_info_by_fd(struct file *file, struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr) { struct bpf_map_info __user *uinfo = u64_to_user_ptr(attr->info.info); struct bpf_map_info info; u32 info_len = attr->info.info_len; int err; err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); memset(&info, 0, sizeof(info)); info.type = map->map_type; info.id = map->id; info.key_size = map->key_size; info.value_size = map->value_size; info.max_entries = map->max_entries; info.map_flags = map->map_flags; info.map_extra = map->map_extra; memcpy(info.name, map->name, sizeof(map->name)); if (map->btf) { info.btf_id = btf_obj_id(map->btf); info.btf_key_type_id = map->btf_key_type_id; info.btf_value_type_id = map->btf_value_type_id; } info.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id; if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) bpf_map_struct_ops_info_fill(&info, map); if (bpf_map_is_offloaded(map)) { err = bpf_map_offload_info_fill(&info, map); if (err) return err; } if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) return -EFAULT; return 0; } static int bpf_btf_get_info_by_fd(struct file *file, struct btf *btf, const union bpf_attr *attr, union bpf_attr __user *uattr) { struct bpf_btf_info __user *uinfo = u64_to_user_ptr(attr->info.info); u32 info_len = attr->info.info_len; int err; err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(*uinfo), info_len); if (err) return err; return btf_get_info_by_fd(btf, attr, uattr); } static int bpf_link_get_info_by_fd(struct file *file, struct bpf_link *link, const union bpf_attr *attr, union bpf_attr __user *uattr) { struct bpf_link_info __user *uinfo = u64_to_user_ptr(attr->info.info); struct bpf_link_info info; u32 info_len = attr->info.info_len; int err; err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(info), info_len); if (err) return err; info_len = min_t(u32, sizeof(info), info_len); memset(&info, 0, sizeof(info)); if (copy_from_user(&info, uinfo, info_len)) return -EFAULT; info.type = link->type; info.id = link->id; if (link->prog) info.prog_id = link->prog->aux->id; if (link->ops->fill_link_info) { err = link->ops->fill_link_info(link, &info); if (err) return err; } if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) return -EFAULT; return 0; } #define BPF_OBJ_GET_INFO_BY_FD_LAST_FIELD info.info static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, union bpf_attr __user *uattr) { if (CHECK_ATTR(BPF_OBJ_GET_INFO_BY_FD)) return -EINVAL; CLASS(fd, f)(attr->info.bpf_fd); if (fd_empty(f)) return -EBADFD; if (fd_file(f)->f_op == &bpf_prog_fops) return bpf_prog_get_info_by_fd(fd_file(f), fd_file(f)->private_data, attr, uattr); else if (fd_file(f)->f_op == &bpf_map_fops) return bpf_map_get_info_by_fd(fd_file(f), fd_file(f)->private_data, attr, uattr); else if (fd_file(f)->f_op == &btf_fops) return bpf_btf_get_info_by_fd(fd_file(f), fd_file(f)->private_data, attr, uattr); else if (fd_file(f)->f_op == &bpf_link_fops || fd_file(f)->f_op == &bpf_link_fops_poll) return bpf_link_get_info_by_fd(fd_file(f), fd_file(f)->private_data, attr, uattr); return -EINVAL; } #define BPF_BTF_LOAD_LAST_FIELD btf_token_fd static int bpf_btf_load(const union bpf_attr *attr, bpfptr_t uattr, __u32 uattr_size) { struct bpf_token *token = NULL; if (CHECK_ATTR(BPF_BTF_LOAD)) return -EINVAL; if (attr->btf_flags & ~BPF_F_TOKEN_FD) return -EINVAL; if (attr->btf_flags & BPF_F_TOKEN_FD) { token = bpf_token_get_from_fd(attr->btf_token_fd); if (IS_ERR(token)) return PTR_ERR(token); if (!bpf_token_allow_cmd(token, BPF_BTF_LOAD)) { bpf_token_put(token); token = NULL; } } if (!bpf_token_capable(token, CAP_BPF)) { bpf_token_put(token); return -EPERM; } bpf_token_put(token); return btf_new_fd(attr, uattr, uattr_size); } #define BPF_BTF_GET_FD_BY_ID_LAST_FIELD btf_id static int bpf_btf_get_fd_by_id(const union bpf_attr *attr) { if (CHECK_ATTR(BPF_BTF_GET_FD_BY_ID)) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; return btf_get_fd_by_id(attr->btf_id); } static int bpf_task_fd_query_copy(const union bpf_attr *attr, union bpf_attr __user *uattr, u32 prog_id, u32 fd_type, const char *buf, u64 probe_offset, u64 probe_addr) { char __user *ubuf = u64_to_user_ptr(attr->task_fd_query.buf); u32 len = buf ? strlen(buf) : 0, input_len; int err = 0; if (put_user(len, &uattr->task_fd_query.buf_len)) return -EFAULT; input_len = attr->task_fd_query.buf_len; if (input_len && ubuf) { if (!len) { /* nothing to copy, just make ubuf NULL terminated */ char zero = '\0'; if (put_user(zero, ubuf)) return -EFAULT; } else if (input_len >= len + 1) { /* ubuf can hold the string with NULL terminator */ if (copy_to_user(ubuf, buf, len + 1)) return -EFAULT; } else { /* ubuf cannot hold the string with NULL terminator, * do a partial copy with NULL terminator. */ char zero = '\0'; err = -ENOSPC; if (copy_to_user(ubuf, buf, input_len - 1)) return -EFAULT; if (put_user(zero, ubuf + input_len - 1)) return -EFAULT; } } if (put_user(prog_id, &uattr->task_fd_query.prog_id) || put_user(fd_type, &uattr->task_fd_query.fd_type) || put_user(probe_offset, &uattr->task_fd_query.probe_offset) || put_user(probe_addr, &uattr->task_fd_query.probe_addr)) return -EFAULT; return err; } #define BPF_TASK_FD_QUERY_LAST_FIELD task_fd_query.probe_addr static int bpf_task_fd_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { pid_t pid = attr->task_fd_query.pid; u32 fd = attr->task_fd_query.fd; const struct perf_event *event; struct task_struct *task; struct file *file; int err; if (CHECK_ATTR(BPF_TASK_FD_QUERY)) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (attr->task_fd_query.flags != 0) return -EINVAL; rcu_read_lock(); task = get_pid_task(find_vpid(pid), PIDTYPE_PID); rcu_read_unlock(); if (!task) return -ENOENT; err = 0; file = fget_task(task, fd); put_task_struct(task); if (!file) return -EBADF; if (file->f_op == &bpf_link_fops || file->f_op == &bpf_link_fops_poll) { struct bpf_link *link = file->private_data; if (link->ops == &bpf_raw_tp_link_lops) { struct bpf_raw_tp_link *raw_tp = container_of(link, struct bpf_raw_tp_link, link); struct bpf_raw_event_map *btp = raw_tp->btp; err = bpf_task_fd_query_copy(attr, uattr, raw_tp->link.prog->aux->id, BPF_FD_TYPE_RAW_TRACEPOINT, btp->tp->name, 0, 0); goto put_file; } goto out_not_supp; } event = perf_get_event(file); if (!IS_ERR(event)) { u64 probe_offset, probe_addr; u32 prog_id, fd_type; const char *buf; err = bpf_get_perf_event_info(event, &prog_id, &fd_type, &buf, &probe_offset, &probe_addr, NULL); if (!err) err = bpf_task_fd_query_copy(attr, uattr, prog_id, fd_type, buf, probe_offset, probe_addr); goto put_file; } out_not_supp: err = -ENOTSUPP; put_file: fput(file); return err; } #define BPF_MAP_BATCH_LAST_FIELD batch.flags #define BPF_DO_BATCH(fn, ...) \ do { \ if (!fn) { \ err = -ENOTSUPP; \ goto err_put; \ } \ err = fn(__VA_ARGS__); \ } while (0) static int bpf_map_do_batch(const union bpf_attr *attr, union bpf_attr __user *uattr, int cmd) { bool has_read = cmd == BPF_MAP_LOOKUP_BATCH || cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH; bool has_write = cmd != BPF_MAP_LOOKUP_BATCH; struct bpf_map *map; int err; if (CHECK_ATTR(BPF_MAP_BATCH)) return -EINVAL; CLASS(fd, f)(attr->batch.map_fd); map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); if (has_write) bpf_map_write_active_inc(map); if (has_read && !(map_get_sys_perms(map, f) & FMODE_CAN_READ)) { err = -EPERM; goto err_put; } if (has_write && !(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) { err = -EPERM; goto err_put; } if (cmd == BPF_MAP_LOOKUP_BATCH) BPF_DO_BATCH(map->ops->map_lookup_batch, map, attr, uattr); else if (cmd == BPF_MAP_LOOKUP_AND_DELETE_BATCH) BPF_DO_BATCH(map->ops->map_lookup_and_delete_batch, map, attr, uattr); else if (cmd == BPF_MAP_UPDATE_BATCH) BPF_DO_BATCH(map->ops->map_update_batch, map, fd_file(f), attr, uattr); else BPF_DO_BATCH(map->ops->map_delete_batch, map, attr, uattr); err_put: if (has_write) { maybe_wait_bpf_programs(map); bpf_map_write_active_dec(map); } return err; } #define BPF_LINK_CREATE_LAST_FIELD link_create.uprobe_multi.pid static int link_create(union bpf_attr *attr, bpfptr_t uattr) { struct bpf_prog *prog; int ret; if (CHECK_ATTR(BPF_LINK_CREATE)) return -EINVAL; if (attr->link_create.attach_type == BPF_STRUCT_OPS) return bpf_struct_ops_link_create(attr); prog = bpf_prog_get(attr->link_create.prog_fd); if (IS_ERR(prog)) return PTR_ERR(prog); ret = bpf_prog_attach_check_attach_type(prog, attr->link_create.attach_type); if (ret) goto out; switch (prog->type) { case BPF_PROG_TYPE_CGROUP_SKB: case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: case BPF_PROG_TYPE_SOCK_OPS: case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SYSCTL: case BPF_PROG_TYPE_CGROUP_SOCKOPT: ret = cgroup_bpf_link_attach(attr, prog); break; case BPF_PROG_TYPE_EXT: ret = bpf_tracing_prog_attach(prog, attr->link_create.target_fd, attr->link_create.target_btf_id, attr->link_create.tracing.cookie); break; case BPF_PROG_TYPE_LSM: case BPF_PROG_TYPE_TRACING: if (attr->link_create.attach_type != prog->expected_attach_type) { ret = -EINVAL; goto out; } if (prog->expected_attach_type == BPF_TRACE_RAW_TP) ret = bpf_raw_tp_link_attach(prog, NULL, attr->link_create.tracing.cookie); else if (prog->expected_attach_type == BPF_TRACE_ITER) ret = bpf_iter_link_attach(attr, uattr, prog); else if (prog->expected_attach_type == BPF_LSM_CGROUP) ret = cgroup_bpf_link_attach(attr, prog); else ret = bpf_tracing_prog_attach(prog, attr->link_create.target_fd, attr->link_create.target_btf_id, attr->link_create.tracing.cookie); break; case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_SK_LOOKUP: ret = netns_bpf_link_create(attr, prog); break; case BPF_PROG_TYPE_SK_MSG: case BPF_PROG_TYPE_SK_SKB: ret = sock_map_link_create(attr, prog); break; #ifdef CONFIG_NET case BPF_PROG_TYPE_XDP: ret = bpf_xdp_link_attach(attr, prog); break; case BPF_PROG_TYPE_SCHED_CLS: if (attr->link_create.attach_type == BPF_TCX_INGRESS || attr->link_create.attach_type == BPF_TCX_EGRESS) ret = tcx_link_attach(attr, prog); else ret = netkit_link_attach(attr, prog); break; case BPF_PROG_TYPE_NETFILTER: ret = bpf_nf_link_attach(attr, prog); break; #endif case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_TRACEPOINT: ret = bpf_perf_link_attach(attr, prog); break; case BPF_PROG_TYPE_KPROBE: if (attr->link_create.attach_type == BPF_PERF_EVENT) ret = bpf_perf_link_attach(attr, prog); else if (attr->link_create.attach_type == BPF_TRACE_KPROBE_MULTI || attr->link_create.attach_type == BPF_TRACE_KPROBE_SESSION) ret = bpf_kprobe_multi_link_attach(attr, prog); else if (attr->link_create.attach_type == BPF_TRACE_UPROBE_MULTI || attr->link_create.attach_type == BPF_TRACE_UPROBE_SESSION) ret = bpf_uprobe_multi_link_attach(attr, prog); break; default: ret = -EINVAL; } out: if (ret < 0) bpf_prog_put(prog); return ret; } static int link_update_map(struct bpf_link *link, union bpf_attr *attr) { struct bpf_map *new_map, *old_map = NULL; int ret; new_map = bpf_map_get(attr->link_update.new_map_fd); if (IS_ERR(new_map)) return PTR_ERR(new_map); if (attr->link_update.flags & BPF_F_REPLACE) { old_map = bpf_map_get(attr->link_update.old_map_fd); if (IS_ERR(old_map)) { ret = PTR_ERR(old_map); goto out_put; } } else if (attr->link_update.old_map_fd) { ret = -EINVAL; goto out_put; } ret = link->ops->update_map(link, new_map, old_map); if (old_map) bpf_map_put(old_map); out_put: bpf_map_put(new_map); return ret; } #define BPF_LINK_UPDATE_LAST_FIELD link_update.old_prog_fd static int link_update(union bpf_attr *attr) { struct bpf_prog *old_prog = NULL, *new_prog; struct bpf_link *link; u32 flags; int ret; if (CHECK_ATTR(BPF_LINK_UPDATE)) return -EINVAL; flags = attr->link_update.flags; if (flags & ~BPF_F_REPLACE) return -EINVAL; link = bpf_link_get_from_fd(attr->link_update.link_fd); if (IS_ERR(link)) return PTR_ERR(link); if (link->ops->update_map) { ret = link_update_map(link, attr); goto out_put_link; } new_prog = bpf_prog_get(attr->link_update.new_prog_fd); if (IS_ERR(new_prog)) { ret = PTR_ERR(new_prog); goto out_put_link; } if (flags & BPF_F_REPLACE) { old_prog = bpf_prog_get(attr->link_update.old_prog_fd); if (IS_ERR(old_prog)) { ret = PTR_ERR(old_prog); old_prog = NULL; goto out_put_progs; } } else if (attr->link_update.old_prog_fd) { ret = -EINVAL; goto out_put_progs; } if (link->ops->update_prog) ret = link->ops->update_prog(link, new_prog, old_prog); else ret = -EINVAL; out_put_progs: if (old_prog) bpf_prog_put(old_prog); if (ret) bpf_prog_put(new_prog); out_put_link: bpf_link_put_direct(link); return ret; } #define BPF_LINK_DETACH_LAST_FIELD link_detach.link_fd static int link_detach(union bpf_attr *attr) { struct bpf_link *link; int ret; if (CHECK_ATTR(BPF_LINK_DETACH)) return -EINVAL; link = bpf_link_get_from_fd(attr->link_detach.link_fd); if (IS_ERR(link)) return PTR_ERR(link); if (link->ops->detach) ret = link->ops->detach(link); else ret = -EOPNOTSUPP; bpf_link_put_direct(link); return ret; } struct bpf_link *bpf_link_inc_not_zero(struct bpf_link *link) { return atomic64_fetch_add_unless(&link->refcnt, 1, 0) ? link : ERR_PTR(-ENOENT); } EXPORT_SYMBOL(bpf_link_inc_not_zero); struct bpf_link *bpf_link_by_id(u32 id) { struct bpf_link *link; if (!id) return ERR_PTR(-ENOENT); spin_lock_bh(&link_idr_lock); /* before link is "settled", ID is 0, pretend it doesn't exist yet */ link = idr_find(&link_idr, id); if (link) { if (link->id) link = bpf_link_inc_not_zero(link); else link = ERR_PTR(-EAGAIN); } else { link = ERR_PTR(-ENOENT); } spin_unlock_bh(&link_idr_lock); return link; } struct bpf_link *bpf_link_get_curr_or_next(u32 *id) { struct bpf_link *link; spin_lock_bh(&link_idr_lock); again: link = idr_get_next(&link_idr, id); if (link) { link = bpf_link_inc_not_zero(link); if (IS_ERR(link)) { (*id)++; goto again; } } spin_unlock_bh(&link_idr_lock); return link; } #define BPF_LINK_GET_FD_BY_ID_LAST_FIELD link_id static int bpf_link_get_fd_by_id(const union bpf_attr *attr) { struct bpf_link *link; u32 id = attr->link_id; int fd; if (CHECK_ATTR(BPF_LINK_GET_FD_BY_ID)) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; link = bpf_link_by_id(id); if (IS_ERR(link)) return PTR_ERR(link); fd = bpf_link_new_fd(link); if (fd < 0) bpf_link_put_direct(link); return fd; } DEFINE_MUTEX(bpf_stats_enabled_mutex); static int bpf_stats_release(struct inode *inode, struct file *file) { mutex_lock(&bpf_stats_enabled_mutex); static_key_slow_dec(&bpf_stats_enabled_key.key); mutex_unlock(&bpf_stats_enabled_mutex); return 0; } static const struct file_operations bpf_stats_fops = { .release = bpf_stats_release, }; static int bpf_enable_runtime_stats(void) { int fd; mutex_lock(&bpf_stats_enabled_mutex); /* Set a very high limit to avoid overflow */ if (static_key_count(&bpf_stats_enabled_key.key) > INT_MAX / 2) { mutex_unlock(&bpf_stats_enabled_mutex); return -EBUSY; } fd = anon_inode_getfd("bpf-stats", &bpf_stats_fops, NULL, O_CLOEXEC); if (fd >= 0) static_key_slow_inc(&bpf_stats_enabled_key.key); mutex_unlock(&bpf_stats_enabled_mutex); return fd; } #define BPF_ENABLE_STATS_LAST_FIELD enable_stats.type static int bpf_enable_stats(union bpf_attr *attr) { if (CHECK_ATTR(BPF_ENABLE_STATS)) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; switch (attr->enable_stats.type) { case BPF_STATS_RUN_TIME: return bpf_enable_runtime_stats(); default: break; } return -EINVAL; } #define BPF_ITER_CREATE_LAST_FIELD iter_create.flags static int bpf_iter_create(union bpf_attr *attr) { struct bpf_link *link; int err; if (CHECK_ATTR(BPF_ITER_CREATE)) return -EINVAL; if (attr->iter_create.flags) return -EINVAL; link = bpf_link_get_from_fd(attr->iter_create.link_fd); if (IS_ERR(link)) return PTR_ERR(link); err = bpf_iter_new_fd(link); bpf_link_put_direct(link); return err; } #define BPF_PROG_BIND_MAP_LAST_FIELD prog_bind_map.flags static int bpf_prog_bind_map(union bpf_attr *attr) { struct bpf_prog *prog; struct bpf_map *map; struct bpf_map **used_maps_old, **used_maps_new; int i, ret = 0; if (CHECK_ATTR(BPF_PROG_BIND_MAP)) return -EINVAL; if (attr->prog_bind_map.flags) return -EINVAL; prog = bpf_prog_get(attr->prog_bind_map.prog_fd); if (IS_ERR(prog)) return PTR_ERR(prog); map = bpf_map_get(attr->prog_bind_map.map_fd); if (IS_ERR(map)) { ret = PTR_ERR(map); goto out_prog_put; } mutex_lock(&prog->aux->used_maps_mutex); used_maps_old = prog->aux->used_maps; for (i = 0; i < prog->aux->used_map_cnt; i++) if (used_maps_old[i] == map) { bpf_map_put(map); goto out_unlock; } used_maps_new = kmalloc_array(prog->aux->used_map_cnt + 1, sizeof(used_maps_new[0]), GFP_KERNEL); if (!used_maps_new) { ret = -ENOMEM; goto out_unlock; } /* The bpf program will not access the bpf map, but for the sake of * simplicity, increase sleepable_refcnt for sleepable program as well. */ if (prog->sleepable) atomic64_inc(&map->sleepable_refcnt); memcpy(used_maps_new, used_maps_old, sizeof(used_maps_old[0]) * prog->aux->used_map_cnt); used_maps_new[prog->aux->used_map_cnt] = map; prog->aux->used_map_cnt++; prog->aux->used_maps = used_maps_new; kfree(used_maps_old); out_unlock: mutex_unlock(&prog->aux->used_maps_mutex); if (ret) bpf_map_put(map); out_prog_put: bpf_prog_put(prog); return ret; } #define BPF_TOKEN_CREATE_LAST_FIELD token_create.bpffs_fd static int token_create(union bpf_attr *attr) { if (CHECK_ATTR(BPF_TOKEN_CREATE)) return -EINVAL; /* no flags are supported yet */ if (attr->token_create.flags) return -EINVAL; return bpf_token_create(attr); } static int __sys_bpf(enum bpf_cmd cmd, bpfptr_t uattr, unsigned int size) { union bpf_attr attr; int err; err = bpf_check_uarg_tail_zero(uattr, sizeof(attr), size); if (err) return err; size = min_t(u32, size, sizeof(attr)); /* copy attributes from user space, may be less than sizeof(bpf_attr) */ memset(&attr, 0, sizeof(attr)); if (copy_from_bpfptr(&attr, uattr, size) != 0) return -EFAULT; err = security_bpf(cmd, &attr, size); if (err < 0) return err; switch (cmd) { case BPF_MAP_CREATE: err = map_create(&attr); break; case BPF_MAP_LOOKUP_ELEM: err = map_lookup_elem(&attr); break; case BPF_MAP_UPDATE_ELEM: err = map_update_elem(&attr, uattr); break; case BPF_MAP_DELETE_ELEM: err = map_delete_elem(&attr, uattr); break; case BPF_MAP_GET_NEXT_KEY: err = map_get_next_key(&attr); break; case BPF_MAP_FREEZE: err = map_freeze(&attr); break; case BPF_PROG_LOAD: err = bpf_prog_load(&attr, uattr, size); break; case BPF_OBJ_PIN: err = bpf_obj_pin(&attr); break; case BPF_OBJ_GET: err = bpf_obj_get(&attr); break; case BPF_PROG_ATTACH: err = bpf_prog_attach(&attr); break; case BPF_PROG_DETACH: err = bpf_prog_detach(&attr); break; case BPF_PROG_QUERY: err = bpf_prog_query(&attr, uattr.user); break; case BPF_PROG_TEST_RUN: err = bpf_prog_test_run(&attr, uattr.user); break; case BPF_PROG_GET_NEXT_ID: err = bpf_obj_get_next_id(&attr, uattr.user, &prog_idr, &prog_idr_lock); break; case BPF_MAP_GET_NEXT_ID: err = bpf_obj_get_next_id(&attr, uattr.user, &map_idr, &map_idr_lock); break; case BPF_BTF_GET_NEXT_ID: err = bpf_obj_get_next_id(&attr, uattr.user, &btf_idr, &btf_idr_lock); break; case BPF_PROG_GET_FD_BY_ID: err = bpf_prog_get_fd_by_id(&attr); break; case BPF_MAP_GET_FD_BY_ID: err = bpf_map_get_fd_by_id(&attr); break; case BPF_OBJ_GET_INFO_BY_FD: err = bpf_obj_get_info_by_fd(&attr, uattr.user); break; case BPF_RAW_TRACEPOINT_OPEN: err = bpf_raw_tracepoint_open(&attr); break; case BPF_BTF_LOAD: err = bpf_btf_load(&attr, uattr, size); break; case BPF_BTF_GET_FD_BY_ID: err = bpf_btf_get_fd_by_id(&attr); break; case BPF_TASK_FD_QUERY: err = bpf_task_fd_query(&attr, uattr.user); break; case BPF_MAP_LOOKUP_AND_DELETE_ELEM: err = map_lookup_and_delete_elem(&attr); break; case BPF_MAP_LOOKUP_BATCH: err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_LOOKUP_BATCH); break; case BPF_MAP_LOOKUP_AND_DELETE_BATCH: err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_LOOKUP_AND_DELETE_BATCH); break; case BPF_MAP_UPDATE_BATCH: err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_UPDATE_BATCH); break; case BPF_MAP_DELETE_BATCH: err = bpf_map_do_batch(&attr, uattr.user, BPF_MAP_DELETE_BATCH); break; case BPF_LINK_CREATE: err = link_create(&attr, uattr); break; case BPF_LINK_UPDATE: err = link_update(&attr); break; case BPF_LINK_GET_FD_BY_ID: err = bpf_link_get_fd_by_id(&attr); break; case BPF_LINK_GET_NEXT_ID: err = bpf_obj_get_next_id(&attr, uattr.user, &link_idr, &link_idr_lock); break; case BPF_ENABLE_STATS: err = bpf_enable_stats(&attr); break; case BPF_ITER_CREATE: err = bpf_iter_create(&attr); break; case BPF_LINK_DETACH: err = link_detach(&attr); break; case BPF_PROG_BIND_MAP: err = bpf_prog_bind_map(&attr); break; case BPF_TOKEN_CREATE: err = token_create(&attr); break; default: err = -EINVAL; break; } return err; } SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) { return __sys_bpf(cmd, USER_BPFPTR(uattr), size); } static bool syscall_prog_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (off < 0 || off >= U16_MAX) return false; if (off % size != 0) return false; return true; } BPF_CALL_3(bpf_sys_bpf, int, cmd, union bpf_attr *, attr, u32, attr_size) { switch (cmd) { case BPF_MAP_CREATE: case BPF_MAP_DELETE_ELEM: case BPF_MAP_UPDATE_ELEM: case BPF_MAP_FREEZE: case BPF_MAP_GET_FD_BY_ID: case BPF_PROG_LOAD: case BPF_BTF_LOAD: case BPF_LINK_CREATE: case BPF_RAW_TRACEPOINT_OPEN: break; default: return -EINVAL; } return __sys_bpf(cmd, KERNEL_BPFPTR(attr), attr_size); } /* To shut up -Wmissing-prototypes. * This function is used by the kernel light skeleton * to load bpf programs when modules are loaded or during kernel boot. * See tools/lib/bpf/skel_internal.h */ int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size); int kern_sys_bpf(int cmd, union bpf_attr *attr, unsigned int size) { struct bpf_prog * __maybe_unused prog; struct bpf_tramp_run_ctx __maybe_unused run_ctx; switch (cmd) { #ifdef CONFIG_BPF_JIT /* __bpf_prog_enter_sleepable used by trampoline and JIT */ case BPF_PROG_TEST_RUN: if (attr->test.data_in || attr->test.data_out || attr->test.ctx_out || attr->test.duration || attr->test.repeat || attr->test.flags) return -EINVAL; prog = bpf_prog_get_type(attr->test.prog_fd, BPF_PROG_TYPE_SYSCALL); if (IS_ERR(prog)) return PTR_ERR(prog); if (attr->test.ctx_size_in < prog->aux->max_ctx_offset || attr->test.ctx_size_in > U16_MAX) { bpf_prog_put(prog); return -EINVAL; } run_ctx.bpf_cookie = 0; if (!__bpf_prog_enter_sleepable_recur(prog, &run_ctx)) { /* recursion detected */ __bpf_prog_exit_sleepable_recur(prog, 0, &run_ctx); bpf_prog_put(prog); return -EBUSY; } attr->test.retval = bpf_prog_run(prog, (void *) (long) attr->test.ctx_in); __bpf_prog_exit_sleepable_recur(prog, 0 /* bpf_prog_run does runtime stats */, &run_ctx); bpf_prog_put(prog); return 0; #endif default: return ____bpf_sys_bpf(cmd, attr, size); } } EXPORT_SYMBOL(kern_sys_bpf); static const struct bpf_func_proto bpf_sys_bpf_proto = { .func = bpf_sys_bpf, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, }; const struct bpf_func_proto * __weak tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { return bpf_base_func_proto(func_id, prog); } BPF_CALL_1(bpf_sys_close, u32, fd) { /* When bpf program calls this helper there should not be * an fdget() without matching completed fdput(). * This helper is allowed in the following callchain only: * sys_bpf->prog_test_run->bpf_prog->bpf_sys_close */ return close_fd(fd); } static const struct bpf_func_proto bpf_sys_close_proto = { .func = bpf_sys_close, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, }; BPF_CALL_4(bpf_kallsyms_lookup_name, const char *, name, int, name_sz, int, flags, u64 *, res) { *res = 0; if (flags) return -EINVAL; if (name_sz <= 1 || name[name_sz - 1]) return -EINVAL; if (!bpf_dump_raw_ok(current_cred())) return -EPERM; *res = kallsyms_lookup_name(name); return *res ? 0 : -ENOENT; } static const struct bpf_func_proto bpf_kallsyms_lookup_name_proto = { .func = bpf_kallsyms_lookup_name, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED, .arg4_size = sizeof(u64), }; static const struct bpf_func_proto * syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_sys_bpf: return !bpf_token_capable(prog->aux->token, CAP_PERFMON) ? NULL : &bpf_sys_bpf_proto; case BPF_FUNC_btf_find_by_name_kind: return &bpf_btf_find_by_name_kind_proto; case BPF_FUNC_sys_close: return &bpf_sys_close_proto; case BPF_FUNC_kallsyms_lookup_name: return &bpf_kallsyms_lookup_name_proto; default: return tracing_prog_func_proto(func_id, prog); } } const struct bpf_verifier_ops bpf_syscall_verifier_ops = { .get_func_proto = syscall_prog_func_proto, .is_valid_access = syscall_prog_is_valid_access, }; const struct bpf_prog_ops bpf_syscall_prog_ops = { .test_run = bpf_prog_test_run_syscall, }; #ifdef CONFIG_SYSCTL static int bpf_stats_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct static_key *key = (struct static_key *)table->data; static int saved_val; int val, ret; struct ctl_table tmp = { .data = &val, .maxlen = sizeof(val), .mode = table->mode, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }; if (write && !capable(CAP_SYS_ADMIN)) return -EPERM; mutex_lock(&bpf_stats_enabled_mutex); val = saved_val; ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && !ret && val != saved_val) { if (val) static_key_slow_inc(key); else static_key_slow_dec(key); saved_val = val; } mutex_unlock(&bpf_stats_enabled_mutex); return ret; } void __weak unpriv_ebpf_notify(int new_state) { } static int bpf_unpriv_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret, unpriv_enable = *(int *)table->data; bool locked_state = unpriv_enable == 1; struct ctl_table tmp = *table; if (write && !capable(CAP_SYS_ADMIN)) return -EPERM; tmp.data = &unpriv_enable; ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); if (write && !ret) { if (locked_state && unpriv_enable != 1) return -EPERM; *(int *)table->data = unpriv_enable; } if (write) unpriv_ebpf_notify(unpriv_enable); return ret; } static const struct ctl_table bpf_syscall_table[] = { { .procname = "unprivileged_bpf_disabled", .data = &sysctl_unprivileged_bpf_disabled, .maxlen = sizeof(sysctl_unprivileged_bpf_disabled), .mode = 0644, .proc_handler = bpf_unpriv_handler, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, { .procname = "bpf_stats_enabled", .data = &bpf_stats_enabled_key.key, .mode = 0644, .proc_handler = bpf_stats_handler, }, }; static int __init bpf_syscall_sysctl_init(void) { register_sysctl_init("kernel", bpf_syscall_table); return 0; } late_initcall(bpf_syscall_sysctl_init); #endif /* CONFIG_SYSCTL */ |
| 38 38 38 7 7 7 7 448 448 450 |