| 2793 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 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 | #include <linux/string.h> #include <linux/kernel.h> #include <linux/of.h> #include <linux/of_device.h> #include <linux/of_address.h> #include <linux/of_iommu.h> #include <linux/dma-mapping.h> #include <linux/init.h> #include <linux/module.h> #include <linux/mod_devicetable.h> #include <linux/slab.h> #include <linux/pci.h> #include <linux/platform_device.h> #include <linux/amba/bus.h> #include <asm/errno.h> #include "of_private.h" /** * of_match_device - Tell if a struct device matches an of_device_id list * @ids: array of of device match structures to search in * @dev: the of device structure to match against * * Used by a driver to check whether an platform_device present in the * system is in its list of supported devices. */ const struct of_device_id *of_match_device(const struct of_device_id *matches, const struct device *dev) { if ((!matches) || (!dev->of_node)) return NULL; return of_match_node(matches, dev->of_node); } EXPORT_SYMBOL(of_match_device); struct platform_device *of_dev_get(struct platform_device *dev) { struct device *tmp; if (!dev) return NULL; tmp = get_device(&dev->dev); if (tmp) return to_platform_device(tmp); else return NULL; } EXPORT_SYMBOL(of_dev_get); void of_dev_put(struct platform_device *dev) { if (dev) put_device(&dev->dev); } EXPORT_SYMBOL(of_dev_put); int of_device_add(struct platform_device *ofdev) { BUG_ON(ofdev->dev.of_node == NULL); /* name and id have to be set so that the platform bus doesn't get * confused on matching */ ofdev->name = dev_name(&ofdev->dev); ofdev->id = PLATFORM_DEVID_NONE; /* * If this device has not binding numa node in devicetree, that is * of_node_to_nid returns NUMA_NO_NODE. device_add will assume that this * device is on the same node as the parent. */ set_dev_node(&ofdev->dev, of_node_to_nid(ofdev->dev.of_node)); return device_add(&ofdev->dev); } /** * of_dma_configure - Setup DMA configuration * @dev: Device to apply DMA configuration * @np: Pointer to OF node having DMA configuration * * Try to get devices's DMA configuration from DT and update it * accordingly. * * If platform code needs to use its own special DMA configuration, it * can use a platform bus notifier and handle BUS_NOTIFY_ADD_DEVICE events * to fix up DMA configuration. */ int of_dma_configure(struct device *dev, struct device_node *np) { u64 dma_addr, paddr, size = 0; int ret; bool coherent; unsigned long offset; const struct iommu_ops *iommu; u64 mask; ret = of_dma_get_range(np, &dma_addr, &paddr, &size); if (ret < 0) { /* * For legacy reasons, we have to assume some devices need * DMA configuration regardless of whether "dma-ranges" is * correctly specified or not. */ if (!dev_is_pci(dev) && #ifdef CONFIG_ARM_AMBA dev->bus != &amba_bustype && #endif dev->bus != &platform_bus_type) return ret == -ENODEV ? 0 : ret; dma_addr = offset = 0; } else { offset = PFN_DOWN(paddr - dma_addr); /* * Add a work around to treat the size as mask + 1 in case * it is defined in DT as a mask. */ if (size & 1) { dev_warn(dev, "Invalid size 0x%llx for dma-range\n", size); size = size + 1; } if (!size) { dev_err(dev, "Adjusted size 0x%llx invalid\n", size); return -EINVAL; } dev_dbg(dev, "dma_pfn_offset(%#08lx)\n", offset); } /* * Set default coherent_dma_mask to 32 bit. Drivers are expected to * setup the correct supported mask. */ if (!dev->coherent_dma_mask) dev->coherent_dma_mask = DMA_BIT_MASK(32); /* * Set it to coherent_dma_mask by default if the architecture * code has not set it. */ if (!dev->dma_mask) dev->dma_mask = &dev->coherent_dma_mask; if (!size) size = max(dev->coherent_dma_mask, dev->coherent_dma_mask + 1); dev->dma_pfn_offset = offset; /* * Limit coherent and dma mask based on size and default mask * set by the driver. */ mask = DMA_BIT_MASK(ilog2(dma_addr + size - 1) + 1); dev->coherent_dma_mask &= mask; *dev->dma_mask &= mask; coherent = of_dma_is_coherent(np); dev_dbg(dev, "device is%sdma coherent\n", coherent ? " " : " not "); iommu = of_iommu_configure(dev, np); if (IS_ERR(iommu) && PTR_ERR(iommu) == -EPROBE_DEFER) return -EPROBE_DEFER; dev_dbg(dev, "device is%sbehind an iommu\n", iommu ? " " : " not "); arch_setup_dma_ops(dev, dma_addr, size, iommu, coherent); return 0; } EXPORT_SYMBOL_GPL(of_dma_configure); /** * of_dma_deconfigure - Clean up DMA configuration * @dev: Device for which to clean up DMA configuration * * Clean up all configuration performed by of_dma_configure_ops() and free all * resources that have been allocated. */ void of_dma_deconfigure(struct device *dev) { arch_teardown_dma_ops(dev); } int of_device_register(struct platform_device *pdev) { device_initialize(&pdev->dev); return of_device_add(pdev); } EXPORT_SYMBOL(of_device_register); void of_device_unregister(struct platform_device *ofdev) { device_unregister(&ofdev->dev); } EXPORT_SYMBOL(of_device_unregister); const void *of_device_get_match_data(const struct device *dev) { const struct of_device_id *match; match = of_match_device(dev->driver->of_match_table, dev); if (!match) return NULL; return match->data; } EXPORT_SYMBOL(of_device_get_match_data); static ssize_t of_device_get_modalias(struct device *dev, char *str, ssize_t len) { const char *compat; char *c; struct property *p; ssize_t csize; ssize_t tsize; if ((!dev) || (!dev->of_node)) return -ENODEV; /* Name & Type */ csize = snprintf(str, len, "of:N%sT%s", dev->of_node->name, dev->of_node->type); tsize = csize; len -= csize; if (str) str += csize; of_property_for_each_string(dev->of_node, "compatible", p, compat) { csize = strlen(compat) + 1; tsize += csize; if (csize > len) continue; csize = snprintf(str, len, "C%s", compat); for (c = str; c; ) { c = strchr(c, ' '); if (c) *c++ = '_'; } len -= csize; str += csize; } return tsize; } int of_device_request_module(struct device *dev) { char *str; ssize_t size; int ret; size = of_device_get_modalias(dev, NULL, 0); if (size < 0) return size; str = kmalloc(size + 1, GFP_KERNEL); if (!str) return -ENOMEM; of_device_get_modalias(dev, str, size); str[size] = '\0'; ret = request_module(str); kfree(str); return ret; } EXPORT_SYMBOL_GPL(of_device_request_module); /** * of_device_modalias - Fill buffer with newline terminated modalias string */ ssize_t of_device_modalias(struct device *dev, char *str, ssize_t len) { ssize_t sl = of_device_get_modalias(dev, str, len - 2); if (sl < 0) return sl; if (sl > len - 2) return -ENOMEM; str[sl++] = '\n'; str[sl] = 0; return sl; } EXPORT_SYMBOL_GPL(of_device_modalias); /** * of_device_uevent - Display OF related uevent information */ void of_device_uevent(struct device *dev, struct kobj_uevent_env *env) { const char *compat; struct alias_prop *app; struct property *p; int seen = 0; if ((!dev) || (!dev->of_node)) return; add_uevent_var(env, "OF_NAME=%s", dev->of_node->name); add_uevent_var(env, "OF_FULLNAME=%pOF", dev->of_node); if (dev->of_node->type && strcmp("<NULL>", dev->of_node->type) != 0) add_uevent_var(env, "OF_TYPE=%s", dev->of_node->type); /* Since the compatible field can contain pretty much anything * it's not really legal to split it out with commas. We split it * up using a number of environment variables instead. */ of_property_for_each_string(dev->of_node, "compatible", p, compat) { add_uevent_var(env, "OF_COMPATIBLE_%d=%s", seen, compat); seen++; } add_uevent_var(env, "OF_COMPATIBLE_N=%d", seen); seen = 0; mutex_lock(&of_mutex); list_for_each_entry(app, &aliases_lookup, link) { if (dev->of_node == app->np) { add_uevent_var(env, "OF_ALIAS_%d=%s", seen, app->alias); seen++; } } mutex_unlock(&of_mutex); } int of_device_uevent_modalias(struct device *dev, struct kobj_uevent_env *env) { int sl; if ((!dev) || (!dev->of_node)) return -ENODEV; /* Devicetree modalias is tricky, we add it in 2 steps */ if (add_uevent_var(env, "MODALIAS=")) return -ENOMEM; sl = of_device_get_modalias(dev, &env->buf[env->buflen-1], sizeof(env->buf) - env->buflen); if (sl >= (sizeof(env->buf) - env->buflen)) return -ENOMEM; env->buflen += sl; return 0; } EXPORT_SYMBOL_GPL(of_device_uevent_modalias); |
| 1587 8 461 13 229 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * workqueue.h --- work queue handling for Linux. */ #ifndef _LINUX_WORKQUEUE_H #define _LINUX_WORKQUEUE_H #include <linux/timer.h> #include <linux/linkage.h> #include <linux/bitops.h> #include <linux/lockdep.h> #include <linux/threads.h> #include <linux/atomic.h> #include <linux/cpumask.h> struct workqueue_struct; struct work_struct; typedef void (*work_func_t)(struct work_struct *work); void delayed_work_timer_fn(unsigned long __data); /* * The first word is the work queue pointer and the flags rolled into * one */ #define work_data_bits(work) ((unsigned long *)(&(work)->data)) enum { WORK_STRUCT_PENDING_BIT = 0, /* work item is pending execution */ WORK_STRUCT_DELAYED_BIT = 1, /* work item is delayed */ WORK_STRUCT_PWQ_BIT = 2, /* data points to pwq */ WORK_STRUCT_LINKED_BIT = 3, /* next work is linked to this one */ #ifdef CONFIG_DEBUG_OBJECTS_WORK WORK_STRUCT_STATIC_BIT = 4, /* static initializer (debugobjects) */ WORK_STRUCT_COLOR_SHIFT = 5, /* color for workqueue flushing */ #else WORK_STRUCT_COLOR_SHIFT = 4, /* color for workqueue flushing */ #endif WORK_STRUCT_COLOR_BITS = 4, WORK_STRUCT_PENDING = 1 << WORK_STRUCT_PENDING_BIT, WORK_STRUCT_DELAYED = 1 << WORK_STRUCT_DELAYED_BIT, WORK_STRUCT_PWQ = 1 << WORK_STRUCT_PWQ_BIT, WORK_STRUCT_LINKED = 1 << WORK_STRUCT_LINKED_BIT, #ifdef CONFIG_DEBUG_OBJECTS_WORK WORK_STRUCT_STATIC = 1 << WORK_STRUCT_STATIC_BIT, #else WORK_STRUCT_STATIC = 0, #endif /* * The last color is no color used for works which don't * participate in workqueue flushing. */ WORK_NR_COLORS = (1 << WORK_STRUCT_COLOR_BITS) - 1, WORK_NO_COLOR = WORK_NR_COLORS, /* not bound to any CPU, prefer the local CPU */ WORK_CPU_UNBOUND = NR_CPUS, /* * Reserve 7 bits off of pwq pointer w/ debugobjects turned off. * This makes pwqs aligned to 256 bytes and allows 15 workqueue * flush colors. */ WORK_STRUCT_FLAG_BITS = WORK_STRUCT_COLOR_SHIFT + WORK_STRUCT_COLOR_BITS, /* data contains off-queue information when !WORK_STRUCT_PWQ */ WORK_OFFQ_FLAG_BASE = WORK_STRUCT_COLOR_SHIFT, __WORK_OFFQ_CANCELING = WORK_OFFQ_FLAG_BASE, WORK_OFFQ_CANCELING = (1 << __WORK_OFFQ_CANCELING), /* * When a work item is off queue, its high bits point to the last * pool it was on. Cap at 31 bits and use the highest number to * indicate that no pool is associated. */ WORK_OFFQ_FLAG_BITS = 1, WORK_OFFQ_POOL_SHIFT = WORK_OFFQ_FLAG_BASE + WORK_OFFQ_FLAG_BITS, WORK_OFFQ_LEFT = BITS_PER_LONG - WORK_OFFQ_POOL_SHIFT, WORK_OFFQ_POOL_BITS = WORK_OFFQ_LEFT <= 31 ? WORK_OFFQ_LEFT : 31, WORK_OFFQ_POOL_NONE = (1LU << WORK_OFFQ_POOL_BITS) - 1, /* convenience constants */ WORK_STRUCT_FLAG_MASK = (1UL << WORK_STRUCT_FLAG_BITS) - 1, WORK_STRUCT_WQ_DATA_MASK = ~WORK_STRUCT_FLAG_MASK, WORK_STRUCT_NO_POOL = (unsigned long)WORK_OFFQ_POOL_NONE << WORK_OFFQ_POOL_SHIFT, /* bit mask for work_busy() return values */ WORK_BUSY_PENDING = 1 << 0, WORK_BUSY_RUNNING = 1 << 1, /* maximum string length for set_worker_desc() */ WORKER_DESC_LEN = 24, }; struct work_struct { atomic_long_t data; struct list_head entry; work_func_t func; #ifdef CONFIG_LOCKDEP struct lockdep_map lockdep_map; #endif }; #define WORK_DATA_INIT() ATOMIC_LONG_INIT((unsigned long)WORK_STRUCT_NO_POOL) #define WORK_DATA_STATIC_INIT() \ ATOMIC_LONG_INIT((unsigned long)(WORK_STRUCT_NO_POOL | WORK_STRUCT_STATIC)) struct delayed_work { struct work_struct work; struct timer_list timer; /* target workqueue and CPU ->timer uses to queue ->work */ struct workqueue_struct *wq; int cpu; }; /** * struct workqueue_attrs - A struct for workqueue attributes. * * This can be used to change attributes of an unbound workqueue. */ struct workqueue_attrs { /** * @nice: nice level */ int nice; /** * @cpumask: allowed CPUs */ cpumask_var_t cpumask; /** * @no_numa: disable NUMA affinity * * Unlike other fields, ``no_numa`` isn't a property of a worker_pool. It * only modifies how :c:func:`apply_workqueue_attrs` select pools and thus * doesn't participate in pool hash calculations or equality comparisons. */ bool no_numa; }; static inline struct delayed_work *to_delayed_work(struct work_struct *work) { return container_of(work, struct delayed_work, work); } struct execute_work { struct work_struct work; }; #ifdef CONFIG_LOCKDEP /* * NB: because we have to copy the lockdep_map, setting _key * here is required, otherwise it could get initialised to the * copy of the lockdep_map! */ #define __WORK_INIT_LOCKDEP_MAP(n, k) \ .lockdep_map = STATIC_LOCKDEP_MAP_INIT(n, k), #else #define __WORK_INIT_LOCKDEP_MAP(n, k) #endif #define __WORK_INITIALIZER(n, f) { \ .data = WORK_DATA_STATIC_INIT(), \ .entry = { &(n).entry, &(n).entry }, \ .func = (f), \ __WORK_INIT_LOCKDEP_MAP(#n, &(n)) \ } #define __DELAYED_WORK_INITIALIZER(n, f, tflags) { \ .work = __WORK_INITIALIZER((n).work, (f)), \ .timer = __TIMER_INITIALIZER(delayed_work_timer_fn, \ 0, (unsigned long)&(n), \ (tflags) | TIMER_IRQSAFE), \ } #define DECLARE_WORK(n, f) \ struct work_struct n = __WORK_INITIALIZER(n, f) #define DECLARE_DELAYED_WORK(n, f) \ struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f, 0) #define DECLARE_DEFERRABLE_WORK(n, f) \ struct delayed_work n = __DELAYED_WORK_INITIALIZER(n, f, TIMER_DEFERRABLE) #ifdef CONFIG_DEBUG_OBJECTS_WORK extern void __init_work(struct work_struct *work, int onstack); extern void destroy_work_on_stack(struct work_struct *work); extern void destroy_delayed_work_on_stack(struct delayed_work *work); static inline unsigned int work_static(struct work_struct *work) { return *work_data_bits(work) & WORK_STRUCT_STATIC; } #else static inline void __init_work(struct work_struct *work, int onstack) { } static inline void destroy_work_on_stack(struct work_struct *work) { } static inline void destroy_delayed_work_on_stack(struct delayed_work *work) { } static inline unsigned int work_static(struct work_struct *work) { return 0; } #endif /* * initialize all of a work item in one go * * NOTE! No point in using "atomic_long_set()": using a direct * assignment of the work data initializer allows the compiler * to generate better code. */ #ifdef CONFIG_LOCKDEP #define __INIT_WORK(_work, _func, _onstack) \ do { \ static struct lock_class_key __key; \ \ __init_work((_work), _onstack); \ (_work)->data = (atomic_long_t) WORK_DATA_INIT(); \ lockdep_init_map(&(_work)->lockdep_map, #_work, &__key, 0); \ INIT_LIST_HEAD(&(_work)->entry); \ (_work)->func = (_func); \ } while (0) #else #define __INIT_WORK(_work, _func, _onstack) \ do { \ __init_work((_work), _onstack); \ (_work)->data = (atomic_long_t) WORK_DATA_INIT(); \ INIT_LIST_HEAD(&(_work)->entry); \ (_work)->func = (_func); \ } while (0) #endif #define INIT_WORK(_work, _func) \ __INIT_WORK((_work), (_func), 0) #define INIT_WORK_ONSTACK(_work, _func) \ __INIT_WORK((_work), (_func), 1) #define __INIT_DELAYED_WORK(_work, _func, _tflags) \ do { \ INIT_WORK(&(_work)->work, (_func)); \ __setup_timer(&(_work)->timer, delayed_work_timer_fn, \ (unsigned long)(_work), \ (_tflags) | TIMER_IRQSAFE); \ } while (0) #define __INIT_DELAYED_WORK_ONSTACK(_work, _func, _tflags) \ do { \ INIT_WORK_ONSTACK(&(_work)->work, (_func)); \ __setup_timer_on_stack(&(_work)->timer, \ delayed_work_timer_fn, \ (unsigned long)(_work), \ (_tflags) | TIMER_IRQSAFE); \ } while (0) #define INIT_DELAYED_WORK(_work, _func) \ __INIT_DELAYED_WORK(_work, _func, 0) #define INIT_DELAYED_WORK_ONSTACK(_work, _func) \ __INIT_DELAYED_WORK_ONSTACK(_work, _func, 0) #define INIT_DEFERRABLE_WORK(_work, _func) \ __INIT_DELAYED_WORK(_work, _func, TIMER_DEFERRABLE) #define INIT_DEFERRABLE_WORK_ONSTACK(_work, _func) \ __INIT_DELAYED_WORK_ONSTACK(_work, _func, TIMER_DEFERRABLE) /** * work_pending - Find out whether a work item is currently pending * @work: The work item in question */ #define work_pending(work) \ test_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) /** * delayed_work_pending - Find out whether a delayable work item is currently * pending * @w: The work item in question */ #define delayed_work_pending(w) \ work_pending(&(w)->work) /* * Workqueue flags and constants. For details, please refer to * Documentation/core-api/workqueue.rst. */ enum { WQ_UNBOUND = 1 << 1, /* not bound to any cpu */ WQ_FREEZABLE = 1 << 2, /* freeze during suspend */ WQ_MEM_RECLAIM = 1 << 3, /* may be used for memory reclaim */ WQ_HIGHPRI = 1 << 4, /* high priority */ WQ_CPU_INTENSIVE = 1 << 5, /* cpu intensive workqueue */ WQ_SYSFS = 1 << 6, /* visible in sysfs, see wq_sysfs_register() */ /* * Per-cpu workqueues are generally preferred because they tend to * show better performance thanks to cache locality. Per-cpu * workqueues exclude the scheduler from choosing the CPU to * execute the worker threads, which has an unfortunate side effect * of increasing power consumption. * * The scheduler considers a CPU idle if it doesn't have any task * to execute and tries to keep idle cores idle to conserve power; * however, for example, a per-cpu work item scheduled from an * interrupt handler on an idle CPU will force the scheduler to * excute the work item on that CPU breaking the idleness, which in * turn may lead to more scheduling choices which are sub-optimal * in terms of power consumption. * * Workqueues marked with WQ_POWER_EFFICIENT are per-cpu by default * but become unbound if workqueue.power_efficient kernel param is * specified. Per-cpu workqueues which are identified to * contribute significantly to power-consumption are identified and * marked with this flag and enabling the power_efficient mode * leads to noticeable power saving at the cost of small * performance disadvantage. * * http://thread.gmane.org/gmane.linux.kernel/1480396 */ WQ_POWER_EFFICIENT = 1 << 7, __WQ_DRAINING = 1 << 16, /* internal: workqueue is draining */ __WQ_ORDERED = 1 << 17, /* internal: workqueue is ordered */ __WQ_LEGACY = 1 << 18, /* internal: create*_workqueue() */ __WQ_ORDERED_EXPLICIT = 1 << 19, /* internal: alloc_ordered_workqueue() */ WQ_MAX_ACTIVE = 512, /* I like 512, better ideas? */ WQ_MAX_UNBOUND_PER_CPU = 4, /* 4 * #cpus for unbound wq */ WQ_DFL_ACTIVE = WQ_MAX_ACTIVE / 2, }; /* unbound wq's aren't per-cpu, scale max_active according to #cpus */ #define WQ_UNBOUND_MAX_ACTIVE \ max_t(int, WQ_MAX_ACTIVE, num_possible_cpus() * WQ_MAX_UNBOUND_PER_CPU) /* * System-wide workqueues which are always present. * * system_wq is the one used by schedule[_delayed]_work[_on](). * Multi-CPU multi-threaded. There are users which expect relatively * short queue flush time. Don't queue works which can run for too * long. * * system_highpri_wq is similar to system_wq but for work items which * require WQ_HIGHPRI. * * system_long_wq is similar to system_wq but may host long running * works. Queue flushing might take relatively long. * * system_unbound_wq is unbound workqueue. Workers are not bound to * any specific CPU, not concurrency managed, and all queued works are * executed immediately as long as max_active limit is not reached and * resources are available. * * system_freezable_wq is equivalent to system_wq except that it's * freezable. * * *_power_efficient_wq are inclined towards saving power and converted * into WQ_UNBOUND variants if 'wq_power_efficient' is enabled; otherwise, * they are same as their non-power-efficient counterparts - e.g. * system_power_efficient_wq is identical to system_wq if * 'wq_power_efficient' is disabled. See WQ_POWER_EFFICIENT for more info. */ extern struct workqueue_struct *system_wq; extern struct workqueue_struct *system_highpri_wq; extern struct workqueue_struct *system_long_wq; extern struct workqueue_struct *system_unbound_wq; extern struct workqueue_struct *system_freezable_wq; extern struct workqueue_struct *system_power_efficient_wq; extern struct workqueue_struct *system_freezable_power_efficient_wq; extern struct workqueue_struct * __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active, struct lock_class_key *key, const char *lock_name, ...) __printf(1, 6); /** * alloc_workqueue - allocate a workqueue * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags * @max_active: max in-flight work items, 0 for default * @args...: args for @fmt * * Allocate a workqueue with the specified parameters. For detailed * information on WQ_* flags, please refer to * Documentation/core-api/workqueue.rst. * * The __lock_name macro dance is to guarantee that single lock_class_key * doesn't end up with different namesm, which isn't allowed by lockdep. * * RETURNS: * Pointer to the allocated workqueue on success, %NULL on failure. */ #ifdef CONFIG_LOCKDEP #define alloc_workqueue(fmt, flags, max_active, args...) \ ({ \ static struct lock_class_key __key; \ const char *__lock_name; \ \ __lock_name = #fmt#args; \ \ __alloc_workqueue_key((fmt), (flags), (max_active), \ &__key, __lock_name, ##args); \ }) #else #define alloc_workqueue(fmt, flags, max_active, args...) \ __alloc_workqueue_key((fmt), (flags), (max_active), \ NULL, NULL, ##args) #endif /** * alloc_ordered_workqueue - allocate an ordered workqueue * @fmt: printf format for the name of the workqueue * @flags: WQ_* flags (only WQ_FREEZABLE and WQ_MEM_RECLAIM are meaningful) * @args...: args for @fmt * * Allocate an ordered workqueue. An ordered workqueue executes at * most one work item at any given time in the queued order. They are * implemented as unbound workqueues with @max_active of one. * * RETURNS: * Pointer to the allocated workqueue on success, %NULL on failure. */ #define alloc_ordered_workqueue(fmt, flags, args...) \ alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | \ __WQ_ORDERED_EXPLICIT | (flags), 1, ##args) #define create_workqueue(name) \ alloc_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, 1, (name)) #define create_freezable_workqueue(name) \ alloc_workqueue("%s", __WQ_LEGACY | WQ_FREEZABLE | WQ_UNBOUND | \ WQ_MEM_RECLAIM, 1, (name)) #define create_singlethread_workqueue(name) \ alloc_ordered_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, name) extern void destroy_workqueue(struct workqueue_struct *wq); struct workqueue_attrs *alloc_workqueue_attrs(gfp_t gfp_mask); void free_workqueue_attrs(struct workqueue_attrs *attrs); int apply_workqueue_attrs(struct workqueue_struct *wq, const struct workqueue_attrs *attrs); int workqueue_set_unbound_cpumask(cpumask_var_t cpumask); extern bool queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work); extern bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *work, unsigned long delay); extern bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay); extern void flush_workqueue(struct workqueue_struct *wq); extern void drain_workqueue(struct workqueue_struct *wq); extern int schedule_on_each_cpu(work_func_t func); int execute_in_process_context(work_func_t fn, struct execute_work *); extern bool flush_work(struct work_struct *work); extern bool cancel_work(struct work_struct *work); extern bool cancel_work_sync(struct work_struct *work); extern bool flush_delayed_work(struct delayed_work *dwork); extern bool cancel_delayed_work(struct delayed_work *dwork); extern bool cancel_delayed_work_sync(struct delayed_work *dwork); extern void workqueue_set_max_active(struct workqueue_struct *wq, int max_active); extern struct work_struct *current_work(void); extern bool current_is_workqueue_rescuer(void); extern bool workqueue_congested(int cpu, struct workqueue_struct *wq); extern unsigned int work_busy(struct work_struct *work); extern __printf(1, 2) void set_worker_desc(const char *fmt, ...); extern void print_worker_info(const char *log_lvl, struct task_struct *task); extern void show_workqueue_state(void); /** * queue_work - queue work on a workqueue * @wq: workqueue to use * @work: work to queue * * Returns %false if @work was already on a queue, %true otherwise. * * We queue the work to the CPU on which it was submitted, but if the CPU dies * it can be processed by another CPU. */ static inline bool queue_work(struct workqueue_struct *wq, struct work_struct *work) { return queue_work_on(WORK_CPU_UNBOUND, wq, work); } /** * queue_delayed_work - queue work on a workqueue after delay * @wq: workqueue to use * @dwork: delayable work to queue * @delay: number of jiffies to wait before queueing * * Equivalent to queue_delayed_work_on() but tries to use the local CPU. */ static inline bool queue_delayed_work(struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { return queue_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay); } /** * mod_delayed_work - modify delay of or queue a delayed work * @wq: workqueue to use * @dwork: work to queue * @delay: number of jiffies to wait before queueing * * mod_delayed_work_on() on local CPU. */ static inline bool mod_delayed_work(struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { return mod_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay); } /** * schedule_work_on - put work task on a specific cpu * @cpu: cpu to put the work task on * @work: job to be done * * This puts a job on a specific cpu */ static inline bool schedule_work_on(int cpu, struct work_struct *work) { return queue_work_on(cpu, system_wq, work); } /** * schedule_work - put work task in global workqueue * @work: job to be done * * Returns %false if @work was already on the kernel-global workqueue and * %true otherwise. * * This puts a job in the kernel-global workqueue if it was not already * queued and leaves it in the same position on the kernel-global * workqueue otherwise. */ static inline bool schedule_work(struct work_struct *work) { return queue_work(system_wq, work); } /** * flush_scheduled_work - ensure that any scheduled work has run to completion. * * Forces execution of the kernel-global workqueue and blocks until its * completion. * * Think twice before calling this function! It's very easy to get into * trouble if you don't take great care. Either of the following situations * will lead to deadlock: * * One of the work items currently on the workqueue needs to acquire * a lock held by your code or its caller. * * Your code is running in the context of a work routine. * * They will be detected by lockdep when they occur, but the first might not * occur very often. It depends on what work items are on the workqueue and * what locks they need, which you have no control over. * * In most situations flushing the entire workqueue is overkill; you merely * need to know that a particular work item isn't queued and isn't running. * In such cases you should use cancel_delayed_work_sync() or * cancel_work_sync() instead. */ static inline void flush_scheduled_work(void) { flush_workqueue(system_wq); } /** * schedule_delayed_work_on - queue work in global workqueue on CPU after delay * @cpu: cpu to use * @dwork: job to be done * @delay: number of jiffies to wait * * After waiting for a given time this puts a job in the kernel-global * workqueue on the specified CPU. */ static inline bool schedule_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay) { return queue_delayed_work_on(cpu, system_wq, dwork, delay); } /** * schedule_delayed_work - put work task in global workqueue after delay * @dwork: job to be done * @delay: number of jiffies to wait or 0 for immediate execution * * After waiting for a given time this puts a job in the kernel-global * workqueue. */ static inline bool schedule_delayed_work(struct delayed_work *dwork, unsigned long delay) { return queue_delayed_work(system_wq, dwork, delay); } #ifndef CONFIG_SMP static inline long work_on_cpu(int cpu, long (*fn)(void *), void *arg) { return fn(arg); } static inline long work_on_cpu_safe(int cpu, long (*fn)(void *), void *arg) { return fn(arg); } #else long work_on_cpu(int cpu, long (*fn)(void *), void *arg); long work_on_cpu_safe(int cpu, long (*fn)(void *), void *arg); #endif /* CONFIG_SMP */ #ifdef CONFIG_FREEZER extern void freeze_workqueues_begin(void); extern bool freeze_workqueues_busy(void); extern void thaw_workqueues(void); #endif /* CONFIG_FREEZER */ #ifdef CONFIG_SYSFS int workqueue_sysfs_register(struct workqueue_struct *wq); #else /* CONFIG_SYSFS */ static inline int workqueue_sysfs_register(struct workqueue_struct *wq) { return 0; } #endif /* CONFIG_SYSFS */ #ifdef CONFIG_WQ_WATCHDOG void wq_watchdog_touch(int cpu); #else /* CONFIG_WQ_WATCHDOG */ static inline void wq_watchdog_touch(int cpu) { } #endif /* CONFIG_WQ_WATCHDOG */ #ifdef CONFIG_SMP int workqueue_prepare_cpu(unsigned int cpu); int workqueue_online_cpu(unsigned int cpu); int workqueue_offline_cpu(unsigned int cpu); #endif int __init workqueue_init_early(void); int __init workqueue_init(void); #endif |
| 481 5070 5004 4852 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 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 | /* * Tracing hooks * * Copyright (C) 2008-2009 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions * of the GNU General Public License v.2. * * This file defines hook entry points called by core code where * user tracing/debugging support might need to do something. These * entry points are called tracehook_*(). Each hook declared below * has a detailed kerneldoc comment giving the context (locking et * al) from which it is called, and the meaning of its return value. * * Each function here typically has only one call site, so it is ok * to have some nontrivial tracehook_*() inlines. In all cases, the * fast path when no tracing is enabled should be very short. * * The purpose of this file and the tracehook_* layer is to consolidate * the interface that the kernel core and arch code uses to enable any * user debugging or tracing facility (such as ptrace). The interfaces * here are carefully documented so that maintainers of core and arch * code do not need to think about the implementation details of the * tracing facilities. Likewise, maintainers of the tracing code do not * need to understand all the calling core or arch code in detail, just * documented circumstances of each call, such as locking conditions. * * If the calling core code changes so that locking is different, then * it is ok to change the interface documented here. The maintainer of * core code changing should notify the maintainers of the tracing code * that they need to work out the change. * * Some tracehook_*() inlines take arguments that the current tracing * implementations might not necessarily use. These function signatures * are chosen to pass in all the information that is on hand in the * caller and might conceivably be relevant to a tracer, so that the * core code won't have to be updated when tracing adds more features. * If a call site changes so that some of those parameters are no longer * already on hand without extra work, then the tracehook_* interface * can change so there is no make-work burden on the core code. The * maintainer of core code changing should notify the maintainers of the * tracing code that they need to work out the change. */ #ifndef _LINUX_TRACEHOOK_H #define _LINUX_TRACEHOOK_H 1 #include <linux/sched.h> #include <linux/ptrace.h> #include <linux/security.h> #include <linux/task_work.h> #include <linux/memcontrol.h> struct linux_binprm; /* * ptrace report for syscall entry and exit looks identical. */ static inline int ptrace_report_syscall(struct pt_regs *regs) { int ptrace = current->ptrace; if (!(ptrace & PT_PTRACED)) return 0; ptrace_notify(SIGTRAP | ((ptrace & PT_TRACESYSGOOD) ? 0x80 : 0)); /* * this isn't the same as continuing with a signal, but it will do * for normal use. strace only continues with a signal if the * stopping signal is not SIGTRAP. -brl */ if (current->exit_code) { send_sig(current->exit_code, current, 1); current->exit_code = 0; } return fatal_signal_pending(current); } /** * tracehook_report_syscall_entry - task is about to attempt a system call * @regs: user register state of current task * * This will be called if %TIF_SYSCALL_TRACE has been set, when the * current task has just entered the kernel for a system call. * Full user register state is available here. Changing the values * in @regs can affect the system call number and arguments to be tried. * It is safe to block here, preventing the system call from beginning. * * Returns zero normally, or nonzero if the calling arch code should abort * the system call. That must prevent normal entry so no system call is * made. If @task ever returns to user mode after this, its register state * is unspecified, but should be something harmless like an %ENOSYS error * return. It should preserve enough information so that syscall_rollback() * can work (see asm-generic/syscall.h). * * Called without locks, just after entering kernel mode. */ static inline __must_check int tracehook_report_syscall_entry( struct pt_regs *regs) { return ptrace_report_syscall(regs); } /** * tracehook_report_syscall_exit - task has just finished a system call * @regs: user register state of current task * @step: nonzero if simulating single-step or block-step * * This will be called if %TIF_SYSCALL_TRACE has been set, when the * current task has just finished an attempted system call. Full * user register state is available here. It is safe to block here, * preventing signals from being processed. * * If @step is nonzero, this report is also in lieu of the normal * trap that would follow the system call instruction because * user_enable_block_step() or user_enable_single_step() was used. * In this case, %TIF_SYSCALL_TRACE might not be set. * * Called without locks, just before checking for pending signals. */ static inline void tracehook_report_syscall_exit(struct pt_regs *regs, int step) { if (step) { siginfo_t info; user_single_step_siginfo(current, regs, &info); force_sig_info(SIGTRAP, &info, current); return; } ptrace_report_syscall(regs); } /** * tracehook_signal_handler - signal handler setup is complete * @stepping: nonzero if debugger single-step or block-step in use * * Called by the arch code after a signal handler has been set up. * Register and stack state reflects the user handler about to run. * Signal mask changes have already been made. * * Called without locks, shortly before returning to user mode * (or handling more signals). */ static inline void tracehook_signal_handler(int stepping) { if (stepping) ptrace_notify(SIGTRAP); } /** * set_notify_resume - cause tracehook_notify_resume() to be called * @task: task that will call tracehook_notify_resume() * * Calling this arranges that @task will call tracehook_notify_resume() * before returning to user mode. If it's already running in user mode, * it will enter the kernel and call tracehook_notify_resume() soon. * If it's blocked, it will not be woken. */ static inline void set_notify_resume(struct task_struct *task) { #ifdef TIF_NOTIFY_RESUME if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_RESUME)) kick_process(task); #endif } /** * tracehook_notify_resume - report when about to return to user mode * @regs: user-mode registers of @current task * * This is called when %TIF_NOTIFY_RESUME has been set. Now we are * about to return to user mode, and the user state in @regs can be * inspected or adjusted. The caller in arch code has cleared * %TIF_NOTIFY_RESUME before the call. If the flag gets set again * asynchronously, this will be called again before we return to * user mode. * * Called without locks. */ static inline void tracehook_notify_resume(struct pt_regs *regs) { /* * The caller just cleared TIF_NOTIFY_RESUME. This barrier * pairs with task_work_add()->set_notify_resume() after * hlist_add_head(task->task_works); */ smp_mb__after_atomic(); if (unlikely(current->task_works)) task_work_run(); mem_cgroup_handle_over_high(); } #endif /* <linux/tracehook.h> */ |
| 14 13 11 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 | /* * net/sched/em_nbyte.c N-Byte ematch * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. * * Authors: Thomas Graf <tgraf@suug.ch> */ #include <linux/gfp.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/skbuff.h> #include <linux/tc_ematch/tc_em_nbyte.h> #include <net/pkt_cls.h> struct nbyte_data { struct tcf_em_nbyte hdr; char pattern[0]; }; static int em_nbyte_change(struct net *net, void *data, int data_len, struct tcf_ematch *em) { struct tcf_em_nbyte *nbyte = data; if (data_len < sizeof(*nbyte) || data_len < (sizeof(*nbyte) + nbyte->len)) return -EINVAL; em->datalen = sizeof(*nbyte) + nbyte->len; em->data = (unsigned long)kmemdup(data, em->datalen, GFP_KERNEL); if (em->data == 0UL) return -ENOBUFS; return 0; } static int em_nbyte_match(struct sk_buff *skb, struct tcf_ematch *em, struct tcf_pkt_info *info) { struct nbyte_data *nbyte = (struct nbyte_data *) em->data; unsigned char *ptr = tcf_get_base_ptr(skb, nbyte->hdr.layer); ptr += nbyte->hdr.off; if (!tcf_valid_offset(skb, ptr, nbyte->hdr.len)) return 0; return !memcmp(ptr + nbyte->hdr.off, nbyte->pattern, nbyte->hdr.len); } static struct tcf_ematch_ops em_nbyte_ops = { .kind = TCF_EM_NBYTE, .change = em_nbyte_change, .match = em_nbyte_match, .owner = THIS_MODULE, .link = LIST_HEAD_INIT(em_nbyte_ops.link) }; static int __init init_em_nbyte(void) { return tcf_em_register(&em_nbyte_ops); } static void __exit exit_em_nbyte(void) { tcf_em_unregister(&em_nbyte_ops); } MODULE_LICENSE("GPL"); module_init(init_em_nbyte); module_exit(exit_em_nbyte); MODULE_ALIAS_TCF_EMATCH(TCF_EM_NBYTE); |
| 20 50 6 2 2 2 2 19 3 1 1 1 1 2 1 25 49 4 25 25 25 23 25 17 37 1 1 1 1 36 33 33 36 36 36 6 2 4 4 1 50 3 49 24 36 23 19 1 44 6 54 51 23 6 1 5 23 19 19 19 86 86 44 20 86 79 39 38 38 38 38 167 167 167 167 167 166 167 167 44 149 150 150 150 150 150 39 78 77 149 43 35 35 35 35 24 35 35 35 45 79 79 35 3 2 3 78 78 79 79 44 43 79 79 79 42 80 86 22 80 53 80 47 96 96 96 96 68 96 96 96 96 96 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 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 | /* * Copyright 2000 by Hans Reiser, licensing governed by reiserfs/README */ #include <linux/uaccess.h> #include <linux/string.h> #include <linux/time.h> #include "reiserfs.h" #include <linux/buffer_head.h> /* * copy copy_count entries from source directory item to dest buffer * (creating new item if needed) */ static void leaf_copy_dir_entries(struct buffer_info *dest_bi, struct buffer_head *source, int last_first, int item_num, int from, int copy_count) { struct buffer_head *dest = dest_bi->bi_bh; /* * either the number of target item, or if we must create a * new item, the number of the item we will create it next to */ int item_num_in_dest; struct item_head *ih; struct reiserfs_de_head *deh; int copy_records_len; /* length of all records in item to be copied */ char *records; ih = item_head(source, item_num); RFALSE(!is_direntry_le_ih(ih), "vs-10000: item must be directory item"); /* * length of all record to be copied and first byte of * the last of them */ deh = B_I_DEH(source, ih); if (copy_count) { copy_records_len = (from ? deh_location(&deh[from - 1]) : ih_item_len(ih)) - deh_location(&deh[from + copy_count - 1]); records = source->b_data + ih_location(ih) + deh_location(&deh[from + copy_count - 1]); } else { copy_records_len = 0; records = NULL; } /* when copy last to first, dest buffer can contain 0 items */ item_num_in_dest = (last_first == LAST_TO_FIRST) ? ((B_NR_ITEMS(dest)) ? 0 : -1) : (B_NR_ITEMS(dest) - 1); /* * if there are no items in dest or the first/last item in * dest is not item of the same directory */ if ((item_num_in_dest == -1) || (last_first == FIRST_TO_LAST && le_ih_k_offset(ih) == DOT_OFFSET) || (last_first == LAST_TO_FIRST && comp_short_le_keys /*COMP_SHORT_KEYS */ (&ih->ih_key, leaf_key(dest, item_num_in_dest)))) { /* create new item in dest */ struct item_head new_ih; /* form item header */ memcpy(&new_ih.ih_key, &ih->ih_key, KEY_SIZE); put_ih_version(&new_ih, KEY_FORMAT_3_5); /* calculate item len */ put_ih_item_len(&new_ih, DEH_SIZE * copy_count + copy_records_len); put_ih_entry_count(&new_ih, 0); if (last_first == LAST_TO_FIRST) { /* form key by the following way */ if (from < ih_entry_count(ih)) { set_le_ih_k_offset(&new_ih, deh_offset(&deh[from])); } else { /* * no entries will be copied to this * item in this function */ set_le_ih_k_offset(&new_ih, U32_MAX); /* * this item is not yet valid, but we * want I_IS_DIRECTORY_ITEM to return 1 * for it, so we -1 */ } set_le_key_k_type(KEY_FORMAT_3_5, &new_ih.ih_key, TYPE_DIRENTRY); } /* insert item into dest buffer */ leaf_insert_into_buf(dest_bi, (last_first == LAST_TO_FIRST) ? 0 : B_NR_ITEMS(dest), &new_ih, NULL, 0); } else { /* prepare space for entries */ leaf_paste_in_buffer(dest_bi, (last_first == FIRST_TO_LAST) ? (B_NR_ITEMS(dest) - 1) : 0, MAX_US_INT, DEH_SIZE * copy_count + copy_records_len, records, 0); } item_num_in_dest = (last_first == FIRST_TO_LAST) ? (B_NR_ITEMS(dest) - 1) : 0; leaf_paste_entries(dest_bi, item_num_in_dest, (last_first == FIRST_TO_LAST) ? ih_entry_count(item_head(dest, item_num_in_dest)) : 0, copy_count, deh + from, records, DEH_SIZE * copy_count + copy_records_len); } /* * Copy the first (if last_first == FIRST_TO_LAST) or last * (last_first == LAST_TO_FIRST) item or part of it or nothing * (see the return 0 below) from SOURCE to the end (if last_first) * or beginning (!last_first) of the DEST */ /* returns 1 if anything was copied, else 0 */ static int leaf_copy_boundary_item(struct buffer_info *dest_bi, struct buffer_head *src, int last_first, int bytes_or_entries) { struct buffer_head *dest = dest_bi->bi_bh; /* number of items in the source and destination buffers */ int dest_nr_item, src_nr_item; struct item_head *ih; struct item_head *dih; dest_nr_item = B_NR_ITEMS(dest); /* * if ( DEST is empty or first item of SOURCE and last item of * DEST are the items of different objects or of different types ) * then there is no need to treat this item differently from the * other items that we copy, so we return */ if (last_first == FIRST_TO_LAST) { ih = item_head(src, 0); dih = item_head(dest, dest_nr_item - 1); /* there is nothing to merge */ if (!dest_nr_item || (!op_is_left_mergeable(&ih->ih_key, src->b_size))) return 0; RFALSE(!ih_item_len(ih), "vs-10010: item can not have empty length"); if (is_direntry_le_ih(ih)) { if (bytes_or_entries == -1) /* copy all entries to dest */ bytes_or_entries = ih_entry_count(ih); leaf_copy_dir_entries(dest_bi, src, FIRST_TO_LAST, 0, 0, bytes_or_entries); return 1; } /* * copy part of the body of the first item of SOURCE * to the end of the body of the last item of the DEST * part defined by 'bytes_or_entries'; if bytes_or_entries * == -1 copy whole body; don't create new item header */ if (bytes_or_entries == -1) bytes_or_entries = ih_item_len(ih); #ifdef CONFIG_REISERFS_CHECK else { if (bytes_or_entries == ih_item_len(ih) && is_indirect_le_ih(ih)) if (get_ih_free_space(ih)) reiserfs_panic(sb_from_bi(dest_bi), "vs-10020", "last unformatted node " "must be filled " "entirely (%h)", ih); } #endif /* * merge first item (or its part) of src buffer with the last * item of dest buffer. Both are of the same file */ leaf_paste_in_buffer(dest_bi, dest_nr_item - 1, ih_item_len(dih), bytes_or_entries, ih_item_body(src, ih), 0); if (is_indirect_le_ih(dih)) { RFALSE(get_ih_free_space(dih), "vs-10030: merge to left: last unformatted node of non-last indirect item %h must have zerto free space", ih); if (bytes_or_entries == ih_item_len(ih)) set_ih_free_space(dih, get_ih_free_space(ih)); } return 1; } /* copy boundary item to right (last_first == LAST_TO_FIRST) */ /* * (DEST is empty or last item of SOURCE and first item of DEST * are the items of different object or of different types) */ src_nr_item = B_NR_ITEMS(src); ih = item_head(src, src_nr_item - 1); dih = item_head(dest, 0); if (!dest_nr_item || !op_is_left_mergeable(&dih->ih_key, src->b_size)) return 0; if (is_direntry_le_ih(ih)) { /* * bytes_or_entries = entries number in last * item body of SOURCE */ if (bytes_or_entries == -1) bytes_or_entries = ih_entry_count(ih); leaf_copy_dir_entries(dest_bi, src, LAST_TO_FIRST, src_nr_item - 1, ih_entry_count(ih) - bytes_or_entries, bytes_or_entries); return 1; } /* * copy part of the body of the last item of SOURCE to the * begin of the body of the first item of the DEST; part defined * by 'bytes_or_entries'; if byte_or_entriess == -1 copy whole body; * change first item key of the DEST; don't create new item header */ RFALSE(is_indirect_le_ih(ih) && get_ih_free_space(ih), "vs-10040: merge to right: last unformatted node of non-last indirect item must be filled entirely (%h)", ih); if (bytes_or_entries == -1) { /* bytes_or_entries = length of last item body of SOURCE */ bytes_or_entries = ih_item_len(ih); RFALSE(le_ih_k_offset(dih) != le_ih_k_offset(ih) + op_bytes_number(ih, src->b_size), "vs-10050: items %h and %h do not match", ih, dih); /* change first item key of the DEST */ set_le_ih_k_offset(dih, le_ih_k_offset(ih)); /* item becomes non-mergeable */ /* or mergeable if left item was */ set_le_ih_k_type(dih, le_ih_k_type(ih)); } else { /* merge to right only part of item */ RFALSE(ih_item_len(ih) <= bytes_or_entries, "vs-10060: no so much bytes %lu (needed %lu)", (unsigned long)ih_item_len(ih), (unsigned long)bytes_or_entries); /* change first item key of the DEST */ if (is_direct_le_ih(dih)) { RFALSE(le_ih_k_offset(dih) <= (unsigned long)bytes_or_entries, "vs-10070: dih %h, bytes_or_entries(%d)", dih, bytes_or_entries); set_le_ih_k_offset(dih, le_ih_k_offset(dih) - bytes_or_entries); } else { RFALSE(le_ih_k_offset(dih) <= (bytes_or_entries / UNFM_P_SIZE) * dest->b_size, "vs-10080: dih %h, bytes_or_entries(%d)", dih, (bytes_or_entries / UNFM_P_SIZE) * dest->b_size); set_le_ih_k_offset(dih, le_ih_k_offset(dih) - ((bytes_or_entries / UNFM_P_SIZE) * dest->b_size)); } } leaf_paste_in_buffer(dest_bi, 0, 0, bytes_or_entries, ih_item_body(src, ih) + ih_item_len(ih) - bytes_or_entries, 0); return 1; } /* * copy cpy_mun items from buffer src to buffer dest * last_first == FIRST_TO_LAST means, that we copy cpy_num items beginning * from first-th item in src to tail of dest * last_first == LAST_TO_FIRST means, that we copy cpy_num items beginning * from first-th item in src to head of dest */ static void leaf_copy_items_entirely(struct buffer_info *dest_bi, struct buffer_head *src, int last_first, int first, int cpy_num) { struct buffer_head *dest; int nr, free_space; int dest_before; int last_loc, last_inserted_loc, location; int i, j; struct block_head *blkh; struct item_head *ih; RFALSE(last_first != LAST_TO_FIRST && last_first != FIRST_TO_LAST, "vs-10090: bad last_first parameter %d", last_first); RFALSE(B_NR_ITEMS(src) - first < cpy_num, "vs-10100: too few items in source %d, required %d from %d", B_NR_ITEMS(src), cpy_num, first); RFALSE(cpy_num < 0, "vs-10110: can not copy negative amount of items"); RFALSE(!dest_bi, "vs-10120: can not copy negative amount of items"); dest = dest_bi->bi_bh; RFALSE(!dest, "vs-10130: can not copy negative amount of items"); if (cpy_num == 0) return; blkh = B_BLK_HEAD(dest); nr = blkh_nr_item(blkh); free_space = blkh_free_space(blkh); /* * we will insert items before 0-th or nr-th item in dest buffer. * It depends of last_first parameter */ dest_before = (last_first == LAST_TO_FIRST) ? 0 : nr; /* location of head of first new item */ ih = item_head(dest, dest_before); RFALSE(blkh_free_space(blkh) < cpy_num * IH_SIZE, "vs-10140: not enough free space for headers %d (needed %d)", B_FREE_SPACE(dest), cpy_num * IH_SIZE); /* prepare space for headers */ memmove(ih + cpy_num, ih, (nr - dest_before) * IH_SIZE); /* copy item headers */ memcpy(ih, item_head(src, first), cpy_num * IH_SIZE); free_space -= (IH_SIZE * cpy_num); set_blkh_free_space(blkh, free_space); /* location of unmovable item */ j = location = (dest_before == 0) ? dest->b_size : ih_location(ih - 1); for (i = dest_before; i < nr + cpy_num; i++) { location -= ih_item_len(ih + i - dest_before); put_ih_location(ih + i - dest_before, location); } /* prepare space for items */ last_loc = ih_location(&ih[nr + cpy_num - 1 - dest_before]); last_inserted_loc = ih_location(&ih[cpy_num - 1]); /* check free space */ RFALSE(free_space < j - last_inserted_loc, "vs-10150: not enough free space for items %d (needed %d)", free_space, j - last_inserted_loc); memmove(dest->b_data + last_loc, dest->b_data + last_loc + j - last_inserted_loc, last_inserted_loc - last_loc); /* copy items */ memcpy(dest->b_data + last_inserted_loc, item_body(src, (first + cpy_num - 1)), j - last_inserted_loc); /* sizes, item number */ set_blkh_nr_item(blkh, nr + cpy_num); set_blkh_free_space(blkh, free_space - (j - last_inserted_loc)); do_balance_mark_leaf_dirty(dest_bi->tb, dest, 0); if (dest_bi->bi_parent) { struct disk_child *t_dc; t_dc = B_N_CHILD(dest_bi->bi_parent, dest_bi->bi_position); RFALSE(dc_block_number(t_dc) != dest->b_blocknr, "vs-10160: block number in bh does not match to field in disk_child structure %lu and %lu", (long unsigned)dest->b_blocknr, (long unsigned)dc_block_number(t_dc)); put_dc_size(t_dc, dc_size(t_dc) + (j - last_inserted_loc + IH_SIZE * cpy_num)); do_balance_mark_internal_dirty(dest_bi->tb, dest_bi->bi_parent, 0); } } /* * This function splits the (liquid) item into two items (useful when * shifting part of an item into another node.) */ static void leaf_item_bottle(struct buffer_info *dest_bi, struct buffer_head *src, int last_first, int item_num, int cpy_bytes) { struct buffer_head *dest = dest_bi->bi_bh; struct item_head *ih; RFALSE(cpy_bytes == -1, "vs-10170: bytes == - 1 means: do not split item"); if (last_first == FIRST_TO_LAST) { /* * if ( if item in position item_num in buffer SOURCE * is directory item ) */ ih = item_head(src, item_num); if (is_direntry_le_ih(ih)) leaf_copy_dir_entries(dest_bi, src, FIRST_TO_LAST, item_num, 0, cpy_bytes); else { struct item_head n_ih; /* * copy part of the body of the item number 'item_num' * of SOURCE to the end of the DEST part defined by * 'cpy_bytes'; create new item header; change old * item_header (????); n_ih = new item_header; */ memcpy(&n_ih, ih, IH_SIZE); put_ih_item_len(&n_ih, cpy_bytes); if (is_indirect_le_ih(ih)) { RFALSE(cpy_bytes == ih_item_len(ih) && get_ih_free_space(ih), "vs-10180: when whole indirect item is bottle to left neighbor, it must have free_space==0 (not %lu)", (long unsigned)get_ih_free_space(ih)); set_ih_free_space(&n_ih, 0); } RFALSE(op_is_left_mergeable(&ih->ih_key, src->b_size), "vs-10190: bad mergeability of item %h", ih); n_ih.ih_version = ih->ih_version; /* JDM Endian safe, both le */ leaf_insert_into_buf(dest_bi, B_NR_ITEMS(dest), &n_ih, item_body(src, item_num), 0); } } else { /* * if ( if item in position item_num in buffer * SOURCE is directory item ) */ ih = item_head(src, item_num); if (is_direntry_le_ih(ih)) leaf_copy_dir_entries(dest_bi, src, LAST_TO_FIRST, item_num, ih_entry_count(ih) - cpy_bytes, cpy_bytes); else { struct item_head n_ih; /* * copy part of the body of the item number 'item_num' * of SOURCE to the begin of the DEST part defined by * 'cpy_bytes'; create new item header; * n_ih = new item_header; */ memcpy(&n_ih.ih_key, &ih->ih_key, KEY_SIZE); /* Endian safe, both le */ n_ih.ih_version = ih->ih_version; if (is_direct_le_ih(ih)) { set_le_ih_k_offset(&n_ih, le_ih_k_offset(ih) + ih_item_len(ih) - cpy_bytes); set_le_ih_k_type(&n_ih, TYPE_DIRECT); set_ih_free_space(&n_ih, MAX_US_INT); } else { /* indirect item */ RFALSE(!cpy_bytes && get_ih_free_space(ih), "vs-10200: ih->ih_free_space must be 0 when indirect item will be appended"); set_le_ih_k_offset(&n_ih, le_ih_k_offset(ih) + (ih_item_len(ih) - cpy_bytes) / UNFM_P_SIZE * dest->b_size); set_le_ih_k_type(&n_ih, TYPE_INDIRECT); set_ih_free_space(&n_ih, get_ih_free_space(ih)); } /* set item length */ put_ih_item_len(&n_ih, cpy_bytes); /* Endian safe, both le */ n_ih.ih_version = ih->ih_version; leaf_insert_into_buf(dest_bi, 0, &n_ih, item_body(src, item_num) + ih_item_len(ih) - cpy_bytes, 0); } } } /* * If cpy_bytes equals minus one than copy cpy_num whole items from SOURCE * to DEST. If cpy_bytes not equal to minus one than copy cpy_num-1 whole * items from SOURCE to DEST. From last item copy cpy_num bytes for regular * item and cpy_num directory entries for directory item. */ static int leaf_copy_items(struct buffer_info *dest_bi, struct buffer_head *src, int last_first, int cpy_num, int cpy_bytes) { struct buffer_head *dest; int pos, i, src_nr_item, bytes; dest = dest_bi->bi_bh; RFALSE(!dest || !src, "vs-10210: !dest || !src"); RFALSE(last_first != FIRST_TO_LAST && last_first != LAST_TO_FIRST, "vs-10220:last_first != FIRST_TO_LAST && last_first != LAST_TO_FIRST"); RFALSE(B_NR_ITEMS(src) < cpy_num, "vs-10230: No enough items: %d, req. %d", B_NR_ITEMS(src), cpy_num); RFALSE(cpy_num < 0, "vs-10240: cpy_num < 0 (%d)", cpy_num); if (cpy_num == 0) return 0; if (last_first == FIRST_TO_LAST) { /* copy items to left */ pos = 0; if (cpy_num == 1) bytes = cpy_bytes; else bytes = -1; /* * copy the first item or it part or nothing to the end of * the DEST (i = leaf_copy_boundary_item(DEST,SOURCE,0,bytes)) */ i = leaf_copy_boundary_item(dest_bi, src, FIRST_TO_LAST, bytes); cpy_num -= i; if (cpy_num == 0) return i; pos += i; if (cpy_bytes == -1) /* * copy first cpy_num items starting from position * 'pos' of SOURCE to end of DEST */ leaf_copy_items_entirely(dest_bi, src, FIRST_TO_LAST, pos, cpy_num); else { /* * copy first cpy_num-1 items starting from position * 'pos-1' of the SOURCE to the end of the DEST */ leaf_copy_items_entirely(dest_bi, src, FIRST_TO_LAST, pos, cpy_num - 1); /* * copy part of the item which number is * cpy_num+pos-1 to the end of the DEST */ leaf_item_bottle(dest_bi, src, FIRST_TO_LAST, cpy_num + pos - 1, cpy_bytes); } } else { /* copy items to right */ src_nr_item = B_NR_ITEMS(src); if (cpy_num == 1) bytes = cpy_bytes; else bytes = -1; /* * copy the last item or it part or nothing to the * begin of the DEST * (i = leaf_copy_boundary_item(DEST,SOURCE,1,bytes)); */ i = leaf_copy_boundary_item(dest_bi, src, LAST_TO_FIRST, bytes); cpy_num -= i; if (cpy_num == 0) return i; pos = src_nr_item - cpy_num - i; if (cpy_bytes == -1) { /* * starting from position 'pos' copy last cpy_num * items of SOURCE to begin of DEST */ leaf_copy_items_entirely(dest_bi, src, LAST_TO_FIRST, pos, cpy_num); } else { /* * copy last cpy_num-1 items starting from position * 'pos+1' of the SOURCE to the begin of the DEST; */ leaf_copy_items_entirely(dest_bi, src, LAST_TO_FIRST, pos + 1, cpy_num - 1); /* * copy part of the item which number is pos to * the begin of the DEST */ leaf_item_bottle(dest_bi, src, LAST_TO_FIRST, pos, cpy_bytes); } } return i; } /* * there are types of coping: from S[0] to L[0], from S[0] to R[0], * from R[0] to L[0]. for each of these we have to define parent and * positions of destination and source buffers */ static void leaf_define_dest_src_infos(int shift_mode, struct tree_balance *tb, struct buffer_info *dest_bi, struct buffer_info *src_bi, int *first_last, struct buffer_head *Snew) { memset(dest_bi, 0, sizeof(struct buffer_info)); memset(src_bi, 0, sizeof(struct buffer_info)); /* define dest, src, dest parent, dest position */ switch (shift_mode) { case LEAF_FROM_S_TO_L: /* it is used in leaf_shift_left */ src_bi->tb = tb; src_bi->bi_bh = PATH_PLAST_BUFFER(tb->tb_path); src_bi->bi_parent = PATH_H_PPARENT(tb->tb_path, 0); /* src->b_item_order */ src_bi->bi_position = PATH_H_B_ITEM_ORDER(tb->tb_path, 0); dest_bi->tb = tb; dest_bi->bi_bh = tb->L[0]; dest_bi->bi_parent = tb->FL[0]; dest_bi->bi_position = get_left_neighbor_position(tb, 0); *first_last = FIRST_TO_LAST; break; case LEAF_FROM_S_TO_R: /* it is used in leaf_shift_right */ src_bi->tb = tb; src_bi->bi_bh = PATH_PLAST_BUFFER(tb->tb_path); src_bi->bi_parent = PATH_H_PPARENT(tb->tb_path, 0); src_bi->bi_position = PATH_H_B_ITEM_ORDER(tb->tb_path, 0); dest_bi->tb = tb; dest_bi->bi_bh = tb->R[0]; dest_bi->bi_parent = tb->FR[0]; dest_bi->bi_position = get_right_neighbor_position(tb, 0); *first_last = LAST_TO_FIRST; break; case LEAF_FROM_R_TO_L: /* it is used in balance_leaf_when_delete */ src_bi->tb = tb; src_bi->bi_bh = tb->R[0]; src_bi->bi_parent = tb->FR[0]; src_bi->bi_position = get_right_neighbor_position(tb, 0); dest_bi->tb = tb; dest_bi->bi_bh = tb->L[0]; dest_bi->bi_parent = tb->FL[0]; dest_bi->bi_position = get_left_neighbor_position(tb, 0); *first_last = FIRST_TO_LAST; break; case LEAF_FROM_L_TO_R: /* it is used in balance_leaf_when_delete */ src_bi->tb = tb; src_bi->bi_bh = tb->L[0]; src_bi->bi_parent = tb->FL[0]; src_bi->bi_position = get_left_neighbor_position(tb, 0); dest_bi->tb = tb; dest_bi->bi_bh = tb->R[0]; dest_bi->bi_parent = tb->FR[0]; dest_bi->bi_position = get_right_neighbor_position(tb, 0); *first_last = LAST_TO_FIRST; break; case LEAF_FROM_S_TO_SNEW: src_bi->tb = tb; src_bi->bi_bh = PATH_PLAST_BUFFER(tb->tb_path); src_bi->bi_parent = PATH_H_PPARENT(tb->tb_path, 0); src_bi->bi_position = PATH_H_B_ITEM_ORDER(tb->tb_path, 0); dest_bi->tb = tb; dest_bi->bi_bh = Snew; dest_bi->bi_parent = NULL; dest_bi->bi_position = 0; *first_last = LAST_TO_FIRST; break; default: reiserfs_panic(sb_from_bi(src_bi), "vs-10250", "shift type is unknown (%d)", shift_mode); } RFALSE(!src_bi->bi_bh || !dest_bi->bi_bh, "vs-10260: mode==%d, source (%p) or dest (%p) buffer is initialized incorrectly", shift_mode, src_bi->bi_bh, dest_bi->bi_bh); } /* * copy mov_num items and mov_bytes of the (mov_num-1)th item to * neighbor. Delete them from source */ int leaf_move_items(int shift_mode, struct tree_balance *tb, int mov_num, int mov_bytes, struct buffer_head *Snew) { int ret_value; struct buffer_info dest_bi, src_bi; int first_last; leaf_define_dest_src_infos(shift_mode, tb, &dest_bi, &src_bi, &first_last, Snew); ret_value = leaf_copy_items(&dest_bi, src_bi.bi_bh, first_last, mov_num, mov_bytes); leaf_delete_items(&src_bi, first_last, (first_last == FIRST_TO_LAST) ? 0 : (B_NR_ITEMS(src_bi.bi_bh) - mov_num), mov_num, mov_bytes); return ret_value; } /* * Shift shift_num items (and shift_bytes of last shifted item if * shift_bytes != -1) from S[0] to L[0] and replace the delimiting key */ int leaf_shift_left(struct tree_balance *tb, int shift_num, int shift_bytes) { struct buffer_head *S0 = PATH_PLAST_BUFFER(tb->tb_path); int i; /* * move shift_num (and shift_bytes bytes) items from S[0] * to left neighbor L[0] */ i = leaf_move_items(LEAF_FROM_S_TO_L, tb, shift_num, shift_bytes, NULL); if (shift_num) { /* number of items in S[0] == 0 */ if (B_NR_ITEMS(S0) == 0) { RFALSE(shift_bytes != -1, "vs-10270: S0 is empty now, but shift_bytes != -1 (%d)", shift_bytes); #ifdef CONFIG_REISERFS_CHECK if (tb->tb_mode == M_PASTE || tb->tb_mode == M_INSERT) { print_cur_tb("vs-10275"); reiserfs_panic(tb->tb_sb, "vs-10275", "balance condition corrupted " "(%c)", tb->tb_mode); } #endif if (PATH_H_POSITION(tb->tb_path, 1) == 0) replace_key(tb, tb->CFL[0], tb->lkey[0], PATH_H_PPARENT(tb->tb_path, 0), 0); } else { /* replace lkey in CFL[0] by 0-th key from S[0]; */ replace_key(tb, tb->CFL[0], tb->lkey[0], S0, 0); RFALSE((shift_bytes != -1 && !(is_direntry_le_ih(item_head(S0, 0)) && !ih_entry_count(item_head(S0, 0)))) && (!op_is_left_mergeable (leaf_key(S0, 0), S0->b_size)), "vs-10280: item must be mergeable"); } } return i; } /* CLEANING STOPPED HERE */ /* * Shift shift_num (shift_bytes) items from S[0] to the right neighbor, * and replace the delimiting key */ int leaf_shift_right(struct tree_balance *tb, int shift_num, int shift_bytes) { int ret_value; /* * move shift_num (and shift_bytes) items from S[0] to * right neighbor R[0] */ ret_value = leaf_move_items(LEAF_FROM_S_TO_R, tb, shift_num, shift_bytes, NULL); /* replace rkey in CFR[0] by the 0-th key from R[0] */ if (shift_num) { replace_key(tb, tb->CFR[0], tb->rkey[0], tb->R[0], 0); } return ret_value; } static void leaf_delete_items_entirely(struct buffer_info *bi, int first, int del_num); /* * If del_bytes == -1, starting from position 'first' delete del_num * items in whole in buffer CUR. * If not. * If last_first == 0. Starting from position 'first' delete del_num-1 * items in whole. Delete part of body of the first item. Part defined by * del_bytes. Don't delete first item header * If last_first == 1. Starting from position 'first+1' delete del_num-1 * items in whole. Delete part of body of the last item . Part defined by * del_bytes. Don't delete last item header. */ void leaf_delete_items(struct buffer_info *cur_bi, int last_first, int first, int del_num, int del_bytes) { struct buffer_head *bh; int item_amount = B_NR_ITEMS(bh = cur_bi->bi_bh); RFALSE(!bh, "10155: bh is not defined"); RFALSE(del_num < 0, "10160: del_num can not be < 0. del_num==%d", del_num); RFALSE(first < 0 || first + del_num > item_amount, "10165: invalid number of first item to be deleted (%d) or " "no so much items (%d) to delete (only %d)", first, first + del_num, item_amount); if (del_num == 0) return; if (first == 0 && del_num == item_amount && del_bytes == -1) { make_empty_node(cur_bi); do_balance_mark_leaf_dirty(cur_bi->tb, bh, 0); return; } if (del_bytes == -1) /* delete del_num items beginning from item in position first */ leaf_delete_items_entirely(cur_bi, first, del_num); else { if (last_first == FIRST_TO_LAST) { /* * delete del_num-1 items beginning from * item in position first */ leaf_delete_items_entirely(cur_bi, first, del_num - 1); /* * delete the part of the first item of the bh * do not delete item header */ leaf_cut_from_buffer(cur_bi, 0, 0, del_bytes); } else { struct item_head *ih; int len; /* * delete del_num-1 items beginning from * item in position first+1 */ leaf_delete_items_entirely(cur_bi, first + 1, del_num - 1); ih = item_head(bh, B_NR_ITEMS(bh) - 1); if (is_direntry_le_ih(ih)) /* the last item is directory */ /* * len = numbers of directory entries * in this item */ len = ih_entry_count(ih); else /* len = body len of item */ len = ih_item_len(ih); /* * delete the part of the last item of the bh * do not delete item header */ leaf_cut_from_buffer(cur_bi, B_NR_ITEMS(bh) - 1, len - del_bytes, del_bytes); } } } /* insert item into the leaf node in position before */ void leaf_insert_into_buf(struct buffer_info *bi, int before, struct item_head * const inserted_item_ih, const char * const inserted_item_body, int zeros_number) { struct buffer_head *bh = bi->bi_bh; int nr, free_space; struct block_head *blkh; struct item_head *ih; int i; int last_loc, unmoved_loc; char *to; blkh = B_BLK_HEAD(bh); nr = blkh_nr_item(blkh); free_space = blkh_free_space(blkh); /* check free space */ RFALSE(free_space < ih_item_len(inserted_item_ih) + IH_SIZE, "vs-10170: not enough free space in block %z, new item %h", bh, inserted_item_ih); RFALSE(zeros_number > ih_item_len(inserted_item_ih), "vs-10172: zero number == %d, item length == %d", zeros_number, ih_item_len(inserted_item_ih)); /* get item new item must be inserted before */ ih = item_head(bh, before); /* prepare space for the body of new item */ last_loc = nr ? ih_location(&ih[nr - before - 1]) : bh->b_size; unmoved_loc = before ? ih_location(ih - 1) : bh->b_size; memmove(bh->b_data + last_loc - ih_item_len(inserted_item_ih), bh->b_data + last_loc, unmoved_loc - last_loc); to = bh->b_data + unmoved_loc - ih_item_len(inserted_item_ih); memset(to, 0, zeros_number); to += zeros_number; /* copy body to prepared space */ if (inserted_item_body) memmove(to, inserted_item_body, ih_item_len(inserted_item_ih) - zeros_number); else memset(to, '\0', ih_item_len(inserted_item_ih) - zeros_number); /* insert item header */ memmove(ih + 1, ih, IH_SIZE * (nr - before)); memmove(ih, inserted_item_ih, IH_SIZE); /* change locations */ for (i = before; i < nr + 1; i++) { unmoved_loc -= ih_item_len(&ih[i - before]); put_ih_location(&ih[i - before], unmoved_loc); } /* sizes, free space, item number */ set_blkh_nr_item(blkh, blkh_nr_item(blkh) + 1); set_blkh_free_space(blkh, free_space - (IH_SIZE + ih_item_len(inserted_item_ih))); do_balance_mark_leaf_dirty(bi->tb, bh, 1); if (bi->bi_parent) { struct disk_child *t_dc; t_dc = B_N_CHILD(bi->bi_parent, bi->bi_position); put_dc_size(t_dc, dc_size(t_dc) + (IH_SIZE + ih_item_len(inserted_item_ih))); do_balance_mark_internal_dirty(bi->tb, bi->bi_parent, 0); } } /* * paste paste_size bytes to affected_item_num-th item. * When item is a directory, this only prepare space for new entries */ void leaf_paste_in_buffer(struct buffer_info *bi, int affected_item_num, int pos_in_item, int paste_size, const char *body, int zeros_number) { struct buffer_head *bh = bi->bi_bh; int nr, free_space; struct block_head *blkh; struct item_head *ih; int i; int last_loc, unmoved_loc; blkh = B_BLK_HEAD(bh); nr = blkh_nr_item(blkh); free_space = blkh_free_space(blkh); /* check free space */ RFALSE(free_space < paste_size, "vs-10175: not enough free space: needed %d, available %d", paste_size, free_space); #ifdef CONFIG_REISERFS_CHECK if (zeros_number > paste_size) { struct super_block *sb = NULL; if (bi && bi->tb) sb = bi->tb->tb_sb; print_cur_tb("10177"); reiserfs_panic(sb, "vs-10177", "zeros_number == %d, paste_size == %d", zeros_number, paste_size); } #endif /* CONFIG_REISERFS_CHECK */ /* item to be appended */ ih = item_head(bh, affected_item_num); last_loc = ih_location(&ih[nr - affected_item_num - 1]); unmoved_loc = affected_item_num ? ih_location(ih - 1) : bh->b_size; /* prepare space */ memmove(bh->b_data + last_loc - paste_size, bh->b_data + last_loc, unmoved_loc - last_loc); /* change locations */ for (i = affected_item_num; i < nr; i++) put_ih_location(&ih[i - affected_item_num], ih_location(&ih[i - affected_item_num]) - paste_size); if (body) { if (!is_direntry_le_ih(ih)) { if (!pos_in_item) { /* shift data to right */ memmove(bh->b_data + ih_location(ih) + paste_size, bh->b_data + ih_location(ih), ih_item_len(ih)); /* paste data in the head of item */ memset(bh->b_data + ih_location(ih), 0, zeros_number); memcpy(bh->b_data + ih_location(ih) + zeros_number, body, paste_size - zeros_number); } else { memset(bh->b_data + unmoved_loc - paste_size, 0, zeros_number); memcpy(bh->b_data + unmoved_loc - paste_size + zeros_number, body, paste_size - zeros_number); } } } else memset(bh->b_data + unmoved_loc - paste_size, '\0', paste_size); put_ih_item_len(ih, ih_item_len(ih) + paste_size); /* change free space */ set_blkh_free_space(blkh, free_space - paste_size); do_balance_mark_leaf_dirty(bi->tb, bh, 0); if (bi->bi_parent) { struct disk_child *t_dc = B_N_CHILD(bi->bi_parent, bi->bi_position); put_dc_size(t_dc, dc_size(t_dc) + paste_size); do_balance_mark_internal_dirty(bi->tb, bi->bi_parent, 0); } } /* * cuts DEL_COUNT entries beginning from FROM-th entry. Directory item * does not have free space, so it moves DEHs and remaining records as * necessary. Return value is size of removed part of directory item * in bytes. */ static int leaf_cut_entries(struct buffer_head *bh, struct item_head *ih, int from, int del_count) { char *item; struct reiserfs_de_head *deh; int prev_record_offset; /* offset of record, that is (from-1)th */ char *prev_record; /* */ int cut_records_len; /* length of all removed records */ int i; /* * make sure that item is directory and there are enough entries to * remove */ RFALSE(!is_direntry_le_ih(ih), "10180: item is not directory item"); RFALSE(ih_entry_count(ih) < from + del_count, "10185: item contains not enough entries: entry_count = %d, from = %d, to delete = %d", ih_entry_count(ih), from, del_count); if (del_count == 0) return 0; /* first byte of item */ item = bh->b_data + ih_location(ih); /* entry head array */ deh = B_I_DEH(bh, ih); /* * first byte of remaining entries, those are BEFORE cut entries * (prev_record) and length of all removed records (cut_records_len) */ prev_record_offset = (from ? deh_location(&deh[from - 1]) : ih_item_len(ih)); cut_records_len = prev_record_offset /*from_record */ - deh_location(&deh[from + del_count - 1]); prev_record = item + prev_record_offset; /* adjust locations of remaining entries */ for (i = ih_entry_count(ih) - 1; i > from + del_count - 1; i--) put_deh_location(&deh[i], deh_location(&deh[i]) - (DEH_SIZE * del_count)); for (i = 0; i < from; i++) put_deh_location(&deh[i], deh_location(&deh[i]) - (DEH_SIZE * del_count + cut_records_len)); put_ih_entry_count(ih, ih_entry_count(ih) - del_count); /* shift entry head array and entries those are AFTER removed entries */ memmove((char *)(deh + from), deh + from + del_count, prev_record - cut_records_len - (char *)(deh + from + del_count)); /* shift records, those are BEFORE removed entries */ memmove(prev_record - cut_records_len - DEH_SIZE * del_count, prev_record, item + ih_item_len(ih) - prev_record); return DEH_SIZE * del_count + cut_records_len; } /* * when cut item is part of regular file * pos_in_item - first byte that must be cut * cut_size - number of bytes to be cut beginning from pos_in_item * * when cut item is part of directory * pos_in_item - number of first deleted entry * cut_size - count of deleted entries */ void leaf_cut_from_buffer(struct buffer_info *bi, int cut_item_num, int pos_in_item, int cut_size) { int nr; struct buffer_head *bh = bi->bi_bh; struct block_head *blkh; struct item_head *ih; int last_loc, unmoved_loc; int i; blkh = B_BLK_HEAD(bh); nr = blkh_nr_item(blkh); /* item head of truncated item */ ih = item_head(bh, cut_item_num); if (is_direntry_le_ih(ih)) { /* first cut entry () */ cut_size = leaf_cut_entries(bh, ih, pos_in_item, cut_size); if (pos_in_item == 0) { /* change key */ RFALSE(cut_item_num, "when 0-th enrty of item is cut, that item must be first in the node, not %d-th", cut_item_num); /* change item key by key of first entry in the item */ set_le_ih_k_offset(ih, deh_offset(B_I_DEH(bh, ih))); } } else { /* item is direct or indirect */ RFALSE(is_statdata_le_ih(ih), "10195: item is stat data"); RFALSE(pos_in_item && pos_in_item + cut_size != ih_item_len(ih), "10200: invalid offset (%lu) or trunc_size (%lu) or ih_item_len (%lu)", (long unsigned)pos_in_item, (long unsigned)cut_size, (long unsigned)ih_item_len(ih)); /* shift item body to left if cut is from the head of item */ if (pos_in_item == 0) { memmove(bh->b_data + ih_location(ih), bh->b_data + ih_location(ih) + cut_size, ih_item_len(ih) - cut_size); /* change key of item */ if (is_direct_le_ih(ih)) set_le_ih_k_offset(ih, le_ih_k_offset(ih) + cut_size); else { set_le_ih_k_offset(ih, le_ih_k_offset(ih) + (cut_size / UNFM_P_SIZE) * bh->b_size); RFALSE(ih_item_len(ih) == cut_size && get_ih_free_space(ih), "10205: invalid ih_free_space (%h)", ih); } } } /* location of the last item */ last_loc = ih_location(&ih[nr - cut_item_num - 1]); /* location of the item, which is remaining at the same place */ unmoved_loc = cut_item_num ? ih_location(ih - 1) : bh->b_size; /* shift */ memmove(bh->b_data + last_loc + cut_size, bh->b_data + last_loc, unmoved_loc - last_loc - cut_size); /* change item length */ put_ih_item_len(ih, ih_item_len(ih) - cut_size); if (is_indirect_le_ih(ih)) { if (pos_in_item) set_ih_free_space(ih, 0); } /* change locations */ for (i = cut_item_num; i < nr; i++) put_ih_location(&ih[i - cut_item_num], ih_location(&ih[i - cut_item_num]) + cut_size); /* size, free space */ set_blkh_free_space(blkh, blkh_free_space(blkh) + cut_size); do_balance_mark_leaf_dirty(bi->tb, bh, 0); if (bi->bi_parent) { struct disk_child *t_dc; t_dc = B_N_CHILD(bi->bi_parent, bi->bi_position); put_dc_size(t_dc, dc_size(t_dc) - cut_size); do_balance_mark_internal_dirty(bi->tb, bi->bi_parent, 0); } } /* delete del_num items from buffer starting from the first'th item */ static void leaf_delete_items_entirely(struct buffer_info *bi, int first, int del_num) { struct buffer_head *bh = bi->bi_bh; int nr; int i, j; int last_loc, last_removed_loc; struct block_head *blkh; struct item_head *ih; RFALSE(bh == NULL, "10210: buffer is 0"); RFALSE(del_num < 0, "10215: del_num less than 0 (%d)", del_num); if (del_num == 0) return; blkh = B_BLK_HEAD(bh); nr = blkh_nr_item(blkh); RFALSE(first < 0 || first + del_num > nr, "10220: first=%d, number=%d, there is %d items", first, del_num, nr); if (first == 0 && del_num == nr) { /* this does not work */ make_empty_node(bi); do_balance_mark_leaf_dirty(bi->tb, bh, 0); return; } ih = item_head(bh, first); /* location of unmovable item */ j = (first == 0) ? bh->b_size : ih_location(ih - 1); /* delete items */ last_loc = ih_location(&ih[nr - 1 - first]); last_removed_loc = ih_location(&ih[del_num - 1]); memmove(bh->b_data + last_loc + j - last_removed_loc, bh->b_data + last_loc, last_removed_loc - last_loc); /* delete item headers */ memmove(ih, ih + del_num, (nr - first - del_num) * IH_SIZE); /* change item location */ for (i = first; i < nr - del_num; i++) put_ih_location(&ih[i - first], ih_location(&ih[i - first]) + (j - last_removed_loc)); /* sizes, item number */ set_blkh_nr_item(blkh, blkh_nr_item(blkh) - del_num); set_blkh_free_space(blkh, blkh_free_space(blkh) + (j - last_removed_loc + IH_SIZE * del_num)); do_balance_mark_leaf_dirty(bi->tb, bh, 0); if (bi->bi_parent) { struct disk_child *t_dc = B_N_CHILD(bi->bi_parent, bi->bi_position); put_dc_size(t_dc, dc_size(t_dc) - (j - last_removed_loc + IH_SIZE * del_num)); do_balance_mark_internal_dirty(bi->tb, bi->bi_parent, 0); } } /* * paste new_entry_count entries (new_dehs, records) into position * before to item_num-th item */ void leaf_paste_entries(struct buffer_info *bi, int item_num, int before, int new_entry_count, struct reiserfs_de_head *new_dehs, const char *records, int paste_size) { struct item_head *ih; char *item; struct reiserfs_de_head *deh; char *insert_point; int i, old_entry_num; struct buffer_head *bh = bi->bi_bh; if (new_entry_count == 0) return; ih = item_head(bh, item_num); /* * make sure, that item is directory, and there are enough * records in it */ RFALSE(!is_direntry_le_ih(ih), "10225: item is not directory item"); RFALSE(ih_entry_count(ih) < before, "10230: there are no entry we paste entries before. entry_count = %d, before = %d", ih_entry_count(ih), before); /* first byte of dest item */ item = bh->b_data + ih_location(ih); /* entry head array */ deh = B_I_DEH(bh, ih); /* new records will be pasted at this point */ insert_point = item + (before ? deh_location(&deh[before - 1]) : (ih_item_len(ih) - paste_size)); /* adjust locations of records that will be AFTER new records */ for (i = ih_entry_count(ih) - 1; i >= before; i--) put_deh_location(&deh[i], deh_location(&deh[i]) + (DEH_SIZE * new_entry_count)); /* adjust locations of records that will be BEFORE new records */ for (i = 0; i < before; i++) put_deh_location(&deh[i], deh_location(&deh[i]) + paste_size); old_entry_num = ih_entry_count(ih); put_ih_entry_count(ih, ih_entry_count(ih) + new_entry_count); /* prepare space for pasted records */ memmove(insert_point + paste_size, insert_point, item + (ih_item_len(ih) - paste_size) - insert_point); /* copy new records */ memcpy(insert_point + DEH_SIZE * new_entry_count, records, paste_size - DEH_SIZE * new_entry_count); /* prepare space for new entry heads */ deh += before; memmove((char *)(deh + new_entry_count), deh, insert_point - (char *)deh); /* copy new entry heads */ deh = (struct reiserfs_de_head *)((char *)deh); memcpy(deh, new_dehs, DEH_SIZE * new_entry_count); /* set locations of new records */ for (i = 0; i < new_entry_count; i++) { put_deh_location(&deh[i], deh_location(&deh[i]) + (-deh_location (&new_dehs[new_entry_count - 1]) + insert_point + DEH_SIZE * new_entry_count - item)); } /* change item key if necessary (when we paste before 0-th entry */ if (!before) { set_le_ih_k_offset(ih, deh_offset(new_dehs)); } #ifdef CONFIG_REISERFS_CHECK { int prev, next; /* check record locations */ deh = B_I_DEH(bh, ih); for (i = 0; i < ih_entry_count(ih); i++) { next = (i < ih_entry_count(ih) - 1) ? deh_location(&deh[i + 1]) : 0; prev = (i != 0) ? deh_location(&deh[i - 1]) : 0; if (prev && prev <= deh_location(&deh[i])) reiserfs_error(sb_from_bi(bi), "vs-10240", "directory item (%h) " "corrupted (prev %a, " "cur(%d) %a)", ih, deh + i - 1, i, deh + i); if (next && next >= deh_location(&deh[i])) reiserfs_error(sb_from_bi(bi), "vs-10250", "directory item (%h) " "corrupted (cur(%d) %a, " "next %a)", ih, i, deh + i, deh + i + 1); } } #endif } |
| 4 1 3 4 1 2 1 1 4 3 1 1 6 3 6 4 5 5 1 1 4 1 5 1 7 7 3 7 7 4 3 3 4 4 4 4 1 5 5 5 5 5 5 5 1 1 2 5 6 13 12 11 4 13 7 4 10 1 1 1 1 7 10 1 1 1 1 10 7 10 3 3 3 6 4 7 4 1 5 5 2 1 12 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 | /* * net/sched/ife.c Inter-FE action based on ForCES WG InterFE LFB * * Refer to: * draft-ietf-forces-interfelfb-03 * and * netdev01 paper: * "Distributing Linux Traffic Control Classifier-Action * Subsystem" * Authors: Jamal Hadi Salim and Damascene M. Joachimpillai * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. * * copyright Jamal Hadi Salim (2015) * */ #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/module.h> #include <linux/init.h> #include <net/net_namespace.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <uapi/linux/tc_act/tc_ife.h> #include <net/tc_act/tc_ife.h> #include <linux/etherdevice.h> #include <net/ife.h> static unsigned int ife_net_id; static int max_metacnt = IFE_META_MAX + 1; static struct tc_action_ops act_ife_ops; static const struct nla_policy ife_policy[TCA_IFE_MAX + 1] = { [TCA_IFE_PARMS] = { .len = sizeof(struct tc_ife)}, [TCA_IFE_DMAC] = { .len = ETH_ALEN}, [TCA_IFE_SMAC] = { .len = ETH_ALEN}, [TCA_IFE_TYPE] = { .type = NLA_U16}, }; int ife_encode_meta_u16(u16 metaval, void *skbdata, struct tcf_meta_info *mi) { u16 edata = 0; if (mi->metaval) edata = *(u16 *)mi->metaval; else if (metaval) edata = metaval; if (!edata) /* will not encode */ return 0; edata = htons(edata); return ife_tlv_meta_encode(skbdata, mi->metaid, 2, &edata); } EXPORT_SYMBOL_GPL(ife_encode_meta_u16); int ife_get_meta_u32(struct sk_buff *skb, struct tcf_meta_info *mi) { if (mi->metaval) return nla_put_u32(skb, mi->metaid, *(u32 *)mi->metaval); else return nla_put(skb, mi->metaid, 0, NULL); } EXPORT_SYMBOL_GPL(ife_get_meta_u32); int ife_check_meta_u32(u32 metaval, struct tcf_meta_info *mi) { if (metaval || mi->metaval) return 8; /* T+L+V == 2+2+4 */ return 0; } EXPORT_SYMBOL_GPL(ife_check_meta_u32); int ife_check_meta_u16(u16 metaval, struct tcf_meta_info *mi) { if (metaval || mi->metaval) return 8; /* T+L+(V) == 2+2+(2+2bytepad) */ return 0; } EXPORT_SYMBOL_GPL(ife_check_meta_u16); int ife_encode_meta_u32(u32 metaval, void *skbdata, struct tcf_meta_info *mi) { u32 edata = metaval; if (mi->metaval) edata = *(u32 *)mi->metaval; else if (metaval) edata = metaval; if (!edata) /* will not encode */ return 0; edata = htonl(edata); return ife_tlv_meta_encode(skbdata, mi->metaid, 4, &edata); } EXPORT_SYMBOL_GPL(ife_encode_meta_u32); int ife_get_meta_u16(struct sk_buff *skb, struct tcf_meta_info *mi) { if (mi->metaval) return nla_put_u16(skb, mi->metaid, *(u16 *)mi->metaval); else return nla_put(skb, mi->metaid, 0, NULL); } EXPORT_SYMBOL_GPL(ife_get_meta_u16); int ife_alloc_meta_u32(struct tcf_meta_info *mi, void *metaval, gfp_t gfp) { mi->metaval = kmemdup(metaval, sizeof(u32), gfp); if (!mi->metaval) return -ENOMEM; return 0; } EXPORT_SYMBOL_GPL(ife_alloc_meta_u32); int ife_alloc_meta_u16(struct tcf_meta_info *mi, void *metaval, gfp_t gfp) { mi->metaval = kmemdup(metaval, sizeof(u16), gfp); if (!mi->metaval) return -ENOMEM; return 0; } EXPORT_SYMBOL_GPL(ife_alloc_meta_u16); void ife_release_meta_gen(struct tcf_meta_info *mi) { kfree(mi->metaval); } EXPORT_SYMBOL_GPL(ife_release_meta_gen); int ife_validate_meta_u32(void *val, int len) { if (len == sizeof(u32)) return 0; return -EINVAL; } EXPORT_SYMBOL_GPL(ife_validate_meta_u32); int ife_validate_meta_u16(void *val, int len) { /* length will not include padding */ if (len == sizeof(u16)) return 0; return -EINVAL; } EXPORT_SYMBOL_GPL(ife_validate_meta_u16); static LIST_HEAD(ifeoplist); static DEFINE_RWLOCK(ife_mod_lock); static struct tcf_meta_ops *find_ife_oplist(u16 metaid) { struct tcf_meta_ops *o; read_lock(&ife_mod_lock); list_for_each_entry(o, &ifeoplist, list) { if (o->metaid == metaid) { if (!try_module_get(o->owner)) o = NULL; read_unlock(&ife_mod_lock); return o; } } read_unlock(&ife_mod_lock); return NULL; } int register_ife_op(struct tcf_meta_ops *mops) { struct tcf_meta_ops *m; if (!mops->metaid || !mops->metatype || !mops->name || !mops->check_presence || !mops->encode || !mops->decode || !mops->get || !mops->alloc) return -EINVAL; write_lock(&ife_mod_lock); list_for_each_entry(m, &ifeoplist, list) { if (m->metaid == mops->metaid || (strcmp(mops->name, m->name) == 0)) { write_unlock(&ife_mod_lock); return -EEXIST; } } if (!mops->release) mops->release = ife_release_meta_gen; list_add_tail(&mops->list, &ifeoplist); write_unlock(&ife_mod_lock); return 0; } EXPORT_SYMBOL_GPL(unregister_ife_op); int unregister_ife_op(struct tcf_meta_ops *mops) { struct tcf_meta_ops *m; int err = -ENOENT; write_lock(&ife_mod_lock); list_for_each_entry(m, &ifeoplist, list) { if (m->metaid == mops->metaid) { list_del(&mops->list); err = 0; break; } } write_unlock(&ife_mod_lock); return err; } EXPORT_SYMBOL_GPL(register_ife_op); static int ife_validate_metatype(struct tcf_meta_ops *ops, void *val, int len) { int ret = 0; /* XXX: unfortunately cant use nla_policy at this point * because a length of 0 is valid in the case of * "allow". "use" semantics do enforce for proper * length and i couldve use nla_policy but it makes it hard * to use it just for that.. */ if (ops->validate) return ops->validate(val, len); if (ops->metatype == NLA_U32) ret = ife_validate_meta_u32(val, len); else if (ops->metatype == NLA_U16) ret = ife_validate_meta_u16(val, len); return ret; } /* called when adding new meta information */ static int load_metaops_and_vet(u32 metaid, void *val, int len) { struct tcf_meta_ops *ops = find_ife_oplist(metaid); int ret = 0; if (!ops) { ret = -ENOENT; #ifdef CONFIG_MODULES rtnl_unlock(); request_module("ifemeta%u", metaid); rtnl_lock(); ops = find_ife_oplist(metaid); #endif } if (ops) { ret = 0; if (len) ret = ife_validate_metatype(ops, val, len); module_put(ops->owner); } return ret; } /* called when adding new meta information */ static int __add_metainfo(const struct tcf_meta_ops *ops, struct tcf_ife_info *ife, u32 metaid, void *metaval, int len, bool atomic, bool exists) { struct tcf_meta_info *mi = NULL; int ret = 0; mi = kzalloc(sizeof(*mi), atomic ? GFP_ATOMIC : GFP_KERNEL); if (!mi) return -ENOMEM; mi->metaid = metaid; mi->ops = ops; if (len > 0) { ret = ops->alloc(mi, metaval, atomic ? GFP_ATOMIC : GFP_KERNEL); if (ret != 0) { kfree(mi); return ret; } } if (exists) spin_lock_bh(&ife->tcf_lock); list_add_tail(&mi->metalist, &ife->metalist); if (exists) spin_unlock_bh(&ife->tcf_lock); return ret; } static int add_metainfo_and_get_ops(const struct tcf_meta_ops *ops, struct tcf_ife_info *ife, u32 metaid, bool exists) { int ret; if (!try_module_get(ops->owner)) return -ENOENT; ret = __add_metainfo(ops, ife, metaid, NULL, 0, true, exists); if (ret) module_put(ops->owner); return ret; } static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval, int len, bool exists) { const struct tcf_meta_ops *ops = find_ife_oplist(metaid); int ret; if (!ops) return -ENOENT; ret = __add_metainfo(ops, ife, metaid, metaval, len, false, exists); if (ret) /*put back what find_ife_oplist took */ module_put(ops->owner); return ret; } static int use_all_metadata(struct tcf_ife_info *ife, bool exists) { struct tcf_meta_ops *o; int rc = 0; int installed = 0; read_lock(&ife_mod_lock); list_for_each_entry(o, &ifeoplist, list) { rc = add_metainfo_and_get_ops(o, ife, o->metaid, exists); if (rc == 0) installed += 1; } read_unlock(&ife_mod_lock); if (installed) return 0; else return -EINVAL; } static int dump_metalist(struct sk_buff *skb, struct tcf_ife_info *ife) { struct tcf_meta_info *e; struct nlattr *nest; unsigned char *b = skb_tail_pointer(skb); int total_encoded = 0; /*can only happen on decode */ if (list_empty(&ife->metalist)) return 0; nest = nla_nest_start(skb, TCA_IFE_METALST); if (!nest) goto out_nlmsg_trim; list_for_each_entry(e, &ife->metalist, metalist) { if (!e->ops->get(skb, e)) total_encoded += 1; } if (!total_encoded) goto out_nlmsg_trim; nla_nest_end(skb, nest); return 0; out_nlmsg_trim: nlmsg_trim(skb, b); return -1; } /* under ife->tcf_lock */ static void _tcf_ife_cleanup(struct tc_action *a, int bind) { struct tcf_ife_info *ife = to_ife(a); struct tcf_meta_info *e, *n; list_for_each_entry_safe(e, n, &ife->metalist, metalist) { list_del(&e->metalist); if (e->metaval) { if (e->ops->release) e->ops->release(e); else kfree(e->metaval); } module_put(e->ops->owner); kfree(e); } } static void tcf_ife_cleanup(struct tc_action *a, int bind) { struct tcf_ife_info *ife = to_ife(a); spin_lock_bh(&ife->tcf_lock); _tcf_ife_cleanup(a, bind); spin_unlock_bh(&ife->tcf_lock); } static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, bool exists) { int len = 0; int rc = 0; int i = 0; void *val; for (i = 1; i < max_metacnt; i++) { if (tb[i]) { val = nla_data(tb[i]); len = nla_len(tb[i]); rc = load_metaops_and_vet(i, val, len); if (rc != 0) return rc; rc = add_metainfo(ife, i, val, len, exists); if (rc) return rc; } } return rc; } static int tcf_ife_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind) { struct tc_action_net *tn = net_generic(net, ife_net_id); struct nlattr *tb[TCA_IFE_MAX + 1]; struct nlattr *tb2[IFE_META_MAX + 1]; struct tcf_ife_info *ife; u16 ife_type = ETH_P_IFE; struct tc_ife *parm; u8 *daddr = NULL; u8 *saddr = NULL; bool exists = false; int ret = 0; int err; if (!nla) return -EINVAL; err = nla_parse_nested(tb, TCA_IFE_MAX, nla, ife_policy, NULL); if (err < 0) return err; if (!tb[TCA_IFE_PARMS]) return -EINVAL; parm = nla_data(tb[TCA_IFE_PARMS]); exists = tcf_idr_check(tn, parm->index, a, bind); if (exists && bind) return 0; if (!exists) { ret = tcf_idr_create(tn, parm->index, est, a, &act_ife_ops, bind, false); if (ret) return ret; ret = ACT_P_CREATED; } else { tcf_idr_release(*a, bind); if (!ovr) return -EEXIST; } ife = to_ife(*a); ife->flags = parm->flags; if (parm->flags & IFE_ENCODE) { if (tb[TCA_IFE_TYPE]) ife_type = nla_get_u16(tb[TCA_IFE_TYPE]); if (tb[TCA_IFE_DMAC]) daddr = nla_data(tb[TCA_IFE_DMAC]); if (tb[TCA_IFE_SMAC]) saddr = nla_data(tb[TCA_IFE_SMAC]); } if (exists) spin_lock_bh(&ife->tcf_lock); ife->tcf_action = parm->action; if (exists) spin_unlock_bh(&ife->tcf_lock); if (parm->flags & IFE_ENCODE) { if (daddr) ether_addr_copy(ife->eth_dst, daddr); else eth_zero_addr(ife->eth_dst); if (saddr) ether_addr_copy(ife->eth_src, saddr); else eth_zero_addr(ife->eth_src); ife->eth_type = ife_type; } if (ret == ACT_P_CREATED) INIT_LIST_HEAD(&ife->metalist); if (tb[TCA_IFE_METALST]) { err = nla_parse_nested(tb2, IFE_META_MAX, tb[TCA_IFE_METALST], NULL, NULL); if (err) { metadata_parse_err: if (exists) tcf_idr_release(*a, bind); if (ret == ACT_P_CREATED) _tcf_ife_cleanup(*a, bind); return err; } err = populate_metalist(ife, tb2, exists); if (err) goto metadata_parse_err; } else { /* if no passed metadata allow list or passed allow-all * then here we process by adding as many supported metadatum * as we can. You better have at least one else we are * going to bail out */ err = use_all_metadata(ife, exists); if (err) { if (ret == ACT_P_CREATED) _tcf_ife_cleanup(*a, bind); return err; } } if (ret == ACT_P_CREATED) tcf_idr_insert(tn, *a); return ret; } static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_ife_info *ife = to_ife(a); struct tc_ife opt = { .index = ife->tcf_index, .refcnt = ife->tcf_refcnt - ref, .bindcnt = ife->tcf_bindcnt - bind, .action = ife->tcf_action, .flags = ife->flags, }; struct tcf_t t; if (nla_put(skb, TCA_IFE_PARMS, sizeof(opt), &opt)) goto nla_put_failure; tcf_tm_dump(&t, &ife->tcf_tm); if (nla_put_64bit(skb, TCA_IFE_TM, sizeof(t), &t, TCA_IFE_PAD)) goto nla_put_failure; if (!is_zero_ether_addr(ife->eth_dst)) { if (nla_put(skb, TCA_IFE_DMAC, ETH_ALEN, ife->eth_dst)) goto nla_put_failure; } if (!is_zero_ether_addr(ife->eth_src)) { if (nla_put(skb, TCA_IFE_SMAC, ETH_ALEN, ife->eth_src)) goto nla_put_failure; } if (nla_put(skb, TCA_IFE_TYPE, 2, &ife->eth_type)) goto nla_put_failure; if (dump_metalist(skb, ife)) { /*ignore failure to dump metalist */ pr_info("Failed to dump metalist\n"); } return skb->len; nla_put_failure: nlmsg_trim(skb, b); return -1; } static int find_decode_metaid(struct sk_buff *skb, struct tcf_ife_info *ife, u16 metaid, u16 mlen, void *mdata) { struct tcf_meta_info *e; /* XXX: use hash to speed up */ list_for_each_entry(e, &ife->metalist, metalist) { if (metaid == e->metaid) { if (e->ops) { /* We check for decode presence already */ return e->ops->decode(skb, mdata, mlen); } } } return -ENOENT; } static int tcf_ife_decode(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_ife_info *ife = to_ife(a); int action = ife->tcf_action; u8 *ifehdr_end; u8 *tlv_data; u16 metalen; spin_lock(&ife->tcf_lock); bstats_update(&ife->tcf_bstats, skb); tcf_lastuse_update(&ife->tcf_tm); spin_unlock(&ife->tcf_lock); if (skb_at_tc_ingress(skb)) skb_push(skb, skb->dev->hard_header_len); tlv_data = ife_decode(skb, &metalen); if (unlikely(!tlv_data)) { spin_lock(&ife->tcf_lock); ife->tcf_qstats.drops++; spin_unlock(&ife->tcf_lock); return TC_ACT_SHOT; } ifehdr_end = tlv_data + metalen; for (; tlv_data < ifehdr_end; tlv_data = ife_tlv_meta_next(tlv_data)) { u8 *curr_data; u16 mtype; u16 dlen; curr_data = ife_tlv_meta_decode(tlv_data, ifehdr_end, &mtype, &dlen, NULL); if (!curr_data) { qstats_drop_inc(this_cpu_ptr(ife->common.cpu_qstats)); return TC_ACT_SHOT; } if (find_decode_metaid(skb, ife, mtype, dlen, curr_data)) { /* abuse overlimits to count when we receive metadata * but dont have an ops for it */ pr_info_ratelimited("Unknown metaid %d dlen %d\n", mtype, dlen); ife->tcf_qstats.overlimits++; } } if (WARN_ON(tlv_data != ifehdr_end)) { spin_lock(&ife->tcf_lock); ife->tcf_qstats.drops++; spin_unlock(&ife->tcf_lock); return TC_ACT_SHOT; } skb->protocol = eth_type_trans(skb, skb->dev); skb_reset_network_header(skb); return action; } /*XXX: check if we can do this at install time instead of current * send data path **/ static int ife_get_sz(struct sk_buff *skb, struct tcf_ife_info *ife) { struct tcf_meta_info *e, *n; int tot_run_sz = 0, run_sz = 0; list_for_each_entry_safe(e, n, &ife->metalist, metalist) { if (e->ops->check_presence) { run_sz = e->ops->check_presence(skb, e); tot_run_sz += run_sz; } } return tot_run_sz; } static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_ife_info *ife = to_ife(a); int action = ife->tcf_action; struct ethhdr *oethh; /* outer ether header */ struct tcf_meta_info *e; /* OUTERHDR:TOTMETALEN:{TLVHDR:Metadatum:TLVHDR..}:ORIGDATA where ORIGDATA = original ethernet header ... */ u16 metalen = ife_get_sz(skb, ife); int hdrm = metalen + skb->dev->hard_header_len + IFE_METAHDRLEN; unsigned int skboff = 0; int new_len = skb->len + hdrm; bool exceed_mtu = false; void *ife_meta; int err = 0; if (!skb_at_tc_ingress(skb)) { if (new_len > skb->dev->mtu) exceed_mtu = true; } spin_lock(&ife->tcf_lock); bstats_update(&ife->tcf_bstats, skb); tcf_lastuse_update(&ife->tcf_tm); if (!metalen) { /* no metadata to send */ /* abuse overlimits to count when we allow packet * with no metadata */ ife->tcf_qstats.overlimits++; spin_unlock(&ife->tcf_lock); return action; } /* could be stupid policy setup or mtu config * so lets be conservative.. */ if ((action == TC_ACT_SHOT) || exceed_mtu) { ife->tcf_qstats.drops++; spin_unlock(&ife->tcf_lock); return TC_ACT_SHOT; } if (skb_at_tc_ingress(skb)) skb_push(skb, skb->dev->hard_header_len); ife_meta = ife_encode(skb, metalen); /* XXX: we dont have a clever way of telling encode to * not repeat some of the computations that are done by * ops->presence_check... */ list_for_each_entry(e, &ife->metalist, metalist) { if (e->ops->encode) { err = e->ops->encode(skb, (void *)(ife_meta + skboff), e); } if (err < 0) { /* too corrupt to keep around if overwritten */ ife->tcf_qstats.drops++; spin_unlock(&ife->tcf_lock); return TC_ACT_SHOT; } skboff += err; } oethh = (struct ethhdr *)skb->data; if (!is_zero_ether_addr(ife->eth_src)) ether_addr_copy(oethh->h_source, ife->eth_src); if (!is_zero_ether_addr(ife->eth_dst)) ether_addr_copy(oethh->h_dest, ife->eth_dst); oethh->h_proto = htons(ife->eth_type); if (skb_at_tc_ingress(skb)) skb_pull(skb, skb->dev->hard_header_len); spin_unlock(&ife->tcf_lock); return action; } static int tcf_ife_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_ife_info *ife = to_ife(a); if (ife->flags & IFE_ENCODE) return tcf_ife_encode(skb, a, res); if (!(ife->flags & IFE_ENCODE)) return tcf_ife_decode(skb, a, res); pr_info_ratelimited("unknown failure(policy neither de/encode\n"); spin_lock(&ife->tcf_lock); bstats_update(&ife->tcf_bstats, skb); tcf_lastuse_update(&ife->tcf_tm); ife->tcf_qstats.drops++; spin_unlock(&ife->tcf_lock); return TC_ACT_SHOT; } static int tcf_ife_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, const struct tc_action_ops *ops) { struct tc_action_net *tn = net_generic(net, ife_net_id); return tcf_generic_walker(tn, skb, cb, type, ops); } static int tcf_ife_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, ife_net_id); return tcf_idr_search(tn, a, index); } static struct tc_action_ops act_ife_ops = { .kind = "ife", .type = TCA_ACT_IFE, .owner = THIS_MODULE, .act = tcf_ife_act, .dump = tcf_ife_dump, .cleanup = tcf_ife_cleanup, .init = tcf_ife_init, .walk = tcf_ife_walker, .lookup = tcf_ife_search, .size = sizeof(struct tcf_ife_info), }; static __net_init int ife_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, ife_net_id); return tc_action_net_init(net, tn, &act_ife_ops); } static void __net_exit ife_exit_net(struct net *net) { struct tc_action_net *tn = net_generic(net, ife_net_id); tc_action_net_exit(tn); } static struct pernet_operations ife_net_ops = { .init = ife_init_net, .exit = ife_exit_net, .id = &ife_net_id, .size = sizeof(struct tc_action_net), }; static int __init ife_init_module(void) { return tcf_register_action(&act_ife_ops, &ife_net_ops); } static void __exit ife_cleanup_module(void) { tcf_unregister_action(&act_ife_ops, &ife_net_ops); } module_init(ife_init_module); module_exit(ife_cleanup_module); MODULE_AUTHOR("Jamal Hadi Salim(2015)"); MODULE_DESCRIPTION("Inter-FE LFB action"); MODULE_LICENSE("GPL"); |
| 1 2 990 113 793 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * descriptor table internals; you almost certainly want file.h instead. */ #ifndef __LINUX_FDTABLE_H #define __LINUX_FDTABLE_H #include <linux/posix_types.h> #include <linux/compiler.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/nospec.h> #include <linux/types.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/atomic.h> /* * The default fd array needs to be at least BITS_PER_LONG, * as this is the granularity returned by copy_fdset(). */ #define NR_OPEN_DEFAULT BITS_PER_LONG struct fdtable { unsigned int max_fds; struct file __rcu **fd; /* current fd array */ unsigned long *close_on_exec; unsigned long *open_fds; unsigned long *full_fds_bits; struct rcu_head rcu; }; static inline bool close_on_exec(unsigned int fd, const struct fdtable *fdt) { return test_bit(fd, fdt->close_on_exec); } static inline bool fd_is_open(unsigned int fd, const struct fdtable *fdt) { return test_bit(fd, fdt->open_fds); } /* * Open file table structure */ struct files_struct { /* * read mostly part */ atomic_t count; bool resize_in_progress; wait_queue_head_t resize_wait; struct fdtable __rcu *fdt; struct fdtable fdtab; /* * written part on a separate cache line in SMP */ spinlock_t file_lock ____cacheline_aligned_in_smp; unsigned int next_fd; unsigned long close_on_exec_init[1]; unsigned long open_fds_init[1]; unsigned long full_fds_bits_init[1]; struct file __rcu * fd_array[NR_OPEN_DEFAULT]; }; struct file_operations; struct vfsmount; struct dentry; #define rcu_dereference_check_fdtable(files, fdtfd) \ rcu_dereference_check((fdtfd), lockdep_is_held(&(files)->file_lock)) #define files_fdtable(files) \ rcu_dereference_check_fdtable((files), (files)->fdt) /* * The caller must ensure that fd table isn't shared or hold rcu or file lock */ static inline struct file *__fcheck_files(struct files_struct *files, unsigned int fd) { struct fdtable *fdt = rcu_dereference_raw(files->fdt); if (fd < fdt->max_fds) { fd = array_index_nospec(fd, fdt->max_fds); return rcu_dereference_raw(fdt->fd[fd]); } return NULL; } static inline struct file *fcheck_files(struct files_struct *files, unsigned int fd) { RCU_LOCKDEP_WARN(!rcu_read_lock_held() && !lockdep_is_held(&files->file_lock), "suspicious rcu_dereference_check() usage"); return __fcheck_files(files, fd); } /* * Check whether the specified fd has an open file. */ #define fcheck(fd) fcheck_files(current->files, fd) struct task_struct; struct files_struct *get_files_struct(struct task_struct *); void put_files_struct(struct files_struct *fs); void reset_files_struct(struct files_struct *); int unshare_files(struct files_struct **); struct files_struct *dup_fd(struct files_struct *, int *) __latent_entropy; void do_close_on_exec(struct files_struct *); int iterate_fd(struct files_struct *, unsigned, int (*)(const void *, struct file *, unsigned), const void *); extern int __alloc_fd(struct files_struct *files, unsigned start, unsigned end, unsigned flags); extern void __fd_install(struct files_struct *files, unsigned int fd, struct file *file); extern int __close_fd(struct files_struct *files, unsigned int fd); extern struct kmem_cache *files_cachep; #endif /* __LINUX_FDTABLE_H */ |
| 2346 24 2128 2905 40 165 1 1 1 25 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 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 | /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for inet_sock * * Authors: Many, reorganised here by * Arnaldo Carvalho de Melo <acme@mandriva.com> * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ #ifndef _INET_SOCK_H #define _INET_SOCK_H #include <linux/bitops.h> #include <linux/string.h> #include <linux/types.h> #include <linux/jhash.h> #include <linux/netdevice.h> #include <net/flow.h> #include <net/sock.h> #include <net/request_sock.h> #include <net/netns/hash.h> #include <net/tcp_states.h> #include <net/l3mdev.h> /** struct ip_options - IP Options * * @faddr - Saved first hop address * @nexthop - Saved nexthop address in LSRR and SSRR * @is_strictroute - Strict source route * @srr_is_hit - Packet destination addr was our one * @is_changed - IP checksum more not valid * @rr_needaddr - Need to record addr of outgoing dev * @ts_needtime - Need to record timestamp * @ts_needaddr - Need to record addr of outgoing dev */ struct ip_options { __be32 faddr; __be32 nexthop; unsigned char optlen; unsigned char srr; unsigned char rr; unsigned char ts; unsigned char is_strictroute:1, srr_is_hit:1, is_changed:1, rr_needaddr:1, ts_needtime:1, ts_needaddr:1; unsigned char router_alert; unsigned char cipso; unsigned char __pad2; unsigned char __data[0]; }; struct ip_options_rcu { struct rcu_head rcu; struct ip_options opt; }; struct ip_options_data { struct ip_options_rcu opt; char data[40]; }; struct inet_request_sock { struct request_sock req; #define ir_loc_addr req.__req_common.skc_rcv_saddr #define ir_rmt_addr req.__req_common.skc_daddr #define ir_num req.__req_common.skc_num #define ir_rmt_port req.__req_common.skc_dport #define ir_v6_rmt_addr req.__req_common.skc_v6_daddr #define ir_v6_loc_addr req.__req_common.skc_v6_rcv_saddr #define ir_iif req.__req_common.skc_bound_dev_if #define ir_cookie req.__req_common.skc_cookie #define ireq_net req.__req_common.skc_net #define ireq_state req.__req_common.skc_state #define ireq_family req.__req_common.skc_family u16 snd_wscale : 4, rcv_wscale : 4, tstamp_ok : 1, sack_ok : 1, wscale_ok : 1, ecn_ok : 1, acked : 1, no_srccheck: 1; u32 ir_mark; union { struct ip_options_rcu __rcu *ireq_opt; #if IS_ENABLED(CONFIG_IPV6) struct { struct ipv6_txoptions *ipv6_opt; struct sk_buff *pktopts; }; #endif }; }; static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk) { return (struct inet_request_sock *)sk; } static inline u32 inet_request_mark(const struct sock *sk, struct sk_buff *skb) { if (!sk->sk_mark && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept)) return skb->mark; return sk->sk_mark; } static inline int inet_request_bound_dev_if(const struct sock *sk, struct sk_buff *skb) { #ifdef CONFIG_NET_L3_MASTER_DEV struct net *net = sock_net(sk); if (!sk->sk_bound_dev_if && net->ipv4.sysctl_tcp_l3mdev_accept) return l3mdev_master_ifindex_by_index(net, skb->skb_iif); #endif return sk->sk_bound_dev_if; } struct inet_cork { unsigned int flags; __be32 addr; struct ip_options *opt; unsigned int fragsize; int length; /* Total length of all frames */ struct dst_entry *dst; u8 tx_flags; __u8 ttl; __s16 tos; char priority; }; struct inet_cork_full { struct inet_cork base; struct flowi fl; }; struct ip_mc_socklist; struct ipv6_pinfo; struct rtable; /** struct inet_sock - representation of INET sockets * * @sk - ancestor class * @pinet6 - pointer to IPv6 control block * @inet_daddr - Foreign IPv4 addr * @inet_rcv_saddr - Bound local IPv4 addr * @inet_dport - Destination port * @inet_num - Local port * @inet_saddr - Sending source * @uc_ttl - Unicast TTL * @inet_sport - Source port * @inet_id - ID counter for DF pkts * @tos - TOS * @mc_ttl - Multicasting TTL * @is_icsk - is this an inet_connection_sock? * @uc_index - Unicast outgoing device index * @mc_index - Multicast device index * @mc_list - Group array * @cork - info to build ip hdr on each ip frag while socket is corked */ struct inet_sock { /* sk and pinet6 has to be the first two members of inet_sock */ struct sock sk; #if IS_ENABLED(CONFIG_IPV6) struct ipv6_pinfo *pinet6; #endif /* Socket demultiplex comparisons on incoming packets. */ #define inet_daddr sk.__sk_common.skc_daddr #define inet_rcv_saddr sk.__sk_common.skc_rcv_saddr #define inet_dport sk.__sk_common.skc_dport #define inet_num sk.__sk_common.skc_num __be32 inet_saddr; __s16 uc_ttl; __u16 cmsg_flags; __be16 inet_sport; __u16 inet_id; struct ip_options_rcu __rcu *inet_opt; int rx_dst_ifindex; __u8 tos; __u8 min_ttl; __u8 mc_ttl; __u8 pmtudisc; __u8 recverr:1, is_icsk:1, freebind:1, hdrincl:1, mc_loop:1, transparent:1, mc_all:1, nodefrag:1; __u8 bind_address_no_port:1, defer_connect:1; /* Indicates that fastopen_connect is set * and cookie exists so we defer connect * until first data frame is written */ __u8 rcv_tos; __u8 convert_csum; int uc_index; int mc_index; __be32 mc_addr; struct ip_mc_socklist __rcu *mc_list; struct inet_cork_full cork; }; #define IPCORK_OPT 1 /* ip-options has been held in ipcork.opt */ #define IPCORK_ALLFRAG 2 /* always fragment (for ipv6 for now) */ /* cmsg flags for inet */ #define IP_CMSG_PKTINFO BIT(0) #define IP_CMSG_TTL BIT(1) #define IP_CMSG_TOS BIT(2) #define IP_CMSG_RECVOPTS BIT(3) #define IP_CMSG_RETOPTS BIT(4) #define IP_CMSG_PASSSEC BIT(5) #define IP_CMSG_ORIGDSTADDR BIT(6) #define IP_CMSG_CHECKSUM BIT(7) #define IP_CMSG_RECVFRAGSIZE BIT(8) /** * sk_to_full_sk - Access to a full socket * @sk: pointer to a socket * * SYNACK messages might be attached to request sockets. * Some places want to reach the listener in this case. */ static inline struct sock *sk_to_full_sk(struct sock *sk) { #ifdef CONFIG_INET if (sk && sk->sk_state == TCP_NEW_SYN_RECV) sk = inet_reqsk(sk)->rsk_listener; #endif return sk; } /* sk_to_full_sk() variant with a const argument */ static inline const struct sock *sk_const_to_full_sk(const struct sock *sk) { #ifdef CONFIG_INET if (sk && sk->sk_state == TCP_NEW_SYN_RECV) sk = ((const struct request_sock *)sk)->rsk_listener; #endif return sk; } static inline struct sock *skb_to_full_sk(const struct sk_buff *skb) { return sk_to_full_sk(skb->sk); } static inline struct inet_sock *inet_sk(const struct sock *sk) { return (struct inet_sock *)sk; } static inline void __inet_sk_copy_descendant(struct sock *sk_to, const struct sock *sk_from, const int ancestor_size) { memcpy(inet_sk(sk_to) + 1, inet_sk(sk_from) + 1, sk_from->sk_prot->obj_size - ancestor_size); } #if !(IS_ENABLED(CONFIG_IPV6)) static inline void inet_sk_copy_descendant(struct sock *sk_to, const struct sock *sk_from) { __inet_sk_copy_descendant(sk_to, sk_from, sizeof(struct inet_sock)); } #endif int inet_sk_rebuild_header(struct sock *sk); static inline unsigned int __inet_ehashfn(const __be32 laddr, const __u16 lport, const __be32 faddr, const __be16 fport, u32 initval) { return jhash_3words((__force __u32) laddr, (__force __u32) faddr, ((__u32) lport) << 16 | (__force __u32)fport, initval); } struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener, bool attach_listener); static inline __u8 inet_sk_flowi_flags(const struct sock *sk) { __u8 flags = 0; if (inet_sk(sk)->transparent || inet_sk(sk)->hdrincl) flags |= FLOWI_FLAG_ANYSRC; return flags; } static inline void inet_inc_convert_csum(struct sock *sk) { inet_sk(sk)->convert_csum++; } static inline void inet_dec_convert_csum(struct sock *sk) { if (inet_sk(sk)->convert_csum > 0) inet_sk(sk)->convert_csum--; } static inline bool inet_get_convert_csum(struct sock *sk) { return !!inet_sk(sk)->convert_csum; } #endif /* _INET_SOCK_H */ |
| 6645 6643 10852 1427 6644 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RCULIST_BL_H #define _LINUX_RCULIST_BL_H /* * RCU-protected bl list version. See include/linux/list_bl.h. */ #include <linux/list_bl.h> #include <linux/rcupdate.h> static inline void hlist_bl_set_first_rcu(struct hlist_bl_head *h, struct hlist_bl_node *n) { LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK); LIST_BL_BUG_ON(((unsigned long)h->first & LIST_BL_LOCKMASK) != LIST_BL_LOCKMASK); rcu_assign_pointer(h->first, (struct hlist_bl_node *)((unsigned long)n | LIST_BL_LOCKMASK)); } static inline struct hlist_bl_node *hlist_bl_first_rcu(struct hlist_bl_head *h) { return (struct hlist_bl_node *) ((unsigned long)rcu_dereference_check(h->first, hlist_bl_is_locked(h)) & ~LIST_BL_LOCKMASK); } /** * hlist_bl_del_init_rcu - deletes entry from hash list with re-initialization * @n: the element to delete from the hash list. * * Note: hlist_bl_unhashed() on the node returns true after this. It is * useful for RCU based read lockfree traversal if the writer side * must know if the list entry is still hashed or already unhashed. * * In particular, it means that we can not poison the forward pointers * that may still be used for walking the hash list and we can only * zero the pprev pointer so list_unhashed() will return true after * this. * * The caller must take whatever precautions are necessary (such as * holding appropriate locks) to avoid racing with another * list-mutation primitive, such as hlist_bl_add_head_rcu() or * hlist_bl_del_rcu(), running on this same list. However, it is * perfectly legal to run concurrently with the _rcu list-traversal * primitives, such as hlist_bl_for_each_entry_rcu(). */ static inline void hlist_bl_del_init_rcu(struct hlist_bl_node *n) { if (!hlist_bl_unhashed(n)) { __hlist_bl_del(n); n->pprev = NULL; } } /** * hlist_bl_del_rcu - deletes entry from hash list without re-initialization * @n: the element to delete from the hash list. * * Note: hlist_bl_unhashed() on entry does not return true after this, * the entry is in an undefined state. It is useful for RCU based * lockfree traversal. * * In particular, it means that we can not poison the forward * pointers that may still be used for walking the hash list. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_bl_add_head_rcu() * or hlist_bl_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_bl_for_each_entry(). */ static inline void hlist_bl_del_rcu(struct hlist_bl_node *n) { __hlist_bl_del(n); n->pprev = LIST_POISON2; } /** * hlist_bl_add_head_rcu * @n: the element to add to the hash list. * @h: the list to add to. * * Description: * Adds the specified element to the specified hlist_bl, * while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_bl_add_head_rcu() * or hlist_bl_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_bl_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. Regardless of the type of CPU, the * list-traversal primitive must be guarded by rcu_read_lock(). */ static inline void hlist_bl_add_head_rcu(struct hlist_bl_node *n, struct hlist_bl_head *h) { struct hlist_bl_node *first; /* don't need hlist_bl_first_rcu because we're under lock */ first = hlist_bl_first(h); n->next = first; if (first) first->pprev = &n->next; n->pprev = &h->first; /* need _rcu because we can have concurrent lock free readers */ hlist_bl_set_first_rcu(h, n); } /** * hlist_bl_for_each_entry_rcu - iterate over rcu list of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_bl_node to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_bl_node within the struct. * */ #define hlist_bl_for_each_entry_rcu(tpos, pos, head, member) \ for (pos = hlist_bl_first_rcu(head); \ pos && \ ({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1; }); \ pos = rcu_dereference_raw(pos->next)) #endif |
| 20 32 29 6 20 20 34 337 12 8 317 324 321 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 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 | /* * net/sched/gen_estimator.c Simple rate estimator. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * Eric Dumazet <edumazet@google.com> * * Changes: * Jamal Hadi Salim - moved it to net/core and reshulfed * names to make it usable in general net subsystem. */ #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/in.h> #include <linux/errno.h> #include <linux/interrupt.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/seqlock.h> #include <net/sock.h> #include <net/gen_stats.h> /* This code is NOT intended to be used for statistics collection, * its purpose is to provide a base for statistical multiplexing * for controlled load service. * If you need only statistics, run a user level daemon which * periodically reads byte counters. */ struct net_rate_estimator { struct gnet_stats_basic_packed *bstats; spinlock_t *stats_lock; seqcount_t *running; struct gnet_stats_basic_cpu __percpu *cpu_bstats; u8 ewma_log; u8 intvl_log; /* period : (250ms << intvl_log) */ seqcount_t seq; u32 last_packets; u64 last_bytes; u64 avpps; u64 avbps; unsigned long next_jiffies; struct timer_list timer; struct rcu_head rcu; }; static void est_fetch_counters(struct net_rate_estimator *e, struct gnet_stats_basic_packed *b) { memset(b, 0, sizeof(*b)); if (e->stats_lock) spin_lock(e->stats_lock); __gnet_stats_copy_basic(e->running, b, e->cpu_bstats, e->bstats); if (e->stats_lock) spin_unlock(e->stats_lock); } static void est_timer(unsigned long arg) { struct net_rate_estimator *est = (struct net_rate_estimator *)arg; struct gnet_stats_basic_packed b; u64 rate, brate; est_fetch_counters(est, &b); brate = (b.bytes - est->last_bytes) << (10 - est->intvl_log); brate = (brate >> est->ewma_log) - (est->avbps >> est->ewma_log); rate = (u64)(b.packets - est->last_packets) << (10 - est->intvl_log); rate = (rate >> est->ewma_log) - (est->avpps >> est->ewma_log); write_seqcount_begin(&est->seq); est->avbps += brate; est->avpps += rate; write_seqcount_end(&est->seq); est->last_bytes = b.bytes; est->last_packets = b.packets; est->next_jiffies += ((HZ/4) << est->intvl_log); if (unlikely(time_after_eq(jiffies, est->next_jiffies))) { /* Ouch... timer was delayed. */ est->next_jiffies = jiffies + 1; } mod_timer(&est->timer, est->next_jiffies); } /** * gen_new_estimator - create a new rate estimator * @bstats: basic statistics * @cpu_bstats: bstats per cpu * @rate_est: rate estimator statistics * @stats_lock: statistics lock * @running: qdisc running seqcount * @opt: rate estimator configuration TLV * * Creates a new rate estimator with &bstats as source and &rate_est * as destination. A new timer with the interval specified in the * configuration TLV is created. Upon each interval, the latest statistics * will be read from &bstats and the estimated rate will be stored in * &rate_est with the statistics lock grabbed during this period. * * Returns 0 on success or a negative error code. * */ int gen_new_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, spinlock_t *stats_lock, seqcount_t *running, struct nlattr *opt) { struct gnet_estimator *parm = nla_data(opt); struct net_rate_estimator *old, *est; struct gnet_stats_basic_packed b; int intvl_log; if (nla_len(opt) < sizeof(*parm)) return -EINVAL; /* allowed timer periods are : * -2 : 250ms, -1 : 500ms, 0 : 1 sec * 1 : 2 sec, 2 : 4 sec, 3 : 8 sec */ if (parm->interval < -2 || parm->interval > 3) return -EINVAL; if (parm->ewma_log == 0 || parm->ewma_log >= 31) return -EINVAL; est = kzalloc(sizeof(*est), GFP_KERNEL); if (!est) return -ENOBUFS; seqcount_init(&est->seq); intvl_log = parm->interval + 2; est->bstats = bstats; est->stats_lock = stats_lock; est->running = running; est->ewma_log = parm->ewma_log; est->intvl_log = intvl_log; est->cpu_bstats = cpu_bstats; if (stats_lock) local_bh_disable(); est_fetch_counters(est, &b); if (stats_lock) local_bh_enable(); est->last_bytes = b.bytes; est->last_packets = b.packets; old = rcu_dereference_protected(*rate_est, 1); if (old) { del_timer_sync(&old->timer); est->avbps = old->avbps; est->avpps = old->avpps; } est->next_jiffies = jiffies + ((HZ/4) << intvl_log); setup_timer(&est->timer, est_timer, (unsigned long)est); mod_timer(&est->timer, est->next_jiffies); rcu_assign_pointer(*rate_est, est); if (old) kfree_rcu(old, rcu); return 0; } EXPORT_SYMBOL(gen_new_estimator); /** * gen_kill_estimator - remove a rate estimator * @rate_est: rate estimator * * Removes the rate estimator. * */ void gen_kill_estimator(struct net_rate_estimator __rcu **rate_est) { struct net_rate_estimator *est; est = xchg((__force struct net_rate_estimator **)rate_est, NULL); if (est) { del_timer_sync(&est->timer); kfree_rcu(est, rcu); } } EXPORT_SYMBOL(gen_kill_estimator); /** * gen_replace_estimator - replace rate estimator configuration * @bstats: basic statistics * @cpu_bstats: bstats per cpu * @rate_est: rate estimator statistics * @stats_lock: statistics lock * @running: qdisc running seqcount (might be NULL) * @opt: rate estimator configuration TLV * * Replaces the configuration of a rate estimator by calling * gen_kill_estimator() and gen_new_estimator(). * * Returns 0 on success or a negative error code. */ int gen_replace_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, spinlock_t *stats_lock, seqcount_t *running, struct nlattr *opt) { return gen_new_estimator(bstats, cpu_bstats, rate_est, stats_lock, running, opt); } EXPORT_SYMBOL(gen_replace_estimator); /** * gen_estimator_active - test if estimator is currently in use * @rate_est: rate estimator * * Returns true if estimator is active, and false if not. */ bool gen_estimator_active(struct net_rate_estimator __rcu **rate_est) { return !!rcu_access_pointer(*rate_est); } EXPORT_SYMBOL(gen_estimator_active); bool gen_estimator_read(struct net_rate_estimator __rcu **rate_est, struct gnet_stats_rate_est64 *sample) { struct net_rate_estimator *est; unsigned seq; rcu_read_lock(); est = rcu_dereference(*rate_est); if (!est) { rcu_read_unlock(); return false; } do { seq = read_seqcount_begin(&est->seq); sample->bps = est->avbps >> 8; sample->pps = est->avpps >> 8; } while (read_seqcount_retry(&est->seq, seq)); rcu_read_unlock(); return true; } EXPORT_SYMBOL(gen_estimator_read); |
| 63 64 64 64 64 64 64 64 64 64 64 64 64 64 64 64 42 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * Add configfs and memory store: Kyungchan Koh <kkc6196@fb.com> and * Shaohua Li <shli@fb.com> */ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/sched.h> #include <linux/fs.h> #include <linux/blkdev.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/blk-mq.h> #include <linux/hrtimer.h> #include <linux/lightnvm.h> #include <linux/configfs.h> #include <linux/badblocks.h> #define PAGE_SECTORS_SHIFT (PAGE_SHIFT - SECTOR_SHIFT) #define PAGE_SECTORS (1 << PAGE_SECTORS_SHIFT) #define SECTOR_MASK (PAGE_SECTORS - 1) #define FREE_BATCH 16 #define TICKS_PER_SEC 50ULL #define TIMER_INTERVAL (NSEC_PER_SEC / TICKS_PER_SEC) static inline u64 mb_per_tick(int mbps) { return (1 << 20) / TICKS_PER_SEC * ((u64) mbps); } struct nullb_cmd { struct list_head list; struct llist_node ll_list; call_single_data_t csd; struct request *rq; struct bio *bio; unsigned int tag; struct nullb_queue *nq; struct hrtimer timer; blk_status_t error; }; struct nullb_queue { unsigned long *tag_map; wait_queue_head_t wait; unsigned int queue_depth; struct nullb_device *dev; struct nullb_cmd *cmds; }; /* * Status flags for nullb_device. * * CONFIGURED: Device has been configured and turned on. Cannot reconfigure. * UP: Device is currently on and visible in userspace. * THROTTLED: Device is being throttled. * CACHE: Device is using a write-back cache. */ enum nullb_device_flags { NULLB_DEV_FL_CONFIGURED = 0, NULLB_DEV_FL_UP = 1, NULLB_DEV_FL_THROTTLED = 2, NULLB_DEV_FL_CACHE = 3, }; #define MAP_SZ ((PAGE_SIZE >> SECTOR_SHIFT) + 2) /* * nullb_page is a page in memory for nullb devices. * * @page: The page holding the data. * @bitmap: The bitmap represents which sector in the page has data. * Each bit represents one block size. For example, sector 8 * will use the 7th bit * The highest 2 bits of bitmap are for special purpose. LOCK means the cache * page is being flushing to storage. FREE means the cache page is freed and * should be skipped from flushing to storage. Please see * null_make_cache_space */ struct nullb_page { struct page *page; DECLARE_BITMAP(bitmap, MAP_SZ); }; #define NULLB_PAGE_LOCK (MAP_SZ - 1) #define NULLB_PAGE_FREE (MAP_SZ - 2) struct nullb_device { struct nullb *nullb; struct config_item item; struct radix_tree_root data; /* data stored in the disk */ struct radix_tree_root cache; /* disk cache data */ unsigned long flags; /* device flags */ unsigned int curr_cache; struct badblocks badblocks; unsigned long size; /* device size in MB */ unsigned long completion_nsec; /* time in ns to complete a request */ unsigned long cache_size; /* disk cache size in MB */ unsigned int submit_queues; /* number of submission queues */ unsigned int home_node; /* home node for the device */ unsigned int queue_mode; /* block interface */ unsigned int blocksize; /* block size */ unsigned int irqmode; /* IRQ completion handler */ unsigned int hw_queue_depth; /* queue depth */ unsigned int index; /* index of the disk, only valid with a disk */ unsigned int mbps; /* Bandwidth throttle cap (in MB/s) */ bool use_lightnvm; /* register as a LightNVM device */ bool blocking; /* blocking blk-mq device */ bool use_per_node_hctx; /* use per-node allocation for hardware context */ bool power; /* power on/off the device */ bool memory_backed; /* if data is stored in memory */ bool discard; /* if support discard */ }; struct nullb { struct nullb_device *dev; struct list_head list; unsigned int index; struct request_queue *q; struct gendisk *disk; struct nvm_dev *ndev; struct blk_mq_tag_set *tag_set; struct blk_mq_tag_set __tag_set; unsigned int queue_depth; atomic_long_t cur_bytes; struct hrtimer bw_timer; unsigned long cache_flush_pos; spinlock_t lock; struct nullb_queue *queues; unsigned int nr_queues; char disk_name[DISK_NAME_LEN]; }; static LIST_HEAD(nullb_list); static struct mutex lock; static int null_major; static DEFINE_IDA(nullb_indexes); static struct kmem_cache *ppa_cache; static struct blk_mq_tag_set tag_set; enum { NULL_IRQ_NONE = 0, NULL_IRQ_SOFTIRQ = 1, NULL_IRQ_TIMER = 2, }; enum { NULL_Q_BIO = 0, NULL_Q_RQ = 1, NULL_Q_MQ = 2, }; static int g_submit_queues = 1; module_param_named(submit_queues, g_submit_queues, int, S_IRUGO); MODULE_PARM_DESC(submit_queues, "Number of submission queues"); static int g_home_node = NUMA_NO_NODE; module_param_named(home_node, g_home_node, int, S_IRUGO); MODULE_PARM_DESC(home_node, "Home node for the device"); static int g_queue_mode = NULL_Q_MQ; static int null_param_store_val(const char *str, int *val, int min, int max) { int ret, new_val; ret = kstrtoint(str, 10, &new_val); if (ret) return -EINVAL; if (new_val < min || new_val > max) return -EINVAL; *val = new_val; return 0; } static int null_set_queue_mode(const char *str, const struct kernel_param *kp) { return null_param_store_val(str, &g_queue_mode, NULL_Q_BIO, NULL_Q_MQ); } static const struct kernel_param_ops null_queue_mode_param_ops = { .set = null_set_queue_mode, .get = param_get_int, }; device_param_cb(queue_mode, &null_queue_mode_param_ops, &g_queue_mode, S_IRUGO); MODULE_PARM_DESC(queue_mode, "Block interface to use (0=bio,1=rq,2=multiqueue)"); static int g_gb = 250; module_param_named(gb, g_gb, int, S_IRUGO); MODULE_PARM_DESC(gb, "Size in GB"); static int g_bs = 512; module_param_named(bs, g_bs, int, S_IRUGO); MODULE_PARM_DESC(bs, "Block size (in bytes)"); static int nr_devices = 1; module_param(nr_devices, int, S_IRUGO); MODULE_PARM_DESC(nr_devices, "Number of devices to register"); static bool g_use_lightnvm; module_param_named(use_lightnvm, g_use_lightnvm, bool, S_IRUGO); MODULE_PARM_DESC(use_lightnvm, "Register as a LightNVM device"); static bool g_blocking; module_param_named(blocking, g_blocking, bool, S_IRUGO); MODULE_PARM_DESC(blocking, "Register as a blocking blk-mq driver device"); static bool shared_tags; module_param(shared_tags, bool, S_IRUGO); MODULE_PARM_DESC(shared_tags, "Share tag set between devices for blk-mq"); static int g_irqmode = NULL_IRQ_SOFTIRQ; static int null_set_irqmode(const char *str, const struct kernel_param *kp) { return null_param_store_val(str, &g_irqmode, NULL_IRQ_NONE, NULL_IRQ_TIMER); } static const struct kernel_param_ops null_irqmode_param_ops = { .set = null_set_irqmode, .get = param_get_int, }; device_param_cb(irqmode, &null_irqmode_param_ops, &g_irqmode, S_IRUGO); MODULE_PARM_DESC(irqmode, "IRQ completion handler. 0-none, 1-softirq, 2-timer"); static unsigned long g_completion_nsec = 10000; module_param_named(completion_nsec, g_completion_nsec, ulong, S_IRUGO); MODULE_PARM_DESC(completion_nsec, "Time in ns to complete a request in hardware. Default: 10,000ns"); static int g_hw_queue_depth = 64; module_param_named(hw_queue_depth, g_hw_queue_depth, int, S_IRUGO); MODULE_PARM_DESC(hw_queue_depth, "Queue depth for each hardware queue. Default: 64"); static bool g_use_per_node_hctx; module_param_named(use_per_node_hctx, g_use_per_node_hctx, bool, S_IRUGO); MODULE_PARM_DESC(use_per_node_hctx, "Use per-node allocation for hardware context queues. Default: false"); static struct nullb_device *null_alloc_dev(void); static void null_free_dev(struct nullb_device *dev); static void null_del_dev(struct nullb *nullb); static int null_add_dev(struct nullb_device *dev); static void null_free_device_storage(struct nullb_device *dev, bool is_cache); static inline struct nullb_device *to_nullb_device(struct config_item *item) { return item ? container_of(item, struct nullb_device, item) : NULL; } static inline ssize_t nullb_device_uint_attr_show(unsigned int val, char *page) { return snprintf(page, PAGE_SIZE, "%u\n", val); } static inline ssize_t nullb_device_ulong_attr_show(unsigned long val, char *page) { return snprintf(page, PAGE_SIZE, "%lu\n", val); } static inline ssize_t nullb_device_bool_attr_show(bool val, char *page) { return snprintf(page, PAGE_SIZE, "%u\n", val); } static ssize_t nullb_device_uint_attr_store(unsigned int *val, const char *page, size_t count) { unsigned int tmp; int result; result = kstrtouint(page, 0, &tmp); if (result) return result; *val = tmp; return count; } static ssize_t nullb_device_ulong_attr_store(unsigned long *val, const char *page, size_t count) { int result; unsigned long tmp; result = kstrtoul(page, 0, &tmp); if (result) return result; *val = tmp; return count; } static ssize_t nullb_device_bool_attr_store(bool *val, const char *page, size_t count) { bool tmp; int result; result = kstrtobool(page, &tmp); if (result) return result; *val = tmp; return count; } /* The following macro should only be used with TYPE = {uint, ulong, bool}. */ #define NULLB_DEVICE_ATTR(NAME, TYPE) \ static ssize_t \ nullb_device_##NAME##_show(struct config_item *item, char *page) \ { \ return nullb_device_##TYPE##_attr_show( \ to_nullb_device(item)->NAME, page); \ } \ static ssize_t \ nullb_device_##NAME##_store(struct config_item *item, const char *page, \ size_t count) \ { \ if (test_bit(NULLB_DEV_FL_CONFIGURED, &to_nullb_device(item)->flags)) \ return -EBUSY; \ return nullb_device_##TYPE##_attr_store( \ &to_nullb_device(item)->NAME, page, count); \ } \ CONFIGFS_ATTR(nullb_device_, NAME); NULLB_DEVICE_ATTR(size, ulong); NULLB_DEVICE_ATTR(completion_nsec, ulong); NULLB_DEVICE_ATTR(submit_queues, uint); NULLB_DEVICE_ATTR(home_node, uint); NULLB_DEVICE_ATTR(queue_mode, uint); NULLB_DEVICE_ATTR(blocksize, uint); NULLB_DEVICE_ATTR(irqmode, uint); NULLB_DEVICE_ATTR(hw_queue_depth, uint); NULLB_DEVICE_ATTR(index, uint); NULLB_DEVICE_ATTR(use_lightnvm, bool); NULLB_DEVICE_ATTR(blocking, bool); NULLB_DEVICE_ATTR(use_per_node_hctx, bool); NULLB_DEVICE_ATTR(memory_backed, bool); NULLB_DEVICE_ATTR(discard, bool); NULLB_DEVICE_ATTR(mbps, uint); NULLB_DEVICE_ATTR(cache_size, ulong); static ssize_t nullb_device_power_show(struct config_item *item, char *page) { return nullb_device_bool_attr_show(to_nullb_device(item)->power, page); } static ssize_t nullb_device_power_store(struct config_item *item, const char *page, size_t count) { struct nullb_device *dev = to_nullb_device(item); bool newp = false; ssize_t ret; ret = nullb_device_bool_attr_store(&newp, page, count); if (ret < 0) return ret; if (!dev->power && newp) { if (test_and_set_bit(NULLB_DEV_FL_UP, &dev->flags)) return count; if (null_add_dev(dev)) { clear_bit(NULLB_DEV_FL_UP, &dev->flags); return -ENOMEM; } set_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags); dev->power = newp; } else if (dev->power && !newp) { mutex_lock(&lock); dev->power = newp; null_del_dev(dev->nullb); mutex_unlock(&lock); clear_bit(NULLB_DEV_FL_UP, &dev->flags); } return count; } CONFIGFS_ATTR(nullb_device_, power); static ssize_t nullb_device_badblocks_show(struct config_item *item, char *page) { struct nullb_device *t_dev = to_nullb_device(item); return badblocks_show(&t_dev->badblocks, page, 0); } static ssize_t nullb_device_badblocks_store(struct config_item *item, const char *page, size_t count) { struct nullb_device *t_dev = to_nullb_device(item); char *orig, *buf, *tmp; u64 start, end; int ret; orig = kstrndup(page, count, GFP_KERNEL); if (!orig) return -ENOMEM; buf = strstrip(orig); ret = -EINVAL; if (buf[0] != '+' && buf[0] != '-') goto out; tmp = strchr(&buf[1], '-'); if (!tmp) goto out; *tmp = '\0'; ret = kstrtoull(buf + 1, 0, &start); if (ret) goto out; ret = kstrtoull(tmp + 1, 0, &end); if (ret) goto out; ret = -EINVAL; if (start > end) goto out; /* enable badblocks */ cmpxchg(&t_dev->badblocks.shift, -1, 0); if (buf[0] == '+') ret = badblocks_set(&t_dev->badblocks, start, end - start + 1, 1); else ret = badblocks_clear(&t_dev->badblocks, start, end - start + 1); if (ret == 0) ret = count; out: kfree(orig); return ret; } CONFIGFS_ATTR(nullb_device_, badblocks); static struct configfs_attribute *nullb_device_attrs[] = { &nullb_device_attr_size, &nullb_device_attr_completion_nsec, &nullb_device_attr_submit_queues, &nullb_device_attr_home_node, &nullb_device_attr_queue_mode, &nullb_device_attr_blocksize, &nullb_device_attr_irqmode, &nullb_device_attr_hw_queue_depth, &nullb_device_attr_index, &nullb_device_attr_use_lightnvm, &nullb_device_attr_blocking, &nullb_device_attr_use_per_node_hctx, &nullb_device_attr_power, &nullb_device_attr_memory_backed, &nullb_device_attr_discard, &nullb_device_attr_mbps, &nullb_device_attr_cache_size, &nullb_device_attr_badblocks, NULL, }; static void nullb_device_release(struct config_item *item) { struct nullb_device *dev = to_nullb_device(item); null_free_device_storage(dev, false); null_free_dev(dev); } static struct configfs_item_operations nullb_device_ops = { .release = nullb_device_release, }; static struct config_item_type nullb_device_type = { .ct_item_ops = &nullb_device_ops, .ct_attrs = nullb_device_attrs, .ct_owner = THIS_MODULE, }; static struct config_item *nullb_group_make_item(struct config_group *group, const char *name) { struct nullb_device *dev; dev = null_alloc_dev(); if (!dev) return ERR_PTR(-ENOMEM); config_item_init_type_name(&dev->item, name, &nullb_device_type); return &dev->item; } static void nullb_group_drop_item(struct config_group *group, struct config_item *item) { struct nullb_device *dev = to_nullb_device(item); if (test_and_clear_bit(NULLB_DEV_FL_UP, &dev->flags)) { mutex_lock(&lock); dev->power = false; null_del_dev(dev->nullb); mutex_unlock(&lock); } config_item_put(item); } static ssize_t memb_group_features_show(struct config_item *item, char *page) { return snprintf(page, PAGE_SIZE, "memory_backed,discard,bandwidth,cache,badblocks\n"); } CONFIGFS_ATTR_RO(memb_group_, features); static struct configfs_attribute *nullb_group_attrs[] = { &memb_group_attr_features, NULL, }; static struct configfs_group_operations nullb_group_ops = { .make_item = nullb_group_make_item, .drop_item = nullb_group_drop_item, }; static struct config_item_type nullb_group_type = { .ct_group_ops = &nullb_group_ops, .ct_attrs = nullb_group_attrs, .ct_owner = THIS_MODULE, }; static struct configfs_subsystem nullb_subsys = { .su_group = { .cg_item = { .ci_namebuf = "nullb", .ci_type = &nullb_group_type, }, }, }; static inline int null_cache_active(struct nullb *nullb) { return test_bit(NULLB_DEV_FL_CACHE, &nullb->dev->flags); } static struct nullb_device *null_alloc_dev(void) { struct nullb_device *dev; dev = kzalloc(sizeof(*dev), GFP_KERNEL); if (!dev) return NULL; INIT_RADIX_TREE(&dev->data, GFP_ATOMIC); INIT_RADIX_TREE(&dev->cache, GFP_ATOMIC); if (badblocks_init(&dev->badblocks, 0)) { kfree(dev); return NULL; } dev->size = g_gb * 1024; dev->completion_nsec = g_completion_nsec; dev->submit_queues = g_submit_queues; dev->home_node = g_home_node; dev->queue_mode = g_queue_mode; dev->blocksize = g_bs; dev->irqmode = g_irqmode; dev->hw_queue_depth = g_hw_queue_depth; dev->use_lightnvm = g_use_lightnvm; dev->blocking = g_blocking; dev->use_per_node_hctx = g_use_per_node_hctx; return dev; } static void null_free_dev(struct nullb_device *dev) { if (!dev) return; badblocks_exit(&dev->badblocks); kfree(dev); } static void put_tag(struct nullb_queue *nq, unsigned int tag) { clear_bit_unlock(tag, nq->tag_map); if (waitqueue_active(&nq->wait)) wake_up(&nq->wait); } static unsigned int get_tag(struct nullb_queue *nq) { unsigned int tag; do { tag = find_first_zero_bit(nq->tag_map, nq->queue_depth); if (tag >= nq->queue_depth) return -1U; } while (test_and_set_bit_lock(tag, nq->tag_map)); return tag; } static void free_cmd(struct nullb_cmd *cmd) { put_tag(cmd->nq, cmd->tag); } static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer); static struct nullb_cmd *__alloc_cmd(struct nullb_queue *nq) { struct nullb_cmd *cmd; unsigned int tag; tag = get_tag(nq); if (tag != -1U) { cmd = &nq->cmds[tag]; cmd->tag = tag; cmd->error = BLK_STS_OK; cmd->nq = nq; if (nq->dev->irqmode == NULL_IRQ_TIMER) { hrtimer_init(&cmd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); cmd->timer.function = null_cmd_timer_expired; } return cmd; } return NULL; } static struct nullb_cmd *alloc_cmd(struct nullb_queue *nq, int can_wait) { struct nullb_cmd *cmd; DEFINE_WAIT(wait); cmd = __alloc_cmd(nq); if (cmd || !can_wait) return cmd; do { prepare_to_wait(&nq->wait, &wait, TASK_UNINTERRUPTIBLE); cmd = __alloc_cmd(nq); if (cmd) break; io_schedule(); } while (1); finish_wait(&nq->wait, &wait); return cmd; } static void end_cmd(struct nullb_cmd *cmd) { struct request_queue *q = NULL; int queue_mode = cmd->nq->dev->queue_mode; if (cmd->rq) q = cmd->rq->q; switch (queue_mode) { case NULL_Q_MQ: blk_mq_end_request(cmd->rq, cmd->error); return; case NULL_Q_RQ: INIT_LIST_HEAD(&cmd->rq->queuelist); blk_end_request_all(cmd->rq, cmd->error); break; case NULL_Q_BIO: cmd->bio->bi_status = cmd->error; bio_endio(cmd->bio); break; } free_cmd(cmd); /* Restart queue if needed, as we are freeing a tag */ if (queue_mode == NULL_Q_RQ && blk_queue_stopped(q)) { unsigned long flags; spin_lock_irqsave(q->queue_lock, flags); blk_start_queue_async(q); spin_unlock_irqrestore(q->queue_lock, flags); } } static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer) { end_cmd(container_of(timer, struct nullb_cmd, timer)); return HRTIMER_NORESTART; } static void null_cmd_end_timer(struct nullb_cmd *cmd) { ktime_t kt = cmd->nq->dev->completion_nsec; hrtimer_start(&cmd->timer, kt, HRTIMER_MODE_REL); } static void null_softirq_done_fn(struct request *rq) { struct nullb *nullb = rq->q->queuedata; if (nullb->dev->queue_mode == NULL_Q_MQ) end_cmd(blk_mq_rq_to_pdu(rq)); else end_cmd(rq->special); } static struct nullb_page *null_alloc_page(gfp_t gfp_flags) { struct nullb_page *t_page; t_page = kmalloc(sizeof(struct nullb_page), gfp_flags); if (!t_page) goto out; t_page->page = alloc_pages(gfp_flags, 0); if (!t_page->page) goto out_freepage; memset(t_page->bitmap, 0, sizeof(t_page->bitmap)); return t_page; out_freepage: kfree(t_page); out: return NULL; } static void null_free_page(struct nullb_page *t_page) { __set_bit(NULLB_PAGE_FREE, t_page->bitmap); if (test_bit(NULLB_PAGE_LOCK, t_page->bitmap)) return; __free_page(t_page->page); kfree(t_page); } static bool null_page_empty(struct nullb_page *page) { int size = MAP_SZ - 2; return find_first_bit(page->bitmap, size) == size; } static void null_free_sector(struct nullb *nullb, sector_t sector, bool is_cache) { unsigned int sector_bit; u64 idx; struct nullb_page *t_page, *ret; struct radix_tree_root *root; root = is_cache ? &nullb->dev->cache : &nullb->dev->data; idx = sector >> PAGE_SECTORS_SHIFT; sector_bit = (sector & SECTOR_MASK); t_page = radix_tree_lookup(root, idx); if (t_page) { __clear_bit(sector_bit, t_page->bitmap); if (null_page_empty(t_page)) { ret = radix_tree_delete_item(root, idx, t_page); WARN_ON(ret != t_page); null_free_page(ret); if (is_cache) nullb->dev->curr_cache -= PAGE_SIZE; } } } static struct nullb_page *null_radix_tree_insert(struct nullb *nullb, u64 idx, struct nullb_page *t_page, bool is_cache) { struct radix_tree_root *root; root = is_cache ? &nullb->dev->cache : &nullb->dev->data; if (radix_tree_insert(root, idx, t_page)) { null_free_page(t_page); t_page = radix_tree_lookup(root, idx); WARN_ON(!t_page || t_page->page->index != idx); } else if (is_cache) nullb->dev->curr_cache += PAGE_SIZE; return t_page; } static void null_free_device_storage(struct nullb_device *dev, bool is_cache) { unsigned long pos = 0; int nr_pages; struct nullb_page *ret, *t_pages[FREE_BATCH]; struct radix_tree_root *root; root = is_cache ? &dev->cache : &dev->data; do { int i; nr_pages = radix_tree_gang_lookup(root, (void **)t_pages, pos, FREE_BATCH); for (i = 0; i < nr_pages; i++) { pos = t_pages[i]->page->index; ret = radix_tree_delete_item(root, pos, t_pages[i]); WARN_ON(ret != t_pages[i]); null_free_page(ret); } pos++; } while (nr_pages == FREE_BATCH); if (is_cache) dev->curr_cache = 0; } static struct nullb_page *__null_lookup_page(struct nullb *nullb, sector_t sector, bool for_write, bool is_cache) { unsigned int sector_bit; u64 idx; struct nullb_page *t_page; struct radix_tree_root *root; idx = sector >> PAGE_SECTORS_SHIFT; sector_bit = (sector & SECTOR_MASK); root = is_cache ? &nullb->dev->cache : &nullb->dev->data; t_page = radix_tree_lookup(root, idx); WARN_ON(t_page && t_page->page->index != idx); if (t_page && (for_write || test_bit(sector_bit, t_page->bitmap))) return t_page; return NULL; } static struct nullb_page *null_lookup_page(struct nullb *nullb, sector_t sector, bool for_write, bool ignore_cache) { struct nullb_page *page = NULL; if (!ignore_cache) page = __null_lookup_page(nullb, sector, for_write, true); if (page) return page; return __null_lookup_page(nullb, sector, for_write, false); } static struct nullb_page *null_insert_page(struct nullb *nullb, sector_t sector, bool ignore_cache) { u64 idx; struct nullb_page *t_page; t_page = null_lookup_page(nullb, sector, true, ignore_cache); if (t_page) return t_page; spin_unlock_irq(&nullb->lock); t_page = null_alloc_page(GFP_NOIO); if (!t_page) goto out_lock; if (radix_tree_preload(GFP_NOIO)) goto out_freepage; spin_lock_irq(&nullb->lock); idx = sector >> PAGE_SECTORS_SHIFT; t_page->page->index = idx; t_page = null_radix_tree_insert(nullb, idx, t_page, !ignore_cache); radix_tree_preload_end(); return t_page; out_freepage: null_free_page(t_page); out_lock: spin_lock_irq(&nullb->lock); return null_lookup_page(nullb, sector, true, ignore_cache); } static int null_flush_cache_page(struct nullb *nullb, struct nullb_page *c_page) { int i; unsigned int offset; u64 idx; struct nullb_page *t_page, *ret; void *dst, *src; idx = c_page->page->index; t_page = null_insert_page(nullb, idx << PAGE_SECTORS_SHIFT, true); __clear_bit(NULLB_PAGE_LOCK, c_page->bitmap); if (test_bit(NULLB_PAGE_FREE, c_page->bitmap)) { null_free_page(c_page); if (t_page && null_page_empty(t_page)) { ret = radix_tree_delete_item(&nullb->dev->data, idx, t_page); null_free_page(t_page); } return 0; } if (!t_page) return -ENOMEM; src = kmap_atomic(c_page->page); dst = kmap_atomic(t_page->page); for (i = 0; i < PAGE_SECTORS; i += (nullb->dev->blocksize >> SECTOR_SHIFT)) { if (test_bit(i, c_page->bitmap)) { offset = (i << SECTOR_SHIFT); memcpy(dst + offset, src + offset, nullb->dev->blocksize); __set_bit(i, t_page->bitmap); } } kunmap_atomic(dst); kunmap_atomic(src); ret = radix_tree_delete_item(&nullb->dev->cache, idx, c_page); null_free_page(ret); nullb->dev->curr_cache -= PAGE_SIZE; return 0; } static int null_make_cache_space(struct nullb *nullb, unsigned long n) { int i, err, nr_pages; struct nullb_page *c_pages[FREE_BATCH]; unsigned long flushed = 0, one_round; again: if ((nullb->dev->cache_size * 1024 * 1024) > nullb->dev->curr_cache + n || nullb->dev->curr_cache == 0) return 0; nr_pages = radix_tree_gang_lookup(&nullb->dev->cache, (void **)c_pages, nullb->cache_flush_pos, FREE_BATCH); /* * nullb_flush_cache_page could unlock before using the c_pages. To * avoid race, we don't allow page free */ for (i = 0; i < nr_pages; i++) { nullb->cache_flush_pos = c_pages[i]->page->index; /* * We found the page which is being flushed to disk by other * threads */ if (test_bit(NULLB_PAGE_LOCK, c_pages[i]->bitmap)) c_pages[i] = NULL; else __set_bit(NULLB_PAGE_LOCK, c_pages[i]->bitmap); } one_round = 0; for (i = 0; i < nr_pages; i++) { if (c_pages[i] == NULL) continue; err = null_flush_cache_page(nullb, c_pages[i]); if (err) return err; one_round++; } flushed += one_round << PAGE_SHIFT; if (n > flushed) { if (nr_pages == 0) nullb->cache_flush_pos = 0; if (one_round == 0) { /* give other threads a chance */ spin_unlock_irq(&nullb->lock); spin_lock_irq(&nullb->lock); } goto again; } return 0; } static int copy_to_nullb(struct nullb *nullb, struct page *source, unsigned int off, sector_t sector, size_t n, bool is_fua) { size_t temp, count = 0; unsigned int offset; struct nullb_page *t_page; void *dst, *src; while (count < n) { temp = min_t(size_t, nullb->dev->blocksize, n - count); if (null_cache_active(nullb) && !is_fua) null_make_cache_space(nullb, PAGE_SIZE); offset = (sector & SECTOR_MASK) << SECTOR_SHIFT; t_page = null_insert_page(nullb, sector, !null_cache_active(nullb) || is_fua); if (!t_page) return -ENOSPC; src = kmap_atomic(source); dst = kmap_atomic(t_page->page); memcpy(dst + offset, src + off + count, temp); kunmap_atomic(dst); kunmap_atomic(src); __set_bit(sector & SECTOR_MASK, t_page->bitmap); if (is_fua) null_free_sector(nullb, sector, true); count += temp; sector += temp >> SECTOR_SHIFT; } return 0; } static int copy_from_nullb(struct nullb *nullb, struct page *dest, unsigned int off, sector_t sector, size_t n) { size_t temp, count = 0; unsigned int offset; struct nullb_page *t_page; void *dst, *src; while (count < n) { temp = min_t(size_t, nullb->dev->blocksize, n - count); offset = (sector & SECTOR_MASK) << SECTOR_SHIFT; t_page = null_lookup_page(nullb, sector, false, !null_cache_active(nullb)); dst = kmap_atomic(dest); if (!t_page) { memset(dst + off + count, 0, temp); goto next; } src = kmap_atomic(t_page->page); memcpy(dst + off + count, src + offset, temp); kunmap_atomic(src); next: kunmap_atomic(dst); count += temp; sector += temp >> SECTOR_SHIFT; } return 0; } static void null_handle_discard(struct nullb *nullb, sector_t sector, size_t n) { size_t temp; spin_lock_irq(&nullb->lock); while (n > 0) { temp = min_t(size_t, n, nullb->dev->blocksize); null_free_sector(nullb, sector, false); if (null_cache_active(nullb)) null_free_sector(nullb, sector, true); sector += temp >> SECTOR_SHIFT; n -= temp; } spin_unlock_irq(&nullb->lock); } static int null_handle_flush(struct nullb *nullb) { int err; if (!null_cache_active(nullb)) return 0; spin_lock_irq(&nullb->lock); while (true) { err = null_make_cache_space(nullb, nullb->dev->cache_size * 1024 * 1024); if (err || nullb->dev->curr_cache == 0) break; } WARN_ON(!radix_tree_empty(&nullb->dev->cache)); spin_unlock_irq(&nullb->lock); return err; } static int null_transfer(struct nullb *nullb, struct page *page, unsigned int len, unsigned int off, bool is_write, sector_t sector, bool is_fua) { int err = 0; if (!is_write) { err = copy_from_nullb(nullb, page, off, sector, len); flush_dcache_page(page); } else { flush_dcache_page(page); err = copy_to_nullb(nullb, page, off, sector, len, is_fua); } return err; } static int null_handle_rq(struct nullb_cmd *cmd) { struct request *rq = cmd->rq; struct nullb *nullb = cmd->nq->dev->nullb; int err; unsigned int len; sector_t sector; struct req_iterator iter; struct bio_vec bvec; sector = blk_rq_pos(rq); if (req_op(rq) == REQ_OP_DISCARD) { null_handle_discard(nullb, sector, blk_rq_bytes(rq)); return 0; } spin_lock_irq(&nullb->lock); rq_for_each_segment(bvec, rq, iter) { len = bvec.bv_len; err = null_transfer(nullb, bvec.bv_page, len, bvec.bv_offset, op_is_write(req_op(rq)), sector, rq->cmd_flags & REQ_FUA); if (err) { spin_unlock_irq(&nullb->lock); return err; } sector += len >> SECTOR_SHIFT; } spin_unlock_irq(&nullb->lock); return 0; } static int null_handle_bio(struct nullb_cmd *cmd) { struct bio *bio = cmd->bio; struct nullb *nullb = cmd->nq->dev->nullb; int err; unsigned int len; sector_t sector; struct bio_vec bvec; struct bvec_iter iter; sector = bio->bi_iter.bi_sector; if (bio_op(bio) == REQ_OP_DISCARD) { null_handle_discard(nullb, sector, bio_sectors(bio) << SECTOR_SHIFT); return 0; } spin_lock_irq(&nullb->lock); bio_for_each_segment(bvec, bio, iter) { len = bvec.bv_len; err = null_transfer(nullb, bvec.bv_page, len, bvec.bv_offset, op_is_write(bio_op(bio)), sector, bio_op(bio) & REQ_FUA); if (err) { spin_unlock_irq(&nullb->lock); return err; } sector += len >> SECTOR_SHIFT; } spin_unlock_irq(&nullb->lock); return 0; } static void null_stop_queue(struct nullb *nullb) { struct request_queue *q = nullb->q; if (nullb->dev->queue_mode == NULL_Q_MQ) blk_mq_stop_hw_queues(q); else { spin_lock_irq(q->queue_lock); blk_stop_queue(q); spin_unlock_irq(q->queue_lock); } } static void null_restart_queue_async(struct nullb *nullb) { struct request_queue *q = nullb->q; unsigned long flags; if (nullb->dev->queue_mode == NULL_Q_MQ) blk_mq_start_stopped_hw_queues(q, true); else { spin_lock_irqsave(q->queue_lock, flags); blk_start_queue_async(q); spin_unlock_irqrestore(q->queue_lock, flags); } } static blk_status_t null_handle_cmd(struct nullb_cmd *cmd) { struct nullb_device *dev = cmd->nq->dev; struct nullb *nullb = dev->nullb; int err = 0; if (test_bit(NULLB_DEV_FL_THROTTLED, &dev->flags)) { struct request *rq = cmd->rq; if (!hrtimer_active(&nullb->bw_timer)) hrtimer_restart(&nullb->bw_timer); if (atomic_long_sub_return(blk_rq_bytes(rq), &nullb->cur_bytes) < 0) { null_stop_queue(nullb); /* race with timer */ if (atomic_long_read(&nullb->cur_bytes) > 0) null_restart_queue_async(nullb); if (dev->queue_mode == NULL_Q_RQ) { struct request_queue *q = nullb->q; spin_lock_irq(q->queue_lock); rq->rq_flags |= RQF_DONTPREP; blk_requeue_request(q, rq); spin_unlock_irq(q->queue_lock); return BLK_STS_OK; } else /* requeue request */ return BLK_STS_RESOURCE; } } if (nullb->dev->badblocks.shift != -1) { int bad_sectors; sector_t sector, size, first_bad; bool is_flush = true; if (dev->queue_mode == NULL_Q_BIO && bio_op(cmd->bio) != REQ_OP_FLUSH) { is_flush = false; sector = cmd->bio->bi_iter.bi_sector; size = bio_sectors(cmd->bio); } if (dev->queue_mode != NULL_Q_BIO && req_op(cmd->rq) != REQ_OP_FLUSH) { is_flush = false; sector = blk_rq_pos(cmd->rq); size = blk_rq_sectors(cmd->rq); } if (!is_flush && badblocks_check(&nullb->dev->badblocks, sector, size, &first_bad, &bad_sectors)) { cmd->error = BLK_STS_IOERR; goto out; } } if (dev->memory_backed) { if (dev->queue_mode == NULL_Q_BIO) { if (bio_op(cmd->bio) == REQ_OP_FLUSH) err = null_handle_flush(nullb); else err = null_handle_bio(cmd); } else { if (req_op(cmd->rq) == REQ_OP_FLUSH) err = null_handle_flush(nullb); else err = null_handle_rq(cmd); } } cmd->error = errno_to_blk_status(err); out: /* Complete IO by inline, softirq or timer */ switch (dev->irqmode) { case NULL_IRQ_SOFTIRQ: switch (dev->queue_mode) { case NULL_Q_MQ: blk_mq_complete_request(cmd->rq); break; case NULL_Q_RQ: blk_complete_request(cmd->rq); break; case NULL_Q_BIO: /* * XXX: no proper submitting cpu information available. */ end_cmd(cmd); break; } break; case NULL_IRQ_NONE: end_cmd(cmd); break; case NULL_IRQ_TIMER: null_cmd_end_timer(cmd); break; } return BLK_STS_OK; } static enum hrtimer_restart nullb_bwtimer_fn(struct hrtimer *timer) { struct nullb *nullb = container_of(timer, struct nullb, bw_timer); ktime_t timer_interval = ktime_set(0, TIMER_INTERVAL); unsigned int mbps = nullb->dev->mbps; if (atomic_long_read(&nullb->cur_bytes) == mb_per_tick(mbps)) return HRTIMER_NORESTART; atomic_long_set(&nullb->cur_bytes, mb_per_tick(mbps)); null_restart_queue_async(nullb); hrtimer_forward_now(&nullb->bw_timer, timer_interval); return HRTIMER_RESTART; } static void nullb_setup_bwtimer(struct nullb *nullb) { ktime_t timer_interval = ktime_set(0, TIMER_INTERVAL); hrtimer_init(&nullb->bw_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); nullb->bw_timer.function = nullb_bwtimer_fn; atomic_long_set(&nullb->cur_bytes, mb_per_tick(nullb->dev->mbps)); hrtimer_start(&nullb->bw_timer, timer_interval, HRTIMER_MODE_REL); } static struct nullb_queue *nullb_to_queue(struct nullb *nullb) { int index = 0; if (nullb->nr_queues != 1) index = raw_smp_processor_id() / ((nr_cpu_ids + nullb->nr_queues - 1) / nullb->nr_queues); return &nullb->queues[index]; } static blk_qc_t null_queue_bio(struct request_queue *q, struct bio *bio) { struct nullb *nullb = q->queuedata; struct nullb_queue *nq = nullb_to_queue(nullb); struct nullb_cmd *cmd; cmd = alloc_cmd(nq, 1); cmd->bio = bio; null_handle_cmd(cmd); return BLK_QC_T_NONE; } static int null_rq_prep_fn(struct request_queue *q, struct request *req) { struct nullb *nullb = q->queuedata; struct nullb_queue *nq = nullb_to_queue(nullb); struct nullb_cmd *cmd; cmd = alloc_cmd(nq, 0); if (cmd) { cmd->rq = req; req->special = cmd; return BLKPREP_OK; } blk_stop_queue(q); return BLKPREP_DEFER; } static void null_request_fn(struct request_queue *q) { struct request *rq; while ((rq = blk_fetch_request(q)) != NULL) { struct nullb_cmd *cmd = rq->special; spin_unlock_irq(q->queue_lock); null_handle_cmd(cmd); spin_lock_irq(q->queue_lock); } } static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { struct nullb_cmd *cmd = blk_mq_rq_to_pdu(bd->rq); struct nullb_queue *nq = hctx->driver_data; might_sleep_if(hctx->flags & BLK_MQ_F_BLOCKING); if (nq->dev->irqmode == NULL_IRQ_TIMER) { hrtimer_init(&cmd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); cmd->timer.function = null_cmd_timer_expired; } cmd->rq = bd->rq; cmd->error = BLK_STS_OK; cmd->nq = nq; blk_mq_start_request(bd->rq); return null_handle_cmd(cmd); } static const struct blk_mq_ops null_mq_ops = { .queue_rq = null_queue_rq, .complete = null_softirq_done_fn, }; static void cleanup_queue(struct nullb_queue *nq) { kfree(nq->tag_map); kfree(nq->cmds); } static void cleanup_queues(struct nullb *nullb) { int i; for (i = 0; i < nullb->nr_queues; i++) cleanup_queue(&nullb->queues[i]); kfree(nullb->queues); } #ifdef CONFIG_NVM static void null_lnvm_end_io(struct request *rq, blk_status_t status) { struct nvm_rq *rqd = rq->end_io_data; /* XXX: lighnvm core seems to expect NVM_RSP_* values here.. */ rqd->error = status ? -EIO : 0; nvm_end_io(rqd); blk_put_request(rq); } static int null_lnvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd) { struct request_queue *q = dev->q; struct request *rq; struct bio *bio = rqd->bio; rq = blk_mq_alloc_request(q, op_is_write(bio_op(bio)) ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0); if (IS_ERR(rq)) return -ENOMEM; blk_init_request_from_bio(rq, bio); rq->end_io_data = rqd; blk_execute_rq_nowait(q, NULL, rq, 0, null_lnvm_end_io); return 0; } static int null_lnvm_id(struct nvm_dev *dev, struct nvm_id *id) { struct nullb *nullb = dev->q->queuedata; sector_t size = (sector_t)nullb->dev->size * 1024 * 1024ULL; sector_t blksize; struct nvm_id_group *grp; id->ver_id = 0x1; id->vmnt = 0; id->cap = 0x2; id->dom = 0x1; id->ppaf.blk_offset = 0; id->ppaf.blk_len = 16; id->ppaf.pg_offset = 16; id->ppaf.pg_len = 16; id->ppaf.sect_offset = 32; id->ppaf.sect_len = 8; id->ppaf.pln_offset = 40; id->ppaf.pln_len = 8; id->ppaf.lun_offset = 48; id->ppaf.lun_len = 8; id->ppaf.ch_offset = 56; id->ppaf.ch_len = 8; sector_div(size, nullb->dev->blocksize); /* convert size to pages */ size >>= 8; /* concert size to pgs pr blk */ grp = &id->grp; grp->mtype = 0; grp->fmtype = 0; grp->num_ch = 1; grp->num_pg = 256; blksize = size; size >>= 16; grp->num_lun = size + 1; sector_div(blksize, grp->num_lun); grp->num_blk = blksize; grp->num_pln = 1; grp->fpg_sz = nullb->dev->blocksize; grp->csecs = nullb->dev->blocksize; grp->trdt = 25000; grp->trdm = 25000; grp->tprt = 500000; grp->tprm = 500000; grp->tbet = 1500000; grp->tbem = 1500000; grp->mpos = 0x010101; /* single plane rwe */ grp->cpar = nullb->dev->hw_queue_depth; return 0; } static void *null_lnvm_create_dma_pool(struct nvm_dev *dev, char *name) { mempool_t *virtmem_pool; virtmem_pool = mempool_create_slab_pool(64, ppa_cache); if (!virtmem_pool) { pr_err("null_blk: Unable to create virtual memory pool\n"); return NULL; } return virtmem_pool; } static void null_lnvm_destroy_dma_pool(void *pool) { mempool_destroy(pool); } static void *null_lnvm_dev_dma_alloc(struct nvm_dev *dev, void *pool, gfp_t mem_flags, dma_addr_t *dma_handler) { return mempool_alloc(pool, mem_flags); } static void null_lnvm_dev_dma_free(void *pool, void *entry, dma_addr_t dma_handler) { mempool_free(entry, pool); } static struct nvm_dev_ops null_lnvm_dev_ops = { .identity = null_lnvm_id, .submit_io = null_lnvm_submit_io, .create_dma_pool = null_lnvm_create_dma_pool, .destroy_dma_pool = null_lnvm_destroy_dma_pool, .dev_dma_alloc = null_lnvm_dev_dma_alloc, .dev_dma_free = null_lnvm_dev_dma_free, /* Simulate nvme protocol restriction */ .max_phys_sect = 64, }; static int null_nvm_register(struct nullb *nullb) { struct nvm_dev *dev; int rv; dev = nvm_alloc_dev(0); if (!dev) return -ENOMEM; dev->q = nullb->q; memcpy(dev->name, nullb->disk_name, DISK_NAME_LEN); dev->ops = &null_lnvm_dev_ops; rv = nvm_register(dev); if (rv) { kfree(dev); return rv; } nullb->ndev = dev; return 0; } static void null_nvm_unregister(struct nullb *nullb) { nvm_unregister(nullb->ndev); } #else static int null_nvm_register(struct nullb *nullb) { pr_err("null_blk: CONFIG_NVM needs to be enabled for LightNVM\n"); return -EINVAL; } static void null_nvm_unregister(struct nullb *nullb) {} #endif /* CONFIG_NVM */ static void null_del_dev(struct nullb *nullb) { struct nullb_device *dev; if (!nullb) return; dev = nullb->dev; ida_simple_remove(&nullb_indexes, nullb->index); list_del_init(&nullb->list); if (dev->use_lightnvm) null_nvm_unregister(nullb); else del_gendisk(nullb->disk); if (test_bit(NULLB_DEV_FL_THROTTLED, &nullb->dev->flags)) { hrtimer_cancel(&nullb->bw_timer); atomic_long_set(&nullb->cur_bytes, LONG_MAX); null_restart_queue_async(nullb); } blk_cleanup_queue(nullb->q); if (dev->queue_mode == NULL_Q_MQ && nullb->tag_set == &nullb->__tag_set) blk_mq_free_tag_set(nullb->tag_set); if (!dev->use_lightnvm) put_disk(nullb->disk); cleanup_queues(nullb); if (null_cache_active(nullb)) null_free_device_storage(nullb->dev, true); kfree(nullb); dev->nullb = NULL; } static void null_config_discard(struct nullb *nullb) { if (nullb->dev->discard == false) return; nullb->q->limits.discard_granularity = nullb->dev->blocksize; nullb->q->limits.discard_alignment = nullb->dev->blocksize; blk_queue_max_discard_sectors(nullb->q, UINT_MAX >> 9); queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, nullb->q); } static int null_open(struct block_device *bdev, fmode_t mode) { return 0; } static void null_release(struct gendisk *disk, fmode_t mode) { } static const struct block_device_operations null_fops = { .owner = THIS_MODULE, .open = null_open, .release = null_release, }; static void null_init_queue(struct nullb *nullb, struct nullb_queue *nq) { BUG_ON(!nullb); BUG_ON(!nq); init_waitqueue_head(&nq->wait); nq->queue_depth = nullb->queue_depth; nq->dev = nullb->dev; } static void null_init_queues(struct nullb *nullb) { struct request_queue *q = nullb->q; struct blk_mq_hw_ctx *hctx; struct nullb_queue *nq; int i; queue_for_each_hw_ctx(q, hctx, i) { if (!hctx->nr_ctx || !hctx->tags) continue; nq = &nullb->queues[i]; hctx->driver_data = nq; null_init_queue(nullb, nq); nullb->nr_queues++; } } static int setup_commands(struct nullb_queue *nq) { struct nullb_cmd *cmd; int i, tag_size; nq->cmds = kzalloc(nq->queue_depth * sizeof(*cmd), GFP_KERNEL); if (!nq->cmds) return -ENOMEM; tag_size = ALIGN(nq->queue_depth, BITS_PER_LONG) / BITS_PER_LONG; nq->tag_map = kzalloc(tag_size * sizeof(unsigned long), GFP_KERNEL); if (!nq->tag_map) { kfree(nq->cmds); return -ENOMEM; } for (i = 0; i < nq->queue_depth; i++) { cmd = &nq->cmds[i]; INIT_LIST_HEAD(&cmd->list); cmd->ll_list.next = NULL; cmd->tag = -1U; } return 0; } static int setup_queues(struct nullb *nullb) { nullb->queues = kzalloc(nullb->dev->submit_queues * sizeof(struct nullb_queue), GFP_KERNEL); if (!nullb->queues) return -ENOMEM; nullb->nr_queues = 0; nullb->queue_depth = nullb->dev->hw_queue_depth; return 0; } static int init_driver_queues(struct nullb *nullb) { struct nullb_queue *nq; int i, ret = 0; for (i = 0; i < nullb->dev->submit_queues; i++) { nq = &nullb->queues[i]; null_init_queue(nullb, nq); ret = setup_commands(nq); if (ret) return ret; nullb->nr_queues++; } return 0; } static int null_gendisk_register(struct nullb *nullb) { struct gendisk *disk; sector_t size; disk = nullb->disk = alloc_disk_node(1, nullb->dev->home_node); if (!disk) return -ENOMEM; size = (sector_t)nullb->dev->size * 1024 * 1024ULL; set_capacity(disk, size >> 9); disk->flags |= GENHD_FL_EXT_DEVT | GENHD_FL_SUPPRESS_PARTITION_INFO; disk->major = null_major; disk->first_minor = nullb->index; disk->fops = &null_fops; disk->private_data = nullb; disk->queue = nullb->q; strncpy(disk->disk_name, nullb->disk_name, DISK_NAME_LEN); add_disk(disk); return 0; } static int null_init_tag_set(struct nullb *nullb, struct blk_mq_tag_set *set) { set->ops = &null_mq_ops; set->nr_hw_queues = nullb ? nullb->dev->submit_queues : g_submit_queues; set->queue_depth = nullb ? nullb->dev->hw_queue_depth : g_hw_queue_depth; set->numa_node = nullb ? nullb->dev->home_node : g_home_node; set->cmd_size = sizeof(struct nullb_cmd); set->flags = BLK_MQ_F_SHOULD_MERGE; set->driver_data = NULL; if ((nullb && nullb->dev->blocking) || g_blocking) set->flags |= BLK_MQ_F_BLOCKING; return blk_mq_alloc_tag_set(set); } static void null_validate_conf(struct nullb_device *dev) { dev->blocksize = round_down(dev->blocksize, 512); dev->blocksize = clamp_t(unsigned int, dev->blocksize, 512, 4096); if (dev->use_lightnvm && dev->blocksize != 4096) dev->blocksize = 4096; if (dev->use_lightnvm && dev->queue_mode != NULL_Q_MQ) dev->queue_mode = NULL_Q_MQ; if (dev->queue_mode == NULL_Q_MQ && dev->use_per_node_hctx) { if (dev->submit_queues != nr_online_nodes) dev->submit_queues = nr_online_nodes; } else if (dev->submit_queues > nr_cpu_ids) dev->submit_queues = nr_cpu_ids; else if (dev->submit_queues == 0) dev->submit_queues = 1; dev->queue_mode = min_t(unsigned int, dev->queue_mode, NULL_Q_MQ); dev->irqmode = min_t(unsigned int, dev->irqmode, NULL_IRQ_TIMER); /* Do memory allocation, so set blocking */ if (dev->memory_backed) dev->blocking = true; else /* cache is meaningless */ dev->cache_size = 0; dev->cache_size = min_t(unsigned long, ULONG_MAX / 1024 / 1024, dev->cache_size); dev->mbps = min_t(unsigned int, 1024 * 40, dev->mbps); /* can not stop a queue */ if (dev->queue_mode == NULL_Q_BIO) dev->mbps = 0; } static int null_add_dev(struct nullb_device *dev) { struct nullb *nullb; int rv; null_validate_conf(dev); nullb = kzalloc_node(sizeof(*nullb), GFP_KERNEL, dev->home_node); if (!nullb) { rv = -ENOMEM; goto out; } nullb->dev = dev; dev->nullb = nullb; spin_lock_init(&nullb->lock); rv = setup_queues(nullb); if (rv) goto out_free_nullb; if (dev->queue_mode == NULL_Q_MQ) { if (shared_tags) { nullb->tag_set = &tag_set; rv = 0; } else { nullb->tag_set = &nullb->__tag_set; rv = null_init_tag_set(nullb, nullb->tag_set); } if (rv) goto out_cleanup_queues; nullb->q = blk_mq_init_queue(nullb->tag_set); if (IS_ERR(nullb->q)) { rv = -ENOMEM; goto out_cleanup_tags; } null_init_queues(nullb); } else if (dev->queue_mode == NULL_Q_BIO) { nullb->q = blk_alloc_queue_node(GFP_KERNEL, dev->home_node); if (!nullb->q) { rv = -ENOMEM; goto out_cleanup_queues; } blk_queue_make_request(nullb->q, null_queue_bio); rv = init_driver_queues(nullb); if (rv) goto out_cleanup_blk_queue; } else { nullb->q = blk_init_queue_node(null_request_fn, &nullb->lock, dev->home_node); if (!nullb->q) { rv = -ENOMEM; goto out_cleanup_queues; } blk_queue_prep_rq(nullb->q, null_rq_prep_fn); blk_queue_softirq_done(nullb->q, null_softirq_done_fn); rv = init_driver_queues(nullb); if (rv) goto out_cleanup_blk_queue; } if (dev->mbps) { set_bit(NULLB_DEV_FL_THROTTLED, &dev->flags); nullb_setup_bwtimer(nullb); } if (dev->cache_size > 0) { set_bit(NULLB_DEV_FL_CACHE, &nullb->dev->flags); blk_queue_write_cache(nullb->q, true, true); blk_queue_flush_queueable(nullb->q, true); } nullb->q->queuedata = nullb; queue_flag_set_unlocked(QUEUE_FLAG_NONROT, nullb->q); queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, nullb->q); mutex_lock(&lock); nullb->index = ida_simple_get(&nullb_indexes, 0, 0, GFP_KERNEL); dev->index = nullb->index; mutex_unlock(&lock); blk_queue_logical_block_size(nullb->q, dev->blocksize); blk_queue_physical_block_size(nullb->q, dev->blocksize); null_config_discard(nullb); sprintf(nullb->disk_name, "nullb%d", nullb->index); if (dev->use_lightnvm) rv = null_nvm_register(nullb); else rv = null_gendisk_register(nullb); if (rv) goto out_cleanup_blk_queue; mutex_lock(&lock); list_add_tail(&nullb->list, &nullb_list); mutex_unlock(&lock); return 0; out_cleanup_blk_queue: blk_cleanup_queue(nullb->q); out_cleanup_tags: if (dev->queue_mode == NULL_Q_MQ && nullb->tag_set == &nullb->__tag_set) blk_mq_free_tag_set(nullb->tag_set); out_cleanup_queues: cleanup_queues(nullb); out_free_nullb: kfree(nullb); dev->nullb = NULL; out: return rv; } static int __init null_init(void) { int ret = 0; unsigned int i; struct nullb *nullb; struct nullb_device *dev; if (g_bs > PAGE_SIZE) { pr_warn("null_blk: invalid block size\n"); pr_warn("null_blk: defaults block size to %lu\n", PAGE_SIZE); g_bs = PAGE_SIZE; } if (g_use_lightnvm && g_bs != 4096) { pr_warn("null_blk: LightNVM only supports 4k block size\n"); pr_warn("null_blk: defaults block size to 4k\n"); g_bs = 4096; } if (g_use_lightnvm && g_queue_mode != NULL_Q_MQ) { pr_warn("null_blk: LightNVM only supported for blk-mq\n"); pr_warn("null_blk: defaults queue mode to blk-mq\n"); g_queue_mode = NULL_Q_MQ; } if (g_queue_mode == NULL_Q_MQ && g_use_per_node_hctx) { if (g_submit_queues != nr_online_nodes) { pr_warn("null_blk: submit_queues param is set to %u.\n", nr_online_nodes); g_submit_queues = nr_online_nodes; } } else if (g_submit_queues > nr_cpu_ids) g_submit_queues = nr_cpu_ids; else if (g_submit_queues <= 0) g_submit_queues = 1; if (g_queue_mode == NULL_Q_MQ && shared_tags) { ret = null_init_tag_set(NULL, &tag_set); if (ret) return ret; } config_group_init(&nullb_subsys.su_group); mutex_init(&nullb_subsys.su_mutex); ret = configfs_register_subsystem(&nullb_subsys); if (ret) goto err_tagset; mutex_init(&lock); null_major = register_blkdev(0, "nullb"); if (null_major < 0) { ret = null_major; goto err_conf; } if (g_use_lightnvm) { ppa_cache = kmem_cache_create("ppa_cache", 64 * sizeof(u64), 0, 0, NULL); if (!ppa_cache) { pr_err("null_blk: unable to create ppa cache\n"); ret = -ENOMEM; goto err_ppa; } } for (i = 0; i < nr_devices; i++) { dev = null_alloc_dev(); if (!dev) { ret = -ENOMEM; goto err_dev; } ret = null_add_dev(dev); if (ret) { null_free_dev(dev); goto err_dev; } } pr_info("null: module loaded\n"); return 0; err_dev: while (!list_empty(&nullb_list)) { nullb = list_entry(nullb_list.next, struct nullb, list); dev = nullb->dev; null_del_dev(nullb); null_free_dev(dev); } kmem_cache_destroy(ppa_cache); err_ppa: unregister_blkdev(null_major, "nullb"); err_conf: configfs_unregister_subsystem(&nullb_subsys); err_tagset: if (g_queue_mode == NULL_Q_MQ && shared_tags) blk_mq_free_tag_set(&tag_set); return ret; } static void __exit null_exit(void) { struct nullb *nullb; configfs_unregister_subsystem(&nullb_subsys); unregister_blkdev(null_major, "nullb"); mutex_lock(&lock); while (!list_empty(&nullb_list)) { struct nullb_device *dev; nullb = list_entry(nullb_list.next, struct nullb, list); dev = nullb->dev; null_del_dev(nullb); null_free_dev(dev); } mutex_unlock(&lock); if (g_queue_mode == NULL_Q_MQ && shared_tags) blk_mq_free_tag_set(&tag_set); kmem_cache_destroy(ppa_cache); } module_init(null_init); module_exit(null_exit); MODULE_AUTHOR("Jens Axboe <axboe@kernel.dk>"); MODULE_LICENSE("GPL"); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 | /* * Copyright (C) 2007 Oracle. All rights reserved. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public * License v2 as published by the Free Software Foundation. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * General Public License for more details. * * You should have received a copy of the GNU General Public * License along with this program; if not, write to the * Free Software Foundation, Inc., 59 Temple Place - Suite 330, * Boston, MA 021110-1307, USA. */ #ifndef __HASH__ #define __HASH__ int __init btrfs_hash_init(void); void btrfs_hash_exit(void); const char* btrfs_crc32c_impl(void); u32 btrfs_crc32c(u32 crc, const void *address, unsigned int length); static inline u64 btrfs_name_hash(const char *name, int len) { return btrfs_crc32c((u32)~1, name, len); } /* * Figure the key offset of an extended inode ref */ static inline u64 btrfs_extref_hash(u64 parent_objectid, const char *name, int len) { return (u64) btrfs_crc32c(parent_objectid, name, len); } #endif |
| 102 102 81 81 81 81 81 100 5 5 1 102 102 101 102 102 102 102 102 50 102 50 50 102 102 102 102 102 106 32 106 106 35 30 35 124 124 124 124 102 102 102 102 81 80 81 80 80 63 63 62 24 24 24 24 24 24 24 29 29 62 20 92 92 88 44 44 92 88 92 102 102 100 43 39 43 43 39 4 102 102 100 92 88 44 44 100 82 82 102 102 102 102 50 50 42 102 102 99 100 82 100 102 102 42 102 102 102 100 61 46 46 26 104 102 100 100 100 101 88 104 91 91 91 91 91 91 126 126 126 126 126 90 126 74 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 | /* * Copyright 2000 by Hans Reiser, licensing governed by reiserfs/README */ /* Reiserfs block (de)allocator, bitmap-based. */ #include <linux/time.h> #include "reiserfs.h" #include <linux/errno.h> #include <linux/buffer_head.h> #include <linux/kernel.h> #include <linux/pagemap.h> #include <linux/vmalloc.h> #include <linux/quotaops.h> #include <linux/seq_file.h> #define PREALLOCATION_SIZE 9 /* different reiserfs block allocator options */ #define SB_ALLOC_OPTS(s) (REISERFS_SB(s)->s_alloc_options.bits) #define _ALLOC_concentrating_formatted_nodes 0 #define _ALLOC_displacing_large_files 1 #define _ALLOC_displacing_new_packing_localities 2 #define _ALLOC_old_hashed_relocation 3 #define _ALLOC_new_hashed_relocation 4 #define _ALLOC_skip_busy 5 #define _ALLOC_displace_based_on_dirid 6 #define _ALLOC_hashed_formatted_nodes 7 #define _ALLOC_old_way 8 #define _ALLOC_hundredth_slices 9 #define _ALLOC_dirid_groups 10 #define _ALLOC_oid_groups 11 #define _ALLOC_packing_groups 12 #define concentrating_formatted_nodes(s) test_bit(_ALLOC_concentrating_formatted_nodes, &SB_ALLOC_OPTS(s)) #define displacing_large_files(s) test_bit(_ALLOC_displacing_large_files, &SB_ALLOC_OPTS(s)) #define displacing_new_packing_localities(s) test_bit(_ALLOC_displacing_new_packing_localities, &SB_ALLOC_OPTS(s)) #define SET_OPTION(optname) \ do { \ reiserfs_info(s, "block allocator option \"%s\" is set", #optname); \ set_bit(_ALLOC_ ## optname , &SB_ALLOC_OPTS(s)); \ } while(0) #define TEST_OPTION(optname, s) \ test_bit(_ALLOC_ ## optname , &SB_ALLOC_OPTS(s)) static inline void get_bit_address(struct super_block *s, b_blocknr_t block, unsigned int *bmap_nr, unsigned int *offset) { /* * It is in the bitmap block number equal to the block * number divided by the number of bits in a block. */ *bmap_nr = block >> (s->s_blocksize_bits + 3); /* Within that bitmap block it is located at bit offset *offset. */ *offset = block & ((s->s_blocksize << 3) - 1); } int is_reusable(struct super_block *s, b_blocknr_t block, int bit_value) { unsigned int bmap, offset; unsigned int bmap_count = reiserfs_bmap_count(s); if (block == 0 || block >= SB_BLOCK_COUNT(s)) { reiserfs_error(s, "vs-4010", "block number is out of range %lu (%u)", block, SB_BLOCK_COUNT(s)); return 0; } get_bit_address(s, block, &bmap, &offset); /* * Old format filesystem? Unlikely, but the bitmaps are all * up front so we need to account for it. */ if (unlikely(test_bit(REISERFS_OLD_FORMAT, &REISERFS_SB(s)->s_properties))) { b_blocknr_t bmap1 = REISERFS_SB(s)->s_sbh->b_blocknr + 1; if (block >= bmap1 && block <= bmap1 + bmap_count) { reiserfs_error(s, "vs-4019", "bitmap block %lu(%u) " "can't be freed or reused", block, bmap_count); return 0; } } else { if (offset == 0) { reiserfs_error(s, "vs-4020", "bitmap block %lu(%u) " "can't be freed or reused", block, bmap_count); return 0; } } if (bmap >= bmap_count) { reiserfs_error(s, "vs-4030", "bitmap for requested block " "is out of range: block=%lu, bitmap_nr=%u", block, bmap); return 0; } if (bit_value == 0 && block == SB_ROOT_BLOCK(s)) { reiserfs_error(s, "vs-4050", "this is root block (%u), " "it must be busy", SB_ROOT_BLOCK(s)); return 0; } return 1; } /* * Searches in journal structures for a given block number (bmap, off). * If block is found in reiserfs journal it suggests next free block * candidate to test. */ static inline int is_block_in_journal(struct super_block *s, unsigned int bmap, int off, int *next) { b_blocknr_t tmp; if (reiserfs_in_journal(s, bmap, off, 1, &tmp)) { if (tmp) { /* hint supplied */ *next = tmp; PROC_INFO_INC(s, scan_bitmap.in_journal_hint); } else { (*next) = off + 1; /* inc offset to avoid looping. */ PROC_INFO_INC(s, scan_bitmap.in_journal_nohint); } PROC_INFO_INC(s, scan_bitmap.retry); return 1; } return 0; } /* * Searches for a window of zero bits with given minimum and maximum * lengths in one bitmap block */ static int scan_bitmap_block(struct reiserfs_transaction_handle *th, unsigned int bmap_n, int *beg, int boundary, int min, int max, int unfm) { struct super_block *s = th->t_super; struct reiserfs_bitmap_info *bi = &SB_AP_BITMAP(s)[bmap_n]; struct buffer_head *bh; int end, next; int org = *beg; BUG_ON(!th->t_trans_id); RFALSE(bmap_n >= reiserfs_bmap_count(s), "Bitmap %u is out of " "range (0..%u)", bmap_n, reiserfs_bmap_count(s) - 1); PROC_INFO_INC(s, scan_bitmap.bmap); if (!bi) { reiserfs_error(s, "jdm-4055", "NULL bitmap info pointer " "for bitmap %d", bmap_n); return 0; } bh = reiserfs_read_bitmap_block(s, bmap_n); if (bh == NULL) return 0; while (1) { cont: if (bi->free_count < min) { brelse(bh); return 0; /* No free blocks in this bitmap */ } /* search for a first zero bit -- beginning of a window */ *beg = reiserfs_find_next_zero_le_bit ((unsigned long *)(bh->b_data), boundary, *beg); /* * search for a zero bit fails or the rest of bitmap block * cannot contain a zero window of minimum size */ if (*beg + min > boundary) { brelse(bh); return 0; } if (unfm && is_block_in_journal(s, bmap_n, *beg, beg)) continue; /* first zero bit found; we check next bits */ for (end = *beg + 1;; end++) { if (end >= *beg + max || end >= boundary || reiserfs_test_le_bit(end, bh->b_data)) { next = end; break; } /* * finding the other end of zero bit window requires * looking into journal structures (in case of * searching for free blocks for unformatted nodes) */ if (unfm && is_block_in_journal(s, bmap_n, end, &next)) break; } /* * now (*beg) points to beginning of zero bits window, * (end) points to one bit after the window end */ /* found window of proper size */ if (end - *beg >= min) { int i; reiserfs_prepare_for_journal(s, bh, 1); /* * try to set all blocks used checking are * they still free */ for (i = *beg; i < end; i++) { /* Don't check in journal again. */ if (reiserfs_test_and_set_le_bit (i, bh->b_data)) { /* * bit was set by another process while * we slept in prepare_for_journal() */ PROC_INFO_INC(s, scan_bitmap.stolen); /* * we can continue with smaller set * of allocated blocks, if length of * this set is more or equal to `min' */ if (i >= *beg + min) { end = i; break; } /* * otherwise we clear all bit * were set ... */ while (--i >= *beg) reiserfs_clear_le_bit (i, bh->b_data); reiserfs_restore_prepared_buffer(s, bh); *beg = org; /* * Search again in current block * from beginning */ goto cont; } } bi->free_count -= (end - *beg); journal_mark_dirty(th, bh); brelse(bh); /* free block count calculation */ reiserfs_prepare_for_journal(s, SB_BUFFER_WITH_SB(s), 1); PUT_SB_FREE_BLOCKS(s, SB_FREE_BLOCKS(s) - (end - *beg)); journal_mark_dirty(th, SB_BUFFER_WITH_SB(s)); return end - (*beg); } else { *beg = next; } } } static int bmap_hash_id(struct super_block *s, u32 id) { char *hash_in = NULL; unsigned long hash; unsigned bm; if (id <= 2) { bm = 1; } else { hash_in = (char *)(&id); hash = keyed_hash(hash_in, 4); bm = hash % reiserfs_bmap_count(s); if (!bm) bm = 1; } /* this can only be true when SB_BMAP_NR = 1 */ if (bm >= reiserfs_bmap_count(s)) bm = 0; return bm; } /* * hashes the id and then returns > 0 if the block group for the * corresponding hash is full */ static inline int block_group_used(struct super_block *s, u32 id) { int bm = bmap_hash_id(s, id); struct reiserfs_bitmap_info *info = &SB_AP_BITMAP(s)[bm]; /* * If we don't have cached information on this bitmap block, we're * going to have to load it later anyway. Loading it here allows us * to make a better decision. This favors long-term performance gain * with a better on-disk layout vs. a short term gain of skipping the * read and potentially having a bad placement. */ if (info->free_count == UINT_MAX) { struct buffer_head *bh = reiserfs_read_bitmap_block(s, bm); brelse(bh); } if (info->free_count > ((s->s_blocksize << 3) * 60 / 100)) { return 0; } return 1; } /* * the packing is returned in disk byte order */ __le32 reiserfs_choose_packing(struct inode * dir) { __le32 packing; if (TEST_OPTION(packing_groups, dir->i_sb)) { u32 parent_dir = le32_to_cpu(INODE_PKEY(dir)->k_dir_id); /* * some versions of reiserfsck expect packing locality 1 to be * special */ if (parent_dir == 1 || block_group_used(dir->i_sb, parent_dir)) packing = INODE_PKEY(dir)->k_objectid; else packing = INODE_PKEY(dir)->k_dir_id; } else packing = INODE_PKEY(dir)->k_objectid; return packing; } /* * Tries to find contiguous zero bit window (given size) in given region of * bitmap and place new blocks there. Returns number of allocated blocks. */ static int scan_bitmap(struct reiserfs_transaction_handle *th, b_blocknr_t * start, b_blocknr_t finish, int min, int max, int unfm, sector_t file_block) { int nr_allocated = 0; struct super_block *s = th->t_super; unsigned int bm, off; unsigned int end_bm, end_off; unsigned int off_max = s->s_blocksize << 3; BUG_ON(!th->t_trans_id); PROC_INFO_INC(s, scan_bitmap.call); /* No point in looking for more free blocks */ if (SB_FREE_BLOCKS(s) <= 0) return 0; get_bit_address(s, *start, &bm, &off); get_bit_address(s, finish, &end_bm, &end_off); if (bm > reiserfs_bmap_count(s)) return 0; if (end_bm > reiserfs_bmap_count(s)) end_bm = reiserfs_bmap_count(s); /* * When the bitmap is more than 10% free, anyone can allocate. * When it's less than 10% free, only files that already use the * bitmap are allowed. Once we pass 80% full, this restriction * is lifted. * * We do this so that files that grow later still have space close to * their original allocation. This improves locality, and presumably * performance as a result. * * This is only an allocation policy and does not make up for getting a * bad hint. Decent hinting must be implemented for this to work well. */ if (TEST_OPTION(skip_busy, s) && SB_FREE_BLOCKS(s) > SB_BLOCK_COUNT(s) / 20) { for (; bm < end_bm; bm++, off = 0) { if ((off && (!unfm || (file_block != 0))) || SB_AP_BITMAP(s)[bm].free_count > (s->s_blocksize << 3) / 10) nr_allocated = scan_bitmap_block(th, bm, &off, off_max, min, max, unfm); if (nr_allocated) goto ret; } /* we know from above that start is a reasonable number */ get_bit_address(s, *start, &bm, &off); } for (; bm < end_bm; bm++, off = 0) { nr_allocated = scan_bitmap_block(th, bm, &off, off_max, min, max, unfm); if (nr_allocated) goto ret; } nr_allocated = scan_bitmap_block(th, bm, &off, end_off + 1, min, max, unfm); ret: *start = bm * off_max + off; return nr_allocated; } static void _reiserfs_free_block(struct reiserfs_transaction_handle *th, struct inode *inode, b_blocknr_t block, int for_unformatted) { struct super_block *s = th->t_super; struct reiserfs_super_block *rs; struct buffer_head *sbh, *bmbh; struct reiserfs_bitmap_info *apbi; unsigned int nr, offset; BUG_ON(!th->t_trans_id); PROC_INFO_INC(s, free_block); rs = SB_DISK_SUPER_BLOCK(s); sbh = SB_BUFFER_WITH_SB(s); apbi = SB_AP_BITMAP(s); get_bit_address(s, block, &nr, &offset); if (nr >= reiserfs_bmap_count(s)) { reiserfs_error(s, "vs-4075", "block %lu is out of range", block); return; } bmbh = reiserfs_read_bitmap_block(s, nr); if (!bmbh) return; reiserfs_prepare_for_journal(s, bmbh, 1); /* clear bit for the given block in bit map */ if (!reiserfs_test_and_clear_le_bit(offset, bmbh->b_data)) { reiserfs_error(s, "vs-4080", "block %lu: bit already cleared", block); } apbi[nr].free_count++; journal_mark_dirty(th, bmbh); brelse(bmbh); reiserfs_prepare_for_journal(s, sbh, 1); /* update super block */ set_sb_free_blocks(rs, sb_free_blocks(rs) + 1); journal_mark_dirty(th, sbh); if (for_unformatted) { int depth = reiserfs_write_unlock_nested(s); dquot_free_block_nodirty(inode, 1); reiserfs_write_lock_nested(s, depth); } } void reiserfs_free_block(struct reiserfs_transaction_handle *th, struct inode *inode, b_blocknr_t block, int for_unformatted) { struct super_block *s = th->t_super; BUG_ON(!th->t_trans_id); RFALSE(!s, "vs-4061: trying to free block on nonexistent device"); if (!is_reusable(s, block, 1)) return; if (block > sb_block_count(REISERFS_SB(s)->s_rs)) { reiserfs_error(th->t_super, "bitmap-4072", "Trying to free block outside file system " "boundaries (%lu > %lu)", block, sb_block_count(REISERFS_SB(s)->s_rs)); return; } /* mark it before we clear it, just in case */ journal_mark_freed(th, s, block); _reiserfs_free_block(th, inode, block, for_unformatted); } /* preallocated blocks don't need to be run through journal_mark_freed */ static void reiserfs_free_prealloc_block(struct reiserfs_transaction_handle *th, struct inode *inode, b_blocknr_t block) { BUG_ON(!th->t_trans_id); RFALSE(!th->t_super, "vs-4060: trying to free block on nonexistent device"); if (!is_reusable(th->t_super, block, 1)) return; _reiserfs_free_block(th, inode, block, 1); } static void __discard_prealloc(struct reiserfs_transaction_handle *th, struct reiserfs_inode_info *ei) { unsigned long save = ei->i_prealloc_block; int dirty = 0; struct inode *inode = &ei->vfs_inode; BUG_ON(!th->t_trans_id); #ifdef CONFIG_REISERFS_CHECK if (ei->i_prealloc_count < 0) reiserfs_error(th->t_super, "zam-4001", "inode has negative prealloc blocks count."); #endif while (ei->i_prealloc_count > 0) { b_blocknr_t block_to_free; /* * reiserfs_free_prealloc_block can drop the write lock, * which could allow another caller to free the same block. * We can protect against it by modifying the prealloc * state before calling it. */ block_to_free = ei->i_prealloc_block++; ei->i_prealloc_count--; reiserfs_free_prealloc_block(th, inode, block_to_free); dirty = 1; } if (dirty) reiserfs_update_sd(th, inode); ei->i_prealloc_block = save; list_del_init(&ei->i_prealloc_list); } /* FIXME: It should be inline function */ void reiserfs_discard_prealloc(struct reiserfs_transaction_handle *th, struct inode *inode) { struct reiserfs_inode_info *ei = REISERFS_I(inode); BUG_ON(!th->t_trans_id); if (ei->i_prealloc_count) __discard_prealloc(th, ei); } void reiserfs_discard_all_prealloc(struct reiserfs_transaction_handle *th) { struct list_head *plist = &SB_JOURNAL(th->t_super)->j_prealloc_list; BUG_ON(!th->t_trans_id); while (!list_empty(plist)) { struct reiserfs_inode_info *ei; ei = list_entry(plist->next, struct reiserfs_inode_info, i_prealloc_list); #ifdef CONFIG_REISERFS_CHECK if (!ei->i_prealloc_count) { reiserfs_error(th->t_super, "zam-4001", "inode is in prealloc list but has " "no preallocated blocks."); } #endif __discard_prealloc(th, ei); } } void reiserfs_init_alloc_options(struct super_block *s) { set_bit(_ALLOC_skip_busy, &SB_ALLOC_OPTS(s)); set_bit(_ALLOC_dirid_groups, &SB_ALLOC_OPTS(s)); set_bit(_ALLOC_packing_groups, &SB_ALLOC_OPTS(s)); } /* block allocator related options are parsed here */ int reiserfs_parse_alloc_options(struct super_block *s, char *options) { char *this_char, *value; /* clear default settings */ REISERFS_SB(s)->s_alloc_options.bits = 0; while ((this_char = strsep(&options, ":")) != NULL) { if ((value = strchr(this_char, '=')) != NULL) *value++ = 0; if (!strcmp(this_char, "concentrating_formatted_nodes")) { int temp; SET_OPTION(concentrating_formatted_nodes); temp = (value && *value) ? simple_strtoul(value, &value, 0) : 10; if (temp <= 0 || temp > 100) { REISERFS_SB(s)->s_alloc_options.border = 10; } else { REISERFS_SB(s)->s_alloc_options.border = 100 / temp; } continue; } if (!strcmp(this_char, "displacing_large_files")) { SET_OPTION(displacing_large_files); REISERFS_SB(s)->s_alloc_options.large_file_size = (value && *value) ? simple_strtoul(value, &value, 0) : 16; continue; } if (!strcmp(this_char, "displacing_new_packing_localities")) { SET_OPTION(displacing_new_packing_localities); continue; } if (!strcmp(this_char, "old_hashed_relocation")) { SET_OPTION(old_hashed_relocation); continue; } if (!strcmp(this_char, "new_hashed_relocation")) { SET_OPTION(new_hashed_relocation); continue; } if (!strcmp(this_char, "dirid_groups")) { SET_OPTION(dirid_groups); continue; } if (!strcmp(this_char, "oid_groups")) { SET_OPTION(oid_groups); continue; } if (!strcmp(this_char, "packing_groups")) { SET_OPTION(packing_groups); continue; } if (!strcmp(this_char, "hashed_formatted_nodes")) { SET_OPTION(hashed_formatted_nodes); continue; } if (!strcmp(this_char, "skip_busy")) { SET_OPTION(skip_busy); continue; } if (!strcmp(this_char, "hundredth_slices")) { SET_OPTION(hundredth_slices); continue; } if (!strcmp(this_char, "old_way")) { SET_OPTION(old_way); continue; } if (!strcmp(this_char, "displace_based_on_dirid")) { SET_OPTION(displace_based_on_dirid); continue; } if (!strcmp(this_char, "preallocmin")) { REISERFS_SB(s)->s_alloc_options.preallocmin = (value && *value) ? simple_strtoul(value, &value, 0) : 4; continue; } if (!strcmp(this_char, "preallocsize")) { REISERFS_SB(s)->s_alloc_options.preallocsize = (value && *value) ? simple_strtoul(value, &value, 0) : PREALLOCATION_SIZE; continue; } reiserfs_warning(s, "zam-4001", "unknown option - %s", this_char); return 1; } reiserfs_info(s, "allocator options = [%08x]\n", SB_ALLOC_OPTS(s)); return 0; } static void print_sep(struct seq_file *seq, int *first) { if (!*first) seq_puts(seq, ":"); else *first = 0; } void show_alloc_options(struct seq_file *seq, struct super_block *s) { int first = 1; if (SB_ALLOC_OPTS(s) == ((1 << _ALLOC_skip_busy) | (1 << _ALLOC_dirid_groups) | (1 << _ALLOC_packing_groups))) return; seq_puts(seq, ",alloc="); if (TEST_OPTION(concentrating_formatted_nodes, s)) { print_sep(seq, &first); if (REISERFS_SB(s)->s_alloc_options.border != 10) { seq_printf(seq, "concentrating_formatted_nodes=%d", 100 / REISERFS_SB(s)->s_alloc_options.border); } else seq_puts(seq, "concentrating_formatted_nodes"); } if (TEST_OPTION(displacing_large_files, s)) { print_sep(seq, &first); if (REISERFS_SB(s)->s_alloc_options.large_file_size != 16) { seq_printf(seq, "displacing_large_files=%lu", REISERFS_SB(s)->s_alloc_options.large_file_size); } else seq_puts(seq, "displacing_large_files"); } if (TEST_OPTION(displacing_new_packing_localities, s)) { print_sep(seq, &first); seq_puts(seq, "displacing_new_packing_localities"); } if (TEST_OPTION(old_hashed_relocation, s)) { print_sep(seq, &first); seq_puts(seq, "old_hashed_relocation"); } if (TEST_OPTION(new_hashed_relocation, s)) { print_sep(seq, &first); seq_puts(seq, "new_hashed_relocation"); } if (TEST_OPTION(dirid_groups, s)) { print_sep(seq, &first); seq_puts(seq, "dirid_groups"); } if (TEST_OPTION(oid_groups, s)) { print_sep(seq, &first); seq_puts(seq, "oid_groups"); } if (TEST_OPTION(packing_groups, s)) { print_sep(seq, &first); seq_puts(seq, "packing_groups"); } if (TEST_OPTION(hashed_formatted_nodes, s)) { print_sep(seq, &first); seq_puts(seq, "hashed_formatted_nodes"); } if (TEST_OPTION(skip_busy, s)) { print_sep(seq, &first); seq_puts(seq, "skip_busy"); } if (TEST_OPTION(hundredth_slices, s)) { print_sep(seq, &first); seq_puts(seq, "hundredth_slices"); } if (TEST_OPTION(old_way, s)) { print_sep(seq, &first); seq_puts(seq, "old_way"); } if (TEST_OPTION(displace_based_on_dirid, s)) { print_sep(seq, &first); seq_puts(seq, "displace_based_on_dirid"); } if (REISERFS_SB(s)->s_alloc_options.preallocmin != 0) { print_sep(seq, &first); seq_printf(seq, "preallocmin=%d", REISERFS_SB(s)->s_alloc_options.preallocmin); } if (REISERFS_SB(s)->s_alloc_options.preallocsize != 17) { print_sep(seq, &first); seq_printf(seq, "preallocsize=%d", REISERFS_SB(s)->s_alloc_options.preallocsize); } } static inline void new_hashed_relocation(reiserfs_blocknr_hint_t * hint) { char *hash_in; if (hint->formatted_node) { hash_in = (char *)&hint->key.k_dir_id; } else { if (!hint->inode) { /*hint->search_start = hint->beg;*/ hash_in = (char *)&hint->key.k_dir_id; } else if (TEST_OPTION(displace_based_on_dirid, hint->th->t_super)) hash_in = (char *)(&INODE_PKEY(hint->inode)->k_dir_id); else hash_in = (char *)(&INODE_PKEY(hint->inode)->k_objectid); } hint->search_start = hint->beg + keyed_hash(hash_in, 4) % (hint->end - hint->beg); } /* * Relocation based on dirid, hashing them into a given bitmap block * files. Formatted nodes are unaffected, a separate policy covers them */ static void dirid_groups(reiserfs_blocknr_hint_t * hint) { unsigned long hash; __u32 dirid = 0; int bm = 0; struct super_block *sb = hint->th->t_super; if (hint->inode) dirid = le32_to_cpu(INODE_PKEY(hint->inode)->k_dir_id); else if (hint->formatted_node) dirid = hint->key.k_dir_id; if (dirid) { bm = bmap_hash_id(sb, dirid); hash = bm * (sb->s_blocksize << 3); /* give a portion of the block group to metadata */ if (hint->inode) hash += sb->s_blocksize / 2; hint->search_start = hash; } } /* * Relocation based on oid, hashing them into a given bitmap block * files. Formatted nodes are unaffected, a separate policy covers them */ static void oid_groups(reiserfs_blocknr_hint_t * hint) { if (hint->inode) { unsigned long hash; __u32 oid; __u32 dirid; int bm; dirid = le32_to_cpu(INODE_PKEY(hint->inode)->k_dir_id); /* * keep the root dir and it's first set of subdirs close to * the start of the disk */ if (dirid <= 2) hash = (hint->inode->i_sb->s_blocksize << 3); else { oid = le32_to_cpu(INODE_PKEY(hint->inode)->k_objectid); bm = bmap_hash_id(hint->inode->i_sb, oid); hash = bm * (hint->inode->i_sb->s_blocksize << 3); } hint->search_start = hash; } } /* * returns 1 if it finds an indirect item and gets valid hint info * from it, otherwise 0 */ static int get_left_neighbor(reiserfs_blocknr_hint_t * hint) { struct treepath *path; struct buffer_head *bh; struct item_head *ih; int pos_in_item; __le32 *item; int ret = 0; /* * reiserfs code can call this function w/o pointer to path * structure supplied; then we rely on supplied search_start */ if (!hint->path) return 0; path = hint->path; bh = get_last_bh(path); RFALSE(!bh, "green-4002: Illegal path specified to get_left_neighbor"); ih = tp_item_head(path); pos_in_item = path->pos_in_item; item = tp_item_body(path); hint->search_start = bh->b_blocknr; /* * for indirect item: go to left and look for the first non-hole entry * in the indirect item */ if (!hint->formatted_node && is_indirect_le_ih(ih)) { if (pos_in_item == I_UNFM_NUM(ih)) pos_in_item--; while (pos_in_item >= 0) { int t = get_block_num(item, pos_in_item); if (t) { hint->search_start = t; ret = 1; break; } pos_in_item--; } } /* does result value fit into specified region? */ return ret; } /* * should be, if formatted node, then try to put on first part of the device * specified as number of percent with mount option device, else try to put * on last of device. This is not to say it is good code to do so, * but the effect should be measured. */ static inline void set_border_in_hint(struct super_block *s, reiserfs_blocknr_hint_t * hint) { b_blocknr_t border = SB_BLOCK_COUNT(s) / REISERFS_SB(s)->s_alloc_options.border; if (hint->formatted_node) hint->end = border - 1; else hint->beg = border; } static inline void displace_large_file(reiserfs_blocknr_hint_t * hint) { if (TEST_OPTION(displace_based_on_dirid, hint->th->t_super)) hint->search_start = hint->beg + keyed_hash((char *)(&INODE_PKEY(hint->inode)->k_dir_id), 4) % (hint->end - hint->beg); else hint->search_start = hint->beg + keyed_hash((char *)(&INODE_PKEY(hint->inode)->k_objectid), 4) % (hint->end - hint->beg); } static inline void hash_formatted_node(reiserfs_blocknr_hint_t * hint) { char *hash_in; if (!hint->inode) hash_in = (char *)&hint->key.k_dir_id; else if (TEST_OPTION(displace_based_on_dirid, hint->th->t_super)) hash_in = (char *)(&INODE_PKEY(hint->inode)->k_dir_id); else hash_in = (char *)(&INODE_PKEY(hint->inode)->k_objectid); hint->search_start = hint->beg + keyed_hash(hash_in, 4) % (hint->end - hint->beg); } static inline int this_blocknr_allocation_would_make_it_a_large_file(reiserfs_blocknr_hint_t * hint) { return hint->block == REISERFS_SB(hint->th->t_super)->s_alloc_options.large_file_size; } #ifdef DISPLACE_NEW_PACKING_LOCALITIES static inline void displace_new_packing_locality(reiserfs_blocknr_hint_t * hint) { struct in_core_key *key = &hint->key; hint->th->displace_new_blocks = 0; hint->search_start = hint->beg + keyed_hash((char *)(&key->k_objectid), 4) % (hint->end - hint->beg); } #endif static inline int old_hashed_relocation(reiserfs_blocknr_hint_t * hint) { b_blocknr_t border; u32 hash_in; if (hint->formatted_node || hint->inode == NULL) { return 0; } hash_in = le32_to_cpu((INODE_PKEY(hint->inode))->k_dir_id); border = hint->beg + (u32) keyed_hash(((char *)(&hash_in)), 4) % (hint->end - hint->beg - 1); if (border > hint->search_start) hint->search_start = border; return 1; } static inline int old_way(reiserfs_blocknr_hint_t * hint) { b_blocknr_t border; if (hint->formatted_node || hint->inode == NULL) { return 0; } border = hint->beg + le32_to_cpu(INODE_PKEY(hint->inode)->k_dir_id) % (hint->end - hint->beg); if (border > hint->search_start) hint->search_start = border; return 1; } static inline void hundredth_slices(reiserfs_blocknr_hint_t * hint) { struct in_core_key *key = &hint->key; b_blocknr_t slice_start; slice_start = (keyed_hash((char *)(&key->k_dir_id), 4) % 100) * (hint->end / 100); if (slice_start > hint->search_start || slice_start + (hint->end / 100) <= hint->search_start) { hint->search_start = slice_start; } } static void determine_search_start(reiserfs_blocknr_hint_t * hint, int amount_needed) { struct super_block *s = hint->th->t_super; int unfm_hint; hint->beg = 0; hint->end = SB_BLOCK_COUNT(s) - 1; /* This is former border algorithm. Now with tunable border offset */ if (concentrating_formatted_nodes(s)) set_border_in_hint(s, hint); #ifdef DISPLACE_NEW_PACKING_LOCALITIES /* * whenever we create a new directory, we displace it. At first * we will hash for location, later we might look for a moderately * empty place for it */ if (displacing_new_packing_localities(s) && hint->th->displace_new_blocks) { displace_new_packing_locality(hint); /* * we do not continue determine_search_start, * if new packing locality is being displaced */ return; } #endif /* * all persons should feel encouraged to add more special cases * here and test them */ if (displacing_large_files(s) && !hint->formatted_node && this_blocknr_allocation_would_make_it_a_large_file(hint)) { displace_large_file(hint); return; } /* * if none of our special cases is relevant, use the left * neighbor in the tree order of the new node we are allocating for */ if (hint->formatted_node && TEST_OPTION(hashed_formatted_nodes, s)) { hash_formatted_node(hint); return; } unfm_hint = get_left_neighbor(hint); /* * Mimic old block allocator behaviour, that is if VFS allowed for * preallocation, new blocks are displaced based on directory ID. * Also, if suggested search_start is less than last preallocated * block, we start searching from it, assuming that HDD dataflow * is faster in forward direction */ if (TEST_OPTION(old_way, s)) { if (!hint->formatted_node) { if (!reiserfs_hashed_relocation(s)) old_way(hint); else if (!reiserfs_no_unhashed_relocation(s)) old_hashed_relocation(hint); if (hint->inode && hint->search_start < REISERFS_I(hint->inode)->i_prealloc_block) hint->search_start = REISERFS_I(hint->inode)->i_prealloc_block; } return; } /* This is an approach proposed by Hans */ if (TEST_OPTION(hundredth_slices, s) && !(displacing_large_files(s) && !hint->formatted_node)) { hundredth_slices(hint); return; } /* old_hashed_relocation only works on unformatted */ if (!unfm_hint && !hint->formatted_node && TEST_OPTION(old_hashed_relocation, s)) { old_hashed_relocation(hint); } /* new_hashed_relocation works with both formatted/unformatted nodes */ if ((!unfm_hint || hint->formatted_node) && TEST_OPTION(new_hashed_relocation, s)) { new_hashed_relocation(hint); } /* dirid grouping works only on unformatted nodes */ if (!unfm_hint && !hint->formatted_node && TEST_OPTION(dirid_groups, s)) { dirid_groups(hint); } #ifdef DISPLACE_NEW_PACKING_LOCALITIES if (hint->formatted_node && TEST_OPTION(dirid_groups, s)) { dirid_groups(hint); } #endif /* oid grouping works only on unformatted nodes */ if (!unfm_hint && !hint->formatted_node && TEST_OPTION(oid_groups, s)) { oid_groups(hint); } return; } static int determine_prealloc_size(reiserfs_blocknr_hint_t * hint) { /* make minimum size a mount option and benchmark both ways */ /* we preallocate blocks only for regular files, specific size */ /* benchmark preallocating always and see what happens */ hint->prealloc_size = 0; if (!hint->formatted_node && hint->preallocate) { if (S_ISREG(hint->inode->i_mode) && !IS_PRIVATE(hint->inode) && hint->inode->i_size >= REISERFS_SB(hint->th->t_super)->s_alloc_options. preallocmin * hint->inode->i_sb->s_blocksize) hint->prealloc_size = REISERFS_SB(hint->th->t_super)->s_alloc_options. preallocsize - 1; } return CARRY_ON; } static inline int allocate_without_wrapping_disk(reiserfs_blocknr_hint_t * hint, b_blocknr_t * new_blocknrs, b_blocknr_t start, b_blocknr_t finish, int min, int amount_needed, int prealloc_size) { int rest = amount_needed; int nr_allocated; while (rest > 0 && start <= finish) { nr_allocated = scan_bitmap(hint->th, &start, finish, min, rest + prealloc_size, !hint->formatted_node, hint->block); if (nr_allocated == 0) /* no new blocks allocated, return */ break; /* fill free_blocknrs array first */ while (rest > 0 && nr_allocated > 0) { *new_blocknrs++ = start++; rest--; nr_allocated--; } /* do we have something to fill prealloc. array also ? */ if (nr_allocated > 0) { /* * it means prealloc_size was greater that 0 and * we do preallocation */ list_add(&REISERFS_I(hint->inode)->i_prealloc_list, &SB_JOURNAL(hint->th->t_super)-> j_prealloc_list); REISERFS_I(hint->inode)->i_prealloc_block = start; REISERFS_I(hint->inode)->i_prealloc_count = nr_allocated; break; } } return (amount_needed - rest); } static inline int blocknrs_and_prealloc_arrays_from_search_start (reiserfs_blocknr_hint_t * hint, b_blocknr_t * new_blocknrs, int amount_needed) { struct super_block *s = hint->th->t_super; b_blocknr_t start = hint->search_start; b_blocknr_t finish = SB_BLOCK_COUNT(s) - 1; int passno = 0; int nr_allocated = 0; int depth; determine_prealloc_size(hint); if (!hint->formatted_node) { int quota_ret; #ifdef REISERQUOTA_DEBUG reiserfs_debug(s, REISERFS_DEBUG_CODE, "reiserquota: allocating %d blocks id=%u", amount_needed, hint->inode->i_uid); #endif depth = reiserfs_write_unlock_nested(s); quota_ret = dquot_alloc_block_nodirty(hint->inode, amount_needed); if (quota_ret) { /* Quota exceeded? */ reiserfs_write_lock_nested(s, depth); return QUOTA_EXCEEDED; } if (hint->preallocate && hint->prealloc_size) { #ifdef REISERQUOTA_DEBUG reiserfs_debug(s, REISERFS_DEBUG_CODE, "reiserquota: allocating (prealloc) %d blocks id=%u", hint->prealloc_size, hint->inode->i_uid); #endif quota_ret = dquot_prealloc_block_nodirty(hint->inode, hint->prealloc_size); if (quota_ret) hint->preallocate = hint->prealloc_size = 0; } /* for unformatted nodes, force large allocations */ reiserfs_write_lock_nested(s, depth); } do { switch (passno++) { case 0: /* Search from hint->search_start to end of disk */ start = hint->search_start; finish = SB_BLOCK_COUNT(s) - 1; break; case 1: /* Search from hint->beg to hint->search_start */ start = hint->beg; finish = hint->search_start; break; case 2: /* Last chance: Search from 0 to hint->beg */ start = 0; finish = hint->beg; break; default: /* We've tried searching everywhere, not enough space */ /* Free the blocks */ if (!hint->formatted_node) { #ifdef REISERQUOTA_DEBUG reiserfs_debug(s, REISERFS_DEBUG_CODE, "reiserquota: freeing (nospace) %d blocks id=%u", amount_needed + hint->prealloc_size - nr_allocated, hint->inode->i_uid); #endif /* Free not allocated blocks */ depth = reiserfs_write_unlock_nested(s); dquot_free_block_nodirty(hint->inode, amount_needed + hint->prealloc_size - nr_allocated); reiserfs_write_lock_nested(s, depth); } while (nr_allocated--) reiserfs_free_block(hint->th, hint->inode, new_blocknrs[nr_allocated], !hint->formatted_node); return NO_DISK_SPACE; } } while ((nr_allocated += allocate_without_wrapping_disk(hint, new_blocknrs + nr_allocated, start, finish, 1, amount_needed - nr_allocated, hint-> prealloc_size)) < amount_needed); if (!hint->formatted_node && amount_needed + hint->prealloc_size > nr_allocated + REISERFS_I(hint->inode)->i_prealloc_count) { /* Some of preallocation blocks were not allocated */ #ifdef REISERQUOTA_DEBUG reiserfs_debug(s, REISERFS_DEBUG_CODE, "reiserquota: freeing (failed prealloc) %d blocks id=%u", amount_needed + hint->prealloc_size - nr_allocated - REISERFS_I(hint->inode)->i_prealloc_count, hint->inode->i_uid); #endif depth = reiserfs_write_unlock_nested(s); dquot_free_block_nodirty(hint->inode, amount_needed + hint->prealloc_size - nr_allocated - REISERFS_I(hint->inode)-> i_prealloc_count); reiserfs_write_lock_nested(s, depth); } return CARRY_ON; } /* grab new blocknrs from preallocated list */ /* return amount still needed after using them */ static int use_preallocated_list_if_available(reiserfs_blocknr_hint_t * hint, b_blocknr_t * new_blocknrs, int amount_needed) { struct inode *inode = hint->inode; if (REISERFS_I(inode)->i_prealloc_count > 0) { while (amount_needed) { *new_blocknrs++ = REISERFS_I(inode)->i_prealloc_block++; REISERFS_I(inode)->i_prealloc_count--; amount_needed--; if (REISERFS_I(inode)->i_prealloc_count <= 0) { list_del(&REISERFS_I(inode)->i_prealloc_list); break; } } } /* return amount still needed after using preallocated blocks */ return amount_needed; } int reiserfs_allocate_blocknrs(reiserfs_blocknr_hint_t *hint, b_blocknr_t *new_blocknrs, int amount_needed, /* Amount of blocks we have already reserved */ int reserved_by_us) { int initial_amount_needed = amount_needed; int ret; struct super_block *s = hint->th->t_super; /* Check if there is enough space, taking into account reserved space */ if (SB_FREE_BLOCKS(s) - REISERFS_SB(s)->reserved_blocks < amount_needed - reserved_by_us) return NO_DISK_SPACE; /* should this be if !hint->inode && hint->preallocate? */ /* do you mean hint->formatted_node can be removed ? - Zam */ /* * hint->formatted_node cannot be removed because we try to access * inode information here, and there is often no inode associated with * metadata allocations - green */ if (!hint->formatted_node && hint->preallocate) { amount_needed = use_preallocated_list_if_available (hint, new_blocknrs, amount_needed); /* * We have all the block numbers we need from the * prealloc list */ if (amount_needed == 0) return CARRY_ON; new_blocknrs += (initial_amount_needed - amount_needed); } /* find search start and save it in hint structure */ determine_search_start(hint, amount_needed); if (hint->search_start >= SB_BLOCK_COUNT(s)) hint->search_start = SB_BLOCK_COUNT(s) - 1; /* allocation itself; fill new_blocknrs and preallocation arrays */ ret = blocknrs_and_prealloc_arrays_from_search_start (hint, new_blocknrs, amount_needed); /* * We used prealloc. list to fill (partially) new_blocknrs array. * If final allocation fails we need to return blocks back to * prealloc. list or just free them. -- Zam (I chose second * variant) */ if (ret != CARRY_ON) { while (amount_needed++ < initial_amount_needed) { reiserfs_free_block(hint->th, hint->inode, *(--new_blocknrs), 1); } } return ret; } void reiserfs_cache_bitmap_metadata(struct super_block *sb, struct buffer_head *bh, struct reiserfs_bitmap_info *info) { unsigned long *cur = (unsigned long *)(bh->b_data + bh->b_size); /* The first bit must ALWAYS be 1 */ if (!reiserfs_test_le_bit(0, (unsigned long *)bh->b_data)) reiserfs_error(sb, "reiserfs-2025", "bitmap block %lu is " "corrupted: first bit must be 1", bh->b_blocknr); info->free_count = 0; while (--cur >= (unsigned long *)bh->b_data) { /* 0 and ~0 are special, we can optimize for them */ if (*cur == 0) info->free_count += BITS_PER_LONG; else if (*cur != ~0L) /* A mix, investigate */ info->free_count += BITS_PER_LONG - hweight_long(*cur); } } struct buffer_head *reiserfs_read_bitmap_block(struct super_block *sb, unsigned int bitmap) { b_blocknr_t block = (sb->s_blocksize << 3) * bitmap; struct reiserfs_bitmap_info *info = SB_AP_BITMAP(sb) + bitmap; struct buffer_head *bh; /* * Way old format filesystems had the bitmaps packed up front. * I doubt there are any of these left, but just in case... */ if (unlikely(test_bit(REISERFS_OLD_FORMAT, &REISERFS_SB(sb)->s_properties))) block = REISERFS_SB(sb)->s_sbh->b_blocknr + 1 + bitmap; else if (bitmap == 0) block = (REISERFS_DISK_OFFSET_IN_BYTES >> sb->s_blocksize_bits) + 1; bh = sb_bread(sb, block); if (bh == NULL) reiserfs_warning(sb, "sh-2029: %s: bitmap block (#%u) " "reading failed", __func__, block); else { if (buffer_locked(bh)) { int depth; PROC_INFO_INC(sb, scan_bitmap.wait); depth = reiserfs_write_unlock_nested(sb); __wait_on_buffer(bh); reiserfs_write_lock_nested(sb, depth); } BUG_ON(!buffer_uptodate(bh)); BUG_ON(atomic_read(&bh->b_count) == 0); if (info->free_count == UINT_MAX) reiserfs_cache_bitmap_metadata(sb, bh, info); } return bh; } int reiserfs_init_bitmap_cache(struct super_block *sb) { struct reiserfs_bitmap_info *bitmap; unsigned int bmap_nr = reiserfs_bmap_count(sb); bitmap = vmalloc(sizeof(*bitmap) * bmap_nr); if (bitmap == NULL) return -ENOMEM; memset(bitmap, 0xff, sizeof(*bitmap) * bmap_nr); SB_AP_BITMAP(sb) = bitmap; return 0; } void reiserfs_free_bitmap_cache(struct super_block *sb) { if (SB_AP_BITMAP(sb)) { vfree(SB_AP_BITMAP(sb)); SB_AP_BITMAP(sb) = NULL; } } |
| 211 211 210 259 250 251 259 6 1 5 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/fs.h> #include <linux/quota.h> #include <linux/export.h> /** * qid_eq - Test to see if to kquid values are the same * @left: A qid value * @right: Another quid value * * Return true if the two qid values are equal and false otherwise. */ bool qid_eq(struct kqid left, struct kqid right) { if (left.type != right.type) return false; switch(left.type) { case USRQUOTA: return uid_eq(left.uid, right.uid); case GRPQUOTA: return gid_eq(left.gid, right.gid); case PRJQUOTA: return projid_eq(left.projid, right.projid); default: BUG(); } } EXPORT_SYMBOL(qid_eq); /** * qid_lt - Test to see if one qid value is less than another * @left: The possibly lesser qid value * @right: The possibly greater qid value * * Return true if left is less than right and false otherwise. */ bool qid_lt(struct kqid left, struct kqid right) { if (left.type < right.type) return true; if (left.type > right.type) return false; switch (left.type) { case USRQUOTA: return uid_lt(left.uid, right.uid); case GRPQUOTA: return gid_lt(left.gid, right.gid); case PRJQUOTA: return projid_lt(left.projid, right.projid); default: BUG(); } } EXPORT_SYMBOL(qid_lt); /** * from_kqid - Create a qid from a kqid user-namespace pair. * @targ: The user namespace we want a qid in. * @kqid: The kernel internal quota identifier to start with. * * Map @kqid into the user-namespace specified by @targ and * return the resulting qid. * * There is always a mapping into the initial user_namespace. * * If @kqid has no mapping in @targ (qid_t)-1 is returned. */ qid_t from_kqid(struct user_namespace *targ, struct kqid kqid) { switch (kqid.type) { case USRQUOTA: return from_kuid(targ, kqid.uid); case GRPQUOTA: return from_kgid(targ, kqid.gid); case PRJQUOTA: return from_kprojid(targ, kqid.projid); default: BUG(); } } EXPORT_SYMBOL(from_kqid); /** * from_kqid_munged - Create a qid from a kqid user-namespace pair. * @targ: The user namespace we want a qid in. * @kqid: The kernel internal quota identifier to start with. * * Map @kqid into the user-namespace specified by @targ and * return the resulting qid. * * There is always a mapping into the initial user_namespace. * * Unlike from_kqid from_kqid_munged never fails and always * returns a valid projid. This makes from_kqid_munged * appropriate for use in places where failing to provide * a qid_t is not a good option. * * If @kqid has no mapping in @targ the kqid.type specific * overflow identifier is returned. */ qid_t from_kqid_munged(struct user_namespace *targ, struct kqid kqid) { switch (kqid.type) { case USRQUOTA: return from_kuid_munged(targ, kqid.uid); case GRPQUOTA: return from_kgid_munged(targ, kqid.gid); case PRJQUOTA: return from_kprojid_munged(targ, kqid.projid); default: BUG(); } } EXPORT_SYMBOL(from_kqid_munged); /** * qid_valid - Report if a valid value is stored in a kqid. * @qid: The kernel internal quota identifier to test. */ bool qid_valid(struct kqid qid) { switch (qid.type) { case USRQUOTA: return uid_valid(qid.uid); case GRPQUOTA: return gid_valid(qid.gid); case PRJQUOTA: return projid_valid(qid.projid); default: BUG(); } } EXPORT_SYMBOL(qid_valid); |
| 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/cpufreq.h> #include <linux/fs.h> #include <linux/init.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> __weak void arch_freq_prepare_all(void) { } extern const struct seq_operations cpuinfo_op; static int cpuinfo_open(struct inode *inode, struct file *file) { arch_freq_prepare_all(); return seq_open(file, &cpuinfo_op); } static const struct file_operations proc_cpuinfo_operations = { .open = cpuinfo_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; static int __init proc_cpuinfo_init(void) { proc_create("cpuinfo", 0, NULL, &proc_cpuinfo_operations); return 0; } fs_initcall(proc_cpuinfo_init); |
| 29 66 1166 1149 1107 1104 70 69 54 30 1126 90 3 3 3 3 3 983 982 3 977 978 979 480 480 52 66 66 66 14 14 5 5 4 3 1 4 1 1 66 66 57 104 104 102 12 11 83 83 82 83 80 79 8 7 30 104 29 23 29 29 11 11 6 6 11 4 241 231 8 8 8 7 3 4 7 15 13 12 4 11 2 10 9 3 4 8 15 25 12 2 1 2 14 100 22 20 19 19 19 14 19 1 18 19 5 17 16 12 13 10 9 24 18 24 13 3 12 1 23 18 3 118 4 119 9 73 38 38 118 116 4 115 1 2 2 2 112 4 107 13 105 2 2 1 1 73 73 24 22 2 19 11 11 1 2 6 5 4 113 120 6 7 7 5 2 1 7 19 19 19 19 302 298 297 298 291 6 6 298 19 19 19 4 23 13 13 23 1742 1165 973 968 1165 10 10 1314 473 472 472 532 289 2 2 37 34 1743 121 120 1 1 1 1 1 121 121 121 121 120 121 121 121 16 16 16 16 16 16 16 16 16 16 16 105 105 105 105 1609 1644 1645 1629 1665 1610 1610 1665 21 21 7 21 8 8 1151 534 533 534 34 511 534 1173 1173 1170 1057 1040 34 1039 34 1059 1040 34 1041 1174 1151 1152 5 4 1 2 1 2 2 5 20 20 20 20 20 20 20 19 17 17 17 20 1019 1018 1019 1017 512 511 1010 1007 1008 1006 34 16 16 16 16 16 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 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 | /* * NET3 IP device support routines. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. * * Derived from the IP parts of dev.c 1.0.19 * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Mark Evans, <evansmp@uhura.aston.ac.uk> * * Additional Authors: * Alan Cox, <gw4pts@gw4pts.ampr.org> * Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * * Changes: * Alexey Kuznetsov: pa_* fields are replaced with ifaddr * lists. * Cyrus Durgin: updated for kmod * Matthias Andree: in devinet_ioctl, compare label and * address (4.4BSD alias style support), * fall back to comparing just the label * if no match found. */ #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/capability.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/in.h> #include <linux/errno.h> #include <linux/interrupt.h> #include <linux/if_addr.h> #include <linux/if_ether.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/skbuff.h> #include <linux/init.h> #include <linux/notifier.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include <linux/slab.h> #include <linux/hash.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif #include <linux/kmod.h> #include <linux/netconf.h> #include <net/arp.h> #include <net/ip.h> #include <net/route.h> #include <net/ip_fib.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> #include <net/addrconf.h> #define IPV6ONLY_FLAGS \ (IFA_F_NODAD | IFA_F_OPTIMISTIC | IFA_F_DADFAILED | \ IFA_F_HOMEADDRESS | IFA_F_TENTATIVE | \ IFA_F_MANAGETEMPADDR | IFA_F_STABLE_PRIVACY) static struct ipv4_devconf ipv4_devconf = { .data = { [IPV4_DEVCONF_ACCEPT_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SEND_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SECURE_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SHARED_MEDIA - 1] = 1, [IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL - 1] = 10000 /*ms*/, [IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL - 1] = 1000 /*ms*/, }, }; static struct ipv4_devconf ipv4_devconf_dflt = { .data = { [IPV4_DEVCONF_ACCEPT_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SEND_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SECURE_REDIRECTS - 1] = 1, [IPV4_DEVCONF_SHARED_MEDIA - 1] = 1, [IPV4_DEVCONF_ACCEPT_SOURCE_ROUTE - 1] = 1, [IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL - 1] = 10000 /*ms*/, [IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL - 1] = 1000 /*ms*/, }, }; #define IPV4_DEVCONF_DFLT(net, attr) \ IPV4_DEVCONF((*net->ipv4.devconf_dflt), attr) static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = { [IFA_LOCAL] = { .type = NLA_U32 }, [IFA_ADDRESS] = { .type = NLA_U32 }, [IFA_BROADCAST] = { .type = NLA_U32 }, [IFA_LABEL] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, [IFA_CACHEINFO] = { .len = sizeof(struct ifa_cacheinfo) }, [IFA_FLAGS] = { .type = NLA_U32 }, }; #define IN4_ADDR_HSIZE_SHIFT 8 #define IN4_ADDR_HSIZE (1U << IN4_ADDR_HSIZE_SHIFT) static struct hlist_head inet_addr_lst[IN4_ADDR_HSIZE]; static u32 inet_addr_hash(const struct net *net, __be32 addr) { u32 val = (__force u32) addr ^ net_hash_mix(net); return hash_32(val, IN4_ADDR_HSIZE_SHIFT); } static void inet_hash_insert(struct net *net, struct in_ifaddr *ifa) { u32 hash = inet_addr_hash(net, ifa->ifa_local); ASSERT_RTNL(); hlist_add_head_rcu(&ifa->hash, &inet_addr_lst[hash]); } static void inet_hash_remove(struct in_ifaddr *ifa) { ASSERT_RTNL(); hlist_del_init_rcu(&ifa->hash); } /** * __ip_dev_find - find the first device with a given source address. * @net: the net namespace * @addr: the source address * @devref: if true, take a reference on the found device * * If a caller uses devref=false, it should be protected by RCU, or RTNL */ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref) { u32 hash = inet_addr_hash(net, addr); struct net_device *result = NULL; struct in_ifaddr *ifa; rcu_read_lock(); hlist_for_each_entry_rcu(ifa, &inet_addr_lst[hash], hash) { if (ifa->ifa_local == addr) { struct net_device *dev = ifa->ifa_dev->dev; if (!net_eq(dev_net(dev), net)) continue; result = dev; break; } } if (!result) { struct flowi4 fl4 = { .daddr = addr }; struct fib_result res = { 0 }; struct fib_table *local; /* Fallback to FIB local table so that communication * over loopback subnets work. */ local = fib_get_table(net, RT_TABLE_LOCAL); if (local && !fib_table_lookup(local, &fl4, &res, FIB_LOOKUP_NOREF) && res.type == RTN_LOCAL) result = FIB_RES_DEV(res); } if (result && devref) dev_hold(result); rcu_read_unlock(); return result; } EXPORT_SYMBOL(__ip_dev_find); static void rtmsg_ifa(int event, struct in_ifaddr *, struct nlmsghdr *, u32); static BLOCKING_NOTIFIER_HEAD(inetaddr_chain); static BLOCKING_NOTIFIER_HEAD(inetaddr_validator_chain); static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, int destroy); #ifdef CONFIG_SYSCTL static int devinet_sysctl_register(struct in_device *idev); static void devinet_sysctl_unregister(struct in_device *idev); #else static int devinet_sysctl_register(struct in_device *idev) { return 0; } static void devinet_sysctl_unregister(struct in_device *idev) { } #endif /* Locks all the inet devices. */ static struct in_ifaddr *inet_alloc_ifa(void) { return kzalloc(sizeof(struct in_ifaddr), GFP_KERNEL); } static void inet_rcu_free_ifa(struct rcu_head *head) { struct in_ifaddr *ifa = container_of(head, struct in_ifaddr, rcu_head); if (ifa->ifa_dev) in_dev_put(ifa->ifa_dev); kfree(ifa); } static void inet_free_ifa(struct in_ifaddr *ifa) { call_rcu(&ifa->rcu_head, inet_rcu_free_ifa); } void in_dev_finish_destroy(struct in_device *idev) { struct net_device *dev = idev->dev; WARN_ON(idev->ifa_list); WARN_ON(idev->mc_list); kfree(rcu_dereference_protected(idev->mc_hash, 1)); #ifdef NET_REFCNT_DEBUG pr_debug("%s: %p=%s\n", __func__, idev, dev ? dev->name : "NIL"); #endif dev_put(dev); if (!idev->dead) pr_err("Freeing alive in_device %p\n", idev); else kfree(idev); } EXPORT_SYMBOL(in_dev_finish_destroy); static struct in_device *inetdev_init(struct net_device *dev) { struct in_device *in_dev; int err = -ENOMEM; ASSERT_RTNL(); in_dev = kzalloc(sizeof(*in_dev), GFP_KERNEL); if (!in_dev) goto out; memcpy(&in_dev->cnf, dev_net(dev)->ipv4.devconf_dflt, sizeof(in_dev->cnf)); in_dev->cnf.sysctl = NULL; in_dev->dev = dev; in_dev->arp_parms = neigh_parms_alloc(dev, &arp_tbl); if (!in_dev->arp_parms) goto out_kfree; if (IPV4_DEVCONF(in_dev->cnf, FORWARDING)) dev_disable_lro(dev); /* Reference in_dev->dev */ dev_hold(dev); /* Account for reference dev->ip_ptr (below) */ refcount_set(&in_dev->refcnt, 1); err = devinet_sysctl_register(in_dev); if (err) { in_dev->dead = 1; neigh_parms_release(&arp_tbl, in_dev->arp_parms); in_dev_put(in_dev); in_dev = NULL; goto out; } ip_mc_init_dev(in_dev); if (dev->flags & IFF_UP) ip_mc_up(in_dev); /* we can receive as soon as ip_ptr is set -- do this last */ rcu_assign_pointer(dev->ip_ptr, in_dev); out: return in_dev ?: ERR_PTR(err); out_kfree: kfree(in_dev); in_dev = NULL; goto out; } static void in_dev_rcu_put(struct rcu_head *head) { struct in_device *idev = container_of(head, struct in_device, rcu_head); in_dev_put(idev); } static void inetdev_destroy(struct in_device *in_dev) { struct in_ifaddr *ifa; struct net_device *dev; ASSERT_RTNL(); dev = in_dev->dev; in_dev->dead = 1; ip_mc_destroy_dev(in_dev); while ((ifa = in_dev->ifa_list) != NULL) { inet_del_ifa(in_dev, &in_dev->ifa_list, 0); inet_free_ifa(ifa); } RCU_INIT_POINTER(dev->ip_ptr, NULL); devinet_sysctl_unregister(in_dev); neigh_parms_release(&arp_tbl, in_dev->arp_parms); arp_ifdown(dev); call_rcu(&in_dev->rcu_head, in_dev_rcu_put); } int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b) { rcu_read_lock(); for_primary_ifa(in_dev) { if (inet_ifa_match(a, ifa)) { if (!b || inet_ifa_match(b, ifa)) { rcu_read_unlock(); return 1; } } } endfor_ifa(in_dev); rcu_read_unlock(); return 0; } static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, int destroy, struct nlmsghdr *nlh, u32 portid) { struct in_ifaddr *promote = NULL; struct in_ifaddr *ifa, *ifa1 = *ifap; struct in_ifaddr *last_prim = in_dev->ifa_list; struct in_ifaddr *prev_prom = NULL; int do_promote = IN_DEV_PROMOTE_SECONDARIES(in_dev); ASSERT_RTNL(); if (in_dev->dead) goto no_promotions; /* 1. Deleting primary ifaddr forces deletion all secondaries * unless alias promotion is set **/ if (!(ifa1->ifa_flags & IFA_F_SECONDARY)) { struct in_ifaddr **ifap1 = &ifa1->ifa_next; while ((ifa = *ifap1) != NULL) { if (!(ifa->ifa_flags & IFA_F_SECONDARY) && ifa1->ifa_scope <= ifa->ifa_scope) last_prim = ifa; if (!(ifa->ifa_flags & IFA_F_SECONDARY) || ifa1->ifa_mask != ifa->ifa_mask || !inet_ifa_match(ifa1->ifa_address, ifa)) { ifap1 = &ifa->ifa_next; prev_prom = ifa; continue; } if (!do_promote) { inet_hash_remove(ifa); *ifap1 = ifa->ifa_next; rtmsg_ifa(RTM_DELADDR, ifa, nlh, portid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_DOWN, ifa); inet_free_ifa(ifa); } else { promote = ifa; break; } } } /* On promotion all secondaries from subnet are changing * the primary IP, we must remove all their routes silently * and later to add them back with new prefsrc. Do this * while all addresses are on the device list. */ for (ifa = promote; ifa; ifa = ifa->ifa_next) { if (ifa1->ifa_mask == ifa->ifa_mask && inet_ifa_match(ifa1->ifa_address, ifa)) fib_del_ifaddr(ifa, ifa1); } no_promotions: /* 2. Unlink it */ *ifap = ifa1->ifa_next; inet_hash_remove(ifa1); /* 3. Announce address deletion */ /* Send message first, then call notifier. At first sight, FIB update triggered by notifier will refer to already deleted ifaddr, that could confuse netlink listeners. It is not true: look, gated sees that route deleted and if it still thinks that ifaddr is valid, it will try to restore deleted routes... Grr. So that, this order is correct. */ rtmsg_ifa(RTM_DELADDR, ifa1, nlh, portid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_DOWN, ifa1); if (promote) { struct in_ifaddr *next_sec = promote->ifa_next; if (prev_prom) { prev_prom->ifa_next = promote->ifa_next; promote->ifa_next = last_prim->ifa_next; last_prim->ifa_next = promote; } promote->ifa_flags &= ~IFA_F_SECONDARY; rtmsg_ifa(RTM_NEWADDR, promote, nlh, portid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, promote); for (ifa = next_sec; ifa; ifa = ifa->ifa_next) { if (ifa1->ifa_mask != ifa->ifa_mask || !inet_ifa_match(ifa1->ifa_address, ifa)) continue; fib_add_ifaddr(ifa); } } if (destroy) inet_free_ifa(ifa1); } static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, int destroy) { __inet_del_ifa(in_dev, ifap, destroy, NULL, 0); } static void check_lifetime(struct work_struct *work); static DECLARE_DELAYED_WORK(check_lifetime_work, check_lifetime); static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, u32 portid) { struct in_device *in_dev = ifa->ifa_dev; struct in_ifaddr *ifa1, **ifap, **last_primary; struct in_validator_info ivi; int ret; ASSERT_RTNL(); if (!ifa->ifa_local) { inet_free_ifa(ifa); return 0; } ifa->ifa_flags &= ~IFA_F_SECONDARY; last_primary = &in_dev->ifa_list; /* Don't set IPv6 only flags to IPv4 addresses */ ifa->ifa_flags &= ~IPV6ONLY_FLAGS; for (ifap = &in_dev->ifa_list; (ifa1 = *ifap) != NULL; ifap = &ifa1->ifa_next) { if (!(ifa1->ifa_flags & IFA_F_SECONDARY) && ifa->ifa_scope <= ifa1->ifa_scope) last_primary = &ifa1->ifa_next; if (ifa1->ifa_mask == ifa->ifa_mask && inet_ifa_match(ifa1->ifa_address, ifa)) { if (ifa1->ifa_local == ifa->ifa_local) { inet_free_ifa(ifa); return -EEXIST; } if (ifa1->ifa_scope != ifa->ifa_scope) { inet_free_ifa(ifa); return -EINVAL; } ifa->ifa_flags |= IFA_F_SECONDARY; } } /* Allow any devices that wish to register ifaddr validtors to weigh * in now, before changes are committed. The rntl lock is serializing * access here, so the state should not change between a validator call * and a final notify on commit. This isn't invoked on promotion under * the assumption that validators are checking the address itself, and * not the flags. */ ivi.ivi_addr = ifa->ifa_address; ivi.ivi_dev = ifa->ifa_dev; ret = blocking_notifier_call_chain(&inetaddr_validator_chain, NETDEV_UP, &ivi); ret = notifier_to_errno(ret); if (ret) { inet_free_ifa(ifa); return ret; } if (!(ifa->ifa_flags & IFA_F_SECONDARY)) { prandom_seed((__force u32) ifa->ifa_local); ifap = last_primary; } ifa->ifa_next = *ifap; *ifap = ifa; inet_hash_insert(dev_net(in_dev->dev), ifa); cancel_delayed_work(&check_lifetime_work); queue_delayed_work(system_power_efficient_wq, &check_lifetime_work, 0); /* Send message first, then call notifier. Notifier will trigger FIB update, so that listeners of netlink will know about new ifaddr */ rtmsg_ifa(RTM_NEWADDR, ifa, nlh, portid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa); return 0; } static int inet_insert_ifa(struct in_ifaddr *ifa) { return __inet_insert_ifa(ifa, NULL, 0); } static int inet_set_ifa(struct net_device *dev, struct in_ifaddr *ifa) { struct in_device *in_dev = __in_dev_get_rtnl(dev); ASSERT_RTNL(); if (!in_dev) { inet_free_ifa(ifa); return -ENOBUFS; } ipv4_devconf_setall(in_dev); neigh_parms_data_state_setall(in_dev->arp_parms); if (ifa->ifa_dev != in_dev) { WARN_ON(ifa->ifa_dev); in_dev_hold(in_dev); ifa->ifa_dev = in_dev; } if (ipv4_is_loopback(ifa->ifa_local)) ifa->ifa_scope = RT_SCOPE_HOST; return inet_insert_ifa(ifa); } /* Caller must hold RCU or RTNL : * We dont take a reference on found in_device */ struct in_device *inetdev_by_index(struct net *net, int ifindex) { struct net_device *dev; struct in_device *in_dev = NULL; rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); if (dev) in_dev = rcu_dereference_rtnl(dev->ip_ptr); rcu_read_unlock(); return in_dev; } EXPORT_SYMBOL(inetdev_by_index); /* Called only from RTNL semaphored context. No locks. */ struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, __be32 mask) { ASSERT_RTNL(); for_primary_ifa(in_dev) { if (ifa->ifa_mask == mask && inet_ifa_match(prefix, ifa)) return ifa; } endfor_ifa(in_dev); return NULL; } static int ip_mc_autojoin_config(struct net *net, bool join, const struct in_ifaddr *ifa) { #if defined(CONFIG_IP_MULTICAST) struct ip_mreqn mreq = { .imr_multiaddr.s_addr = ifa->ifa_address, .imr_ifindex = ifa->ifa_dev->dev->ifindex, }; struct sock *sk = net->ipv4.mc_autojoin_sk; int ret; ASSERT_RTNL(); lock_sock(sk); if (join) ret = ip_mc_join_group(sk, &mreq); else ret = ip_mc_leave_group(sk, &mreq); release_sock(sk); return ret; #else return -EOPNOTSUPP; #endif } static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct nlattr *tb[IFA_MAX+1]; struct in_device *in_dev; struct ifaddrmsg *ifm; struct in_ifaddr *ifa, **ifap; int err = -EINVAL; ASSERT_RTNL(); err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy, extack); if (err < 0) goto errout; ifm = nlmsg_data(nlh); in_dev = inetdev_by_index(net, ifm->ifa_index); if (!in_dev) { err = -ENODEV; goto errout; } for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL; ifap = &ifa->ifa_next) { if (tb[IFA_LOCAL] && ifa->ifa_local != nla_get_in_addr(tb[IFA_LOCAL])) continue; if (tb[IFA_LABEL] && nla_strcmp(tb[IFA_LABEL], ifa->ifa_label)) continue; if (tb[IFA_ADDRESS] && (ifm->ifa_prefixlen != ifa->ifa_prefixlen || !inet_ifa_match(nla_get_in_addr(tb[IFA_ADDRESS]), ifa))) continue; if (ipv4_is_multicast(ifa->ifa_address)) ip_mc_autojoin_config(net, false, ifa); __inet_del_ifa(in_dev, ifap, 1, nlh, NETLINK_CB(skb).portid); return 0; } err = -EADDRNOTAVAIL; errout: return err; } #define INFINITY_LIFE_TIME 0xFFFFFFFF static void check_lifetime(struct work_struct *work) { unsigned long now, next, next_sec, next_sched; struct in_ifaddr *ifa; struct hlist_node *n; int i; now = jiffies; next = round_jiffies_up(now + ADDR_CHECK_FREQUENCY); for (i = 0; i < IN4_ADDR_HSIZE; i++) { bool change_needed = false; rcu_read_lock(); hlist_for_each_entry_rcu(ifa, &inet_addr_lst[i], hash) { unsigned long age; if (ifa->ifa_flags & IFA_F_PERMANENT) continue; /* We try to batch several events at once. */ age = (now - ifa->ifa_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME && age >= ifa->ifa_valid_lft) { change_needed = true; } else if (ifa->ifa_preferred_lft == INFINITY_LIFE_TIME) { continue; } else if (age >= ifa->ifa_preferred_lft) { if (time_before(ifa->ifa_tstamp + ifa->ifa_valid_lft * HZ, next)) next = ifa->ifa_tstamp + ifa->ifa_valid_lft * HZ; if (!(ifa->ifa_flags & IFA_F_DEPRECATED)) change_needed = true; } else if (time_before(ifa->ifa_tstamp + ifa->ifa_preferred_lft * HZ, next)) { next = ifa->ifa_tstamp + ifa->ifa_preferred_lft * HZ; } } rcu_read_unlock(); if (!change_needed) continue; rtnl_lock(); hlist_for_each_entry_safe(ifa, n, &inet_addr_lst[i], hash) { unsigned long age; if (ifa->ifa_flags & IFA_F_PERMANENT) continue; /* We try to batch several events at once. */ age = (now - ifa->ifa_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME && age >= ifa->ifa_valid_lft) { struct in_ifaddr **ifap; for (ifap = &ifa->ifa_dev->ifa_list; *ifap != NULL; ifap = &(*ifap)->ifa_next) { if (*ifap == ifa) { inet_del_ifa(ifa->ifa_dev, ifap, 1); break; } } } else if (ifa->ifa_preferred_lft != INFINITY_LIFE_TIME && age >= ifa->ifa_preferred_lft && !(ifa->ifa_flags & IFA_F_DEPRECATED)) { ifa->ifa_flags |= IFA_F_DEPRECATED; rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0); } } rtnl_unlock(); } next_sec = round_jiffies_up(next); next_sched = next; /* If rounded timeout is accurate enough, accept it. */ if (time_before(next_sec, next + ADDRCONF_TIMER_FUZZ)) next_sched = next_sec; now = jiffies; /* And minimum interval is ADDRCONF_TIMER_FUZZ_MAX. */ if (time_before(next_sched, now + ADDRCONF_TIMER_FUZZ_MAX)) next_sched = now + ADDRCONF_TIMER_FUZZ_MAX; queue_delayed_work(system_power_efficient_wq, &check_lifetime_work, next_sched - now); } static void set_ifa_lifetime(struct in_ifaddr *ifa, __u32 valid_lft, __u32 prefered_lft) { unsigned long timeout; ifa->ifa_flags &= ~(IFA_F_PERMANENT | IFA_F_DEPRECATED); timeout = addrconf_timeout_fixup(valid_lft, HZ); if (addrconf_finite_timeout(timeout)) ifa->ifa_valid_lft = timeout; else ifa->ifa_flags |= IFA_F_PERMANENT; timeout = addrconf_timeout_fixup(prefered_lft, HZ); if (addrconf_finite_timeout(timeout)) { if (timeout == 0) ifa->ifa_flags |= IFA_F_DEPRECATED; ifa->ifa_preferred_lft = timeout; } ifa->ifa_tstamp = jiffies; if (!ifa->ifa_cstamp) ifa->ifa_cstamp = ifa->ifa_tstamp; } static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh, __u32 *pvalid_lft, __u32 *pprefered_lft) { struct nlattr *tb[IFA_MAX+1]; struct in_ifaddr *ifa; struct ifaddrmsg *ifm; struct net_device *dev; struct in_device *in_dev; int err; err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv4_policy, NULL); if (err < 0) goto errout; ifm = nlmsg_data(nlh); err = -EINVAL; if (ifm->ifa_prefixlen > 32 || !tb[IFA_LOCAL]) goto errout; dev = __dev_get_by_index(net, ifm->ifa_index); err = -ENODEV; if (!dev) goto errout; in_dev = __in_dev_get_rtnl(dev); err = -ENOBUFS; if (!in_dev) goto errout; ifa = inet_alloc_ifa(); if (!ifa) /* * A potential indev allocation can be left alive, it stays * assigned to its device and is destroy with it. */ goto errout; ipv4_devconf_setall(in_dev); neigh_parms_data_state_setall(in_dev->arp_parms); in_dev_hold(in_dev); if (!tb[IFA_ADDRESS]) tb[IFA_ADDRESS] = tb[IFA_LOCAL]; INIT_HLIST_NODE(&ifa->hash); ifa->ifa_prefixlen = ifm->ifa_prefixlen; ifa->ifa_mask = inet_make_mask(ifm->ifa_prefixlen); ifa->ifa_flags = tb[IFA_FLAGS] ? nla_get_u32(tb[IFA_FLAGS]) : ifm->ifa_flags; ifa->ifa_scope = ifm->ifa_scope; ifa->ifa_dev = in_dev; ifa->ifa_local = nla_get_in_addr(tb[IFA_LOCAL]); ifa->ifa_address = nla_get_in_addr(tb[IFA_ADDRESS]); if (tb[IFA_BROADCAST]) ifa->ifa_broadcast = nla_get_in_addr(tb[IFA_BROADCAST]); if (tb[IFA_LABEL]) nla_strlcpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ); else memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); if (tb[IFA_CACHEINFO]) { struct ifa_cacheinfo *ci; ci = nla_data(tb[IFA_CACHEINFO]); if (!ci->ifa_valid || ci->ifa_prefered > ci->ifa_valid) { err = -EINVAL; goto errout_free; } *pvalid_lft = ci->ifa_valid; *pprefered_lft = ci->ifa_prefered; } return ifa; errout_free: inet_free_ifa(ifa); errout: return ERR_PTR(err); } static struct in_ifaddr *find_matching_ifa(struct in_ifaddr *ifa) { struct in_device *in_dev = ifa->ifa_dev; struct in_ifaddr *ifa1, **ifap; if (!ifa->ifa_local) return NULL; for (ifap = &in_dev->ifa_list; (ifa1 = *ifap) != NULL; ifap = &ifa1->ifa_next) { if (ifa1->ifa_mask == ifa->ifa_mask && inet_ifa_match(ifa1->ifa_address, ifa) && ifa1->ifa_local == ifa->ifa_local) return ifa1; } return NULL; } static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct in_ifaddr *ifa; struct in_ifaddr *ifa_existing; __u32 valid_lft = INFINITY_LIFE_TIME; __u32 prefered_lft = INFINITY_LIFE_TIME; ASSERT_RTNL(); ifa = rtm_to_ifaddr(net, nlh, &valid_lft, &prefered_lft); if (IS_ERR(ifa)) return PTR_ERR(ifa); ifa_existing = find_matching_ifa(ifa); if (!ifa_existing) { /* It would be best to check for !NLM_F_CREATE here but * userspace already relies on not having to provide this. */ set_ifa_lifetime(ifa, valid_lft, prefered_lft); if (ifa->ifa_flags & IFA_F_MCAUTOJOIN) { int ret = ip_mc_autojoin_config(net, true, ifa); if (ret < 0) { inet_free_ifa(ifa); return ret; } } return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid); } else { inet_free_ifa(ifa); if (nlh->nlmsg_flags & NLM_F_EXCL || !(nlh->nlmsg_flags & NLM_F_REPLACE)) return -EEXIST; ifa = ifa_existing; set_ifa_lifetime(ifa, valid_lft, prefered_lft); cancel_delayed_work(&check_lifetime_work); queue_delayed_work(system_power_efficient_wq, &check_lifetime_work, 0); rtmsg_ifa(RTM_NEWADDR, ifa, nlh, NETLINK_CB(skb).portid); } return 0; } /* * Determine a default network mask, based on the IP address. */ static int inet_abc_len(__be32 addr) { int rc = -1; /* Something else, probably a multicast. */ if (ipv4_is_zeronet(addr)) rc = 0; else { __u32 haddr = ntohl(addr); if (IN_CLASSA(haddr)) rc = 8; else if (IN_CLASSB(haddr)) rc = 16; else if (IN_CLASSC(haddr)) rc = 24; } return rc; } int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) { struct ifreq ifr; struct sockaddr_in sin_orig; struct sockaddr_in *sin = (struct sockaddr_in *)&ifr.ifr_addr; struct in_device *in_dev; struct in_ifaddr **ifap = NULL; struct in_ifaddr *ifa = NULL; struct net_device *dev; char *colon; int ret = -EFAULT; int tryaddrmatch = 0; /* * Fetch the caller's info block into kernel space */ if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) goto out; ifr.ifr_name[IFNAMSIZ - 1] = 0; /* save original address for comparison */ memcpy(&sin_orig, sin, sizeof(*sin)); colon = strchr(ifr.ifr_name, ':'); if (colon) *colon = 0; dev_load(net, ifr.ifr_name); switch (cmd) { case SIOCGIFADDR: /* Get interface address */ case SIOCGIFBRDADDR: /* Get the broadcast address */ case SIOCGIFDSTADDR: /* Get the destination address */ case SIOCGIFNETMASK: /* Get the netmask for the interface */ /* Note that these ioctls will not sleep, so that we do not impose a lock. One day we will be forced to put shlock here (I mean SMP) */ tryaddrmatch = (sin_orig.sin_family == AF_INET); memset(sin, 0, sizeof(*sin)); sin->sin_family = AF_INET; break; case SIOCSIFFLAGS: ret = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto out; break; case SIOCSIFADDR: /* Set interface address (and family) */ case SIOCSIFBRDADDR: /* Set the broadcast address */ case SIOCSIFDSTADDR: /* Set the destination address */ case SIOCSIFNETMASK: /* Set the netmask for the interface */ ret = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) goto out; ret = -EINVAL; if (sin->sin_family != AF_INET) goto out; break; default: ret = -EINVAL; goto out; } rtnl_lock(); ret = -ENODEV; dev = __dev_get_by_name(net, ifr.ifr_name); if (!dev) goto done; if (colon) *colon = ':'; in_dev = __in_dev_get_rtnl(dev); if (in_dev) { if (tryaddrmatch) { /* Matthias Andree */ /* compare label and address (4.4BSD style) */ /* note: we only do this for a limited set of ioctls and only if the original address family was AF_INET. This is checked above. */ for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL; ifap = &ifa->ifa_next) { if (!strcmp(ifr.ifr_name, ifa->ifa_label) && sin_orig.sin_addr.s_addr == ifa->ifa_local) { break; /* found */ } } } /* we didn't get a match, maybe the application is 4.3BSD-style and passed in junk so we fall back to comparing just the label */ if (!ifa) { for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL; ifap = &ifa->ifa_next) if (!strcmp(ifr.ifr_name, ifa->ifa_label)) break; } } ret = -EADDRNOTAVAIL; if (!ifa && cmd != SIOCSIFADDR && cmd != SIOCSIFFLAGS) goto done; switch (cmd) { case SIOCGIFADDR: /* Get interface address */ sin->sin_addr.s_addr = ifa->ifa_local; goto rarok; case SIOCGIFBRDADDR: /* Get the broadcast address */ sin->sin_addr.s_addr = ifa->ifa_broadcast; goto rarok; case SIOCGIFDSTADDR: /* Get the destination address */ sin->sin_addr.s_addr = ifa->ifa_address; goto rarok; case SIOCGIFNETMASK: /* Get the netmask for the interface */ sin->sin_addr.s_addr = ifa->ifa_mask; goto rarok; case SIOCSIFFLAGS: if (colon) { ret = -EADDRNOTAVAIL; if (!ifa) break; ret = 0; if (!(ifr.ifr_flags & IFF_UP)) inet_del_ifa(in_dev, ifap, 1); break; } ret = dev_change_flags(dev, ifr.ifr_flags); break; case SIOCSIFADDR: /* Set interface address (and family) */ ret = -EINVAL; if (inet_abc_len(sin->sin_addr.s_addr) < 0) break; if (!ifa) { ret = -ENOBUFS; ifa = inet_alloc_ifa(); if (!ifa) break; INIT_HLIST_NODE(&ifa->hash); if (colon) memcpy(ifa->ifa_label, ifr.ifr_name, IFNAMSIZ); else memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); } else { ret = 0; if (ifa->ifa_local == sin->sin_addr.s_addr) break; inet_del_ifa(in_dev, ifap, 0); ifa->ifa_broadcast = 0; ifa->ifa_scope = 0; } ifa->ifa_address = ifa->ifa_local = sin->sin_addr.s_addr; if (!(dev->flags & IFF_POINTOPOINT)) { ifa->ifa_prefixlen = inet_abc_len(ifa->ifa_address); ifa->ifa_mask = inet_make_mask(ifa->ifa_prefixlen); if ((dev->flags & IFF_BROADCAST) && ifa->ifa_prefixlen < 31) ifa->ifa_broadcast = ifa->ifa_address | ~ifa->ifa_mask; } else { ifa->ifa_prefixlen = 32; ifa->ifa_mask = inet_make_mask(32); } set_ifa_lifetime(ifa, INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); ret = inet_set_ifa(dev, ifa); break; case SIOCSIFBRDADDR: /* Set the broadcast address */ ret = 0; if (ifa->ifa_broadcast != sin->sin_addr.s_addr) { inet_del_ifa(in_dev, ifap, 0); ifa->ifa_broadcast = sin->sin_addr.s_addr; inet_insert_ifa(ifa); } break; case SIOCSIFDSTADDR: /* Set the destination address */ ret = 0; if (ifa->ifa_address == sin->sin_addr.s_addr) break; ret = -EINVAL; if (inet_abc_len(sin->sin_addr.s_addr) < 0) break; ret = 0; inet_del_ifa(in_dev, ifap, 0); ifa->ifa_address = sin->sin_addr.s_addr; inet_insert_ifa(ifa); break; case SIOCSIFNETMASK: /* Set the netmask for the interface */ /* * The mask we set must be legal. */ ret = -EINVAL; if (bad_mask(sin->sin_addr.s_addr, 0)) break; ret = 0; if (ifa->ifa_mask != sin->sin_addr.s_addr) { __be32 old_mask = ifa->ifa_mask; inet_del_ifa(in_dev, ifap, 0); ifa->ifa_mask = sin->sin_addr.s_addr; ifa->ifa_prefixlen = inet_mask_len(ifa->ifa_mask); /* See if current broadcast address matches * with current netmask, then recalculate * the broadcast address. Otherwise it's a * funny address, so don't touch it since * the user seems to know what (s)he's doing... */ if ((dev->flags & IFF_BROADCAST) && (ifa->ifa_prefixlen < 31) && (ifa->ifa_broadcast == (ifa->ifa_local|~old_mask))) { ifa->ifa_broadcast = (ifa->ifa_local | ~sin->sin_addr.s_addr); } inet_insert_ifa(ifa); } break; } done: rtnl_unlock(); out: return ret; rarok: rtnl_unlock(); ret = copy_to_user(arg, &ifr, sizeof(struct ifreq)) ? -EFAULT : 0; goto out; } static int inet_gifconf(struct net_device *dev, char __user *buf, int len) { struct in_device *in_dev = __in_dev_get_rtnl(dev); struct in_ifaddr *ifa; struct ifreq ifr; int done = 0; if (!in_dev) goto out; for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) { if (!buf) { done += sizeof(ifr); continue; } if (len < (int) sizeof(ifr)) break; memset(&ifr, 0, sizeof(struct ifreq)); strcpy(ifr.ifr_name, ifa->ifa_label); (*(struct sockaddr_in *)&ifr.ifr_addr).sin_family = AF_INET; (*(struct sockaddr_in *)&ifr.ifr_addr).sin_addr.s_addr = ifa->ifa_local; if (copy_to_user(buf, &ifr, sizeof(struct ifreq))) { done = -EFAULT; break; } buf += sizeof(struct ifreq); len -= sizeof(struct ifreq); done += sizeof(struct ifreq); } out: return done; } static __be32 in_dev_select_addr(const struct in_device *in_dev, int scope) { for_primary_ifa(in_dev) { if (ifa->ifa_scope != RT_SCOPE_LINK && ifa->ifa_scope <= scope) return ifa->ifa_local; } endfor_ifa(in_dev); return 0; } __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope) { __be32 addr = 0; struct in_device *in_dev; struct net *net = dev_net(dev); int master_idx; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (!in_dev) goto no_in_dev; for_primary_ifa(in_dev) { if (ifa->ifa_scope > scope) continue; if (!dst || inet_ifa_match(dst, ifa)) { addr = ifa->ifa_local; break; } if (!addr) addr = ifa->ifa_local; } endfor_ifa(in_dev); if (addr) goto out_unlock; no_in_dev: master_idx = l3mdev_master_ifindex_rcu(dev); /* For VRFs, the VRF device takes the place of the loopback device, * with addresses on it being preferred. Note in such cases the * loopback device will be among the devices that fail the master_idx * equality check in the loop below. */ if (master_idx && (dev = dev_get_by_index_rcu(net, master_idx)) && (in_dev = __in_dev_get_rcu(dev))) { addr = in_dev_select_addr(in_dev, scope); if (addr) goto out_unlock; } /* Not loopback addresses on loopback should be preferred in this case. It is important that lo is the first interface in dev_base list. */ for_each_netdev_rcu(net, dev) { if (l3mdev_master_ifindex_rcu(dev) != master_idx) continue; in_dev = __in_dev_get_rcu(dev); if (!in_dev) continue; addr = in_dev_select_addr(in_dev, scope); if (addr) goto out_unlock; } out_unlock: rcu_read_unlock(); return addr; } EXPORT_SYMBOL(inet_select_addr); static __be32 confirm_addr_indev(struct in_device *in_dev, __be32 dst, __be32 local, int scope) { int same = 0; __be32 addr = 0; for_ifa(in_dev) { if (!addr && (local == ifa->ifa_local || !local) && ifa->ifa_scope <= scope) { addr = ifa->ifa_local; if (same) break; } if (!same) { same = (!local || inet_ifa_match(local, ifa)) && (!dst || inet_ifa_match(dst, ifa)); if (same && addr) { if (local || !dst) break; /* Is the selected addr into dst subnet? */ if (inet_ifa_match(addr, ifa)) break; /* No, then can we use new local src? */ if (ifa->ifa_scope <= scope) { addr = ifa->ifa_local; break; } /* search for large dst subnet for addr */ same = 0; } } } endfor_ifa(in_dev); return same ? addr : 0; } /* * Confirm that local IP address exists using wildcards: * - net: netns to check, cannot be NULL * - in_dev: only on this interface, NULL=any interface * - dst: only in the same subnet as dst, 0=any dst * - local: address, 0=autoselect the local address * - scope: maximum allowed scope value for the local address */ __be32 inet_confirm_addr(struct net *net, struct in_device *in_dev, __be32 dst, __be32 local, int scope) { __be32 addr = 0; struct net_device *dev; if (in_dev) return confirm_addr_indev(in_dev, dst, local, scope); rcu_read_lock(); for_each_netdev_rcu(net, dev) { in_dev = __in_dev_get_rcu(dev); if (in_dev) { addr = confirm_addr_indev(in_dev, dst, local, scope); if (addr) break; } } rcu_read_unlock(); return addr; } EXPORT_SYMBOL(inet_confirm_addr); /* * Device notifier */ int register_inetaddr_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&inetaddr_chain, nb); } EXPORT_SYMBOL(register_inetaddr_notifier); int unregister_inetaddr_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&inetaddr_chain, nb); } EXPORT_SYMBOL(unregister_inetaddr_notifier); int register_inetaddr_validator_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&inetaddr_validator_chain, nb); } EXPORT_SYMBOL(register_inetaddr_validator_notifier); int unregister_inetaddr_validator_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&inetaddr_validator_chain, nb); } EXPORT_SYMBOL(unregister_inetaddr_validator_notifier); /* Rename ifa_labels for a device name change. Make some effort to preserve * existing alias numbering and to create unique labels if possible. */ static void inetdev_changename(struct net_device *dev, struct in_device *in_dev) { struct in_ifaddr *ifa; int named = 0; for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) { char old[IFNAMSIZ], *dot; memcpy(old, ifa->ifa_label, IFNAMSIZ); memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); if (named++ == 0) goto skip; dot = strchr(old, ':'); if (!dot) { sprintf(old, ":%d", named); dot = old; } if (strlen(dot) + strlen(dev->name) < IFNAMSIZ) strcat(ifa->ifa_label, dot); else strcpy(ifa->ifa_label + (IFNAMSIZ - strlen(dot) - 1), dot); skip: rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0); } } static void inetdev_send_gratuitous_arp(struct net_device *dev, struct in_device *in_dev) { struct in_ifaddr *ifa; for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) { arp_send(ARPOP_REQUEST, ETH_P_ARP, ifa->ifa_local, dev, ifa->ifa_local, NULL, dev->dev_addr, NULL); } } /* Called only under RTNL semaphore */ static int inetdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct in_device *in_dev = __in_dev_get_rtnl(dev); ASSERT_RTNL(); if (!in_dev) { if (event == NETDEV_REGISTER) { in_dev = inetdev_init(dev); if (IS_ERR(in_dev)) return notifier_from_errno(PTR_ERR(in_dev)); if (dev->flags & IFF_LOOPBACK) { IN_DEV_CONF_SET(in_dev, NOXFRM, 1); IN_DEV_CONF_SET(in_dev, NOPOLICY, 1); } } else if (event == NETDEV_CHANGEMTU) { /* Re-enabling IP */ if (inetdev_valid_mtu(dev->mtu)) in_dev = inetdev_init(dev); } goto out; } switch (event) { case NETDEV_REGISTER: pr_debug("%s: bug\n", __func__); RCU_INIT_POINTER(dev->ip_ptr, NULL); break; case NETDEV_UP: if (!inetdev_valid_mtu(dev->mtu)) break; if (dev->flags & IFF_LOOPBACK) { struct in_ifaddr *ifa = inet_alloc_ifa(); if (ifa) { INIT_HLIST_NODE(&ifa->hash); ifa->ifa_local = ifa->ifa_address = htonl(INADDR_LOOPBACK); ifa->ifa_prefixlen = 8; ifa->ifa_mask = inet_make_mask(8); in_dev_hold(in_dev); ifa->ifa_dev = in_dev; ifa->ifa_scope = RT_SCOPE_HOST; memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); set_ifa_lifetime(ifa, INFINITY_LIFE_TIME, INFINITY_LIFE_TIME); ipv4_devconf_setall(in_dev); neigh_parms_data_state_setall(in_dev->arp_parms); inet_insert_ifa(ifa); } } ip_mc_up(in_dev); /* fall through */ case NETDEV_CHANGEADDR: if (!IN_DEV_ARP_NOTIFY(in_dev)) break; /* fall through */ case NETDEV_NOTIFY_PEERS: /* Send gratuitous ARP to notify of link change */ inetdev_send_gratuitous_arp(dev, in_dev); break; case NETDEV_DOWN: ip_mc_down(in_dev); break; case NETDEV_PRE_TYPE_CHANGE: ip_mc_unmap(in_dev); break; case NETDEV_POST_TYPE_CHANGE: ip_mc_remap(in_dev); break; case NETDEV_CHANGEMTU: if (inetdev_valid_mtu(dev->mtu)) break; /* disable IP when MTU is not enough */ case NETDEV_UNREGISTER: inetdev_destroy(in_dev); break; case NETDEV_CHANGENAME: /* Do not notify about label change, this event is * not interesting to applications using netlink. */ inetdev_changename(dev, in_dev); devinet_sysctl_unregister(in_dev); devinet_sysctl_register(in_dev); break; } out: return NOTIFY_DONE; } static struct notifier_block ip_netdev_notifier = { .notifier_call = inetdev_event, }; static size_t inet_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + nla_total_size(4) /* IFA_ADDRESS */ + nla_total_size(4) /* IFA_LOCAL */ + nla_total_size(4) /* IFA_BROADCAST */ + nla_total_size(IFNAMSIZ) /* IFA_LABEL */ + nla_total_size(4) /* IFA_FLAGS */ + nla_total_size(sizeof(struct ifa_cacheinfo)); /* IFA_CACHEINFO */ } static inline u32 cstamp_delta(unsigned long cstamp) { return (cstamp - INITIAL_JIFFIES) * 100UL / HZ; } static int put_cacheinfo(struct sk_buff *skb, unsigned long cstamp, unsigned long tstamp, u32 preferred, u32 valid) { struct ifa_cacheinfo ci; ci.cstamp = cstamp_delta(cstamp); ci.tstamp = cstamp_delta(tstamp); ci.ifa_prefered = preferred; ci.ifa_valid = valid; return nla_put(skb, IFA_CACHEINFO, sizeof(ci), &ci); } static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, u32 portid, u32 seq, int event, unsigned int flags) { struct ifaddrmsg *ifm; struct nlmsghdr *nlh; u32 preferred, valid; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*ifm), flags); if (!nlh) return -EMSGSIZE; ifm = nlmsg_data(nlh); ifm->ifa_family = AF_INET; ifm->ifa_prefixlen = ifa->ifa_prefixlen; ifm->ifa_flags = ifa->ifa_flags; ifm->ifa_scope = ifa->ifa_scope; ifm->ifa_index = ifa->ifa_dev->dev->ifindex; if (!(ifm->ifa_flags & IFA_F_PERMANENT)) { preferred = ifa->ifa_preferred_lft; valid = ifa->ifa_valid_lft; if (preferred != INFINITY_LIFE_TIME) { long tval = (jiffies - ifa->ifa_tstamp) / HZ; if (preferred > tval) preferred -= tval; else preferred = 0; if (valid != INFINITY_LIFE_TIME) { if (valid > tval) valid -= tval; else valid = 0; } } } else { preferred = INFINITY_LIFE_TIME; valid = INFINITY_LIFE_TIME; } if ((ifa->ifa_address && nla_put_in_addr(skb, IFA_ADDRESS, ifa->ifa_address)) || (ifa->ifa_local && nla_put_in_addr(skb, IFA_LOCAL, ifa->ifa_local)) || (ifa->ifa_broadcast && nla_put_in_addr(skb, IFA_BROADCAST, ifa->ifa_broadcast)) || (ifa->ifa_label[0] && nla_put_string(skb, IFA_LABEL, ifa->ifa_label)) || nla_put_u32(skb, IFA_FLAGS, ifa->ifa_flags) || put_cacheinfo(skb, ifa->ifa_cstamp, ifa->ifa_tstamp, preferred, valid)) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); int h, s_h; int idx, s_idx; int ip_idx, s_ip_idx; struct net_device *dev; struct in_device *in_dev; struct in_ifaddr *ifa; struct hlist_head *head; s_h = cb->args[0]; s_idx = idx = cb->args[1]; s_ip_idx = ip_idx = cb->args[2]; for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; head = &net->dev_index_head[h]; rcu_read_lock(); cb->seq = atomic_read(&net->ipv4.dev_addr_genid) ^ net->dev_base_seq; hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; if (h > s_h || idx > s_idx) s_ip_idx = 0; in_dev = __in_dev_get_rcu(dev); if (!in_dev) goto cont; for (ifa = in_dev->ifa_list, ip_idx = 0; ifa; ifa = ifa->ifa_next, ip_idx++) { if (ip_idx < s_ip_idx) continue; if (inet_fill_ifaddr(skb, ifa, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWADDR, NLM_F_MULTI) < 0) { rcu_read_unlock(); goto done; } nl_dump_check_consistent(cb, nlmsg_hdr(skb)); } cont: idx++; } rcu_read_unlock(); } done: cb->args[0] = h; cb->args[1] = idx; cb->args[2] = ip_idx; return skb->len; } static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh, u32 portid) { struct sk_buff *skb; u32 seq = nlh ? nlh->nlmsg_seq : 0; int err = -ENOBUFS; struct net *net; net = dev_net(ifa->ifa_dev->dev); skb = nlmsg_new(inet_nlmsg_size(), GFP_KERNEL); if (!skb) goto errout; err = inet_fill_ifaddr(skb, ifa, portid, seq, event, 0); if (err < 0) { /* -EMSGSIZE implies BUG in inet_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, portid, RTNLGRP_IPV4_IFADDR, nlh, GFP_KERNEL); return; errout: if (err < 0) rtnl_set_sk_err(net, RTNLGRP_IPV4_IFADDR, err); } static size_t inet_get_link_af_size(const struct net_device *dev, u32 ext_filter_mask) { struct in_device *in_dev = rcu_dereference_rtnl(dev->ip_ptr); if (!in_dev) return 0; return nla_total_size(IPV4_DEVCONF_MAX * 4); /* IFLA_INET_CONF */ } static int inet_fill_link_af(struct sk_buff *skb, const struct net_device *dev, u32 ext_filter_mask) { struct in_device *in_dev = rcu_dereference_rtnl(dev->ip_ptr); struct nlattr *nla; int i; if (!in_dev) return -ENODATA; nla = nla_reserve(skb, IFLA_INET_CONF, IPV4_DEVCONF_MAX * 4); if (!nla) return -EMSGSIZE; for (i = 0; i < IPV4_DEVCONF_MAX; i++) ((u32 *) nla_data(nla))[i] = in_dev->cnf.data[i]; return 0; } static const struct nla_policy inet_af_policy[IFLA_INET_MAX+1] = { [IFLA_INET_CONF] = { .type = NLA_NESTED }, }; static int inet_validate_link_af(const struct net_device *dev, const struct nlattr *nla) { struct nlattr *a, *tb[IFLA_INET_MAX+1]; int err, rem; if (dev && !__in_dev_get_rtnl(dev)) return -EAFNOSUPPORT; err = nla_parse_nested(tb, IFLA_INET_MAX, nla, inet_af_policy, NULL); if (err < 0) return err; if (tb[IFLA_INET_CONF]) { nla_for_each_nested(a, tb[IFLA_INET_CONF], rem) { int cfgid = nla_type(a); if (nla_len(a) < 4) return -EINVAL; if (cfgid <= 0 || cfgid > IPV4_DEVCONF_MAX) return -EINVAL; } } return 0; } static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla) { struct in_device *in_dev = __in_dev_get_rtnl(dev); struct nlattr *a, *tb[IFLA_INET_MAX+1]; int rem; if (!in_dev) return -EAFNOSUPPORT; if (nla_parse_nested(tb, IFLA_INET_MAX, nla, NULL, NULL) < 0) BUG(); if (tb[IFLA_INET_CONF]) { nla_for_each_nested(a, tb[IFLA_INET_CONF], rem) ipv4_devconf_set(in_dev, nla_type(a), nla_get_u32(a)); } return 0; } static int inet_netconf_msgsize_devconf(int type) { int size = NLMSG_ALIGN(sizeof(struct netconfmsg)) + nla_total_size(4); /* NETCONFA_IFINDEX */ bool all = false; if (type == NETCONFA_ALL) all = true; if (all || type == NETCONFA_FORWARDING) size += nla_total_size(4); if (all || type == NETCONFA_RP_FILTER) size += nla_total_size(4); if (all || type == NETCONFA_MC_FORWARDING) size += nla_total_size(4); if (all || type == NETCONFA_PROXY_NEIGH) size += nla_total_size(4); if (all || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) size += nla_total_size(4); return size; } static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex, struct ipv4_devconf *devconf, u32 portid, u32 seq, int event, unsigned int flags, int type) { struct nlmsghdr *nlh; struct netconfmsg *ncm; bool all = false; nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct netconfmsg), flags); if (!nlh) return -EMSGSIZE; if (type == NETCONFA_ALL) all = true; ncm = nlmsg_data(nlh); ncm->ncm_family = AF_INET; if (nla_put_s32(skb, NETCONFA_IFINDEX, ifindex) < 0) goto nla_put_failure; if (!devconf) goto out; if ((all || type == NETCONFA_FORWARDING) && nla_put_s32(skb, NETCONFA_FORWARDING, IPV4_DEVCONF(*devconf, FORWARDING)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_RP_FILTER) && nla_put_s32(skb, NETCONFA_RP_FILTER, IPV4_DEVCONF(*devconf, RP_FILTER)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_MC_FORWARDING) && nla_put_s32(skb, NETCONFA_MC_FORWARDING, IPV4_DEVCONF(*devconf, MC_FORWARDING)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_PROXY_NEIGH) && nla_put_s32(skb, NETCONFA_PROXY_NEIGH, IPV4_DEVCONF(*devconf, PROXY_ARP)) < 0) goto nla_put_failure; if ((all || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) && nla_put_s32(skb, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, IPV4_DEVCONF(*devconf, IGNORE_ROUTES_WITH_LINKDOWN)) < 0) goto nla_put_failure; out: nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } void inet_netconf_notify_devconf(struct net *net, int event, int type, int ifindex, struct ipv4_devconf *devconf) { struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(inet_netconf_msgsize_devconf(type), GFP_KERNEL); if (!skb) goto errout; err = inet_netconf_fill_devconf(skb, ifindex, devconf, 0, 0, event, 0, type); if (err < 0) { /* -EMSGSIZE implies BUG in inet_netconf_msgsize_devconf() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_IPV4_NETCONF, NULL, GFP_KERNEL); return; errout: if (err < 0) rtnl_set_sk_err(net, RTNLGRP_IPV4_NETCONF, err); } static const struct nla_policy devconf_ipv4_policy[NETCONFA_MAX+1] = { [NETCONFA_IFINDEX] = { .len = sizeof(int) }, [NETCONFA_FORWARDING] = { .len = sizeof(int) }, [NETCONFA_RP_FILTER] = { .len = sizeof(int) }, [NETCONFA_PROXY_NEIGH] = { .len = sizeof(int) }, [NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN] = { .len = sizeof(int) }, }; static int inet_netconf_get_devconf(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[NETCONFA_MAX+1]; struct netconfmsg *ncm; struct sk_buff *skb; struct ipv4_devconf *devconf; struct in_device *in_dev; struct net_device *dev; int ifindex; int err; err = nlmsg_parse(nlh, sizeof(*ncm), tb, NETCONFA_MAX, devconf_ipv4_policy, extack); if (err < 0) goto errout; err = -EINVAL; if (!tb[NETCONFA_IFINDEX]) goto errout; ifindex = nla_get_s32(tb[NETCONFA_IFINDEX]); switch (ifindex) { case NETCONFA_IFINDEX_ALL: devconf = net->ipv4.devconf_all; break; case NETCONFA_IFINDEX_DEFAULT: devconf = net->ipv4.devconf_dflt; break; default: dev = __dev_get_by_index(net, ifindex); if (!dev) goto errout; in_dev = __in_dev_get_rtnl(dev); if (!in_dev) goto errout; devconf = &in_dev->cnf; break; } err = -ENOBUFS; skb = nlmsg_new(inet_netconf_msgsize_devconf(NETCONFA_ALL), GFP_KERNEL); if (!skb) goto errout; err = inet_netconf_fill_devconf(skb, ifindex, devconf, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWNETCONF, 0, NETCONFA_ALL); if (err < 0) { /* -EMSGSIZE implies BUG in inet_netconf_msgsize_devconf() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout: return err; } static int inet_netconf_dump_devconf(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); int h, s_h; int idx, s_idx; struct net_device *dev; struct in_device *in_dev; struct hlist_head *head; s_h = cb->args[0]; s_idx = idx = cb->args[1]; for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; head = &net->dev_index_head[h]; rcu_read_lock(); cb->seq = atomic_read(&net->ipv4.dev_addr_genid) ^ net->dev_base_seq; hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; in_dev = __in_dev_get_rcu(dev); if (!in_dev) goto cont; if (inet_netconf_fill_devconf(skb, dev->ifindex, &in_dev->cnf, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNETCONF, NLM_F_MULTI, NETCONFA_ALL) < 0) { rcu_read_unlock(); goto done; } nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: idx++; } rcu_read_unlock(); } if (h == NETDEV_HASHENTRIES) { if (inet_netconf_fill_devconf(skb, NETCONFA_IFINDEX_ALL, net->ipv4.devconf_all, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNETCONF, NLM_F_MULTI, NETCONFA_ALL) < 0) goto done; else h++; } if (h == NETDEV_HASHENTRIES + 1) { if (inet_netconf_fill_devconf(skb, NETCONFA_IFINDEX_DEFAULT, net->ipv4.devconf_dflt, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNETCONF, NLM_F_MULTI, NETCONFA_ALL) < 0) goto done; else h++; } done: cb->args[0] = h; cb->args[1] = idx; return skb->len; } #ifdef CONFIG_SYSCTL static void devinet_copy_dflt_conf(struct net *net, int i) { struct net_device *dev; rcu_read_lock(); for_each_netdev_rcu(net, dev) { struct in_device *in_dev; in_dev = __in_dev_get_rcu(dev); if (in_dev && !test_bit(i, in_dev->cnf.state)) in_dev->cnf.data[i] = net->ipv4.devconf_dflt->data[i]; } rcu_read_unlock(); } /* called with RTNL locked */ static void inet_forward_change(struct net *net) { struct net_device *dev; int on = IPV4_DEVCONF_ALL(net, FORWARDING); IPV4_DEVCONF_ALL(net, ACCEPT_REDIRECTS) = !on; IPV4_DEVCONF_DFLT(net, FORWARDING) = on; inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, NETCONFA_IFINDEX_ALL, net->ipv4.devconf_all); inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, NETCONFA_IFINDEX_DEFAULT, net->ipv4.devconf_dflt); for_each_netdev(net, dev) { struct in_device *in_dev; if (on) dev_disable_lro(dev); in_dev = __in_dev_get_rtnl(dev); if (in_dev) { IN_DEV_CONF_SET(in_dev, FORWARDING, on); inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, dev->ifindex, &in_dev->cnf); } } } static int devinet_conf_ifindex(struct net *net, struct ipv4_devconf *cnf) { if (cnf == net->ipv4.devconf_dflt) return NETCONFA_IFINDEX_DEFAULT; else if (cnf == net->ipv4.devconf_all) return NETCONFA_IFINDEX_ALL; else { struct in_device *idev = container_of(cnf, struct in_device, cnf); return idev->dev->ifindex; } } static int devinet_conf_proc(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int old_value = *(int *)ctl->data; int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); int new_value = *(int *)ctl->data; if (write) { struct ipv4_devconf *cnf = ctl->extra1; struct net *net = ctl->extra2; int i = (int *)ctl->data - cnf->data; int ifindex; set_bit(i, cnf->state); if (cnf == net->ipv4.devconf_dflt) devinet_copy_dflt_conf(net, i); if (i == IPV4_DEVCONF_ACCEPT_LOCAL - 1 || i == IPV4_DEVCONF_ROUTE_LOCALNET - 1) if ((new_value == 0) && (old_value != 0)) rt_cache_flush(net); if (i == IPV4_DEVCONF_RP_FILTER - 1 && new_value != old_value) { ifindex = devinet_conf_ifindex(net, cnf); inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_RP_FILTER, ifindex, cnf); } if (i == IPV4_DEVCONF_PROXY_ARP - 1 && new_value != old_value) { ifindex = devinet_conf_ifindex(net, cnf); inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_PROXY_NEIGH, ifindex, cnf); } if (i == IPV4_DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN - 1 && new_value != old_value) { ifindex = devinet_conf_ifindex(net, cnf); inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, ifindex, cnf); } } return ret; } static int devinet_sysctl_forward(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; loff_t pos = *ppos; int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (write && *valp != val) { struct net *net = ctl->extra2; if (valp != &IPV4_DEVCONF_DFLT(net, FORWARDING)) { if (!rtnl_trylock()) { /* Restore the original values before restarting */ *valp = val; *ppos = pos; return restart_syscall(); } if (valp == &IPV4_DEVCONF_ALL(net, FORWARDING)) { inet_forward_change(net); } else { struct ipv4_devconf *cnf = ctl->extra1; struct in_device *idev = container_of(cnf, struct in_device, cnf); if (*valp) dev_disable_lro(idev->dev); inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, idev->dev->ifindex, cnf); } rtnl_unlock(); rt_cache_flush(net); } else inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_FORWARDING, NETCONFA_IFINDEX_DEFAULT, net->ipv4.devconf_dflt); } return ret; } static int ipv4_doint_and_flush(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); struct net *net = ctl->extra2; if (write && *valp != val) rt_cache_flush(net); return ret; } #define DEVINET_SYSCTL_ENTRY(attr, name, mval, proc) \ { \ .procname = name, \ .data = ipv4_devconf.data + \ IPV4_DEVCONF_ ## attr - 1, \ .maxlen = sizeof(int), \ .mode = mval, \ .proc_handler = proc, \ .extra1 = &ipv4_devconf, \ } #define DEVINET_SYSCTL_RW_ENTRY(attr, name) \ DEVINET_SYSCTL_ENTRY(attr, name, 0644, devinet_conf_proc) #define DEVINET_SYSCTL_RO_ENTRY(attr, name) \ DEVINET_SYSCTL_ENTRY(attr, name, 0444, devinet_conf_proc) #define DEVINET_SYSCTL_COMPLEX_ENTRY(attr, name, proc) \ DEVINET_SYSCTL_ENTRY(attr, name, 0644, proc) #define DEVINET_SYSCTL_FLUSHING_ENTRY(attr, name) \ DEVINET_SYSCTL_COMPLEX_ENTRY(attr, name, ipv4_doint_and_flush) static struct devinet_sysctl_table { struct ctl_table_header *sysctl_header; struct ctl_table devinet_vars[__IPV4_DEVCONF_MAX]; } devinet_sysctl = { .devinet_vars = { DEVINET_SYSCTL_COMPLEX_ENTRY(FORWARDING, "forwarding", devinet_sysctl_forward), DEVINET_SYSCTL_RO_ENTRY(MC_FORWARDING, "mc_forwarding"), DEVINET_SYSCTL_RW_ENTRY(ACCEPT_REDIRECTS, "accept_redirects"), DEVINET_SYSCTL_RW_ENTRY(SECURE_REDIRECTS, "secure_redirects"), DEVINET_SYSCTL_RW_ENTRY(SHARED_MEDIA, "shared_media"), DEVINET_SYSCTL_RW_ENTRY(RP_FILTER, "rp_filter"), DEVINET_SYSCTL_RW_ENTRY(SEND_REDIRECTS, "send_redirects"), DEVINET_SYSCTL_RW_ENTRY(ACCEPT_SOURCE_ROUTE, "accept_source_route"), DEVINET_SYSCTL_RW_ENTRY(ACCEPT_LOCAL, "accept_local"), DEVINET_SYSCTL_RW_ENTRY(SRC_VMARK, "src_valid_mark"), DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP, "proxy_arp"), DEVINET_SYSCTL_RW_ENTRY(MEDIUM_ID, "medium_id"), DEVINET_SYSCTL_RW_ENTRY(BOOTP_RELAY, "bootp_relay"), DEVINET_SYSCTL_RW_ENTRY(LOG_MARTIANS, "log_martians"), DEVINET_SYSCTL_RW_ENTRY(TAG, "tag"), DEVINET_SYSCTL_RW_ENTRY(ARPFILTER, "arp_filter"), DEVINET_SYSCTL_RW_ENTRY(ARP_ANNOUNCE, "arp_announce"), DEVINET_SYSCTL_RW_ENTRY(ARP_IGNORE, "arp_ignore"), DEVINET_SYSCTL_RW_ENTRY(ARP_ACCEPT, "arp_accept"), DEVINET_SYSCTL_RW_ENTRY(ARP_NOTIFY, "arp_notify"), DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP_PVLAN, "proxy_arp_pvlan"), DEVINET_SYSCTL_RW_ENTRY(FORCE_IGMP_VERSION, "force_igmp_version"), DEVINET_SYSCTL_RW_ENTRY(IGMPV2_UNSOLICITED_REPORT_INTERVAL, "igmpv2_unsolicited_report_interval"), DEVINET_SYSCTL_RW_ENTRY(IGMPV3_UNSOLICITED_REPORT_INTERVAL, "igmpv3_unsolicited_report_interval"), DEVINET_SYSCTL_RW_ENTRY(IGNORE_ROUTES_WITH_LINKDOWN, "ignore_routes_with_linkdown"), DEVINET_SYSCTL_RW_ENTRY(DROP_GRATUITOUS_ARP, "drop_gratuitous_arp"), DEVINET_SYSCTL_FLUSHING_ENTRY(NOXFRM, "disable_xfrm"), DEVINET_SYSCTL_FLUSHING_ENTRY(NOPOLICY, "disable_policy"), DEVINET_SYSCTL_FLUSHING_ENTRY(PROMOTE_SECONDARIES, "promote_secondaries"), DEVINET_SYSCTL_FLUSHING_ENTRY(ROUTE_LOCALNET, "route_localnet"), DEVINET_SYSCTL_FLUSHING_ENTRY(DROP_UNICAST_IN_L2_MULTICAST, "drop_unicast_in_l2_multicast"), }, }; static int __devinet_sysctl_register(struct net *net, char *dev_name, int ifindex, struct ipv4_devconf *p) { int i; struct devinet_sysctl_table *t; char path[sizeof("net/ipv4/conf/") + IFNAMSIZ]; t = kmemdup(&devinet_sysctl, sizeof(*t), GFP_KERNEL); if (!t) goto out; for (i = 0; i < ARRAY_SIZE(t->devinet_vars) - 1; i++) { t->devinet_vars[i].data += (char *)p - (char *)&ipv4_devconf; t->devinet_vars[i].extra1 = p; t->devinet_vars[i].extra2 = net; } snprintf(path, sizeof(path), "net/ipv4/conf/%s", dev_name); t->sysctl_header = register_net_sysctl(net, path, t->devinet_vars); if (!t->sysctl_header) goto free; p->sysctl = t; inet_netconf_notify_devconf(net, RTM_NEWNETCONF, NETCONFA_ALL, ifindex, p); return 0; free: kfree(t); out: return -ENOMEM; } static void __devinet_sysctl_unregister(struct net *net, struct ipv4_devconf *cnf, int ifindex) { struct devinet_sysctl_table *t = cnf->sysctl; if (t) { cnf->sysctl = NULL; unregister_net_sysctl_table(t->sysctl_header); kfree(t); } inet_netconf_notify_devconf(net, RTM_DELNETCONF, 0, ifindex, NULL); } static int devinet_sysctl_register(struct in_device *idev) { int err; if (!sysctl_dev_name_is_allowed(idev->dev->name)) return -EINVAL; err = neigh_sysctl_register(idev->dev, idev->arp_parms, NULL); if (err) return err; err = __devinet_sysctl_register(dev_net(idev->dev), idev->dev->name, idev->dev->ifindex, &idev->cnf); if (err) neigh_sysctl_unregister(idev->arp_parms); return err; } static void devinet_sysctl_unregister(struct in_device *idev) { struct net *net = dev_net(idev->dev); __devinet_sysctl_unregister(net, &idev->cnf, idev->dev->ifindex); neigh_sysctl_unregister(idev->arp_parms); } static struct ctl_table ctl_forward_entry[] = { { .procname = "ip_forward", .data = &ipv4_devconf.data[ IPV4_DEVCONF_FORWARDING - 1], .maxlen = sizeof(int), .mode = 0644, .proc_handler = devinet_sysctl_forward, .extra1 = &ipv4_devconf, .extra2 = &init_net, }, { }, }; #endif static __net_init int devinet_init_net(struct net *net) { int err; struct ipv4_devconf *all, *dflt; #ifdef CONFIG_SYSCTL struct ctl_table *tbl = ctl_forward_entry; struct ctl_table_header *forw_hdr; #endif err = -ENOMEM; all = &ipv4_devconf; dflt = &ipv4_devconf_dflt; if (!net_eq(net, &init_net)) { all = kmemdup(all, sizeof(ipv4_devconf), GFP_KERNEL); if (!all) goto err_alloc_all; dflt = kmemdup(dflt, sizeof(ipv4_devconf_dflt), GFP_KERNEL); if (!dflt) goto err_alloc_dflt; #ifdef CONFIG_SYSCTL tbl = kmemdup(tbl, sizeof(ctl_forward_entry), GFP_KERNEL); if (!tbl) goto err_alloc_ctl; tbl[0].data = &all->data[IPV4_DEVCONF_FORWARDING - 1]; tbl[0].extra1 = all; tbl[0].extra2 = net; #endif } #ifdef CONFIG_SYSCTL err = __devinet_sysctl_register(net, "all", NETCONFA_IFINDEX_ALL, all); if (err < 0) goto err_reg_all; err = __devinet_sysctl_register(net, "default", NETCONFA_IFINDEX_DEFAULT, dflt); if (err < 0) goto err_reg_dflt; err = -ENOMEM; forw_hdr = register_net_sysctl(net, "net/ipv4", tbl); if (!forw_hdr) goto err_reg_ctl; net->ipv4.forw_hdr = forw_hdr; #endif net->ipv4.devconf_all = all; net->ipv4.devconf_dflt = dflt; return 0; #ifdef CONFIG_SYSCTL err_reg_ctl: __devinet_sysctl_unregister(net, dflt, NETCONFA_IFINDEX_DEFAULT); err_reg_dflt: __devinet_sysctl_unregister(net, all, NETCONFA_IFINDEX_ALL); err_reg_all: if (tbl != ctl_forward_entry) kfree(tbl); err_alloc_ctl: #endif if (dflt != &ipv4_devconf_dflt) kfree(dflt); err_alloc_dflt: if (all != &ipv4_devconf) kfree(all); err_alloc_all: return err; } static __net_exit void devinet_exit_net(struct net *net) { #ifdef CONFIG_SYSCTL struct ctl_table *tbl; tbl = net->ipv4.forw_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv4.forw_hdr); __devinet_sysctl_unregister(net, net->ipv4.devconf_dflt, NETCONFA_IFINDEX_DEFAULT); __devinet_sysctl_unregister(net, net->ipv4.devconf_all, NETCONFA_IFINDEX_ALL); kfree(tbl); #endif kfree(net->ipv4.devconf_dflt); kfree(net->ipv4.devconf_all); } static __net_initdata struct pernet_operations devinet_ops = { .init = devinet_init_net, .exit = devinet_exit_net, }; static struct rtnl_af_ops inet_af_ops __read_mostly = { .family = AF_INET, .fill_link_af = inet_fill_link_af, .get_link_af_size = inet_get_link_af_size, .validate_link_af = inet_validate_link_af, .set_link_af = inet_set_link_af, }; void __init devinet_init(void) { int i; for (i = 0; i < IN4_ADDR_HSIZE; i++) INIT_HLIST_HEAD(&inet_addr_lst[i]); register_pernet_subsys(&devinet_ops); register_gifconf(PF_INET, inet_gifconf); register_netdevice_notifier(&ip_netdev_notifier); queue_delayed_work(system_power_efficient_wq, &check_lifetime_work, 0); rtnl_af_register(&inet_af_ops); rtnl_register(PF_INET, RTM_NEWADDR, inet_rtm_newaddr, NULL, 0); rtnl_register(PF_INET, RTM_DELADDR, inet_rtm_deladdr, NULL, 0); rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr, 0); rtnl_register(PF_INET, RTM_GETNETCONF, inet_netconf_get_devconf, inet_netconf_dump_devconf, 0); } |
| 1785 1782 1785 1784 1784 1785 1784 1785 708 397 876 877 39 39 39 39 39 39 39 39 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 | /* * fs/sysfs/symlink.c - sysfs symlink implementation * * Copyright (c) 2001-3 Patrick Mochel * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007 Tejun Heo <teheo@suse.de> * * This file is released under the GPLv2. * * Please see Documentation/filesystems/sysfs.txt for more information. */ #include <linux/fs.h> #include <linux/module.h> #include <linux/kobject.h> #include <linux/mutex.h> #include <linux/security.h> #include "sysfs.h" static int sysfs_do_create_link_sd(struct kernfs_node *parent, struct kobject *target_kobj, const char *name, int warn) { struct kernfs_node *kn, *target = NULL; BUG_ON(!name || !parent); /* * We don't own @target_kobj and it may be removed at any time. * Synchronize using sysfs_symlink_target_lock. See * sysfs_remove_dir() for details. */ spin_lock(&sysfs_symlink_target_lock); if (target_kobj->sd) { target = target_kobj->sd; kernfs_get(target); } spin_unlock(&sysfs_symlink_target_lock); if (!target) return -ENOENT; kn = kernfs_create_link(parent, name, target); kernfs_put(target); if (!IS_ERR(kn)) return 0; if (warn && PTR_ERR(kn) == -EEXIST) sysfs_warn_dup(parent, name); return PTR_ERR(kn); } /** * sysfs_create_link_sd - create symlink to a given object. * @kn: directory we're creating the link in. * @target: object we're pointing to. * @name: name of the symlink. */ int sysfs_create_link_sd(struct kernfs_node *kn, struct kobject *target, const char *name) { return sysfs_do_create_link_sd(kn, target, name, 1); } static int sysfs_do_create_link(struct kobject *kobj, struct kobject *target, const char *name, int warn) { struct kernfs_node *parent = NULL; if (!kobj) parent = sysfs_root_kn; else parent = kobj->sd; if (!parent) return -EFAULT; return sysfs_do_create_link_sd(parent, target, name, warn); } /** * sysfs_create_link - create symlink between two objects. * @kobj: object whose directory we're creating the link in. * @target: object we're pointing to. * @name: name of the symlink. */ int sysfs_create_link(struct kobject *kobj, struct kobject *target, const char *name) { return sysfs_do_create_link(kobj, target, name, 1); } EXPORT_SYMBOL_GPL(sysfs_create_link); /** * sysfs_create_link_nowarn - create symlink between two objects. * @kobj: object whose directory we're creating the link in. * @target: object we're pointing to. * @name: name of the symlink. * * This function does the same as sysfs_create_link(), but it * doesn't warn if the link already exists. */ int sysfs_create_link_nowarn(struct kobject *kobj, struct kobject *target, const char *name) { return sysfs_do_create_link(kobj, target, name, 0); } EXPORT_SYMBOL_GPL(sysfs_create_link_nowarn); /** * sysfs_delete_link - remove symlink in object's directory. * @kobj: object we're acting for. * @targ: object we're pointing to. * @name: name of the symlink to remove. * * Unlike sysfs_remove_link sysfs_delete_link has enough information * to successfully delete symlinks in tagged directories. */ void sysfs_delete_link(struct kobject *kobj, struct kobject *targ, const char *name) { const void *ns = NULL; /* * We don't own @target and it may be removed at any time. * Synchronize using sysfs_symlink_target_lock. See * sysfs_remove_dir() for details. */ spin_lock(&sysfs_symlink_target_lock); if (targ->sd && kernfs_ns_enabled(kobj->sd)) ns = targ->sd->ns; spin_unlock(&sysfs_symlink_target_lock); kernfs_remove_by_name_ns(kobj->sd, name, ns); } /** * sysfs_remove_link - remove symlink in object's directory. * @kobj: object we're acting for. * @name: name of the symlink to remove. */ void sysfs_remove_link(struct kobject *kobj, const char *name) { struct kernfs_node *parent = NULL; if (!kobj) parent = sysfs_root_kn; else parent = kobj->sd; kernfs_remove_by_name(parent, name); } EXPORT_SYMBOL_GPL(sysfs_remove_link); /** * sysfs_rename_link_ns - rename symlink in object's directory. * @kobj: object we're acting for. * @targ: object we're pointing to. * @old: previous name of the symlink. * @new: new name of the symlink. * @new_ns: new namespace of the symlink. * * A helper function for the common rename symlink idiom. */ int sysfs_rename_link_ns(struct kobject *kobj, struct kobject *targ, const char *old, const char *new, const void *new_ns) { struct kernfs_node *parent, *kn = NULL; const void *old_ns = NULL; int result; if (!kobj) parent = sysfs_root_kn; else parent = kobj->sd; if (targ->sd) old_ns = targ->sd->ns; result = -ENOENT; kn = kernfs_find_and_get_ns(parent, old, old_ns); if (!kn) goto out; result = -EINVAL; if (kernfs_type(kn) != KERNFS_LINK) goto out; if (kn->symlink.target_kn->priv != targ) goto out; result = kernfs_rename_ns(kn, parent, new, new_ns); out: kernfs_put(kn); return result; } EXPORT_SYMBOL_GPL(sysfs_rename_link_ns); |
| 3 3 2 2 2 4 4 4 4 4 4 3 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 | /* * cec-edid - HDMI Consumer Electronics Control EDID & CEC helper functions * * Copyright 2016 Cisco Systems, Inc. and/or its affiliates. All rights reserved. * * This program is free software; you may redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; version 2 of the License. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/types.h> #include <media/cec.h> u16 cec_get_edid_phys_addr(const u8 *edid, unsigned int size, unsigned int *offset) { unsigned int loc = cec_get_edid_spa_location(edid, size); if (offset) *offset = loc; if (loc == 0) return CEC_PHYS_ADDR_INVALID; return (edid[loc] << 8) | edid[loc + 1]; } EXPORT_SYMBOL_GPL(cec_get_edid_phys_addr); void cec_set_edid_phys_addr(u8 *edid, unsigned int size, u16 phys_addr) { unsigned int loc = cec_get_edid_spa_location(edid, size); u8 sum = 0; unsigned int i; if (loc == 0) return; edid[loc] = phys_addr >> 8; edid[loc + 1] = phys_addr & 0xff; loc &= ~0x7f; /* update the checksum */ for (i = loc; i < loc + 127; i++) sum += edid[i]; edid[i] = 256 - sum; } EXPORT_SYMBOL_GPL(cec_set_edid_phys_addr); u16 cec_phys_addr_for_input(u16 phys_addr, u8 input) { /* Check if input is sane */ if (WARN_ON(input == 0 || input > 0xf)) return CEC_PHYS_ADDR_INVALID; if (phys_addr == 0) return input << 12; if ((phys_addr & 0x0fff) == 0) return phys_addr | (input << 8); if ((phys_addr & 0x00ff) == 0) return phys_addr | (input << 4); if ((phys_addr & 0x000f) == 0) return phys_addr | input; /* * All nibbles are used so no valid physical addresses can be assigned * to the input. */ return CEC_PHYS_ADDR_INVALID; } EXPORT_SYMBOL_GPL(cec_phys_addr_for_input); int cec_phys_addr_validate(u16 phys_addr, u16 *parent, u16 *port) { int i; if (parent) *parent = phys_addr; if (port) *port = 0; if (phys_addr == CEC_PHYS_ADDR_INVALID) return 0; for (i = 0; i < 16; i += 4) if (phys_addr & (0xf << i)) break; if (i == 16) return 0; if (parent) *parent = phys_addr & (0xfff0 << i); if (port) *port = (phys_addr >> i) & 0xf; for (i += 4; i < 16; i += 4) if ((phys_addr & (0xf << i)) == 0) return -EINVAL; return 0; } EXPORT_SYMBOL_GPL(cec_phys_addr_validate); |
| 74 10 10 8 1 2 63 74 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 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 | /* * xfrm_replay.c - xfrm replay detection, derived from xfrm_state.c. * * Copyright (C) 2010 secunet Security Networks AG * Copyright (C) 2010 Steffen Klassert <steffen.klassert@secunet.com> * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, * version 2, as published by the Free Software Foundation. * * This program is distributed in the hope it will be useful, but WITHOUT * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for * more details. * * You should have received a copy of the GNU General Public License along with * this program; if not, write to the Free Software Foundation, Inc., * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. */ #include <linux/export.h> #include <net/xfrm.h> u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq) { u32 seq, seq_hi, bottom; struct xfrm_replay_state_esn *replay_esn = x->replay_esn; if (!(x->props.flags & XFRM_STATE_ESN)) return 0; seq = ntohl(net_seq); seq_hi = replay_esn->seq_hi; bottom = replay_esn->seq - replay_esn->replay_window + 1; if (likely(replay_esn->seq >= replay_esn->replay_window - 1)) { /* A. same subspace */ if (unlikely(seq < bottom)) seq_hi++; } else { /* B. window spans two subspaces */ if (unlikely(seq >= bottom)) seq_hi--; } return seq_hi; } EXPORT_SYMBOL(xfrm_replay_seqhi); ; static void xfrm_replay_notify(struct xfrm_state *x, int event) { struct km_event c; /* we send notify messages in case * 1. we updated on of the sequence numbers, and the seqno difference * is at least x->replay_maxdiff, in this case we also update the * timeout of our timer function * 2. if x->replay_maxage has elapsed since last update, * and there were changes * * The state structure must be locked! */ switch (event) { case XFRM_REPLAY_UPDATE: if (!x->replay_maxdiff || ((x->replay.seq - x->preplay.seq < x->replay_maxdiff) && (x->replay.oseq - x->preplay.oseq < x->replay_maxdiff))) { if (x->xflags & XFRM_TIME_DEFER) event = XFRM_REPLAY_TIMEOUT; else return; } break; case XFRM_REPLAY_TIMEOUT: if (memcmp(&x->replay, &x->preplay, sizeof(struct xfrm_replay_state)) == 0) { x->xflags |= XFRM_TIME_DEFER; return; } break; } memcpy(&x->preplay, &x->replay, sizeof(struct xfrm_replay_state)); c.event = XFRM_MSG_NEWAE; c.data.aevent = event; km_state_notify(x, &c); if (x->replay_maxage && !mod_timer(&x->rtimer, jiffies + x->replay_maxage)) x->xflags &= ~XFRM_TIME_DEFER; } static int xfrm_replay_overflow(struct xfrm_state *x, struct sk_buff *skb) { int err = 0; struct net *net = xs_net(x); if (x->type->flags & XFRM_TYPE_REPLAY_PROT) { XFRM_SKB_CB(skb)->seq.output.low = ++x->replay.oseq; XFRM_SKB_CB(skb)->seq.output.hi = 0; if (unlikely(x->replay.oseq == 0)) { x->replay.oseq--; xfrm_audit_state_replay_overflow(x, skb); err = -EOVERFLOW; return err; } if (xfrm_aevent_is_on(net)) x->repl->notify(x, XFRM_REPLAY_UPDATE); } return err; } static int xfrm_replay_check(struct xfrm_state *x, struct sk_buff *skb, __be32 net_seq) { u32 diff; u32 seq = ntohl(net_seq); if (!x->props.replay_window) return 0; if (unlikely(seq == 0)) goto err; if (likely(seq > x->replay.seq)) return 0; diff = x->replay.seq - seq; if (diff >= x->props.replay_window) { x->stats.replay_window++; goto err; } if (x->replay.bitmap & (1U << diff)) { x->stats.replay++; goto err; } return 0; err: xfrm_audit_state_replay(x, skb, net_seq); return -EINVAL; } static void xfrm_replay_advance(struct xfrm_state *x, __be32 net_seq) { u32 diff; u32 seq = ntohl(net_seq); if (!x->props.replay_window) return; if (seq > x->replay.seq) { diff = seq - x->replay.seq; if (diff < x->props.replay_window) x->replay.bitmap = ((x->replay.bitmap) << diff) | 1; else x->replay.bitmap = 1; x->replay.seq = seq; } else { diff = x->replay.seq - seq; x->replay.bitmap |= (1U << diff); } if (xfrm_aevent_is_on(xs_net(x))) x->repl->notify(x, XFRM_REPLAY_UPDATE); } static int xfrm_replay_overflow_bmp(struct xfrm_state *x, struct sk_buff *skb) { int err = 0; struct xfrm_replay_state_esn *replay_esn = x->replay_esn; struct net *net = xs_net(x); if (x->type->flags & XFRM_TYPE_REPLAY_PROT) { XFRM_SKB_CB(skb)->seq.output.low = ++replay_esn->oseq; XFRM_SKB_CB(skb)->seq.output.hi = 0; if (unlikely(replay_esn->oseq == 0)) { replay_esn->oseq--; xfrm_audit_state_replay_overflow(x, skb); err = -EOVERFLOW; return err; } if (xfrm_aevent_is_on(net)) x->repl->notify(x, XFRM_REPLAY_UPDATE); } return err; } static int xfrm_replay_check_bmp(struct xfrm_state *x, struct sk_buff *skb, __be32 net_seq) { unsigned int bitnr, nr; struct xfrm_replay_state_esn *replay_esn = x->replay_esn; u32 pos; u32 seq = ntohl(net_seq); u32 diff = replay_esn->seq - seq; if (!replay_esn->replay_window) return 0; if (unlikely(seq == 0)) goto err; if (likely(seq > replay_esn->seq)) return 0; if (diff >= replay_esn->replay_window) { x->stats.replay_window++; goto err; } pos = (replay_esn->seq - 1) % replay_esn->replay_window; if (pos >= diff) bitnr = (pos - diff) % replay_esn->replay_window; else bitnr = replay_esn->replay_window - (diff - pos); nr = bitnr >> 5; bitnr = bitnr & 0x1F; if (replay_esn->bmp[nr] & (1U << bitnr)) goto err_replay; return 0; err_replay: x->stats.replay++; err: xfrm_audit_state_replay(x, skb, net_seq); return -EINVAL; } static void xfrm_replay_advance_bmp(struct xfrm_state *x, __be32 net_seq) { unsigned int bitnr, nr, i; u32 diff; struct xfrm_replay_state_esn *replay_esn = x->replay_esn; u32 seq = ntohl(net_seq); u32 pos; if (!replay_esn->replay_window) return; pos = (replay_esn->seq - 1) % replay_esn->replay_window; if (seq > replay_esn->seq) { diff = seq - replay_esn->seq; if (diff < replay_esn->replay_window) { for (i = 1; i < diff; i++) { bitnr = (pos + i) % replay_esn->replay_window; nr = bitnr >> 5; bitnr = bitnr & 0x1F; replay_esn->bmp[nr] &= ~(1U << bitnr); } } else { nr = (replay_esn->replay_window - 1) >> 5; for (i = 0; i <= nr; i++) replay_esn->bmp[i] = 0; } bitnr = (pos + diff) % replay_esn->replay_window; replay_esn->seq = seq; } else { diff = replay_esn->seq - seq; if (pos >= diff) bitnr = (pos - diff) % replay_esn->replay_window; else bitnr = replay_esn->replay_window - (diff - pos); } nr = bitnr >> 5; bitnr = bitnr & 0x1F; replay_esn->bmp[nr] |= (1U << bitnr); if (xfrm_aevent_is_on(xs_net(x))) x->repl->notify(x, XFRM_REPLAY_UPDATE); } static void xfrm_replay_notify_bmp(struct xfrm_state *x, int event) { struct km_event c; struct xfrm_replay_state_esn *replay_esn = x->replay_esn; struct xfrm_replay_state_esn *preplay_esn = x->preplay_esn; /* we send notify messages in case * 1. we updated on of the sequence numbers, and the seqno difference * is at least x->replay_maxdiff, in this case we also update the * timeout of our timer function * 2. if x->replay_maxage has elapsed since last update, * and there were changes * * The state structure must be locked! */ switch (event) { case XFRM_REPLAY_UPDATE: if (!x->replay_maxdiff || ((replay_esn->seq - preplay_esn->seq < x->replay_maxdiff) && (replay_esn->oseq - preplay_esn->oseq < x->replay_maxdiff))) { if (x->xflags & XFRM_TIME_DEFER) event = XFRM_REPLAY_TIMEOUT; else return; } break; case XFRM_REPLAY_TIMEOUT: if (memcmp(x->replay_esn, x->preplay_esn, xfrm_replay_state_esn_len(replay_esn)) == 0) { x->xflags |= XFRM_TIME_DEFER; return; } break; } memcpy(x->preplay_esn, x->replay_esn, xfrm_replay_state_esn_len(replay_esn)); c.event = XFRM_MSG_NEWAE; c.data.aevent = event; km_state_notify(x, &c); if (x->replay_maxage && !mod_timer(&x->rtimer, jiffies + x->replay_maxage)) x->xflags &= ~XFRM_TIME_DEFER; } static void xfrm_replay_notify_esn(struct xfrm_state *x, int event) { u32 seq_diff, oseq_diff; struct km_event c; struct xfrm_replay_state_esn *replay_esn = x->replay_esn; struct xfrm_replay_state_esn *preplay_esn = x->preplay_esn; /* we send notify messages in case * 1. we updated on of the sequence numbers, and the seqno difference * is at least x->replay_maxdiff, in this case we also update the * timeout of our timer function * 2. if x->replay_maxage has elapsed since last update, * and there were changes * * The state structure must be locked! */ switch (event) { case XFRM_REPLAY_UPDATE: if (x->replay_maxdiff) { if (replay_esn->seq_hi == preplay_esn->seq_hi) seq_diff = replay_esn->seq - preplay_esn->seq; else seq_diff = ~preplay_esn->seq + replay_esn->seq + 1; if (replay_esn->oseq_hi == preplay_esn->oseq_hi) oseq_diff = replay_esn->oseq - preplay_esn->oseq; else oseq_diff = ~preplay_esn->oseq + replay_esn->oseq + 1; if (seq_diff >= x->replay_maxdiff || oseq_diff >= x->replay_maxdiff) break; } if (x->xflags & XFRM_TIME_DEFER) event = XFRM_REPLAY_TIMEOUT; else return; break; case XFRM_REPLAY_TIMEOUT: if (memcmp(x->replay_esn, x->preplay_esn, xfrm_replay_state_esn_len(replay_esn)) == 0) { x->xflags |= XFRM_TIME_DEFER; return; } break; } memcpy(x->preplay_esn, x->replay_esn, xfrm_replay_state_esn_len(replay_esn)); c.event = XFRM_MSG_NEWAE; c.data.aevent = event; km_state_notify(x, &c); if (x->replay_maxage && !mod_timer(&x->rtimer, jiffies + x->replay_maxage)) x->xflags &= ~XFRM_TIME_DEFER; } static int xfrm_replay_overflow_esn(struct xfrm_state *x, struct sk_buff *skb) { int err = 0; struct xfrm_replay_state_esn *replay_esn = x->replay_esn; struct net *net = xs_net(x); if (x->type->flags & XFRM_TYPE_REPLAY_PROT) { XFRM_SKB_CB(skb)->seq.output.low = ++replay_esn->oseq; XFRM_SKB_CB(skb)->seq.output.hi = replay_esn->oseq_hi; if (unlikely(replay_esn->oseq == 0)) { XFRM_SKB_CB(skb)->seq.output.hi = ++replay_esn->oseq_hi; if (replay_esn->oseq_hi == 0) { replay_esn->oseq--; replay_esn->oseq_hi--; xfrm_audit_state_replay_overflow(x, skb); err = -EOVERFLOW; return err; } } if (xfrm_aevent_is_on(net)) x->repl->notify(x, XFRM_REPLAY_UPDATE); } return err; } static int xfrm_replay_check_esn(struct xfrm_state *x, struct sk_buff *skb, __be32 net_seq) { unsigned int bitnr, nr; u32 diff; struct xfrm_replay_state_esn *replay_esn = x->replay_esn; u32 pos; u32 seq = ntohl(net_seq); u32 wsize = replay_esn->replay_window; u32 top = replay_esn->seq; u32 bottom = top - wsize + 1; if (!wsize) return 0; if (unlikely(seq == 0 && replay_esn->seq_hi == 0 && (replay_esn->seq < replay_esn->replay_window - 1))) goto err; diff = top - seq; if (likely(top >= wsize - 1)) { /* A. same subspace */ if (likely(seq > top) || seq < bottom) return 0; } else { /* B. window spans two subspaces */ if (likely(seq > top && seq < bottom)) return 0; if (seq >= bottom) diff = ~seq + top + 1; } if (diff >= replay_esn->replay_window) { x->stats.replay_window++; goto err; } pos = (replay_esn->seq - 1) % replay_esn->replay_window; if (pos >= diff) bitnr = (pos - diff) % replay_esn->replay_window; else bitnr = replay_esn->replay_window - (diff - pos); nr = bitnr >> 5; bitnr = bitnr & 0x1F; if (replay_esn->bmp[nr] & (1U << bitnr)) goto err_replay; return 0; err_replay: x->stats.replay++; err: xfrm_audit_state_replay(x, skb, net_seq); return -EINVAL; } static int xfrm_replay_recheck_esn(struct xfrm_state *x, struct sk_buff *skb, __be32 net_seq) { if (unlikely(XFRM_SKB_CB(skb)->seq.input.hi != htonl(xfrm_replay_seqhi(x, net_seq)))) { x->stats.replay_window++; return -EINVAL; } return xfrm_replay_check_esn(x, skb, net_seq); } static void xfrm_replay_advance_esn(struct xfrm_state *x, __be32 net_seq) { unsigned int bitnr, nr, i; int wrap; u32 diff, pos, seq, seq_hi; struct xfrm_replay_state_esn *replay_esn = x->replay_esn; if (!replay_esn->replay_window) return; seq = ntohl(net_seq); pos = (replay_esn->seq - 1) % replay_esn->replay_window; seq_hi = xfrm_replay_seqhi(x, net_seq); wrap = seq_hi - replay_esn->seq_hi; if ((!wrap && seq > replay_esn->seq) || wrap > 0) { if (likely(!wrap)) diff = seq - replay_esn->seq; else diff = ~replay_esn->seq + seq + 1; if (diff < replay_esn->replay_window) { for (i = 1; i < diff; i++) { bitnr = (pos + i) % replay_esn->replay_window; nr = bitnr >> 5; bitnr = bitnr & 0x1F; replay_esn->bmp[nr] &= ~(1U << bitnr); } } else { nr = (replay_esn->replay_window - 1) >> 5; for (i = 0; i <= nr; i++) replay_esn->bmp[i] = 0; } bitnr = (pos + diff) % replay_esn->replay_window; replay_esn->seq = seq; if (unlikely(wrap > 0)) replay_esn->seq_hi++; } else { diff = replay_esn->seq - seq; if (pos >= diff) bitnr = (pos - diff) % replay_esn->replay_window; else bitnr = replay_esn->replay_window - (diff - pos); } nr = bitnr >> 5; bitnr = bitnr & 0x1F; replay_esn->bmp[nr] |= (1U << bitnr); if (xfrm_aevent_is_on(xs_net(x))) x->repl->notify(x, XFRM_REPLAY_UPDATE); } #ifdef CONFIG_XFRM_OFFLOAD static int xfrm_replay_overflow_offload(struct xfrm_state *x, struct sk_buff *skb) { int err = 0; struct net *net = xs_net(x); struct xfrm_offload *xo = xfrm_offload(skb); __u32 oseq = x->replay.oseq; if (!xo) return xfrm_replay_overflow(x, skb); if (x->type->flags & XFRM_TYPE_REPLAY_PROT) { if (!skb_is_gso(skb)) { XFRM_SKB_CB(skb)->seq.output.low = ++oseq; xo->seq.low = oseq; } else { XFRM_SKB_CB(skb)->seq.output.low = oseq + 1; xo->seq.low = oseq + 1; oseq += skb_shinfo(skb)->gso_segs; } XFRM_SKB_CB(skb)->seq.output.hi = 0; xo->seq.hi = 0; if (unlikely(oseq < x->replay.oseq)) { xfrm_audit_state_replay_overflow(x, skb); err = -EOVERFLOW; return err; } x->replay.oseq = oseq; if (xfrm_aevent_is_on(net)) x->repl->notify(x, XFRM_REPLAY_UPDATE); } return err; } static int xfrm_replay_overflow_offload_bmp(struct xfrm_state *x, struct sk_buff *skb) { int err = 0; struct xfrm_offload *xo = xfrm_offload(skb); struct xfrm_replay_state_esn *replay_esn = x->replay_esn; struct net *net = xs_net(x); __u32 oseq = replay_esn->oseq; if (!xo) return xfrm_replay_overflow_bmp(x, skb); if (x->type->flags & XFRM_TYPE_REPLAY_PROT) { if (!skb_is_gso(skb)) { XFRM_SKB_CB(skb)->seq.output.low = ++oseq; xo->seq.low = oseq; } else { XFRM_SKB_CB(skb)->seq.output.low = oseq + 1; xo->seq.low = oseq + 1; oseq += skb_shinfo(skb)->gso_segs; } XFRM_SKB_CB(skb)->seq.output.hi = 0; xo->seq.hi = 0; if (unlikely(oseq < replay_esn->oseq)) { xfrm_audit_state_replay_overflow(x, skb); err = -EOVERFLOW; return err; } else { replay_esn->oseq = oseq; } if (xfrm_aevent_is_on(net)) x->repl->notify(x, XFRM_REPLAY_UPDATE); } return err; } static int xfrm_replay_overflow_offload_esn(struct xfrm_state *x, struct sk_buff *skb) { int err = 0; struct xfrm_offload *xo = xfrm_offload(skb); struct xfrm_replay_state_esn *replay_esn = x->replay_esn; struct net *net = xs_net(x); __u32 oseq = replay_esn->oseq; __u32 oseq_hi = replay_esn->oseq_hi; if (!xo) return xfrm_replay_overflow_esn(x, skb); if (x->type->flags & XFRM_TYPE_REPLAY_PROT) { if (!skb_is_gso(skb)) { XFRM_SKB_CB(skb)->seq.output.low = ++oseq; XFRM_SKB_CB(skb)->seq.output.hi = oseq_hi; xo->seq.low = oseq; xo->seq.hi = oseq_hi; } else { XFRM_SKB_CB(skb)->seq.output.low = oseq + 1; XFRM_SKB_CB(skb)->seq.output.hi = oseq_hi; xo->seq.low = oseq + 1; xo->seq.hi = oseq_hi; oseq += skb_shinfo(skb)->gso_segs; } if (unlikely(oseq < replay_esn->oseq)) { XFRM_SKB_CB(skb)->seq.output.hi = ++oseq_hi; xo->seq.hi = oseq_hi; replay_esn->oseq_hi = oseq_hi; if (replay_esn->oseq_hi == 0) { replay_esn->oseq--; replay_esn->oseq_hi--; xfrm_audit_state_replay_overflow(x, skb); err = -EOVERFLOW; return err; } } replay_esn->oseq = oseq; if (xfrm_aevent_is_on(net)) x->repl->notify(x, XFRM_REPLAY_UPDATE); } return err; } static const struct xfrm_replay xfrm_replay_legacy = { .advance = xfrm_replay_advance, .check = xfrm_replay_check, .recheck = xfrm_replay_check, .notify = xfrm_replay_notify, .overflow = xfrm_replay_overflow_offload, }; static const struct xfrm_replay xfrm_replay_bmp = { .advance = xfrm_replay_advance_bmp, .check = xfrm_replay_check_bmp, .recheck = xfrm_replay_check_bmp, .notify = xfrm_replay_notify_bmp, .overflow = xfrm_replay_overflow_offload_bmp, }; static const struct xfrm_replay xfrm_replay_esn = { .advance = xfrm_replay_advance_esn, .check = xfrm_replay_check_esn, .recheck = xfrm_replay_recheck_esn, .notify = xfrm_replay_notify_esn, .overflow = xfrm_replay_overflow_offload_esn, }; #else static const struct xfrm_replay xfrm_replay_legacy = { .advance = xfrm_replay_advance, .check = xfrm_replay_check, .recheck = xfrm_replay_check, .notify = xfrm_replay_notify, .overflow = xfrm_replay_overflow, }; static const struct xfrm_replay xfrm_replay_bmp = { .advance = xfrm_replay_advance_bmp, .check = xfrm_replay_check_bmp, .recheck = xfrm_replay_check_bmp, .notify = xfrm_replay_notify_bmp, .overflow = xfrm_replay_overflow_bmp, }; static const struct xfrm_replay xfrm_replay_esn = { .advance = xfrm_replay_advance_esn, .check = xfrm_replay_check_esn, .recheck = xfrm_replay_recheck_esn, .notify = xfrm_replay_notify_esn, .overflow = xfrm_replay_overflow_esn, }; #endif int xfrm_init_replay(struct xfrm_state *x) { struct xfrm_replay_state_esn *replay_esn = x->replay_esn; if (replay_esn) { if (replay_esn->replay_window > replay_esn->bmp_len * sizeof(__u32) * 8) return -EINVAL; if (x->props.flags & XFRM_STATE_ESN) { if (replay_esn->replay_window == 0) return -EINVAL; x->repl = &xfrm_replay_esn; } else { x->repl = &xfrm_replay_bmp; } } else { x->repl = &xfrm_replay_legacy; } return 0; } EXPORT_SYMBOL(xfrm_init_replay); |
| 175 1 2 3 1 1 1 10 10 2 61 121 89 89 115 121 81 53 37 41 50 108 108 108 108 108 108 120 121 81 121 73 121 6 6 121 121 120 37 121 108 121 150 108 108 108 4 3 6 6 5 6 6 6 162 140 86 56 162 64 28 63 35 35 4 35 34 161 162 157 158 161 66 141 61 66 52 53 1 52 62 4 65 66 66 60 56 61 160 59 3 3 39 37 161 12 12 12 8 12 29 4 4 29 30 3 3 3 3 3 1 3 3 1 1 1 1 1 1 1 1 1 1 31 31 29 2 1 1 31 29 30 30 31 31 31 4 4 30 30 11 11 9 9 8 8 8 8 8 83 102 102 101 101 101 101 101 4 102 2 2 175 10 9 3 176 176 175 1 174 9 9 175 155 4 3 2 2 2 2 2 74 74 74 74 71 74 1 74 74 74 74 37 39 3 36 38 38 38 38 37 2 2 37 2 1 37 37 2 37 37 37 38 38 36 38 37 39 53 53 53 53 53 53 48 53 53 1 53 53 53 53 53 53 53 53 53 53 53 36 36 22 22 22 22 22 36 144 125 125 2 104 3 104 104 104 102 102 101 3 3 3 3 3 3 167 167 107 2 2 2 2 3 2 3 2 2 2 2 2 102 102 102 102 101 6 2 2 1 53 53 1 1 1 1 1 1 1 52 52 53 53 53 52 52 1 1 53 52 1 53 53 54 53 52 1 53 53 53 53 53 94 94 94 94 92 91 91 91 91 94 94 93 93 93 93 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 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 | /* * fs/f2fs/node.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> #include <linux/mpage.h> #include <linux/backing-dev.h> #include <linux/blkdev.h> #include <linux/pagevec.h> #include <linux/swap.h> #include "f2fs.h" #include "node.h" #include "segment.h" #include "xattr.h" #include "trace.h" #include <trace/events/f2fs.h> #define on_build_free_nids(nmi) mutex_is_locked(&(nm_i)->build_lock) static struct kmem_cache *nat_entry_slab; static struct kmem_cache *free_nid_slab; static struct kmem_cache *nat_entry_set_slab; /* * Check whether the given nid is within node id range. */ int check_nid_range(struct f2fs_sb_info *sbi, nid_t nid) { if (unlikely(nid < F2FS_ROOT_INO(sbi) || nid >= NM_I(sbi)->max_nid)) { set_sbi_flag(sbi, SBI_NEED_FSCK); f2fs_msg(sbi->sb, KERN_WARNING, "%s: out-of-range nid=%x, run fsck to fix.", __func__, nid); return -EFSCORRUPTED; } return 0; } bool available_free_memory(struct f2fs_sb_info *sbi, int type) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct sysinfo val; unsigned long avail_ram; unsigned long mem_size = 0; bool res = false; si_meminfo(&val); /* only uses low memory */ avail_ram = val.totalram - val.totalhigh; /* * give 25%, 25%, 50%, 50%, 50% memory for each components respectively */ if (type == FREE_NIDS) { mem_size = (nm_i->nid_cnt[FREE_NID_LIST] * sizeof(struct free_nid)) >> PAGE_SHIFT; res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2); } else if (type == NAT_ENTRIES) { mem_size = (nm_i->nat_cnt * sizeof(struct nat_entry)) >> PAGE_SHIFT; res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 2); if (excess_cached_nats(sbi)) res = false; } else if (type == DIRTY_DENTS) { if (sbi->sb->s_bdi->wb.dirty_exceeded) return false; mem_size = get_pages(sbi, F2FS_DIRTY_DENTS); res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1); } else if (type == INO_ENTRIES) { int i; for (i = 0; i <= UPDATE_INO; i++) mem_size += sbi->im[i].ino_num * sizeof(struct ino_entry); mem_size >>= PAGE_SHIFT; res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1); } else if (type == EXTENT_CACHE) { mem_size = (atomic_read(&sbi->total_ext_tree) * sizeof(struct extent_tree) + atomic_read(&sbi->total_ext_node) * sizeof(struct extent_node)) >> PAGE_SHIFT; res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1); } else { if (!sbi->sb->s_bdi->wb.dirty_exceeded) return true; } return res; } static void clear_node_page_dirty(struct page *page) { struct address_space *mapping = page->mapping; unsigned int long flags; if (PageDirty(page)) { spin_lock_irqsave(&mapping->tree_lock, flags); radix_tree_tag_clear(&mapping->page_tree, page_index(page), PAGECACHE_TAG_DIRTY); spin_unlock_irqrestore(&mapping->tree_lock, flags); clear_page_dirty_for_io(page); dec_page_count(F2FS_M_SB(mapping), F2FS_DIRTY_NODES); } ClearPageUptodate(page); } static struct page *get_current_nat_page(struct f2fs_sb_info *sbi, nid_t nid) { pgoff_t index = current_nat_addr(sbi, nid); return get_meta_page(sbi, index); } static struct page *get_next_nat_page(struct f2fs_sb_info *sbi, nid_t nid) { struct page *src_page; struct page *dst_page; pgoff_t src_off; pgoff_t dst_off; void *src_addr; void *dst_addr; struct f2fs_nm_info *nm_i = NM_I(sbi); src_off = current_nat_addr(sbi, nid); dst_off = next_nat_addr(sbi, src_off); /* get current nat block page with lock */ src_page = get_meta_page(sbi, src_off); dst_page = grab_meta_page(sbi, dst_off); f2fs_bug_on(sbi, PageDirty(src_page)); src_addr = page_address(src_page); dst_addr = page_address(dst_page); memcpy(dst_addr, src_addr, PAGE_SIZE); set_page_dirty(dst_page); f2fs_put_page(src_page, 1); set_to_next_nat(nm_i, nid); return dst_page; } static struct nat_entry *__lookup_nat_cache(struct f2fs_nm_info *nm_i, nid_t n) { return radix_tree_lookup(&nm_i->nat_root, n); } static unsigned int __gang_lookup_nat_cache(struct f2fs_nm_info *nm_i, nid_t start, unsigned int nr, struct nat_entry **ep) { return radix_tree_gang_lookup(&nm_i->nat_root, (void **)ep, start, nr); } static void __del_from_nat_cache(struct f2fs_nm_info *nm_i, struct nat_entry *e) { list_del(&e->list); radix_tree_delete(&nm_i->nat_root, nat_get_nid(e)); nm_i->nat_cnt--; kmem_cache_free(nat_entry_slab, e); } static void __set_nat_cache_dirty(struct f2fs_nm_info *nm_i, struct nat_entry *ne) { nid_t set = NAT_BLOCK_OFFSET(ne->ni.nid); struct nat_entry_set *head; head = radix_tree_lookup(&nm_i->nat_set_root, set); if (!head) { head = f2fs_kmem_cache_alloc(nat_entry_set_slab, GFP_NOFS); INIT_LIST_HEAD(&head->entry_list); INIT_LIST_HEAD(&head->set_list); head->set = set; head->entry_cnt = 0; f2fs_radix_tree_insert(&nm_i->nat_set_root, set, head); } if (get_nat_flag(ne, IS_DIRTY)) goto refresh_list; nm_i->dirty_nat_cnt++; head->entry_cnt++; set_nat_flag(ne, IS_DIRTY, true); refresh_list: if (nat_get_blkaddr(ne) == NEW_ADDR) list_del_init(&ne->list); else list_move_tail(&ne->list, &head->entry_list); } static void __clear_nat_cache_dirty(struct f2fs_nm_info *nm_i, struct nat_entry_set *set, struct nat_entry *ne) { list_move_tail(&ne->list, &nm_i->nat_entries); set_nat_flag(ne, IS_DIRTY, false); set->entry_cnt--; nm_i->dirty_nat_cnt--; } static unsigned int __gang_lookup_nat_set(struct f2fs_nm_info *nm_i, nid_t start, unsigned int nr, struct nat_entry_set **ep) { return radix_tree_gang_lookup(&nm_i->nat_set_root, (void **)ep, start, nr); } int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct nat_entry *e; bool need = false; down_read(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, nid); if (e) { if (!get_nat_flag(e, IS_CHECKPOINTED) && !get_nat_flag(e, HAS_FSYNCED_INODE)) need = true; } up_read(&nm_i->nat_tree_lock); return need; } bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct nat_entry *e; bool is_cp = true; down_read(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, nid); if (e && !get_nat_flag(e, IS_CHECKPOINTED)) is_cp = false; up_read(&nm_i->nat_tree_lock); return is_cp; } bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct nat_entry *e; bool need_update = true; down_read(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, ino); if (e && get_nat_flag(e, HAS_LAST_FSYNC) && (get_nat_flag(e, IS_CHECKPOINTED) || get_nat_flag(e, HAS_FSYNCED_INODE))) need_update = false; up_read(&nm_i->nat_tree_lock); return need_update; } static struct nat_entry *grab_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid, bool no_fail) { struct nat_entry *new; if (no_fail) { new = f2fs_kmem_cache_alloc(nat_entry_slab, GFP_NOFS); f2fs_radix_tree_insert(&nm_i->nat_root, nid, new); } else { new = kmem_cache_alloc(nat_entry_slab, GFP_NOFS); if (!new) return NULL; if (radix_tree_insert(&nm_i->nat_root, nid, new)) { kmem_cache_free(nat_entry_slab, new); return NULL; } } memset(new, 0, sizeof(struct nat_entry)); nat_set_nid(new, nid); nat_reset_flag(new); list_add_tail(&new->list, &nm_i->nat_entries); nm_i->nat_cnt++; return new; } static void cache_nat_entry(struct f2fs_sb_info *sbi, nid_t nid, struct f2fs_nat_entry *ne) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct nat_entry *e; e = __lookup_nat_cache(nm_i, nid); if (!e) { e = grab_nat_entry(nm_i, nid, false); if (e) node_info_from_raw_nat(&e->ni, ne); } else { f2fs_bug_on(sbi, nat_get_ino(e) != le32_to_cpu(ne->ino) || nat_get_blkaddr(e) != le32_to_cpu(ne->block_addr) || nat_get_version(e) != ne->version); } } static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, block_t new_blkaddr, bool fsync_done) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct nat_entry *e; down_write(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, ni->nid); if (!e) { e = grab_nat_entry(nm_i, ni->nid, true); copy_node_info(&e->ni, ni); f2fs_bug_on(sbi, ni->blk_addr == NEW_ADDR); } else if (new_blkaddr == NEW_ADDR) { /* * when nid is reallocated, * previous nat entry can be remained in nat cache. * So, reinitialize it with new information. */ copy_node_info(&e->ni, ni); f2fs_bug_on(sbi, ni->blk_addr != NULL_ADDR); } /* sanity check */ f2fs_bug_on(sbi, nat_get_blkaddr(e) != ni->blk_addr); f2fs_bug_on(sbi, nat_get_blkaddr(e) == NULL_ADDR && new_blkaddr == NULL_ADDR); f2fs_bug_on(sbi, nat_get_blkaddr(e) == NEW_ADDR && new_blkaddr == NEW_ADDR); f2fs_bug_on(sbi, is_valid_data_blkaddr(sbi, nat_get_blkaddr(e)) && new_blkaddr == NEW_ADDR); /* increment version no as node is removed */ if (nat_get_blkaddr(e) != NEW_ADDR && new_blkaddr == NULL_ADDR) { unsigned char version = nat_get_version(e); nat_set_version(e, inc_node_version(version)); /* in order to reuse the nid */ if (nm_i->next_scan_nid > ni->nid) nm_i->next_scan_nid = ni->nid; } /* change address */ nat_set_blkaddr(e, new_blkaddr); if (!is_valid_data_blkaddr(sbi, new_blkaddr)) set_nat_flag(e, IS_CHECKPOINTED, false); __set_nat_cache_dirty(nm_i, e); /* update fsync_mark if its inode nat entry is still alive */ if (ni->nid != ni->ino) e = __lookup_nat_cache(nm_i, ni->ino); if (e) { if (fsync_done && ni->nid == ni->ino) set_nat_flag(e, HAS_FSYNCED_INODE, true); set_nat_flag(e, HAS_LAST_FSYNC, fsync_done); } up_write(&nm_i->nat_tree_lock); } int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) { struct f2fs_nm_info *nm_i = NM_I(sbi); int nr = nr_shrink; if (!down_write_trylock(&nm_i->nat_tree_lock)) return 0; while (nr_shrink && !list_empty(&nm_i->nat_entries)) { struct nat_entry *ne; ne = list_first_entry(&nm_i->nat_entries, struct nat_entry, list); __del_from_nat_cache(nm_i, ne); nr_shrink--; } up_write(&nm_i->nat_tree_lock); return nr - nr_shrink; } /* * This function always returns success */ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); struct f2fs_journal *journal = curseg->journal; nid_t start_nid = START_NID(nid); struct f2fs_nat_block *nat_blk; struct page *page = NULL; struct f2fs_nat_entry ne; struct nat_entry *e; pgoff_t index; int i; ni->nid = nid; /* Check nat cache */ down_read(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, nid); if (e) { ni->ino = nat_get_ino(e); ni->blk_addr = nat_get_blkaddr(e); ni->version = nat_get_version(e); up_read(&nm_i->nat_tree_lock); return; } memset(&ne, 0, sizeof(struct f2fs_nat_entry)); /* Check current segment summary */ down_read(&curseg->journal_rwsem); i = lookup_journal_in_cursum(journal, NAT_JOURNAL, nid, 0); if (i >= 0) { ne = nat_in_journal(journal, i); node_info_from_raw_nat(ni, &ne); } up_read(&curseg->journal_rwsem); if (i >= 0) { up_read(&nm_i->nat_tree_lock); goto cache; } /* Fill node_info from nat page */ index = current_nat_addr(sbi, nid); up_read(&nm_i->nat_tree_lock); page = get_meta_page(sbi, index); nat_blk = (struct f2fs_nat_block *)page_address(page); ne = nat_blk->entries[nid - start_nid]; node_info_from_raw_nat(ni, &ne); f2fs_put_page(page, 1); cache: /* cache nat entry */ down_write(&nm_i->nat_tree_lock); cache_nat_entry(sbi, nid, &ne); up_write(&nm_i->nat_tree_lock); } /* * readahead MAX_RA_NODE number of node pages. */ static void ra_node_pages(struct page *parent, int start, int n) { struct f2fs_sb_info *sbi = F2FS_P_SB(parent); struct blk_plug plug; int i, end; nid_t nid; blk_start_plug(&plug); /* Then, try readahead for siblings of the desired node */ end = start + n; end = min(end, NIDS_PER_BLOCK); for (i = start; i < end; i++) { nid = get_nid(parent, i, false); ra_node_page(sbi, nid); } blk_finish_plug(&plug); } pgoff_t get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs) { const long direct_index = ADDRS_PER_INODE(dn->inode); const long direct_blks = ADDRS_PER_BLOCK; const long indirect_blks = ADDRS_PER_BLOCK * NIDS_PER_BLOCK; unsigned int skipped_unit = ADDRS_PER_BLOCK; int cur_level = dn->cur_level; int max_level = dn->max_level; pgoff_t base = 0; if (!dn->max_level) return pgofs + 1; while (max_level-- > cur_level) skipped_unit *= NIDS_PER_BLOCK; switch (dn->max_level) { case 3: base += 2 * indirect_blks; case 2: base += 2 * direct_blks; case 1: base += direct_index; break; default: f2fs_bug_on(F2FS_I_SB(dn->inode), 1); } return ((pgofs - base) / skipped_unit + 1) * skipped_unit + base; } /* * The maximum depth is four. * Offset[0] will have raw inode offset. */ static int get_node_path(struct inode *inode, long block, int offset[4], unsigned int noffset[4]) { const long direct_index = ADDRS_PER_INODE(inode); const long direct_blks = ADDRS_PER_BLOCK; const long dptrs_per_blk = NIDS_PER_BLOCK; const long indirect_blks = ADDRS_PER_BLOCK * NIDS_PER_BLOCK; const long dindirect_blks = indirect_blks * NIDS_PER_BLOCK; int n = 0; int level = 0; noffset[0] = 0; if (block < direct_index) { offset[n] = block; goto got; } block -= direct_index; if (block < direct_blks) { offset[n++] = NODE_DIR1_BLOCK; noffset[n] = 1; offset[n] = block; level = 1; goto got; } block -= direct_blks; if (block < direct_blks) { offset[n++] = NODE_DIR2_BLOCK; noffset[n] = 2; offset[n] = block; level = 1; goto got; } block -= direct_blks; if (block < indirect_blks) { offset[n++] = NODE_IND1_BLOCK; noffset[n] = 3; offset[n++] = block / direct_blks; noffset[n] = 4 + offset[n - 1]; offset[n] = block % direct_blks; level = 2; goto got; } block -= indirect_blks; if (block < indirect_blks) { offset[n++] = NODE_IND2_BLOCK; noffset[n] = 4 + dptrs_per_blk; offset[n++] = block / direct_blks; noffset[n] = 5 + dptrs_per_blk + offset[n - 1]; offset[n] = block % direct_blks; level = 2; goto got; } block -= indirect_blks; if (block < dindirect_blks) { offset[n++] = NODE_DIND_BLOCK; noffset[n] = 5 + (dptrs_per_blk * 2); offset[n++] = block / indirect_blks; noffset[n] = 6 + (dptrs_per_blk * 2) + offset[n - 1] * (dptrs_per_blk + 1); offset[n++] = (block / direct_blks) % dptrs_per_blk; noffset[n] = 7 + (dptrs_per_blk * 2) + offset[n - 2] * (dptrs_per_blk + 1) + offset[n - 1]; offset[n] = block % direct_blks; level = 3; goto got; } else { return -E2BIG; } got: return level; } /* * Caller should call f2fs_put_dnode(dn). * Also, it should grab and release a rwsem by calling f2fs_lock_op() and * f2fs_unlock_op() only if ro is not set RDONLY_NODE. * In the case of RDONLY_NODE, we don't need to care about mutex. */ int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode) { struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); struct page *npage[4]; struct page *parent = NULL; int offset[4]; unsigned int noffset[4]; nid_t nids[4]; int level, i = 0; int err = 0; level = get_node_path(dn->inode, index, offset, noffset); if (level < 0) return level; nids[0] = dn->inode->i_ino; npage[0] = dn->inode_page; if (!npage[0]) { npage[0] = get_node_page(sbi, nids[0]); if (IS_ERR(npage[0])) return PTR_ERR(npage[0]); } /* if inline_data is set, should not report any block indices */ if (f2fs_has_inline_data(dn->inode) && index) { err = -ENOENT; f2fs_put_page(npage[0], 1); goto release_out; } parent = npage[0]; if (level != 0) nids[1] = get_nid(parent, offset[0], true); dn->inode_page = npage[0]; dn->inode_page_locked = true; /* get indirect or direct nodes */ for (i = 1; i <= level; i++) { bool done = false; if (!nids[i] && mode == ALLOC_NODE) { /* alloc new node */ if (!alloc_nid(sbi, &(nids[i]))) { err = -ENOSPC; goto release_pages; } dn->nid = nids[i]; npage[i] = new_node_page(dn, noffset[i]); if (IS_ERR(npage[i])) { alloc_nid_failed(sbi, nids[i]); err = PTR_ERR(npage[i]); goto release_pages; } set_nid(parent, offset[i - 1], nids[i], i == 1); alloc_nid_done(sbi, nids[i]); done = true; } else if (mode == LOOKUP_NODE_RA && i == level && level > 1) { npage[i] = get_node_page_ra(parent, offset[i - 1]); if (IS_ERR(npage[i])) { err = PTR_ERR(npage[i]); goto release_pages; } done = true; } if (i == 1) { dn->inode_page_locked = false; unlock_page(parent); } else { f2fs_put_page(parent, 1); } if (!done) { npage[i] = get_node_page(sbi, nids[i]); if (IS_ERR(npage[i])) { err = PTR_ERR(npage[i]); f2fs_put_page(npage[0], 0); goto release_out; } } if (i < level) { parent = npage[i]; nids[i + 1] = get_nid(parent, offset[i], false); } } dn->nid = nids[level]; dn->ofs_in_node = offset[level]; dn->node_page = npage[level]; dn->data_blkaddr = datablock_addr(dn->inode, dn->node_page, dn->ofs_in_node); return 0; release_pages: f2fs_put_page(parent, 1); if (i > 1) f2fs_put_page(npage[0], 0); release_out: dn->inode_page = NULL; dn->node_page = NULL; if (err == -ENOENT) { dn->cur_level = i; dn->max_level = level; dn->ofs_in_node = offset[level]; } return err; } static void truncate_node(struct dnode_of_data *dn) { struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); struct node_info ni; pgoff_t index; get_node_info(sbi, dn->nid, &ni); f2fs_bug_on(sbi, ni.blk_addr == NULL_ADDR); /* Deallocate node address */ invalidate_blocks(sbi, ni.blk_addr); dec_valid_node_count(sbi, dn->inode, dn->nid == dn->inode->i_ino); set_node_addr(sbi, &ni, NULL_ADDR, false); if (dn->nid == dn->inode->i_ino) { remove_orphan_inode(sbi, dn->nid); dec_valid_inode_count(sbi); f2fs_inode_synced(dn->inode); } clear_node_page_dirty(dn->node_page); set_sbi_flag(sbi, SBI_IS_DIRTY); index = dn->node_page->index; f2fs_put_page(dn->node_page, 1); invalidate_mapping_pages(NODE_MAPPING(sbi), index, index); dn->node_page = NULL; trace_f2fs_truncate_node(dn->inode, dn->nid, ni.blk_addr); } static int truncate_dnode(struct dnode_of_data *dn) { struct page *page; if (dn->nid == 0) return 1; /* get direct node */ page = get_node_page(F2FS_I_SB(dn->inode), dn->nid); if (IS_ERR(page) && PTR_ERR(page) == -ENOENT) return 1; else if (IS_ERR(page)) return PTR_ERR(page); /* Make dnode_of_data for parameter */ dn->node_page = page; dn->ofs_in_node = 0; truncate_data_blocks(dn); truncate_node(dn); return 1; } static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs, int ofs, int depth) { struct dnode_of_data rdn = *dn; struct page *page; struct f2fs_node *rn; nid_t child_nid; unsigned int child_nofs; int freed = 0; int i, ret; if (dn->nid == 0) return NIDS_PER_BLOCK + 1; trace_f2fs_truncate_nodes_enter(dn->inode, dn->nid, dn->data_blkaddr); page = get_node_page(F2FS_I_SB(dn->inode), dn->nid); if (IS_ERR(page)) { trace_f2fs_truncate_nodes_exit(dn->inode, PTR_ERR(page)); return PTR_ERR(page); } ra_node_pages(page, ofs, NIDS_PER_BLOCK); rn = F2FS_NODE(page); if (depth < 3) { for (i = ofs; i < NIDS_PER_BLOCK; i++, freed++) { child_nid = le32_to_cpu(rn->in.nid[i]); if (child_nid == 0) continue; rdn.nid = child_nid; ret = truncate_dnode(&rdn); if (ret < 0) goto out_err; if (set_nid(page, i, 0, false)) dn->node_changed = true; } } else { child_nofs = nofs + ofs * (NIDS_PER_BLOCK + 1) + 1; for (i = ofs; i < NIDS_PER_BLOCK; i++) { child_nid = le32_to_cpu(rn->in.nid[i]); if (child_nid == 0) { child_nofs += NIDS_PER_BLOCK + 1; continue; } rdn.nid = child_nid; ret = truncate_nodes(&rdn, child_nofs, 0, depth - 1); if (ret == (NIDS_PER_BLOCK + 1)) { if (set_nid(page, i, 0, false)) dn->node_changed = true; child_nofs += ret; } else if (ret < 0 && ret != -ENOENT) { goto out_err; } } freed = child_nofs; } if (!ofs) { /* remove current indirect node */ dn->node_page = page; truncate_node(dn); freed++; } else { f2fs_put_page(page, 1); } trace_f2fs_truncate_nodes_exit(dn->inode, freed); return freed; out_err: f2fs_put_page(page, 1); trace_f2fs_truncate_nodes_exit(dn->inode, ret); return ret; } static int truncate_partial_nodes(struct dnode_of_data *dn, struct f2fs_inode *ri, int *offset, int depth) { struct page *pages[2]; nid_t nid[3]; nid_t child_nid; int err = 0; int i; int idx = depth - 2; nid[0] = le32_to_cpu(ri->i_nid[offset[0] - NODE_DIR1_BLOCK]); if (!nid[0]) return 0; /* get indirect nodes in the path */ for (i = 0; i < idx + 1; i++) { /* reference count'll be increased */ pages[i] = get_node_page(F2FS_I_SB(dn->inode), nid[i]); if (IS_ERR(pages[i])) { err = PTR_ERR(pages[i]); idx = i - 1; goto fail; } nid[i + 1] = get_nid(pages[i], offset[i + 1], false); } ra_node_pages(pages[idx], offset[idx + 1], NIDS_PER_BLOCK); /* free direct nodes linked to a partial indirect node */ for (i = offset[idx + 1]; i < NIDS_PER_BLOCK; i++) { child_nid = get_nid(pages[idx], i, false); if (!child_nid) continue; dn->nid = child_nid; err = truncate_dnode(dn); if (err < 0) goto fail; if (set_nid(pages[idx], i, 0, false)) dn->node_changed = true; } if (offset[idx + 1] == 0) { dn->node_page = pages[idx]; dn->nid = nid[idx]; truncate_node(dn); } else { f2fs_put_page(pages[idx], 1); } offset[idx]++; offset[idx + 1] = 0; idx--; fail: for (i = idx; i >= 0; i--) f2fs_put_page(pages[i], 1); trace_f2fs_truncate_partial_nodes(dn->inode, nid, depth, err); return err; } /* * All the block addresses of data and nodes should be nullified. */ int truncate_inode_blocks(struct inode *inode, pgoff_t from) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); int err = 0, cont = 1; int level, offset[4], noffset[4]; unsigned int nofs = 0; struct f2fs_inode *ri; struct dnode_of_data dn; struct page *page; trace_f2fs_truncate_inode_blocks_enter(inode, from); level = get_node_path(inode, from, offset, noffset); if (level < 0) return level; page = get_node_page(sbi, inode->i_ino); if (IS_ERR(page)) { trace_f2fs_truncate_inode_blocks_exit(inode, PTR_ERR(page)); return PTR_ERR(page); } set_new_dnode(&dn, inode, page, NULL, 0); unlock_page(page); ri = F2FS_INODE(page); switch (level) { case 0: case 1: nofs = noffset[1]; break; case 2: nofs = noffset[1]; if (!offset[level - 1]) goto skip_partial; err = truncate_partial_nodes(&dn, ri, offset, level); if (err < 0 && err != -ENOENT) goto fail; nofs += 1 + NIDS_PER_BLOCK; break; case 3: nofs = 5 + 2 * NIDS_PER_BLOCK; if (!offset[level - 1]) goto skip_partial; err = truncate_partial_nodes(&dn, ri, offset, level); if (err < 0 && err != -ENOENT) goto fail; break; default: BUG(); } skip_partial: while (cont) { dn.nid = le32_to_cpu(ri->i_nid[offset[0] - NODE_DIR1_BLOCK]); switch (offset[0]) { case NODE_DIR1_BLOCK: case NODE_DIR2_BLOCK: err = truncate_dnode(&dn); break; case NODE_IND1_BLOCK: case NODE_IND2_BLOCK: err = truncate_nodes(&dn, nofs, offset[1], 2); break; case NODE_DIND_BLOCK: err = truncate_nodes(&dn, nofs, offset[1], 3); cont = 0; break; default: BUG(); } if (err < 0 && err != -ENOENT) goto fail; if (offset[1] == 0 && ri->i_nid[offset[0] - NODE_DIR1_BLOCK]) { lock_page(page); BUG_ON(page->mapping != NODE_MAPPING(sbi)); f2fs_wait_on_page_writeback(page, NODE, true); ri->i_nid[offset[0] - NODE_DIR1_BLOCK] = 0; set_page_dirty(page); unlock_page(page); } offset[1] = 0; offset[0]++; nofs += err; } fail: f2fs_put_page(page, 0); trace_f2fs_truncate_inode_blocks_exit(inode, err); return err > 0 ? 0 : err; } int truncate_xattr_node(struct inode *inode, struct page *page) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); nid_t nid = F2FS_I(inode)->i_xattr_nid; struct dnode_of_data dn; struct page *npage; if (!nid) return 0; npage = get_node_page(sbi, nid); if (IS_ERR(npage)) return PTR_ERR(npage); f2fs_i_xnid_write(inode, 0); set_new_dnode(&dn, inode, page, npage, nid); if (page) dn.inode_page_locked = true; truncate_node(&dn); return 0; } /* * Caller should grab and release a rwsem by calling f2fs_lock_op() and * f2fs_unlock_op(). */ int remove_inode_page(struct inode *inode) { struct dnode_of_data dn; int err; set_new_dnode(&dn, inode, NULL, NULL, inode->i_ino); err = get_dnode_of_data(&dn, 0, LOOKUP_NODE); if (err) return err; err = truncate_xattr_node(inode, dn.inode_page); if (err) { f2fs_put_dnode(&dn); return err; } /* remove potential inline_data blocks */ if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) truncate_data_blocks_range(&dn, 1); /* 0 is possible, after f2fs_new_inode() has failed */ f2fs_bug_on(F2FS_I_SB(inode), inode->i_blocks != 0 && inode->i_blocks != 8); /* will put inode & node pages */ truncate_node(&dn); return 0; } struct page *new_inode_page(struct inode *inode) { struct dnode_of_data dn; /* allocate inode page for new inode */ set_new_dnode(&dn, inode, NULL, NULL, inode->i_ino); /* caller should f2fs_put_page(page, 1); */ return new_node_page(&dn, 0); } struct page *new_node_page(struct dnode_of_data *dn, unsigned int ofs) { struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); struct node_info new_ni; struct page *page; int err; if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC))) return ERR_PTR(-EPERM); page = f2fs_grab_cache_page(NODE_MAPPING(sbi), dn->nid, false); if (!page) return ERR_PTR(-ENOMEM); if (unlikely((err = inc_valid_node_count(sbi, dn->inode, !ofs)))) goto fail; #ifdef CONFIG_F2FS_CHECK_FS get_node_info(sbi, dn->nid, &new_ni); f2fs_bug_on(sbi, new_ni.blk_addr != NULL_ADDR); #endif new_ni.nid = dn->nid; new_ni.ino = dn->inode->i_ino; new_ni.blk_addr = NULL_ADDR; new_ni.flag = 0; new_ni.version = 0; set_node_addr(sbi, &new_ni, NEW_ADDR, false); f2fs_wait_on_page_writeback(page, NODE, true); fill_node_footer(page, dn->nid, dn->inode->i_ino, ofs, true); set_cold_node(dn->inode, page); if (!PageUptodate(page)) SetPageUptodate(page); if (set_page_dirty(page)) dn->node_changed = true; if (f2fs_has_xattr_block(ofs)) f2fs_i_xnid_write(dn->inode, dn->nid); if (ofs == 0) inc_valid_inode_count(sbi); return page; fail: clear_node_page_dirty(page); f2fs_put_page(page, 1); return ERR_PTR(err); } /* * Caller should do after getting the following values. * 0: f2fs_put_page(page, 0) * LOCKED_PAGE or error: f2fs_put_page(page, 1) */ static int read_node_page(struct page *page, int op_flags) { struct f2fs_sb_info *sbi = F2FS_P_SB(page); struct node_info ni; struct f2fs_io_info fio = { .sbi = sbi, .type = NODE, .op = REQ_OP_READ, .op_flags = op_flags, .page = page, .encrypted_page = NULL, }; if (PageUptodate(page)) return LOCKED_PAGE; get_node_info(sbi, page->index, &ni); if (unlikely(ni.blk_addr == NULL_ADDR)) { ClearPageUptodate(page); return -ENOENT; } fio.new_blkaddr = fio.old_blkaddr = ni.blk_addr; return f2fs_submit_page_bio(&fio); } /* * Readahead a node page */ void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid) { struct page *apage; int err; if (!nid) return; if (check_nid_range(sbi, nid)) return; rcu_read_lock(); apage = radix_tree_lookup(&NODE_MAPPING(sbi)->page_tree, nid); rcu_read_unlock(); if (apage) return; apage = f2fs_grab_cache_page(NODE_MAPPING(sbi), nid, false); if (!apage) return; err = read_node_page(apage, REQ_RAHEAD); f2fs_put_page(apage, err ? 1 : 0); } static struct page *__get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid, struct page *parent, int start) { struct page *page; int err; if (!nid) return ERR_PTR(-ENOENT); if (check_nid_range(sbi, nid)) return ERR_PTR(-EINVAL); repeat: page = f2fs_grab_cache_page(NODE_MAPPING(sbi), nid, false); if (!page) return ERR_PTR(-ENOMEM); err = read_node_page(page, 0); if (err < 0) { f2fs_put_page(page, 1); return ERR_PTR(err); } else if (err == LOCKED_PAGE) { err = 0; goto page_hit; } if (parent) ra_node_pages(parent, start + 1, MAX_RA_NODE); lock_page(page); if (unlikely(page->mapping != NODE_MAPPING(sbi))) { f2fs_put_page(page, 1); goto repeat; } if (unlikely(!PageUptodate(page))) { err = -EIO; goto out_err; } if (!f2fs_inode_chksum_verify(sbi, page)) { err = -EFSBADCRC; goto out_err; } page_hit: if(unlikely(nid != nid_of_node(page))) { f2fs_msg(sbi->sb, KERN_WARNING, "inconsistent node block, " "nid:%lu, node_footer[nid:%u,ino:%u,ofs:%u,cpver:%llu,blkaddr:%u]", nid, nid_of_node(page), ino_of_node(page), ofs_of_node(page), cpver_of_node(page), next_blkaddr_of_node(page)); err = -EINVAL; out_err: ClearPageUptodate(page); f2fs_put_page(page, 1); return ERR_PTR(err); } return page; } struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid) { return __get_node_page(sbi, nid, NULL, 0); } struct page *get_node_page_ra(struct page *parent, int start) { struct f2fs_sb_info *sbi = F2FS_P_SB(parent); nid_t nid = get_nid(parent, start, false); return __get_node_page(sbi, nid, parent, start); } static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino) { struct inode *inode; struct page *page; int ret; /* should flush inline_data before evict_inode */ inode = ilookup(sbi->sb, ino); if (!inode) return; page = pagecache_get_page(inode->i_mapping, 0, FGP_LOCK|FGP_NOWAIT, 0); if (!page) goto iput_out; if (!PageUptodate(page)) goto page_out; if (!PageDirty(page)) goto page_out; if (!clear_page_dirty_for_io(page)) goto page_out; ret = f2fs_write_inline_data(inode, page); inode_dec_dirty_pages(inode); remove_dirty_inode(inode); if (ret) set_page_dirty(page); page_out: f2fs_put_page(page, 1); iput_out: iput(inode); } void move_node_page(struct page *node_page, int gc_type) { if (gc_type == FG_GC) { struct f2fs_sb_info *sbi = F2FS_P_SB(node_page); struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, .nr_to_write = 1, .for_reclaim = 0, }; set_page_dirty(node_page); f2fs_wait_on_page_writeback(node_page, NODE, true); f2fs_bug_on(sbi, PageWriteback(node_page)); if (!clear_page_dirty_for_io(node_page)) goto out_page; if (NODE_MAPPING(sbi)->a_ops->writepage(node_page, &wbc)) unlock_page(node_page); goto release_page; } else { /* set page dirty and write it */ if (!PageWriteback(node_page)) set_page_dirty(node_page); } out_page: unlock_page(node_page); release_page: f2fs_put_page(node_page, 0); } static struct page *last_fsync_dnode(struct f2fs_sb_info *sbi, nid_t ino) { pgoff_t index, end; struct pagevec pvec; struct page *last_page = NULL; pagevec_init(&pvec, 0); index = 0; end = ULONG_MAX; while (index <= end) { int i, nr_pages; nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index, PAGECACHE_TAG_DIRTY, min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1); if (nr_pages == 0) break; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; if (unlikely(f2fs_cp_error(sbi))) { f2fs_put_page(last_page, 0); pagevec_release(&pvec); return ERR_PTR(-EIO); } if (!IS_DNODE(page) || !is_cold_node(page)) continue; if (ino_of_node(page) != ino) continue; lock_page(page); if (unlikely(page->mapping != NODE_MAPPING(sbi))) { continue_unlock: unlock_page(page); continue; } if (ino_of_node(page) != ino) goto continue_unlock; if (!PageDirty(page)) { /* someone wrote it for us */ goto continue_unlock; } if (last_page) f2fs_put_page(last_page, 0); get_page(page); last_page = page; unlock_page(page); } pagevec_release(&pvec); cond_resched(); } return last_page; } static int __write_node_page(struct page *page, bool atomic, bool *submitted, struct writeback_control *wbc, bool do_balance, enum iostat_type io_type) { struct f2fs_sb_info *sbi = F2FS_P_SB(page); nid_t nid; struct node_info ni; struct f2fs_io_info fio = { .sbi = sbi, .type = NODE, .op = REQ_OP_WRITE, .op_flags = wbc_to_write_flags(wbc), .page = page, .encrypted_page = NULL, .submitted = false, .io_type = io_type, }; trace_f2fs_writepage(page, NODE); if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) goto redirty_out; if (unlikely(f2fs_cp_error(sbi))) goto redirty_out; /* get old block addr of this node page */ nid = nid_of_node(page); f2fs_bug_on(sbi, page->index != nid); if (wbc->for_reclaim) { if (!down_read_trylock(&sbi->node_write)) goto redirty_out; } else { down_read(&sbi->node_write); } get_node_info(sbi, nid, &ni); /* This page is already truncated */ if (unlikely(ni.blk_addr == NULL_ADDR)) { ClearPageUptodate(page); dec_page_count(sbi, F2FS_DIRTY_NODES); up_read(&sbi->node_write); unlock_page(page); return 0; } if (__is_valid_data_blkaddr(ni.blk_addr) && !f2fs_is_valid_blkaddr(sbi, ni.blk_addr, DATA_GENERIC)) { up_read(&sbi->node_write); goto redirty_out; } if (atomic && !test_opt(sbi, NOBARRIER)) fio.op_flags |= REQ_PREFLUSH | REQ_FUA; set_page_writeback(page); fio.old_blkaddr = ni.blk_addr; write_node_page(nid, &fio); set_node_addr(sbi, &ni, fio.new_blkaddr, is_fsync_dnode(page)); dec_page_count(sbi, F2FS_DIRTY_NODES); up_read(&sbi->node_write); if (wbc->for_reclaim) { f2fs_submit_merged_write_cond(sbi, page->mapping->host, 0, page->index, NODE); submitted = NULL; } unlock_page(page); if (unlikely(f2fs_cp_error(sbi))) { f2fs_submit_merged_write(sbi, NODE); submitted = NULL; } if (submitted) *submitted = fio.submitted; if (do_balance) f2fs_balance_fs(sbi, false); return 0; redirty_out: redirty_page_for_writepage(wbc, page); return AOP_WRITEPAGE_ACTIVATE; } static int f2fs_write_node_page(struct page *page, struct writeback_control *wbc) { return __write_node_page(page, false, NULL, wbc, false, FS_NODE_IO); } int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode, struct writeback_control *wbc, bool atomic) { pgoff_t index, end; pgoff_t last_idx = ULONG_MAX; struct pagevec pvec; int ret = 0; struct page *last_page = NULL; bool marked = false; nid_t ino = inode->i_ino; if (atomic) { last_page = last_fsync_dnode(sbi, ino); if (IS_ERR_OR_NULL(last_page)) return PTR_ERR_OR_ZERO(last_page); } retry: pagevec_init(&pvec, 0); index = 0; end = ULONG_MAX; while (index <= end) { int i, nr_pages; nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index, PAGECACHE_TAG_DIRTY, min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1); if (nr_pages == 0) break; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; bool submitted = false; if (unlikely(f2fs_cp_error(sbi))) { f2fs_put_page(last_page, 0); pagevec_release(&pvec); ret = -EIO; goto out; } if (!IS_DNODE(page) || !is_cold_node(page)) continue; if (ino_of_node(page) != ino) continue; lock_page(page); if (unlikely(page->mapping != NODE_MAPPING(sbi))) { continue_unlock: unlock_page(page); continue; } if (ino_of_node(page) != ino) goto continue_unlock; if (!PageDirty(page) && page != last_page) { /* someone wrote it for us */ goto continue_unlock; } f2fs_wait_on_page_writeback(page, NODE, true); BUG_ON(PageWriteback(page)); set_fsync_mark(page, 0); set_dentry_mark(page, 0); if (!atomic || page == last_page) { set_fsync_mark(page, 1); if (IS_INODE(page)) { if (is_inode_flag_set(inode, FI_DIRTY_INODE)) update_inode(inode, page); set_dentry_mark(page, need_dentry_mark(sbi, ino)); } /* may be written by other thread */ if (!PageDirty(page)) set_page_dirty(page); } if (!clear_page_dirty_for_io(page)) goto continue_unlock; ret = __write_node_page(page, atomic && page == last_page, &submitted, wbc, true, FS_NODE_IO); if (ret) { unlock_page(page); f2fs_put_page(last_page, 0); break; } else if (submitted) { last_idx = page->index; } if (page == last_page) { f2fs_put_page(page, 0); marked = true; break; } } pagevec_release(&pvec); cond_resched(); if (ret || marked) break; } if (!ret && atomic && !marked) { f2fs_msg(sbi->sb, KERN_DEBUG, "Retry to write fsync mark: ino=%u, idx=%lx", ino, last_page->index); lock_page(last_page); f2fs_wait_on_page_writeback(last_page, NODE, true); set_page_dirty(last_page); unlock_page(last_page); goto retry; } out: if (last_idx != ULONG_MAX) f2fs_submit_merged_write_cond(sbi, NULL, ino, last_idx, NODE); return ret ? -EIO: 0; } int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc, bool do_balance, enum iostat_type io_type) { pgoff_t index, end; struct pagevec pvec; int step = 0; int nwritten = 0; int ret = 0; pagevec_init(&pvec, 0); next_step: index = 0; end = ULONG_MAX; while (index <= end) { int i, nr_pages; nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index, PAGECACHE_TAG_DIRTY, min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1); if (nr_pages == 0) break; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; bool submitted = false; if (unlikely(f2fs_cp_error(sbi))) { pagevec_release(&pvec); ret = -EIO; goto out; } /* * flushing sequence with step: * 0. indirect nodes * 1. dentry dnodes * 2. file dnodes */ if (step == 0 && IS_DNODE(page)) continue; if (step == 1 && (!IS_DNODE(page) || is_cold_node(page))) continue; if (step == 2 && (!IS_DNODE(page) || !is_cold_node(page))) continue; lock_node: if (wbc->sync_mode == WB_SYNC_ALL) lock_page(page); else if (!trylock_page(page)) continue; if (unlikely(page->mapping != NODE_MAPPING(sbi))) { continue_unlock: unlock_page(page); continue; } if (!PageDirty(page)) { /* someone wrote it for us */ goto continue_unlock; } /* flush inline_data */ if (is_inline_node(page)) { clear_inline_node(page); unlock_page(page); flush_inline_data(sbi, ino_of_node(page)); goto lock_node; } f2fs_wait_on_page_writeback(page, NODE, true); BUG_ON(PageWriteback(page)); if (!clear_page_dirty_for_io(page)) goto continue_unlock; set_fsync_mark(page, 0); set_dentry_mark(page, 0); ret = __write_node_page(page, false, &submitted, wbc, do_balance, io_type); if (ret) unlock_page(page); else if (submitted) nwritten++; if (--wbc->nr_to_write == 0) break; } pagevec_release(&pvec); cond_resched(); if (wbc->nr_to_write == 0) { step = 2; break; } } if (step < 2) { step++; goto next_step; } out: if (nwritten) f2fs_submit_merged_write(sbi, NODE); return ret; } int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino) { pgoff_t index = 0, end = ULONG_MAX; struct pagevec pvec; int ret2, ret = 0; pagevec_init(&pvec, 0); while (index <= end) { int i, nr_pages; nr_pages = pagevec_lookup_tag(&pvec, NODE_MAPPING(sbi), &index, PAGECACHE_TAG_WRITEBACK, min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1); if (nr_pages == 0) break; for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; /* until radix tree lookup accepts end_index */ if (unlikely(page->index > end)) continue; if (ino && ino_of_node(page) == ino) { f2fs_wait_on_page_writeback(page, NODE, true); if (TestClearPageError(page)) ret = -EIO; } } pagevec_release(&pvec); cond_resched(); } ret2 = filemap_check_errors(NODE_MAPPING(sbi)); if (!ret) ret = ret2; return ret; } static int f2fs_write_node_pages(struct address_space *mapping, struct writeback_control *wbc) { struct f2fs_sb_info *sbi = F2FS_M_SB(mapping); struct blk_plug plug; long diff; if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING))) goto skip_write; /* balancing f2fs's metadata in background */ f2fs_balance_fs_bg(sbi); /* collect a number of dirty node pages and write together */ if (get_pages(sbi, F2FS_DIRTY_NODES) < nr_pages_to_skip(sbi, NODE)) goto skip_write; trace_f2fs_writepages(mapping->host, wbc, NODE); diff = nr_pages_to_write(sbi, NODE, wbc); wbc->sync_mode = WB_SYNC_NONE; blk_start_plug(&plug); sync_node_pages(sbi, wbc, true, FS_NODE_IO); blk_finish_plug(&plug); wbc->nr_to_write = max((long)0, wbc->nr_to_write - diff); return 0; skip_write: wbc->pages_skipped += get_pages(sbi, F2FS_DIRTY_NODES); trace_f2fs_writepages(mapping->host, wbc, NODE); return 0; } static int f2fs_set_node_page_dirty(struct page *page) { trace_f2fs_set_page_dirty(page, NODE); if (!PageUptodate(page)) SetPageUptodate(page); if (!PageDirty(page)) { f2fs_set_page_dirty_nobuffers(page); inc_page_count(F2FS_P_SB(page), F2FS_DIRTY_NODES); SetPagePrivate(page); f2fs_trace_pid(page); return 1; } return 0; } /* * Structure of the f2fs node operations */ const struct address_space_operations f2fs_node_aops = { .writepage = f2fs_write_node_page, .writepages = f2fs_write_node_pages, .set_page_dirty = f2fs_set_node_page_dirty, .invalidatepage = f2fs_invalidate_page, .releasepage = f2fs_release_page, #ifdef CONFIG_MIGRATION .migratepage = f2fs_migrate_page, #endif }; static struct free_nid *__lookup_free_nid_list(struct f2fs_nm_info *nm_i, nid_t n) { return radix_tree_lookup(&nm_i->free_nid_root, n); } static int __insert_nid_to_list(struct f2fs_sb_info *sbi, struct free_nid *i, enum nid_list list, bool new) { struct f2fs_nm_info *nm_i = NM_I(sbi); if (new) { int err = radix_tree_insert(&nm_i->free_nid_root, i->nid, i); if (err) return err; } f2fs_bug_on(sbi, list == FREE_NID_LIST ? i->state != NID_NEW : i->state != NID_ALLOC); nm_i->nid_cnt[list]++; list_add_tail(&i->list, &nm_i->nid_list[list]); return 0; } static void __remove_nid_from_list(struct f2fs_sb_info *sbi, struct free_nid *i, enum nid_list list, bool reuse) { struct f2fs_nm_info *nm_i = NM_I(sbi); f2fs_bug_on(sbi, list == FREE_NID_LIST ? i->state != NID_NEW : i->state != NID_ALLOC); nm_i->nid_cnt[list]--; list_del(&i->list); if (!reuse) radix_tree_delete(&nm_i->free_nid_root, i->nid); } /* return if the nid is recognized as free */ static bool add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i, *e; struct nat_entry *ne; int err = -EINVAL; bool ret = false; /* 0 nid should not be used */ if (unlikely(nid == 0)) return false; i = f2fs_kmem_cache_alloc(free_nid_slab, GFP_NOFS); i->nid = nid; i->state = NID_NEW; if (radix_tree_preload(GFP_NOFS)) goto err; spin_lock(&nm_i->nid_list_lock); if (build) { /* * Thread A Thread B * - f2fs_create * - f2fs_new_inode * - alloc_nid * - __insert_nid_to_list(ALLOC_NID_LIST) * - f2fs_balance_fs_bg * - build_free_nids * - __build_free_nids * - scan_nat_page * - add_free_nid * - __lookup_nat_cache * - f2fs_add_link * - init_inode_metadata * - new_inode_page * - new_node_page * - set_node_addr * - alloc_nid_done * - __remove_nid_from_list(ALLOC_NID_LIST) * - __insert_nid_to_list(FREE_NID_LIST) */ ne = __lookup_nat_cache(nm_i, nid); if (ne && (!get_nat_flag(ne, IS_CHECKPOINTED) || nat_get_blkaddr(ne) != NULL_ADDR)) goto err_out; e = __lookup_free_nid_list(nm_i, nid); if (e) { if (e->state == NID_NEW) ret = true; goto err_out; } } ret = true; err = __insert_nid_to_list(sbi, i, FREE_NID_LIST, true); err_out: spin_unlock(&nm_i->nid_list_lock); radix_tree_preload_end(); err: if (err) kmem_cache_free(free_nid_slab, i); return ret; } static void remove_free_nid(struct f2fs_sb_info *sbi, nid_t nid) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i; bool need_free = false; spin_lock(&nm_i->nid_list_lock); i = __lookup_free_nid_list(nm_i, nid); if (i && i->state == NID_NEW) { __remove_nid_from_list(sbi, i, FREE_NID_LIST, false); need_free = true; } spin_unlock(&nm_i->nid_list_lock); if (need_free) kmem_cache_free(free_nid_slab, i); } static void update_free_nid_bitmap(struct f2fs_sb_info *sbi, nid_t nid, bool set, bool build) { struct f2fs_nm_info *nm_i = NM_I(sbi); unsigned int nat_ofs = NAT_BLOCK_OFFSET(nid); unsigned int nid_ofs = nid - START_NID(nid); if (!test_bit_le(nat_ofs, nm_i->nat_block_bitmap)) return; if (set) __set_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]); else __clear_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]); if (set) nm_i->free_nid_count[nat_ofs]++; else if (!build) nm_i->free_nid_count[nat_ofs]--; } static void scan_nat_page(struct f2fs_sb_info *sbi, struct page *nat_page, nid_t start_nid) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct f2fs_nat_block *nat_blk = page_address(nat_page); block_t blk_addr; unsigned int nat_ofs = NAT_BLOCK_OFFSET(start_nid); int i; if (test_bit_le(nat_ofs, nm_i->nat_block_bitmap)) return; __set_bit_le(nat_ofs, nm_i->nat_block_bitmap); i = start_nid % NAT_ENTRY_PER_BLOCK; for (; i < NAT_ENTRY_PER_BLOCK; i++, start_nid++) { bool freed = false; if (unlikely(start_nid >= nm_i->max_nid)) break; blk_addr = le32_to_cpu(nat_blk->entries[i].block_addr); f2fs_bug_on(sbi, blk_addr == NEW_ADDR); if (blk_addr == NULL_ADDR) freed = add_free_nid(sbi, start_nid, true); spin_lock(&NM_I(sbi)->nid_list_lock); update_free_nid_bitmap(sbi, start_nid, freed, true); spin_unlock(&NM_I(sbi)->nid_list_lock); } } static void scan_free_nid_bits(struct f2fs_sb_info *sbi) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); struct f2fs_journal *journal = curseg->journal; unsigned int i, idx; down_read(&nm_i->nat_tree_lock); for (i = 0; i < nm_i->nat_blocks; i++) { if (!test_bit_le(i, nm_i->nat_block_bitmap)) continue; if (!nm_i->free_nid_count[i]) continue; for (idx = 0; idx < NAT_ENTRY_PER_BLOCK; idx++) { nid_t nid; if (!test_bit_le(idx, nm_i->free_nid_bitmap[i])) continue; nid = i * NAT_ENTRY_PER_BLOCK + idx; add_free_nid(sbi, nid, true); if (nm_i->nid_cnt[FREE_NID_LIST] >= MAX_FREE_NIDS) goto out; } } out: down_read(&curseg->journal_rwsem); for (i = 0; i < nats_in_cursum(journal); i++) { block_t addr; nid_t nid; addr = le32_to_cpu(nat_in_journal(journal, i).block_addr); nid = le32_to_cpu(nid_in_journal(journal, i)); if (addr == NULL_ADDR) add_free_nid(sbi, nid, true); else remove_free_nid(sbi, nid); } up_read(&curseg->journal_rwsem); up_read(&nm_i->nat_tree_lock); } static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); struct f2fs_journal *journal = curseg->journal; int i = 0; nid_t nid = nm_i->next_scan_nid; if (unlikely(nid >= nm_i->max_nid)) nid = 0; if (unlikely(nid % NAT_ENTRY_PER_BLOCK)) nid = NAT_BLOCK_OFFSET(nid) * NAT_ENTRY_PER_BLOCK; /* Enough entries */ if (nm_i->nid_cnt[FREE_NID_LIST] >= NAT_ENTRY_PER_BLOCK) return; if (!sync && !available_free_memory(sbi, FREE_NIDS)) return; if (!mount) { /* try to find free nids in free_nid_bitmap */ scan_free_nid_bits(sbi); if (nm_i->nid_cnt[FREE_NID_LIST]) return; } /* readahead nat pages to be scanned */ ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES, META_NAT, true); down_read(&nm_i->nat_tree_lock); while (1) { struct page *page = get_current_nat_page(sbi, nid); scan_nat_page(sbi, page, nid); f2fs_put_page(page, 1); nid += (NAT_ENTRY_PER_BLOCK - (nid % NAT_ENTRY_PER_BLOCK)); if (unlikely(nid >= nm_i->max_nid)) nid = 0; if (++i >= FREE_NID_PAGES) break; } /* go to the next free nat pages to find free nids abundantly */ nm_i->next_scan_nid = nid; /* find free nids from current sum_pages */ down_read(&curseg->journal_rwsem); for (i = 0; i < nats_in_cursum(journal); i++) { block_t addr; addr = le32_to_cpu(nat_in_journal(journal, i).block_addr); nid = le32_to_cpu(nid_in_journal(journal, i)); if (addr == NULL_ADDR) add_free_nid(sbi, nid, true); else remove_free_nid(sbi, nid); } up_read(&curseg->journal_rwsem); up_read(&nm_i->nat_tree_lock); ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid), nm_i->ra_nid_pages, META_NAT, false); } void build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount) { mutex_lock(&NM_I(sbi)->build_lock); __build_free_nids(sbi, sync, mount); mutex_unlock(&NM_I(sbi)->build_lock); } /* * If this function returns success, caller can obtain a new nid * from second parameter of this function. * The returned nid could be used ino as well as nid when inode is created. */ bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i = NULL; retry: #ifdef CONFIG_F2FS_FAULT_INJECTION if (time_to_inject(sbi, FAULT_ALLOC_NID)) { f2fs_show_injection_info(FAULT_ALLOC_NID); return false; } #endif spin_lock(&nm_i->nid_list_lock); if (unlikely(nm_i->available_nids == 0)) { spin_unlock(&nm_i->nid_list_lock); return false; } /* We should not use stale free nids created by build_free_nids */ if (nm_i->nid_cnt[FREE_NID_LIST] && !on_build_free_nids(nm_i)) { f2fs_bug_on(sbi, list_empty(&nm_i->nid_list[FREE_NID_LIST])); i = list_first_entry(&nm_i->nid_list[FREE_NID_LIST], struct free_nid, list); *nid = i->nid; __remove_nid_from_list(sbi, i, FREE_NID_LIST, true); i->state = NID_ALLOC; __insert_nid_to_list(sbi, i, ALLOC_NID_LIST, false); nm_i->available_nids--; update_free_nid_bitmap(sbi, *nid, false, false); spin_unlock(&nm_i->nid_list_lock); return true; } spin_unlock(&nm_i->nid_list_lock); /* Let's scan nat pages and its caches to get free nids */ build_free_nids(sbi, true, false); goto retry; } /* * alloc_nid() should be called prior to this function. */ void alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i; spin_lock(&nm_i->nid_list_lock); i = __lookup_free_nid_list(nm_i, nid); f2fs_bug_on(sbi, !i); __remove_nid_from_list(sbi, i, ALLOC_NID_LIST, false); spin_unlock(&nm_i->nid_list_lock); kmem_cache_free(free_nid_slab, i); } /* * alloc_nid() should be called prior to this function. */ void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i; bool need_free = false; if (!nid) return; spin_lock(&nm_i->nid_list_lock); i = __lookup_free_nid_list(nm_i, nid); f2fs_bug_on(sbi, !i); if (!available_free_memory(sbi, FREE_NIDS)) { __remove_nid_from_list(sbi, i, ALLOC_NID_LIST, false); need_free = true; } else { __remove_nid_from_list(sbi, i, ALLOC_NID_LIST, true); i->state = NID_NEW; __insert_nid_to_list(sbi, i, FREE_NID_LIST, false); } nm_i->available_nids++; update_free_nid_bitmap(sbi, nid, true, false); spin_unlock(&nm_i->nid_list_lock); if (need_free) kmem_cache_free(free_nid_slab, i); } int try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i, *next; int nr = nr_shrink; if (nm_i->nid_cnt[FREE_NID_LIST] <= MAX_FREE_NIDS) return 0; if (!mutex_trylock(&nm_i->build_lock)) return 0; spin_lock(&nm_i->nid_list_lock); list_for_each_entry_safe(i, next, &nm_i->nid_list[FREE_NID_LIST], list) { if (nr_shrink <= 0 || nm_i->nid_cnt[FREE_NID_LIST] <= MAX_FREE_NIDS) break; __remove_nid_from_list(sbi, i, FREE_NID_LIST, false); kmem_cache_free(free_nid_slab, i); nr_shrink--; } spin_unlock(&nm_i->nid_list_lock); mutex_unlock(&nm_i->build_lock); return nr - nr_shrink; } void recover_inline_xattr(struct inode *inode, struct page *page) { void *src_addr, *dst_addr; size_t inline_size; struct page *ipage; struct f2fs_inode *ri; ipage = get_node_page(F2FS_I_SB(inode), inode->i_ino); f2fs_bug_on(F2FS_I_SB(inode), IS_ERR(ipage)); ri = F2FS_INODE(page); if (!(ri->i_inline & F2FS_INLINE_XATTR)) { clear_inode_flag(inode, FI_INLINE_XATTR); goto update_inode; } dst_addr = inline_xattr_addr(ipage); src_addr = inline_xattr_addr(page); inline_size = inline_xattr_size(inode); f2fs_wait_on_page_writeback(ipage, NODE, true); memcpy(dst_addr, src_addr, inline_size); update_inode: update_inode(inode, ipage); f2fs_put_page(ipage, 1); } int recover_xattr_data(struct inode *inode, struct page *page, block_t blkaddr) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); nid_t prev_xnid = F2FS_I(inode)->i_xattr_nid; nid_t new_xnid; struct dnode_of_data dn; struct node_info ni; struct page *xpage; if (!prev_xnid) goto recover_xnid; /* 1: invalidate the previous xattr nid */ get_node_info(sbi, prev_xnid, &ni); f2fs_bug_on(sbi, ni.blk_addr == NULL_ADDR); invalidate_blocks(sbi, ni.blk_addr); dec_valid_node_count(sbi, inode, false); set_node_addr(sbi, &ni, NULL_ADDR, false); recover_xnid: /* 2: update xattr nid in inode */ if (!alloc_nid(sbi, &new_xnid)) return -ENOSPC; set_new_dnode(&dn, inode, NULL, NULL, new_xnid); xpage = new_node_page(&dn, XATTR_NODE_OFFSET); if (IS_ERR(xpage)) { alloc_nid_failed(sbi, new_xnid); return PTR_ERR(xpage); } alloc_nid_done(sbi, new_xnid); update_inode_page(inode); /* 3: update and set xattr node page dirty */ memcpy(F2FS_NODE(xpage), F2FS_NODE(page), VALID_XATTR_BLOCK_SIZE); set_page_dirty(xpage); f2fs_put_page(xpage, 1); return 0; } int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page) { struct f2fs_inode *src, *dst; nid_t ino = ino_of_node(page); struct node_info old_ni, new_ni; struct page *ipage; get_node_info(sbi, ino, &old_ni); if (unlikely(old_ni.blk_addr != NULL_ADDR)) return -EINVAL; retry: ipage = f2fs_grab_cache_page(NODE_MAPPING(sbi), ino, false); if (!ipage) { congestion_wait(BLK_RW_ASYNC, HZ/50); goto retry; } /* Should not use this inode from free nid list */ remove_free_nid(sbi, ino); if (!PageUptodate(ipage)) SetPageUptodate(ipage); fill_node_footer(ipage, ino, ino, 0, true); src = F2FS_INODE(page); dst = F2FS_INODE(ipage); memcpy(dst, src, (unsigned long)&src->i_ext - (unsigned long)src); dst->i_size = 0; dst->i_blocks = cpu_to_le64(1); dst->i_links = cpu_to_le32(1); dst->i_xattr_nid = 0; dst->i_inline = src->i_inline & (F2FS_INLINE_XATTR | F2FS_EXTRA_ATTR); if (dst->i_inline & F2FS_EXTRA_ATTR) { dst->i_extra_isize = src->i_extra_isize; if (f2fs_sb_has_project_quota(sbi->sb) && F2FS_FITS_IN_INODE(src, le16_to_cpu(src->i_extra_isize), i_projid)) dst->i_projid = src->i_projid; } new_ni = old_ni; new_ni.ino = ino; if (unlikely(inc_valid_node_count(sbi, NULL, true))) WARN_ON(1); set_node_addr(sbi, &new_ni, NEW_ADDR, false); inc_valid_inode_count(sbi); set_page_dirty(ipage); f2fs_put_page(ipage, 1); return 0; } int restore_node_summary(struct f2fs_sb_info *sbi, unsigned int segno, struct f2fs_summary_block *sum) { struct f2fs_node *rn; struct f2fs_summary *sum_entry; block_t addr; int i, idx, last_offset, nrpages; /* scan the node segment */ last_offset = sbi->blocks_per_seg; addr = START_BLOCK(sbi, segno); sum_entry = &sum->entries[0]; for (i = 0; i < last_offset; i += nrpages, addr += nrpages) { nrpages = min(last_offset - i, BIO_MAX_PAGES); /* readahead node pages */ ra_meta_pages(sbi, addr, nrpages, META_POR, true); for (idx = addr; idx < addr + nrpages; idx++) { struct page *page = get_tmp_page(sbi, idx); rn = F2FS_NODE(page); sum_entry->nid = rn->footer.nid; sum_entry->version = 0; sum_entry->ofs_in_node = 0; sum_entry++; f2fs_put_page(page, 1); } invalidate_mapping_pages(META_MAPPING(sbi), addr, addr + nrpages); } return 0; } static void remove_nats_in_journal(struct f2fs_sb_info *sbi) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); struct f2fs_journal *journal = curseg->journal; int i; down_write(&curseg->journal_rwsem); for (i = 0; i < nats_in_cursum(journal); i++) { struct nat_entry *ne; struct f2fs_nat_entry raw_ne; nid_t nid = le32_to_cpu(nid_in_journal(journal, i)); raw_ne = nat_in_journal(journal, i); ne = __lookup_nat_cache(nm_i, nid); if (!ne) { ne = grab_nat_entry(nm_i, nid, true); node_info_from_raw_nat(&ne->ni, &raw_ne); } /* * if a free nat in journal has not been used after last * checkpoint, we should remove it from available nids, * since later we will add it again. */ if (!get_nat_flag(ne, IS_DIRTY) && le32_to_cpu(raw_ne.block_addr) == NULL_ADDR) { spin_lock(&nm_i->nid_list_lock); nm_i->available_nids--; spin_unlock(&nm_i->nid_list_lock); } __set_nat_cache_dirty(nm_i, ne); } update_nats_in_cursum(journal, -i); up_write(&curseg->journal_rwsem); } static void __adjust_nat_entry_set(struct nat_entry_set *nes, struct list_head *head, int max) { struct nat_entry_set *cur; if (nes->entry_cnt >= max) goto add_out; list_for_each_entry(cur, head, set_list) { if (cur->entry_cnt >= nes->entry_cnt) { list_add(&nes->set_list, cur->set_list.prev); return; } } add_out: list_add_tail(&nes->set_list, head); } static void __update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid, struct page *page) { struct f2fs_nm_info *nm_i = NM_I(sbi); unsigned int nat_index = start_nid / NAT_ENTRY_PER_BLOCK; struct f2fs_nat_block *nat_blk = page_address(page); int valid = 0; int i; if (!enabled_nat_bits(sbi, NULL)) return; for (i = 0; i < NAT_ENTRY_PER_BLOCK; i++) { if (start_nid == 0 && i == 0) valid++; if (nat_blk->entries[i].block_addr) valid++; } if (valid == 0) { __set_bit_le(nat_index, nm_i->empty_nat_bits); __clear_bit_le(nat_index, nm_i->full_nat_bits); return; } __clear_bit_le(nat_index, nm_i->empty_nat_bits); if (valid == NAT_ENTRY_PER_BLOCK) __set_bit_le(nat_index, nm_i->full_nat_bits); else __clear_bit_le(nat_index, nm_i->full_nat_bits); } static void __flush_nat_entry_set(struct f2fs_sb_info *sbi, struct nat_entry_set *set, struct cp_control *cpc) { struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); struct f2fs_journal *journal = curseg->journal; nid_t start_nid = set->set * NAT_ENTRY_PER_BLOCK; bool to_journal = true; struct f2fs_nat_block *nat_blk; struct nat_entry *ne, *cur; struct page *page = NULL; /* * there are two steps to flush nat entries: * #1, flush nat entries to journal in current hot data summary block. * #2, flush nat entries to nat page. */ if (enabled_nat_bits(sbi, cpc) || !__has_cursum_space(journal, set->entry_cnt, NAT_JOURNAL)) to_journal = false; if (to_journal) { down_write(&curseg->journal_rwsem); } else { page = get_next_nat_page(sbi, start_nid); nat_blk = page_address(page); f2fs_bug_on(sbi, !nat_blk); } /* flush dirty nats in nat entry set */ list_for_each_entry_safe(ne, cur, &set->entry_list, list) { struct f2fs_nat_entry *raw_ne; nid_t nid = nat_get_nid(ne); int offset; f2fs_bug_on(sbi, nat_get_blkaddr(ne) == NEW_ADDR); if (to_journal) { offset = lookup_journal_in_cursum(journal, NAT_JOURNAL, nid, 1); f2fs_bug_on(sbi, offset < 0); raw_ne = &nat_in_journal(journal, offset); nid_in_journal(journal, offset) = cpu_to_le32(nid); } else { raw_ne = &nat_blk->entries[nid - start_nid]; } raw_nat_from_node_info(raw_ne, &ne->ni); nat_reset_flag(ne); __clear_nat_cache_dirty(NM_I(sbi), set, ne); if (nat_get_blkaddr(ne) == NULL_ADDR) { add_free_nid(sbi, nid, false); spin_lock(&NM_I(sbi)->nid_list_lock); NM_I(sbi)->available_nids++; update_free_nid_bitmap(sbi, nid, true, false); spin_unlock(&NM_I(sbi)->nid_list_lock); } else { spin_lock(&NM_I(sbi)->nid_list_lock); update_free_nid_bitmap(sbi, nid, false, false); spin_unlock(&NM_I(sbi)->nid_list_lock); } } if (to_journal) { up_write(&curseg->journal_rwsem); } else { __update_nat_bits(sbi, start_nid, page); f2fs_put_page(page, 1); } /* Allow dirty nats by node block allocation in write_begin */ if (!set->entry_cnt) { radix_tree_delete(&NM_I(sbi)->nat_set_root, set->set); kmem_cache_free(nat_entry_set_slab, set); } } /* * This function is called during the checkpointing process. */ void flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA); struct f2fs_journal *journal = curseg->journal; struct nat_entry_set *setvec[SETVEC_SIZE]; struct nat_entry_set *set, *tmp; unsigned int found; nid_t set_idx = 0; LIST_HEAD(sets); if (!nm_i->dirty_nat_cnt) return; down_write(&nm_i->nat_tree_lock); /* * if there are no enough space in journal to store dirty nat * entries, remove all entries from journal and merge them * into nat entry set. */ if (enabled_nat_bits(sbi, cpc) || !__has_cursum_space(journal, nm_i->dirty_nat_cnt, NAT_JOURNAL)) remove_nats_in_journal(sbi); while ((found = __gang_lookup_nat_set(nm_i, set_idx, SETVEC_SIZE, setvec))) { unsigned idx; set_idx = setvec[found - 1]->set + 1; for (idx = 0; idx < found; idx++) __adjust_nat_entry_set(setvec[idx], &sets, MAX_NAT_JENTRIES(journal)); } /* flush dirty nats in nat entry set */ list_for_each_entry_safe(set, tmp, &sets, set_list) __flush_nat_entry_set(sbi, set, cpc); up_write(&nm_i->nat_tree_lock); /* Allow dirty nats by node block allocation in write_begin */ } static int __get_nat_bitmaps(struct f2fs_sb_info *sbi) { struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi); struct f2fs_nm_info *nm_i = NM_I(sbi); unsigned int nat_bits_bytes = nm_i->nat_blocks / BITS_PER_BYTE; unsigned int i; __u64 cp_ver = cur_cp_version(ckpt); block_t nat_bits_addr; if (!enabled_nat_bits(sbi, NULL)) return 0; nm_i->nat_bits_blocks = F2FS_BYTES_TO_BLK((nat_bits_bytes << 1) + 8 + F2FS_BLKSIZE - 1); nm_i->nat_bits = kzalloc(nm_i->nat_bits_blocks << F2FS_BLKSIZE_BITS, GFP_KERNEL); if (!nm_i->nat_bits) return -ENOMEM; nat_bits_addr = __start_cp_addr(sbi) + sbi->blocks_per_seg - nm_i->nat_bits_blocks; for (i = 0; i < nm_i->nat_bits_blocks; i++) { struct page *page = get_meta_page(sbi, nat_bits_addr++); memcpy(nm_i->nat_bits + (i << F2FS_BLKSIZE_BITS), page_address(page), F2FS_BLKSIZE); f2fs_put_page(page, 1); } cp_ver |= (cur_cp_crc(ckpt) << 32); if (cpu_to_le64(cp_ver) != *(__le64 *)nm_i->nat_bits) { disable_nat_bits(sbi, true); return 0; } nm_i->full_nat_bits = nm_i->nat_bits + 8; nm_i->empty_nat_bits = nm_i->full_nat_bits + nat_bits_bytes; f2fs_msg(sbi->sb, KERN_NOTICE, "Found nat_bits in checkpoint"); return 0; } static inline void load_free_nid_bitmap(struct f2fs_sb_info *sbi) { struct f2fs_nm_info *nm_i = NM_I(sbi); unsigned int i = 0; nid_t nid, last_nid; if (!enabled_nat_bits(sbi, NULL)) return; for (i = 0; i < nm_i->nat_blocks; i++) { i = find_next_bit_le(nm_i->empty_nat_bits, nm_i->nat_blocks, i); if (i >= nm_i->nat_blocks) break; __set_bit_le(i, nm_i->nat_block_bitmap); nid = i * NAT_ENTRY_PER_BLOCK; last_nid = (i + 1) * NAT_ENTRY_PER_BLOCK; spin_lock(&NM_I(sbi)->nid_list_lock); for (; nid < last_nid; nid++) update_free_nid_bitmap(sbi, nid, true, true); spin_unlock(&NM_I(sbi)->nid_list_lock); } for (i = 0; i < nm_i->nat_blocks; i++) { i = find_next_bit_le(nm_i->full_nat_bits, nm_i->nat_blocks, i); if (i >= nm_i->nat_blocks) break; __set_bit_le(i, nm_i->nat_block_bitmap); } } static int init_node_manager(struct f2fs_sb_info *sbi) { struct f2fs_super_block *sb_raw = F2FS_RAW_SUPER(sbi); struct f2fs_nm_info *nm_i = NM_I(sbi); unsigned char *version_bitmap; unsigned int nat_segs; int err; nm_i->nat_blkaddr = le32_to_cpu(sb_raw->nat_blkaddr); /* segment_count_nat includes pair segment so divide to 2. */ nat_segs = le32_to_cpu(sb_raw->segment_count_nat) >> 1; nm_i->nat_blocks = nat_segs << le32_to_cpu(sb_raw->log_blocks_per_seg); nm_i->max_nid = NAT_ENTRY_PER_BLOCK * nm_i->nat_blocks; /* not used nids: 0, node, meta, (and root counted as valid node) */ nm_i->available_nids = nm_i->max_nid - sbi->total_valid_node_count - F2FS_RESERVED_NODE_NUM; nm_i->nid_cnt[FREE_NID_LIST] = 0; nm_i->nid_cnt[ALLOC_NID_LIST] = 0; nm_i->nat_cnt = 0; nm_i->ram_thresh = DEF_RAM_THRESHOLD; nm_i->ra_nid_pages = DEF_RA_NID_PAGES; nm_i->dirty_nats_ratio = DEF_DIRTY_NAT_RATIO_THRESHOLD; INIT_RADIX_TREE(&nm_i->free_nid_root, GFP_ATOMIC); INIT_LIST_HEAD(&nm_i->nid_list[FREE_NID_LIST]); INIT_LIST_HEAD(&nm_i->nid_list[ALLOC_NID_LIST]); INIT_RADIX_TREE(&nm_i->nat_root, GFP_NOIO); INIT_RADIX_TREE(&nm_i->nat_set_root, GFP_NOIO); INIT_LIST_HEAD(&nm_i->nat_entries); mutex_init(&nm_i->build_lock); spin_lock_init(&nm_i->nid_list_lock); init_rwsem(&nm_i->nat_tree_lock); nm_i->next_scan_nid = le32_to_cpu(sbi->ckpt->next_free_nid); nm_i->bitmap_size = __bitmap_size(sbi, NAT_BITMAP); version_bitmap = __bitmap_ptr(sbi, NAT_BITMAP); if (!version_bitmap) return -EFAULT; nm_i->nat_bitmap = kmemdup(version_bitmap, nm_i->bitmap_size, GFP_KERNEL); if (!nm_i->nat_bitmap) return -ENOMEM; err = __get_nat_bitmaps(sbi); if (err) return err; #ifdef CONFIG_F2FS_CHECK_FS nm_i->nat_bitmap_mir = kmemdup(version_bitmap, nm_i->bitmap_size, GFP_KERNEL); if (!nm_i->nat_bitmap_mir) return -ENOMEM; #endif return 0; } static int init_free_nid_cache(struct f2fs_sb_info *sbi) { struct f2fs_nm_info *nm_i = NM_I(sbi); nm_i->free_nid_bitmap = kvzalloc(nm_i->nat_blocks * NAT_ENTRY_BITMAP_SIZE, GFP_KERNEL); if (!nm_i->free_nid_bitmap) return -ENOMEM; nm_i->nat_block_bitmap = kvzalloc(nm_i->nat_blocks / 8, GFP_KERNEL); if (!nm_i->nat_block_bitmap) return -ENOMEM; nm_i->free_nid_count = kvzalloc(nm_i->nat_blocks * sizeof(unsigned short), GFP_KERNEL); if (!nm_i->free_nid_count) return -ENOMEM; return 0; } int build_node_manager(struct f2fs_sb_info *sbi) { int err; sbi->nm_info = kzalloc(sizeof(struct f2fs_nm_info), GFP_KERNEL); if (!sbi->nm_info) return -ENOMEM; err = init_node_manager(sbi); if (err) return err; err = init_free_nid_cache(sbi); if (err) return err; /* load free nid status from nat_bits table */ load_free_nid_bitmap(sbi); build_free_nids(sbi, true, true); return 0; } void destroy_node_manager(struct f2fs_sb_info *sbi) { struct f2fs_nm_info *nm_i = NM_I(sbi); struct free_nid *i, *next_i; struct nat_entry *natvec[NATVEC_SIZE]; struct nat_entry_set *setvec[SETVEC_SIZE]; nid_t nid = 0; unsigned int found; if (!nm_i) return; /* destroy free nid list */ spin_lock(&nm_i->nid_list_lock); list_for_each_entry_safe(i, next_i, &nm_i->nid_list[FREE_NID_LIST], list) { __remove_nid_from_list(sbi, i, FREE_NID_LIST, false); spin_unlock(&nm_i->nid_list_lock); kmem_cache_free(free_nid_slab, i); spin_lock(&nm_i->nid_list_lock); } f2fs_bug_on(sbi, nm_i->nid_cnt[FREE_NID_LIST]); f2fs_bug_on(sbi, nm_i->nid_cnt[ALLOC_NID_LIST]); f2fs_bug_on(sbi, !list_empty(&nm_i->nid_list[ALLOC_NID_LIST])); spin_unlock(&nm_i->nid_list_lock); /* destroy nat cache */ down_write(&nm_i->nat_tree_lock); while ((found = __gang_lookup_nat_cache(nm_i, nid, NATVEC_SIZE, natvec))) { unsigned idx; nid = nat_get_nid(natvec[found - 1]) + 1; for (idx = 0; idx < found; idx++) __del_from_nat_cache(nm_i, natvec[idx]); } f2fs_bug_on(sbi, nm_i->nat_cnt); /* destroy nat set cache */ nid = 0; while ((found = __gang_lookup_nat_set(nm_i, nid, SETVEC_SIZE, setvec))) { unsigned idx; nid = setvec[found - 1]->set + 1; for (idx = 0; idx < found; idx++) { /* entry_cnt is not zero, when cp_error was occurred */ f2fs_bug_on(sbi, !list_empty(&setvec[idx]->entry_list)); radix_tree_delete(&nm_i->nat_set_root, setvec[idx]->set); kmem_cache_free(nat_entry_set_slab, setvec[idx]); } } up_write(&nm_i->nat_tree_lock); kvfree(nm_i->nat_block_bitmap); kvfree(nm_i->free_nid_bitmap); kvfree(nm_i->free_nid_count); kfree(nm_i->nat_bitmap); kfree(nm_i->nat_bits); #ifdef CONFIG_F2FS_CHECK_FS kfree(nm_i->nat_bitmap_mir); #endif sbi->nm_info = NULL; kfree(nm_i); } int __init create_node_manager_caches(void) { nat_entry_slab = f2fs_kmem_cache_create("nat_entry", sizeof(struct nat_entry)); if (!nat_entry_slab) goto fail; free_nid_slab = f2fs_kmem_cache_create("free_nid", sizeof(struct free_nid)); if (!free_nid_slab) goto destroy_nat_entry; nat_entry_set_slab = f2fs_kmem_cache_create("nat_entry_set", sizeof(struct nat_entry_set)); if (!nat_entry_set_slab) goto destroy_free_nid; return 0; destroy_free_nid: kmem_cache_destroy(free_nid_slab); destroy_nat_entry: kmem_cache_destroy(nat_entry_slab); fail: return -ENOMEM; } void destroy_node_manager_caches(void) { kmem_cache_destroy(nat_entry_set_slab); kmem_cache_destroy(free_nid_slab); kmem_cache_destroy(nat_entry_slab); } |
| 1961 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 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 | /* * ACPI device specific properties support. * * Copyright (C) 2014, Intel Corporation * All rights reserved. * * Authors: Mika Westerberg <mika.westerberg@linux.intel.com> * Darren Hart <dvhart@linux.intel.com> * Rafael J. Wysocki <rafael.j.wysocki@intel.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ #include <linux/acpi.h> #include <linux/device.h> #include <linux/export.h> #include "internal.h" static int acpi_data_get_property_array(const struct acpi_device_data *data, const char *name, acpi_object_type type, const union acpi_object **obj); /* ACPI _DSD device properties GUID: daffd814-6eba-4d8c-8a91-bc9bbf4aa301 */ static const guid_t prp_guid = GUID_INIT(0xdaffd814, 0x6eba, 0x4d8c, 0x8a, 0x91, 0xbc, 0x9b, 0xbf, 0x4a, 0xa3, 0x01); /* ACPI _DSD data subnodes GUID: dbb8e3e6-5886-4ba6-8795-1319f52a966b */ static const guid_t ads_guid = GUID_INIT(0xdbb8e3e6, 0x5886, 0x4ba6, 0x87, 0x95, 0x13, 0x19, 0xf5, 0x2a, 0x96, 0x6b); static bool acpi_enumerate_nondev_subnodes(acpi_handle scope, const union acpi_object *desc, struct acpi_device_data *data, struct fwnode_handle *parent); static bool acpi_extract_properties(const union acpi_object *desc, struct acpi_device_data *data); static bool acpi_nondev_subnode_extract(const union acpi_object *desc, acpi_handle handle, const union acpi_object *link, struct list_head *list, struct fwnode_handle *parent) { struct acpi_data_node *dn; bool result; dn = kzalloc(sizeof(*dn), GFP_KERNEL); if (!dn) return false; dn->name = link->package.elements[0].string.pointer; dn->fwnode.ops = &acpi_data_fwnode_ops; dn->parent = parent; INIT_LIST_HEAD(&dn->data.subnodes); result = acpi_extract_properties(desc, &dn->data); if (handle) { acpi_handle scope; acpi_status status; /* * The scope for the subnode object lookup is the one of the * namespace node (device) containing the object that has * returned the package. That is, it's the scope of that * object's parent. */ status = acpi_get_parent(handle, &scope); if (ACPI_SUCCESS(status) && acpi_enumerate_nondev_subnodes(scope, desc, &dn->data, &dn->fwnode)) result = true; } else if (acpi_enumerate_nondev_subnodes(NULL, desc, &dn->data, &dn->fwnode)) { result = true; } if (result) { dn->handle = handle; dn->data.pointer = desc; list_add_tail(&dn->sibling, list); return true; } kfree(dn); acpi_handle_debug(handle, "Invalid properties/subnodes data, skipping\n"); return false; } static bool acpi_nondev_subnode_data_ok(acpi_handle handle, const union acpi_object *link, struct list_head *list, struct fwnode_handle *parent) { struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER }; acpi_status status; status = acpi_evaluate_object_typed(handle, NULL, NULL, &buf, ACPI_TYPE_PACKAGE); if (ACPI_FAILURE(status)) return false; if (acpi_nondev_subnode_extract(buf.pointer, handle, link, list, parent)) return true; ACPI_FREE(buf.pointer); return false; } static bool acpi_nondev_subnode_ok(acpi_handle scope, const union acpi_object *link, struct list_head *list, struct fwnode_handle *parent) { acpi_handle handle; acpi_status status; if (!scope) return false; status = acpi_get_handle(scope, link->package.elements[1].string.pointer, &handle); if (ACPI_FAILURE(status)) return false; return acpi_nondev_subnode_data_ok(handle, link, list, parent); } static bool acpi_add_nondev_subnodes(acpi_handle scope, const union acpi_object *links, struct list_head *list, struct fwnode_handle *parent) { bool ret = false; int i; for (i = 0; i < links->package.count; i++) { const union acpi_object *link, *desc; acpi_handle handle; bool result; link = &links->package.elements[i]; /* Only two elements allowed. */ if (link->package.count != 2) continue; /* The first one must be a string. */ if (link->package.elements[0].type != ACPI_TYPE_STRING) continue; /* The second one may be a string, a reference or a package. */ switch (link->package.elements[1].type) { case ACPI_TYPE_STRING: result = acpi_nondev_subnode_ok(scope, link, list, parent); break; case ACPI_TYPE_LOCAL_REFERENCE: handle = link->package.elements[1].reference.handle; result = acpi_nondev_subnode_data_ok(handle, link, list, parent); break; case ACPI_TYPE_PACKAGE: desc = &link->package.elements[1]; result = acpi_nondev_subnode_extract(desc, NULL, link, list, parent); break; default: result = false; break; } ret = ret || result; } return ret; } static bool acpi_enumerate_nondev_subnodes(acpi_handle scope, const union acpi_object *desc, struct acpi_device_data *data, struct fwnode_handle *parent) { int i; /* Look for the ACPI data subnodes GUID. */ for (i = 0; i < desc->package.count; i += 2) { const union acpi_object *guid, *links; guid = &desc->package.elements[i]; links = &desc->package.elements[i + 1]; /* * The first element must be a GUID and the second one must be * a package. */ if (guid->type != ACPI_TYPE_BUFFER || guid->buffer.length != 16 || links->type != ACPI_TYPE_PACKAGE) break; if (!guid_equal((guid_t *)guid->buffer.pointer, &ads_guid)) continue; return acpi_add_nondev_subnodes(scope, links, &data->subnodes, parent); } return false; } static bool acpi_property_value_ok(const union acpi_object *value) { int j; /* * The value must be an integer, a string, a reference, or a package * whose every element must be an integer, a string, or a reference. */ switch (value->type) { case ACPI_TYPE_INTEGER: case ACPI_TYPE_STRING: case ACPI_TYPE_LOCAL_REFERENCE: return true; case ACPI_TYPE_PACKAGE: for (j = 0; j < value->package.count; j++) switch (value->package.elements[j].type) { case ACPI_TYPE_INTEGER: case ACPI_TYPE_STRING: case ACPI_TYPE_LOCAL_REFERENCE: continue; default: return false; } return true; } return false; } static bool acpi_properties_format_valid(const union acpi_object *properties) { int i; for (i = 0; i < properties->package.count; i++) { const union acpi_object *property; property = &properties->package.elements[i]; /* * Only two elements allowed, the first one must be a string and * the second one has to satisfy certain conditions. */ if (property->package.count != 2 || property->package.elements[0].type != ACPI_TYPE_STRING || !acpi_property_value_ok(&property->package.elements[1])) return false; } return true; } static void acpi_init_of_compatible(struct acpi_device *adev) { const union acpi_object *of_compatible; int ret; ret = acpi_data_get_property_array(&adev->data, "compatible", ACPI_TYPE_STRING, &of_compatible); if (ret) { ret = acpi_dev_get_property(adev, "compatible", ACPI_TYPE_STRING, &of_compatible); if (ret) { if (adev->parent && adev->parent->flags.of_compatible_ok) goto out; return; } } adev->data.of_compatible = of_compatible; out: adev->flags.of_compatible_ok = 1; } static bool acpi_extract_properties(const union acpi_object *desc, struct acpi_device_data *data) { int i; if (desc->package.count % 2) return false; /* Look for the device properties GUID. */ for (i = 0; i < desc->package.count; i += 2) { const union acpi_object *guid, *properties; guid = &desc->package.elements[i]; properties = &desc->package.elements[i + 1]; /* * The first element must be a GUID and the second one must be * a package. */ if (guid->type != ACPI_TYPE_BUFFER || guid->buffer.length != 16 || properties->type != ACPI_TYPE_PACKAGE) break; if (!guid_equal((guid_t *)guid->buffer.pointer, &prp_guid)) continue; /* * We found the matching GUID. Now validate the format of the * package immediately following it. */ if (!acpi_properties_format_valid(properties)) break; data->properties = properties; return true; } return false; } void acpi_init_properties(struct acpi_device *adev) { struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER }; struct acpi_hardware_id *hwid; acpi_status status; bool acpi_of = false; INIT_LIST_HEAD(&adev->data.subnodes); if (!adev->handle) return; /* * Check if ACPI_DT_NAMESPACE_HID is present and inthat case we fill in * Device Tree compatible properties for this device. */ list_for_each_entry(hwid, &adev->pnp.ids, list) { if (!strcmp(hwid->id, ACPI_DT_NAMESPACE_HID)) { acpi_of = true; break; } } status = acpi_evaluate_object_typed(adev->handle, "_DSD", NULL, &buf, ACPI_TYPE_PACKAGE); if (ACPI_FAILURE(status)) goto out; if (acpi_extract_properties(buf.pointer, &adev->data)) { adev->data.pointer = buf.pointer; if (acpi_of) acpi_init_of_compatible(adev); } if (acpi_enumerate_nondev_subnodes(adev->handle, buf.pointer, &adev->data, acpi_fwnode_handle(adev))) adev->data.pointer = buf.pointer; if (!adev->data.pointer) { acpi_handle_debug(adev->handle, "Invalid _DSD data, skipping\n"); ACPI_FREE(buf.pointer); } out: if (acpi_of && !adev->flags.of_compatible_ok) acpi_handle_info(adev->handle, ACPI_DT_NAMESPACE_HID " requires 'compatible' property\n"); if (!adev->data.pointer) acpi_extract_apple_properties(adev); } static void acpi_destroy_nondev_subnodes(struct list_head *list) { struct acpi_data_node *dn, *next; if (list_empty(list)) return; list_for_each_entry_safe_reverse(dn, next, list, sibling) { acpi_destroy_nondev_subnodes(&dn->data.subnodes); wait_for_completion(&dn->kobj_done); list_del(&dn->sibling); ACPI_FREE((void *)dn->data.pointer); kfree(dn); } } void acpi_free_properties(struct acpi_device *adev) { acpi_destroy_nondev_subnodes(&adev->data.subnodes); ACPI_FREE((void *)adev->data.pointer); adev->data.of_compatible = NULL; adev->data.pointer = NULL; adev->data.properties = NULL; } /** * acpi_data_get_property - return an ACPI property with given name * @data: ACPI device deta object to get the property from * @name: Name of the property * @type: Expected property type * @obj: Location to store the property value (if not %NULL) * * Look up a property with @name and store a pointer to the resulting ACPI * object at the location pointed to by @obj if found. * * Callers must not attempt to free the returned objects. These objects will be * freed by the ACPI core automatically during the removal of @data. * * Return: %0 if property with @name has been found (success), * %-EINVAL if the arguments are invalid, * %-EINVAL if the property doesn't exist, * %-EPROTO if the property value type doesn't match @type. */ static int acpi_data_get_property(const struct acpi_device_data *data, const char *name, acpi_object_type type, const union acpi_object **obj) { const union acpi_object *properties; int i; if (!data || !name) return -EINVAL; if (!data->pointer || !data->properties) return -EINVAL; properties = data->properties; for (i = 0; i < properties->package.count; i++) { const union acpi_object *propname, *propvalue; const union acpi_object *property; property = &properties->package.elements[i]; propname = &property->package.elements[0]; propvalue = &property->package.elements[1]; if (!strcmp(name, propname->string.pointer)) { if (type != ACPI_TYPE_ANY && propvalue->type != type) return -EPROTO; if (obj) *obj = propvalue; return 0; } } return -EINVAL; } /** * acpi_dev_get_property - return an ACPI property with given name. * @adev: ACPI device to get the property from. * @name: Name of the property. * @type: Expected property type. * @obj: Location to store the property value (if not %NULL). */ int acpi_dev_get_property(const struct acpi_device *adev, const char *name, acpi_object_type type, const union acpi_object **obj) { return adev ? acpi_data_get_property(&adev->data, name, type, obj) : -EINVAL; } EXPORT_SYMBOL_GPL(acpi_dev_get_property); static const struct acpi_device_data * acpi_device_data_of_node(const struct fwnode_handle *fwnode) { if (is_acpi_device_node(fwnode)) { const struct acpi_device *adev = to_acpi_device_node(fwnode); return &adev->data; } else if (is_acpi_data_node(fwnode)) { const struct acpi_data_node *dn = to_acpi_data_node(fwnode); return &dn->data; } return NULL; } /** * acpi_node_prop_get - return an ACPI property with given name. * @fwnode: Firmware node to get the property from. * @propname: Name of the property. * @valptr: Location to store a pointer to the property value (if not %NULL). */ int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname, void **valptr) { return acpi_data_get_property(acpi_device_data_of_node(fwnode), propname, ACPI_TYPE_ANY, (const union acpi_object **)valptr); } /** * acpi_data_get_property_array - return an ACPI array property with given name * @adev: ACPI data object to get the property from * @name: Name of the property * @type: Expected type of array elements * @obj: Location to store a pointer to the property value (if not NULL) * * Look up an array property with @name and store a pointer to the resulting * ACPI object at the location pointed to by @obj if found. * * Callers must not attempt to free the returned objects. Those objects will be * freed by the ACPI core automatically during the removal of @data. * * Return: %0 if array property (package) with @name has been found (success), * %-EINVAL if the arguments are invalid, * %-EINVAL if the property doesn't exist, * %-EPROTO if the property is not a package or the type of its elements * doesn't match @type. */ static int acpi_data_get_property_array(const struct acpi_device_data *data, const char *name, acpi_object_type type, const union acpi_object **obj) { const union acpi_object *prop; int ret, i; ret = acpi_data_get_property(data, name, ACPI_TYPE_PACKAGE, &prop); if (ret) return ret; if (type != ACPI_TYPE_ANY) { /* Check that all elements are of correct type. */ for (i = 0; i < prop->package.count; i++) if (prop->package.elements[i].type != type) return -EPROTO; } if (obj) *obj = prop; return 0; } /** * __acpi_node_get_property_reference - returns handle to the referenced object * @fwnode: Firmware node to get the property from * @propname: Name of the property * @index: Index of the reference to return * @num_args: Maximum number of arguments after each reference * @args: Location to store the returned reference with optional arguments * * Find property with @name, verifify that it is a package containing at least * one object reference and if so, store the ACPI device object pointer to the * target object in @args->adev. If the reference includes arguments, store * them in the @args->args[] array. * * If there's more than one reference in the property value package, @index is * used to select the one to return. * * It is possible to leave holes in the property value set like in the * example below: * * Package () { * "cs-gpios", * Package () { * ^GPIO, 19, 0, 0, * ^GPIO, 20, 0, 0, * 0, * ^GPIO, 21, 0, 0, * } * } * * Calling this function with index %2 or index %3 return %-ENOENT. If the * property does not contain any more values %-ENOENT is returned. The NULL * entry must be single integer and preferably contain value %0. * * Return: %0 on success, negative error code on failure. */ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, const char *propname, size_t index, size_t num_args, struct acpi_reference_args *args) { const union acpi_object *element, *end; const union acpi_object *obj; const struct acpi_device_data *data; struct acpi_device *device; int ret, idx = 0; data = acpi_device_data_of_node(fwnode); if (!data) return -ENOENT; ret = acpi_data_get_property(data, propname, ACPI_TYPE_ANY, &obj); if (ret) return ret == -EINVAL ? -ENOENT : -EINVAL; /* * The simplest case is when the value is a single reference. Just * return that reference then. */ if (obj->type == ACPI_TYPE_LOCAL_REFERENCE) { if (index) return -ENOENT; ret = acpi_bus_get_device(obj->reference.handle, &device); if (ret) return ret == -ENODEV ? -EINVAL : ret; args->adev = device; args->nargs = 0; return 0; } /* * If it is not a single reference, then it is a package of * references followed by number of ints as follows: * * Package () { REF, INT, REF, INT, INT } * * The index argument is then used to determine which reference * the caller wants (along with the arguments). */ if (obj->type != ACPI_TYPE_PACKAGE) return -EINVAL; if (index >= obj->package.count) return -ENOENT; element = obj->package.elements; end = element + obj->package.count; while (element < end) { u32 nargs, i; if (element->type == ACPI_TYPE_LOCAL_REFERENCE) { ret = acpi_bus_get_device(element->reference.handle, &device); if (ret) return -EINVAL; nargs = 0; element++; /* assume following integer elements are all args */ for (i = 0; element + i < end && i < num_args; i++) { int type = element[i].type; if (type == ACPI_TYPE_INTEGER) nargs++; else if (type == ACPI_TYPE_LOCAL_REFERENCE) break; else return -EINVAL; } if (nargs > MAX_ACPI_REFERENCE_ARGS) return -EINVAL; if (idx == index) { args->adev = device; args->nargs = nargs; for (i = 0; i < nargs; i++) args->args[i] = element[i].integer.value; return 0; } element += nargs; } else if (element->type == ACPI_TYPE_INTEGER) { if (idx == index) return -ENOENT; element++; } else { return -EINVAL; } idx++; } return -ENOENT; } EXPORT_SYMBOL_GPL(__acpi_node_get_property_reference); static int acpi_data_prop_read_single(const struct acpi_device_data *data, const char *propname, enum dev_prop_type proptype, void *val) { const union acpi_object *obj; int ret; if (proptype >= DEV_PROP_U8 && proptype <= DEV_PROP_U64) { ret = acpi_data_get_property(data, propname, ACPI_TYPE_INTEGER, &obj); if (ret) return ret; switch (proptype) { case DEV_PROP_U8: if (obj->integer.value > U8_MAX) return -EOVERFLOW; if (val) *(u8 *)val = obj->integer.value; break; case DEV_PROP_U16: if (obj->integer.value > U16_MAX) return -EOVERFLOW; if (val) *(u16 *)val = obj->integer.value; break; case DEV_PROP_U32: if (obj->integer.value > U32_MAX) return -EOVERFLOW; if (val) *(u32 *)val = obj->integer.value; break; default: if (val) *(u64 *)val = obj->integer.value; break; } if (!val) return 1; } else if (proptype == DEV_PROP_STRING) { ret = acpi_data_get_property(data, propname, ACPI_TYPE_STRING, &obj); if (ret) return ret; if (val) *(char **)val = obj->string.pointer; return 1; } else { ret = -EINVAL; } return ret; } int acpi_dev_prop_read_single(struct acpi_device *adev, const char *propname, enum dev_prop_type proptype, void *val) { int ret; if (!adev || !val) return -EINVAL; ret = acpi_data_prop_read_single(&adev->data, propname, proptype, val); if (ret < 0 || proptype != ACPI_TYPE_STRING) return ret; return 0; } static int acpi_copy_property_array_u8(const union acpi_object *items, u8 *val, size_t nval) { int i; for (i = 0; i < nval; i++) { if (items[i].type != ACPI_TYPE_INTEGER) return -EPROTO; if (items[i].integer.value > U8_MAX) return -EOVERFLOW; val[i] = items[i].integer.value; } return 0; } static int acpi_copy_property_array_u16(const union acpi_object *items, u16 *val, size_t nval) { int i; for (i = 0; i < nval; i++) { if (items[i].type != ACPI_TYPE_INTEGER) return -EPROTO; if (items[i].integer.value > U16_MAX) return -EOVERFLOW; val[i] = items[i].integer.value; } return 0; } static int acpi_copy_property_array_u32(const union acpi_object *items, u32 *val, size_t nval) { int i; for (i = 0; i < nval; i++) { if (items[i].type != ACPI_TYPE_INTEGER) return -EPROTO; if (items[i].integer.value > U32_MAX) return -EOVERFLOW; val[i] = items[i].integer.value; } return 0; } static int acpi_copy_property_array_u64(const union acpi_object *items, u64 *val, size_t nval) { int i; for (i = 0; i < nval; i++) { if (items[i].type != ACPI_TYPE_INTEGER) return -EPROTO; val[i] = items[i].integer.value; } return 0; } static int acpi_copy_property_array_string(const union acpi_object *items, char **val, size_t nval) { int i; for (i = 0; i < nval; i++) { if (items[i].type != ACPI_TYPE_STRING) return -EPROTO; val[i] = items[i].string.pointer; } return nval; } static int acpi_data_prop_read(const struct acpi_device_data *data, const char *propname, enum dev_prop_type proptype, void *val, size_t nval) { const union acpi_object *obj; const union acpi_object *items; int ret; if (nval == 1 || !val) { ret = acpi_data_prop_read_single(data, propname, proptype, val); /* * The overflow error means that the property is there and it is * single-value, but its type does not match, so return. */ if (ret >= 0 || ret == -EOVERFLOW) return ret; /* * Reading this property as a single-value one failed, but its * value may still be represented as one-element array, so * continue. */ } ret = acpi_data_get_property_array(data, propname, ACPI_TYPE_ANY, &obj); if (ret) return ret; if (!val) return obj->package.count; if (proptype != DEV_PROP_STRING && nval > obj->package.count) return -EOVERFLOW; else if (nval <= 0) return -EINVAL; items = obj->package.elements; switch (proptype) { case DEV_PROP_U8: ret = acpi_copy_property_array_u8(items, (u8 *)val, nval); break; case DEV_PROP_U16: ret = acpi_copy_property_array_u16(items, (u16 *)val, nval); break; case DEV_PROP_U32: ret = acpi_copy_property_array_u32(items, (u32 *)val, nval); break; case DEV_PROP_U64: ret = acpi_copy_property_array_u64(items, (u64 *)val, nval); break; case DEV_PROP_STRING: ret = acpi_copy_property_array_string( items, (char **)val, min_t(u32, nval, obj->package.count)); break; default: ret = -EINVAL; break; } return ret; } int acpi_dev_prop_read(const struct acpi_device *adev, const char *propname, enum dev_prop_type proptype, void *val, size_t nval) { return adev ? acpi_data_prop_read(&adev->data, propname, proptype, val, nval) : -EINVAL; } /** * acpi_node_prop_read - retrieve the value of an ACPI property with given name. * @fwnode: Firmware node to get the property from. * @propname: Name of the property. * @proptype: Expected property type. * @val: Location to store the property value (if not %NULL). * @nval: Size of the array pointed to by @val. * * If @val is %NULL, return the number of array elements comprising the value * of the property. Otherwise, read at most @nval values to the array at the * location pointed to by @val. */ int acpi_node_prop_read(const struct fwnode_handle *fwnode, const char *propname, enum dev_prop_type proptype, void *val, size_t nval) { return acpi_data_prop_read(acpi_device_data_of_node(fwnode), propname, proptype, val, nval); } /** * acpi_get_next_subnode - Return the next child node handle for a fwnode * @fwnode: Firmware node to find the next child node for. * @child: Handle to one of the device's child nodes or a null handle. */ struct fwnode_handle *acpi_get_next_subnode(const struct fwnode_handle *fwnode, struct fwnode_handle *child) { const struct acpi_device *adev = to_acpi_device_node(fwnode); const struct list_head *head; struct list_head *next; if (!child || is_acpi_device_node(child)) { struct acpi_device *child_adev; if (adev) head = &adev->children; else goto nondev; if (list_empty(head)) goto nondev; if (child) { adev = to_acpi_device_node(child); next = adev->node.next; if (next == head) { child = NULL; goto nondev; } child_adev = list_entry(next, struct acpi_device, node); } else { child_adev = list_first_entry(head, struct acpi_device, node); } return acpi_fwnode_handle(child_adev); } nondev: if (!child || is_acpi_data_node(child)) { const struct acpi_data_node *data = to_acpi_data_node(fwnode); struct acpi_data_node *dn; /* * We can have a combination of device and data nodes, e.g. with * hierarchical _DSD properties. Make sure the adev pointer is * restored before going through data nodes, otherwise we will * be looking for data_nodes below the last device found instead * of the common fwnode shared by device_nodes and data_nodes. */ adev = to_acpi_device_node(fwnode); if (adev) head = &adev->data.subnodes; else if (data) head = &data->data.subnodes; else return NULL; if (list_empty(head)) return NULL; if (child) { dn = to_acpi_data_node(child); next = dn->sibling.next; if (next == head) return NULL; dn = list_entry(next, struct acpi_data_node, sibling); } else { dn = list_first_entry(head, struct acpi_data_node, sibling); } return &dn->fwnode; } return NULL; } /** * acpi_node_get_parent - Return parent fwnode of this fwnode * @fwnode: Firmware node whose parent to get * * Returns parent node of an ACPI device or data firmware node or %NULL if * not available. */ struct fwnode_handle *acpi_node_get_parent(const struct fwnode_handle *fwnode) { if (is_acpi_data_node(fwnode)) { /* All data nodes have parent pointer so just return that */ return to_acpi_data_node(fwnode)->parent; } else if (is_acpi_device_node(fwnode)) { acpi_handle handle, parent_handle; handle = to_acpi_device_node(fwnode)->handle; if (ACPI_SUCCESS(acpi_get_parent(handle, &parent_handle))) { struct acpi_device *adev; if (!acpi_bus_get_device(parent_handle, &adev)) return acpi_fwnode_handle(adev); } } return NULL; } /** * acpi_graph_get_next_endpoint - Get next endpoint ACPI firmware node * @fwnode: Pointer to the parent firmware node * @prev: Previous endpoint node or %NULL to get the first * * Looks up next endpoint ACPI firmware node below a given @fwnode. Returns * %NULL if there is no next endpoint, ERR_PTR() in case of error. In case * of success the next endpoint is returned. */ struct fwnode_handle *acpi_graph_get_next_endpoint( const struct fwnode_handle *fwnode, struct fwnode_handle *prev) { struct fwnode_handle *port = NULL; struct fwnode_handle *endpoint; if (!prev) { do { port = fwnode_get_next_child_node(fwnode, port); /* Ports must have port property */ if (fwnode_property_present(port, "port")) break; } while (port); } else { port = fwnode_get_parent(prev); } if (!port) return NULL; endpoint = fwnode_get_next_child_node(port, prev); while (!endpoint) { port = fwnode_get_next_child_node(fwnode, port); if (!port) break; if (fwnode_property_present(port, "port")) endpoint = fwnode_get_next_child_node(port, NULL); } if (endpoint) { /* Endpoints must have "endpoint" property */ if (!fwnode_property_present(endpoint, "endpoint")) return ERR_PTR(-EPROTO); } return endpoint; } /** * acpi_graph_get_child_prop_value - Return a child with a given property value * @fwnode: device fwnode * @prop_name: The name of the property to look for * @val: the desired property value * * Return the port node corresponding to a given port number. Returns * the child node on success, NULL otherwise. */ static struct fwnode_handle *acpi_graph_get_child_prop_value( const struct fwnode_handle *fwnode, const char *prop_name, unsigned int val) { struct fwnode_handle *child; fwnode_for_each_child_node(fwnode, child) { u32 nr; if (fwnode_property_read_u32(child, prop_name, &nr)) continue; if (val == nr) return child; } return NULL; } /** * acpi_graph_get_remote_enpoint - Parses and returns remote end of an endpoint * @fwnode: Endpoint firmware node pointing to a remote device * @parent: Firmware node of remote port parent is filled here if not %NULL * @port: Firmware node of remote port is filled here if not %NULL * @endpoint: Firmware node of remote endpoint is filled here if not %NULL * * Function parses remote end of ACPI firmware remote endpoint and fills in * fields requested by the caller. Returns %0 in case of success and * negative errno otherwise. */ int acpi_graph_get_remote_endpoint(const struct fwnode_handle *__fwnode, struct fwnode_handle **parent, struct fwnode_handle **port, struct fwnode_handle **endpoint) { struct fwnode_handle *fwnode; unsigned int port_nr, endpoint_nr; struct acpi_reference_args args; int ret; memset(&args, 0, sizeof(args)); ret = acpi_node_get_property_reference(__fwnode, "remote-endpoint", 0, &args); if (ret) return ret; /* * Always require two arguments with the reference: port and * endpoint indices. */ if (args.nargs != 2) return -EPROTO; fwnode = acpi_fwnode_handle(args.adev); port_nr = args.args[0]; endpoint_nr = args.args[1]; if (parent) *parent = fwnode; if (!port && !endpoint) return 0; fwnode = acpi_graph_get_child_prop_value(fwnode, "port", port_nr); if (!fwnode) return -EPROTO; if (port) *port = fwnode; if (!endpoint) return 0; fwnode = acpi_graph_get_child_prop_value(fwnode, "endpoint", endpoint_nr); if (!fwnode) return -EPROTO; *endpoint = fwnode; return 0; } static bool acpi_fwnode_device_is_available(const struct fwnode_handle *fwnode) { if (!is_acpi_device_node(fwnode)) return false; return acpi_device_is_present(to_acpi_device_node(fwnode)); } static bool acpi_fwnode_property_present(const struct fwnode_handle *fwnode, const char *propname) { return !acpi_node_prop_get(fwnode, propname, NULL); } static int acpi_fwnode_property_read_int_array(const struct fwnode_handle *fwnode, const char *propname, unsigned int elem_size, void *val, size_t nval) { enum dev_prop_type type; switch (elem_size) { case sizeof(u8): type = DEV_PROP_U8; break; case sizeof(u16): type = DEV_PROP_U16; break; case sizeof(u32): type = DEV_PROP_U32; break; case sizeof(u64): type = DEV_PROP_U64; break; default: return -ENXIO; } return acpi_node_prop_read(fwnode, propname, type, val, nval); } static int acpi_fwnode_property_read_string_array(const struct fwnode_handle *fwnode, const char *propname, const char **val, size_t nval) { return acpi_node_prop_read(fwnode, propname, DEV_PROP_STRING, val, nval); } static struct fwnode_handle * acpi_fwnode_get_named_child_node(const struct fwnode_handle *fwnode, const char *childname) { struct fwnode_handle *child; /* * Find first matching named child node of this fwnode. * For ACPI this will be a data only sub-node. */ fwnode_for_each_child_node(fwnode, child) if (acpi_data_node_match(child, childname)) return child; return NULL; } static int acpi_fwnode_get_reference_args(const struct fwnode_handle *fwnode, const char *prop, const char *nargs_prop, unsigned int args_count, unsigned int index, struct fwnode_reference_args *args) { struct acpi_reference_args acpi_args; unsigned int i; int ret; ret = __acpi_node_get_property_reference(fwnode, prop, index, args_count, &acpi_args); if (ret < 0) return ret; if (!args) return 0; args->nargs = acpi_args.nargs; args->fwnode = acpi_fwnode_handle(acpi_args.adev); for (i = 0; i < NR_FWNODE_REFERENCE_ARGS; i++) args->args[i] = i < acpi_args.nargs ? acpi_args.args[i] : 0; return 0; } static struct fwnode_handle * acpi_fwnode_graph_get_next_endpoint(const struct fwnode_handle *fwnode, struct fwnode_handle *prev) { struct fwnode_handle *endpoint; endpoint = acpi_graph_get_next_endpoint(fwnode, prev); if (IS_ERR(endpoint)) return NULL; return endpoint; } static struct fwnode_handle * acpi_fwnode_graph_get_remote_endpoint(const struct fwnode_handle *fwnode) { struct fwnode_handle *endpoint = NULL; acpi_graph_get_remote_endpoint(fwnode, NULL, NULL, &endpoint); return endpoint; } static struct fwnode_handle * acpi_fwnode_get_parent(struct fwnode_handle *fwnode) { return acpi_node_get_parent(fwnode); } static int acpi_fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode, struct fwnode_endpoint *endpoint) { struct fwnode_handle *port_fwnode = fwnode_get_parent(fwnode); endpoint->local_fwnode = fwnode; fwnode_property_read_u32(port_fwnode, "port", &endpoint->port); fwnode_property_read_u32(fwnode, "endpoint", &endpoint->id); return 0; } #define DECLARE_ACPI_FWNODE_OPS(ops) \ const struct fwnode_operations ops = { \ .device_is_available = acpi_fwnode_device_is_available, \ .property_present = acpi_fwnode_property_present, \ .property_read_int_array = \ acpi_fwnode_property_read_int_array, \ .property_read_string_array = \ acpi_fwnode_property_read_string_array, \ .get_parent = acpi_node_get_parent, \ .get_next_child_node = acpi_get_next_subnode, \ .get_named_child_node = acpi_fwnode_get_named_child_node, \ .get_reference_args = acpi_fwnode_get_reference_args, \ .graph_get_next_endpoint = \ acpi_fwnode_graph_get_next_endpoint, \ .graph_get_remote_endpoint = \ acpi_fwnode_graph_get_remote_endpoint, \ .graph_get_port_parent = acpi_fwnode_get_parent, \ .graph_parse_endpoint = acpi_fwnode_graph_parse_endpoint, \ }; \ EXPORT_SYMBOL_GPL(ops) DECLARE_ACPI_FWNODE_OPS(acpi_device_fwnode_ops); DECLARE_ACPI_FWNODE_OPS(acpi_data_fwnode_ops); const struct fwnode_operations acpi_static_fwnode_ops; bool is_acpi_device_node(const struct fwnode_handle *fwnode) { return !IS_ERR_OR_NULL(fwnode) && fwnode->ops == &acpi_device_fwnode_ops; } EXPORT_SYMBOL(is_acpi_device_node); bool is_acpi_data_node(const struct fwnode_handle *fwnode) { return !IS_ERR_OR_NULL(fwnode) && fwnode->ops == &acpi_data_fwnode_ops; } EXPORT_SYMBOL(is_acpi_data_node); |
| 150 258 3 82 229 197 189 11 5 71 73 90 41 40 33 30 41 43 4 32 38 415 56 18 2 10 189 38 4 105 151 1 150 415 414 415 400 8 7 187 187 150 8 70 41 6 49 2 2 47 47 47 41 41 41 41 6 48 1 11 1 1 8 8 469 469 468 468 393 395 16 181 130 67 176 181 1 1 39 215 134 115 118 41 3 1 1 1 1 1 3 1 1 1 3 1 1 1 2 5 4 4 4 141 79 141 3 137 5 138 138 80 10 199 157 137 138 2 136 3 156 78 79 79 79 65 8 46 13 76 57 21 10 7 31 3 29 22 12 29 33 78 85 18 6 18 18 18 12 81 7 4 76 85 39 9 154 122 5 4 15 2 1 1 1 1 2 159 158 159 137 138 159 5 159 138 138 3 190 4 41 14 27 41 25 3 3 2 25 1 3 84 84 85 3 84 83 85 79 84 10 10 92 8 64 2 84 64 78 6 6 1 74 74 3 71 2 49 49 49 49 49 64 7 5 4 1 66 2 64 49 64 43 64 61 52 78 49 91 10 1 10 119 191 132 129 2 5 15 15 10 5 33 33 30 8 3 3 3 4 4 2 6 1 5 3 5 6 3 2 5 5 5 5 5 1 1 1 1 1 1 1 3 2 2 1 1 2 1 1 1 1 1 3 48 48 47 2 3 3 6 6 2 2 1 1 1 1 1 1 1 2 2 1 1 2 3 3 3 3 3 2 2 2 1 1 1 2 2 1 1 1 1 58 2 28 2 2 2 2 56 56 2 2 2 2 2 2 2 2 2 2 2 2 2 1 1 1 1 2 1 9 9 9 9 9 9 9 9 9 8 8 2 6 8 8 6 3 3 3 3 10 2 12 12 11 12 9 12 12 10 4 1 4 4 4 4 4 12 35 34 35 27 27 1 27 2 26 2 27 1 27 1 1 1 1 1 2 2 1 1 1 3 3 3 7 7 29 29 1 1 1 1 70 42 42 42 3 2 3 3 3 2 2 2 1 2 3 3 2 2 2 2 2 6 65 2 1 2 1 19 19 19 3 3 1 3 2 3 1 1 1 7 7 3 6 2 1 2 41 41 41 19 2 2 1 1 2 2 2 6 6 6 6 6 6 5 5 5 5 1 1 1 1 1 1 1 44 43 43 43 43 42 41 41 41 41 1 2 1 3 3 3 3 1 3 3 2 2 41 18 20 9 86 108 54 18 78 107 7 3 4 108 260 3 164 172 172 98 97 1 1 1 1 28 28 28 53 2 2 42 4 86 11 1 72 4 19 19 17 1 1 1 1 49 49 4 2 1 3 3 1 1 259 260 469 468 391 148 393 71 12 12 8 30 6 3 8 16 99 45 34 20 132 393 42 323 392 233 230 210 25 25 394 338 389 36 65 358 223 129 82 48 34 41 11 8 3 7 1 1 2 8 1 7 2 2 22 22 223 389 389 213 262 199 66 21 66 201 4 48 201 1 201 3 198 5 261 136 195 198 187 183 260 187 260 259 4 4 4 267 1 469 146 5 5 5 3 124 102 29 125 124 475 260 4 257 258 209 209 208 209 5 206 3 5 206 5 205 204 1 204 101 202 5 203 1 3 252 73 69 249 1 248 229 131 25 6 3 219 240 5 240 6 240 234 125 208 109 97 97 13 1 6 4 2 1 1 1 1 2 71 1 20 2 1 1 1 192 4 4 191 191 192 192 17 192 23 192 5 2 3 5 5 3 3 189 78 43 259 56 193 56 64 1 44 1 1 4 2 1 1 1 1 1 1 165 166 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 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 | /****************************************************************************** * emulate.c * * Generic x86 (32-bit and 64-bit) instruction decoder and emulator. * * Copyright (c) 2005 Keir Fraser * * Linux coding style, mod r/m decoder, segment base fixes, real-mode * privileged instructions: * * Copyright (C) 2006 Qumranet * Copyright 2010 Red Hat, Inc. and/or its affiliates. * * Avi Kivity <avi@qumranet.com> * Yaniv Kamay <yaniv@qumranet.com> * * This work is licensed under the terms of the GNU GPL, version 2. See * the COPYING file in the top-level directory. * * From: xen-unstable 10676:af9809f51f81a3c43f276f00c81a52ef558afda4 */ #include <linux/kvm_host.h> #include "kvm_cache_regs.h" #include <asm/kvm_emulate.h> #include <linux/stringify.h> #include <asm/debugreg.h> #include <asm/nospec-branch.h> #include "x86.h" #include "tss.h" #include "mmu.h" /* * Operand types */ #define OpNone 0ull #define OpImplicit 1ull /* No generic decode */ #define OpReg 2ull /* Register */ #define OpMem 3ull /* Memory */ #define OpAcc 4ull /* Accumulator: AL/AX/EAX/RAX */ #define OpDI 5ull /* ES:DI/EDI/RDI */ #define OpMem64 6ull /* Memory, 64-bit */ #define OpImmUByte 7ull /* Zero-extended 8-bit immediate */ #define OpDX 8ull /* DX register */ #define OpCL 9ull /* CL register (for shifts) */ #define OpImmByte 10ull /* 8-bit sign extended immediate */ #define OpOne 11ull /* Implied 1 */ #define OpImm 12ull /* Sign extended up to 32-bit immediate */ #define OpMem16 13ull /* Memory operand (16-bit). */ #define OpMem32 14ull /* Memory operand (32-bit). */ #define OpImmU 15ull /* Immediate operand, zero extended */ #define OpSI 16ull /* SI/ESI/RSI */ #define OpImmFAddr 17ull /* Immediate far address */ #define OpMemFAddr 18ull /* Far address in memory */ #define OpImmU16 19ull /* Immediate operand, 16 bits, zero extended */ #define OpES 20ull /* ES */ #define OpCS 21ull /* CS */ #define OpSS 22ull /* SS */ #define OpDS 23ull /* DS */ #define OpFS 24ull /* FS */ #define OpGS 25ull /* GS */ #define OpMem8 26ull /* 8-bit zero extended memory operand */ #define OpImm64 27ull /* Sign extended 16/32/64-bit immediate */ #define OpXLat 28ull /* memory at BX/EBX/RBX + zero-extended AL */ #define OpAccLo 29ull /* Low part of extended acc (AX/AX/EAX/RAX) */ #define OpAccHi 30ull /* High part of extended acc (-/DX/EDX/RDX) */ #define OpBits 5 /* Width of operand field */ #define OpMask ((1ull << OpBits) - 1) /* * Opcode effective-address decode tables. * Note that we only emulate instructions that have at least one memory * operand (excluding implicit stack references). We assume that stack * references and instruction fetches will never occur in special memory * areas that require emulation. So, for example, 'mov <imm>,<reg>' need * not be handled. */ /* Operand sizes: 8-bit operands or specified/overridden size. */ #define ByteOp (1<<0) /* 8-bit operands. */ /* Destination operand type. */ #define DstShift 1 #define ImplicitOps (OpImplicit << DstShift) #define DstReg (OpReg << DstShift) #define DstMem (OpMem << DstShift) #define DstAcc (OpAcc << DstShift) #define DstDI (OpDI << DstShift) #define DstMem64 (OpMem64 << DstShift) #define DstMem16 (OpMem16 << DstShift) #define DstImmUByte (OpImmUByte << DstShift) #define DstDX (OpDX << DstShift) #define DstAccLo (OpAccLo << DstShift) #define DstMask (OpMask << DstShift) /* Source operand type. */ #define SrcShift 6 #define SrcNone (OpNone << SrcShift) #define SrcReg (OpReg << SrcShift) #define SrcMem (OpMem << SrcShift) #define SrcMem16 (OpMem16 << SrcShift) #define SrcMem32 (OpMem32 << SrcShift) #define SrcImm (OpImm << SrcShift) #define SrcImmByte (OpImmByte << SrcShift) #define SrcOne (OpOne << SrcShift) #define SrcImmUByte (OpImmUByte << SrcShift) #define SrcImmU (OpImmU << SrcShift) #define SrcSI (OpSI << SrcShift) #define SrcXLat (OpXLat << SrcShift) #define SrcImmFAddr (OpImmFAddr << SrcShift) #define SrcMemFAddr (OpMemFAddr << SrcShift) #define SrcAcc (OpAcc << SrcShift) #define SrcImmU16 (OpImmU16 << SrcShift) #define SrcImm64 (OpImm64 << SrcShift) #define SrcDX (OpDX << SrcShift) #define SrcMem8 (OpMem8 << SrcShift) #define SrcAccHi (OpAccHi << SrcShift) #define SrcMask (OpMask << SrcShift) #define BitOp (1<<11) #define MemAbs (1<<12) /* Memory operand is absolute displacement */ #define String (1<<13) /* String instruction (rep capable) */ #define Stack (1<<14) /* Stack instruction (push/pop) */ #define GroupMask (7<<15) /* Opcode uses one of the group mechanisms */ #define Group (1<<15) /* Bits 3:5 of modrm byte extend opcode */ #define GroupDual (2<<15) /* Alternate decoding of mod == 3 */ #define Prefix (3<<15) /* Instruction varies with 66/f2/f3 prefix */ #define RMExt (4<<15) /* Opcode extension in ModRM r/m if mod == 3 */ #define Escape (5<<15) /* Escape to coprocessor instruction */ #define InstrDual (6<<15) /* Alternate instruction decoding of mod == 3 */ #define ModeDual (7<<15) /* Different instruction for 32/64 bit */ #define Sse (1<<18) /* SSE Vector instruction */ /* Generic ModRM decode. */ #define ModRM (1<<19) /* Destination is only written; never read. */ #define Mov (1<<20) /* Misc flags */ #define Prot (1<<21) /* instruction generates #UD if not in prot-mode */ #define EmulateOnUD (1<<22) /* Emulate if unsupported by the host */ #define NoAccess (1<<23) /* Don't access memory (lea/invlpg/verr etc) */ #define Op3264 (1<<24) /* Operand is 64b in long mode, 32b otherwise */ #define Undefined (1<<25) /* No Such Instruction */ #define Lock (1<<26) /* lock prefix is allowed for the instruction */ #define Priv (1<<27) /* instruction generates #GP if current CPL != 0 */ #define No64 (1<<28) #define PageTable (1 << 29) /* instruction used to write page table */ #define NotImpl (1 << 30) /* instruction is not implemented */ /* Source 2 operand type */ #define Src2Shift (31) #define Src2None (OpNone << Src2Shift) #define Src2Mem (OpMem << Src2Shift) #define Src2CL (OpCL << Src2Shift) #define Src2ImmByte (OpImmByte << Src2Shift) #define Src2One (OpOne << Src2Shift) #define Src2Imm (OpImm << Src2Shift) #define Src2ES (OpES << Src2Shift) #define Src2CS (OpCS << Src2Shift) #define Src2SS (OpSS << Src2Shift) #define Src2DS (OpDS << Src2Shift) #define Src2FS (OpFS << Src2Shift) #define Src2GS (OpGS << Src2Shift) #define Src2Mask (OpMask << Src2Shift) #define Mmx ((u64)1 << 40) /* MMX Vector instruction */ #define AlignMask ((u64)7 << 41) #define Aligned ((u64)1 << 41) /* Explicitly aligned (e.g. MOVDQA) */ #define Unaligned ((u64)2 << 41) /* Explicitly unaligned (e.g. MOVDQU) */ #define Avx ((u64)3 << 41) /* Advanced Vector Extensions */ #define Aligned16 ((u64)4 << 41) /* Aligned to 16 byte boundary (e.g. FXSAVE) */ #define Fastop ((u64)1 << 44) /* Use opcode::u.fastop */ #define NoWrite ((u64)1 << 45) /* No writeback */ #define SrcWrite ((u64)1 << 46) /* Write back src operand */ #define NoMod ((u64)1 << 47) /* Mod field is ignored */ #define Intercept ((u64)1 << 48) /* Has valid intercept field */ #define CheckPerm ((u64)1 << 49) /* Has valid check_perm field */ #define PrivUD ((u64)1 << 51) /* #UD instead of #GP on CPL > 0 */ #define NearBranch ((u64)1 << 52) /* Near branches */ #define No16 ((u64)1 << 53) /* No 16 bit operand */ #define IncSP ((u64)1 << 54) /* SP is incremented before ModRM calc */ #define TwoMemOp ((u64)1 << 55) /* Instruction has two memory operand */ #define DstXacc (DstAccLo | SrcAccHi | SrcWrite) #define X2(x...) x, x #define X3(x...) X2(x), x #define X4(x...) X2(x), X2(x) #define X5(x...) X4(x), x #define X6(x...) X4(x), X2(x) #define X7(x...) X4(x), X3(x) #define X8(x...) X4(x), X4(x) #define X16(x...) X8(x), X8(x) #define NR_FASTOP (ilog2(sizeof(ulong)) + 1) #define FASTOP_SIZE 8 /* * fastop functions have a special calling convention: * * dst: rax (in/out) * src: rdx (in/out) * src2: rcx (in) * flags: rflags (in/out) * ex: rsi (in:fastop pointer, out:zero if exception) * * Moreover, they are all exactly FASTOP_SIZE bytes long, so functions for * different operand sizes can be reached by calculation, rather than a jump * table (which would be bigger than the code). * * fastop functions are declared as taking a never-defined fastop parameter, * so they can't be called from C directly. */ struct fastop; struct opcode { u64 flags : 56; u64 intercept : 8; union { int (*execute)(struct x86_emulate_ctxt *ctxt); const struct opcode *group; const struct group_dual *gdual; const struct gprefix *gprefix; const struct escape *esc; const struct instr_dual *idual; const struct mode_dual *mdual; void (*fastop)(struct fastop *fake); } u; int (*check_perm)(struct x86_emulate_ctxt *ctxt); }; struct group_dual { struct opcode mod012[8]; struct opcode mod3[8]; }; struct gprefix { struct opcode pfx_no; struct opcode pfx_66; struct opcode pfx_f2; struct opcode pfx_f3; }; struct escape { struct opcode op[8]; struct opcode high[64]; }; struct instr_dual { struct opcode mod012; struct opcode mod3; }; struct mode_dual { struct opcode mode32; struct opcode mode64; }; #define EFLG_RESERVED_ZEROS_MASK 0xffc0802a enum x86_transfer_type { X86_TRANSFER_NONE, X86_TRANSFER_CALL_JMP, X86_TRANSFER_RET, X86_TRANSFER_TASK_SWITCH, }; static ulong reg_read(struct x86_emulate_ctxt *ctxt, unsigned nr) { if (!(ctxt->regs_valid & (1 << nr))) { ctxt->regs_valid |= 1 << nr; ctxt->_regs[nr] = ctxt->ops->read_gpr(ctxt, nr); } return ctxt->_regs[nr]; } static ulong *reg_write(struct x86_emulate_ctxt *ctxt, unsigned nr) { ctxt->regs_valid |= 1 << nr; ctxt->regs_dirty |= 1 << nr; return &ctxt->_regs[nr]; } static ulong *reg_rmw(struct x86_emulate_ctxt *ctxt, unsigned nr) { reg_read(ctxt, nr); return reg_write(ctxt, nr); } static void writeback_registers(struct x86_emulate_ctxt *ctxt) { unsigned reg; for_each_set_bit(reg, (ulong *)&ctxt->regs_dirty, 16) ctxt->ops->write_gpr(ctxt, reg, ctxt->_regs[reg]); } static void invalidate_registers(struct x86_emulate_ctxt *ctxt) { ctxt->regs_dirty = 0; ctxt->regs_valid = 0; } /* * These EFLAGS bits are restored from saved value during emulation, and * any changes are written back to the saved value after emulation. */ #define EFLAGS_MASK (X86_EFLAGS_OF|X86_EFLAGS_SF|X86_EFLAGS_ZF|X86_EFLAGS_AF|\ X86_EFLAGS_PF|X86_EFLAGS_CF) #ifdef CONFIG_X86_64 #define ON64(x) x #else #define ON64(x) #endif static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)); #define FOP_FUNC(name) \ ".align " __stringify(FASTOP_SIZE) " \n\t" \ ".type " name ", @function \n\t" \ name ":\n\t" #define FOP_RET "ret \n\t" #define FOP_START(op) \ extern void em_##op(struct fastop *fake); \ asm(".pushsection .text, \"ax\" \n\t" \ ".global em_" #op " \n\t" \ FOP_FUNC("em_" #op) #define FOP_END \ ".popsection") #define FOPNOP() \ FOP_FUNC(__stringify(__UNIQUE_ID(nop))) \ FOP_RET #define FOP1E(op, dst) \ FOP_FUNC(#op "_" #dst) \ "10: " #op " %" #dst " \n\t" FOP_RET #define FOP1EEX(op, dst) \ FOP1E(op, dst) _ASM_EXTABLE(10b, kvm_fastop_exception) #define FASTOP1(op) \ FOP_START(op) \ FOP1E(op##b, al) \ FOP1E(op##w, ax) \ FOP1E(op##l, eax) \ ON64(FOP1E(op##q, rax)) \ FOP_END /* 1-operand, using src2 (for MUL/DIV r/m) */ #define FASTOP1SRC2(op, name) \ FOP_START(name) \ FOP1E(op, cl) \ FOP1E(op, cx) \ FOP1E(op, ecx) \ ON64(FOP1E(op, rcx)) \ FOP_END /* 1-operand, using src2 (for MUL/DIV r/m), with exceptions */ #define FASTOP1SRC2EX(op, name) \ FOP_START(name) \ FOP1EEX(op, cl) \ FOP1EEX(op, cx) \ FOP1EEX(op, ecx) \ ON64(FOP1EEX(op, rcx)) \ FOP_END #define FOP2E(op, dst, src) \ FOP_FUNC(#op "_" #dst "_" #src) \ #op " %" #src ", %" #dst " \n\t" FOP_RET #define FASTOP2(op) \ FOP_START(op) \ FOP2E(op##b, al, dl) \ FOP2E(op##w, ax, dx) \ FOP2E(op##l, eax, edx) \ ON64(FOP2E(op##q, rax, rdx)) \ FOP_END /* 2 operand, word only */ #define FASTOP2W(op) \ FOP_START(op) \ FOPNOP() \ FOP2E(op##w, ax, dx) \ FOP2E(op##l, eax, edx) \ ON64(FOP2E(op##q, rax, rdx)) \ FOP_END /* 2 operand, src is CL */ #define FASTOP2CL(op) \ FOP_START(op) \ FOP2E(op##b, al, cl) \ FOP2E(op##w, ax, cl) \ FOP2E(op##l, eax, cl) \ ON64(FOP2E(op##q, rax, cl)) \ FOP_END /* 2 operand, src and dest are reversed */ #define FASTOP2R(op, name) \ FOP_START(name) \ FOP2E(op##b, dl, al) \ FOP2E(op##w, dx, ax) \ FOP2E(op##l, edx, eax) \ ON64(FOP2E(op##q, rdx, rax)) \ FOP_END #define FOP3E(op, dst, src, src2) \ FOP_FUNC(#op "_" #dst "_" #src "_" #src2) \ #op " %" #src2 ", %" #src ", %" #dst " \n\t" FOP_RET /* 3-operand, word-only, src2=cl */ #define FASTOP3WCL(op) \ FOP_START(op) \ FOPNOP() \ FOP3E(op##w, ax, dx, cl) \ FOP3E(op##l, eax, edx, cl) \ ON64(FOP3E(op##q, rax, rdx, cl)) \ FOP_END /* Special case for SETcc - 1 instruction per cc */ #define FOP_SETCC(op) \ ".align 4 \n\t" \ ".type " #op ", @function \n\t" \ #op ": \n\t" \ #op " %al \n\t" \ FOP_RET asm(".pushsection .fixup, \"ax\"\n" ".global kvm_fastop_exception \n" "kvm_fastop_exception: xor %esi, %esi; ret\n" ".popsection"); FOP_START(setcc) FOP_SETCC(seto) FOP_SETCC(setno) FOP_SETCC(setc) FOP_SETCC(setnc) FOP_SETCC(setz) FOP_SETCC(setnz) FOP_SETCC(setbe) FOP_SETCC(setnbe) FOP_SETCC(sets) FOP_SETCC(setns) FOP_SETCC(setp) FOP_SETCC(setnp) FOP_SETCC(setl) FOP_SETCC(setnl) FOP_SETCC(setle) FOP_SETCC(setnle) FOP_END; FOP_START(salc) "pushf; sbb %al, %al; popf \n\t" FOP_RET FOP_END; /* * XXX: inoutclob user must know where the argument is being expanded. * Relying on CC_HAVE_ASM_GOTO would allow us to remove _fault. */ #define asm_safe(insn, inoutclob...) \ ({ \ int _fault = 0; \ \ asm volatile("1:" insn "\n" \ "2:\n" \ ".pushsection .fixup, \"ax\"\n" \ "3: movl $1, %[_fault]\n" \ " jmp 2b\n" \ ".popsection\n" \ _ASM_EXTABLE(1b, 3b) \ : [_fault] "+qm"(_fault) inoutclob ); \ \ _fault ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE; \ }) static int emulator_check_intercept(struct x86_emulate_ctxt *ctxt, enum x86_intercept intercept, enum x86_intercept_stage stage) { struct x86_instruction_info info = { .intercept = intercept, .rep_prefix = ctxt->rep_prefix, .modrm_mod = ctxt->modrm_mod, .modrm_reg = ctxt->modrm_reg, .modrm_rm = ctxt->modrm_rm, .src_val = ctxt->src.val64, .dst_val = ctxt->dst.val64, .src_bytes = ctxt->src.bytes, .dst_bytes = ctxt->dst.bytes, .ad_bytes = ctxt->ad_bytes, .next_rip = ctxt->eip, }; return ctxt->ops->intercept(ctxt, &info, stage); } static void assign_masked(ulong *dest, ulong src, ulong mask) { *dest = (*dest & ~mask) | (src & mask); } static void assign_register(unsigned long *reg, u64 val, int bytes) { /* The 4-byte case *is* correct: in 64-bit mode we zero-extend. */ switch (bytes) { case 1: *(u8 *)reg = (u8)val; break; case 2: *(u16 *)reg = (u16)val; break; case 4: *reg = (u32)val; break; /* 64b: zero-extend */ case 8: *reg = val; break; } } static inline unsigned long ad_mask(struct x86_emulate_ctxt *ctxt) { return (1UL << (ctxt->ad_bytes << 3)) - 1; } static ulong stack_mask(struct x86_emulate_ctxt *ctxt) { u16 sel; struct desc_struct ss; if (ctxt->mode == X86EMUL_MODE_PROT64) return ~0UL; ctxt->ops->get_segment(ctxt, &sel, &ss, NULL, VCPU_SREG_SS); return ~0U >> ((ss.d ^ 1) * 16); /* d=0: 0xffff; d=1: 0xffffffff */ } static int stack_size(struct x86_emulate_ctxt *ctxt) { return (__fls(stack_mask(ctxt)) + 1) >> 3; } /* Access/update address held in a register, based on addressing mode. */ static inline unsigned long address_mask(struct x86_emulate_ctxt *ctxt, unsigned long reg) { if (ctxt->ad_bytes == sizeof(unsigned long)) return reg; else return reg & ad_mask(ctxt); } static inline unsigned long register_address(struct x86_emulate_ctxt *ctxt, int reg) { return address_mask(ctxt, reg_read(ctxt, reg)); } static void masked_increment(ulong *reg, ulong mask, int inc) { assign_masked(reg, *reg + inc, mask); } static inline void register_address_increment(struct x86_emulate_ctxt *ctxt, int reg, int inc) { ulong *preg = reg_rmw(ctxt, reg); assign_register(preg, *preg + inc, ctxt->ad_bytes); } static void rsp_increment(struct x86_emulate_ctxt *ctxt, int inc) { masked_increment(reg_rmw(ctxt, VCPU_REGS_RSP), stack_mask(ctxt), inc); } static u32 desc_limit_scaled(struct desc_struct *desc) { u32 limit = get_desc_limit(desc); return desc->g ? (limit << 12) | 0xfff : limit; } static unsigned long seg_base(struct x86_emulate_ctxt *ctxt, int seg) { if (ctxt->mode == X86EMUL_MODE_PROT64 && seg < VCPU_SREG_FS) return 0; return ctxt->ops->get_cached_segment_base(ctxt, seg); } static int emulate_exception(struct x86_emulate_ctxt *ctxt, int vec, u32 error, bool valid) { WARN_ON(vec > 0x1f); ctxt->exception.vector = vec; ctxt->exception.error_code = error; ctxt->exception.error_code_valid = valid; return X86EMUL_PROPAGATE_FAULT; } static int emulate_db(struct x86_emulate_ctxt *ctxt) { return emulate_exception(ctxt, DB_VECTOR, 0, false); } static int emulate_gp(struct x86_emulate_ctxt *ctxt, int err) { return emulate_exception(ctxt, GP_VECTOR, err, true); } static int emulate_ss(struct x86_emulate_ctxt *ctxt, int err) { return emulate_exception(ctxt, SS_VECTOR, err, true); } static int emulate_ud(struct x86_emulate_ctxt *ctxt) { return emulate_exception(ctxt, UD_VECTOR, 0, false); } static int emulate_ts(struct x86_emulate_ctxt *ctxt, int err) { return emulate_exception(ctxt, TS_VECTOR, err, true); } static int emulate_de(struct x86_emulate_ctxt *ctxt) { return emulate_exception(ctxt, DE_VECTOR, 0, false); } static int emulate_nm(struct x86_emulate_ctxt *ctxt) { return emulate_exception(ctxt, NM_VECTOR, 0, false); } static u16 get_segment_selector(struct x86_emulate_ctxt *ctxt, unsigned seg) { u16 selector; struct desc_struct desc; ctxt->ops->get_segment(ctxt, &selector, &desc, NULL, seg); return selector; } static void set_segment_selector(struct x86_emulate_ctxt *ctxt, u16 selector, unsigned seg) { u16 dummy; u32 base3; struct desc_struct desc; ctxt->ops->get_segment(ctxt, &dummy, &desc, &base3, seg); ctxt->ops->set_segment(ctxt, selector, &desc, base3, seg); } /* * x86 defines three classes of vector instructions: explicitly * aligned, explicitly unaligned, and the rest, which change behaviour * depending on whether they're AVX encoded or not. * * Also included is CMPXCHG16B which is not a vector instruction, yet it is * subject to the same check. FXSAVE and FXRSTOR are checked here too as their * 512 bytes of data must be aligned to a 16 byte boundary. */ static unsigned insn_alignment(struct x86_emulate_ctxt *ctxt, unsigned size) { u64 alignment = ctxt->d & AlignMask; if (likely(size < 16)) return 1; switch (alignment) { case Unaligned: case Avx: return 1; case Aligned16: return 16; case Aligned: default: return size; } } static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, struct segmented_address addr, unsigned *max_size, unsigned size, bool write, bool fetch, enum x86emul_mode mode, ulong *linear) { struct desc_struct desc; bool usable; ulong la; u32 lim; u16 sel; u8 va_bits; la = seg_base(ctxt, addr.seg) + addr.ea; *max_size = 0; switch (mode) { case X86EMUL_MODE_PROT64: *linear = la; va_bits = ctxt_virt_addr_bits(ctxt); if (get_canonical(la, va_bits) != la) goto bad; *max_size = min_t(u64, ~0u, (1ull << va_bits) - la); if (size > *max_size) goto bad; break; default: *linear = la = (u32)la; usable = ctxt->ops->get_segment(ctxt, &sel, &desc, NULL, addr.seg); if (!usable) goto bad; /* code segment in protected mode or read-only data segment */ if ((((ctxt->mode != X86EMUL_MODE_REAL) && (desc.type & 8)) || !(desc.type & 2)) && write) goto bad; /* unreadable code segment */ if (!fetch && (desc.type & 8) && !(desc.type & 2)) goto bad; lim = desc_limit_scaled(&desc); if (!(desc.type & 8) && (desc.type & 4)) { /* expand-down segment */ if (addr.ea <= lim) goto bad; lim = desc.d ? 0xffffffff : 0xffff; } if (addr.ea > lim) goto bad; if (lim == 0xffffffff) *max_size = ~0u; else { *max_size = (u64)lim + 1 - addr.ea; if (size > *max_size) goto bad; } break; } if (la & (insn_alignment(ctxt, size) - 1)) return emulate_gp(ctxt, 0); return X86EMUL_CONTINUE; bad: if (addr.seg == VCPU_SREG_SS) return emulate_ss(ctxt, 0); else return emulate_gp(ctxt, 0); } static int linearize(struct x86_emulate_ctxt *ctxt, struct segmented_address addr, unsigned size, bool write, ulong *linear) { unsigned max_size; return __linearize(ctxt, addr, &max_size, size, write, false, ctxt->mode, linear); } static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst) { ulong linear; int rc; unsigned max_size; struct segmented_address addr = { .seg = VCPU_SREG_CS, .ea = dst }; if (ctxt->op_bytes != sizeof(unsigned long)) addr.ea = dst & ((1UL << (ctxt->op_bytes << 3)) - 1); rc = __linearize(ctxt, addr, &max_size, 1, false, true, ctxt->mode, &linear); if (rc == X86EMUL_CONTINUE) ctxt->_eip = addr.ea; return rc; } static inline int emulator_recalc_and_set_mode(struct x86_emulate_ctxt *ctxt) { u64 efer; struct desc_struct cs; u16 selector; u32 base3; ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); if (!(ctxt->ops->get_cr(ctxt, 0) & X86_CR0_PE)) { /* Real mode. cpu must not have long mode active */ if (efer & EFER_LMA) return X86EMUL_UNHANDLEABLE; ctxt->mode = X86EMUL_MODE_REAL; return X86EMUL_CONTINUE; } if (ctxt->eflags & X86_EFLAGS_VM) { /* Protected/VM86 mode. cpu must not have long mode active */ if (efer & EFER_LMA) return X86EMUL_UNHANDLEABLE; ctxt->mode = X86EMUL_MODE_VM86; return X86EMUL_CONTINUE; } if (!ctxt->ops->get_segment(ctxt, &selector, &cs, &base3, VCPU_SREG_CS)) return X86EMUL_UNHANDLEABLE; if (efer & EFER_LMA) { if (cs.l) { /* Proper long mode */ ctxt->mode = X86EMUL_MODE_PROT64; } else if (cs.d) { /* 32 bit compatibility mode*/ ctxt->mode = X86EMUL_MODE_PROT32; } else { ctxt->mode = X86EMUL_MODE_PROT16; } } else { /* Legacy 32 bit / 16 bit mode */ ctxt->mode = cs.d ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; } return X86EMUL_CONTINUE; } static inline int assign_eip_near(struct x86_emulate_ctxt *ctxt, ulong dst) { return assign_eip(ctxt, dst); } static int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst) { int rc = emulator_recalc_and_set_mode(ctxt); if (rc != X86EMUL_CONTINUE) return rc; return assign_eip(ctxt, dst); } static inline int jmp_rel(struct x86_emulate_ctxt *ctxt, int rel) { return assign_eip_near(ctxt, ctxt->_eip + rel); } static int linear_read_system(struct x86_emulate_ctxt *ctxt, ulong linear, void *data, unsigned size) { return ctxt->ops->read_std(ctxt, linear, data, size, &ctxt->exception, true); } static int linear_write_system(struct x86_emulate_ctxt *ctxt, ulong linear, void *data, unsigned int size) { return ctxt->ops->write_std(ctxt, linear, data, size, &ctxt->exception, true); } static int segmented_read_std(struct x86_emulate_ctxt *ctxt, struct segmented_address addr, void *data, unsigned size) { int rc; ulong linear; rc = linearize(ctxt, addr, size, false, &linear); if (rc != X86EMUL_CONTINUE) return rc; return ctxt->ops->read_std(ctxt, linear, data, size, &ctxt->exception, false); } static int segmented_write_std(struct x86_emulate_ctxt *ctxt, struct segmented_address addr, void *data, unsigned int size) { int rc; ulong linear; rc = linearize(ctxt, addr, size, true, &linear); if (rc != X86EMUL_CONTINUE) return rc; return ctxt->ops->write_std(ctxt, linear, data, size, &ctxt->exception, false); } /* * Prefetch the remaining bytes of the instruction without crossing page * boundary if they are not in fetch_cache yet. */ static int __do_insn_fetch_bytes(struct x86_emulate_ctxt *ctxt, int op_size) { int rc; unsigned size, max_size; unsigned long linear; int cur_size = ctxt->fetch.end - ctxt->fetch.data; struct segmented_address addr = { .seg = VCPU_SREG_CS, .ea = ctxt->eip + cur_size }; /* * We do not know exactly how many bytes will be needed, and * __linearize is expensive, so fetch as much as possible. We * just have to avoid going beyond the 15 byte limit, the end * of the segment, or the end of the page. * * __linearize is called with size 0 so that it does not do any * boundary check itself. Instead, we use max_size to check * against op_size. */ rc = __linearize(ctxt, addr, &max_size, 0, false, true, ctxt->mode, &linear); if (unlikely(rc != X86EMUL_CONTINUE)) return rc; size = min_t(unsigned, 15UL ^ cur_size, max_size); size = min_t(unsigned, size, PAGE_SIZE - offset_in_page(linear)); /* * One instruction can only straddle two pages, * and one has been loaded at the beginning of * x86_decode_insn. So, if not enough bytes * still, we must have hit the 15-byte boundary. */ if (unlikely(size < op_size)) return emulate_gp(ctxt, 0); rc = ctxt->ops->fetch(ctxt, linear, ctxt->fetch.end, size, &ctxt->exception); if (unlikely(rc != X86EMUL_CONTINUE)) return rc; ctxt->fetch.end += size; return X86EMUL_CONTINUE; } static __always_inline int do_insn_fetch_bytes(struct x86_emulate_ctxt *ctxt, unsigned size) { unsigned done_size = ctxt->fetch.end - ctxt->fetch.ptr; if (unlikely(done_size < size)) return __do_insn_fetch_bytes(ctxt, size - done_size); else return X86EMUL_CONTINUE; } /* Fetch next part of the instruction being emulated. */ #define insn_fetch(_type, _ctxt) \ ({ _type _x; \ \ rc = do_insn_fetch_bytes(_ctxt, sizeof(_type)); \ if (rc != X86EMUL_CONTINUE) \ goto done; \ ctxt->_eip += sizeof(_type); \ memcpy(&_x, ctxt->fetch.ptr, sizeof(_type)); \ ctxt->fetch.ptr += sizeof(_type); \ _x; \ }) #define insn_fetch_arr(_arr, _size, _ctxt) \ ({ \ rc = do_insn_fetch_bytes(_ctxt, _size); \ if (rc != X86EMUL_CONTINUE) \ goto done; \ ctxt->_eip += (_size); \ memcpy(_arr, ctxt->fetch.ptr, _size); \ ctxt->fetch.ptr += (_size); \ }) /* * Given the 'reg' portion of a ModRM byte, and a register block, return a * pointer into the block that addresses the relevant register. * @highbyte_regs specifies whether to decode AH,CH,DH,BH. */ static void *decode_register(struct x86_emulate_ctxt *ctxt, u8 modrm_reg, int byteop) { void *p; int highbyte_regs = (ctxt->rex_prefix == 0) && byteop; if (highbyte_regs && modrm_reg >= 4 && modrm_reg < 8) p = (unsigned char *)reg_rmw(ctxt, modrm_reg & 3) + 1; else p = reg_rmw(ctxt, modrm_reg); return p; } static int read_descriptor(struct x86_emulate_ctxt *ctxt, struct segmented_address addr, u16 *size, unsigned long *address, int op_bytes) { int rc; if (op_bytes == 2) op_bytes = 3; *address = 0; rc = segmented_read_std(ctxt, addr, size, 2); if (rc != X86EMUL_CONTINUE) return rc; addr.ea += 2; rc = segmented_read_std(ctxt, addr, address, op_bytes); return rc; } FASTOP2(add); FASTOP2(or); FASTOP2(adc); FASTOP2(sbb); FASTOP2(and); FASTOP2(sub); FASTOP2(xor); FASTOP2(cmp); FASTOP2(test); FASTOP1SRC2(mul, mul_ex); FASTOP1SRC2(imul, imul_ex); FASTOP1SRC2EX(div, div_ex); FASTOP1SRC2EX(idiv, idiv_ex); FASTOP3WCL(shld); FASTOP3WCL(shrd); FASTOP2W(imul); FASTOP1(not); FASTOP1(neg); FASTOP1(inc); FASTOP1(dec); FASTOP2CL(rol); FASTOP2CL(ror); FASTOP2CL(rcl); FASTOP2CL(rcr); FASTOP2CL(shl); FASTOP2CL(shr); FASTOP2CL(sar); FASTOP2W(bsf); FASTOP2W(bsr); FASTOP2W(bt); FASTOP2W(bts); FASTOP2W(btr); FASTOP2W(btc); FASTOP2(xadd); FASTOP2R(cmp, cmp_r); static int em_bsf_c(struct x86_emulate_ctxt *ctxt) { /* If src is zero, do not writeback, but update flags */ if (ctxt->src.val == 0) ctxt->dst.type = OP_NONE; return fastop(ctxt, em_bsf); } static int em_bsr_c(struct x86_emulate_ctxt *ctxt) { /* If src is zero, do not writeback, but update flags */ if (ctxt->src.val == 0) ctxt->dst.type = OP_NONE; return fastop(ctxt, em_bsr); } static __always_inline u8 test_cc(unsigned int condition, unsigned long flags) { u8 rc; void (*fop)(void) = (void *)em_setcc + 4 * (condition & 0xf); flags = (flags & EFLAGS_MASK) | X86_EFLAGS_IF; asm("push %[flags]; popf; " CALL_NOSPEC : "=a"(rc) : [thunk_target]"r"(fop), [flags]"r"(flags)); return rc; } static void fetch_register_operand(struct operand *op) { switch (op->bytes) { case 1: op->val = *(u8 *)op->addr.reg; break; case 2: op->val = *(u16 *)op->addr.reg; break; case 4: op->val = *(u32 *)op->addr.reg; break; case 8: op->val = *(u64 *)op->addr.reg; break; } } static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg) { ctxt->ops->get_fpu(ctxt); switch (reg) { case 0: asm("movdqa %%xmm0, %0" : "=m"(*data)); break; case 1: asm("movdqa %%xmm1, %0" : "=m"(*data)); break; case 2: asm("movdqa %%xmm2, %0" : "=m"(*data)); break; case 3: asm("movdqa %%xmm3, %0" : "=m"(*data)); break; case 4: asm("movdqa %%xmm4, %0" : "=m"(*data)); break; case 5: asm("movdqa %%xmm5, %0" : "=m"(*data)); break; case 6: asm("movdqa %%xmm6, %0" : "=m"(*data)); break; case 7: asm("movdqa %%xmm7, %0" : "=m"(*data)); break; #ifdef CONFIG_X86_64 case 8: asm("movdqa %%xmm8, %0" : "=m"(*data)); break; case 9: asm("movdqa %%xmm9, %0" : "=m"(*data)); break; case 10: asm("movdqa %%xmm10, %0" : "=m"(*data)); break; case 11: asm("movdqa %%xmm11, %0" : "=m"(*data)); break; case 12: asm("movdqa %%xmm12, %0" : "=m"(*data)); break; case 13: asm("movdqa %%xmm13, %0" : "=m"(*data)); break; case 14: asm("movdqa %%xmm14, %0" : "=m"(*data)); break; case 15: asm("movdqa %%xmm15, %0" : "=m"(*data)); break; #endif default: BUG(); } ctxt->ops->put_fpu(ctxt); } static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg) { ctxt->ops->get_fpu(ctxt); switch (reg) { case 0: asm("movdqa %0, %%xmm0" : : "m"(*data)); break; case 1: asm("movdqa %0, %%xmm1" : : "m"(*data)); break; case 2: asm("movdqa %0, %%xmm2" : : "m"(*data)); break; case 3: asm("movdqa %0, %%xmm3" : : "m"(*data)); break; case 4: asm("movdqa %0, %%xmm4" : : "m"(*data)); break; case 5: asm("movdqa %0, %%xmm5" : : "m"(*data)); break; case 6: asm("movdqa %0, %%xmm6" : : "m"(*data)); break; case 7: asm("movdqa %0, %%xmm7" : : "m"(*data)); break; #ifdef CONFIG_X86_64 case 8: asm("movdqa %0, %%xmm8" : : "m"(*data)); break; case 9: asm("movdqa %0, %%xmm9" : : "m"(*data)); break; case 10: asm("movdqa %0, %%xmm10" : : "m"(*data)); break; case 11: asm("movdqa %0, %%xmm11" : : "m"(*data)); break; case 12: asm("movdqa %0, %%xmm12" : : "m"(*data)); break; case 13: asm("movdqa %0, %%xmm13" : : "m"(*data)); break; case 14: asm("movdqa %0, %%xmm14" : : "m"(*data)); break; case 15: asm("movdqa %0, %%xmm15" : : "m"(*data)); break; #endif default: BUG(); } ctxt->ops->put_fpu(ctxt); } static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg) { ctxt->ops->get_fpu(ctxt); switch (reg) { case 0: asm("movq %%mm0, %0" : "=m"(*data)); break; case 1: asm("movq %%mm1, %0" : "=m"(*data)); break; case 2: asm("movq %%mm2, %0" : "=m"(*data)); break; case 3: asm("movq %%mm3, %0" : "=m"(*data)); break; case 4: asm("movq %%mm4, %0" : "=m"(*data)); break; case 5: asm("movq %%mm5, %0" : "=m"(*data)); break; case 6: asm("movq %%mm6, %0" : "=m"(*data)); break; case 7: asm("movq %%mm7, %0" : "=m"(*data)); break; default: BUG(); } ctxt->ops->put_fpu(ctxt); } static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg) { ctxt->ops->get_fpu(ctxt); switch (reg) { case 0: asm("movq %0, %%mm0" : : "m"(*data)); break; case 1: asm("movq %0, %%mm1" : : "m"(*data)); break; case 2: asm("movq %0, %%mm2" : : "m"(*data)); break; case 3: asm("movq %0, %%mm3" : : "m"(*data)); break; case 4: asm("movq %0, %%mm4" : : "m"(*data)); break; case 5: asm("movq %0, %%mm5" : : "m"(*data)); break; case 6: asm("movq %0, %%mm6" : : "m"(*data)); break; case 7: asm("movq %0, %%mm7" : : "m"(*data)); break; default: BUG(); } ctxt->ops->put_fpu(ctxt); } static int em_fninit(struct x86_emulate_ctxt *ctxt) { if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) return emulate_nm(ctxt); ctxt->ops->get_fpu(ctxt); asm volatile("fninit"); ctxt->ops->put_fpu(ctxt); return X86EMUL_CONTINUE; } static int em_fnstcw(struct x86_emulate_ctxt *ctxt) { u16 fcw; if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) return emulate_nm(ctxt); ctxt->ops->get_fpu(ctxt); asm volatile("fnstcw %0": "+m"(fcw)); ctxt->ops->put_fpu(ctxt); ctxt->dst.val = fcw; return X86EMUL_CONTINUE; } static int em_fnstsw(struct x86_emulate_ctxt *ctxt) { u16 fsw; if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) return emulate_nm(ctxt); ctxt->ops->get_fpu(ctxt); asm volatile("fnstsw %0": "+m"(fsw)); ctxt->ops->put_fpu(ctxt); ctxt->dst.val = fsw; return X86EMUL_CONTINUE; } static void decode_register_operand(struct x86_emulate_ctxt *ctxt, struct operand *op) { unsigned reg = ctxt->modrm_reg; if (!(ctxt->d & ModRM)) reg = (ctxt->b & 7) | ((ctxt->rex_prefix & 1) << 3); if (ctxt->d & Sse) { op->type = OP_XMM; op->bytes = 16; op->addr.xmm = reg; read_sse_reg(ctxt, &op->vec_val, reg); return; } if (ctxt->d & Mmx) { reg &= 7; op->type = OP_MM; op->bytes = 8; op->addr.mm = reg; return; } op->type = OP_REG; op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; op->addr.reg = decode_register(ctxt, reg, ctxt->d & ByteOp); fetch_register_operand(op); op->orig_val = op->val; } static void adjust_modrm_seg(struct x86_emulate_ctxt *ctxt, int base_reg) { if (base_reg == VCPU_REGS_RSP || base_reg == VCPU_REGS_RBP) ctxt->modrm_seg = VCPU_SREG_SS; } static int decode_modrm(struct x86_emulate_ctxt *ctxt, struct operand *op) { u8 sib; int index_reg, base_reg, scale; int rc = X86EMUL_CONTINUE; ulong modrm_ea = 0; ctxt->modrm_reg = ((ctxt->rex_prefix << 1) & 8); /* REX.R */ index_reg = (ctxt->rex_prefix << 2) & 8; /* REX.X */ base_reg = (ctxt->rex_prefix << 3) & 8; /* REX.B */ ctxt->modrm_mod = (ctxt->modrm & 0xc0) >> 6; ctxt->modrm_reg |= (ctxt->modrm & 0x38) >> 3; ctxt->modrm_rm = base_reg | (ctxt->modrm & 0x07); ctxt->modrm_seg = VCPU_SREG_DS; if (ctxt->modrm_mod == 3 || (ctxt->d & NoMod)) { op->type = OP_REG; op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; op->addr.reg = decode_register(ctxt, ctxt->modrm_rm, ctxt->d & ByteOp); if (ctxt->d & Sse) { op->type = OP_XMM; op->bytes = 16; op->addr.xmm = ctxt->modrm_rm; read_sse_reg(ctxt, &op->vec_val, ctxt->modrm_rm); return rc; } if (ctxt->d & Mmx) { op->type = OP_MM; op->bytes = 8; op->addr.mm = ctxt->modrm_rm & 7; return rc; } fetch_register_operand(op); return rc; } op->type = OP_MEM; if (ctxt->ad_bytes == 2) { unsigned bx = reg_read(ctxt, VCPU_REGS_RBX); unsigned bp = reg_read(ctxt, VCPU_REGS_RBP); unsigned si = reg_read(ctxt, VCPU_REGS_RSI); unsigned di = reg_read(ctxt, VCPU_REGS_RDI); /* 16-bit ModR/M decode. */ switch (ctxt->modrm_mod) { case 0: if (ctxt->modrm_rm == 6) modrm_ea += insn_fetch(u16, ctxt); break; case 1: modrm_ea += insn_fetch(s8, ctxt); break; case 2: modrm_ea += insn_fetch(u16, ctxt); break; } switch (ctxt->modrm_rm) { case 0: modrm_ea += bx + si; break; case 1: modrm_ea += bx + di; break; case 2: modrm_ea += bp + si; break; case 3: modrm_ea += bp + di; break; case 4: modrm_ea += si; break; case 5: modrm_ea += di; break; case 6: if (ctxt->modrm_mod != 0) modrm_ea += bp; break; case 7: modrm_ea += bx; break; } if (ctxt->modrm_rm == 2 || ctxt->modrm_rm == 3 || (ctxt->modrm_rm == 6 && ctxt->modrm_mod != 0)) ctxt->modrm_seg = VCPU_SREG_SS; modrm_ea = (u16)modrm_ea; } else { /* 32/64-bit ModR/M decode. */ if ((ctxt->modrm_rm & 7) == 4) { sib = insn_fetch(u8, ctxt); index_reg |= (sib >> 3) & 7; base_reg |= sib & 7; scale = sib >> 6; if ((base_reg & 7) == 5 && ctxt->modrm_mod == 0) modrm_ea += insn_fetch(s32, ctxt); else { modrm_ea += reg_read(ctxt, base_reg); adjust_modrm_seg(ctxt, base_reg); /* Increment ESP on POP [ESP] */ if ((ctxt->d & IncSP) && base_reg == VCPU_REGS_RSP) modrm_ea += ctxt->op_bytes; } if (index_reg != 4) modrm_ea += reg_read(ctxt, index_reg) << scale; } else if ((ctxt->modrm_rm & 7) == 5 && ctxt->modrm_mod == 0) { modrm_ea += insn_fetch(s32, ctxt); if (ctxt->mode == X86EMUL_MODE_PROT64) ctxt->rip_relative = 1; } else { base_reg = ctxt->modrm_rm; modrm_ea += reg_read(ctxt, base_reg); adjust_modrm_seg(ctxt, base_reg); } switch (ctxt->modrm_mod) { case 1: modrm_ea += insn_fetch(s8, ctxt); break; case 2: modrm_ea += insn_fetch(s32, ctxt); break; } } op->addr.mem.ea = modrm_ea; if (ctxt->ad_bytes != 8) ctxt->memop.addr.mem.ea = (u32)ctxt->memop.addr.mem.ea; done: return rc; } static int decode_abs(struct x86_emulate_ctxt *ctxt, struct operand *op) { int rc = X86EMUL_CONTINUE; op->type = OP_MEM; switch (ctxt->ad_bytes) { case 2: op->addr.mem.ea = insn_fetch(u16, ctxt); break; case 4: op->addr.mem.ea = insn_fetch(u32, ctxt); break; case 8: op->addr.mem.ea = insn_fetch(u64, ctxt); break; } done: return rc; } static void fetch_bit_operand(struct x86_emulate_ctxt *ctxt) { long sv = 0, mask; if (ctxt->dst.type == OP_MEM && ctxt->src.type == OP_REG) { mask = ~((long)ctxt->dst.bytes * 8 - 1); if (ctxt->src.bytes == 2) sv = (s16)ctxt->src.val & (s16)mask; else if (ctxt->src.bytes == 4) sv = (s32)ctxt->src.val & (s32)mask; else sv = (s64)ctxt->src.val & (s64)mask; ctxt->dst.addr.mem.ea = address_mask(ctxt, ctxt->dst.addr.mem.ea + (sv >> 3)); } /* only subword offset */ ctxt->src.val &= (ctxt->dst.bytes << 3) - 1; } static int read_emulated(struct x86_emulate_ctxt *ctxt, unsigned long addr, void *dest, unsigned size) { int rc; struct read_cache *mc = &ctxt->mem_read; if (mc->pos < mc->end) goto read_cached; WARN_ON((mc->end + size) >= sizeof(mc->data)); rc = ctxt->ops->read_emulated(ctxt, addr, mc->data + mc->end, size, &ctxt->exception); if (rc != X86EMUL_CONTINUE) return rc; mc->end += size; read_cached: memcpy(dest, mc->data + mc->pos, size); mc->pos += size; return X86EMUL_CONTINUE; } static int segmented_read(struct x86_emulate_ctxt *ctxt, struct segmented_address addr, void *data, unsigned size) { int rc; ulong linear; rc = linearize(ctxt, addr, size, false, &linear); if (rc != X86EMUL_CONTINUE) return rc; return read_emulated(ctxt, linear, data, size); } static int segmented_write(struct x86_emulate_ctxt *ctxt, struct segmented_address addr, const void *data, unsigned size) { int rc; ulong linear; rc = linearize(ctxt, addr, size, true, &linear); if (rc != X86EMUL_CONTINUE) return rc; return ctxt->ops->write_emulated(ctxt, linear, data, size, &ctxt->exception); } static int segmented_cmpxchg(struct x86_emulate_ctxt *ctxt, struct segmented_address addr, const void *orig_data, const void *data, unsigned size) { int rc; ulong linear; rc = linearize(ctxt, addr, size, true, &linear); if (rc != X86EMUL_CONTINUE) return rc; return ctxt->ops->cmpxchg_emulated(ctxt, linear, orig_data, data, size, &ctxt->exception); } static int pio_in_emulated(struct x86_emulate_ctxt *ctxt, unsigned int size, unsigned short port, void *dest) { struct read_cache *rc = &ctxt->io_read; if (rc->pos == rc->end) { /* refill pio read ahead */ unsigned int in_page, n; unsigned int count = ctxt->rep_prefix ? address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) : 1; in_page = (ctxt->eflags & X86_EFLAGS_DF) ? offset_in_page(reg_read(ctxt, VCPU_REGS_RDI)) : PAGE_SIZE - offset_in_page(reg_read(ctxt, VCPU_REGS_RDI)); n = min3(in_page, (unsigned int)sizeof(rc->data) / size, count); if (n == 0) n = 1; rc->pos = rc->end = 0; if (!ctxt->ops->pio_in_emulated(ctxt, size, port, rc->data, n)) return 0; rc->end = n * size; } if (ctxt->rep_prefix && (ctxt->d & String) && !(ctxt->eflags & X86_EFLAGS_DF)) { ctxt->dst.data = rc->data + rc->pos; ctxt->dst.type = OP_MEM_STR; ctxt->dst.count = (rc->end - rc->pos) / size; rc->pos = rc->end; } else { memcpy(dest, rc->data + rc->pos, size); rc->pos += size; } return 1; } static int read_interrupt_descriptor(struct x86_emulate_ctxt *ctxt, u16 index, struct desc_struct *desc) { struct desc_ptr dt; ulong addr; ctxt->ops->get_idt(ctxt, &dt); if (dt.size < index * 8 + 7) return emulate_gp(ctxt, index << 3 | 0x2); addr = dt.address + index * 8; return linear_read_system(ctxt, addr, desc, sizeof *desc); } static void get_descriptor_table_ptr(struct x86_emulate_ctxt *ctxt, u16 selector, struct desc_ptr *dt) { const struct x86_emulate_ops *ops = ctxt->ops; u32 base3 = 0; if (selector & 1 << 2) { struct desc_struct desc; u16 sel; memset (dt, 0, sizeof *dt); if (!ops->get_segment(ctxt, &sel, &desc, &base3, VCPU_SREG_LDTR)) return; dt->size = desc_limit_scaled(&desc); /* what if limit > 65535? */ dt->address = get_desc_base(&desc) | ((u64)base3 << 32); } else ops->get_gdt(ctxt, dt); } static int get_descriptor_ptr(struct x86_emulate_ctxt *ctxt, u16 selector, ulong *desc_addr_p) { struct desc_ptr dt; u16 index = selector >> 3; ulong addr; get_descriptor_table_ptr(ctxt, selector, &dt); if (dt.size < index * 8 + 7) return emulate_gp(ctxt, selector & 0xfffc); addr = dt.address + index * 8; #ifdef CONFIG_X86_64 if (addr >> 32 != 0) { u64 efer = 0; ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); if (!(efer & EFER_LMA)) addr &= (u32)-1; } #endif *desc_addr_p = addr; return X86EMUL_CONTINUE; } /* allowed just for 8 bytes segments */ static int read_segment_descriptor(struct x86_emulate_ctxt *ctxt, u16 selector, struct desc_struct *desc, ulong *desc_addr_p) { int rc; rc = get_descriptor_ptr(ctxt, selector, desc_addr_p); if (rc != X86EMUL_CONTINUE) return rc; return linear_read_system(ctxt, *desc_addr_p, desc, sizeof(*desc)); } /* allowed just for 8 bytes segments */ static int write_segment_descriptor(struct x86_emulate_ctxt *ctxt, u16 selector, struct desc_struct *desc) { int rc; ulong addr; rc = get_descriptor_ptr(ctxt, selector, &addr); if (rc != X86EMUL_CONTINUE) return rc; return linear_write_system(ctxt, addr, desc, sizeof *desc); } static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt, u16 selector, int seg, u8 cpl, enum x86_transfer_type transfer, struct desc_struct *desc) { struct desc_struct seg_desc, old_desc; u8 dpl, rpl; unsigned err_vec = GP_VECTOR; u32 err_code = 0; bool null_selector = !(selector & ~0x3); /* 0000-0003 are null */ ulong desc_addr; int ret; u16 dummy; u32 base3 = 0; memset(&seg_desc, 0, sizeof seg_desc); if (ctxt->mode == X86EMUL_MODE_REAL) { /* set real mode segment descriptor (keep limit etc. for * unreal mode) */ ctxt->ops->get_segment(ctxt, &dummy, &seg_desc, NULL, seg); set_desc_base(&seg_desc, selector << 4); goto load; } else if (seg <= VCPU_SREG_GS && ctxt->mode == X86EMUL_MODE_VM86) { /* VM86 needs a clean new segment descriptor */ set_desc_base(&seg_desc, selector << 4); set_desc_limit(&seg_desc, 0xffff); seg_desc.type = 3; seg_desc.p = 1; seg_desc.s = 1; seg_desc.dpl = 3; goto load; } rpl = selector & 3; /* TR should be in GDT only */ if (seg == VCPU_SREG_TR && (selector & (1 << 2))) goto exception; /* NULL selector is not valid for TR, CS and (except for long mode) SS */ if (null_selector) { if (seg == VCPU_SREG_CS || seg == VCPU_SREG_TR) goto exception; if (seg == VCPU_SREG_SS) { if (ctxt->mode != X86EMUL_MODE_PROT64 || rpl != cpl) goto exception; /* * ctxt->ops->set_segment expects the CPL to be in * SS.DPL, so fake an expand-up 32-bit data segment. */ seg_desc.type = 3; seg_desc.p = 1; seg_desc.s = 1; seg_desc.dpl = cpl; seg_desc.d = 1; seg_desc.g = 1; } /* Skip all following checks */ goto load; } ret = read_segment_descriptor(ctxt, selector, &seg_desc, &desc_addr); if (ret != X86EMUL_CONTINUE) return ret; err_code = selector & 0xfffc; err_vec = (transfer == X86_TRANSFER_TASK_SWITCH) ? TS_VECTOR : GP_VECTOR; /* can't load system descriptor into segment selector */ if (seg <= VCPU_SREG_GS && !seg_desc.s) { if (transfer == X86_TRANSFER_CALL_JMP) return X86EMUL_UNHANDLEABLE; goto exception; } dpl = seg_desc.dpl; switch (seg) { case VCPU_SREG_SS: /* * segment is not a writable data segment or segment * selector's RPL != CPL or segment selector's RPL != CPL */ if (rpl != cpl || (seg_desc.type & 0xa) != 0x2 || dpl != cpl) goto exception; break; case VCPU_SREG_CS: if (!(seg_desc.type & 8)) goto exception; if (seg_desc.type & 4) { /* conforming */ if (dpl > cpl) goto exception; } else { /* nonconforming */ if (rpl > cpl || dpl != cpl) goto exception; } /* in long-mode d/b must be clear if l is set */ if (seg_desc.d && seg_desc.l) { u64 efer = 0; ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); if (efer & EFER_LMA) goto exception; } /* CS(RPL) <- CPL */ selector = (selector & 0xfffc) | cpl; break; case VCPU_SREG_TR: if (seg_desc.s || (seg_desc.type != 1 && seg_desc.type != 9)) goto exception; break; case VCPU_SREG_LDTR: if (seg_desc.s || seg_desc.type != 2) goto exception; break; default: /* DS, ES, FS, or GS */ /* * segment is not a data or readable code segment or * ((segment is a data or nonconforming code segment) * and (both RPL and CPL > DPL)) */ if ((seg_desc.type & 0xa) == 0x8 || (((seg_desc.type & 0xc) != 0xc) && (rpl > dpl && cpl > dpl))) goto exception; break; } if (!seg_desc.p) { err_vec = (seg == VCPU_SREG_SS) ? SS_VECTOR : NP_VECTOR; goto exception; } if (seg_desc.s) { /* mark segment as accessed */ if (!(seg_desc.type & 1)) { seg_desc.type |= 1; ret = write_segment_descriptor(ctxt, selector, &seg_desc); if (ret != X86EMUL_CONTINUE) return ret; } } else if (ctxt->mode == X86EMUL_MODE_PROT64) { ret = linear_read_system(ctxt, desc_addr+8, &base3, sizeof(base3)); if (ret != X86EMUL_CONTINUE) return ret; if (emul_is_noncanonical_address(get_desc_base(&seg_desc) | ((u64)base3 << 32), ctxt)) return emulate_gp(ctxt, err_code); } if (seg == VCPU_SREG_TR) { old_desc = seg_desc; seg_desc.type |= 2; /* busy */ ret = ctxt->ops->cmpxchg_emulated(ctxt, desc_addr, &old_desc, &seg_desc, sizeof(seg_desc), &ctxt->exception); if (ret != X86EMUL_CONTINUE) return ret; } load: ctxt->ops->set_segment(ctxt, selector, &seg_desc, base3, seg); if (desc) *desc = seg_desc; return X86EMUL_CONTINUE; exception: return emulate_exception(ctxt, err_vec, err_code, true); } static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, u16 selector, int seg) { u8 cpl = ctxt->ops->cpl(ctxt); /* * None of MOV, POP and LSS can load a NULL selector in CPL=3, but * they can load it at CPL<3 (Intel's manual says only LSS can, * but it's wrong). * * However, the Intel manual says that putting IST=1/DPL=3 in * an interrupt gate will result in SS=3 (the AMD manual instead * says it doesn't), so allow SS=3 in __load_segment_descriptor * and only forbid it here. */ if (seg == VCPU_SREG_SS && selector == 3 && ctxt->mode == X86EMUL_MODE_PROT64) return emulate_exception(ctxt, GP_VECTOR, 0, true); return __load_segment_descriptor(ctxt, selector, seg, cpl, X86_TRANSFER_NONE, NULL); } static void write_register_operand(struct operand *op) { return assign_register(op->addr.reg, op->val, op->bytes); } static int writeback(struct x86_emulate_ctxt *ctxt, struct operand *op) { switch (op->type) { case OP_REG: write_register_operand(op); break; case OP_MEM: if (ctxt->lock_prefix) return segmented_cmpxchg(ctxt, op->addr.mem, &op->orig_val, &op->val, op->bytes); else return segmented_write(ctxt, op->addr.mem, &op->val, op->bytes); break; case OP_MEM_STR: return segmented_write(ctxt, op->addr.mem, op->data, op->bytes * op->count); break; case OP_XMM: write_sse_reg(ctxt, &op->vec_val, op->addr.xmm); break; case OP_MM: write_mmx_reg(ctxt, &op->mm_val, op->addr.mm); break; case OP_NONE: /* no writeback */ break; default: break; } return X86EMUL_CONTINUE; } static int push(struct x86_emulate_ctxt *ctxt, void *data, int bytes) { struct segmented_address addr; rsp_increment(ctxt, -bytes); addr.ea = reg_read(ctxt, VCPU_REGS_RSP) & stack_mask(ctxt); addr.seg = VCPU_SREG_SS; return segmented_write(ctxt, addr, data, bytes); } static int em_push(struct x86_emulate_ctxt *ctxt) { /* Disable writeback. */ ctxt->dst.type = OP_NONE; return push(ctxt, &ctxt->src.val, ctxt->op_bytes); } static int emulate_pop(struct x86_emulate_ctxt *ctxt, void *dest, int len) { int rc; struct segmented_address addr; addr.ea = reg_read(ctxt, VCPU_REGS_RSP) & stack_mask(ctxt); addr.seg = VCPU_SREG_SS; rc = segmented_read(ctxt, addr, dest, len); if (rc != X86EMUL_CONTINUE) return rc; rsp_increment(ctxt, len); return rc; } static int em_pop(struct x86_emulate_ctxt *ctxt) { return emulate_pop(ctxt, &ctxt->dst.val, ctxt->op_bytes); } static int emulate_popf(struct x86_emulate_ctxt *ctxt, void *dest, int len) { int rc; unsigned long val, change_mask; int iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> X86_EFLAGS_IOPL_BIT; int cpl = ctxt->ops->cpl(ctxt); rc = emulate_pop(ctxt, &val, len); if (rc != X86EMUL_CONTINUE) return rc; change_mask = X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF | X86_EFLAGS_ZF | X86_EFLAGS_SF | X86_EFLAGS_OF | X86_EFLAGS_TF | X86_EFLAGS_DF | X86_EFLAGS_NT | X86_EFLAGS_AC | X86_EFLAGS_ID; switch(ctxt->mode) { case X86EMUL_MODE_PROT64: case X86EMUL_MODE_PROT32: case X86EMUL_MODE_PROT16: if (cpl == 0) change_mask |= X86_EFLAGS_IOPL; if (cpl <= iopl) change_mask |= X86_EFLAGS_IF; break; case X86EMUL_MODE_VM86: if (iopl < 3) return emulate_gp(ctxt, 0); change_mask |= X86_EFLAGS_IF; break; default: /* real mode */ change_mask |= (X86_EFLAGS_IOPL | X86_EFLAGS_IF); break; } *(unsigned long *)dest = (ctxt->eflags & ~change_mask) | (val & change_mask); return rc; } static int em_popf(struct x86_emulate_ctxt *ctxt) { ctxt->dst.type = OP_REG; ctxt->dst.addr.reg = &ctxt->eflags; ctxt->dst.bytes = ctxt->op_bytes; return emulate_popf(ctxt, &ctxt->dst.val, ctxt->op_bytes); } static int em_enter(struct x86_emulate_ctxt *ctxt) { int rc; unsigned frame_size = ctxt->src.val; unsigned nesting_level = ctxt->src2.val & 31; ulong rbp; if (nesting_level) return X86EMUL_UNHANDLEABLE; rbp = reg_read(ctxt, VCPU_REGS_RBP); rc = push(ctxt, &rbp, stack_size(ctxt)); if (rc != X86EMUL_CONTINUE) return rc; assign_masked(reg_rmw(ctxt, VCPU_REGS_RBP), reg_read(ctxt, VCPU_REGS_RSP), stack_mask(ctxt)); assign_masked(reg_rmw(ctxt, VCPU_REGS_RSP), reg_read(ctxt, VCPU_REGS_RSP) - frame_size, stack_mask(ctxt)); return X86EMUL_CONTINUE; } static int em_leave(struct x86_emulate_ctxt *ctxt) { assign_masked(reg_rmw(ctxt, VCPU_REGS_RSP), reg_read(ctxt, VCPU_REGS_RBP), stack_mask(ctxt)); return emulate_pop(ctxt, reg_rmw(ctxt, VCPU_REGS_RBP), ctxt->op_bytes); } static int em_push_sreg(struct x86_emulate_ctxt *ctxt) { int seg = ctxt->src2.val; ctxt->src.val = get_segment_selector(ctxt, seg); if (ctxt->op_bytes == 4) { rsp_increment(ctxt, -2); ctxt->op_bytes = 2; } return em_push(ctxt); } static int em_pop_sreg(struct x86_emulate_ctxt *ctxt) { int seg = ctxt->src2.val; unsigned long selector; int rc; rc = emulate_pop(ctxt, &selector, 2); if (rc != X86EMUL_CONTINUE) return rc; if (seg == VCPU_SREG_SS) ctxt->interruptibility = KVM_X86_SHADOW_INT_MOV_SS; if (ctxt->op_bytes > 2) rsp_increment(ctxt, ctxt->op_bytes - 2); rc = load_segment_descriptor(ctxt, (u16)selector, seg); return rc; } static int em_pusha(struct x86_emulate_ctxt *ctxt) { unsigned long old_esp = reg_read(ctxt, VCPU_REGS_RSP); int rc = X86EMUL_CONTINUE; int reg = VCPU_REGS_RAX; while (reg <= VCPU_REGS_RDI) { (reg == VCPU_REGS_RSP) ? (ctxt->src.val = old_esp) : (ctxt->src.val = reg_read(ctxt, reg)); rc = em_push(ctxt); if (rc != X86EMUL_CONTINUE) return rc; ++reg; } return rc; } static int em_pushf(struct x86_emulate_ctxt *ctxt) { ctxt->src.val = (unsigned long)ctxt->eflags & ~X86_EFLAGS_VM; return em_push(ctxt); } static int em_popa(struct x86_emulate_ctxt *ctxt) { int rc = X86EMUL_CONTINUE; int reg = VCPU_REGS_RDI; u32 val; while (reg >= VCPU_REGS_RAX) { if (reg == VCPU_REGS_RSP) { rsp_increment(ctxt, ctxt->op_bytes); --reg; } rc = emulate_pop(ctxt, &val, ctxt->op_bytes); if (rc != X86EMUL_CONTINUE) break; assign_register(reg_rmw(ctxt, reg), val, ctxt->op_bytes); --reg; } return rc; } static int __emulate_int_real(struct x86_emulate_ctxt *ctxt, int irq) { const struct x86_emulate_ops *ops = ctxt->ops; int rc; struct desc_ptr dt; gva_t cs_addr; gva_t eip_addr; u16 cs, eip; /* TODO: Add limit checks */ ctxt->src.val = ctxt->eflags; rc = em_push(ctxt); if (rc != X86EMUL_CONTINUE) return rc; ctxt->eflags &= ~(X86_EFLAGS_IF | X86_EFLAGS_TF | X86_EFLAGS_AC); ctxt->src.val = get_segment_selector(ctxt, VCPU_SREG_CS); rc = em_push(ctxt); if (rc != X86EMUL_CONTINUE) return rc; ctxt->src.val = ctxt->_eip; rc = em_push(ctxt); if (rc != X86EMUL_CONTINUE) return rc; ops->get_idt(ctxt, &dt); eip_addr = dt.address + (irq << 2); cs_addr = dt.address + (irq << 2) + 2; rc = linear_read_system(ctxt, cs_addr, &cs, 2); if (rc != X86EMUL_CONTINUE) return rc; rc = linear_read_system(ctxt, eip_addr, &eip, 2); if (rc != X86EMUL_CONTINUE) return rc; rc = load_segment_descriptor(ctxt, cs, VCPU_SREG_CS); if (rc != X86EMUL_CONTINUE) return rc; ctxt->_eip = eip; return rc; } int emulate_int_real(struct x86_emulate_ctxt *ctxt, int irq) { int rc; invalidate_registers(ctxt); rc = __emulate_int_real(ctxt, irq); if (rc == X86EMUL_CONTINUE) writeback_registers(ctxt); return rc; } static int emulate_int(struct x86_emulate_ctxt *ctxt, int irq) { switch(ctxt->mode) { case X86EMUL_MODE_REAL: return __emulate_int_real(ctxt, irq); case X86EMUL_MODE_VM86: case X86EMUL_MODE_PROT16: case X86EMUL_MODE_PROT32: case X86EMUL_MODE_PROT64: default: /* Protected mode interrupts unimplemented yet */ return X86EMUL_UNHANDLEABLE; } } static int emulate_iret_real(struct x86_emulate_ctxt *ctxt) { int rc = X86EMUL_CONTINUE; unsigned long temp_eip = 0; unsigned long temp_eflags = 0; unsigned long cs = 0; unsigned long mask = X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF | X86_EFLAGS_ZF | X86_EFLAGS_SF | X86_EFLAGS_TF | X86_EFLAGS_IF | X86_EFLAGS_DF | X86_EFLAGS_OF | X86_EFLAGS_IOPL | X86_EFLAGS_NT | X86_EFLAGS_RF | X86_EFLAGS_AC | X86_EFLAGS_ID | X86_EFLAGS_FIXED; unsigned long vm86_mask = X86_EFLAGS_VM | X86_EFLAGS_VIF | X86_EFLAGS_VIP; /* TODO: Add stack limit check */ rc = emulate_pop(ctxt, &temp_eip, ctxt->op_bytes); if (rc != X86EMUL_CONTINUE) return rc; if (temp_eip & ~0xffff) return emulate_gp(ctxt, 0); rc = emulate_pop(ctxt, &cs, ctxt->op_bytes); if (rc != X86EMUL_CONTINUE) return rc; rc = emulate_pop(ctxt, &temp_eflags, ctxt->op_bytes); if (rc != X86EMUL_CONTINUE) return rc; rc = load_segment_descriptor(ctxt, (u16)cs, VCPU_SREG_CS); if (rc != X86EMUL_CONTINUE) return rc; ctxt->_eip = temp_eip; if (ctxt->op_bytes == 4) ctxt->eflags = ((temp_eflags & mask) | (ctxt->eflags & vm86_mask)); else if (ctxt->op_bytes == 2) { ctxt->eflags &= ~0xffff; ctxt->eflags |= temp_eflags; } ctxt->eflags &= ~EFLG_RESERVED_ZEROS_MASK; /* Clear reserved zeros */ ctxt->eflags |= X86_EFLAGS_FIXED; ctxt->ops->set_nmi_mask(ctxt, false); return rc; } static int em_iret(struct x86_emulate_ctxt *ctxt) { switch(ctxt->mode) { case X86EMUL_MODE_REAL: return emulate_iret_real(ctxt); case X86EMUL_MODE_VM86: case X86EMUL_MODE_PROT16: case X86EMUL_MODE_PROT32: case X86EMUL_MODE_PROT64: default: /* iret from protected mode unimplemented yet */ return X86EMUL_UNHANDLEABLE; } } static int em_jmp_far(struct x86_emulate_ctxt *ctxt) { int rc; unsigned short sel; struct desc_struct new_desc; u8 cpl = ctxt->ops->cpl(ctxt); memcpy(&sel, ctxt->src.valptr + ctxt->op_bytes, 2); rc = __load_segment_descriptor(ctxt, sel, VCPU_SREG_CS, cpl, X86_TRANSFER_CALL_JMP, &new_desc); if (rc != X86EMUL_CONTINUE) return rc; rc = assign_eip_far(ctxt, ctxt->src.val); /* Error handling is not implemented. */ if (rc != X86EMUL_CONTINUE) return X86EMUL_UNHANDLEABLE; return rc; } static int em_jmp_abs(struct x86_emulate_ctxt *ctxt) { return assign_eip_near(ctxt, ctxt->src.val); } static int em_call_near_abs(struct x86_emulate_ctxt *ctxt) { int rc; long int old_eip; old_eip = ctxt->_eip; rc = assign_eip_near(ctxt, ctxt->src.val); if (rc != X86EMUL_CONTINUE) return rc; ctxt->src.val = old_eip; rc = em_push(ctxt); return rc; } static int em_cmpxchg8b(struct x86_emulate_ctxt *ctxt) { u64 old = ctxt->dst.orig_val64; if (ctxt->dst.bytes == 16) return X86EMUL_UNHANDLEABLE; if (((u32) (old >> 0) != (u32) reg_read(ctxt, VCPU_REGS_RAX)) || ((u32) (old >> 32) != (u32) reg_read(ctxt, VCPU_REGS_RDX))) { *reg_write(ctxt, VCPU_REGS_RAX) = (u32) (old >> 0); *reg_write(ctxt, VCPU_REGS_RDX) = (u32) (old >> 32); ctxt->eflags &= ~X86_EFLAGS_ZF; } else { ctxt->dst.val64 = ((u64)reg_read(ctxt, VCPU_REGS_RCX) << 32) | (u32) reg_read(ctxt, VCPU_REGS_RBX); ctxt->eflags |= X86_EFLAGS_ZF; } return X86EMUL_CONTINUE; } static int em_ret(struct x86_emulate_ctxt *ctxt) { int rc; unsigned long eip; rc = emulate_pop(ctxt, &eip, ctxt->op_bytes); if (rc != X86EMUL_CONTINUE) return rc; return assign_eip_near(ctxt, eip); } static int em_ret_far(struct x86_emulate_ctxt *ctxt) { int rc; unsigned long eip, cs; int cpl = ctxt->ops->cpl(ctxt); struct desc_struct new_desc; rc = emulate_pop(ctxt, &eip, ctxt->op_bytes); if (rc != X86EMUL_CONTINUE) return rc; rc = emulate_pop(ctxt, &cs, ctxt->op_bytes); if (rc != X86EMUL_CONTINUE) return rc; /* Outer-privilege level return is not implemented */ if (ctxt->mode >= X86EMUL_MODE_PROT16 && (cs & 3) > cpl) return X86EMUL_UNHANDLEABLE; rc = __load_segment_descriptor(ctxt, (u16)cs, VCPU_SREG_CS, cpl, X86_TRANSFER_RET, &new_desc); if (rc != X86EMUL_CONTINUE) return rc; rc = assign_eip_far(ctxt, eip); /* Error handling is not implemented. */ if (rc != X86EMUL_CONTINUE) return X86EMUL_UNHANDLEABLE; return rc; } static int em_ret_far_imm(struct x86_emulate_ctxt *ctxt) { int rc; rc = em_ret_far(ctxt); if (rc != X86EMUL_CONTINUE) return rc; rsp_increment(ctxt, ctxt->src.val); return X86EMUL_CONTINUE; } static int em_cmpxchg(struct x86_emulate_ctxt *ctxt) { /* Save real source value, then compare EAX against destination. */ ctxt->dst.orig_val = ctxt->dst.val; ctxt->dst.val = reg_read(ctxt, VCPU_REGS_RAX); ctxt->src.orig_val = ctxt->src.val; ctxt->src.val = ctxt->dst.orig_val; fastop(ctxt, em_cmp); if (ctxt->eflags & X86_EFLAGS_ZF) { /* Success: write back to memory; no update of EAX */ ctxt->src.type = OP_NONE; ctxt->dst.val = ctxt->src.orig_val; } else { /* Failure: write the value we saw to EAX. */ ctxt->src.type = OP_REG; ctxt->src.addr.reg = reg_rmw(ctxt, VCPU_REGS_RAX); ctxt->src.val = ctxt->dst.orig_val; /* Create write-cycle to dest by writing the same value */ ctxt->dst.val = ctxt->dst.orig_val; } return X86EMUL_CONTINUE; } static int em_lseg(struct x86_emulate_ctxt *ctxt) { int seg = ctxt->src2.val; unsigned short sel; int rc; memcpy(&sel, ctxt->src.valptr + ctxt->op_bytes, 2); rc = load_segment_descriptor(ctxt, sel, seg); if (rc != X86EMUL_CONTINUE) return rc; ctxt->dst.val = ctxt->src.val; return rc; } static int emulator_has_longmode(struct x86_emulate_ctxt *ctxt) { u32 eax, ebx, ecx, edx; eax = 0x80000001; ecx = 0; ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false); return edx & bit(X86_FEATURE_LM); } #define GET_SMSTATE(type, smbase, offset) \ ({ \ type __val; \ int r = ctxt->ops->read_phys(ctxt, smbase + offset, &__val, \ sizeof(__val)); \ if (r != X86EMUL_CONTINUE) \ return X86EMUL_UNHANDLEABLE; \ __val; \ }) static void rsm_set_desc_flags(struct desc_struct *desc, u32 flags) { desc->g = (flags >> 23) & 1; desc->d = (flags >> 22) & 1; desc->l = (flags >> 21) & 1; desc->avl = (flags >> 20) & 1; desc->p = (flags >> 15) & 1; desc->dpl = (flags >> 13) & 3; desc->s = (flags >> 12) & 1; desc->type = (flags >> 8) & 15; } static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, u64 smbase, int n) { struct desc_struct desc; int offset; u16 selector; selector = GET_SMSTATE(u32, smbase, 0x7fa8 + n * 4); if (n < 3) offset = 0x7f84 + n * 12; else offset = 0x7f2c + (n - 3) * 12; set_desc_base(&desc, GET_SMSTATE(u32, smbase, offset + 8)); set_desc_limit(&desc, GET_SMSTATE(u32, smbase, offset + 4)); rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, offset)); ctxt->ops->set_segment(ctxt, selector, &desc, 0, n); return X86EMUL_CONTINUE; } static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n) { struct desc_struct desc; int offset; u16 selector; u32 base3; offset = 0x7e00 + n * 16; selector = GET_SMSTATE(u16, smbase, offset); rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smbase, offset + 2) << 8); set_desc_limit(&desc, GET_SMSTATE(u32, smbase, offset + 4)); set_desc_base(&desc, GET_SMSTATE(u32, smbase, offset + 8)); base3 = GET_SMSTATE(u32, smbase, offset + 12); ctxt->ops->set_segment(ctxt, selector, &desc, base3, n); return X86EMUL_CONTINUE; } static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt, u64 cr0, u64 cr3, u64 cr4) { int bad; u64 pcid; /* In order to later set CR4.PCIDE, CR3[11:0] must be zero. */ pcid = 0; if (cr4 & X86_CR4_PCIDE) { pcid = cr3 & 0xfff; cr3 &= ~0xfff; } bad = ctxt->ops->set_cr(ctxt, 3, cr3); if (bad) return X86EMUL_UNHANDLEABLE; /* * First enable PAE, long mode needs it before CR0.PG = 1 is set. * Then enable protected mode. However, PCID cannot be enabled * if EFER.LMA=0, so set it separately. */ bad = ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE); if (bad) return X86EMUL_UNHANDLEABLE; bad = ctxt->ops->set_cr(ctxt, 0, cr0); if (bad) return X86EMUL_UNHANDLEABLE; if (cr4 & X86_CR4_PCIDE) { bad = ctxt->ops->set_cr(ctxt, 4, cr4); if (bad) return X86EMUL_UNHANDLEABLE; if (pcid) { bad = ctxt->ops->set_cr(ctxt, 3, cr3 | pcid); if (bad) return X86EMUL_UNHANDLEABLE; } } return X86EMUL_CONTINUE; } static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase) { struct desc_struct desc; struct desc_ptr dt; u16 selector; u32 val, cr0, cr3, cr4; int i; cr0 = GET_SMSTATE(u32, smbase, 0x7ffc); cr3 = GET_SMSTATE(u32, smbase, 0x7ff8); ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7ff4) | X86_EFLAGS_FIXED; ctxt->_eip = GET_SMSTATE(u32, smbase, 0x7ff0); for (i = 0; i < 8; i++) *reg_write(ctxt, i) = GET_SMSTATE(u32, smbase, 0x7fd0 + i * 4); val = GET_SMSTATE(u32, smbase, 0x7fcc); ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1); val = GET_SMSTATE(u32, smbase, 0x7fc8); ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1); selector = GET_SMSTATE(u32, smbase, 0x7fc4); set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7f64)); set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7f60)); rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7f5c)); ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_TR); selector = GET_SMSTATE(u32, smbase, 0x7fc0); set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7f80)); set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7f7c)); rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7f78)); ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_LDTR); dt.address = GET_SMSTATE(u32, smbase, 0x7f74); dt.size = GET_SMSTATE(u32, smbase, 0x7f70); ctxt->ops->set_gdt(ctxt, &dt); dt.address = GET_SMSTATE(u32, smbase, 0x7f58); dt.size = GET_SMSTATE(u32, smbase, 0x7f54); ctxt->ops->set_idt(ctxt, &dt); for (i = 0; i < 6; i++) { int r = rsm_load_seg_32(ctxt, smbase, i); if (r != X86EMUL_CONTINUE) return r; } cr4 = GET_SMSTATE(u32, smbase, 0x7f14); ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7ef8)); return rsm_enter_protected_mode(ctxt, cr0, cr3, cr4); } static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase) { struct desc_struct desc; struct desc_ptr dt; u64 val, cr0, cr3, cr4; u32 base3; u16 selector; int i, r; for (i = 0; i < 16; i++) *reg_write(ctxt, i) = GET_SMSTATE(u64, smbase, 0x7ff8 - i * 8); ctxt->_eip = GET_SMSTATE(u64, smbase, 0x7f78); ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7f70) | X86_EFLAGS_FIXED; val = GET_SMSTATE(u32, smbase, 0x7f68); ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1); val = GET_SMSTATE(u32, smbase, 0x7f60); ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1); cr0 = GET_SMSTATE(u64, smbase, 0x7f58); cr3 = GET_SMSTATE(u64, smbase, 0x7f50); cr4 = GET_SMSTATE(u64, smbase, 0x7f48); ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7f00)); val = GET_SMSTATE(u64, smbase, 0x7ed0); ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA); selector = GET_SMSTATE(u32, smbase, 0x7e90); rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7e92) << 8); set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7e94)); set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7e98)); base3 = GET_SMSTATE(u32, smbase, 0x7e9c); ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_TR); dt.size = GET_SMSTATE(u32, smbase, 0x7e84); dt.address = GET_SMSTATE(u64, smbase, 0x7e88); ctxt->ops->set_idt(ctxt, &dt); selector = GET_SMSTATE(u32, smbase, 0x7e70); rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7e72) << 8); set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7e74)); set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7e78)); base3 = GET_SMSTATE(u32, smbase, 0x7e7c); ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_LDTR); dt.size = GET_SMSTATE(u32, smbase, 0x7e64); dt.address = GET_SMSTATE(u64, smbase, 0x7e68); ctxt->ops->set_gdt(ctxt, &dt); r = rsm_enter_protected_mode(ctxt, cr0, cr3, cr4); if (r != X86EMUL_CONTINUE) return r; for (i = 0; i < 6; i++) { r = rsm_load_seg_64(ctxt, smbase, i); if (r != X86EMUL_CONTINUE) return r; } return X86EMUL_CONTINUE; } static int em_rsm(struct x86_emulate_ctxt *ctxt) { unsigned long cr0, cr4, efer; u64 smbase; int ret; if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_MASK) == 0) return emulate_ud(ctxt); /* * Get back to real mode, to prepare a safe state in which to load * CR0/CR3/CR4/EFER. It's all a bit more complicated if the vCPU * supports long mode. */ if (emulator_has_longmode(ctxt)) { struct desc_struct cs_desc; /* Zero CR4.PCIDE before CR0.PG. */ cr4 = ctxt->ops->get_cr(ctxt, 4); if (cr4 & X86_CR4_PCIDE) ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE); /* A 32-bit code segment is required to clear EFER.LMA. */ memset(&cs_desc, 0, sizeof(cs_desc)); cs_desc.type = 0xb; cs_desc.s = cs_desc.g = cs_desc.p = 1; ctxt->ops->set_segment(ctxt, 0, &cs_desc, 0, VCPU_SREG_CS); } /* For the 64-bit case, this will clear EFER.LMA. */ cr0 = ctxt->ops->get_cr(ctxt, 0); if (cr0 & X86_CR0_PE) ctxt->ops->set_cr(ctxt, 0, cr0 & ~(X86_CR0_PG | X86_CR0_PE)); if (emulator_has_longmode(ctxt)) { /* Clear CR4.PAE before clearing EFER.LME. */ cr4 = ctxt->ops->get_cr(ctxt, 4); if (cr4 & X86_CR4_PAE) ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE); /* And finally go back to 32-bit mode. */ efer = 0; ctxt->ops->set_msr(ctxt, MSR_EFER, efer); } smbase = ctxt->ops->get_smbase(ctxt); if (emulator_has_longmode(ctxt)) ret = rsm_load_state_64(ctxt, smbase + 0x8000); else ret = rsm_load_state_32(ctxt, smbase + 0x8000); if (ret != X86EMUL_CONTINUE) { /* FIXME: should triple fault */ return X86EMUL_UNHANDLEABLE; } if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_INSIDE_NMI_MASK) == 0) ctxt->ops->set_nmi_mask(ctxt, false); ctxt->ops->set_hflags(ctxt, ctxt->ops->get_hflags(ctxt) & ~(X86EMUL_SMM_INSIDE_NMI_MASK | X86EMUL_SMM_MASK)); return X86EMUL_CONTINUE; } static void setup_syscalls_segments(struct x86_emulate_ctxt *ctxt, struct desc_struct *cs, struct desc_struct *ss) { cs->l = 0; /* will be adjusted later */ set_desc_base(cs, 0); /* flat segment */ cs->g = 1; /* 4kb granularity */ set_desc_limit(cs, 0xfffff); /* 4GB limit */ cs->type = 0x0b; /* Read, Execute, Accessed */ cs->s = 1; cs->dpl = 0; /* will be adjusted later */ cs->p = 1; cs->d = 1; cs->avl = 0; set_desc_base(ss, 0); /* flat segment */ set_desc_limit(ss, 0xfffff); /* 4GB limit */ ss->g = 1; /* 4kb granularity */ ss->s = 1; ss->type = 0x03; /* Read/Write, Accessed */ ss->d = 1; /* 32bit stack segment */ ss->dpl = 0; ss->p = 1; ss->l = 0; ss->avl = 0; } static bool vendor_intel(struct x86_emulate_ctxt *ctxt) { u32 eax, ebx, ecx, edx; eax = ecx = 0; ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false); return ebx == X86EMUL_CPUID_VENDOR_GenuineIntel_ebx && ecx == X86EMUL_CPUID_VENDOR_GenuineIntel_ecx && edx == X86EMUL_CPUID_VENDOR_GenuineIntel_edx; } static bool em_syscall_is_enabled(struct x86_emulate_ctxt *ctxt) { const struct x86_emulate_ops *ops = ctxt->ops; u32 eax, ebx, ecx, edx; /* * syscall should always be enabled in longmode - so only become * vendor specific (cpuid) if other modes are active... */ if (ctxt->mode == X86EMUL_MODE_PROT64) return true; eax = 0x00000000; ecx = 0x00000000; ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false); /* * Intel ("GenuineIntel") * remark: Intel CPUs only support "syscall" in 64bit * longmode. Also an 64bit guest with a * 32bit compat-app running will #UD !! While this * behaviour can be fixed (by emulating) into AMD * response - CPUs of AMD can't behave like Intel. */ if (ebx == X86EMUL_CPUID_VENDOR_GenuineIntel_ebx && ecx == X86EMUL_CPUID_VENDOR_GenuineIntel_ecx && edx == X86EMUL_CPUID_VENDOR_GenuineIntel_edx) return false; /* AMD ("AuthenticAMD") */ if (ebx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx && ecx == X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx && edx == X86EMUL_CPUID_VENDOR_AuthenticAMD_edx) return true; /* AMD ("AMDisbetter!") */ if (ebx == X86EMUL_CPUID_VENDOR_AMDisbetterI_ebx && ecx == X86EMUL_CPUID_VENDOR_AMDisbetterI_ecx && edx == X86EMUL_CPUID_VENDOR_AMDisbetterI_edx) return true; /* default: (not Intel, not AMD), apply Intel's stricter rules... */ return false; } static int em_syscall(struct x86_emulate_ctxt *ctxt) { const struct x86_emulate_ops *ops = ctxt->ops; struct desc_struct cs, ss; u64 msr_data; u16 cs_sel, ss_sel; u64 efer = 0; /* syscall is not available in real mode */ if (ctxt->mode == X86EMUL_MODE_REAL || ctxt->mode == X86EMUL_MODE_VM86) return emulate_ud(ctxt); if (!(em_syscall_is_enabled(ctxt))) return emulate_ud(ctxt); ops->get_msr(ctxt, MSR_EFER, &efer); setup_syscalls_segments(ctxt, &cs, &ss); if (!(efer & EFER_SCE)) return emulate_ud(ctxt); ops->get_msr(ctxt, MSR_STAR, &msr_data); msr_data >>= 32; cs_sel = (u16)(msr_data & 0xfffc); ss_sel = (u16)(msr_data + 8); if (efer & EFER_LMA) { cs.d = 0; cs.l = 1; } ops->set_segment(ctxt, cs_sel, &cs, 0, VCPU_SREG_CS); ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS); *reg_write(ctxt, VCPU_REGS_RCX) = ctxt->_eip; if (efer & EFER_LMA) { #ifdef CONFIG_X86_64 *reg_write(ctxt, VCPU_REGS_R11) = ctxt->eflags; ops->get_msr(ctxt, ctxt->mode == X86EMUL_MODE_PROT64 ? MSR_LSTAR : MSR_CSTAR, &msr_data); ctxt->_eip = msr_data; ops->get_msr(ctxt, MSR_SYSCALL_MASK, &msr_data); ctxt->eflags &= ~msr_data; ctxt->eflags |= X86_EFLAGS_FIXED; #endif } else { /* legacy mode */ ops->get_msr(ctxt, MSR_STAR, &msr_data); ctxt->_eip = (u32)msr_data; ctxt->eflags &= ~(X86_EFLAGS_VM | X86_EFLAGS_IF); } ctxt->tf = (ctxt->eflags & X86_EFLAGS_TF) != 0; return X86EMUL_CONTINUE; } static int em_sysenter(struct x86_emulate_ctxt *ctxt) { const struct x86_emulate_ops *ops = ctxt->ops; struct desc_struct cs, ss; u64 msr_data; u16 cs_sel, ss_sel; u64 efer = 0; ops->get_msr(ctxt, MSR_EFER, &efer); /* inject #GP if in real mode */ if (ctxt->mode == X86EMUL_MODE_REAL) return emulate_gp(ctxt, 0); /* * Not recognized on AMD in compat mode (but is recognized in legacy * mode). */ if ((ctxt->mode != X86EMUL_MODE_PROT64) && (efer & EFER_LMA) && !vendor_intel(ctxt)) return emulate_ud(ctxt); /* sysenter/sysexit have not been tested in 64bit mode. */ if (ctxt->mode == X86EMUL_MODE_PROT64) return X86EMUL_UNHANDLEABLE; setup_syscalls_segments(ctxt, &cs, &ss); ops->get_msr(ctxt, MSR_IA32_SYSENTER_CS, &msr_data); if ((msr_data & 0xfffc) == 0x0) return emulate_gp(ctxt, 0); ctxt->eflags &= ~(X86_EFLAGS_VM | X86_EFLAGS_IF); cs_sel = (u16)msr_data & ~SEGMENT_RPL_MASK; ss_sel = cs_sel + 8; if (efer & EFER_LMA) { cs.d = 0; cs.l = 1; } ops->set_segment(ctxt, cs_sel, &cs, 0, VCPU_SREG_CS); ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS); ops->get_msr(ctxt, MSR_IA32_SYSENTER_EIP, &msr_data); ctxt->_eip = (efer & EFER_LMA) ? msr_data : (u32)msr_data; ops->get_msr(ctxt, MSR_IA32_SYSENTER_ESP, &msr_data); *reg_write(ctxt, VCPU_REGS_RSP) = (efer & EFER_LMA) ? msr_data : (u32)msr_data; return X86EMUL_CONTINUE; } static int em_sysexit(struct x86_emulate_ctxt *ctxt) { const struct x86_emulate_ops *ops = ctxt->ops; struct desc_struct cs, ss; u64 msr_data, rcx, rdx; int usermode; u16 cs_sel = 0, ss_sel = 0; /* inject #GP if in real mode or Virtual 8086 mode */ if (ctxt->mode == X86EMUL_MODE_REAL || ctxt->mode == X86EMUL_MODE_VM86) return emulate_gp(ctxt, 0); setup_syscalls_segments(ctxt, &cs, &ss); if ((ctxt->rex_prefix & 0x8) != 0x0) usermode = X86EMUL_MODE_PROT64; else usermode = X86EMUL_MODE_PROT32; rcx = reg_read(ctxt, VCPU_REGS_RCX); rdx = reg_read(ctxt, VCPU_REGS_RDX); cs.dpl = 3; ss.dpl = 3; ops->get_msr(ctxt, MSR_IA32_SYSENTER_CS, &msr_data); switch (usermode) { case X86EMUL_MODE_PROT32: cs_sel = (u16)(msr_data + 16); if ((msr_data & 0xfffc) == 0x0) return emulate_gp(ctxt, 0); ss_sel = (u16)(msr_data + 24); rcx = (u32)rcx; rdx = (u32)rdx; break; case X86EMUL_MODE_PROT64: cs_sel = (u16)(msr_data + 32); if (msr_data == 0x0) return emulate_gp(ctxt, 0); ss_sel = cs_sel + 8; cs.d = 0; cs.l = 1; if (emul_is_noncanonical_address(rcx, ctxt) || emul_is_noncanonical_address(rdx, ctxt)) return emulate_gp(ctxt, 0); break; } cs_sel |= SEGMENT_RPL_MASK; ss_sel |= SEGMENT_RPL_MASK; ops->set_segment(ctxt, cs_sel, &cs, 0, VCPU_SREG_CS); ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS); ctxt->_eip = rdx; ctxt->mode = usermode; *reg_write(ctxt, VCPU_REGS_RSP) = rcx; return X86EMUL_CONTINUE; } static bool emulator_bad_iopl(struct x86_emulate_ctxt *ctxt) { int iopl; if (ctxt->mode == X86EMUL_MODE_REAL) return false; if (ctxt->mode == X86EMUL_MODE_VM86) return true; iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> X86_EFLAGS_IOPL_BIT; return ctxt->ops->cpl(ctxt) > iopl; } static bool emulator_io_port_access_allowed(struct x86_emulate_ctxt *ctxt, u16 port, u16 len) { const struct x86_emulate_ops *ops = ctxt->ops; struct desc_struct tr_seg; u32 base3; int r; u16 tr, io_bitmap_ptr, perm, bit_idx = port & 0x7; unsigned mask = (1 << len) - 1; unsigned long base; ops->get_segment(ctxt, &tr, &tr_seg, &base3, VCPU_SREG_TR); if (!tr_seg.p) return false; if (desc_limit_scaled(&tr_seg) < 103) return false; base = get_desc_base(&tr_seg); #ifdef CONFIG_X86_64 base |= ((u64)base3) << 32; #endif r = ops->read_std(ctxt, base + 102, &io_bitmap_ptr, 2, NULL, true); if (r != X86EMUL_CONTINUE) return false; if (io_bitmap_ptr + port/8 > desc_limit_scaled(&tr_seg)) return false; r = ops->read_std(ctxt, base + io_bitmap_ptr + port/8, &perm, 2, NULL, true); if (r != X86EMUL_CONTINUE) return false; if ((perm >> bit_idx) & mask) return false; return true; } static bool emulator_io_permited(struct x86_emulate_ctxt *ctxt, u16 port, u16 len) { if (ctxt->perm_ok) return true; if (emulator_bad_iopl(ctxt)) if (!emulator_io_port_access_allowed(ctxt, port, len)) return false; ctxt->perm_ok = true; return true; } static void string_registers_quirk(struct x86_emulate_ctxt *ctxt) { /* * Intel CPUs mask the counter and pointers in quite strange * manner when ECX is zero due to REP-string optimizations. */ #ifdef CONFIG_X86_64 if (ctxt->ad_bytes != 4 || !vendor_intel(ctxt)) return; *reg_write(ctxt, VCPU_REGS_RCX) = 0; switch (ctxt->b) { case 0xa4: /* movsb */ case 0xa5: /* movsd/w */ *reg_rmw(ctxt, VCPU_REGS_RSI) &= (u32)-1; /* fall through */ case 0xaa: /* stosb */ case 0xab: /* stosd/w */ *reg_rmw(ctxt, VCPU_REGS_RDI) &= (u32)-1; } #endif } static void save_state_to_tss16(struct x86_emulate_ctxt *ctxt, struct tss_segment_16 *tss) { tss->ip = ctxt->_eip; tss->flag = ctxt->eflags; tss->ax = reg_read(ctxt, VCPU_REGS_RAX); tss->cx = reg_read(ctxt, VCPU_REGS_RCX); tss->dx = reg_read(ctxt, VCPU_REGS_RDX); tss->bx = reg_read(ctxt, VCPU_REGS_RBX); tss->sp = reg_read(ctxt, VCPU_REGS_RSP); tss->bp = reg_read(ctxt, VCPU_REGS_RBP); tss->si = reg_read(ctxt, VCPU_REGS_RSI); tss->di = reg_read(ctxt, VCPU_REGS_RDI); tss->es = get_segment_selector(ctxt, VCPU_SREG_ES); tss->cs = get_segment_selector(ctxt, VCPU_SREG_CS); tss->ss = get_segment_selector(ctxt, VCPU_SREG_SS); tss->ds = get_segment_selector(ctxt, VCPU_SREG_DS); tss->ldt = get_segment_selector(ctxt, VCPU_SREG_LDTR); } static int load_state_from_tss16(struct x86_emulate_ctxt *ctxt, struct tss_segment_16 *tss) { int ret; u8 cpl; ctxt->_eip = tss->ip; ctxt->eflags = tss->flag | 2; *reg_write(ctxt, VCPU_REGS_RAX) = tss->ax; *reg_write(ctxt, VCPU_REGS_RCX) = tss->cx; *reg_write(ctxt, VCPU_REGS_RDX) = tss->dx; *reg_write(ctxt, VCPU_REGS_RBX) = tss->bx; *reg_write(ctxt, VCPU_REGS_RSP) = tss->sp; *reg_write(ctxt, VCPU_REGS_RBP) = tss->bp; *reg_write(ctxt, VCPU_REGS_RSI) = tss->si; *reg_write(ctxt, VCPU_REGS_RDI) = tss->di; /* * SDM says that segment selectors are loaded before segment * descriptors */ set_segment_selector(ctxt, tss->ldt, VCPU_SREG_LDTR); set_segment_selector(ctxt, tss->es, VCPU_SREG_ES); set_segment_selector(ctxt, tss->cs, VCPU_SREG_CS); set_segment_selector(ctxt, tss->ss, VCPU_SREG_SS); set_segment_selector(ctxt, tss->ds, VCPU_SREG_DS); cpl = tss->cs & 3; /* * Now load segment descriptors. If fault happens at this stage * it is handled in a context of new task */ ret = __load_segment_descriptor(ctxt, tss->ldt, VCPU_SREG_LDTR, cpl, X86_TRANSFER_TASK_SWITCH, NULL); if (ret != X86EMUL_CONTINUE) return ret; ret = __load_segment_descriptor(ctxt, tss->es, VCPU_SREG_ES, cpl, X86_TRANSFER_TASK_SWITCH, NULL); if (ret != X86EMUL_CONTINUE) return ret; ret = __load_segment_descriptor(ctxt, tss->cs, VCPU_SREG_CS, cpl, X86_TRANSFER_TASK_SWITCH, NULL); if (ret != X86EMUL_CONTINUE) return ret; ret = __load_segment_descriptor(ctxt, tss->ss, VCPU_SREG_SS, cpl, X86_TRANSFER_TASK_SWITCH, NULL); if (ret != X86EMUL_CONTINUE) return ret; ret = __load_segment_descriptor(ctxt, tss->ds, VCPU_SREG_DS, cpl, X86_TRANSFER_TASK_SWITCH, NULL); if (ret != X86EMUL_CONTINUE) return ret; return X86EMUL_CONTINUE; } static int task_switch_16(struct x86_emulate_ctxt *ctxt, u16 tss_selector, u16 old_tss_sel, ulong old_tss_base, struct desc_struct *new_desc) { struct tss_segment_16 tss_seg; int ret; u32 new_tss_base = get_desc_base(new_desc); ret = linear_read_system(ctxt, old_tss_base, &tss_seg, sizeof tss_seg); if (ret != X86EMUL_CONTINUE) return ret; save_state_to_tss16(ctxt, &tss_seg); ret = linear_write_system(ctxt, old_tss_base, &tss_seg, sizeof tss_seg); if (ret != X86EMUL_CONTINUE) return ret; ret = linear_read_system(ctxt, new_tss_base, &tss_seg, sizeof tss_seg); if (ret != X86EMUL_CONTINUE) return ret; if (old_tss_sel != 0xffff) { tss_seg.prev_task_link = old_tss_sel; ret = linear_write_system(ctxt, new_tss_base, &tss_seg.prev_task_link, sizeof tss_seg.prev_task_link); if (ret != X86EMUL_CONTINUE) return ret; } return load_state_from_tss16(ctxt, &tss_seg); } static void save_state_to_tss32(struct x86_emulate_ctxt *ctxt, struct tss_segment_32 *tss) { /* CR3 and ldt selector are not saved intentionally */ tss->eip = ctxt->_eip; tss->eflags = ctxt->eflags; tss->eax = reg_read(ctxt, VCPU_REGS_RAX); tss->ecx = reg_read(ctxt, VCPU_REGS_RCX); tss->edx = reg_read(ctxt, VCPU_REGS_RDX); tss->ebx = reg_read(ctxt, VCPU_REGS_RBX); tss->esp = reg_read(ctxt, VCPU_REGS_RSP); tss->ebp = reg_read(ctxt, VCPU_REGS_RBP); tss->esi = reg_read(ctxt, VCPU_REGS_RSI); tss->edi = reg_read(ctxt, VCPU_REGS_RDI); tss->es = get_segment_selector(ctxt, VCPU_SREG_ES); tss->cs = get_segment_selector(ctxt, VCPU_SREG_CS); tss->ss = get_segment_selector(ctxt, VCPU_SREG_SS); tss->ds = get_segment_selector(ctxt, VCPU_SREG_DS); tss->fs = get_segment_selector(ctxt, VCPU_SREG_FS); tss->gs = get_segment_selector(ctxt, VCPU_SREG_GS); } static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt, struct tss_segment_32 *tss) { int ret; u8 cpl; if (ctxt->ops->set_cr(ctxt, 3, tss->cr3)) return emulate_gp(ctxt, 0); ctxt->_eip = tss->eip; ctxt->eflags = tss->eflags | 2; /* General purpose registers */ *reg_write(ctxt, VCPU_REGS_RAX) = tss->eax; *reg_write(ctxt, VCPU_REGS_RCX) = tss->ecx; *reg_write(ctxt, VCPU_REGS_RDX) = tss->edx; *reg_write(ctxt, VCPU_REGS_RBX) = tss->ebx; *reg_write(ctxt, VCPU_REGS_RSP) = tss->esp; *reg_write(ctxt, VCPU_REGS_RBP) = tss->ebp; *reg_write(ctxt, VCPU_REGS_RSI) = tss->esi; *reg_write(ctxt, VCPU_REGS_RDI) = tss->edi; /* * SDM says that segment selectors are loaded before segment * descriptors. This is important because CPL checks will * use CS.RPL. */ set_segment_selector(ctxt, tss->ldt_selector, VCPU_SREG_LDTR); set_segment_selector(ctxt, tss->es, VCPU_SREG_ES); set_segment_selector(ctxt, tss->cs, VCPU_SREG_CS); set_segment_selector(ctxt, tss->ss, VCPU_SREG_SS); set_segment_selector(ctxt, tss->ds, VCPU_SREG_DS); set_segment_selector(ctxt, tss->fs, VCPU_SREG_FS); set_segment_selector(ctxt, tss->gs, VCPU_SREG_GS); /* * If we're switching between Protected Mode and VM86, we need to make * sure to update the mode before loading the segment descriptors so * that the selectors are interpreted correctly. */ if (ctxt->eflags & X86_EFLAGS_VM) { ctxt->mode = X86EMUL_MODE_VM86; cpl = 3; } else { ctxt->mode = X86EMUL_MODE_PROT32; cpl = tss->cs & 3; } /* * Now load segment descriptors. If fault happenes at this stage * it is handled in a context of new task */ ret = __load_segment_descriptor(ctxt, tss->ldt_selector, VCPU_SREG_LDTR, cpl, X86_TRANSFER_TASK_SWITCH, NULL); if (ret != X86EMUL_CONTINUE) return ret; ret = __load_segment_descriptor(ctxt, tss->es, VCPU_SREG_ES, cpl, X86_TRANSFER_TASK_SWITCH, NULL); if (ret != X86EMUL_CONTINUE) return ret; ret = __load_segment_descriptor(ctxt, tss->cs, VCPU_SREG_CS, cpl, X86_TRANSFER_TASK_SWITCH, NULL); if (ret != X86EMUL_CONTINUE) return ret; ret = __load_segment_descriptor(ctxt, tss->ss, VCPU_SREG_SS, cpl, X86_TRANSFER_TASK_SWITCH, NULL); if (ret != X86EMUL_CONTINUE) return ret; ret = __load_segment_descriptor(ctxt, tss->ds, VCPU_SREG_DS, cpl, X86_TRANSFER_TASK_SWITCH, NULL); if (ret != X86EMUL_CONTINUE) return ret; ret = __load_segment_descriptor(ctxt, tss->fs, VCPU_SREG_FS, cpl, X86_TRANSFER_TASK_SWITCH, NULL); if (ret != X86EMUL_CONTINUE) return ret; ret = __load_segment_descriptor(ctxt, tss->gs, VCPU_SREG_GS, cpl, X86_TRANSFER_TASK_SWITCH, NULL); return ret; } static int task_switch_32(struct x86_emulate_ctxt *ctxt, u16 tss_selector, u16 old_tss_sel, ulong old_tss_base, struct desc_struct *new_desc) { struct tss_segment_32 tss_seg; int ret; u32 new_tss_base = get_desc_base(new_desc); u32 eip_offset = offsetof(struct tss_segment_32, eip); u32 ldt_sel_offset = offsetof(struct tss_segment_32, ldt_selector); ret = linear_read_system(ctxt, old_tss_base, &tss_seg, sizeof tss_seg); if (ret != X86EMUL_CONTINUE) return ret; save_state_to_tss32(ctxt, &tss_seg); /* Only GP registers and segment selectors are saved */ ret = linear_write_system(ctxt, old_tss_base + eip_offset, &tss_seg.eip, ldt_sel_offset - eip_offset); if (ret != X86EMUL_CONTINUE) return ret; ret = linear_read_system(ctxt, new_tss_base, &tss_seg, sizeof tss_seg); if (ret != X86EMUL_CONTINUE) return ret; if (old_tss_sel != 0xffff) { tss_seg.prev_task_link = old_tss_sel; ret = linear_write_system(ctxt, new_tss_base, &tss_seg.prev_task_link, sizeof tss_seg.prev_task_link); if (ret != X86EMUL_CONTINUE) return ret; } return load_state_from_tss32(ctxt, &tss_seg); } static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt, u16 tss_selector, int idt_index, int reason, bool has_error_code, u32 error_code) { const struct x86_emulate_ops *ops = ctxt->ops; struct desc_struct curr_tss_desc, next_tss_desc; int ret; u16 old_tss_sel = get_segment_selector(ctxt, VCPU_SREG_TR); ulong old_tss_base = ops->get_cached_segment_base(ctxt, VCPU_SREG_TR); u32 desc_limit; ulong desc_addr, dr7; /* FIXME: old_tss_base == ~0 ? */ ret = read_segment_descriptor(ctxt, tss_selector, &next_tss_desc, &desc_addr); if (ret != X86EMUL_CONTINUE) return ret; ret = read_segment_descriptor(ctxt, old_tss_sel, &curr_tss_desc, &desc_addr); if (ret != X86EMUL_CONTINUE) return ret; /* FIXME: check that next_tss_desc is tss */ /* * Check privileges. The three cases are task switch caused by... * * 1. jmp/call/int to task gate: Check against DPL of the task gate * 2. Exception/IRQ/iret: No check is performed * 3. jmp/call to TSS/task-gate: No check is performed since the * hardware checks it before exiting. */ if (reason == TASK_SWITCH_GATE) { if (idt_index != -1) { /* Software interrupts */ struct desc_struct task_gate_desc; int dpl; ret = read_interrupt_descriptor(ctxt, idt_index, &task_gate_desc); if (ret != X86EMUL_CONTINUE) return ret; dpl = task_gate_desc.dpl; if ((tss_selector & 3) > dpl || ops->cpl(ctxt) > dpl) return emulate_gp(ctxt, (idt_index << 3) | 0x2); } } desc_limit = desc_limit_scaled(&next_tss_desc); if (!next_tss_desc.p || ((desc_limit < 0x67 && (next_tss_desc.type & 8)) || desc_limit < 0x2b)) { return emulate_ts(ctxt, tss_selector & 0xfffc); } if (reason == TASK_SWITCH_IRET || reason == TASK_SWITCH_JMP) { curr_tss_desc.type &= ~(1 << 1); /* clear busy flag */ write_segment_descriptor(ctxt, old_tss_sel, &curr_tss_desc); } if (reason == TASK_SWITCH_IRET) ctxt->eflags = ctxt->eflags & ~X86_EFLAGS_NT; /* set back link to prev task only if NT bit is set in eflags note that old_tss_sel is not used after this point */ if (reason != TASK_SWITCH_CALL && reason != TASK_SWITCH_GATE) old_tss_sel = 0xffff; if (next_tss_desc.type & 8) ret = task_switch_32(ctxt, tss_selector, old_tss_sel, old_tss_base, &next_tss_desc); else ret = task_switch_16(ctxt, tss_selector, old_tss_sel, old_tss_base, &next_tss_desc); if (ret != X86EMUL_CONTINUE) return ret; if (reason == TASK_SWITCH_CALL || reason == TASK_SWITCH_GATE) ctxt->eflags = ctxt->eflags | X86_EFLAGS_NT; if (reason != TASK_SWITCH_IRET) { next_tss_desc.type |= (1 << 1); /* set busy flag */ write_segment_descriptor(ctxt, tss_selector, &next_tss_desc); } ops->set_cr(ctxt, 0, ops->get_cr(ctxt, 0) | X86_CR0_TS); ops->set_segment(ctxt, tss_selector, &next_tss_desc, 0, VCPU_SREG_TR); if (has_error_code) { ctxt->op_bytes = ctxt->ad_bytes = (next_tss_desc.type & 8) ? 4 : 2; ctxt->lock_prefix = 0; ctxt->src.val = (unsigned long) error_code; ret = em_push(ctxt); } ops->get_dr(ctxt, 7, &dr7); ops->set_dr(ctxt, 7, dr7 & ~(DR_LOCAL_ENABLE_MASK | DR_LOCAL_SLOWDOWN)); return ret; } int emulator_task_switch(struct x86_emulate_ctxt *ctxt, u16 tss_selector, int idt_index, int reason, bool has_error_code, u32 error_code) { int rc; invalidate_registers(ctxt); ctxt->_eip = ctxt->eip; ctxt->dst.type = OP_NONE; rc = emulator_do_task_switch(ctxt, tss_selector, idt_index, reason, has_error_code, error_code); if (rc == X86EMUL_CONTINUE) { ctxt->eip = ctxt->_eip; writeback_registers(ctxt); } return (rc == X86EMUL_UNHANDLEABLE) ? EMULATION_FAILED : EMULATION_OK; } static void string_addr_inc(struct x86_emulate_ctxt *ctxt, int reg, struct operand *op) { int df = (ctxt->eflags & X86_EFLAGS_DF) ? -op->count : op->count; register_address_increment(ctxt, reg, df * op->bytes); op->addr.mem.ea = register_address(ctxt, reg); } static int em_das(struct x86_emulate_ctxt *ctxt) { u8 al, old_al; bool af, cf, old_cf; cf = ctxt->eflags & X86_EFLAGS_CF; al = ctxt->dst.val; old_al = al; old_cf = cf; cf = false; af = ctxt->eflags & X86_EFLAGS_AF; if ((al & 0x0f) > 9 || af) { al -= 6; cf = old_cf | (al >= 250); af = true; } else { af = false; } if (old_al > 0x99 || old_cf) { al -= 0x60; cf = true; } ctxt->dst.val = al; /* Set PF, ZF, SF */ ctxt->src.type = OP_IMM; ctxt->src.val = 0; ctxt->src.bytes = 1; fastop(ctxt, em_or); ctxt->eflags &= ~(X86_EFLAGS_AF | X86_EFLAGS_CF); if (cf) ctxt->eflags |= X86_EFLAGS_CF; if (af) ctxt->eflags |= X86_EFLAGS_AF; return X86EMUL_CONTINUE; } static int em_aam(struct x86_emulate_ctxt *ctxt) { u8 al, ah; if (ctxt->src.val == 0) return emulate_de(ctxt); al = ctxt->dst.val & 0xff; ah = al / ctxt->src.val; al %= ctxt->src.val; ctxt->dst.val = (ctxt->dst.val & 0xffff0000) | al | (ah << 8); /* Set PF, ZF, SF */ ctxt->src.type = OP_IMM; ctxt->src.val = 0; ctxt->src.bytes = 1; fastop(ctxt, em_or); return X86EMUL_CONTINUE; } static int em_aad(struct x86_emulate_ctxt *ctxt) { u8 al = ctxt->dst.val & 0xff; u8 ah = (ctxt->dst.val >> 8) & 0xff; al = (al + (ah * ctxt->src.val)) & 0xff; ctxt->dst.val = (ctxt->dst.val & 0xffff0000) | al; /* Set PF, ZF, SF */ ctxt->src.type = OP_IMM; ctxt->src.val = 0; ctxt->src.bytes = 1; fastop(ctxt, em_or); return X86EMUL_CONTINUE; } static int em_call(struct x86_emulate_ctxt *ctxt) { int rc; long rel = ctxt->src.val; ctxt->src.val = (unsigned long)ctxt->_eip; rc = jmp_rel(ctxt, rel); if (rc != X86EMUL_CONTINUE) return rc; return em_push(ctxt); } static int em_call_far(struct x86_emulate_ctxt *ctxt) { u16 sel, old_cs; ulong old_eip; int rc; struct desc_struct old_desc, new_desc; const struct x86_emulate_ops *ops = ctxt->ops; int cpl = ctxt->ops->cpl(ctxt); enum x86emul_mode prev_mode = ctxt->mode; old_eip = ctxt->_eip; ops->get_segment(ctxt, &old_cs, &old_desc, NULL, VCPU_SREG_CS); memcpy(&sel, ctxt->src.valptr + ctxt->op_bytes, 2); rc = __load_segment_descriptor(ctxt, sel, VCPU_SREG_CS, cpl, X86_TRANSFER_CALL_JMP, &new_desc); if (rc != X86EMUL_CONTINUE) return rc; rc = assign_eip_far(ctxt, ctxt->src.val); if (rc != X86EMUL_CONTINUE) goto fail; ctxt->src.val = old_cs; rc = em_push(ctxt); if (rc != X86EMUL_CONTINUE) goto fail; ctxt->src.val = old_eip; rc = em_push(ctxt); /* If we failed, we tainted the memory, but the very least we should restore cs */ if (rc != X86EMUL_CONTINUE) { pr_warn_once("faulting far call emulation tainted memory\n"); goto fail; } return rc; fail: ops->set_segment(ctxt, old_cs, &old_desc, 0, VCPU_SREG_CS); ctxt->mode = prev_mode; return rc; } static int em_ret_near_imm(struct x86_emulate_ctxt *ctxt) { int rc; unsigned long eip; rc = emulate_pop(ctxt, &eip, ctxt->op_bytes); if (rc != X86EMUL_CONTINUE) return rc; rc = assign_eip_near(ctxt, eip); if (rc != X86EMUL_CONTINUE) return rc; rsp_increment(ctxt, ctxt->src.val); return X86EMUL_CONTINUE; } static int em_xchg(struct x86_emulate_ctxt *ctxt) { /* Write back the register source. */ ctxt->src.val = ctxt->dst.val; write_register_operand(&ctxt->src); /* Write back the memory destination with implicit LOCK prefix. */ ctxt->dst.val = ctxt->src.orig_val; ctxt->lock_prefix = 1; return X86EMUL_CONTINUE; } static int em_imul_3op(struct x86_emulate_ctxt *ctxt) { ctxt->dst.val = ctxt->src2.val; return fastop(ctxt, em_imul); } static int em_cwd(struct x86_emulate_ctxt *ctxt) { ctxt->dst.type = OP_REG; ctxt->dst.bytes = ctxt->src.bytes; ctxt->dst.addr.reg = reg_rmw(ctxt, VCPU_REGS_RDX); ctxt->dst.val = ~((ctxt->src.val >> (ctxt->src.bytes * 8 - 1)) - 1); return X86EMUL_CONTINUE; } static int em_rdpid(struct x86_emulate_ctxt *ctxt) { u64 tsc_aux = 0; if (ctxt->ops->get_msr(ctxt, MSR_TSC_AUX, &tsc_aux)) return emulate_ud(ctxt); ctxt->dst.val = tsc_aux; return X86EMUL_CONTINUE; } static int em_rdtsc(struct x86_emulate_ctxt *ctxt) { u64 tsc = 0; ctxt->ops->get_msr(ctxt, MSR_IA32_TSC, &tsc); *reg_write(ctxt, VCPU_REGS_RAX) = (u32)tsc; *reg_write(ctxt, VCPU_REGS_RDX) = tsc >> 32; return X86EMUL_CONTINUE; } static int em_rdpmc(struct x86_emulate_ctxt *ctxt) { u64 pmc; if (ctxt->ops->read_pmc(ctxt, reg_read(ctxt, VCPU_REGS_RCX), &pmc)) return emulate_gp(ctxt, 0); *reg_write(ctxt, VCPU_REGS_RAX) = (u32)pmc; *reg_write(ctxt, VCPU_REGS_RDX) = pmc >> 32; return X86EMUL_CONTINUE; } static int em_mov(struct x86_emulate_ctxt *ctxt) { memcpy(ctxt->dst.valptr, ctxt->src.valptr, sizeof(ctxt->src.valptr)); return X86EMUL_CONTINUE; } #define FFL(x) bit(X86_FEATURE_##x) static int em_movbe(struct x86_emulate_ctxt *ctxt) { u32 ebx, ecx, edx, eax = 1; u16 tmp; /* * Check MOVBE is set in the guest-visible CPUID leaf. */ ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false); if (!(ecx & FFL(MOVBE))) return emulate_ud(ctxt); switch (ctxt->op_bytes) { case 2: /* * From MOVBE definition: "...When the operand size is 16 bits, * the upper word of the destination register remains unchanged * ..." * * Both casting ->valptr and ->val to u16 breaks strict aliasing * rules so we have to do the operation almost per hand. */ tmp = (u16)ctxt->src.val; ctxt->dst.val &= ~0xffffUL; ctxt->dst.val |= (unsigned long)swab16(tmp); break; case 4: ctxt->dst.val = swab32((u32)ctxt->src.val); break; case 8: ctxt->dst.val = swab64(ctxt->src.val); break; default: BUG(); } return X86EMUL_CONTINUE; } static int em_cr_write(struct x86_emulate_ctxt *ctxt) { int cr_num = ctxt->modrm_reg; int r; if (ctxt->ops->set_cr(ctxt, cr_num, ctxt->src.val)) return emulate_gp(ctxt, 0); /* Disable writeback. */ ctxt->dst.type = OP_NONE; if (cr_num == 0) { /* * CR0 write might have updated CR0.PE and/or CR0.PG * which can affect the cpu's execution mode. */ r = emulator_recalc_and_set_mode(ctxt); if (r != X86EMUL_CONTINUE) return r; } return X86EMUL_CONTINUE; } static int em_dr_write(struct x86_emulate_ctxt *ctxt) { unsigned long val; if (ctxt->mode == X86EMUL_MODE_PROT64) val = ctxt->src.val & ~0ULL; else val = ctxt->src.val & ~0U; /* #UD condition is already handled. */ if (ctxt->ops->set_dr(ctxt, ctxt->modrm_reg, val) < 0) return emulate_gp(ctxt, 0); /* Disable writeback. */ ctxt->dst.type = OP_NONE; return X86EMUL_CONTINUE; } static int em_wrmsr(struct x86_emulate_ctxt *ctxt) { u64 msr_data; msr_data = (u32)reg_read(ctxt, VCPU_REGS_RAX) | ((u64)reg_read(ctxt, VCPU_REGS_RDX) << 32); if (ctxt->ops->set_msr(ctxt, reg_read(ctxt, VCPU_REGS_RCX), msr_data)) return emulate_gp(ctxt, 0); return X86EMUL_CONTINUE; } static int em_rdmsr(struct x86_emulate_ctxt *ctxt) { u64 msr_data; if (ctxt->ops->get_msr(ctxt, reg_read(ctxt, VCPU_REGS_RCX), &msr_data)) return emulate_gp(ctxt, 0); *reg_write(ctxt, VCPU_REGS_RAX) = (u32)msr_data; *reg_write(ctxt, VCPU_REGS_RDX) = msr_data >> 32; return X86EMUL_CONTINUE; } static int em_mov_rm_sreg(struct x86_emulate_ctxt *ctxt) { if (ctxt->modrm_reg > VCPU_SREG_GS) return emulate_ud(ctxt); ctxt->dst.val = get_segment_selector(ctxt, ctxt->modrm_reg); if (ctxt->dst.bytes == 4 && ctxt->dst.type == OP_MEM) ctxt->dst.bytes = 2; return X86EMUL_CONTINUE; } static int em_mov_sreg_rm(struct x86_emulate_ctxt *ctxt) { u16 sel = ctxt->src.val; if (ctxt->modrm_reg == VCPU_SREG_CS || ctxt->modrm_reg > VCPU_SREG_GS) return emulate_ud(ctxt); if (ctxt->modrm_reg == VCPU_SREG_SS) ctxt->interruptibility = KVM_X86_SHADOW_INT_MOV_SS; /* Disable writeback. */ ctxt->dst.type = OP_NONE; return load_segment_descriptor(ctxt, sel, ctxt->modrm_reg); } static int em_lldt(struct x86_emulate_ctxt *ctxt) { u16 sel = ctxt->src.val; /* Disable writeback. */ ctxt->dst.type = OP_NONE; return load_segment_descriptor(ctxt, sel, VCPU_SREG_LDTR); } static int em_ltr(struct x86_emulate_ctxt *ctxt) { u16 sel = ctxt->src.val; /* Disable writeback. */ ctxt->dst.type = OP_NONE; return load_segment_descriptor(ctxt, sel, VCPU_SREG_TR); } static int em_invlpg(struct x86_emulate_ctxt *ctxt) { int rc; ulong linear; rc = linearize(ctxt, ctxt->src.addr.mem, 1, false, &linear); if (rc == X86EMUL_CONTINUE) ctxt->ops->invlpg(ctxt, linear); /* Disable writeback. */ ctxt->dst.type = OP_NONE; return X86EMUL_CONTINUE; } static int em_clts(struct x86_emulate_ctxt *ctxt) { ulong cr0; cr0 = ctxt->ops->get_cr(ctxt, 0); cr0 &= ~X86_CR0_TS; ctxt->ops->set_cr(ctxt, 0, cr0); return X86EMUL_CONTINUE; } static int em_hypercall(struct x86_emulate_ctxt *ctxt) { int rc = ctxt->ops->fix_hypercall(ctxt); if (rc != X86EMUL_CONTINUE) return rc; /* Let the processor re-execute the fixed hypercall */ ctxt->_eip = ctxt->eip; /* Disable writeback. */ ctxt->dst.type = OP_NONE; return X86EMUL_CONTINUE; } static int emulate_store_desc_ptr(struct x86_emulate_ctxt *ctxt, void (*get)(struct x86_emulate_ctxt *ctxt, struct desc_ptr *ptr)) { struct desc_ptr desc_ptr; if (ctxt->mode == X86EMUL_MODE_PROT64) ctxt->op_bytes = 8; get(ctxt, &desc_ptr); if (ctxt->op_bytes == 2) { ctxt->op_bytes = 4; desc_ptr.address &= 0x00ffffff; } /* Disable writeback. */ ctxt->dst.type = OP_NONE; return segmented_write_std(ctxt, ctxt->dst.addr.mem, &desc_ptr, 2 + ctxt->op_bytes); } static int em_sgdt(struct x86_emulate_ctxt *ctxt) { return emulate_store_desc_ptr(ctxt, ctxt->ops->get_gdt); } static int em_sidt(struct x86_emulate_ctxt *ctxt) { return emulate_store_desc_ptr(ctxt, ctxt->ops->get_idt); } static int em_lgdt_lidt(struct x86_emulate_ctxt *ctxt, bool lgdt) { struct desc_ptr desc_ptr; int rc; if (ctxt->mode == X86EMUL_MODE_PROT64) ctxt->op_bytes = 8; rc = read_descriptor(ctxt, ctxt->src.addr.mem, &desc_ptr.size, &desc_ptr.address, ctxt->op_bytes); if (rc != X86EMUL_CONTINUE) return rc; if (ctxt->mode == X86EMUL_MODE_PROT64 && emul_is_noncanonical_address(desc_ptr.address, ctxt)) return emulate_gp(ctxt, 0); if (lgdt) ctxt->ops->set_gdt(ctxt, &desc_ptr); else ctxt->ops->set_idt(ctxt, &desc_ptr); /* Disable writeback. */ ctxt->dst.type = OP_NONE; return X86EMUL_CONTINUE; } static int em_lgdt(struct x86_emulate_ctxt *ctxt) { return em_lgdt_lidt(ctxt, true); } static int em_lidt(struct x86_emulate_ctxt *ctxt) { return em_lgdt_lidt(ctxt, false); } static int em_smsw(struct x86_emulate_ctxt *ctxt) { if (ctxt->dst.type == OP_MEM) ctxt->dst.bytes = 2; ctxt->dst.val = ctxt->ops->get_cr(ctxt, 0); return X86EMUL_CONTINUE; } static int em_lmsw(struct x86_emulate_ctxt *ctxt) { ctxt->ops->set_cr(ctxt, 0, (ctxt->ops->get_cr(ctxt, 0) & ~0x0eul) | (ctxt->src.val & 0x0f)); ctxt->dst.type = OP_NONE; return X86EMUL_CONTINUE; } static int em_loop(struct x86_emulate_ctxt *ctxt) { int rc = X86EMUL_CONTINUE; register_address_increment(ctxt, VCPU_REGS_RCX, -1); if ((address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) != 0) && (ctxt->b == 0xe2 || test_cc(ctxt->b ^ 0x5, ctxt->eflags))) rc = jmp_rel(ctxt, ctxt->src.val); return rc; } static int em_jcxz(struct x86_emulate_ctxt *ctxt) { int rc = X86EMUL_CONTINUE; if (address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) == 0) rc = jmp_rel(ctxt, ctxt->src.val); return rc; } static int em_in(struct x86_emulate_ctxt *ctxt) { if (!pio_in_emulated(ctxt, ctxt->dst.bytes, ctxt->src.val, &ctxt->dst.val)) return X86EMUL_IO_NEEDED; return X86EMUL_CONTINUE; } static int em_out(struct x86_emulate_ctxt *ctxt) { ctxt->ops->pio_out_emulated(ctxt, ctxt->src.bytes, ctxt->dst.val, &ctxt->src.val, 1); /* Disable writeback. */ ctxt->dst.type = OP_NONE; return X86EMUL_CONTINUE; } static int em_cli(struct x86_emulate_ctxt *ctxt) { if (emulator_bad_iopl(ctxt)) return emulate_gp(ctxt, 0); ctxt->eflags &= ~X86_EFLAGS_IF; return X86EMUL_CONTINUE; } static int em_sti(struct x86_emulate_ctxt *ctxt) { if (emulator_bad_iopl(ctxt)) return emulate_gp(ctxt, 0); ctxt->interruptibility = KVM_X86_SHADOW_INT_STI; ctxt->eflags |= X86_EFLAGS_IF; return X86EMUL_CONTINUE; } static int em_cpuid(struct x86_emulate_ctxt *ctxt) { u32 eax, ebx, ecx, edx; u64 msr = 0; ctxt->ops->get_msr(ctxt, MSR_MISC_FEATURES_ENABLES, &msr); if (msr & MSR_MISC_FEATURES_ENABLES_CPUID_FAULT && ctxt->ops->cpl(ctxt)) { return emulate_gp(ctxt, 0); } eax = reg_read(ctxt, VCPU_REGS_RAX); ecx = reg_read(ctxt, VCPU_REGS_RCX); ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, true); *reg_write(ctxt, VCPU_REGS_RAX) = eax; *reg_write(ctxt, VCPU_REGS_RBX) = ebx; *reg_write(ctxt, VCPU_REGS_RCX) = ecx; *reg_write(ctxt, VCPU_REGS_RDX) = edx; return X86EMUL_CONTINUE; } static int em_sahf(struct x86_emulate_ctxt *ctxt) { u32 flags; flags = X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF | X86_EFLAGS_ZF | X86_EFLAGS_SF; flags &= *reg_rmw(ctxt, VCPU_REGS_RAX) >> 8; ctxt->eflags &= ~0xffUL; ctxt->eflags |= flags | X86_EFLAGS_FIXED; return X86EMUL_CONTINUE; } static int em_lahf(struct x86_emulate_ctxt *ctxt) { *reg_rmw(ctxt, VCPU_REGS_RAX) &= ~0xff00UL; *reg_rmw(ctxt, VCPU_REGS_RAX) |= (ctxt->eflags & 0xff) << 8; return X86EMUL_CONTINUE; } static int em_bswap(struct x86_emulate_ctxt *ctxt) { switch (ctxt->op_bytes) { #ifdef CONFIG_X86_64 case 8: asm("bswap %0" : "+r"(ctxt->dst.val)); break; #endif default: asm("bswap %0" : "+r"(*(u32 *)&ctxt->dst.val)); break; } return X86EMUL_CONTINUE; } static int em_clflush(struct x86_emulate_ctxt *ctxt) { /* emulating clflush regardless of cpuid */ return X86EMUL_CONTINUE; } static int em_clflushopt(struct x86_emulate_ctxt *ctxt) { /* emulating clflushopt regardless of cpuid */ return X86EMUL_CONTINUE; } static int em_movsxd(struct x86_emulate_ctxt *ctxt) { ctxt->dst.val = (s32) ctxt->src.val; return X86EMUL_CONTINUE; } static int check_fxsr(struct x86_emulate_ctxt *ctxt) { u32 eax = 1, ebx, ecx = 0, edx; ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false); if (!(edx & FFL(FXSR))) return emulate_ud(ctxt); if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) return emulate_nm(ctxt); /* * Don't emulate a case that should never be hit, instead of working * around a lack of fxsave64/fxrstor64 on old compilers. */ if (ctxt->mode >= X86EMUL_MODE_PROT64) return X86EMUL_UNHANDLEABLE; return X86EMUL_CONTINUE; } /* * Hardware doesn't save and restore XMM 0-7 without CR4.OSFXSR, but does save * and restore MXCSR. */ static size_t __fxstate_size(int nregs) { return offsetof(struct fxregs_state, xmm_space[0]) + nregs * 16; } static inline size_t fxstate_size(struct x86_emulate_ctxt *ctxt) { bool cr4_osfxsr; if (ctxt->mode == X86EMUL_MODE_PROT64) return __fxstate_size(16); cr4_osfxsr = ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR; return __fxstate_size(cr4_osfxsr ? 8 : 0); } /* * FXSAVE and FXRSTOR have 4 different formats depending on execution mode, * 1) 16 bit mode * 2) 32 bit mode * - like (1), but FIP and FDP (foo) are only 16 bit. At least Intel CPUs * preserve whole 32 bit values, though, so (1) and (2) are the same wrt. * save and restore * 3) 64-bit mode with REX.W prefix * - like (2), but XMM 8-15 are being saved and restored * 4) 64-bit mode without REX.W prefix * - like (3), but FIP and FDP are 64 bit * * Emulation uses (3) for (1) and (2) and preserves XMM 8-15 to reach the * desired result. (4) is not emulated. * * Note: Guest and host CPUID.(EAX=07H,ECX=0H):EBX[bit 13] (deprecate FPU CS * and FPU DS) should match. */ static int em_fxsave(struct x86_emulate_ctxt *ctxt) { struct fxregs_state fx_state; int rc; rc = check_fxsr(ctxt); if (rc != X86EMUL_CONTINUE) return rc; ctxt->ops->get_fpu(ctxt); rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state)); ctxt->ops->put_fpu(ctxt); if (rc != X86EMUL_CONTINUE) return rc; return segmented_write_std(ctxt, ctxt->memop.addr.mem, &fx_state, fxstate_size(ctxt)); } /* * FXRSTOR might restore XMM registers not provided by the guest. Fill * in the host registers (via FXSAVE) instead, so they won't be modified. * (preemption has to stay disabled until FXRSTOR). * * Use noinline to keep the stack for other functions called by callers small. */ static noinline int fxregs_fixup(struct fxregs_state *fx_state, const size_t used_size) { struct fxregs_state fx_tmp; int rc; rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_tmp)); memcpy((void *)fx_state + used_size, (void *)&fx_tmp + used_size, __fxstate_size(16) - used_size); return rc; } static int em_fxrstor(struct x86_emulate_ctxt *ctxt) { struct fxregs_state fx_state; int rc; size_t size; rc = check_fxsr(ctxt); if (rc != X86EMUL_CONTINUE) return rc; size = fxstate_size(ctxt); rc = segmented_read_std(ctxt, ctxt->memop.addr.mem, &fx_state, size); if (rc != X86EMUL_CONTINUE) return rc; ctxt->ops->get_fpu(ctxt); if (size < __fxstate_size(16)) { rc = fxregs_fixup(&fx_state, size); if (rc != X86EMUL_CONTINUE) goto out; } if (fx_state.mxcsr >> 16) { rc = emulate_gp(ctxt, 0); goto out; } if (rc == X86EMUL_CONTINUE) rc = asm_safe("fxrstor %[fx]", : [fx] "m"(fx_state)); out: ctxt->ops->put_fpu(ctxt); return rc; } static bool valid_cr(int nr) { switch (nr) { case 0: case 2 ... 4: case 8: return true; default: return false; } } static int check_cr_read(struct x86_emulate_ctxt *ctxt) { if (!valid_cr(ctxt->modrm_reg)) return emulate_ud(ctxt); return X86EMUL_CONTINUE; } static int check_cr_write(struct x86_emulate_ctxt *ctxt) { u64 new_val = ctxt->src.val64; int cr = ctxt->modrm_reg; u64 efer = 0; static u64 cr_reserved_bits[] = { 0xffffffff00000000ULL, 0, 0, 0, /* CR3 checked later */ CR4_RESERVED_BITS, 0, 0, 0, CR8_RESERVED_BITS, }; if (!valid_cr(cr)) return emulate_ud(ctxt); if (new_val & cr_reserved_bits[cr]) return emulate_gp(ctxt, 0); switch (cr) { case 0: { u64 cr4; if (((new_val & X86_CR0_PG) && !(new_val & X86_CR0_PE)) || ((new_val & X86_CR0_NW) && !(new_val & X86_CR0_CD))) return emulate_gp(ctxt, 0); cr4 = ctxt->ops->get_cr(ctxt, 4); ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); if ((new_val & X86_CR0_PG) && (efer & EFER_LME) && !(cr4 & X86_CR4_PAE)) return emulate_gp(ctxt, 0); break; } case 3: { u64 rsvd = 0; ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); if (efer & EFER_LMA) { u64 maxphyaddr; u32 eax, ebx, ecx, edx; eax = 0x80000008; ecx = 0; if (ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false)) maxphyaddr = eax & 0xff; else maxphyaddr = 36; rsvd = rsvd_bits(maxphyaddr, 63); if (ctxt->ops->get_cr(ctxt, 4) & X86_CR4_PCIDE) rsvd &= ~CR3_PCID_INVD; } if (new_val & rsvd) return emulate_gp(ctxt, 0); break; } case 4: { ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); if ((efer & EFER_LMA) && !(new_val & X86_CR4_PAE)) return emulate_gp(ctxt, 0); break; } } return X86EMUL_CONTINUE; } static int check_dr7_gd(struct x86_emulate_ctxt *ctxt) { unsigned long dr7; ctxt->ops->get_dr(ctxt, 7, &dr7); /* Check if DR7.Global_Enable is set */ return dr7 & (1 << 13); } static int check_dr_read(struct x86_emulate_ctxt *ctxt) { int dr = ctxt->modrm_reg; u64 cr4; if (dr > 7) return emulate_ud(ctxt); cr4 = ctxt->ops->get_cr(ctxt, 4); if ((cr4 & X86_CR4_DE) && (dr == 4 || dr == 5)) return emulate_ud(ctxt); if (check_dr7_gd(ctxt)) { ulong dr6; ctxt->ops->get_dr(ctxt, 6, &dr6); dr6 &= ~15; dr6 |= DR6_BD | DR6_RTM; ctxt->ops->set_dr(ctxt, 6, dr6); return emulate_db(ctxt); } return X86EMUL_CONTINUE; } static int check_dr_write(struct x86_emulate_ctxt *ctxt) { u64 new_val = ctxt->src.val64; int dr = ctxt->modrm_reg; if ((dr == 6 || dr == 7) && (new_val & 0xffffffff00000000ULL)) return emulate_gp(ctxt, 0); return check_dr_read(ctxt); } static int check_svme(struct x86_emulate_ctxt *ctxt) { u64 efer = 0; ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); if (!(efer & EFER_SVME)) return emulate_ud(ctxt); return X86EMUL_CONTINUE; } static int check_svme_pa(struct x86_emulate_ctxt *ctxt) { u64 rax = reg_read(ctxt, VCPU_REGS_RAX); /* Valid physical address? */ if (rax & 0xffff000000000000ULL) return emulate_gp(ctxt, 0); return check_svme(ctxt); } static int check_rdtsc(struct x86_emulate_ctxt *ctxt) { u64 cr4 = ctxt->ops->get_cr(ctxt, 4); if (cr4 & X86_CR4_TSD && ctxt->ops->cpl(ctxt)) return emulate_ud(ctxt); return X86EMUL_CONTINUE; } static int check_rdpmc(struct x86_emulate_ctxt *ctxt) { u64 cr4 = ctxt->ops->get_cr(ctxt, 4); u64 rcx = reg_read(ctxt, VCPU_REGS_RCX); if ((!(cr4 & X86_CR4_PCE) && ctxt->ops->cpl(ctxt)) || ctxt->ops->check_pmc(ctxt, rcx)) return emulate_gp(ctxt, 0); return X86EMUL_CONTINUE; } static int check_perm_in(struct x86_emulate_ctxt *ctxt) { ctxt->dst.bytes = min(ctxt->dst.bytes, 4u); if (!emulator_io_permited(ctxt, ctxt->src.val, ctxt->dst.bytes)) return emulate_gp(ctxt, 0); return X86EMUL_CONTINUE; } static int check_perm_out(struct x86_emulate_ctxt *ctxt) { ctxt->src.bytes = min(ctxt->src.bytes, 4u); if (!emulator_io_permited(ctxt, ctxt->dst.val, ctxt->src.bytes)) return emulate_gp(ctxt, 0); return X86EMUL_CONTINUE; } #define D(_y) { .flags = (_y) } #define DI(_y, _i) { .flags = (_y)|Intercept, .intercept = x86_intercept_##_i } #define DIP(_y, _i, _p) { .flags = (_y)|Intercept|CheckPerm, \ .intercept = x86_intercept_##_i, .check_perm = (_p) } #define N D(NotImpl) #define EXT(_f, _e) { .flags = ((_f) | RMExt), .u.group = (_e) } #define G(_f, _g) { .flags = ((_f) | Group | ModRM), .u.group = (_g) } #define GD(_f, _g) { .flags = ((_f) | GroupDual | ModRM), .u.gdual = (_g) } #define ID(_f, _i) { .flags = ((_f) | InstrDual | ModRM), .u.idual = (_i) } #define MD(_f, _m) { .flags = ((_f) | ModeDual), .u.mdual = (_m) } #define E(_f, _e) { .flags = ((_f) | Escape | ModRM), .u.esc = (_e) } #define I(_f, _e) { .flags = (_f), .u.execute = (_e) } #define F(_f, _e) { .flags = (_f) | Fastop, .u.fastop = (_e) } #define II(_f, _e, _i) \ { .flags = (_f)|Intercept, .u.execute = (_e), .intercept = x86_intercept_##_i } #define IIP(_f, _e, _i, _p) \ { .flags = (_f)|Intercept|CheckPerm, .u.execute = (_e), \ .intercept = x86_intercept_##_i, .check_perm = (_p) } #define GP(_f, _g) { .flags = ((_f) | Prefix), .u.gprefix = (_g) } #define D2bv(_f) D((_f) | ByteOp), D(_f) #define D2bvIP(_f, _i, _p) DIP((_f) | ByteOp, _i, _p), DIP(_f, _i, _p) #define I2bv(_f, _e) I((_f) | ByteOp, _e), I(_f, _e) #define F2bv(_f, _e) F((_f) | ByteOp, _e), F(_f, _e) #define I2bvIP(_f, _e, _i, _p) \ IIP((_f) | ByteOp, _e, _i, _p), IIP(_f, _e, _i, _p) #define F6ALU(_f, _e) F2bv((_f) | DstMem | SrcReg | ModRM, _e), \ F2bv(((_f) | DstReg | SrcMem | ModRM) & ~Lock, _e), \ F2bv(((_f) & ~Lock) | DstAcc | SrcImm, _e) static const struct opcode group7_rm0[] = { N, I(SrcNone | Priv | EmulateOnUD, em_hypercall), N, N, N, N, N, N, }; static const struct opcode group7_rm1[] = { DI(SrcNone | Priv, monitor), DI(SrcNone | Priv, mwait), N, N, N, N, N, N, }; static const struct opcode group7_rm3[] = { DIP(SrcNone | Prot | Priv, vmrun, check_svme_pa), II(SrcNone | Prot | EmulateOnUD, em_hypercall, vmmcall), DIP(SrcNone | Prot | Priv, vmload, check_svme_pa), DIP(SrcNone | Prot | Priv, vmsave, check_svme_pa), DIP(SrcNone | Prot | Priv, stgi, check_svme), DIP(SrcNone | Prot | Priv, clgi, check_svme), DIP(SrcNone | Prot | Priv, skinit, check_svme), DIP(SrcNone | Prot | Priv, invlpga, check_svme), }; static const struct opcode group7_rm7[] = { N, DIP(SrcNone, rdtscp, check_rdtsc), N, N, N, N, N, N, }; static const struct opcode group1[] = { F(Lock, em_add), F(Lock | PageTable, em_or), F(Lock, em_adc), F(Lock, em_sbb), F(Lock | PageTable, em_and), F(Lock, em_sub), F(Lock, em_xor), F(NoWrite, em_cmp), }; static const struct opcode group1A[] = { I(DstMem | SrcNone | Mov | Stack | IncSP | TwoMemOp, em_pop), N, N, N, N, N, N, N, }; static const struct opcode group2[] = { F(DstMem | ModRM, em_rol), F(DstMem | ModRM, em_ror), F(DstMem | ModRM, em_rcl), F(DstMem | ModRM, em_rcr), F(DstMem | ModRM, em_shl), F(DstMem | ModRM, em_shr), F(DstMem | ModRM, em_shl), F(DstMem | ModRM, em_sar), }; static const struct opcode group3[] = { F(DstMem | SrcImm | NoWrite, em_test), F(DstMem | SrcImm | NoWrite, em_test), F(DstMem | SrcNone | Lock, em_not), F(DstMem | SrcNone | Lock, em_neg), F(DstXacc | Src2Mem, em_mul_ex), F(DstXacc | Src2Mem, em_imul_ex), F(DstXacc | Src2Mem, em_div_ex), F(DstXacc | Src2Mem, em_idiv_ex), }; static const struct opcode group4[] = { F(ByteOp | DstMem | SrcNone | Lock, em_inc), F(ByteOp | DstMem | SrcNone | Lock, em_dec), N, N, N, N, N, N, }; static const struct opcode group5[] = { F(DstMem | SrcNone | Lock, em_inc), F(DstMem | SrcNone | Lock, em_dec), I(SrcMem | NearBranch, em_call_near_abs), I(SrcMemFAddr | ImplicitOps, em_call_far), I(SrcMem | NearBranch, em_jmp_abs), I(SrcMemFAddr | ImplicitOps, em_jmp_far), I(SrcMem | Stack | TwoMemOp, em_push), D(Undefined), }; static const struct opcode group6[] = { DI(Prot | DstMem, sldt), DI(Prot | DstMem, str), II(Prot | Priv | SrcMem16, em_lldt, lldt), II(Prot | Priv | SrcMem16, em_ltr, ltr), N, N, N, N, }; static const struct group_dual group7 = { { II(Mov | DstMem, em_sgdt, sgdt), II(Mov | DstMem, em_sidt, sidt), II(SrcMem | Priv, em_lgdt, lgdt), II(SrcMem | Priv, em_lidt, lidt), II(SrcNone | DstMem | Mov, em_smsw, smsw), N, II(SrcMem16 | Mov | Priv, em_lmsw, lmsw), II(SrcMem | ByteOp | Priv | NoAccess, em_invlpg, invlpg), }, { EXT(0, group7_rm0), EXT(0, group7_rm1), N, EXT(0, group7_rm3), II(SrcNone | DstMem | Mov, em_smsw, smsw), N, II(SrcMem16 | Mov | Priv, em_lmsw, lmsw), EXT(0, group7_rm7), } }; static const struct opcode group8[] = { N, N, N, N, F(DstMem | SrcImmByte | NoWrite, em_bt), F(DstMem | SrcImmByte | Lock | PageTable, em_bts), F(DstMem | SrcImmByte | Lock, em_btr), F(DstMem | SrcImmByte | Lock | PageTable, em_btc), }; /* * The "memory" destination is actually always a register, since we come * from the register case of group9. */ static const struct gprefix pfx_0f_c7_7 = { N, N, N, II(DstMem | ModRM | Op3264 | EmulateOnUD, em_rdpid, rdtscp), }; static const struct group_dual group9 = { { N, I(DstMem64 | Lock | PageTable, em_cmpxchg8b), N, N, N, N, N, N, }, { N, N, N, N, N, N, N, GP(0, &pfx_0f_c7_7), } }; static const struct opcode group11[] = { I(DstMem | SrcImm | Mov | PageTable, em_mov), X7(D(Undefined)), }; static const struct gprefix pfx_0f_ae_7 = { I(SrcMem | ByteOp, em_clflush), I(SrcMem | ByteOp, em_clflushopt), N, N, }; static const struct group_dual group15 = { { I(ModRM | Aligned16, em_fxsave), I(ModRM | Aligned16, em_fxrstor), N, N, N, N, N, GP(0, &pfx_0f_ae_7), }, { N, N, N, N, N, N, N, N, } }; static const struct gprefix pfx_0f_6f_0f_7f = { I(Mmx, em_mov), I(Sse | Aligned, em_mov), N, I(Sse | Unaligned, em_mov), }; static const struct instr_dual instr_dual_0f_2b = { I(0, em_mov), N }; static const struct gprefix pfx_0f_2b = { ID(0, &instr_dual_0f_2b), ID(0, &instr_dual_0f_2b), N, N, }; static const struct gprefix pfx_0f_28_0f_29 = { I(Aligned, em_mov), I(Aligned, em_mov), N, N, }; static const struct gprefix pfx_0f_e7 = { N, I(Sse, em_mov), N, N, }; static const struct escape escape_d9 = { { N, N, N, N, N, N, N, I(DstMem16 | Mov, em_fnstcw), }, { /* 0xC0 - 0xC7 */ N, N, N, N, N, N, N, N, /* 0xC8 - 0xCF */ N, N, N, N, N, N, N, N, /* 0xD0 - 0xC7 */ N, N, N, N, N, N, N, N, /* 0xD8 - 0xDF */ N, N, N, N, N, N, N, N, /* 0xE0 - 0xE7 */ N, N, N, N, N, N, N, N, /* 0xE8 - 0xEF */ N, N, N, N, N, N, N, N, /* 0xF0 - 0xF7 */ N, N, N, N, N, N, N, N, /* 0xF8 - 0xFF */ N, N, N, N, N, N, N, N, } }; static const struct escape escape_db = { { N, N, N, N, N, N, N, N, }, { /* 0xC0 - 0xC7 */ N, N, N, N, N, N, N, N, /* 0xC8 - 0xCF */ N, N, N, N, N, N, N, N, /* 0xD0 - 0xC7 */ N, N, N, N, N, N, N, N, /* 0xD8 - 0xDF */ N, N, N, N, N, N, N, N, /* 0xE0 - 0xE7 */ N, N, N, I(ImplicitOps, em_fninit), N, N, N, N, /* 0xE8 - 0xEF */ N, N, N, N, N, N, N, N, /* 0xF0 - 0xF7 */ N, N, N, N, N, N, N, N, /* 0xF8 - 0xFF */ N, N, N, N, N, N, N, N, } }; static const struct escape escape_dd = { { N, N, N, N, N, N, N, I(DstMem16 | Mov, em_fnstsw), }, { /* 0xC0 - 0xC7 */ N, N, N, N, N, N, N, N, /* 0xC8 - 0xCF */ N, N, N, N, N, N, N, N, /* 0xD0 - 0xC7 */ N, N, N, N, N, N, N, N, /* 0xD8 - 0xDF */ N, N, N, N, N, N, N, N, /* 0xE0 - 0xE7 */ N, N, N, N, N, N, N, N, /* 0xE8 - 0xEF */ N, N, N, N, N, N, N, N, /* 0xF0 - 0xF7 */ N, N, N, N, N, N, N, N, /* 0xF8 - 0xFF */ N, N, N, N, N, N, N, N, } }; static const struct instr_dual instr_dual_0f_c3 = { I(DstMem | SrcReg | ModRM | No16 | Mov, em_mov), N }; static const struct mode_dual mode_dual_63 = { N, I(DstReg | SrcMem32 | ModRM | Mov, em_movsxd) }; static const struct opcode opcode_table[256] = { /* 0x00 - 0x07 */ F6ALU(Lock, em_add), I(ImplicitOps | Stack | No64 | Src2ES, em_push_sreg), I(ImplicitOps | Stack | No64 | Src2ES, em_pop_sreg), /* 0x08 - 0x0F */ F6ALU(Lock | PageTable, em_or), I(ImplicitOps | Stack | No64 | Src2CS, em_push_sreg), N, /* 0x10 - 0x17 */ F6ALU(Lock, em_adc), I(ImplicitOps | Stack | No64 | Src2SS, em_push_sreg), I(ImplicitOps | Stack | No64 | Src2SS, em_pop_sreg), /* 0x18 - 0x1F */ F6ALU(Lock, em_sbb), I(ImplicitOps | Stack | No64 | Src2DS, em_push_sreg), I(ImplicitOps | Stack | No64 | Src2DS, em_pop_sreg), /* 0x20 - 0x27 */ F6ALU(Lock | PageTable, em_and), N, N, /* 0x28 - 0x2F */ F6ALU(Lock, em_sub), N, I(ByteOp | DstAcc | No64, em_das), /* 0x30 - 0x37 */ F6ALU(Lock, em_xor), N, N, /* 0x38 - 0x3F */ F6ALU(NoWrite, em_cmp), N, N, /* 0x40 - 0x4F */ X8(F(DstReg, em_inc)), X8(F(DstReg, em_dec)), /* 0x50 - 0x57 */ X8(I(SrcReg | Stack, em_push)), /* 0x58 - 0x5F */ X8(I(DstReg | Stack, em_pop)), /* 0x60 - 0x67 */ I(ImplicitOps | Stack | No64, em_pusha), I(ImplicitOps | Stack | No64, em_popa), N, MD(ModRM, &mode_dual_63), N, N, N, N, /* 0x68 - 0x6F */ I(SrcImm | Mov | Stack, em_push), I(DstReg | SrcMem | ModRM | Src2Imm, em_imul_3op), I(SrcImmByte | Mov | Stack, em_push), I(DstReg | SrcMem | ModRM | Src2ImmByte, em_imul_3op), I2bvIP(DstDI | SrcDX | Mov | String | Unaligned, em_in, ins, check_perm_in), /* insb, insw/insd */ I2bvIP(SrcSI | DstDX | String, em_out, outs, check_perm_out), /* outsb, outsw/outsd */ /* 0x70 - 0x7F */ X16(D(SrcImmByte | NearBranch)), /* 0x80 - 0x87 */ G(ByteOp | DstMem | SrcImm, group1), G(DstMem | SrcImm, group1), G(ByteOp | DstMem | SrcImm | No64, group1), G(DstMem | SrcImmByte, group1), F2bv(DstMem | SrcReg | ModRM | NoWrite, em_test), I2bv(DstMem | SrcReg | ModRM | Lock | PageTable, em_xchg), /* 0x88 - 0x8F */ I2bv(DstMem | SrcReg | ModRM | Mov | PageTable, em_mov), I2bv(DstReg | SrcMem | ModRM | Mov, em_mov), I(DstMem | SrcNone | ModRM | Mov | PageTable, em_mov_rm_sreg), D(ModRM | SrcMem | NoAccess | DstReg), I(ImplicitOps | SrcMem16 | ModRM, em_mov_sreg_rm), G(0, group1A), /* 0x90 - 0x97 */ DI(SrcAcc | DstReg, pause), X7(D(SrcAcc | DstReg)), /* 0x98 - 0x9F */ D(DstAcc | SrcNone), I(ImplicitOps | SrcAcc, em_cwd), I(SrcImmFAddr | No64, em_call_far), N, II(ImplicitOps | Stack, em_pushf, pushf), II(ImplicitOps | Stack, em_popf, popf), I(ImplicitOps, em_sahf), I(ImplicitOps, em_lahf), /* 0xA0 - 0xA7 */ I2bv(DstAcc | SrcMem | Mov | MemAbs, em_mov), I2bv(DstMem | SrcAcc | Mov | MemAbs | PageTable, em_mov), I2bv(SrcSI | DstDI | Mov | String | TwoMemOp, em_mov), F2bv(SrcSI | DstDI | String | NoWrite | TwoMemOp, em_cmp_r), /* 0xA8 - 0xAF */ F2bv(DstAcc | SrcImm | NoWrite, em_test), I2bv(SrcAcc | DstDI | Mov | String, em_mov), I2bv(SrcSI | DstAcc | Mov | String, em_mov), F2bv(SrcAcc | DstDI | String | NoWrite, em_cmp_r), /* 0xB0 - 0xB7 */ X8(I(ByteOp | DstReg | SrcImm | Mov, em_mov)), /* 0xB8 - 0xBF */ X8(I(DstReg | SrcImm64 | Mov, em_mov)), /* 0xC0 - 0xC7 */ G(ByteOp | Src2ImmByte, group2), G(Src2ImmByte, group2), I(ImplicitOps | NearBranch | SrcImmU16, em_ret_near_imm), I(ImplicitOps | NearBranch, em_ret), I(DstReg | SrcMemFAddr | ModRM | No64 | Src2ES, em_lseg), I(DstReg | SrcMemFAddr | ModRM | No64 | Src2DS, em_lseg), G(ByteOp, group11), G(0, group11), /* 0xC8 - 0xCF */ I(Stack | SrcImmU16 | Src2ImmByte, em_enter), I(Stack, em_leave), I(ImplicitOps | SrcImmU16, em_ret_far_imm), I(ImplicitOps, em_ret_far), D(ImplicitOps), DI(SrcImmByte, intn), D(ImplicitOps | No64), II(ImplicitOps, em_iret, iret), /* 0xD0 - 0xD7 */ G(Src2One | ByteOp, group2), G(Src2One, group2), G(Src2CL | ByteOp, group2), G(Src2CL, group2), I(DstAcc | SrcImmUByte | No64, em_aam), I(DstAcc | SrcImmUByte | No64, em_aad), F(DstAcc | ByteOp | No64, em_salc), I(DstAcc | SrcXLat | ByteOp, em_mov), /* 0xD8 - 0xDF */ N, E(0, &escape_d9), N, E(0, &escape_db), N, E(0, &escape_dd), N, N, /* 0xE0 - 0xE7 */ X3(I(SrcImmByte | NearBranch, em_loop)), I(SrcImmByte | NearBranch, em_jcxz), I2bvIP(SrcImmUByte | DstAcc, em_in, in, check_perm_in), I2bvIP(SrcAcc | DstImmUByte, em_out, out, check_perm_out), /* 0xE8 - 0xEF */ I(SrcImm | NearBranch, em_call), D(SrcImm | ImplicitOps | NearBranch), I(SrcImmFAddr | No64, em_jmp_far), D(SrcImmByte | ImplicitOps | NearBranch), I2bvIP(SrcDX | DstAcc, em_in, in, check_perm_in), I2bvIP(SrcAcc | DstDX, em_out, out, check_perm_out), /* 0xF0 - 0xF7 */ N, DI(ImplicitOps, icebp), N, N, DI(ImplicitOps | Priv, hlt), D(ImplicitOps), G(ByteOp, group3), G(0, group3), /* 0xF8 - 0xFF */ D(ImplicitOps), D(ImplicitOps), I(ImplicitOps, em_cli), I(ImplicitOps, em_sti), D(ImplicitOps), D(ImplicitOps), G(0, group4), G(0, group5), }; static const struct opcode twobyte_table[256] = { /* 0x00 - 0x0F */ G(0, group6), GD(0, &group7), N, N, N, I(ImplicitOps | EmulateOnUD, em_syscall), II(ImplicitOps | Priv, em_clts, clts), N, DI(ImplicitOps | Priv, invd), DI(ImplicitOps | Priv, wbinvd), N, N, N, D(ImplicitOps | ModRM | SrcMem | NoAccess), N, N, /* 0x10 - 0x1F */ N, N, N, N, N, N, N, N, D(ImplicitOps | ModRM | SrcMem | NoAccess), N, N, N, N, N, N, D(ImplicitOps | ModRM | SrcMem | NoAccess), /* 0x20 - 0x2F */ DIP(ModRM | DstMem | Priv | Op3264 | NoMod, cr_read, check_cr_read), DIP(ModRM | DstMem | Priv | Op3264 | NoMod, dr_read, check_dr_read), IIP(ModRM | SrcMem | Priv | Op3264 | NoMod, em_cr_write, cr_write, check_cr_write), IIP(ModRM | SrcMem | Priv | Op3264 | NoMod, em_dr_write, dr_write, check_dr_write), N, N, N, N, GP(ModRM | DstReg | SrcMem | Mov | Sse, &pfx_0f_28_0f_29), GP(ModRM | DstMem | SrcReg | Mov | Sse, &pfx_0f_28_0f_29), N, GP(ModRM | DstMem | SrcReg | Mov | Sse, &pfx_0f_2b), N, N, N, N, /* 0x30 - 0x3F */ II(ImplicitOps | Priv, em_wrmsr, wrmsr), IIP(ImplicitOps, em_rdtsc, rdtsc, check_rdtsc), II(ImplicitOps | Priv, em_rdmsr, rdmsr), IIP(ImplicitOps, em_rdpmc, rdpmc, check_rdpmc), I(ImplicitOps | EmulateOnUD, em_sysenter), I(ImplicitOps | Priv | EmulateOnUD, em_sysexit), N, N, N, N, N, N, N, N, N, N, /* 0x40 - 0x4F */ X16(D(DstReg | SrcMem | ModRM)), /* 0x50 - 0x5F */ N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, /* 0x60 - 0x6F */ N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, GP(SrcMem | DstReg | ModRM | Mov, &pfx_0f_6f_0f_7f), /* 0x70 - 0x7F */ N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, GP(SrcReg | DstMem | ModRM | Mov, &pfx_0f_6f_0f_7f), /* 0x80 - 0x8F */ X16(D(SrcImm | NearBranch)), /* 0x90 - 0x9F */ X16(D(ByteOp | DstMem | SrcNone | ModRM| Mov)), /* 0xA0 - 0xA7 */ I(Stack | Src2FS, em_push_sreg), I(Stack | Src2FS, em_pop_sreg), II(ImplicitOps, em_cpuid, cpuid), F(DstMem | SrcReg | ModRM | BitOp | NoWrite, em_bt), F(DstMem | SrcReg | Src2ImmByte | ModRM, em_shld), F(DstMem | SrcReg | Src2CL | ModRM, em_shld), N, N, /* 0xA8 - 0xAF */ I(Stack | Src2GS, em_push_sreg), I(Stack | Src2GS, em_pop_sreg), II(EmulateOnUD | ImplicitOps, em_rsm, rsm), F(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_bts), F(DstMem | SrcReg | Src2ImmByte | ModRM, em_shrd), F(DstMem | SrcReg | Src2CL | ModRM, em_shrd), GD(0, &group15), F(DstReg | SrcMem | ModRM, em_imul), /* 0xB0 - 0xB7 */ I2bv(DstMem | SrcReg | ModRM | Lock | PageTable | SrcWrite, em_cmpxchg), I(DstReg | SrcMemFAddr | ModRM | Src2SS, em_lseg), F(DstMem | SrcReg | ModRM | BitOp | Lock, em_btr), I(DstReg | SrcMemFAddr | ModRM | Src2FS, em_lseg), I(DstReg | SrcMemFAddr | ModRM | Src2GS, em_lseg), D(DstReg | SrcMem8 | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov), /* 0xB8 - 0xBF */ N, N, G(BitOp, group8), F(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_btc), I(DstReg | SrcMem | ModRM, em_bsf_c), I(DstReg | SrcMem | ModRM, em_bsr_c), D(DstReg | SrcMem8 | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov), /* 0xC0 - 0xC7 */ F2bv(DstMem | SrcReg | ModRM | SrcWrite | Lock, em_xadd), N, ID(0, &instr_dual_0f_c3), N, N, N, GD(0, &group9), /* 0xC8 - 0xCF */ X8(I(DstReg, em_bswap)), /* 0xD0 - 0xDF */ N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, /* 0xE0 - 0xEF */ N, N, N, N, N, N, N, GP(SrcReg | DstMem | ModRM | Mov, &pfx_0f_e7), N, N, N, N, N, N, N, N, /* 0xF0 - 0xFF */ N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, N }; static const struct instr_dual instr_dual_0f_38_f0 = { I(DstReg | SrcMem | Mov, em_movbe), N }; static const struct instr_dual instr_dual_0f_38_f1 = { I(DstMem | SrcReg | Mov, em_movbe), N }; static const struct gprefix three_byte_0f_38_f0 = { ID(0, &instr_dual_0f_38_f0), N, N, N }; static const struct gprefix three_byte_0f_38_f1 = { ID(0, &instr_dual_0f_38_f1), N, N, N }; /* * Insns below are selected by the prefix which indexed by the third opcode * byte. */ static const struct opcode opcode_map_0f_38[256] = { /* 0x00 - 0x7f */ X16(N), X16(N), X16(N), X16(N), X16(N), X16(N), X16(N), X16(N), /* 0x80 - 0xef */ X16(N), X16(N), X16(N), X16(N), X16(N), X16(N), X16(N), /* 0xf0 - 0xf1 */ GP(EmulateOnUD | ModRM, &three_byte_0f_38_f0), GP(EmulateOnUD | ModRM, &three_byte_0f_38_f1), /* 0xf2 - 0xff */ N, N, X4(N), X8(N) }; #undef D #undef N #undef G #undef GD #undef I #undef GP #undef EXT #undef MD #undef ID #undef D2bv #undef D2bvIP #undef I2bv #undef I2bvIP #undef I6ALU static unsigned imm_size(struct x86_emulate_ctxt *ctxt) { unsigned size; size = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; if (size == 8) size = 4; return size; } static int decode_imm(struct x86_emulate_ctxt *ctxt, struct operand *op, unsigned size, bool sign_extension) { int rc = X86EMUL_CONTINUE; op->type = OP_IMM; op->bytes = size; op->addr.mem.ea = ctxt->_eip; /* NB. Immediates are sign-extended as necessary. */ switch (op->bytes) { case 1: op->val = insn_fetch(s8, ctxt); break; case 2: op->val = insn_fetch(s16, ctxt); break; case 4: op->val = insn_fetch(s32, ctxt); break; case 8: op->val = insn_fetch(s64, ctxt); break; } if (!sign_extension) { switch (op->bytes) { case 1: op->val &= 0xff; break; case 2: op->val &= 0xffff; break; case 4: op->val &= 0xffffffff; break; } } done: return rc; } static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op, unsigned d) { int rc = X86EMUL_CONTINUE; switch (d) { case OpReg: decode_register_operand(ctxt, op); break; case OpImmUByte: rc = decode_imm(ctxt, op, 1, false); break; case OpMem: ctxt->memop.bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; mem_common: *op = ctxt->memop; ctxt->memopp = op; if (ctxt->d & BitOp) fetch_bit_operand(ctxt); op->orig_val = op->val; break; case OpMem64: ctxt->memop.bytes = (ctxt->op_bytes == 8) ? 16 : 8; goto mem_common; case OpAcc: op->type = OP_REG; op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; op->addr.reg = reg_rmw(ctxt, VCPU_REGS_RAX); fetch_register_operand(op); op->orig_val = op->val; break; case OpAccLo: op->type = OP_REG; op->bytes = (ctxt->d & ByteOp) ? 2 : ctxt->op_bytes; op->addr.reg = reg_rmw(ctxt, VCPU_REGS_RAX); fetch_register_operand(op); op->orig_val = op->val; break; case OpAccHi: if (ctxt->d & ByteOp) { op->type = OP_NONE; break; } op->type = OP_REG; op->bytes = ctxt->op_bytes; op->addr.reg = reg_rmw(ctxt, VCPU_REGS_RDX); fetch_register_operand(op); op->orig_val = op->val; break; case OpDI: op->type = OP_MEM; op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; op->addr.mem.ea = register_address(ctxt, VCPU_REGS_RDI); op->addr.mem.seg = VCPU_SREG_ES; op->val = 0; op->count = 1; break; case OpDX: op->type = OP_REG; op->bytes = 2; op->addr.reg = reg_rmw(ctxt, VCPU_REGS_RDX); fetch_register_operand(op); break; case OpCL: op->type = OP_IMM; op->bytes = 1; op->val = reg_read(ctxt, VCPU_REGS_RCX) & 0xff; break; case OpImmByte: rc = decode_imm(ctxt, op, 1, true); break; case OpOne: op->type = OP_IMM; op->bytes = 1; op->val = 1; break; case OpImm: rc = decode_imm(ctxt, op, imm_size(ctxt), true); break; case OpImm64: rc = decode_imm(ctxt, op, ctxt->op_bytes, true); break; case OpMem8: ctxt->memop.bytes = 1; if (ctxt->memop.type == OP_REG) { ctxt->memop.addr.reg = decode_register(ctxt, ctxt->modrm_rm, true); fetch_register_operand(&ctxt->memop); } goto mem_common; case OpMem16: ctxt->memop.bytes = 2; goto mem_common; case OpMem32: ctxt->memop.bytes = 4; goto mem_common; case OpImmU16: rc = decode_imm(ctxt, op, 2, false); break; case OpImmU: rc = decode_imm(ctxt, op, imm_size(ctxt), false); break; case OpSI: op->type = OP_MEM; op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; op->addr.mem.ea = register_address(ctxt, VCPU_REGS_RSI); op->addr.mem.seg = ctxt->seg_override; op->val = 0; op->count = 1; break; case OpXLat: op->type = OP_MEM; op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; op->addr.mem.ea = address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RBX) + (reg_read(ctxt, VCPU_REGS_RAX) & 0xff)); op->addr.mem.seg = ctxt->seg_override; op->val = 0; break; case OpImmFAddr: op->type = OP_IMM; op->addr.mem.ea = ctxt->_eip; op->bytes = ctxt->op_bytes + 2; insn_fetch_arr(op->valptr, op->bytes, ctxt); break; case OpMemFAddr: ctxt->memop.bytes = ctxt->op_bytes + 2; goto mem_common; case OpES: op->type = OP_IMM; op->val = VCPU_SREG_ES; break; case OpCS: op->type = OP_IMM; op->val = VCPU_SREG_CS; break; case OpSS: op->type = OP_IMM; op->val = VCPU_SREG_SS; break; case OpDS: op->type = OP_IMM; op->val = VCPU_SREG_DS; break; case OpFS: op->type = OP_IMM; op->val = VCPU_SREG_FS; break; case OpGS: op->type = OP_IMM; op->val = VCPU_SREG_GS; break; case OpImplicit: /* Special instructions do their own operand decoding. */ default: op->type = OP_NONE; /* Disable writeback. */ break; } done: return rc; } int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len) { int rc = X86EMUL_CONTINUE; int mode = ctxt->mode; int def_op_bytes, def_ad_bytes, goffset, simd_prefix; bool op_prefix = false; bool has_seg_override = false; struct opcode opcode; u16 dummy; struct desc_struct desc; ctxt->memop.type = OP_NONE; ctxt->memopp = NULL; ctxt->_eip = ctxt->eip; ctxt->fetch.ptr = ctxt->fetch.data; ctxt->fetch.end = ctxt->fetch.data + insn_len; ctxt->opcode_len = 1; ctxt->intercept = x86_intercept_none; if (insn_len > 0) memcpy(ctxt->fetch.data, insn, insn_len); else { rc = __do_insn_fetch_bytes(ctxt, 1); if (rc != X86EMUL_CONTINUE) return rc; } switch (mode) { case X86EMUL_MODE_REAL: case X86EMUL_MODE_VM86: def_op_bytes = def_ad_bytes = 2; ctxt->ops->get_segment(ctxt, &dummy, &desc, NULL, VCPU_SREG_CS); if (desc.d) def_op_bytes = def_ad_bytes = 4; break; case X86EMUL_MODE_PROT16: def_op_bytes = def_ad_bytes = 2; break; case X86EMUL_MODE_PROT32: def_op_bytes = def_ad_bytes = 4; break; #ifdef CONFIG_X86_64 case X86EMUL_MODE_PROT64: def_op_bytes = 4; def_ad_bytes = 8; break; #endif default: return EMULATION_FAILED; } ctxt->op_bytes = def_op_bytes; ctxt->ad_bytes = def_ad_bytes; /* Legacy prefixes. */ for (;;) { switch (ctxt->b = insn_fetch(u8, ctxt)) { case 0x66: /* operand-size override */ op_prefix = true; /* switch between 2/4 bytes */ ctxt->op_bytes = def_op_bytes ^ 6; break; case 0x67: /* address-size override */ if (mode == X86EMUL_MODE_PROT64) /* switch between 4/8 bytes */ ctxt->ad_bytes = def_ad_bytes ^ 12; else /* switch between 2/4 bytes */ ctxt->ad_bytes = def_ad_bytes ^ 6; break; case 0x26: /* ES override */ has_seg_override = true; ctxt->seg_override = VCPU_SREG_ES; break; case 0x2e: /* CS override */ has_seg_override = true; ctxt->seg_override = VCPU_SREG_CS; break; case 0x36: /* SS override */ has_seg_override = true; ctxt->seg_override = VCPU_SREG_SS; break; case 0x3e: /* DS override */ has_seg_override = true; ctxt->seg_override = VCPU_SREG_DS; break; case 0x64: /* FS override */ has_seg_override = true; ctxt->seg_override = VCPU_SREG_FS; break; case 0x65: /* GS override */ has_seg_override = true; ctxt->seg_override = VCPU_SREG_GS; break; case 0x40 ... 0x4f: /* REX */ if (mode != X86EMUL_MODE_PROT64) goto done_prefixes; ctxt->rex_prefix = ctxt->b; continue; case 0xf0: /* LOCK */ ctxt->lock_prefix = 1; break; case 0xf2: /* REPNE/REPNZ */ case 0xf3: /* REP/REPE/REPZ */ ctxt->rep_prefix = ctxt->b; break; default: goto done_prefixes; } /* Any legacy prefix after a REX prefix nullifies its effect. */ ctxt->rex_prefix = 0; } done_prefixes: /* REX prefix. */ if (ctxt->rex_prefix & 8) ctxt->op_bytes = 8; /* REX.W */ /* Opcode byte(s). */ opcode = opcode_table[ctxt->b]; /* Two-byte opcode? */ if (ctxt->b == 0x0f) { ctxt->opcode_len = 2; ctxt->b = insn_fetch(u8, ctxt); opcode = twobyte_table[ctxt->b]; /* 0F_38 opcode map */ if (ctxt->b == 0x38) { ctxt->opcode_len = 3; ctxt->b = insn_fetch(u8, ctxt); opcode = opcode_map_0f_38[ctxt->b]; } } ctxt->d = opcode.flags; if (ctxt->d & ModRM) ctxt->modrm = insn_fetch(u8, ctxt); /* vex-prefix instructions are not implemented */ if (ctxt->opcode_len == 1 && (ctxt->b == 0xc5 || ctxt->b == 0xc4) && (mode == X86EMUL_MODE_PROT64 || (ctxt->modrm & 0xc0) == 0xc0)) { ctxt->d = NotImpl; } while (ctxt->d & GroupMask) { switch (ctxt->d & GroupMask) { case Group: goffset = (ctxt->modrm >> 3) & 7; opcode = opcode.u.group[goffset]; break; case GroupDual: goffset = (ctxt->modrm >> 3) & 7; if ((ctxt->modrm >> 6) == 3) opcode = opcode.u.gdual->mod3[goffset]; else opcode = opcode.u.gdual->mod012[goffset]; break; case RMExt: goffset = ctxt->modrm & 7; opcode = opcode.u.group[goffset]; break; case Prefix: if (ctxt->rep_prefix && op_prefix) return EMULATION_FAILED; simd_prefix = op_prefix ? 0x66 : ctxt->rep_prefix; switch (simd_prefix) { case 0x00: opcode = opcode.u.gprefix->pfx_no; break; case 0x66: opcode = opcode.u.gprefix->pfx_66; break; case 0xf2: opcode = opcode.u.gprefix->pfx_f2; break; case 0xf3: opcode = opcode.u.gprefix->pfx_f3; break; } break; case Escape: if (ctxt->modrm > 0xbf) { size_t size = ARRAY_SIZE(opcode.u.esc->high); u32 index = array_index_nospec( ctxt->modrm - 0xc0, size); opcode = opcode.u.esc->high[index]; } else { opcode = opcode.u.esc->op[(ctxt->modrm >> 3) & 7]; } break; case InstrDual: if ((ctxt->modrm >> 6) == 3) opcode = opcode.u.idual->mod3; else opcode = opcode.u.idual->mod012; break; case ModeDual: if (ctxt->mode == X86EMUL_MODE_PROT64) opcode = opcode.u.mdual->mode64; else opcode = opcode.u.mdual->mode32; break; default: return EMULATION_FAILED; } ctxt->d &= ~(u64)GroupMask; ctxt->d |= opcode.flags; } /* Unrecognised? */ if (ctxt->d == 0) return EMULATION_FAILED; ctxt->execute = opcode.u.execute; if (unlikely(ctxt->ud) && likely(!(ctxt->d & EmulateOnUD))) return EMULATION_FAILED; if (unlikely(ctxt->d & (NotImpl|Stack|Op3264|Sse|Mmx|Intercept|CheckPerm|NearBranch| No16))) { /* * These are copied unconditionally here, and checked unconditionally * in x86_emulate_insn. */ ctxt->check_perm = opcode.check_perm; ctxt->intercept = opcode.intercept; if (ctxt->d & NotImpl) return EMULATION_FAILED; if (mode == X86EMUL_MODE_PROT64) { if (ctxt->op_bytes == 4 && (ctxt->d & Stack)) ctxt->op_bytes = 8; else if (ctxt->d & NearBranch) ctxt->op_bytes = 8; } if (ctxt->d & Op3264) { if (mode == X86EMUL_MODE_PROT64) ctxt->op_bytes = 8; else ctxt->op_bytes = 4; } if ((ctxt->d & No16) && ctxt->op_bytes == 2) ctxt->op_bytes = 4; if (ctxt->d & Sse) ctxt->op_bytes = 16; else if (ctxt->d & Mmx) ctxt->op_bytes = 8; } /* ModRM and SIB bytes. */ if (ctxt->d & ModRM) { rc = decode_modrm(ctxt, &ctxt->memop); if (!has_seg_override) { has_seg_override = true; ctxt->seg_override = ctxt->modrm_seg; } } else if (ctxt->d & MemAbs) rc = decode_abs(ctxt, &ctxt->memop); if (rc != X86EMUL_CONTINUE) goto done; if (!has_seg_override) ctxt->seg_override = VCPU_SREG_DS; ctxt->memop.addr.mem.seg = ctxt->seg_override; /* * Decode and fetch the source operand: register, memory * or immediate. */ rc = decode_operand(ctxt, &ctxt->src, (ctxt->d >> SrcShift) & OpMask); if (rc != X86EMUL_CONTINUE) goto done; /* * Decode and fetch the second source operand: register, memory * or immediate. */ rc = decode_operand(ctxt, &ctxt->src2, (ctxt->d >> Src2Shift) & OpMask); if (rc != X86EMUL_CONTINUE) goto done; /* Decode and fetch the destination operand: register or memory. */ rc = decode_operand(ctxt, &ctxt->dst, (ctxt->d >> DstShift) & OpMask); if (ctxt->rip_relative && likely(ctxt->memopp)) ctxt->memopp->addr.mem.ea = address_mask(ctxt, ctxt->memopp->addr.mem.ea + ctxt->_eip); done: if (rc == X86EMUL_PROPAGATE_FAULT) ctxt->have_exception = true; return (rc != X86EMUL_CONTINUE) ? EMULATION_FAILED : EMULATION_OK; } bool x86_page_table_writing_insn(struct x86_emulate_ctxt *ctxt) { return ctxt->d & PageTable; } static bool string_insn_completed(struct x86_emulate_ctxt *ctxt) { /* The second termination condition only applies for REPE * and REPNE. Test if the repeat string operation prefix is * REPE/REPZ or REPNE/REPNZ and if it's the case it tests the * corresponding termination condition according to: * - if REPE/REPZ and ZF = 0 then done * - if REPNE/REPNZ and ZF = 1 then done */ if (((ctxt->b == 0xa6) || (ctxt->b == 0xa7) || (ctxt->b == 0xae) || (ctxt->b == 0xaf)) && (((ctxt->rep_prefix == REPE_PREFIX) && ((ctxt->eflags & X86_EFLAGS_ZF) == 0)) || ((ctxt->rep_prefix == REPNE_PREFIX) && ((ctxt->eflags & X86_EFLAGS_ZF) == X86_EFLAGS_ZF)))) return true; return false; } static int flush_pending_x87_faults(struct x86_emulate_ctxt *ctxt) { int rc; ctxt->ops->get_fpu(ctxt); rc = asm_safe("fwait"); ctxt->ops->put_fpu(ctxt); if (unlikely(rc != X86EMUL_CONTINUE)) return emulate_exception(ctxt, MF_VECTOR, 0, false); return X86EMUL_CONTINUE; } static void fetch_possible_mmx_operand(struct x86_emulate_ctxt *ctxt, struct operand *op) { if (op->type == OP_MM) read_mmx_reg(ctxt, &op->mm_val, op->addr.mm); } static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *)) { ulong flags = (ctxt->eflags & EFLAGS_MASK) | X86_EFLAGS_IF; if (!(ctxt->d & ByteOp)) fop += __ffs(ctxt->dst.bytes) * FASTOP_SIZE; asm("push %[flags]; popf; " CALL_NOSPEC " ; pushf; pop %[flags]\n" : "+a"(ctxt->dst.val), "+d"(ctxt->src.val), [flags]"+D"(flags), [thunk_target]"+S"(fop), ASM_CALL_CONSTRAINT : "c"(ctxt->src2.val)); ctxt->eflags = (ctxt->eflags & ~EFLAGS_MASK) | (flags & EFLAGS_MASK); if (!fop) /* exception is returned in fop variable */ return emulate_de(ctxt); return X86EMUL_CONTINUE; } void init_decode_cache(struct x86_emulate_ctxt *ctxt) { memset(&ctxt->rip_relative, 0, (void *)&ctxt->modrm - (void *)&ctxt->rip_relative); ctxt->io_read.pos = 0; ctxt->io_read.end = 0; ctxt->mem_read.end = 0; } int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) { const struct x86_emulate_ops *ops = ctxt->ops; int rc = X86EMUL_CONTINUE; int saved_dst_type = ctxt->dst.type; unsigned emul_flags; ctxt->mem_read.pos = 0; /* LOCK prefix is allowed only with some instructions */ if (ctxt->lock_prefix && (!(ctxt->d & Lock) || ctxt->dst.type != OP_MEM)) { rc = emulate_ud(ctxt); goto done; } if ((ctxt->d & SrcMask) == SrcMemFAddr && ctxt->src.type != OP_MEM) { rc = emulate_ud(ctxt); goto done; } emul_flags = ctxt->ops->get_hflags(ctxt); if (unlikely(ctxt->d & (No64|Undefined|Sse|Mmx|Intercept|CheckPerm|Priv|Prot|String))) { if ((ctxt->mode == X86EMUL_MODE_PROT64 && (ctxt->d & No64)) || (ctxt->d & Undefined)) { rc = emulate_ud(ctxt); goto done; } if (((ctxt->d & (Sse|Mmx)) && ((ops->get_cr(ctxt, 0) & X86_CR0_EM))) || ((ctxt->d & Sse) && !(ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR))) { rc = emulate_ud(ctxt); goto done; } if ((ctxt->d & (Sse|Mmx)) && (ops->get_cr(ctxt, 0) & X86_CR0_TS)) { rc = emulate_nm(ctxt); goto done; } if (ctxt->d & Mmx) { rc = flush_pending_x87_faults(ctxt); if (rc != X86EMUL_CONTINUE) goto done; /* * Now that we know the fpu is exception safe, we can fetch * operands from it. */ fetch_possible_mmx_operand(ctxt, &ctxt->src); fetch_possible_mmx_operand(ctxt, &ctxt->src2); if (!(ctxt->d & Mov)) fetch_possible_mmx_operand(ctxt, &ctxt->dst); } if (unlikely(emul_flags & X86EMUL_GUEST_MASK) && ctxt->intercept) { rc = emulator_check_intercept(ctxt, ctxt->intercept, X86_ICPT_PRE_EXCEPT); if (rc != X86EMUL_CONTINUE) goto done; } /* Instruction can only be executed in protected mode */ if ((ctxt->d & Prot) && ctxt->mode < X86EMUL_MODE_PROT16) { rc = emulate_ud(ctxt); goto done; } /* Privileged instruction can be executed only in CPL=0 */ if ((ctxt->d & Priv) && ops->cpl(ctxt)) { if (ctxt->d & PrivUD) rc = emulate_ud(ctxt); else rc = emulate_gp(ctxt, 0); goto done; } /* Do instruction specific permission checks */ if (ctxt->d & CheckPerm) { rc = ctxt->check_perm(ctxt); if (rc != X86EMUL_CONTINUE) goto done; } if (unlikely(emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) { rc = emulator_check_intercept(ctxt, ctxt->intercept, X86_ICPT_POST_EXCEPT); if (rc != X86EMUL_CONTINUE) goto done; } if (ctxt->rep_prefix && (ctxt->d & String)) { /* All REP prefixes have the same first termination condition */ if (address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) == 0) { string_registers_quirk(ctxt); ctxt->eip = ctxt->_eip; ctxt->eflags &= ~X86_EFLAGS_RF; goto done; } } } if ((ctxt->src.type == OP_MEM) && !(ctxt->d & NoAccess)) { rc = segmented_read(ctxt, ctxt->src.addr.mem, ctxt->src.valptr, ctxt->src.bytes); if (rc != X86EMUL_CONTINUE) goto done; ctxt->src.orig_val64 = ctxt->src.val64; } if (ctxt->src2.type == OP_MEM) { rc = segmented_read(ctxt, ctxt->src2.addr.mem, &ctxt->src2.val, ctxt->src2.bytes); if (rc != X86EMUL_CONTINUE) goto done; } if ((ctxt->d & DstMask) == ImplicitOps) goto special_insn; if ((ctxt->dst.type == OP_MEM) && !(ctxt->d & Mov)) { /* optimisation - avoid slow emulated read if Mov */ rc = segmented_read(ctxt, ctxt->dst.addr.mem, &ctxt->dst.val, ctxt->dst.bytes); if (rc != X86EMUL_CONTINUE) { if (!(ctxt->d & NoWrite) && rc == X86EMUL_PROPAGATE_FAULT && ctxt->exception.vector == PF_VECTOR) ctxt->exception.error_code |= PFERR_WRITE_MASK; goto done; } } /* Copy full 64-bit value for CMPXCHG8B. */ ctxt->dst.orig_val64 = ctxt->dst.val64; special_insn: if (unlikely(emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) { rc = emulator_check_intercept(ctxt, ctxt->intercept, X86_ICPT_POST_MEMACCESS); if (rc != X86EMUL_CONTINUE) goto done; } if (ctxt->rep_prefix && (ctxt->d & String)) ctxt->eflags |= X86_EFLAGS_RF; else ctxt->eflags &= ~X86_EFLAGS_RF; if (ctxt->execute) { if (ctxt->d & Fastop) { void (*fop)(struct fastop *) = (void *)ctxt->execute; rc = fastop(ctxt, fop); if (rc != X86EMUL_CONTINUE) goto done; goto writeback; } rc = ctxt->execute(ctxt); if (rc != X86EMUL_CONTINUE) goto done; goto writeback; } if (ctxt->opcode_len == 2) goto twobyte_insn; else if (ctxt->opcode_len == 3) goto threebyte_insn; switch (ctxt->b) { case 0x70 ... 0x7f: /* jcc (short) */ if (test_cc(ctxt->b, ctxt->eflags)) rc = jmp_rel(ctxt, ctxt->src.val); break; case 0x8d: /* lea r16/r32, m */ ctxt->dst.val = ctxt->src.addr.mem.ea; break; case 0x90 ... 0x97: /* nop / xchg reg, rax */ if (ctxt->dst.addr.reg == reg_rmw(ctxt, VCPU_REGS_RAX)) ctxt->dst.type = OP_NONE; else rc = em_xchg(ctxt); break; case 0x98: /* cbw/cwde/cdqe */ switch (ctxt->op_bytes) { case 2: ctxt->dst.val = (s8)ctxt->dst.val; break; case 4: ctxt->dst.val = (s16)ctxt->dst.val; break; case 8: ctxt->dst.val = (s32)ctxt->dst.val; break; } break; case 0xcc: /* int3 */ rc = emulate_int(ctxt, 3); break; case 0xcd: /* int n */ rc = emulate_int(ctxt, ctxt->src.val); break; case 0xce: /* into */ if (ctxt->eflags & X86_EFLAGS_OF) rc = emulate_int(ctxt, 4); break; case 0xe9: /* jmp rel */ case 0xeb: /* jmp rel short */ rc = jmp_rel(ctxt, ctxt->src.val); ctxt->dst.type = OP_NONE; /* Disable writeback. */ break; case 0xf4: /* hlt */ ctxt->ops->halt(ctxt); break; case 0xf5: /* cmc */ /* complement carry flag from eflags reg */ ctxt->eflags ^= X86_EFLAGS_CF; break; case 0xf8: /* clc */ ctxt->eflags &= ~X86_EFLAGS_CF; break; case 0xf9: /* stc */ ctxt->eflags |= X86_EFLAGS_CF; break; case 0xfc: /* cld */ ctxt->eflags &= ~X86_EFLAGS_DF; break; case 0xfd: /* std */ ctxt->eflags |= X86_EFLAGS_DF; break; default: goto cannot_emulate; } if (rc != X86EMUL_CONTINUE) goto done; writeback: if (ctxt->d & SrcWrite) { BUG_ON(ctxt->src.type == OP_MEM || ctxt->src.type == OP_MEM_STR); rc = writeback(ctxt, &ctxt->src); if (rc != X86EMUL_CONTINUE) goto done; } if (!(ctxt->d & NoWrite)) { rc = writeback(ctxt, &ctxt->dst); if (rc != X86EMUL_CONTINUE) goto done; } /* * restore dst type in case the decoding will be reused * (happens for string instruction ) */ ctxt->dst.type = saved_dst_type; if ((ctxt->d & SrcMask) == SrcSI) string_addr_inc(ctxt, VCPU_REGS_RSI, &ctxt->src); if ((ctxt->d & DstMask) == DstDI) string_addr_inc(ctxt, VCPU_REGS_RDI, &ctxt->dst); if (ctxt->rep_prefix && (ctxt->d & String)) { unsigned int count; struct read_cache *r = &ctxt->io_read; if ((ctxt->d & SrcMask) == SrcSI) count = ctxt->src.count; else count = ctxt->dst.count; register_address_increment(ctxt, VCPU_REGS_RCX, -count); if (!string_insn_completed(ctxt)) { /* * Re-enter guest when pio read ahead buffer is empty * or, if it is not used, after each 1024 iteration. */ if ((r->end != 0 || reg_read(ctxt, VCPU_REGS_RCX) & 0x3ff) && (r->end == 0 || r->end != r->pos)) { /* * Reset read cache. Usually happens before * decode, but since instruction is restarted * we have to do it here. */ ctxt->mem_read.end = 0; writeback_registers(ctxt); return EMULATION_RESTART; } goto done; /* skip rip writeback */ } ctxt->eflags &= ~X86_EFLAGS_RF; } ctxt->eip = ctxt->_eip; done: if (rc == X86EMUL_PROPAGATE_FAULT) { WARN_ON(ctxt->exception.vector > 0x1f); ctxt->have_exception = true; } if (rc == X86EMUL_INTERCEPTED) return EMULATION_INTERCEPTED; if (rc == X86EMUL_CONTINUE) writeback_registers(ctxt); return (rc == X86EMUL_UNHANDLEABLE) ? EMULATION_FAILED : EMULATION_OK; twobyte_insn: switch (ctxt->b) { case 0x09: /* wbinvd */ (ctxt->ops->wbinvd)(ctxt); break; case 0x08: /* invd */ case 0x0d: /* GrpP (prefetch) */ case 0x18: /* Grp16 (prefetch/nop) */ case 0x1f: /* nop */ break; case 0x20: /* mov cr, reg */ ctxt->dst.val = ops->get_cr(ctxt, ctxt->modrm_reg); break; case 0x21: /* mov from dr to reg */ ops->get_dr(ctxt, ctxt->modrm_reg, &ctxt->dst.val); break; case 0x40 ... 0x4f: /* cmov */ if (test_cc(ctxt->b, ctxt->eflags)) ctxt->dst.val = ctxt->src.val; else if (ctxt->op_bytes != 4) ctxt->dst.type = OP_NONE; /* no writeback */ break; case 0x80 ... 0x8f: /* jnz rel, etc*/ if (test_cc(ctxt->b, ctxt->eflags)) rc = jmp_rel(ctxt, ctxt->src.val); break; case 0x90 ... 0x9f: /* setcc r/m8 */ ctxt->dst.val = test_cc(ctxt->b, ctxt->eflags); break; case 0xb6 ... 0xb7: /* movzx */ ctxt->dst.bytes = ctxt->op_bytes; ctxt->dst.val = (ctxt->src.bytes == 1) ? (u8) ctxt->src.val : (u16) ctxt->src.val; break; case 0xbe ... 0xbf: /* movsx */ ctxt->dst.bytes = ctxt->op_bytes; ctxt->dst.val = (ctxt->src.bytes == 1) ? (s8) ctxt->src.val : (s16) ctxt->src.val; break; default: goto cannot_emulate; } threebyte_insn: if (rc != X86EMUL_CONTINUE) goto done; goto writeback; cannot_emulate: return EMULATION_FAILED; } void emulator_invalidate_register_cache(struct x86_emulate_ctxt *ctxt) { invalidate_registers(ctxt); } void emulator_writeback_register_cache(struct x86_emulate_ctxt *ctxt) { writeback_registers(ctxt); } bool emulator_can_use_gpa(struct x86_emulate_ctxt *ctxt) { if (ctxt->rep_prefix && (ctxt->d & String)) return false; if (ctxt->d & TwoMemOp) return false; return true; } |
| 5 5 5 8 8 8 90 25 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 | /* * IEEE 802.1Q GARP VLAN Registration Protocol (GVRP) * * Copyright (c) 2008 Patrick McHardy <kaber@trash.net> * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * version 2 as published by the Free Software Foundation. */ #include <linux/types.h> #include <linux/if_vlan.h> #include <net/garp.h> #include "vlan.h" #define GARP_GVRP_ADDRESS { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x21 } enum gvrp_attributes { GVRP_ATTR_INVALID, GVRP_ATTR_VID, __GVRP_ATTR_MAX }; #define GVRP_ATTR_MAX (__GVRP_ATTR_MAX - 1) static struct garp_application vlan_gvrp_app __read_mostly = { .proto.group_address = GARP_GVRP_ADDRESS, .maxattr = GVRP_ATTR_MAX, .type = GARP_APPLICATION_GVRP, }; int vlan_gvrp_request_join(const struct net_device *dev) { const struct vlan_dev_priv *vlan = vlan_dev_priv(dev); __be16 vlan_id = htons(vlan->vlan_id); if (vlan->vlan_proto != htons(ETH_P_8021Q)) return 0; return garp_request_join(vlan->real_dev, &vlan_gvrp_app, &vlan_id, sizeof(vlan_id), GVRP_ATTR_VID); } void vlan_gvrp_request_leave(const struct net_device *dev) { const struct vlan_dev_priv *vlan = vlan_dev_priv(dev); __be16 vlan_id = htons(vlan->vlan_id); if (vlan->vlan_proto != htons(ETH_P_8021Q)) return; garp_request_leave(vlan->real_dev, &vlan_gvrp_app, &vlan_id, sizeof(vlan_id), GVRP_ATTR_VID); } int vlan_gvrp_init_applicant(struct net_device *dev) { return garp_init_applicant(dev, &vlan_gvrp_app); } void vlan_gvrp_uninit_applicant(struct net_device *dev) { garp_uninit_applicant(dev, &vlan_gvrp_app); } int __init vlan_gvrp_init(void) { return garp_register_application(&vlan_gvrp_app); } void vlan_gvrp_uninit(void) { garp_unregister_application(&vlan_gvrp_app); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef ASM_X86_CAMELLIA_H #define ASM_X86_CAMELLIA_H #include <linux/kernel.h> #include <linux/crypto.h> #define CAMELLIA_MIN_KEY_SIZE 16 #define CAMELLIA_MAX_KEY_SIZE 32 #define CAMELLIA_BLOCK_SIZE 16 #define CAMELLIA_TABLE_BYTE_LEN 272 #define CAMELLIA_PARALLEL_BLOCKS 2 struct camellia_ctx { u64 key_table[CAMELLIA_TABLE_BYTE_LEN / sizeof(u64)]; u32 key_length; }; struct camellia_lrw_ctx { struct lrw_table_ctx lrw_table; struct camellia_ctx camellia_ctx; }; struct camellia_xts_ctx { struct camellia_ctx tweak_ctx; struct camellia_ctx crypt_ctx; }; extern int __camellia_setkey(struct camellia_ctx *cctx, const unsigned char *key, unsigned int key_len, u32 *flags); extern int lrw_camellia_setkey(struct crypto_tfm *tfm, const u8 *key, unsigned int keylen); extern void lrw_camellia_exit_tfm(struct crypto_tfm *tfm); extern int xts_camellia_setkey(struct crypto_tfm *tfm, const u8 *key, unsigned int keylen); /* regular block cipher functions */ asmlinkage void __camellia_enc_blk(struct camellia_ctx *ctx, u8 *dst, const u8 *src, bool xor); asmlinkage void camellia_dec_blk(struct camellia_ctx *ctx, u8 *dst, const u8 *src); /* 2-way parallel cipher functions */ asmlinkage void __camellia_enc_blk_2way(struct camellia_ctx *ctx, u8 *dst, const u8 *src, bool xor); asmlinkage void camellia_dec_blk_2way(struct camellia_ctx *ctx, u8 *dst, const u8 *src); /* 16-way parallel cipher functions (avx/aes-ni) */ asmlinkage void camellia_ecb_enc_16way(struct camellia_ctx *ctx, u8 *dst, const u8 *src); asmlinkage void camellia_ecb_dec_16way(struct camellia_ctx *ctx, u8 *dst, const u8 *src); asmlinkage void camellia_cbc_dec_16way(struct camellia_ctx *ctx, u8 *dst, const u8 *src); asmlinkage void camellia_ctr_16way(struct camellia_ctx *ctx, u8 *dst, const u8 *src, le128 *iv); asmlinkage void camellia_xts_enc_16way(struct camellia_ctx *ctx, u8 *dst, const u8 *src, le128 *iv); asmlinkage void camellia_xts_dec_16way(struct camellia_ctx *ctx, u8 *dst, const u8 *src, le128 *iv); static inline void camellia_enc_blk(struct camellia_ctx *ctx, u8 *dst, const u8 *src) { __camellia_enc_blk(ctx, dst, src, false); } static inline void camellia_enc_blk_xor(struct camellia_ctx *ctx, u8 *dst, const u8 *src) { __camellia_enc_blk(ctx, dst, src, true); } static inline void camellia_enc_blk_2way(struct camellia_ctx *ctx, u8 *dst, const u8 *src) { __camellia_enc_blk_2way(ctx, dst, src, false); } static inline void camellia_enc_blk_xor_2way(struct camellia_ctx *ctx, u8 *dst, const u8 *src) { __camellia_enc_blk_2way(ctx, dst, src, true); } /* glue helpers */ extern void camellia_decrypt_cbc_2way(void *ctx, u128 *dst, const u128 *src); extern void camellia_crypt_ctr(void *ctx, u128 *dst, const u128 *src, le128 *iv); extern void camellia_crypt_ctr_2way(void *ctx, u128 *dst, const u128 *src, le128 *iv); extern void camellia_xts_enc(void *ctx, u128 *dst, const u128 *src, le128 *iv); extern void camellia_xts_dec(void *ctx, u128 *dst, const u128 *src, le128 *iv); #endif /* ASM_X86_CAMELLIA_H */ |
| 12 9 11 63 63 64 3 3 3 2 2 3 62 64 64 64 64 64 12 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 | /* Helper handling for netfilter. */ /* (C) 1999-2001 Paul `Rusty' Russell * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org> * (C) 2003,2004 USAGI/WIDE Project <http://www.linux-ipv6.org> * (C) 2006-2012 Patrick McHardy <kaber@trash.net> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ #include <linux/types.h> #include <linux/netfilter.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/vmalloc.h> #include <linux/stddef.h> #include <linux/random.h> #include <linux/err.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/rculist.h> #include <linux/rtnetlink.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_l3proto.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_extend.h> #include <net/netfilter/nf_log.h> static DEFINE_MUTEX(nf_ct_helper_mutex); struct hlist_head *nf_ct_helper_hash __read_mostly; EXPORT_SYMBOL_GPL(nf_ct_helper_hash); unsigned int nf_ct_helper_hsize __read_mostly; EXPORT_SYMBOL_GPL(nf_ct_helper_hsize); static unsigned int nf_ct_helper_count __read_mostly; static bool nf_ct_auto_assign_helper __read_mostly = false; module_param_named(nf_conntrack_helper, nf_ct_auto_assign_helper, bool, 0644); MODULE_PARM_DESC(nf_conntrack_helper, "Enable automatic conntrack helper assignment (default 0)"); #ifdef CONFIG_SYSCTL static struct ctl_table helper_sysctl_table[] = { { .procname = "nf_conntrack_helper", .data = &init_net.ct.sysctl_auto_assign_helper, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec, }, {} }; static int nf_conntrack_helper_init_sysctl(struct net *net) { struct ctl_table *table; table = kmemdup(helper_sysctl_table, sizeof(helper_sysctl_table), GFP_KERNEL); if (!table) goto out; table[0].data = &net->ct.sysctl_auto_assign_helper; /* Don't export sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) table[0].procname = NULL; net->ct.helper_sysctl_header = register_net_sysctl(net, "net/netfilter", table); if (!net->ct.helper_sysctl_header) { pr_err("nf_conntrack_helper: can't register to sysctl.\n"); goto out_register; } return 0; out_register: kfree(table); out: return -ENOMEM; } static void nf_conntrack_helper_fini_sysctl(struct net *net) { struct ctl_table *table; table = net->ct.helper_sysctl_header->ctl_table_arg; unregister_net_sysctl_table(net->ct.helper_sysctl_header); kfree(table); } #else static int nf_conntrack_helper_init_sysctl(struct net *net) { return 0; } static void nf_conntrack_helper_fini_sysctl(struct net *net) { } #endif /* CONFIG_SYSCTL */ /* Stupid hash, but collision free for the default registrations of the * helpers currently in the kernel. */ static unsigned int helper_hash(const struct nf_conntrack_tuple *tuple) { return (((tuple->src.l3num << 8) | tuple->dst.protonum) ^ (__force __u16)tuple->src.u.all) % nf_ct_helper_hsize; } static struct nf_conntrack_helper * __nf_ct_helper_find(const struct nf_conntrack_tuple *tuple) { struct nf_conntrack_helper *helper; struct nf_conntrack_tuple_mask mask = { .src.u.all = htons(0xFFFF) }; unsigned int h; if (!nf_ct_helper_count) return NULL; h = helper_hash(tuple); hlist_for_each_entry_rcu(helper, &nf_ct_helper_hash[h], hnode) { if (nf_ct_tuple_src_mask_cmp(tuple, &helper->tuple, &mask)) return helper; } return NULL; } struct nf_conntrack_helper * __nf_conntrack_helper_find(const char *name, u16 l3num, u8 protonum) { struct nf_conntrack_helper *h; unsigned int i; for (i = 0; i < nf_ct_helper_hsize; i++) { hlist_for_each_entry_rcu(h, &nf_ct_helper_hash[i], hnode) { if (strcmp(h->name, name)) continue; if (h->tuple.src.l3num != NFPROTO_UNSPEC && h->tuple.src.l3num != l3num) continue; if (h->tuple.dst.protonum == protonum) return h; } } return NULL; } EXPORT_SYMBOL_GPL(__nf_conntrack_helper_find); struct nf_conntrack_helper * nf_conntrack_helper_try_module_get(const char *name, u16 l3num, u8 protonum) { struct nf_conntrack_helper *h; rcu_read_lock(); h = __nf_conntrack_helper_find(name, l3num, protonum); #ifdef CONFIG_MODULES if (h == NULL) { rcu_read_unlock(); if (request_module("nfct-helper-%s", name) == 0) { rcu_read_lock(); h = __nf_conntrack_helper_find(name, l3num, protonum); } else { return h; } } #endif if (h != NULL && !try_module_get(h->me)) h = NULL; if (h != NULL && !refcount_inc_not_zero(&h->refcnt)) { module_put(h->me); h = NULL; } rcu_read_unlock(); return h; } EXPORT_SYMBOL_GPL(nf_conntrack_helper_try_module_get); void nf_conntrack_helper_put(struct nf_conntrack_helper *helper) { refcount_dec(&helper->refcnt); module_put(helper->me); } EXPORT_SYMBOL_GPL(nf_conntrack_helper_put); struct nf_conn_help * nf_ct_helper_ext_add(struct nf_conn *ct, struct nf_conntrack_helper *helper, gfp_t gfp) { struct nf_conn_help *help; help = nf_ct_ext_add(ct, NF_CT_EXT_HELPER, gfp); if (help) INIT_HLIST_HEAD(&help->expectations); else pr_debug("failed to add helper extension area"); return help; } EXPORT_SYMBOL_GPL(nf_ct_helper_ext_add); static struct nf_conntrack_helper * nf_ct_lookup_helper(struct nf_conn *ct, struct net *net) { if (!net->ct.sysctl_auto_assign_helper) { if (net->ct.auto_assign_helper_warned) return NULL; if (!__nf_ct_helper_find(&ct->tuplehash[IP_CT_DIR_REPLY].tuple)) return NULL; pr_info("nf_conntrack: default automatic helper assignment " "has been turned off for security reasons and CT-based " " firewall rule not found. Use the iptables CT target " "to attach helpers instead.\n"); net->ct.auto_assign_helper_warned = 1; return NULL; } return __nf_ct_helper_find(&ct->tuplehash[IP_CT_DIR_REPLY].tuple); } int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl, gfp_t flags) { struct nf_conntrack_helper *helper = NULL; struct nf_conn_help *help; struct net *net = nf_ct_net(ct); /* We already got a helper explicitly attached. The function * nf_conntrack_alter_reply - in case NAT is in use - asks for looking * the helper up again. Since now the user is in full control of * making consistent helper configurations, skip this automatic * re-lookup, otherwise we'll lose the helper. */ if (test_bit(IPS_HELPER_BIT, &ct->status)) return 0; if (tmpl != NULL) { help = nfct_help(tmpl); if (help != NULL) { helper = help->helper; set_bit(IPS_HELPER_BIT, &ct->status); } } help = nfct_help(ct); if (helper == NULL) { helper = nf_ct_lookup_helper(ct, net); if (helper == NULL) { if (help) RCU_INIT_POINTER(help->helper, NULL); return 0; } } if (help == NULL) { help = nf_ct_helper_ext_add(ct, helper, flags); if (help == NULL) return -ENOMEM; } else { /* We only allow helper re-assignment of the same sort since * we cannot reallocate the helper extension area. */ struct nf_conntrack_helper *tmp = rcu_dereference(help->helper); if (tmp && tmp->help != helper->help) { RCU_INIT_POINTER(help->helper, NULL); return 0; } } rcu_assign_pointer(help->helper, helper); return 0; } EXPORT_SYMBOL_GPL(__nf_ct_try_assign_helper); /* appropriate ct lock protecting must be taken by caller */ static int unhelp(struct nf_conn *ct, void *me) { struct nf_conn_help *help = nfct_help(ct); if (help && rcu_dereference_raw(help->helper) == me) { nf_conntrack_event(IPCT_HELPER, ct); RCU_INIT_POINTER(help->helper, NULL); } /* We are not intended to delete this conntrack. */ return 0; } void nf_ct_helper_destroy(struct nf_conn *ct) { struct nf_conn_help *help = nfct_help(ct); struct nf_conntrack_helper *helper; if (help) { rcu_read_lock(); helper = rcu_dereference(help->helper); if (helper && helper->destroy) helper->destroy(ct); rcu_read_unlock(); } } static LIST_HEAD(nf_ct_helper_expectfn_list); void nf_ct_helper_expectfn_register(struct nf_ct_helper_expectfn *n) { spin_lock_bh(&nf_conntrack_expect_lock); list_add_rcu(&n->head, &nf_ct_helper_expectfn_list); spin_unlock_bh(&nf_conntrack_expect_lock); } EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_register); void nf_ct_helper_expectfn_unregister(struct nf_ct_helper_expectfn *n) { spin_lock_bh(&nf_conntrack_expect_lock); list_del_rcu(&n->head); spin_unlock_bh(&nf_conntrack_expect_lock); } EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_unregister); /* Caller should hold the rcu lock */ struct nf_ct_helper_expectfn * nf_ct_helper_expectfn_find_by_name(const char *name) { struct nf_ct_helper_expectfn *cur; bool found = false; list_for_each_entry_rcu(cur, &nf_ct_helper_expectfn_list, head) { if (!strcmp(cur->name, name)) { found = true; break; } } return found ? cur : NULL; } EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_find_by_name); /* Caller should hold the rcu lock */ struct nf_ct_helper_expectfn * nf_ct_helper_expectfn_find_by_symbol(const void *symbol) { struct nf_ct_helper_expectfn *cur; bool found = false; list_for_each_entry_rcu(cur, &nf_ct_helper_expectfn_list, head) { if (cur->expectfn == symbol) { found = true; break; } } return found ? cur : NULL; } EXPORT_SYMBOL_GPL(nf_ct_helper_expectfn_find_by_symbol); __printf(3, 4) void nf_ct_helper_log(struct sk_buff *skb, const struct nf_conn *ct, const char *fmt, ...) { const struct nf_conn_help *help; const struct nf_conntrack_helper *helper; struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; /* Called from the helper function, this call never fails */ help = nfct_help(ct); /* rcu_read_lock()ed by nf_hook_thresh */ helper = rcu_dereference(help->helper); nf_log_packet(nf_ct_net(ct), nf_ct_l3num(ct), 0, skb, NULL, NULL, NULL, "nf_ct_%s: dropping packet: %pV ", helper->name, &vaf); va_end(args); } EXPORT_SYMBOL_GPL(nf_ct_helper_log); int nf_conntrack_helper_register(struct nf_conntrack_helper *me) { struct nf_conntrack_tuple_mask mask = { .src.u.all = htons(0xFFFF) }; unsigned int h = helper_hash(&me->tuple); struct nf_conntrack_helper *cur; int ret = 0, i; BUG_ON(me->expect_policy == NULL); BUG_ON(me->expect_class_max >= NF_CT_MAX_EXPECT_CLASSES); BUG_ON(strlen(me->name) > NF_CT_HELPER_NAME_LEN - 1); if (me->expect_policy->max_expected > NF_CT_EXPECT_MAX_CNT) return -EINVAL; mutex_lock(&nf_ct_helper_mutex); for (i = 0; i < nf_ct_helper_hsize; i++) { hlist_for_each_entry(cur, &nf_ct_helper_hash[i], hnode) { if (!strcmp(cur->name, me->name) && (cur->tuple.src.l3num == NFPROTO_UNSPEC || cur->tuple.src.l3num == me->tuple.src.l3num) && cur->tuple.dst.protonum == me->tuple.dst.protonum) { ret = -EEXIST; goto out; } } } /* avoid unpredictable behaviour for auto_assign_helper */ if (!(me->flags & NF_CT_HELPER_F_USERSPACE)) { hlist_for_each_entry(cur, &nf_ct_helper_hash[h], hnode) { if (nf_ct_tuple_src_mask_cmp(&cur->tuple, &me->tuple, &mask)) { ret = -EEXIST; goto out; } } } refcount_set(&me->refcnt, 1); hlist_add_head_rcu(&me->hnode, &nf_ct_helper_hash[h]); nf_ct_helper_count++; out: mutex_unlock(&nf_ct_helper_mutex); return ret; } EXPORT_SYMBOL_GPL(nf_conntrack_helper_register); static bool expect_iter_me(struct nf_conntrack_expect *exp, void *data) { struct nf_conn_help *help = nfct_help(exp->master); const struct nf_conntrack_helper *me = data; const struct nf_conntrack_helper *this; if (exp->helper == me) return true; this = rcu_dereference_protected(help->helper, lockdep_is_held(&nf_conntrack_expect_lock)); return this == me; } void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me) { mutex_lock(&nf_ct_helper_mutex); hlist_del_rcu(&me->hnode); nf_ct_helper_count--; mutex_unlock(&nf_ct_helper_mutex); /* Make sure every nothing is still using the helper unless its a * connection in the hash. */ synchronize_rcu(); nf_ct_expect_iterate_destroy(expect_iter_me, NULL); nf_ct_iterate_destroy(unhelp, me); /* Maybe someone has gotten the helper already when unhelp above. * So need to wait it. */ synchronize_rcu(); } EXPORT_SYMBOL_GPL(nf_conntrack_helper_unregister); void nf_ct_helper_init(struct nf_conntrack_helper *helper, u16 l3num, u16 protonum, const char *name, u16 default_port, u16 spec_port, u32 id, const struct nf_conntrack_expect_policy *exp_pol, u32 expect_class_max, int (*help)(struct sk_buff *skb, unsigned int protoff, struct nf_conn *ct, enum ip_conntrack_info ctinfo), int (*from_nlattr)(struct nlattr *attr, struct nf_conn *ct), struct module *module) { helper->tuple.src.l3num = l3num; helper->tuple.dst.protonum = protonum; helper->tuple.src.u.all = htons(spec_port); helper->expect_policy = exp_pol; helper->expect_class_max = expect_class_max; helper->help = help; helper->from_nlattr = from_nlattr; helper->me = module; if (spec_port == default_port) snprintf(helper->name, sizeof(helper->name), "%s", name); else snprintf(helper->name, sizeof(helper->name), "%s-%u", name, id); } EXPORT_SYMBOL_GPL(nf_ct_helper_init); int nf_conntrack_helpers_register(struct nf_conntrack_helper *helper, unsigned int n) { unsigned int i; int err = 0; for (i = 0; i < n; i++) { err = nf_conntrack_helper_register(&helper[i]); if (err < 0) goto err; } return err; err: if (i > 0) nf_conntrack_helpers_unregister(helper, i); return err; } EXPORT_SYMBOL_GPL(nf_conntrack_helpers_register); void nf_conntrack_helpers_unregister(struct nf_conntrack_helper *helper, unsigned int n) { while (n-- > 0) nf_conntrack_helper_unregister(&helper[n]); } EXPORT_SYMBOL_GPL(nf_conntrack_helpers_unregister); static const struct nf_ct_ext_type helper_extend = { .len = sizeof(struct nf_conn_help), .align = __alignof__(struct nf_conn_help), .id = NF_CT_EXT_HELPER, }; int nf_conntrack_helper_pernet_init(struct net *net) { net->ct.auto_assign_helper_warned = false; net->ct.sysctl_auto_assign_helper = nf_ct_auto_assign_helper; return nf_conntrack_helper_init_sysctl(net); } void nf_conntrack_helper_pernet_fini(struct net *net) { nf_conntrack_helper_fini_sysctl(net); } int nf_conntrack_helper_init(void) { int ret; nf_ct_helper_hsize = 1; /* gets rounded up to use one page */ nf_ct_helper_hash = nf_ct_alloc_hashtable(&nf_ct_helper_hsize, 0); if (!nf_ct_helper_hash) return -ENOMEM; ret = nf_ct_extend_register(&helper_extend); if (ret < 0) { pr_err("nf_ct_helper: Unable to register helper extension.\n"); goto out_extend; } return 0; out_extend: nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_hsize); return ret; } void nf_conntrack_helper_fini(void) { nf_ct_extend_unregister(&helper_extend); nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_hsize); } |
| 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 | /* * net/dccp/diag.c * * An implementation of the DCCP protocol * Arnaldo Carvalho de Melo <acme@mandriva.com> * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ #include <linux/module.h> #include <linux/inet_diag.h> #include "ccid.h" #include "dccp.h" static void dccp_get_info(struct sock *sk, struct tcp_info *info) { struct dccp_sock *dp = dccp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); memset(info, 0, sizeof(*info)); info->tcpi_state = sk->sk_state; info->tcpi_retransmits = icsk->icsk_retransmits; info->tcpi_probes = icsk->icsk_probes_out; info->tcpi_backoff = icsk->icsk_backoff; info->tcpi_pmtu = icsk->icsk_pmtu_cookie; if (dp->dccps_hc_rx_ackvec != NULL) info->tcpi_options |= TCPI_OPT_SACK; if (dp->dccps_hc_rx_ccid != NULL) ccid_hc_rx_get_info(dp->dccps_hc_rx_ccid, sk, info); if (dp->dccps_hc_tx_ccid != NULL) ccid_hc_tx_get_info(dp->dccps_hc_tx_ccid, sk, info); } static void dccp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, void *_info) { r->idiag_rqueue = r->idiag_wqueue = 0; if (_info != NULL) dccp_get_info(sk, _info); } static void dccp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, const struct inet_diag_req_v2 *r, struct nlattr *bc) { inet_diag_dump_icsk(&dccp_hashinfo, skb, cb, r, bc); } static int dccp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh, const struct inet_diag_req_v2 *req) { return inet_diag_dump_one_icsk(&dccp_hashinfo, in_skb, nlh, req); } static const struct inet_diag_handler dccp_diag_handler = { .dump = dccp_diag_dump, .dump_one = dccp_diag_dump_one, .idiag_get_info = dccp_diag_get_info, .idiag_type = IPPROTO_DCCP, .idiag_info_size = sizeof(struct tcp_info), }; static int __init dccp_diag_init(void) { return inet_diag_register(&dccp_diag_handler); } static void __exit dccp_diag_fini(void) { inet_diag_unregister(&dccp_diag_handler); } module_init(dccp_diag_init); module_exit(dccp_diag_fini); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Arnaldo Carvalho de Melo <acme@mandriva.com>"); MODULE_DESCRIPTION("DCCP inet_diag handler"); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-33 /* AF_INET - IPPROTO_DCCP */); |
| 4493 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 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 | // SPDX-License-Identifier: GPL-2.0 /* * Detect hard lockups on a system * * started by Don Zickus, Copyright (C) 2010 Red Hat, Inc. * * Note: Most of this code is borrowed heavily from the original softlockup * detector, so thanks to Ingo for the initial implementation. * Some chunks also taken from the old x86-specific nmi watchdog code, thanks * to those contributors as well. */ #define pr_fmt(fmt) "NMI watchdog: " fmt #include <linux/nmi.h> #include <linux/atomic.h> #include <linux/module.h> #include <linux/sched/debug.h> #include <asm/irq_regs.h> #include <linux/perf_event.h> static DEFINE_PER_CPU(bool, hard_watchdog_warn); static DEFINE_PER_CPU(bool, watchdog_nmi_touch); static DEFINE_PER_CPU(struct perf_event *, watchdog_ev); static DEFINE_PER_CPU(struct perf_event *, dead_event); static struct cpumask dead_events_mask; static unsigned long hardlockup_allcpu_dumped; static atomic_t watchdog_cpus = ATOMIC_INIT(0); notrace void arch_touch_nmi_watchdog(void) { /* * Using __raw here because some code paths have * preemption enabled. If preemption is enabled * then interrupts should be enabled too, in which * case we shouldn't have to worry about the watchdog * going off. */ raw_cpu_write(watchdog_nmi_touch, true); } EXPORT_SYMBOL(arch_touch_nmi_watchdog); #ifdef CONFIG_HARDLOCKUP_CHECK_TIMESTAMP static DEFINE_PER_CPU(ktime_t, last_timestamp); static DEFINE_PER_CPU(unsigned int, nmi_rearmed); static ktime_t watchdog_hrtimer_sample_threshold __read_mostly; void watchdog_update_hrtimer_threshold(u64 period) { /* * The hrtimer runs with a period of (watchdog_threshold * 2) / 5 * * So it runs effectively with 2.5 times the rate of the NMI * watchdog. That means the hrtimer should fire 2-3 times before * the NMI watchdog expires. The NMI watchdog on x86 is based on * unhalted CPU cycles, so if Turbo-Mode is enabled the CPU cycles * might run way faster than expected and the NMI fires in a * smaller period than the one deduced from the nominal CPU * frequency. Depending on the Turbo-Mode factor this might be fast * enough to get the NMI period smaller than the hrtimer watchdog * period and trigger false positives. * * The sample threshold is used to check in the NMI handler whether * the minimum time between two NMI samples has elapsed. That * prevents false positives. * * Set this to 4/5 of the actual watchdog threshold period so the * hrtimer is guaranteed to fire at least once within the real * watchdog threshold. */ watchdog_hrtimer_sample_threshold = period * 2; } static bool watchdog_check_timestamp(void) { ktime_t delta, now = ktime_get_mono_fast_ns(); delta = now - __this_cpu_read(last_timestamp); if (delta < watchdog_hrtimer_sample_threshold) { /* * If ktime is jiffies based, a stalled timer would prevent * jiffies from being incremented and the filter would look * at a stale timestamp and never trigger. */ if (__this_cpu_inc_return(nmi_rearmed) < 10) return false; } __this_cpu_write(nmi_rearmed, 0); __this_cpu_write(last_timestamp, now); return true; } #else static inline bool watchdog_check_timestamp(void) { return true; } #endif static struct perf_event_attr wd_hw_attr = { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES, .size = sizeof(struct perf_event_attr), .pinned = 1, .disabled = 1, }; /* Callback function for perf event subsystem */ static void watchdog_overflow_callback(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs) { /* Ensure the watchdog never gets throttled */ event->hw.interrupts = 0; if (__this_cpu_read(watchdog_nmi_touch) == true) { __this_cpu_write(watchdog_nmi_touch, false); return; } if (!watchdog_check_timestamp()) return; /* check for a hardlockup * This is done by making sure our timer interrupt * is incrementing. The timer interrupt should have * fired multiple times before we overflow'd. If it hasn't * then this is a good indication the cpu is stuck */ if (is_hardlockup()) { int this_cpu = smp_processor_id(); /* only print hardlockups once */ if (__this_cpu_read(hard_watchdog_warn) == true) return; pr_emerg("Watchdog detected hard LOCKUP on cpu %d", this_cpu); print_modules(); print_irqtrace_events(current); if (regs) show_regs(regs); else dump_stack(); /* * Perform all-CPU dump only once to avoid multiple hardlockups * generating interleaving traces */ if (sysctl_hardlockup_all_cpu_backtrace && !test_and_set_bit(0, &hardlockup_allcpu_dumped)) trigger_allbutself_cpu_backtrace(); if (hardlockup_panic) nmi_panic(regs, "Hard LOCKUP"); __this_cpu_write(hard_watchdog_warn, true); return; } __this_cpu_write(hard_watchdog_warn, false); return; } static int hardlockup_detector_event_create(void) { unsigned int cpu = smp_processor_id(); struct perf_event_attr *wd_attr; struct perf_event *evt; wd_attr = &wd_hw_attr; wd_attr->sample_period = hw_nmi_get_sample_period(watchdog_thresh); /* Try to register using hardware perf events */ evt = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL); if (IS_ERR(evt)) { pr_info("Perf event create on CPU %d failed with %ld\n", cpu, PTR_ERR(evt)); return PTR_ERR(evt); } this_cpu_write(watchdog_ev, evt); return 0; } /** * hardlockup_detector_perf_enable - Enable the local event */ void hardlockup_detector_perf_enable(void) { if (hardlockup_detector_event_create()) return; /* use original value for check */ if (!atomic_fetch_inc(&watchdog_cpus)) pr_info("Enabled. Permanently consumes one hw-PMU counter.\n"); perf_event_enable(this_cpu_read(watchdog_ev)); } /** * hardlockup_detector_perf_disable - Disable the local event */ void hardlockup_detector_perf_disable(void) { struct perf_event *event = this_cpu_read(watchdog_ev); if (event) { perf_event_disable(event); this_cpu_write(watchdog_ev, NULL); this_cpu_write(dead_event, event); cpumask_set_cpu(smp_processor_id(), &dead_events_mask); atomic_dec(&watchdog_cpus); } } /** * hardlockup_detector_perf_cleanup - Cleanup disabled events and destroy them * * Called from lockup_detector_cleanup(). Serialized by the caller. */ void hardlockup_detector_perf_cleanup(void) { int cpu; for_each_cpu(cpu, &dead_events_mask) { struct perf_event *event = per_cpu(dead_event, cpu); /* * Required because for_each_cpu() reports unconditionally * CPU0 as set on UP kernels. Sigh. */ if (event) perf_event_release_kernel(event); per_cpu(dead_event, cpu) = NULL; } cpumask_clear(&dead_events_mask); } /** * hardlockup_detector_perf_stop - Globally stop watchdog events * * Special interface for x86 to handle the perf HT bug. */ void __init hardlockup_detector_perf_stop(void) { int cpu; lockdep_assert_cpus_held(); for_each_online_cpu(cpu) { struct perf_event *event = per_cpu(watchdog_ev, cpu); if (event) perf_event_disable(event); } } /** * hardlockup_detector_perf_restart - Globally restart watchdog events * * Special interface for x86 to handle the perf HT bug. */ void __init hardlockup_detector_perf_restart(void) { int cpu; lockdep_assert_cpus_held(); if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) return; for_each_online_cpu(cpu) { struct perf_event *event = per_cpu(watchdog_ev, cpu); if (event) perf_event_enable(event); } } /** * hardlockup_detector_perf_init - Probe whether NMI event is available at all */ int __init hardlockup_detector_perf_init(void) { int ret = hardlockup_detector_event_create(); if (ret) { pr_info("Perf NMI watchdog permanently disabled\n"); } else { perf_event_release_kernel(this_cpu_read(watchdog_ev)); this_cpu_write(watchdog_ev, NULL); } return ret; } |
| 5 3 3 3 3 3 3 1 43 42 41 40 40 3 3 1 6 50 49 48 48 47 17 43 3 3 3 44 44 6 39 39 39 36 39 39 39 36 43 4 3 4 3 1 1 4 2 2 2 2 4 4 4 4 2 1 1 7 9 9 8 4 4 74 73 74 47 46 47 47 21 14 21 10 9 21 47 21 46 46 4 35 6 30 6 5 1 5 5 4 35 36 36 36 6 31 31 31 31 31 35 30 35 34 27 27 12 25 5 5 5 5 5 5 5 13 23 7 23 8 23 5 23 18 23 18 23 5 19 26 7 25 2 26 17 15 2 1 1 23 5 5 23 25 4 4 4 4 10 1 1 9 10 10 10 10 10 1 1 1 1 1 1 1 1 3 3 3 15 15 15 9 9 15 15 15 15 13 10 10 10 8 10 10 6 6 6 6 15 15 11 9 4 4 4 4 4 4 3 4 4 4 4 4 2 4 4 4 4 4 4 2 2 4 4 4 4 4 3 2 3 4 12 11 20 11 11 10 11 11 7 8 20 20 20 7 13 20 2 2 2 20 42 2 41 37 1 33 1 34 28 6 4 1 3 2 5 5 5 5 5 5 5 4 3 7 6 6 6 6 3 3 3 1 1 1 2 2 1 1 1 1 1 1 1 1 1 41 1 1 2 2 2 2 1 2 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 3 3 3 3 2 2 2 2 2 2 2 1 1 2 5 5 5 5 4 4 1 1 2 1 2 2 2 2 2 2 1 2 2 2 2 2 10 44 1 1 2 78 78 76 13 62 63 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 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 | /* * fs/f2fs/file.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ #include <linux/fs.h> #include <linux/f2fs_fs.h> #include <linux/stat.h> #include <linux/buffer_head.h> #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/falloc.h> #include <linux/types.h> #include <linux/compat.h> #include <linux/uaccess.h> #include <linux/mount.h> #include <linux/pagevec.h> #include <linux/uio.h> #include <linux/uuid.h> #include <linux/file.h> #include "f2fs.h" #include "node.h" #include "segment.h" #include "xattr.h" #include "acl.h" #include "gc.h" #include "trace.h" #include <trace/events/f2fs.h> static int f2fs_filemap_fault(struct vm_fault *vmf) { struct inode *inode = file_inode(vmf->vma->vm_file); int err; down_read(&F2FS_I(inode)->i_mmap_sem); err = filemap_fault(vmf); up_read(&F2FS_I(inode)->i_mmap_sem); return err; } static int f2fs_vm_page_mkwrite(struct vm_fault *vmf) { struct page *page = vmf->page; struct inode *inode = file_inode(vmf->vma->vm_file); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct dnode_of_data dn; int err; sb_start_pagefault(inode->i_sb); f2fs_bug_on(sbi, f2fs_has_inline_data(inode)); /* block allocation */ f2fs_lock_op(sbi); set_new_dnode(&dn, inode, NULL, NULL, 0); err = f2fs_reserve_block(&dn, page->index); if (err) { f2fs_unlock_op(sbi); goto out; } f2fs_put_dnode(&dn); f2fs_unlock_op(sbi); f2fs_balance_fs(sbi, dn.node_changed); file_update_time(vmf->vma->vm_file); down_read(&F2FS_I(inode)->i_mmap_sem); lock_page(page); if (unlikely(page->mapping != inode->i_mapping || page_offset(page) > i_size_read(inode) || !PageUptodate(page))) { unlock_page(page); err = -EFAULT; goto out_sem; } /* * check to see if the page is mapped already (no holes) */ if (PageMappedToDisk(page)) goto mapped; /* page is wholly or partially inside EOF */ if (((loff_t)(page->index + 1) << PAGE_SHIFT) > i_size_read(inode)) { unsigned offset; offset = i_size_read(inode) & ~PAGE_MASK; zero_user_segment(page, offset, PAGE_SIZE); } set_page_dirty(page); if (!PageUptodate(page)) SetPageUptodate(page); f2fs_update_iostat(sbi, APP_MAPPED_IO, F2FS_BLKSIZE); trace_f2fs_vm_page_mkwrite(page, DATA); mapped: /* fill the page */ f2fs_wait_on_page_writeback(page, DATA, false); /* wait for GCed encrypted page writeback */ if (f2fs_encrypted_file(inode)) f2fs_wait_on_block_writeback(sbi, dn.data_blkaddr); out_sem: up_read(&F2FS_I(inode)->i_mmap_sem); out: sb_end_pagefault(inode->i_sb); f2fs_update_time(sbi, REQ_TIME); return block_page_mkwrite_return(err); } static const struct vm_operations_struct f2fs_file_vm_ops = { .fault = f2fs_filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = f2fs_vm_page_mkwrite, }; static int get_parent_ino(struct inode *inode, nid_t *pino) { struct dentry *dentry; inode = igrab(inode); dentry = d_find_any_alias(inode); iput(inode); if (!dentry) return 0; *pino = parent_ino(dentry); dput(dentry); return 1; } static inline bool need_do_checkpoint(struct inode *inode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); bool need_cp = false; if (!S_ISREG(inode->i_mode) || inode->i_nlink != 1) need_cp = true; else if (is_sbi_flag_set(sbi, SBI_NEED_CP)) need_cp = true; else if (file_wrong_pino(inode)) need_cp = true; else if (!space_for_roll_forward(sbi)) need_cp = true; else if (!is_checkpointed_node(sbi, F2FS_I(inode)->i_pino)) need_cp = true; else if (test_opt(sbi, FASTBOOT)) need_cp = true; else if (sbi->active_logs == 2) need_cp = true; return need_cp; } static bool need_inode_page_update(struct f2fs_sb_info *sbi, nid_t ino) { struct page *i = find_get_page(NODE_MAPPING(sbi), ino); bool ret = false; /* But we need to avoid that there are some inode updates */ if ((i && PageDirty(i)) || need_inode_block_update(sbi, ino)) ret = true; f2fs_put_page(i, 0); return ret; } static void try_to_fix_pino(struct inode *inode) { struct f2fs_inode_info *fi = F2FS_I(inode); nid_t pino; down_write(&fi->i_sem); if (file_wrong_pino(inode) && inode->i_nlink == 1 && get_parent_ino(inode, &pino)) { f2fs_i_pino_write(inode, pino); file_got_pino(inode); } up_write(&fi->i_sem); } static int f2fs_do_sync_file(struct file *file, loff_t start, loff_t end, int datasync, bool atomic) { struct inode *inode = file->f_mapping->host; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); nid_t ino = inode->i_ino; int ret = 0; bool need_cp = false; struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, .nr_to_write = LONG_MAX, .for_reclaim = 0, }; if (unlikely(f2fs_readonly(inode->i_sb))) return 0; trace_f2fs_sync_file_enter(inode); if (S_ISDIR(inode->i_mode)) goto go_write; /* if fdatasync is triggered, let's do in-place-update */ if (datasync || get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks) set_inode_flag(inode, FI_NEED_IPU); ret = file_write_and_wait_range(file, start, end); clear_inode_flag(inode, FI_NEED_IPU); if (ret) { trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret); return ret; } /* if the inode is dirty, let's recover all the time */ if (!f2fs_skip_inode_update(inode, datasync)) { f2fs_write_inode(inode, NULL); goto go_write; } /* * if there is no written data, don't waste time to write recovery info. */ if (!is_inode_flag_set(inode, FI_APPEND_WRITE) && !exist_written_data(sbi, ino, APPEND_INO)) { /* it may call write_inode just prior to fsync */ if (need_inode_page_update(sbi, ino)) goto go_write; if (is_inode_flag_set(inode, FI_UPDATE_WRITE) || exist_written_data(sbi, ino, UPDATE_INO)) goto flush_out; goto out; } go_write: /* * Both of fdatasync() and fsync() are able to be recovered from * sudden-power-off. */ down_read(&F2FS_I(inode)->i_sem); need_cp = need_do_checkpoint(inode); up_read(&F2FS_I(inode)->i_sem); if (need_cp) { /* all the dirty node pages should be flushed for POR */ ret = f2fs_sync_fs(inode->i_sb, 1); /* * We've secured consistency through sync_fs. Following pino * will be used only for fsynced inodes after checkpoint. */ try_to_fix_pino(inode); clear_inode_flag(inode, FI_APPEND_WRITE); clear_inode_flag(inode, FI_UPDATE_WRITE); goto out; } sync_nodes: ret = fsync_node_pages(sbi, inode, &wbc, atomic); if (ret) goto out; /* if cp_error was enabled, we should avoid infinite loop */ if (unlikely(f2fs_cp_error(sbi))) { ret = -EIO; goto out; } if (need_inode_block_update(sbi, ino)) { f2fs_mark_inode_dirty_sync(inode, true); f2fs_write_inode(inode, NULL); goto sync_nodes; } /* * If it's atomic_write, it's just fine to keep write ordering. So * here we don't need to wait for node write completion, since we use * node chain which serializes node blocks. If one of node writes are * reordered, we can see simply broken chain, resulting in stopping * roll-forward recovery. It means we'll recover all or none node blocks * given fsync mark. */ if (!atomic) { ret = wait_on_node_pages_writeback(sbi, ino); if (ret) goto out; } /* once recovery info is written, don't need to tack this */ remove_ino_entry(sbi, ino, APPEND_INO); clear_inode_flag(inode, FI_APPEND_WRITE); flush_out: remove_ino_entry(sbi, ino, UPDATE_INO); clear_inode_flag(inode, FI_UPDATE_WRITE); if (!atomic) ret = f2fs_issue_flush(sbi); f2fs_update_time(sbi, REQ_TIME); out: trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret); f2fs_trace_ios(NULL, 1); return ret; } int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) { return f2fs_do_sync_file(file, start, end, datasync, false); } static pgoff_t __get_first_dirty_index(struct address_space *mapping, pgoff_t pgofs, int whence) { struct pagevec pvec; int nr_pages; if (whence != SEEK_DATA) return 0; /* find first dirty page index */ pagevec_init(&pvec, 0); nr_pages = pagevec_lookup_tag(&pvec, mapping, &pgofs, PAGECACHE_TAG_DIRTY, 1); pgofs = nr_pages ? pvec.pages[0]->index : ULONG_MAX; pagevec_release(&pvec); return pgofs; } static bool __found_offset(struct f2fs_sb_info *sbi, block_t blkaddr, pgoff_t dirty, pgoff_t pgofs, int whence) { switch (whence) { case SEEK_DATA: if ((blkaddr == NEW_ADDR && dirty == pgofs) || is_valid_data_blkaddr(sbi, blkaddr)) return true; break; case SEEK_HOLE: if (blkaddr == NULL_ADDR) return true; break; } return false; } static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence) { struct inode *inode = file->f_mapping->host; loff_t maxbytes = inode->i_sb->s_maxbytes; struct dnode_of_data dn; pgoff_t pgofs, end_offset, dirty; loff_t data_ofs = offset; loff_t isize; int err = 0; inode_lock(inode); isize = i_size_read(inode); if (offset >= isize) goto fail; /* handle inline data case */ if (f2fs_has_inline_data(inode) || f2fs_has_inline_dentry(inode)) { if (whence == SEEK_HOLE) data_ofs = isize; goto found; } pgofs = (pgoff_t)(offset >> PAGE_SHIFT); dirty = __get_first_dirty_index(inode->i_mapping, pgofs, whence); for (; data_ofs < isize; data_ofs = (loff_t)pgofs << PAGE_SHIFT) { set_new_dnode(&dn, inode, NULL, NULL, 0); err = get_dnode_of_data(&dn, pgofs, LOOKUP_NODE); if (err && err != -ENOENT) { goto fail; } else if (err == -ENOENT) { /* direct node does not exists */ if (whence == SEEK_DATA) { pgofs = get_next_page_offset(&dn, pgofs); continue; } else { goto found; } } end_offset = ADDRS_PER_PAGE(dn.node_page, inode); /* find data/hole in dnode block */ for (; dn.ofs_in_node < end_offset; dn.ofs_in_node++, pgofs++, data_ofs = (loff_t)pgofs << PAGE_SHIFT) { block_t blkaddr; blkaddr = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node); if (__is_valid_data_blkaddr(blkaddr) && !f2fs_is_valid_blkaddr(F2FS_I_SB(inode), blkaddr, DATA_GENERIC)) { f2fs_put_dnode(&dn); goto fail; } if (__found_offset(F2FS_I_SB(inode), blkaddr, dirty, pgofs, whence)) { f2fs_put_dnode(&dn); goto found; } } f2fs_put_dnode(&dn); } if (whence == SEEK_DATA) goto fail; found: if (whence == SEEK_HOLE && data_ofs > isize) data_ofs = isize; inode_unlock(inode); return vfs_setpos(file, data_ofs, maxbytes); fail: inode_unlock(inode); return -ENXIO; } static loff_t f2fs_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file->f_mapping->host; loff_t maxbytes = inode->i_sb->s_maxbytes; switch (whence) { case SEEK_SET: case SEEK_CUR: case SEEK_END: return generic_file_llseek_size(file, offset, whence, maxbytes, i_size_read(inode)); case SEEK_DATA: case SEEK_HOLE: if (offset < 0) return -ENXIO; return f2fs_seek_block(file, offset, whence); } return -EINVAL; } static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma) { struct inode *inode = file_inode(file); int err; /* we don't need to use inline_data strictly */ err = f2fs_convert_inline_inode(inode); if (err) return err; file_accessed(file); vma->vm_ops = &f2fs_file_vm_ops; return 0; } static int f2fs_file_open(struct inode *inode, struct file *filp) { struct dentry *dir; if (f2fs_encrypted_inode(inode)) { int ret = fscrypt_get_encryption_info(inode); if (ret) return -EACCES; if (!fscrypt_has_encryption_key(inode)) return -ENOKEY; } dir = dget_parent(file_dentry(filp)); if (f2fs_encrypted_inode(d_inode(dir)) && !fscrypt_has_permitted_context(d_inode(dir), inode)) { dput(dir); return -EPERM; } dput(dir); return dquot_file_open(inode, filp); } int truncate_data_blocks_range(struct dnode_of_data *dn, int count) { struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); struct f2fs_node *raw_node; int nr_free = 0, ofs = dn->ofs_in_node, len = count; __le32 *addr; int base = 0; if (IS_INODE(dn->node_page) && f2fs_has_extra_attr(dn->inode)) base = get_extra_isize(dn->inode); raw_node = F2FS_NODE(dn->node_page); addr = blkaddr_in_node(raw_node) + base + ofs; for (; count > 0; count--, addr++, dn->ofs_in_node++) { block_t blkaddr = le32_to_cpu(*addr); if (blkaddr == NULL_ADDR) continue; dn->data_blkaddr = NULL_ADDR; set_data_blkaddr(dn); if (__is_valid_data_blkaddr(blkaddr) && !f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC)) continue; invalidate_blocks(sbi, blkaddr); if (dn->ofs_in_node == 0 && IS_INODE(dn->node_page)) clear_inode_flag(dn->inode, FI_FIRST_BLOCK_WRITTEN); nr_free++; } if (nr_free) { pgoff_t fofs; /* * once we invalidate valid blkaddr in range [ofs, ofs + count], * we will invalidate all blkaddr in the whole range. */ fofs = start_bidx_of_node(ofs_of_node(dn->node_page), dn->inode) + ofs; f2fs_update_extent_cache_range(dn, fofs, 0, len); dec_valid_block_count(sbi, dn->inode, nr_free); } dn->ofs_in_node = ofs; f2fs_update_time(sbi, REQ_TIME); trace_f2fs_truncate_data_blocks_range(dn->inode, dn->nid, dn->ofs_in_node, nr_free); return nr_free; } void truncate_data_blocks(struct dnode_of_data *dn) { truncate_data_blocks_range(dn, ADDRS_PER_BLOCK); } static int truncate_partial_data_page(struct inode *inode, u64 from, bool cache_only) { unsigned offset = from & (PAGE_SIZE - 1); pgoff_t index = from >> PAGE_SHIFT; struct address_space *mapping = inode->i_mapping; struct page *page; if (!offset && !cache_only) return 0; if (cache_only) { page = find_lock_page(mapping, index); if (page && PageUptodate(page)) goto truncate_out; f2fs_put_page(page, 1); return 0; } page = get_lock_data_page(inode, index, true); if (IS_ERR(page)) return PTR_ERR(page) == -ENOENT ? 0 : PTR_ERR(page); truncate_out: f2fs_wait_on_page_writeback(page, DATA, true); zero_user(page, offset, PAGE_SIZE - offset); /* An encrypted inode should have a key and truncate the last page. */ f2fs_bug_on(F2FS_I_SB(inode), cache_only && f2fs_encrypted_inode(inode)); if (!cache_only) set_page_dirty(page); f2fs_put_page(page, 1); return 0; } int truncate_blocks(struct inode *inode, u64 from, bool lock) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); unsigned int blocksize = inode->i_sb->s_blocksize; struct dnode_of_data dn; pgoff_t free_from; int count = 0, err = 0; struct page *ipage; bool truncate_page = false; trace_f2fs_truncate_blocks_enter(inode, from); free_from = (pgoff_t)F2FS_BYTES_TO_BLK(from + blocksize - 1); if (free_from >= sbi->max_file_blocks) goto free_partial; if (lock) f2fs_lock_op(sbi); ipage = get_node_page(sbi, inode->i_ino); if (IS_ERR(ipage)) { err = PTR_ERR(ipage); goto out; } if (f2fs_has_inline_data(inode)) { truncate_inline_inode(inode, ipage, from); f2fs_put_page(ipage, 1); truncate_page = true; goto out; } set_new_dnode(&dn, inode, ipage, NULL, 0); err = get_dnode_of_data(&dn, free_from, LOOKUP_NODE_RA); if (err) { if (err == -ENOENT) goto free_next; goto out; } count = ADDRS_PER_PAGE(dn.node_page, inode); count -= dn.ofs_in_node; f2fs_bug_on(sbi, count < 0); if (dn.ofs_in_node || IS_INODE(dn.node_page)) { truncate_data_blocks_range(&dn, count); free_from += count; } f2fs_put_dnode(&dn); free_next: err = truncate_inode_blocks(inode, free_from); out: if (lock) f2fs_unlock_op(sbi); free_partial: /* lastly zero out the first data page */ if (!err) err = truncate_partial_data_page(inode, from, truncate_page); trace_f2fs_truncate_blocks_exit(inode, err); return err; } int f2fs_truncate(struct inode *inode) { int err; if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))) return 0; trace_f2fs_truncate(inode); #ifdef CONFIG_F2FS_FAULT_INJECTION if (time_to_inject(F2FS_I_SB(inode), FAULT_TRUNCATE)) { f2fs_show_injection_info(FAULT_TRUNCATE); return -EIO; } #endif /* we should check inline_data size */ if (!f2fs_may_inline_data(inode)) { err = f2fs_convert_inline_inode(inode); if (err) return err; } err = truncate_blocks(inode, i_size_read(inode), true); if (err) return err; inode->i_mtime = inode->i_ctime = current_time(inode); f2fs_mark_inode_dirty_sync(inode, false); return 0; } int f2fs_getattr(const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct f2fs_inode_info *fi = F2FS_I(inode); unsigned int flags; flags = fi->i_flags & (FS_FL_USER_VISIBLE | FS_PROJINHERIT_FL); if (flags & FS_APPEND_FL) stat->attributes |= STATX_ATTR_APPEND; if (flags & FS_COMPR_FL) stat->attributes |= STATX_ATTR_COMPRESSED; if (f2fs_encrypted_inode(inode)) stat->attributes |= STATX_ATTR_ENCRYPTED; if (flags & FS_IMMUTABLE_FL) stat->attributes |= STATX_ATTR_IMMUTABLE; if (flags & FS_NODUMP_FL) stat->attributes |= STATX_ATTR_NODUMP; stat->attributes_mask |= (STATX_ATTR_APPEND | STATX_ATTR_COMPRESSED | STATX_ATTR_ENCRYPTED | STATX_ATTR_IMMUTABLE | STATX_ATTR_NODUMP); generic_fillattr(inode, stat); /* we need to show initial sectors used for inline_data/dentries */ if ((S_ISREG(inode->i_mode) && f2fs_has_inline_data(inode)) || f2fs_has_inline_dentry(inode)) stat->blocks += (stat->size + 511) >> 9; return 0; } #ifdef CONFIG_F2FS_FS_POSIX_ACL static void __setattr_copy(struct inode *inode, const struct iattr *attr) { unsigned int ia_valid = attr->ia_valid; if (ia_valid & ATTR_UID) inode->i_uid = attr->ia_uid; if (ia_valid & ATTR_GID) inode->i_gid = attr->ia_gid; if (ia_valid & ATTR_ATIME) inode->i_atime = timespec_trunc(attr->ia_atime, inode->i_sb->s_time_gran); if (ia_valid & ATTR_MTIME) inode->i_mtime = timespec_trunc(attr->ia_mtime, inode->i_sb->s_time_gran); if (ia_valid & ATTR_CTIME) inode->i_ctime = timespec_trunc(attr->ia_ctime, inode->i_sb->s_time_gran); if (ia_valid & ATTR_MODE) { umode_t mode = attr->ia_mode; if (!in_group_p(inode->i_gid) && !capable_wrt_inode_uidgid(inode, CAP_FSETID)) mode &= ~S_ISGID; set_acl_inode(inode, mode); } } #else #define __setattr_copy setattr_copy #endif int f2fs_setattr(struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); int err; bool size_changed = false; err = setattr_prepare(dentry, attr); if (err) return err; if (is_quota_modification(inode, attr)) { err = dquot_initialize(inode); if (err) return err; } if ((attr->ia_valid & ATTR_UID && !uid_eq(attr->ia_uid, inode->i_uid)) || (attr->ia_valid & ATTR_GID && !gid_eq(attr->ia_gid, inode->i_gid))) { err = dquot_transfer(inode, attr); if (err) return err; } if (attr->ia_valid & ATTR_SIZE) { if (f2fs_encrypted_inode(inode)) { err = fscrypt_get_encryption_info(inode); if (err) return err; if (!fscrypt_has_encryption_key(inode)) return -ENOKEY; } if (attr->ia_size <= i_size_read(inode)) { down_write(&F2FS_I(inode)->i_mmap_sem); truncate_setsize(inode, attr->ia_size); err = f2fs_truncate(inode); up_write(&F2FS_I(inode)->i_mmap_sem); if (err) return err; } else { /* * do not trim all blocks after i_size if target size is * larger than i_size. */ down_write(&F2FS_I(inode)->i_mmap_sem); truncate_setsize(inode, attr->ia_size); up_write(&F2FS_I(inode)->i_mmap_sem); /* should convert inline inode here */ if (!f2fs_may_inline_data(inode)) { err = f2fs_convert_inline_inode(inode); if (err) return err; } inode->i_mtime = inode->i_ctime = current_time(inode); } size_changed = true; } __setattr_copy(inode, attr); if (attr->ia_valid & ATTR_MODE) { err = posix_acl_chmod(inode, get_inode_mode(inode)); if (err || is_inode_flag_set(inode, FI_ACL_MODE)) { inode->i_mode = F2FS_I(inode)->i_acl_mode; clear_inode_flag(inode, FI_ACL_MODE); } } /* file size may changed here */ f2fs_mark_inode_dirty_sync(inode, size_changed); /* inode change will produce dirty node pages flushed by checkpoint */ f2fs_balance_fs(F2FS_I_SB(inode), true); return err; } const struct inode_operations f2fs_file_inode_operations = { .getattr = f2fs_getattr, .setattr = f2fs_setattr, .get_acl = f2fs_get_acl, .set_acl = f2fs_set_acl, #ifdef CONFIG_F2FS_FS_XATTR .listxattr = f2fs_listxattr, #endif .fiemap = f2fs_fiemap, }; static int fill_zero(struct inode *inode, pgoff_t index, loff_t start, loff_t len) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct page *page; if (!len) return 0; f2fs_balance_fs(sbi, true); f2fs_lock_op(sbi); page = get_new_data_page(inode, NULL, index, false); f2fs_unlock_op(sbi); if (IS_ERR(page)) return PTR_ERR(page); f2fs_wait_on_page_writeback(page, DATA, true); zero_user(page, start, len); set_page_dirty(page); f2fs_put_page(page, 1); return 0; } int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end) { int err; while (pg_start < pg_end) { struct dnode_of_data dn; pgoff_t end_offset, count; set_new_dnode(&dn, inode, NULL, NULL, 0); err = get_dnode_of_data(&dn, pg_start, LOOKUP_NODE); if (err) { if (err == -ENOENT) { pg_start++; continue; } return err; } end_offset = ADDRS_PER_PAGE(dn.node_page, inode); count = min(end_offset - dn.ofs_in_node, pg_end - pg_start); f2fs_bug_on(F2FS_I_SB(inode), count == 0 || count > end_offset); truncate_data_blocks_range(&dn, count); f2fs_put_dnode(&dn); pg_start += count; } return 0; } static int punch_hole(struct inode *inode, loff_t offset, loff_t len) { pgoff_t pg_start, pg_end; loff_t off_start, off_end; int ret; ret = f2fs_convert_inline_inode(inode); if (ret) return ret; pg_start = ((unsigned long long) offset) >> PAGE_SHIFT; pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT; off_start = offset & (PAGE_SIZE - 1); off_end = (offset + len) & (PAGE_SIZE - 1); if (pg_start == pg_end) { ret = fill_zero(inode, pg_start, off_start, off_end - off_start); if (ret) return ret; } else { if (off_start) { ret = fill_zero(inode, pg_start++, off_start, PAGE_SIZE - off_start); if (ret) return ret; } if (off_end) { ret = fill_zero(inode, pg_end, 0, off_end); if (ret) return ret; } if (pg_start < pg_end) { struct address_space *mapping = inode->i_mapping; loff_t blk_start, blk_end; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); f2fs_balance_fs(sbi, true); blk_start = (loff_t)pg_start << PAGE_SHIFT; blk_end = (loff_t)pg_end << PAGE_SHIFT; down_write(&F2FS_I(inode)->i_mmap_sem); truncate_inode_pages_range(mapping, blk_start, blk_end - 1); f2fs_lock_op(sbi); ret = truncate_hole(inode, pg_start, pg_end); f2fs_unlock_op(sbi); up_write(&F2FS_I(inode)->i_mmap_sem); } } return ret; } static int __read_out_blkaddrs(struct inode *inode, block_t *blkaddr, int *do_replace, pgoff_t off, pgoff_t len) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct dnode_of_data dn; int ret, done, i; next_dnode: set_new_dnode(&dn, inode, NULL, NULL, 0); ret = get_dnode_of_data(&dn, off, LOOKUP_NODE_RA); if (ret && ret != -ENOENT) { return ret; } else if (ret == -ENOENT) { if (dn.max_level == 0) return -ENOENT; done = min((pgoff_t)ADDRS_PER_BLOCK - dn.ofs_in_node, len); blkaddr += done; do_replace += done; goto next; } done = min((pgoff_t)ADDRS_PER_PAGE(dn.node_page, inode) - dn.ofs_in_node, len); for (i = 0; i < done; i++, blkaddr++, do_replace++, dn.ofs_in_node++) { *blkaddr = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node); if (!is_checkpointed_data(sbi, *blkaddr)) { if (test_opt(sbi, LFS)) { f2fs_put_dnode(&dn); return -ENOTSUPP; } /* do not invalidate this block address */ f2fs_update_data_blkaddr(&dn, NULL_ADDR); *do_replace = 1; } } f2fs_put_dnode(&dn); next: len -= done; off += done; if (len) goto next_dnode; return 0; } static int __roll_back_blkaddrs(struct inode *inode, block_t *blkaddr, int *do_replace, pgoff_t off, int len) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct dnode_of_data dn; int ret, i; for (i = 0; i < len; i++, do_replace++, blkaddr++) { if (*do_replace == 0) continue; set_new_dnode(&dn, inode, NULL, NULL, 0); ret = get_dnode_of_data(&dn, off + i, LOOKUP_NODE_RA); if (ret) { dec_valid_block_count(sbi, inode, 1); invalidate_blocks(sbi, *blkaddr); } else { f2fs_update_data_blkaddr(&dn, *blkaddr); } f2fs_put_dnode(&dn); } return 0; } static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode, block_t *blkaddr, int *do_replace, pgoff_t src, pgoff_t dst, pgoff_t len, bool full) { struct f2fs_sb_info *sbi = F2FS_I_SB(src_inode); pgoff_t i = 0; int ret; while (i < len) { if (blkaddr[i] == NULL_ADDR && !full) { i++; continue; } if (do_replace[i] || blkaddr[i] == NULL_ADDR) { struct dnode_of_data dn; struct node_info ni; size_t new_size; pgoff_t ilen; set_new_dnode(&dn, dst_inode, NULL, NULL, 0); ret = get_dnode_of_data(&dn, dst + i, ALLOC_NODE); if (ret) return ret; get_node_info(sbi, dn.nid, &ni); ilen = min((pgoff_t) ADDRS_PER_PAGE(dn.node_page, dst_inode) - dn.ofs_in_node, len - i); do { dn.data_blkaddr = datablock_addr(dn.inode, dn.node_page, dn.ofs_in_node); truncate_data_blocks_range(&dn, 1); if (do_replace[i]) { f2fs_i_blocks_write(src_inode, 1, false, false); f2fs_i_blocks_write(dst_inode, 1, true, false); f2fs_replace_block(sbi, &dn, dn.data_blkaddr, blkaddr[i], ni.version, true, false); do_replace[i] = 0; } dn.ofs_in_node++; i++; new_size = (loff_t)(dst + i) << PAGE_SHIFT; if (dst_inode->i_size < new_size) f2fs_i_size_write(dst_inode, new_size); } while (--ilen && (do_replace[i] || blkaddr[i] == NULL_ADDR)); f2fs_put_dnode(&dn); } else { struct page *psrc, *pdst; psrc = get_lock_data_page(src_inode, src + i, true); if (IS_ERR(psrc)) return PTR_ERR(psrc); pdst = get_new_data_page(dst_inode, NULL, dst + i, true); if (IS_ERR(pdst)) { f2fs_put_page(psrc, 1); return PTR_ERR(pdst); } f2fs_copy_page(psrc, pdst); set_page_dirty(pdst); f2fs_put_page(pdst, 1); f2fs_put_page(psrc, 1); ret = truncate_hole(src_inode, src + i, src + i + 1); if (ret) return ret; i++; } } return 0; } static int __exchange_data_block(struct inode *src_inode, struct inode *dst_inode, pgoff_t src, pgoff_t dst, pgoff_t len, bool full) { block_t *src_blkaddr; int *do_replace; pgoff_t olen; int ret; while (len) { olen = min((pgoff_t)4 * ADDRS_PER_BLOCK, len); src_blkaddr = kvzalloc(sizeof(block_t) * olen, GFP_KERNEL); if (!src_blkaddr) return -ENOMEM; do_replace = kvzalloc(sizeof(int) * olen, GFP_KERNEL); if (!do_replace) { kvfree(src_blkaddr); return -ENOMEM; } ret = __read_out_blkaddrs(src_inode, src_blkaddr, do_replace, src, olen); if (ret) goto roll_back; ret = __clone_blkaddrs(src_inode, dst_inode, src_blkaddr, do_replace, src, dst, olen, full); if (ret) goto roll_back; src += olen; dst += olen; len -= olen; kvfree(src_blkaddr); kvfree(do_replace); } return 0; roll_back: __roll_back_blkaddrs(src_inode, src_blkaddr, do_replace, src, len); kvfree(src_blkaddr); kvfree(do_replace); return ret; } static int f2fs_do_collapse(struct inode *inode, pgoff_t start, pgoff_t end) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); pgoff_t nrpages = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE; int ret; f2fs_balance_fs(sbi, true); f2fs_lock_op(sbi); f2fs_drop_extent_tree(inode); ret = __exchange_data_block(inode, inode, end, start, nrpages - end, true); f2fs_unlock_op(sbi); return ret; } static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len) { pgoff_t pg_start, pg_end; loff_t new_size; int ret; if (offset + len >= i_size_read(inode)) return -EINVAL; /* collapse range should be aligned to block size of f2fs. */ if (offset & (F2FS_BLKSIZE - 1) || len & (F2FS_BLKSIZE - 1)) return -EINVAL; ret = f2fs_convert_inline_inode(inode); if (ret) return ret; pg_start = offset >> PAGE_SHIFT; pg_end = (offset + len) >> PAGE_SHIFT; down_write(&F2FS_I(inode)->i_mmap_sem); /* write out all dirty pages from offset */ ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX); if (ret) goto out; truncate_pagecache(inode, offset); ret = f2fs_do_collapse(inode, pg_start, pg_end); if (ret) goto out; /* write out all moved pages, if possible */ filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX); truncate_pagecache(inode, offset); new_size = i_size_read(inode) - len; truncate_pagecache(inode, new_size); ret = truncate_blocks(inode, new_size, true); if (!ret) f2fs_i_size_write(inode, new_size); out: up_write(&F2FS_I(inode)->i_mmap_sem); return ret; } static int f2fs_do_zero_range(struct dnode_of_data *dn, pgoff_t start, pgoff_t end) { struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); pgoff_t index = start; unsigned int ofs_in_node = dn->ofs_in_node; blkcnt_t count = 0; int ret; for (; index < end; index++, dn->ofs_in_node++) { if (datablock_addr(dn->inode, dn->node_page, dn->ofs_in_node) == NULL_ADDR) count++; } dn->ofs_in_node = ofs_in_node; ret = reserve_new_blocks(dn, count); if (ret) return ret; dn->ofs_in_node = ofs_in_node; for (index = start; index < end; index++, dn->ofs_in_node++) { dn->data_blkaddr = datablock_addr(dn->inode, dn->node_page, dn->ofs_in_node); /* * reserve_new_blocks will not guarantee entire block * allocation. */ if (dn->data_blkaddr == NULL_ADDR) { ret = -ENOSPC; break; } if (dn->data_blkaddr != NEW_ADDR) { invalidate_blocks(sbi, dn->data_blkaddr); dn->data_blkaddr = NEW_ADDR; set_data_blkaddr(dn); } } f2fs_update_extent_cache_range(dn, start, 0, index - start); return ret; } static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len, int mode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct address_space *mapping = inode->i_mapping; pgoff_t index, pg_start, pg_end; loff_t new_size = i_size_read(inode); loff_t off_start, off_end; int ret = 0; ret = inode_newsize_ok(inode, (len + offset)); if (ret) return ret; ret = f2fs_convert_inline_inode(inode); if (ret) return ret; down_write(&F2FS_I(inode)->i_mmap_sem); ret = filemap_write_and_wait_range(mapping, offset, offset + len - 1); if (ret) goto out_sem; truncate_pagecache_range(inode, offset, offset + len - 1); pg_start = ((unsigned long long) offset) >> PAGE_SHIFT; pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT; off_start = offset & (PAGE_SIZE - 1); off_end = (offset + len) & (PAGE_SIZE - 1); if (pg_start == pg_end) { ret = fill_zero(inode, pg_start, off_start, off_end - off_start); if (ret) goto out_sem; new_size = max_t(loff_t, new_size, offset + len); } else { if (off_start) { ret = fill_zero(inode, pg_start++, off_start, PAGE_SIZE - off_start); if (ret) goto out_sem; new_size = max_t(loff_t, new_size, (loff_t)pg_start << PAGE_SHIFT); } for (index = pg_start; index < pg_end;) { struct dnode_of_data dn; unsigned int end_offset; pgoff_t end; f2fs_lock_op(sbi); set_new_dnode(&dn, inode, NULL, NULL, 0); ret = get_dnode_of_data(&dn, index, ALLOC_NODE); if (ret) { f2fs_unlock_op(sbi); goto out; } end_offset = ADDRS_PER_PAGE(dn.node_page, inode); end = min(pg_end, end_offset - dn.ofs_in_node + index); ret = f2fs_do_zero_range(&dn, index, end); f2fs_put_dnode(&dn); f2fs_unlock_op(sbi); f2fs_balance_fs(sbi, dn.node_changed); if (ret) goto out; index = end; new_size = max_t(loff_t, new_size, (loff_t)index << PAGE_SHIFT); } if (off_end) { ret = fill_zero(inode, pg_end, 0, off_end); if (ret) goto out; new_size = max_t(loff_t, new_size, offset + len); } } out: if (new_size > i_size_read(inode)) { if (mode & FALLOC_FL_KEEP_SIZE) file_set_keep_isize(inode); else f2fs_i_size_write(inode, new_size); } out_sem: up_write(&F2FS_I(inode)->i_mmap_sem); return ret; } static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); pgoff_t nr, pg_start, pg_end, delta, idx; loff_t new_size; int ret = 0; new_size = i_size_read(inode) + len; ret = inode_newsize_ok(inode, new_size); if (ret) return ret; if (offset >= i_size_read(inode)) return -EINVAL; /* insert range should be aligned to block size of f2fs. */ if (offset & (F2FS_BLKSIZE - 1) || len & (F2FS_BLKSIZE - 1)) return -EINVAL; ret = f2fs_convert_inline_inode(inode); if (ret) return ret; f2fs_balance_fs(sbi, true); down_write(&F2FS_I(inode)->i_mmap_sem); ret = truncate_blocks(inode, i_size_read(inode), true); if (ret) goto out; /* write out all dirty pages from offset */ ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX); if (ret) goto out; truncate_pagecache(inode, offset); pg_start = offset >> PAGE_SHIFT; pg_end = (offset + len) >> PAGE_SHIFT; delta = pg_end - pg_start; idx = (i_size_read(inode) + PAGE_SIZE - 1) / PAGE_SIZE; while (!ret && idx > pg_start) { nr = idx - pg_start; if (nr > delta) nr = delta; idx -= nr; f2fs_lock_op(sbi); f2fs_drop_extent_tree(inode); ret = __exchange_data_block(inode, inode, idx, idx + delta, nr, false); f2fs_unlock_op(sbi); } /* write out all moved pages, if possible */ filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX); truncate_pagecache(inode, offset); if (!ret) f2fs_i_size_write(inode, new_size); out: up_write(&F2FS_I(inode)->i_mmap_sem); return ret; } static int expand_inode_data(struct inode *inode, loff_t offset, loff_t len, int mode) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_map_blocks map = { .m_next_pgofs = NULL }; pgoff_t pg_end; loff_t new_size = i_size_read(inode); loff_t off_end; int err; err = inode_newsize_ok(inode, (len + offset)); if (err) return err; err = f2fs_convert_inline_inode(inode); if (err) return err; f2fs_balance_fs(sbi, true); pg_end = ((unsigned long long)offset + len) >> PAGE_SHIFT; off_end = (offset + len) & (PAGE_SIZE - 1); map.m_lblk = ((unsigned long long)offset) >> PAGE_SHIFT; map.m_len = pg_end - map.m_lblk; if (off_end) map.m_len++; err = f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_AIO); if (err) { pgoff_t last_off; if (!map.m_len) return err; last_off = map.m_lblk + map.m_len - 1; /* update new size to the failed position */ new_size = (last_off == pg_end) ? offset + len: (loff_t)(last_off + 1) << PAGE_SHIFT; } else { new_size = ((loff_t)pg_end << PAGE_SHIFT) + off_end; } if (!(mode & FALLOC_FL_KEEP_SIZE) && i_size_read(inode) < new_size) f2fs_i_size_write(inode, new_size); return err; } static long f2fs_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); long ret = 0; /* f2fs only support ->fallocate for regular file */ if (!S_ISREG(inode->i_mode)) return -EINVAL; if (f2fs_encrypted_inode(inode) && (mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE))) return -EOPNOTSUPP; if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_ZERO_RANGE | FALLOC_FL_INSERT_RANGE)) return -EOPNOTSUPP; inode_lock(inode); if (mode & FALLOC_FL_PUNCH_HOLE) { if (offset >= inode->i_size) goto out; ret = punch_hole(inode, offset, len); } else if (mode & FALLOC_FL_COLLAPSE_RANGE) { ret = f2fs_collapse_range(inode, offset, len); } else if (mode & FALLOC_FL_ZERO_RANGE) { ret = f2fs_zero_range(inode, offset, len, mode); } else if (mode & FALLOC_FL_INSERT_RANGE) { ret = f2fs_insert_range(inode, offset, len); } else { ret = expand_inode_data(inode, offset, len, mode); } if (!ret) { inode->i_mtime = inode->i_ctime = current_time(inode); f2fs_mark_inode_dirty_sync(inode, false); if (mode & FALLOC_FL_KEEP_SIZE) file_set_keep_isize(inode); f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); } out: inode_unlock(inode); trace_f2fs_fallocate(inode, mode, offset, len, ret); return ret; } static int f2fs_release_file(struct inode *inode, struct file *filp) { /* * f2fs_relase_file is called at every close calls. So we should * not drop any inmemory pages by close called by other process. */ if (!(filp->f_mode & FMODE_WRITE) || atomic_read(&inode->i_writecount) != 1) return 0; /* some remained atomic pages should discarded */ if (f2fs_is_atomic_file(inode)) drop_inmem_pages(inode); if (f2fs_is_volatile_file(inode)) { clear_inode_flag(inode, FI_VOLATILE_FILE); stat_dec_volatile_write(inode); set_inode_flag(inode, FI_DROP_CACHE); filemap_fdatawrite(inode->i_mapping); clear_inode_flag(inode, FI_DROP_CACHE); } return 0; } static int f2fs_file_flush(struct file *file, fl_owner_t id) { struct inode *inode = file_inode(file); /* * If the process doing a transaction is crashed, we should do * roll-back. Otherwise, other reader/write can see corrupted database * until all the writers close its file. Since this should be done * before dropping file lock, it needs to do in ->flush. */ if (f2fs_is_atomic_file(inode) && F2FS_I(inode)->inmem_task == current) drop_inmem_pages(inode); return 0; } static int f2fs_ioc_getflags(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); struct f2fs_inode_info *fi = F2FS_I(inode); unsigned int flags = fi->i_flags & (FS_FL_USER_VISIBLE | FS_PROJINHERIT_FL); return put_user(flags, (int __user *)arg); } static int __f2fs_ioc_setflags(struct inode *inode, unsigned int flags) { struct f2fs_inode_info *fi = F2FS_I(inode); unsigned int oldflags; /* Is it quota file? Do not allow user to mess with it */ if (IS_NOQUOTA(inode)) return -EPERM; flags = f2fs_mask_flags(inode->i_mode, flags); oldflags = fi->i_flags; if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) if (!capable(CAP_LINUX_IMMUTABLE)) return -EPERM; flags = flags & (FS_FL_USER_MODIFIABLE | FS_PROJINHERIT_FL); flags |= oldflags & ~(FS_FL_USER_MODIFIABLE | FS_PROJINHERIT_FL); fi->i_flags = flags; if (fi->i_flags & FS_PROJINHERIT_FL) set_inode_flag(inode, FI_PROJ_INHERIT); else clear_inode_flag(inode, FI_PROJ_INHERIT); inode->i_ctime = current_time(inode); f2fs_set_inode_flags(inode); f2fs_mark_inode_dirty_sync(inode, true); return 0; } static int f2fs_ioc_setflags(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); unsigned int flags; int ret; if (!inode_owner_or_capable(inode)) return -EACCES; if (get_user(flags, (int __user *)arg)) return -EFAULT; ret = mnt_want_write_file(filp); if (ret) return ret; inode_lock(inode); ret = __f2fs_ioc_setflags(inode, flags); inode_unlock(inode); mnt_drop_write_file(filp); return ret; } static int f2fs_ioc_getversion(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); return put_user(inode->i_generation, (int __user *)arg); } static int f2fs_ioc_start_atomic_write(struct file *filp) { struct inode *inode = file_inode(filp); int ret; if (!inode_owner_or_capable(inode)) return -EACCES; if (!S_ISREG(inode->i_mode)) return -EINVAL; ret = mnt_want_write_file(filp); if (ret) return ret; inode_lock(inode); down_write(&F2FS_I(inode)->dio_rwsem[WRITE]); if (f2fs_is_atomic_file(inode)) goto out; ret = f2fs_convert_inline_inode(inode); if (ret) goto out; set_inode_flag(inode, FI_ATOMIC_FILE); set_inode_flag(inode, FI_HOT_DATA); f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); if (!get_dirty_pages(inode)) goto inc_stat; f2fs_msg(F2FS_I_SB(inode)->sb, KERN_WARNING, "Unexpected flush for atomic writes: ino=%lu, npages=%u", inode->i_ino, get_dirty_pages(inode)); ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX); if (ret) { clear_inode_flag(inode, FI_ATOMIC_FILE); clear_inode_flag(inode, FI_HOT_DATA); goto out; } inc_stat: F2FS_I(inode)->inmem_task = current; stat_inc_atomic_write(inode); stat_update_max_atomic_write(inode); out: up_write(&F2FS_I(inode)->dio_rwsem[WRITE]); inode_unlock(inode); mnt_drop_write_file(filp); return ret; } static int f2fs_ioc_commit_atomic_write(struct file *filp) { struct inode *inode = file_inode(filp); int ret; if (!inode_owner_or_capable(inode)) return -EACCES; ret = mnt_want_write_file(filp); if (ret) return ret; inode_lock(inode); if (f2fs_is_volatile_file(inode)) goto err_out; if (f2fs_is_atomic_file(inode)) { ret = commit_inmem_pages(inode); if (ret) goto err_out; ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true); if (!ret) { clear_inode_flag(inode, FI_ATOMIC_FILE); clear_inode_flag(inode, FI_HOT_DATA); stat_dec_atomic_write(inode); } } else { ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 1, false); } err_out: inode_unlock(inode); mnt_drop_write_file(filp); return ret; } static int f2fs_ioc_start_volatile_write(struct file *filp) { struct inode *inode = file_inode(filp); int ret; if (!inode_owner_or_capable(inode)) return -EACCES; if (!S_ISREG(inode->i_mode)) return -EINVAL; ret = mnt_want_write_file(filp); if (ret) return ret; inode_lock(inode); if (f2fs_is_volatile_file(inode)) goto out; ret = f2fs_convert_inline_inode(inode); if (ret) goto out; stat_inc_volatile_write(inode); stat_update_max_volatile_write(inode); set_inode_flag(inode, FI_VOLATILE_FILE); f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); out: inode_unlock(inode); mnt_drop_write_file(filp); return ret; } static int f2fs_ioc_release_volatile_write(struct file *filp) { struct inode *inode = file_inode(filp); int ret; if (!inode_owner_or_capable(inode)) return -EACCES; ret = mnt_want_write_file(filp); if (ret) return ret; inode_lock(inode); if (!f2fs_is_volatile_file(inode)) goto out; if (!f2fs_is_first_block_written(inode)) { ret = truncate_partial_data_page(inode, 0, true); goto out; } ret = punch_hole(inode, 0, F2FS_BLKSIZE); out: inode_unlock(inode); mnt_drop_write_file(filp); return ret; } static int f2fs_ioc_abort_volatile_write(struct file *filp) { struct inode *inode = file_inode(filp); int ret; if (!inode_owner_or_capable(inode)) return -EACCES; ret = mnt_want_write_file(filp); if (ret) return ret; inode_lock(inode); if (f2fs_is_atomic_file(inode)) drop_inmem_pages(inode); if (f2fs_is_volatile_file(inode)) { clear_inode_flag(inode, FI_VOLATILE_FILE); stat_dec_volatile_write(inode); ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true); } inode_unlock(inode); mnt_drop_write_file(filp); f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); return ret; } static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct super_block *sb = sbi->sb; __u32 in; int ret = 0; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (get_user(in, (__u32 __user *)arg)) return -EFAULT; if (in != F2FS_GOING_DOWN_FULLSYNC) { ret = mnt_want_write_file(filp); if (ret) return ret; } switch (in) { case F2FS_GOING_DOWN_FULLSYNC: sb = freeze_bdev(sb->s_bdev); if (sb && !IS_ERR(sb)) { f2fs_stop_checkpoint(sbi, false); thaw_bdev(sb->s_bdev, sb); } break; case F2FS_GOING_DOWN_METASYNC: /* do checkpoint only */ f2fs_sync_fs(sb, 1); f2fs_stop_checkpoint(sbi, false); break; case F2FS_GOING_DOWN_NOSYNC: f2fs_stop_checkpoint(sbi, false); break; case F2FS_GOING_DOWN_METAFLUSH: sync_meta_pages(sbi, META, LONG_MAX, FS_META_IO); f2fs_stop_checkpoint(sbi, false); break; default: ret = -EINVAL; goto out; } f2fs_update_time(sbi, REQ_TIME); out: if (in != F2FS_GOING_DOWN_FULLSYNC) mnt_drop_write_file(filp); return ret; } static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); struct super_block *sb = inode->i_sb; struct request_queue *q = bdev_get_queue(sb->s_bdev); struct fstrim_range range; int ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!blk_queue_discard(q)) return -EOPNOTSUPP; if (copy_from_user(&range, (struct fstrim_range __user *)arg, sizeof(range))) return -EFAULT; ret = mnt_want_write_file(filp); if (ret) return ret; range.minlen = max((unsigned int)range.minlen, q->limits.discard_granularity); ret = f2fs_trim_fs(F2FS_SB(sb), &range); mnt_drop_write_file(filp); if (ret < 0) return ret; if (copy_to_user((struct fstrim_range __user *)arg, &range, sizeof(range))) return -EFAULT; f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); return 0; } static bool uuid_is_nonzero(__u8 u[16]) { int i; for (i = 0; i < 16; i++) if (u[i]) return true; return false; } static int f2fs_ioc_set_encryption_policy(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); return fscrypt_ioctl_set_policy(filp, (const void __user *)arg); } static int f2fs_ioc_get_encryption_policy(struct file *filp, unsigned long arg) { return fscrypt_ioctl_get_policy(filp, (void __user *)arg); } static int f2fs_ioc_get_encryption_pwsalt(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); int err; if (!f2fs_sb_has_crypto(inode->i_sb)) return -EOPNOTSUPP; if (uuid_is_nonzero(sbi->raw_super->encrypt_pw_salt)) goto got_it; err = mnt_want_write_file(filp); if (err) return err; /* update superblock with uuid */ generate_random_uuid(sbi->raw_super->encrypt_pw_salt); err = f2fs_commit_super(sbi, false); if (err) { /* undo new data */ memset(sbi->raw_super->encrypt_pw_salt, 0, 16); mnt_drop_write_file(filp); return err; } mnt_drop_write_file(filp); got_it: if (copy_to_user((__u8 __user *)arg, sbi->raw_super->encrypt_pw_salt, 16)) return -EFAULT; return 0; } static int f2fs_ioc_gc(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); __u32 sync; int ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (get_user(sync, (__u32 __user *)arg)) return -EFAULT; if (f2fs_readonly(sbi->sb)) return -EROFS; ret = mnt_want_write_file(filp); if (ret) return ret; if (!sync) { if (!mutex_trylock(&sbi->gc_mutex)) { ret = -EBUSY; goto out; } } else { mutex_lock(&sbi->gc_mutex); } ret = f2fs_gc(sbi, sync, true, NULL_SEGNO); out: mnt_drop_write_file(filp); return ret; } static int f2fs_ioc_gc_range(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_gc_range range; u64 end; int ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (copy_from_user(&range, (struct f2fs_gc_range __user *)arg, sizeof(range))) return -EFAULT; if (f2fs_readonly(sbi->sb)) return -EROFS; ret = mnt_want_write_file(filp); if (ret) return ret; end = range.start + range.len; if (range.start < MAIN_BLKADDR(sbi) || end >= MAX_BLKADDR(sbi)) return -EINVAL; do_more: if (!range.sync) { if (!mutex_trylock(&sbi->gc_mutex)) { ret = -EBUSY; goto out; } } else { mutex_lock(&sbi->gc_mutex); } ret = f2fs_gc(sbi, range.sync, true, GET_SEGNO(sbi, range.start)); range.start += BLKS_PER_SEC(sbi); if (range.start <= end) goto do_more; out: mnt_drop_write_file(filp); return ret; } static int f2fs_ioc_write_checkpoint(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); int ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (f2fs_readonly(sbi->sb)) return -EROFS; ret = mnt_want_write_file(filp); if (ret) return ret; ret = f2fs_sync_fs(sbi->sb, 1); mnt_drop_write_file(filp); return ret; } static int f2fs_defragment_range(struct f2fs_sb_info *sbi, struct file *filp, struct f2fs_defragment *range) { struct inode *inode = file_inode(filp); struct f2fs_map_blocks map = { .m_next_pgofs = NULL }; struct extent_info ei = {0,0,0}; pgoff_t pg_start, pg_end; unsigned int blk_per_seg = sbi->blocks_per_seg; unsigned int total = 0, sec_num; block_t blk_end = 0; bool fragmented = false; int err; /* if in-place-update policy is enabled, don't waste time here */ if (need_inplace_update_policy(inode, NULL)) return -EINVAL; pg_start = range->start >> PAGE_SHIFT; pg_end = (range->start + range->len) >> PAGE_SHIFT; f2fs_balance_fs(sbi, true); inode_lock(inode); /* writeback all dirty pages in the range */ err = filemap_write_and_wait_range(inode->i_mapping, range->start, range->start + range->len - 1); if (err) goto out; /* * lookup mapping info in extent cache, skip defragmenting if physical * block addresses are continuous. */ if (f2fs_lookup_extent_cache(inode, pg_start, &ei)) { if (ei.fofs + ei.len >= pg_end) goto out; } map.m_lblk = pg_start; /* * lookup mapping info in dnode page cache, skip defragmenting if all * physical block addresses are continuous even if there are hole(s) * in logical blocks. */ while (map.m_lblk < pg_end) { map.m_len = pg_end - map.m_lblk; err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_DEFAULT); if (err) goto out; if (!(map.m_flags & F2FS_MAP_FLAGS)) { map.m_lblk++; continue; } if (blk_end && blk_end != map.m_pblk) { fragmented = true; break; } blk_end = map.m_pblk + map.m_len; map.m_lblk += map.m_len; } if (!fragmented) goto out; map.m_lblk = pg_start; map.m_len = pg_end - pg_start; sec_num = (map.m_len + BLKS_PER_SEC(sbi) - 1) / BLKS_PER_SEC(sbi); /* * make sure there are enough free section for LFS allocation, this can * avoid defragment running in SSR mode when free section are allocated * intensively */ if (has_not_enough_free_secs(sbi, 0, sec_num)) { err = -EAGAIN; goto out; } while (map.m_lblk < pg_end) { pgoff_t idx; int cnt = 0; do_map: map.m_len = pg_end - map.m_lblk; err = f2fs_map_blocks(inode, &map, 0, F2FS_GET_BLOCK_DEFAULT); if (err) goto clear_out; if (!(map.m_flags & F2FS_MAP_FLAGS)) { map.m_lblk++; continue; } set_inode_flag(inode, FI_DO_DEFRAG); idx = map.m_lblk; while (idx < map.m_lblk + map.m_len && cnt < blk_per_seg) { struct page *page; page = get_lock_data_page(inode, idx, true); if (IS_ERR(page)) { err = PTR_ERR(page); goto clear_out; } set_page_dirty(page); f2fs_put_page(page, 1); idx++; cnt++; total++; } map.m_lblk = idx; if (idx < pg_end && cnt < blk_per_seg) goto do_map; clear_inode_flag(inode, FI_DO_DEFRAG); err = filemap_fdatawrite(inode->i_mapping); if (err) goto out; } clear_out: clear_inode_flag(inode, FI_DO_DEFRAG); out: inode_unlock(inode); if (!err) range->len = (u64)total << PAGE_SHIFT; return err; } static int f2fs_ioc_defragment(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_defragment range; int err; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!S_ISREG(inode->i_mode) || f2fs_is_atomic_file(inode)) return -EINVAL; if (f2fs_readonly(sbi->sb)) return -EROFS; if (copy_from_user(&range, (struct f2fs_defragment __user *)arg, sizeof(range))) return -EFAULT; /* verify alignment of offset & size */ if (range.start & (F2FS_BLKSIZE - 1) || range.len & (F2FS_BLKSIZE - 1)) return -EINVAL; if (unlikely((range.start + range.len) >> PAGE_SHIFT > sbi->max_file_blocks)) return -EINVAL; err = mnt_want_write_file(filp); if (err) return err; err = f2fs_defragment_range(sbi, filp, &range); mnt_drop_write_file(filp); f2fs_update_time(sbi, REQ_TIME); if (err < 0) return err; if (copy_to_user((struct f2fs_defragment __user *)arg, &range, sizeof(range))) return -EFAULT; return 0; } static int f2fs_move_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t len) { struct inode *src = file_inode(file_in); struct inode *dst = file_inode(file_out); struct f2fs_sb_info *sbi = F2FS_I_SB(src); size_t olen = len, dst_max_i_size = 0; size_t dst_osize; int ret; if (file_in->f_path.mnt != file_out->f_path.mnt || src->i_sb != dst->i_sb) return -EXDEV; if (unlikely(f2fs_readonly(src->i_sb))) return -EROFS; if (!S_ISREG(src->i_mode) || !S_ISREG(dst->i_mode)) return -EINVAL; if (f2fs_encrypted_inode(src) || f2fs_encrypted_inode(dst)) return -EOPNOTSUPP; if (src == dst) { if (pos_in == pos_out) return 0; if (pos_out > pos_in && pos_out < pos_in + len) return -EINVAL; } inode_lock(src); if (src != dst) { if (!inode_trylock(dst)) { ret = -EBUSY; goto out; } } ret = -EINVAL; if (pos_in + len > src->i_size || pos_in + len < pos_in) goto out_unlock; if (len == 0) olen = len = src->i_size - pos_in; if (pos_in + len == src->i_size) len = ALIGN(src->i_size, F2FS_BLKSIZE) - pos_in; if (len == 0) { ret = 0; goto out_unlock; } dst_osize = dst->i_size; if (pos_out + olen > dst->i_size) dst_max_i_size = pos_out + olen; /* verify the end result is block aligned */ if (!IS_ALIGNED(pos_in, F2FS_BLKSIZE) || !IS_ALIGNED(pos_in + len, F2FS_BLKSIZE) || !IS_ALIGNED(pos_out, F2FS_BLKSIZE)) goto out_unlock; ret = f2fs_convert_inline_inode(src); if (ret) goto out_unlock; ret = f2fs_convert_inline_inode(dst); if (ret) goto out_unlock; /* write out all dirty pages from offset */ ret = filemap_write_and_wait_range(src->i_mapping, pos_in, pos_in + len); if (ret) goto out_unlock; ret = filemap_write_and_wait_range(dst->i_mapping, pos_out, pos_out + len); if (ret) goto out_unlock; f2fs_balance_fs(sbi, true); f2fs_lock_op(sbi); ret = __exchange_data_block(src, dst, pos_in >> F2FS_BLKSIZE_BITS, pos_out >> F2FS_BLKSIZE_BITS, len >> F2FS_BLKSIZE_BITS, false); if (!ret) { if (dst_max_i_size) f2fs_i_size_write(dst, dst_max_i_size); else if (dst_osize != dst->i_size) f2fs_i_size_write(dst, dst_osize); } f2fs_unlock_op(sbi); out_unlock: if (src != dst) inode_unlock(dst); out: inode_unlock(src); return ret; } static int f2fs_ioc_move_range(struct file *filp, unsigned long arg) { struct f2fs_move_range range; struct fd dst; int err; if (!(filp->f_mode & FMODE_READ) || !(filp->f_mode & FMODE_WRITE)) return -EBADF; if (copy_from_user(&range, (struct f2fs_move_range __user *)arg, sizeof(range))) return -EFAULT; dst = fdget(range.dst_fd); if (!dst.file) return -EBADF; if (!(dst.file->f_mode & FMODE_WRITE)) { err = -EBADF; goto err_out; } err = mnt_want_write_file(filp); if (err) goto err_out; err = f2fs_move_file_range(filp, range.pos_in, dst.file, range.pos_out, range.len); mnt_drop_write_file(filp); if (err) goto err_out; if (copy_to_user((struct f2fs_move_range __user *)arg, &range, sizeof(range))) err = -EFAULT; err_out: fdput(dst); return err; } static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct sit_info *sm = SIT_I(sbi); unsigned int start_segno = 0, end_segno = 0; unsigned int dev_start_segno = 0, dev_end_segno = 0; struct f2fs_flush_device range; int ret; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (f2fs_readonly(sbi->sb)) return -EROFS; if (copy_from_user(&range, (struct f2fs_flush_device __user *)arg, sizeof(range))) return -EFAULT; if (!f2fs_is_multi_device(sbi) || sbi->s_ndevs - 1 <= range.dev_num || sbi->segs_per_sec != 1) { f2fs_msg(sbi->sb, KERN_WARNING, "Can't flush %u in %d for segs_per_sec %u != 1\n", range.dev_num, sbi->s_ndevs, sbi->segs_per_sec); return -EINVAL; } ret = mnt_want_write_file(filp); if (ret) return ret; if (range.dev_num != 0) dev_start_segno = GET_SEGNO(sbi, FDEV(range.dev_num).start_blk); dev_end_segno = GET_SEGNO(sbi, FDEV(range.dev_num).end_blk); start_segno = sm->last_victim[FLUSH_DEVICE]; if (start_segno < dev_start_segno || start_segno >= dev_end_segno) start_segno = dev_start_segno; end_segno = min(start_segno + range.segments, dev_end_segno); while (start_segno < end_segno) { if (!mutex_trylock(&sbi->gc_mutex)) { ret = -EBUSY; goto out; } sm->last_victim[GC_CB] = end_segno + 1; sm->last_victim[GC_GREEDY] = end_segno + 1; sm->last_victim[ALLOC_NEXT] = end_segno + 1; ret = f2fs_gc(sbi, true, true, start_segno); if (ret == -EAGAIN) ret = 0; else if (ret < 0) break; start_segno++; } out: mnt_drop_write_file(filp); return ret; } static int f2fs_ioc_get_features(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); u32 sb_feature = le32_to_cpu(F2FS_I_SB(inode)->raw_super->feature); /* Must validate to set it with SQLite behavior in Android. */ sb_feature |= F2FS_FEATURE_ATOMIC_WRITE; return put_user(sb_feature, (u32 __user *)arg); } #ifdef CONFIG_QUOTA static int f2fs_ioc_setproject(struct file *filp, __u32 projid) { struct inode *inode = file_inode(filp); struct f2fs_inode_info *fi = F2FS_I(inode); struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct super_block *sb = sbi->sb; struct dquot *transfer_to[MAXQUOTAS] = {}; struct page *ipage; kprojid_t kprojid; int err; if (!f2fs_sb_has_project_quota(sb)) { if (projid != F2FS_DEF_PROJID) return -EOPNOTSUPP; else return 0; } if (!f2fs_has_extra_attr(inode)) return -EOPNOTSUPP; kprojid = make_kprojid(&init_user_ns, (projid_t)projid); if (projid_eq(kprojid, F2FS_I(inode)->i_projid)) return 0; err = mnt_want_write_file(filp); if (err) return err; err = -EPERM; inode_lock(inode); /* Is it quota file? Do not allow user to mess with it */ if (IS_NOQUOTA(inode)) goto out_unlock; ipage = get_node_page(sbi, inode->i_ino); if (IS_ERR(ipage)) { err = PTR_ERR(ipage); goto out_unlock; } if (!F2FS_FITS_IN_INODE(F2FS_INODE(ipage), fi->i_extra_isize, i_projid)) { err = -EOVERFLOW; f2fs_put_page(ipage, 1); goto out_unlock; } f2fs_put_page(ipage, 1); err = dquot_initialize(inode); if (err) goto out_unlock; transfer_to[PRJQUOTA] = dqget(sb, make_kqid_projid(kprojid)); if (!IS_ERR(transfer_to[PRJQUOTA])) { err = __dquot_transfer(inode, transfer_to); dqput(transfer_to[PRJQUOTA]); if (err) goto out_dirty; } F2FS_I(inode)->i_projid = kprojid; inode->i_ctime = current_time(inode); out_dirty: f2fs_mark_inode_dirty_sync(inode, true); out_unlock: inode_unlock(inode); mnt_drop_write_file(filp); return err; } #else static int f2fs_ioc_setproject(struct file *filp, __u32 projid) { if (projid != F2FS_DEF_PROJID) return -EOPNOTSUPP; return 0; } #endif /* Transfer internal flags to xflags */ static inline __u32 f2fs_iflags_to_xflags(unsigned long iflags) { __u32 xflags = 0; if (iflags & FS_SYNC_FL) xflags |= FS_XFLAG_SYNC; if (iflags & FS_IMMUTABLE_FL) xflags |= FS_XFLAG_IMMUTABLE; if (iflags & FS_APPEND_FL) xflags |= FS_XFLAG_APPEND; if (iflags & FS_NODUMP_FL) xflags |= FS_XFLAG_NODUMP; if (iflags & FS_NOATIME_FL) xflags |= FS_XFLAG_NOATIME; if (iflags & FS_PROJINHERIT_FL) xflags |= FS_XFLAG_PROJINHERIT; return xflags; } #define F2FS_SUPPORTED_FS_XFLAGS (FS_XFLAG_SYNC | FS_XFLAG_IMMUTABLE | \ FS_XFLAG_APPEND | FS_XFLAG_NODUMP | \ FS_XFLAG_NOATIME | FS_XFLAG_PROJINHERIT) /* Flags we can manipulate with through EXT4_IOC_FSSETXATTR */ #define F2FS_FL_XFLAG_VISIBLE (FS_SYNC_FL | \ FS_IMMUTABLE_FL | \ FS_APPEND_FL | \ FS_NODUMP_FL | \ FS_NOATIME_FL | \ FS_PROJINHERIT_FL) /* Transfer xflags flags to internal */ static inline unsigned long f2fs_xflags_to_iflags(__u32 xflags) { unsigned long iflags = 0; if (xflags & FS_XFLAG_SYNC) iflags |= FS_SYNC_FL; if (xflags & FS_XFLAG_IMMUTABLE) iflags |= FS_IMMUTABLE_FL; if (xflags & FS_XFLAG_APPEND) iflags |= FS_APPEND_FL; if (xflags & FS_XFLAG_NODUMP) iflags |= FS_NODUMP_FL; if (xflags & FS_XFLAG_NOATIME) iflags |= FS_NOATIME_FL; if (xflags & FS_XFLAG_PROJINHERIT) iflags |= FS_PROJINHERIT_FL; return iflags; } static int f2fs_ioc_fsgetxattr(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); struct f2fs_inode_info *fi = F2FS_I(inode); struct fsxattr fa; memset(&fa, 0, sizeof(struct fsxattr)); fa.fsx_xflags = f2fs_iflags_to_xflags(fi->i_flags & (FS_FL_USER_VISIBLE | FS_PROJINHERIT_FL)); if (f2fs_sb_has_project_quota(inode->i_sb)) fa.fsx_projid = (__u32)from_kprojid(&init_user_ns, fi->i_projid); if (copy_to_user((struct fsxattr __user *)arg, &fa, sizeof(fa))) return -EFAULT; return 0; } static int f2fs_ioc_fssetxattr(struct file *filp, unsigned long arg) { struct inode *inode = file_inode(filp); struct f2fs_inode_info *fi = F2FS_I(inode); struct fsxattr fa; unsigned int flags; int err; if (copy_from_user(&fa, (struct fsxattr __user *)arg, sizeof(fa))) return -EFAULT; /* Make sure caller has proper permission */ if (!inode_owner_or_capable(inode)) return -EACCES; if (fa.fsx_xflags & ~F2FS_SUPPORTED_FS_XFLAGS) return -EOPNOTSUPP; flags = f2fs_xflags_to_iflags(fa.fsx_xflags); if (f2fs_mask_flags(inode->i_mode, flags) != flags) return -EOPNOTSUPP; err = mnt_want_write_file(filp); if (err) return err; inode_lock(inode); flags = (fi->i_flags & ~F2FS_FL_XFLAG_VISIBLE) | (flags & F2FS_FL_XFLAG_VISIBLE); err = __f2fs_ioc_setflags(inode, flags); inode_unlock(inode); mnt_drop_write_file(filp); if (err) return err; err = f2fs_ioc_setproject(filp, fa.fsx_projid); if (err) return err; return 0; } long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { switch (cmd) { case F2FS_IOC_GETFLAGS: return f2fs_ioc_getflags(filp, arg); case F2FS_IOC_SETFLAGS: return f2fs_ioc_setflags(filp, arg); case F2FS_IOC_GETVERSION: return f2fs_ioc_getversion(filp, arg); case F2FS_IOC_START_ATOMIC_WRITE: return f2fs_ioc_start_atomic_write(filp); case F2FS_IOC_COMMIT_ATOMIC_WRITE: return f2fs_ioc_commit_atomic_write(filp); case F2FS_IOC_START_VOLATILE_WRITE: return f2fs_ioc_start_volatile_write(filp); case F2FS_IOC_RELEASE_VOLATILE_WRITE: return f2fs_ioc_release_volatile_write(filp); case F2FS_IOC_ABORT_VOLATILE_WRITE: return f2fs_ioc_abort_volatile_write(filp); case F2FS_IOC_SHUTDOWN: return f2fs_ioc_shutdown(filp, arg); case FITRIM: return f2fs_ioc_fitrim(filp, arg); case F2FS_IOC_SET_ENCRYPTION_POLICY: return f2fs_ioc_set_encryption_policy(filp, arg); case F2FS_IOC_GET_ENCRYPTION_POLICY: return f2fs_ioc_get_encryption_policy(filp, arg); case F2FS_IOC_GET_ENCRYPTION_PWSALT: return f2fs_ioc_get_encryption_pwsalt(filp, arg); case F2FS_IOC_GARBAGE_COLLECT: return f2fs_ioc_gc(filp, arg); case F2FS_IOC_GARBAGE_COLLECT_RANGE: return f2fs_ioc_gc_range(filp, arg); case F2FS_IOC_WRITE_CHECKPOINT: return f2fs_ioc_write_checkpoint(filp, arg); case F2FS_IOC_DEFRAGMENT: return f2fs_ioc_defragment(filp, arg); case F2FS_IOC_MOVE_RANGE: return f2fs_ioc_move_range(filp, arg); case F2FS_IOC_FLUSH_DEVICE: return f2fs_ioc_flush_device(filp, arg); case F2FS_IOC_GET_FEATURES: return f2fs_ioc_get_features(filp, arg); case F2FS_IOC_FSGETXATTR: return f2fs_ioc_fsgetxattr(filp, arg); case F2FS_IOC_FSSETXATTR: return f2fs_ioc_fssetxattr(filp, arg); default: return -ENOTTY; } } static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); struct blk_plug plug; ssize_t ret; inode_lock(inode); ret = generic_write_checks(iocb, from); if (ret > 0) { bool preallocated = false; size_t target_size = 0; int err; if (iov_iter_fault_in_readable(from, iov_iter_count(from))) set_inode_flag(inode, FI_NO_PREALLOC); preallocated = true; target_size = iocb->ki_pos + iov_iter_count(from); err = f2fs_preallocate_blocks(iocb, from); if (err) { clear_inode_flag(inode, FI_NO_PREALLOC); inode_unlock(inode); return err; } blk_start_plug(&plug); ret = __generic_file_write_iter(iocb, from); blk_finish_plug(&plug); clear_inode_flag(inode, FI_NO_PREALLOC); /* if we couldn't write data, we should deallocate blocks. */ if (preallocated && i_size_read(inode) < target_size) f2fs_truncate(inode); if (ret > 0) f2fs_update_iostat(F2FS_I_SB(inode), APP_WRITE_IO, ret); } inode_unlock(inode); if (ret > 0) ret = generic_write_sync(iocb, ret); return ret; } #ifdef CONFIG_COMPAT long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { switch (cmd) { case F2FS_IOC32_GETFLAGS: cmd = F2FS_IOC_GETFLAGS; break; case F2FS_IOC32_SETFLAGS: cmd = F2FS_IOC_SETFLAGS; break; case F2FS_IOC32_GETVERSION: cmd = F2FS_IOC_GETVERSION; break; case F2FS_IOC_START_ATOMIC_WRITE: case F2FS_IOC_COMMIT_ATOMIC_WRITE: case F2FS_IOC_START_VOLATILE_WRITE: case F2FS_IOC_RELEASE_VOLATILE_WRITE: case F2FS_IOC_ABORT_VOLATILE_WRITE: case F2FS_IOC_SHUTDOWN: case F2FS_IOC_SET_ENCRYPTION_POLICY: case F2FS_IOC_GET_ENCRYPTION_PWSALT: case F2FS_IOC_GET_ENCRYPTION_POLICY: case F2FS_IOC_GARBAGE_COLLECT: case F2FS_IOC_GARBAGE_COLLECT_RANGE: case F2FS_IOC_WRITE_CHECKPOINT: case F2FS_IOC_DEFRAGMENT: case F2FS_IOC_MOVE_RANGE: case F2FS_IOC_FLUSH_DEVICE: case F2FS_IOC_GET_FEATURES: case F2FS_IOC_FSGETXATTR: case F2FS_IOC_FSSETXATTR: break; default: return -ENOIOCTLCMD; } return f2fs_ioctl(file, cmd, (unsigned long) compat_ptr(arg)); } #endif const struct file_operations f2fs_file_operations = { .llseek = f2fs_llseek, .read_iter = generic_file_read_iter, .write_iter = f2fs_file_write_iter, .open = f2fs_file_open, .release = f2fs_release_file, .mmap = f2fs_file_mmap, .flush = f2fs_file_flush, .fsync = f2fs_sync_file, .fallocate = f2fs_fallocate, .unlocked_ioctl = f2fs_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = f2fs_compat_ioctl, #endif .splice_read = generic_file_splice_read, .splice_write = iter_file_splice_write, }; |
| 17 17 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 | /* * x86 APERF/MPERF KHz calculation for * /sys/.../cpufreq/scaling_cur_freq * * Copyright (C) 2017 Intel Corp. * Author: Len Brown <len.brown@intel.com> * * This file is licensed under GPLv2. */ #include <linux/delay.h> #include <linux/ktime.h> #include <linux/math64.h> #include <linux/percpu.h> #include <linux/smp.h> #include "cpu.h" struct aperfmperf_sample { unsigned int khz; ktime_t time; u64 aperf; u64 mperf; }; static DEFINE_PER_CPU(struct aperfmperf_sample, samples); #define APERFMPERF_CACHE_THRESHOLD_MS 10 #define APERFMPERF_REFRESH_DELAY_MS 10 #define APERFMPERF_STALE_THRESHOLD_MS 1000 /* * aperfmperf_snapshot_khz() * On the current CPU, snapshot APERF, MPERF, and jiffies * unless we already did it within 10ms * calculate kHz, save snapshot */ static void aperfmperf_snapshot_khz(void *dummy) { u64 aperf, aperf_delta; u64 mperf, mperf_delta; struct aperfmperf_sample *s = this_cpu_ptr(&samples); unsigned long flags; local_irq_save(flags); rdmsrl(MSR_IA32_APERF, aperf); rdmsrl(MSR_IA32_MPERF, mperf); local_irq_restore(flags); aperf_delta = aperf - s->aperf; mperf_delta = mperf - s->mperf; /* * There is no architectural guarantee that MPERF * increments faster than we can read it. */ if (mperf_delta == 0) return; s->time = ktime_get(); s->aperf = aperf; s->mperf = mperf; s->khz = div64_u64((cpu_khz * aperf_delta), mperf_delta); } static bool aperfmperf_snapshot_cpu(int cpu, ktime_t now, bool wait) { s64 time_delta = ktime_ms_delta(now, per_cpu(samples.time, cpu)); /* Don't bother re-computing within the cache threshold time. */ if (time_delta < APERFMPERF_CACHE_THRESHOLD_MS) return true; smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, wait); /* Return false if the previous iteration was too long ago. */ return time_delta <= APERFMPERF_STALE_THRESHOLD_MS; } unsigned int aperfmperf_get_khz(int cpu) { if (!cpu_khz) return 0; if (!static_cpu_has(X86_FEATURE_APERFMPERF)) return 0; aperfmperf_snapshot_cpu(cpu, ktime_get(), true); return per_cpu(samples.khz, cpu); } void arch_freq_prepare_all(void) { ktime_t now = ktime_get(); bool wait = false; int cpu; if (!cpu_khz) return; if (!static_cpu_has(X86_FEATURE_APERFMPERF)) return; for_each_online_cpu(cpu) if (!aperfmperf_snapshot_cpu(cpu, now, false)) wait = true; if (wait) msleep(APERFMPERF_REFRESH_DELAY_MS); } unsigned int arch_freq_get_on_cpu(int cpu) { if (!cpu_khz) return 0; if (!static_cpu_has(X86_FEATURE_APERFMPERF)) return 0; if (aperfmperf_snapshot_cpu(cpu, ktime_get(), true)) return per_cpu(samples.khz, cpu); msleep(APERFMPERF_REFRESH_DELAY_MS); smp_call_function_single(cpu, aperfmperf_snapshot_khz, NULL, 1); return per_cpu(samples.khz, cpu); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 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 | /* * Copyright(c) 2017 Intel Corporation. * * This file is provided under a dual BSD/GPLv2 license. When using or * redistributing this file, you may do so under either license. * * GPL LICENSE SUMMARY * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as * published by the Free Software Foundation. * * This program is distributed in the hope that it will be useful, but * WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * General Public License for more details. * * BSD LICENSE * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * * - Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * - Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in * the documentation and/or other materials provided with the * distribution. * - Neither the name of Intel Corporation nor the names of its * contributors may be used to endorse or promote products derived * from this software without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. * */ #ifndef OPA_ADDR_H #define OPA_ADDR_H #include <rdma/opa_smi.h> #define OPA_SPECIAL_OUI (0x00066AULL) #define OPA_MAKE_ID(x) (cpu_to_be64(OPA_SPECIAL_OUI << 40 | (x))) #define OPA_TO_IB_UCAST_LID(x) (((x) >= be16_to_cpu(IB_MULTICAST_LID_BASE)) \ ? 0 : x) #define OPA_GID_INDEX 0x1 /** * 0xF8 - 4 bits of multicast range and 1 bit for collective range * Example: For 24 bit LID space, * Multicast range: 0xF00000 to 0xF7FFFF * Collective range: 0xF80000 to 0xFFFFFE */ #define OPA_MCAST_NR 0x4 /* Number of top bits set */ #define OPA_COLLECTIVE_NR 0x1 /* Number of bits after MCAST_NR */ /** * ib_is_opa_gid: Returns true if the top 24 bits of the gid * contains the OPA_STL_OUI identifier. This identifies that * the provided gid is a special purpose GID meant to carry * extended LID information. * * @gid: The Global identifier */ static inline bool ib_is_opa_gid(const union ib_gid *gid) { return ((be64_to_cpu(gid->global.interface_id) >> 40) == OPA_SPECIAL_OUI); } /** * opa_get_lid_from_gid: Returns the last 32 bits of the gid. * OPA devices use one of the gids in the gid table to also * store the lid. * * @gid: The Global identifier */ static inline u32 opa_get_lid_from_gid(const union ib_gid *gid) { return be64_to_cpu(gid->global.interface_id) & 0xFFFFFFFF; } /** * opa_is_extended_lid: Returns true if dlid or slid are * extended. * * @dlid: The DLID * @slid: The SLID */ static inline bool opa_is_extended_lid(u32 dlid, u32 slid) { if ((be32_to_cpu(dlid) >= be16_to_cpu(IB_MULTICAST_LID_BASE)) || (be32_to_cpu(slid) >= be16_to_cpu(IB_MULTICAST_LID_BASE))) return true; else return false; } /* Get multicast lid base */ static inline u32 opa_get_mcast_base(u32 nr_top_bits) { return (be32_to_cpu(OPA_LID_PERMISSIVE) << (32 - nr_top_bits)); } #endif /* OPA_ADDR_H */ |
| 91 82 29 29 29 11 29 8 29 29 24 29 1 110 110 92 82 92 92 89 90 92 92 81 81 81 81 1 1 1 1 1 60 58 1 57 58 51 1 1 4 1 1 2 2 2 102 81 23 81 1740 410 32 1742 275 12 1742 1741 129 10 24 4 39 15 15 3 3 2 15 2 15 33 1 1 1 1 3 3 3 3 3 1 1 89 82 73 20 1 1 1 1 2 2 7 7 6 61 61 6 5 1 1 78 81 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 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 | /* * INET 802.1Q VLAN * Ethernet-type device handling. * * Authors: Ben Greear <greearb@candelatech.com> * Please send support related email to: netdev@vger.kernel.org * VLAN Home Page: http://www.candelatech.com/~greear/vlan.html * * Fixes: * Fix for packet capture - Nick Eggleston <nick@dccinc.com>; * Add HW acceleration hooks - David S. Miller <davem@redhat.com>; * Correct all the locking - David S. Miller <davem@redhat.com>; * Use hash table for VLAN groups - David S. Miller <davem@redhat.com> * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/capability.h> #include <linux/module.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/rculist.h> #include <net/p8022.h> #include <net/arp.h> #include <linux/rtnetlink.h> #include <linux/notifier.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <linux/uaccess.h> #include <linux/if_vlan.h> #include "vlan.h" #include "vlanproc.h" #define DRV_VERSION "1.8" /* Global VLAN variables */ unsigned int vlan_net_id __read_mostly; const char vlan_fullname[] = "802.1Q VLAN Support"; const char vlan_version[] = DRV_VERSION; /* End of global variables definitions. */ static int vlan_group_prealloc_vid(struct vlan_group *vg, __be16 vlan_proto, u16 vlan_id) { struct net_device **array; unsigned int pidx, vidx; unsigned int size; ASSERT_RTNL(); pidx = vlan_proto_idx(vlan_proto); vidx = vlan_id / VLAN_GROUP_ARRAY_PART_LEN; array = vg->vlan_devices_arrays[pidx][vidx]; if (array != NULL) return 0; size = sizeof(struct net_device *) * VLAN_GROUP_ARRAY_PART_LEN; array = kzalloc(size, GFP_KERNEL); if (array == NULL) return -ENOBUFS; vg->vlan_devices_arrays[pidx][vidx] = array; return 0; } void unregister_vlan_dev(struct net_device *dev, struct list_head *head) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev = vlan->real_dev; struct vlan_info *vlan_info; struct vlan_group *grp; u16 vlan_id = vlan->vlan_id; ASSERT_RTNL(); vlan_info = rtnl_dereference(real_dev->vlan_info); BUG_ON(!vlan_info); grp = &vlan_info->grp; grp->nr_vlan_devs--; if (vlan->flags & VLAN_FLAG_MVRP) vlan_mvrp_request_leave(dev); if (vlan->flags & VLAN_FLAG_GVRP) vlan_gvrp_request_leave(dev); vlan_group_set_device(grp, vlan->vlan_proto, vlan_id, NULL); netdev_upper_dev_unlink(real_dev, dev); /* Because unregister_netdevice_queue() makes sure at least one rcu * grace period is respected before device freeing, * we dont need to call synchronize_net() here. */ unregister_netdevice_queue(dev, head); if (grp->nr_vlan_devs == 0) { vlan_mvrp_uninit_applicant(real_dev); vlan_gvrp_uninit_applicant(real_dev); } vlan_vid_del(real_dev, vlan->vlan_proto, vlan_id); /* Get rid of the vlan's reference to real_dev */ dev_put(real_dev); } int vlan_check_real_dev(struct net_device *real_dev, __be16 protocol, u16 vlan_id) { const char *name = real_dev->name; if (real_dev->features & NETIF_F_VLAN_CHALLENGED) { pr_info("VLANs not supported on %s\n", name); return -EOPNOTSUPP; } if (vlan_find_dev(real_dev, protocol, vlan_id) != NULL) return -EEXIST; return 0; } int register_vlan_dev(struct net_device *dev) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); struct net_device *real_dev = vlan->real_dev; u16 vlan_id = vlan->vlan_id; struct vlan_info *vlan_info; struct vlan_group *grp; int err; err = vlan_vid_add(real_dev, vlan->vlan_proto, vlan_id); if (err) return err; vlan_info = rtnl_dereference(real_dev->vlan_info); /* vlan_info should be there now. vlan_vid_add took care of it */ BUG_ON(!vlan_info); grp = &vlan_info->grp; if (grp->nr_vlan_devs == 0) { err = vlan_gvrp_init_applicant(real_dev); if (err < 0) goto out_vid_del; err = vlan_mvrp_init_applicant(real_dev); if (err < 0) goto out_uninit_gvrp; } err = vlan_group_prealloc_vid(grp, vlan->vlan_proto, vlan_id); if (err < 0) goto out_uninit_mvrp; vlan->nest_level = dev_get_nest_level(real_dev) + 1; err = register_netdevice(dev); if (err < 0) goto out_uninit_mvrp; err = netdev_upper_dev_link(real_dev, dev); if (err) goto out_unregister_netdev; /* Account for reference in struct vlan_dev_priv */ dev_hold(real_dev); netif_stacked_transfer_operstate(real_dev, dev); linkwatch_fire_event(dev); /* _MUST_ call rfc2863_policy() */ /* So, got the sucker initialized, now lets place * it into our local structure. */ vlan_group_set_device(grp, vlan->vlan_proto, vlan_id, dev); grp->nr_vlan_devs++; return 0; out_unregister_netdev: unregister_netdevice(dev); out_uninit_mvrp: if (grp->nr_vlan_devs == 0) vlan_mvrp_uninit_applicant(real_dev); out_uninit_gvrp: if (grp->nr_vlan_devs == 0) vlan_gvrp_uninit_applicant(real_dev); out_vid_del: vlan_vid_del(real_dev, vlan->vlan_proto, vlan_id); return err; } /* Attach a VLAN device to a mac address (ie Ethernet Card). * Returns 0 if the device was created or a negative error code otherwise. */ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id) { struct net_device *new_dev; struct vlan_dev_priv *vlan; struct net *net = dev_net(real_dev); struct vlan_net *vn = net_generic(net, vlan_net_id); char name[IFNAMSIZ]; int err; if (vlan_id >= VLAN_VID_MASK) return -ERANGE; err = vlan_check_real_dev(real_dev, htons(ETH_P_8021Q), vlan_id); if (err < 0) return err; /* Gotta set up the fields for the device. */ switch (vn->name_type) { case VLAN_NAME_TYPE_RAW_PLUS_VID: /* name will look like: eth1.0005 */ snprintf(name, IFNAMSIZ, "%s.%.4i", real_dev->name, vlan_id); break; case VLAN_NAME_TYPE_PLUS_VID_NO_PAD: /* Put our vlan.VID in the name. * Name will look like: vlan5 */ snprintf(name, IFNAMSIZ, "vlan%i", vlan_id); break; case VLAN_NAME_TYPE_RAW_PLUS_VID_NO_PAD: /* Put our vlan.VID in the name. * Name will look like: eth0.5 */ snprintf(name, IFNAMSIZ, "%s.%i", real_dev->name, vlan_id); break; case VLAN_NAME_TYPE_PLUS_VID: /* Put our vlan.VID in the name. * Name will look like: vlan0005 */ default: snprintf(name, IFNAMSIZ, "vlan%.4i", vlan_id); } new_dev = alloc_netdev(sizeof(struct vlan_dev_priv), name, NET_NAME_UNKNOWN, vlan_setup); if (new_dev == NULL) return -ENOBUFS; dev_net_set(new_dev, net); /* need 4 bytes for extra VLAN header info, * hope the underlying device can handle it. */ new_dev->mtu = real_dev->mtu; vlan = vlan_dev_priv(new_dev); vlan->vlan_proto = htons(ETH_P_8021Q); vlan->vlan_id = vlan_id; vlan->real_dev = real_dev; vlan->dent = NULL; vlan->flags = VLAN_FLAG_REORDER_HDR; new_dev->rtnl_link_ops = &vlan_link_ops; err = register_vlan_dev(new_dev); if (err < 0) goto out_free_newdev; return 0; out_free_newdev: if (new_dev->reg_state == NETREG_UNINITIALIZED || new_dev->reg_state == NETREG_UNREGISTERED) free_netdev(new_dev); return err; } static void vlan_sync_address(struct net_device *dev, struct net_device *vlandev) { struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev); /* May be called without an actual change */ if (ether_addr_equal(vlan->real_dev_addr, dev->dev_addr)) return; /* vlan continues to inherit address of lower device */ if (vlan_dev_inherit_address(vlandev, dev)) goto out; /* vlan address was different from the old address and is equal to * the new address */ if (!ether_addr_equal(vlandev->dev_addr, vlan->real_dev_addr) && ether_addr_equal(vlandev->dev_addr, dev->dev_addr)) dev_uc_del(dev, vlandev->dev_addr); /* vlan address was equal to the old address and is different from * the new address */ if (ether_addr_equal(vlandev->dev_addr, vlan->real_dev_addr) && !ether_addr_equal(vlandev->dev_addr, dev->dev_addr)) dev_uc_add(dev, vlandev->dev_addr); out: ether_addr_copy(vlan->real_dev_addr, dev->dev_addr); } static void vlan_transfer_features(struct net_device *dev, struct net_device *vlandev) { struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev); vlandev->gso_max_size = dev->gso_max_size; vlandev->gso_max_segs = dev->gso_max_segs; if (vlan_hw_offload_capable(dev->features, vlan->vlan_proto)) vlandev->hard_header_len = dev->hard_header_len; else vlandev->hard_header_len = dev->hard_header_len + VLAN_HLEN; #if IS_ENABLED(CONFIG_FCOE) vlandev->fcoe_ddp_xid = dev->fcoe_ddp_xid; #endif netdev_update_features(vlandev); } static int __vlan_device_event(struct net_device *dev, unsigned long event) { int err = 0; switch (event) { case NETDEV_CHANGENAME: vlan_proc_rem_dev(dev); err = vlan_proc_add_dev(dev); break; case NETDEV_REGISTER: err = vlan_proc_add_dev(dev); break; case NETDEV_UNREGISTER: vlan_proc_rem_dev(dev); break; } return err; } static int vlan_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct vlan_group *grp; struct vlan_info *vlan_info; int i, flgs; struct net_device *vlandev; struct vlan_dev_priv *vlan; bool last = false; LIST_HEAD(list); if (is_vlan_dev(dev)) { int err = __vlan_device_event(dev, event); if (err) return notifier_from_errno(err); } if ((event == NETDEV_UP) && (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) { pr_info("adding VLAN 0 to HW filter on device %s\n", dev->name); vlan_vid_add(dev, htons(ETH_P_8021Q), 0); } if (event == NETDEV_DOWN && (dev->features & NETIF_F_HW_VLAN_CTAG_FILTER)) vlan_vid_del(dev, htons(ETH_P_8021Q), 0); vlan_info = rtnl_dereference(dev->vlan_info); if (!vlan_info) goto out; grp = &vlan_info->grp; /* It is OK that we do not hold the group lock right now, * as we run under the RTNL lock. */ switch (event) { case NETDEV_CHANGE: /* Propagate real device state to vlan devices */ vlan_group_for_each_dev(grp, i, vlandev) netif_stacked_transfer_operstate(dev, vlandev); break; case NETDEV_CHANGEADDR: /* Adjust unicast filters on underlying device */ vlan_group_for_each_dev(grp, i, vlandev) { flgs = vlandev->flags; if (!(flgs & IFF_UP)) continue; vlan_sync_address(dev, vlandev); } break; case NETDEV_CHANGEMTU: vlan_group_for_each_dev(grp, i, vlandev) { if (vlandev->mtu <= dev->mtu) continue; dev_set_mtu(vlandev, dev->mtu); } break; case NETDEV_FEAT_CHANGE: /* Propagate device features to underlying device */ vlan_group_for_each_dev(grp, i, vlandev) vlan_transfer_features(dev, vlandev); break; case NETDEV_DOWN: { struct net_device *tmp; LIST_HEAD(close_list); /* Put all VLANs for this dev in the down state too. */ vlan_group_for_each_dev(grp, i, vlandev) { flgs = vlandev->flags; if (!(flgs & IFF_UP)) continue; vlan = vlan_dev_priv(vlandev); if (!(vlan->flags & VLAN_FLAG_LOOSE_BINDING)) list_add(&vlandev->close_list, &close_list); } dev_close_many(&close_list, false); list_for_each_entry_safe(vlandev, tmp, &close_list, close_list) { netif_stacked_transfer_operstate(dev, vlandev); list_del_init(&vlandev->close_list); } list_del(&close_list); break; } case NETDEV_UP: /* Put all VLANs for this dev in the up state too. */ vlan_group_for_each_dev(grp, i, vlandev) { flgs = dev_get_flags(vlandev); if (flgs & IFF_UP) continue; vlan = vlan_dev_priv(vlandev); if (!(vlan->flags & VLAN_FLAG_LOOSE_BINDING)) dev_change_flags(vlandev, flgs | IFF_UP); netif_stacked_transfer_operstate(dev, vlandev); } break; case NETDEV_UNREGISTER: /* twiddle thumbs on netns device moves */ if (dev->reg_state != NETREG_UNREGISTERING) break; vlan_group_for_each_dev(grp, i, vlandev) { /* removal of last vid destroys vlan_info, abort * afterwards */ if (vlan_info->nr_vids == 1) last = true; unregister_vlan_dev(vlandev, &list); if (last) break; } unregister_netdevice_many(&list); break; case NETDEV_PRE_TYPE_CHANGE: /* Forbid underlaying device to change its type. */ if (vlan_uses_dev(dev)) return NOTIFY_BAD; break; case NETDEV_NOTIFY_PEERS: case NETDEV_BONDING_FAILOVER: case NETDEV_RESEND_IGMP: /* Propagate to vlan devices */ vlan_group_for_each_dev(grp, i, vlandev) call_netdevice_notifiers(event, vlandev); break; } out: return NOTIFY_DONE; } static struct notifier_block vlan_notifier_block __read_mostly = { .notifier_call = vlan_device_event, }; /* * VLAN IOCTL handler. * o execute requested action or pass command to the device driver * arg is really a struct vlan_ioctl_args __user *. */ static int vlan_ioctl_handler(struct net *net, void __user *arg) { int err; struct vlan_ioctl_args args; struct net_device *dev = NULL; if (copy_from_user(&args, arg, sizeof(struct vlan_ioctl_args))) return -EFAULT; /* Null terminate this sucker, just in case. */ args.device1[sizeof(args.device1) - 1] = 0; args.u.device2[sizeof(args.u.device2) - 1] = 0; rtnl_lock(); switch (args.cmd) { case SET_VLAN_INGRESS_PRIORITY_CMD: case SET_VLAN_EGRESS_PRIORITY_CMD: case SET_VLAN_FLAG_CMD: case ADD_VLAN_CMD: case DEL_VLAN_CMD: case GET_VLAN_REALDEV_NAME_CMD: case GET_VLAN_VID_CMD: err = -ENODEV; dev = __dev_get_by_name(net, args.device1); if (!dev) goto out; err = -EINVAL; if (args.cmd != ADD_VLAN_CMD && !is_vlan_dev(dev)) goto out; } switch (args.cmd) { case SET_VLAN_INGRESS_PRIORITY_CMD: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; vlan_dev_set_ingress_priority(dev, args.u.skb_priority, args.vlan_qos); err = 0; break; case SET_VLAN_EGRESS_PRIORITY_CMD: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = vlan_dev_set_egress_priority(dev, args.u.skb_priority, args.vlan_qos); break; case SET_VLAN_FLAG_CMD: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = vlan_dev_change_flags(dev, args.vlan_qos ? args.u.flag : 0, args.u.flag); break; case SET_VLAN_NAME_TYPE_CMD: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; if (args.u.name_type < VLAN_NAME_TYPE_HIGHEST) { struct vlan_net *vn; vn = net_generic(net, vlan_net_id); vn->name_type = args.u.name_type; err = 0; } else { err = -EINVAL; } break; case ADD_VLAN_CMD: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = register_vlan_device(dev, args.u.VID); break; case DEL_VLAN_CMD: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; unregister_vlan_dev(dev, NULL); err = 0; break; case GET_VLAN_REALDEV_NAME_CMD: err = 0; vlan_dev_get_realdev_name(dev, args.u.device2); if (copy_to_user(arg, &args, sizeof(struct vlan_ioctl_args))) err = -EFAULT; break; case GET_VLAN_VID_CMD: err = 0; args.u.VID = vlan_dev_vlan_id(dev); if (copy_to_user(arg, &args, sizeof(struct vlan_ioctl_args))) err = -EFAULT; break; default: err = -EOPNOTSUPP; break; } out: rtnl_unlock(); return err; } static struct sk_buff **vlan_gro_receive(struct sk_buff **head, struct sk_buff *skb) { struct sk_buff *p, **pp = NULL; struct vlan_hdr *vhdr; unsigned int hlen, off_vlan; const struct packet_offload *ptype; __be16 type; int flush = 1; off_vlan = skb_gro_offset(skb); hlen = off_vlan + sizeof(*vhdr); vhdr = skb_gro_header_fast(skb, off_vlan); if (skb_gro_header_hard(skb, hlen)) { vhdr = skb_gro_header_slow(skb, hlen, off_vlan); if (unlikely(!vhdr)) goto out; } type = vhdr->h_vlan_encapsulated_proto; rcu_read_lock(); ptype = gro_find_receive_by_type(type); if (!ptype) goto out_unlock; flush = 0; for (p = *head; p; p = p->next) { struct vlan_hdr *vhdr2; if (!NAPI_GRO_CB(p)->same_flow) continue; vhdr2 = (struct vlan_hdr *)(p->data + off_vlan); if (compare_vlan_header(vhdr, vhdr2)) NAPI_GRO_CB(p)->same_flow = 0; } skb_gro_pull(skb, sizeof(*vhdr)); skb_gro_postpull_rcsum(skb, vhdr, sizeof(*vhdr)); pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb); out_unlock: rcu_read_unlock(); out: skb_gro_flush_final(skb, pp, flush); return pp; } static int vlan_gro_complete(struct sk_buff *skb, int nhoff) { struct vlan_hdr *vhdr = (struct vlan_hdr *)(skb->data + nhoff); __be16 type = vhdr->h_vlan_encapsulated_proto; struct packet_offload *ptype; int err = -ENOENT; rcu_read_lock(); ptype = gro_find_complete_by_type(type); if (ptype) err = ptype->callbacks.gro_complete(skb, nhoff + sizeof(*vhdr)); rcu_read_unlock(); return err; } static struct packet_offload vlan_packet_offloads[] __read_mostly = { { .type = cpu_to_be16(ETH_P_8021Q), .priority = 10, .callbacks = { .gro_receive = vlan_gro_receive, .gro_complete = vlan_gro_complete, }, }, { .type = cpu_to_be16(ETH_P_8021AD), .priority = 10, .callbacks = { .gro_receive = vlan_gro_receive, .gro_complete = vlan_gro_complete, }, }, }; static int __net_init vlan_init_net(struct net *net) { struct vlan_net *vn = net_generic(net, vlan_net_id); int err; vn->name_type = VLAN_NAME_TYPE_RAW_PLUS_VID_NO_PAD; err = vlan_proc_init(net); return err; } static void __net_exit vlan_exit_net(struct net *net) { vlan_proc_cleanup(net); } static struct pernet_operations vlan_net_ops = { .init = vlan_init_net, .exit = vlan_exit_net, .id = &vlan_net_id, .size = sizeof(struct vlan_net), }; static int __init vlan_proto_init(void) { int err; unsigned int i; pr_info("%s v%s\n", vlan_fullname, vlan_version); err = register_pernet_subsys(&vlan_net_ops); if (err < 0) goto err0; err = register_netdevice_notifier(&vlan_notifier_block); if (err < 0) goto err2; err = vlan_gvrp_init(); if (err < 0) goto err3; err = vlan_mvrp_init(); if (err < 0) goto err4; err = vlan_netlink_init(); if (err < 0) goto err5; for (i = 0; i < ARRAY_SIZE(vlan_packet_offloads); i++) dev_add_offload(&vlan_packet_offloads[i]); vlan_ioctl_set(vlan_ioctl_handler); return 0; err5: vlan_mvrp_uninit(); err4: vlan_gvrp_uninit(); err3: unregister_netdevice_notifier(&vlan_notifier_block); err2: unregister_pernet_subsys(&vlan_net_ops); err0: return err; } static void __exit vlan_cleanup_module(void) { unsigned int i; vlan_ioctl_set(NULL); for (i = 0; i < ARRAY_SIZE(vlan_packet_offloads); i++) dev_remove_offload(&vlan_packet_offloads[i]); vlan_netlink_fini(); unregister_netdevice_notifier(&vlan_notifier_block); unregister_pernet_subsys(&vlan_net_ops); rcu_barrier(); /* Wait for completion of call_rcu()'s */ vlan_mvrp_uninit(); vlan_gvrp_uninit(); } module_init(vlan_proto_init); module_exit(vlan_cleanup_module); MODULE_LICENSE("GPL"); MODULE_VERSION(DRV_VERSION); |
| 19 2 142 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 | #undef TRACE_SYSTEM #define TRACE_SYSTEM bridge #if !defined(_TRACE_BRIDGE_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_BRIDGE_H #include <linux/netdevice.h> #include <linux/tracepoint.h> #include "../../../net/bridge/br_private.h" TRACE_EVENT(br_fdb_add, TP_PROTO(struct ndmsg *ndm, struct net_device *dev, const unsigned char *addr, u16 vid, u16 nlh_flags), TP_ARGS(ndm, dev, addr, vid, nlh_flags), TP_STRUCT__entry( __field(u8, ndm_flags) __string(dev, dev->name) __array(unsigned char, addr, ETH_ALEN) __field(u16, vid) __field(u16, nlh_flags) ), TP_fast_assign( __assign_str(dev, dev->name); memcpy(__entry->addr, addr, ETH_ALEN); __entry->vid = vid; __entry->nlh_flags = nlh_flags; __entry->ndm_flags = ndm->ndm_flags; ), TP_printk("dev %s addr %02x:%02x:%02x:%02x:%02x:%02x vid %u nlh_flags %04x ndm_flags %02x", __get_str(dev), __entry->addr[0], __entry->addr[1], __entry->addr[2], __entry->addr[3], __entry->addr[4], __entry->addr[5], __entry->vid, __entry->nlh_flags, __entry->ndm_flags) ); TRACE_EVENT(br_fdb_external_learn_add, TP_PROTO(struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, u16 vid), TP_ARGS(br, p, addr, vid), TP_STRUCT__entry( __string(br_dev, br->dev->name) __string(dev, p ? p->dev->name : "null") __array(unsigned char, addr, ETH_ALEN) __field(u16, vid) ), TP_fast_assign( __assign_str(br_dev, br->dev->name); __assign_str(dev, p ? p->dev->name : "null"); memcpy(__entry->addr, addr, ETH_ALEN); __entry->vid = vid; ), TP_printk("br_dev %s port %s addr %02x:%02x:%02x:%02x:%02x:%02x vid %u", __get_str(br_dev), __get_str(dev), __entry->addr[0], __entry->addr[1], __entry->addr[2], __entry->addr[3], __entry->addr[4], __entry->addr[5], __entry->vid) ); TRACE_EVENT(fdb_delete, TP_PROTO(struct net_bridge *br, struct net_bridge_fdb_entry *f), TP_ARGS(br, f), TP_STRUCT__entry( __string(br_dev, br->dev->name) __string(dev, f->dst ? f->dst->dev->name : "null") __array(unsigned char, addr, ETH_ALEN) __field(u16, vid) ), TP_fast_assign( __assign_str(br_dev, br->dev->name); __assign_str(dev, f->dst ? f->dst->dev->name : "null"); memcpy(__entry->addr, f->addr.addr, ETH_ALEN); __entry->vid = f->vlan_id; ), TP_printk("br_dev %s dev %s addr %02x:%02x:%02x:%02x:%02x:%02x vid %u", __get_str(br_dev), __get_str(dev), __entry->addr[0], __entry->addr[1], __entry->addr[2], __entry->addr[3], __entry->addr[4], __entry->addr[5], __entry->vid) ); TRACE_EVENT(br_fdb_update, TP_PROTO(struct net_bridge *br, struct net_bridge_port *source, const unsigned char *addr, u16 vid, bool added_by_user), TP_ARGS(br, source, addr, vid, added_by_user), TP_STRUCT__entry( __string(br_dev, br->dev->name) __string(dev, source->dev->name) __array(unsigned char, addr, ETH_ALEN) __field(u16, vid) __field(bool, added_by_user) ), TP_fast_assign( __assign_str(br_dev, br->dev->name); __assign_str(dev, source->dev->name); memcpy(__entry->addr, addr, ETH_ALEN); __entry->vid = vid; __entry->added_by_user = added_by_user; ), TP_printk("br_dev %s source %s addr %02x:%02x:%02x:%02x:%02x:%02x vid %u added_by_user %d", __get_str(br_dev), __get_str(dev), __entry->addr[0], __entry->addr[1], __entry->addr[2], __entry->addr[3], __entry->addr[4], __entry->addr[5], __entry->vid, __entry->added_by_user) ); #endif /* _TRACE_BRIDGE_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 30 30 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 | /* * NetLabel NETLINK Interface * * This file defines the NETLINK interface for the NetLabel system. The * NetLabel system manages static and dynamic label mappings for network * protocols such as CIPSO and RIPSO. * * Author: Paul Moore <paul@paul-moore.com> * */ /* * (c) Copyright Hewlett-Packard Development Company, L.P., 2006 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See * the GNU General Public License for more details. * * You should have received a copy of the GNU General Public License * along with this program; if not, see <http://www.gnu.org/licenses/>. * */ #include <linux/init.h> #include <linux/types.h> #include <linux/list.h> #include <linux/socket.h> #include <linux/audit.h> #include <linux/tty.h> #include <linux/security.h> #include <linux/gfp.h> #include <net/sock.h> #include <net/netlink.h> #include <net/genetlink.h> #include <net/netlabel.h> #include <asm/bug.h> #include "netlabel_mgmt.h" #include "netlabel_unlabeled.h" #include "netlabel_cipso_v4.h" #include "netlabel_calipso.h" #include "netlabel_user.h" /* * NetLabel NETLINK Setup Functions */ /** * netlbl_netlink_init - Initialize the NETLINK communication channel * * Description: * Call out to the NetLabel components so they can register their families and * commands with the Generic NETLINK mechanism. Returns zero on success and * non-zero on failure. * */ int __init netlbl_netlink_init(void) { int ret_val; ret_val = netlbl_mgmt_genl_init(); if (ret_val != 0) return ret_val; ret_val = netlbl_cipsov4_genl_init(); if (ret_val != 0) return ret_val; ret_val = netlbl_calipso_genl_init(); if (ret_val != 0) return ret_val; return netlbl_unlabel_genl_init(); } /* * NetLabel Audit Functions */ /** * netlbl_audit_start_common - Start an audit message * @type: audit message type * @audit_info: NetLabel audit information * * Description: * Start an audit message using the type specified in @type and fill the audit * message with some fields common to all NetLabel audit messages. Returns * a pointer to the audit buffer on success, NULL on failure. * */ struct audit_buffer *netlbl_audit_start_common(int type, struct netlbl_audit *audit_info) { struct audit_buffer *audit_buf; char *secctx; u32 secctx_len; if (audit_enabled == 0) return NULL; audit_buf = audit_log_start(current->audit_context, GFP_ATOMIC, type); if (audit_buf == NULL) return NULL; audit_log_format(audit_buf, "netlabel: auid=%u ses=%u", from_kuid(&init_user_ns, audit_info->loginuid), audit_info->sessionid); if (audit_info->secid != 0 && security_secid_to_secctx(audit_info->secid, &secctx, &secctx_len) == 0) { audit_log_format(audit_buf, " subj=%s", secctx); security_release_secctx(secctx, secctx_len); } return audit_buf; } |
| 3 3 3 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 | /****************************************************************************** ******************************************************************************* ** ** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. ** Copyright (C) 2004-2009 Red Hat, Inc. All rights reserved. ** ** This copyrighted material is made available to anyone wishing to use, ** modify, copy, or redistribute it subject to the terms and conditions ** of the GNU General Public License v.2. ** ******************************************************************************* ******************************************************************************/ /* * lowcomms.c * * This is the "low-level" comms layer. * * It is responsible for sending/receiving messages * from other nodes in the cluster. * * Cluster nodes are referred to by their nodeids. nodeids are * simply 32 bit numbers to the locking module - if they need to * be expanded for the cluster infrastructure then that is its * responsibility. It is this layer's * responsibility to resolve these into IP address or * whatever it needs for inter-node communication. * * The comms level is two kernel threads that deal mainly with * the receiving of messages from other nodes and passing them * up to the mid-level comms layer (which understands the * message format) for execution by the locking core, and * a send thread which does all the setting up of connections * to remote nodes and the sending of data. Threads are not allowed * to send their own data because it may cause them to wait in times * of high load. Also, this way, the sending thread can collect together * messages bound for one node and send them in one block. * * lowcomms will choose to use either TCP or SCTP as its transport layer * depending on the configuration variable 'protocol'. This should be set * to 0 (default) for TCP or 1 for SCTP. It should be configured using a * cluster-wide mechanism as it must be the same on all nodes of the cluster * for the DLM to function. * */ #include <asm/ioctls.h> #include <net/sock.h> #include <net/tcp.h> #include <linux/pagemap.h> #include <linux/file.h> #include <linux/mutex.h> #include <linux/sctp.h> #include <linux/slab.h> #include <net/sctp/sctp.h> #include <net/ipv6.h> #include "dlm_internal.h" #include "lowcomms.h" #include "midcomms.h" #include "config.h" #define NEEDED_RMEM (4*1024*1024) #define CONN_HASH_SIZE 32 /* Number of messages to send before rescheduling */ #define MAX_SEND_MSG_COUNT 25 struct cbuf { unsigned int base; unsigned int len; unsigned int mask; }; static void cbuf_add(struct cbuf *cb, int n) { cb->len += n; } static int cbuf_data(struct cbuf *cb) { return ((cb->base + cb->len) & cb->mask); } static void cbuf_init(struct cbuf *cb, int size) { cb->base = cb->len = 0; cb->mask = size-1; } static void cbuf_eat(struct cbuf *cb, int n) { cb->len -= n; cb->base += n; cb->base &= cb->mask; } static bool cbuf_empty(struct cbuf *cb) { return cb->len == 0; } struct connection { struct socket *sock; /* NULL if not connected */ uint32_t nodeid; /* So we know who we are in the list */ struct mutex sock_mutex; unsigned long flags; #define CF_READ_PENDING 1 #define CF_WRITE_PENDING 2 #define CF_CONNECT_PENDING 3 #define CF_INIT_PENDING 4 #define CF_IS_OTHERCON 5 #define CF_CLOSE 6 #define CF_APP_LIMITED 7 struct list_head writequeue; /* List of outgoing writequeue_entries */ spinlock_t writequeue_lock; int (*rx_action) (struct connection *); /* What to do when active */ void (*connect_action) (struct connection *); /* What to do to connect */ struct page *rx_page; struct cbuf cb; int retries; #define MAX_CONNECT_RETRIES 3 struct hlist_node list; struct connection *othercon; struct work_struct rwork; /* Receive workqueue */ struct work_struct swork; /* Send workqueue */ void (*orig_error_report)(struct sock *); void (*orig_data_ready)(struct sock *); void (*orig_state_change)(struct sock *); void (*orig_write_space)(struct sock *); }; #define sock2con(x) ((struct connection *)(x)->sk_user_data) /* An entry waiting to be sent */ struct writequeue_entry { struct list_head list; struct page *page; int offset; int len; int end; int users; struct connection *con; }; struct dlm_node_addr { struct list_head list; int nodeid; int addr_count; int curr_addr_index; struct sockaddr_storage *addr[DLM_MAX_ADDR_COUNT]; }; static LIST_HEAD(dlm_node_addrs); static DEFINE_SPINLOCK(dlm_node_addrs_spin); static struct sockaddr_storage *dlm_local_addr[DLM_MAX_ADDR_COUNT]; static int dlm_local_count; static int dlm_allow_conn; /* Work queues */ static struct workqueue_struct *recv_workqueue; static struct workqueue_struct *send_workqueue; static struct hlist_head connection_hash[CONN_HASH_SIZE]; static DEFINE_MUTEX(connections_lock); static struct kmem_cache *con_cache; static void process_recv_sockets(struct work_struct *work); static void process_send_sockets(struct work_struct *work); /* This is deliberately very simple because most clusters have simple sequential nodeids, so we should be able to go straight to a connection struct in the array */ static inline int nodeid_hash(int nodeid) { return nodeid & (CONN_HASH_SIZE-1); } static struct connection *__find_con(int nodeid) { int r; struct connection *con; r = nodeid_hash(nodeid); hlist_for_each_entry(con, &connection_hash[r], list) { if (con->nodeid == nodeid) return con; } return NULL; } /* * If 'allocation' is zero then we don't attempt to create a new * connection structure for this node. */ static struct connection *__nodeid2con(int nodeid, gfp_t alloc) { struct connection *con = NULL; int r; con = __find_con(nodeid); if (con || !alloc) return con; con = kmem_cache_zalloc(con_cache, alloc); if (!con) return NULL; r = nodeid_hash(nodeid); hlist_add_head(&con->list, &connection_hash[r]); con->nodeid = nodeid; mutex_init(&con->sock_mutex); INIT_LIST_HEAD(&con->writequeue); spin_lock_init(&con->writequeue_lock); INIT_WORK(&con->swork, process_send_sockets); INIT_WORK(&con->rwork, process_recv_sockets); /* Setup action pointers for child sockets */ if (con->nodeid) { struct connection *zerocon = __find_con(0); con->connect_action = zerocon->connect_action; if (!con->rx_action) con->rx_action = zerocon->rx_action; } return con; } /* Loop round all connections */ static void foreach_conn(void (*conn_func)(struct connection *c)) { int i; struct hlist_node *n; struct connection *con; for (i = 0; i < CONN_HASH_SIZE; i++) { hlist_for_each_entry_safe(con, n, &connection_hash[i], list) conn_func(con); } } static struct connection *nodeid2con(int nodeid, gfp_t allocation) { struct connection *con; mutex_lock(&connections_lock); con = __nodeid2con(nodeid, allocation); mutex_unlock(&connections_lock); return con; } static struct dlm_node_addr *find_node_addr(int nodeid) { struct dlm_node_addr *na; list_for_each_entry(na, &dlm_node_addrs, list) { if (na->nodeid == nodeid) return na; } return NULL; } static int addr_compare(struct sockaddr_storage *x, struct sockaddr_storage *y) { switch (x->ss_family) { case AF_INET: { struct sockaddr_in *sinx = (struct sockaddr_in *)x; struct sockaddr_in *siny = (struct sockaddr_in *)y; if (sinx->sin_addr.s_addr != siny->sin_addr.s_addr) return 0; if (sinx->sin_port != siny->sin_port) return 0; break; } case AF_INET6: { struct sockaddr_in6 *sinx = (struct sockaddr_in6 *)x; struct sockaddr_in6 *siny = (struct sockaddr_in6 *)y; if (!ipv6_addr_equal(&sinx->sin6_addr, &siny->sin6_addr)) return 0; if (sinx->sin6_port != siny->sin6_port) return 0; break; } default: return 0; } return 1; } static int nodeid_to_addr(int nodeid, struct sockaddr_storage *sas_out, struct sockaddr *sa_out, bool try_new_addr) { struct sockaddr_storage sas; struct dlm_node_addr *na; if (!dlm_local_count) return -1; spin_lock(&dlm_node_addrs_spin); na = find_node_addr(nodeid); if (na && na->addr_count) { memcpy(&sas, na->addr[na->curr_addr_index], sizeof(struct sockaddr_storage)); if (try_new_addr) { na->curr_addr_index++; if (na->curr_addr_index == na->addr_count) na->curr_addr_index = 0; } } spin_unlock(&dlm_node_addrs_spin); if (!na) return -EEXIST; if (!na->addr_count) return -ENOENT; if (sas_out) memcpy(sas_out, &sas, sizeof(struct sockaddr_storage)); if (!sa_out) return 0; if (dlm_local_addr[0]->ss_family == AF_INET) { struct sockaddr_in *in4 = (struct sockaddr_in *) &sas; struct sockaddr_in *ret4 = (struct sockaddr_in *) sa_out; ret4->sin_addr.s_addr = in4->sin_addr.s_addr; } else { struct sockaddr_in6 *in6 = (struct sockaddr_in6 *) &sas; struct sockaddr_in6 *ret6 = (struct sockaddr_in6 *) sa_out; ret6->sin6_addr = in6->sin6_addr; } return 0; } static int addr_to_nodeid(struct sockaddr_storage *addr, int *nodeid) { struct dlm_node_addr *na; int rv = -EEXIST; int addr_i; spin_lock(&dlm_node_addrs_spin); list_for_each_entry(na, &dlm_node_addrs, list) { if (!na->addr_count) continue; for (addr_i = 0; addr_i < na->addr_count; addr_i++) { if (addr_compare(na->addr[addr_i], addr)) { *nodeid = na->nodeid; rv = 0; goto unlock; } } } unlock: spin_unlock(&dlm_node_addrs_spin); return rv; } int dlm_lowcomms_addr(int nodeid, struct sockaddr_storage *addr, int len) { struct sockaddr_storage *new_addr; struct dlm_node_addr *new_node, *na; new_node = kzalloc(sizeof(struct dlm_node_addr), GFP_NOFS); if (!new_node) return -ENOMEM; new_addr = kzalloc(sizeof(struct sockaddr_storage), GFP_NOFS); if (!new_addr) { kfree(new_node); return -ENOMEM; } memcpy(new_addr, addr, len); spin_lock(&dlm_node_addrs_spin); na = find_node_addr(nodeid); if (!na) { new_node->nodeid = nodeid; new_node->addr[0] = new_addr; new_node->addr_count = 1; list_add(&new_node->list, &dlm_node_addrs); spin_unlock(&dlm_node_addrs_spin); return 0; } if (na->addr_count >= DLM_MAX_ADDR_COUNT) { spin_unlock(&dlm_node_addrs_spin); kfree(new_addr); kfree(new_node); return -ENOSPC; } na->addr[na->addr_count++] = new_addr; spin_unlock(&dlm_node_addrs_spin); kfree(new_node); return 0; } /* Data available on socket or listen socket received a connect */ static void lowcomms_data_ready(struct sock *sk) { struct connection *con = sock2con(sk); if (con && !test_and_set_bit(CF_READ_PENDING, &con->flags)) queue_work(recv_workqueue, &con->rwork); } static void lowcomms_write_space(struct sock *sk) { struct connection *con = sock2con(sk); if (!con) return; clear_bit(SOCK_NOSPACE, &con->sock->flags); if (test_and_clear_bit(CF_APP_LIMITED, &con->flags)) { con->sock->sk->sk_write_pending--; clear_bit(SOCKWQ_ASYNC_NOSPACE, &con->sock->flags); } if (!test_and_set_bit(CF_WRITE_PENDING, &con->flags)) queue_work(send_workqueue, &con->swork); } static inline void lowcomms_connect_sock(struct connection *con) { if (test_bit(CF_CLOSE, &con->flags)) return; if (!test_and_set_bit(CF_CONNECT_PENDING, &con->flags)) queue_work(send_workqueue, &con->swork); } static void lowcomms_state_change(struct sock *sk) { /* SCTP layer is not calling sk_data_ready when the connection * is done, so we catch the signal through here. Also, it * doesn't switch socket state when entering shutdown, so we * skip the write in that case. */ if (sk->sk_shutdown) { if (sk->sk_shutdown == RCV_SHUTDOWN) lowcomms_data_ready(sk); } else if (sk->sk_state == TCP_ESTABLISHED) { lowcomms_write_space(sk); } } int dlm_lowcomms_connect_node(int nodeid) { struct connection *con; if (nodeid == dlm_our_nodeid()) return 0; con = nodeid2con(nodeid, GFP_NOFS); if (!con) return -ENOMEM; lowcomms_connect_sock(con); return 0; } static void lowcomms_error_report(struct sock *sk) { struct connection *con; struct sockaddr_storage saddr; int buflen; void (*orig_report)(struct sock *) = NULL; read_lock_bh(&sk->sk_callback_lock); con = sock2con(sk); if (con == NULL) goto out; orig_report = con->orig_error_report; if (con->sock == NULL || kernel_getpeername(con->sock, (struct sockaddr *)&saddr, &buflen)) { printk_ratelimited(KERN_ERR "dlm: node %d: socket error " "sending to node %d, port %d, " "sk_err=%d/%d\n", dlm_our_nodeid(), con->nodeid, dlm_config.ci_tcp_port, sk->sk_err, sk->sk_err_soft); } else if (saddr.ss_family == AF_INET) { struct sockaddr_in *sin4 = (struct sockaddr_in *)&saddr; printk_ratelimited(KERN_ERR "dlm: node %d: socket error " "sending to node %d at %pI4, port %d, " "sk_err=%d/%d\n", dlm_our_nodeid(), con->nodeid, &sin4->sin_addr.s_addr, dlm_config.ci_tcp_port, sk->sk_err, sk->sk_err_soft); } else { struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&saddr; printk_ratelimited(KERN_ERR "dlm: node %d: socket error " "sending to node %d at %u.%u.%u.%u, " "port %d, sk_err=%d/%d\n", dlm_our_nodeid(), con->nodeid, sin6->sin6_addr.s6_addr32[0], sin6->sin6_addr.s6_addr32[1], sin6->sin6_addr.s6_addr32[2], sin6->sin6_addr.s6_addr32[3], dlm_config.ci_tcp_port, sk->sk_err, sk->sk_err_soft); } out: read_unlock_bh(&sk->sk_callback_lock); if (orig_report) orig_report(sk); } /* Note: sk_callback_lock must be locked before calling this function. */ static void save_callbacks(struct connection *con, struct sock *sk) { con->orig_data_ready = sk->sk_data_ready; con->orig_state_change = sk->sk_state_change; con->orig_write_space = sk->sk_write_space; con->orig_error_report = sk->sk_error_report; } static void restore_callbacks(struct connection *con, struct sock *sk) { write_lock_bh(&sk->sk_callback_lock); sk->sk_user_data = NULL; sk->sk_data_ready = con->orig_data_ready; sk->sk_state_change = con->orig_state_change; sk->sk_write_space = con->orig_write_space; sk->sk_error_report = con->orig_error_report; write_unlock_bh(&sk->sk_callback_lock); } /* Make a socket active */ static void add_sock(struct socket *sock, struct connection *con, bool save_cb) { struct sock *sk = sock->sk; write_lock_bh(&sk->sk_callback_lock); con->sock = sock; sk->sk_user_data = con; if (save_cb) save_callbacks(con, sk); /* Install a data_ready callback */ sk->sk_data_ready = lowcomms_data_ready; sk->sk_write_space = lowcomms_write_space; sk->sk_state_change = lowcomms_state_change; sk->sk_allocation = GFP_NOFS; sk->sk_error_report = lowcomms_error_report; write_unlock_bh(&sk->sk_callback_lock); } /* Add the port number to an IPv6 or 4 sockaddr and return the address length */ static void make_sockaddr(struct sockaddr_storage *saddr, uint16_t port, int *addr_len) { saddr->ss_family = dlm_local_addr[0]->ss_family; if (saddr->ss_family == AF_INET) { struct sockaddr_in *in4_addr = (struct sockaddr_in *)saddr; in4_addr->sin_port = cpu_to_be16(port); *addr_len = sizeof(struct sockaddr_in); memset(&in4_addr->sin_zero, 0, sizeof(in4_addr->sin_zero)); } else { struct sockaddr_in6 *in6_addr = (struct sockaddr_in6 *)saddr; in6_addr->sin6_port = cpu_to_be16(port); *addr_len = sizeof(struct sockaddr_in6); } memset((char *)saddr + *addr_len, 0, sizeof(struct sockaddr_storage) - *addr_len); } /* Close a remote connection and tidy up */ static void close_connection(struct connection *con, bool and_other, bool tx, bool rx) { clear_bit(CF_CONNECT_PENDING, &con->flags); clear_bit(CF_WRITE_PENDING, &con->flags); if (tx && cancel_work_sync(&con->swork)) log_print("canceled swork for node %d", con->nodeid); if (rx && cancel_work_sync(&con->rwork)) log_print("canceled rwork for node %d", con->nodeid); mutex_lock(&con->sock_mutex); if (con->sock) { if (!test_bit(CF_IS_OTHERCON, &con->flags)) restore_callbacks(con, con->sock->sk); sock_release(con->sock); con->sock = NULL; } if (con->othercon && and_other) { /* Will only re-enter once. */ close_connection(con->othercon, false, tx, rx); } if (con->rx_page) { __free_page(con->rx_page); con->rx_page = NULL; } con->retries = 0; mutex_unlock(&con->sock_mutex); } /* Data received from remote end */ static int receive_from_sock(struct connection *con) { int ret = 0; struct msghdr msg = {}; struct kvec iov[2]; unsigned len; int r; int call_again_soon = 0; int nvec; mutex_lock(&con->sock_mutex); if (con->sock == NULL) { ret = -EAGAIN; goto out_close; } if (con->nodeid == 0) { ret = -EINVAL; goto out_close; } if (con->rx_page == NULL) { /* * This doesn't need to be atomic, but I think it should * improve performance if it is. */ con->rx_page = alloc_page(GFP_ATOMIC); if (con->rx_page == NULL) goto out_resched; cbuf_init(&con->cb, PAGE_SIZE); } /* * iov[0] is the bit of the circular buffer between the current end * point (cb.base + cb.len) and the end of the buffer. */ iov[0].iov_len = con->cb.base - cbuf_data(&con->cb); iov[0].iov_base = page_address(con->rx_page) + cbuf_data(&con->cb); iov[1].iov_len = 0; nvec = 1; /* * iov[1] is the bit of the circular buffer between the start of the * buffer and the start of the currently used section (cb.base) */ if (cbuf_data(&con->cb) >= con->cb.base) { iov[0].iov_len = PAGE_SIZE - cbuf_data(&con->cb); iov[1].iov_len = con->cb.base; iov[1].iov_base = page_address(con->rx_page); nvec = 2; } len = iov[0].iov_len + iov[1].iov_len; r = ret = kernel_recvmsg(con->sock, &msg, iov, nvec, len, MSG_DONTWAIT | MSG_NOSIGNAL); if (ret <= 0) goto out_close; else if (ret == len) call_again_soon = 1; cbuf_add(&con->cb, ret); ret = dlm_process_incoming_buffer(con->nodeid, page_address(con->rx_page), con->cb.base, con->cb.len, PAGE_SIZE); if (ret == -EBADMSG) { log_print("lowcomms: addr=%p, base=%u, len=%u, read=%d", page_address(con->rx_page), con->cb.base, con->cb.len, r); } if (ret < 0) goto out_close; cbuf_eat(&con->cb, ret); if (cbuf_empty(&con->cb) && !call_again_soon) { __free_page(con->rx_page); con->rx_page = NULL; } if (call_again_soon) goto out_resched; mutex_unlock(&con->sock_mutex); return 0; out_resched: if (!test_and_set_bit(CF_READ_PENDING, &con->flags)) queue_work(recv_workqueue, &con->rwork); mutex_unlock(&con->sock_mutex); return -EAGAIN; out_close: mutex_unlock(&con->sock_mutex); if (ret != -EAGAIN) { close_connection(con, false, true, false); /* Reconnect when there is something to send */ } /* Don't return success if we really got EOF */ if (ret == 0) ret = -EAGAIN; return ret; } /* Listening socket is busy, accept a connection */ static int tcp_accept_from_sock(struct connection *con) { int result; struct sockaddr_storage peeraddr; struct socket *newsock; int len; int nodeid; struct connection *newcon; struct connection *addcon; mutex_lock(&connections_lock); if (!dlm_allow_conn) { mutex_unlock(&connections_lock); return -1; } mutex_unlock(&connections_lock); memset(&peeraddr, 0, sizeof(peeraddr)); result = sock_create_lite(dlm_local_addr[0]->ss_family, SOCK_STREAM, IPPROTO_TCP, &newsock); if (result < 0) return -ENOMEM; mutex_lock_nested(&con->sock_mutex, 0); result = -ENOTCONN; if (con->sock == NULL) goto accept_err; newsock->type = con->sock->type; newsock->ops = con->sock->ops; result = con->sock->ops->accept(con->sock, newsock, O_NONBLOCK, true); if (result < 0) goto accept_err; /* Get the connected socket's peer */ memset(&peeraddr, 0, sizeof(peeraddr)); if (newsock->ops->getname(newsock, (struct sockaddr *)&peeraddr, &len, 2)) { result = -ECONNABORTED; goto accept_err; } /* Get the new node's NODEID */ make_sockaddr(&peeraddr, 0, &len); if (addr_to_nodeid(&peeraddr, &nodeid)) { unsigned char *b=(unsigned char *)&peeraddr; log_print("connect from non cluster node"); print_hex_dump_bytes("ss: ", DUMP_PREFIX_NONE, b, sizeof(struct sockaddr_storage)); sock_release(newsock); mutex_unlock(&con->sock_mutex); return -1; } log_print("got connection from %d", nodeid); /* Check to see if we already have a connection to this node. This * could happen if the two nodes initiate a connection at roughly * the same time and the connections cross on the wire. * In this case we store the incoming one in "othercon" */ newcon = nodeid2con(nodeid, GFP_NOFS); if (!newcon) { result = -ENOMEM; goto accept_err; } mutex_lock_nested(&newcon->sock_mutex, 1); if (newcon->sock) { struct connection *othercon = newcon->othercon; if (!othercon) { othercon = kmem_cache_zalloc(con_cache, GFP_NOFS); if (!othercon) { log_print("failed to allocate incoming socket"); mutex_unlock(&newcon->sock_mutex); result = -ENOMEM; goto accept_err; } othercon->nodeid = nodeid; othercon->rx_action = receive_from_sock; mutex_init(&othercon->sock_mutex); INIT_WORK(&othercon->swork, process_send_sockets); INIT_WORK(&othercon->rwork, process_recv_sockets); set_bit(CF_IS_OTHERCON, &othercon->flags); } if (!othercon->sock) { newcon->othercon = othercon; othercon->sock = newsock; newsock->sk->sk_user_data = othercon; add_sock(newsock, othercon, false); addcon = othercon; } else { printk("Extra connection from node %d attempted\n", nodeid); result = -EAGAIN; mutex_unlock(&newcon->sock_mutex); goto accept_err; } } else { newsock->sk->sk_user_data = newcon; newcon->rx_action = receive_from_sock; /* accept copies the sk after we've saved the callbacks, so we don't want to save them a second time or comm errors will result in calling sk_error_report recursively. */ add_sock(newsock, newcon, false); addcon = newcon; } mutex_unlock(&newcon->sock_mutex); /* * Add it to the active queue in case we got data * between processing the accept adding the socket * to the read_sockets list */ if (!test_and_set_bit(CF_READ_PENDING, &addcon->flags)) queue_work(recv_workqueue, &addcon->rwork); mutex_unlock(&con->sock_mutex); return 0; accept_err: mutex_unlock(&con->sock_mutex); sock_release(newsock); if (result != -EAGAIN) log_print("error accepting connection from node: %d", result); return result; } static int sctp_accept_from_sock(struct connection *con) { /* Check that the new node is in the lockspace */ struct sctp_prim prim; int nodeid; int prim_len, ret; int addr_len; struct connection *newcon; struct connection *addcon; struct socket *newsock; mutex_lock(&connections_lock); if (!dlm_allow_conn) { mutex_unlock(&connections_lock); return -1; } mutex_unlock(&connections_lock); mutex_lock_nested(&con->sock_mutex, 0); ret = kernel_accept(con->sock, &newsock, O_NONBLOCK); if (ret < 0) goto accept_err; memset(&prim, 0, sizeof(struct sctp_prim)); prim_len = sizeof(struct sctp_prim); ret = kernel_getsockopt(newsock, IPPROTO_SCTP, SCTP_PRIMARY_ADDR, (char *)&prim, &prim_len); if (ret < 0) { log_print("getsockopt/sctp_primary_addr failed: %d", ret); goto accept_err; } make_sockaddr(&prim.ssp_addr, 0, &addr_len); ret = addr_to_nodeid(&prim.ssp_addr, &nodeid); if (ret) { unsigned char *b = (unsigned char *)&prim.ssp_addr; log_print("reject connect from unknown addr"); print_hex_dump_bytes("ss: ", DUMP_PREFIX_NONE, b, sizeof(struct sockaddr_storage)); goto accept_err; } newcon = nodeid2con(nodeid, GFP_NOFS); if (!newcon) { ret = -ENOMEM; goto accept_err; } mutex_lock_nested(&newcon->sock_mutex, 1); if (newcon->sock) { struct connection *othercon = newcon->othercon; if (!othercon) { othercon = kmem_cache_zalloc(con_cache, GFP_NOFS); if (!othercon) { log_print("failed to allocate incoming socket"); mutex_unlock(&newcon->sock_mutex); ret = -ENOMEM; goto accept_err; } othercon->nodeid = nodeid; othercon->rx_action = receive_from_sock; mutex_init(&othercon->sock_mutex); INIT_WORK(&othercon->swork, process_send_sockets); INIT_WORK(&othercon->rwork, process_recv_sockets); set_bit(CF_IS_OTHERCON, &othercon->flags); } if (!othercon->sock) { newcon->othercon = othercon; othercon->sock = newsock; newsock->sk->sk_user_data = othercon; add_sock(newsock, othercon, false); addcon = othercon; } else { printk("Extra connection from node %d attempted\n", nodeid); ret = -EAGAIN; mutex_unlock(&newcon->sock_mutex); goto accept_err; } } else { newsock->sk->sk_user_data = newcon; newcon->rx_action = receive_from_sock; add_sock(newsock, newcon, false); addcon = newcon; } log_print("connected to %d", nodeid); mutex_unlock(&newcon->sock_mutex); /* * Add it to the active queue in case we got data * between processing the accept adding the socket * to the read_sockets list */ if (!test_and_set_bit(CF_READ_PENDING, &addcon->flags)) queue_work(recv_workqueue, &addcon->rwork); mutex_unlock(&con->sock_mutex); return 0; accept_err: mutex_unlock(&con->sock_mutex); if (newsock) sock_release(newsock); if (ret != -EAGAIN) log_print("error accepting connection from node: %d", ret); return ret; } static void free_entry(struct writequeue_entry *e) { __free_page(e->page); kfree(e); } /* * writequeue_entry_complete - try to delete and free write queue entry * @e: write queue entry to try to delete * @completed: bytes completed * * writequeue_lock must be held. */ static void writequeue_entry_complete(struct writequeue_entry *e, int completed) { e->offset += completed; e->len -= completed; if (e->len == 0 && e->users == 0) { list_del(&e->list); free_entry(e); } } /* * sctp_bind_addrs - bind a SCTP socket to all our addresses */ static int sctp_bind_addrs(struct connection *con, uint16_t port) { struct sockaddr_storage localaddr; int i, addr_len, result = 0; for (i = 0; i < dlm_local_count; i++) { memcpy(&localaddr, dlm_local_addr[i], sizeof(localaddr)); make_sockaddr(&localaddr, port, &addr_len); if (!i) result = kernel_bind(con->sock, (struct sockaddr *)&localaddr, addr_len); else result = kernel_setsockopt(con->sock, SOL_SCTP, SCTP_SOCKOPT_BINDX_ADD, (char *)&localaddr, addr_len); if (result < 0) { log_print("Can't bind to %d addr number %d, %d.\n", port, i + 1, result); break; } } return result; } /* Initiate an SCTP association. This is a special case of send_to_sock() in that we don't yet have a peeled-off socket for this association, so we use the listening socket and add the primary IP address of the remote node. */ static void sctp_connect_to_sock(struct connection *con) { struct sockaddr_storage daddr; int one = 1; int result; int addr_len; struct socket *sock; if (con->nodeid == 0) { log_print("attempt to connect sock 0 foiled"); return; } mutex_lock(&con->sock_mutex); /* Some odd races can cause double-connects, ignore them */ if (con->retries++ > MAX_CONNECT_RETRIES) goto out; if (con->sock) { log_print("node %d already connected.", con->nodeid); goto out; } memset(&daddr, 0, sizeof(daddr)); result = nodeid_to_addr(con->nodeid, &daddr, NULL, true); if (result < 0) { log_print("no address for nodeid %d", con->nodeid); goto out; } /* Create a socket to communicate with */ result = sock_create_kern(&init_net, dlm_local_addr[0]->ss_family, SOCK_STREAM, IPPROTO_SCTP, &sock); if (result < 0) goto socket_err; sock->sk->sk_user_data = con; con->rx_action = receive_from_sock; con->connect_action = sctp_connect_to_sock; add_sock(sock, con, true); /* Bind to all addresses. */ if (sctp_bind_addrs(con, 0)) goto bind_err; make_sockaddr(&daddr, dlm_config.ci_tcp_port, &addr_len); log_print("connecting to %d", con->nodeid); /* Turn off Nagle's algorithm */ kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY, (char *)&one, sizeof(one)); result = sock->ops->connect(sock, (struct sockaddr *)&daddr, addr_len, O_NONBLOCK); if (result == -EINPROGRESS) result = 0; if (result == 0) goto out; bind_err: con->sock = NULL; sock_release(sock); socket_err: /* * Some errors are fatal and this list might need adjusting. For other * errors we try again until the max number of retries is reached. */ if (result != -EHOSTUNREACH && result != -ENETUNREACH && result != -ENETDOWN && result != -EINVAL && result != -EPROTONOSUPPORT) { log_print("connect %d try %d error %d", con->nodeid, con->retries, result); mutex_unlock(&con->sock_mutex); msleep(1000); clear_bit(CF_CONNECT_PENDING, &con->flags); lowcomms_connect_sock(con); return; } out: mutex_unlock(&con->sock_mutex); set_bit(CF_WRITE_PENDING, &con->flags); } /* Connect a new socket to its peer */ static void tcp_connect_to_sock(struct connection *con) { struct sockaddr_storage saddr, src_addr; int addr_len; struct socket *sock = NULL; int one = 1; int result; if (con->nodeid == 0) { log_print("attempt to connect sock 0 foiled"); return; } mutex_lock(&con->sock_mutex); if (con->retries++ > MAX_CONNECT_RETRIES) goto out; /* Some odd races can cause double-connects, ignore them */ if (con->sock) goto out; /* Create a socket to communicate with */ result = sock_create_kern(&init_net, dlm_local_addr[0]->ss_family, SOCK_STREAM, IPPROTO_TCP, &sock); if (result < 0) goto out_err; memset(&saddr, 0, sizeof(saddr)); result = nodeid_to_addr(con->nodeid, &saddr, NULL, false); if (result < 0) { log_print("no address for nodeid %d", con->nodeid); goto out_err; } sock->sk->sk_user_data = con; con->rx_action = receive_from_sock; con->connect_action = tcp_connect_to_sock; add_sock(sock, con, true); /* Bind to our cluster-known address connecting to avoid routing problems */ memcpy(&src_addr, dlm_local_addr[0], sizeof(src_addr)); make_sockaddr(&src_addr, 0, &addr_len); result = sock->ops->bind(sock, (struct sockaddr *) &src_addr, addr_len); if (result < 0) { log_print("could not bind for connect: %d", result); /* This *may* not indicate a critical error */ } make_sockaddr(&saddr, dlm_config.ci_tcp_port, &addr_len); log_print("connecting to %d", con->nodeid); /* Turn off Nagle's algorithm */ kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY, (char *)&one, sizeof(one)); result = sock->ops->connect(sock, (struct sockaddr *)&saddr, addr_len, O_NONBLOCK); if (result == -EINPROGRESS) result = 0; if (result == 0) goto out; out_err: if (con->sock) { sock_release(con->sock); con->sock = NULL; } else if (sock) { sock_release(sock); } /* * Some errors are fatal and this list might need adjusting. For other * errors we try again until the max number of retries is reached. */ if (result != -EHOSTUNREACH && result != -ENETUNREACH && result != -ENETDOWN && result != -EINVAL && result != -EPROTONOSUPPORT) { log_print("connect %d try %d error %d", con->nodeid, con->retries, result); mutex_unlock(&con->sock_mutex); msleep(1000); clear_bit(CF_CONNECT_PENDING, &con->flags); lowcomms_connect_sock(con); return; } out: mutex_unlock(&con->sock_mutex); set_bit(CF_WRITE_PENDING, &con->flags); return; } static struct socket *tcp_create_listen_sock(struct connection *con, struct sockaddr_storage *saddr) { struct socket *sock = NULL; int result = 0; int one = 1; int addr_len; if (dlm_local_addr[0]->ss_family == AF_INET) addr_len = sizeof(struct sockaddr_in); else addr_len = sizeof(struct sockaddr_in6); /* Create a socket to communicate with */ result = sock_create_kern(&init_net, dlm_local_addr[0]->ss_family, SOCK_STREAM, IPPROTO_TCP, &sock); if (result < 0) { log_print("Can't create listening comms socket"); goto create_out; } /* Turn off Nagle's algorithm */ kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY, (char *)&one, sizeof(one)); result = kernel_setsockopt(sock, SOL_SOCKET, SO_REUSEADDR, (char *)&one, sizeof(one)); if (result < 0) { log_print("Failed to set SO_REUSEADDR on socket: %d", result); } sock->sk->sk_user_data = con; con->rx_action = tcp_accept_from_sock; con->connect_action = tcp_connect_to_sock; /* Bind to our port */ make_sockaddr(saddr, dlm_config.ci_tcp_port, &addr_len); result = sock->ops->bind(sock, (struct sockaddr *) saddr, addr_len); if (result < 0) { log_print("Can't bind to port %d", dlm_config.ci_tcp_port); sock_release(sock); sock = NULL; con->sock = NULL; goto create_out; } result = kernel_setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE, (char *)&one, sizeof(one)); if (result < 0) { log_print("Set keepalive failed: %d", result); } result = sock->ops->listen(sock, 5); if (result < 0) { log_print("Can't listen on port %d", dlm_config.ci_tcp_port); sock_release(sock); sock = NULL; goto create_out; } create_out: return sock; } /* Get local addresses */ static void init_local(void) { struct sockaddr_storage sas, *addr; int i; dlm_local_count = 0; for (i = 0; i < DLM_MAX_ADDR_COUNT; i++) { if (dlm_our_addr(&sas, i)) break; addr = kmemdup(&sas, sizeof(*addr), GFP_NOFS); if (!addr) break; dlm_local_addr[dlm_local_count++] = addr; } } /* Initialise SCTP socket and bind to all interfaces */ static int sctp_listen_for_all(void) { struct socket *sock = NULL; int result = -EINVAL; struct connection *con = nodeid2con(0, GFP_NOFS); int bufsize = NEEDED_RMEM; int one = 1; if (!con) return -ENOMEM; log_print("Using SCTP for communications"); result = sock_create_kern(&init_net, dlm_local_addr[0]->ss_family, SOCK_STREAM, IPPROTO_SCTP, &sock); if (result < 0) { log_print("Can't create comms socket, check SCTP is loaded"); goto out; } result = kernel_setsockopt(sock, SOL_SOCKET, SO_RCVBUFFORCE, (char *)&bufsize, sizeof(bufsize)); if (result) log_print("Error increasing buffer space on socket %d", result); result = kernel_setsockopt(sock, SOL_SCTP, SCTP_NODELAY, (char *)&one, sizeof(one)); if (result < 0) log_print("Could not set SCTP NODELAY error %d\n", result); write_lock_bh(&sock->sk->sk_callback_lock); /* Init con struct */ sock->sk->sk_user_data = con; con->sock = sock; con->sock->sk->sk_data_ready = lowcomms_data_ready; con->rx_action = sctp_accept_from_sock; con->connect_action = sctp_connect_to_sock; write_unlock_bh(&sock->sk->sk_callback_lock); /* Bind to all addresses. */ if (sctp_bind_addrs(con, dlm_config.ci_tcp_port)) goto create_delsock; result = sock->ops->listen(sock, 5); if (result < 0) { log_print("Can't set socket listening"); goto create_delsock; } return 0; create_delsock: sock_release(sock); con->sock = NULL; out: return result; } static int tcp_listen_for_all(void) { struct socket *sock = NULL; struct connection *con = nodeid2con(0, GFP_NOFS); int result = -EINVAL; if (!con) return -ENOMEM; /* We don't support multi-homed hosts */ if (dlm_local_addr[1] != NULL) { log_print("TCP protocol can't handle multi-homed hosts, " "try SCTP"); return -EINVAL; } log_print("Using TCP for communications"); sock = tcp_create_listen_sock(con, dlm_local_addr[0]); if (sock) { add_sock(sock, con, true); result = 0; } else { result = -EADDRINUSE; } return result; } static struct writequeue_entry *new_writequeue_entry(struct connection *con, gfp_t allocation) { struct writequeue_entry *entry; entry = kmalloc(sizeof(struct writequeue_entry), allocation); if (!entry) return NULL; entry->page = alloc_page(allocation); if (!entry->page) { kfree(entry); return NULL; } entry->offset = 0; entry->len = 0; entry->end = 0; entry->users = 0; entry->con = con; return entry; } void *dlm_lowcomms_get_buffer(int nodeid, int len, gfp_t allocation, char **ppc) { struct connection *con; struct writequeue_entry *e; int offset = 0; con = nodeid2con(nodeid, allocation); if (!con) return NULL; spin_lock(&con->writequeue_lock); e = list_entry(con->writequeue.prev, struct writequeue_entry, list); if ((&e->list == &con->writequeue) || (PAGE_SIZE - e->end < len)) { e = NULL; } else { offset = e->end; e->end += len; e->users++; } spin_unlock(&con->writequeue_lock); if (e) { got_one: *ppc = page_address(e->page) + offset; return e; } e = new_writequeue_entry(con, allocation); if (e) { spin_lock(&con->writequeue_lock); offset = e->end; e->end += len; e->users++; list_add_tail(&e->list, &con->writequeue); spin_unlock(&con->writequeue_lock); goto got_one; } return NULL; } void dlm_lowcomms_commit_buffer(void *mh) { struct writequeue_entry *e = (struct writequeue_entry *)mh; struct connection *con = e->con; int users; spin_lock(&con->writequeue_lock); users = --e->users; if (users) goto out; e->len = e->end - e->offset; spin_unlock(&con->writequeue_lock); if (!test_and_set_bit(CF_WRITE_PENDING, &con->flags)) { queue_work(send_workqueue, &con->swork); } return; out: spin_unlock(&con->writequeue_lock); return; } /* Send a message */ static void send_to_sock(struct connection *con) { int ret = 0; const int msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL; struct writequeue_entry *e; int len, offset; int count = 0; mutex_lock(&con->sock_mutex); if (con->sock == NULL) goto out_connect; spin_lock(&con->writequeue_lock); for (;;) { e = list_entry(con->writequeue.next, struct writequeue_entry, list); if ((struct list_head *) e == &con->writequeue) break; len = e->len; offset = e->offset; BUG_ON(len == 0 && e->users == 0); spin_unlock(&con->writequeue_lock); ret = 0; if (len) { ret = kernel_sendpage(con->sock, e->page, offset, len, msg_flags); if (ret == -EAGAIN || ret == 0) { if (ret == -EAGAIN && test_bit(SOCKWQ_ASYNC_NOSPACE, &con->sock->flags) && !test_and_set_bit(CF_APP_LIMITED, &con->flags)) { /* Notify TCP that we're limited by the * application window size. */ set_bit(SOCK_NOSPACE, &con->sock->flags); con->sock->sk->sk_write_pending++; } cond_resched(); goto out; } else if (ret < 0) goto send_error; } /* Don't starve people filling buffers */ if (++count >= MAX_SEND_MSG_COUNT) { cond_resched(); count = 0; } spin_lock(&con->writequeue_lock); writequeue_entry_complete(e, ret); } spin_unlock(&con->writequeue_lock); out: mutex_unlock(&con->sock_mutex); return; send_error: mutex_unlock(&con->sock_mutex); close_connection(con, false, false, true); lowcomms_connect_sock(con); return; out_connect: mutex_unlock(&con->sock_mutex); lowcomms_connect_sock(con); } static void clean_one_writequeue(struct connection *con) { struct writequeue_entry *e, *safe; spin_lock(&con->writequeue_lock); list_for_each_entry_safe(e, safe, &con->writequeue, list) { list_del(&e->list); free_entry(e); } spin_unlock(&con->writequeue_lock); } /* Called from recovery when it knows that a node has left the cluster */ int dlm_lowcomms_close(int nodeid) { struct connection *con; struct dlm_node_addr *na; log_print("closing connection to node %d", nodeid); con = nodeid2con(nodeid, 0); if (con) { set_bit(CF_CLOSE, &con->flags); close_connection(con, true, true, true); clean_one_writequeue(con); } spin_lock(&dlm_node_addrs_spin); na = find_node_addr(nodeid); if (na) { list_del(&na->list); while (na->addr_count--) kfree(na->addr[na->addr_count]); kfree(na); } spin_unlock(&dlm_node_addrs_spin); return 0; } /* Receive workqueue function */ static void process_recv_sockets(struct work_struct *work) { struct connection *con = container_of(work, struct connection, rwork); int err; clear_bit(CF_READ_PENDING, &con->flags); do { err = con->rx_action(con); } while (!err); } /* Send workqueue function */ static void process_send_sockets(struct work_struct *work) { struct connection *con = container_of(work, struct connection, swork); if (test_and_clear_bit(CF_CONNECT_PENDING, &con->flags)) con->connect_action(con); if (test_and_clear_bit(CF_WRITE_PENDING, &con->flags)) send_to_sock(con); } /* Discard all entries on the write queues */ static void clean_writequeues(void) { foreach_conn(clean_one_writequeue); } static void work_stop(void) { destroy_workqueue(recv_workqueue); destroy_workqueue(send_workqueue); } static int work_start(void) { recv_workqueue = alloc_workqueue("dlm_recv", WQ_UNBOUND | WQ_MEM_RECLAIM, 1); if (!recv_workqueue) { log_print("can't start dlm_recv"); return -ENOMEM; } send_workqueue = alloc_workqueue("dlm_send", WQ_UNBOUND | WQ_MEM_RECLAIM, 1); if (!send_workqueue) { log_print("can't start dlm_send"); destroy_workqueue(recv_workqueue); return -ENOMEM; } return 0; } static void stop_conn(struct connection *con) { con->flags |= 0x0F; if (con->sock && con->sock->sk) con->sock->sk->sk_user_data = NULL; } static void free_conn(struct connection *con) { close_connection(con, true, true, true); if (con->othercon) kmem_cache_free(con_cache, con->othercon); hlist_del(&con->list); kmem_cache_free(con_cache, con); } void dlm_lowcomms_stop(void) { /* Set all the flags to prevent any socket activity. */ mutex_lock(&connections_lock); dlm_allow_conn = 0; foreach_conn(stop_conn); clean_writequeues(); foreach_conn(free_conn); mutex_unlock(&connections_lock); work_stop(); kmem_cache_destroy(con_cache); } int dlm_lowcomms_start(void) { int error = -EINVAL; struct connection *con; int i; for (i = 0; i < CONN_HASH_SIZE; i++) INIT_HLIST_HEAD(&connection_hash[i]); init_local(); if (!dlm_local_count) { error = -ENOTCONN; log_print("no local IP address has been set"); goto fail; } error = -ENOMEM; con_cache = kmem_cache_create("dlm_conn", sizeof(struct connection), __alignof__(struct connection), 0, NULL); if (!con_cache) goto fail; error = work_start(); if (error) goto fail_destroy; dlm_allow_conn = 1; /* Start listening */ if (dlm_config.ci_protocol == 0) error = tcp_listen_for_all(); else error = sctp_listen_for_all(); if (error) goto fail_unlisten; return 0; fail_unlisten: dlm_allow_conn = 0; con = nodeid2con(0,0); if (con) { close_connection(con, false, true, true); kmem_cache_free(con_cache, con); } fail_destroy: kmem_cache_destroy(con_cache); fail: return error; } void dlm_lowcomms_exit(void) { struct dlm_node_addr *na, *safe; spin_lock(&dlm_node_addrs_spin); list_for_each_entry_safe(na, safe, &dlm_node_addrs, list) { list_del(&na->list); while (na->addr_count--) kfree(na->addr[na->addr_count]); kfree(na); } spin_unlock(&dlm_node_addrs_spin); } |
| 3039 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 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 | /* * include/net/dsa.h - Driver for Distributed Switch Architecture switch chips * Copyright (c) 2008-2009 Marvell Semiconductor * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. */ #ifndef __LINUX_NET_DSA_H #define __LINUX_NET_DSA_H #include <linux/if.h> #include <linux/if_ether.h> #include <linux/list.h> #include <linux/notifier.h> #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/of.h> #include <linux/ethtool.h> #include <net/devlink.h> #include <net/switchdev.h> struct tc_action; struct phy_device; struct fixed_phy_status; enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = 0, DSA_TAG_PROTO_BRCM, DSA_TAG_PROTO_DSA, DSA_TAG_PROTO_EDSA, DSA_TAG_PROTO_KSZ, DSA_TAG_PROTO_LAN9303, DSA_TAG_PROTO_MTK, DSA_TAG_PROTO_QCA, DSA_TAG_PROTO_TRAILER, DSA_TAG_LAST, /* MUST BE LAST */ }; #define DSA_MAX_SWITCHES 4 #define DSA_MAX_PORTS 12 #define DSA_RTABLE_NONE -1 struct dsa_chip_data { /* * How to access the switch configuration registers. */ struct device *host_dev; int sw_addr; /* * Reference to network devices */ struct device *netdev[DSA_MAX_PORTS]; /* set to size of eeprom if supported by the switch */ int eeprom_len; /* Device tree node pointer for this specific switch chip * used during switch setup in case additional properties * and resources needs to be used */ struct device_node *of_node; /* * The names of the switch's ports. Use "cpu" to * designate the switch port that the cpu is connected to, * "dsa" to indicate that this port is a DSA link to * another switch, NULL to indicate the port is unused, * or any other string to indicate this is a physical port. */ char *port_names[DSA_MAX_PORTS]; struct device_node *port_dn[DSA_MAX_PORTS]; /* * An array of which element [a] indicates which port on this * switch should be used to send packets to that are destined * for switch a. Can be NULL if there is only one switch chip. */ s8 rtable[DSA_MAX_SWITCHES]; }; struct dsa_platform_data { /* * Reference to a Linux network interface that connects * to the root switch chip of the tree. */ struct device *netdev; struct net_device *of_netdev; /* * Info structs describing each of the switch chips * connected via this network interface. */ int nr_chips; struct dsa_chip_data *chip; }; struct packet_type; struct dsa_device_ops { struct sk_buff *(*xmit)(struct sk_buff *skb, struct net_device *dev); struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt); int (*flow_dissect)(const struct sk_buff *skb, __be16 *proto, int *offset); }; struct dsa_switch_tree { struct list_head list; /* Notifier chain for switch-wide events */ struct raw_notifier_head nh; /* Tree identifier */ u32 tree; /* Number of switches attached to this tree */ struct kref refcount; /* Has this tree been applied to the hardware? */ bool applied; /* * Configuration data for the platform device that owns * this dsa switch tree instance. */ struct dsa_platform_data *pd; /* Copy of tag_ops->rcv for faster access in hot path */ struct sk_buff * (*rcv)(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt); /* * The switch port to which the CPU is attached. */ struct dsa_port *cpu_dp; /* * Data for the individual switch chips. */ struct dsa_switch *ds[DSA_MAX_SWITCHES]; /* * Tagging protocol operations for adding and removing an * encapsulation tag. */ const struct dsa_device_ops *tag_ops; }; /* TC matchall action types, only mirroring for now */ enum dsa_port_mall_action_type { DSA_PORT_MALL_MIRROR, }; /* TC mirroring entry */ struct dsa_mall_mirror_tc_entry { u8 to_local_port; bool ingress; }; /* TC matchall entry */ struct dsa_mall_tc_entry { struct list_head list; unsigned long cookie; enum dsa_port_mall_action_type type; union { struct dsa_mall_mirror_tc_entry mirror; }; }; struct dsa_port { struct dsa_switch *ds; unsigned int index; const char *name; struct dsa_port *cpu_dp; struct net_device *netdev; struct device_node *dn; unsigned int ageing_time; u8 stp_state; struct net_device *bridge_dev; struct devlink_port devlink_port; /* * Original copy of the master netdev ethtool_ops */ struct ethtool_ops ethtool_ops; const struct ethtool_ops *orig_ethtool_ops; }; struct dsa_switch { struct device *dev; /* * Parent switch tree, and switch index. */ struct dsa_switch_tree *dst; int index; /* Listener for switch fabric events */ struct notifier_block nb; /* * Give the switch driver somewhere to hang its private data * structure. */ void *priv; /* * Configuration data for this switch. */ struct dsa_chip_data *cd; /* * The switch operations. */ const struct dsa_switch_ops *ops; /* * An array of which element [a] indicates which port on this * switch should be used to send packets to that are destined * for switch a. Can be NULL if there is only one switch chip. */ s8 rtable[DSA_MAX_SWITCHES]; /* * Slave mii_bus and devices for the individual ports. */ u32 dsa_port_mask; u32 cpu_port_mask; u32 enabled_port_mask; u32 phys_mii_mask; struct mii_bus *slave_mii_bus; /* Ageing Time limits in msecs */ unsigned int ageing_time_min; unsigned int ageing_time_max; /* devlink used to represent this switch device */ struct devlink *devlink; /* Number of switch port queues */ unsigned int num_tx_queues; /* Dynamically allocated ports, keep last */ size_t num_ports; struct dsa_port ports[]; }; static inline bool dsa_is_cpu_port(struct dsa_switch *ds, int p) { return !!(ds->cpu_port_mask & (1 << p)); } static inline bool dsa_is_dsa_port(struct dsa_switch *ds, int p) { return !!((ds->dsa_port_mask) & (1 << p)); } static inline bool dsa_is_normal_port(struct dsa_switch *ds, int p) { return !dsa_is_cpu_port(ds, p) && !dsa_is_dsa_port(ds, p); } static inline u8 dsa_upstream_port(struct dsa_switch *ds) { struct dsa_switch_tree *dst = ds->dst; /* * If this is the root switch (i.e. the switch that connects * to the CPU), return the cpu port number on this switch. * Else return the (DSA) port number that connects to the * switch that is one hop closer to the cpu. */ if (dst->cpu_dp->ds == ds) return dst->cpu_dp->index; else return ds->rtable[dst->cpu_dp->ds->index]; } typedef int dsa_fdb_dump_cb_t(const unsigned char *addr, u16 vid, bool is_static, void *data); struct dsa_switch_ops { /* * Legacy probing. */ const char *(*probe)(struct device *dsa_dev, struct device *host_dev, int sw_addr, void **priv); enum dsa_tag_protocol (*get_tag_protocol)(struct dsa_switch *ds); int (*setup)(struct dsa_switch *ds); int (*set_addr)(struct dsa_switch *ds, u8 *addr); u32 (*get_phy_flags)(struct dsa_switch *ds, int port); /* * Access to the switch's PHY registers. */ int (*phy_read)(struct dsa_switch *ds, int port, int regnum); int (*phy_write)(struct dsa_switch *ds, int port, int regnum, u16 val); /* * Link state adjustment (called from libphy) */ void (*adjust_link)(struct dsa_switch *ds, int port, struct phy_device *phydev); void (*fixed_link_update)(struct dsa_switch *ds, int port, struct fixed_phy_status *st); /* * ethtool hardware statistics. */ void (*get_strings)(struct dsa_switch *ds, int port, uint8_t *data); void (*get_ethtool_stats)(struct dsa_switch *ds, int port, uint64_t *data); int (*get_sset_count)(struct dsa_switch *ds); /* * ethtool Wake-on-LAN */ void (*get_wol)(struct dsa_switch *ds, int port, struct ethtool_wolinfo *w); int (*set_wol)(struct dsa_switch *ds, int port, struct ethtool_wolinfo *w); /* * Suspend and resume */ int (*suspend)(struct dsa_switch *ds); int (*resume)(struct dsa_switch *ds); /* * Port enable/disable */ int (*port_enable)(struct dsa_switch *ds, int port, struct phy_device *phy); void (*port_disable)(struct dsa_switch *ds, int port, struct phy_device *phy); /* * Port's MAC EEE settings */ int (*set_mac_eee)(struct dsa_switch *ds, int port, struct ethtool_eee *e); int (*get_mac_eee)(struct dsa_switch *ds, int port, struct ethtool_eee *e); /* EEPROM access */ int (*get_eeprom_len)(struct dsa_switch *ds); int (*get_eeprom)(struct dsa_switch *ds, struct ethtool_eeprom *eeprom, u8 *data); int (*set_eeprom)(struct dsa_switch *ds, struct ethtool_eeprom *eeprom, u8 *data); /* * Register access. */ int (*get_regs_len)(struct dsa_switch *ds, int port); void (*get_regs)(struct dsa_switch *ds, int port, struct ethtool_regs *regs, void *p); /* * Bridge integration */ int (*set_ageing_time)(struct dsa_switch *ds, unsigned int msecs); int (*port_bridge_join)(struct dsa_switch *ds, int port, struct net_device *bridge); void (*port_bridge_leave)(struct dsa_switch *ds, int port, struct net_device *bridge); void (*port_stp_state_set)(struct dsa_switch *ds, int port, u8 state); void (*port_fast_age)(struct dsa_switch *ds, int port); /* * VLAN support */ int (*port_vlan_filtering)(struct dsa_switch *ds, int port, bool vlan_filtering); int (*port_vlan_prepare)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan, struct switchdev_trans *trans); void (*port_vlan_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan, struct switchdev_trans *trans); int (*port_vlan_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan); /* * Forwarding database */ int (*port_fdb_add)(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid); int (*port_fdb_del)(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid); int (*port_fdb_dump)(struct dsa_switch *ds, int port, dsa_fdb_dump_cb_t *cb, void *data); /* * Multicast database */ int (*port_mdb_prepare)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb, struct switchdev_trans *trans); void (*port_mdb_add)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb, struct switchdev_trans *trans); int (*port_mdb_del)(struct dsa_switch *ds, int port, const struct switchdev_obj_port_mdb *mdb); /* * RXNFC */ int (*get_rxnfc)(struct dsa_switch *ds, int port, struct ethtool_rxnfc *nfc, u32 *rule_locs); int (*set_rxnfc)(struct dsa_switch *ds, int port, struct ethtool_rxnfc *nfc); /* * TC integration */ int (*port_mirror_add)(struct dsa_switch *ds, int port, struct dsa_mall_mirror_tc_entry *mirror, bool ingress); void (*port_mirror_del)(struct dsa_switch *ds, int port, struct dsa_mall_mirror_tc_entry *mirror); /* * Cross-chip operations */ int (*crosschip_bridge_join)(struct dsa_switch *ds, int sw_index, int port, struct net_device *br); void (*crosschip_bridge_leave)(struct dsa_switch *ds, int sw_index, int port, struct net_device *br); }; struct dsa_switch_driver { struct list_head list; const struct dsa_switch_ops *ops; }; /* Legacy driver registration */ void register_switch_driver(struct dsa_switch_driver *type); void unregister_switch_driver(struct dsa_switch_driver *type); struct mii_bus *dsa_host_dev_to_mii_bus(struct device *dev); struct net_device *dsa_dev_to_net_device(struct device *dev); /* Keep inline for faster access in hot path */ static inline bool netdev_uses_dsa(struct net_device *dev) { #if IS_ENABLED(CONFIG_NET_DSA) return dev->dsa_ptr && dev->dsa_ptr->rcv; #endif return false; } struct dsa_switch *dsa_switch_alloc(struct device *dev, size_t n); void dsa_unregister_switch(struct dsa_switch *ds); int dsa_register_switch(struct dsa_switch *ds); #ifdef CONFIG_PM_SLEEP int dsa_switch_suspend(struct dsa_switch *ds); int dsa_switch_resume(struct dsa_switch *ds); #else static inline int dsa_switch_suspend(struct dsa_switch *ds) { return 0; } static inline int dsa_switch_resume(struct dsa_switch *ds) { return 0; } #endif /* CONFIG_PM_SLEEP */ #endif |
| 158 158 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_IRQDESC_H #define _LINUX_IRQDESC_H #include <linux/rcupdate.h> #include <linux/kobject.h> #include <linux/mutex.h> /* * Core internal functions to deal with irq descriptors */ struct irq_affinity_notify; struct proc_dir_entry; struct module; struct irq_desc; struct irq_domain; struct pt_regs; /** * struct irq_desc - interrupt descriptor * @irq_common_data: per irq and chip data passed down to chip functions * @kstat_irqs: irq stats per cpu * @handle_irq: highlevel irq-events handler * @preflow_handler: handler called before the flow handler (currently used by sparc) * @action: the irq action chain * @status: status information * @core_internal_state__do_not_mess_with_it: core internal status information * @depth: disable-depth, for nested irq_disable() calls * @wake_depth: enable depth, for multiple irq_set_irq_wake() callers * @irq_count: stats field to detect stalled irqs * @last_unhandled: aging timer for unhandled count * @irqs_unhandled: stats field for spurious unhandled interrupts * @threads_handled: stats field for deferred spurious detection of threaded handlers * @threads_handled_last: comparator field for deferred spurious detection of theraded handlers * @lock: locking for SMP * @affinity_hint: hint to user space for preferred irq affinity * @affinity_notify: context for notification of affinity changes * @pending_mask: pending rebalanced interrupts * @threads_oneshot: bitfield to handle shared oneshot threads * @threads_active: number of irqaction threads currently running * @wait_for_threads: wait queue for sync_irq to wait for threaded handlers * @nr_actions: number of installed actions on this descriptor * @no_suspend_depth: number of irqactions on a irq descriptor with * IRQF_NO_SUSPEND set * @force_resume_depth: number of irqactions on a irq descriptor with * IRQF_FORCE_RESUME set * @rcu: rcu head for delayed free * @kobj: kobject used to represent this struct in sysfs * @request_mutex: mutex to protect request/free before locking desc->lock * @dir: /proc/irq/ procfs entry * @debugfs_file: dentry for the debugfs file * @name: flow handler name for /proc/interrupts output */ struct irq_desc { struct irq_common_data irq_common_data; struct irq_data irq_data; unsigned int __percpu *kstat_irqs; irq_flow_handler_t handle_irq; #ifdef CONFIG_IRQ_PREFLOW_FASTEOI irq_preflow_handler_t preflow_handler; #endif struct irqaction *action; /* IRQ action list */ unsigned int status_use_accessors; unsigned int core_internal_state__do_not_mess_with_it; unsigned int depth; /* nested irq disables */ unsigned int wake_depth; /* nested wake enables */ unsigned int tot_count; unsigned int irq_count; /* For detecting broken IRQs */ unsigned long last_unhandled; /* Aging timer for unhandled count */ unsigned int irqs_unhandled; atomic_t threads_handled; int threads_handled_last; raw_spinlock_t lock; struct cpumask *percpu_enabled; const struct cpumask *percpu_affinity; #ifdef CONFIG_SMP const struct cpumask *affinity_hint; struct irq_affinity_notify *affinity_notify; #ifdef CONFIG_GENERIC_PENDING_IRQ cpumask_var_t pending_mask; #endif #endif unsigned long threads_oneshot; atomic_t threads_active; wait_queue_head_t wait_for_threads; #ifdef CONFIG_PM_SLEEP unsigned int nr_actions; unsigned int no_suspend_depth; unsigned int cond_suspend_depth; unsigned int force_resume_depth; #endif #ifdef CONFIG_PROC_FS struct proc_dir_entry *dir; #endif #ifdef CONFIG_GENERIC_IRQ_DEBUGFS struct dentry *debugfs_file; #endif #ifdef CONFIG_SPARSE_IRQ struct rcu_head rcu; struct kobject kobj; #endif struct mutex request_mutex; int parent_irq; struct module *owner; const char *name; } ____cacheline_internodealigned_in_smp; #ifdef CONFIG_SPARSE_IRQ extern void irq_lock_sparse(void); extern void irq_unlock_sparse(void); #else static inline void irq_lock_sparse(void) { } static inline void irq_unlock_sparse(void) { } extern struct irq_desc irq_desc[NR_IRQS]; #endif static inline struct irq_desc *irq_data_to_desc(struct irq_data *data) { return container_of(data->common, struct irq_desc, irq_common_data); } static inline unsigned int irq_desc_get_irq(struct irq_desc *desc) { return desc->irq_data.irq; } static inline struct irq_data *irq_desc_get_irq_data(struct irq_desc *desc) { return &desc->irq_data; } static inline struct irq_chip *irq_desc_get_chip(struct irq_desc *desc) { return desc->irq_data.chip; } static inline void *irq_desc_get_chip_data(struct irq_desc *desc) { return desc->irq_data.chip_data; } static inline void *irq_desc_get_handler_data(struct irq_desc *desc) { return desc->irq_common_data.handler_data; } static inline struct msi_desc *irq_desc_get_msi_desc(struct irq_desc *desc) { return desc->irq_common_data.msi_desc; } /* * Architectures call this to let the generic IRQ layer * handle an interrupt. */ static inline void generic_handle_irq_desc(struct irq_desc *desc) { desc->handle_irq(desc); } int generic_handle_irq(unsigned int irq); #ifdef CONFIG_HANDLE_DOMAIN_IRQ /* * Convert a HW interrupt number to a logical one using a IRQ domain, * and handle the result interrupt number. Return -EINVAL if * conversion failed. Providing a NULL domain indicates that the * conversion has already been done. */ int __handle_domain_irq(struct irq_domain *domain, unsigned int hwirq, bool lookup, struct pt_regs *regs); static inline int handle_domain_irq(struct irq_domain *domain, unsigned int hwirq, struct pt_regs *regs) { return __handle_domain_irq(domain, hwirq, true, regs); } #endif /* Test to see if a driver has successfully requested an irq */ static inline int irq_desc_has_action(struct irq_desc *desc) { return desc->action != NULL; } static inline int irq_has_action(unsigned int irq) { return irq_desc_has_action(irq_to_desc(irq)); } /** * irq_set_handler_locked - Set irq handler from a locked region * @data: Pointer to the irq_data structure which identifies the irq * @handler: Flow control handler function for this interrupt * * Sets the handler in the irq descriptor associated to @data. * * Must be called with irq_desc locked and valid parameters. Typical * call site is the irq_set_type() callback. */ static inline void irq_set_handler_locked(struct irq_data *data, irq_flow_handler_t handler) { struct irq_desc *desc = irq_data_to_desc(data); desc->handle_irq = handler; } /** * irq_set_chip_handler_name_locked - Set chip, handler and name from a locked region * @data: Pointer to the irq_data structure for which the chip is set * @chip: Pointer to the new irq chip * @handler: Flow control handler function for this interrupt * @name: Name of the interrupt * * Replace the irq chip at the proper hierarchy level in @data and * sets the handler and name in the associated irq descriptor. * * Must be called with irq_desc locked and valid parameters. */ static inline void irq_set_chip_handler_name_locked(struct irq_data *data, struct irq_chip *chip, irq_flow_handler_t handler, const char *name) { struct irq_desc *desc = irq_data_to_desc(data); desc->handle_irq = handler; desc->name = name; data->chip = chip; } static inline int irq_balancing_disabled(unsigned int irq) { struct irq_desc *desc; desc = irq_to_desc(irq); return desc->status_use_accessors & IRQ_NO_BALANCING_MASK; } static inline int irq_is_percpu(unsigned int irq) { struct irq_desc *desc; desc = irq_to_desc(irq); return desc->status_use_accessors & IRQ_PER_CPU; } static inline void irq_set_lockdep_class(unsigned int irq, struct lock_class_key *class) { struct irq_desc *desc = irq_to_desc(irq); if (desc) lockdep_set_class(&desc->lock, class); } #ifdef CONFIG_IRQ_PREFLOW_FASTEOI static inline void __irq_set_preflow_handler(unsigned int irq, irq_preflow_handler_t handler) { struct irq_desc *desc; desc = irq_to_desc(irq); desc->preflow_handler = handler; } #endif #endif |
| 80 75 75 62 57 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 | /* * Key-agreement Protocol Primitives (KPP) * * Copyright (c) 2016, Intel Corporation * Authors: Salvatore Benedetto <salvatore.benedetto@intel.com> * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the Free * Software Foundation; either version 2 of the License, or (at your option) * any later version. * */ #ifndef _CRYPTO_KPP_ #define _CRYPTO_KPP_ #include <linux/crypto.h> /** * struct kpp_request * * @base: Common attributes for async crypto requests * @src: Source data * @dst: Destination data * @src_len: Size of the input buffer * @dst_len: Size of the output buffer. It needs to be at least * as big as the expected result depending on the operation * After operation it will be updated with the actual size of the * result. In case of error where the dst sgl size was insufficient, * it will be updated to the size required for the operation. * @__ctx: Start of private context data */ struct kpp_request { struct crypto_async_request base; struct scatterlist *src; struct scatterlist *dst; unsigned int src_len; unsigned int dst_len; void *__ctx[] CRYPTO_MINALIGN_ATTR; }; /** * struct crypto_kpp - user-instantiated object which encapsulate * algorithms and core processing logic * * @base: Common crypto API algorithm data structure */ struct crypto_kpp { struct crypto_tfm base; }; /** * struct kpp_alg - generic key-agreement protocol primitives * * @set_secret: Function invokes the protocol specific function to * store the secret private key along with parameters. * The implementation knows how to decode the buffer * @generate_public_key: Function generate the public key to be sent to the * counterpart. In case of error, where output is not big * enough req->dst_len will be updated to the size * required * @compute_shared_secret: Function compute the shared secret as defined by * the algorithm. The result is given back to the user. * In case of error, where output is not big enough, * req->dst_len will be updated to the size required * @max_size: Function returns the size of the output buffer * @init: Initialize the object. This is called only once at * instantiation time. In case the cryptographic hardware * needs to be initialized. Software fallback should be * put in place here. * @exit: Undo everything @init did. * * @reqsize: Request context size required by algorithm * implementation * @base: Common crypto API algorithm data structure */ struct kpp_alg { int (*set_secret)(struct crypto_kpp *tfm, const void *buffer, unsigned int len); int (*generate_public_key)(struct kpp_request *req); int (*compute_shared_secret)(struct kpp_request *req); unsigned int (*max_size)(struct crypto_kpp *tfm); int (*init)(struct crypto_kpp *tfm); void (*exit)(struct crypto_kpp *tfm); unsigned int reqsize; struct crypto_alg base; }; /** * DOC: Generic Key-agreement Protocol Primitives API * * The KPP API is used with the algorithm type * CRYPTO_ALG_TYPE_KPP (listed as type "kpp" in /proc/crypto) */ /** * crypto_alloc_kpp() - allocate KPP tfm handle * @alg_name: is the name of the kpp algorithm (e.g. "dh", "ecdh") * @type: specifies the type of the algorithm * @mask: specifies the mask for the algorithm * * Allocate a handle for kpp algorithm. The returned struct crypto_kpp * is required for any following API invocation * * Return: allocated handle in case of success; IS_ERR() is true in case of * an error, PTR_ERR() returns the error code. */ struct crypto_kpp *crypto_alloc_kpp(const char *alg_name, u32 type, u32 mask); static inline struct crypto_tfm *crypto_kpp_tfm(struct crypto_kpp *tfm) { return &tfm->base; } static inline struct kpp_alg *__crypto_kpp_alg(struct crypto_alg *alg) { return container_of(alg, struct kpp_alg, base); } static inline struct crypto_kpp *__crypto_kpp_tfm(struct crypto_tfm *tfm) { return container_of(tfm, struct crypto_kpp, base); } static inline struct kpp_alg *crypto_kpp_alg(struct crypto_kpp *tfm) { return __crypto_kpp_alg(crypto_kpp_tfm(tfm)->__crt_alg); } static inline unsigned int crypto_kpp_reqsize(struct crypto_kpp *tfm) { return crypto_kpp_alg(tfm)->reqsize; } static inline void kpp_request_set_tfm(struct kpp_request *req, struct crypto_kpp *tfm) { req->base.tfm = crypto_kpp_tfm(tfm); } static inline struct crypto_kpp *crypto_kpp_reqtfm(struct kpp_request *req) { return __crypto_kpp_tfm(req->base.tfm); } static inline u32 crypto_kpp_get_flags(struct crypto_kpp *tfm) { return crypto_tfm_get_flags(crypto_kpp_tfm(tfm)); } static inline void crypto_kpp_set_flags(struct crypto_kpp *tfm, u32 flags) { crypto_tfm_set_flags(crypto_kpp_tfm(tfm), flags); } /** * crypto_free_kpp() - free KPP tfm handle * * @tfm: KPP tfm handle allocated with crypto_alloc_kpp() * * If @tfm is a NULL or error pointer, this function does nothing. */ static inline void crypto_free_kpp(struct crypto_kpp *tfm) { crypto_destroy_tfm(tfm, crypto_kpp_tfm(tfm)); } /** * kpp_request_alloc() - allocates kpp request * * @tfm: KPP tfm handle allocated with crypto_alloc_kpp() * @gfp: allocation flags * * Return: allocated handle in case of success or NULL in case of an error. */ static inline struct kpp_request *kpp_request_alloc(struct crypto_kpp *tfm, gfp_t gfp) { struct kpp_request *req; req = kmalloc(sizeof(*req) + crypto_kpp_reqsize(tfm), gfp); if (likely(req)) kpp_request_set_tfm(req, tfm); return req; } /** * kpp_request_free() - zeroize and free kpp request * * @req: request to free */ static inline void kpp_request_free(struct kpp_request *req) { kzfree(req); } /** * kpp_request_set_callback() - Sets an asynchronous callback. * * Callback will be called when an asynchronous operation on a given * request is finished. * * @req: request that the callback will be set for * @flgs: specify for instance if the operation may backlog * @cmpl: callback which will be called * @data: private data used by the caller */ static inline void kpp_request_set_callback(struct kpp_request *req, u32 flgs, crypto_completion_t cmpl, void *data) { req->base.complete = cmpl; req->base.data = data; req->base.flags = flgs; } /** * kpp_request_set_input() - Sets input buffer * * Sets parameters required by generate_public_key * * @req: kpp request * @input: ptr to input scatter list * @input_len: size of the input scatter list */ static inline void kpp_request_set_input(struct kpp_request *req, struct scatterlist *input, unsigned int input_len) { req->src = input; req->src_len = input_len; } /** * kpp_request_set_output() - Sets output buffer * * Sets parameters required by kpp operation * * @req: kpp request * @output: ptr to output scatter list * @output_len: size of the output scatter list */ static inline void kpp_request_set_output(struct kpp_request *req, struct scatterlist *output, unsigned int output_len) { req->dst = output; req->dst_len = output_len; } enum { CRYPTO_KPP_SECRET_TYPE_UNKNOWN, CRYPTO_KPP_SECRET_TYPE_DH, CRYPTO_KPP_SECRET_TYPE_ECDH, }; /** * struct kpp_secret - small header for packing secret buffer * * @type: define type of secret. Each kpp type will define its own * @len: specify the len of the secret, include the header, that * follows the struct */ struct kpp_secret { unsigned short type; unsigned short len; }; /** * crypto_kpp_set_secret() - Invoke kpp operation * * Function invokes the specific kpp operation for a given alg. * * @tfm: tfm handle * @buffer: Buffer holding the packet representation of the private * key. The structure of the packet key depends on the particular * KPP implementation. Packing and unpacking helpers are provided * for ECDH and DH (see the respective header files for those * implementations). * @len: Length of the packet private key buffer. * * Return: zero on success; error code in case of error */ static inline int crypto_kpp_set_secret(struct crypto_kpp *tfm, const void *buffer, unsigned int len) { struct kpp_alg *alg = crypto_kpp_alg(tfm); return alg->set_secret(tfm, buffer, len); } /** * crypto_kpp_generate_public_key() - Invoke kpp operation * * Function invokes the specific kpp operation for generating the public part * for a given kpp algorithm. * * To generate a private key, the caller should use a random number generator. * The output of the requested length serves as the private key. * * @req: kpp key request * * Return: zero on success; error code in case of error */ static inline int crypto_kpp_generate_public_key(struct kpp_request *req) { struct crypto_kpp *tfm = crypto_kpp_reqtfm(req); struct kpp_alg *alg = crypto_kpp_alg(tfm); return alg->generate_public_key(req); } /** * crypto_kpp_compute_shared_secret() - Invoke kpp operation * * Function invokes the specific kpp operation for computing the shared secret * for a given kpp algorithm. * * @req: kpp key request * * Return: zero on success; error code in case of error */ static inline int crypto_kpp_compute_shared_secret(struct kpp_request *req) { struct crypto_kpp *tfm = crypto_kpp_reqtfm(req); struct kpp_alg *alg = crypto_kpp_alg(tfm); return alg->compute_shared_secret(req); } /** * crypto_kpp_maxsize() - Get len for output buffer * * Function returns the output buffer size required for a given key. * Function assumes that the key is already set in the transformation. If this * function is called without a setkey or with a failed setkey, you will end up * in a NULL dereference. * * @tfm: KPP tfm handle allocated with crypto_alloc_kpp() */ static inline unsigned int crypto_kpp_maxsize(struct crypto_kpp *tfm) { struct kpp_alg *alg = crypto_kpp_alg(tfm); return alg->max_size(tfm); } #endif |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NF_QUEUE_H #define _NF_QUEUE_H #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/jhash.h> /* Each queued (to userspace) skbuff has one of these. */ struct nf_queue_entry { struct list_head list; struct sk_buff *skb; unsigned int id; unsigned int hook_index; /* index in hook_entries->hook[] */ struct nf_hook_state state; u16 size; /* sizeof(entry) + saved route keys */ /* extra space to store route keys */ }; #define nf_queue_entry_reroute(x) ((void *)x + sizeof(struct nf_queue_entry)) /* Packet queuing */ struct nf_queue_handler { int (*outfn)(struct nf_queue_entry *entry, unsigned int queuenum); unsigned int (*nf_hook_drop)(struct net *net); }; void nf_register_queue_handler(struct net *net, const struct nf_queue_handler *qh); void nf_unregister_queue_handler(struct net *net); void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict); bool nf_queue_entry_get_refs(struct nf_queue_entry *entry); void nf_queue_entry_release_refs(struct nf_queue_entry *entry); static inline void init_hashrandom(u32 *jhash_initval) { while (*jhash_initval == 0) *jhash_initval = prandom_u32(); } static inline u32 hash_v4(const struct iphdr *iph, u32 initval) { /* packets in either direction go into same queue */ if ((__force u32)iph->saddr < (__force u32)iph->daddr) return jhash_3words((__force u32)iph->saddr, (__force u32)iph->daddr, iph->protocol, initval); return jhash_3words((__force u32)iph->daddr, (__force u32)iph->saddr, iph->protocol, initval); } static inline u32 hash_v6(const struct ipv6hdr *ip6h, u32 initval) { u32 a, b, c; if ((__force u32)ip6h->saddr.s6_addr32[3] < (__force u32)ip6h->daddr.s6_addr32[3]) { a = (__force u32) ip6h->saddr.s6_addr32[3]; b = (__force u32) ip6h->daddr.s6_addr32[3]; } else { b = (__force u32) ip6h->saddr.s6_addr32[3]; a = (__force u32) ip6h->daddr.s6_addr32[3]; } if ((__force u32)ip6h->saddr.s6_addr32[1] < (__force u32)ip6h->daddr.s6_addr32[1]) c = (__force u32) ip6h->saddr.s6_addr32[1]; else c = (__force u32) ip6h->daddr.s6_addr32[1]; return jhash_3words(a, b, c, initval); } static inline u32 hash_bridge(const struct sk_buff *skb, u32 initval) { struct ipv6hdr *ip6h, _ip6h; struct iphdr *iph, _iph; switch (eth_hdr(skb)->h_proto) { case htons(ETH_P_IP): iph = skb_header_pointer(skb, skb_network_offset(skb), sizeof(*iph), &_iph); if (iph) return hash_v4(iph, initval); break; case htons(ETH_P_IPV6): ip6h = skb_header_pointer(skb, skb_network_offset(skb), sizeof(*ip6h), &_ip6h); if (ip6h) return hash_v6(ip6h, initval); break; } return 0; } static inline u32 nfqueue_hash(const struct sk_buff *skb, u16 queue, u16 queues_total, u8 family, u32 initval) { switch (family) { case NFPROTO_IPV4: queue += reciprocal_scale(hash_v4(ip_hdr(skb), initval), queues_total); break; case NFPROTO_IPV6: queue += reciprocal_scale(hash_v6(ipv6_hdr(skb), initval), queues_total); break; case NFPROTO_BRIDGE: queue += reciprocal_scale(hash_bridge(skb, initval), queues_total); break; } return queue; } #endif /* _NF_QUEUE_H */ |
| 752 752 751 753 557 3416 739 739 3416 2100 2102 1814 1813 1813 1814 1808 1501 1813 3761 38 38 494 487 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 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 | /* * Copyright (C) 2008 IBM Corporation * * Authors: * Mimi Zohar <zohar@us.ibm.com> * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License as * published by the Free Software Foundation, version 2 of the * License. * * File: integrity_iint.c * - implements the integrity hooks: integrity_inode_alloc, * integrity_inode_free * - cache integrity information associated with an inode * using a rbtree tree. */ #include <linux/slab.h> #include <linux/module.h> #include <linux/spinlock.h> #include <linux/rbtree.h> #include <linux/file.h> #include <linux/uaccess.h> #include "integrity.h" static struct rb_root integrity_iint_tree = RB_ROOT; static DEFINE_RWLOCK(integrity_iint_lock); static struct kmem_cache *iint_cache __read_mostly; /* * __integrity_iint_find - return the iint associated with an inode */ static struct integrity_iint_cache *__integrity_iint_find(struct inode *inode) { struct integrity_iint_cache *iint; struct rb_node *n = integrity_iint_tree.rb_node; while (n) { iint = rb_entry(n, struct integrity_iint_cache, rb_node); if (inode < iint->inode) n = n->rb_left; else if (inode > iint->inode) n = n->rb_right; else break; } if (!n) return NULL; return iint; } /* * integrity_iint_find - return the iint associated with an inode */ struct integrity_iint_cache *integrity_iint_find(struct inode *inode) { struct integrity_iint_cache *iint; if (!IS_IMA(inode)) return NULL; read_lock(&integrity_iint_lock); iint = __integrity_iint_find(inode); read_unlock(&integrity_iint_lock); return iint; } static void iint_free(struct integrity_iint_cache *iint) { kfree(iint->ima_hash); iint->ima_hash = NULL; iint->version = 0; iint->flags = 0UL; iint->atomic_flags = 0UL; iint->ima_file_status = INTEGRITY_UNKNOWN; iint->ima_mmap_status = INTEGRITY_UNKNOWN; iint->ima_bprm_status = INTEGRITY_UNKNOWN; iint->ima_read_status = INTEGRITY_UNKNOWN; iint->evm_status = INTEGRITY_UNKNOWN; iint->measured_pcrs = 0; kmem_cache_free(iint_cache, iint); } /** * integrity_inode_get - find or allocate an iint associated with an inode * @inode: pointer to the inode * @return: allocated iint * * Caller must lock i_mutex */ struct integrity_iint_cache *integrity_inode_get(struct inode *inode) { struct rb_node **p; struct rb_node *node, *parent = NULL; struct integrity_iint_cache *iint, *test_iint; iint = integrity_iint_find(inode); if (iint) return iint; iint = kmem_cache_alloc(iint_cache, GFP_NOFS); if (!iint) return NULL; write_lock(&integrity_iint_lock); p = &integrity_iint_tree.rb_node; while (*p) { parent = *p; test_iint = rb_entry(parent, struct integrity_iint_cache, rb_node); if (inode < test_iint->inode) p = &(*p)->rb_left; else p = &(*p)->rb_right; } iint->inode = inode; node = &iint->rb_node; inode->i_flags |= S_IMA; rb_link_node(node, parent, p); rb_insert_color(node, &integrity_iint_tree); write_unlock(&integrity_iint_lock); return iint; } /** * integrity_inode_free - called on security_inode_free * @inode: pointer to the inode * * Free the integrity information(iint) associated with an inode. */ void integrity_inode_free(struct inode *inode) { struct integrity_iint_cache *iint; if (!IS_IMA(inode)) return; write_lock(&integrity_iint_lock); iint = __integrity_iint_find(inode); rb_erase(&iint->rb_node, &integrity_iint_tree); write_unlock(&integrity_iint_lock); iint_free(iint); } static void init_once(void *foo) { struct integrity_iint_cache *iint = foo; memset(iint, 0, sizeof(*iint)); iint->version = 0; iint->flags = 0UL; iint->atomic_flags = 0; iint->ima_file_status = INTEGRITY_UNKNOWN; iint->ima_mmap_status = INTEGRITY_UNKNOWN; iint->ima_bprm_status = INTEGRITY_UNKNOWN; iint->ima_read_status = INTEGRITY_UNKNOWN; iint->evm_status = INTEGRITY_UNKNOWN; iint->measured_pcrs = 0; mutex_init(&iint->mutex); } static int __init integrity_iintcache_init(void) { iint_cache = kmem_cache_create("iint_cache", sizeof(struct integrity_iint_cache), 0, SLAB_PANIC, init_once); return 0; } security_initcall(integrity_iintcache_init); /* * integrity_kernel_read - read data from the file * * This is a function for reading file content instead of kernel_read(). * It does not perform locking checks to ensure it cannot be blocked. * It does not perform security checks because it is irrelevant for IMA. * */ int integrity_kernel_read(struct file *file, loff_t offset, void *addr, unsigned long count) { mm_segment_t old_fs; char __user *buf = (char __user *)addr; ssize_t ret; if (!(file->f_mode & FMODE_READ)) return -EBADF; old_fs = get_fs(); set_fs(get_ds()); ret = __vfs_read(file, buf, count, &offset); set_fs(old_fs); return ret; } /* * integrity_read_file - read entire file content into the buffer * * This is function opens a file, allocates the buffer of required * size, read entire file content to the buffer and closes the file * * It is used only by init code. * */ int __init integrity_read_file(const char *path, char **data) { struct file *file; loff_t size; char *buf; int rc = -EINVAL; if (!path || !*path) return -EINVAL; file = filp_open(path, O_RDONLY, 0); if (IS_ERR(file)) { rc = PTR_ERR(file); pr_err("Unable to open file: %s (%d)", path, rc); return rc; } size = i_size_read(file_inode(file)); if (size <= 0) goto out; buf = kmalloc(size, GFP_KERNEL); if (!buf) { rc = -ENOMEM; goto out; } rc = integrity_kernel_read(file, 0, buf, size); if (rc == size) { *data = buf; } else { kfree(buf); if (rc >= 0) rc = -EIO; } out: fput(file); return rc; } /* * integrity_load_keys - load integrity keys hook * * Hooks is called from init/main.c:kernel_init_freeable() * when rootfs is ready */ void __init integrity_load_keys(void) { ima_load_x509(); evm_load_x509(); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 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 | /* * Copyright (c) 2000-2002,2005 Silicon Graphics, Inc. * All Rights Reserved. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License as * published by the Free Software Foundation. * * This program is distributed in the hope that it would be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License * along with this program; if not, write the Free Software Foundation, * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA */ #ifndef __XFS_TRANS_H__ #define __XFS_TRANS_H__ /* kernel only transaction subsystem defines */ struct xfs_buf; struct xfs_buftarg; struct xfs_efd_log_item; struct xfs_efi_log_item; struct xfs_inode; struct xfs_item_ops; struct xfs_log_iovec; struct xfs_log_item_desc; struct xfs_mount; struct xfs_trans; struct xfs_trans_res; struct xfs_dquot_acct; struct xfs_rud_log_item; struct xfs_rui_log_item; struct xfs_btree_cur; struct xfs_cui_log_item; struct xfs_cud_log_item; struct xfs_defer_ops; struct xfs_bui_log_item; struct xfs_bud_log_item; typedef struct xfs_log_item { struct list_head li_ail; /* AIL pointers */ xfs_lsn_t li_lsn; /* last on-disk lsn */ struct xfs_log_item_desc *li_desc; /* ptr to current desc*/ struct xfs_mount *li_mountp; /* ptr to fs mount */ struct xfs_ail *li_ailp; /* ptr to AIL */ uint li_type; /* item type */ uint li_flags; /* misc flags */ struct xfs_buf *li_buf; /* real buffer pointer */ struct xfs_log_item *li_bio_list; /* buffer item list */ void (*li_cb)(struct xfs_buf *, struct xfs_log_item *); /* buffer item iodone */ /* callback func */ const struct xfs_item_ops *li_ops; /* function list */ /* delayed logging */ struct list_head li_cil; /* CIL pointers */ struct xfs_log_vec *li_lv; /* active log vector */ struct xfs_log_vec *li_lv_shadow; /* standby vector */ xfs_lsn_t li_seq; /* CIL commit seq */ } xfs_log_item_t; #define XFS_LI_IN_AIL 0x1 #define XFS_LI_ABORTED 0x2 #define XFS_LI_FAILED 0x4 #define XFS_LI_FLAGS \ { XFS_LI_IN_AIL, "IN_AIL" }, \ { XFS_LI_ABORTED, "ABORTED" }, \ { XFS_LI_FAILED, "FAILED" } struct xfs_item_ops { void (*iop_size)(xfs_log_item_t *, int *, int *); void (*iop_format)(xfs_log_item_t *, struct xfs_log_vec *); void (*iop_pin)(xfs_log_item_t *); void (*iop_unpin)(xfs_log_item_t *, int remove); uint (*iop_push)(struct xfs_log_item *, struct list_head *); void (*iop_unlock)(xfs_log_item_t *); xfs_lsn_t (*iop_committed)(xfs_log_item_t *, xfs_lsn_t); void (*iop_committing)(xfs_log_item_t *, xfs_lsn_t); void (*iop_error)(xfs_log_item_t *, xfs_buf_t *); }; void xfs_log_item_init(struct xfs_mount *mp, struct xfs_log_item *item, int type, const struct xfs_item_ops *ops); /* * Return values for the iop_push() routines. */ #define XFS_ITEM_SUCCESS 0 #define XFS_ITEM_PINNED 1 #define XFS_ITEM_LOCKED 2 #define XFS_ITEM_FLUSHING 3 /* * This is the structure maintained for every active transaction. */ typedef struct xfs_trans { unsigned int t_magic; /* magic number */ unsigned int t_log_res; /* amt of log space resvd */ unsigned int t_log_count; /* count for perm log res */ unsigned int t_blk_res; /* # of blocks resvd */ unsigned int t_blk_res_used; /* # of resvd blocks used */ unsigned int t_rtx_res; /* # of rt extents resvd */ unsigned int t_rtx_res_used; /* # of resvd rt extents used */ struct xlog_ticket *t_ticket; /* log mgr ticket */ struct xfs_mount *t_mountp; /* ptr to fs mount struct */ struct xfs_dquot_acct *t_dqinfo; /* acctg info for dquots */ unsigned int t_flags; /* misc flags */ int64_t t_icount_delta; /* superblock icount change */ int64_t t_ifree_delta; /* superblock ifree change */ int64_t t_fdblocks_delta; /* superblock fdblocks chg */ int64_t t_res_fdblocks_delta; /* on-disk only chg */ int64_t t_frextents_delta;/* superblock freextents chg*/ int64_t t_res_frextents_delta; /* on-disk only chg */ #if defined(DEBUG) || defined(XFS_WARN) int64_t t_ag_freeblks_delta; /* debugging counter */ int64_t t_ag_flist_delta; /* debugging counter */ int64_t t_ag_btree_delta; /* debugging counter */ #endif int64_t t_dblocks_delta;/* superblock dblocks change */ int64_t t_agcount_delta;/* superblock agcount change */ int64_t t_imaxpct_delta;/* superblock imaxpct change */ int64_t t_rextsize_delta;/* superblock rextsize chg */ int64_t t_rbmblocks_delta;/* superblock rbmblocks chg */ int64_t t_rblocks_delta;/* superblock rblocks change */ int64_t t_rextents_delta;/* superblocks rextents chg */ int64_t t_rextslog_delta;/* superblocks rextslog chg */ struct list_head t_items; /* log item descriptors */ struct list_head t_busy; /* list of busy extents */ unsigned long t_pflags; /* saved process flags state */ } xfs_trans_t; /* * XFS transaction mechanism exported interfaces that are * actually macros. */ #define xfs_trans_set_sync(tp) ((tp)->t_flags |= XFS_TRANS_SYNC) #if defined(DEBUG) || defined(XFS_WARN) #define xfs_trans_agblocks_delta(tp, d) ((tp)->t_ag_freeblks_delta += (int64_t)d) #define xfs_trans_agflist_delta(tp, d) ((tp)->t_ag_flist_delta += (int64_t)d) #define xfs_trans_agbtree_delta(tp, d) ((tp)->t_ag_btree_delta += (int64_t)d) #else #define xfs_trans_agblocks_delta(tp, d) #define xfs_trans_agflist_delta(tp, d) #define xfs_trans_agbtree_delta(tp, d) #endif /* * XFS transaction mechanism exported interfaces. */ int xfs_trans_alloc(struct xfs_mount *mp, struct xfs_trans_res *resp, uint blocks, uint rtextents, uint flags, struct xfs_trans **tpp); int xfs_trans_alloc_empty(struct xfs_mount *mp, struct xfs_trans **tpp); void xfs_trans_mod_sb(xfs_trans_t *, uint, int64_t); struct xfs_buf *xfs_trans_get_buf_map(struct xfs_trans *tp, struct xfs_buftarg *target, struct xfs_buf_map *map, int nmaps, uint flags); static inline struct xfs_buf * xfs_trans_get_buf( struct xfs_trans *tp, struct xfs_buftarg *target, xfs_daddr_t blkno, int numblks, uint flags) { DEFINE_SINGLE_BUF_MAP(map, blkno, numblks); return xfs_trans_get_buf_map(tp, target, &map, 1, flags); } int xfs_trans_read_buf_map(struct xfs_mount *mp, struct xfs_trans *tp, struct xfs_buftarg *target, struct xfs_buf_map *map, int nmaps, xfs_buf_flags_t flags, struct xfs_buf **bpp, const struct xfs_buf_ops *ops); static inline int xfs_trans_read_buf( struct xfs_mount *mp, struct xfs_trans *tp, struct xfs_buftarg *target, xfs_daddr_t blkno, int numblks, xfs_buf_flags_t flags, struct xfs_buf **bpp, const struct xfs_buf_ops *ops) { DEFINE_SINGLE_BUF_MAP(map, blkno, numblks); return xfs_trans_read_buf_map(mp, tp, target, &map, 1, flags, bpp, ops); } struct xfs_buf *xfs_trans_getsb(xfs_trans_t *, struct xfs_mount *, int); void xfs_trans_brelse(xfs_trans_t *, struct xfs_buf *); void xfs_trans_bjoin(xfs_trans_t *, struct xfs_buf *); void xfs_trans_bhold(xfs_trans_t *, struct xfs_buf *); void xfs_trans_bhold_release(xfs_trans_t *, struct xfs_buf *); void xfs_trans_binval(xfs_trans_t *, struct xfs_buf *); void xfs_trans_inode_buf(xfs_trans_t *, struct xfs_buf *); void xfs_trans_stale_inode_buf(xfs_trans_t *, struct xfs_buf *); bool xfs_trans_ordered_buf(xfs_trans_t *, struct xfs_buf *); void xfs_trans_dquot_buf(xfs_trans_t *, struct xfs_buf *, uint); void xfs_trans_inode_alloc_buf(xfs_trans_t *, struct xfs_buf *); void xfs_trans_ichgtime(struct xfs_trans *, struct xfs_inode *, int); void xfs_trans_ijoin(struct xfs_trans *, struct xfs_inode *, uint); void xfs_trans_log_buf(struct xfs_trans *, struct xfs_buf *, uint, uint); void xfs_trans_dirty_buf(struct xfs_trans *, struct xfs_buf *); void xfs_trans_log_inode(xfs_trans_t *, struct xfs_inode *, uint); void xfs_extent_free_init_defer_op(void); struct xfs_efd_log_item *xfs_trans_get_efd(struct xfs_trans *, struct xfs_efi_log_item *, uint); int xfs_trans_free_extent(struct xfs_trans *, struct xfs_efd_log_item *, xfs_fsblock_t, xfs_extlen_t, struct xfs_owner_info *); int xfs_trans_commit(struct xfs_trans *); int xfs_trans_roll(struct xfs_trans **); int xfs_trans_roll_inode(struct xfs_trans **, struct xfs_inode *); void xfs_trans_cancel(xfs_trans_t *); int xfs_trans_ail_init(struct xfs_mount *); void xfs_trans_ail_destroy(struct xfs_mount *); void xfs_trans_buf_set_type(struct xfs_trans *, struct xfs_buf *, enum xfs_blft); void xfs_trans_buf_copy_type(struct xfs_buf *dst_bp, struct xfs_buf *src_bp); extern kmem_zone_t *xfs_trans_zone; extern kmem_zone_t *xfs_log_item_desc_zone; /* rmap updates */ enum xfs_rmap_intent_type; void xfs_rmap_update_init_defer_op(void); struct xfs_rud_log_item *xfs_trans_get_rud(struct xfs_trans *tp, struct xfs_rui_log_item *ruip); int xfs_trans_log_finish_rmap_update(struct xfs_trans *tp, struct xfs_rud_log_item *rudp, enum xfs_rmap_intent_type type, uint64_t owner, int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock, xfs_filblks_t blockcount, xfs_exntst_t state, struct xfs_btree_cur **pcur); /* refcount updates */ enum xfs_refcount_intent_type; void xfs_refcount_update_init_defer_op(void); struct xfs_cud_log_item *xfs_trans_get_cud(struct xfs_trans *tp, struct xfs_cui_log_item *cuip); int xfs_trans_log_finish_refcount_update(struct xfs_trans *tp, struct xfs_cud_log_item *cudp, struct xfs_defer_ops *dfops, enum xfs_refcount_intent_type type, xfs_fsblock_t startblock, xfs_extlen_t blockcount, xfs_fsblock_t *new_fsb, xfs_extlen_t *new_len, struct xfs_btree_cur **pcur); /* mapping updates */ enum xfs_bmap_intent_type; void xfs_bmap_update_init_defer_op(void); struct xfs_bud_log_item *xfs_trans_get_bud(struct xfs_trans *tp, struct xfs_bui_log_item *buip); int xfs_trans_log_finish_bmap_update(struct xfs_trans *tp, struct xfs_bud_log_item *rudp, struct xfs_defer_ops *dfops, enum xfs_bmap_intent_type type, struct xfs_inode *ip, int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock, xfs_filblks_t *blockcount, xfs_exntst_t state); #endif /* __XFS_TRANS_H__ */ |
| 13 9 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 | /* * X.25 Packet Layer release 002 * * This is ALPHA test software. This code may break your machine, * randomly fail to work with new releases, misbehave and/or generally * screw up. It might even work. * * This code REQUIRES 2.1.15 or higher * * This module: * This module is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. * * History * X.25 001 Jonathan Naylor Started coding. * X.25 002 Jonathan Naylor New timer architecture. * Centralised disconnection processing. */ #include <linux/errno.h> #include <linux/jiffies.h> #include <linux/timer.h> #include <net/sock.h> #include <net/tcp_states.h> #include <net/x25.h> static void x25_heartbeat_expiry(unsigned long); static void x25_timer_expiry(unsigned long); void x25_init_timers(struct sock *sk) { struct x25_sock *x25 = x25_sk(sk); setup_timer(&x25->timer, x25_timer_expiry, (unsigned long)sk); /* initialized by sock_init_data */ sk->sk_timer.data = (unsigned long)sk; sk->sk_timer.function = &x25_heartbeat_expiry; } void x25_start_heartbeat(struct sock *sk) { mod_timer(&sk->sk_timer, jiffies + 5 * HZ); } void x25_stop_heartbeat(struct sock *sk) { del_timer(&sk->sk_timer); } void x25_start_t2timer(struct sock *sk) { struct x25_sock *x25 = x25_sk(sk); mod_timer(&x25->timer, jiffies + x25->t2); } void x25_start_t21timer(struct sock *sk) { struct x25_sock *x25 = x25_sk(sk); mod_timer(&x25->timer, jiffies + x25->t21); } void x25_start_t22timer(struct sock *sk) { struct x25_sock *x25 = x25_sk(sk); mod_timer(&x25->timer, jiffies + x25->t22); } void x25_start_t23timer(struct sock *sk) { struct x25_sock *x25 = x25_sk(sk); mod_timer(&x25->timer, jiffies + x25->t23); } void x25_stop_timer(struct sock *sk) { del_timer(&x25_sk(sk)->timer); } unsigned long x25_display_timer(struct sock *sk) { struct x25_sock *x25 = x25_sk(sk); if (!timer_pending(&x25->timer)) return 0; return x25->timer.expires - jiffies; } static void x25_heartbeat_expiry(unsigned long param) { struct sock *sk = (struct sock *)param; bh_lock_sock(sk); if (sock_owned_by_user(sk)) /* can currently only occur in state 3 */ goto restart_heartbeat; switch (x25_sk(sk)->state) { case X25_STATE_0: /* * Magic here: If we listen() and a new link dies * before it is accepted() it isn't 'dead' so doesn't * get removed. */ if (sock_flag(sk, SOCK_DESTROY) || (sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_DEAD))) { bh_unlock_sock(sk); x25_destroy_socket_from_timer(sk); return; } break; case X25_STATE_3: /* * Check for the state of the receive buffer. */ x25_check_rbuf(sk); break; } restart_heartbeat: x25_start_heartbeat(sk); bh_unlock_sock(sk); } /* * Timer has expired, it may have been T2, T21, T22, or T23. We can tell * by the state machine state. */ static inline void x25_do_timer_expiry(struct sock * sk) { struct x25_sock *x25 = x25_sk(sk); switch (x25->state) { case X25_STATE_3: /* T2 */ if (x25->condition & X25_COND_ACK_PENDING) { x25->condition &= ~X25_COND_ACK_PENDING; x25_enquiry_response(sk); } break; case X25_STATE_1: /* T21 */ case X25_STATE_4: /* T22 */ x25_write_internal(sk, X25_CLEAR_REQUEST); x25->state = X25_STATE_2; x25_start_t23timer(sk); break; case X25_STATE_2: /* T23 */ x25_disconnect(sk, ETIMEDOUT, 0, 0); break; } } static void x25_timer_expiry(unsigned long param) { struct sock *sk = (struct sock *)param; bh_lock_sock(sk); if (sock_owned_by_user(sk)) { /* can currently only occur in state 3 */ if (x25_sk(sk)->state == X25_STATE_3) x25_start_t2timer(sk); } else x25_do_timer_expiry(sk); bh_unlock_sock(sk); } |
| 210 154 167 305 304 304 303 303 303 305 303 371 371 373 22 202 202 370 373 373 379 348 25 25 22 24 25 1 1 1 8 7 3 7 8 281 280 281 20 25 342 335 28 1 13 337 328 328 6 325 7 316 15 368 358 327 22 372 370 359 48 48 368 370 341 212 214 211 154 153 213 369 118 318 316 54 369 368 366 368 315 15 6 3 12 15 4 13 4 3 2 18 14 13 11 13 12 2 2 17 19 120 11 11 11 2 2 2 11 11 1 3 3 20 20 298 298 297 296 134 296 296 278 296 298 1 54 20 264 296 296 134 296 52 32 53 296 59 5 60 51 59 60 6 5 5 3 5 6 9 7 7 1 7 7 9 13 13 3 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* Keyring handling * * Copyright (C) 2004-2005, 2008, 2013 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ #include <linux/module.h> #include <linux/init.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/security.h> #include <linux/seq_file.h> #include <linux/err.h> #include <keys/keyring-type.h> #include <keys/user-type.h> #include <linux/assoc_array_priv.h> #include <linux/uaccess.h> #include "internal.h" /* * When plumbing the depths of the key tree, this sets a hard limit * set on how deep we're willing to go. */ #define KEYRING_SEARCH_MAX_DEPTH 6 /* * We keep all named keyrings in a hash to speed looking them up. */ #define KEYRING_NAME_HASH_SIZE (1 << 5) /* * We mark pointers we pass to the associative array with bit 1 set if * they're keyrings and clear otherwise. */ #define KEYRING_PTR_SUBTYPE 0x2UL static inline bool keyring_ptr_is_keyring(const struct assoc_array_ptr *x) { return (unsigned long)x & KEYRING_PTR_SUBTYPE; } static inline struct key *keyring_ptr_to_key(const struct assoc_array_ptr *x) { void *object = assoc_array_ptr_to_leaf(x); return (struct key *)((unsigned long)object & ~KEYRING_PTR_SUBTYPE); } static inline void *keyring_key_to_ptr(struct key *key) { if (key->type == &key_type_keyring) return (void *)((unsigned long)key | KEYRING_PTR_SUBTYPE); return key; } static struct list_head keyring_name_hash[KEYRING_NAME_HASH_SIZE]; static DEFINE_RWLOCK(keyring_name_lock); static inline unsigned keyring_hash(const char *desc) { unsigned bucket = 0; for (; *desc; desc++) bucket += (unsigned char)*desc; return bucket & (KEYRING_NAME_HASH_SIZE - 1); } /* * The keyring key type definition. Keyrings are simply keys of this type and * can be treated as ordinary keys in addition to having their own special * operations. */ static int keyring_preparse(struct key_preparsed_payload *prep); static void keyring_free_preparse(struct key_preparsed_payload *prep); static int keyring_instantiate(struct key *keyring, struct key_preparsed_payload *prep); static void keyring_revoke(struct key *keyring); static void keyring_destroy(struct key *keyring); static void keyring_describe(const struct key *keyring, struct seq_file *m); static long keyring_read(const struct key *keyring, char __user *buffer, size_t buflen); struct key_type key_type_keyring = { .name = "keyring", .def_datalen = 0, .preparse = keyring_preparse, .free_preparse = keyring_free_preparse, .instantiate = keyring_instantiate, .revoke = keyring_revoke, .destroy = keyring_destroy, .describe = keyring_describe, .read = keyring_read, }; EXPORT_SYMBOL(key_type_keyring); /* * Semaphore to serialise link/link calls to prevent two link calls in parallel * introducing a cycle. */ static DECLARE_RWSEM(keyring_serialise_link_sem); /* * Publish the name of a keyring so that it can be found by name (if it has * one). */ static void keyring_publish_name(struct key *keyring) { int bucket; if (keyring->description) { bucket = keyring_hash(keyring->description); write_lock(&keyring_name_lock); if (!keyring_name_hash[bucket].next) INIT_LIST_HEAD(&keyring_name_hash[bucket]); list_add_tail(&keyring->name_link, &keyring_name_hash[bucket]); write_unlock(&keyring_name_lock); } } /* * Preparse a keyring payload */ static int keyring_preparse(struct key_preparsed_payload *prep) { return prep->datalen != 0 ? -EINVAL : 0; } /* * Free a preparse of a user defined key payload */ static void keyring_free_preparse(struct key_preparsed_payload *prep) { } /* * Initialise a keyring. * * Returns 0 on success, -EINVAL if given any data. */ static int keyring_instantiate(struct key *keyring, struct key_preparsed_payload *prep) { assoc_array_init(&keyring->keys); /* make the keyring available by name if it has one */ keyring_publish_name(keyring); return 0; } /* * Multiply 64-bits by 32-bits to 96-bits and fold back to 64-bit. Ideally we'd * fold the carry back too, but that requires inline asm. */ static u64 mult_64x32_and_fold(u64 x, u32 y) { u64 hi = (u64)(u32)(x >> 32) * y; u64 lo = (u64)(u32)(x) * y; return lo + ((u64)(u32)hi << 32) + (u32)(hi >> 32); } /* * Hash a key type and description. */ static unsigned long hash_key_type_and_desc(const struct keyring_index_key *index_key) { const unsigned level_shift = ASSOC_ARRAY_LEVEL_STEP; const unsigned long fan_mask = ASSOC_ARRAY_FAN_MASK; const char *description = index_key->description; unsigned long hash, type; u32 piece; u64 acc; int n, desc_len = index_key->desc_len; type = (unsigned long)index_key->type; acc = mult_64x32_and_fold(type, desc_len + 13); acc = mult_64x32_and_fold(acc, 9207); for (;;) { n = desc_len; if (n <= 0) break; if (n > 4) n = 4; piece = 0; memcpy(&piece, description, n); description += n; desc_len -= n; acc = mult_64x32_and_fold(acc, piece); acc = mult_64x32_and_fold(acc, 9207); } /* Fold the hash down to 32 bits if need be. */ hash = acc; if (ASSOC_ARRAY_KEY_CHUNK_SIZE == 32) hash ^= acc >> 32; /* Squidge all the keyrings into a separate part of the tree to * ordinary keys by making sure the lowest level segment in the hash is * zero for keyrings and non-zero otherwise. */ if (index_key->type != &key_type_keyring && (hash & fan_mask) == 0) return hash | (hash >> (ASSOC_ARRAY_KEY_CHUNK_SIZE - level_shift)) | 1; if (index_key->type == &key_type_keyring && (hash & fan_mask) != 0) return (hash + (hash << level_shift)) & ~fan_mask; return hash; } /* * Build the next index key chunk. * * On 32-bit systems the index key is laid out as: * * 0 4 5 9... * hash desclen typeptr desc[] * * On 64-bit systems: * * 0 8 9 17... * hash desclen typeptr desc[] * * We return it one word-sized chunk at a time. */ static unsigned long keyring_get_key_chunk(const void *data, int level) { const struct keyring_index_key *index_key = data; unsigned long chunk = 0; long offset = 0; int desc_len = index_key->desc_len, n = sizeof(chunk); level /= ASSOC_ARRAY_KEY_CHUNK_SIZE; switch (level) { case 0: return hash_key_type_and_desc(index_key); case 1: return ((unsigned long)index_key->type << 8) | desc_len; case 2: if (desc_len == 0) return (u8)((unsigned long)index_key->type >> (ASSOC_ARRAY_KEY_CHUNK_SIZE - 8)); n--; offset = 1; default: offset += sizeof(chunk) - 1; offset += (level - 3) * sizeof(chunk); if (offset >= desc_len) return 0; desc_len -= offset; if (desc_len > n) desc_len = n; offset += desc_len; do { chunk <<= 8; chunk |= ((u8*)index_key->description)[--offset]; } while (--desc_len > 0); if (level == 2) { chunk <<= 8; chunk |= (u8)((unsigned long)index_key->type >> (ASSOC_ARRAY_KEY_CHUNK_SIZE - 8)); } return chunk; } } static unsigned long keyring_get_object_key_chunk(const void *object, int level) { const struct key *key = keyring_ptr_to_key(object); return keyring_get_key_chunk(&key->index_key, level); } static bool keyring_compare_object(const void *object, const void *data) { const struct keyring_index_key *index_key = data; const struct key *key = keyring_ptr_to_key(object); return key->index_key.type == index_key->type && key->index_key.desc_len == index_key->desc_len && memcmp(key->index_key.description, index_key->description, index_key->desc_len) == 0; } /* * Compare the index keys of a pair of objects and determine the bit position * at which they differ - if they differ. */ static int keyring_diff_objects(const void *object, const void *data) { const struct key *key_a = keyring_ptr_to_key(object); const struct keyring_index_key *a = &key_a->index_key; const struct keyring_index_key *b = data; unsigned long seg_a, seg_b; int level, i; level = 0; seg_a = hash_key_type_and_desc(a); seg_b = hash_key_type_and_desc(b); if ((seg_a ^ seg_b) != 0) goto differ; /* The number of bits contributed by the hash is controlled by a * constant in the assoc_array headers. Everything else thereafter we * can deal with as being machine word-size dependent. */ level += ASSOC_ARRAY_KEY_CHUNK_SIZE / 8; seg_a = a->desc_len; seg_b = b->desc_len; if ((seg_a ^ seg_b) != 0) goto differ; /* The next bit may not work on big endian */ level++; seg_a = (unsigned long)a->type; seg_b = (unsigned long)b->type; if ((seg_a ^ seg_b) != 0) goto differ; level += sizeof(unsigned long); if (a->desc_len == 0) goto same; i = 0; if (((unsigned long)a->description | (unsigned long)b->description) & (sizeof(unsigned long) - 1)) { do { seg_a = *(unsigned long *)(a->description + i); seg_b = *(unsigned long *)(b->description + i); if ((seg_a ^ seg_b) != 0) goto differ_plus_i; i += sizeof(unsigned long); } while (i < (a->desc_len & (sizeof(unsigned long) - 1))); } for (; i < a->desc_len; i++) { seg_a = *(unsigned char *)(a->description + i); seg_b = *(unsigned char *)(b->description + i); if ((seg_a ^ seg_b) != 0) goto differ_plus_i; } same: return -1; differ_plus_i: level += i; differ: i = level * 8 + __ffs(seg_a ^ seg_b); return i; } /* * Free an object after stripping the keyring flag off of the pointer. */ static void keyring_free_object(void *object) { key_put(keyring_ptr_to_key(object)); } /* * Operations for keyring management by the index-tree routines. */ static const struct assoc_array_ops keyring_assoc_array_ops = { .get_key_chunk = keyring_get_key_chunk, .get_object_key_chunk = keyring_get_object_key_chunk, .compare_object = keyring_compare_object, .diff_objects = keyring_diff_objects, .free_object = keyring_free_object, }; /* * Clean up a keyring when it is destroyed. Unpublish its name if it had one * and dispose of its data. * * The garbage collector detects the final key_put(), removes the keyring from * the serial number tree and then does RCU synchronisation before coming here, * so we shouldn't need to worry about code poking around here with the RCU * readlock held by this time. */ static void keyring_destroy(struct key *keyring) { if (keyring->description) { write_lock(&keyring_name_lock); if (keyring->name_link.next != NULL && !list_empty(&keyring->name_link)) list_del(&keyring->name_link); write_unlock(&keyring_name_lock); } if (keyring->restrict_link) { struct key_restriction *keyres = keyring->restrict_link; key_put(keyres->key); kfree(keyres); } assoc_array_destroy(&keyring->keys, &keyring_assoc_array_ops); } /* * Describe a keyring for /proc. */ static void keyring_describe(const struct key *keyring, struct seq_file *m) { if (keyring->description) seq_puts(m, keyring->description); else seq_puts(m, "[anon]"); if (key_is_positive(keyring)) { if (keyring->keys.nr_leaves_on_tree != 0) seq_printf(m, ": %lu", keyring->keys.nr_leaves_on_tree); else seq_puts(m, ": empty"); } } struct keyring_read_iterator_context { size_t buflen; size_t count; key_serial_t __user *buffer; }; static int keyring_read_iterator(const void *object, void *data) { struct keyring_read_iterator_context *ctx = data; const struct key *key = keyring_ptr_to_key(object); kenter("{%s,%d},,{%zu/%zu}", key->type->name, key->serial, ctx->count, ctx->buflen); if (ctx->count >= ctx->buflen) return 1; *ctx->buffer++ = key->serial; ctx->count += sizeof(key->serial); return 0; } /* * Read a list of key IDs from the keyring's contents in binary form * * The keyring's semaphore is read-locked by the caller. This prevents someone * from modifying it under us - which could cause us to read key IDs multiple * times. */ static long keyring_read(const struct key *keyring, char __user *buffer, size_t buflen) { struct keyring_read_iterator_context ctx; long ret; kenter("{%d},,%zu", key_serial(keyring), buflen); if (buflen & (sizeof(key_serial_t) - 1)) return -EINVAL; /* Copy as many key IDs as fit into the buffer */ if (buffer && buflen) { ctx.buffer = (key_serial_t __user *)buffer; ctx.buflen = buflen; ctx.count = 0; ret = assoc_array_iterate(&keyring->keys, keyring_read_iterator, &ctx); if (ret < 0) { kleave(" = %ld [iterate]", ret); return ret; } } /* Return the size of the buffer needed */ ret = keyring->keys.nr_leaves_on_tree * sizeof(key_serial_t); if (ret <= buflen) kleave("= %ld [ok]", ret); else kleave("= %ld [buffer too small]", ret); return ret; } /* * Allocate a keyring and link into the destination keyring. */ struct key *keyring_alloc(const char *description, kuid_t uid, kgid_t gid, const struct cred *cred, key_perm_t perm, unsigned long flags, struct key_restriction *restrict_link, struct key *dest) { struct key *keyring; int ret; keyring = key_alloc(&key_type_keyring, description, uid, gid, cred, perm, flags, restrict_link); if (!IS_ERR(keyring)) { ret = key_instantiate_and_link(keyring, NULL, 0, dest, NULL); if (ret < 0) { key_put(keyring); keyring = ERR_PTR(ret); } } return keyring; } EXPORT_SYMBOL(keyring_alloc); /** * restrict_link_reject - Give -EPERM to restrict link * @keyring: The keyring being added to. * @type: The type of key being added. * @payload: The payload of the key intended to be added. * @data: Additional data for evaluating restriction. * * Reject the addition of any links to a keyring. It can be overridden by * passing KEY_ALLOC_BYPASS_RESTRICTION to key_instantiate_and_link() when * adding a key to a keyring. * * This is meant to be stored in a key_restriction structure which is passed * in the restrict_link parameter to keyring_alloc(). */ int restrict_link_reject(struct key *keyring, const struct key_type *type, const union key_payload *payload, struct key *restriction_key) { return -EPERM; } /* * By default, we keys found by getting an exact match on their descriptions. */ bool key_default_cmp(const struct key *key, const struct key_match_data *match_data) { return strcmp(key->description, match_data->raw_data) == 0; } /* * Iteration function to consider each key found. */ static int keyring_search_iterator(const void *object, void *iterator_data) { struct keyring_search_context *ctx = iterator_data; const struct key *key = keyring_ptr_to_key(object); unsigned long kflags = READ_ONCE(key->flags); short state = READ_ONCE(key->state); kenter("{%d}", key->serial); /* ignore keys not of this type */ if (key->type != ctx->index_key.type) { kleave(" = 0 [!type]"); return 0; } /* skip invalidated, revoked and expired keys */ if (ctx->flags & KEYRING_SEARCH_DO_STATE_CHECK) { time_t expiry = READ_ONCE(key->expiry); if (kflags & ((1 << KEY_FLAG_INVALIDATED) | (1 << KEY_FLAG_REVOKED))) { ctx->result = ERR_PTR(-EKEYREVOKED); kleave(" = %d [invrev]", ctx->skipped_ret); goto skipped; } if (expiry && ctx->now.tv_sec >= expiry) { if (!(ctx->flags & KEYRING_SEARCH_SKIP_EXPIRED)) ctx->result = ERR_PTR(-EKEYEXPIRED); kleave(" = %d [expire]", ctx->skipped_ret); goto skipped; } } /* keys that don't match */ if (!ctx->match_data.cmp(key, &ctx->match_data)) { kleave(" = 0 [!match]"); return 0; } /* key must have search permissions */ if (!(ctx->flags & KEYRING_SEARCH_NO_CHECK_PERM) && key_task_permission(make_key_ref(key, ctx->possessed), ctx->cred, KEY_NEED_SEARCH) < 0) { ctx->result = ERR_PTR(-EACCES); kleave(" = %d [!perm]", ctx->skipped_ret); goto skipped; } if (ctx->flags & KEYRING_SEARCH_DO_STATE_CHECK) { /* we set a different error code if we pass a negative key */ if (state < 0) { ctx->result = ERR_PTR(state); kleave(" = %d [neg]", ctx->skipped_ret); goto skipped; } } /* Found */ ctx->result = make_key_ref(key, ctx->possessed); kleave(" = 1 [found]"); return 1; skipped: return ctx->skipped_ret; } /* * Search inside a keyring for a key. We can search by walking to it * directly based on its index-key or we can iterate over the entire * tree looking for it, based on the match function. */ static int search_keyring(struct key *keyring, struct keyring_search_context *ctx) { if (ctx->match_data.lookup_type == KEYRING_SEARCH_LOOKUP_DIRECT) { const void *object; object = assoc_array_find(&keyring->keys, &keyring_assoc_array_ops, &ctx->index_key); return object ? ctx->iterator(object, ctx) : 0; } return assoc_array_iterate(&keyring->keys, ctx->iterator, ctx); } /* * Search a tree of keyrings that point to other keyrings up to the maximum * depth. */ static bool search_nested_keyrings(struct key *keyring, struct keyring_search_context *ctx) { struct { struct key *keyring; struct assoc_array_node *node; int slot; } stack[KEYRING_SEARCH_MAX_DEPTH]; struct assoc_array_shortcut *shortcut; struct assoc_array_node *node; struct assoc_array_ptr *ptr; struct key *key; int sp = 0, slot; kenter("{%d},{%s,%s}", keyring->serial, ctx->index_key.type->name, ctx->index_key.description); #define STATE_CHECKS (KEYRING_SEARCH_NO_STATE_CHECK | KEYRING_SEARCH_DO_STATE_CHECK) BUG_ON((ctx->flags & STATE_CHECKS) == 0 || (ctx->flags & STATE_CHECKS) == STATE_CHECKS); /* Check to see if this top-level keyring is what we are looking for * and whether it is valid or not. */ if (ctx->match_data.lookup_type == KEYRING_SEARCH_LOOKUP_ITERATE || keyring_compare_object(keyring, &ctx->index_key)) { ctx->skipped_ret = 2; switch (ctx->iterator(keyring_key_to_ptr(keyring), ctx)) { case 1: goto found; case 2: return false; default: break; } } ctx->skipped_ret = 0; /* Start processing a new keyring */ descend_to_keyring: kdebug("descend to %d", keyring->serial); if (keyring->flags & ((1 << KEY_FLAG_INVALIDATED) | (1 << KEY_FLAG_REVOKED))) goto not_this_keyring; /* Search through the keys in this keyring before its searching its * subtrees. */ if (search_keyring(keyring, ctx)) goto found; /* Then manually iterate through the keyrings nested in this one. * * Start from the root node of the index tree. Because of the way the * hash function has been set up, keyrings cluster on the leftmost * branch of the root node (root slot 0) or in the root node itself. * Non-keyrings avoid the leftmost branch of the root entirely (root * slots 1-15). */ ptr = READ_ONCE(keyring->keys.root); if (!ptr) goto not_this_keyring; if (assoc_array_ptr_is_shortcut(ptr)) { /* If the root is a shortcut, either the keyring only contains * keyring pointers (everything clusters behind root slot 0) or * doesn't contain any keyring pointers. */ shortcut = assoc_array_ptr_to_shortcut(ptr); smp_read_barrier_depends(); if ((shortcut->index_key[0] & ASSOC_ARRAY_FAN_MASK) != 0) goto not_this_keyring; ptr = READ_ONCE(shortcut->next_node); node = assoc_array_ptr_to_node(ptr); goto begin_node; } node = assoc_array_ptr_to_node(ptr); smp_read_barrier_depends(); ptr = node->slots[0]; if (!assoc_array_ptr_is_meta(ptr)) goto begin_node; descend_to_node: /* Descend to a more distal node in this keyring's content tree and go * through that. */ kdebug("descend"); if (assoc_array_ptr_is_shortcut(ptr)) { shortcut = assoc_array_ptr_to_shortcut(ptr); smp_read_barrier_depends(); ptr = READ_ONCE(shortcut->next_node); BUG_ON(!assoc_array_ptr_is_node(ptr)); } node = assoc_array_ptr_to_node(ptr); begin_node: kdebug("begin_node"); smp_read_barrier_depends(); slot = 0; ascend_to_node: /* Go through the slots in a node */ for (; slot < ASSOC_ARRAY_FAN_OUT; slot++) { ptr = READ_ONCE(node->slots[slot]); if (assoc_array_ptr_is_meta(ptr) && node->back_pointer) goto descend_to_node; if (!keyring_ptr_is_keyring(ptr)) continue; key = keyring_ptr_to_key(ptr); if (sp >= KEYRING_SEARCH_MAX_DEPTH) { if (ctx->flags & KEYRING_SEARCH_DETECT_TOO_DEEP) { ctx->result = ERR_PTR(-ELOOP); return false; } goto not_this_keyring; } /* Search a nested keyring */ if (!(ctx->flags & KEYRING_SEARCH_NO_CHECK_PERM) && key_task_permission(make_key_ref(key, ctx->possessed), ctx->cred, KEY_NEED_SEARCH) < 0) continue; /* stack the current position */ stack[sp].keyring = keyring; stack[sp].node = node; stack[sp].slot = slot; sp++; /* begin again with the new keyring */ keyring = key; goto descend_to_keyring; } /* We've dealt with all the slots in the current node, so now we need * to ascend to the parent and continue processing there. */ ptr = READ_ONCE(node->back_pointer); slot = node->parent_slot; if (ptr && assoc_array_ptr_is_shortcut(ptr)) { shortcut = assoc_array_ptr_to_shortcut(ptr); smp_read_barrier_depends(); ptr = READ_ONCE(shortcut->back_pointer); slot = shortcut->parent_slot; } if (!ptr) goto not_this_keyring; node = assoc_array_ptr_to_node(ptr); smp_read_barrier_depends(); slot++; /* If we've ascended to the root (zero backpointer), we must have just * finished processing the leftmost branch rather than the root slots - * so there can't be any more keyrings for us to find. */ if (node->back_pointer) { kdebug("ascend %d", slot); goto ascend_to_node; } /* The keyring we're looking at was disqualified or didn't contain a * matching key. */ not_this_keyring: kdebug("not_this_keyring %d", sp); if (sp <= 0) { kleave(" = false"); return false; } /* Resume the processing of a keyring higher up in the tree */ sp--; keyring = stack[sp].keyring; node = stack[sp].node; slot = stack[sp].slot + 1; kdebug("ascend to %d [%d]", keyring->serial, slot); goto ascend_to_node; /* We found a viable match */ found: key = key_ref_to_ptr(ctx->result); key_check(key); if (!(ctx->flags & KEYRING_SEARCH_NO_UPDATE_TIME)) { key->last_used_at = ctx->now.tv_sec; keyring->last_used_at = ctx->now.tv_sec; while (sp > 0) stack[--sp].keyring->last_used_at = ctx->now.tv_sec; } kleave(" = true"); return true; } /** * keyring_search_aux - Search a keyring tree for a key matching some criteria * @keyring_ref: A pointer to the keyring with possession indicator. * @ctx: The keyring search context. * * Search the supplied keyring tree for a key that matches the criteria given. * The root keyring and any linked keyrings must grant Search permission to the * caller to be searchable and keys can only be found if they too grant Search * to the caller. The possession flag on the root keyring pointer controls use * of the possessor bits in permissions checking of the entire tree. In * addition, the LSM gets to forbid keyring searches and key matches. * * The search is performed as a breadth-then-depth search up to the prescribed * limit (KEYRING_SEARCH_MAX_DEPTH). * * Keys are matched to the type provided and are then filtered by the match * function, which is given the description to use in any way it sees fit. The * match function may use any attributes of a key that it wishes to to * determine the match. Normally the match function from the key type would be * used. * * RCU can be used to prevent the keyring key lists from disappearing without * the need to take lots of locks. * * Returns a pointer to the found key and increments the key usage count if * successful; -EAGAIN if no matching keys were found, or if expired or revoked * keys were found; -ENOKEY if only negative keys were found; -ENOTDIR if the * specified keyring wasn't a keyring. * * In the case of a successful return, the possession attribute from * @keyring_ref is propagated to the returned key reference. */ key_ref_t keyring_search_aux(key_ref_t keyring_ref, struct keyring_search_context *ctx) { struct key *keyring; long err; ctx->iterator = keyring_search_iterator; ctx->possessed = is_key_possessed(keyring_ref); ctx->result = ERR_PTR(-EAGAIN); keyring = key_ref_to_ptr(keyring_ref); key_check(keyring); if (keyring->type != &key_type_keyring) return ERR_PTR(-ENOTDIR); if (!(ctx->flags & KEYRING_SEARCH_NO_CHECK_PERM)) { err = key_task_permission(keyring_ref, ctx->cred, KEY_NEED_SEARCH); if (err < 0) return ERR_PTR(err); } rcu_read_lock(); ctx->now = current_kernel_time(); if (search_nested_keyrings(keyring, ctx)) __key_get(key_ref_to_ptr(ctx->result)); rcu_read_unlock(); return ctx->result; } /** * keyring_search - Search the supplied keyring tree for a matching key * @keyring: The root of the keyring tree to be searched. * @type: The type of keyring we want to find. * @description: The name of the keyring we want to find. * * As keyring_search_aux() above, but using the current task's credentials and * type's default matching function and preferred search method. */ key_ref_t keyring_search(key_ref_t keyring, struct key_type *type, const char *description) { struct keyring_search_context ctx = { .index_key.type = type, .index_key.description = description, .index_key.desc_len = strlen(description), .cred = current_cred(), .match_data.cmp = key_default_cmp, .match_data.raw_data = description, .match_data.lookup_type = KEYRING_SEARCH_LOOKUP_DIRECT, .flags = KEYRING_SEARCH_DO_STATE_CHECK, }; key_ref_t key; int ret; if (type->match_preparse) { ret = type->match_preparse(&ctx.match_data); if (ret < 0) return ERR_PTR(ret); } key = keyring_search_aux(keyring, &ctx); if (type->match_free) type->match_free(&ctx.match_data); return key; } EXPORT_SYMBOL(keyring_search); static struct key_restriction *keyring_restriction_alloc( key_restrict_link_func_t check) { struct key_restriction *keyres = kzalloc(sizeof(struct key_restriction), GFP_KERNEL); if (!keyres) return ERR_PTR(-ENOMEM); keyres->check = check; return keyres; } /* * Semaphore to serialise restriction setup to prevent reference count * cycles through restriction key pointers. */ static DECLARE_RWSEM(keyring_serialise_restrict_sem); /* * Check for restriction cycles that would prevent keyring garbage collection. * keyring_serialise_restrict_sem must be held. */ static bool keyring_detect_restriction_cycle(const struct key *dest_keyring, struct key_restriction *keyres) { while (keyres && keyres->key && keyres->key->type == &key_type_keyring) { if (keyres->key == dest_keyring) return true; keyres = keyres->key->restrict_link; } return false; } /** * keyring_restrict - Look up and apply a restriction to a keyring * * @keyring: The keyring to be restricted * @restriction: The restriction options to apply to the keyring */ int keyring_restrict(key_ref_t keyring_ref, const char *type, const char *restriction) { struct key *keyring; struct key_type *restrict_type = NULL; struct key_restriction *restrict_link; int ret = 0; keyring = key_ref_to_ptr(keyring_ref); key_check(keyring); if (keyring->type != &key_type_keyring) return -ENOTDIR; if (!type) { restrict_link = keyring_restriction_alloc(restrict_link_reject); } else { restrict_type = key_type_lookup(type); if (IS_ERR(restrict_type)) return PTR_ERR(restrict_type); if (!restrict_type->lookup_restriction) { ret = -ENOENT; goto error; } restrict_link = restrict_type->lookup_restriction(restriction); } if (IS_ERR(restrict_link)) { ret = PTR_ERR(restrict_link); goto error; } down_write(&keyring->sem); down_write(&keyring_serialise_restrict_sem); if (keyring->restrict_link) ret = -EEXIST; else if (keyring_detect_restriction_cycle(keyring, restrict_link)) ret = -EDEADLK; else keyring->restrict_link = restrict_link; up_write(&keyring_serialise_restrict_sem); up_write(&keyring->sem); if (ret < 0) { key_put(restrict_link->key); kfree(restrict_link); } error: if (restrict_type) key_type_put(restrict_type); return ret; } EXPORT_SYMBOL(keyring_restrict); /* * Search the given keyring for a key that might be updated. * * The caller must guarantee that the keyring is a keyring and that the * permission is granted to modify the keyring as no check is made here. The * caller must also hold a lock on the keyring semaphore. * * Returns a pointer to the found key with usage count incremented if * successful and returns NULL if not found. Revoked and invalidated keys are * skipped over. * * If successful, the possession indicator is propagated from the keyring ref * to the returned key reference. */ key_ref_t find_key_to_update(key_ref_t keyring_ref, const struct keyring_index_key *index_key) { struct key *keyring, *key; const void *object; keyring = key_ref_to_ptr(keyring_ref); kenter("{%d},{%s,%s}", keyring->serial, index_key->type->name, index_key->description); object = assoc_array_find(&keyring->keys, &keyring_assoc_array_ops, index_key); if (object) goto found; kleave(" = NULL"); return NULL; found: key = keyring_ptr_to_key(object); if (key->flags & ((1 << KEY_FLAG_INVALIDATED) | (1 << KEY_FLAG_REVOKED))) { kleave(" = NULL [x]"); return NULL; } __key_get(key); kleave(" = {%d}", key->serial); return make_key_ref(key, is_key_possessed(keyring_ref)); } /* * Find a keyring with the specified name. * * Only keyrings that have nonzero refcount, are not revoked, and are owned by a * user in the current user namespace are considered. If @uid_keyring is %true, * the keyring additionally must have been allocated as a user or user session * keyring; otherwise, it must grant Search permission directly to the caller. * * Returns a pointer to the keyring with the keyring's refcount having being * incremented on success. -ENOKEY is returned if a key could not be found. */ struct key *find_keyring_by_name(const char *name, bool uid_keyring) { struct key *keyring; int bucket; if (!name) return ERR_PTR(-EINVAL); bucket = keyring_hash(name); read_lock(&keyring_name_lock); if (keyring_name_hash[bucket].next) { /* search this hash bucket for a keyring with a matching name * that's readable and that hasn't been revoked */ list_for_each_entry(keyring, &keyring_name_hash[bucket], name_link ) { if (!kuid_has_mapping(current_user_ns(), keyring->user->uid)) continue; if (test_bit(KEY_FLAG_REVOKED, &keyring->flags)) continue; if (strcmp(keyring->description, name) != 0) continue; if (uid_keyring) { if (!test_bit(KEY_FLAG_UID_KEYRING, &keyring->flags)) continue; } else { if (key_permission(make_key_ref(keyring, 0), KEY_NEED_SEARCH) < 0) continue; } /* we've got a match but we might end up racing with * key_cleanup() if the keyring is currently 'dead' * (ie. it has a zero usage count) */ if (!refcount_inc_not_zero(&keyring->usage)) continue; keyring->last_used_at = current_kernel_time().tv_sec; goto out; } } keyring = ERR_PTR(-ENOKEY); out: read_unlock(&keyring_name_lock); return keyring; } static int keyring_detect_cycle_iterator(const void *object, void *iterator_data) { struct keyring_search_context *ctx = iterator_data; const struct key *key = keyring_ptr_to_key(object); kenter("{%d}", key->serial); /* We might get a keyring with matching index-key that is nonetheless a * different keyring. */ if (key != ctx->match_data.raw_data) return 0; ctx->result = ERR_PTR(-EDEADLK); return 1; } /* * See if a cycle will will be created by inserting acyclic tree B in acyclic * tree A at the topmost level (ie: as a direct child of A). * * Since we are adding B to A at the top level, checking for cycles should just * be a matter of seeing if node A is somewhere in tree B. */ static int keyring_detect_cycle(struct key *A, struct key *B) { struct keyring_search_context ctx = { .index_key = A->index_key, .match_data.raw_data = A, .match_data.lookup_type = KEYRING_SEARCH_LOOKUP_DIRECT, .iterator = keyring_detect_cycle_iterator, .flags = (KEYRING_SEARCH_NO_STATE_CHECK | KEYRING_SEARCH_NO_UPDATE_TIME | KEYRING_SEARCH_NO_CHECK_PERM | KEYRING_SEARCH_DETECT_TOO_DEEP), }; rcu_read_lock(); search_nested_keyrings(B, &ctx); rcu_read_unlock(); return PTR_ERR(ctx.result) == -EAGAIN ? 0 : PTR_ERR(ctx.result); } /* * Preallocate memory so that a key can be linked into to a keyring. */ int __key_link_begin(struct key *keyring, const struct keyring_index_key *index_key, struct assoc_array_edit **_edit) __acquires(&keyring->sem) __acquires(&keyring_serialise_link_sem) { struct assoc_array_edit *edit; int ret; kenter("%d,%s,%s,", keyring->serial, index_key->type->name, index_key->description); BUG_ON(index_key->desc_len == 0); if (keyring->type != &key_type_keyring) return -ENOTDIR; down_write(&keyring->sem); ret = -EKEYREVOKED; if (test_bit(KEY_FLAG_REVOKED, &keyring->flags)) goto error_krsem; /* serialise link/link calls to prevent parallel calls causing a cycle * when linking two keyring in opposite orders */ if (index_key->type == &key_type_keyring) down_write(&keyring_serialise_link_sem); /* Create an edit script that will insert/replace the key in the * keyring tree. */ edit = assoc_array_insert(&keyring->keys, &keyring_assoc_array_ops, index_key, NULL); if (IS_ERR(edit)) { ret = PTR_ERR(edit); goto error_sem; } /* If we're not replacing a link in-place then we're going to need some * extra quota. */ if (!edit->dead_leaf) { ret = key_payload_reserve(keyring, keyring->datalen + KEYQUOTA_LINK_BYTES); if (ret < 0) goto error_cancel; } *_edit = edit; kleave(" = 0"); return 0; error_cancel: assoc_array_cancel_edit(edit); error_sem: if (index_key->type == &key_type_keyring) up_write(&keyring_serialise_link_sem); error_krsem: up_write(&keyring->sem); kleave(" = %d", ret); return ret; } /* * Check already instantiated keys aren't going to be a problem. * * The caller must have called __key_link_begin(). Don't need to call this for * keys that were created since __key_link_begin() was called. */ int __key_link_check_live_key(struct key *keyring, struct key *key) { if (key->type == &key_type_keyring) /* check that we aren't going to create a cycle by linking one * keyring to another */ return keyring_detect_cycle(keyring, key); return 0; } /* * Link a key into to a keyring. * * Must be called with __key_link_begin() having being called. Discards any * already extant link to matching key if there is one, so that each keyring * holds at most one link to any given key of a particular type+description * combination. */ void __key_link(struct key *key, struct assoc_array_edit **_edit) { __key_get(key); assoc_array_insert_set_object(*_edit, keyring_key_to_ptr(key)); assoc_array_apply_edit(*_edit); *_edit = NULL; } /* * Finish linking a key into to a keyring. * * Must be called with __key_link_begin() having being called. */ void __key_link_end(struct key *keyring, const struct keyring_index_key *index_key, struct assoc_array_edit *edit) __releases(&keyring->sem) __releases(&keyring_serialise_link_sem) { BUG_ON(index_key->type == NULL); kenter("%d,%s,", keyring->serial, index_key->type->name); if (index_key->type == &key_type_keyring) up_write(&keyring_serialise_link_sem); if (edit) { if (!edit->dead_leaf) { key_payload_reserve(keyring, keyring->datalen - KEYQUOTA_LINK_BYTES); } assoc_array_cancel_edit(edit); } up_write(&keyring->sem); } /* * Check addition of keys to restricted keyrings. */ static int __key_link_check_restriction(struct key *keyring, struct key *key) { if (!keyring->restrict_link || !keyring->restrict_link->check) return 0; return keyring->restrict_link->check(keyring, key->type, &key->payload, keyring->restrict_link->key); } /** * key_link - Link a key to a keyring * @keyring: The keyring to make the link in. * @key: The key to link to. * * Make a link in a keyring to a key, such that the keyring holds a reference * on that key and the key can potentially be found by searching that keyring. * * This function will write-lock the keyring's semaphore and will consume some * of the user's key data quota to hold the link. * * Returns 0 if successful, -ENOTDIR if the keyring isn't a keyring, * -EKEYREVOKED if the keyring has been revoked, -ENFILE if the keyring is * full, -EDQUOT if there is insufficient key data quota remaining to add * another link or -ENOMEM if there's insufficient memory. * * It is assumed that the caller has checked that it is permitted for a link to * be made (the keyring should have Write permission and the key Link * permission). */ int key_link(struct key *keyring, struct key *key) { struct assoc_array_edit *edit; int ret; kenter("{%d,%d}", keyring->serial, refcount_read(&keyring->usage)); key_check(keyring); key_check(key); ret = __key_link_begin(keyring, &key->index_key, &edit); if (ret == 0) { kdebug("begun {%d,%d}", keyring->serial, refcount_read(&keyring->usage)); ret = __key_link_check_restriction(keyring, key); if (ret == 0) ret = __key_link_check_live_key(keyring, key); if (ret == 0) __key_link(key, &edit); __key_link_end(keyring, &key->index_key, edit); } kleave(" = %d {%d,%d}", ret, keyring->serial, refcount_read(&keyring->usage)); return ret; } EXPORT_SYMBOL(key_link); /** * key_unlink - Unlink the first link to a key from a keyring. * @keyring: The keyring to remove the link from. * @key: The key the link is to. * * Remove a link from a keyring to a key. * * This function will write-lock the keyring's semaphore. * * Returns 0 if successful, -ENOTDIR if the keyring isn't a keyring, -ENOENT if * the key isn't linked to by the keyring or -ENOMEM if there's insufficient * memory. * * It is assumed that the caller has checked that it is permitted for a link to * be removed (the keyring should have Write permission; no permissions are * required on the key). */ int key_unlink(struct key *keyring, struct key *key) { struct assoc_array_edit *edit; int ret; key_check(keyring); key_check(key); if (keyring->type != &key_type_keyring) return -ENOTDIR; down_write(&keyring->sem); edit = assoc_array_delete(&keyring->keys, &keyring_assoc_array_ops, &key->index_key); if (IS_ERR(edit)) { ret = PTR_ERR(edit); goto error; } ret = -ENOENT; if (edit == NULL) goto error; assoc_array_apply_edit(edit); key_payload_reserve(keyring, keyring->datalen - KEYQUOTA_LINK_BYTES); ret = 0; error: up_write(&keyring->sem); return ret; } EXPORT_SYMBOL(key_unlink); /** * keyring_clear - Clear a keyring * @keyring: The keyring to clear. * * Clear the contents of the specified keyring. * * Returns 0 if successful or -ENOTDIR if the keyring isn't a keyring. */ int keyring_clear(struct key *keyring) { struct assoc_array_edit *edit; int ret; if (keyring->type != &key_type_keyring) return -ENOTDIR; down_write(&keyring->sem); edit = assoc_array_clear(&keyring->keys, &keyring_assoc_array_ops); if (IS_ERR(edit)) { ret = PTR_ERR(edit); } else { if (edit) assoc_array_apply_edit(edit); key_payload_reserve(keyring, 0); ret = 0; } up_write(&keyring->sem); return ret; } EXPORT_SYMBOL(keyring_clear); /* * Dispose of the links from a revoked keyring. * * This is called with the key sem write-locked. */ static void keyring_revoke(struct key *keyring) { struct assoc_array_edit *edit; edit = assoc_array_clear(&keyring->keys, &keyring_assoc_array_ops); if (!IS_ERR(edit)) { if (edit) assoc_array_apply_edit(edit); key_payload_reserve(keyring, 0); } } static bool keyring_gc_select_iterator(void *object, void *iterator_data) { struct key *key = keyring_ptr_to_key(object); time_t *limit = iterator_data; if (key_is_dead(key, *limit)) return false; key_get(key); return true; } static int keyring_gc_check_iterator(const void *object, void *iterator_data) { const struct key *key = keyring_ptr_to_key(object); time_t *limit = iterator_data; key_check(key); return key_is_dead(key, *limit); } /* * Garbage collect pointers from a keyring. * * Not called with any locks held. The keyring's key struct will not be * deallocated under us as only our caller may deallocate it. */ void keyring_gc(struct key *keyring, time_t limit) { int result; kenter("%x{%s}", keyring->serial, keyring->description ?: ""); if (keyring->flags & ((1 << KEY_FLAG_INVALIDATED) | (1 << KEY_FLAG_REVOKED))) goto dont_gc; /* scan the keyring looking for dead keys */ rcu_read_lock(); result = assoc_array_iterate(&keyring->keys, keyring_gc_check_iterator, &limit); rcu_read_unlock(); if (result == true) goto do_gc; dont_gc: kleave(" [no gc]"); return; do_gc: down_write(&keyring->sem); assoc_array_gc(&keyring->keys, &keyring_assoc_array_ops, keyring_gc_select_iterator, &limit); up_write(&keyring->sem); kleave(" [gc]"); } /* * Garbage collect restriction pointers from a keyring. * * Keyring restrictions are associated with a key type, and must be cleaned * up if the key type is unregistered. The restriction is altered to always * reject additional keys so a keyring cannot be opened up by unregistering * a key type. * * Not called with any keyring locks held. The keyring's key struct will not * be deallocated under us as only our caller may deallocate it. * * The caller is required to hold key_types_sem and dead_type->sem. This is * fulfilled by key_gc_keytype() holding the locks on behalf of * key_garbage_collector(), which it invokes on a workqueue. */ void keyring_restriction_gc(struct key *keyring, struct key_type *dead_type) { struct key_restriction *keyres; kenter("%x{%s}", keyring->serial, keyring->description ?: ""); /* * keyring->restrict_link is only assigned at key allocation time * or with the key type locked, so the only values that could be * concurrently assigned to keyring->restrict_link are for key * types other than dead_type. Given this, it's ok to check * the key type before acquiring keyring->sem. */ if (!dead_type || !keyring->restrict_link || keyring->restrict_link->keytype != dead_type) { kleave(" [no restriction gc]"); return; } /* Lock the keyring to ensure that a link is not in progress */ down_write(&keyring->sem); keyres = keyring->restrict_link; keyres->check = restrict_link_reject; key_put(keyres->key); keyres->key = NULL; keyres->keytype = NULL; up_write(&keyring->sem); kleave(" [restriction gc]"); } |
| 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 | /** * udc.c - Core UDC Framework * * Copyright (C) 2010 Texas Instruments * Author: Felipe Balbi <balbi@ti.com> * * This program is free software: you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 of * the License as published by the Free Software Foundation. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License * along with this program. If not, see <http://www.gnu.org/licenses/>. */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/device.h> #include <linux/list.h> #include <linux/err.h> #include <linux/dma-mapping.h> #include <linux/sched/task_stack.h> #include <linux/workqueue.h> #include <linux/usb/ch9.h> #include <linux/usb/gadget.h> #include <linux/usb.h> #include "trace.h" /** * struct usb_udc - describes one usb device controller * @driver - the gadget driver pointer. For use by the class code * @dev - the child device to the actual controller * @gadget - the gadget. For use by the class code * @list - for use by the udc class driver * @vbus - for udcs who care about vbus status, this value is real vbus status; * for udcs who do not care about vbus status, this value is always true * * This represents the internal data structure which is used by the UDC-class * to hold information about udc driver and gadget together. */ struct usb_udc { struct usb_gadget_driver *driver; struct usb_gadget *gadget; struct device dev; struct list_head list; bool vbus; }; static struct class *udc_class; static LIST_HEAD(udc_list); static LIST_HEAD(gadget_driver_pending_list); static DEFINE_MUTEX(udc_lock); static int udc_bind_to_driver(struct usb_udc *udc, struct usb_gadget_driver *driver); /* ------------------------------------------------------------------------- */ /** * usb_ep_set_maxpacket_limit - set maximum packet size limit for endpoint * @ep:the endpoint being configured * @maxpacket_limit:value of maximum packet size limit * * This function should be used only in UDC drivers to initialize endpoint * (usually in probe function). */ void usb_ep_set_maxpacket_limit(struct usb_ep *ep, unsigned maxpacket_limit) { ep->maxpacket_limit = maxpacket_limit; ep->maxpacket = maxpacket_limit; trace_usb_ep_set_maxpacket_limit(ep, 0); } EXPORT_SYMBOL_GPL(usb_ep_set_maxpacket_limit); /** * usb_ep_enable - configure endpoint, making it usable * @ep:the endpoint being configured. may not be the endpoint named "ep0". * drivers discover endpoints through the ep_list of a usb_gadget. * * When configurations are set, or when interface settings change, the driver * will enable or disable the relevant endpoints. while it is enabled, an * endpoint may be used for i/o until the driver receives a disconnect() from * the host or until the endpoint is disabled. * * the ep0 implementation (which calls this routine) must ensure that the * hardware capabilities of each endpoint match the descriptor provided * for it. for example, an endpoint named "ep2in-bulk" would be usable * for interrupt transfers as well as bulk, but it likely couldn't be used * for iso transfers or for endpoint 14. some endpoints are fully * configurable, with more generic names like "ep-a". (remember that for * USB, "in" means "towards the USB master".) * * returns zero, or a negative error code. */ int usb_ep_enable(struct usb_ep *ep) { int ret = 0; if (ep->enabled) goto out; /* UDC drivers can't handle endpoints with maxpacket size 0 */ if (usb_endpoint_maxp(ep->desc) == 0) { /* * We should log an error message here, but we can't call * dev_err() because there's no way to find the gadget * given only ep. */ ret = -EINVAL; goto out; } ret = ep->ops->enable(ep, ep->desc); if (ret) goto out; ep->enabled = true; out: trace_usb_ep_enable(ep, ret); return ret; } EXPORT_SYMBOL_GPL(usb_ep_enable); /** * usb_ep_disable - endpoint is no longer usable * @ep:the endpoint being unconfigured. may not be the endpoint named "ep0". * * no other task may be using this endpoint when this is called. * any pending and uncompleted requests will complete with status * indicating disconnect (-ESHUTDOWN) before this call returns. * gadget drivers must call usb_ep_enable() again before queueing * requests to the endpoint. * * returns zero, or a negative error code. */ int usb_ep_disable(struct usb_ep *ep) { int ret = 0; if (!ep->enabled) goto out; ret = ep->ops->disable(ep); if (ret) goto out; ep->enabled = false; out: trace_usb_ep_disable(ep, ret); return ret; } EXPORT_SYMBOL_GPL(usb_ep_disable); /** * usb_ep_alloc_request - allocate a request object to use with this endpoint * @ep:the endpoint to be used with with the request * @gfp_flags:GFP_* flags to use * * Request objects must be allocated with this call, since they normally * need controller-specific setup and may even need endpoint-specific * resources such as allocation of DMA descriptors. * Requests may be submitted with usb_ep_queue(), and receive a single * completion callback. Free requests with usb_ep_free_request(), when * they are no longer needed. * * Returns the request, or null if one could not be allocated. */ struct usb_request *usb_ep_alloc_request(struct usb_ep *ep, gfp_t gfp_flags) { struct usb_request *req = NULL; req = ep->ops->alloc_request(ep, gfp_flags); trace_usb_ep_alloc_request(ep, req, req ? 0 : -ENOMEM); return req; } EXPORT_SYMBOL_GPL(usb_ep_alloc_request); /** * usb_ep_free_request - frees a request object * @ep:the endpoint associated with the request * @req:the request being freed * * Reverses the effect of usb_ep_alloc_request(). * Caller guarantees the request is not queued, and that it will * no longer be requeued (or otherwise used). */ void usb_ep_free_request(struct usb_ep *ep, struct usb_request *req) { trace_usb_ep_free_request(ep, req, 0); ep->ops->free_request(ep, req); } EXPORT_SYMBOL_GPL(usb_ep_free_request); /** * usb_ep_queue - queues (submits) an I/O request to an endpoint. * @ep:the endpoint associated with the request * @req:the request being submitted * @gfp_flags: GFP_* flags to use in case the lower level driver couldn't * pre-allocate all necessary memory with the request. * * This tells the device controller to perform the specified request through * that endpoint (reading or writing a buffer). When the request completes, * including being canceled by usb_ep_dequeue(), the request's completion * routine is called to return the request to the driver. Any endpoint * (except control endpoints like ep0) may have more than one transfer * request queued; they complete in FIFO order. Once a gadget driver * submits a request, that request may not be examined or modified until it * is given back to that driver through the completion callback. * * Each request is turned into one or more packets. The controller driver * never merges adjacent requests into the same packet. OUT transfers * will sometimes use data that's already buffered in the hardware. * Drivers can rely on the fact that the first byte of the request's buffer * always corresponds to the first byte of some USB packet, for both * IN and OUT transfers. * * Bulk endpoints can queue any amount of data; the transfer is packetized * automatically. The last packet will be short if the request doesn't fill it * out completely. Zero length packets (ZLPs) should be avoided in portable * protocols since not all usb hardware can successfully handle zero length * packets. (ZLPs may be explicitly written, and may be implicitly written if * the request 'zero' flag is set.) Bulk endpoints may also be used * for interrupt transfers; but the reverse is not true, and some endpoints * won't support every interrupt transfer. (Such as 768 byte packets.) * * Interrupt-only endpoints are less functional than bulk endpoints, for * example by not supporting queueing or not handling buffers that are * larger than the endpoint's maxpacket size. They may also treat data * toggle differently. * * Control endpoints ... after getting a setup() callback, the driver queues * one response (even if it would be zero length). That enables the * status ack, after transferring data as specified in the response. Setup * functions may return negative error codes to generate protocol stalls. * (Note that some USB device controllers disallow protocol stall responses * in some cases.) When control responses are deferred (the response is * written after the setup callback returns), then usb_ep_set_halt() may be * used on ep0 to trigger protocol stalls. Depending on the controller, * it may not be possible to trigger a status-stage protocol stall when the * data stage is over, that is, from within the response's completion * routine. * * For periodic endpoints, like interrupt or isochronous ones, the usb host * arranges to poll once per interval, and the gadget driver usually will * have queued some data to transfer at that time. * * Note that @req's ->complete() callback must never be called from * within usb_ep_queue() as that can create deadlock situations. * * Returns zero, or a negative error code. Endpoints that are not enabled * report errors; errors will also be * reported when the usb peripheral is disconnected. */ int usb_ep_queue(struct usb_ep *ep, struct usb_request *req, gfp_t gfp_flags) { int ret = 0; if (WARN_ON_ONCE(!ep->enabled && ep->address)) { ret = -ESHUTDOWN; goto out; } ret = ep->ops->queue(ep, req, gfp_flags); out: trace_usb_ep_queue(ep, req, ret); return ret; } EXPORT_SYMBOL_GPL(usb_ep_queue); /** * usb_ep_dequeue - dequeues (cancels, unlinks) an I/O request from an endpoint * @ep:the endpoint associated with the request * @req:the request being canceled * * If the request is still active on the endpoint, it is dequeued and its * completion routine is called (with status -ECONNRESET); else a negative * error code is returned. This is guaranteed to happen before the call to * usb_ep_dequeue() returns. * * Note that some hardware can't clear out write fifos (to unlink the request * at the head of the queue) except as part of disconnecting from usb. Such * restrictions prevent drivers from supporting configuration changes, * even to configuration zero (a "chapter 9" requirement). */ int usb_ep_dequeue(struct usb_ep *ep, struct usb_request *req) { int ret; ret = ep->ops->dequeue(ep, req); trace_usb_ep_dequeue(ep, req, ret); return ret; } EXPORT_SYMBOL_GPL(usb_ep_dequeue); /** * usb_ep_set_halt - sets the endpoint halt feature. * @ep: the non-isochronous endpoint being stalled * * Use this to stall an endpoint, perhaps as an error report. * Except for control endpoints, * the endpoint stays halted (will not stream any data) until the host * clears this feature; drivers may need to empty the endpoint's request * queue first, to make sure no inappropriate transfers happen. * * Note that while an endpoint CLEAR_FEATURE will be invisible to the * gadget driver, a SET_INTERFACE will not be. To reset endpoints for the * current altsetting, see usb_ep_clear_halt(). When switching altsettings, * it's simplest to use usb_ep_enable() or usb_ep_disable() for the endpoints. * * Returns zero, or a negative error code. On success, this call sets * underlying hardware state that blocks data transfers. * Attempts to halt IN endpoints will fail (returning -EAGAIN) if any * transfer requests are still queued, or if the controller hardware * (usually a FIFO) still holds bytes that the host hasn't collected. */ int usb_ep_set_halt(struct usb_ep *ep) { int ret; ret = ep->ops->set_halt(ep, 1); trace_usb_ep_set_halt(ep, ret); return ret; } EXPORT_SYMBOL_GPL(usb_ep_set_halt); /** * usb_ep_clear_halt - clears endpoint halt, and resets toggle * @ep:the bulk or interrupt endpoint being reset * * Use this when responding to the standard usb "set interface" request, * for endpoints that aren't reconfigured, after clearing any other state * in the endpoint's i/o queue. * * Returns zero, or a negative error code. On success, this call clears * the underlying hardware state reflecting endpoint halt and data toggle. * Note that some hardware can't support this request (like pxa2xx_udc), * and accordingly can't correctly implement interface altsettings. */ int usb_ep_clear_halt(struct usb_ep *ep) { int ret; ret = ep->ops->set_halt(ep, 0); trace_usb_ep_clear_halt(ep, ret); return ret; } EXPORT_SYMBOL_GPL(usb_ep_clear_halt); /** * usb_ep_set_wedge - sets the halt feature and ignores clear requests * @ep: the endpoint being wedged * * Use this to stall an endpoint and ignore CLEAR_FEATURE(HALT_ENDPOINT) * requests. If the gadget driver clears the halt status, it will * automatically unwedge the endpoint. * * Returns zero on success, else negative errno. */ int usb_ep_set_wedge(struct usb_ep *ep) { int ret; if (ep->ops->set_wedge) ret = ep->ops->set_wedge(ep); else ret = ep->ops->set_halt(ep, 1); trace_usb_ep_set_wedge(ep, ret); return ret; } EXPORT_SYMBOL_GPL(usb_ep_set_wedge); /** * usb_ep_fifo_status - returns number of bytes in fifo, or error * @ep: the endpoint whose fifo status is being checked. * * FIFO endpoints may have "unclaimed data" in them in certain cases, * such as after aborted transfers. Hosts may not have collected all * the IN data written by the gadget driver (and reported by a request * completion). The gadget driver may not have collected all the data * written OUT to it by the host. Drivers that need precise handling for * fault reporting or recovery may need to use this call. * * This returns the number of such bytes in the fifo, or a negative * errno if the endpoint doesn't use a FIFO or doesn't support such * precise handling. */ int usb_ep_fifo_status(struct usb_ep *ep) { int ret; if (ep->ops->fifo_status) ret = ep->ops->fifo_status(ep); else ret = -EOPNOTSUPP; trace_usb_ep_fifo_status(ep, ret); return ret; } EXPORT_SYMBOL_GPL(usb_ep_fifo_status); /** * usb_ep_fifo_flush - flushes contents of a fifo * @ep: the endpoint whose fifo is being flushed. * * This call may be used to flush the "unclaimed data" that may exist in * an endpoint fifo after abnormal transaction terminations. The call * must never be used except when endpoint is not being used for any * protocol translation. */ void usb_ep_fifo_flush(struct usb_ep *ep) { if (ep->ops->fifo_flush) ep->ops->fifo_flush(ep); trace_usb_ep_fifo_flush(ep, 0); } EXPORT_SYMBOL_GPL(usb_ep_fifo_flush); /* ------------------------------------------------------------------------- */ /** * usb_gadget_frame_number - returns the current frame number * @gadget: controller that reports the frame number * * Returns the usb frame number, normally eleven bits from a SOF packet, * or negative errno if this device doesn't support this capability. */ int usb_gadget_frame_number(struct usb_gadget *gadget) { int ret; ret = gadget->ops->get_frame(gadget); trace_usb_gadget_frame_number(gadget, ret); return ret; } EXPORT_SYMBOL_GPL(usb_gadget_frame_number); /** * usb_gadget_wakeup - tries to wake up the host connected to this gadget * @gadget: controller used to wake up the host * * Returns zero on success, else negative error code if the hardware * doesn't support such attempts, or its support has not been enabled * by the usb host. Drivers must return device descriptors that report * their ability to support this, or hosts won't enable it. * * This may also try to use SRP to wake the host and start enumeration, * even if OTG isn't otherwise in use. OTG devices may also start * remote wakeup even when hosts don't explicitly enable it. */ int usb_gadget_wakeup(struct usb_gadget *gadget) { int ret = 0; if (!gadget->ops->wakeup) { ret = -EOPNOTSUPP; goto out; } ret = gadget->ops->wakeup(gadget); out: trace_usb_gadget_wakeup(gadget, ret); return ret; } EXPORT_SYMBOL_GPL(usb_gadget_wakeup); /** * usb_gadget_set_selfpowered - sets the device selfpowered feature. * @gadget:the device being declared as self-powered * * this affects the device status reported by the hardware driver * to reflect that it now has a local power supply. * * returns zero on success, else negative errno. */ int usb_gadget_set_selfpowered(struct usb_gadget *gadget) { int ret = 0; if (!gadget->ops->set_selfpowered) { ret = -EOPNOTSUPP; goto out; } ret = gadget->ops->set_selfpowered(gadget, 1); out: trace_usb_gadget_set_selfpowered(gadget, ret); return ret; } EXPORT_SYMBOL_GPL(usb_gadget_set_selfpowered); /** * usb_gadget_clear_selfpowered - clear the device selfpowered feature. * @gadget:the device being declared as bus-powered * * this affects the device status reported by the hardware driver. * some hardware may not support bus-powered operation, in which * case this feature's value can never change. * * returns zero on success, else negative errno. */ int usb_gadget_clear_selfpowered(struct usb_gadget *gadget) { int ret = 0; if (!gadget->ops->set_selfpowered) { ret = -EOPNOTSUPP; goto out; } ret = gadget->ops->set_selfpowered(gadget, 0); out: trace_usb_gadget_clear_selfpowered(gadget, ret); return ret; } EXPORT_SYMBOL_GPL(usb_gadget_clear_selfpowered); /** * usb_gadget_vbus_connect - Notify controller that VBUS is powered * @gadget:The device which now has VBUS power. * Context: can sleep * * This call is used by a driver for an external transceiver (or GPIO) * that detects a VBUS power session starting. Common responses include * resuming the controller, activating the D+ (or D-) pullup to let the * host detect that a USB device is attached, and starting to draw power * (8mA or possibly more, especially after SET_CONFIGURATION). * * Returns zero on success, else negative errno. */ int usb_gadget_vbus_connect(struct usb_gadget *gadget) { int ret = 0; if (!gadget->ops->vbus_session) { ret = -EOPNOTSUPP; goto out; } ret = gadget->ops->vbus_session(gadget, 1); out: trace_usb_gadget_vbus_connect(gadget, ret); return ret; } EXPORT_SYMBOL_GPL(usb_gadget_vbus_connect); /** * usb_gadget_vbus_draw - constrain controller's VBUS power usage * @gadget:The device whose VBUS usage is being described * @mA:How much current to draw, in milliAmperes. This should be twice * the value listed in the configuration descriptor bMaxPower field. * * This call is used by gadget drivers during SET_CONFIGURATION calls, * reporting how much power the device may consume. For example, this * could affect how quickly batteries are recharged. * * Returns zero on success, else negative errno. */ int usb_gadget_vbus_draw(struct usb_gadget *gadget, unsigned mA) { int ret = 0; if (!gadget->ops->vbus_draw) { ret = -EOPNOTSUPP; goto out; } ret = gadget->ops->vbus_draw(gadget, mA); if (!ret) gadget->mA = mA; out: trace_usb_gadget_vbus_draw(gadget, ret); return ret; } EXPORT_SYMBOL_GPL(usb_gadget_vbus_draw); /** * usb_gadget_vbus_disconnect - notify controller about VBUS session end * @gadget:the device whose VBUS supply is being described * Context: can sleep * * This call is used by a driver for an external transceiver (or GPIO) * that detects a VBUS power session ending. Common responses include * reversing everything done in usb_gadget_vbus_connect(). * * Returns zero on success, else negative errno. */ int usb_gadget_vbus_disconnect(struct usb_gadget *gadget) { int ret = 0; if (!gadget->ops->vbus_session) { ret = -EOPNOTSUPP; goto out; } ret = gadget->ops->vbus_session(gadget, 0); out: trace_usb_gadget_vbus_disconnect(gadget, ret); return ret; } EXPORT_SYMBOL_GPL(usb_gadget_vbus_disconnect); /** * usb_gadget_connect - software-controlled connect to USB host * @gadget:the peripheral being connected * * Enables the D+ (or potentially D-) pullup. The host will start * enumerating this gadget when the pullup is active and a VBUS session * is active (the link is powered). This pullup is always enabled unless * usb_gadget_disconnect() has been used to disable it. * * Returns zero on success, else negative errno. */ int usb_gadget_connect(struct usb_gadget *gadget) { int ret = 0; if (!gadget->ops->pullup) { ret = -EOPNOTSUPP; goto out; } if (gadget->deactivated) { /* * If gadget is deactivated we only save new state. * Gadget will be connected automatically after activation. */ gadget->connected = true; goto out; } ret = gadget->ops->pullup(gadget, 1); if (!ret) gadget->connected = 1; out: trace_usb_gadget_connect(gadget, ret); return ret; } EXPORT_SYMBOL_GPL(usb_gadget_connect); /** * usb_gadget_disconnect - software-controlled disconnect from USB host * @gadget:the peripheral being disconnected * * Disables the D+ (or potentially D-) pullup, which the host may see * as a disconnect (when a VBUS session is active). Not all systems * support software pullup controls. * * Returns zero on success, else negative errno. */ int usb_gadget_disconnect(struct usb_gadget *gadget) { int ret = 0; if (!gadget->ops->pullup) { ret = -EOPNOTSUPP; goto out; } if (gadget->deactivated) { /* * If gadget is deactivated we only save new state. * Gadget will stay disconnected after activation. */ gadget->connected = false; goto out; } ret = gadget->ops->pullup(gadget, 0); if (!ret) gadget->connected = 0; out: trace_usb_gadget_disconnect(gadget, ret); return ret; } EXPORT_SYMBOL_GPL(usb_gadget_disconnect); /** * usb_gadget_deactivate - deactivate function which is not ready to work * @gadget: the peripheral being deactivated * * This routine may be used during the gadget driver bind() call to prevent * the peripheral from ever being visible to the USB host, unless later * usb_gadget_activate() is called. For example, user mode components may * need to be activated before the system can talk to hosts. * * Returns zero on success, else negative errno. */ int usb_gadget_deactivate(struct usb_gadget *gadget) { int ret = 0; if (gadget->deactivated) goto out; if (gadget->connected) { ret = usb_gadget_disconnect(gadget); if (ret) goto out; /* * If gadget was being connected before deactivation, we want * to reconnect it in usb_gadget_activate(). */ gadget->connected = true; } gadget->deactivated = true; out: trace_usb_gadget_deactivate(gadget, ret); return ret; } EXPORT_SYMBOL_GPL(usb_gadget_deactivate); /** * usb_gadget_activate - activate function which is not ready to work * @gadget: the peripheral being activated * * This routine activates gadget which was previously deactivated with * usb_gadget_deactivate() call. It calls usb_gadget_connect() if needed. * * Returns zero on success, else negative errno. */ int usb_gadget_activate(struct usb_gadget *gadget) { int ret = 0; if (!gadget->deactivated) goto out; gadget->deactivated = false; /* * If gadget has been connected before deactivation, or became connected * while it was being deactivated, we call usb_gadget_connect(). */ if (gadget->connected) ret = usb_gadget_connect(gadget); out: trace_usb_gadget_activate(gadget, ret); return ret; } EXPORT_SYMBOL_GPL(usb_gadget_activate); /* ------------------------------------------------------------------------- */ #ifdef CONFIG_HAS_DMA int usb_gadget_map_request_by_dev(struct device *dev, struct usb_request *req, int is_in) { if (req->length == 0) return 0; if (req->num_sgs) { int mapped; mapped = dma_map_sg(dev, req->sg, req->num_sgs, is_in ? DMA_TO_DEVICE : DMA_FROM_DEVICE); if (mapped == 0) { dev_err(dev, "failed to map SGs\n"); return -EFAULT; } req->num_mapped_sgs = mapped; } else { if (is_vmalloc_addr(req->buf)) { dev_err(dev, "buffer is not dma capable\n"); return -EFAULT; } else if (object_is_on_stack(req->buf)) { dev_err(dev, "buffer is on stack\n"); return -EFAULT; } req->dma = dma_map_single(dev, req->buf, req->length, is_in ? DMA_TO_DEVICE : DMA_FROM_DEVICE); if (dma_mapping_error(dev, req->dma)) { dev_err(dev, "failed to map buffer\n"); return -EFAULT; } req->dma_mapped = 1; } return 0; } EXPORT_SYMBOL_GPL(usb_gadget_map_request_by_dev); int usb_gadget_map_request(struct usb_gadget *gadget, struct usb_request *req, int is_in) { return usb_gadget_map_request_by_dev(gadget->dev.parent, req, is_in); } EXPORT_SYMBOL_GPL(usb_gadget_map_request); void usb_gadget_unmap_request_by_dev(struct device *dev, struct usb_request *req, int is_in) { if (req->length == 0) return; if (req->num_mapped_sgs) { dma_unmap_sg(dev, req->sg, req->num_sgs, is_in ? DMA_TO_DEVICE : DMA_FROM_DEVICE); req->num_mapped_sgs = 0; } else if (req->dma_mapped) { dma_unmap_single(dev, req->dma, req->length, is_in ? DMA_TO_DEVICE : DMA_FROM_DEVICE); req->dma_mapped = 0; } } EXPORT_SYMBOL_GPL(usb_gadget_unmap_request_by_dev); void usb_gadget_unmap_request(struct usb_gadget *gadget, struct usb_request *req, int is_in) { usb_gadget_unmap_request_by_dev(gadget->dev.parent, req, is_in); } EXPORT_SYMBOL_GPL(usb_gadget_unmap_request); #endif /* CONFIG_HAS_DMA */ /* ------------------------------------------------------------------------- */ /** * usb_gadget_giveback_request - give the request back to the gadget layer * Context: in_interrupt() * * This is called by device controller drivers in order to return the * completed request back to the gadget layer. */ void usb_gadget_giveback_request(struct usb_ep *ep, struct usb_request *req) { if (likely(req->status == 0)) usb_led_activity(USB_LED_EVENT_GADGET); trace_usb_gadget_giveback_request(ep, req, 0); req->complete(ep, req); } EXPORT_SYMBOL_GPL(usb_gadget_giveback_request); /* ------------------------------------------------------------------------- */ /** * gadget_find_ep_by_name - returns ep whose name is the same as sting passed * in second parameter or NULL if searched endpoint not found * @g: controller to check for quirk * @name: name of searched endpoint */ struct usb_ep *gadget_find_ep_by_name(struct usb_gadget *g, const char *name) { struct usb_ep *ep; gadget_for_each_ep(ep, g) { if (!strcmp(ep->name, name)) return ep; } return NULL; } EXPORT_SYMBOL_GPL(gadget_find_ep_by_name); /* ------------------------------------------------------------------------- */ int usb_gadget_ep_match_desc(struct usb_gadget *gadget, struct usb_ep *ep, struct usb_endpoint_descriptor *desc, struct usb_ss_ep_comp_descriptor *ep_comp) { u8 type; u16 max; int num_req_streams = 0; /* endpoint already claimed? */ if (ep->claimed) return 0; type = usb_endpoint_type(desc); max = 0x7ff & usb_endpoint_maxp(desc); if (usb_endpoint_dir_in(desc) && !ep->caps.dir_in) return 0; if (usb_endpoint_dir_out(desc) && !ep->caps.dir_out) return 0; if (max > ep->maxpacket_limit) return 0; /* "high bandwidth" works only at high speed */ if (!gadget_is_dualspeed(gadget) && usb_endpoint_maxp_mult(desc) > 1) return 0; switch (type) { case USB_ENDPOINT_XFER_CONTROL: /* only support ep0 for portable CONTROL traffic */ return 0; case USB_ENDPOINT_XFER_ISOC: if (!ep->caps.type_iso) return 0; /* ISO: limit 1023 bytes full speed, 1024 high/super speed */ if (!gadget_is_dualspeed(gadget) && max > 1023) return 0; break; case USB_ENDPOINT_XFER_BULK: if (!ep->caps.type_bulk) return 0; if (ep_comp && gadget_is_superspeed(gadget)) { /* Get the number of required streams from the * EP companion descriptor and see if the EP * matches it */ num_req_streams = ep_comp->bmAttributes & 0x1f; if (num_req_streams > ep->max_streams) return 0; } break; case USB_ENDPOINT_XFER_INT: /* Bulk endpoints handle interrupt transfers, * except the toggle-quirky iso-synch kind */ if (!ep->caps.type_int && !ep->caps.type_bulk) return 0; /* INT: limit 64 bytes full speed, 1024 high/super speed */ if (!gadget_is_dualspeed(gadget) && max > 64) return 0; break; } return 1; } EXPORT_SYMBOL_GPL(usb_gadget_ep_match_desc); /* ------------------------------------------------------------------------- */ static void usb_gadget_state_work(struct work_struct *work) { struct usb_gadget *gadget = work_to_gadget(work); struct usb_udc *udc = gadget->udc; if (udc) sysfs_notify(&udc->dev.kobj, NULL, "state"); } void usb_gadget_set_state(struct usb_gadget *gadget, enum usb_device_state state) { gadget->state = state; schedule_work(&gadget->work); } EXPORT_SYMBOL_GPL(usb_gadget_set_state); /* ------------------------------------------------------------------------- */ static void usb_udc_connect_control(struct usb_udc *udc) { if (udc->vbus) usb_gadget_connect(udc->gadget); else usb_gadget_disconnect(udc->gadget); } /** * usb_udc_vbus_handler - updates the udc core vbus status, and try to * connect or disconnect gadget * @gadget: The gadget which vbus change occurs * @status: The vbus status * * The udc driver calls it when it wants to connect or disconnect gadget * according to vbus status. */ void usb_udc_vbus_handler(struct usb_gadget *gadget, bool status) { struct usb_udc *udc = gadget->udc; if (udc) { udc->vbus = status; usb_udc_connect_control(udc); } } EXPORT_SYMBOL_GPL(usb_udc_vbus_handler); /** * usb_gadget_udc_reset - notifies the udc core that bus reset occurs * @gadget: The gadget which bus reset occurs * @driver: The gadget driver we want to notify * * If the udc driver has bus reset handler, it needs to call this when the bus * reset occurs, it notifies the gadget driver that the bus reset occurs as * well as updates gadget state. */ void usb_gadget_udc_reset(struct usb_gadget *gadget, struct usb_gadget_driver *driver) { driver->reset(gadget); usb_gadget_set_state(gadget, USB_STATE_DEFAULT); } EXPORT_SYMBOL_GPL(usb_gadget_udc_reset); /** * usb_gadget_udc_start - tells usb device controller to start up * @udc: The UDC to be started * * This call is issued by the UDC Class driver when it's about * to register a gadget driver to the device controller, before * calling gadget driver's bind() method. * * It allows the controller to be powered off until strictly * necessary to have it powered on. * * Returns zero on success, else negative errno. */ static inline int usb_gadget_udc_start(struct usb_udc *udc) { return udc->gadget->ops->udc_start(udc->gadget, udc->driver); } /** * usb_gadget_udc_stop - tells usb device controller we don't need it anymore * @gadget: The device we want to stop activity * @driver: The driver to unbind from @gadget * * This call is issued by the UDC Class driver after calling * gadget driver's unbind() method. * * The details are implementation specific, but it can go as * far as powering off UDC completely and disable its data * line pullups. */ static inline void usb_gadget_udc_stop(struct usb_udc *udc) { udc->gadget->ops->udc_stop(udc->gadget); } /** * usb_gadget_udc_set_speed - tells usb device controller speed supported by * current driver * @udc: The device we want to set maximum speed * @speed: The maximum speed to allowed to run * * This call is issued by the UDC Class driver before calling * usb_gadget_udc_start() in order to make sure that we don't try to * connect on speeds the gadget driver doesn't support. */ static inline void usb_gadget_udc_set_speed(struct usb_udc *udc, enum usb_device_speed speed) { if (udc->gadget->ops->udc_set_speed) { enum usb_device_speed s; s = min(speed, udc->gadget->max_speed); udc->gadget->ops->udc_set_speed(udc->gadget, s); } } /** * usb_udc_release - release the usb_udc struct * @dev: the dev member within usb_udc * * This is called by driver's core in order to free memory once the last * reference is released. */ static void usb_udc_release(struct device *dev) { struct usb_udc *udc; udc = container_of(dev, struct usb_udc, dev); dev_dbg(dev, "releasing '%s'\n", dev_name(dev)); kfree(udc); } static const struct attribute_group *usb_udc_attr_groups[]; static void usb_udc_nop_release(struct device *dev) { dev_vdbg(dev, "%s\n", __func__); } /* should be called with udc_lock held */ static int check_pending_gadget_drivers(struct usb_udc *udc) { struct usb_gadget_driver *driver; int ret = 0; list_for_each_entry(driver, &gadget_driver_pending_list, pending) if (!driver->udc_name || strcmp(driver->udc_name, dev_name(&udc->dev)) == 0) { ret = udc_bind_to_driver(udc, driver); if (ret != -EPROBE_DEFER) list_del(&driver->pending); break; } return ret; } /** * usb_add_gadget_udc_release - adds a new gadget to the udc class driver list * @parent: the parent device to this udc. Usually the controller driver's * device. * @gadget: the gadget to be added to the list. * @release: a gadget release function. * * Returns zero on success, negative errno otherwise. * Calls the gadget release function in the latter case. */ int usb_add_gadget_udc_release(struct device *parent, struct usb_gadget *gadget, void (*release)(struct device *dev)) { struct usb_udc *udc; int ret = -ENOMEM; dev_set_name(&gadget->dev, "gadget"); INIT_WORK(&gadget->work, usb_gadget_state_work); gadget->dev.parent = parent; if (release) gadget->dev.release = release; else gadget->dev.release = usb_udc_nop_release; device_initialize(&gadget->dev); udc = kzalloc(sizeof(*udc), GFP_KERNEL); if (!udc) goto err_put_gadget; device_initialize(&udc->dev); udc->dev.release = usb_udc_release; udc->dev.class = udc_class; udc->dev.groups = usb_udc_attr_groups; udc->dev.parent = parent; ret = dev_set_name(&udc->dev, "%s", kobject_name(&parent->kobj)); if (ret) goto err_put_udc; ret = device_add(&gadget->dev); if (ret) goto err_put_udc; udc->gadget = gadget; gadget->udc = udc; mutex_lock(&udc_lock); list_add_tail(&udc->list, &udc_list); ret = device_add(&udc->dev); if (ret) goto err_unlist_udc; usb_gadget_set_state(gadget, USB_STATE_NOTATTACHED); udc->vbus = true; /* pick up one of pending gadget drivers */ ret = check_pending_gadget_drivers(udc); if (ret) goto err_del_udc; mutex_unlock(&udc_lock); return 0; err_del_udc: device_del(&udc->dev); err_unlist_udc: list_del(&udc->list); mutex_unlock(&udc_lock); device_del(&gadget->dev); err_put_udc: put_device(&udc->dev); err_put_gadget: put_device(&gadget->dev); return ret; } EXPORT_SYMBOL_GPL(usb_add_gadget_udc_release); /** * usb_get_gadget_udc_name - get the name of the first UDC controller * This functions returns the name of the first UDC controller in the system. * Please note that this interface is usefull only for legacy drivers which * assume that there is only one UDC controller in the system and they need to * get its name before initialization. There is no guarantee that the UDC * of the returned name will be still available, when gadget driver registers * itself. * * Returns pointer to string with UDC controller name on success, NULL * otherwise. Caller should kfree() returned string. */ char *usb_get_gadget_udc_name(void) { struct usb_udc *udc; char *name = NULL; /* For now we take the first available UDC */ mutex_lock(&udc_lock); list_for_each_entry(udc, &udc_list, list) { if (!udc->driver) { name = kstrdup(udc->gadget->name, GFP_KERNEL); break; } } mutex_unlock(&udc_lock); return name; } EXPORT_SYMBOL_GPL(usb_get_gadget_udc_name); /** * usb_add_gadget_udc - adds a new gadget to the udc class driver list * @parent: the parent device to this udc. Usually the controller * driver's device. * @gadget: the gadget to be added to the list * * Returns zero on success, negative errno otherwise. */ int usb_add_gadget_udc(struct device *parent, struct usb_gadget *gadget) { return usb_add_gadget_udc_release(parent, gadget, NULL); } EXPORT_SYMBOL_GPL(usb_add_gadget_udc); static void usb_gadget_remove_driver(struct usb_udc *udc) { dev_dbg(&udc->dev, "unregistering UDC driver [%s]\n", udc->driver->function); kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE); usb_gadget_disconnect(udc->gadget); udc->driver->disconnect(udc->gadget); udc->driver->unbind(udc->gadget); usb_gadget_udc_stop(udc); udc->driver = NULL; udc->gadget->dev.driver = NULL; } /** * usb_del_gadget_udc - deletes @udc from udc_list * @gadget: the gadget to be removed. * * This, will call usb_gadget_unregister_driver() if * the @udc is still busy. */ void usb_del_gadget_udc(struct usb_gadget *gadget) { struct usb_udc *udc = gadget->udc; if (!udc) return; dev_vdbg(gadget->dev.parent, "unregistering gadget\n"); mutex_lock(&udc_lock); list_del(&udc->list); if (udc->driver) { struct usb_gadget_driver *driver = udc->driver; usb_gadget_remove_driver(udc); list_add(&driver->pending, &gadget_driver_pending_list); } mutex_unlock(&udc_lock); kobject_uevent(&udc->dev.kobj, KOBJ_REMOVE); flush_work(&gadget->work); device_unregister(&udc->dev); device_unregister(&gadget->dev); memset(&gadget->dev, 0x00, sizeof(gadget->dev)); } EXPORT_SYMBOL_GPL(usb_del_gadget_udc); /* ------------------------------------------------------------------------- */ static int udc_bind_to_driver(struct usb_udc *udc, struct usb_gadget_driver *driver) { int ret; dev_dbg(&udc->dev, "registering UDC driver [%s]\n", driver->function); udc->driver = driver; udc->gadget->dev.driver = &driver->driver; usb_gadget_udc_set_speed(udc, driver->max_speed); ret = driver->bind(udc->gadget, driver); if (ret) goto err1; ret = usb_gadget_udc_start(udc); if (ret) { driver->unbind(udc->gadget); goto err1; } usb_udc_connect_control(udc); kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE); return 0; err1: if (ret != -EISNAM) dev_err(&udc->dev, "failed to start %s: %d\n", udc->driver->function, ret); udc->driver = NULL; udc->gadget->dev.driver = NULL; return ret; } int usb_gadget_probe_driver(struct usb_gadget_driver *driver) { struct usb_udc *udc = NULL; int ret = -ENODEV; if (!driver || !driver->bind || !driver->setup) return -EINVAL; mutex_lock(&udc_lock); if (driver->udc_name) { list_for_each_entry(udc, &udc_list, list) { ret = strcmp(driver->udc_name, dev_name(&udc->dev)); if (!ret) break; } if (ret) ret = -ENODEV; else if (udc->driver) ret = -EBUSY; else goto found; } else { list_for_each_entry(udc, &udc_list, list) { /* For now we take the first one */ if (!udc->driver) goto found; } } if (!driver->match_existing_only) { list_add_tail(&driver->pending, &gadget_driver_pending_list); pr_info("udc-core: couldn't find an available UDC - added [%s] to list of pending drivers\n", driver->function); ret = 0; } mutex_unlock(&udc_lock); return ret; found: ret = udc_bind_to_driver(udc, driver); mutex_unlock(&udc_lock); return ret; } EXPORT_SYMBOL_GPL(usb_gadget_probe_driver); int usb_gadget_unregister_driver(struct usb_gadget_driver *driver) { struct usb_udc *udc = NULL; int ret = -ENODEV; if (!driver || !driver->unbind) return -EINVAL; mutex_lock(&udc_lock); list_for_each_entry(udc, &udc_list, list) { if (udc->driver == driver) { usb_gadget_remove_driver(udc); usb_gadget_set_state(udc->gadget, USB_STATE_NOTATTACHED); /* Maybe there is someone waiting for this UDC? */ check_pending_gadget_drivers(udc); /* * For now we ignore bind errors as probably it's * not a valid reason to fail other's gadget unbind */ ret = 0; break; } } if (ret) { list_del(&driver->pending); ret = 0; } mutex_unlock(&udc_lock); return ret; } EXPORT_SYMBOL_GPL(usb_gadget_unregister_driver); /* ------------------------------------------------------------------------- */ static ssize_t usb_udc_srp_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t n) { struct usb_udc *udc = container_of(dev, struct usb_udc, dev); if (sysfs_streq(buf, "1")) usb_gadget_wakeup(udc->gadget); return n; } static DEVICE_ATTR(srp, S_IWUSR, NULL, usb_udc_srp_store); static ssize_t usb_udc_softconn_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t n) { struct usb_udc *udc = container_of(dev, struct usb_udc, dev); ssize_t ret; mutex_lock(&udc_lock); if (!udc->driver) { dev_err(dev, "soft-connect without a gadget driver\n"); ret = -EOPNOTSUPP; goto out; } if (sysfs_streq(buf, "connect")) { usb_gadget_udc_start(udc); usb_gadget_connect(udc->gadget); } else if (sysfs_streq(buf, "disconnect")) { usb_gadget_disconnect(udc->gadget); udc->driver->disconnect(udc->gadget); usb_gadget_udc_stop(udc); } else { dev_err(dev, "unsupported command '%s'\n", buf); ret = -EINVAL; goto out; } ret = n; out: mutex_unlock(&udc_lock); return ret; } static DEVICE_ATTR(soft_connect, S_IWUSR, NULL, usb_udc_softconn_store); static ssize_t state_show(struct device *dev, struct device_attribute *attr, char *buf) { struct usb_udc *udc = container_of(dev, struct usb_udc, dev); struct usb_gadget *gadget = udc->gadget; return sprintf(buf, "%s\n", usb_state_string(gadget->state)); } static DEVICE_ATTR_RO(state); static ssize_t function_show(struct device *dev, struct device_attribute *attr, char *buf) { struct usb_udc *udc = container_of(dev, struct usb_udc, dev); struct usb_gadget_driver *drv = udc->driver; if (!drv || !drv->function) return 0; return scnprintf(buf, PAGE_SIZE, "%s\n", drv->function); } static DEVICE_ATTR_RO(function); #define USB_UDC_SPEED_ATTR(name, param) \ ssize_t name##_show(struct device *dev, \ struct device_attribute *attr, char *buf) \ { \ struct usb_udc *udc = container_of(dev, struct usb_udc, dev); \ return snprintf(buf, PAGE_SIZE, "%s\n", \ usb_speed_string(udc->gadget->param)); \ } \ static DEVICE_ATTR_RO(name) static USB_UDC_SPEED_ATTR(current_speed, speed); static USB_UDC_SPEED_ATTR(maximum_speed, max_speed); #define USB_UDC_ATTR(name) \ ssize_t name##_show(struct device *dev, \ struct device_attribute *attr, char *buf) \ { \ struct usb_udc *udc = container_of(dev, struct usb_udc, dev); \ struct usb_gadget *gadget = udc->gadget; \ \ return snprintf(buf, PAGE_SIZE, "%d\n", gadget->name); \ } \ static DEVICE_ATTR_RO(name) static USB_UDC_ATTR(is_otg); static USB_UDC_ATTR(is_a_peripheral); static USB_UDC_ATTR(b_hnp_enable); static USB_UDC_ATTR(a_hnp_support); static USB_UDC_ATTR(a_alt_hnp_support); static USB_UDC_ATTR(is_selfpowered); static struct attribute *usb_udc_attrs[] = { &dev_attr_srp.attr, &dev_attr_soft_connect.attr, &dev_attr_state.attr, &dev_attr_function.attr, &dev_attr_current_speed.attr, &dev_attr_maximum_speed.attr, &dev_attr_is_otg.attr, &dev_attr_is_a_peripheral.attr, &dev_attr_b_hnp_enable.attr, &dev_attr_a_hnp_support.attr, &dev_attr_a_alt_hnp_support.attr, &dev_attr_is_selfpowered.attr, NULL, }; static const struct attribute_group usb_udc_attr_group = { .attrs = usb_udc_attrs, }; static const struct attribute_group *usb_udc_attr_groups[] = { &usb_udc_attr_group, NULL, }; static int usb_udc_uevent(struct device *dev, struct kobj_uevent_env *env) { struct usb_udc *udc = container_of(dev, struct usb_udc, dev); int ret; ret = add_uevent_var(env, "USB_UDC_NAME=%s", udc->gadget->name); if (ret) { dev_err(dev, "failed to add uevent USB_UDC_NAME\n"); return ret; } if (udc->driver) { ret = add_uevent_var(env, "USB_UDC_DRIVER=%s", udc->driver->function); if (ret) { dev_err(dev, "failed to add uevent USB_UDC_DRIVER\n"); return ret; } } return 0; } static int __init usb_udc_init(void) { udc_class = class_create(THIS_MODULE, "udc"); if (IS_ERR(udc_class)) { pr_err("failed to create udc class --> %ld\n", PTR_ERR(udc_class)); return PTR_ERR(udc_class); } udc_class->dev_uevent = usb_udc_uevent; return 0; } subsys_initcall(usb_udc_init); static void __exit usb_udc_exit(void) { class_destroy(udc_class); } module_exit(usb_udc_exit); MODULE_DESCRIPTION("UDC Framework"); MODULE_AUTHOR("Felipe Balbi <balbi@ti.com>"); MODULE_LICENSE("GPL v2"); |
| 14924 8991 9105 7219 5383 1003 205 957 3400 1988 2365 10930 860 5421 2956 6194 5013 8374 5874 904 906 6623 6622 2916 9770 12 12 12 12 12 9772 391 5427 808 26 26 808 809 9880 662 3737 3737 3736 3736 5015 370 370 321 370 265 427 8402 5950 2711 1806 1729 8400 6260 6259 6260 4050 4051 6263 5186 2474 1952 6261 6261 6261 6264 7 6 7 7 959 1307 1311 1310 1309 1309 1309 957 1308 1310 1310 1309 1309 956 5668 13759 13680 13025 13020 13662 4155 13665 13763 8724 8728 10513 8389 9360 8402 9357 4040 4030 5883 9025 9031 8049 5177 8054 32 4029 3816 2937 4478 4161 4161 4477 6536 6153 2602 1514 1517 1275 1517 1517 146 146 145 3 1231 7138 3 1 1 2 3 8064 8068 7900 7902 5120 4936 3216 5227 1234 3489 850 3128 3124 3127 3445 2905 3138 5158 1231 5145 73 73 56 31 31 7 7 7 123 123 84 1884 294 2125 2127 81 2057 2053 2049 2052 2052 2057 296 2682 2117 3068 5505 5505 5507 47 47 5508 7136 204 7135 7128 1037 1036 7135 4279 2920 2155 4282 2170 2170 2170 2171 7136 4497 7 317 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 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 | /* * Copyright (C) 2001 Momchil Velikov * Portions Copyright (C) 2001 Christoph Hellwig * Copyright (C) 2005 SGI, Christoph Lameter * Copyright (C) 2006 Nick Piggin * Copyright (C) 2012 Konstantin Khlebnikov * Copyright (C) 2016 Intel, Matthew Wilcox * Copyright (C) 2016 Intel, Ross Zwisler * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License as * published by the Free Software Foundation; either version 2, or (at * your option) any later version. * * This program is distributed in the hope that it will be useful, but * WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * General Public License for more details. * * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #include <linux/bitmap.h> #include <linux/bitops.h> #include <linux/cpu.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/idr.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/kmemleak.h> #include <linux/percpu.h> #include <linux/preempt.h> /* in_interrupt() */ #include <linux/radix-tree.h> #include <linux/rcupdate.h> #include <linux/slab.h> #include <linux/string.h> /* Number of nodes in fully populated tree of given height */ static unsigned long height_to_maxnodes[RADIX_TREE_MAX_PATH + 1] __read_mostly; /* * Radix tree node cache. */ static struct kmem_cache *radix_tree_node_cachep; /* * The radix tree is variable-height, so an insert operation not only has * to build the branch to its corresponding item, it also has to build the * branch to existing items if the size has to be increased (by * radix_tree_extend). * * The worst case is a zero height tree with just a single item at index 0, * and then inserting an item at index ULONG_MAX. This requires 2 new branches * of RADIX_TREE_MAX_PATH size to be created, with only the root node shared. * Hence: */ #define RADIX_TREE_PRELOAD_SIZE (RADIX_TREE_MAX_PATH * 2 - 1) /* * The IDR does not have to be as high as the radix tree since it uses * signed integers, not unsigned longs. */ #define IDR_INDEX_BITS (8 /* CHAR_BIT */ * sizeof(int) - 1) #define IDR_MAX_PATH (DIV_ROUND_UP(IDR_INDEX_BITS, \ RADIX_TREE_MAP_SHIFT)) #define IDR_PRELOAD_SIZE (IDR_MAX_PATH * 2 - 1) /* * The IDA is even shorter since it uses a bitmap at the last level. */ #define IDA_INDEX_BITS (8 * sizeof(int) - 1 - ilog2(IDA_BITMAP_BITS)) #define IDA_MAX_PATH (DIV_ROUND_UP(IDA_INDEX_BITS, \ RADIX_TREE_MAP_SHIFT)) #define IDA_PRELOAD_SIZE (IDA_MAX_PATH * 2 - 1) /* * Per-cpu pool of preloaded nodes */ struct radix_tree_preload { unsigned nr; /* nodes->parent points to next preallocated node */ struct radix_tree_node *nodes; }; static DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = { 0, }; static inline struct radix_tree_node *entry_to_node(void *ptr) { return (void *)((unsigned long)ptr & ~RADIX_TREE_INTERNAL_NODE); } static inline void *node_to_entry(void *ptr) { return (void *)((unsigned long)ptr | RADIX_TREE_INTERNAL_NODE); } #define RADIX_TREE_RETRY node_to_entry(NULL) #ifdef CONFIG_RADIX_TREE_MULTIORDER /* Sibling slots point directly to another slot in the same node */ static inline bool is_sibling_entry(const struct radix_tree_node *parent, void *node) { void __rcu **ptr = node; return (parent->slots <= ptr) && (ptr < parent->slots + RADIX_TREE_MAP_SIZE); } #else static inline bool is_sibling_entry(const struct radix_tree_node *parent, void *node) { return false; } #endif static inline unsigned long get_slot_offset(const struct radix_tree_node *parent, void __rcu **slot) { return slot - parent->slots; } static unsigned int radix_tree_descend(const struct radix_tree_node *parent, struct radix_tree_node **nodep, unsigned long index) { unsigned int offset = (index >> parent->shift) & RADIX_TREE_MAP_MASK; void __rcu **entry = rcu_dereference_raw(parent->slots[offset]); #ifdef CONFIG_RADIX_TREE_MULTIORDER if (radix_tree_is_internal_node(entry)) { if (is_sibling_entry(parent, entry)) { void __rcu **sibentry; sibentry = (void __rcu **) entry_to_node(entry); offset = get_slot_offset(parent, sibentry); entry = rcu_dereference_raw(*sibentry); } } #endif *nodep = (void *)entry; return offset; } static inline gfp_t root_gfp_mask(const struct radix_tree_root *root) { return root->gfp_mask & __GFP_BITS_MASK; } static inline void tag_set(struct radix_tree_node *node, unsigned int tag, int offset) { __set_bit(offset, node->tags[tag]); } static inline void tag_clear(struct radix_tree_node *node, unsigned int tag, int offset) { __clear_bit(offset, node->tags[tag]); } static inline int tag_get(const struct radix_tree_node *node, unsigned int tag, int offset) { return test_bit(offset, node->tags[tag]); } static inline void root_tag_set(struct radix_tree_root *root, unsigned tag) { root->gfp_mask |= (__force gfp_t)(1 << (tag + ROOT_TAG_SHIFT)); } static inline void root_tag_clear(struct radix_tree_root *root, unsigned tag) { root->gfp_mask &= (__force gfp_t)~(1 << (tag + ROOT_TAG_SHIFT)); } static inline void root_tag_clear_all(struct radix_tree_root *root) { root->gfp_mask &= (1 << ROOT_TAG_SHIFT) - 1; } static inline int root_tag_get(const struct radix_tree_root *root, unsigned tag) { return (__force int)root->gfp_mask & (1 << (tag + ROOT_TAG_SHIFT)); } static inline unsigned root_tags_get(const struct radix_tree_root *root) { return (__force unsigned)root->gfp_mask >> ROOT_TAG_SHIFT; } static inline bool is_idr(const struct radix_tree_root *root) { return !!(root->gfp_mask & ROOT_IS_IDR); } /* * Returns 1 if any slot in the node has this tag set. * Otherwise returns 0. */ static inline int any_tag_set(const struct radix_tree_node *node, unsigned int tag) { unsigned idx; for (idx = 0; idx < RADIX_TREE_TAG_LONGS; idx++) { if (node->tags[tag][idx]) return 1; } return 0; } static inline void all_tag_set(struct radix_tree_node *node, unsigned int tag) { bitmap_fill(node->tags[tag], RADIX_TREE_MAP_SIZE); } /** * radix_tree_find_next_bit - find the next set bit in a memory region * * @addr: The address to base the search on * @size: The bitmap size in bits * @offset: The bitnumber to start searching at * * Unrollable variant of find_next_bit() for constant size arrays. * Tail bits starting from size to roundup(size, BITS_PER_LONG) must be zero. * Returns next bit offset, or size if nothing found. */ static __always_inline unsigned long radix_tree_find_next_bit(struct radix_tree_node *node, unsigned int tag, unsigned long offset) { const unsigned long *addr = node->tags[tag]; if (offset < RADIX_TREE_MAP_SIZE) { unsigned long tmp; addr += offset / BITS_PER_LONG; tmp = *addr >> (offset % BITS_PER_LONG); if (tmp) return __ffs(tmp) + offset; offset = (offset + BITS_PER_LONG) & ~(BITS_PER_LONG - 1); while (offset < RADIX_TREE_MAP_SIZE) { tmp = *++addr; if (tmp) return __ffs(tmp) + offset; offset += BITS_PER_LONG; } } return RADIX_TREE_MAP_SIZE; } static unsigned int iter_offset(const struct radix_tree_iter *iter) { return (iter->index >> iter_shift(iter)) & RADIX_TREE_MAP_MASK; } /* * The maximum index which can be stored in a radix tree */ static inline unsigned long shift_maxindex(unsigned int shift) { return (RADIX_TREE_MAP_SIZE << shift) - 1; } static inline unsigned long node_maxindex(const struct radix_tree_node *node) { return shift_maxindex(node->shift); } static unsigned long next_index(unsigned long index, const struct radix_tree_node *node, unsigned long offset) { return (index & ~node_maxindex(node)) + (offset << node->shift); } #ifndef __KERNEL__ static void dump_node(struct radix_tree_node *node, unsigned long index) { unsigned long i; pr_debug("radix node: %p offset %d indices %lu-%lu parent %p tags %lx %lx %lx shift %d count %d exceptional %d\n", node, node->offset, index, index | node_maxindex(node), node->parent, node->tags[0][0], node->tags[1][0], node->tags[2][0], node->shift, node->count, node->exceptional); for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) { unsigned long first = index | (i << node->shift); unsigned long last = first | ((1UL << node->shift) - 1); void *entry = node->slots[i]; if (!entry) continue; if (entry == RADIX_TREE_RETRY) { pr_debug("radix retry offset %ld indices %lu-%lu parent %p\n", i, first, last, node); } else if (!radix_tree_is_internal_node(entry)) { pr_debug("radix entry %p offset %ld indices %lu-%lu parent %p\n", entry, i, first, last, node); } else if (is_sibling_entry(node, entry)) { pr_debug("radix sblng %p offset %ld indices %lu-%lu parent %p val %p\n", entry, i, first, last, node, *(void **)entry_to_node(entry)); } else { dump_node(entry_to_node(entry), first); } } } /* For debug */ static void radix_tree_dump(struct radix_tree_root *root) { pr_debug("radix root: %p rnode %p tags %x\n", root, root->rnode, root->gfp_mask >> ROOT_TAG_SHIFT); if (!radix_tree_is_internal_node(root->rnode)) return; dump_node(entry_to_node(root->rnode), 0); } static void dump_ida_node(void *entry, unsigned long index) { unsigned long i; if (!entry) return; if (radix_tree_is_internal_node(entry)) { struct radix_tree_node *node = entry_to_node(entry); pr_debug("ida node: %p offset %d indices %lu-%lu parent %p free %lx shift %d count %d\n", node, node->offset, index * IDA_BITMAP_BITS, ((index | node_maxindex(node)) + 1) * IDA_BITMAP_BITS - 1, node->parent, node->tags[0][0], node->shift, node->count); for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) dump_ida_node(node->slots[i], index | (i << node->shift)); } else if (radix_tree_exceptional_entry(entry)) { pr_debug("ida excp: %p offset %d indices %lu-%lu data %lx\n", entry, (int)(index & RADIX_TREE_MAP_MASK), index * IDA_BITMAP_BITS, index * IDA_BITMAP_BITS + BITS_PER_LONG - RADIX_TREE_EXCEPTIONAL_SHIFT, (unsigned long)entry >> RADIX_TREE_EXCEPTIONAL_SHIFT); } else { struct ida_bitmap *bitmap = entry; pr_debug("ida btmp: %p offset %d indices %lu-%lu data", bitmap, (int)(index & RADIX_TREE_MAP_MASK), index * IDA_BITMAP_BITS, (index + 1) * IDA_BITMAP_BITS - 1); for (i = 0; i < IDA_BITMAP_LONGS; i++) pr_cont(" %lx", bitmap->bitmap[i]); pr_cont("\n"); } } static void ida_dump(struct ida *ida) { struct radix_tree_root *root = &ida->ida_rt; pr_debug("ida: %p node %p free %d\n", ida, root->rnode, root->gfp_mask >> ROOT_TAG_SHIFT); dump_ida_node(root->rnode, 0); } #endif /* * This assumes that the caller has performed appropriate preallocation, and * that the caller has pinned this thread of control to the current CPU. */ static struct radix_tree_node * radix_tree_node_alloc(gfp_t gfp_mask, struct radix_tree_node *parent, struct radix_tree_root *root, unsigned int shift, unsigned int offset, unsigned int count, unsigned int exceptional) { struct radix_tree_node *ret = NULL; /* * Preload code isn't irq safe and it doesn't make sense to use * preloading during an interrupt anyway as all the allocations have * to be atomic. So just do normal allocation when in interrupt. */ if (!gfpflags_allow_blocking(gfp_mask) && !in_interrupt()) { struct radix_tree_preload *rtp; /* * Even if the caller has preloaded, try to allocate from the * cache first for the new node to get accounted to the memory * cgroup. */ ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask | __GFP_NOWARN); if (ret) goto out; /* * Provided the caller has preloaded here, we will always * succeed in getting a node here (and never reach * kmem_cache_alloc) */ rtp = this_cpu_ptr(&radix_tree_preloads); if (rtp->nr) { ret = rtp->nodes; rtp->nodes = ret->parent; rtp->nr--; } /* * Update the allocation stack trace as this is more useful * for debugging. */ kmemleak_update_trace(ret); goto out; } ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); out: BUG_ON(radix_tree_is_internal_node(ret)); if (ret) { ret->shift = shift; ret->offset = offset; ret->count = count; ret->exceptional = exceptional; ret->parent = parent; ret->root = root; } return ret; } static void radix_tree_node_rcu_free(struct rcu_head *head) { struct radix_tree_node *node = container_of(head, struct radix_tree_node, rcu_head); /* * Must only free zeroed nodes into the slab. We can be left with * non-NULL entries by radix_tree_free_nodes, so clear the entries * and tags here. */ memset(node->slots, 0, sizeof(node->slots)); memset(node->tags, 0, sizeof(node->tags)); INIT_LIST_HEAD(&node->private_list); kmem_cache_free(radix_tree_node_cachep, node); } static inline void radix_tree_node_free(struct radix_tree_node *node) { call_rcu(&node->rcu_head, radix_tree_node_rcu_free); } /* * Load up this CPU's radix_tree_node buffer with sufficient objects to * ensure that the addition of a single element in the tree cannot fail. On * success, return zero, with preemption disabled. On error, return -ENOMEM * with preemption not disabled. * * To make use of this facility, the radix tree must be initialised without * __GFP_DIRECT_RECLAIM being passed to INIT_RADIX_TREE(). */ static __must_check int __radix_tree_preload(gfp_t gfp_mask, unsigned nr) { struct radix_tree_preload *rtp; struct radix_tree_node *node; int ret = -ENOMEM; /* * Nodes preloaded by one cgroup can be be used by another cgroup, so * they should never be accounted to any particular memory cgroup. */ gfp_mask &= ~__GFP_ACCOUNT; preempt_disable(); rtp = this_cpu_ptr(&radix_tree_preloads); while (rtp->nr < nr) { preempt_enable(); node = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); if (node == NULL) goto out; preempt_disable(); rtp = this_cpu_ptr(&radix_tree_preloads); if (rtp->nr < nr) { node->parent = rtp->nodes; rtp->nodes = node; rtp->nr++; } else { kmem_cache_free(radix_tree_node_cachep, node); } } ret = 0; out: return ret; } /* * Load up this CPU's radix_tree_node buffer with sufficient objects to * ensure that the addition of a single element in the tree cannot fail. On * success, return zero, with preemption disabled. On error, return -ENOMEM * with preemption not disabled. * * To make use of this facility, the radix tree must be initialised without * __GFP_DIRECT_RECLAIM being passed to INIT_RADIX_TREE(). */ int radix_tree_preload(gfp_t gfp_mask) { /* Warn on non-sensical use... */ WARN_ON_ONCE(!gfpflags_allow_blocking(gfp_mask)); return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE); } EXPORT_SYMBOL(radix_tree_preload); /* * The same as above function, except we don't guarantee preloading happens. * We do it, if we decide it helps. On success, return zero with preemption * disabled. On error, return -ENOMEM with preemption not disabled. */ int radix_tree_maybe_preload(gfp_t gfp_mask) { if (gfpflags_allow_blocking(gfp_mask)) return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE); /* Preloading doesn't help anything with this gfp mask, skip it */ preempt_disable(); return 0; } EXPORT_SYMBOL(radix_tree_maybe_preload); #ifdef CONFIG_RADIX_TREE_MULTIORDER /* * Preload with enough objects to ensure that we can split a single entry * of order @old_order into many entries of size @new_order */ int radix_tree_split_preload(unsigned int old_order, unsigned int new_order, gfp_t gfp_mask) { unsigned top = 1 << (old_order % RADIX_TREE_MAP_SHIFT); unsigned layers = (old_order / RADIX_TREE_MAP_SHIFT) - (new_order / RADIX_TREE_MAP_SHIFT); unsigned nr = 0; WARN_ON_ONCE(!gfpflags_allow_blocking(gfp_mask)); BUG_ON(new_order >= old_order); while (layers--) nr = nr * RADIX_TREE_MAP_SIZE + 1; return __radix_tree_preload(gfp_mask, top * nr); } #endif /* * The same as function above, but preload number of nodes required to insert * (1 << order) continuous naturally-aligned elements. */ int radix_tree_maybe_preload_order(gfp_t gfp_mask, int order) { unsigned long nr_subtrees; int nr_nodes, subtree_height; /* Preloading doesn't help anything with this gfp mask, skip it */ if (!gfpflags_allow_blocking(gfp_mask)) { preempt_disable(); return 0; } /* * Calculate number and height of fully populated subtrees it takes to * store (1 << order) elements. */ nr_subtrees = 1 << order; for (subtree_height = 0; nr_subtrees > RADIX_TREE_MAP_SIZE; subtree_height++) nr_subtrees >>= RADIX_TREE_MAP_SHIFT; /* * The worst case is zero height tree with a single item at index 0 and * then inserting items starting at ULONG_MAX - (1 << order). * * This requires RADIX_TREE_MAX_PATH nodes to build branch from root to * 0-index item. */ nr_nodes = RADIX_TREE_MAX_PATH; /* Plus branch to fully populated subtrees. */ nr_nodes += RADIX_TREE_MAX_PATH - subtree_height; /* Root node is shared. */ nr_nodes--; /* Plus nodes required to build subtrees. */ nr_nodes += nr_subtrees * height_to_maxnodes[subtree_height]; return __radix_tree_preload(gfp_mask, nr_nodes); } static unsigned radix_tree_load_root(const struct radix_tree_root *root, struct radix_tree_node **nodep, unsigned long *maxindex) { struct radix_tree_node *node = rcu_dereference_raw(root->rnode); *nodep = node; if (likely(radix_tree_is_internal_node(node))) { node = entry_to_node(node); *maxindex = node_maxindex(node); return node->shift + RADIX_TREE_MAP_SHIFT; } *maxindex = 0; return 0; } /* * Extend a radix tree so it can store key @index. */ static int radix_tree_extend(struct radix_tree_root *root, gfp_t gfp, unsigned long index, unsigned int shift) { void *entry; unsigned int maxshift; int tag; /* Figure out what the shift should be. */ maxshift = shift; while (index > shift_maxindex(maxshift)) maxshift += RADIX_TREE_MAP_SHIFT; entry = rcu_dereference_raw(root->rnode); if (!entry && (!is_idr(root) || root_tag_get(root, IDR_FREE))) goto out; do { struct radix_tree_node *node = radix_tree_node_alloc(gfp, NULL, root, shift, 0, 1, 0); if (!node) return -ENOMEM; if (is_idr(root)) { all_tag_set(node, IDR_FREE); if (!root_tag_get(root, IDR_FREE)) { tag_clear(node, IDR_FREE, 0); root_tag_set(root, IDR_FREE); } } else { /* Propagate the aggregated tag info to the new child */ for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) { if (root_tag_get(root, tag)) tag_set(node, tag, 0); } } BUG_ON(shift > BITS_PER_LONG); if (radix_tree_is_internal_node(entry)) { entry_to_node(entry)->parent = node; } else if (radix_tree_exceptional_entry(entry)) { /* Moving an exceptional root->rnode to a node */ node->exceptional = 1; } /* * entry was already in the radix tree, so we do not need * rcu_assign_pointer here */ node->slots[0] = (void __rcu *)entry; entry = node_to_entry(node); rcu_assign_pointer(root->rnode, entry); shift += RADIX_TREE_MAP_SHIFT; } while (shift <= maxshift); out: return maxshift + RADIX_TREE_MAP_SHIFT; } /** * radix_tree_shrink - shrink radix tree to minimum height * @root radix tree root */ static inline bool radix_tree_shrink(struct radix_tree_root *root, radix_tree_update_node_t update_node, void *private) { bool shrunk = false; for (;;) { struct radix_tree_node *node = rcu_dereference_raw(root->rnode); struct radix_tree_node *child; if (!radix_tree_is_internal_node(node)) break; node = entry_to_node(node); /* * The candidate node has more than one child, or its child * is not at the leftmost slot, or the child is a multiorder * entry, we cannot shrink. */ if (node->count != 1) break; child = rcu_dereference_raw(node->slots[0]); if (!child) break; if (!radix_tree_is_internal_node(child) && node->shift) break; if (radix_tree_is_internal_node(child)) entry_to_node(child)->parent = NULL; /* * We don't need rcu_assign_pointer(), since we are simply * moving the node from one part of the tree to another: if it * was safe to dereference the old pointer to it * (node->slots[0]), it will be safe to dereference the new * one (root->rnode) as far as dependent read barriers go. */ root->rnode = (void __rcu *)child; if (is_idr(root) && !tag_get(node, IDR_FREE, 0)) root_tag_clear(root, IDR_FREE); /* * We have a dilemma here. The node's slot[0] must not be * NULLed in case there are concurrent lookups expecting to * find the item. However if this was a bottom-level node, * then it may be subject to the slot pointer being visible * to callers dereferencing it. If item corresponding to * slot[0] is subsequently deleted, these callers would expect * their slot to become empty sooner or later. * * For example, lockless pagecache will look up a slot, deref * the page pointer, and if the page has 0 refcount it means it * was concurrently deleted from pagecache so try the deref * again. Fortunately there is already a requirement for logic * to retry the entire slot lookup -- the indirect pointer * problem (replacing direct root node with an indirect pointer * also results in a stale slot). So tag the slot as indirect * to force callers to retry. */ node->count = 0; if (!radix_tree_is_internal_node(child)) { node->slots[0] = (void __rcu *)RADIX_TREE_RETRY; if (update_node) update_node(node, private); } WARN_ON_ONCE(!list_empty(&node->private_list)); radix_tree_node_free(node); shrunk = true; } return shrunk; } static bool delete_node(struct radix_tree_root *root, struct radix_tree_node *node, radix_tree_update_node_t update_node, void *private) { bool deleted = false; do { struct radix_tree_node *parent; if (node->count) { if (node_to_entry(node) == rcu_dereference_raw(root->rnode)) deleted |= radix_tree_shrink(root, update_node, private); return deleted; } parent = node->parent; if (parent) { parent->slots[node->offset] = NULL; parent->count--; } else { /* * Shouldn't the tags already have all been cleared * by the caller? */ if (!is_idr(root)) root_tag_clear_all(root); root->rnode = NULL; } WARN_ON_ONCE(!list_empty(&node->private_list)); radix_tree_node_free(node); deleted = true; node = parent; } while (node); return deleted; } /** * __radix_tree_create - create a slot in a radix tree * @root: radix tree root * @index: index key * @order: index occupies 2^order aligned slots * @nodep: returns node * @slotp: returns slot * * Create, if necessary, and return the node and slot for an item * at position @index in the radix tree @root. * * Until there is more than one item in the tree, no nodes are * allocated and @root->rnode is used as a direct slot instead of * pointing to a node, in which case *@nodep will be NULL. * * Returns -ENOMEM, or 0 for success. */ int __radix_tree_create(struct radix_tree_root *root, unsigned long index, unsigned order, struct radix_tree_node **nodep, void __rcu ***slotp) { struct radix_tree_node *node = NULL, *child; void __rcu **slot = (void __rcu **)&root->rnode; unsigned long maxindex; unsigned int shift, offset = 0; unsigned long max = index | ((1UL << order) - 1); gfp_t gfp = root_gfp_mask(root); shift = radix_tree_load_root(root, &child, &maxindex); /* Make sure the tree is high enough. */ if (order > 0 && max == ((1UL << order) - 1)) max++; if (max > maxindex) { int error = radix_tree_extend(root, gfp, max, shift); if (error < 0) return error; shift = error; child = rcu_dereference_raw(root->rnode); } while (shift > order) { shift -= RADIX_TREE_MAP_SHIFT; if (child == NULL) { /* Have to add a child node. */ child = radix_tree_node_alloc(gfp, node, root, shift, offset, 0, 0); if (!child) return -ENOMEM; rcu_assign_pointer(*slot, node_to_entry(child)); if (node) node->count++; } else if (!radix_tree_is_internal_node(child)) break; /* Go a level down */ node = entry_to_node(child); offset = radix_tree_descend(node, &child, index); slot = &node->slots[offset]; } if (nodep) *nodep = node; if (slotp) *slotp = slot; return 0; } /* * Free any nodes below this node. The tree is presumed to not need * shrinking, and any user data in the tree is presumed to not need a * destructor called on it. If we need to add a destructor, we can * add that functionality later. Note that we may not clear tags or * slots from the tree as an RCU walker may still have a pointer into * this subtree. We could replace the entries with RADIX_TREE_RETRY, * but we'll still have to clear those in rcu_free. */ static void radix_tree_free_nodes(struct radix_tree_node *node) { unsigned offset = 0; struct radix_tree_node *child = entry_to_node(node); for (;;) { void *entry = rcu_dereference_raw(child->slots[offset]); if (radix_tree_is_internal_node(entry) && !is_sibling_entry(child, entry)) { child = entry_to_node(entry); offset = 0; continue; } offset++; while (offset == RADIX_TREE_MAP_SIZE) { struct radix_tree_node *old = child; offset = child->offset + 1; child = child->parent; WARN_ON_ONCE(!list_empty(&old->private_list)); radix_tree_node_free(old); if (old == entry_to_node(node)) return; } } } #ifdef CONFIG_RADIX_TREE_MULTIORDER static inline int insert_entries(struct radix_tree_node *node, void __rcu **slot, void *item, unsigned order, bool replace) { struct radix_tree_node *child; unsigned i, n, tag, offset, tags = 0; if (node) { if (order > node->shift) n = 1 << (order - node->shift); else n = 1; offset = get_slot_offset(node, slot); } else { n = 1; offset = 0; } if (n > 1) { offset = offset & ~(n - 1); slot = &node->slots[offset]; } child = node_to_entry(slot); for (i = 0; i < n; i++) { if (slot[i]) { if (replace) { node->count--; for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) if (tag_get(node, tag, offset + i)) tags |= 1 << tag; } else return -EEXIST; } } for (i = 0; i < n; i++) { struct radix_tree_node *old = rcu_dereference_raw(slot[i]); if (i) { rcu_assign_pointer(slot[i], child); for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) if (tags & (1 << tag)) tag_clear(node, tag, offset + i); } else { rcu_assign_pointer(slot[i], item); for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) if (tags & (1 << tag)) tag_set(node, tag, offset); } if (radix_tree_is_internal_node(old) && !is_sibling_entry(node, old) && (old != RADIX_TREE_RETRY)) radix_tree_free_nodes(old); if (radix_tree_exceptional_entry(old)) node->exceptional--; } if (node) { node->count += n; if (radix_tree_exceptional_entry(item)) node->exceptional += n; } return n; } #else static inline int insert_entries(struct radix_tree_node *node, void __rcu **slot, void *item, unsigned order, bool replace) { if (*slot) return -EEXIST; rcu_assign_pointer(*slot, item); if (node) { node->count++; if (radix_tree_exceptional_entry(item)) node->exceptional++; } return 1; } #endif /** * __radix_tree_insert - insert into a radix tree * @root: radix tree root * @index: index key * @order: key covers the 2^order indices around index * @item: item to insert * * Insert an item into the radix tree at position @index. */ int __radix_tree_insert(struct radix_tree_root *root, unsigned long index, unsigned order, void *item) { struct radix_tree_node *node; void __rcu **slot; int error; BUG_ON(radix_tree_is_internal_node(item)); error = __radix_tree_create(root, index, order, &node, &slot); if (error) return error; error = insert_entries(node, slot, item, order, false); if (error < 0) return error; if (node) { unsigned offset = get_slot_offset(node, slot); BUG_ON(tag_get(node, 0, offset)); BUG_ON(tag_get(node, 1, offset)); BUG_ON(tag_get(node, 2, offset)); } else { BUG_ON(root_tags_get(root)); } return 0; } EXPORT_SYMBOL(__radix_tree_insert); /** * __radix_tree_lookup - lookup an item in a radix tree * @root: radix tree root * @index: index key * @nodep: returns node * @slotp: returns slot * * Lookup and return the item at position @index in the radix * tree @root. * * Until there is more than one item in the tree, no nodes are * allocated and @root->rnode is used as a direct slot instead of * pointing to a node, in which case *@nodep will be NULL. */ void *__radix_tree_lookup(const struct radix_tree_root *root, unsigned long index, struct radix_tree_node **nodep, void __rcu ***slotp) { struct radix_tree_node *node, *parent; unsigned long maxindex; void __rcu **slot; restart: parent = NULL; slot = (void __rcu **)&root->rnode; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return NULL; while (radix_tree_is_internal_node(node)) { unsigned offset; if (node == RADIX_TREE_RETRY) goto restart; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); slot = parent->slots + offset; } if (nodep) *nodep = parent; if (slotp) *slotp = slot; return node; } /** * radix_tree_lookup_slot - lookup a slot in a radix tree * @root: radix tree root * @index: index key * * Returns: the slot corresponding to the position @index in the * radix tree @root. This is useful for update-if-exists operations. * * This function can be called under rcu_read_lock iff the slot is not * modified by radix_tree_replace_slot, otherwise it must be called * exclusive from other writers. Any dereference of the slot must be done * using radix_tree_deref_slot. */ void __rcu **radix_tree_lookup_slot(const struct radix_tree_root *root, unsigned long index) { void __rcu **slot; if (!__radix_tree_lookup(root, index, NULL, &slot)) return NULL; return slot; } EXPORT_SYMBOL(radix_tree_lookup_slot); /** * radix_tree_lookup - perform lookup operation on a radix tree * @root: radix tree root * @index: index key * * Lookup the item at the position @index in the radix tree @root. * * This function can be called under rcu_read_lock, however the caller * must manage lifetimes of leaf nodes (eg. RCU may also be used to free * them safely). No RCU barriers are required to access or modify the * returned item, however. */ void *radix_tree_lookup(const struct radix_tree_root *root, unsigned long index) { return __radix_tree_lookup(root, index, NULL, NULL); } EXPORT_SYMBOL(radix_tree_lookup); static inline void replace_sibling_entries(struct radix_tree_node *node, void __rcu **slot, int count, int exceptional) { #ifdef CONFIG_RADIX_TREE_MULTIORDER void *ptr = node_to_entry(slot); unsigned offset = get_slot_offset(node, slot) + 1; while (offset < RADIX_TREE_MAP_SIZE) { if (rcu_dereference_raw(node->slots[offset]) != ptr) break; if (count < 0) { node->slots[offset] = NULL; node->count--; } node->exceptional += exceptional; offset++; } #endif } static void replace_slot(void __rcu **slot, void *item, struct radix_tree_node *node, int count, int exceptional) { if (WARN_ON_ONCE(radix_tree_is_internal_node(item))) return; if (node && (count || exceptional)) { node->count += count; node->exceptional += exceptional; replace_sibling_entries(node, slot, count, exceptional); } rcu_assign_pointer(*slot, item); } static bool node_tag_get(const struct radix_tree_root *root, const struct radix_tree_node *node, unsigned int tag, unsigned int offset) { if (node) return tag_get(node, tag, offset); return root_tag_get(root, tag); } /* * IDR users want to be able to store NULL in the tree, so if the slot isn't * free, don't adjust the count, even if it's transitioning between NULL and * non-NULL. For the IDA, we mark slots as being IDR_FREE while they still * have empty bits, but it only stores NULL in slots when they're being * deleted. */ static int calculate_count(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot, void *item, void *old) { if (is_idr(root)) { unsigned offset = get_slot_offset(node, slot); bool free = node_tag_get(root, node, IDR_FREE, offset); if (!free) return 0; if (!old) return 1; } return !!item - !!old; } /** * __radix_tree_replace - replace item in a slot * @root: radix tree root * @node: pointer to tree node * @slot: pointer to slot in @node * @item: new item to store in the slot. * @update_node: callback for changing leaf nodes * @private: private data to pass to @update_node * * For use with __radix_tree_lookup(). Caller must hold tree write locked * across slot lookup and replacement. */ void __radix_tree_replace(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot, void *item, radix_tree_update_node_t update_node, void *private) { void *old = rcu_dereference_raw(*slot); int exceptional = !!radix_tree_exceptional_entry(item) - !!radix_tree_exceptional_entry(old); int count = calculate_count(root, node, slot, item, old); /* * This function supports replacing exceptional entries and * deleting entries, but that needs accounting against the * node unless the slot is root->rnode. */ WARN_ON_ONCE(!node && (slot != (void __rcu **)&root->rnode) && (count || exceptional)); replace_slot(slot, item, node, count, exceptional); if (!node) return; if (update_node) update_node(node, private); delete_node(root, node, update_node, private); } /** * radix_tree_replace_slot - replace item in a slot * @root: radix tree root * @slot: pointer to slot * @item: new item to store in the slot. * * For use with radix_tree_lookup_slot(), radix_tree_gang_lookup_slot(), * radix_tree_gang_lookup_tag_slot(). Caller must hold tree write locked * across slot lookup and replacement. * * NOTE: This cannot be used to switch between non-entries (empty slots), * regular entries, and exceptional entries, as that requires accounting * inside the radix tree node. When switching from one type of entry or * deleting, use __radix_tree_lookup() and __radix_tree_replace() or * radix_tree_iter_replace(). */ void radix_tree_replace_slot(struct radix_tree_root *root, void __rcu **slot, void *item) { __radix_tree_replace(root, NULL, slot, item, NULL, NULL); } EXPORT_SYMBOL(radix_tree_replace_slot); /** * radix_tree_iter_replace - replace item in a slot * @root: radix tree root * @slot: pointer to slot * @item: new item to store in the slot. * * For use with radix_tree_split() and radix_tree_for_each_slot(). * Caller must hold tree write locked across split and replacement. */ void radix_tree_iter_replace(struct radix_tree_root *root, const struct radix_tree_iter *iter, void __rcu **slot, void *item) { __radix_tree_replace(root, iter->node, slot, item, NULL, NULL); } #ifdef CONFIG_RADIX_TREE_MULTIORDER /** * radix_tree_join - replace multiple entries with one multiorder entry * @root: radix tree root * @index: an index inside the new entry * @order: order of the new entry * @item: new entry * * Call this function to replace several entries with one larger entry. * The existing entries are presumed to not need freeing as a result of * this call. * * The replacement entry will have all the tags set on it that were set * on any of the entries it is replacing. */ int radix_tree_join(struct radix_tree_root *root, unsigned long index, unsigned order, void *item) { struct radix_tree_node *node; void __rcu **slot; int error; BUG_ON(radix_tree_is_internal_node(item)); error = __radix_tree_create(root, index, order, &node, &slot); if (!error) error = insert_entries(node, slot, item, order, true); if (error > 0) error = 0; return error; } /** * radix_tree_split - Split an entry into smaller entries * @root: radix tree root * @index: An index within the large entry * @order: Order of new entries * * Call this function as the first step in replacing a multiorder entry * with several entries of lower order. After this function returns, * loop over the relevant portion of the tree using radix_tree_for_each_slot() * and call radix_tree_iter_replace() to set up each new entry. * * The tags from this entry are replicated to all the new entries. * * The radix tree should be locked against modification during the entire * replacement operation. Lock-free lookups will see RADIX_TREE_RETRY which * should prompt RCU walkers to restart the lookup from the root. */ int radix_tree_split(struct radix_tree_root *root, unsigned long index, unsigned order) { struct radix_tree_node *parent, *node, *child; void __rcu **slot; unsigned int offset, end; unsigned n, tag, tags = 0; gfp_t gfp = root_gfp_mask(root); if (!__radix_tree_lookup(root, index, &parent, &slot)) return -ENOENT; if (!parent) return -ENOENT; offset = get_slot_offset(parent, slot); for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) if (tag_get(parent, tag, offset)) tags |= 1 << tag; for (end = offset + 1; end < RADIX_TREE_MAP_SIZE; end++) { if (!is_sibling_entry(parent, rcu_dereference_raw(parent->slots[end]))) break; for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) if (tags & (1 << tag)) tag_set(parent, tag, end); /* rcu_assign_pointer ensures tags are set before RETRY */ rcu_assign_pointer(parent->slots[end], RADIX_TREE_RETRY); } rcu_assign_pointer(parent->slots[offset], RADIX_TREE_RETRY); parent->exceptional -= (end - offset); if (order == parent->shift) return 0; if (order > parent->shift) { while (offset < end) offset += insert_entries(parent, &parent->slots[offset], RADIX_TREE_RETRY, order, true); return 0; } node = parent; for (;;) { if (node->shift > order) { child = radix_tree_node_alloc(gfp, node, root, node->shift - RADIX_TREE_MAP_SHIFT, offset, 0, 0); if (!child) goto nomem; if (node != parent) { node->count++; rcu_assign_pointer(node->slots[offset], node_to_entry(child)); for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) if (tags & (1 << tag)) tag_set(node, tag, offset); } node = child; offset = 0; continue; } n = insert_entries(node, &node->slots[offset], RADIX_TREE_RETRY, order, false); BUG_ON(n > RADIX_TREE_MAP_SIZE); for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) if (tags & (1 << tag)) tag_set(node, tag, offset); offset += n; while (offset == RADIX_TREE_MAP_SIZE) { if (node == parent) break; offset = node->offset; child = node; node = node->parent; rcu_assign_pointer(node->slots[offset], node_to_entry(child)); offset++; } if ((node == parent) && (offset == end)) return 0; } nomem: /* Shouldn't happen; did user forget to preload? */ /* TODO: free all the allocated nodes */ WARN_ON(1); return -ENOMEM; } #endif static void node_tag_set(struct radix_tree_root *root, struct radix_tree_node *node, unsigned int tag, unsigned int offset) { while (node) { if (tag_get(node, tag, offset)) return; tag_set(node, tag, offset); offset = node->offset; node = node->parent; } if (!root_tag_get(root, tag)) root_tag_set(root, tag); } /** * radix_tree_tag_set - set a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index * * Set the search tag (which must be < RADIX_TREE_MAX_TAGS) * corresponding to @index in the radix tree. From * the root all the way down to the leaf node. * * Returns the address of the tagged item. Setting a tag on a not-present * item is a bug. */ void *radix_tree_tag_set(struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; radix_tree_load_root(root, &node, &maxindex); BUG_ON(index > maxindex); while (radix_tree_is_internal_node(node)) { unsigned offset; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); BUG_ON(!node); if (!tag_get(parent, tag, offset)) tag_set(parent, tag, offset); } /* set the root's tag bit */ if (!root_tag_get(root, tag)) root_tag_set(root, tag); return node; } EXPORT_SYMBOL(radix_tree_tag_set); /** * radix_tree_iter_tag_set - set a tag on the current iterator entry * @root: radix tree root * @iter: iterator state * @tag: tag to set */ void radix_tree_iter_tag_set(struct radix_tree_root *root, const struct radix_tree_iter *iter, unsigned int tag) { node_tag_set(root, iter->node, tag, iter_offset(iter)); } static void node_tag_clear(struct radix_tree_root *root, struct radix_tree_node *node, unsigned int tag, unsigned int offset) { while (node) { if (!tag_get(node, tag, offset)) return; tag_clear(node, tag, offset); if (any_tag_set(node, tag)) return; offset = node->offset; node = node->parent; } /* clear the root's tag bit */ if (root_tag_get(root, tag)) root_tag_clear(root, tag); } /** * radix_tree_tag_clear - clear a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index * * Clear the search tag (which must be < RADIX_TREE_MAX_TAGS) * corresponding to @index in the radix tree. If this causes * the leaf node to have no tags set then clear the tag in the * next-to-leaf node, etc. * * Returns the address of the tagged item on success, else NULL. ie: * has the same return value and semantics as radix_tree_lookup(). */ void *radix_tree_tag_clear(struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; int uninitialized_var(offset); radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return NULL; parent = NULL; while (radix_tree_is_internal_node(node)) { parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); } if (node) node_tag_clear(root, parent, tag, offset); return node; } EXPORT_SYMBOL(radix_tree_tag_clear); /** * radix_tree_iter_tag_clear - clear a tag on the current iterator entry * @root: radix tree root * @iter: iterator state * @tag: tag to clear */ void radix_tree_iter_tag_clear(struct radix_tree_root *root, const struct radix_tree_iter *iter, unsigned int tag) { node_tag_clear(root, iter->node, tag, iter_offset(iter)); } /** * radix_tree_tag_get - get a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index (< RADIX_TREE_MAX_TAGS) * * Return values: * * 0: tag not present or not set * 1: tag set * * Note that the return value of this function may not be relied on, even if * the RCU lock is held, unless tag modification and node deletion are excluded * from concurrency. */ int radix_tree_tag_get(const struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; if (!root_tag_get(root, tag)) return 0; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return 0; while (radix_tree_is_internal_node(node)) { unsigned offset; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); if (!tag_get(parent, tag, offset)) return 0; if (node == RADIX_TREE_RETRY) break; } return 1; } EXPORT_SYMBOL(radix_tree_tag_get); static inline void __set_iter_shift(struct radix_tree_iter *iter, unsigned int shift) { #ifdef CONFIG_RADIX_TREE_MULTIORDER iter->shift = shift; #endif } /* Construct iter->tags bit-mask from node->tags[tag] array */ static void set_iter_tags(struct radix_tree_iter *iter, struct radix_tree_node *node, unsigned offset, unsigned tag) { unsigned tag_long = offset / BITS_PER_LONG; unsigned tag_bit = offset % BITS_PER_LONG; if (!node) { iter->tags = 1; return; } iter->tags = node->tags[tag][tag_long] >> tag_bit; /* This never happens if RADIX_TREE_TAG_LONGS == 1 */ if (tag_long < RADIX_TREE_TAG_LONGS - 1) { /* Pick tags from next element */ if (tag_bit) iter->tags |= node->tags[tag][tag_long + 1] << (BITS_PER_LONG - tag_bit); /* Clip chunk size, here only BITS_PER_LONG tags */ iter->next_index = __radix_tree_iter_add(iter, BITS_PER_LONG); } } #ifdef CONFIG_RADIX_TREE_MULTIORDER static void __rcu **skip_siblings(struct radix_tree_node **nodep, void __rcu **slot, struct radix_tree_iter *iter) { while (iter->index < iter->next_index) { *nodep = rcu_dereference_raw(*slot); if (*nodep && !is_sibling_entry(iter->node, *nodep)) return slot; slot++; iter->index = __radix_tree_iter_add(iter, 1); iter->tags >>= 1; } *nodep = NULL; return NULL; } void __rcu **__radix_tree_next_slot(void __rcu **slot, struct radix_tree_iter *iter, unsigned flags) { unsigned tag = flags & RADIX_TREE_ITER_TAG_MASK; struct radix_tree_node *node; slot = skip_siblings(&node, slot, iter); while (radix_tree_is_internal_node(node)) { unsigned offset; unsigned long next_index; if (node == RADIX_TREE_RETRY) return slot; node = entry_to_node(node); iter->node = node; iter->shift = node->shift; if (flags & RADIX_TREE_ITER_TAGGED) { offset = radix_tree_find_next_bit(node, tag, 0); if (offset == RADIX_TREE_MAP_SIZE) return NULL; slot = &node->slots[offset]; iter->index = __radix_tree_iter_add(iter, offset); set_iter_tags(iter, node, offset, tag); node = rcu_dereference_raw(*slot); } else { offset = 0; slot = &node->slots[0]; for (;;) { node = rcu_dereference_raw(*slot); if (node) break; slot++; offset++; if (offset == RADIX_TREE_MAP_SIZE) return NULL; } iter->index = __radix_tree_iter_add(iter, offset); } if ((flags & RADIX_TREE_ITER_CONTIG) && (offset > 0)) goto none; next_index = (iter->index | shift_maxindex(iter->shift)) + 1; if (next_index < iter->next_index) iter->next_index = next_index; } return slot; none: iter->next_index = 0; return NULL; } EXPORT_SYMBOL(__radix_tree_next_slot); #else static void __rcu **skip_siblings(struct radix_tree_node **nodep, void __rcu **slot, struct radix_tree_iter *iter) { return slot; } #endif void __rcu **radix_tree_iter_resume(void __rcu **slot, struct radix_tree_iter *iter) { struct radix_tree_node *node; slot++; iter->index = __radix_tree_iter_add(iter, 1); skip_siblings(&node, slot, iter); iter->next_index = iter->index; iter->tags = 0; return NULL; } EXPORT_SYMBOL(radix_tree_iter_resume); /** * radix_tree_next_chunk - find next chunk of slots for iteration * * @root: radix tree root * @iter: iterator state * @flags: RADIX_TREE_ITER_* flags and tag index * Returns: pointer to chunk first slot, or NULL if iteration is over */ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root, struct radix_tree_iter *iter, unsigned flags) { unsigned tag = flags & RADIX_TREE_ITER_TAG_MASK; struct radix_tree_node *node, *child; unsigned long index, offset, maxindex; if ((flags & RADIX_TREE_ITER_TAGGED) && !root_tag_get(root, tag)) return NULL; /* * Catch next_index overflow after ~0UL. iter->index never overflows * during iterating; it can be zero only at the beginning. * And we cannot overflow iter->next_index in a single step, * because RADIX_TREE_MAP_SHIFT < BITS_PER_LONG. * * This condition also used by radix_tree_next_slot() to stop * contiguous iterating, and forbid switching to the next chunk. */ index = iter->next_index; if (!index && iter->index) return NULL; restart: radix_tree_load_root(root, &child, &maxindex); if (index > maxindex) return NULL; if (!child) return NULL; if (!radix_tree_is_internal_node(child)) { /* Single-slot tree */ iter->index = index; iter->next_index = maxindex + 1; iter->tags = 1; iter->node = NULL; __set_iter_shift(iter, 0); return (void __rcu **)&root->rnode; } do { node = entry_to_node(child); offset = radix_tree_descend(node, &child, index); if ((flags & RADIX_TREE_ITER_TAGGED) ? !tag_get(node, tag, offset) : !child) { /* Hole detected */ if (flags & RADIX_TREE_ITER_CONTIG) return NULL; if (flags & RADIX_TREE_ITER_TAGGED) offset = radix_tree_find_next_bit(node, tag, offset + 1); else while (++offset < RADIX_TREE_MAP_SIZE) { void *slot = rcu_dereference_raw( node->slots[offset]); if (is_sibling_entry(node, slot)) continue; if (slot) break; } index &= ~node_maxindex(node); index += offset << node->shift; /* Overflow after ~0UL */ if (!index) return NULL; if (offset == RADIX_TREE_MAP_SIZE) goto restart; child = rcu_dereference_raw(node->slots[offset]); } if (!child) goto restart; if (child == RADIX_TREE_RETRY) break; } while (radix_tree_is_internal_node(child)); /* Update the iterator state */ iter->index = (index &~ node_maxindex(node)) | (offset << node->shift); iter->next_index = (index | node_maxindex(node)) + 1; iter->node = node; __set_iter_shift(iter, node->shift); if (flags & RADIX_TREE_ITER_TAGGED) set_iter_tags(iter, node, offset, tag); return node->slots + offset; } EXPORT_SYMBOL(radix_tree_next_chunk); /** * radix_tree_gang_lookup - perform multiple lookup on a radix tree * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * * Performs an index-ascending scan of the tree for present items. Places * them at *@results and returns the number of items which were placed at * *@results. * * The implementation is naive. * * Like radix_tree_lookup, radix_tree_gang_lookup may be called under * rcu_read_lock. In this case, rather than the returned results being * an atomic snapshot of the tree at a single point in time, the * semantics of an RCU protected gang lookup are as though multiple * radix_tree_lookups have been issued in individual locks, and results * stored in 'results'. */ unsigned int radix_tree_gang_lookup(const struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_slot(slot, root, &iter, first_index) { results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; if (radix_tree_is_internal_node(results[ret])) { slot = radix_tree_iter_retry(&iter); continue; } if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup); /** * radix_tree_gang_lookup_slot - perform multiple slot lookup on radix tree * @root: radix tree root * @results: where the results of the lookup are placed * @indices: where their indices should be placed (but usually NULL) * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * * Performs an index-ascending scan of the tree for present items. Places * their slots at *@results and returns the number of items which were * placed at *@results. * * The implementation is naive. * * Like radix_tree_gang_lookup as far as RCU and locking goes. Slots must * be dereferenced with radix_tree_deref_slot, and if using only RCU * protection, radix_tree_deref_slot may fail requiring a retry. */ unsigned int radix_tree_gang_lookup_slot(const struct radix_tree_root *root, void __rcu ***results, unsigned long *indices, unsigned long first_index, unsigned int max_items) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_slot(slot, root, &iter, first_index) { results[ret] = slot; if (indices) indices[ret] = iter.index; if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup_slot); /** * radix_tree_gang_lookup_tag - perform multiple lookup on a radix tree * based on a tag * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * @tag: the tag index (< RADIX_TREE_MAX_TAGS) * * Performs an index-ascending scan of the tree for present items which * have the tag indexed by @tag set. Places the items at *@results and * returns the number of items which were placed at *@results. */ unsigned int radix_tree_gang_lookup_tag(const struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items, unsigned int tag) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) { results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; if (radix_tree_is_internal_node(results[ret])) { slot = radix_tree_iter_retry(&iter); continue; } if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup_tag); /** * radix_tree_gang_lookup_tag_slot - perform multiple slot lookup on a * radix tree based on a tag * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * @tag: the tag index (< RADIX_TREE_MAX_TAGS) * * Performs an index-ascending scan of the tree for present items which * have the tag indexed by @tag set. Places the slots at *@results and * returns the number of slots which were placed at *@results. */ unsigned int radix_tree_gang_lookup_tag_slot(const struct radix_tree_root *root, void __rcu ***results, unsigned long first_index, unsigned int max_items, unsigned int tag) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) { results[ret] = slot; if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup_tag_slot); /** * __radix_tree_delete_node - try to free node after clearing a slot * @root: radix tree root * @node: node containing @index * @update_node: callback for changing leaf nodes * @private: private data to pass to @update_node * * After clearing the slot at @index in @node from radix tree * rooted at @root, call this function to attempt freeing the * node and shrinking the tree. */ void __radix_tree_delete_node(struct radix_tree_root *root, struct radix_tree_node *node, radix_tree_update_node_t update_node, void *private) { delete_node(root, node, update_node, private); } static bool __radix_tree_delete(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot) { void *old = rcu_dereference_raw(*slot); int exceptional = radix_tree_exceptional_entry(old) ? -1 : 0; unsigned offset = get_slot_offset(node, slot); int tag; if (is_idr(root)) node_tag_set(root, node, IDR_FREE, offset); else for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) node_tag_clear(root, node, tag, offset); replace_slot(slot, NULL, node, -1, exceptional); return node && delete_node(root, node, NULL, NULL); } /** * radix_tree_iter_delete - delete the entry at this iterator position * @root: radix tree root * @iter: iterator state * @slot: pointer to slot * * Delete the entry at the position currently pointed to by the iterator. * This may result in the current node being freed; if it is, the iterator * is advanced so that it will not reference the freed memory. This * function may be called without any locking if there are no other threads * which can access this tree. */ void radix_tree_iter_delete(struct radix_tree_root *root, struct radix_tree_iter *iter, void __rcu **slot) { if (__radix_tree_delete(root, iter->node, slot)) iter->index = iter->next_index; } EXPORT_SYMBOL(radix_tree_iter_delete); /** * radix_tree_delete_item - delete an item from a radix tree * @root: radix tree root * @index: index key * @item: expected item * * Remove @item at @index from the radix tree rooted at @root. * * Return: the deleted entry, or %NULL if it was not present * or the entry at the given @index was not @item. */ void *radix_tree_delete_item(struct radix_tree_root *root, unsigned long index, void *item) { struct radix_tree_node *node = NULL; void __rcu **slot = NULL; void *entry; entry = __radix_tree_lookup(root, index, &node, &slot); if (!slot) return NULL; if (!entry && (!is_idr(root) || node_tag_get(root, node, IDR_FREE, get_slot_offset(node, slot)))) return NULL; if (item && entry != item) return NULL; __radix_tree_delete(root, node, slot); return entry; } EXPORT_SYMBOL(radix_tree_delete_item); /** * radix_tree_delete - delete an entry from a radix tree * @root: radix tree root * @index: index key * * Remove the entry at @index from the radix tree rooted at @root. * * Return: The deleted entry, or %NULL if it was not present. */ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index) { return radix_tree_delete_item(root, index, NULL); } EXPORT_SYMBOL(radix_tree_delete); void radix_tree_clear_tags(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot) { if (node) { unsigned int tag, offset = get_slot_offset(node, slot); for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) node_tag_clear(root, node, tag, offset); } else { root_tag_clear_all(root); } } /** * radix_tree_tagged - test whether any items in the tree are tagged * @root: radix tree root * @tag: tag to test */ int radix_tree_tagged(const struct radix_tree_root *root, unsigned int tag) { return root_tag_get(root, tag); } EXPORT_SYMBOL(radix_tree_tagged); /** * idr_preload - preload for idr_alloc() * @gfp_mask: allocation mask to use for preloading * * Preallocate memory to use for the next call to idr_alloc(). This function * returns with preemption disabled. It will be enabled by idr_preload_end(). */ void idr_preload(gfp_t gfp_mask) { if (__radix_tree_preload(gfp_mask, IDR_PRELOAD_SIZE)) preempt_disable(); } EXPORT_SYMBOL(idr_preload); /** * ida_pre_get - reserve resources for ida allocation * @ida: ida handle * @gfp: memory allocation flags * * This function should be called before calling ida_get_new_above(). If it * is unable to allocate memory, it will return %0. On success, it returns %1. */ int ida_pre_get(struct ida *ida, gfp_t gfp) { /* * The IDA API has no preload_end() equivalent. Instead, * ida_get_new() can return -EAGAIN, prompting the caller * to return to the ida_pre_get() step. */ if (!__radix_tree_preload(gfp, IDA_PRELOAD_SIZE)) preempt_enable(); if (!this_cpu_read(ida_bitmap)) { struct ida_bitmap *bitmap = kmalloc(sizeof(*bitmap), gfp); if (!bitmap) return 0; if (this_cpu_cmpxchg(ida_bitmap, NULL, bitmap)) kfree(bitmap); } return 1; } EXPORT_SYMBOL(ida_pre_get); void __rcu **idr_get_free_cmn(struct radix_tree_root *root, struct radix_tree_iter *iter, gfp_t gfp, unsigned long max) { struct radix_tree_node *node = NULL, *child; void __rcu **slot = (void __rcu **)&root->rnode; unsigned long maxindex, start = iter->next_index; unsigned int shift, offset = 0; grow: shift = radix_tree_load_root(root, &child, &maxindex); if (!radix_tree_tagged(root, IDR_FREE)) start = max(start, maxindex + 1); if (start > max) return ERR_PTR(-ENOSPC); if (start > maxindex) { int error = radix_tree_extend(root, gfp, start, shift); if (error < 0) return ERR_PTR(error); shift = error; child = rcu_dereference_raw(root->rnode); } while (shift) { shift -= RADIX_TREE_MAP_SHIFT; if (child == NULL) { /* Have to add a child node. */ child = radix_tree_node_alloc(gfp, node, root, shift, offset, 0, 0); if (!child) return ERR_PTR(-ENOMEM); all_tag_set(child, IDR_FREE); rcu_assign_pointer(*slot, node_to_entry(child)); if (node) node->count++; } else if (!radix_tree_is_internal_node(child)) break; node = entry_to_node(child); offset = radix_tree_descend(node, &child, start); if (!tag_get(node, IDR_FREE, offset)) { offset = radix_tree_find_next_bit(node, IDR_FREE, offset + 1); start = next_index(start, node, offset); if (start > max || start == 0) return ERR_PTR(-ENOSPC); while (offset == RADIX_TREE_MAP_SIZE) { offset = node->offset + 1; node = node->parent; if (!node) goto grow; shift = node->shift; } child = rcu_dereference_raw(node->slots[offset]); } slot = &node->slots[offset]; } iter->index = start; if (node) iter->next_index = 1 + min(max, (start | node_maxindex(node))); else iter->next_index = 1; iter->node = node; __set_iter_shift(iter, shift); set_iter_tags(iter, node, offset, IDR_FREE); return slot; } /** * idr_destroy - release all internal memory from an IDR * @idr: idr handle * * After this function is called, the IDR is empty, and may be reused or * the data structure containing it may be freed. * * A typical clean-up sequence for objects stored in an idr tree will use * idr_for_each() to free all objects, if necessary, then idr_destroy() to * free the memory used to keep track of those objects. */ void idr_destroy(struct idr *idr) { struct radix_tree_node *node = rcu_dereference_raw(idr->idr_rt.rnode); if (radix_tree_is_internal_node(node)) radix_tree_free_nodes(node); idr->idr_rt.rnode = NULL; root_tag_set(&idr->idr_rt, IDR_FREE); } EXPORT_SYMBOL(idr_destroy); static void radix_tree_node_ctor(void *arg) { struct radix_tree_node *node = arg; memset(node, 0, sizeof(*node)); INIT_LIST_HEAD(&node->private_list); } static __init unsigned long __maxindex(unsigned int height) { unsigned int width = height * RADIX_TREE_MAP_SHIFT; int shift = RADIX_TREE_INDEX_BITS - width; if (shift < 0) return ~0UL; if (shift >= BITS_PER_LONG) return 0UL; return ~0UL >> shift; } static __init void radix_tree_init_maxnodes(void) { unsigned long height_to_maxindex[RADIX_TREE_MAX_PATH + 1]; unsigned int i, j; for (i = 0; i < ARRAY_SIZE(height_to_maxindex); i++) height_to_maxindex[i] = __maxindex(i); for (i = 0; i < ARRAY_SIZE(height_to_maxnodes); i++) { for (j = i; j > 0; j--) height_to_maxnodes[i] += height_to_maxindex[j - 1] + 1; } } static int radix_tree_cpu_dead(unsigned int cpu) { struct radix_tree_preload *rtp; struct radix_tree_node *node; /* Free per-cpu pool of preloaded nodes */ rtp = &per_cpu(radix_tree_preloads, cpu); while (rtp->nr) { node = rtp->nodes; rtp->nodes = node->parent; kmem_cache_free(radix_tree_node_cachep, node); rtp->nr--; } kfree(per_cpu(ida_bitmap, cpu)); per_cpu(ida_bitmap, cpu) = NULL; return 0; } void __init radix_tree_init(void) { int ret; BUILD_BUG_ON(RADIX_TREE_MAX_TAGS + __GFP_BITS_SHIFT > 32); radix_tree_node_cachep = kmem_cache_create("radix_tree_node", sizeof(struct radix_tree_node), 0, SLAB_PANIC | SLAB_RECLAIM_ACCOUNT, radix_tree_node_ctor); radix_tree_init_maxnodes(); ret = cpuhp_setup_state_nocalls(CPUHP_RADIX_DEAD, "lib/radix:dead", NULL, radix_tree_cpu_dead); WARN_ON(ret < 0); } |
| 12 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 | /* * UDPLITEv6 An implementation of the UDP-Lite protocol over IPv6. * See also net/ipv4/udplite.c * * Authors: Gerrit Renker <gerrit@erg.abdn.ac.uk> * * Changes: * Fixes: * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ #include <linux/export.h> #include "udp_impl.h" static int udplitev6_rcv(struct sk_buff *skb) { return __udp6_lib_rcv(skb, &udplite_table, IPPROTO_UDPLITE); } static void udplitev6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { __udp6_lib_err(skb, opt, type, code, offset, info, &udplite_table); } static const struct inet6_protocol udplitev6_protocol = { .handler = udplitev6_rcv, .err_handler = udplitev6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; struct proto udplitev6_prot = { .name = "UDPLITEv6", .owner = THIS_MODULE, .close = udp_lib_close, .connect = ip6_datagram_connect, .disconnect = udp_disconnect, .ioctl = udp_ioctl, .init = udplite_sk_init, .destroy = udpv6_destroy_sock, .setsockopt = udpv6_setsockopt, .getsockopt = udpv6_getsockopt, .sendmsg = udpv6_sendmsg, .recvmsg = udpv6_recvmsg, .hash = udp_lib_hash, .unhash = udp_lib_unhash, .get_port = udp_v6_get_port, .memory_allocated = &udp_memory_allocated, .sysctl_mem = sysctl_udp_mem, .obj_size = sizeof(struct udp6_sock), .h.udp_table = &udplite_table, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_udpv6_setsockopt, .compat_getsockopt = compat_udpv6_getsockopt, #endif }; static struct inet_protosw udplite6_protosw = { .type = SOCK_DGRAM, .protocol = IPPROTO_UDPLITE, .prot = &udplitev6_prot, .ops = &inet6_dgram_ops, .flags = INET_PROTOSW_PERMANENT, }; int __init udplitev6_init(void) { int ret; ret = inet6_add_protocol(&udplitev6_protocol, IPPROTO_UDPLITE); if (ret) goto out; ret = inet6_register_protosw(&udplite6_protosw); if (ret) goto out_udplitev6_protocol; out: return ret; out_udplitev6_protocol: inet6_del_protocol(&udplitev6_protocol, IPPROTO_UDPLITE); goto out; } void udplitev6_exit(void) { inet6_unregister_protosw(&udplite6_protosw); inet6_del_protocol(&udplitev6_protocol, IPPROTO_UDPLITE); } #ifdef CONFIG_PROC_FS static const struct file_operations udplite6_afinfo_seq_fops = { .owner = THIS_MODULE, .open = udp_seq_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release_net }; static struct udp_seq_afinfo udplite6_seq_afinfo = { .name = "udplite6", .family = AF_INET6, .udp_table = &udplite_table, .seq_fops = &udplite6_afinfo_seq_fops, .seq_ops = { .show = udp6_seq_show, }, }; static int __net_init udplite6_proc_init_net(struct net *net) { return udp_proc_register(net, &udplite6_seq_afinfo); } static void __net_exit udplite6_proc_exit_net(struct net *net) { udp_proc_unregister(net, &udplite6_seq_afinfo); } static struct pernet_operations udplite6_net_ops = { .init = udplite6_proc_init_net, .exit = udplite6_proc_exit_net, }; int __init udplite6_proc_init(void) { return register_pernet_subsys(&udplite6_net_ops); } void udplite6_proc_exit(void) { unregister_pernet_subsys(&udplite6_net_ops); } #endif |
| 17036 11544 17050 4859 2176 11552 11553 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 | // SPDX-License-Identifier: GPL-2.0 #include <linux/slab.h> #include <linux/kernel.h> #include <linux/bitops.h> #include <linux/cpumask.h> #include <linux/export.h> #include <linux/bootmem.h> /** * cpumask_next - get the next cpu in a cpumask * @n: the cpu prior to the place to search (ie. return will be > @n) * @srcp: the cpumask pointer * * Returns >= nr_cpu_ids if no further cpus set. */ unsigned int cpumask_next(int n, const struct cpumask *srcp) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n + 1); } EXPORT_SYMBOL(cpumask_next); /** * cpumask_next_and - get the next cpu in *src1p & *src2p * @n: the cpu prior to the place to search (ie. return will be > @n) * @src1p: the first cpumask pointer * @src2p: the second cpumask pointer * * Returns >= nr_cpu_ids if no further cpus set in both. */ int cpumask_next_and(int n, const struct cpumask *src1p, const struct cpumask *src2p) { while ((n = cpumask_next(n, src1p)) < nr_cpu_ids) if (cpumask_test_cpu(n, src2p)) break; return n; } EXPORT_SYMBOL(cpumask_next_and); /** * cpumask_any_but - return a "random" in a cpumask, but not this one. * @mask: the cpumask to search * @cpu: the cpu to ignore. * * Often used to find any cpu but smp_processor_id() in a mask. * Returns >= nr_cpu_ids if no cpus set. */ int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) { unsigned int i; cpumask_check(cpu); for_each_cpu(i, mask) if (i != cpu) break; return i; } EXPORT_SYMBOL(cpumask_any_but); /** * cpumask_next_wrap - helper to implement for_each_cpu_wrap * @n: the cpu prior to the place to search * @mask: the cpumask pointer * @start: the start point of the iteration * @wrap: assume @n crossing @start terminates the iteration * * Returns >= nr_cpu_ids on completion * * Note: the @wrap argument is required for the start condition when * we cannot assume @start is set in @mask. */ int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap) { int next; again: next = cpumask_next(n, mask); if (wrap && n < start && next >= start) { return nr_cpumask_bits; } else if (next >= nr_cpumask_bits) { wrap = true; n = -1; goto again; } return next; } EXPORT_SYMBOL(cpumask_next_wrap); /* These are not inline because of header tangles. */ #ifdef CONFIG_CPUMASK_OFFSTACK /** * alloc_cpumask_var_node - allocate a struct cpumask on a given node * @mask: pointer to cpumask_var_t where the cpumask is returned * @flags: GFP_ flags * * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is * a nop returning a constant 1 (in <linux/cpumask.h>) * Returns TRUE if memory allocation succeeded, FALSE otherwise. * * In addition, mask will be NULL if this fails. Note that gcc is * usually smart enough to know that mask can never be NULL if * CONFIG_CPUMASK_OFFSTACK=n, so does code elimination in that case * too. */ bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { *mask = kmalloc_node(cpumask_size(), flags, node); #ifdef CONFIG_DEBUG_PER_CPU_MAPS if (!*mask) { printk(KERN_ERR "=> alloc_cpumask_var: failed!\n"); dump_stack(); } #endif return *mask != NULL; } EXPORT_SYMBOL(alloc_cpumask_var_node); bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node); } EXPORT_SYMBOL(zalloc_cpumask_var_node); /** * alloc_cpumask_var - allocate a struct cpumask * @mask: pointer to cpumask_var_t where the cpumask is returned * @flags: GFP_ flags * * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is * a nop returning a constant 1 (in <linux/cpumask.h>). * * See alloc_cpumask_var_node. */ bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE); } EXPORT_SYMBOL(alloc_cpumask_var); bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return alloc_cpumask_var(mask, flags | __GFP_ZERO); } EXPORT_SYMBOL(zalloc_cpumask_var); /** * alloc_bootmem_cpumask_var - allocate a struct cpumask from the bootmem arena. * @mask: pointer to cpumask_var_t where the cpumask is returned * * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is * a nop (in <linux/cpumask.h>). * Either returns an allocated (zero-filled) cpumask, or causes the * system to panic. */ void __init alloc_bootmem_cpumask_var(cpumask_var_t *mask) { *mask = memblock_virt_alloc(cpumask_size(), 0); } /** * free_cpumask_var - frees memory allocated for a struct cpumask. * @mask: cpumask to free * * This is safe on a NULL mask. */ void free_cpumask_var(cpumask_var_t mask) { kfree(mask); } EXPORT_SYMBOL(free_cpumask_var); /** * free_bootmem_cpumask_var - frees result of alloc_bootmem_cpumask_var * @mask: cpumask to free */ void __init free_bootmem_cpumask_var(cpumask_var_t mask) { memblock_free_early(__pa(mask), cpumask_size()); } #endif /** * cpumask_local_spread - select the i'th cpu with local numa cpu's first * @i: index number * @node: local numa_node * * This function selects an online CPU according to a numa aware policy; * local cpus are returned first, followed by non-local ones, then it * wraps around. * * It's not very efficient, but useful for setup. */ unsigned int cpumask_local_spread(unsigned int i, int node) { int cpu; /* Wrap: we always want a cpu. */ i %= num_online_cpus(); if (node == -1) { for_each_cpu(cpu, cpu_online_mask) if (i-- == 0) return cpu; } else { /* NUMA first. */ for_each_cpu_and(cpu, cpumask_of_node(node), cpu_online_mask) if (i-- == 0) return cpu; for_each_cpu(cpu, cpu_online_mask) { /* Skip NUMA nodes, done above. */ if (cpumask_test_cpu(cpu, cpumask_of_node(node))) continue; if (i-- == 0) return cpu; } } BUG(); } EXPORT_SYMBOL(cpumask_local_spread); |
| 129 129 125 73 68 73 129 125 125 124 125 129 129 129 129 129 4 1 1 3 3 129 3 129 129 56 56 55 128 129 63 64 64 64 62 3 2 2 3 4 64 64 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 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 | /* * linux/fs/hfs/bitmap.c * * Copyright (C) 1996-1997 Paul H. Hargrove * (C) 2003 Ardis Technologies <roman@ardistech.com> * This file may be distributed under the terms of the GNU General Public License. * * Based on GPLed code Copyright (C) 1995 Michael Dreher * * This file contains the code to modify the volume bitmap: * search/set/clear bits. */ #include "hfs_fs.h" /* * hfs_find_zero_bit() * * Description: * Given a block of memory, its length in bits, and a starting bit number, * determine the number of the first zero bits (in left-to-right ordering) * in that range. * * Returns >= 'size' if no zero bits are found in the range. * * Accesses memory in 32-bit aligned chunks of 32-bits and thus * may read beyond the 'size'th bit. */ static u32 hfs_find_set_zero_bits(__be32 *bitmap, u32 size, u32 offset, u32 *max) { __be32 *curr, *end; u32 mask, start, len, n; __be32 val; int i; len = *max; if (!len) return size; curr = bitmap + (offset / 32); end = bitmap + ((size + 31) / 32); /* scan the first partial u32 for zero bits */ val = *curr; if (~val) { n = be32_to_cpu(val); i = offset % 32; mask = (1U << 31) >> i; for (; i < 32; mask >>= 1, i++) { if (!(n & mask)) goto found; } } /* scan complete u32s for the first zero bit */ while (++curr < end) { val = *curr; if (~val) { n = be32_to_cpu(val); mask = 1 << 31; for (i = 0; i < 32; mask >>= 1, i++) { if (!(n & mask)) goto found; } } } return size; found: start = (curr - bitmap) * 32 + i; if (start >= size) return start; /* do any partial u32 at the start */ len = min(size - start, len); while (1) { n |= mask; if (++i >= 32) break; mask >>= 1; if (!--len || n & mask) goto done; } if (!--len) goto done; *curr++ = cpu_to_be32(n); /* do full u32s */ while (1) { n = be32_to_cpu(*curr); if (len < 32) break; if (n) { len = 32; break; } *curr++ = cpu_to_be32(0xffffffff); len -= 32; } /* do any partial u32 at end */ mask = 1U << 31; for (i = 0; i < len; i++) { if (n & mask) break; n |= mask; mask >>= 1; } done: *curr = cpu_to_be32(n); *max = (curr - bitmap) * 32 + i - start; return start; } /* * hfs_vbm_search_free() * * Description: * Search for 'num_bits' consecutive cleared bits in the bitmap blocks of * the hfs MDB. 'mdb' had better be locked or the returned range * may be no longer free, when this functions returns! * XXX Currently the search starts from bit 0, but it should start with * the bit number stored in 's_alloc_ptr' of the MDB. * Input Variable(s): * struct hfs_mdb *mdb: Pointer to the hfs MDB * u16 *num_bits: Pointer to the number of cleared bits * to search for * Output Variable(s): * u16 *num_bits: The number of consecutive clear bits of the * returned range. If the bitmap is fragmented, this will be less than * requested and it will be zero, when the disk is full. * Returns: * The number of the first bit of the range of cleared bits which has been * found. When 'num_bits' is zero, this is invalid! * Preconditions: * 'mdb' points to a "valid" (struct hfs_mdb). * 'num_bits' points to a variable of type (u16), which contains * the number of cleared bits to find. * Postconditions: * 'num_bits' is set to the length of the found sequence. */ u32 hfs_vbm_search_free(struct super_block *sb, u32 goal, u32 *num_bits) { void *bitmap; u32 pos; /* make sure we have actual work to perform */ if (!*num_bits) return 0; mutex_lock(&HFS_SB(sb)->bitmap_lock); bitmap = HFS_SB(sb)->bitmap; pos = hfs_find_set_zero_bits(bitmap, HFS_SB(sb)->fs_ablocks, goal, num_bits); if (pos >= HFS_SB(sb)->fs_ablocks) { if (goal) pos = hfs_find_set_zero_bits(bitmap, goal, 0, num_bits); if (pos >= HFS_SB(sb)->fs_ablocks) { *num_bits = pos = 0; goto out; } } hfs_dbg(BITMAP, "alloc_bits: %u,%u\n", pos, *num_bits); HFS_SB(sb)->free_ablocks -= *num_bits; hfs_bitmap_dirty(sb); out: mutex_unlock(&HFS_SB(sb)->bitmap_lock); return pos; } /* * hfs_clear_vbm_bits() * * Description: * Clear the requested bits in the volume bitmap of the hfs filesystem * Input Variable(s): * struct hfs_mdb *mdb: Pointer to the hfs MDB * u16 start: The offset of the first bit * u16 count: The number of bits * Output Variable(s): * None * Returns: * 0: no error * -1: One of the bits was already clear. This is a strange * error and when it happens, the filesystem must be repaired! * -2: One or more of the bits are out of range of the bitmap. * Preconditions: * 'mdb' points to a "valid" (struct hfs_mdb). * Postconditions: * Starting with bit number 'start', 'count' bits in the volume bitmap * are cleared. The affected bitmap blocks are marked "dirty", the free * block count of the MDB is updated and the MDB is marked dirty. */ int hfs_clear_vbm_bits(struct super_block *sb, u16 start, u16 count) { __be32 *curr; u32 mask; int i, len; /* is there any actual work to be done? */ if (!count) return 0; hfs_dbg(BITMAP, "clear_bits: %u,%u\n", start, count); /* are all of the bits in range? */ if ((start + count) > HFS_SB(sb)->fs_ablocks) return -2; mutex_lock(&HFS_SB(sb)->bitmap_lock); /* bitmap is always on a 32-bit boundary */ curr = HFS_SB(sb)->bitmap + (start / 32); len = count; /* do any partial u32 at the start */ i = start % 32; if (i) { int j = 32 - i; mask = 0xffffffffU << j; if (j > count) { mask |= 0xffffffffU >> (i + count); *curr &= cpu_to_be32(mask); goto out; } *curr++ &= cpu_to_be32(mask); count -= j; } /* do full u32s */ while (count >= 32) { *curr++ = 0; count -= 32; } /* do any partial u32 at end */ if (count) { mask = 0xffffffffU >> count; *curr &= cpu_to_be32(mask); } out: HFS_SB(sb)->free_ablocks += len; mutex_unlock(&HFS_SB(sb)->bitmap_lock); hfs_bitmap_dirty(sb); return 0; } |
| 36 35 36 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 | /* * llc_output.c - LLC minimal output path * * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> * * This program can be redistributed or modified under the terms of the * GNU General Public License version 2 as published by the Free Software * Foundation. * This program is distributed without any warranty or implied warranty * of merchantability or fitness for a particular purpose. * * See the GNU General Public License version 2 for more details. */ #include <linux/if_arp.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/export.h> #include <net/llc.h> #include <net/llc_pdu.h> /** * llc_mac_hdr_init - fills MAC header fields * @skb: Address of the frame to initialize its MAC header * @sa: The MAC source address * @da: The MAC destination address * * Fills MAC header fields, depending on MAC type. Returns 0, If MAC type * is a valid type and initialization completes correctly 1, otherwise. */ int llc_mac_hdr_init(struct sk_buff *skb, const unsigned char *sa, const unsigned char *da) { int rc = -EINVAL; switch (skb->dev->type) { case ARPHRD_ETHER: case ARPHRD_LOOPBACK: rc = dev_hard_header(skb, skb->dev, ETH_P_802_2, da, sa, skb->len); if (rc > 0) rc = 0; break; default: break; } return rc; } /** * llc_build_and_send_ui_pkt - unitdata request interface for upper layers * @sap: sap to use * @skb: packet to send * @dmac: destination mac address * @dsap: destination sap * * Upper layers calls this function when upper layer wants to send data * using connection-less mode communication (UI pdu). * * Accept data frame from network layer to be sent using connection- * less mode communication; timeout/retries handled by network layer; * package primitive as an event and send to SAP event handler */ int llc_build_and_send_ui_pkt(struct llc_sap *sap, struct sk_buff *skb, unsigned char *dmac, unsigned char dsap) { int rc; llc_pdu_header_init(skb, LLC_PDU_TYPE_U, sap->laddr.lsap, dsap, LLC_PDU_CMD); llc_pdu_init_as_ui_cmd(skb); rc = llc_mac_hdr_init(skb, skb->dev->dev_addr, dmac); if (likely(!rc)) rc = dev_queue_xmit(skb); else kfree_skb(skb); return rc; } EXPORT_SYMBOL(llc_mac_hdr_init); EXPORT_SYMBOL(llc_build_and_send_ui_pkt); |
| 6572 2911 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM pagemap #if !defined(_TRACE_PAGEMAP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PAGEMAP_H #include <linux/tracepoint.h> #include <linux/mm.h> #define PAGEMAP_MAPPED 0x0001u #define PAGEMAP_ANONYMOUS 0x0002u #define PAGEMAP_FILE 0x0004u #define PAGEMAP_SWAPCACHE 0x0008u #define PAGEMAP_SWAPBACKED 0x0010u #define PAGEMAP_MAPPEDDISK 0x0020u #define PAGEMAP_BUFFERS 0x0040u #define trace_pagemap_flags(page) ( \ (PageAnon(page) ? PAGEMAP_ANONYMOUS : PAGEMAP_FILE) | \ (page_mapped(page) ? PAGEMAP_MAPPED : 0) | \ (PageSwapCache(page) ? PAGEMAP_SWAPCACHE : 0) | \ (PageSwapBacked(page) ? PAGEMAP_SWAPBACKED : 0) | \ (PageMappedToDisk(page) ? PAGEMAP_MAPPEDDISK : 0) | \ (page_has_private(page) ? PAGEMAP_BUFFERS : 0) \ ) TRACE_EVENT(mm_lru_insertion, TP_PROTO( struct page *page, int lru ), TP_ARGS(page, lru), TP_STRUCT__entry( __field(struct page *, page ) __field(unsigned long, pfn ) __field(int, lru ) __field(unsigned long, flags ) ), TP_fast_assign( __entry->page = page; __entry->pfn = page_to_pfn(page); __entry->lru = lru; __entry->flags = trace_pagemap_flags(page); ), /* Flag format is based on page-types.c formatting for pagemap */ TP_printk("page=%p pfn=%lu lru=%d flags=%s%s%s%s%s%s", __entry->page, __entry->pfn, __entry->lru, __entry->flags & PAGEMAP_MAPPED ? "M" : " ", __entry->flags & PAGEMAP_ANONYMOUS ? "a" : "f", __entry->flags & PAGEMAP_SWAPCACHE ? "s" : " ", __entry->flags & PAGEMAP_SWAPBACKED ? "b" : " ", __entry->flags & PAGEMAP_MAPPEDDISK ? "d" : " ", __entry->flags & PAGEMAP_BUFFERS ? "B" : " ") ); TRACE_EVENT(mm_lru_activate, TP_PROTO(struct page *page), TP_ARGS(page), TP_STRUCT__entry( __field(struct page *, page ) __field(unsigned long, pfn ) ), TP_fast_assign( __entry->page = page; __entry->pfn = page_to_pfn(page); ), /* Flag format is based on page-types.c formatting for pagemap */ TP_printk("page=%p pfn=%lu", __entry->page, __entry->pfn) ); #endif /* _TRACE_PAGEMAP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 9 9 1 1 1 1 1 1 1 6 1 6 7 2 2 2 2 2 2 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 | /* * VMware VMCI Driver * * Copyright (C) 2012 VMware, Inc. All rights reserved. * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the * Free Software Foundation version 2 and no later version. * * This program is distributed in the hope that it will be useful, but * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY * or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License * for more details. */ #include <linux/vmw_vmci_defs.h> #include <linux/hash.h> #include <linux/types.h> #include <linux/rculist.h> #include <linux/completion.h> #include "vmci_resource.h" #include "vmci_driver.h" #define VMCI_RESOURCE_HASH_BITS 7 #define VMCI_RESOURCE_HASH_BUCKETS (1 << VMCI_RESOURCE_HASH_BITS) struct vmci_hash_table { spinlock_t lock; struct hlist_head entries[VMCI_RESOURCE_HASH_BUCKETS]; }; static struct vmci_hash_table vmci_resource_table = { .lock = __SPIN_LOCK_UNLOCKED(vmci_resource_table.lock), }; static unsigned int vmci_resource_hash(struct vmci_handle handle) { return hash_32(handle.resource, VMCI_RESOURCE_HASH_BITS); } /* * Gets a resource (if one exists) matching given handle from the hash table. */ static struct vmci_resource *vmci_resource_lookup(struct vmci_handle handle, enum vmci_resource_type type) { struct vmci_resource *r, *resource = NULL; unsigned int idx = vmci_resource_hash(handle); rcu_read_lock(); hlist_for_each_entry_rcu(r, &vmci_resource_table.entries[idx], node) { u32 cid = r->handle.context; u32 rid = r->handle.resource; if (r->type == type && rid == handle.resource && (cid == handle.context || cid == VMCI_INVALID_ID || handle.context == VMCI_INVALID_ID)) { resource = r; break; } } rcu_read_unlock(); return resource; } /* * Find an unused resource ID and return it. The first * VMCI_RESERVED_RESOURCE_ID_MAX are reserved so we start from * its value + 1. * Returns VMCI resource id on success, VMCI_INVALID_ID on failure. */ static u32 vmci_resource_find_id(u32 context_id, enum vmci_resource_type resource_type) { static u32 resource_id = VMCI_RESERVED_RESOURCE_ID_MAX + 1; u32 old_rid = resource_id; u32 current_rid; /* * Generate a unique resource ID. Keep on trying until we wrap around * in the RID space. */ do { struct vmci_handle handle; current_rid = resource_id; resource_id++; if (unlikely(resource_id == VMCI_INVALID_ID)) { /* Skip the reserved rids. */ resource_id = VMCI_RESERVED_RESOURCE_ID_MAX + 1; } handle = vmci_make_handle(context_id, current_rid); if (!vmci_resource_lookup(handle, resource_type)) return current_rid; } while (resource_id != old_rid); return VMCI_INVALID_ID; } int vmci_resource_add(struct vmci_resource *resource, enum vmci_resource_type resource_type, struct vmci_handle handle) { unsigned int idx; int result; spin_lock(&vmci_resource_table.lock); if (handle.resource == VMCI_INVALID_ID) { handle.resource = vmci_resource_find_id(handle.context, resource_type); if (handle.resource == VMCI_INVALID_ID) { result = VMCI_ERROR_NO_HANDLE; goto out; } } else if (vmci_resource_lookup(handle, resource_type)) { result = VMCI_ERROR_ALREADY_EXISTS; goto out; } resource->handle = handle; resource->type = resource_type; INIT_HLIST_NODE(&resource->node); kref_init(&resource->kref); init_completion(&resource->done); idx = vmci_resource_hash(resource->handle); hlist_add_head_rcu(&resource->node, &vmci_resource_table.entries[idx]); result = VMCI_SUCCESS; out: spin_unlock(&vmci_resource_table.lock); return result; } void vmci_resource_remove(struct vmci_resource *resource) { struct vmci_handle handle = resource->handle; unsigned int idx = vmci_resource_hash(handle); struct vmci_resource *r; /* Remove resource from hash table. */ spin_lock(&vmci_resource_table.lock); hlist_for_each_entry(r, &vmci_resource_table.entries[idx], node) { if (vmci_handle_is_equal(r->handle, resource->handle)) { hlist_del_init_rcu(&r->node); break; } } spin_unlock(&vmci_resource_table.lock); synchronize_rcu(); vmci_resource_put(resource); wait_for_completion(&resource->done); } struct vmci_resource * vmci_resource_by_handle(struct vmci_handle resource_handle, enum vmci_resource_type resource_type) { struct vmci_resource *r, *resource = NULL; rcu_read_lock(); r = vmci_resource_lookup(resource_handle, resource_type); if (r && (resource_type == r->type || resource_type == VMCI_RESOURCE_TYPE_ANY)) { resource = vmci_resource_get(r); } rcu_read_unlock(); return resource; } /* * Get a reference to given resource. */ struct vmci_resource *vmci_resource_get(struct vmci_resource *resource) { kref_get(&resource->kref); return resource; } static void vmci_release_resource(struct kref *kref) { struct vmci_resource *resource = container_of(kref, struct vmci_resource, kref); /* Verify the resource has been unlinked from hash table */ WARN_ON(!hlist_unhashed(&resource->node)); /* Signal that container of this resource can now be destroyed */ complete(&resource->done); } /* * Resource's release function will get called if last reference. * If it is the last reference, then we are sure that nobody else * can increment the count again (it's gone from the resource hash * table), so there's no need for locking here. */ int vmci_resource_put(struct vmci_resource *resource) { /* * We propagate the information back to caller in case it wants to know * whether entry was freed. */ return kref_put(&resource->kref, vmci_release_resource) ? VMCI_SUCCESS_ENTRY_DEAD : VMCI_SUCCESS; } struct vmci_handle vmci_resource_handle(struct vmci_resource *resource) { return resource->handle; } |
| 43 2 1 4 2 49 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_FUTEX_H #define _ASM_X86_FUTEX_H #ifdef __KERNEL__ #include <linux/futex.h> #include <linux/uaccess.h> #include <asm/asm.h> #include <asm/errno.h> #include <asm/processor.h> #include <asm/smap.h> #define __futex_atomic_op1(insn, ret, oldval, uaddr, oparg) \ asm volatile("\t" ASM_STAC "\n" \ "1:\t" insn "\n" \ "2:\t" ASM_CLAC "\n" \ "\t.section .fixup,\"ax\"\n" \ "3:\tmov\t%3, %1\n" \ "\tjmp\t2b\n" \ "\t.previous\n" \ _ASM_EXTABLE(1b, 3b) \ : "=r" (oldval), "=r" (ret), "+m" (*uaddr) \ : "i" (-EFAULT), "0" (oparg), "1" (0)) #define __futex_atomic_op2(insn, ret, oldval, uaddr, oparg) \ asm volatile("\t" ASM_STAC "\n" \ "1:\tmovl %2, %0\n" \ "\tmovl\t%0, %3\n" \ "\t" insn "\n" \ "2:\t" LOCK_PREFIX "cmpxchgl %3, %2\n" \ "\tjnz\t1b\n" \ "3:\t" ASM_CLAC "\n" \ "\t.section .fixup,\"ax\"\n" \ "4:\tmov\t%5, %1\n" \ "\tjmp\t3b\n" \ "\t.previous\n" \ _ASM_EXTABLE(1b, 4b) \ _ASM_EXTABLE(2b, 4b) \ : "=&a" (oldval), "=&r" (ret), \ "+m" (*uaddr), "=&r" (tem) \ : "r" (oparg), "i" (-EFAULT), "1" (0)) static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) { int oldval = 0, ret, tem; pagefault_disable(); switch (op) { case FUTEX_OP_SET: __futex_atomic_op1("xchgl %0, %2", ret, oldval, uaddr, oparg); break; case FUTEX_OP_ADD: __futex_atomic_op1(LOCK_PREFIX "xaddl %0, %2", ret, oldval, uaddr, oparg); break; case FUTEX_OP_OR: __futex_atomic_op2("orl %4, %3", ret, oldval, uaddr, oparg); break; case FUTEX_OP_ANDN: __futex_atomic_op2("andl %4, %3", ret, oldval, uaddr, ~oparg); break; case FUTEX_OP_XOR: __futex_atomic_op2("xorl %4, %3", ret, oldval, uaddr, oparg); break; default: ret = -ENOSYS; } pagefault_enable(); if (!ret) *oval = oldval; return ret; } static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, u32 newval) { return user_atomic_cmpxchg_inatomic(uval, uaddr, oldval, newval); } #endif #endif /* _ASM_X86_FUTEX_H */ |
| 80 1 80 15 4 4 4 15 22 22 2 1 2 19 40 34 40 33 32 33 20 7 24 11 11 2 2 33 1339 1339 2 344 1 342 342 342 27 91 296 231 230 66 324 325 321 66 3 2 3 1 1 1 80 80 80 80 76 80 80 79 80 80 80 76 76 69 6 69 69 69 69 69 69 11 11 11 11 11 11 69 69 69 69 19 6 5 1 4 1 9 4 4 6 4 4 4 3 2 1 1 1 1 1 1 1 1 21 21 21 21 22 20 20 20 20 20 20 20 19 20 8 8 3 12 1 1 1 5 6 20 20 3 3 2 2 20 20 2 18 2 2 19 2 20 11 2 20 19 19 19 19 10 10 10 10 10 10 19 19 6 19 7 6 5 2 7 19 2 2 10 10 9 8 6 2 2 52 52 52 1 52 50 49 9 6 1 23 10 103 464 464 445 166 274 1740 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * Neighbour Discovery for IPv6 * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * Mike Shaver <shaver@ingenia.com> * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ /* * Changes: * * Alexey I. Froloff : RFC6106 (DNSSL) support * Pierre Ynard : export userland ND options * through netlink (RDNSS support) * Lars Fenneberg : fixed MTU setting on receipt * of an RA. * Janos Farkas : kmalloc failure checks * Alexey Kuznetsov : state machine reworked * and moved to net/core. * Pekka Savola : RFC2461 validation * YOSHIFUJI Hideaki @USAGI : Verify ND options properly */ #define pr_fmt(fmt) "ICMPv6: " fmt #include <linux/module.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/sched.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/route.h> #include <linux/init.h> #include <linux/rcupdate.h> #include <linux/slab.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif #include <linux/if_addr.h> #include <linux/if_arp.h> #include <linux/ipv6.h> #include <linux/icmpv6.h> #include <linux/jhash.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/ndisc.h> #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/icmp.h> #include <net/netlink.h> #include <linux/rtnetlink.h> #include <net/flow.h> #include <net/ip6_checksum.h> #include <net/inet_common.h> #include <linux/proc_fs.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> static u32 ndisc_hash(const void *pkey, const struct net_device *dev, __u32 *hash_rnd); static bool ndisc_key_eq(const struct neighbour *neigh, const void *pkey); static int ndisc_constructor(struct neighbour *neigh); static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb); static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb); static int pndisc_constructor(struct pneigh_entry *n); static void pndisc_destructor(struct pneigh_entry *n); static void pndisc_redo(struct sk_buff *skb); static const struct neigh_ops ndisc_generic_ops = { .family = AF_INET6, .solicit = ndisc_solicit, .error_report = ndisc_error_report, .output = neigh_resolve_output, .connected_output = neigh_connected_output, }; static const struct neigh_ops ndisc_hh_ops = { .family = AF_INET6, .solicit = ndisc_solicit, .error_report = ndisc_error_report, .output = neigh_resolve_output, .connected_output = neigh_resolve_output, }; static const struct neigh_ops ndisc_direct_ops = { .family = AF_INET6, .output = neigh_direct_output, .connected_output = neigh_direct_output, }; struct neigh_table nd_tbl = { .family = AF_INET6, .key_len = sizeof(struct in6_addr), .protocol = cpu_to_be16(ETH_P_IPV6), .hash = ndisc_hash, .key_eq = ndisc_key_eq, .constructor = ndisc_constructor, .pconstructor = pndisc_constructor, .pdestructor = pndisc_destructor, .proxy_redo = pndisc_redo, .id = "ndisc_cache", .parms = { .tbl = &nd_tbl, .reachable_time = ND_REACHABLE_TIME, .data = { [NEIGH_VAR_MCAST_PROBES] = 3, [NEIGH_VAR_UCAST_PROBES] = 3, [NEIGH_VAR_RETRANS_TIME] = ND_RETRANS_TIMER, [NEIGH_VAR_BASE_REACHABLE_TIME] = ND_REACHABLE_TIME, [NEIGH_VAR_DELAY_PROBE_TIME] = 5 * HZ, [NEIGH_VAR_GC_STALETIME] = 60 * HZ, [NEIGH_VAR_QUEUE_LEN_BYTES] = SK_WMEM_MAX, [NEIGH_VAR_PROXY_QLEN] = 64, [NEIGH_VAR_ANYCAST_DELAY] = 1 * HZ, [NEIGH_VAR_PROXY_DELAY] = (8 * HZ) / 10, }, }, .gc_interval = 30 * HZ, .gc_thresh1 = 128, .gc_thresh2 = 512, .gc_thresh3 = 1024, }; EXPORT_SYMBOL_GPL(nd_tbl); void __ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data, int data_len, int pad) { int space = __ndisc_opt_addr_space(data_len, pad); u8 *opt = skb_put(skb, space); opt[0] = type; opt[1] = space>>3; memset(opt + 2, 0, pad); opt += pad; space -= pad; memcpy(opt+2, data, data_len); data_len += 2; opt += data_len; space -= data_len; if (space > 0) memset(opt, 0, space); } EXPORT_SYMBOL_GPL(__ndisc_fill_addr_option); static inline void ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data, u8 icmp6_type) { __ndisc_fill_addr_option(skb, type, data, skb->dev->addr_len, ndisc_addr_option_pad(skb->dev->type)); ndisc_ops_fill_addr_option(skb->dev, skb, icmp6_type); } static inline void ndisc_fill_redirect_addr_option(struct sk_buff *skb, void *ha, const u8 *ops_data) { ndisc_fill_addr_option(skb, ND_OPT_TARGET_LL_ADDR, ha, NDISC_REDIRECT); ndisc_ops_fill_redirect_addr_option(skb->dev, skb, ops_data); } static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur, struct nd_opt_hdr *end) { int type; if (!cur || !end || cur >= end) return NULL; type = cur->nd_opt_type; do { cur = ((void *)cur) + (cur->nd_opt_len << 3); } while (cur < end && cur->nd_opt_type != type); return cur <= end && cur->nd_opt_type == type ? cur : NULL; } static inline int ndisc_is_useropt(const struct net_device *dev, struct nd_opt_hdr *opt) { return opt->nd_opt_type == ND_OPT_RDNSS || opt->nd_opt_type == ND_OPT_DNSSL || ndisc_ops_is_useropt(dev, opt->nd_opt_type); } static struct nd_opt_hdr *ndisc_next_useropt(const struct net_device *dev, struct nd_opt_hdr *cur, struct nd_opt_hdr *end) { if (!cur || !end || cur >= end) return NULL; do { cur = ((void *)cur) + (cur->nd_opt_len << 3); } while (cur < end && !ndisc_is_useropt(dev, cur)); return cur <= end && ndisc_is_useropt(dev, cur) ? cur : NULL; } struct ndisc_options *ndisc_parse_options(const struct net_device *dev, u8 *opt, int opt_len, struct ndisc_options *ndopts) { struct nd_opt_hdr *nd_opt = (struct nd_opt_hdr *)opt; if (!nd_opt || opt_len < 0 || !ndopts) return NULL; memset(ndopts, 0, sizeof(*ndopts)); while (opt_len) { int l; if (opt_len < sizeof(struct nd_opt_hdr)) return NULL; l = nd_opt->nd_opt_len << 3; if (opt_len < l || l == 0) return NULL; if (ndisc_ops_parse_options(dev, nd_opt, ndopts)) goto next_opt; switch (nd_opt->nd_opt_type) { case ND_OPT_SOURCE_LL_ADDR: case ND_OPT_TARGET_LL_ADDR: case ND_OPT_MTU: case ND_OPT_NONCE: case ND_OPT_REDIRECT_HDR: if (ndopts->nd_opt_array[nd_opt->nd_opt_type]) { ND_PRINTK(2, warn, "%s: duplicated ND6 option found: type=%d\n", __func__, nd_opt->nd_opt_type); } else { ndopts->nd_opt_array[nd_opt->nd_opt_type] = nd_opt; } break; case ND_OPT_PREFIX_INFO: ndopts->nd_opts_pi_end = nd_opt; if (!ndopts->nd_opt_array[nd_opt->nd_opt_type]) ndopts->nd_opt_array[nd_opt->nd_opt_type] = nd_opt; break; #ifdef CONFIG_IPV6_ROUTE_INFO case ND_OPT_ROUTE_INFO: ndopts->nd_opts_ri_end = nd_opt; if (!ndopts->nd_opts_ri) ndopts->nd_opts_ri = nd_opt; break; #endif default: if (ndisc_is_useropt(dev, nd_opt)) { ndopts->nd_useropts_end = nd_opt; if (!ndopts->nd_useropts) ndopts->nd_useropts = nd_opt; } else { /* * Unknown options must be silently ignored, * to accommodate future extension to the * protocol. */ ND_PRINTK(2, notice, "%s: ignored unsupported option; type=%d, len=%d\n", __func__, nd_opt->nd_opt_type, nd_opt->nd_opt_len); } } next_opt: opt_len -= l; nd_opt = ((void *)nd_opt) + l; } return ndopts; } int ndisc_mc_map(const struct in6_addr *addr, char *buf, struct net_device *dev, int dir) { switch (dev->type) { case ARPHRD_ETHER: case ARPHRD_IEEE802: /* Not sure. Check it later. --ANK */ case ARPHRD_FDDI: ipv6_eth_mc_map(addr, buf); return 0; case ARPHRD_ARCNET: ipv6_arcnet_mc_map(addr, buf); return 0; case ARPHRD_INFINIBAND: ipv6_ib_mc_map(addr, dev->broadcast, buf); return 0; case ARPHRD_IPGRE: return ipv6_ipgre_mc_map(addr, dev->broadcast, buf); default: if (dir) { memcpy(buf, dev->broadcast, dev->addr_len); return 0; } } return -EINVAL; } EXPORT_SYMBOL(ndisc_mc_map); static u32 ndisc_hash(const void *pkey, const struct net_device *dev, __u32 *hash_rnd) { return ndisc_hashfn(pkey, dev, hash_rnd); } static bool ndisc_key_eq(const struct neighbour *n, const void *pkey) { return neigh_key_eq128(n, pkey); } static int ndisc_constructor(struct neighbour *neigh) { struct in6_addr *addr = (struct in6_addr *)&neigh->primary_key; struct net_device *dev = neigh->dev; struct inet6_dev *in6_dev; struct neigh_parms *parms; bool is_multicast = ipv6_addr_is_multicast(addr); in6_dev = in6_dev_get(dev); if (!in6_dev) { return -EINVAL; } parms = in6_dev->nd_parms; __neigh_parms_put(neigh->parms); neigh->parms = neigh_parms_clone(parms); neigh->type = is_multicast ? RTN_MULTICAST : RTN_UNICAST; if (!dev->header_ops) { neigh->nud_state = NUD_NOARP; neigh->ops = &ndisc_direct_ops; neigh->output = neigh_direct_output; } else { if (is_multicast) { neigh->nud_state = NUD_NOARP; ndisc_mc_map(addr, neigh->ha, dev, 1); } else if (dev->flags&(IFF_NOARP|IFF_LOOPBACK)) { neigh->nud_state = NUD_NOARP; memcpy(neigh->ha, dev->dev_addr, dev->addr_len); if (dev->flags&IFF_LOOPBACK) neigh->type = RTN_LOCAL; } else if (dev->flags&IFF_POINTOPOINT) { neigh->nud_state = NUD_NOARP; memcpy(neigh->ha, dev->broadcast, dev->addr_len); } if (dev->header_ops->cache) neigh->ops = &ndisc_hh_ops; else neigh->ops = &ndisc_generic_ops; if (neigh->nud_state&NUD_VALID) neigh->output = neigh->ops->connected_output; else neigh->output = neigh->ops->output; } in6_dev_put(in6_dev); return 0; } static int pndisc_constructor(struct pneigh_entry *n) { struct in6_addr *addr = (struct in6_addr *)&n->key; struct in6_addr maddr; struct net_device *dev = n->dev; if (!dev || !__in6_dev_get(dev)) return -EINVAL; addrconf_addr_solict_mult(addr, &maddr); ipv6_dev_mc_inc(dev, &maddr); return 0; } static void pndisc_destructor(struct pneigh_entry *n) { struct in6_addr *addr = (struct in6_addr *)&n->key; struct in6_addr maddr; struct net_device *dev = n->dev; if (!dev || !__in6_dev_get(dev)) return; addrconf_addr_solict_mult(addr, &maddr); ipv6_dev_mc_dec(dev, &maddr); } static struct sk_buff *ndisc_alloc_skb(struct net_device *dev, int len) { int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; struct sock *sk = dev_net(dev)->ipv6.ndisc_sk; struct sk_buff *skb; skb = alloc_skb(hlen + sizeof(struct ipv6hdr) + len + tlen, GFP_ATOMIC); if (!skb) { ND_PRINTK(0, err, "ndisc: %s failed to allocate an skb\n", __func__); return NULL; } skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; skb_reserve(skb, hlen + sizeof(struct ipv6hdr)); skb_reset_transport_header(skb); /* Manually assign socket ownership as we avoid calling * sock_alloc_send_pskb() to bypass wmem buffer limits */ skb_set_owner_w(skb, sk); return skb; } static void ip6_nd_hdr(struct sk_buff *skb, const struct in6_addr *saddr, const struct in6_addr *daddr, int hop_limit, int len) { struct ipv6hdr *hdr; skb_push(skb, sizeof(*hdr)); skb_reset_network_header(skb); hdr = ipv6_hdr(skb); ip6_flow_hdr(hdr, 0, 0); hdr->payload_len = htons(len); hdr->nexthdr = IPPROTO_ICMPV6; hdr->hop_limit = hop_limit; hdr->saddr = *saddr; hdr->daddr = *daddr; } static void ndisc_send_skb(struct sk_buff *skb, const struct in6_addr *daddr, const struct in6_addr *saddr) { struct dst_entry *dst = skb_dst(skb); struct net *net = dev_net(skb->dev); struct sock *sk = net->ipv6.ndisc_sk; struct inet6_dev *idev; int err; struct icmp6hdr *icmp6h = icmp6_hdr(skb); u8 type; type = icmp6h->icmp6_type; if (!dst) { struct flowi6 fl6; int oif = skb->dev->ifindex; icmpv6_flow_init(sk, &fl6, type, saddr, daddr, oif); dst = icmp6_dst_alloc(skb->dev, &fl6); if (IS_ERR(dst)) { kfree_skb(skb); return; } skb_dst_set(skb, dst); } icmp6h->icmp6_cksum = csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_ICMPV6, csum_partial(icmp6h, skb->len, 0)); ip6_nd_hdr(skb, saddr, daddr, inet6_sk(sk)->hop_limit, skb->len); rcu_read_lock(); idev = __in6_dev_get(dst->dev); IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, dst->dev, dst_output); if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, type); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); } rcu_read_unlock(); } void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr, const struct in6_addr *solicited_addr, bool router, bool solicited, bool override, bool inc_opt) { struct sk_buff *skb; struct in6_addr tmpaddr; struct inet6_ifaddr *ifp; const struct in6_addr *src_addr; struct nd_msg *msg; int optlen = 0; /* for anycast or proxy, solicited_addr != src_addr */ ifp = ipv6_get_ifaddr(dev_net(dev), solicited_addr, dev, 1); if (ifp) { src_addr = solicited_addr; if (ifp->flags & IFA_F_OPTIMISTIC) override = false; inc_opt |= ifp->idev->cnf.force_tllao; in6_ifa_put(ifp); } else { if (ipv6_dev_get_saddr(dev_net(dev), dev, daddr, inet6_sk(dev_net(dev)->ipv6.ndisc_sk)->srcprefs, &tmpaddr)) return; src_addr = &tmpaddr; } if (!dev->addr_len) inc_opt = 0; if (inc_opt) optlen += ndisc_opt_addr_space(dev, NDISC_NEIGHBOUR_ADVERTISEMENT); skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); if (!skb) return; msg = skb_put(skb, sizeof(*msg)); *msg = (struct nd_msg) { .icmph = { .icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT, .icmp6_router = router, .icmp6_solicited = solicited, .icmp6_override = override, }, .target = *solicited_addr, }; if (inc_opt) ndisc_fill_addr_option(skb, ND_OPT_TARGET_LL_ADDR, dev->dev_addr, NDISC_NEIGHBOUR_ADVERTISEMENT); ndisc_send_skb(skb, daddr, src_addr); } static void ndisc_send_unsol_na(struct net_device *dev) { struct inet6_dev *idev; struct inet6_ifaddr *ifa; idev = in6_dev_get(dev); if (!idev) return; read_lock_bh(&idev->lock); list_for_each_entry(ifa, &idev->addr_list, if_list) { /* skip tentative addresses until dad completes */ if (ifa->flags & IFA_F_TENTATIVE && !(ifa->flags & IFA_F_OPTIMISTIC)) continue; ndisc_send_na(dev, &in6addr_linklocal_allnodes, &ifa->addr, /*router=*/ !!idev->cnf.forwarding, /*solicited=*/ false, /*override=*/ true, /*inc_opt=*/ true); } read_unlock_bh(&idev->lock); in6_dev_put(idev); } void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit, const struct in6_addr *daddr, const struct in6_addr *saddr, u64 nonce) { struct sk_buff *skb; struct in6_addr addr_buf; int inc_opt = dev->addr_len; int optlen = 0; struct nd_msg *msg; if (!saddr) { if (ipv6_get_lladdr(dev, &addr_buf, (IFA_F_TENTATIVE|IFA_F_OPTIMISTIC))) return; saddr = &addr_buf; } if (ipv6_addr_any(saddr)) inc_opt = false; if (inc_opt) optlen += ndisc_opt_addr_space(dev, NDISC_NEIGHBOUR_SOLICITATION); if (nonce != 0) optlen += 8; skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); if (!skb) return; msg = skb_put(skb, sizeof(*msg)); *msg = (struct nd_msg) { .icmph = { .icmp6_type = NDISC_NEIGHBOUR_SOLICITATION, }, .target = *solicit, }; if (inc_opt) ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR, dev->dev_addr, NDISC_NEIGHBOUR_SOLICITATION); if (nonce != 0) { u8 *opt = skb_put(skb, 8); opt[0] = ND_OPT_NONCE; opt[1] = 8 >> 3; memcpy(opt + 2, &nonce, 6); } ndisc_send_skb(skb, daddr, saddr); } void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr, const struct in6_addr *daddr) { struct sk_buff *skb; struct rs_msg *msg; int send_sllao = dev->addr_len; int optlen = 0; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD /* * According to section 2.2 of RFC 4429, we must not * send router solicitations with a sllao from * optimistic addresses, but we may send the solicitation * if we don't include the sllao. So here we check * if our address is optimistic, and if so, we * suppress the inclusion of the sllao. */ if (send_sllao) { struct inet6_ifaddr *ifp = ipv6_get_ifaddr(dev_net(dev), saddr, dev, 1); if (ifp) { if (ifp->flags & IFA_F_OPTIMISTIC) { send_sllao = 0; } in6_ifa_put(ifp); } else { send_sllao = 0; } } #endif if (send_sllao) optlen += ndisc_opt_addr_space(dev, NDISC_ROUTER_SOLICITATION); skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); if (!skb) return; msg = skb_put(skb, sizeof(*msg)); *msg = (struct rs_msg) { .icmph = { .icmp6_type = NDISC_ROUTER_SOLICITATION, }, }; if (send_sllao) ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR, dev->dev_addr, NDISC_ROUTER_SOLICITATION); ndisc_send_skb(skb, daddr, saddr); } static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb) { /* * "The sender MUST return an ICMP * destination unreachable" */ dst_link_failure(skb); kfree_skb(skb); } /* Called with locked neigh: either read or both */ static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb) { struct in6_addr *saddr = NULL; struct in6_addr mcaddr; struct net_device *dev = neigh->dev; struct in6_addr *target = (struct in6_addr *)&neigh->primary_key; int probes = atomic_read(&neigh->probes); if (skb && ipv6_chk_addr_and_flags(dev_net(dev), &ipv6_hdr(skb)->saddr, dev, 1, IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)) saddr = &ipv6_hdr(skb)->saddr; probes -= NEIGH_VAR(neigh->parms, UCAST_PROBES); if (probes < 0) { if (!(neigh->nud_state & NUD_VALID)) { ND_PRINTK(1, dbg, "%s: trying to ucast probe in NUD_INVALID: %pI6\n", __func__, target); } ndisc_send_ns(dev, target, target, saddr, 0); } else if ((probes -= NEIGH_VAR(neigh->parms, APP_PROBES)) < 0) { neigh_app_ns(neigh); } else { addrconf_addr_solict_mult(target, &mcaddr); ndisc_send_ns(dev, target, &mcaddr, saddr, 0); } } static int pndisc_is_router(const void *pkey, struct net_device *dev) { struct pneigh_entry *n; int ret = -1; read_lock_bh(&nd_tbl.lock); n = __pneigh_lookup(&nd_tbl, dev_net(dev), pkey, dev); if (n) ret = !!(n->flags & NTF_ROUTER); read_unlock_bh(&nd_tbl.lock); return ret; } void ndisc_update(const struct net_device *dev, struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags, u8 icmp6_type, struct ndisc_options *ndopts) { neigh_update(neigh, lladdr, new, flags, 0); /* report ndisc ops about neighbour update */ ndisc_ops_update(dev, neigh, flags, icmp6_type, ndopts); } static void ndisc_recv_ns(struct sk_buff *skb) { struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb); const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr; u8 *lladdr = NULL; u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) + offsetof(struct nd_msg, opt)); struct ndisc_options ndopts; struct net_device *dev = skb->dev; struct inet6_ifaddr *ifp; struct inet6_dev *idev = NULL; struct neighbour *neigh; int dad = ipv6_addr_any(saddr); bool inc; int is_router = -1; u64 nonce = 0; if (skb->len < sizeof(struct nd_msg)) { ND_PRINTK(2, warn, "NS: packet too short\n"); return; } if (ipv6_addr_is_multicast(&msg->target)) { ND_PRINTK(2, warn, "NS: multicast target address\n"); return; } /* * RFC2461 7.1.1: * DAD has to be destined for solicited node multicast address. */ if (dad && !ipv6_addr_is_solict_mult(daddr)) { ND_PRINTK(2, warn, "NS: bad DAD packet (wrong destination)\n"); return; } if (!ndisc_parse_options(dev, msg->opt, ndoptlen, &ndopts)) { ND_PRINTK(2, warn, "NS: invalid ND options\n"); return; } if (ndopts.nd_opts_src_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr, dev); if (!lladdr) { ND_PRINTK(2, warn, "NS: invalid link-layer address length\n"); return; } /* RFC2461 7.1.1: * If the IP source address is the unspecified address, * there MUST NOT be source link-layer address option * in the message. */ if (dad) { ND_PRINTK(2, warn, "NS: bad DAD packet (link-layer address option)\n"); return; } } if (ndopts.nd_opts_nonce && ndopts.nd_opts_nonce->nd_opt_len == 1) memcpy(&nonce, (u8 *)(ndopts.nd_opts_nonce + 1), 6); inc = ipv6_addr_is_multicast(daddr); ifp = ipv6_get_ifaddr(dev_net(dev), &msg->target, dev, 1); if (ifp) { have_ifp: if (ifp->flags & (IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)) { if (dad) { if (nonce != 0 && ifp->dad_nonce == nonce) { u8 *np = (u8 *)&nonce; /* Matching nonce if looped back */ ND_PRINTK(2, notice, "%s: IPv6 DAD loopback for address %pI6c nonce %pM ignored\n", ifp->idev->dev->name, &ifp->addr, np); goto out; } /* * We are colliding with another node * who is doing DAD * so fail our DAD process */ addrconf_dad_failure(ifp); return; } else { /* * This is not a dad solicitation. * If we are an optimistic node, * we should respond. * Otherwise, we should ignore it. */ if (!(ifp->flags & IFA_F_OPTIMISTIC)) goto out; } } idev = ifp->idev; } else { struct net *net = dev_net(dev); /* perhaps an address on the master device */ if (netif_is_l3_slave(dev)) { struct net_device *mdev; mdev = netdev_master_upper_dev_get_rcu(dev); if (mdev) { ifp = ipv6_get_ifaddr(net, &msg->target, mdev, 1); if (ifp) goto have_ifp; } } idev = in6_dev_get(dev); if (!idev) { /* XXX: count this drop? */ return; } if (ipv6_chk_acast_addr(net, dev, &msg->target) || (idev->cnf.forwarding && (net->ipv6.devconf_all->proxy_ndp || idev->cnf.proxy_ndp) && (is_router = pndisc_is_router(&msg->target, dev)) >= 0)) { if (!(NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED) && skb->pkt_type != PACKET_HOST && inc && NEIGH_VAR(idev->nd_parms, PROXY_DELAY) != 0) { /* * for anycast or proxy, * sender should delay its response * by a random time between 0 and * MAX_ANYCAST_DELAY_TIME seconds. * (RFC2461) -- yoshfuji */ struct sk_buff *n = skb_clone(skb, GFP_ATOMIC); if (n) pneigh_enqueue(&nd_tbl, idev->nd_parms, n); goto out; } } else goto out; } if (is_router < 0) is_router = idev->cnf.forwarding; if (dad) { ndisc_send_na(dev, &in6addr_linklocal_allnodes, &msg->target, !!is_router, false, (ifp != NULL), true); goto out; } if (inc) NEIGH_CACHE_STAT_INC(&nd_tbl, rcv_probes_mcast); else NEIGH_CACHE_STAT_INC(&nd_tbl, rcv_probes_ucast); /* * update / create cache entry * for the source address */ neigh = __neigh_lookup(&nd_tbl, saddr, dev, !inc || lladdr || !dev->addr_len); if (neigh) ndisc_update(dev, neigh, lladdr, NUD_STALE, NEIGH_UPDATE_F_WEAK_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE, NDISC_NEIGHBOUR_SOLICITATION, &ndopts); if (neigh || !dev->header_ops) { ndisc_send_na(dev, saddr, &msg->target, !!is_router, true, (ifp != NULL && inc), inc); if (neigh) neigh_release(neigh); } out: if (ifp) in6_ifa_put(ifp); else in6_dev_put(idev); } static void ndisc_recv_na(struct sk_buff *skb) { struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb); struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr; u8 *lladdr = NULL; u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) + offsetof(struct nd_msg, opt)); struct ndisc_options ndopts; struct net_device *dev = skb->dev; struct inet6_dev *idev = __in6_dev_get(dev); struct inet6_ifaddr *ifp; struct neighbour *neigh; if (skb->len < sizeof(struct nd_msg)) { ND_PRINTK(2, warn, "NA: packet too short\n"); return; } if (ipv6_addr_is_multicast(&msg->target)) { ND_PRINTK(2, warn, "NA: target address is multicast\n"); return; } if (ipv6_addr_is_multicast(daddr) && msg->icmph.icmp6_solicited) { ND_PRINTK(2, warn, "NA: solicited NA is multicasted\n"); return; } /* For some 802.11 wireless deployments (and possibly other networks), * there will be a NA proxy and unsolicitd packets are attacks * and thus should not be accepted. */ if (!msg->icmph.icmp6_solicited && idev && idev->cnf.drop_unsolicited_na) return; if (!ndisc_parse_options(dev, msg->opt, ndoptlen, &ndopts)) { ND_PRINTK(2, warn, "NS: invalid ND option\n"); return; } if (ndopts.nd_opts_tgt_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_tgt_lladdr, dev); if (!lladdr) { ND_PRINTK(2, warn, "NA: invalid link-layer address length\n"); return; } } ifp = ipv6_get_ifaddr(dev_net(dev), &msg->target, dev, 1); if (ifp) { if (skb->pkt_type != PACKET_LOOPBACK && (ifp->flags & IFA_F_TENTATIVE)) { addrconf_dad_failure(ifp); return; } /* What should we make now? The advertisement is invalid, but ndisc specs say nothing about it. It could be misconfiguration, or an smart proxy agent tries to help us :-) We should not print the error if NA has been received from loopback - it is just our own unsolicited advertisement. */ if (skb->pkt_type != PACKET_LOOPBACK) ND_PRINTK(1, warn, "NA: someone advertises our address %pI6 on %s!\n", &ifp->addr, ifp->idev->dev->name); in6_ifa_put(ifp); return; } neigh = neigh_lookup(&nd_tbl, &msg->target, dev); if (neigh) { u8 old_flags = neigh->flags; struct net *net = dev_net(dev); if (neigh->nud_state & NUD_FAILED) goto out; /* * Don't update the neighbor cache entry on a proxy NA from * ourselves because either the proxied node is off link or it * has already sent a NA to us. */ if (lladdr && !memcmp(lladdr, dev->dev_addr, dev->addr_len) && net->ipv6.devconf_all->forwarding && net->ipv6.devconf_all->proxy_ndp && pneigh_lookup(&nd_tbl, net, &msg->target, dev, 0)) { /* XXX: idev->cnf.proxy_ndp */ goto out; } ndisc_update(dev, neigh, lladdr, msg->icmph.icmp6_solicited ? NUD_REACHABLE : NUD_STALE, NEIGH_UPDATE_F_WEAK_OVERRIDE| (msg->icmph.icmp6_override ? NEIGH_UPDATE_F_OVERRIDE : 0)| NEIGH_UPDATE_F_OVERRIDE_ISROUTER| (msg->icmph.icmp6_router ? NEIGH_UPDATE_F_ISROUTER : 0), NDISC_NEIGHBOUR_ADVERTISEMENT, &ndopts); if ((old_flags & ~neigh->flags) & NTF_ROUTER) { /* * Change: router to host */ rt6_clean_tohost(dev_net(dev), saddr); } out: neigh_release(neigh); } } static void ndisc_recv_rs(struct sk_buff *skb) { struct rs_msg *rs_msg = (struct rs_msg *)skb_transport_header(skb); unsigned long ndoptlen = skb->len - sizeof(*rs_msg); struct neighbour *neigh; struct inet6_dev *idev; const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr; struct ndisc_options ndopts; u8 *lladdr = NULL; if (skb->len < sizeof(*rs_msg)) return; idev = __in6_dev_get(skb->dev); if (!idev) { ND_PRINTK(1, err, "RS: can't find in6 device\n"); return; } /* Don't accept RS if we're not in router mode */ if (!idev->cnf.forwarding) goto out; /* * Don't update NCE if src = ::; * this implies that the source node has no ip address assigned yet. */ if (ipv6_addr_any(saddr)) goto out; /* Parse ND options */ if (!ndisc_parse_options(skb->dev, rs_msg->opt, ndoptlen, &ndopts)) { ND_PRINTK(2, notice, "NS: invalid ND option, ignored\n"); goto out; } if (ndopts.nd_opts_src_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr, skb->dev); if (!lladdr) goto out; } neigh = __neigh_lookup(&nd_tbl, saddr, skb->dev, 1); if (neigh) { ndisc_update(skb->dev, neigh, lladdr, NUD_STALE, NEIGH_UPDATE_F_WEAK_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE_ISROUTER, NDISC_ROUTER_SOLICITATION, &ndopts); neigh_release(neigh); } out: return; } static void ndisc_ra_useropt(struct sk_buff *ra, struct nd_opt_hdr *opt) { struct icmp6hdr *icmp6h = (struct icmp6hdr *)skb_transport_header(ra); struct sk_buff *skb; struct nlmsghdr *nlh; struct nduseroptmsg *ndmsg; struct net *net = dev_net(ra->dev); int err; int base_size = NLMSG_ALIGN(sizeof(struct nduseroptmsg) + (opt->nd_opt_len << 3)); size_t msg_size = base_size + nla_total_size(sizeof(struct in6_addr)); skb = nlmsg_new(msg_size, GFP_ATOMIC); if (!skb) { err = -ENOBUFS; goto errout; } nlh = nlmsg_put(skb, 0, 0, RTM_NEWNDUSEROPT, base_size, 0); if (!nlh) { goto nla_put_failure; } ndmsg = nlmsg_data(nlh); ndmsg->nduseropt_family = AF_INET6; ndmsg->nduseropt_ifindex = ra->dev->ifindex; ndmsg->nduseropt_icmp_type = icmp6h->icmp6_type; ndmsg->nduseropt_icmp_code = icmp6h->icmp6_code; ndmsg->nduseropt_opts_len = opt->nd_opt_len << 3; memcpy(ndmsg + 1, opt, opt->nd_opt_len << 3); if (nla_put_in6_addr(skb, NDUSEROPT_SRCADDR, &ipv6_hdr(ra)->saddr)) goto nla_put_failure; nlmsg_end(skb, nlh); rtnl_notify(skb, net, 0, RTNLGRP_ND_USEROPT, NULL, GFP_ATOMIC); return; nla_put_failure: nlmsg_free(skb); err = -EMSGSIZE; errout: rtnl_set_sk_err(net, RTNLGRP_ND_USEROPT, err); } static void ndisc_router_discovery(struct sk_buff *skb) { struct ra_msg *ra_msg = (struct ra_msg *)skb_transport_header(skb); struct neighbour *neigh = NULL; struct inet6_dev *in6_dev; struct rt6_info *rt = NULL; int lifetime; struct ndisc_options ndopts; int optlen; unsigned int pref = 0; __u32 old_if_flags; bool send_ifinfo_notify = false; __u8 *opt = (__u8 *)(ra_msg + 1); optlen = (skb_tail_pointer(skb) - skb_transport_header(skb)) - sizeof(struct ra_msg); ND_PRINTK(2, info, "RA: %s, dev: %s\n", __func__, skb->dev->name); if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) { ND_PRINTK(2, warn, "RA: source address is not link-local\n"); return; } if (optlen < 0) { ND_PRINTK(2, warn, "RA: packet too short\n"); return; } #ifdef CONFIG_IPV6_NDISC_NODETYPE if (skb->ndisc_nodetype == NDISC_NODETYPE_HOST) { ND_PRINTK(2, warn, "RA: from host or unauthorized router\n"); return; } #endif /* * set the RA_RECV flag in the interface */ in6_dev = __in6_dev_get(skb->dev); if (!in6_dev) { ND_PRINTK(0, err, "RA: can't find inet6 device for %s\n", skb->dev->name); return; } if (!ndisc_parse_options(skb->dev, opt, optlen, &ndopts)) { ND_PRINTK(2, warn, "RA: invalid ND options\n"); return; } if (!ipv6_accept_ra(in6_dev)) { ND_PRINTK(2, info, "RA: %s, did not accept ra for dev: %s\n", __func__, skb->dev->name); goto skip_linkparms; } #ifdef CONFIG_IPV6_NDISC_NODETYPE /* skip link-specific parameters from interior routers */ if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) { ND_PRINTK(2, info, "RA: %s, nodetype is NODEFAULT, dev: %s\n", __func__, skb->dev->name); goto skip_linkparms; } #endif if (in6_dev->if_flags & IF_RS_SENT) { /* * flag that an RA was received after an RS was sent * out on this interface. */ in6_dev->if_flags |= IF_RA_RCVD; } /* * Remember the managed/otherconf flags from most recently * received RA message (RFC 2462) -- yoshfuji */ old_if_flags = in6_dev->if_flags; in6_dev->if_flags = (in6_dev->if_flags & ~(IF_RA_MANAGED | IF_RA_OTHERCONF)) | (ra_msg->icmph.icmp6_addrconf_managed ? IF_RA_MANAGED : 0) | (ra_msg->icmph.icmp6_addrconf_other ? IF_RA_OTHERCONF : 0); if (old_if_flags != in6_dev->if_flags) send_ifinfo_notify = true; if (!in6_dev->cnf.accept_ra_defrtr) { ND_PRINTK(2, info, "RA: %s, defrtr is false for dev: %s\n", __func__, skb->dev->name); goto skip_defrtr; } /* Do not accept RA with source-addr found on local machine unless * accept_ra_from_local is set to true. */ if (!in6_dev->cnf.accept_ra_from_local && ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, in6_dev->dev, 0)) { ND_PRINTK(2, info, "RA from local address detected on dev: %s: default router ignored\n", skb->dev->name); goto skip_defrtr; } lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime); #ifdef CONFIG_IPV6_ROUTER_PREF pref = ra_msg->icmph.icmp6_router_pref; /* 10b is handled as if it were 00b (medium) */ if (pref == ICMPV6_ROUTER_PREF_INVALID || !in6_dev->cnf.accept_ra_rtr_pref) pref = ICMPV6_ROUTER_PREF_MEDIUM; #endif rt = rt6_get_dflt_router(&ipv6_hdr(skb)->saddr, skb->dev); if (rt) { neigh = dst_neigh_lookup(&rt->dst, &ipv6_hdr(skb)->saddr); if (!neigh) { ND_PRINTK(0, err, "RA: %s got default router without neighbour\n", __func__); ip6_rt_put(rt); return; } } if (rt && lifetime == 0) { ip6_del_rt(rt); rt = NULL; } ND_PRINTK(3, info, "RA: rt: %p lifetime: %d, for dev: %s\n", rt, lifetime, skb->dev->name); if (!rt && lifetime) { ND_PRINTK(3, info, "RA: adding default router\n"); rt = rt6_add_dflt_router(&ipv6_hdr(skb)->saddr, skb->dev, pref); if (!rt) { ND_PRINTK(0, err, "RA: %s failed to add default route\n", __func__); return; } neigh = dst_neigh_lookup(&rt->dst, &ipv6_hdr(skb)->saddr); if (!neigh) { ND_PRINTK(0, err, "RA: %s got default router without neighbour\n", __func__); ip6_rt_put(rt); return; } neigh->flags |= NTF_ROUTER; } else if (rt) { rt->rt6i_flags = (rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); } if (rt) rt6_set_expires(rt, jiffies + (HZ * lifetime)); if (in6_dev->cnf.accept_ra_min_hop_limit < 256 && ra_msg->icmph.icmp6_hop_limit) { if (in6_dev->cnf.accept_ra_min_hop_limit <= ra_msg->icmph.icmp6_hop_limit) { in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit; if (rt) dst_metric_set(&rt->dst, RTAX_HOPLIMIT, ra_msg->icmph.icmp6_hop_limit); } else { ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than minimum\n"); } } skip_defrtr: /* * Update Reachable Time and Retrans Timer */ if (in6_dev->nd_parms) { unsigned long rtime = ntohl(ra_msg->retrans_timer); if (rtime && rtime/1000 < MAX_SCHEDULE_TIMEOUT/HZ) { rtime = (rtime*HZ)/1000; if (rtime < HZ/10) rtime = HZ/10; NEIGH_VAR_SET(in6_dev->nd_parms, RETRANS_TIME, rtime); in6_dev->tstamp = jiffies; send_ifinfo_notify = true; } rtime = ntohl(ra_msg->reachable_time); if (rtime && rtime/1000 < MAX_SCHEDULE_TIMEOUT/(3*HZ)) { rtime = (rtime*HZ)/1000; if (rtime < HZ/10) rtime = HZ/10; if (rtime != NEIGH_VAR(in6_dev->nd_parms, BASE_REACHABLE_TIME)) { NEIGH_VAR_SET(in6_dev->nd_parms, BASE_REACHABLE_TIME, rtime); NEIGH_VAR_SET(in6_dev->nd_parms, GC_STALETIME, 3 * rtime); in6_dev->nd_parms->reachable_time = neigh_rand_reach_time(rtime); in6_dev->tstamp = jiffies; send_ifinfo_notify = true; } } } /* * Send a notify if RA changed managed/otherconf flags or timer settings */ if (send_ifinfo_notify) inet6_ifinfo_notify(RTM_NEWLINK, in6_dev); skip_linkparms: /* * Process options. */ if (!neigh) neigh = __neigh_lookup(&nd_tbl, &ipv6_hdr(skb)->saddr, skb->dev, 1); if (neigh) { u8 *lladdr = NULL; if (ndopts.nd_opts_src_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr, skb->dev); if (!lladdr) { ND_PRINTK(2, warn, "RA: invalid link-layer address length\n"); goto out; } } ndisc_update(skb->dev, neigh, lladdr, NUD_STALE, NEIGH_UPDATE_F_WEAK_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE_ISROUTER| NEIGH_UPDATE_F_ISROUTER, NDISC_ROUTER_ADVERTISEMENT, &ndopts); } if (!ipv6_accept_ra(in6_dev)) { ND_PRINTK(2, info, "RA: %s, accept_ra is false for dev: %s\n", __func__, skb->dev->name); goto out; } #ifdef CONFIG_IPV6_ROUTE_INFO if (!in6_dev->cnf.accept_ra_from_local && ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, in6_dev->dev, 0)) { ND_PRINTK(2, info, "RA from local address detected on dev: %s: router info ignored.\n", skb->dev->name); goto skip_routeinfo; } if (in6_dev->cnf.accept_ra_rtr_pref && ndopts.nd_opts_ri) { struct nd_opt_hdr *p; for (p = ndopts.nd_opts_ri; p; p = ndisc_next_option(p, ndopts.nd_opts_ri_end)) { struct route_info *ri = (struct route_info *)p; #ifdef CONFIG_IPV6_NDISC_NODETYPE if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT && ri->prefix_len == 0) continue; #endif if (ri->prefix_len == 0 && !in6_dev->cnf.accept_ra_defrtr) continue; if (ri->prefix_len < in6_dev->cnf.accept_ra_rt_info_min_plen) continue; if (ri->prefix_len > in6_dev->cnf.accept_ra_rt_info_max_plen) continue; rt6_route_rcv(skb->dev, (u8 *)p, (p->nd_opt_len) << 3, &ipv6_hdr(skb)->saddr); } } skip_routeinfo: #endif #ifdef CONFIG_IPV6_NDISC_NODETYPE /* skip link-specific ndopts from interior routers */ if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) { ND_PRINTK(2, info, "RA: %s, nodetype is NODEFAULT (interior routes), dev: %s\n", __func__, skb->dev->name); goto out; } #endif if (in6_dev->cnf.accept_ra_pinfo && ndopts.nd_opts_pi) { struct nd_opt_hdr *p; for (p = ndopts.nd_opts_pi; p; p = ndisc_next_option(p, ndopts.nd_opts_pi_end)) { addrconf_prefix_rcv(skb->dev, (u8 *)p, (p->nd_opt_len) << 3, ndopts.nd_opts_src_lladdr != NULL); } } if (ndopts.nd_opts_mtu && in6_dev->cnf.accept_ra_mtu) { __be32 n; u32 mtu; memcpy(&n, ((u8 *)(ndopts.nd_opts_mtu+1))+2, sizeof(mtu)); mtu = ntohl(n); if (mtu < IPV6_MIN_MTU || mtu > skb->dev->mtu) { ND_PRINTK(2, warn, "RA: invalid mtu: %d\n", mtu); } else if (in6_dev->cnf.mtu6 != mtu) { in6_dev->cnf.mtu6 = mtu; if (rt) dst_metric_set(&rt->dst, RTAX_MTU, mtu); rt6_mtu_change(skb->dev, mtu); } } if (ndopts.nd_useropts) { struct nd_opt_hdr *p; for (p = ndopts.nd_useropts; p; p = ndisc_next_useropt(skb->dev, p, ndopts.nd_useropts_end)) { ndisc_ra_useropt(skb, p); } } if (ndopts.nd_opts_tgt_lladdr || ndopts.nd_opts_rh) { ND_PRINTK(2, warn, "RA: invalid RA options\n"); } out: ip6_rt_put(rt); if (neigh) neigh_release(neigh); } static void ndisc_redirect_rcv(struct sk_buff *skb) { u8 *hdr; struct ndisc_options ndopts; struct rd_msg *msg = (struct rd_msg *)skb_transport_header(skb); u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) + offsetof(struct rd_msg, opt)); #ifdef CONFIG_IPV6_NDISC_NODETYPE switch (skb->ndisc_nodetype) { case NDISC_NODETYPE_HOST: case NDISC_NODETYPE_NODEFAULT: ND_PRINTK(2, warn, "Redirect: from host or unauthorized router\n"); return; } #endif if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) { ND_PRINTK(2, warn, "Redirect: source address is not link-local\n"); return; } if (!ndisc_parse_options(skb->dev, msg->opt, ndoptlen, &ndopts)) return; if (!ndopts.nd_opts_rh) { ip6_redirect_no_header(skb, dev_net(skb->dev), skb->dev->ifindex, 0); return; } hdr = (u8 *)ndopts.nd_opts_rh; hdr += 8; if (!pskb_pull(skb, hdr - skb_transport_header(skb))) return; icmpv6_notify(skb, NDISC_REDIRECT, 0, 0); } static void ndisc_fill_redirect_hdr_option(struct sk_buff *skb, struct sk_buff *orig_skb, int rd_len) { u8 *opt = skb_put(skb, rd_len); memset(opt, 0, 8); *(opt++) = ND_OPT_REDIRECT_HDR; *(opt++) = (rd_len >> 3); opt += 6; skb_copy_bits(orig_skb, skb_network_offset(orig_skb), opt, rd_len - 8); } void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target) { struct net_device *dev = skb->dev; struct net *net = dev_net(dev); struct sock *sk = net->ipv6.ndisc_sk; int optlen = 0; struct inet_peer *peer; struct sk_buff *buff; struct rd_msg *msg; struct in6_addr saddr_buf; struct rt6_info *rt; struct dst_entry *dst; struct flowi6 fl6; int rd_len; u8 ha_buf[MAX_ADDR_LEN], *ha = NULL, ops_data_buf[NDISC_OPS_REDIRECT_DATA_SPACE], *ops_data = NULL; bool ret; if (netif_is_l3_master(skb->dev)) { dev = __dev_get_by_index(dev_net(skb->dev), IPCB(skb)->iif); if (!dev) return; } if (ipv6_get_lladdr(dev, &saddr_buf, IFA_F_TENTATIVE)) { ND_PRINTK(2, warn, "Redirect: no link-local address on %s\n", dev->name); return; } if (!ipv6_addr_equal(&ipv6_hdr(skb)->daddr, target) && ipv6_addr_type(target) != (IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) { ND_PRINTK(2, warn, "Redirect: target address is not link-local unicast\n"); return; } icmpv6_flow_init(sk, &fl6, NDISC_REDIRECT, &saddr_buf, &ipv6_hdr(skb)->saddr, dev->ifindex); dst = ip6_route_output(net, NULL, &fl6); if (dst->error) { dst_release(dst); return; } dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0); if (IS_ERR(dst)) return; rt = (struct rt6_info *) dst; if (rt->rt6i_flags & RTF_GATEWAY) { ND_PRINTK(2, warn, "Redirect: destination is not a neighbour\n"); goto release; } peer = inet_getpeer_v6(net->ipv6.peers, &ipv6_hdr(skb)->saddr, 1); ret = inet_peer_xrlim_allow(peer, 1*HZ); if (peer) inet_putpeer(peer); if (!ret) goto release; if (dev->addr_len) { struct neighbour *neigh = dst_neigh_lookup(skb_dst(skb), target); if (!neigh) { ND_PRINTK(2, warn, "Redirect: no neigh for target address\n"); goto release; } read_lock_bh(&neigh->lock); if (neigh->nud_state & NUD_VALID) { memcpy(ha_buf, neigh->ha, dev->addr_len); read_unlock_bh(&neigh->lock); ha = ha_buf; optlen += ndisc_redirect_opt_addr_space(dev, neigh, ops_data_buf, &ops_data); } else read_unlock_bh(&neigh->lock); neigh_release(neigh); } rd_len = min_t(unsigned int, IPV6_MIN_MTU - sizeof(struct ipv6hdr) - sizeof(*msg) - optlen, skb->len + 8); rd_len &= ~0x7; optlen += rd_len; buff = ndisc_alloc_skb(dev, sizeof(*msg) + optlen); if (!buff) goto release; msg = skb_put(buff, sizeof(*msg)); *msg = (struct rd_msg) { .icmph = { .icmp6_type = NDISC_REDIRECT, }, .target = *target, .dest = ipv6_hdr(skb)->daddr, }; /* * include target_address option */ if (ha) ndisc_fill_redirect_addr_option(buff, ha, ops_data); /* * build redirect option and copy skb over to the new packet. */ if (rd_len) ndisc_fill_redirect_hdr_option(buff, skb, rd_len); skb_dst_set(buff, dst); ndisc_send_skb(buff, &ipv6_hdr(skb)->saddr, &saddr_buf); return; release: dst_release(dst); } static void pndisc_redo(struct sk_buff *skb) { ndisc_recv_ns(skb); kfree_skb(skb); } static bool ndisc_suppress_frag_ndisc(struct sk_buff *skb) { struct inet6_dev *idev = __in6_dev_get(skb->dev); if (!idev) return true; if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED && idev->cnf.suppress_frag_ndisc) { net_warn_ratelimited("Received fragmented ndisc packet. Carefully consider disabling suppress_frag_ndisc.\n"); return true; } return false; } int ndisc_rcv(struct sk_buff *skb) { struct nd_msg *msg; if (ndisc_suppress_frag_ndisc(skb)) return 0; if (skb_linearize(skb)) return 0; msg = (struct nd_msg *)skb_transport_header(skb); __skb_push(skb, skb->data - skb_transport_header(skb)); if (ipv6_hdr(skb)->hop_limit != 255) { ND_PRINTK(2, warn, "NDISC: invalid hop-limit: %d\n", ipv6_hdr(skb)->hop_limit); return 0; } if (msg->icmph.icmp6_code != 0) { ND_PRINTK(2, warn, "NDISC: invalid ICMPv6 code: %d\n", msg->icmph.icmp6_code); return 0; } switch (msg->icmph.icmp6_type) { case NDISC_NEIGHBOUR_SOLICITATION: memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb)); ndisc_recv_ns(skb); break; case NDISC_NEIGHBOUR_ADVERTISEMENT: ndisc_recv_na(skb); break; case NDISC_ROUTER_SOLICITATION: ndisc_recv_rs(skb); break; case NDISC_ROUTER_ADVERTISEMENT: ndisc_router_discovery(skb); break; case NDISC_REDIRECT: ndisc_redirect_rcv(skb); break; } return 0; } static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netdev_notifier_change_info *change_info; struct net *net = dev_net(dev); struct inet6_dev *idev; switch (event) { case NETDEV_CHANGEADDR: neigh_changeaddr(&nd_tbl, dev); fib6_run_gc(0, net, false); /* fallthrough */ case NETDEV_UP: idev = in6_dev_get(dev); if (!idev) break; if (idev->cnf.ndisc_notify || net->ipv6.devconf_all->ndisc_notify) ndisc_send_unsol_na(dev); in6_dev_put(idev); break; case NETDEV_CHANGE: change_info = ptr; if (change_info->flags_changed & IFF_NOARP) neigh_changeaddr(&nd_tbl, dev); break; case NETDEV_DOWN: neigh_ifdown(&nd_tbl, dev); fib6_run_gc(0, net, false); break; case NETDEV_NOTIFY_PEERS: ndisc_send_unsol_na(dev); break; default: break; } return NOTIFY_DONE; } static struct notifier_block ndisc_netdev_notifier = { .notifier_call = ndisc_netdev_event, .priority = ADDRCONF_NOTIFY_PRIORITY - 5, }; #ifdef CONFIG_SYSCTL static void ndisc_warn_deprecated_sysctl(struct ctl_table *ctl, const char *func, const char *dev_name) { static char warncomm[TASK_COMM_LEN]; static int warned; if (strcmp(warncomm, current->comm) && warned < 5) { strcpy(warncomm, current->comm); pr_warn("process `%s' is using deprecated sysctl (%s) net.ipv6.neigh.%s.%s - use net.ipv6.neigh.%s.%s_ms instead\n", warncomm, func, dev_name, ctl->procname, dev_name, ctl->procname); warned++; } } int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct net_device *dev = ctl->extra1; struct inet6_dev *idev; int ret; if ((strcmp(ctl->procname, "retrans_time") == 0) || (strcmp(ctl->procname, "base_reachable_time") == 0)) ndisc_warn_deprecated_sysctl(ctl, "syscall", dev ? dev->name : "default"); if (strcmp(ctl->procname, "retrans_time") == 0) ret = neigh_proc_dointvec(ctl, write, buffer, lenp, ppos); else if (strcmp(ctl->procname, "base_reachable_time") == 0) ret = neigh_proc_dointvec_jiffies(ctl, write, buffer, lenp, ppos); else if ((strcmp(ctl->procname, "retrans_time_ms") == 0) || (strcmp(ctl->procname, "base_reachable_time_ms") == 0)) ret = neigh_proc_dointvec_ms_jiffies(ctl, write, buffer, lenp, ppos); else ret = -1; if (write && ret == 0 && dev && (idev = in6_dev_get(dev)) != NULL) { if (ctl->data == &NEIGH_VAR(idev->nd_parms, BASE_REACHABLE_TIME)) idev->nd_parms->reachable_time = neigh_rand_reach_time(NEIGH_VAR(idev->nd_parms, BASE_REACHABLE_TIME)); idev->tstamp = jiffies; inet6_ifinfo_notify(RTM_NEWLINK, idev); in6_dev_put(idev); } return ret; } #endif static int __net_init ndisc_net_init(struct net *net) { struct ipv6_pinfo *np; struct sock *sk; int err; err = inet_ctl_sock_create(&sk, PF_INET6, SOCK_RAW, IPPROTO_ICMPV6, net); if (err < 0) { ND_PRINTK(0, err, "NDISC: Failed to initialize the control socket (err %d)\n", err); return err; } net->ipv6.ndisc_sk = sk; np = inet6_sk(sk); np->hop_limit = 255; /* Do not loopback ndisc messages */ np->mc_loop = 0; return 0; } static void __net_exit ndisc_net_exit(struct net *net) { inet_ctl_sock_destroy(net->ipv6.ndisc_sk); } static struct pernet_operations ndisc_net_ops = { .init = ndisc_net_init, .exit = ndisc_net_exit, }; int __init ndisc_init(void) { int err; err = register_pernet_subsys(&ndisc_net_ops); if (err) return err; /* * Initialize the neighbour table */ neigh_table_init(NEIGH_ND_TABLE, &nd_tbl); #ifdef CONFIG_SYSCTL err = neigh_sysctl_register(NULL, &nd_tbl.parms, ndisc_ifinfo_sysctl_change); if (err) goto out_unregister_pernet; out: #endif return err; #ifdef CONFIG_SYSCTL out_unregister_pernet: unregister_pernet_subsys(&ndisc_net_ops); goto out; #endif } int __init ndisc_late_init(void) { return register_netdevice_notifier(&ndisc_netdev_notifier); } void ndisc_late_cleanup(void) { unregister_netdevice_notifier(&ndisc_netdev_notifier); } void ndisc_cleanup(void) { #ifdef CONFIG_SYSCTL neigh_sysctl_unregister(&nd_tbl.parms); #endif neigh_table_clear(NEIGH_ND_TABLE, &nd_tbl); unregister_pernet_subsys(&ndisc_net_ops); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_SPECIAL_INSNS_H #define _ASM_X86_SPECIAL_INSNS_H #ifdef __KERNEL__ #include <asm/nops.h> /* * Volatile isn't enough to prevent the compiler from reordering the * read/write functions for the control registers and messing everything up. * A memory clobber would solve the problem, but would prevent reordering of * all loads stores around it, which can hurt performance. Solution is to * use a variable and mimic reads and writes to it to enforce serialization */ extern unsigned long __force_order; static inline unsigned long native_read_cr0(void) { unsigned long val; asm volatile("mov %%cr0,%0\n\t" : "=r" (val), "=m" (__force_order)); return val; } static inline void native_write_cr0(unsigned long val) { asm volatile("mov %0,%%cr0": : "r" (val), "m" (__force_order)); } static inline unsigned long native_read_cr2(void) { unsigned long val; asm volatile("mov %%cr2,%0\n\t" : "=r" (val), "=m" (__force_order)); return val; } static inline void native_write_cr2(unsigned long val) { asm volatile("mov %0,%%cr2": : "r" (val), "m" (__force_order)); } static inline unsigned long __native_read_cr3(void) { unsigned long val; asm volatile("mov %%cr3,%0\n\t" : "=r" (val), "=m" (__force_order)); return val; } static inline void native_write_cr3(unsigned long val) { asm volatile("mov %0,%%cr3": : "r" (val), "m" (__force_order)); } static inline unsigned long native_read_cr4(void) { unsigned long val; #ifdef CONFIG_X86_32 /* * This could fault if CR4 does not exist. Non-existent CR4 * is functionally equivalent to CR4 == 0. Keep it simple and pretend * that CR4 == 0 on CPUs that don't have CR4. */ asm volatile("1: mov %%cr4, %0\n" "2:\n" _ASM_EXTABLE(1b, 2b) : "=r" (val), "=m" (__force_order) : "0" (0)); #else /* CR4 always exists on x86_64. */ asm volatile("mov %%cr4,%0\n\t" : "=r" (val), "=m" (__force_order)); #endif return val; } static inline void native_write_cr4(unsigned long val) { asm volatile("mov %0,%%cr4": : "r" (val), "m" (__force_order)); } #ifdef CONFIG_X86_64 static inline unsigned long native_read_cr8(void) { unsigned long cr8; asm volatile("movq %%cr8,%0" : "=r" (cr8)); return cr8; } static inline void native_write_cr8(unsigned long val) { asm volatile("movq %0,%%cr8" :: "r" (val) : "memory"); } #endif #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS static inline u32 __read_pkru(void) { u32 ecx = 0; u32 edx, pkru; /* * "rdpkru" instruction. Places PKRU contents in to EAX, * clears EDX and requires that ecx=0. */ asm volatile(".byte 0x0f,0x01,0xee\n\t" : "=a" (pkru), "=d" (edx) : "c" (ecx)); return pkru; } static inline void __write_pkru(u32 pkru) { u32 ecx = 0, edx = 0; /* * "wrpkru" instruction. Loads contents in EAX to PKRU, * requires that ecx = edx = 0. */ asm volatile(".byte 0x0f,0x01,0xef\n\t" : : "a" (pkru), "c"(ecx), "d"(edx)); } #else static inline u32 __read_pkru(void) { return 0; } static inline void __write_pkru(u32 pkru) { } #endif static inline void native_wbinvd(void) { asm volatile("wbinvd": : :"memory"); } extern asmlinkage void native_load_gs_index(unsigned); static inline unsigned long __read_cr4(void) { return native_read_cr4(); } #ifdef CONFIG_PARAVIRT #include <asm/paravirt.h> #else static inline unsigned long read_cr0(void) { return native_read_cr0(); } static inline void write_cr0(unsigned long x) { native_write_cr0(x); } static inline unsigned long read_cr2(void) { return native_read_cr2(); } static inline void write_cr2(unsigned long x) { native_write_cr2(x); } /* * Careful! CR3 contains more than just an address. You probably want * read_cr3_pa() instead. */ static inline unsigned long __read_cr3(void) { return __native_read_cr3(); } static inline void write_cr3(unsigned long x) { native_write_cr3(x); } static inline void __write_cr4(unsigned long x) { native_write_cr4(x); } static inline void wbinvd(void) { native_wbinvd(); } #ifdef CONFIG_X86_64 static inline unsigned long read_cr8(void) { return native_read_cr8(); } static inline void write_cr8(unsigned long x) { native_write_cr8(x); } static inline void load_gs_index(unsigned selector) { native_load_gs_index(selector); } #endif #endif/* CONFIG_PARAVIRT */ static inline void clflush(volatile void *__p) { asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p)); } static inline void clflushopt(volatile void *__p) { alternative_io(".byte " __stringify(NOP_DS_PREFIX) "; clflush %P0", ".byte 0x66; clflush %P0", X86_FEATURE_CLFLUSHOPT, "+m" (*(volatile char __force *)__p)); } static inline void clwb(volatile void *__p) { volatile struct { char x[64]; } *p = __p; asm volatile(ALTERNATIVE_2( ".byte " __stringify(NOP_DS_PREFIX) "; clflush (%[pax])", ".byte 0x66; clflush (%[pax])", /* clflushopt (%%rax) */ X86_FEATURE_CLFLUSHOPT, ".byte 0x66, 0x0f, 0xae, 0x30", /* clwb (%%rax) */ X86_FEATURE_CLWB) : [p] "+m" (*p) : [pax] "a" (p)); } #define nop() asm volatile ("nop") #endif /* __KERNEL__ */ #endif /* _ASM_X86_SPECIAL_INSNS_H */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MBCACHE_H #define _LINUX_MBCACHE_H #include <linux/hash.h> #include <linux/list_bl.h> #include <linux/list.h> #include <linux/atomic.h> #include <linux/fs.h> struct mb_cache; struct mb_cache_entry { /* List of entries in cache - protected by cache->c_list_lock */ struct list_head e_list; /* Hash table list - protected by hash chain bitlock */ struct hlist_bl_node e_hash_list; atomic_t e_refcnt; /* Key in hash - stable during lifetime of the entry */ u32 e_key; u32 e_referenced:1; u32 e_reusable:1; /* User provided value - stable during lifetime of the entry */ u64 e_value; }; struct mb_cache *mb_cache_create(int bucket_bits); void mb_cache_destroy(struct mb_cache *cache); int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key, u64 value, bool reusable); void __mb_cache_entry_free(struct mb_cache_entry *entry); static inline int mb_cache_entry_put(struct mb_cache *cache, struct mb_cache_entry *entry) { if (!atomic_dec_and_test(&entry->e_refcnt)) return 0; __mb_cache_entry_free(entry); return 1; } void mb_cache_entry_delete(struct mb_cache *cache, u32 key, u64 value); struct mb_cache_entry *mb_cache_entry_get(struct mb_cache *cache, u32 key, u64 value); struct mb_cache_entry *mb_cache_entry_find_first(struct mb_cache *cache, u32 key); struct mb_cache_entry *mb_cache_entry_find_next(struct mb_cache *cache, struct mb_cache_entry *entry); void mb_cache_entry_touch(struct mb_cache *cache, struct mb_cache_entry *entry); #endif /* _LINUX_MBCACHE_H */ |
| 4 6 6 2 2 3 3 4 4 4 4 2 2 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * net/core/devlink.c - Network physical/parent device Netlink interface * * Heavily inspired by net/wireless/ * Copyright (c) 2016 Mellanox Technologies. All rights reserved. * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/gfp.h> #include <linux/device.h> #include <linux/list.h> #include <linux/netdevice.h> #include <rdma/ib_verbs.h> #include <net/netlink.h> #include <net/genetlink.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/devlink.h> #define CREATE_TRACE_POINTS #include <trace/events/devlink.h> static struct devlink_dpipe_field devlink_dpipe_fields_ethernet[] = { { .name = "destination mac", .id = DEVLINK_DPIPE_FIELD_ETHERNET_DST_MAC, .bitwidth = 48, }, }; struct devlink_dpipe_header devlink_dpipe_header_ethernet = { .name = "ethernet", .id = DEVLINK_DPIPE_HEADER_ETHERNET, .fields = devlink_dpipe_fields_ethernet, .fields_count = ARRAY_SIZE(devlink_dpipe_fields_ethernet), .global = true, }; EXPORT_SYMBOL(devlink_dpipe_header_ethernet); static struct devlink_dpipe_field devlink_dpipe_fields_ipv4[] = { { .name = "destination ip", .id = DEVLINK_DPIPE_FIELD_IPV4_DST_IP, .bitwidth = 32, }, }; struct devlink_dpipe_header devlink_dpipe_header_ipv4 = { .name = "ipv4", .id = DEVLINK_DPIPE_HEADER_IPV4, .fields = devlink_dpipe_fields_ipv4, .fields_count = ARRAY_SIZE(devlink_dpipe_fields_ipv4), .global = true, }; EXPORT_SYMBOL(devlink_dpipe_header_ipv4); static struct devlink_dpipe_field devlink_dpipe_fields_ipv6[] = { { .name = "destination ip", .id = DEVLINK_DPIPE_FIELD_IPV6_DST_IP, .bitwidth = 128, }, }; struct devlink_dpipe_header devlink_dpipe_header_ipv6 = { .name = "ipv6", .id = DEVLINK_DPIPE_HEADER_IPV6, .fields = devlink_dpipe_fields_ipv6, .fields_count = ARRAY_SIZE(devlink_dpipe_fields_ipv6), .global = true, }; EXPORT_SYMBOL(devlink_dpipe_header_ipv6); EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwmsg); static LIST_HEAD(devlink_list); /* devlink_mutex * * An overall lock guarding every operation coming from userspace. * It also guards devlink devices list and it is taken when * driver registers/unregisters it. */ static DEFINE_MUTEX(devlink_mutex); /* devlink_port_mutex * * Shared lock to guard lists of ports in all devlink devices. */ static DEFINE_MUTEX(devlink_port_mutex); static struct net *devlink_net(const struct devlink *devlink) { return read_pnet(&devlink->_net); } static void devlink_net_set(struct devlink *devlink, struct net *net) { write_pnet(&devlink->_net, net); } static struct devlink *devlink_get_from_attrs(struct net *net, struct nlattr **attrs) { struct devlink *devlink; char *busname; char *devname; if (!attrs[DEVLINK_ATTR_BUS_NAME] || !attrs[DEVLINK_ATTR_DEV_NAME]) return ERR_PTR(-EINVAL); busname = nla_data(attrs[DEVLINK_ATTR_BUS_NAME]); devname = nla_data(attrs[DEVLINK_ATTR_DEV_NAME]); list_for_each_entry(devlink, &devlink_list, list) { if (strcmp(devlink->dev->bus->name, busname) == 0 && strcmp(dev_name(devlink->dev), devname) == 0 && net_eq(devlink_net(devlink), net)) return devlink; } return ERR_PTR(-ENODEV); } static struct devlink *devlink_get_from_info(struct genl_info *info) { return devlink_get_from_attrs(genl_info_net(info), info->attrs); } static struct devlink_port *devlink_port_get_by_index(struct devlink *devlink, int port_index) { struct devlink_port *devlink_port; list_for_each_entry(devlink_port, &devlink->port_list, list) { if (devlink_port->index == port_index) return devlink_port; } return NULL; } static bool devlink_port_index_exists(struct devlink *devlink, int port_index) { return devlink_port_get_by_index(devlink, port_index); } static struct devlink_port *devlink_port_get_from_attrs(struct devlink *devlink, struct nlattr **attrs) { if (attrs[DEVLINK_ATTR_PORT_INDEX]) { u32 port_index = nla_get_u32(attrs[DEVLINK_ATTR_PORT_INDEX]); struct devlink_port *devlink_port; devlink_port = devlink_port_get_by_index(devlink, port_index); if (!devlink_port) return ERR_PTR(-ENODEV); return devlink_port; } return ERR_PTR(-EINVAL); } static struct devlink_port *devlink_port_get_from_info(struct devlink *devlink, struct genl_info *info) { return devlink_port_get_from_attrs(devlink, info->attrs); } struct devlink_sb { struct list_head list; unsigned int index; u32 size; u16 ingress_pools_count; u16 egress_pools_count; u16 ingress_tc_count; u16 egress_tc_count; }; static u16 devlink_sb_pool_count(struct devlink_sb *devlink_sb) { return devlink_sb->ingress_pools_count + devlink_sb->egress_pools_count; } static struct devlink_sb *devlink_sb_get_by_index(struct devlink *devlink, unsigned int sb_index) { struct devlink_sb *devlink_sb; list_for_each_entry(devlink_sb, &devlink->sb_list, list) { if (devlink_sb->index == sb_index) return devlink_sb; } return NULL; } static bool devlink_sb_index_exists(struct devlink *devlink, unsigned int sb_index) { return devlink_sb_get_by_index(devlink, sb_index); } static struct devlink_sb *devlink_sb_get_from_attrs(struct devlink *devlink, struct nlattr **attrs) { if (attrs[DEVLINK_ATTR_SB_INDEX]) { u32 sb_index = nla_get_u32(attrs[DEVLINK_ATTR_SB_INDEX]); struct devlink_sb *devlink_sb; devlink_sb = devlink_sb_get_by_index(devlink, sb_index); if (!devlink_sb) return ERR_PTR(-ENODEV); return devlink_sb; } return ERR_PTR(-EINVAL); } static struct devlink_sb *devlink_sb_get_from_info(struct devlink *devlink, struct genl_info *info) { return devlink_sb_get_from_attrs(devlink, info->attrs); } static int devlink_sb_pool_index_get_from_attrs(struct devlink_sb *devlink_sb, struct nlattr **attrs, u16 *p_pool_index) { u16 val; if (!attrs[DEVLINK_ATTR_SB_POOL_INDEX]) return -EINVAL; val = nla_get_u16(attrs[DEVLINK_ATTR_SB_POOL_INDEX]); if (val >= devlink_sb_pool_count(devlink_sb)) return -EINVAL; *p_pool_index = val; return 0; } static int devlink_sb_pool_index_get_from_info(struct devlink_sb *devlink_sb, struct genl_info *info, u16 *p_pool_index) { return devlink_sb_pool_index_get_from_attrs(devlink_sb, info->attrs, p_pool_index); } static int devlink_sb_pool_type_get_from_attrs(struct nlattr **attrs, enum devlink_sb_pool_type *p_pool_type) { u8 val; if (!attrs[DEVLINK_ATTR_SB_POOL_TYPE]) return -EINVAL; val = nla_get_u8(attrs[DEVLINK_ATTR_SB_POOL_TYPE]); if (val != DEVLINK_SB_POOL_TYPE_INGRESS && val != DEVLINK_SB_POOL_TYPE_EGRESS) return -EINVAL; *p_pool_type = val; return 0; } static int devlink_sb_pool_type_get_from_info(struct genl_info *info, enum devlink_sb_pool_type *p_pool_type) { return devlink_sb_pool_type_get_from_attrs(info->attrs, p_pool_type); } static int devlink_sb_th_type_get_from_attrs(struct nlattr **attrs, enum devlink_sb_threshold_type *p_th_type) { u8 val; if (!attrs[DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE]) return -EINVAL; val = nla_get_u8(attrs[DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE]); if (val != DEVLINK_SB_THRESHOLD_TYPE_STATIC && val != DEVLINK_SB_THRESHOLD_TYPE_DYNAMIC) return -EINVAL; *p_th_type = val; return 0; } static int devlink_sb_th_type_get_from_info(struct genl_info *info, enum devlink_sb_threshold_type *p_th_type) { return devlink_sb_th_type_get_from_attrs(info->attrs, p_th_type); } static int devlink_sb_tc_index_get_from_attrs(struct devlink_sb *devlink_sb, struct nlattr **attrs, enum devlink_sb_pool_type pool_type, u16 *p_tc_index) { u16 val; if (!attrs[DEVLINK_ATTR_SB_TC_INDEX]) return -EINVAL; val = nla_get_u16(attrs[DEVLINK_ATTR_SB_TC_INDEX]); if (pool_type == DEVLINK_SB_POOL_TYPE_INGRESS && val >= devlink_sb->ingress_tc_count) return -EINVAL; if (pool_type == DEVLINK_SB_POOL_TYPE_EGRESS && val >= devlink_sb->egress_tc_count) return -EINVAL; *p_tc_index = val; return 0; } static int devlink_sb_tc_index_get_from_info(struct devlink_sb *devlink_sb, struct genl_info *info, enum devlink_sb_pool_type pool_type, u16 *p_tc_index) { return devlink_sb_tc_index_get_from_attrs(devlink_sb, info->attrs, pool_type, p_tc_index); } #define DEVLINK_NL_FLAG_NEED_DEVLINK BIT(0) #define DEVLINK_NL_FLAG_NEED_PORT BIT(1) #define DEVLINK_NL_FLAG_NEED_SB BIT(2) #define DEVLINK_NL_FLAG_LOCK_PORTS BIT(3) /* port is not needed but we need to ensure they don't * change in the middle of command */ static int devlink_nl_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink; mutex_lock(&devlink_mutex); devlink = devlink_get_from_info(info); if (IS_ERR(devlink)) { mutex_unlock(&devlink_mutex); return PTR_ERR(devlink); } if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_DEVLINK) { info->user_ptr[0] = devlink; } else if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_PORT) { struct devlink_port *devlink_port; mutex_lock(&devlink_port_mutex); devlink_port = devlink_port_get_from_info(devlink, info); if (IS_ERR(devlink_port)) { mutex_unlock(&devlink_port_mutex); mutex_unlock(&devlink_mutex); return PTR_ERR(devlink_port); } info->user_ptr[0] = devlink_port; } if (ops->internal_flags & DEVLINK_NL_FLAG_LOCK_PORTS) { mutex_lock(&devlink_port_mutex); } if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_SB) { struct devlink_sb *devlink_sb; devlink_sb = devlink_sb_get_from_info(devlink, info); if (IS_ERR(devlink_sb)) { if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_PORT) mutex_unlock(&devlink_port_mutex); mutex_unlock(&devlink_mutex); return PTR_ERR(devlink_sb); } info->user_ptr[1] = devlink_sb; } return 0; } static void devlink_nl_post_doit(const struct genl_ops *ops, struct sk_buff *skb, struct genl_info *info) { if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_PORT || ops->internal_flags & DEVLINK_NL_FLAG_LOCK_PORTS) mutex_unlock(&devlink_port_mutex); mutex_unlock(&devlink_mutex); } static struct genl_family devlink_nl_family; enum devlink_multicast_groups { DEVLINK_MCGRP_CONFIG, }; static const struct genl_multicast_group devlink_nl_mcgrps[] = { [DEVLINK_MCGRP_CONFIG] = { .name = DEVLINK_GENL_MCGRP_CONFIG_NAME }, }; static int devlink_nl_put_handle(struct sk_buff *msg, struct devlink *devlink) { if (nla_put_string(msg, DEVLINK_ATTR_BUS_NAME, devlink->dev->bus->name)) return -EMSGSIZE; if (nla_put_string(msg, DEVLINK_ATTR_DEV_NAME, dev_name(devlink->dev))) return -EMSGSIZE; return 0; } static int devlink_nl_fill(struct sk_buff *msg, struct devlink *devlink, enum devlink_command cmd, u32 portid, u32 seq, int flags) { void *hdr; hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); if (!hdr) return -EMSGSIZE; if (devlink_nl_put_handle(msg, devlink)) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static void devlink_notify(struct devlink *devlink, enum devlink_command cmd) { struct sk_buff *msg; int err; WARN_ON(cmd != DEVLINK_CMD_NEW && cmd != DEVLINK_CMD_DEL); msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; err = devlink_nl_fill(msg, devlink, cmd, 0, 0, 0); if (err) { nlmsg_free(msg); return; } genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); } static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink, struct devlink_port *devlink_port, enum devlink_command cmd, u32 portid, u32 seq, int flags) { void *hdr; hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); if (!hdr) return -EMSGSIZE; if (devlink_nl_put_handle(msg, devlink)) goto nla_put_failure; if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index)) goto nla_put_failure; if (nla_put_u16(msg, DEVLINK_ATTR_PORT_TYPE, devlink_port->type)) goto nla_put_failure; if (devlink_port->desired_type != DEVLINK_PORT_TYPE_NOTSET && nla_put_u16(msg, DEVLINK_ATTR_PORT_DESIRED_TYPE, devlink_port->desired_type)) goto nla_put_failure; if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) { struct net_device *netdev = devlink_port->type_dev; if (netdev && (nla_put_u32(msg, DEVLINK_ATTR_PORT_NETDEV_IFINDEX, netdev->ifindex) || nla_put_string(msg, DEVLINK_ATTR_PORT_NETDEV_NAME, netdev->name))) goto nla_put_failure; } if (devlink_port->type == DEVLINK_PORT_TYPE_IB) { struct ib_device *ibdev = devlink_port->type_dev; if (ibdev && nla_put_string(msg, DEVLINK_ATTR_PORT_IBDEV_NAME, ibdev->name)) goto nla_put_failure; } if (devlink_port->split && nla_put_u32(msg, DEVLINK_ATTR_PORT_SPLIT_GROUP, devlink_port->split_group)) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static void devlink_port_notify(struct devlink_port *devlink_port, enum devlink_command cmd) { struct devlink *devlink = devlink_port->devlink; struct sk_buff *msg; int err; if (!devlink_port->registered) return; WARN_ON(cmd != DEVLINK_CMD_PORT_NEW && cmd != DEVLINK_CMD_PORT_DEL); msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; err = devlink_nl_port_fill(msg, devlink, devlink_port, cmd, 0, 0, 0); if (err) { nlmsg_free(msg); return; } genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); } static int devlink_nl_cmd_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct sk_buff *msg; int err; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; err = devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW, info->snd_portid, info->snd_seq, 0); if (err) { nlmsg_free(msg); return err; } return genlmsg_reply(msg, info); } static int devlink_nl_cmd_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb) { struct devlink *devlink; int start = cb->args[0]; int idx = 0; int err; mutex_lock(&devlink_mutex); list_for_each_entry(devlink, &devlink_list, list) { if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) continue; if (idx < start) { idx++; continue; } err = devlink_nl_fill(msg, devlink, DEVLINK_CMD_NEW, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI); if (err) goto out; idx++; } out: mutex_unlock(&devlink_mutex); cb->args[0] = idx; return msg->len; } static int devlink_nl_cmd_port_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[0]; struct devlink *devlink = devlink_port->devlink; struct sk_buff *msg; int err; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; err = devlink_nl_port_fill(msg, devlink, devlink_port, DEVLINK_CMD_PORT_NEW, info->snd_portid, info->snd_seq, 0); if (err) { nlmsg_free(msg); return err; } return genlmsg_reply(msg, info); } static int devlink_nl_cmd_port_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb) { struct devlink *devlink; struct devlink_port *devlink_port; int start = cb->args[0]; int idx = 0; int err; mutex_lock(&devlink_mutex); mutex_lock(&devlink_port_mutex); list_for_each_entry(devlink, &devlink_list, list) { if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) continue; list_for_each_entry(devlink_port, &devlink->port_list, list) { if (idx < start) { idx++; continue; } err = devlink_nl_port_fill(msg, devlink, devlink_port, DEVLINK_CMD_NEW, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI); if (err) goto out; idx++; } } out: mutex_unlock(&devlink_port_mutex); mutex_unlock(&devlink_mutex); cb->args[0] = idx; return msg->len; } static int devlink_port_type_set(struct devlink *devlink, struct devlink_port *devlink_port, enum devlink_port_type port_type) { int err; if (devlink->ops && devlink->ops->port_type_set) { if (port_type == DEVLINK_PORT_TYPE_NOTSET) return -EINVAL; if (port_type == devlink_port->type) return 0; err = devlink->ops->port_type_set(devlink_port, port_type); if (err) return err; devlink_port->desired_type = port_type; devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); return 0; } return -EOPNOTSUPP; } static int devlink_nl_cmd_port_set_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[0]; struct devlink *devlink = devlink_port->devlink; int err; if (info->attrs[DEVLINK_ATTR_PORT_TYPE]) { enum devlink_port_type port_type; port_type = nla_get_u16(info->attrs[DEVLINK_ATTR_PORT_TYPE]); err = devlink_port_type_set(devlink, devlink_port, port_type); if (err) return err; } return 0; } static int devlink_port_split(struct devlink *devlink, u32 port_index, u32 count) { if (devlink->ops && devlink->ops->port_split) return devlink->ops->port_split(devlink, port_index, count); return -EOPNOTSUPP; } static int devlink_nl_cmd_port_split_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; u32 port_index; u32 count; if (!info->attrs[DEVLINK_ATTR_PORT_INDEX] || !info->attrs[DEVLINK_ATTR_PORT_SPLIT_COUNT]) return -EINVAL; port_index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); count = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_SPLIT_COUNT]); return devlink_port_split(devlink, port_index, count); } static int devlink_port_unsplit(struct devlink *devlink, u32 port_index) { if (devlink->ops && devlink->ops->port_unsplit) return devlink->ops->port_unsplit(devlink, port_index); return -EOPNOTSUPP; } static int devlink_nl_cmd_port_unsplit_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; u32 port_index; if (!info->attrs[DEVLINK_ATTR_PORT_INDEX]) return -EINVAL; port_index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); return devlink_port_unsplit(devlink, port_index); } static int devlink_nl_sb_fill(struct sk_buff *msg, struct devlink *devlink, struct devlink_sb *devlink_sb, enum devlink_command cmd, u32 portid, u32 seq, int flags) { void *hdr; hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); if (!hdr) return -EMSGSIZE; if (devlink_nl_put_handle(msg, devlink)) goto nla_put_failure; if (nla_put_u32(msg, DEVLINK_ATTR_SB_INDEX, devlink_sb->index)) goto nla_put_failure; if (nla_put_u32(msg, DEVLINK_ATTR_SB_SIZE, devlink_sb->size)) goto nla_put_failure; if (nla_put_u16(msg, DEVLINK_ATTR_SB_INGRESS_POOL_COUNT, devlink_sb->ingress_pools_count)) goto nla_put_failure; if (nla_put_u16(msg, DEVLINK_ATTR_SB_EGRESS_POOL_COUNT, devlink_sb->egress_pools_count)) goto nla_put_failure; if (nla_put_u16(msg, DEVLINK_ATTR_SB_INGRESS_TC_COUNT, devlink_sb->ingress_tc_count)) goto nla_put_failure; if (nla_put_u16(msg, DEVLINK_ATTR_SB_EGRESS_TC_COUNT, devlink_sb->egress_tc_count)) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static int devlink_nl_cmd_sb_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_sb *devlink_sb = info->user_ptr[1]; struct sk_buff *msg; int err; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; err = devlink_nl_sb_fill(msg, devlink, devlink_sb, DEVLINK_CMD_SB_NEW, info->snd_portid, info->snd_seq, 0); if (err) { nlmsg_free(msg); return err; } return genlmsg_reply(msg, info); } static int devlink_nl_cmd_sb_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb) { struct devlink *devlink; struct devlink_sb *devlink_sb; int start = cb->args[0]; int idx = 0; int err; mutex_lock(&devlink_mutex); list_for_each_entry(devlink, &devlink_list, list) { if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) continue; list_for_each_entry(devlink_sb, &devlink->sb_list, list) { if (idx < start) { idx++; continue; } err = devlink_nl_sb_fill(msg, devlink, devlink_sb, DEVLINK_CMD_SB_NEW, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI); if (err) goto out; idx++; } } out: mutex_unlock(&devlink_mutex); cb->args[0] = idx; return msg->len; } static int devlink_nl_sb_pool_fill(struct sk_buff *msg, struct devlink *devlink, struct devlink_sb *devlink_sb, u16 pool_index, enum devlink_command cmd, u32 portid, u32 seq, int flags) { struct devlink_sb_pool_info pool_info; void *hdr; int err; err = devlink->ops->sb_pool_get(devlink, devlink_sb->index, pool_index, &pool_info); if (err) return err; hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); if (!hdr) return -EMSGSIZE; if (devlink_nl_put_handle(msg, devlink)) goto nla_put_failure; if (nla_put_u32(msg, DEVLINK_ATTR_SB_INDEX, devlink_sb->index)) goto nla_put_failure; if (nla_put_u16(msg, DEVLINK_ATTR_SB_POOL_INDEX, pool_index)) goto nla_put_failure; if (nla_put_u8(msg, DEVLINK_ATTR_SB_POOL_TYPE, pool_info.pool_type)) goto nla_put_failure; if (nla_put_u32(msg, DEVLINK_ATTR_SB_POOL_SIZE, pool_info.size)) goto nla_put_failure; if (nla_put_u8(msg, DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE, pool_info.threshold_type)) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static int devlink_nl_cmd_sb_pool_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_sb *devlink_sb = info->user_ptr[1]; struct sk_buff *msg; u16 pool_index; int err; err = devlink_sb_pool_index_get_from_info(devlink_sb, info, &pool_index); if (err) return err; if (!devlink->ops || !devlink->ops->sb_pool_get) return -EOPNOTSUPP; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; err = devlink_nl_sb_pool_fill(msg, devlink, devlink_sb, pool_index, DEVLINK_CMD_SB_POOL_NEW, info->snd_portid, info->snd_seq, 0); if (err) { nlmsg_free(msg); return err; } return genlmsg_reply(msg, info); } static int __sb_pool_get_dumpit(struct sk_buff *msg, int start, int *p_idx, struct devlink *devlink, struct devlink_sb *devlink_sb, u32 portid, u32 seq) { u16 pool_count = devlink_sb_pool_count(devlink_sb); u16 pool_index; int err; for (pool_index = 0; pool_index < pool_count; pool_index++) { if (*p_idx < start) { (*p_idx)++; continue; } err = devlink_nl_sb_pool_fill(msg, devlink, devlink_sb, pool_index, DEVLINK_CMD_SB_POOL_NEW, portid, seq, NLM_F_MULTI); if (err) return err; (*p_idx)++; } return 0; } static int devlink_nl_cmd_sb_pool_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb) { struct devlink *devlink; struct devlink_sb *devlink_sb; int start = cb->args[0]; int idx = 0; int err; mutex_lock(&devlink_mutex); list_for_each_entry(devlink, &devlink_list, list) { if (!net_eq(devlink_net(devlink), sock_net(msg->sk)) || !devlink->ops || !devlink->ops->sb_pool_get) continue; list_for_each_entry(devlink_sb, &devlink->sb_list, list) { err = __sb_pool_get_dumpit(msg, start, &idx, devlink, devlink_sb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq); if (err && err != -EOPNOTSUPP) goto out; } } out: mutex_unlock(&devlink_mutex); cb->args[0] = idx; return msg->len; } static int devlink_sb_pool_set(struct devlink *devlink, unsigned int sb_index, u16 pool_index, u32 size, enum devlink_sb_threshold_type threshold_type) { const struct devlink_ops *ops = devlink->ops; if (ops && ops->sb_pool_set) return ops->sb_pool_set(devlink, sb_index, pool_index, size, threshold_type); return -EOPNOTSUPP; } static int devlink_nl_cmd_sb_pool_set_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_sb *devlink_sb = info->user_ptr[1]; enum devlink_sb_threshold_type threshold_type; u16 pool_index; u32 size; int err; err = devlink_sb_pool_index_get_from_info(devlink_sb, info, &pool_index); if (err) return err; err = devlink_sb_th_type_get_from_info(info, &threshold_type); if (err) return err; if (!info->attrs[DEVLINK_ATTR_SB_POOL_SIZE]) return -EINVAL; size = nla_get_u32(info->attrs[DEVLINK_ATTR_SB_POOL_SIZE]); return devlink_sb_pool_set(devlink, devlink_sb->index, pool_index, size, threshold_type); } static int devlink_nl_sb_port_pool_fill(struct sk_buff *msg, struct devlink *devlink, struct devlink_port *devlink_port, struct devlink_sb *devlink_sb, u16 pool_index, enum devlink_command cmd, u32 portid, u32 seq, int flags) { const struct devlink_ops *ops = devlink->ops; u32 threshold; void *hdr; int err; err = ops->sb_port_pool_get(devlink_port, devlink_sb->index, pool_index, &threshold); if (err) return err; hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); if (!hdr) return -EMSGSIZE; if (devlink_nl_put_handle(msg, devlink)) goto nla_put_failure; if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index)) goto nla_put_failure; if (nla_put_u32(msg, DEVLINK_ATTR_SB_INDEX, devlink_sb->index)) goto nla_put_failure; if (nla_put_u16(msg, DEVLINK_ATTR_SB_POOL_INDEX, pool_index)) goto nla_put_failure; if (nla_put_u32(msg, DEVLINK_ATTR_SB_THRESHOLD, threshold)) goto nla_put_failure; if (ops->sb_occ_port_pool_get) { u32 cur; u32 max; err = ops->sb_occ_port_pool_get(devlink_port, devlink_sb->index, pool_index, &cur, &max); if (err && err != -EOPNOTSUPP) goto sb_occ_get_failure; if (!err) { if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_CUR, cur)) goto nla_put_failure; if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_MAX, max)) goto nla_put_failure; } } genlmsg_end(msg, hdr); return 0; nla_put_failure: err = -EMSGSIZE; sb_occ_get_failure: genlmsg_cancel(msg, hdr); return err; } static int devlink_nl_cmd_sb_port_pool_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[0]; struct devlink *devlink = devlink_port->devlink; struct devlink_sb *devlink_sb = info->user_ptr[1]; struct sk_buff *msg; u16 pool_index; int err; err = devlink_sb_pool_index_get_from_info(devlink_sb, info, &pool_index); if (err) return err; if (!devlink->ops || !devlink->ops->sb_port_pool_get) return -EOPNOTSUPP; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; err = devlink_nl_sb_port_pool_fill(msg, devlink, devlink_port, devlink_sb, pool_index, DEVLINK_CMD_SB_PORT_POOL_NEW, info->snd_portid, info->snd_seq, 0); if (err) { nlmsg_free(msg); return err; } return genlmsg_reply(msg, info); } static int __sb_port_pool_get_dumpit(struct sk_buff *msg, int start, int *p_idx, struct devlink *devlink, struct devlink_sb *devlink_sb, u32 portid, u32 seq) { struct devlink_port *devlink_port; u16 pool_count = devlink_sb_pool_count(devlink_sb); u16 pool_index; int err; list_for_each_entry(devlink_port, &devlink->port_list, list) { for (pool_index = 0; pool_index < pool_count; pool_index++) { if (*p_idx < start) { (*p_idx)++; continue; } err = devlink_nl_sb_port_pool_fill(msg, devlink, devlink_port, devlink_sb, pool_index, DEVLINK_CMD_SB_PORT_POOL_NEW, portid, seq, NLM_F_MULTI); if (err) return err; (*p_idx)++; } } return 0; } static int devlink_nl_cmd_sb_port_pool_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb) { struct devlink *devlink; struct devlink_sb *devlink_sb; int start = cb->args[0]; int idx = 0; int err; mutex_lock(&devlink_mutex); mutex_lock(&devlink_port_mutex); list_for_each_entry(devlink, &devlink_list, list) { if (!net_eq(devlink_net(devlink), sock_net(msg->sk)) || !devlink->ops || !devlink->ops->sb_port_pool_get) continue; list_for_each_entry(devlink_sb, &devlink->sb_list, list) { err = __sb_port_pool_get_dumpit(msg, start, &idx, devlink, devlink_sb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq); if (err && err != -EOPNOTSUPP) goto out; } } out: mutex_unlock(&devlink_port_mutex); mutex_unlock(&devlink_mutex); cb->args[0] = idx; return msg->len; } static int devlink_sb_port_pool_set(struct devlink_port *devlink_port, unsigned int sb_index, u16 pool_index, u32 threshold) { const struct devlink_ops *ops = devlink_port->devlink->ops; if (ops && ops->sb_port_pool_set) return ops->sb_port_pool_set(devlink_port, sb_index, pool_index, threshold); return -EOPNOTSUPP; } static int devlink_nl_cmd_sb_port_pool_set_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[0]; struct devlink_sb *devlink_sb = info->user_ptr[1]; u16 pool_index; u32 threshold; int err; err = devlink_sb_pool_index_get_from_info(devlink_sb, info, &pool_index); if (err) return err; if (!info->attrs[DEVLINK_ATTR_SB_THRESHOLD]) return -EINVAL; threshold = nla_get_u32(info->attrs[DEVLINK_ATTR_SB_THRESHOLD]); return devlink_sb_port_pool_set(devlink_port, devlink_sb->index, pool_index, threshold); } static int devlink_nl_sb_tc_pool_bind_fill(struct sk_buff *msg, struct devlink *devlink, struct devlink_port *devlink_port, struct devlink_sb *devlink_sb, u16 tc_index, enum devlink_sb_pool_type pool_type, enum devlink_command cmd, u32 portid, u32 seq, int flags) { const struct devlink_ops *ops = devlink->ops; u16 pool_index; u32 threshold; void *hdr; int err; err = ops->sb_tc_pool_bind_get(devlink_port, devlink_sb->index, tc_index, pool_type, &pool_index, &threshold); if (err) return err; hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); if (!hdr) return -EMSGSIZE; if (devlink_nl_put_handle(msg, devlink)) goto nla_put_failure; if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index)) goto nla_put_failure; if (nla_put_u32(msg, DEVLINK_ATTR_SB_INDEX, devlink_sb->index)) goto nla_put_failure; if (nla_put_u16(msg, DEVLINK_ATTR_SB_TC_INDEX, tc_index)) goto nla_put_failure; if (nla_put_u8(msg, DEVLINK_ATTR_SB_POOL_TYPE, pool_type)) goto nla_put_failure; if (nla_put_u16(msg, DEVLINK_ATTR_SB_POOL_INDEX, pool_index)) goto nla_put_failure; if (nla_put_u32(msg, DEVLINK_ATTR_SB_THRESHOLD, threshold)) goto nla_put_failure; if (ops->sb_occ_tc_port_bind_get) { u32 cur; u32 max; err = ops->sb_occ_tc_port_bind_get(devlink_port, devlink_sb->index, tc_index, pool_type, &cur, &max); if (err && err != -EOPNOTSUPP) return err; if (!err) { if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_CUR, cur)) goto nla_put_failure; if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_MAX, max)) goto nla_put_failure; } } genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } static int devlink_nl_cmd_sb_tc_pool_bind_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[0]; struct devlink *devlink = devlink_port->devlink; struct devlink_sb *devlink_sb = info->user_ptr[1]; struct sk_buff *msg; enum devlink_sb_pool_type pool_type; u16 tc_index; int err; err = devlink_sb_pool_type_get_from_info(info, &pool_type); if (err) return err; err = devlink_sb_tc_index_get_from_info(devlink_sb, info, pool_type, &tc_index); if (err) return err; if (!devlink->ops || !devlink->ops->sb_tc_pool_bind_get) return -EOPNOTSUPP; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; err = devlink_nl_sb_tc_pool_bind_fill(msg, devlink, devlink_port, devlink_sb, tc_index, pool_type, DEVLINK_CMD_SB_TC_POOL_BIND_NEW, info->snd_portid, info->snd_seq, 0); if (err) { nlmsg_free(msg); return err; } return genlmsg_reply(msg, info); } static int __sb_tc_pool_bind_get_dumpit(struct sk_buff *msg, int start, int *p_idx, struct devlink *devlink, struct devlink_sb *devlink_sb, u32 portid, u32 seq) { struct devlink_port *devlink_port; u16 tc_index; int err; list_for_each_entry(devlink_port, &devlink->port_list, list) { for (tc_index = 0; tc_index < devlink_sb->ingress_tc_count; tc_index++) { if (*p_idx < start) { (*p_idx)++; continue; } err = devlink_nl_sb_tc_pool_bind_fill(msg, devlink, devlink_port, devlink_sb, tc_index, DEVLINK_SB_POOL_TYPE_INGRESS, DEVLINK_CMD_SB_TC_POOL_BIND_NEW, portid, seq, NLM_F_MULTI); if (err) return err; (*p_idx)++; } for (tc_index = 0; tc_index < devlink_sb->egress_tc_count; tc_index++) { if (*p_idx < start) { (*p_idx)++; continue; } err = devlink_nl_sb_tc_pool_bind_fill(msg, devlink, devlink_port, devlink_sb, tc_index, DEVLINK_SB_POOL_TYPE_EGRESS, DEVLINK_CMD_SB_TC_POOL_BIND_NEW, portid, seq, NLM_F_MULTI); if (err) return err; (*p_idx)++; } } return 0; } static int devlink_nl_cmd_sb_tc_pool_bind_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb) { struct devlink *devlink; struct devlink_sb *devlink_sb; int start = cb->args[0]; int idx = 0; int err; mutex_lock(&devlink_mutex); mutex_lock(&devlink_port_mutex); list_for_each_entry(devlink, &devlink_list, list) { if (!net_eq(devlink_net(devlink), sock_net(msg->sk)) || !devlink->ops || !devlink->ops->sb_tc_pool_bind_get) continue; list_for_each_entry(devlink_sb, &devlink->sb_list, list) { err = __sb_tc_pool_bind_get_dumpit(msg, start, &idx, devlink, devlink_sb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq); if (err && err != -EOPNOTSUPP) goto out; } } out: mutex_unlock(&devlink_port_mutex); mutex_unlock(&devlink_mutex); cb->args[0] = idx; return msg->len; } static int devlink_sb_tc_pool_bind_set(struct devlink_port *devlink_port, unsigned int sb_index, u16 tc_index, enum devlink_sb_pool_type pool_type, u16 pool_index, u32 threshold) { const struct devlink_ops *ops = devlink_port->devlink->ops; if (ops && ops->sb_tc_pool_bind_set) return ops->sb_tc_pool_bind_set(devlink_port, sb_index, tc_index, pool_type, pool_index, threshold); return -EOPNOTSUPP; } static int devlink_nl_cmd_sb_tc_pool_bind_set_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[0]; struct devlink_sb *devlink_sb = info->user_ptr[1]; enum devlink_sb_pool_type pool_type; u16 tc_index; u16 pool_index; u32 threshold; int err; err = devlink_sb_pool_type_get_from_info(info, &pool_type); if (err) return err; err = devlink_sb_tc_index_get_from_info(devlink_sb, info, pool_type, &tc_index); if (err) return err; err = devlink_sb_pool_index_get_from_info(devlink_sb, info, &pool_index); if (err) return err; if (!info->attrs[DEVLINK_ATTR_SB_THRESHOLD]) return -EINVAL; threshold = nla_get_u32(info->attrs[DEVLINK_ATTR_SB_THRESHOLD]); return devlink_sb_tc_pool_bind_set(devlink_port, devlink_sb->index, tc_index, pool_type, pool_index, threshold); } static int devlink_nl_cmd_sb_occ_snapshot_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_sb *devlink_sb = info->user_ptr[1]; const struct devlink_ops *ops = devlink->ops; if (ops && ops->sb_occ_snapshot) return ops->sb_occ_snapshot(devlink, devlink_sb->index); return -EOPNOTSUPP; } static int devlink_nl_cmd_sb_occ_max_clear_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_sb *devlink_sb = info->user_ptr[1]; const struct devlink_ops *ops = devlink->ops; if (ops && ops->sb_occ_max_clear) return ops->sb_occ_max_clear(devlink, devlink_sb->index); return -EOPNOTSUPP; } static int devlink_nl_eswitch_fill(struct sk_buff *msg, struct devlink *devlink, enum devlink_command cmd, u32 portid, u32 seq, int flags) { const struct devlink_ops *ops = devlink->ops; u8 inline_mode, encap_mode; void *hdr; int err = 0; u16 mode; hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); if (!hdr) return -EMSGSIZE; err = devlink_nl_put_handle(msg, devlink); if (err) goto nla_put_failure; if (ops->eswitch_mode_get) { err = ops->eswitch_mode_get(devlink, &mode); if (err) goto nla_put_failure; err = nla_put_u16(msg, DEVLINK_ATTR_ESWITCH_MODE, mode); if (err) goto nla_put_failure; } if (ops->eswitch_inline_mode_get) { err = ops->eswitch_inline_mode_get(devlink, &inline_mode); if (err) goto nla_put_failure; err = nla_put_u8(msg, DEVLINK_ATTR_ESWITCH_INLINE_MODE, inline_mode); if (err) goto nla_put_failure; } if (ops->eswitch_encap_mode_get) { err = ops->eswitch_encap_mode_get(devlink, &encap_mode); if (err) goto nla_put_failure; err = nla_put_u8(msg, DEVLINK_ATTR_ESWITCH_ENCAP_MODE, encap_mode); if (err) goto nla_put_failure; } genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return err; } static int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; const struct devlink_ops *ops = devlink->ops; struct sk_buff *msg; int err; if (!ops) return -EOPNOTSUPP; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; err = devlink_nl_eswitch_fill(msg, devlink, DEVLINK_CMD_ESWITCH_GET, info->snd_portid, info->snd_seq, 0); if (err) { nlmsg_free(msg); return err; } return genlmsg_reply(msg, info); } static int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; const struct devlink_ops *ops = devlink->ops; u8 inline_mode, encap_mode; int err = 0; u16 mode; if (!ops) return -EOPNOTSUPP; if (info->attrs[DEVLINK_ATTR_ESWITCH_MODE]) { if (!ops->eswitch_mode_set) return -EOPNOTSUPP; mode = nla_get_u16(info->attrs[DEVLINK_ATTR_ESWITCH_MODE]); err = ops->eswitch_mode_set(devlink, mode); if (err) return err; } if (info->attrs[DEVLINK_ATTR_ESWITCH_INLINE_MODE]) { if (!ops->eswitch_inline_mode_set) return -EOPNOTSUPP; inline_mode = nla_get_u8( info->attrs[DEVLINK_ATTR_ESWITCH_INLINE_MODE]); err = ops->eswitch_inline_mode_set(devlink, inline_mode); if (err) return err; } if (info->attrs[DEVLINK_ATTR_ESWITCH_ENCAP_MODE]) { if (!ops->eswitch_encap_mode_set) return -EOPNOTSUPP; encap_mode = nla_get_u8(info->attrs[DEVLINK_ATTR_ESWITCH_ENCAP_MODE]); err = ops->eswitch_encap_mode_set(devlink, encap_mode); if (err) return err; } return 0; } int devlink_dpipe_match_put(struct sk_buff *skb, struct devlink_dpipe_match *match) { struct devlink_dpipe_header *header = match->header; struct devlink_dpipe_field *field = &header->fields[match->field_id]; struct nlattr *match_attr; match_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_MATCH); if (!match_attr) return -EMSGSIZE; if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_MATCH_TYPE, match->type) || nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_INDEX, match->header_index) || nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) || nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) || nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global)) goto nla_put_failure; nla_nest_end(skb, match_attr); return 0; nla_put_failure: nla_nest_cancel(skb, match_attr); return -EMSGSIZE; } EXPORT_SYMBOL_GPL(devlink_dpipe_match_put); static int devlink_dpipe_matches_put(struct devlink_dpipe_table *table, struct sk_buff *skb) { struct nlattr *matches_attr; matches_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLE_MATCHES); if (!matches_attr) return -EMSGSIZE; if (table->table_ops->matches_dump(table->priv, skb)) goto nla_put_failure; nla_nest_end(skb, matches_attr); return 0; nla_put_failure: nla_nest_cancel(skb, matches_attr); return -EMSGSIZE; } int devlink_dpipe_action_put(struct sk_buff *skb, struct devlink_dpipe_action *action) { struct devlink_dpipe_header *header = action->header; struct devlink_dpipe_field *field = &header->fields[action->field_id]; struct nlattr *action_attr; action_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_ACTION); if (!action_attr) return -EMSGSIZE; if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_ACTION_TYPE, action->type) || nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_INDEX, action->header_index) || nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) || nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) || nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global)) goto nla_put_failure; nla_nest_end(skb, action_attr); return 0; nla_put_failure: nla_nest_cancel(skb, action_attr); return -EMSGSIZE; } EXPORT_SYMBOL_GPL(devlink_dpipe_action_put); static int devlink_dpipe_actions_put(struct devlink_dpipe_table *table, struct sk_buff *skb) { struct nlattr *actions_attr; actions_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLE_ACTIONS); if (!actions_attr) return -EMSGSIZE; if (table->table_ops->actions_dump(table->priv, skb)) goto nla_put_failure; nla_nest_end(skb, actions_attr); return 0; nla_put_failure: nla_nest_cancel(skb, actions_attr); return -EMSGSIZE; } static int devlink_dpipe_table_put(struct sk_buff *skb, struct devlink_dpipe_table *table) { struct nlattr *table_attr; u64 table_size; table_size = table->table_ops->size_get(table->priv); table_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLE); if (!table_attr) return -EMSGSIZE; if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_TABLE_NAME, table->name) || nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_TABLE_SIZE, table_size, DEVLINK_ATTR_PAD)) goto nla_put_failure; if (nla_put_u8(skb, DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED, table->counters_enabled)) goto nla_put_failure; if (devlink_dpipe_matches_put(table, skb)) goto nla_put_failure; if (devlink_dpipe_actions_put(table, skb)) goto nla_put_failure; nla_nest_end(skb, table_attr); return 0; nla_put_failure: nla_nest_cancel(skb, table_attr); return -EMSGSIZE; } static int devlink_dpipe_send_and_alloc_skb(struct sk_buff **pskb, struct genl_info *info) { int err; if (*pskb) { err = genlmsg_reply(*pskb, info); if (err) return err; } *pskb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!*pskb) return -ENOMEM; return 0; } static int devlink_dpipe_tables_fill(struct genl_info *info, enum devlink_command cmd, int flags, struct list_head *dpipe_tables, const char *table_name) { struct devlink *devlink = info->user_ptr[0]; struct devlink_dpipe_table *table; struct nlattr *tables_attr; struct sk_buff *skb = NULL; struct nlmsghdr *nlh; bool incomplete; void *hdr; int i; int err; table = list_first_entry(dpipe_tables, struct devlink_dpipe_table, list); start_again: err = devlink_dpipe_send_and_alloc_skb(&skb, info); if (err) return err; hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq, &devlink_nl_family, NLM_F_MULTI, cmd); if (!hdr) { nlmsg_free(skb); return -EMSGSIZE; } if (devlink_nl_put_handle(skb, devlink)) goto nla_put_failure; tables_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_TABLES); if (!tables_attr) goto nla_put_failure; i = 0; incomplete = false; list_for_each_entry_from(table, dpipe_tables, list) { if (!table_name) { err = devlink_dpipe_table_put(skb, table); if (err) { if (!i) goto err_table_put; incomplete = true; break; } } else { if (!strcmp(table->name, table_name)) { err = devlink_dpipe_table_put(skb, table); if (err) break; } } i++; } nla_nest_end(skb, tables_attr); genlmsg_end(skb, hdr); if (incomplete) goto start_again; send_done: nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq, NLMSG_DONE, 0, flags | NLM_F_MULTI); if (!nlh) { err = devlink_dpipe_send_and_alloc_skb(&skb, info); if (err) return err; goto send_done; } return genlmsg_reply(skb, info); nla_put_failure: err = -EMSGSIZE; err_table_put: genlmsg_cancel(skb, hdr); nlmsg_free(skb); return err; } static int devlink_nl_cmd_dpipe_table_get(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; const char *table_name = NULL; if (info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]) table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]); return devlink_dpipe_tables_fill(info, DEVLINK_CMD_DPIPE_TABLE_GET, 0, &devlink->dpipe_table_list, table_name); } static int devlink_dpipe_value_put(struct sk_buff *skb, struct devlink_dpipe_value *value) { if (nla_put(skb, DEVLINK_ATTR_DPIPE_VALUE, value->value_size, value->value)) return -EMSGSIZE; if (value->mask) if (nla_put(skb, DEVLINK_ATTR_DPIPE_VALUE_MASK, value->value_size, value->mask)) return -EMSGSIZE; if (value->mapping_valid) if (nla_put_u32(skb, DEVLINK_ATTR_DPIPE_VALUE_MAPPING, value->mapping_value)) return -EMSGSIZE; return 0; } static int devlink_dpipe_action_value_put(struct sk_buff *skb, struct devlink_dpipe_value *value) { if (!value->action) return -EINVAL; if (devlink_dpipe_action_put(skb, value->action)) return -EMSGSIZE; if (devlink_dpipe_value_put(skb, value)) return -EMSGSIZE; return 0; } static int devlink_dpipe_action_values_put(struct sk_buff *skb, struct devlink_dpipe_value *values, unsigned int values_count) { struct nlattr *action_attr; int i; int err; for (i = 0; i < values_count; i++) { action_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_ACTION_VALUE); if (!action_attr) return -EMSGSIZE; err = devlink_dpipe_action_value_put(skb, &values[i]); if (err) goto err_action_value_put; nla_nest_end(skb, action_attr); } return 0; err_action_value_put: nla_nest_cancel(skb, action_attr); return err; } static int devlink_dpipe_match_value_put(struct sk_buff *skb, struct devlink_dpipe_value *value) { if (!value->match) return -EINVAL; if (devlink_dpipe_match_put(skb, value->match)) return -EMSGSIZE; if (devlink_dpipe_value_put(skb, value)) return -EMSGSIZE; return 0; } static int devlink_dpipe_match_values_put(struct sk_buff *skb, struct devlink_dpipe_value *values, unsigned int values_count) { struct nlattr *match_attr; int i; int err; for (i = 0; i < values_count; i++) { match_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_MATCH_VALUE); if (!match_attr) return -EMSGSIZE; err = devlink_dpipe_match_value_put(skb, &values[i]); if (err) goto err_match_value_put; nla_nest_end(skb, match_attr); } return 0; err_match_value_put: nla_nest_cancel(skb, match_attr); return err; } static int devlink_dpipe_entry_put(struct sk_buff *skb, struct devlink_dpipe_entry *entry) { struct nlattr *entry_attr, *matches_attr, *actions_attr; int err; entry_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_ENTRY); if (!entry_attr) return -EMSGSIZE; if (nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_ENTRY_INDEX, entry->index, DEVLINK_ATTR_PAD)) goto nla_put_failure; if (entry->counter_valid) if (nla_put_u64_64bit(skb, DEVLINK_ATTR_DPIPE_ENTRY_COUNTER, entry->counter, DEVLINK_ATTR_PAD)) goto nla_put_failure; matches_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_ENTRY_MATCH_VALUES); if (!matches_attr) goto nla_put_failure; err = devlink_dpipe_match_values_put(skb, entry->match_values, entry->match_values_count); if (err) { nla_nest_cancel(skb, matches_attr); goto err_match_values_put; } nla_nest_end(skb, matches_attr); actions_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_ENTRY_ACTION_VALUES); if (!actions_attr) goto nla_put_failure; err = devlink_dpipe_action_values_put(skb, entry->action_values, entry->action_values_count); if (err) { nla_nest_cancel(skb, actions_attr); goto err_action_values_put; } nla_nest_end(skb, actions_attr); nla_nest_end(skb, entry_attr); return 0; nla_put_failure: err = -EMSGSIZE; err_match_values_put: err_action_values_put: nla_nest_cancel(skb, entry_attr); return err; } static struct devlink_dpipe_table * devlink_dpipe_table_find(struct list_head *dpipe_tables, const char *table_name) { struct devlink_dpipe_table *table; list_for_each_entry_rcu(table, dpipe_tables, list) { if (!strcmp(table->name, table_name)) return table; } return NULL; } int devlink_dpipe_entry_ctx_prepare(struct devlink_dpipe_dump_ctx *dump_ctx) { struct devlink *devlink; int err; err = devlink_dpipe_send_and_alloc_skb(&dump_ctx->skb, dump_ctx->info); if (err) return err; dump_ctx->hdr = genlmsg_put(dump_ctx->skb, dump_ctx->info->snd_portid, dump_ctx->info->snd_seq, &devlink_nl_family, NLM_F_MULTI, dump_ctx->cmd); if (!dump_ctx->hdr) goto nla_put_failure; devlink = dump_ctx->info->user_ptr[0]; if (devlink_nl_put_handle(dump_ctx->skb, devlink)) goto nla_put_failure; dump_ctx->nest = nla_nest_start(dump_ctx->skb, DEVLINK_ATTR_DPIPE_ENTRIES); if (!dump_ctx->nest) goto nla_put_failure; return 0; nla_put_failure: genlmsg_cancel(dump_ctx->skb, dump_ctx->hdr); nlmsg_free(dump_ctx->skb); return -EMSGSIZE; } EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_prepare); int devlink_dpipe_entry_ctx_append(struct devlink_dpipe_dump_ctx *dump_ctx, struct devlink_dpipe_entry *entry) { return devlink_dpipe_entry_put(dump_ctx->skb, entry); } EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_append); int devlink_dpipe_entry_ctx_close(struct devlink_dpipe_dump_ctx *dump_ctx) { nla_nest_end(dump_ctx->skb, dump_ctx->nest); genlmsg_end(dump_ctx->skb, dump_ctx->hdr); return 0; } EXPORT_SYMBOL_GPL(devlink_dpipe_entry_ctx_close); void devlink_dpipe_entry_clear(struct devlink_dpipe_entry *entry) { unsigned int value_count, value_index; struct devlink_dpipe_value *value; value = entry->action_values; value_count = entry->action_values_count; for (value_index = 0; value_index < value_count; value_index++) { kfree(value[value_index].value); kfree(value[value_index].mask); } value = entry->match_values; value_count = entry->match_values_count; for (value_index = 0; value_index < value_count; value_index++) { kfree(value[value_index].value); kfree(value[value_index].mask); } } EXPORT_SYMBOL(devlink_dpipe_entry_clear); static int devlink_dpipe_entries_fill(struct genl_info *info, enum devlink_command cmd, int flags, struct devlink_dpipe_table *table) { struct devlink_dpipe_dump_ctx dump_ctx; struct nlmsghdr *nlh; int err; dump_ctx.skb = NULL; dump_ctx.cmd = cmd; dump_ctx.info = info; err = table->table_ops->entries_dump(table->priv, table->counters_enabled, &dump_ctx); if (err) return err; send_done: nlh = nlmsg_put(dump_ctx.skb, info->snd_portid, info->snd_seq, NLMSG_DONE, 0, flags | NLM_F_MULTI); if (!nlh) { err = devlink_dpipe_send_and_alloc_skb(&dump_ctx.skb, info); if (err) return err; goto send_done; } return genlmsg_reply(dump_ctx.skb, info); } static int devlink_nl_cmd_dpipe_entries_get(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_dpipe_table *table; const char *table_name; if (!info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]) return -EINVAL; table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]); table = devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name); if (!table) return -EINVAL; if (!table->table_ops->entries_dump) return -EINVAL; return devlink_dpipe_entries_fill(info, DEVLINK_CMD_DPIPE_ENTRIES_GET, 0, table); } static int devlink_dpipe_fields_put(struct sk_buff *skb, const struct devlink_dpipe_header *header) { struct devlink_dpipe_field *field; struct nlattr *field_attr; int i; for (i = 0; i < header->fields_count; i++) { field = &header->fields[i]; field_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_FIELD); if (!field_attr) return -EMSGSIZE; if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_FIELD_NAME, field->name) || nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_ID, field->id) || nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_BITWIDTH, field->bitwidth) || nla_put_u32(skb, DEVLINK_ATTR_DPIPE_FIELD_MAPPING_TYPE, field->mapping_type)) goto nla_put_failure; nla_nest_end(skb, field_attr); } return 0; nla_put_failure: nla_nest_cancel(skb, field_attr); return -EMSGSIZE; } static int devlink_dpipe_header_put(struct sk_buff *skb, struct devlink_dpipe_header *header) { struct nlattr *fields_attr, *header_attr; int err; header_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_HEADER); if (!header_attr) return -EMSGSIZE; if (nla_put_string(skb, DEVLINK_ATTR_DPIPE_HEADER_NAME, header->name) || nla_put_u32(skb, DEVLINK_ATTR_DPIPE_HEADER_ID, header->id) || nla_put_u8(skb, DEVLINK_ATTR_DPIPE_HEADER_GLOBAL, header->global)) goto nla_put_failure; fields_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_HEADER_FIELDS); if (!fields_attr) goto nla_put_failure; err = devlink_dpipe_fields_put(skb, header); if (err) { nla_nest_cancel(skb, fields_attr); goto nla_put_failure; } nla_nest_end(skb, fields_attr); nla_nest_end(skb, header_attr); return 0; nla_put_failure: err = -EMSGSIZE; nla_nest_cancel(skb, header_attr); return err; } static int devlink_dpipe_headers_fill(struct genl_info *info, enum devlink_command cmd, int flags, struct devlink_dpipe_headers * dpipe_headers) { struct devlink *devlink = info->user_ptr[0]; struct nlattr *headers_attr; struct sk_buff *skb = NULL; struct nlmsghdr *nlh; void *hdr; int i, j; int err; i = 0; start_again: err = devlink_dpipe_send_and_alloc_skb(&skb, info); if (err) return err; hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq, &devlink_nl_family, NLM_F_MULTI, cmd); if (!hdr) { nlmsg_free(skb); return -EMSGSIZE; } if (devlink_nl_put_handle(skb, devlink)) goto nla_put_failure; headers_attr = nla_nest_start(skb, DEVLINK_ATTR_DPIPE_HEADERS); if (!headers_attr) goto nla_put_failure; j = 0; for (; i < dpipe_headers->headers_count; i++) { err = devlink_dpipe_header_put(skb, dpipe_headers->headers[i]); if (err) { if (!j) goto err_table_put; break; } j++; } nla_nest_end(skb, headers_attr); genlmsg_end(skb, hdr); if (i != dpipe_headers->headers_count) goto start_again; send_done: nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq, NLMSG_DONE, 0, flags | NLM_F_MULTI); if (!nlh) { err = devlink_dpipe_send_and_alloc_skb(&skb, info); if (err) return err; goto send_done; } return genlmsg_reply(skb, info); nla_put_failure: err = -EMSGSIZE; err_table_put: genlmsg_cancel(skb, hdr); nlmsg_free(skb); return err; } static int devlink_nl_cmd_dpipe_headers_get(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; if (!devlink->dpipe_headers) return -EOPNOTSUPP; return devlink_dpipe_headers_fill(info, DEVLINK_CMD_DPIPE_HEADERS_GET, 0, devlink->dpipe_headers); } static int devlink_dpipe_table_counters_set(struct devlink *devlink, const char *table_name, bool enable) { struct devlink_dpipe_table *table; table = devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name); if (!table) return -EINVAL; if (table->counter_control_extern) return -EOPNOTSUPP; if (!(table->counters_enabled ^ enable)) return 0; table->counters_enabled = enable; if (table->table_ops->counters_set_update) table->table_ops->counters_set_update(table->priv, enable); return 0; } static int devlink_nl_cmd_dpipe_table_counters_set(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; const char *table_name; bool counters_enable; if (!info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME] || !info->attrs[DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED]) return -EINVAL; table_name = nla_data(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_NAME]); counters_enable = !!nla_get_u8(info->attrs[DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED]); return devlink_dpipe_table_counters_set(devlink, table_name, counters_enable); } static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32 }, [DEVLINK_ATTR_PORT_TYPE] = { .type = NLA_U16 }, [DEVLINK_ATTR_PORT_SPLIT_COUNT] = { .type = NLA_U32 }, [DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32 }, [DEVLINK_ATTR_SB_POOL_INDEX] = { .type = NLA_U16 }, [DEVLINK_ATTR_SB_POOL_TYPE] = { .type = NLA_U8 }, [DEVLINK_ATTR_SB_POOL_SIZE] = { .type = NLA_U32 }, [DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE] = { .type = NLA_U8 }, [DEVLINK_ATTR_SB_THRESHOLD] = { .type = NLA_U32 }, [DEVLINK_ATTR_SB_TC_INDEX] = { .type = NLA_U16 }, [DEVLINK_ATTR_ESWITCH_MODE] = { .type = NLA_U16 }, [DEVLINK_ATTR_ESWITCH_INLINE_MODE] = { .type = NLA_U8 }, [DEVLINK_ATTR_ESWITCH_ENCAP_MODE] = { .type = NLA_U8 }, [DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED] = { .type = NLA_U8 }, }; static const struct genl_ops devlink_nl_ops[] = { { .cmd = DEVLINK_CMD_GET, .doit = devlink_nl_cmd_get_doit, .dumpit = devlink_nl_cmd_get_dumpit, .policy = devlink_nl_policy, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, /* can be retrieved by unprivileged users */ }, { .cmd = DEVLINK_CMD_PORT_GET, .doit = devlink_nl_cmd_port_get_doit, .dumpit = devlink_nl_cmd_port_get_dumpit, .policy = devlink_nl_policy, .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, /* can be retrieved by unprivileged users */ }, { .cmd = DEVLINK_CMD_PORT_SET, .doit = devlink_nl_cmd_port_set_doit, .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, }, { .cmd = DEVLINK_CMD_PORT_SPLIT, .doit = devlink_nl_cmd_port_split_doit, .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, { .cmd = DEVLINK_CMD_PORT_UNSPLIT, .doit = devlink_nl_cmd_port_unsplit_doit, .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, { .cmd = DEVLINK_CMD_SB_GET, .doit = devlink_nl_cmd_sb_get_doit, .dumpit = devlink_nl_cmd_sb_get_dumpit, .policy = devlink_nl_policy, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | DEVLINK_NL_FLAG_NEED_SB, /* can be retrieved by unprivileged users */ }, { .cmd = DEVLINK_CMD_SB_POOL_GET, .doit = devlink_nl_cmd_sb_pool_get_doit, .dumpit = devlink_nl_cmd_sb_pool_get_dumpit, .policy = devlink_nl_policy, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | DEVLINK_NL_FLAG_NEED_SB, /* can be retrieved by unprivileged users */ }, { .cmd = DEVLINK_CMD_SB_POOL_SET, .doit = devlink_nl_cmd_sb_pool_set_doit, .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | DEVLINK_NL_FLAG_NEED_SB, }, { .cmd = DEVLINK_CMD_SB_PORT_POOL_GET, .doit = devlink_nl_cmd_sb_port_pool_get_doit, .dumpit = devlink_nl_cmd_sb_port_pool_get_dumpit, .policy = devlink_nl_policy, .internal_flags = DEVLINK_NL_FLAG_NEED_PORT | DEVLINK_NL_FLAG_NEED_SB, /* can be retrieved by unprivileged users */ }, { .cmd = DEVLINK_CMD_SB_PORT_POOL_SET, .doit = devlink_nl_cmd_sb_port_pool_set_doit, .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_PORT | DEVLINK_NL_FLAG_NEED_SB, }, { .cmd = DEVLINK_CMD_SB_TC_POOL_BIND_GET, .doit = devlink_nl_cmd_sb_tc_pool_bind_get_doit, .dumpit = devlink_nl_cmd_sb_tc_pool_bind_get_dumpit, .policy = devlink_nl_policy, .internal_flags = DEVLINK_NL_FLAG_NEED_PORT | DEVLINK_NL_FLAG_NEED_SB, /* can be retrieved by unprivileged users */ }, { .cmd = DEVLINK_CMD_SB_TC_POOL_BIND_SET, .doit = devlink_nl_cmd_sb_tc_pool_bind_set_doit, .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_PORT | DEVLINK_NL_FLAG_NEED_SB, }, { .cmd = DEVLINK_CMD_SB_OCC_SNAPSHOT, .doit = devlink_nl_cmd_sb_occ_snapshot_doit, .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | DEVLINK_NL_FLAG_NEED_SB | DEVLINK_NL_FLAG_LOCK_PORTS, }, { .cmd = DEVLINK_CMD_SB_OCC_MAX_CLEAR, .doit = devlink_nl_cmd_sb_occ_max_clear_doit, .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | DEVLINK_NL_FLAG_NEED_SB | DEVLINK_NL_FLAG_LOCK_PORTS, }, { .cmd = DEVLINK_CMD_ESWITCH_GET, .doit = devlink_nl_cmd_eswitch_get_doit, .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, { .cmd = DEVLINK_CMD_ESWITCH_SET, .doit = devlink_nl_cmd_eswitch_set_doit, .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, { .cmd = DEVLINK_CMD_DPIPE_TABLE_GET, .doit = devlink_nl_cmd_dpipe_table_get, .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, { .cmd = DEVLINK_CMD_DPIPE_ENTRIES_GET, .doit = devlink_nl_cmd_dpipe_entries_get, .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, { .cmd = DEVLINK_CMD_DPIPE_HEADERS_GET, .doit = devlink_nl_cmd_dpipe_headers_get, .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, { .cmd = DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET, .doit = devlink_nl_cmd_dpipe_table_counters_set, .policy = devlink_nl_policy, .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, }; static struct genl_family devlink_nl_family __ro_after_init = { .name = DEVLINK_GENL_NAME, .version = DEVLINK_GENL_VERSION, .maxattr = DEVLINK_ATTR_MAX, .netnsok = true, .pre_doit = devlink_nl_pre_doit, .post_doit = devlink_nl_post_doit, .module = THIS_MODULE, .ops = devlink_nl_ops, .n_ops = ARRAY_SIZE(devlink_nl_ops), .mcgrps = devlink_nl_mcgrps, .n_mcgrps = ARRAY_SIZE(devlink_nl_mcgrps), }; /** * devlink_alloc - Allocate new devlink instance resources * * @ops: ops * @priv_size: size of user private data * * Allocate new devlink instance resources, including devlink index * and name. */ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size) { struct devlink *devlink; devlink = kzalloc(sizeof(*devlink) + priv_size, GFP_KERNEL); if (!devlink) return NULL; devlink->ops = ops; devlink_net_set(devlink, &init_net); INIT_LIST_HEAD(&devlink->port_list); INIT_LIST_HEAD(&devlink->sb_list); INIT_LIST_HEAD_RCU(&devlink->dpipe_table_list); return devlink; } EXPORT_SYMBOL_GPL(devlink_alloc); /** * devlink_register - Register devlink instance * * @devlink: devlink */ int devlink_register(struct devlink *devlink, struct device *dev) { mutex_lock(&devlink_mutex); devlink->dev = dev; list_add_tail(&devlink->list, &devlink_list); devlink_notify(devlink, DEVLINK_CMD_NEW); mutex_unlock(&devlink_mutex); return 0; } EXPORT_SYMBOL_GPL(devlink_register); /** * devlink_unregister - Unregister devlink instance * * @devlink: devlink */ void devlink_unregister(struct devlink *devlink) { mutex_lock(&devlink_mutex); devlink_notify(devlink, DEVLINK_CMD_DEL); list_del(&devlink->list); mutex_unlock(&devlink_mutex); } EXPORT_SYMBOL_GPL(devlink_unregister); /** * devlink_free - Free devlink instance resources * * @devlink: devlink */ void devlink_free(struct devlink *devlink) { kfree(devlink); } EXPORT_SYMBOL_GPL(devlink_free); /** * devlink_port_register - Register devlink port * * @devlink: devlink * @devlink_port: devlink port * @port_index * * Register devlink port with provided port index. User can use * any indexing, even hw-related one. devlink_port structure * is convenient to be embedded inside user driver private structure. * Note that the caller should take care of zeroing the devlink_port * structure. */ int devlink_port_register(struct devlink *devlink, struct devlink_port *devlink_port, unsigned int port_index) { mutex_lock(&devlink_port_mutex); if (devlink_port_index_exists(devlink, port_index)) { mutex_unlock(&devlink_port_mutex); return -EEXIST; } devlink_port->devlink = devlink; devlink_port->index = port_index; devlink_port->registered = true; list_add_tail(&devlink_port->list, &devlink->port_list); mutex_unlock(&devlink_port_mutex); devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); return 0; } EXPORT_SYMBOL_GPL(devlink_port_register); /** * devlink_port_unregister - Unregister devlink port * * @devlink_port: devlink port */ void devlink_port_unregister(struct devlink_port *devlink_port) { devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL); mutex_lock(&devlink_port_mutex); list_del(&devlink_port->list); mutex_unlock(&devlink_port_mutex); } EXPORT_SYMBOL_GPL(devlink_port_unregister); static void __devlink_port_type_set(struct devlink_port *devlink_port, enum devlink_port_type type, void *type_dev) { devlink_port->type = type; devlink_port->type_dev = type_dev; devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); } /** * devlink_port_type_eth_set - Set port type to Ethernet * * @devlink_port: devlink port * @netdev: related netdevice */ void devlink_port_type_eth_set(struct devlink_port *devlink_port, struct net_device *netdev) { return __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH, netdev); } EXPORT_SYMBOL_GPL(devlink_port_type_eth_set); /** * devlink_port_type_ib_set - Set port type to InfiniBand * * @devlink_port: devlink port * @ibdev: related IB device */ void devlink_port_type_ib_set(struct devlink_port *devlink_port, struct ib_device *ibdev) { return __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_IB, ibdev); } EXPORT_SYMBOL_GPL(devlink_port_type_ib_set); /** * devlink_port_type_clear - Clear port type * * @devlink_port: devlink port */ void devlink_port_type_clear(struct devlink_port *devlink_port) { return __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_NOTSET, NULL); } EXPORT_SYMBOL_GPL(devlink_port_type_clear); /** * devlink_port_split_set - Set port is split * * @devlink_port: devlink port * @split_group: split group - identifies group split port is part of */ void devlink_port_split_set(struct devlink_port *devlink_port, u32 split_group) { devlink_port->split = true; devlink_port->split_group = split_group; devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); } EXPORT_SYMBOL_GPL(devlink_port_split_set); int devlink_sb_register(struct devlink *devlink, unsigned int sb_index, u32 size, u16 ingress_pools_count, u16 egress_pools_count, u16 ingress_tc_count, u16 egress_tc_count) { struct devlink_sb *devlink_sb; int err = 0; mutex_lock(&devlink_mutex); if (devlink_sb_index_exists(devlink, sb_index)) { err = -EEXIST; goto unlock; } devlink_sb = kzalloc(sizeof(*devlink_sb), GFP_KERNEL); if (!devlink_sb) { err = -ENOMEM; goto unlock; } devlink_sb->index = sb_index; devlink_sb->size = size; devlink_sb->ingress_pools_count = ingress_pools_count; devlink_sb->egress_pools_count = egress_pools_count; devlink_sb->ingress_tc_count = ingress_tc_count; devlink_sb->egress_tc_count = egress_tc_count; list_add_tail(&devlink_sb->list, &devlink->sb_list); unlock: mutex_unlock(&devlink_mutex); return err; } EXPORT_SYMBOL_GPL(devlink_sb_register); void devlink_sb_unregister(struct devlink *devlink, unsigned int sb_index) { struct devlink_sb *devlink_sb; mutex_lock(&devlink_mutex); devlink_sb = devlink_sb_get_by_index(devlink, sb_index); WARN_ON(!devlink_sb); list_del(&devlink_sb->list); mutex_unlock(&devlink_mutex); kfree(devlink_sb); } EXPORT_SYMBOL_GPL(devlink_sb_unregister); /** * devlink_dpipe_headers_register - register dpipe headers * * @devlink: devlink * @dpipe_headers: dpipe header array * * Register the headers supported by hardware. */ int devlink_dpipe_headers_register(struct devlink *devlink, struct devlink_dpipe_headers *dpipe_headers) { mutex_lock(&devlink_mutex); devlink->dpipe_headers = dpipe_headers; mutex_unlock(&devlink_mutex); return 0; } EXPORT_SYMBOL_GPL(devlink_dpipe_headers_register); /** * devlink_dpipe_headers_unregister - unregister dpipe headers * * @devlink: devlink * * Unregister the headers supported by hardware. */ void devlink_dpipe_headers_unregister(struct devlink *devlink) { mutex_lock(&devlink_mutex); devlink->dpipe_headers = NULL; mutex_unlock(&devlink_mutex); } EXPORT_SYMBOL_GPL(devlink_dpipe_headers_unregister); /** * devlink_dpipe_table_counter_enabled - check if counter allocation * required * @devlink: devlink * @table_name: tables name * * Used by driver to check if counter allocation is required. * After counter allocation is turned on the table entries * are updated to include counter statistics. * * After that point on the driver must respect the counter * state so that each entry added to the table is added * with a counter. */ bool devlink_dpipe_table_counter_enabled(struct devlink *devlink, const char *table_name) { struct devlink_dpipe_table *table; bool enabled; rcu_read_lock(); table = devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name); enabled = false; if (table) enabled = table->counters_enabled; rcu_read_unlock(); return enabled; } EXPORT_SYMBOL_GPL(devlink_dpipe_table_counter_enabled); /** * devlink_dpipe_table_register - register dpipe table * * @devlink: devlink * @table_name: table name * @table_ops: table ops * @priv: priv * @counter_control_extern: external control for counters */ int devlink_dpipe_table_register(struct devlink *devlink, const char *table_name, struct devlink_dpipe_table_ops *table_ops, void *priv, bool counter_control_extern) { struct devlink_dpipe_table *table; if (devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name)) return -EEXIST; if (WARN_ON(!table_ops->size_get)) return -EINVAL; table = kzalloc(sizeof(*table), GFP_KERNEL); if (!table) return -ENOMEM; table->name = table_name; table->table_ops = table_ops; table->priv = priv; table->counter_control_extern = counter_control_extern; mutex_lock(&devlink_mutex); list_add_tail_rcu(&table->list, &devlink->dpipe_table_list); mutex_unlock(&devlink_mutex); return 0; } EXPORT_SYMBOL_GPL(devlink_dpipe_table_register); /** * devlink_dpipe_table_unregister - unregister dpipe table * * @devlink: devlink * @table_name: table name */ void devlink_dpipe_table_unregister(struct devlink *devlink, const char *table_name) { struct devlink_dpipe_table *table; mutex_lock(&devlink_mutex); table = devlink_dpipe_table_find(&devlink->dpipe_table_list, table_name); if (!table) goto unlock; list_del_rcu(&table->list); mutex_unlock(&devlink_mutex); kfree_rcu(table, rcu); return; unlock: mutex_unlock(&devlink_mutex); } EXPORT_SYMBOL_GPL(devlink_dpipe_table_unregister); static int __init devlink_module_init(void) { return genl_register_family(&devlink_nl_family); } static void __exit devlink_module_exit(void) { genl_unregister_family(&devlink_nl_family); } module_init(devlink_module_init); module_exit(devlink_module_exit); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Jiri Pirko <jiri@mellanox.com>"); MODULE_DESCRIPTION("Network physical device Netlink interface"); MODULE_ALIAS_GENL_FAMILY(DEVLINK_GENL_NAME); |
| 4861 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 | /* * include/linux/eventpoll.h ( Efficient event polling implementation ) * Copyright (C) 2001,...,2006 Davide Libenzi * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. * * Davide Libenzi <davidel@xmailserver.org> * */ #ifndef _LINUX_EVENTPOLL_H #define _LINUX_EVENTPOLL_H #include <uapi/linux/eventpoll.h> #include <uapi/linux/kcmp.h> /* Forward declarations to avoid compiler errors */ struct file; #ifdef CONFIG_EPOLL #ifdef CONFIG_CHECKPOINT_RESTORE struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long toff); #endif /* Used to initialize the epoll bits inside the "struct file" */ static inline void eventpoll_init_file(struct file *file) { INIT_LIST_HEAD(&file->f_ep_links); INIT_LIST_HEAD(&file->f_tfile_llink); } /* Used to release the epoll bits inside the "struct file" */ void eventpoll_release_file(struct file *file); /* * This is called from inside fs/file_table.c:__fput() to unlink files * from the eventpoll interface. We need to have this facility to cleanup * correctly files that are closed without being removed from the eventpoll * interface. */ static inline void eventpoll_release(struct file *file) { /* * Fast check to avoid the get/release of the semaphore. Since * we're doing this outside the semaphore lock, it might return * false negatives, but we don't care. It'll help in 99.99% of cases * to avoid the semaphore lock. False positives simply cannot happen * because the file in on the way to be removed and nobody ( but * eventpoll ) has still a reference to this file. */ if (likely(list_empty(&file->f_ep_links))) return; /* * The file is being closed while it is still linked to an epoll * descriptor. We need to handle this by correctly unlinking it * from its containers. */ eventpoll_release_file(file); } #else static inline void eventpoll_init_file(struct file *file) {} static inline void eventpoll_release(struct file *file) {} #endif #endif /* #ifndef _LINUX_EVENTPOLL_H */ |
| 10 12 16 3 3 3 3 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 9 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 13 1 3 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 9 9 10 9 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 2 2 3 3 2 1 1 1 2 10 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * Copyright 2002-2005, Instant802 Networks, Inc. * Copyright 2005-2006, Devicescape Software, Inc. * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright 2008-2011 Luis R. Rodriguez <mcgrof@qca.qualcomm.com> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2017 Intel Deutschland GmbH * * Permission to use, copy, modify, and/or distribute this software for any * purpose with or without fee is hereby granted, provided that the above * copyright notice and this permission notice appear in all copies. * * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. */ /** * DOC: Wireless regulatory infrastructure * * The usual implementation is for a driver to read a device EEPROM to * determine which regulatory domain it should be operating under, then * looking up the allowable channels in a driver-local table and finally * registering those channels in the wiphy structure. * * Another set of compliance enforcement is for drivers to use their * own compliance limits which can be stored on the EEPROM. The host * driver or firmware may ensure these are used. * * In addition to all this we provide an extra layer of regulatory * conformance. For drivers which do not have any regulatory * information CRDA provides the complete regulatory solution. * For others it provides a community effort on further restrictions * to enhance compliance. * * Note: When number of rules --> infinity we will not be able to * index on alpha2 any more, instead we'll probably have to * rely on some SHA1 checksum of the regdomain for example. * */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/list.h> #include <linux/ctype.h> #include <linux/nl80211.h> #include <linux/platform_device.h> #include <linux/moduleparam.h> #include <net/cfg80211.h> #include "core.h" #include "reg.h" #include "rdev-ops.h" #include "regdb.h" #include "nl80211.h" /* * Grace period we give before making sure all current interfaces reside on * channels allowed by the current regulatory domain. */ #define REG_ENFORCE_GRACE_MS 60000 /** * enum reg_request_treatment - regulatory request treatment * * @REG_REQ_OK: continue processing the regulatory request * @REG_REQ_IGNORE: ignore the regulatory request * @REG_REQ_INTERSECT: the regulatory domain resulting from this request should * be intersected with the current one. * @REG_REQ_ALREADY_SET: the regulatory request will not change the current * regulatory settings, and no further processing is required. */ enum reg_request_treatment { REG_REQ_OK, REG_REQ_IGNORE, REG_REQ_INTERSECT, REG_REQ_ALREADY_SET, }; static struct regulatory_request core_request_world = { .initiator = NL80211_REGDOM_SET_BY_CORE, .alpha2[0] = '0', .alpha2[1] = '0', .intersect = false, .processed = true, .country_ie_env = ENVIRON_ANY, }; /* * Receipt of information from last regulatory request, * protected by RTNL (and can be accessed with RCU protection) */ static struct regulatory_request __rcu *last_request = (void __force __rcu *)&core_request_world; /* To trigger userspace events */ static struct platform_device *reg_pdev; /* * Central wireless core regulatory domains, we only need two, * the current one and a world regulatory domain in case we have no * information to give us an alpha2. * (protected by RTNL, can be read under RCU) */ const struct ieee80211_regdomain __rcu *cfg80211_regdomain; /* * Number of devices that registered to the core * that support cellular base station regulatory hints * (protected by RTNL) */ static int reg_num_devs_support_basehint; /* * State variable indicating if the platform on which the devices * are attached is operating in an indoor environment. The state variable * is relevant for all registered devices. */ static bool reg_is_indoor; static spinlock_t reg_indoor_lock; /* Used to track the userspace process controlling the indoor setting */ static u32 reg_is_indoor_portid; static void restore_regulatory_settings(bool reset_user); static const struct ieee80211_regdomain *get_cfg80211_regdom(void) { return rtnl_dereference(cfg80211_regdomain); } const struct ieee80211_regdomain *get_wiphy_regdom(struct wiphy *wiphy) { return rtnl_dereference(wiphy->regd); } static const char *reg_dfs_region_str(enum nl80211_dfs_regions dfs_region) { switch (dfs_region) { case NL80211_DFS_UNSET: return "unset"; case NL80211_DFS_FCC: return "FCC"; case NL80211_DFS_ETSI: return "ETSI"; case NL80211_DFS_JP: return "JP"; } return "Unknown"; } enum nl80211_dfs_regions reg_get_dfs_region(struct wiphy *wiphy) { const struct ieee80211_regdomain *regd = NULL; const struct ieee80211_regdomain *wiphy_regd = NULL; regd = get_cfg80211_regdom(); if (!wiphy) goto out; wiphy_regd = get_wiphy_regdom(wiphy); if (!wiphy_regd) goto out; if (wiphy_regd->dfs_region == regd->dfs_region) goto out; pr_debug("%s: device specific dfs_region (%s) disagrees with cfg80211's central dfs_region (%s)\n", dev_name(&wiphy->dev), reg_dfs_region_str(wiphy_regd->dfs_region), reg_dfs_region_str(regd->dfs_region)); out: return regd->dfs_region; } static void rcu_free_regdom(const struct ieee80211_regdomain *r) { if (!r) return; kfree_rcu((struct ieee80211_regdomain *)r, rcu_head); } static struct regulatory_request *get_last_request(void) { return rcu_dereference_rtnl(last_request); } /* Used to queue up regulatory hints */ static LIST_HEAD(reg_requests_list); static spinlock_t reg_requests_lock; /* Used to queue up beacon hints for review */ static LIST_HEAD(reg_pending_beacons); static spinlock_t reg_pending_beacons_lock; /* Used to keep track of processed beacon hints */ static LIST_HEAD(reg_beacon_list); struct reg_beacon { struct list_head list; struct ieee80211_channel chan; }; static void reg_check_chans_work(struct work_struct *work); static DECLARE_DELAYED_WORK(reg_check_chans, reg_check_chans_work); static void reg_todo(struct work_struct *work); static DECLARE_WORK(reg_work, reg_todo); /* We keep a static world regulatory domain in case of the absence of CRDA */ static const struct ieee80211_regdomain world_regdom = { .n_reg_rules = 8, .alpha2 = "00", .reg_rules = { /* IEEE 802.11b/g, channels 1..11 */ REG_RULE(2412-10, 2462+10, 40, 6, 20, 0), /* IEEE 802.11b/g, channels 12..13. */ REG_RULE(2467-10, 2472+10, 20, 6, 20, NL80211_RRF_NO_IR | NL80211_RRF_AUTO_BW), /* IEEE 802.11 channel 14 - Only JP enables * this and for 802.11b only */ REG_RULE(2484-10, 2484+10, 20, 6, 20, NL80211_RRF_NO_IR | NL80211_RRF_NO_OFDM), /* IEEE 802.11a, channel 36..48 */ REG_RULE(5180-10, 5240+10, 80, 6, 20, NL80211_RRF_NO_IR | NL80211_RRF_AUTO_BW), /* IEEE 802.11a, channel 52..64 - DFS required */ REG_RULE(5260-10, 5320+10, 80, 6, 20, NL80211_RRF_NO_IR | NL80211_RRF_AUTO_BW | NL80211_RRF_DFS), /* IEEE 802.11a, channel 100..144 - DFS required */ REG_RULE(5500-10, 5720+10, 160, 6, 20, NL80211_RRF_NO_IR | NL80211_RRF_DFS), /* IEEE 802.11a, channel 149..165 */ REG_RULE(5745-10, 5825+10, 80, 6, 20, NL80211_RRF_NO_IR), /* IEEE 802.11ad (60GHz), channels 1..3 */ REG_RULE(56160+2160*1-1080, 56160+2160*3+1080, 2160, 0, 0, 0), } }; /* protected by RTNL */ static const struct ieee80211_regdomain *cfg80211_world_regdom = &world_regdom; static char *ieee80211_regdom = "00"; static char user_alpha2[2]; module_param(ieee80211_regdom, charp, 0444); MODULE_PARM_DESC(ieee80211_regdom, "IEEE 802.11 regulatory domain code"); static void reg_free_request(struct regulatory_request *request) { if (request == &core_request_world) return; if (request != get_last_request()) kfree(request); } static void reg_free_last_request(void) { struct regulatory_request *lr = get_last_request(); if (lr != &core_request_world && lr) kfree_rcu(lr, rcu_head); } static void reg_update_last_request(struct regulatory_request *request) { struct regulatory_request *lr; lr = get_last_request(); if (lr == request) return; reg_free_last_request(); rcu_assign_pointer(last_request, request); } static void reset_regdomains(bool full_reset, const struct ieee80211_regdomain *new_regdom) { const struct ieee80211_regdomain *r; ASSERT_RTNL(); r = get_cfg80211_regdom(); /* avoid freeing static information or freeing something twice */ if (r == cfg80211_world_regdom) r = NULL; if (cfg80211_world_regdom == &world_regdom) cfg80211_world_regdom = NULL; if (r == &world_regdom) r = NULL; rcu_free_regdom(r); rcu_free_regdom(cfg80211_world_regdom); cfg80211_world_regdom = &world_regdom; rcu_assign_pointer(cfg80211_regdomain, new_regdom); if (!full_reset) return; reg_update_last_request(&core_request_world); } /* * Dynamic world regulatory domain requested by the wireless * core upon initialization */ static void update_world_regdomain(const struct ieee80211_regdomain *rd) { struct regulatory_request *lr; lr = get_last_request(); WARN_ON(!lr); reset_regdomains(false, rd); cfg80211_world_regdom = rd; } bool is_world_regdom(const char *alpha2) { if (!alpha2) return false; return alpha2[0] == '0' && alpha2[1] == '0'; } static bool is_alpha2_set(const char *alpha2) { if (!alpha2) return false; return alpha2[0] && alpha2[1]; } static bool is_unknown_alpha2(const char *alpha2) { if (!alpha2) return false; /* * Special case where regulatory domain was built by driver * but a specific alpha2 cannot be determined */ return alpha2[0] == '9' && alpha2[1] == '9'; } static bool is_intersected_alpha2(const char *alpha2) { if (!alpha2) return false; /* * Special case where regulatory domain is the * result of an intersection between two regulatory domain * structures */ return alpha2[0] == '9' && alpha2[1] == '8'; } static bool is_an_alpha2(const char *alpha2) { if (!alpha2) return false; return isalpha(alpha2[0]) && isalpha(alpha2[1]); } static bool alpha2_equal(const char *alpha2_x, const char *alpha2_y) { if (!alpha2_x || !alpha2_y) return false; return alpha2_x[0] == alpha2_y[0] && alpha2_x[1] == alpha2_y[1]; } static bool regdom_changes(const char *alpha2) { const struct ieee80211_regdomain *r = get_cfg80211_regdom(); if (!r) return true; return !alpha2_equal(r->alpha2, alpha2); } /* * The NL80211_REGDOM_SET_BY_USER regdom alpha2 is cached, this lets * you know if a valid regulatory hint with NL80211_REGDOM_SET_BY_USER * has ever been issued. */ static bool is_user_regdom_saved(void) { if (user_alpha2[0] == '9' && user_alpha2[1] == '7') return false; /* This would indicate a mistake on the design */ if (WARN(!is_world_regdom(user_alpha2) && !is_an_alpha2(user_alpha2), "Unexpected user alpha2: %c%c\n", user_alpha2[0], user_alpha2[1])) return false; return true; } static const struct ieee80211_regdomain * reg_copy_regd(const struct ieee80211_regdomain *src_regd) { struct ieee80211_regdomain *regd; int size_of_regd; unsigned int i; size_of_regd = sizeof(struct ieee80211_regdomain) + src_regd->n_reg_rules * sizeof(struct ieee80211_reg_rule); regd = kzalloc(size_of_regd, GFP_KERNEL); if (!regd) return ERR_PTR(-ENOMEM); memcpy(regd, src_regd, sizeof(struct ieee80211_regdomain)); for (i = 0; i < src_regd->n_reg_rules; i++) memcpy(®d->reg_rules[i], &src_regd->reg_rules[i], sizeof(struct ieee80211_reg_rule)); return regd; } #ifdef CONFIG_CFG80211_INTERNAL_REGDB struct reg_regdb_apply_request { struct list_head list; const struct ieee80211_regdomain *regdom; }; static LIST_HEAD(reg_regdb_apply_list); static DEFINE_MUTEX(reg_regdb_apply_mutex); static void reg_regdb_apply(struct work_struct *work) { struct reg_regdb_apply_request *request; rtnl_lock(); mutex_lock(®_regdb_apply_mutex); while (!list_empty(®_regdb_apply_list)) { request = list_first_entry(®_regdb_apply_list, struct reg_regdb_apply_request, list); list_del(&request->list); set_regdom(request->regdom, REGD_SOURCE_INTERNAL_DB); kfree(request); } mutex_unlock(®_regdb_apply_mutex); rtnl_unlock(); } static DECLARE_WORK(reg_regdb_work, reg_regdb_apply); static int reg_query_builtin(const char *alpha2) { const struct ieee80211_regdomain *regdom = NULL; struct reg_regdb_apply_request *request; unsigned int i; for (i = 0; i < reg_regdb_size; i++) { if (alpha2_equal(alpha2, reg_regdb[i]->alpha2)) { regdom = reg_regdb[i]; break; } } if (!regdom) return -ENODATA; request = kzalloc(sizeof(struct reg_regdb_apply_request), GFP_KERNEL); if (!request) return -ENOMEM; request->regdom = reg_copy_regd(regdom); if (IS_ERR_OR_NULL(request->regdom)) { kfree(request); return -ENOMEM; } mutex_lock(®_regdb_apply_mutex); list_add_tail(&request->list, ®_regdb_apply_list); mutex_unlock(®_regdb_apply_mutex); schedule_work(®_regdb_work); return 0; } /* Feel free to add any other sanity checks here */ static void reg_regdb_size_check(void) { /* We should ideally BUILD_BUG_ON() but then random builds would fail */ WARN_ONCE(!reg_regdb_size, "db.txt is empty, you should update it..."); } #else static inline void reg_regdb_size_check(void) {} static inline int reg_query_builtin(const char *alpha2) { return -ENODATA; } #endif /* CONFIG_CFG80211_INTERNAL_REGDB */ #ifdef CONFIG_CFG80211_CRDA_SUPPORT /* Max number of consecutive attempts to communicate with CRDA */ #define REG_MAX_CRDA_TIMEOUTS 10 static u32 reg_crda_timeouts; static void crda_timeout_work(struct work_struct *work); static DECLARE_DELAYED_WORK(crda_timeout, crda_timeout_work); static void crda_timeout_work(struct work_struct *work) { pr_debug("Timeout while waiting for CRDA to reply, restoring regulatory settings\n"); rtnl_lock(); reg_crda_timeouts++; restore_regulatory_settings(true); rtnl_unlock(); } static void cancel_crda_timeout(void) { cancel_delayed_work(&crda_timeout); } static void cancel_crda_timeout_sync(void) { cancel_delayed_work_sync(&crda_timeout); } static void reset_crda_timeouts(void) { reg_crda_timeouts = 0; } /* * This lets us keep regulatory code which is updated on a regulatory * basis in userspace. */ static int call_crda(const char *alpha2) { char country[12]; char *env[] = { country, NULL }; int ret; snprintf(country, sizeof(country), "COUNTRY=%c%c", alpha2[0], alpha2[1]); if (reg_crda_timeouts > REG_MAX_CRDA_TIMEOUTS) { pr_debug("Exceeded CRDA call max attempts. Not calling CRDA\n"); return -EINVAL; } if (!is_world_regdom((char *) alpha2)) pr_debug("Calling CRDA for country: %c%c\n", alpha2[0], alpha2[1]); else pr_debug("Calling CRDA to update world regulatory domain\n"); ret = kobject_uevent_env(®_pdev->dev.kobj, KOBJ_CHANGE, env); if (ret) return ret; queue_delayed_work(system_power_efficient_wq, &crda_timeout, msecs_to_jiffies(3142)); return 0; } #else static inline void cancel_crda_timeout(void) {} static inline void cancel_crda_timeout_sync(void) {} static inline void reset_crda_timeouts(void) {} static inline int call_crda(const char *alpha2) { return -ENODATA; } #endif /* CONFIG_CFG80211_CRDA_SUPPORT */ static bool reg_query_database(struct regulatory_request *request) { /* query internal regulatory database (if it exists) */ if (reg_query_builtin(request->alpha2) == 0) return true; if (call_crda(request->alpha2) == 0) return true; return false; } bool reg_is_valid_request(const char *alpha2) { struct regulatory_request *lr = get_last_request(); if (!lr || lr->processed) return false; return alpha2_equal(lr->alpha2, alpha2); } static const struct ieee80211_regdomain *reg_get_regdomain(struct wiphy *wiphy) { struct regulatory_request *lr = get_last_request(); /* * Follow the driver's regulatory domain, if present, unless a country * IE has been processed or a user wants to help complaince further */ if (lr->initiator != NL80211_REGDOM_SET_BY_COUNTRY_IE && lr->initiator != NL80211_REGDOM_SET_BY_USER && wiphy->regd) return get_wiphy_regdom(wiphy); return get_cfg80211_regdom(); } static unsigned int reg_get_max_bandwidth_from_range(const struct ieee80211_regdomain *rd, const struct ieee80211_reg_rule *rule) { const struct ieee80211_freq_range *freq_range = &rule->freq_range; const struct ieee80211_freq_range *freq_range_tmp; const struct ieee80211_reg_rule *tmp; u32 start_freq, end_freq, idx, no; for (idx = 0; idx < rd->n_reg_rules; idx++) if (rule == &rd->reg_rules[idx]) break; if (idx == rd->n_reg_rules) return 0; /* get start_freq */ no = idx; while (no) { tmp = &rd->reg_rules[--no]; freq_range_tmp = &tmp->freq_range; if (freq_range_tmp->end_freq_khz < freq_range->start_freq_khz) break; freq_range = freq_range_tmp; } start_freq = freq_range->start_freq_khz; /* get end_freq */ freq_range = &rule->freq_range; no = idx; while (no < rd->n_reg_rules - 1) { tmp = &rd->reg_rules[++no]; freq_range_tmp = &tmp->freq_range; if (freq_range_tmp->start_freq_khz > freq_range->end_freq_khz) break; freq_range = freq_range_tmp; } end_freq = freq_range->end_freq_khz; return end_freq - start_freq; } unsigned int reg_get_max_bandwidth(const struct ieee80211_regdomain *rd, const struct ieee80211_reg_rule *rule) { unsigned int bw = reg_get_max_bandwidth_from_range(rd, rule); if (rule->flags & NL80211_RRF_NO_160MHZ) bw = min_t(unsigned int, bw, MHZ_TO_KHZ(80)); if (rule->flags & NL80211_RRF_NO_80MHZ) bw = min_t(unsigned int, bw, MHZ_TO_KHZ(40)); /* * HT40+/HT40- limits are handled per-channel. Only limit BW if both * are not allowed. */ if (rule->flags & NL80211_RRF_NO_HT40MINUS && rule->flags & NL80211_RRF_NO_HT40PLUS) bw = min_t(unsigned int, bw, MHZ_TO_KHZ(20)); return bw; } /* Sanity check on a regulatory rule */ static bool is_valid_reg_rule(const struct ieee80211_reg_rule *rule) { const struct ieee80211_freq_range *freq_range = &rule->freq_range; u32 freq_diff; if (freq_range->start_freq_khz <= 0 || freq_range->end_freq_khz <= 0) return false; if (freq_range->start_freq_khz > freq_range->end_freq_khz) return false; freq_diff = freq_range->end_freq_khz - freq_range->start_freq_khz; if (freq_range->end_freq_khz <= freq_range->start_freq_khz || freq_range->max_bandwidth_khz > freq_diff) return false; return true; } static bool is_valid_rd(const struct ieee80211_regdomain *rd) { const struct ieee80211_reg_rule *reg_rule = NULL; unsigned int i; if (!rd->n_reg_rules) return false; if (WARN_ON(rd->n_reg_rules > NL80211_MAX_SUPP_REG_RULES)) return false; for (i = 0; i < rd->n_reg_rules; i++) { reg_rule = &rd->reg_rules[i]; if (!is_valid_reg_rule(reg_rule)) return false; } return true; } /** * freq_in_rule_band - tells us if a frequency is in a frequency band * @freq_range: frequency rule we want to query * @freq_khz: frequency we are inquiring about * * This lets us know if a specific frequency rule is or is not relevant to * a specific frequency's band. Bands are device specific and artificial * definitions (the "2.4 GHz band", the "5 GHz band" and the "60GHz band"), * however it is safe for now to assume that a frequency rule should not be * part of a frequency's band if the start freq or end freq are off by more * than 2 GHz for the 2.4 and 5 GHz bands, and by more than 20 GHz for the * 60 GHz band. * This resolution can be lowered and should be considered as we add * regulatory rule support for other "bands". **/ static bool freq_in_rule_band(const struct ieee80211_freq_range *freq_range, u32 freq_khz) { #define ONE_GHZ_IN_KHZ 1000000 /* * From 802.11ad: directional multi-gigabit (DMG): * Pertaining to operation in a frequency band containing a channel * with the Channel starting frequency above 45 GHz. */ u32 limit = freq_khz > 45 * ONE_GHZ_IN_KHZ ? 20 * ONE_GHZ_IN_KHZ : 2 * ONE_GHZ_IN_KHZ; if (abs(freq_khz - freq_range->start_freq_khz) <= limit) return true; if (abs(freq_khz - freq_range->end_freq_khz) <= limit) return true; return false; #undef ONE_GHZ_IN_KHZ } /* * Later on we can perhaps use the more restrictive DFS * region but we don't have information for that yet so * for now simply disallow conflicts. */ static enum nl80211_dfs_regions reg_intersect_dfs_region(const enum nl80211_dfs_regions dfs_region1, const enum nl80211_dfs_regions dfs_region2) { if (dfs_region1 != dfs_region2) return NL80211_DFS_UNSET; return dfs_region1; } /* * Helper for regdom_intersect(), this does the real * mathematical intersection fun */ static int reg_rules_intersect(const struct ieee80211_regdomain *rd1, const struct ieee80211_regdomain *rd2, const struct ieee80211_reg_rule *rule1, const struct ieee80211_reg_rule *rule2, struct ieee80211_reg_rule *intersected_rule) { const struct ieee80211_freq_range *freq_range1, *freq_range2; struct ieee80211_freq_range *freq_range; const struct ieee80211_power_rule *power_rule1, *power_rule2; struct ieee80211_power_rule *power_rule; u32 freq_diff, max_bandwidth1, max_bandwidth2; freq_range1 = &rule1->freq_range; freq_range2 = &rule2->freq_range; freq_range = &intersected_rule->freq_range; power_rule1 = &rule1->power_rule; power_rule2 = &rule2->power_rule; power_rule = &intersected_rule->power_rule; freq_range->start_freq_khz = max(freq_range1->start_freq_khz, freq_range2->start_freq_khz); freq_range->end_freq_khz = min(freq_range1->end_freq_khz, freq_range2->end_freq_khz); max_bandwidth1 = freq_range1->max_bandwidth_khz; max_bandwidth2 = freq_range2->max_bandwidth_khz; if (rule1->flags & NL80211_RRF_AUTO_BW) max_bandwidth1 = reg_get_max_bandwidth(rd1, rule1); if (rule2->flags & NL80211_RRF_AUTO_BW) max_bandwidth2 = reg_get_max_bandwidth(rd2, rule2); freq_range->max_bandwidth_khz = min(max_bandwidth1, max_bandwidth2); intersected_rule->flags = rule1->flags | rule2->flags; /* * In case NL80211_RRF_AUTO_BW requested for both rules * set AUTO_BW in intersected rule also. Next we will * calculate BW correctly in handle_channel function. * In other case remove AUTO_BW flag while we calculate * maximum bandwidth correctly and auto calculation is * not required. */ if ((rule1->flags & NL80211_RRF_AUTO_BW) && (rule2->flags & NL80211_RRF_AUTO_BW)) intersected_rule->flags |= NL80211_RRF_AUTO_BW; else intersected_rule->flags &= ~NL80211_RRF_AUTO_BW; freq_diff = freq_range->end_freq_khz - freq_range->start_freq_khz; if (freq_range->max_bandwidth_khz > freq_diff) freq_range->max_bandwidth_khz = freq_diff; power_rule->max_eirp = min(power_rule1->max_eirp, power_rule2->max_eirp); power_rule->max_antenna_gain = min(power_rule1->max_antenna_gain, power_rule2->max_antenna_gain); intersected_rule->dfs_cac_ms = max(rule1->dfs_cac_ms, rule2->dfs_cac_ms); if (!is_valid_reg_rule(intersected_rule)) return -EINVAL; return 0; } /* check whether old rule contains new rule */ static bool rule_contains(struct ieee80211_reg_rule *r1, struct ieee80211_reg_rule *r2) { /* for simplicity, currently consider only same flags */ if (r1->flags != r2->flags) return false; /* verify r1 is more restrictive */ if ((r1->power_rule.max_antenna_gain > r2->power_rule.max_antenna_gain) || r1->power_rule.max_eirp > r2->power_rule.max_eirp) return false; /* make sure r2's range is contained within r1 */ if (r1->freq_range.start_freq_khz > r2->freq_range.start_freq_khz || r1->freq_range.end_freq_khz < r2->freq_range.end_freq_khz) return false; /* and finally verify that r1.max_bw >= r2.max_bw */ if (r1->freq_range.max_bandwidth_khz < r2->freq_range.max_bandwidth_khz) return false; return true; } /* add or extend current rules. do nothing if rule is already contained */ static void add_rule(struct ieee80211_reg_rule *rule, struct ieee80211_reg_rule *reg_rules, u32 *n_rules) { struct ieee80211_reg_rule *tmp_rule; int i; for (i = 0; i < *n_rules; i++) { tmp_rule = ®_rules[i]; /* rule is already contained - do nothing */ if (rule_contains(tmp_rule, rule)) return; /* extend rule if possible */ if (rule_contains(rule, tmp_rule)) { memcpy(tmp_rule, rule, sizeof(*rule)); return; } } memcpy(®_rules[*n_rules], rule, sizeof(*rule)); (*n_rules)++; } /** * regdom_intersect - do the intersection between two regulatory domains * @rd1: first regulatory domain * @rd2: second regulatory domain * * Use this function to get the intersection between two regulatory domains. * Once completed we will mark the alpha2 for the rd as intersected, "98", * as no one single alpha2 can represent this regulatory domain. * * Returns a pointer to the regulatory domain structure which will hold the * resulting intersection of rules between rd1 and rd2. We will * kzalloc() this structure for you. */ static struct ieee80211_regdomain * regdom_intersect(const struct ieee80211_regdomain *rd1, const struct ieee80211_regdomain *rd2) { int r, size_of_regd; unsigned int x, y; unsigned int num_rules = 0; const struct ieee80211_reg_rule *rule1, *rule2; struct ieee80211_reg_rule intersected_rule; struct ieee80211_regdomain *rd; if (!rd1 || !rd2) return NULL; /* * First we get a count of the rules we'll need, then we actually * build them. This is to so we can malloc() and free() a * regdomain once. The reason we use reg_rules_intersect() here * is it will return -EINVAL if the rule computed makes no sense. * All rules that do check out OK are valid. */ for (x = 0; x < rd1->n_reg_rules; x++) { rule1 = &rd1->reg_rules[x]; for (y = 0; y < rd2->n_reg_rules; y++) { rule2 = &rd2->reg_rules[y]; if (!reg_rules_intersect(rd1, rd2, rule1, rule2, &intersected_rule)) num_rules++; } } if (!num_rules) return NULL; size_of_regd = sizeof(struct ieee80211_regdomain) + num_rules * sizeof(struct ieee80211_reg_rule); rd = kzalloc(size_of_regd, GFP_KERNEL); if (!rd) return NULL; for (x = 0; x < rd1->n_reg_rules; x++) { rule1 = &rd1->reg_rules[x]; for (y = 0; y < rd2->n_reg_rules; y++) { rule2 = &rd2->reg_rules[y]; r = reg_rules_intersect(rd1, rd2, rule1, rule2, &intersected_rule); /* * No need to memset here the intersected rule here as * we're not using the stack anymore */ if (r) continue; add_rule(&intersected_rule, rd->reg_rules, &rd->n_reg_rules); } } rd->alpha2[0] = '9'; rd->alpha2[1] = '8'; rd->dfs_region = reg_intersect_dfs_region(rd1->dfs_region, rd2->dfs_region); return rd; } /* * XXX: add support for the rest of enum nl80211_reg_rule_flags, we may * want to just have the channel structure use these */ static u32 map_regdom_flags(u32 rd_flags) { u32 channel_flags = 0; if (rd_flags & NL80211_RRF_NO_IR_ALL) channel_flags |= IEEE80211_CHAN_NO_IR; if (rd_flags & NL80211_RRF_DFS) channel_flags |= IEEE80211_CHAN_RADAR; if (rd_flags & NL80211_RRF_NO_OFDM) channel_flags |= IEEE80211_CHAN_NO_OFDM; if (rd_flags & NL80211_RRF_NO_OUTDOOR) channel_flags |= IEEE80211_CHAN_INDOOR_ONLY; if (rd_flags & NL80211_RRF_IR_CONCURRENT) channel_flags |= IEEE80211_CHAN_IR_CONCURRENT; if (rd_flags & NL80211_RRF_NO_HT40MINUS) channel_flags |= IEEE80211_CHAN_NO_HT40MINUS; if (rd_flags & NL80211_RRF_NO_HT40PLUS) channel_flags |= IEEE80211_CHAN_NO_HT40PLUS; if (rd_flags & NL80211_RRF_NO_80MHZ) channel_flags |= IEEE80211_CHAN_NO_80MHZ; if (rd_flags & NL80211_RRF_NO_160MHZ) channel_flags |= IEEE80211_CHAN_NO_160MHZ; return channel_flags; } static const struct ieee80211_reg_rule * freq_reg_info_regd(u32 center_freq, const struct ieee80211_regdomain *regd, u32 bw) { int i; bool band_rule_found = false; bool bw_fits = false; if (!regd) return ERR_PTR(-EINVAL); for (i = 0; i < regd->n_reg_rules; i++) { const struct ieee80211_reg_rule *rr; const struct ieee80211_freq_range *fr = NULL; rr = ®d->reg_rules[i]; fr = &rr->freq_range; /* * We only need to know if one frequency rule was * was in center_freq's band, that's enough, so lets * not overwrite it once found */ if (!band_rule_found) band_rule_found = freq_in_rule_band(fr, center_freq); bw_fits = cfg80211_does_bw_fit_range(fr, center_freq, bw); if (band_rule_found && bw_fits) return rr; } if (!band_rule_found) return ERR_PTR(-ERANGE); return ERR_PTR(-EINVAL); } static const struct ieee80211_reg_rule * __freq_reg_info(struct wiphy *wiphy, u32 center_freq, u32 min_bw) { const struct ieee80211_regdomain *regd = reg_get_regdomain(wiphy); const struct ieee80211_reg_rule *reg_rule = NULL; u32 bw; for (bw = MHZ_TO_KHZ(20); bw >= min_bw; bw = bw / 2) { reg_rule = freq_reg_info_regd(center_freq, regd, bw); if (!IS_ERR(reg_rule)) return reg_rule; } return reg_rule; } const struct ieee80211_reg_rule *freq_reg_info(struct wiphy *wiphy, u32 center_freq) { return __freq_reg_info(wiphy, center_freq, MHZ_TO_KHZ(20)); } EXPORT_SYMBOL(freq_reg_info); const char *reg_initiator_name(enum nl80211_reg_initiator initiator) { switch (initiator) { case NL80211_REGDOM_SET_BY_CORE: return "core"; case NL80211_REGDOM_SET_BY_USER: return "user"; case NL80211_REGDOM_SET_BY_DRIVER: return "driver"; case NL80211_REGDOM_SET_BY_COUNTRY_IE: return "country IE"; default: WARN_ON(1); return "bug"; } } EXPORT_SYMBOL(reg_initiator_name); static uint32_t reg_rule_to_chan_bw_flags(const struct ieee80211_regdomain *regd, const struct ieee80211_reg_rule *reg_rule, const struct ieee80211_channel *chan) { const struct ieee80211_freq_range *freq_range = NULL; u32 max_bandwidth_khz, bw_flags = 0; freq_range = ®_rule->freq_range; max_bandwidth_khz = freq_range->max_bandwidth_khz; /* Check if auto calculation requested */ if (reg_rule->flags & NL80211_RRF_AUTO_BW) max_bandwidth_khz = reg_get_max_bandwidth(regd, reg_rule); /* If we get a reg_rule we can assume that at least 5Mhz fit */ if (!cfg80211_does_bw_fit_range(freq_range, MHZ_TO_KHZ(chan->center_freq), MHZ_TO_KHZ(10))) bw_flags |= IEEE80211_CHAN_NO_10MHZ; if (!cfg80211_does_bw_fit_range(freq_range, MHZ_TO_KHZ(chan->center_freq), MHZ_TO_KHZ(20))) bw_flags |= IEEE80211_CHAN_NO_20MHZ; if (max_bandwidth_khz < MHZ_TO_KHZ(10)) bw_flags |= IEEE80211_CHAN_NO_10MHZ; if (max_bandwidth_khz < MHZ_TO_KHZ(20)) bw_flags |= IEEE80211_CHAN_NO_20MHZ; if (max_bandwidth_khz < MHZ_TO_KHZ(40)) bw_flags |= IEEE80211_CHAN_NO_HT40; if (max_bandwidth_khz < MHZ_TO_KHZ(80)) bw_flags |= IEEE80211_CHAN_NO_80MHZ; if (max_bandwidth_khz < MHZ_TO_KHZ(160)) bw_flags |= IEEE80211_CHAN_NO_160MHZ; return bw_flags; } /* * Note that right now we assume the desired channel bandwidth * is always 20 MHz for each individual channel (HT40 uses 20 MHz * per channel, the primary and the extension channel). */ static void handle_channel(struct wiphy *wiphy, enum nl80211_reg_initiator initiator, struct ieee80211_channel *chan) { u32 flags, bw_flags = 0; const struct ieee80211_reg_rule *reg_rule = NULL; const struct ieee80211_power_rule *power_rule = NULL; struct wiphy *request_wiphy = NULL; struct regulatory_request *lr = get_last_request(); const struct ieee80211_regdomain *regd; request_wiphy = wiphy_idx_to_wiphy(lr->wiphy_idx); flags = chan->orig_flags; reg_rule = freq_reg_info(wiphy, MHZ_TO_KHZ(chan->center_freq)); if (IS_ERR(reg_rule)) { /* * We will disable all channels that do not match our * received regulatory rule unless the hint is coming * from a Country IE and the Country IE had no information * about a band. The IEEE 802.11 spec allows for an AP * to send only a subset of the regulatory rules allowed, * so an AP in the US that only supports 2.4 GHz may only send * a country IE with information for the 2.4 GHz band * while 5 GHz is still supported. */ if (initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE && PTR_ERR(reg_rule) == -ERANGE) return; if (lr->initiator == NL80211_REGDOM_SET_BY_DRIVER && request_wiphy && request_wiphy == wiphy && request_wiphy->regulatory_flags & REGULATORY_STRICT_REG) { pr_debug("Disabling freq %d MHz for good\n", chan->center_freq); chan->orig_flags |= IEEE80211_CHAN_DISABLED; chan->flags = chan->orig_flags; } else { pr_debug("Disabling freq %d MHz\n", chan->center_freq); chan->flags |= IEEE80211_CHAN_DISABLED; } return; } regd = reg_get_regdomain(wiphy); power_rule = ®_rule->power_rule; bw_flags = reg_rule_to_chan_bw_flags(regd, reg_rule, chan); if (lr->initiator == NL80211_REGDOM_SET_BY_DRIVER && request_wiphy && request_wiphy == wiphy && request_wiphy->regulatory_flags & REGULATORY_STRICT_REG) { /* * This guarantees the driver's requested regulatory domain * will always be used as a base for further regulatory * settings */ chan->flags = chan->orig_flags = map_regdom_flags(reg_rule->flags) | bw_flags; chan->max_antenna_gain = chan->orig_mag = (int) MBI_TO_DBI(power_rule->max_antenna_gain); chan->max_reg_power = chan->max_power = chan->orig_mpwr = (int) MBM_TO_DBM(power_rule->max_eirp); if (chan->flags & IEEE80211_CHAN_RADAR) { chan->dfs_cac_ms = IEEE80211_DFS_MIN_CAC_TIME_MS; if (reg_rule->dfs_cac_ms) chan->dfs_cac_ms = reg_rule->dfs_cac_ms; } return; } chan->dfs_state = NL80211_DFS_USABLE; chan->dfs_state_entered = jiffies; chan->beacon_found = false; chan->flags = flags | bw_flags | map_regdom_flags(reg_rule->flags); chan->max_antenna_gain = min_t(int, chan->orig_mag, MBI_TO_DBI(power_rule->max_antenna_gain)); chan->max_reg_power = (int) MBM_TO_DBM(power_rule->max_eirp); if (chan->flags & IEEE80211_CHAN_RADAR) { if (reg_rule->dfs_cac_ms) chan->dfs_cac_ms = reg_rule->dfs_cac_ms; else chan->dfs_cac_ms = IEEE80211_DFS_MIN_CAC_TIME_MS; } if (chan->orig_mpwr) { /* * Devices that use REGULATORY_COUNTRY_IE_FOLLOW_POWER * will always follow the passed country IE power settings. */ if (initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE && wiphy->regulatory_flags & REGULATORY_COUNTRY_IE_FOLLOW_POWER) chan->max_power = chan->max_reg_power; else chan->max_power = min(chan->orig_mpwr, chan->max_reg_power); } else chan->max_power = chan->max_reg_power; } static void handle_band(struct wiphy *wiphy, enum nl80211_reg_initiator initiator, struct ieee80211_supported_band *sband) { unsigned int i; if (!sband) return; for (i = 0; i < sband->n_channels; i++) handle_channel(wiphy, initiator, &sband->channels[i]); } static bool reg_request_cell_base(struct regulatory_request *request) { if (request->initiator != NL80211_REGDOM_SET_BY_USER) return false; return request->user_reg_hint_type == NL80211_USER_REG_HINT_CELL_BASE; } bool reg_last_request_cell_base(void) { return reg_request_cell_base(get_last_request()); } #ifdef CONFIG_CFG80211_REG_CELLULAR_HINTS /* Core specific check */ static enum reg_request_treatment reg_ignore_cell_hint(struct regulatory_request *pending_request) { struct regulatory_request *lr = get_last_request(); if (!reg_num_devs_support_basehint) return REG_REQ_IGNORE; if (reg_request_cell_base(lr) && !regdom_changes(pending_request->alpha2)) return REG_REQ_ALREADY_SET; return REG_REQ_OK; } /* Device specific check */ static bool reg_dev_ignore_cell_hint(struct wiphy *wiphy) { return !(wiphy->features & NL80211_FEATURE_CELL_BASE_REG_HINTS); } #else static enum reg_request_treatment reg_ignore_cell_hint(struct regulatory_request *pending_request) { return REG_REQ_IGNORE; } static bool reg_dev_ignore_cell_hint(struct wiphy *wiphy) { return true; } #endif static bool wiphy_strict_alpha2_regd(struct wiphy *wiphy) { if (wiphy->regulatory_flags & REGULATORY_STRICT_REG && !(wiphy->regulatory_flags & REGULATORY_CUSTOM_REG)) return true; return false; } static bool ignore_reg_update(struct wiphy *wiphy, enum nl80211_reg_initiator initiator) { struct regulatory_request *lr = get_last_request(); if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) return true; if (!lr) { pr_debug("Ignoring regulatory request set by %s since last_request is not set\n", reg_initiator_name(initiator)); return true; } if (initiator == NL80211_REGDOM_SET_BY_CORE && wiphy->regulatory_flags & REGULATORY_CUSTOM_REG) { pr_debug("Ignoring regulatory request set by %s since the driver uses its own custom regulatory domain\n", reg_initiator_name(initiator)); return true; } /* * wiphy->regd will be set once the device has its own * desired regulatory domain set */ if (wiphy_strict_alpha2_regd(wiphy) && !wiphy->regd && initiator != NL80211_REGDOM_SET_BY_COUNTRY_IE && !is_world_regdom(lr->alpha2)) { pr_debug("Ignoring regulatory request set by %s since the driver requires its own regulatory domain to be set first\n", reg_initiator_name(initiator)); return true; } if (reg_request_cell_base(lr)) return reg_dev_ignore_cell_hint(wiphy); return false; } static bool reg_is_world_roaming(struct wiphy *wiphy) { const struct ieee80211_regdomain *cr = get_cfg80211_regdom(); const struct ieee80211_regdomain *wr = get_wiphy_regdom(wiphy); struct regulatory_request *lr = get_last_request(); if (is_world_regdom(cr->alpha2) || (wr && is_world_regdom(wr->alpha2))) return true; if (lr && lr->initiator != NL80211_REGDOM_SET_BY_COUNTRY_IE && wiphy->regulatory_flags & REGULATORY_CUSTOM_REG) return true; return false; } static void handle_reg_beacon(struct wiphy *wiphy, unsigned int chan_idx, struct reg_beacon *reg_beacon) { struct ieee80211_supported_band *sband; struct ieee80211_channel *chan; bool channel_changed = false; struct ieee80211_channel chan_before; sband = wiphy->bands[reg_beacon->chan.band]; chan = &sband->channels[chan_idx]; if (likely(chan->center_freq != reg_beacon->chan.center_freq)) return; if (chan->beacon_found) return; chan->beacon_found = true; if (!reg_is_world_roaming(wiphy)) return; if (wiphy->regulatory_flags & REGULATORY_DISABLE_BEACON_HINTS) return; chan_before.center_freq = chan->center_freq; chan_before.flags = chan->flags; if (chan->flags & IEEE80211_CHAN_NO_IR) { chan->flags &= ~IEEE80211_CHAN_NO_IR; channel_changed = true; } if (channel_changed) nl80211_send_beacon_hint_event(wiphy, &chan_before, chan); } /* * Called when a scan on a wiphy finds a beacon on * new channel */ static void wiphy_update_new_beacon(struct wiphy *wiphy, struct reg_beacon *reg_beacon) { unsigned int i; struct ieee80211_supported_band *sband; if (!wiphy->bands[reg_beacon->chan.band]) return; sband = wiphy->bands[reg_beacon->chan.band]; for (i = 0; i < sband->n_channels; i++) handle_reg_beacon(wiphy, i, reg_beacon); } /* * Called upon reg changes or a new wiphy is added */ static void wiphy_update_beacon_reg(struct wiphy *wiphy) { unsigned int i; struct ieee80211_supported_band *sband; struct reg_beacon *reg_beacon; list_for_each_entry(reg_beacon, ®_beacon_list, list) { if (!wiphy->bands[reg_beacon->chan.band]) continue; sband = wiphy->bands[reg_beacon->chan.band]; for (i = 0; i < sband->n_channels; i++) handle_reg_beacon(wiphy, i, reg_beacon); } } /* Reap the advantages of previously found beacons */ static void reg_process_beacons(struct wiphy *wiphy) { /* * Means we are just firing up cfg80211, so no beacons would * have been processed yet. */ if (!last_request) return; wiphy_update_beacon_reg(wiphy); } static bool is_ht40_allowed(struct ieee80211_channel *chan) { if (!chan) return false; if (chan->flags & IEEE80211_CHAN_DISABLED) return false; /* This would happen when regulatory rules disallow HT40 completely */ if ((chan->flags & IEEE80211_CHAN_NO_HT40) == IEEE80211_CHAN_NO_HT40) return false; return true; } static void reg_process_ht_flags_channel(struct wiphy *wiphy, struct ieee80211_channel *channel) { struct ieee80211_supported_band *sband = wiphy->bands[channel->band]; struct ieee80211_channel *channel_before = NULL, *channel_after = NULL; const struct ieee80211_regdomain *regd; unsigned int i; u32 flags; if (!is_ht40_allowed(channel)) { channel->flags |= IEEE80211_CHAN_NO_HT40; return; } /* * We need to ensure the extension channels exist to * be able to use HT40- or HT40+, this finds them (or not) */ for (i = 0; i < sband->n_channels; i++) { struct ieee80211_channel *c = &sband->channels[i]; if (c->center_freq == (channel->center_freq - 20)) channel_before = c; if (c->center_freq == (channel->center_freq + 20)) channel_after = c; } flags = 0; regd = get_wiphy_regdom(wiphy); if (regd) { const struct ieee80211_reg_rule *reg_rule = freq_reg_info_regd(MHZ_TO_KHZ(channel->center_freq), regd, MHZ_TO_KHZ(20)); if (!IS_ERR(reg_rule)) flags = reg_rule->flags; } /* * Please note that this assumes target bandwidth is 20 MHz, * if that ever changes we also need to change the below logic * to include that as well. */ if (!is_ht40_allowed(channel_before) || flags & NL80211_RRF_NO_HT40MINUS) channel->flags |= IEEE80211_CHAN_NO_HT40MINUS; else channel->flags &= ~IEEE80211_CHAN_NO_HT40MINUS; if (!is_ht40_allowed(channel_after) || flags & NL80211_RRF_NO_HT40PLUS) channel->flags |= IEEE80211_CHAN_NO_HT40PLUS; else channel->flags &= ~IEEE80211_CHAN_NO_HT40PLUS; } static void reg_process_ht_flags_band(struct wiphy *wiphy, struct ieee80211_supported_band *sband) { unsigned int i; if (!sband) return; for (i = 0; i < sband->n_channels; i++) reg_process_ht_flags_channel(wiphy, &sband->channels[i]); } static void reg_process_ht_flags(struct wiphy *wiphy) { enum nl80211_band band; if (!wiphy) return; for (band = 0; band < NUM_NL80211_BANDS; band++) reg_process_ht_flags_band(wiphy, wiphy->bands[band]); } static void reg_call_notifier(struct wiphy *wiphy, struct regulatory_request *request) { if (wiphy->reg_notifier) wiphy->reg_notifier(wiphy, request); } static bool reg_wdev_chan_valid(struct wiphy *wiphy, struct wireless_dev *wdev) { struct cfg80211_chan_def chandef = {}; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); enum nl80211_iftype iftype; wdev_lock(wdev); iftype = wdev->iftype; /* make sure the interface is active */ if (!wdev->netdev || !netif_running(wdev->netdev)) goto wdev_inactive_unlock; switch (iftype) { case NL80211_IFTYPE_AP: case NL80211_IFTYPE_P2P_GO: if (!wdev->beacon_interval) goto wdev_inactive_unlock; chandef = wdev->chandef; break; case NL80211_IFTYPE_ADHOC: if (!wdev->ssid_len) goto wdev_inactive_unlock; chandef = wdev->chandef; break; case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_P2P_CLIENT: if (!wdev->current_bss || !wdev->current_bss->pub.channel) goto wdev_inactive_unlock; if (!rdev->ops->get_channel || rdev_get_channel(rdev, wdev, &chandef)) cfg80211_chandef_create(&chandef, wdev->current_bss->pub.channel, NL80211_CHAN_NO_HT); break; case NL80211_IFTYPE_MONITOR: case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_P2P_DEVICE: /* no enforcement required */ break; default: /* others not implemented for now */ WARN_ON(1); break; } wdev_unlock(wdev); switch (iftype) { case NL80211_IFTYPE_AP: case NL80211_IFTYPE_P2P_GO: case NL80211_IFTYPE_ADHOC: return cfg80211_reg_can_beacon_relax(wiphy, &chandef, iftype); case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_P2P_CLIENT: return cfg80211_chandef_usable(wiphy, &chandef, IEEE80211_CHAN_DISABLED); default: break; } return true; wdev_inactive_unlock: wdev_unlock(wdev); return true; } static void reg_leave_invalid_chans(struct wiphy *wiphy) { struct wireless_dev *wdev; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy); ASSERT_RTNL(); list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) if (!reg_wdev_chan_valid(wiphy, wdev)) cfg80211_leave(rdev, wdev); } static void reg_check_chans_work(struct work_struct *work) { struct cfg80211_registered_device *rdev; pr_debug("Verifying active interfaces after reg change\n"); rtnl_lock(); list_for_each_entry(rdev, &cfg80211_rdev_list, list) if (!(rdev->wiphy.regulatory_flags & REGULATORY_IGNORE_STALE_KICKOFF)) reg_leave_invalid_chans(&rdev->wiphy); rtnl_unlock(); } static void reg_check_channels(void) { /* * Give usermode a chance to do something nicer (move to another * channel, orderly disconnection), before forcing a disconnection. */ mod_delayed_work(system_power_efficient_wq, ®_check_chans, msecs_to_jiffies(REG_ENFORCE_GRACE_MS)); } static void wiphy_update_regulatory(struct wiphy *wiphy, enum nl80211_reg_initiator initiator) { enum nl80211_band band; struct regulatory_request *lr = get_last_request(); if (ignore_reg_update(wiphy, initiator)) { /* * Regulatory updates set by CORE are ignored for custom * regulatory cards. Let us notify the changes to the driver, * as some drivers used this to restore its orig_* reg domain. */ if (initiator == NL80211_REGDOM_SET_BY_CORE && wiphy->regulatory_flags & REGULATORY_CUSTOM_REG) reg_call_notifier(wiphy, lr); return; } lr->dfs_region = get_cfg80211_regdom()->dfs_region; for (band = 0; band < NUM_NL80211_BANDS; band++) handle_band(wiphy, initiator, wiphy->bands[band]); reg_process_beacons(wiphy); reg_process_ht_flags(wiphy); reg_call_notifier(wiphy, lr); } static void update_all_wiphy_regulatory(enum nl80211_reg_initiator initiator) { struct cfg80211_registered_device *rdev; struct wiphy *wiphy; ASSERT_RTNL(); list_for_each_entry(rdev, &cfg80211_rdev_list, list) { wiphy = &rdev->wiphy; wiphy_update_regulatory(wiphy, initiator); } reg_check_channels(); } static void handle_channel_custom(struct wiphy *wiphy, struct ieee80211_channel *chan, const struct ieee80211_regdomain *regd, u32 min_bw) { u32 bw_flags = 0; const struct ieee80211_reg_rule *reg_rule = NULL; const struct ieee80211_power_rule *power_rule = NULL; u32 bw; for (bw = MHZ_TO_KHZ(20); bw >= min_bw; bw = bw / 2) { reg_rule = freq_reg_info_regd(MHZ_TO_KHZ(chan->center_freq), regd, bw); if (!IS_ERR(reg_rule)) break; } if (IS_ERR_OR_NULL(reg_rule)) { pr_debug("Disabling freq %d MHz as custom regd has no rule that fits it\n", chan->center_freq); if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) { chan->flags |= IEEE80211_CHAN_DISABLED; } else { chan->orig_flags |= IEEE80211_CHAN_DISABLED; chan->flags = chan->orig_flags; } return; } power_rule = ®_rule->power_rule; bw_flags = reg_rule_to_chan_bw_flags(regd, reg_rule, chan); chan->dfs_state_entered = jiffies; chan->dfs_state = NL80211_DFS_USABLE; chan->beacon_found = false; if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) chan->flags = chan->orig_flags | bw_flags | map_regdom_flags(reg_rule->flags); else chan->flags |= map_regdom_flags(reg_rule->flags) | bw_flags; chan->max_antenna_gain = (int) MBI_TO_DBI(power_rule->max_antenna_gain); chan->max_reg_power = chan->max_power = (int) MBM_TO_DBM(power_rule->max_eirp); if (chan->flags & IEEE80211_CHAN_RADAR) { if (reg_rule->dfs_cac_ms) chan->dfs_cac_ms = reg_rule->dfs_cac_ms; else chan->dfs_cac_ms = IEEE80211_DFS_MIN_CAC_TIME_MS; } chan->max_power = chan->max_reg_power; } static void handle_band_custom(struct wiphy *wiphy, struct ieee80211_supported_band *sband, const struct ieee80211_regdomain *regd) { unsigned int i; if (!sband) return; /* * We currently assume that you always want at least 20 MHz, * otherwise channel 12 might get enabled if this rule is * compatible to US, which permits 2402 - 2472 MHz. */ for (i = 0; i < sband->n_channels; i++) handle_channel_custom(wiphy, &sband->channels[i], regd, MHZ_TO_KHZ(20)); } /* Used by drivers prior to wiphy registration */ void wiphy_apply_custom_regulatory(struct wiphy *wiphy, const struct ieee80211_regdomain *regd) { enum nl80211_band band; unsigned int bands_set = 0; WARN(!(wiphy->regulatory_flags & REGULATORY_CUSTOM_REG), "wiphy should have REGULATORY_CUSTOM_REG\n"); wiphy->regulatory_flags |= REGULATORY_CUSTOM_REG; for (band = 0; band < NUM_NL80211_BANDS; band++) { if (!wiphy->bands[band]) continue; handle_band_custom(wiphy, wiphy->bands[band], regd); bands_set++; } /* * no point in calling this if it won't have any effect * on your device's supported bands. */ WARN_ON(!bands_set); } EXPORT_SYMBOL(wiphy_apply_custom_regulatory); static void reg_set_request_processed(void) { bool need_more_processing = false; struct regulatory_request *lr = get_last_request(); lr->processed = true; spin_lock(®_requests_lock); if (!list_empty(®_requests_list)) need_more_processing = true; spin_unlock(®_requests_lock); cancel_crda_timeout(); if (need_more_processing) schedule_work(®_work); } /** * reg_process_hint_core - process core regulatory requests * @pending_request: a pending core regulatory request * * The wireless subsystem can use this function to process * a regulatory request issued by the regulatory core. */ static enum reg_request_treatment reg_process_hint_core(struct regulatory_request *core_request) { if (reg_query_database(core_request)) { core_request->intersect = false; core_request->processed = false; reg_update_last_request(core_request); return REG_REQ_OK; } return REG_REQ_IGNORE; } static enum reg_request_treatment __reg_process_hint_user(struct regulatory_request *user_request) { struct regulatory_request *lr = get_last_request(); if (reg_request_cell_base(user_request)) return reg_ignore_cell_hint(user_request); if (reg_request_cell_base(lr)) return REG_REQ_IGNORE; if (lr->initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE) return REG_REQ_INTERSECT; /* * If the user knows better the user should set the regdom * to their country before the IE is picked up */ if (lr->initiator == NL80211_REGDOM_SET_BY_USER && lr->intersect) return REG_REQ_IGNORE; /* * Process user requests only after previous user/driver/core * requests have been processed */ if ((lr->initiator == NL80211_REGDOM_SET_BY_CORE || lr->initiator == NL80211_REGDOM_SET_BY_DRIVER || lr->initiator == NL80211_REGDOM_SET_BY_USER) && regdom_changes(lr->alpha2)) return REG_REQ_IGNORE; if (!regdom_changes(user_request->alpha2)) return REG_REQ_ALREADY_SET; return REG_REQ_OK; } /** * reg_process_hint_user - process user regulatory requests * @user_request: a pending user regulatory request * * The wireless subsystem can use this function to process * a regulatory request initiated by userspace. */ static enum reg_request_treatment reg_process_hint_user(struct regulatory_request *user_request) { enum reg_request_treatment treatment; treatment = __reg_process_hint_user(user_request); if (treatment == REG_REQ_IGNORE || treatment == REG_REQ_ALREADY_SET) return REG_REQ_IGNORE; user_request->intersect = treatment == REG_REQ_INTERSECT; user_request->processed = false; if (reg_query_database(user_request)) { reg_update_last_request(user_request); user_alpha2[0] = user_request->alpha2[0]; user_alpha2[1] = user_request->alpha2[1]; return REG_REQ_OK; } return REG_REQ_IGNORE; } static enum reg_request_treatment __reg_process_hint_driver(struct regulatory_request *driver_request) { struct regulatory_request *lr = get_last_request(); if (lr->initiator == NL80211_REGDOM_SET_BY_CORE) { if (regdom_changes(driver_request->alpha2)) return REG_REQ_OK; return REG_REQ_ALREADY_SET; } /* * This would happen if you unplug and plug your card * back in or if you add a new device for which the previously * loaded card also agrees on the regulatory domain. */ if (lr->initiator == NL80211_REGDOM_SET_BY_DRIVER && !regdom_changes(driver_request->alpha2)) return REG_REQ_ALREADY_SET; return REG_REQ_INTERSECT; } /** * reg_process_hint_driver - process driver regulatory requests * @driver_request: a pending driver regulatory request * * The wireless subsystem can use this function to process * a regulatory request issued by an 802.11 driver. * * Returns one of the different reg request treatment values. */ static enum reg_request_treatment reg_process_hint_driver(struct wiphy *wiphy, struct regulatory_request *driver_request) { const struct ieee80211_regdomain *regd, *tmp; enum reg_request_treatment treatment; treatment = __reg_process_hint_driver(driver_request); switch (treatment) { case REG_REQ_OK: break; case REG_REQ_IGNORE: return REG_REQ_IGNORE; case REG_REQ_INTERSECT: case REG_REQ_ALREADY_SET: regd = reg_copy_regd(get_cfg80211_regdom()); if (IS_ERR(regd)) return REG_REQ_IGNORE; tmp = get_wiphy_regdom(wiphy); rcu_assign_pointer(wiphy->regd, regd); rcu_free_regdom(tmp); } driver_request->intersect = treatment == REG_REQ_INTERSECT; driver_request->processed = false; /* * Since CRDA will not be called in this case as we already * have applied the requested regulatory domain before we just * inform userspace we have processed the request */ if (treatment == REG_REQ_ALREADY_SET) { nl80211_send_reg_change_event(driver_request); reg_update_last_request(driver_request); reg_set_request_processed(); return REG_REQ_ALREADY_SET; } if (reg_query_database(driver_request)) { reg_update_last_request(driver_request); return REG_REQ_OK; } return REG_REQ_IGNORE; } static enum reg_request_treatment __reg_process_hint_country_ie(struct wiphy *wiphy, struct regulatory_request *country_ie_request) { struct wiphy *last_wiphy = NULL; struct regulatory_request *lr = get_last_request(); if (reg_request_cell_base(lr)) { /* Trust a Cell base station over the AP's country IE */ if (regdom_changes(country_ie_request->alpha2)) return REG_REQ_IGNORE; return REG_REQ_ALREADY_SET; } else { if (wiphy->regulatory_flags & REGULATORY_COUNTRY_IE_IGNORE) return REG_REQ_IGNORE; } if (unlikely(!is_an_alpha2(country_ie_request->alpha2))) return -EINVAL; if (lr->initiator != NL80211_REGDOM_SET_BY_COUNTRY_IE) return REG_REQ_OK; last_wiphy = wiphy_idx_to_wiphy(lr->wiphy_idx); if (last_wiphy != wiphy) { /* * Two cards with two APs claiming different * Country IE alpha2s. We could * intersect them, but that seems unlikely * to be correct. Reject second one for now. */ if (regdom_changes(country_ie_request->alpha2)) return REG_REQ_IGNORE; return REG_REQ_ALREADY_SET; } if (regdom_changes(country_ie_request->alpha2)) return REG_REQ_OK; return REG_REQ_ALREADY_SET; } /** * reg_process_hint_country_ie - process regulatory requests from country IEs * @country_ie_request: a regulatory request from a country IE * * The wireless subsystem can use this function to process * a regulatory request issued by a country Information Element. * * Returns one of the different reg request treatment values. */ static enum reg_request_treatment reg_process_hint_country_ie(struct wiphy *wiphy, struct regulatory_request *country_ie_request) { enum reg_request_treatment treatment; treatment = __reg_process_hint_country_ie(wiphy, country_ie_request); switch (treatment) { case REG_REQ_OK: break; case REG_REQ_IGNORE: return REG_REQ_IGNORE; case REG_REQ_ALREADY_SET: reg_free_request(country_ie_request); return REG_REQ_ALREADY_SET; case REG_REQ_INTERSECT: /* * This doesn't happen yet, not sure we * ever want to support it for this case. */ WARN_ONCE(1, "Unexpected intersection for country IEs"); return REG_REQ_IGNORE; } country_ie_request->intersect = false; country_ie_request->processed = false; if (reg_query_database(country_ie_request)) { reg_update_last_request(country_ie_request); return REG_REQ_OK; } return REG_REQ_IGNORE; } bool reg_dfs_domain_same(struct wiphy *wiphy1, struct wiphy *wiphy2) { const struct ieee80211_regdomain *wiphy1_regd = NULL; const struct ieee80211_regdomain *wiphy2_regd = NULL; const struct ieee80211_regdomain *cfg80211_regd = NULL; bool dfs_domain_same; rcu_read_lock(); cfg80211_regd = rcu_dereference(cfg80211_regdomain); wiphy1_regd = rcu_dereference(wiphy1->regd); if (!wiphy1_regd) wiphy1_regd = cfg80211_regd; wiphy2_regd = rcu_dereference(wiphy2->regd); if (!wiphy2_regd) wiphy2_regd = cfg80211_regd; dfs_domain_same = wiphy1_regd->dfs_region == wiphy2_regd->dfs_region; rcu_read_unlock(); return dfs_domain_same; } static void reg_copy_dfs_chan_state(struct ieee80211_channel *dst_chan, struct ieee80211_channel *src_chan) { if (!(dst_chan->flags & IEEE80211_CHAN_RADAR) || !(src_chan->flags & IEEE80211_CHAN_RADAR)) return; if (dst_chan->flags & IEEE80211_CHAN_DISABLED || src_chan->flags & IEEE80211_CHAN_DISABLED) return; if (src_chan->center_freq == dst_chan->center_freq && dst_chan->dfs_state == NL80211_DFS_USABLE) { dst_chan->dfs_state = src_chan->dfs_state; dst_chan->dfs_state_entered = src_chan->dfs_state_entered; } } static void wiphy_share_dfs_chan_state(struct wiphy *dst_wiphy, struct wiphy *src_wiphy) { struct ieee80211_supported_band *src_sband, *dst_sband; struct ieee80211_channel *src_chan, *dst_chan; int i, j, band; if (!reg_dfs_domain_same(dst_wiphy, src_wiphy)) return; for (band = 0; band < NUM_NL80211_BANDS; band++) { dst_sband = dst_wiphy->bands[band]; src_sband = src_wiphy->bands[band]; if (!dst_sband || !src_sband) continue; for (i = 0; i < dst_sband->n_channels; i++) { dst_chan = &dst_sband->channels[i]; for (j = 0; j < src_sband->n_channels; j++) { src_chan = &src_sband->channels[j]; reg_copy_dfs_chan_state(dst_chan, src_chan); } } } } static void wiphy_all_share_dfs_chan_state(struct wiphy *wiphy) { struct cfg80211_registered_device *rdev; ASSERT_RTNL(); list_for_each_entry(rdev, &cfg80211_rdev_list, list) { if (wiphy == &rdev->wiphy) continue; wiphy_share_dfs_chan_state(wiphy, &rdev->wiphy); } } /* This processes *all* regulatory hints */ static void reg_process_hint(struct regulatory_request *reg_request) { struct wiphy *wiphy = NULL; enum reg_request_treatment treatment; enum nl80211_reg_initiator initiator = reg_request->initiator; if (reg_request->wiphy_idx != WIPHY_IDX_INVALID) wiphy = wiphy_idx_to_wiphy(reg_request->wiphy_idx); switch (initiator) { case NL80211_REGDOM_SET_BY_CORE: treatment = reg_process_hint_core(reg_request); break; case NL80211_REGDOM_SET_BY_USER: treatment = reg_process_hint_user(reg_request); break; case NL80211_REGDOM_SET_BY_DRIVER: if (!wiphy) goto out_free; treatment = reg_process_hint_driver(wiphy, reg_request); break; case NL80211_REGDOM_SET_BY_COUNTRY_IE: if (!wiphy) goto out_free; treatment = reg_process_hint_country_ie(wiphy, reg_request); break; default: WARN(1, "invalid initiator %d\n", initiator); goto out_free; } if (treatment == REG_REQ_IGNORE) goto out_free; WARN(treatment != REG_REQ_OK && treatment != REG_REQ_ALREADY_SET, "unexpected treatment value %d\n", treatment); /* This is required so that the orig_* parameters are saved. * NOTE: treatment must be set for any case that reaches here! */ if (treatment == REG_REQ_ALREADY_SET && wiphy && wiphy->regulatory_flags & REGULATORY_STRICT_REG) { wiphy_update_regulatory(wiphy, initiator); wiphy_all_share_dfs_chan_state(wiphy); reg_check_channels(); } return; out_free: reg_free_request(reg_request); } static bool reg_only_self_managed_wiphys(void) { struct cfg80211_registered_device *rdev; struct wiphy *wiphy; bool self_managed_found = false; ASSERT_RTNL(); list_for_each_entry(rdev, &cfg80211_rdev_list, list) { wiphy = &rdev->wiphy; if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) self_managed_found = true; else return false; } /* make sure at least one self-managed wiphy exists */ return self_managed_found; } /* * Processes regulatory hints, this is all the NL80211_REGDOM_SET_BY_* * Regulatory hints come on a first come first serve basis and we * must process each one atomically. */ static void reg_process_pending_hints(void) { struct regulatory_request *reg_request, *lr; lr = get_last_request(); /* When last_request->processed becomes true this will be rescheduled */ if (lr && !lr->processed) { pr_debug("Pending regulatory request, waiting for it to be processed...\n"); return; } spin_lock(®_requests_lock); if (list_empty(®_requests_list)) { spin_unlock(®_requests_lock); return; } reg_request = list_first_entry(®_requests_list, struct regulatory_request, list); list_del_init(®_request->list); spin_unlock(®_requests_lock); if (reg_only_self_managed_wiphys()) { reg_free_request(reg_request); return; } reg_process_hint(reg_request); lr = get_last_request(); spin_lock(®_requests_lock); if (!list_empty(®_requests_list) && lr && lr->processed) schedule_work(®_work); spin_unlock(®_requests_lock); } /* Processes beacon hints -- this has nothing to do with country IEs */ static void reg_process_pending_beacon_hints(void) { struct cfg80211_registered_device *rdev; struct reg_beacon *pending_beacon, *tmp; /* This goes through the _pending_ beacon list */ spin_lock_bh(®_pending_beacons_lock); list_for_each_entry_safe(pending_beacon, tmp, ®_pending_beacons, list) { list_del_init(&pending_beacon->list); /* Applies the beacon hint to current wiphys */ list_for_each_entry(rdev, &cfg80211_rdev_list, list) wiphy_update_new_beacon(&rdev->wiphy, pending_beacon); /* Remembers the beacon hint for new wiphys or reg changes */ list_add_tail(&pending_beacon->list, ®_beacon_list); } spin_unlock_bh(®_pending_beacons_lock); } static void reg_process_self_managed_hints(void) { struct cfg80211_registered_device *rdev; struct wiphy *wiphy; const struct ieee80211_regdomain *tmp; const struct ieee80211_regdomain *regd; enum nl80211_band band; struct regulatory_request request = {}; list_for_each_entry(rdev, &cfg80211_rdev_list, list) { wiphy = &rdev->wiphy; spin_lock(®_requests_lock); regd = rdev->requested_regd; rdev->requested_regd = NULL; spin_unlock(®_requests_lock); if (regd == NULL) continue; tmp = get_wiphy_regdom(wiphy); rcu_assign_pointer(wiphy->regd, regd); rcu_free_regdom(tmp); for (band = 0; band < NUM_NL80211_BANDS; band++) handle_band_custom(wiphy, wiphy->bands[band], regd); reg_process_ht_flags(wiphy); request.wiphy_idx = get_wiphy_idx(wiphy); request.alpha2[0] = regd->alpha2[0]; request.alpha2[1] = regd->alpha2[1]; request.initiator = NL80211_REGDOM_SET_BY_DRIVER; nl80211_send_wiphy_reg_change_event(&request); } reg_check_channels(); } static void reg_todo(struct work_struct *work) { rtnl_lock(); reg_process_pending_hints(); reg_process_pending_beacon_hints(); reg_process_self_managed_hints(); rtnl_unlock(); } static void queue_regulatory_request(struct regulatory_request *request) { request->alpha2[0] = toupper(request->alpha2[0]); request->alpha2[1] = toupper(request->alpha2[1]); spin_lock(®_requests_lock); list_add_tail(&request->list, ®_requests_list); spin_unlock(®_requests_lock); schedule_work(®_work); } /* * Core regulatory hint -- happens during cfg80211_init() * and when we restore regulatory settings. */ static int regulatory_hint_core(const char *alpha2) { struct regulatory_request *request; request = kzalloc(sizeof(struct regulatory_request), GFP_KERNEL); if (!request) return -ENOMEM; request->alpha2[0] = alpha2[0]; request->alpha2[1] = alpha2[1]; request->initiator = NL80211_REGDOM_SET_BY_CORE; request->wiphy_idx = WIPHY_IDX_INVALID; queue_regulatory_request(request); return 0; } /* User hints */ int regulatory_hint_user(const char *alpha2, enum nl80211_user_reg_hint_type user_reg_hint_type) { struct regulatory_request *request; if (WARN_ON(!alpha2)) return -EINVAL; if (!is_world_regdom(alpha2) && !is_an_alpha2(alpha2)) return -EINVAL; request = kzalloc(sizeof(struct regulatory_request), GFP_KERNEL); if (!request) return -ENOMEM; request->wiphy_idx = WIPHY_IDX_INVALID; request->alpha2[0] = alpha2[0]; request->alpha2[1] = alpha2[1]; request->initiator = NL80211_REGDOM_SET_BY_USER; request->user_reg_hint_type = user_reg_hint_type; /* Allow calling CRDA again */ reset_crda_timeouts(); queue_regulatory_request(request); return 0; } int regulatory_hint_indoor(bool is_indoor, u32 portid) { spin_lock(®_indoor_lock); /* It is possible that more than one user space process is trying to * configure the indoor setting. To handle such cases, clear the indoor * setting in case that some process does not think that the device * is operating in an indoor environment. In addition, if a user space * process indicates that it is controlling the indoor setting, save its * portid, i.e., make it the owner. */ reg_is_indoor = is_indoor; if (reg_is_indoor) { if (!reg_is_indoor_portid) reg_is_indoor_portid = portid; } else { reg_is_indoor_portid = 0; } spin_unlock(®_indoor_lock); if (!is_indoor) reg_check_channels(); return 0; } void regulatory_netlink_notify(u32 portid) { spin_lock(®_indoor_lock); if (reg_is_indoor_portid != portid) { spin_unlock(®_indoor_lock); return; } reg_is_indoor = false; reg_is_indoor_portid = 0; spin_unlock(®_indoor_lock); reg_check_channels(); } /* Driver hints */ int regulatory_hint(struct wiphy *wiphy, const char *alpha2) { struct regulatory_request *request; if (WARN_ON(!alpha2 || !wiphy)) return -EINVAL; wiphy->regulatory_flags &= ~REGULATORY_CUSTOM_REG; request = kzalloc(sizeof(struct regulatory_request), GFP_KERNEL); if (!request) return -ENOMEM; request->wiphy_idx = get_wiphy_idx(wiphy); request->alpha2[0] = alpha2[0]; request->alpha2[1] = alpha2[1]; request->initiator = NL80211_REGDOM_SET_BY_DRIVER; /* Allow calling CRDA again */ reset_crda_timeouts(); queue_regulatory_request(request); return 0; } EXPORT_SYMBOL(regulatory_hint); void regulatory_hint_country_ie(struct wiphy *wiphy, enum nl80211_band band, const u8 *country_ie, u8 country_ie_len) { char alpha2[2]; enum environment_cap env = ENVIRON_ANY; struct regulatory_request *request = NULL, *lr; /* IE len must be evenly divisible by 2 */ if (country_ie_len & 0x01) return; if (country_ie_len < IEEE80211_COUNTRY_IE_MIN_LEN) return; request = kzalloc(sizeof(*request), GFP_KERNEL); if (!request) return; alpha2[0] = country_ie[0]; alpha2[1] = country_ie[1]; if (country_ie[2] == 'I') env = ENVIRON_INDOOR; else if (country_ie[2] == 'O') env = ENVIRON_OUTDOOR; rcu_read_lock(); lr = get_last_request(); if (unlikely(!lr)) goto out; /* * We will run this only upon a successful connection on cfg80211. * We leave conflict resolution to the workqueue, where can hold * the RTNL. */ if (lr->initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE && lr->wiphy_idx != WIPHY_IDX_INVALID) goto out; request->wiphy_idx = get_wiphy_idx(wiphy); request->alpha2[0] = alpha2[0]; request->alpha2[1] = alpha2[1]; request->initiator = NL80211_REGDOM_SET_BY_COUNTRY_IE; request->country_ie_env = env; /* Allow calling CRDA again */ reset_crda_timeouts(); queue_regulatory_request(request); request = NULL; out: kfree(request); rcu_read_unlock(); } static void restore_alpha2(char *alpha2, bool reset_user) { /* indicates there is no alpha2 to consider for restoration */ alpha2[0] = '9'; alpha2[1] = '7'; /* The user setting has precedence over the module parameter */ if (is_user_regdom_saved()) { /* Unless we're asked to ignore it and reset it */ if (reset_user) { pr_debug("Restoring regulatory settings including user preference\n"); user_alpha2[0] = '9'; user_alpha2[1] = '7'; /* * If we're ignoring user settings, we still need to * check the module parameter to ensure we put things * back as they were for a full restore. */ if (!is_world_regdom(ieee80211_regdom)) { pr_debug("Keeping preference on module parameter ieee80211_regdom: %c%c\n", ieee80211_regdom[0], ieee80211_regdom[1]); alpha2[0] = ieee80211_regdom[0]; alpha2[1] = ieee80211_regdom[1]; } } else { pr_debug("Restoring regulatory settings while preserving user preference for: %c%c\n", user_alpha2[0], user_alpha2[1]); alpha2[0] = user_alpha2[0]; alpha2[1] = user_alpha2[1]; } } else if (!is_world_regdom(ieee80211_regdom)) { pr_debug("Keeping preference on module parameter ieee80211_regdom: %c%c\n", ieee80211_regdom[0], ieee80211_regdom[1]); alpha2[0] = ieee80211_regdom[0]; alpha2[1] = ieee80211_regdom[1]; } else pr_debug("Restoring regulatory settings\n"); } static void restore_custom_reg_settings(struct wiphy *wiphy) { struct ieee80211_supported_band *sband; enum nl80211_band band; struct ieee80211_channel *chan; int i; for (band = 0; band < NUM_NL80211_BANDS; band++) { sband = wiphy->bands[band]; if (!sband) continue; for (i = 0; i < sband->n_channels; i++) { chan = &sband->channels[i]; chan->flags = chan->orig_flags; chan->max_antenna_gain = chan->orig_mag; chan->max_power = chan->orig_mpwr; chan->beacon_found = false; } } } /* * Restoring regulatory settings involves ingoring any * possibly stale country IE information and user regulatory * settings if so desired, this includes any beacon hints * learned as we could have traveled outside to another country * after disconnection. To restore regulatory settings we do * exactly what we did at bootup: * * - send a core regulatory hint * - send a user regulatory hint if applicable * * Device drivers that send a regulatory hint for a specific country * keep their own regulatory domain on wiphy->regd so that does does * not need to be remembered. */ static void restore_regulatory_settings(bool reset_user) { char alpha2[2]; char world_alpha2[2]; struct reg_beacon *reg_beacon, *btmp; LIST_HEAD(tmp_reg_req_list); struct cfg80211_registered_device *rdev; ASSERT_RTNL(); /* * Clear the indoor setting in case that it is not controlled by user * space, as otherwise there is no guarantee that the device is still * operating in an indoor environment. */ spin_lock(®_indoor_lock); if (reg_is_indoor && !reg_is_indoor_portid) { reg_is_indoor = false; reg_check_channels(); } spin_unlock(®_indoor_lock); reset_regdomains(true, &world_regdom); restore_alpha2(alpha2, reset_user); /* * If there's any pending requests we simply * stash them to a temporary pending queue and * add then after we've restored regulatory * settings. */ spin_lock(®_requests_lock); list_splice_tail_init(®_requests_list, &tmp_reg_req_list); spin_unlock(®_requests_lock); /* Clear beacon hints */ spin_lock_bh(®_pending_beacons_lock); list_for_each_entry_safe(reg_beacon, btmp, ®_pending_beacons, list) { list_del(®_beacon->list); kfree(reg_beacon); } spin_unlock_bh(®_pending_beacons_lock); list_for_each_entry_safe(reg_beacon, btmp, ®_beacon_list, list) { list_del(®_beacon->list); kfree(reg_beacon); } /* First restore to the basic regulatory settings */ world_alpha2[0] = cfg80211_world_regdom->alpha2[0]; world_alpha2[1] = cfg80211_world_regdom->alpha2[1]; list_for_each_entry(rdev, &cfg80211_rdev_list, list) { if (rdev->wiphy.regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) continue; if (rdev->wiphy.regulatory_flags & REGULATORY_CUSTOM_REG) restore_custom_reg_settings(&rdev->wiphy); } regulatory_hint_core(world_alpha2); /* * This restores the ieee80211_regdom module parameter * preference or the last user requested regulatory * settings, user regulatory settings takes precedence. */ if (is_an_alpha2(alpha2)) regulatory_hint_user(alpha2, NL80211_USER_REG_HINT_USER); spin_lock(®_requests_lock); list_splice_tail_init(&tmp_reg_req_list, ®_requests_list); spin_unlock(®_requests_lock); pr_debug("Kicking the queue\n"); schedule_work(®_work); } static bool is_wiphy_all_set_reg_flag(enum ieee80211_regulatory_flags flag) { struct cfg80211_registered_device *rdev; struct wireless_dev *wdev; list_for_each_entry(rdev, &cfg80211_rdev_list, list) { list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { wdev_lock(wdev); if (!(wdev->wiphy->regulatory_flags & flag)) { wdev_unlock(wdev); return false; } wdev_unlock(wdev); } } return true; } void regulatory_hint_disconnect(void) { /* Restore of regulatory settings is not required when wiphy(s) * ignore IE from connected access point but clearance of beacon hints * is required when wiphy(s) supports beacon hints. */ if (is_wiphy_all_set_reg_flag(REGULATORY_COUNTRY_IE_IGNORE)) { struct reg_beacon *reg_beacon, *btmp; if (is_wiphy_all_set_reg_flag(REGULATORY_DISABLE_BEACON_HINTS)) return; spin_lock_bh(®_pending_beacons_lock); list_for_each_entry_safe(reg_beacon, btmp, ®_pending_beacons, list) { list_del(®_beacon->list); kfree(reg_beacon); } spin_unlock_bh(®_pending_beacons_lock); list_for_each_entry_safe(reg_beacon, btmp, ®_beacon_list, list) { list_del(®_beacon->list); kfree(reg_beacon); } return; } pr_debug("All devices are disconnected, going to restore regulatory settings\n"); restore_regulatory_settings(false); } static bool freq_is_chan_12_13_14(u16 freq) { if (freq == ieee80211_channel_to_frequency(12, NL80211_BAND_2GHZ) || freq == ieee80211_channel_to_frequency(13, NL80211_BAND_2GHZ) || freq == ieee80211_channel_to_frequency(14, NL80211_BAND_2GHZ)) return true; return false; } static bool pending_reg_beacon(struct ieee80211_channel *beacon_chan) { struct reg_beacon *pending_beacon; list_for_each_entry(pending_beacon, ®_pending_beacons, list) if (beacon_chan->center_freq == pending_beacon->chan.center_freq) return true; return false; } int regulatory_hint_found_beacon(struct wiphy *wiphy, struct ieee80211_channel *beacon_chan, gfp_t gfp) { struct reg_beacon *reg_beacon; bool processing; if (beacon_chan->beacon_found || beacon_chan->flags & IEEE80211_CHAN_RADAR || (beacon_chan->band == NL80211_BAND_2GHZ && !freq_is_chan_12_13_14(beacon_chan->center_freq))) return 0; spin_lock_bh(®_pending_beacons_lock); processing = pending_reg_beacon(beacon_chan); spin_unlock_bh(®_pending_beacons_lock); if (processing) return 0; reg_beacon = kzalloc(sizeof(struct reg_beacon), gfp); if (!reg_beacon) return -ENOMEM; pr_debug("Found new beacon on frequency: %d MHz (Ch %d) on %s\n", beacon_chan->center_freq, ieee80211_frequency_to_channel(beacon_chan->center_freq), wiphy_name(wiphy)); memcpy(®_beacon->chan, beacon_chan, sizeof(struct ieee80211_channel)); /* * Since we can be called from BH or and non-BH context * we must use spin_lock_bh() */ spin_lock_bh(®_pending_beacons_lock); list_add_tail(®_beacon->list, ®_pending_beacons); spin_unlock_bh(®_pending_beacons_lock); schedule_work(®_work); return 0; } static void print_rd_rules(const struct ieee80211_regdomain *rd) { unsigned int i; const struct ieee80211_reg_rule *reg_rule = NULL; const struct ieee80211_freq_range *freq_range = NULL; const struct ieee80211_power_rule *power_rule = NULL; char bw[32], cac_time[32]; pr_debug(" (start_freq - end_freq @ bandwidth), (max_antenna_gain, max_eirp), (dfs_cac_time)\n"); for (i = 0; i < rd->n_reg_rules; i++) { reg_rule = &rd->reg_rules[i]; freq_range = ®_rule->freq_range; power_rule = ®_rule->power_rule; if (reg_rule->flags & NL80211_RRF_AUTO_BW) snprintf(bw, sizeof(bw), "%d KHz, %u KHz AUTO", freq_range->max_bandwidth_khz, reg_get_max_bandwidth(rd, reg_rule)); else snprintf(bw, sizeof(bw), "%d KHz", freq_range->max_bandwidth_khz); if (reg_rule->flags & NL80211_RRF_DFS) scnprintf(cac_time, sizeof(cac_time), "%u s", reg_rule->dfs_cac_ms/1000); else scnprintf(cac_time, sizeof(cac_time), "N/A"); /* * There may not be documentation for max antenna gain * in certain regions */ if (power_rule->max_antenna_gain) pr_debug(" (%d KHz - %d KHz @ %s), (%d mBi, %d mBm), (%s)\n", freq_range->start_freq_khz, freq_range->end_freq_khz, bw, power_rule->max_antenna_gain, power_rule->max_eirp, cac_time); else pr_debug(" (%d KHz - %d KHz @ %s), (N/A, %d mBm), (%s)\n", freq_range->start_freq_khz, freq_range->end_freq_khz, bw, power_rule->max_eirp, cac_time); } } bool reg_supported_dfs_region(enum nl80211_dfs_regions dfs_region) { switch (dfs_region) { case NL80211_DFS_UNSET: case NL80211_DFS_FCC: case NL80211_DFS_ETSI: case NL80211_DFS_JP: return true; default: pr_debug("Ignoring uknown DFS master region: %d\n", dfs_region); return false; } } static void print_regdomain(const struct ieee80211_regdomain *rd) { struct regulatory_request *lr = get_last_request(); if (is_intersected_alpha2(rd->alpha2)) { if (lr->initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE) { struct cfg80211_registered_device *rdev; rdev = cfg80211_rdev_by_wiphy_idx(lr->wiphy_idx); if (rdev) { pr_debug("Current regulatory domain updated by AP to: %c%c\n", rdev->country_ie_alpha2[0], rdev->country_ie_alpha2[1]); } else pr_debug("Current regulatory domain intersected:\n"); } else pr_debug("Current regulatory domain intersected:\n"); } else if (is_world_regdom(rd->alpha2)) { pr_debug("World regulatory domain updated:\n"); } else { if (is_unknown_alpha2(rd->alpha2)) pr_debug("Regulatory domain changed to driver built-in settings (unknown country)\n"); else { if (reg_request_cell_base(lr)) pr_debug("Regulatory domain changed to country: %c%c by Cell Station\n", rd->alpha2[0], rd->alpha2[1]); else pr_debug("Regulatory domain changed to country: %c%c\n", rd->alpha2[0], rd->alpha2[1]); } } pr_debug(" DFS Master region: %s", reg_dfs_region_str(rd->dfs_region)); print_rd_rules(rd); } static void print_regdomain_info(const struct ieee80211_regdomain *rd) { pr_debug("Regulatory domain: %c%c\n", rd->alpha2[0], rd->alpha2[1]); print_rd_rules(rd); } static int reg_set_rd_core(const struct ieee80211_regdomain *rd) { if (!is_world_regdom(rd->alpha2)) return -EINVAL; update_world_regdomain(rd); return 0; } static int reg_set_rd_user(const struct ieee80211_regdomain *rd, struct regulatory_request *user_request) { const struct ieee80211_regdomain *intersected_rd = NULL; if (!regdom_changes(rd->alpha2)) return -EALREADY; if (!is_valid_rd(rd)) { pr_err("Invalid regulatory domain detected: %c%c\n", rd->alpha2[0], rd->alpha2[1]); print_regdomain_info(rd); return -EINVAL; } if (!user_request->intersect) { reset_regdomains(false, rd); return 0; } intersected_rd = regdom_intersect(rd, get_cfg80211_regdom()); if (!intersected_rd) return -EINVAL; kfree(rd); rd = NULL; reset_regdomains(false, intersected_rd); return 0; } static int reg_set_rd_driver(const struct ieee80211_regdomain *rd, struct regulatory_request *driver_request) { const struct ieee80211_regdomain *regd; const struct ieee80211_regdomain *intersected_rd = NULL; const struct ieee80211_regdomain *tmp; struct wiphy *request_wiphy; if (is_world_regdom(rd->alpha2)) return -EINVAL; if (!regdom_changes(rd->alpha2)) return -EALREADY; if (!is_valid_rd(rd)) { pr_err("Invalid regulatory domain detected: %c%c\n", rd->alpha2[0], rd->alpha2[1]); print_regdomain_info(rd); return -EINVAL; } request_wiphy = wiphy_idx_to_wiphy(driver_request->wiphy_idx); if (!request_wiphy) return -ENODEV; if (!driver_request->intersect) { if (request_wiphy->regd) return -EALREADY; regd = reg_copy_regd(rd); if (IS_ERR(regd)) return PTR_ERR(regd); rcu_assign_pointer(request_wiphy->regd, regd); reset_regdomains(false, rd); return 0; } intersected_rd = regdom_intersect(rd, get_cfg80211_regdom()); if (!intersected_rd) return -EINVAL; /* * We can trash what CRDA provided now. * However if a driver requested this specific regulatory * domain we keep it for its private use */ tmp = get_wiphy_regdom(request_wiphy); rcu_assign_pointer(request_wiphy->regd, rd); rcu_free_regdom(tmp); rd = NULL; reset_regdomains(false, intersected_rd); return 0; } static int reg_set_rd_country_ie(const struct ieee80211_regdomain *rd, struct regulatory_request *country_ie_request) { struct wiphy *request_wiphy; if (!is_alpha2_set(rd->alpha2) && !is_an_alpha2(rd->alpha2) && !is_unknown_alpha2(rd->alpha2)) return -EINVAL; /* * Lets only bother proceeding on the same alpha2 if the current * rd is non static (it means CRDA was present and was used last) * and the pending request came in from a country IE */ if (!is_valid_rd(rd)) { pr_err("Invalid regulatory domain detected: %c%c\n", rd->alpha2[0], rd->alpha2[1]); print_regdomain_info(rd); return -EINVAL; } request_wiphy = wiphy_idx_to_wiphy(country_ie_request->wiphy_idx); if (!request_wiphy) return -ENODEV; if (country_ie_request->intersect) return -EINVAL; reset_regdomains(false, rd); return 0; } /* * Use this call to set the current regulatory domain. Conflicts with * multiple drivers can be ironed out later. Caller must've already * kmalloc'd the rd structure. */ int set_regdom(const struct ieee80211_regdomain *rd, enum ieee80211_regd_source regd_src) { struct regulatory_request *lr; bool user_reset = false; int r; if (!reg_is_valid_request(rd->alpha2)) { kfree(rd); return -EINVAL; } if (regd_src == REGD_SOURCE_CRDA) reset_crda_timeouts(); lr = get_last_request(); /* Note that this doesn't update the wiphys, this is done below */ switch (lr->initiator) { case NL80211_REGDOM_SET_BY_CORE: r = reg_set_rd_core(rd); break; case NL80211_REGDOM_SET_BY_USER: r = reg_set_rd_user(rd, lr); user_reset = true; break; case NL80211_REGDOM_SET_BY_DRIVER: r = reg_set_rd_driver(rd, lr); break; case NL80211_REGDOM_SET_BY_COUNTRY_IE: r = reg_set_rd_country_ie(rd, lr); break; default: WARN(1, "invalid initiator %d\n", lr->initiator); kfree(rd); return -EINVAL; } if (r) { switch (r) { case -EALREADY: reg_set_request_processed(); break; default: /* Back to world regulatory in case of errors */ restore_regulatory_settings(user_reset); } kfree(rd); return r; } /* This would make this whole thing pointless */ if (WARN_ON(!lr->intersect && rd != get_cfg80211_regdom())) return -EINVAL; /* update all wiphys now with the new established regulatory domain */ update_all_wiphy_regulatory(lr->initiator); print_regdomain(get_cfg80211_regdom()); nl80211_send_reg_change_event(lr); reg_set_request_processed(); return 0; } static int __regulatory_set_wiphy_regd(struct wiphy *wiphy, struct ieee80211_regdomain *rd) { const struct ieee80211_regdomain *regd; const struct ieee80211_regdomain *prev_regd; struct cfg80211_registered_device *rdev; if (WARN_ON(!wiphy || !rd)) return -EINVAL; if (WARN(!(wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED), "wiphy should have REGULATORY_WIPHY_SELF_MANAGED\n")) return -EPERM; if (WARN(!is_valid_rd(rd), "Invalid regulatory domain detected\n")) { print_regdomain_info(rd); return -EINVAL; } regd = reg_copy_regd(rd); if (IS_ERR(regd)) return PTR_ERR(regd); rdev = wiphy_to_rdev(wiphy); spin_lock(®_requests_lock); prev_regd = rdev->requested_regd; rdev->requested_regd = regd; spin_unlock(®_requests_lock); kfree(prev_regd); return 0; } int regulatory_set_wiphy_regd(struct wiphy *wiphy, struct ieee80211_regdomain *rd) { int ret = __regulatory_set_wiphy_regd(wiphy, rd); if (ret) return ret; schedule_work(®_work); return 0; } EXPORT_SYMBOL(regulatory_set_wiphy_regd); int regulatory_set_wiphy_regd_sync_rtnl(struct wiphy *wiphy, struct ieee80211_regdomain *rd) { int ret; ASSERT_RTNL(); ret = __regulatory_set_wiphy_regd(wiphy, rd); if (ret) return ret; /* process the request immediately */ reg_process_self_managed_hints(); return 0; } EXPORT_SYMBOL(regulatory_set_wiphy_regd_sync_rtnl); void wiphy_regulatory_register(struct wiphy *wiphy) { struct regulatory_request *lr; /* self-managed devices ignore external hints */ if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) wiphy->regulatory_flags |= REGULATORY_DISABLE_BEACON_HINTS | REGULATORY_COUNTRY_IE_IGNORE; if (!reg_dev_ignore_cell_hint(wiphy)) reg_num_devs_support_basehint++; lr = get_last_request(); wiphy_update_regulatory(wiphy, lr->initiator); wiphy_all_share_dfs_chan_state(wiphy); } void wiphy_regulatory_deregister(struct wiphy *wiphy) { struct wiphy *request_wiphy = NULL; struct regulatory_request *lr; lr = get_last_request(); if (!reg_dev_ignore_cell_hint(wiphy)) reg_num_devs_support_basehint--; rcu_free_regdom(get_wiphy_regdom(wiphy)); RCU_INIT_POINTER(wiphy->regd, NULL); if (lr) request_wiphy = wiphy_idx_to_wiphy(lr->wiphy_idx); if (!request_wiphy || request_wiphy != wiphy) return; lr->wiphy_idx = WIPHY_IDX_INVALID; lr->country_ie_env = ENVIRON_ANY; } /* * See http://www.fcc.gov/document/5-ghz-unlicensed-spectrum-unii, for * UNII band definitions */ int cfg80211_get_unii(int freq) { /* UNII-1 */ if (freq >= 5150 && freq <= 5250) return 0; /* UNII-2A */ if (freq > 5250 && freq <= 5350) return 1; /* UNII-2B */ if (freq > 5350 && freq <= 5470) return 2; /* UNII-2C */ if (freq > 5470 && freq <= 5725) return 3; /* UNII-3 */ if (freq > 5725 && freq <= 5825) return 4; return -EINVAL; } bool regulatory_indoor_allowed(void) { return reg_is_indoor; } bool regulatory_pre_cac_allowed(struct wiphy *wiphy) { const struct ieee80211_regdomain *regd = NULL; const struct ieee80211_regdomain *wiphy_regd = NULL; bool pre_cac_allowed = false; rcu_read_lock(); regd = rcu_dereference(cfg80211_regdomain); wiphy_regd = rcu_dereference(wiphy->regd); if (!wiphy_regd) { if (regd->dfs_region == NL80211_DFS_ETSI) pre_cac_allowed = true; rcu_read_unlock(); return pre_cac_allowed; } if (regd->dfs_region == wiphy_regd->dfs_region && wiphy_regd->dfs_region == NL80211_DFS_ETSI) pre_cac_allowed = true; rcu_read_unlock(); return pre_cac_allowed; } static void cfg80211_check_and_end_cac(struct cfg80211_registered_device *rdev) { struct wireless_dev *wdev; /* If we finished CAC or received radar, we should end any * CAC running on the same channels. * the check !cfg80211_chandef_dfs_usable contain 2 options: * either all channels are available - those the CAC_FINISHED * event has effected another wdev state, or there is a channel * in unavailable state in wdev chandef - those the RADAR_DETECTED * event has effected another wdev state. * In both cases we should end the CAC on the wdev. */ list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { if (wdev->cac_started && !cfg80211_chandef_dfs_usable(&rdev->wiphy, &wdev->chandef)) rdev_end_cac(rdev, wdev->netdev); } } void regulatory_propagate_dfs_state(struct wiphy *wiphy, struct cfg80211_chan_def *chandef, enum nl80211_dfs_state dfs_state, enum nl80211_radar_event event) { struct cfg80211_registered_device *rdev; ASSERT_RTNL(); if (WARN_ON(!cfg80211_chandef_valid(chandef))) return; list_for_each_entry(rdev, &cfg80211_rdev_list, list) { if (wiphy == &rdev->wiphy) continue; if (!reg_dfs_domain_same(wiphy, &rdev->wiphy)) continue; if (!ieee80211_get_channel(&rdev->wiphy, chandef->chan->center_freq)) continue; cfg80211_set_dfs_state(&rdev->wiphy, chandef, dfs_state); if (event == NL80211_RADAR_DETECTED || event == NL80211_RADAR_CAC_FINISHED) { cfg80211_sched_dfs_chan_update(rdev); cfg80211_check_and_end_cac(rdev); } nl80211_radar_notify(rdev, chandef, event, NULL, GFP_KERNEL); } } int __init regulatory_init(void) { int err = 0; reg_pdev = platform_device_register_simple("regulatory", 0, NULL, 0); if (IS_ERR(reg_pdev)) return PTR_ERR(reg_pdev); spin_lock_init(®_requests_lock); spin_lock_init(®_pending_beacons_lock); spin_lock_init(®_indoor_lock); reg_regdb_size_check(); rcu_assign_pointer(cfg80211_regdomain, cfg80211_world_regdom); user_alpha2[0] = '9'; user_alpha2[1] = '7'; /* We always try to get an update for the static regdomain */ err = regulatory_hint_core(cfg80211_world_regdom->alpha2); if (err) { if (err == -ENOMEM) { platform_device_unregister(reg_pdev); return err; } /* * N.B. kobject_uevent_env() can fail mainly for when we're out * memory which is handled and propagated appropriately above * but it can also fail during a netlink_broadcast() or during * early boot for call_usermodehelper(). For now treat these * errors as non-fatal. */ pr_err("kobject_uevent_env() was unable to call CRDA during init\n"); } /* * Finally, if the user set the module parameter treat it * as a user hint. */ if (!is_world_regdom(ieee80211_regdom)) regulatory_hint_user(ieee80211_regdom, NL80211_USER_REG_HINT_USER); return 0; } void regulatory_exit(void) { struct regulatory_request *reg_request, *tmp; struct reg_beacon *reg_beacon, *btmp; cancel_work_sync(®_work); cancel_crda_timeout_sync(); cancel_delayed_work_sync(®_check_chans); /* Lock to suppress warnings */ rtnl_lock(); reset_regdomains(true, NULL); rtnl_unlock(); dev_set_uevent_suppress(®_pdev->dev, true); platform_device_unregister(reg_pdev); list_for_each_entry_safe(reg_beacon, btmp, ®_pending_beacons, list) { list_del(®_beacon->list); kfree(reg_beacon); } list_for_each_entry_safe(reg_beacon, btmp, ®_beacon_list, list) { list_del(®_beacon->list); kfree(reg_beacon); } list_for_each_entry_safe(reg_request, tmp, ®_requests_list, list) { list_del(®_request->list); kfree(reg_request); } } |
| 1 23 23 3 3 23 23 23 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 | /* * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved. * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved. * * This copyrighted material is made available to anyone wishing to use, * modify, copy, or redistribute it subject to the terms and conditions * of the GNU General Public License version 2. */ #ifndef __GLOCK_DOT_H__ #define __GLOCK_DOT_H__ #include <linux/sched.h> #include <linux/parser.h> #include "incore.h" #include "util.h" /* Options for hostdata parser */ enum { Opt_jid, Opt_id, Opt_first, Opt_nodir, Opt_err, }; /* * lm_lockname types */ #define LM_TYPE_RESERVED 0x00 #define LM_TYPE_NONDISK 0x01 #define LM_TYPE_INODE 0x02 #define LM_TYPE_RGRP 0x03 #define LM_TYPE_META 0x04 #define LM_TYPE_IOPEN 0x05 #define LM_TYPE_FLOCK 0x06 #define LM_TYPE_PLOCK 0x07 #define LM_TYPE_QUOTA 0x08 #define LM_TYPE_JOURNAL 0x09 /* * lm_lock() states * * SHARED is compatible with SHARED, not with DEFERRED or EX. * DEFERRED is compatible with DEFERRED, not with SHARED or EX. */ #define LM_ST_UNLOCKED 0 #define LM_ST_EXCLUSIVE 1 #define LM_ST_DEFERRED 2 #define LM_ST_SHARED 3 /* * lm_lock() flags * * LM_FLAG_TRY * Don't wait to acquire the lock if it can't be granted immediately. * * LM_FLAG_TRY_1CB * Send one blocking callback if TRY is set and the lock is not granted. * * LM_FLAG_NOEXP * GFS sets this flag on lock requests it makes while doing journal recovery. * These special requests should not be blocked due to the recovery like * ordinary locks would be. * * LM_FLAG_ANY * A SHARED request may also be granted in DEFERRED, or a DEFERRED request may * also be granted in SHARED. The preferred state is whichever is compatible * with other granted locks, or the specified state if no other locks exist. * * LM_FLAG_PRIORITY * Override fairness considerations. Suppose a lock is held in a shared state * and there is a pending request for the deferred state. A shared lock * request with the priority flag would be allowed to bypass the deferred * request and directly join the other shared lock. A shared lock request * without the priority flag might be forced to wait until the deferred * requested had acquired and released the lock. */ #define LM_FLAG_TRY 0x0001 #define LM_FLAG_TRY_1CB 0x0002 #define LM_FLAG_NOEXP 0x0004 #define LM_FLAG_ANY 0x0008 #define LM_FLAG_PRIORITY 0x0010 #define GL_ASYNC 0x0040 #define GL_EXACT 0x0080 #define GL_SKIP 0x0100 #define GL_NOCACHE 0x0400 /* * lm_async_cb return flags * * LM_OUT_ST_MASK * Masks the lower two bits of lock state in the returned value. * * LM_OUT_CANCELED * The lock request was canceled. * */ #define LM_OUT_ST_MASK 0x00000003 #define LM_OUT_CANCELED 0x00000008 #define LM_OUT_ERROR 0x00000004 /* * lm_recovery_done() messages */ #define LM_RD_GAVEUP 308 #define LM_RD_SUCCESS 309 #define GLR_TRYFAILED 13 #define GL_GLOCK_MAX_HOLD (long)(HZ / 5) #define GL_GLOCK_DFT_HOLD (long)(HZ / 5) #define GL_GLOCK_MIN_HOLD (long)(10) #define GL_GLOCK_HOLD_INCR (long)(HZ / 20) #define GL_GLOCK_HOLD_DECR (long)(HZ / 40) struct lm_lockops { const char *lm_proto_name; int (*lm_mount) (struct gfs2_sbd *sdp, const char *table); void (*lm_first_done) (struct gfs2_sbd *sdp); void (*lm_recovery_result) (struct gfs2_sbd *sdp, unsigned int jid, unsigned int result); void (*lm_unmount) (struct gfs2_sbd *sdp); void (*lm_withdraw) (struct gfs2_sbd *sdp); void (*lm_put_lock) (struct gfs2_glock *gl); int (*lm_lock) (struct gfs2_glock *gl, unsigned int req_state, unsigned int flags); void (*lm_cancel) (struct gfs2_glock *gl); const match_table_t *lm_tokens; }; extern struct workqueue_struct *gfs2_delete_workqueue; static inline struct gfs2_holder *gfs2_glock_is_locked_by_me(struct gfs2_glock *gl) { struct gfs2_holder *gh; struct pid *pid; /* Look in glock's list of holders for one with current task as owner */ spin_lock(&gl->gl_lockref.lock); pid = task_pid(current); list_for_each_entry(gh, &gl->gl_holders, gh_list) { if (!test_bit(HIF_HOLDER, &gh->gh_iflags)) break; if (gh->gh_owner_pid == pid) goto out; } gh = NULL; out: spin_unlock(&gl->gl_lockref.lock); return gh; } static inline int gfs2_glock_is_held_excl(struct gfs2_glock *gl) { return gl->gl_state == LM_ST_EXCLUSIVE; } static inline int gfs2_glock_is_held_dfrd(struct gfs2_glock *gl) { return gl->gl_state == LM_ST_DEFERRED; } static inline int gfs2_glock_is_held_shrd(struct gfs2_glock *gl) { return gl->gl_state == LM_ST_SHARED; } static inline struct address_space *gfs2_glock2aspace(struct gfs2_glock *gl) { if (gl->gl_ops->go_flags & GLOF_ASPACE) return (struct address_space *)(gl + 1); return NULL; } extern int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number, const struct gfs2_glock_operations *glops, int create, struct gfs2_glock **glp); extern void gfs2_glock_hold(struct gfs2_glock *gl); extern void gfs2_glock_put(struct gfs2_glock *gl); extern void gfs2_glock_queue_put(struct gfs2_glock *gl); extern void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, u16 flags, struct gfs2_holder *gh); extern void gfs2_holder_reinit(unsigned int state, u16 flags, struct gfs2_holder *gh); extern void gfs2_holder_uninit(struct gfs2_holder *gh); extern int gfs2_glock_nq(struct gfs2_holder *gh); extern int gfs2_glock_poll(struct gfs2_holder *gh); extern int gfs2_glock_wait(struct gfs2_holder *gh); extern void gfs2_glock_dq(struct gfs2_holder *gh); extern void gfs2_glock_dq_wait(struct gfs2_holder *gh); extern void gfs2_glock_dq_uninit(struct gfs2_holder *gh); extern int gfs2_glock_nq_num(struct gfs2_sbd *sdp, u64 number, const struct gfs2_glock_operations *glops, unsigned int state, u16 flags, struct gfs2_holder *gh); extern int gfs2_glock_nq_m(unsigned int num_gh, struct gfs2_holder *ghs); extern void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs); extern void gfs2_dump_glock(struct seq_file *seq, const struct gfs2_glock *gl); #define GLOCK_BUG_ON(gl,x) do { if (unlikely(x)) { gfs2_dump_glock(NULL, gl); BUG(); } } while(0) extern __printf(2, 3) void gfs2_print_dbg(struct seq_file *seq, const char *fmt, ...); /** * gfs2_glock_nq_init - initialize a holder and enqueue it on a glock * @gl: the glock * @state: the state we're requesting * @flags: the modifier flags * @gh: the holder structure * * Returns: 0, GLR_*, or errno */ static inline int gfs2_glock_nq_init(struct gfs2_glock *gl, unsigned int state, u16 flags, struct gfs2_holder *gh) { int error; gfs2_holder_init(gl, state, flags, gh); error = gfs2_glock_nq(gh); if (error) gfs2_holder_uninit(gh); return error; } extern void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state); extern void gfs2_glock_complete(struct gfs2_glock *gl, int ret); extern void gfs2_gl_hash_clear(struct gfs2_sbd *sdp); extern void gfs2_glock_finish_truncate(struct gfs2_inode *ip); extern void gfs2_glock_thaw(struct gfs2_sbd *sdp); extern void gfs2_glock_add_to_lru(struct gfs2_glock *gl); extern void gfs2_glock_free(struct gfs2_glock *gl); extern int __init gfs2_glock_init(void); extern void gfs2_glock_exit(void); extern int gfs2_create_debugfs_file(struct gfs2_sbd *sdp); extern void gfs2_delete_debugfs_file(struct gfs2_sbd *sdp); extern int gfs2_register_debugfs(void); extern void gfs2_unregister_debugfs(void); extern const struct lm_lockops gfs2_dlm_ops; static inline void gfs2_holder_mark_uninitialized(struct gfs2_holder *gh) { gh->gh_gl = NULL; } static inline bool gfs2_holder_initialized(struct gfs2_holder *gh) { return gh->gh_gl; } /** * glock_set_object - set the gl_object field of a glock * @gl: the glock * @object: the object */ static inline void glock_set_object(struct gfs2_glock *gl, void *object) { spin_lock(&gl->gl_lockref.lock); if (gfs2_assert_warn(gl->gl_name.ln_sbd, gl->gl_object == NULL)) gfs2_dump_glock(NULL, gl); gl->gl_object = object; spin_unlock(&gl->gl_lockref.lock); } /** * glock_clear_object - clear the gl_object field of a glock * @gl: the glock * @object: the object * * I'd love to similarly add this: * else if (gfs2_assert_warn(gl->gl_sbd, gl->gl_object == object)) * gfs2_dump_glock(NULL, gl); * Unfortunately, that's not possible because as soon as gfs2_delete_inode * frees the block in the rgrp, another process can reassign it for an I_NEW * inode in gfs2_create_inode because that calls new_inode, not gfs2_iget. * That means gfs2_delete_inode may subsequently try to call this function * for a glock that's already pointing to a brand new inode. If we clear the * new inode's gl_object, we'll introduce metadata corruption. Function * gfs2_delete_inode calls clear_inode which calls gfs2_clear_inode which also * tries to clear gl_object, so it's more than just gfs2_delete_inode. * */ static inline void glock_clear_object(struct gfs2_glock *gl, void *object) { spin_lock(&gl->gl_lockref.lock); if (gl->gl_object == object) gl->gl_object = NULL; spin_unlock(&gl->gl_lockref.lock); } #endif /* __GLOCK_DOT_H__ */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 | /* Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ /* Kernel module implementing an IP set type: the hash:ip,port type */ #include <linux/jhash.h> #include <linux/module.h> #include <linux/ip.h> #include <linux/skbuff.h> #include <linux/errno.h> #include <linux/random.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/netlink.h> #include <net/tcp.h> #include <linux/netfilter.h> #include <linux/netfilter/ipset/pfxlen.h> #include <linux/netfilter/ipset/ip_set.h> #include <linux/netfilter/ipset/ip_set_getport.h> #include <linux/netfilter/ipset/ip_set_hash.h> #define IPSET_TYPE_REV_MIN 0 /* 1 SCTP and UDPLITE support added */ /* 2 Counters support added */ /* 3 Comments support added */ /* 4 Forceadd support added */ #define IPSET_TYPE_REV_MAX 5 /* skbinfo support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); IP_SET_MODULE_DESC("hash:ip,port", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX); MODULE_ALIAS("ip_set_hash:ip,port"); /* Type specific function prefix */ #define HTYPE hash_ipport /* IPv4 variant */ /* Member elements */ struct hash_ipport4_elem { __be32 ip; __be16 port; u8 proto; u8 padding; }; /* Common functions */ static inline bool hash_ipport4_data_equal(const struct hash_ipport4_elem *ip1, const struct hash_ipport4_elem *ip2, u32 *multi) { return ip1->ip == ip2->ip && ip1->port == ip2->port && ip1->proto == ip2->proto; } static bool hash_ipport4_data_list(struct sk_buff *skb, const struct hash_ipport4_elem *data) { if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip) || nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto)) goto nla_put_failure; return false; nla_put_failure: return true; } static inline void hash_ipport4_data_next(struct hash_ipport4_elem *next, const struct hash_ipport4_elem *d) { next->ip = d->ip; next->port = d->port; } #define MTYPE hash_ipport4 #define HOST_MASK 32 #include "ip_set_hash_gen.h" static int hash_ipport4_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, enum ipset_adt adt, struct ip_set_adt_opt *opt) { ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipport4_elem e = { .ip = 0 }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); if (!ip_set_get_ip4_port(skb, opt->flags & IPSET_DIM_TWO_SRC, &e.port, &e.proto)) return -EINVAL; ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip); return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } static int hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { const struct hash_ipport4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipport4_elem e = { .ip = 0 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 ip, ip_to = 0, p = 0, port, port_to; bool with_ports = false; int ret; if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); if (unlikely(!tb[IPSET_ATTR_IP] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO))) return -IPSET_ERR_PROTOCOL; ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &e.ip); if (ret) return ret; ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); with_ports = ip_set_proto_with_ports(e.proto); if (e.proto == 0) return -IPSET_ERR_INVALID_PROTO; } else { return -IPSET_ERR_MISSING_PROTO; } if (!(with_ports || e.proto == IPPROTO_ICMP)) e.port = 0; if (adt == IPSET_TEST || !(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR] || tb[IPSET_ATTR_PORT_TO])) { ret = adtfn(set, &e, &ext, &ext, flags); return ip_set_eexist(ret, flags) ? 0 : ret; } ip_to = ip = ntohl(e.ip); if (tb[IPSET_ATTR_IP_TO]) { ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); if (ret) return ret; if (ip > ip_to) swap(ip, ip_to); } else if (tb[IPSET_ATTR_CIDR]) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); if (!cidr || cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; ip_set_mask_from_to(ip, ip_to, cidr); } port_to = port = ntohs(e.port); if (with_ports && tb[IPSET_ATTR_PORT_TO]) { port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); if (port > port_to) swap(port, port_to); } if (retried) ip = ntohl(h->next.ip); for (; ip <= ip_to; ip++) { p = retried && ip == ntohl(h->next.ip) ? ntohs(h->next.port) : port; for (; p <= port_to; p++) { e.ip = htonl(ip); e.port = htons(p); ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; ret = 0; } } return ret; } /* IPv6 variant */ struct hash_ipport6_elem { union nf_inet_addr ip; __be16 port; u8 proto; u8 padding; }; /* Common functions */ static inline bool hash_ipport6_data_equal(const struct hash_ipport6_elem *ip1, const struct hash_ipport6_elem *ip2, u32 *multi) { return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6) && ip1->port == ip2->port && ip1->proto == ip2->proto; } static bool hash_ipport6_data_list(struct sk_buff *skb, const struct hash_ipport6_elem *data) { if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &data->ip.in6) || nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto)) goto nla_put_failure; return false; nla_put_failure: return true; } static inline void hash_ipport6_data_next(struct hash_ipport6_elem *next, const struct hash_ipport6_elem *d) { next->port = d->port; } #undef MTYPE #undef HOST_MASK #define MTYPE hash_ipport6 #define HOST_MASK 128 #define IP_SET_EMIT_CREATE #include "ip_set_hash_gen.h" static int hash_ipport6_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, enum ipset_adt adt, struct ip_set_adt_opt *opt) { ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipport6_elem e = { .ip = { .all = { 0 } } }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); if (!ip_set_get_ip6_port(skb, opt->flags & IPSET_DIM_TWO_SRC, &e.port, &e.proto)) return -EINVAL; ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip.in6); return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } static int hash_ipport6_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { const struct hash_ipport6 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipport6_elem e = { .ip = { .all = { 0 } } }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 port, port_to; bool with_ports = false; int ret; if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); if (unlikely(!tb[IPSET_ATTR_IP] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO))) return -IPSET_ERR_PROTOCOL; if (unlikely(tb[IPSET_ATTR_IP_TO])) return -IPSET_ERR_HASH_RANGE_UNSUPPORTED; if (unlikely(tb[IPSET_ATTR_CIDR])) { u8 cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); if (cidr != HOST_MASK) return -IPSET_ERR_INVALID_CIDR; } ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip); if (ret) return ret; ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); with_ports = ip_set_proto_with_ports(e.proto); if (e.proto == 0) return -IPSET_ERR_INVALID_PROTO; } else { return -IPSET_ERR_MISSING_PROTO; } if (!(with_ports || e.proto == IPPROTO_ICMPV6)) e.port = 0; if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) { ret = adtfn(set, &e, &ext, &ext, flags); return ip_set_eexist(ret, flags) ? 0 : ret; } port = ntohs(e.port); port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); if (port > port_to) swap(port, port_to); if (retried) port = ntohs(h->next.port); for (; port <= port_to; port++) { e.port = htons(port); ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; ret = 0; } return ret; } static struct ip_set_type hash_ipport_type __read_mostly = { .name = "hash:ip,port", .protocol = IPSET_PROTOCOL, .features = IPSET_TYPE_IP | IPSET_TYPE_PORT, .dimension = IPSET_DIM_TWO, .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, .create = hash_ipport_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, }, .adt_policy = { [IPSET_ATTR_IP] = { .type = NLA_NESTED }, [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED }, [IPSET_ATTR_PORT] = { .type = NLA_U16 }, [IPSET_ATTR_PORT_TO] = { .type = NLA_U16 }, [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, }, .me = THIS_MODULE, }; static int __init hash_ipport_init(void) { return ip_set_type_register(&hash_ipport_type); } static void __exit hash_ipport_fini(void) { rcu_barrier(); ip_set_type_unregister(&hash_ipport_type); } module_init(hash_ipport_init); module_exit(hash_ipport_fini); |
| 9 9 9 7 8 9 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 | /* * Copyright (c) 2006 Jiri Benc <jbenc@suse.cz> * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ #include <linux/kernel.h> #include <linux/device.h> #include <linux/if.h> #include <linux/if_ether.h> #include <linux/interrupt.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> #include <linux/slab.h> #include <linux/notifier.h> #include <net/mac80211.h> #include <net/cfg80211.h> #include "ieee80211_i.h" #include "rate.h" #include "debugfs.h" #include "debugfs_netdev.h" #include "driver-ops.h" static ssize_t ieee80211_if_read( struct ieee80211_sub_if_data *sdata, char __user *userbuf, size_t count, loff_t *ppos, ssize_t (*format)(const struct ieee80211_sub_if_data *, char *, int)) { char buf[200]; ssize_t ret = -EINVAL; read_lock(&dev_base_lock); ret = (*format)(sdata, buf, sizeof(buf)); read_unlock(&dev_base_lock); if (ret >= 0) ret = simple_read_from_buffer(userbuf, count, ppos, buf, ret); return ret; } static ssize_t ieee80211_if_write( struct ieee80211_sub_if_data *sdata, const char __user *userbuf, size_t count, loff_t *ppos, ssize_t (*write)(struct ieee80211_sub_if_data *, const char *, int)) { char buf[64]; ssize_t ret; if (count >= sizeof(buf)) return -E2BIG; if (copy_from_user(buf, userbuf, count)) return -EFAULT; buf[count] = '\0'; ret = -ENODEV; rtnl_lock(); ret = (*write)(sdata, buf, count); rtnl_unlock(); return ret; } #define IEEE80211_IF_FMT(name, field, format_string) \ static ssize_t ieee80211_if_fmt_##name( \ const struct ieee80211_sub_if_data *sdata, char *buf, \ int buflen) \ { \ return scnprintf(buf, buflen, format_string, sdata->field); \ } #define IEEE80211_IF_FMT_DEC(name, field) \ IEEE80211_IF_FMT(name, field, "%d\n") #define IEEE80211_IF_FMT_HEX(name, field) \ IEEE80211_IF_FMT(name, field, "%#x\n") #define IEEE80211_IF_FMT_LHEX(name, field) \ IEEE80211_IF_FMT(name, field, "%#lx\n") #define IEEE80211_IF_FMT_SIZE(name, field) \ IEEE80211_IF_FMT(name, field, "%zd\n") #define IEEE80211_IF_FMT_HEXARRAY(name, field) \ static ssize_t ieee80211_if_fmt_##name( \ const struct ieee80211_sub_if_data *sdata, \ char *buf, int buflen) \ { \ char *p = buf; \ int i; \ for (i = 0; i < sizeof(sdata->field); i++) { \ p += scnprintf(p, buflen + buf - p, "%.2x ", \ sdata->field[i]); \ } \ p += scnprintf(p, buflen + buf - p, "\n"); \ return p - buf; \ } #define IEEE80211_IF_FMT_ATOMIC(name, field) \ static ssize_t ieee80211_if_fmt_##name( \ const struct ieee80211_sub_if_data *sdata, \ char *buf, int buflen) \ { \ return scnprintf(buf, buflen, "%d\n", atomic_read(&sdata->field));\ } #define IEEE80211_IF_FMT_MAC(name, field) \ static ssize_t ieee80211_if_fmt_##name( \ const struct ieee80211_sub_if_data *sdata, char *buf, \ int buflen) \ { \ return scnprintf(buf, buflen, "%pM\n", sdata->field); \ } #define IEEE80211_IF_FMT_JIFFIES_TO_MS(name, field) \ static ssize_t ieee80211_if_fmt_##name( \ const struct ieee80211_sub_if_data *sdata, \ char *buf, int buflen) \ { \ return scnprintf(buf, buflen, "%d\n", \ jiffies_to_msecs(sdata->field)); \ } #define _IEEE80211_IF_FILE_OPS(name, _read, _write) \ static const struct file_operations name##_ops = { \ .read = (_read), \ .write = (_write), \ .open = simple_open, \ .llseek = generic_file_llseek, \ } #define _IEEE80211_IF_FILE_R_FN(name) \ static ssize_t ieee80211_if_read_##name(struct file *file, \ char __user *userbuf, \ size_t count, loff_t *ppos) \ { \ return ieee80211_if_read(file->private_data, \ userbuf, count, ppos, \ ieee80211_if_fmt_##name); \ } #define _IEEE80211_IF_FILE_W_FN(name) \ static ssize_t ieee80211_if_write_##name(struct file *file, \ const char __user *userbuf, \ size_t count, loff_t *ppos) \ { \ return ieee80211_if_write(file->private_data, userbuf, count, \ ppos, ieee80211_if_parse_##name); \ } #define IEEE80211_IF_FILE_R(name) \ _IEEE80211_IF_FILE_R_FN(name) \ _IEEE80211_IF_FILE_OPS(name, ieee80211_if_read_##name, NULL) #define IEEE80211_IF_FILE_W(name) \ _IEEE80211_IF_FILE_W_FN(name) \ _IEEE80211_IF_FILE_OPS(name, NULL, ieee80211_if_write_##name) #define IEEE80211_IF_FILE_RW(name) \ _IEEE80211_IF_FILE_R_FN(name) \ _IEEE80211_IF_FILE_W_FN(name) \ _IEEE80211_IF_FILE_OPS(name, ieee80211_if_read_##name, \ ieee80211_if_write_##name) #define IEEE80211_IF_FILE(name, field, format) \ IEEE80211_IF_FMT_##format(name, field) \ IEEE80211_IF_FILE_R(name) /* common attributes */ IEEE80211_IF_FILE(rc_rateidx_mask_2ghz, rc_rateidx_mask[NL80211_BAND_2GHZ], HEX); IEEE80211_IF_FILE(rc_rateidx_mask_5ghz, rc_rateidx_mask[NL80211_BAND_5GHZ], HEX); IEEE80211_IF_FILE(rc_rateidx_mcs_mask_2ghz, rc_rateidx_mcs_mask[NL80211_BAND_2GHZ], HEXARRAY); IEEE80211_IF_FILE(rc_rateidx_mcs_mask_5ghz, rc_rateidx_mcs_mask[NL80211_BAND_5GHZ], HEXARRAY); static ssize_t ieee80211_if_fmt_rc_rateidx_vht_mcs_mask_2ghz( const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) { int i, len = 0; const u16 *mask = sdata->rc_rateidx_vht_mcs_mask[NL80211_BAND_2GHZ]; for (i = 0; i < NL80211_VHT_NSS_MAX; i++) len += scnprintf(buf + len, buflen - len, "%04x ", mask[i]); len += scnprintf(buf + len, buflen - len, "\n"); return len; } IEEE80211_IF_FILE_R(rc_rateidx_vht_mcs_mask_2ghz); static ssize_t ieee80211_if_fmt_rc_rateidx_vht_mcs_mask_5ghz( const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) { int i, len = 0; const u16 *mask = sdata->rc_rateidx_vht_mcs_mask[NL80211_BAND_5GHZ]; for (i = 0; i < NL80211_VHT_NSS_MAX; i++) len += scnprintf(buf + len, buflen - len, "%04x ", mask[i]); len += scnprintf(buf + len, buflen - len, "\n"); return len; } IEEE80211_IF_FILE_R(rc_rateidx_vht_mcs_mask_5ghz); IEEE80211_IF_FILE(flags, flags, HEX); IEEE80211_IF_FILE(state, state, LHEX); IEEE80211_IF_FILE(txpower, vif.bss_conf.txpower, DEC); IEEE80211_IF_FILE(ap_power_level, ap_power_level, DEC); IEEE80211_IF_FILE(user_power_level, user_power_level, DEC); static ssize_t ieee80211_if_fmt_hw_queues(const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) { int len; len = scnprintf(buf, buflen, "AC queues: VO:%d VI:%d BE:%d BK:%d\n", sdata->vif.hw_queue[IEEE80211_AC_VO], sdata->vif.hw_queue[IEEE80211_AC_VI], sdata->vif.hw_queue[IEEE80211_AC_BE], sdata->vif.hw_queue[IEEE80211_AC_BK]); if (sdata->vif.type == NL80211_IFTYPE_AP) len += scnprintf(buf + len, buflen - len, "cab queue: %d\n", sdata->vif.cab_queue); return len; } IEEE80211_IF_FILE_R(hw_queues); /* STA attributes */ IEEE80211_IF_FILE(bssid, u.mgd.bssid, MAC); IEEE80211_IF_FILE(aid, u.mgd.aid, DEC); IEEE80211_IF_FILE(beacon_timeout, u.mgd.beacon_timeout, JIFFIES_TO_MS); static int ieee80211_set_smps(struct ieee80211_sub_if_data *sdata, enum ieee80211_smps_mode smps_mode) { struct ieee80211_local *local = sdata->local; int err; if (!(local->hw.wiphy->features & NL80211_FEATURE_STATIC_SMPS) && smps_mode == IEEE80211_SMPS_STATIC) return -EINVAL; /* auto should be dynamic if in PS mode */ if (!(local->hw.wiphy->features & NL80211_FEATURE_DYNAMIC_SMPS) && (smps_mode == IEEE80211_SMPS_DYNAMIC || smps_mode == IEEE80211_SMPS_AUTOMATIC)) return -EINVAL; if (sdata->vif.type != NL80211_IFTYPE_STATION && sdata->vif.type != NL80211_IFTYPE_AP) return -EOPNOTSUPP; sdata_lock(sdata); if (sdata->vif.type == NL80211_IFTYPE_STATION) err = __ieee80211_request_smps_mgd(sdata, smps_mode); else err = __ieee80211_request_smps_ap(sdata, smps_mode); sdata_unlock(sdata); return err; } static const char *smps_modes[IEEE80211_SMPS_NUM_MODES] = { [IEEE80211_SMPS_AUTOMATIC] = "auto", [IEEE80211_SMPS_OFF] = "off", [IEEE80211_SMPS_STATIC] = "static", [IEEE80211_SMPS_DYNAMIC] = "dynamic", }; static ssize_t ieee80211_if_fmt_smps(const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) { if (sdata->vif.type == NL80211_IFTYPE_STATION) return snprintf(buf, buflen, "request: %s\nused: %s\n", smps_modes[sdata->u.mgd.req_smps], smps_modes[sdata->smps_mode]); if (sdata->vif.type == NL80211_IFTYPE_AP) return snprintf(buf, buflen, "request: %s\nused: %s\n", smps_modes[sdata->u.ap.req_smps], smps_modes[sdata->smps_mode]); return -EINVAL; } static ssize_t ieee80211_if_parse_smps(struct ieee80211_sub_if_data *sdata, const char *buf, int buflen) { enum ieee80211_smps_mode mode; for (mode = 0; mode < IEEE80211_SMPS_NUM_MODES; mode++) { if (strncmp(buf, smps_modes[mode], buflen) == 0) { int err = ieee80211_set_smps(sdata, mode); if (!err) return buflen; return err; } } return -EINVAL; } IEEE80211_IF_FILE_RW(smps); static ssize_t ieee80211_if_parse_tkip_mic_test( struct ieee80211_sub_if_data *sdata, const char *buf, int buflen) { struct ieee80211_local *local = sdata->local; u8 addr[ETH_ALEN]; struct sk_buff *skb; struct ieee80211_hdr *hdr; __le16 fc; if (!mac_pton(buf, addr)) return -EINVAL; if (!ieee80211_sdata_running(sdata)) return -ENOTCONN; skb = dev_alloc_skb(local->hw.extra_tx_headroom + 24 + 100); if (!skb) return -ENOMEM; skb_reserve(skb, local->hw.extra_tx_headroom); hdr = skb_put_zero(skb, 24); fc = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_DATA); switch (sdata->vif.type) { case NL80211_IFTYPE_AP: fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS); /* DA BSSID SA */ memcpy(hdr->addr1, addr, ETH_ALEN); memcpy(hdr->addr2, sdata->vif.addr, ETH_ALEN); memcpy(hdr->addr3, sdata->vif.addr, ETH_ALEN); break; case NL80211_IFTYPE_STATION: fc |= cpu_to_le16(IEEE80211_FCTL_TODS); /* BSSID SA DA */ sdata_lock(sdata); if (!sdata->u.mgd.associated) { sdata_unlock(sdata); dev_kfree_skb(skb); return -ENOTCONN; } memcpy(hdr->addr1, sdata->u.mgd.associated->bssid, ETH_ALEN); memcpy(hdr->addr2, sdata->vif.addr, ETH_ALEN); memcpy(hdr->addr3, addr, ETH_ALEN); sdata_unlock(sdata); break; default: dev_kfree_skb(skb); return -EOPNOTSUPP; } hdr->frame_control = fc; /* * Add some length to the test frame to make it look bit more valid. * The exact contents does not matter since the recipient is required * to drop this because of the Michael MIC failure. */ skb_put_zero(skb, 50); IEEE80211_SKB_CB(skb)->flags |= IEEE80211_TX_INTFL_TKIP_MIC_FAILURE; ieee80211_tx_skb(sdata, skb); return buflen; } IEEE80211_IF_FILE_W(tkip_mic_test); static ssize_t ieee80211_if_parse_beacon_loss( struct ieee80211_sub_if_data *sdata, const char *buf, int buflen) { if (!ieee80211_sdata_running(sdata) || !sdata->vif.bss_conf.assoc) return -ENOTCONN; ieee80211_beacon_loss(&sdata->vif); return buflen; } IEEE80211_IF_FILE_W(beacon_loss); static ssize_t ieee80211_if_fmt_uapsd_queues( const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) { const struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; return snprintf(buf, buflen, "0x%x\n", ifmgd->uapsd_queues); } static ssize_t ieee80211_if_parse_uapsd_queues( struct ieee80211_sub_if_data *sdata, const char *buf, int buflen) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; u8 val; int ret; ret = kstrtou8(buf, 0, &val); if (ret) return ret; if (val & ~IEEE80211_WMM_IE_STA_QOSINFO_AC_MASK) return -ERANGE; ifmgd->uapsd_queues = val; return buflen; } IEEE80211_IF_FILE_RW(uapsd_queues); static ssize_t ieee80211_if_fmt_uapsd_max_sp_len( const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) { const struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; return snprintf(buf, buflen, "0x%x\n", ifmgd->uapsd_max_sp_len); } static ssize_t ieee80211_if_parse_uapsd_max_sp_len( struct ieee80211_sub_if_data *sdata, const char *buf, int buflen) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; unsigned long val; int ret; ret = kstrtoul(buf, 0, &val); if (ret) return -EINVAL; if (val & ~IEEE80211_WMM_IE_STA_QOSINFO_SP_MASK) return -ERANGE; ifmgd->uapsd_max_sp_len = val; return buflen; } IEEE80211_IF_FILE_RW(uapsd_max_sp_len); static ssize_t ieee80211_if_fmt_tdls_wider_bw( const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) { const struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; bool tdls_wider_bw; tdls_wider_bw = ieee80211_hw_check(&sdata->local->hw, TDLS_WIDER_BW) && !ifmgd->tdls_wider_bw_prohibited; return snprintf(buf, buflen, "%d\n", tdls_wider_bw); } static ssize_t ieee80211_if_parse_tdls_wider_bw( struct ieee80211_sub_if_data *sdata, const char *buf, int buflen) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; u8 val; int ret; ret = kstrtou8(buf, 0, &val); if (ret) return ret; ifmgd->tdls_wider_bw_prohibited = !val; return buflen; } IEEE80211_IF_FILE_RW(tdls_wider_bw); /* AP attributes */ IEEE80211_IF_FILE(num_mcast_sta, u.ap.num_mcast_sta, ATOMIC); IEEE80211_IF_FILE(num_sta_ps, u.ap.ps.num_sta_ps, ATOMIC); IEEE80211_IF_FILE(dtim_count, u.ap.ps.dtim_count, DEC); IEEE80211_IF_FILE(num_mcast_sta_vlan, u.vlan.num_mcast_sta, ATOMIC); static ssize_t ieee80211_if_fmt_num_buffered_multicast( const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) { return scnprintf(buf, buflen, "%u\n", skb_queue_len(&sdata->u.ap.ps.bc_buf)); } IEEE80211_IF_FILE_R(num_buffered_multicast); static ssize_t ieee80211_if_fmt_aqm( const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) { struct ieee80211_local *local = sdata->local; struct txq_info *txqi; int len; if (!sdata->vif.txq) return 0; txqi = to_txq_info(sdata->vif.txq); spin_lock_bh(&local->fq.lock); rcu_read_lock(); len = scnprintf(buf, buflen, "ac backlog-bytes backlog-packets new-flows drops marks overlimit collisions tx-bytes tx-packets\n" "%u %u %u %u %u %u %u %u %u %u\n", txqi->txq.ac, txqi->tin.backlog_bytes, txqi->tin.backlog_packets, txqi->tin.flows, txqi->cstats.drop_count, txqi->cstats.ecn_mark, txqi->tin.overlimit, txqi->tin.collisions, txqi->tin.tx_bytes, txqi->tin.tx_packets); rcu_read_unlock(); spin_unlock_bh(&local->fq.lock); return len; } IEEE80211_IF_FILE_R(aqm); IEEE80211_IF_FILE(multicast_to_unicast, u.ap.multicast_to_unicast, HEX); /* IBSS attributes */ static ssize_t ieee80211_if_fmt_tsf( const struct ieee80211_sub_if_data *sdata, char *buf, int buflen) { struct ieee80211_local *local = sdata->local; u64 tsf; tsf = drv_get_tsf(local, (struct ieee80211_sub_if_data *)sdata); return scnprintf(buf, buflen, "0x%016llx\n", (unsigned long long) tsf); } static ssize_t ieee80211_if_parse_tsf( struct ieee80211_sub_if_data *sdata, const char *buf, int buflen) { struct ieee80211_local *local = sdata->local; unsigned long long tsf; int ret; int tsf_is_delta = 0; if (strncmp(buf, "reset", 5) == 0) { if (local->ops->reset_tsf) { drv_reset_tsf(local, sdata); wiphy_info(local->hw.wiphy, "debugfs reset TSF\n"); } } else { if (buflen > 10 && buf[1] == '=') { if (buf[0] == '+') tsf_is_delta = 1; else if (buf[0] == '-') tsf_is_delta = -1; else return -EINVAL; buf += 2; } ret = kstrtoull(buf, 10, &tsf); if (ret < 0) return ret; if (tsf_is_delta && local->ops->offset_tsf) { drv_offset_tsf(local, sdata, tsf_is_delta * tsf); wiphy_info(local->hw.wiphy, "debugfs offset TSF by %018lld\n", tsf_is_delta * tsf); } else if (local->ops->set_tsf) { if (tsf_is_delta) tsf = drv_get_tsf(local, sdata) + tsf_is_delta * tsf; drv_set_tsf(local, sdata, tsf); wiphy_info(local->hw.wiphy, "debugfs set TSF to %#018llx\n", tsf); } } ieee80211_recalc_dtim(local, sdata); return buflen; } IEEE80211_IF_FILE_RW(tsf); /* WDS attributes */ IEEE80211_IF_FILE(peer, u.wds.remote_addr, MAC); #ifdef CONFIG_MAC80211_MESH IEEE80211_IF_FILE(estab_plinks, u.mesh.estab_plinks, ATOMIC); /* Mesh stats attributes */ IEEE80211_IF_FILE(fwded_mcast, u.mesh.mshstats.fwded_mcast, DEC); IEEE80211_IF_FILE(fwded_unicast, u.mesh.mshstats.fwded_unicast, DEC); IEEE80211_IF_FILE(fwded_frames, u.mesh.mshstats.fwded_frames, DEC); IEEE80211_IF_FILE(dropped_frames_ttl, u.mesh.mshstats.dropped_frames_ttl, DEC); IEEE80211_IF_FILE(dropped_frames_congestion, u.mesh.mshstats.dropped_frames_congestion, DEC); IEEE80211_IF_FILE(dropped_frames_no_route, u.mesh.mshstats.dropped_frames_no_route, DEC); /* Mesh parameters */ IEEE80211_IF_FILE(dot11MeshMaxRetries, u.mesh.mshcfg.dot11MeshMaxRetries, DEC); IEEE80211_IF_FILE(dot11MeshRetryTimeout, u.mesh.mshcfg.dot11MeshRetryTimeout, DEC); IEEE80211_IF_FILE(dot11MeshConfirmTimeout, u.mesh.mshcfg.dot11MeshConfirmTimeout, DEC); IEEE80211_IF_FILE(dot11MeshHoldingTimeout, u.mesh.mshcfg.dot11MeshHoldingTimeout, DEC); IEEE80211_IF_FILE(dot11MeshTTL, u.mesh.mshcfg.dot11MeshTTL, DEC); IEEE80211_IF_FILE(element_ttl, u.mesh.mshcfg.element_ttl, DEC); IEEE80211_IF_FILE(auto_open_plinks, u.mesh.mshcfg.auto_open_plinks, DEC); IEEE80211_IF_FILE(dot11MeshMaxPeerLinks, u.mesh.mshcfg.dot11MeshMaxPeerLinks, DEC); IEEE80211_IF_FILE(dot11MeshHWMPactivePathTimeout, u.mesh.mshcfg.dot11MeshHWMPactivePathTimeout, DEC); IEEE80211_IF_FILE(dot11MeshHWMPpreqMinInterval, u.mesh.mshcfg.dot11MeshHWMPpreqMinInterval, DEC); IEEE80211_IF_FILE(dot11MeshHWMPperrMinInterval, u.mesh.mshcfg.dot11MeshHWMPperrMinInterval, DEC); IEEE80211_IF_FILE(dot11MeshHWMPnetDiameterTraversalTime, u.mesh.mshcfg.dot11MeshHWMPnetDiameterTraversalTime, DEC); IEEE80211_IF_FILE(dot11MeshHWMPmaxPREQretries, u.mesh.mshcfg.dot11MeshHWMPmaxPREQretries, DEC); IEEE80211_IF_FILE(path_refresh_time, u.mesh.mshcfg.path_refresh_time, DEC); IEEE80211_IF_FILE(min_discovery_timeout, u.mesh.mshcfg.min_discovery_timeout, DEC); IEEE80211_IF_FILE(dot11MeshHWMPRootMode, u.mesh.mshcfg.dot11MeshHWMPRootMode, DEC); IEEE80211_IF_FILE(dot11MeshGateAnnouncementProtocol, u.mesh.mshcfg.dot11MeshGateAnnouncementProtocol, DEC); IEEE80211_IF_FILE(dot11MeshHWMPRannInterval, u.mesh.mshcfg.dot11MeshHWMPRannInterval, DEC); IEEE80211_IF_FILE(dot11MeshForwarding, u.mesh.mshcfg.dot11MeshForwarding, DEC); IEEE80211_IF_FILE(rssi_threshold, u.mesh.mshcfg.rssi_threshold, DEC); IEEE80211_IF_FILE(ht_opmode, u.mesh.mshcfg.ht_opmode, DEC); IEEE80211_IF_FILE(dot11MeshHWMPactivePathToRootTimeout, u.mesh.mshcfg.dot11MeshHWMPactivePathToRootTimeout, DEC); IEEE80211_IF_FILE(dot11MeshHWMProotInterval, u.mesh.mshcfg.dot11MeshHWMProotInterval, DEC); IEEE80211_IF_FILE(dot11MeshHWMPconfirmationInterval, u.mesh.mshcfg.dot11MeshHWMPconfirmationInterval, DEC); IEEE80211_IF_FILE(power_mode, u.mesh.mshcfg.power_mode, DEC); IEEE80211_IF_FILE(dot11MeshAwakeWindowDuration, u.mesh.mshcfg.dot11MeshAwakeWindowDuration, DEC); #endif #define DEBUGFS_ADD_MODE(name, mode) \ debugfs_create_file(#name, mode, sdata->vif.debugfs_dir, \ sdata, &name##_ops); #define DEBUGFS_ADD(name) DEBUGFS_ADD_MODE(name, 0400) static void add_common_files(struct ieee80211_sub_if_data *sdata) { DEBUGFS_ADD(rc_rateidx_mask_2ghz); DEBUGFS_ADD(rc_rateidx_mask_5ghz); DEBUGFS_ADD(rc_rateidx_mcs_mask_2ghz); DEBUGFS_ADD(rc_rateidx_mcs_mask_5ghz); DEBUGFS_ADD(rc_rateidx_vht_mcs_mask_2ghz); DEBUGFS_ADD(rc_rateidx_vht_mcs_mask_5ghz); DEBUGFS_ADD(hw_queues); if (sdata->local->ops->wake_tx_queue && sdata->vif.type != NL80211_IFTYPE_P2P_DEVICE && sdata->vif.type != NL80211_IFTYPE_NAN) DEBUGFS_ADD(aqm); } static void add_sta_files(struct ieee80211_sub_if_data *sdata) { DEBUGFS_ADD(bssid); DEBUGFS_ADD(aid); DEBUGFS_ADD(beacon_timeout); DEBUGFS_ADD_MODE(smps, 0600); DEBUGFS_ADD_MODE(tkip_mic_test, 0200); DEBUGFS_ADD_MODE(beacon_loss, 0200); DEBUGFS_ADD_MODE(uapsd_queues, 0600); DEBUGFS_ADD_MODE(uapsd_max_sp_len, 0600); DEBUGFS_ADD_MODE(tdls_wider_bw, 0600); } static void add_ap_files(struct ieee80211_sub_if_data *sdata) { DEBUGFS_ADD(num_mcast_sta); DEBUGFS_ADD_MODE(smps, 0600); DEBUGFS_ADD(num_sta_ps); DEBUGFS_ADD(dtim_count); DEBUGFS_ADD(num_buffered_multicast); DEBUGFS_ADD_MODE(tkip_mic_test, 0200); DEBUGFS_ADD_MODE(multicast_to_unicast, 0600); } static void add_vlan_files(struct ieee80211_sub_if_data *sdata) { /* add num_mcast_sta_vlan using name num_mcast_sta */ debugfs_create_file("num_mcast_sta", 0400, sdata->vif.debugfs_dir, sdata, &num_mcast_sta_vlan_ops); } static void add_ibss_files(struct ieee80211_sub_if_data *sdata) { DEBUGFS_ADD_MODE(tsf, 0600); } static void add_wds_files(struct ieee80211_sub_if_data *sdata) { DEBUGFS_ADD(peer); } #ifdef CONFIG_MAC80211_MESH static void add_mesh_files(struct ieee80211_sub_if_data *sdata) { DEBUGFS_ADD_MODE(tsf, 0600); DEBUGFS_ADD_MODE(estab_plinks, 0400); } static void add_mesh_stats(struct ieee80211_sub_if_data *sdata) { struct dentry *dir = debugfs_create_dir("mesh_stats", sdata->vif.debugfs_dir); #define MESHSTATS_ADD(name)\ debugfs_create_file(#name, 0400, dir, sdata, &name##_ops); MESHSTATS_ADD(fwded_mcast); MESHSTATS_ADD(fwded_unicast); MESHSTATS_ADD(fwded_frames); MESHSTATS_ADD(dropped_frames_ttl); MESHSTATS_ADD(dropped_frames_no_route); MESHSTATS_ADD(dropped_frames_congestion); #undef MESHSTATS_ADD } static void add_mesh_config(struct ieee80211_sub_if_data *sdata) { struct dentry *dir = debugfs_create_dir("mesh_config", sdata->vif.debugfs_dir); #define MESHPARAMS_ADD(name) \ debugfs_create_file(#name, 0600, dir, sdata, &name##_ops); MESHPARAMS_ADD(dot11MeshMaxRetries); MESHPARAMS_ADD(dot11MeshRetryTimeout); MESHPARAMS_ADD(dot11MeshConfirmTimeout); MESHPARAMS_ADD(dot11MeshHoldingTimeout); MESHPARAMS_ADD(dot11MeshTTL); MESHPARAMS_ADD(element_ttl); MESHPARAMS_ADD(auto_open_plinks); MESHPARAMS_ADD(dot11MeshMaxPeerLinks); MESHPARAMS_ADD(dot11MeshHWMPactivePathTimeout); MESHPARAMS_ADD(dot11MeshHWMPpreqMinInterval); MESHPARAMS_ADD(dot11MeshHWMPperrMinInterval); MESHPARAMS_ADD(dot11MeshHWMPnetDiameterTraversalTime); MESHPARAMS_ADD(dot11MeshHWMPmaxPREQretries); MESHPARAMS_ADD(path_refresh_time); MESHPARAMS_ADD(min_discovery_timeout); MESHPARAMS_ADD(dot11MeshHWMPRootMode); MESHPARAMS_ADD(dot11MeshHWMPRannInterval); MESHPARAMS_ADD(dot11MeshForwarding); MESHPARAMS_ADD(dot11MeshGateAnnouncementProtocol); MESHPARAMS_ADD(rssi_threshold); MESHPARAMS_ADD(ht_opmode); MESHPARAMS_ADD(dot11MeshHWMPactivePathToRootTimeout); MESHPARAMS_ADD(dot11MeshHWMProotInterval); MESHPARAMS_ADD(dot11MeshHWMPconfirmationInterval); MESHPARAMS_ADD(power_mode); MESHPARAMS_ADD(dot11MeshAwakeWindowDuration); #undef MESHPARAMS_ADD } #endif static void add_files(struct ieee80211_sub_if_data *sdata) { if (!sdata->vif.debugfs_dir) return; DEBUGFS_ADD(flags); DEBUGFS_ADD(state); DEBUGFS_ADD(txpower); DEBUGFS_ADD(user_power_level); DEBUGFS_ADD(ap_power_level); if (sdata->vif.type != NL80211_IFTYPE_MONITOR) add_common_files(sdata); switch (sdata->vif.type) { case NL80211_IFTYPE_MESH_POINT: #ifdef CONFIG_MAC80211_MESH add_mesh_files(sdata); add_mesh_stats(sdata); add_mesh_config(sdata); #endif break; case NL80211_IFTYPE_STATION: add_sta_files(sdata); break; case NL80211_IFTYPE_ADHOC: add_ibss_files(sdata); break; case NL80211_IFTYPE_AP: add_ap_files(sdata); break; case NL80211_IFTYPE_AP_VLAN: add_vlan_files(sdata); break; case NL80211_IFTYPE_WDS: add_wds_files(sdata); break; default: break; } } void ieee80211_debugfs_add_netdev(struct ieee80211_sub_if_data *sdata) { char buf[10+IFNAMSIZ]; sprintf(buf, "netdev:%s", sdata->name); sdata->vif.debugfs_dir = debugfs_create_dir(buf, sdata->local->hw.wiphy->debugfsdir); if (sdata->vif.debugfs_dir) sdata->debugfs.subdir_stations = debugfs_create_dir("stations", sdata->vif.debugfs_dir); add_files(sdata); } void ieee80211_debugfs_remove_netdev(struct ieee80211_sub_if_data *sdata) { if (!sdata->vif.debugfs_dir) return; debugfs_remove_recursive(sdata->vif.debugfs_dir); sdata->vif.debugfs_dir = NULL; sdata->debugfs.subdir_stations = NULL; } void ieee80211_debugfs_rename_netdev(struct ieee80211_sub_if_data *sdata) { struct dentry *dir; char buf[10 + IFNAMSIZ]; dir = sdata->vif.debugfs_dir; if (!dir) return; sprintf(buf, "netdev:%s", sdata->name); if (!debugfs_rename(dir->d_parent, dir, dir->d_parent, buf)) sdata_err(sdata, "debugfs: failed to rename debugfs dir to %s\n", buf); } |
| 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 | /* * Copyright 2015, Heiner Kallweit <hkallweit1@gmail.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include "leds.h" DEFINE_LED_TRIGGER(bt_power_led_trigger); struct hci_basic_led_trigger { struct led_trigger led_trigger; struct hci_dev *hdev; }; #define to_hci_basic_led_trigger(arg) container_of(arg, \ struct hci_basic_led_trigger, led_trigger) void hci_leds_update_powered(struct hci_dev *hdev, bool enabled) { if (hdev->power_led) led_trigger_event(hdev->power_led, enabled ? LED_FULL : LED_OFF); if (!enabled) { struct hci_dev *d; read_lock(&hci_dev_list_lock); list_for_each_entry(d, &hci_dev_list, list) { if (test_bit(HCI_UP, &d->flags)) enabled = true; } read_unlock(&hci_dev_list_lock); } led_trigger_event(bt_power_led_trigger, enabled ? LED_FULL : LED_OFF); } static void power_activate(struct led_classdev *led_cdev) { struct hci_basic_led_trigger *htrig; bool powered; htrig = to_hci_basic_led_trigger(led_cdev->trigger); powered = test_bit(HCI_UP, &htrig->hdev->flags); led_trigger_event(led_cdev->trigger, powered ? LED_FULL : LED_OFF); } static struct led_trigger *led_allocate_basic(struct hci_dev *hdev, void (*activate)(struct led_classdev *led_cdev), const char *name) { struct hci_basic_led_trigger *htrig; htrig = devm_kzalloc(&hdev->dev, sizeof(*htrig), GFP_KERNEL); if (!htrig) return NULL; htrig->hdev = hdev; htrig->led_trigger.activate = activate; htrig->led_trigger.name = devm_kasprintf(&hdev->dev, GFP_KERNEL, "%s-%s", hdev->name, name); if (!htrig->led_trigger.name) goto err_alloc; if (devm_led_trigger_register(&hdev->dev, &htrig->led_trigger)) goto err_register; return &htrig->led_trigger; err_register: devm_kfree(&hdev->dev, (void *)htrig->led_trigger.name); err_alloc: devm_kfree(&hdev->dev, htrig); return NULL; } void hci_leds_init(struct hci_dev *hdev) { /* initialize power_led */ hdev->power_led = led_allocate_basic(hdev, power_activate, "power"); } void bt_leds_init(void) { led_trigger_register_simple("bluetooth-power", &bt_power_led_trigger); } void bt_leds_cleanup(void) { led_trigger_unregister_simple(bt_power_led_trigger); } |
| 741 612 703 7 5 729 729 48 48 48 2 48 696 697 626 864 825 801 637 835 769 835 282 834 834 801 738 738 835 759 759 835 864 272 272 864 92 864 863 36 863 864 485 470 709 708 729 8 28 28 28 19 28 11 778 521 1062 49 1062 766 1061 964 964 700 1062 32 1061 730 1061 182 182 182 182 182 1062 607 64 606 607 606 729 31 729 729 699 729 728 729 728 31 729 607 606 607 729 37 37 1 37 6 37 2 1 37 930 45 930 845 844 930 188 187 929 41 41 22 41 1753 188 188 41 188 55 187 143 188 1001 1001 1000 48 47 1025 1025 1008 1008 1008 1025 864 1024 1025 1025 1025 221 216 178 60 59 1024 728 1024 1025 1024 1025 51 1022 1003 1024 854 40 713 237 131 131 130 134 1 134 134 130 2 2 134 116 110 134 150 231 2 208 208 209 209 24 209 209 209 93 209 27 29 24 29 29 29 29 38 38 29 38 954 330 954 832 291 832 954 12 954 954 954 849 3 849 252 848 26 25 23 23 26 741 645 586 501 738 391 624 611 624 623 31 503 38 226 121 473 239 279 269 43 759 43 743 759 189 178 122 61 746 703 596 579 291 745 241 198 216 132 198 198 217 180 179 179 169 163 163 117 78 71 12 8 749 48 732 4 4 4 732 1174 37 628 1174 693 840 756 757 213 709 756 11 334 733 218 189 731 46 731 731 741 741 731 756 579 741 141 739 756 578 894 894 893 710 894 673 671 456 558 672 673 670 9 2 7 6 6 6 8 9 748 360 360 872 872 7 871 412 412 388 869 758 869 872 91 91 25 91 1 34 34 34 11 23 34 34 34 141 141 141 141 141 141 44 33 192 177 21 21 177 177 1 1 177 22 177 119 174 63 174 177 177 176 192 186 171 171 185 154 186 186 186 170 186 186 186 186 185 185 54 185 185 185 170 169 150 1014 24 20 40 60 485 484 484 16 37 4 37 37 36 37 800 800 799 36 799 177 800 800 800 3 2 800 52 729 72 800 800 729 729 607 607 607 3 605 72 729 729 729 123 729 728 801 596 159 5 160 160 159 596 304 302 302 597 767 768 15 14 14 1 1 1 1 1 1 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 | /* * 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. * * Implementation of the Transmission Control Protocol(TCP). * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Mark Evans, <evansmp@uhura.aston.ac.uk> * Corey Minyard <wf-rch!minyard@relay.EU.net> * Florian La Roche, <flla@stud.uni-sb.de> * Charles Hedrick, <hedrick@klinzhai.rutgers.edu> * Linus Torvalds, <torvalds@cs.helsinki.fi> * Alan Cox, <gw4pts@gw4pts.ampr.org> * Matthew Dillon, <dillon@apollo.west.oic.com> * Arnt Gulbrandsen, <agulbra@nvg.unit.no> * Jorge Cwik, <jorge@laser.satlink.net> */ /* * Changes: Pedro Roque : Retransmit queue handled by TCP. * : Fragmentation on mtu decrease * : Segment collapse on retransmit * : AF independence * * Linus Torvalds : send_delayed_ack * David S. Miller : Charge memory using the right skb * during syn/ack processing. * David S. Miller : Output engine completely rewritten. * Andrea Arcangeli: SYNACK carry ts_recent in tsecr. * Cacophonix Gaul : draft-minshall-nagle-01 * J Hadi Salim : ECN support * */ #define pr_fmt(fmt) "TCP: " fmt #include <net/tcp.h> #include <linux/compiler.h> #include <linux/gfp.h> #include <linux/module.h> /* People can turn this off for buggy TCP's found in printers etc. */ int sysctl_tcp_retrans_collapse __read_mostly = 1; /* People can turn this on to work with those rare, broken TCPs that * interpret the window field as a signed quantity. */ int sysctl_tcp_workaround_signed_windows __read_mostly = 0; /* Default TSQ limit of four TSO segments */ int sysctl_tcp_limit_output_bytes __read_mostly = 262144; /* This limits the percentage of the congestion window which we * will allow a single TSO frame to consume. Building TSO frames * which are too large can cause TCP streams to be bursty. */ int sysctl_tcp_tso_win_divisor __read_mostly = 3; /* By default, RFC2861 behavior. */ int sysctl_tcp_slow_start_after_idle __read_mostly = 1; static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, int push_one, gfp_t gfp); /* Account for new data that has been sent to the network. */ static void tcp_event_new_data_sent(struct sock *sk, const struct sk_buff *skb) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); unsigned int prior_packets = tp->packets_out; tcp_advance_send_head(sk, skb); tp->snd_nxt = TCP_SKB_CB(skb)->end_seq; tp->packets_out += tcp_skb_pcount(skb); if (!prior_packets || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) tcp_rearm_rto(sk); NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT, tcp_skb_pcount(skb)); tcp_check_space(sk); } /* SND.NXT, if window was not shrunk or the amount of shrunk was less than one * window scaling factor due to loss of precision. * If window has been shrunk, what should we make? It is not clear at all. * Using SND.UNA we will fail to open window, SND.NXT is out of window. :-( * Anything in between SND.UNA...SND.UNA+SND.WND also can be already * invalid. OK, let's make this for now: */ static inline __u32 tcp_acceptable_seq(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); if (!before(tcp_wnd_end(tp), tp->snd_nxt) || (tp->rx_opt.wscale_ok && ((tp->snd_nxt - tcp_wnd_end(tp)) < (1 << tp->rx_opt.rcv_wscale)))) return tp->snd_nxt; else return tcp_wnd_end(tp); } /* Calculate mss to advertise in SYN segment. * RFC1122, RFC1063, draft-ietf-tcpimpl-pmtud-01 state that: * * 1. It is independent of path mtu. * 2. Ideally, it is maximal possible segment size i.e. 65535-40. * 3. For IPv4 it is reasonable to calculate it from maximal MTU of * attached devices, because some buggy hosts are confused by * large MSS. * 4. We do not make 3, we advertise MSS, calculated from first * hop device mtu, but allow to raise it to ip_rt_min_advmss. * This may be overridden via information stored in routing table. * 5. Value 65535 for MSS is valid in IPv6 and means "as large as possible, * probably even Jumbo". */ static __u16 tcp_advertise_mss(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); const struct dst_entry *dst = __sk_dst_get(sk); int mss = tp->advmss; if (dst) { unsigned int metric = dst_metric_advmss(dst); if (metric < mss) { mss = metric; tp->advmss = mss; } } return (__u16)mss; } /* RFC2861. Reset CWND after idle period longer RTO to "restart window". * This is the first part of cwnd validation mechanism. */ void tcp_cwnd_restart(struct sock *sk, s32 delta) { struct tcp_sock *tp = tcp_sk(sk); u32 restart_cwnd = tcp_init_cwnd(tp, __sk_dst_get(sk)); u32 cwnd = tp->snd_cwnd; tcp_ca_event(sk, CA_EVENT_CWND_RESTART); tp->snd_ssthresh = tcp_current_ssthresh(sk); restart_cwnd = min(restart_cwnd, cwnd); while ((delta -= inet_csk(sk)->icsk_rto) > 0 && cwnd > restart_cwnd) cwnd >>= 1; tp->snd_cwnd = max(cwnd, restart_cwnd); tp->snd_cwnd_stamp = tcp_jiffies32; tp->snd_cwnd_used = 0; } /* Congestion state accounting after a packet has been sent. */ static void tcp_event_data_sent(struct tcp_sock *tp, struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); const u32 now = tcp_jiffies32; if (tcp_packets_in_flight(tp) == 0) tcp_ca_event(sk, CA_EVENT_TX_START); tp->lsndtime = now; /* If it is a reply for ato after last received * packet, enter pingpong mode. */ if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato) icsk->icsk_ack.pingpong = 1; } /* Account for an ACK we sent. */ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts, u32 rcv_nxt) { struct tcp_sock *tp = tcp_sk(sk); if (unlikely(rcv_nxt != tp->rcv_nxt)) return; /* Special ACK sent by DCTCP to reflect ECN */ tcp_dec_quickack_mode(sk, pkts); inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); } u32 tcp_default_init_rwnd(u32 mss) { /* Initial receive window should be twice of TCP_INIT_CWND to * enable proper sending of new unsent data during fast recovery * (RFC 3517, Section 4, NextSeg() rule (2)). Further place a * limit when mss is larger than 1460. */ u32 init_rwnd = TCP_INIT_CWND * 2; if (mss > 1460) init_rwnd = max((1460 * init_rwnd) / mss, 2U); return init_rwnd; } /* Determine a window scaling and initial window to offer. * Based on the assumption that the given amount of space * will be offered. Store the results in the tp structure. * NOTE: for smooth operation initial space offering should * be a multiple of mss if possible. We assume here that mss >= 1. * This MUST be enforced by all callers. */ void tcp_select_initial_window(int __space, __u32 mss, __u32 *rcv_wnd, __u32 *window_clamp, int wscale_ok, __u8 *rcv_wscale, __u32 init_rcv_wnd) { unsigned int space = (__space < 0 ? 0 : __space); /* If no clamp set the clamp to the max possible scaled window */ if (*window_clamp == 0) (*window_clamp) = (U16_MAX << TCP_MAX_WSCALE); space = min(*window_clamp, space); /* Quantize space offering to a multiple of mss if possible. */ if (space > mss) space = rounddown(space, mss); /* NOTE: offering an initial window larger than 32767 * will break some buggy TCP stacks. If the admin tells us * it is likely we could be speaking with such a buggy stack * we will truncate our initial window offering to 32K-1 * unless the remote has sent us a window scaling option, * which we interpret as a sign the remote TCP is not * misinterpreting the window field as a signed quantity. */ if (sysctl_tcp_workaround_signed_windows) (*rcv_wnd) = min(space, MAX_TCP_WINDOW); else (*rcv_wnd) = space; (*rcv_wscale) = 0; if (wscale_ok) { /* Set window scaling on max possible window */ space = max_t(u32, space, sysctl_tcp_rmem[2]); space = max_t(u32, space, sysctl_rmem_max); space = min_t(u32, space, *window_clamp); while (space > U16_MAX && (*rcv_wscale) < TCP_MAX_WSCALE) { space >>= 1; (*rcv_wscale)++; } } if (mss > (1 << *rcv_wscale)) { if (!init_rcv_wnd) /* Use default unless specified otherwise */ init_rcv_wnd = tcp_default_init_rwnd(mss); *rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss); } /* Set the clamp no higher than max representable value */ (*window_clamp) = min_t(__u32, U16_MAX << (*rcv_wscale), *window_clamp); } EXPORT_SYMBOL(tcp_select_initial_window); /* Chose a new window to advertise, update state in tcp_sock for the * socket, and return result with RFC1323 scaling applied. The return * value can be stuffed directly into th->window for an outgoing * frame. */ static u16 tcp_select_window(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); u32 old_win = tp->rcv_wnd; u32 cur_win = tcp_receive_window(tp); u32 new_win = __tcp_select_window(sk); /* Never shrink the offered window */ if (new_win < cur_win) { /* Danger Will Robinson! * Don't update rcv_wup/rcv_wnd here or else * we will not be able to advertise a zero * window in time. --DaveM * * Relax Will Robinson. */ if (new_win == 0) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPWANTZEROWINDOWADV); new_win = ALIGN(cur_win, 1 << tp->rx_opt.rcv_wscale); } tp->rcv_wnd = new_win; tp->rcv_wup = tp->rcv_nxt; /* Make sure we do not exceed the maximum possible * scaled window. */ if (!tp->rx_opt.rcv_wscale && sysctl_tcp_workaround_signed_windows) new_win = min(new_win, MAX_TCP_WINDOW); else new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale)); /* RFC1323 scaling applied */ new_win >>= tp->rx_opt.rcv_wscale; /* If we advertise zero window, disable fast path. */ if (new_win == 0) { tp->pred_flags = 0; if (old_win) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPTOZEROWINDOWADV); } else if (old_win == 0) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFROMZEROWINDOWADV); } return new_win; } /* Packet ECN state for a SYN-ACK */ static void tcp_ecn_send_synack(struct sock *sk, struct sk_buff *skb) { const struct tcp_sock *tp = tcp_sk(sk); TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_CWR; if (!(tp->ecn_flags & TCP_ECN_OK)) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_ECE; else if (tcp_ca_needs_ecn(sk) || tcp_bpf_ca_needs_ecn(sk)) INET_ECN_xmit(sk); } /* Packet ECN state for a SYN. */ static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); bool bpf_needs_ecn = tcp_bpf_ca_needs_ecn(sk); bool use_ecn = sock_net(sk)->ipv4.sysctl_tcp_ecn == 1 || tcp_ca_needs_ecn(sk) || bpf_needs_ecn; if (!use_ecn) { const struct dst_entry *dst = __sk_dst_get(sk); if (dst && dst_feature(dst, RTAX_FEATURE_ECN)) use_ecn = true; } tp->ecn_flags = 0; if (use_ecn) { TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR; tp->ecn_flags = TCP_ECN_OK; if (tcp_ca_needs_ecn(sk) || bpf_needs_ecn) INET_ECN_xmit(sk); } } static void tcp_ecn_clear_syn(struct sock *sk, struct sk_buff *skb) { if (sock_net(sk)->ipv4.sysctl_tcp_ecn_fallback) /* tp->ecn_flags are cleared at a later point in time when * SYN ACK is ultimatively being received. */ TCP_SKB_CB(skb)->tcp_flags &= ~(TCPHDR_ECE | TCPHDR_CWR); } static void tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th) { if (inet_rsk(req)->ecn_ok) th->ece = 1; } /* Set up ECN state for a packet on a ESTABLISHED socket that is about to * be sent. */ static void tcp_ecn_send(struct sock *sk, struct sk_buff *skb, struct tcphdr *th, int tcp_header_len) { struct tcp_sock *tp = tcp_sk(sk); if (tp->ecn_flags & TCP_ECN_OK) { /* Not-retransmitted data segment: set ECT and inject CWR. */ if (skb->len != tcp_header_len && !before(TCP_SKB_CB(skb)->seq, tp->snd_nxt)) { INET_ECN_xmit(sk); if (tp->ecn_flags & TCP_ECN_QUEUE_CWR) { tp->ecn_flags &= ~TCP_ECN_QUEUE_CWR; th->cwr = 1; skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN; } } else if (!tcp_ca_needs_ecn(sk)) { /* ACK or retransmitted segment: clear ECT|CE */ INET_ECN_dontxmit(sk); } if (tp->ecn_flags & TCP_ECN_DEMAND_CWR) th->ece = 1; } } /* Constructs common control bits of non-data skb. If SYN/FIN is present, * auto increment end seqno. */ static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u8 flags) { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum = 0; TCP_SKB_CB(skb)->tcp_flags = flags; TCP_SKB_CB(skb)->sacked = 0; tcp_skb_pcount_set(skb, 1); TCP_SKB_CB(skb)->seq = seq; if (flags & (TCPHDR_SYN | TCPHDR_FIN)) seq++; TCP_SKB_CB(skb)->end_seq = seq; } static inline bool tcp_urg_mode(const struct tcp_sock *tp) { return tp->snd_una != tp->snd_up; } #define OPTION_SACK_ADVERTISE (1 << 0) #define OPTION_TS (1 << 1) #define OPTION_MD5 (1 << 2) #define OPTION_WSCALE (1 << 3) #define OPTION_FAST_OPEN_COOKIE (1 << 8) struct tcp_out_options { u16 options; /* bit field of OPTION_* */ u16 mss; /* 0 to disable */ u8 ws; /* window scale, 0 to disable */ u8 num_sack_blocks; /* number of SACK blocks to include */ u8 hash_size; /* bytes in hash_location */ __u8 *hash_location; /* temporary pointer, overloaded */ __u32 tsval, tsecr; /* need to include OPTION_TS */ struct tcp_fastopen_cookie *fastopen_cookie; /* Fast open cookie */ }; /* Write previously computed TCP options to the packet. * * Beware: Something in the Internet is very sensitive to the ordering of * TCP options, we learned this through the hard way, so be careful here. * Luckily we can at least blame others for their non-compliance but from * inter-operability perspective it seems that we're somewhat stuck with * the ordering which we have been using if we want to keep working with * those broken things (not that it currently hurts anybody as there isn't * particular reason why the ordering would need to be changed). * * At least SACK_PERM as the first option is known to lead to a disaster * (but it may well be that other scenarios fail similarly). */ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp, struct tcp_out_options *opts) { u16 options = opts->options; /* mungable copy */ if (unlikely(OPTION_MD5 & options)) { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG); /* overload cookie hash location */ opts->hash_location = (__u8 *)ptr; ptr += 4; } if (unlikely(opts->mss)) { *ptr++ = htonl((TCPOPT_MSS << 24) | (TCPOLEN_MSS << 16) | opts->mss); } if (likely(OPTION_TS & options)) { if (unlikely(OPTION_SACK_ADVERTISE & options)) { *ptr++ = htonl((TCPOPT_SACK_PERM << 24) | (TCPOLEN_SACK_PERM << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); options &= ~OPTION_SACK_ADVERTISE; } else { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); } *ptr++ = htonl(opts->tsval); *ptr++ = htonl(opts->tsecr); } if (unlikely(OPTION_SACK_ADVERTISE & options)) { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_SACK_PERM << 8) | TCPOLEN_SACK_PERM); } if (unlikely(OPTION_WSCALE & options)) { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_WINDOW << 16) | (TCPOLEN_WINDOW << 8) | opts->ws); } if (unlikely(opts->num_sack_blocks)) { struct tcp_sack_block *sp = tp->rx_opt.dsack ? tp->duplicate_sack : tp->selective_acks; int this_sack; *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_SACK << 8) | (TCPOLEN_SACK_BASE + (opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK))); for (this_sack = 0; this_sack < opts->num_sack_blocks; ++this_sack) { *ptr++ = htonl(sp[this_sack].start_seq); *ptr++ = htonl(sp[this_sack].end_seq); } tp->rx_opt.dsack = 0; } if (unlikely(OPTION_FAST_OPEN_COOKIE & options)) { struct tcp_fastopen_cookie *foc = opts->fastopen_cookie; u8 *p = (u8 *)ptr; u32 len; /* Fast Open option length */ if (foc->exp) { len = TCPOLEN_EXP_FASTOPEN_BASE + foc->len; *ptr = htonl((TCPOPT_EXP << 24) | (len << 16) | TCPOPT_FASTOPEN_MAGIC); p += TCPOLEN_EXP_FASTOPEN_BASE; } else { len = TCPOLEN_FASTOPEN_BASE + foc->len; *p++ = TCPOPT_FASTOPEN; *p++ = len; } memcpy(p, foc->val, foc->len); if ((len & 3) == 2) { p[foc->len] = TCPOPT_NOP; p[foc->len + 1] = TCPOPT_NOP; } ptr += (len + 3) >> 2; } } /* Compute TCP options for SYN packets. This is not the final * network wire format yet. */ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, struct tcp_out_options *opts, struct tcp_md5sig_key **md5) { struct tcp_sock *tp = tcp_sk(sk); unsigned int remaining = MAX_TCP_OPTION_SPACE; struct tcp_fastopen_request *fastopen = tp->fastopen_req; #ifdef CONFIG_TCP_MD5SIG *md5 = tp->af_specific->md5_lookup(sk, sk); if (*md5) { opts->options |= OPTION_MD5; remaining -= TCPOLEN_MD5SIG_ALIGNED; } #else *md5 = NULL; #endif /* We always get an MSS option. The option bytes which will be seen in * normal data packets should timestamps be used, must be in the MSS * advertised. But we subtract them from tp->mss_cache so that * calculations in tcp_sendmsg are simpler etc. So account for this * fact here if necessary. If we don't do this correctly, as a * receiver we won't recognize data packets as being full sized when we * should, and thus we won't abide by the delayed ACK rules correctly. * SACKs don't matter, we never delay an ACK when we have any of those * going out. */ opts->mss = tcp_advertise_mss(sk); remaining -= TCPOLEN_MSS_ALIGNED; if (likely(sock_net(sk)->ipv4.sysctl_tcp_timestamps && !*md5)) { opts->options |= OPTION_TS; opts->tsval = tcp_skb_timestamp(skb) + tp->tsoffset; opts->tsecr = tp->rx_opt.ts_recent; remaining -= TCPOLEN_TSTAMP_ALIGNED; } if (likely(sock_net(sk)->ipv4.sysctl_tcp_window_scaling)) { opts->ws = tp->rx_opt.rcv_wscale; opts->options |= OPTION_WSCALE; remaining -= TCPOLEN_WSCALE_ALIGNED; } if (likely(sock_net(sk)->ipv4.sysctl_tcp_sack)) { opts->options |= OPTION_SACK_ADVERTISE; if (unlikely(!(OPTION_TS & opts->options))) remaining -= TCPOLEN_SACKPERM_ALIGNED; } if (fastopen && fastopen->cookie.len >= 0) { u32 need = fastopen->cookie.len; need += fastopen->cookie.exp ? TCPOLEN_EXP_FASTOPEN_BASE : TCPOLEN_FASTOPEN_BASE; need = (need + 3) & ~3U; /* Align to 32 bits */ if (remaining >= need) { opts->options |= OPTION_FAST_OPEN_COOKIE; opts->fastopen_cookie = &fastopen->cookie; remaining -= need; tp->syn_fastopen = 1; tp->syn_fastopen_exp = fastopen->cookie.exp ? 1 : 0; } } return MAX_TCP_OPTION_SPACE - remaining; } /* Set up TCP options for SYN-ACKs. */ static unsigned int tcp_synack_options(struct request_sock *req, unsigned int mss, struct sk_buff *skb, struct tcp_out_options *opts, const struct tcp_md5sig_key *md5, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type) { struct inet_request_sock *ireq = inet_rsk(req); unsigned int remaining = MAX_TCP_OPTION_SPACE; #ifdef CONFIG_TCP_MD5SIG if (md5) { opts->options |= OPTION_MD5; remaining -= TCPOLEN_MD5SIG_ALIGNED; /* We can't fit any SACK blocks in a packet with MD5 + TS * options. There was discussion about disabling SACK * rather than TS in order to fit in better with old, * buggy kernels, but that was deemed to be unnecessary. */ if (synack_type != TCP_SYNACK_COOKIE) ireq->tstamp_ok &= !ireq->sack_ok; } #endif /* We always send an MSS option. */ opts->mss = mss; remaining -= TCPOLEN_MSS_ALIGNED; if (likely(ireq->wscale_ok)) { opts->ws = ireq->rcv_wscale; opts->options |= OPTION_WSCALE; remaining -= TCPOLEN_WSCALE_ALIGNED; } if (likely(ireq->tstamp_ok)) { opts->options |= OPTION_TS; opts->tsval = tcp_skb_timestamp(skb) + tcp_rsk(req)->ts_off; opts->tsecr = req->ts_recent; remaining -= TCPOLEN_TSTAMP_ALIGNED; } if (likely(ireq->sack_ok)) { opts->options |= OPTION_SACK_ADVERTISE; if (unlikely(!ireq->tstamp_ok)) remaining -= TCPOLEN_SACKPERM_ALIGNED; } if (foc != NULL && foc->len >= 0) { u32 need = foc->len; need += foc->exp ? TCPOLEN_EXP_FASTOPEN_BASE : TCPOLEN_FASTOPEN_BASE; need = (need + 3) & ~3U; /* Align to 32 bits */ if (remaining >= need) { opts->options |= OPTION_FAST_OPEN_COOKIE; opts->fastopen_cookie = foc; remaining -= need; } } return MAX_TCP_OPTION_SPACE - remaining; } /* Compute TCP options for ESTABLISHED sockets. This is not the * final wire format yet. */ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb, struct tcp_out_options *opts, struct tcp_md5sig_key **md5) { struct tcp_sock *tp = tcp_sk(sk); unsigned int size = 0; unsigned int eff_sacks; opts->options = 0; #ifdef CONFIG_TCP_MD5SIG *md5 = tp->af_specific->md5_lookup(sk, sk); if (unlikely(*md5)) { opts->options |= OPTION_MD5; size += TCPOLEN_MD5SIG_ALIGNED; } #else *md5 = NULL; #endif if (likely(tp->rx_opt.tstamp_ok)) { opts->options |= OPTION_TS; opts->tsval = skb ? tcp_skb_timestamp(skb) + tp->tsoffset : 0; opts->tsecr = tp->rx_opt.ts_recent; size += TCPOLEN_TSTAMP_ALIGNED; } eff_sacks = tp->rx_opt.num_sacks + tp->rx_opt.dsack; if (unlikely(eff_sacks)) { const unsigned int remaining = MAX_TCP_OPTION_SPACE - size; opts->num_sack_blocks = min_t(unsigned int, eff_sacks, (remaining - TCPOLEN_SACK_BASE_ALIGNED) / TCPOLEN_SACK_PERBLOCK); if (likely(opts->num_sack_blocks)) size += TCPOLEN_SACK_BASE_ALIGNED + opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK; } return size; } /* TCP SMALL QUEUES (TSQ) * * TSQ goal is to keep small amount of skbs per tcp flow in tx queues (qdisc+dev) * to reduce RTT and bufferbloat. * We do this using a special skb destructor (tcp_wfree). * * Its important tcp_wfree() can be replaced by sock_wfree() in the event skb * needs to be reallocated in a driver. * The invariant being skb->truesize subtracted from sk->sk_wmem_alloc * * Since transmit from skb destructor is forbidden, we use a tasklet * to process all sockets that eventually need to send more skbs. * We use one tasklet per cpu, with its own queue of sockets. */ struct tsq_tasklet { struct tasklet_struct tasklet; struct list_head head; /* queue of tcp sockets */ }; static DEFINE_PER_CPU(struct tsq_tasklet, tsq_tasklet); static void tcp_tsq_handler(struct sock *sk) { if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_CLOSE_WAIT | TCPF_LAST_ACK)) { struct tcp_sock *tp = tcp_sk(sk); if (tp->lost_out > tp->retrans_out && tp->snd_cwnd > tcp_packets_in_flight(tp)) { tcp_mstamp_refresh(tp); tcp_xmit_retransmit_queue(sk); } tcp_write_xmit(sk, tcp_current_mss(sk), tp->nonagle, 0, GFP_ATOMIC); } } /* * One tasklet per cpu tries to send more skbs. * We run in tasklet context but need to disable irqs when * transferring tsq->head because tcp_wfree() might * interrupt us (non NAPI drivers) */ static void tcp_tasklet_func(unsigned long data) { struct tsq_tasklet *tsq = (struct tsq_tasklet *)data; LIST_HEAD(list); unsigned long flags; struct list_head *q, *n; struct tcp_sock *tp; struct sock *sk; local_irq_save(flags); list_splice_init(&tsq->head, &list); local_irq_restore(flags); list_for_each_safe(q, n, &list) { tp = list_entry(q, struct tcp_sock, tsq_node); list_del(&tp->tsq_node); sk = (struct sock *)tp; smp_mb__before_atomic(); clear_bit(TSQ_QUEUED, &sk->sk_tsq_flags); if (!sk->sk_lock.owned && test_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags)) { bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { clear_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags); tcp_tsq_handler(sk); } bh_unlock_sock(sk); } sk_free(sk); } } #define TCP_DEFERRED_ALL (TCPF_TSQ_DEFERRED | \ TCPF_WRITE_TIMER_DEFERRED | \ TCPF_DELACK_TIMER_DEFERRED | \ TCPF_MTU_REDUCED_DEFERRED) /** * tcp_release_cb - tcp release_sock() callback * @sk: socket * * called from release_sock() to perform protocol dependent * actions before socket release. */ void tcp_release_cb(struct sock *sk) { unsigned long flags, nflags; /* perform an atomic operation only if at least one flag is set */ do { flags = sk->sk_tsq_flags; if (!(flags & TCP_DEFERRED_ALL)) return; nflags = flags & ~TCP_DEFERRED_ALL; } while (cmpxchg(&sk->sk_tsq_flags, flags, nflags) != flags); if (flags & TCPF_TSQ_DEFERRED) tcp_tsq_handler(sk); /* Here begins the tricky part : * We are called from release_sock() with : * 1) BH disabled * 2) sk_lock.slock spinlock held * 3) socket owned by us (sk->sk_lock.owned == 1) * * But following code is meant to be called from BH handlers, * so we should keep BH disabled, but early release socket ownership */ sock_release_ownership(sk); if (flags & TCPF_WRITE_TIMER_DEFERRED) { tcp_write_timer_handler(sk); __sock_put(sk); } if (flags & TCPF_DELACK_TIMER_DEFERRED) { tcp_delack_timer_handler(sk); __sock_put(sk); } if (flags & TCPF_MTU_REDUCED_DEFERRED) { inet_csk(sk)->icsk_af_ops->mtu_reduced(sk); __sock_put(sk); } } EXPORT_SYMBOL(tcp_release_cb); void __init tcp_tasklet_init(void) { int i; for_each_possible_cpu(i) { struct tsq_tasklet *tsq = &per_cpu(tsq_tasklet, i); INIT_LIST_HEAD(&tsq->head); tasklet_init(&tsq->tasklet, tcp_tasklet_func, (unsigned long)tsq); } } /* * Write buffer destructor automatically called from kfree_skb. * We can't xmit new skbs from this context, as we might already * hold qdisc lock. */ void tcp_wfree(struct sk_buff *skb) { struct sock *sk = skb->sk; struct tcp_sock *tp = tcp_sk(sk); unsigned long flags, nval, oval; /* Keep one reference on sk_wmem_alloc. * Will be released by sk_free() from here or tcp_tasklet_func() */ WARN_ON(refcount_sub_and_test(skb->truesize - 1, &sk->sk_wmem_alloc)); /* If this softirq is serviced by ksoftirqd, we are likely under stress. * Wait until our queues (qdisc + devices) are drained. * This gives : * - less callbacks to tcp_write_xmit(), reducing stress (batches) * - chance for incoming ACK (processed by another cpu maybe) * to migrate this flow (skb->ooo_okay will be eventually set) */ if (refcount_read(&sk->sk_wmem_alloc) >= SKB_TRUESIZE(1) && this_cpu_ksoftirqd() == current) goto out; for (oval = READ_ONCE(sk->sk_tsq_flags);; oval = nval) { struct tsq_tasklet *tsq; bool empty; if (!(oval & TSQF_THROTTLED) || (oval & TSQF_QUEUED)) goto out; nval = (oval & ~TSQF_THROTTLED) | TSQF_QUEUED | TCPF_TSQ_DEFERRED; nval = cmpxchg(&sk->sk_tsq_flags, oval, nval); if (nval != oval) continue; /* queue this socket to tasklet queue */ local_irq_save(flags); tsq = this_cpu_ptr(&tsq_tasklet); empty = list_empty(&tsq->head); list_add(&tp->tsq_node, &tsq->head); if (empty) tasklet_schedule(&tsq->tasklet); local_irq_restore(flags); return; } out: sk_free(sk); } /* Note: Called under hard irq. * We can not call TCP stack right away. */ enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer) { struct tcp_sock *tp = container_of(timer, struct tcp_sock, pacing_timer); struct sock *sk = (struct sock *)tp; unsigned long nval, oval; for (oval = READ_ONCE(sk->sk_tsq_flags);; oval = nval) { struct tsq_tasklet *tsq; bool empty; if (oval & TSQF_QUEUED) break; nval = (oval & ~TSQF_THROTTLED) | TSQF_QUEUED | TCPF_TSQ_DEFERRED; nval = cmpxchg(&sk->sk_tsq_flags, oval, nval); if (nval != oval) continue; if (!refcount_inc_not_zero(&sk->sk_wmem_alloc)) break; /* queue this socket to tasklet queue */ tsq = this_cpu_ptr(&tsq_tasklet); empty = list_empty(&tsq->head); list_add(&tp->tsq_node, &tsq->head); if (empty) tasklet_schedule(&tsq->tasklet); break; } return HRTIMER_NORESTART; } /* BBR congestion control needs pacing. * Same remark for SO_MAX_PACING_RATE. * sch_fq packet scheduler is efficiently handling pacing, * but is not always installed/used. * Return true if TCP stack should pace packets itself. */ static bool tcp_needs_internal_pacing(const struct sock *sk) { return smp_load_acquire(&sk->sk_pacing_status) == SK_PACING_NEEDED; } static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb) { u64 len_ns; u32 rate; if (!tcp_needs_internal_pacing(sk)) return; rate = sk->sk_pacing_rate; if (!rate || rate == ~0U) return; /* Should account for header sizes as sch_fq does, * but lets make things simple. */ len_ns = (u64)skb->len * NSEC_PER_SEC; do_div(len_ns, rate); hrtimer_start(&tcp_sk(sk)->pacing_timer, ktime_add_ns(ktime_get(), len_ns), HRTIMER_MODE_ABS_PINNED); } /* This routine actually transmits TCP packets queued in by * tcp_do_sendmsg(). This is used by both the initial * transmission and possible later retransmissions. * All SKB's seen here are completely headerless. It is our * job to build the TCP header, and pass the packet down to * IP so it can do the same plus pass the packet off to the * device. * * We are working here with either a clone of the original * SKB, or a fresh unique copy made by the retransmit engine. */ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, gfp_t gfp_mask, u32 rcv_nxt) { const struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet; struct tcp_sock *tp; struct tcp_skb_cb *tcb; struct tcp_out_options opts; unsigned int tcp_options_size, tcp_header_size; struct sk_buff *oskb = NULL; struct tcp_md5sig_key *md5; struct tcphdr *th; int err; BUG_ON(!skb || !tcp_skb_pcount(skb)); tp = tcp_sk(sk); if (clone_it) { TCP_SKB_CB(skb)->tx.in_flight = TCP_SKB_CB(skb)->end_seq - tp->snd_una; oskb = skb; if (unlikely(skb_cloned(skb))) skb = pskb_copy(skb, gfp_mask); else skb = skb_clone(skb, gfp_mask); if (unlikely(!skb)) return -ENOBUFS; } skb->skb_mstamp = tp->tcp_mstamp; inet = inet_sk(sk); tcb = TCP_SKB_CB(skb); memset(&opts, 0, sizeof(opts)); if (unlikely(tcb->tcp_flags & TCPHDR_SYN)) tcp_options_size = tcp_syn_options(sk, skb, &opts, &md5); else tcp_options_size = tcp_established_options(sk, skb, &opts, &md5); tcp_header_size = tcp_options_size + sizeof(struct tcphdr); /* if no packet is in qdisc/device queue, then allow XPS to select * another queue. We can be called from tcp_tsq_handler() * which holds one reference to sk_wmem_alloc. * * TODO: Ideally, in-flight pure ACK packets should not matter here. * One way to get this would be to set skb->truesize = 2 on them. */ skb->ooo_okay = sk_wmem_alloc_get(sk) < SKB_TRUESIZE(1); /* If we had to use memory reserve to allocate this skb, * this might cause drops if packet is looped back : * Other socket might not have SOCK_MEMALLOC. * Packets not looped back do not care about pfmemalloc. */ skb->pfmemalloc = 0; skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); skb_orphan(skb); skb->sk = sk; skb->destructor = skb_is_tcp_pure_ack(skb) ? __sock_wfree : tcp_wfree; skb_set_hash_from_sk(skb, sk); refcount_add(skb->truesize, &sk->sk_wmem_alloc); skb_set_dst_pending_confirm(skb, sk->sk_dst_pending_confirm); /* Build TCP header and checksum it. */ th = (struct tcphdr *)skb->data; th->source = inet->inet_sport; th->dest = inet->inet_dport; th->seq = htonl(tcb->seq); th->ack_seq = htonl(rcv_nxt); *(((__be16 *)th) + 6) = htons(((tcp_header_size >> 2) << 12) | tcb->tcp_flags); th->check = 0; th->urg_ptr = 0; /* The urg_mode check is necessary during a below snd_una win probe */ if (unlikely(tcp_urg_mode(tp) && before(tcb->seq, tp->snd_up))) { if (before(tp->snd_up, tcb->seq + 0x10000)) { th->urg_ptr = htons(tp->snd_up - tcb->seq); th->urg = 1; } else if (after(tcb->seq + 0xFFFF, tp->snd_nxt)) { th->urg_ptr = htons(0xFFFF); th->urg = 1; } } tcp_options_write((__be32 *)(th + 1), tp, &opts); skb_shinfo(skb)->gso_type = sk->sk_gso_type; if (likely(!(tcb->tcp_flags & TCPHDR_SYN))) { th->window = htons(tcp_select_window(sk)); tcp_ecn_send(sk, skb, th, tcp_header_size); } else { /* RFC1323: The window in SYN & SYN/ACK segments * is never scaled. */ th->window = htons(min(tp->rcv_wnd, 65535U)); } #ifdef CONFIG_TCP_MD5SIG /* Calculate the MD5 hash, as we have all we need now */ if (md5) { sk_nocaps_add(sk, NETIF_F_GSO_MASK); tp->af_specific->calc_md5_hash(opts.hash_location, md5, sk, skb); } #endif icsk->icsk_af_ops->send_check(sk, skb); if (likely(tcb->tcp_flags & TCPHDR_ACK)) tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt); if (skb->len != tcp_header_size) { tcp_event_data_sent(tp, sk); tp->data_segs_out += tcp_skb_pcount(skb); tcp_internal_pacing(sk, skb); } if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq) TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS, tcp_skb_pcount(skb)); tp->segs_out += tcp_skb_pcount(skb); /* OK, its time to fill skb_shinfo(skb)->gso_{segs|size} */ skb_shinfo(skb)->gso_segs = tcp_skb_pcount(skb); skb_shinfo(skb)->gso_size = tcp_skb_mss(skb); /* Our usage of tstamp should remain private */ skb->tstamp = 0; /* Cleanup our debris for IP stacks */ memset(skb->cb, 0, max(sizeof(struct inet_skb_parm), sizeof(struct inet6_skb_parm))); err = icsk->icsk_af_ops->queue_xmit(sk, skb, &inet->cork.fl); if (unlikely(err > 0)) { tcp_enter_cwr(sk); err = net_xmit_eval(err); } if (!err && oskb) { oskb->skb_mstamp = tp->tcp_mstamp; tcp_rate_skb_sent(sk, oskb); } return err; } static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, gfp_t gfp_mask) { return __tcp_transmit_skb(sk, skb, clone_it, gfp_mask, tcp_sk(sk)->rcv_nxt); } /* This routine just queues the buffer for sending. * * NOTE: probe0 timer is not checked, do not forget tcp_push_pending_frames, * otherwise socket can stall. */ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); /* Advance write_seq and place onto the write_queue. */ tp->write_seq = TCP_SKB_CB(skb)->end_seq; __skb_header_release(skb); tcp_add_write_queue_tail(sk, skb); sk->sk_wmem_queued += skb->truesize; sk_mem_charge(sk, skb->truesize); } /* Initialize TSO segments for a packet. */ static void tcp_set_skb_tso_segs(struct sk_buff *skb, unsigned int mss_now) { if (skb->len <= mss_now || skb->ip_summed == CHECKSUM_NONE) { /* Avoid the costly divide in the normal * non-TSO case. */ tcp_skb_pcount_set(skb, 1); TCP_SKB_CB(skb)->tcp_gso_size = 0; } else { tcp_skb_pcount_set(skb, DIV_ROUND_UP(skb->len, mss_now)); TCP_SKB_CB(skb)->tcp_gso_size = mss_now; } } /* When a modification to fackets out becomes necessary, we need to check * skb is counted to fackets_out or not. */ static void tcp_adjust_fackets_out(struct sock *sk, const struct sk_buff *skb, int decr) { struct tcp_sock *tp = tcp_sk(sk); if (!tp->sacked_out || tcp_is_reno(tp)) return; if (after(tcp_highest_sack_seq(tp), TCP_SKB_CB(skb)->seq)) tp->fackets_out -= decr; } /* Pcount in the middle of the write queue got changed, we need to do various * tweaks to fix counters */ static void tcp_adjust_pcount(struct sock *sk, const struct sk_buff *skb, int decr) { struct tcp_sock *tp = tcp_sk(sk); tp->packets_out -= decr; if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) tp->sacked_out -= decr; if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) tp->retrans_out -= decr; if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST) tp->lost_out -= decr; /* Reno case is special. Sigh... */ if (tcp_is_reno(tp) && decr > 0) tp->sacked_out -= min_t(u32, tp->sacked_out, decr); tcp_adjust_fackets_out(sk, skb, decr); if (tp->lost_skb_hint && before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(tp->lost_skb_hint)->seq) && (tcp_is_fack(tp) || (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED))) tp->lost_cnt_hint -= decr; tcp_verify_left_out(tp); } static bool tcp_has_tx_tstamp(const struct sk_buff *skb) { return TCP_SKB_CB(skb)->txstamp_ack || (skb_shinfo(skb)->tx_flags & SKBTX_ANY_TSTAMP); } static void tcp_fragment_tstamp(struct sk_buff *skb, struct sk_buff *skb2) { struct skb_shared_info *shinfo = skb_shinfo(skb); if (unlikely(tcp_has_tx_tstamp(skb)) && !before(shinfo->tskey, TCP_SKB_CB(skb2)->seq)) { struct skb_shared_info *shinfo2 = skb_shinfo(skb2); u8 tsflags = shinfo->tx_flags & SKBTX_ANY_TSTAMP; shinfo->tx_flags &= ~tsflags; shinfo2->tx_flags |= tsflags; swap(shinfo->tskey, shinfo2->tskey); TCP_SKB_CB(skb2)->txstamp_ack = TCP_SKB_CB(skb)->txstamp_ack; TCP_SKB_CB(skb)->txstamp_ack = 0; } } static void tcp_skb_fragment_eor(struct sk_buff *skb, struct sk_buff *skb2) { TCP_SKB_CB(skb2)->eor = TCP_SKB_CB(skb)->eor; TCP_SKB_CB(skb)->eor = 0; } /* Function to create two new TCP segments. Shrinks the given segment * to the specified size and appends a new segment with the rest of the * packet to the list. This won't be called frequently, I hope. * Remember, these are still headerless SKBs at this point. */ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, unsigned int mss_now, gfp_t gfp) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *buff; int nsize, old_factor; long limit; int nlen; u8 flags; if (WARN_ON(len > skb->len)) return -EINVAL; nsize = skb_headlen(skb) - len; if (nsize < 0) nsize = 0; /* tcp_sendmsg() can overshoot sk_wmem_queued by one full size skb. * We need some allowance to not penalize applications setting small * SO_SNDBUF values. * Also allow first and last skb in retransmit queue to be split. */ limit = sk->sk_sndbuf + 2 * SKB_TRUESIZE(GSO_MAX_SIZE); if (unlikely((sk->sk_wmem_queued >> 1) > limit && skb != tcp_rtx_queue_head(sk) && skb != tcp_rtx_queue_tail(sk))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPWQUEUETOOBIG); return -ENOMEM; } if (skb_unclone(skb, gfp)) return -ENOMEM; /* Get a new skb... force flag on. */ buff = sk_stream_alloc_skb(sk, nsize, gfp, true); if (!buff) return -ENOMEM; /* We'll just try again later. */ sk->sk_wmem_queued += buff->truesize; sk_mem_charge(sk, buff->truesize); nlen = skb->len - len - nsize; buff->truesize += nlen; skb->truesize -= nlen; /* Correct the sequence numbers. */ TCP_SKB_CB(buff)->seq = TCP_SKB_CB(skb)->seq + len; TCP_SKB_CB(buff)->end_seq = TCP_SKB_CB(skb)->end_seq; TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(buff)->seq; /* PSH and FIN should only be set in the second packet. */ flags = TCP_SKB_CB(skb)->tcp_flags; TCP_SKB_CB(skb)->tcp_flags = flags & ~(TCPHDR_FIN | TCPHDR_PSH); TCP_SKB_CB(buff)->tcp_flags = flags; TCP_SKB_CB(buff)->sacked = TCP_SKB_CB(skb)->sacked; tcp_skb_fragment_eor(skb, buff); if (!skb_shinfo(skb)->nr_frags && skb->ip_summed != CHECKSUM_PARTIAL) { /* Copy and checksum data tail into the new buffer. */ buff->csum = csum_partial_copy_nocheck(skb->data + len, skb_put(buff, nsize), nsize, 0); skb_trim(skb, len); skb->csum = csum_block_sub(skb->csum, buff->csum, len); } else { skb->ip_summed = CHECKSUM_PARTIAL; skb_split(skb, buff, len); } buff->ip_summed = skb->ip_summed; buff->tstamp = skb->tstamp; tcp_fragment_tstamp(skb, buff); old_factor = tcp_skb_pcount(skb); /* Fix up tso_factor for both original and new SKB. */ tcp_set_skb_tso_segs(skb, mss_now); tcp_set_skb_tso_segs(buff, mss_now); /* Update delivered info for the new segment */ TCP_SKB_CB(buff)->tx = TCP_SKB_CB(skb)->tx; /* If this packet has been sent out already, we must * adjust the various packet counters. */ if (!before(tp->snd_nxt, TCP_SKB_CB(buff)->end_seq)) { int diff = old_factor - tcp_skb_pcount(skb) - tcp_skb_pcount(buff); if (diff) tcp_adjust_pcount(sk, skb, diff); } /* Link BUFF into the send queue. */ __skb_header_release(buff); tcp_insert_write_queue_after(skb, buff, sk); return 0; } /* This is similar to __pskb_pull_tail(). The difference is that pulled * data is not copied, but immediately discarded. */ static int __pskb_trim_head(struct sk_buff *skb, int len) { struct skb_shared_info *shinfo; int i, k, eat; eat = min_t(int, len, skb_headlen(skb)); if (eat) { __skb_pull(skb, eat); len -= eat; if (!len) return 0; } eat = len; k = 0; shinfo = skb_shinfo(skb); for (i = 0; i < shinfo->nr_frags; i++) { int size = skb_frag_size(&shinfo->frags[i]); if (size <= eat) { skb_frag_unref(skb, i); eat -= size; } else { shinfo->frags[k] = shinfo->frags[i]; if (eat) { shinfo->frags[k].page_offset += eat; skb_frag_size_sub(&shinfo->frags[k], eat); eat = 0; } k++; } } shinfo->nr_frags = k; skb->data_len -= len; skb->len = skb->data_len; return len; } /* Remove acked data from a packet in the transmit queue. */ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) { u32 delta_truesize; if (skb_unclone(skb, GFP_ATOMIC)) return -ENOMEM; delta_truesize = __pskb_trim_head(skb, len); TCP_SKB_CB(skb)->seq += len; skb->ip_summed = CHECKSUM_PARTIAL; if (delta_truesize) { skb->truesize -= delta_truesize; sk->sk_wmem_queued -= delta_truesize; sk_mem_uncharge(sk, delta_truesize); sock_set_flag(sk, SOCK_QUEUE_SHRUNK); } /* Any change of skb->len requires recalculation of tso factor. */ if (tcp_skb_pcount(skb) > 1) tcp_set_skb_tso_segs(skb, tcp_skb_mss(skb)); return 0; } /* Calculate MSS not accounting any TCP options. */ static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu) { const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); int mss_now; /* Calculate base mss without TCP options: It is MMS_S - sizeof(tcphdr) of rfc1122 */ mss_now = pmtu - icsk->icsk_af_ops->net_header_len - sizeof(struct tcphdr); /* IPv6 adds a frag_hdr in case RTAX_FEATURE_ALLFRAG is set */ if (icsk->icsk_af_ops->net_frag_header_len) { const struct dst_entry *dst = __sk_dst_get(sk); if (dst && dst_allfrag(dst)) mss_now -= icsk->icsk_af_ops->net_frag_header_len; } /* Clamp it (mss_clamp does not include tcp options) */ if (mss_now > tp->rx_opt.mss_clamp) mss_now = tp->rx_opt.mss_clamp; /* Now subtract optional transport overhead */ mss_now -= icsk->icsk_ext_hdr_len; /* Then reserve room for full set of TCP options and 8 bytes of data */ mss_now = max(mss_now, sock_net(sk)->ipv4.sysctl_tcp_min_snd_mss); return mss_now; } /* Calculate MSS. Not accounting for SACKs here. */ int tcp_mtu_to_mss(struct sock *sk, int pmtu) { /* Subtract TCP options size, not including SACKs */ return __tcp_mtu_to_mss(sk, pmtu) - (tcp_sk(sk)->tcp_header_len - sizeof(struct tcphdr)); } EXPORT_SYMBOL(tcp_mtu_to_mss); /* Inverse of above */ int tcp_mss_to_mtu(struct sock *sk, int mss) { const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); int mtu; mtu = mss + tp->tcp_header_len + icsk->icsk_ext_hdr_len + icsk->icsk_af_ops->net_header_len; /* IPv6 adds a frag_hdr in case RTAX_FEATURE_ALLFRAG is set */ if (icsk->icsk_af_ops->net_frag_header_len) { const struct dst_entry *dst = __sk_dst_get(sk); if (dst && dst_allfrag(dst)) mtu += icsk->icsk_af_ops->net_frag_header_len; } return mtu; } EXPORT_SYMBOL(tcp_mss_to_mtu); /* MTU probing init per socket */ void tcp_mtup_init(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); struct net *net = sock_net(sk); icsk->icsk_mtup.enabled = net->ipv4.sysctl_tcp_mtu_probing > 1; icsk->icsk_mtup.search_high = tp->rx_opt.mss_clamp + sizeof(struct tcphdr) + icsk->icsk_af_ops->net_header_len; icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, net->ipv4.sysctl_tcp_base_mss); icsk->icsk_mtup.probe_size = 0; if (icsk->icsk_mtup.enabled) icsk->icsk_mtup.probe_timestamp = tcp_jiffies32; } EXPORT_SYMBOL(tcp_mtup_init); /* This function synchronize snd mss to current pmtu/exthdr set. tp->rx_opt.user_mss is mss set by user by TCP_MAXSEG. It does NOT counts for TCP options, but includes only bare TCP header. tp->rx_opt.mss_clamp is mss negotiated at connection setup. It is minimum of user_mss and mss received with SYN. It also does not include TCP options. inet_csk(sk)->icsk_pmtu_cookie is last pmtu, seen by this function. tp->mss_cache is current effective sending mss, including all tcp options except for SACKs. It is evaluated, taking into account current pmtu, but never exceeds tp->rx_opt.mss_clamp. NOTE1. rfc1122 clearly states that advertised MSS DOES NOT include either tcp or ip options. NOTE2. inet_csk(sk)->icsk_pmtu_cookie and tp->mss_cache are READ ONLY outside this function. --ANK (980731) */ unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); int mss_now; if (icsk->icsk_mtup.search_high > pmtu) icsk->icsk_mtup.search_high = pmtu; mss_now = tcp_mtu_to_mss(sk, pmtu); mss_now = tcp_bound_to_half_wnd(tp, mss_now); /* And store cached results */ icsk->icsk_pmtu_cookie = pmtu; if (icsk->icsk_mtup.enabled) mss_now = min(mss_now, tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low)); tp->mss_cache = mss_now; return mss_now; } EXPORT_SYMBOL(tcp_sync_mss); /* Compute the current effective MSS, taking SACKs and IP options, * and even PMTU discovery events into account. */ unsigned int tcp_current_mss(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); const struct dst_entry *dst = __sk_dst_get(sk); u32 mss_now; unsigned int header_len; struct tcp_out_options opts; struct tcp_md5sig_key *md5; mss_now = tp->mss_cache; if (dst) { u32 mtu = dst_mtu(dst); if (mtu != inet_csk(sk)->icsk_pmtu_cookie) mss_now = tcp_sync_mss(sk, mtu); } header_len = tcp_established_options(sk, NULL, &opts, &md5) + sizeof(struct tcphdr); /* The mss_cache is sized based on tp->tcp_header_len, which assumes * some common options. If this is an odd packet (because we have SACK * blocks etc) then our calculated header_len will be different, and * we have to adjust mss_now correspondingly */ if (header_len != tp->tcp_header_len) { int delta = (int) header_len - tp->tcp_header_len; mss_now -= delta; } return mss_now; } /* RFC2861, slow part. Adjust cwnd, after it was not full during one rto. * As additional protections, we do not touch cwnd in retransmission phases, * and if application hit its sndbuf limit recently. */ static void tcp_cwnd_application_limited(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); if (inet_csk(sk)->icsk_ca_state == TCP_CA_Open && sk->sk_socket && !test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { /* Limited by application or receiver window. */ u32 init_win = tcp_init_cwnd(tp, __sk_dst_get(sk)); u32 win_used = max(tp->snd_cwnd_used, init_win); if (win_used < tp->snd_cwnd) { tp->snd_ssthresh = tcp_current_ssthresh(sk); tp->snd_cwnd = (tp->snd_cwnd + win_used) >> 1; } tp->snd_cwnd_used = 0; } tp->snd_cwnd_stamp = tcp_jiffies32; } static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited) { const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; struct tcp_sock *tp = tcp_sk(sk); /* Track the strongest available signal of the degree to which the cwnd * is fully utilized. If cwnd-limited then remember that fact for the * current window. If not cwnd-limited then track the maximum number of * outstanding packets in the current window. (If cwnd-limited then we * chose to not update tp->max_packets_out to avoid an extra else * clause with no functional impact.) */ if (!before(tp->snd_una, tp->cwnd_usage_seq) || is_cwnd_limited || (!tp->is_cwnd_limited && tp->packets_out > tp->max_packets_out)) { tp->is_cwnd_limited = is_cwnd_limited; tp->max_packets_out = tp->packets_out; tp->cwnd_usage_seq = tp->snd_nxt; } if (tcp_is_cwnd_limited(sk)) { /* Network is feed fully. */ tp->snd_cwnd_used = 0; tp->snd_cwnd_stamp = tcp_jiffies32; } else { /* Network starves. */ if (tp->packets_out > tp->snd_cwnd_used) tp->snd_cwnd_used = tp->packets_out; if (sysctl_tcp_slow_start_after_idle && (s32)(tcp_jiffies32 - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto && !ca_ops->cong_control) tcp_cwnd_application_limited(sk); /* The following conditions together indicate the starvation * is caused by insufficient sender buffer: * 1) just sent some data (see tcp_write_xmit) * 2) not cwnd limited (this else condition) * 3) no more data to send (null tcp_send_head ) * 4) application is hitting buffer limit (SOCK_NOSPACE) */ if (!tcp_send_head(sk) && sk->sk_socket && test_bit(SOCK_NOSPACE, &sk->sk_socket->flags) && (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) tcp_chrono_start(sk, TCP_CHRONO_SNDBUF_LIMITED); } } /* Minshall's variant of the Nagle send check. */ static bool tcp_minshall_check(const struct tcp_sock *tp) { return after(tp->snd_sml, tp->snd_una) && !after(tp->snd_sml, tp->snd_nxt); } /* Update snd_sml if this skb is under mss * Note that a TSO packet might end with a sub-mss segment * The test is really : * if ((skb->len % mss) != 0) * tp->snd_sml = TCP_SKB_CB(skb)->end_seq; * But we can avoid doing the divide again given we already have * skb_pcount = skb->len / mss_now */ static void tcp_minshall_update(struct tcp_sock *tp, unsigned int mss_now, const struct sk_buff *skb) { if (skb->len < tcp_skb_pcount(skb) * mss_now) tp->snd_sml = TCP_SKB_CB(skb)->end_seq; } /* Return false, if packet can be sent now without violation Nagle's rules: * 1. It is full sized. (provided by caller in %partial bool) * 2. Or it contains FIN. (already checked by caller) * 3. Or TCP_CORK is not set, and TCP_NODELAY is set. * 4. Or TCP_CORK is not set, and all sent packets are ACKed. * With Minshall's modification: all sent small packets are ACKed. */ static bool tcp_nagle_check(bool partial, const struct tcp_sock *tp, int nonagle) { return partial && ((nonagle & TCP_NAGLE_CORK) || (!nonagle && tp->packets_out && tcp_minshall_check(tp))); } /* Return how many segs we'd like on a TSO packet, * to send one TSO packet per ms */ u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, int min_tso_segs) { u32 bytes, segs; bytes = min(sk->sk_pacing_rate >> 10, sk->sk_gso_max_size - 1 - MAX_TCP_HEADER); /* Goal is to send at least one packet per ms, * not one big TSO packet every 100 ms. * This preserves ACK clocking and is consistent * with tcp_tso_should_defer() heuristic. */ segs = max_t(u32, bytes / mss_now, min_tso_segs); return segs; } EXPORT_SYMBOL(tcp_tso_autosize); /* Return the number of segments we want in the skb we are transmitting. * See if congestion control module wants to decide; otherwise, autosize. */ static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now) { const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; u32 tso_segs = ca_ops->tso_segs_goal ? ca_ops->tso_segs_goal(sk) : 0; if (!tso_segs) tso_segs = tcp_tso_autosize(sk, mss_now, sysctl_tcp_min_tso_segs); return min_t(u32, tso_segs, sk->sk_gso_max_segs); } /* Returns the portion of skb which can be sent right away */ static unsigned int tcp_mss_split_point(const struct sock *sk, const struct sk_buff *skb, unsigned int mss_now, unsigned int max_segs, int nonagle) { const struct tcp_sock *tp = tcp_sk(sk); u32 partial, needed, window, max_len; window = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; max_len = mss_now * max_segs; if (likely(max_len <= window && skb != tcp_write_queue_tail(sk))) return max_len; needed = min(skb->len, window); if (max_len <= needed) return max_len; partial = needed % mss_now; /* If last segment is not a full MSS, check if Nagle rules allow us * to include this last segment in this skb. * Otherwise, we'll split the skb at last MSS boundary */ if (tcp_nagle_check(partial != 0, tp, nonagle)) return needed - partial; return needed; } /* Can at least one segment of SKB be sent right now, according to the * congestion window rules? If so, return how many segments are allowed. */ static inline unsigned int tcp_cwnd_test(const struct tcp_sock *tp, const struct sk_buff *skb) { u32 in_flight, cwnd, halfcwnd; /* Don't be strict about the congestion window for the final FIN. */ if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) && tcp_skb_pcount(skb) == 1) return 1; in_flight = tcp_packets_in_flight(tp); cwnd = tp->snd_cwnd; if (in_flight >= cwnd) return 0; /* For better scheduling, ensure we have at least * 2 GSO packets in flight. */ halfcwnd = max(cwnd >> 1, 1U); return min(halfcwnd, cwnd - in_flight); } /* Initialize TSO state of a skb. * This must be invoked the first time we consider transmitting * SKB onto the wire. */ static int tcp_init_tso_segs(struct sk_buff *skb, unsigned int mss_now) { int tso_segs = tcp_skb_pcount(skb); if (!tso_segs || (tso_segs > 1 && tcp_skb_mss(skb) != mss_now)) { tcp_set_skb_tso_segs(skb, mss_now); tso_segs = tcp_skb_pcount(skb); } return tso_segs; } /* Return true if the Nagle test allows this packet to be * sent now. */ static inline bool tcp_nagle_test(const struct tcp_sock *tp, const struct sk_buff *skb, unsigned int cur_mss, int nonagle) { /* Nagle rule does not apply to frames, which sit in the middle of the * write_queue (they have no chances to get new data). * * This is implemented in the callers, where they modify the 'nonagle' * argument based upon the location of SKB in the send queue. */ if (nonagle & TCP_NAGLE_PUSH) return true; /* Don't use the nagle rule for urgent data (or for the final FIN). */ if (tcp_urg_mode(tp) || (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)) return true; if (!tcp_nagle_check(skb->len < cur_mss, tp, nonagle)) return true; return false; } /* Does at least the first segment of SKB fit into the send window? */ static bool tcp_snd_wnd_test(const struct tcp_sock *tp, const struct sk_buff *skb, unsigned int cur_mss) { u32 end_seq = TCP_SKB_CB(skb)->end_seq; if (skb->len > cur_mss) end_seq = TCP_SKB_CB(skb)->seq + cur_mss; return !after(end_seq, tcp_wnd_end(tp)); } /* Trim TSO SKB to LEN bytes, put the remaining data into a new packet * which is put after SKB on the list. It is very much like * tcp_fragment() except that it may make several kinds of assumptions * in order to speed up the splitting operation. In particular, we * know that all the data is in scatter-gather pages, and that the * packet has never been sent out before (and thus is not cloned). */ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, unsigned int mss_now, gfp_t gfp) { struct sk_buff *buff; int nlen = skb->len - len; u8 flags; /* All of a TSO frame must be composed of paged data. */ if (skb->len != skb->data_len) return tcp_fragment(sk, skb, len, mss_now, gfp); buff = sk_stream_alloc_skb(sk, 0, gfp, true); if (unlikely(!buff)) return -ENOMEM; sk->sk_wmem_queued += buff->truesize; sk_mem_charge(sk, buff->truesize); buff->truesize += nlen; skb->truesize -= nlen; /* Correct the sequence numbers. */ TCP_SKB_CB(buff)->seq = TCP_SKB_CB(skb)->seq + len; TCP_SKB_CB(buff)->end_seq = TCP_SKB_CB(skb)->end_seq; TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(buff)->seq; /* PSH and FIN should only be set in the second packet. */ flags = TCP_SKB_CB(skb)->tcp_flags; TCP_SKB_CB(skb)->tcp_flags = flags & ~(TCPHDR_FIN | TCPHDR_PSH); TCP_SKB_CB(buff)->tcp_flags = flags; /* This packet was never sent out yet, so no SACK bits. */ TCP_SKB_CB(buff)->sacked = 0; tcp_skb_fragment_eor(skb, buff); buff->ip_summed = skb->ip_summed = CHECKSUM_PARTIAL; skb_split(skb, buff, len); tcp_fragment_tstamp(skb, buff); /* Fix up tso_factor for both original and new SKB. */ tcp_set_skb_tso_segs(skb, mss_now); tcp_set_skb_tso_segs(buff, mss_now); /* Link BUFF into the send queue. */ __skb_header_release(buff); tcp_insert_write_queue_after(skb, buff, sk); return 0; } /* Try to defer sending, if possible, in order to minimize the amount * of TSO splitting we do. View it as a kind of TSO Nagle test. * * This algorithm is from John Heffner. */ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, bool *is_cwnd_limited, bool *is_rwnd_limited, u32 max_segs) { const struct inet_connection_sock *icsk = inet_csk(sk); u32 age, send_win, cong_win, limit, in_flight; struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *head; int win_divisor; if (icsk->icsk_ca_state >= TCP_CA_Recovery) goto send_now; /* Avoid bursty behavior by allowing defer * only if the last write was recent. */ if ((s32)(tcp_jiffies32 - tp->lsndtime) > 0) goto send_now; in_flight = tcp_packets_in_flight(tp); BUG_ON(tcp_skb_pcount(skb) <= 1 || (tp->snd_cwnd <= in_flight)); send_win = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; /* From in_flight test above, we know that cwnd > in_flight. */ cong_win = (tp->snd_cwnd - in_flight) * tp->mss_cache; limit = min(send_win, cong_win); /* If a full-sized TSO skb can be sent, do it. */ if (limit >= max_segs * tp->mss_cache) goto send_now; /* Middle in queue won't get any more data, full sendable already? */ if ((skb != tcp_write_queue_tail(sk)) && (limit >= skb->len)) goto send_now; win_divisor = ACCESS_ONCE(sysctl_tcp_tso_win_divisor); if (win_divisor) { u32 chunk = min(tp->snd_wnd, tp->snd_cwnd * tp->mss_cache); /* If at least some fraction of a window is available, * just use it. */ chunk /= win_divisor; if (limit >= chunk) goto send_now; } else { /* Different approach, try not to defer past a single * ACK. Receiver should ACK every other full sized * frame, so if we have space for more than 3 frames * then send now. */ if (limit > tcp_max_tso_deferred_mss(tp) * tp->mss_cache) goto send_now; } head = tcp_write_queue_head(sk); age = tcp_stamp_us_delta(tp->tcp_mstamp, head->skb_mstamp); /* If next ACK is likely to come too late (half srtt), do not defer */ if (age < (tp->srtt_us >> 4)) goto send_now; /* Ok, it looks like it is advisable to defer. * Three cases are tracked : * 1) We are cwnd-limited * 2) We are rwnd-limited * 3) We are application limited. */ if (cong_win < send_win) { if (cong_win <= skb->len) { *is_cwnd_limited = true; return true; } } else { if (send_win <= skb->len) { *is_rwnd_limited = true; return true; } } /* If this packet won't get more data, do not wait. */ if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) goto send_now; return true; send_now: return false; } static inline void tcp_mtu_check_reprobe(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); u32 interval; s32 delta; interval = READ_ONCE(net->ipv4.sysctl_tcp_probe_interval); delta = tcp_jiffies32 - icsk->icsk_mtup.probe_timestamp; if (unlikely(delta >= interval * HZ)) { int mss = tcp_current_mss(sk); /* Update current search range */ icsk->icsk_mtup.probe_size = 0; icsk->icsk_mtup.search_high = tp->rx_opt.mss_clamp + sizeof(struct tcphdr) + icsk->icsk_af_ops->net_header_len; icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss); /* Update probe time stamp */ icsk->icsk_mtup.probe_timestamp = tcp_jiffies32; } } static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len) { struct sk_buff *skb, *next; skb = tcp_send_head(sk); tcp_for_write_queue_from_safe(skb, next, sk) { if (len <= skb->len) break; if (unlikely(TCP_SKB_CB(skb)->eor) || tcp_has_tx_tstamp(skb)) return false; len -= skb->len; } return true; } /* Create a new MTU probe if we are ready. * MTU probe is regularly attempting to increase the path MTU by * deliberately sending larger packets. This discovers routing * changes resulting in larger path MTUs. * * Returns 0 if we should wait to probe (no cwnd available), * 1 if a probe was sent, * -1 otherwise */ static int tcp_mtu_probe(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb, *nskb, *next; struct net *net = sock_net(sk); int probe_size; int size_needed; int copy, len; int mss_now; int interval; /* Not currently probing/verifying, * not in recovery, * have enough cwnd, and * not SACKing (the variable headers throw things off) */ if (likely(!icsk->icsk_mtup.enabled || icsk->icsk_mtup.probe_size || inet_csk(sk)->icsk_ca_state != TCP_CA_Open || tp->snd_cwnd < 11 || tp->rx_opt.num_sacks || tp->rx_opt.dsack)) return -1; /* Use binary search for probe_size between tcp_mss_base, * and current mss_clamp. if (search_high - search_low) * smaller than a threshold, backoff from probing. */ mss_now = tcp_current_mss(sk); probe_size = tcp_mtu_to_mss(sk, (icsk->icsk_mtup.search_high + icsk->icsk_mtup.search_low) >> 1); size_needed = probe_size + (tp->reordering + 1) * tp->mss_cache; interval = icsk->icsk_mtup.search_high - icsk->icsk_mtup.search_low; /* When misfortune happens, we are reprobing actively, * and then reprobe timer has expired. We stick with current * probing process by not resetting search range to its orignal. */ if (probe_size > tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_high) || interval < READ_ONCE(net->ipv4.sysctl_tcp_probe_threshold)) { /* Check whether enough time has elaplased for * another round of probing. */ tcp_mtu_check_reprobe(sk); return -1; } /* Have enough data in the send queue to probe? */ if (tp->write_seq - tp->snd_nxt < size_needed) return -1; if (tp->snd_wnd < size_needed) return -1; if (after(tp->snd_nxt + size_needed, tcp_wnd_end(tp))) return 0; /* Do we need to wait to drain cwnd? With none in flight, don't stall */ if (tcp_packets_in_flight(tp) + 2 > tp->snd_cwnd) { if (!tcp_packets_in_flight(tp)) return -1; else return 0; } if (!tcp_can_coalesce_send_queue_head(sk, probe_size)) return -1; /* We're allowed to probe. Build it now. */ nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC, false); if (!nskb) return -1; sk->sk_wmem_queued += nskb->truesize; sk_mem_charge(sk, nskb->truesize); skb = tcp_send_head(sk); TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(skb)->seq; TCP_SKB_CB(nskb)->end_seq = TCP_SKB_CB(skb)->seq + probe_size; TCP_SKB_CB(nskb)->tcp_flags = TCPHDR_ACK; TCP_SKB_CB(nskb)->sacked = 0; nskb->csum = 0; nskb->ip_summed = skb->ip_summed; tcp_insert_write_queue_before(nskb, skb, sk); tcp_highest_sack_replace(sk, skb, nskb); len = 0; tcp_for_write_queue_from_safe(skb, next, sk) { copy = min_t(int, skb->len, probe_size - len); if (nskb->ip_summed) { skb_copy_bits(skb, 0, skb_put(nskb, copy), copy); } else { __wsum csum = skb_copy_and_csum_bits(skb, 0, skb_put(nskb, copy), copy, 0); nskb->csum = csum_block_add(nskb->csum, csum, len); } if (skb->len <= copy) { /* We've eaten all the data from this skb. * Throw it away. */ TCP_SKB_CB(nskb)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags; /* If this is the last SKB we copy and eor is set * we need to propagate it to the new skb. */ TCP_SKB_CB(nskb)->eor = TCP_SKB_CB(skb)->eor; tcp_skb_collapse_tstamp(nskb, skb); tcp_unlink_write_queue(skb, sk); sk_wmem_free_skb(sk, skb); } else { TCP_SKB_CB(nskb)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags & ~(TCPHDR_FIN|TCPHDR_PSH); if (!skb_shinfo(skb)->nr_frags) { skb_pull(skb, copy); if (skb->ip_summed != CHECKSUM_PARTIAL) skb->csum = csum_partial(skb->data, skb->len, 0); } else { __pskb_trim_head(skb, copy); tcp_set_skb_tso_segs(skb, mss_now); } TCP_SKB_CB(skb)->seq += copy; } len += copy; if (len >= probe_size) break; } tcp_init_tso_segs(nskb, nskb->len); /* We're ready to send. If this fails, the probe will * be resegmented into mss-sized pieces by tcp_write_xmit(). */ if (!tcp_transmit_skb(sk, nskb, 1, GFP_ATOMIC)) { /* Decrement cwnd here because we are sending * effectively two packets. */ tp->snd_cwnd--; tcp_event_new_data_sent(sk, nskb); icsk->icsk_mtup.probe_size = tcp_mss_to_mtu(sk, nskb->len); tp->mtu_probe.probe_seq_start = TCP_SKB_CB(nskb)->seq; tp->mtu_probe.probe_seq_end = TCP_SKB_CB(nskb)->end_seq; return 1; } return -1; } static bool tcp_pacing_check(const struct sock *sk) { return tcp_needs_internal_pacing(sk) && hrtimer_active(&tcp_sk(sk)->pacing_timer); } /* TCP Small Queues : * Control number of packets in qdisc/devices to two packets / or ~1 ms. * (These limits are doubled for retransmits) * This allows for : * - better RTT estimation and ACK scheduling * - faster recovery * - high rates * Alas, some drivers / subsystems require a fair amount * of queued bytes to ensure line rate. * One example is wifi aggregation (802.11 AMPDU) */ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, unsigned int factor) { unsigned int limit; limit = max(2 * skb->truesize, sk->sk_pacing_rate >> 10); limit = min_t(u32, limit, sysctl_tcp_limit_output_bytes); limit <<= factor; if (refcount_read(&sk->sk_wmem_alloc) > limit) { /* Always send the 1st or 2nd skb in write queue. * No need to wait for TX completion to call us back, * after softirq/tasklet schedule. * This helps when TX completions are delayed too much. */ if (skb == sk->sk_write_queue.next || skb->prev == sk->sk_write_queue.next) return false; set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags); /* It is possible TX completion already happened * before we set TSQ_THROTTLED, so we must * test again the condition. */ smp_mb__after_atomic(); if (refcount_read(&sk->sk_wmem_alloc) > limit) return true; } return false; } static void tcp_chrono_set(struct tcp_sock *tp, const enum tcp_chrono new) { const u32 now = tcp_jiffies32; enum tcp_chrono old = tp->chrono_type; if (old > TCP_CHRONO_UNSPEC) tp->chrono_stat[old - 1] += now - tp->chrono_start; tp->chrono_start = now; tp->chrono_type = new; } void tcp_chrono_start(struct sock *sk, const enum tcp_chrono type) { struct tcp_sock *tp = tcp_sk(sk); /* If there are multiple conditions worthy of tracking in a * chronograph then the highest priority enum takes precedence * over the other conditions. So that if something "more interesting" * starts happening, stop the previous chrono and start a new one. */ if (type > tp->chrono_type) tcp_chrono_set(tp, type); } void tcp_chrono_stop(struct sock *sk, const enum tcp_chrono type) { struct tcp_sock *tp = tcp_sk(sk); /* There are multiple conditions worthy of tracking in a * chronograph, so that the highest priority enum takes * precedence over the other conditions (see tcp_chrono_start). * If a condition stops, we only stop chrono tracking if * it's the "most interesting" or current chrono we are * tracking and starts busy chrono if we have pending data. */ if (tcp_write_queue_empty(sk)) tcp_chrono_set(tp, TCP_CHRONO_UNSPEC); else if (type == tp->chrono_type) tcp_chrono_set(tp, TCP_CHRONO_BUSY); } /* This routine writes packets to the network. It advances the * send_head. This happens as incoming acks open up the remote * window for us. * * LARGESEND note: !tcp_urg_mode is overkill, only frames between * snd_up-64k-mss .. snd_up cannot be large. However, taking into * account rare use of URG, this is not a big flaw. * * Send at most one packet when push_one > 0. Temporarily ignore * cwnd limit to force at most one packet out when push_one == 2. * Returns true, if no segments are in flight and we have queued segments, * but cannot send anything now because of SWS or another problem. */ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, int push_one, gfp_t gfp) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; unsigned int tso_segs, sent_pkts; int cwnd_quota; int result; bool is_cwnd_limited = false, is_rwnd_limited = false; u32 max_segs; sent_pkts = 0; tcp_mstamp_refresh(tp); if (!push_one) { /* Do MTU probing. */ result = tcp_mtu_probe(sk); if (!result) { return false; } else if (result > 0) { sent_pkts = 1; } } max_segs = tcp_tso_segs(sk, mss_now); while ((skb = tcp_send_head(sk))) { unsigned int limit; if (tcp_pacing_check(sk)) break; tso_segs = tcp_init_tso_segs(skb, mss_now); BUG_ON(!tso_segs); if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) { /* "skb_mstamp" is used as a start point for the retransmit timer */ skb->skb_mstamp = tp->tcp_mstamp; goto repair; /* Skip network transmission */ } cwnd_quota = tcp_cwnd_test(tp, skb); if (!cwnd_quota) { if (push_one == 2) /* Force out a loss probe pkt. */ cwnd_quota = 1; else break; } if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now))) { is_rwnd_limited = true; break; } if (tso_segs == 1) { if (unlikely(!tcp_nagle_test(tp, skb, mss_now, (tcp_skb_is_last(sk, skb) ? nonagle : TCP_NAGLE_PUSH)))) break; } else { if (!push_one && tcp_tso_should_defer(sk, skb, &is_cwnd_limited, &is_rwnd_limited, max_segs)) break; } limit = mss_now; if (tso_segs > 1 && !tcp_urg_mode(tp)) limit = tcp_mss_split_point(sk, skb, mss_now, min_t(unsigned int, cwnd_quota, max_segs), nonagle); if (skb->len > limit && unlikely(tso_fragment(sk, skb, limit, mss_now, gfp))) break; if (test_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags)) clear_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags); if (tcp_small_queue_check(sk, skb, 0)) break; /* Argh, we hit an empty skb(), presumably a thread * is sleeping in sendmsg()/sk_stream_wait_memory(). * We do not want to send a pure-ack packet and have * a strange looking rtx queue with empty packet(s). */ if (TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq) break; if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp))) break; repair: /* Advance the send_head. This one is sent out. * This call will increment packets_out. */ tcp_event_new_data_sent(sk, skb); tcp_minshall_update(tp, mss_now, skb); sent_pkts += tcp_skb_pcount(skb); if (push_one) break; } if (is_rwnd_limited) tcp_chrono_start(sk, TCP_CHRONO_RWND_LIMITED); else tcp_chrono_stop(sk, TCP_CHRONO_RWND_LIMITED); is_cwnd_limited |= (tcp_packets_in_flight(tp) >= tp->snd_cwnd); if (likely(sent_pkts || is_cwnd_limited)) tcp_cwnd_validate(sk, is_cwnd_limited); if (likely(sent_pkts)) { if (tcp_in_cwnd_reduction(sk)) tp->prr_out += sent_pkts; /* Send one loss probe per tail loss episode. */ if (push_one != 2) tcp_schedule_loss_probe(sk, false); return false; } return !tp->packets_out && tcp_send_head(sk); } bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); u32 timeout, rto_delta_us; /* Don't do any loss probe on a Fast Open connection before 3WHS * finishes. */ if (tp->fastopen_rsk) return false; /* Schedule a loss probe in 2*RTT for SACK capable connections * in Open state, that are either limited by cwnd or application. */ if ((sysctl_tcp_early_retrans != 3 && sysctl_tcp_early_retrans != 4) || !tp->packets_out || !tcp_is_sack(tp) || icsk->icsk_ca_state != TCP_CA_Open) return false; if ((tp->snd_cwnd > tcp_packets_in_flight(tp)) && tcp_send_head(sk)) return false; /* Probe timeout is 2*rtt. Add minimum RTO to account * for delayed ack when there's one outstanding packet. If no RTT * sample is available then probe after TCP_TIMEOUT_INIT. */ if (tp->srtt_us) { timeout = usecs_to_jiffies(tp->srtt_us >> 2); if (tp->packets_out == 1) timeout += TCP_RTO_MIN; else timeout += TCP_TIMEOUT_MIN; } else { timeout = TCP_TIMEOUT_INIT; } /* If the RTO formula yields an earlier time, then use that time. */ rto_delta_us = advancing_rto ? jiffies_to_usecs(inet_csk(sk)->icsk_rto) : tcp_rto_delta_us(sk); /* How far in future is RTO? */ if (rto_delta_us > 0) timeout = min_t(u32, timeout, usecs_to_jiffies(rto_delta_us)); inet_csk_reset_xmit_timer(sk, ICSK_TIME_LOSS_PROBE, timeout, TCP_RTO_MAX); return true; } /* Thanks to skb fast clones, we can detect if a prior transmit of * a packet is still in a qdisc or driver queue. * In this case, there is very little point doing a retransmit ! */ static bool skb_still_in_host_queue(const struct sock *sk, const struct sk_buff *skb) { if (unlikely(skb_fclone_busy(sk, skb))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES); return true; } return false; } /* When probe timeout (PTO) fires, try send a new segment if possible, else * retransmit the last segment. */ void tcp_send_loss_probe(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; int pcount; int mss = tcp_current_mss(sk); /* At most one outstanding TLP */ if (tp->tlp_high_seq) goto rearm_timer; tp->tlp_retrans = 0; skb = tcp_send_head(sk); if (skb) { if (tcp_snd_wnd_test(tp, skb, mss)) { pcount = tp->packets_out; tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC); if (tp->packets_out > pcount) goto probe_sent; goto rearm_timer; } skb = tcp_write_queue_prev(sk, skb); } else { skb = tcp_write_queue_tail(sk); } if (unlikely(!skb)) { WARN_ONCE(tp->packets_out, "invalid inflight: %u state %u cwnd %u mss %d\n", tp->packets_out, sk->sk_state, tp->snd_cwnd, mss); inet_csk(sk)->icsk_pending = 0; return; } if (skb_still_in_host_queue(sk, skb)) goto rearm_timer; pcount = tcp_skb_pcount(skb); if (WARN_ON(!pcount)) goto rearm_timer; if ((pcount > 1) && (skb->len > (pcount - 1) * mss)) { if (unlikely(tcp_fragment(sk, skb, (pcount - 1) * mss, mss, GFP_ATOMIC))) goto rearm_timer; skb = tcp_write_queue_next(sk, skb); } if (WARN_ON(!skb || !tcp_skb_pcount(skb))) goto rearm_timer; if (__tcp_retransmit_skb(sk, skb, 1)) goto rearm_timer; tp->tlp_retrans = 1; probe_sent: /* Record snd_nxt for loss detection. */ tp->tlp_high_seq = tp->snd_nxt; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSSPROBES); /* Reset s.t. tcp_rearm_rto will restart timer from now */ inet_csk(sk)->icsk_pending = 0; rearm_timer: tcp_rearm_rto(sk); } /* Push out any pending frames which were held back due to * TCP_CORK or attempt at coalescing tiny packets. * The socket must be locked by the caller. */ void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss, int nonagle) { /* If we are closed, the bytes will have to remain here. * In time closedown will finish, we empty the write queue and * all will be happy. */ if (unlikely(sk->sk_state == TCP_CLOSE)) return; if (tcp_write_xmit(sk, cur_mss, nonagle, 0, sk_gfp_mask(sk, GFP_ATOMIC))) tcp_check_probe_timer(sk); } /* Send _single_ skb sitting at the send head. This function requires * true push pending frames to setup probe timer etc. */ void tcp_push_one(struct sock *sk, unsigned int mss_now) { struct sk_buff *skb = tcp_send_head(sk); BUG_ON(!skb || skb->len < mss_now); tcp_write_xmit(sk, mss_now, TCP_NAGLE_PUSH, 1, sk->sk_allocation); } /* This function returns the amount that we can raise the * usable window based on the following constraints * * 1. The window can never be shrunk once it is offered (RFC 793) * 2. We limit memory per socket * * RFC 1122: * "the suggested [SWS] avoidance algorithm for the receiver is to keep * RECV.NEXT + RCV.WIN fixed until: * RCV.BUFF - RCV.USER - RCV.WINDOW >= min(1/2 RCV.BUFF, MSS)" * * i.e. don't raise the right edge of the window until you can raise * it at least MSS bytes. * * Unfortunately, the recommended algorithm breaks header prediction, * since header prediction assumes th->window stays fixed. * * Strictly speaking, keeping th->window fixed violates the receiver * side SWS prevention criteria. The problem is that under this rule * a stream of single byte packets will cause the right side of the * window to always advance by a single byte. * * Of course, if the sender implements sender side SWS prevention * then this will not be a problem. * * BSD seems to make the following compromise: * * If the free space is less than the 1/4 of the maximum * space available and the free space is less than 1/2 mss, * then set the window to 0. * [ Actually, bsd uses MSS and 1/4 of maximal _window_ ] * Otherwise, just prevent the window from shrinking * and from being larger than the largest representable value. * * This prevents incremental opening of the window in the regime * where TCP is limited by the speed of the reader side taking * data out of the TCP receive queue. It does nothing about * those cases where the window is constrained on the sender side * because the pipeline is full. * * BSD also seems to "accidentally" limit itself to windows that are a * multiple of MSS, at least until the free space gets quite small. * This would appear to be a side effect of the mbuf implementation. * Combining these two algorithms results in the observed behavior * of having a fixed window size at almost all times. * * Below we obtain similar behavior by forcing the offered window to * a multiple of the mss when it is feasible to do so. * * Note, we don't "adjust" for TIMESTAMP or SACK option bytes. * Regular options like TIMESTAMP are taken into account. */ u32 __tcp_select_window(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); /* MSS for the peer's data. Previous versions used mss_clamp * here. I don't know if the value based on our guesses * of peer's MSS is better for the performance. It's more correct * but may be worse for the performance because of rcv_mss * fluctuations. --SAW 1998/11/1 */ int mss = icsk->icsk_ack.rcv_mss; int free_space = tcp_space(sk); int allowed_space = tcp_full_space(sk); int full_space = min_t(int, tp->window_clamp, allowed_space); int window; if (unlikely(mss > full_space)) { mss = full_space; if (mss <= 0) return 0; } if (free_space < (full_space >> 1)) { icsk->icsk_ack.quick = 0; if (tcp_under_memory_pressure(sk)) tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss); /* free_space might become our new window, make sure we don't * increase it due to wscale. */ free_space = round_down(free_space, 1 << tp->rx_opt.rcv_wscale); /* if free space is less than mss estimate, or is below 1/16th * of the maximum allowed, try to move to zero-window, else * tcp_clamp_window() will grow rcv buf up to tcp_rmem[2], and * new incoming data is dropped due to memory limits. * With large window, mss test triggers way too late in order * to announce zero window in time before rmem limit kicks in. */ if (free_space < (allowed_space >> 4) || free_space < mss) return 0; } if (free_space > tp->rcv_ssthresh) free_space = tp->rcv_ssthresh; /* Don't do rounding if we are using window scaling, since the * scaled window will not line up with the MSS boundary anyway. */ if (tp->rx_opt.rcv_wscale) { window = free_space; /* Advertise enough space so that it won't get scaled away. * Import case: prevent zero window announcement if * 1<<rcv_wscale > mss. */ window = ALIGN(window, (1 << tp->rx_opt.rcv_wscale)); } else { window = tp->rcv_wnd; /* Get the largest window that is a nice multiple of mss. * Window clamp already applied above. * If our current window offering is within 1 mss of the * free space we just keep it. This prevents the divide * and multiply from happening most of the time. * We also don't do any window rounding when the free space * is too small. */ if (window <= free_space - mss || window > free_space) window = rounddown(free_space, mss); else if (mss == full_space && free_space > window + (full_space >> 1)) window = free_space; } return window; } void tcp_skb_collapse_tstamp(struct sk_buff *skb, const struct sk_buff *next_skb) { if (unlikely(tcp_has_tx_tstamp(next_skb))) { const struct skb_shared_info *next_shinfo = skb_shinfo(next_skb); struct skb_shared_info *shinfo = skb_shinfo(skb); shinfo->tx_flags |= next_shinfo->tx_flags & SKBTX_ANY_TSTAMP; shinfo->tskey = next_shinfo->tskey; TCP_SKB_CB(skb)->txstamp_ack |= TCP_SKB_CB(next_skb)->txstamp_ack; } } /* Collapses two adjacent SKB's during retransmission. */ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *next_skb = tcp_write_queue_next(sk, skb); int skb_size, next_skb_size; skb_size = skb->len; next_skb_size = next_skb->len; BUG_ON(tcp_skb_pcount(skb) != 1 || tcp_skb_pcount(next_skb) != 1); if (next_skb_size) { if (next_skb_size <= skb_availroom(skb)) skb_copy_bits(next_skb, 0, skb_put(skb, next_skb_size), next_skb_size); else if (!tcp_skb_shift(skb, next_skb, 1, next_skb_size)) return false; } tcp_highest_sack_replace(sk, next_skb, skb); tcp_unlink_write_queue(next_skb, sk); if (next_skb->ip_summed == CHECKSUM_PARTIAL) skb->ip_summed = CHECKSUM_PARTIAL; if (skb->ip_summed != CHECKSUM_PARTIAL) skb->csum = csum_block_add(skb->csum, next_skb->csum, skb_size); /* Update sequence range on original skb. */ TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(next_skb)->end_seq; /* Merge over control information. This moves PSH/FIN etc. over */ TCP_SKB_CB(skb)->tcp_flags |= TCP_SKB_CB(next_skb)->tcp_flags; /* All done, get rid of second SKB and account for it so * packet counting does not break. */ TCP_SKB_CB(skb)->sacked |= TCP_SKB_CB(next_skb)->sacked & TCPCB_EVER_RETRANS; TCP_SKB_CB(skb)->eor = TCP_SKB_CB(next_skb)->eor; /* changed transmit queue under us so clear hints */ tcp_clear_retrans_hints_partial(tp); if (next_skb == tp->retransmit_skb_hint) tp->retransmit_skb_hint = skb; tcp_adjust_pcount(sk, next_skb, tcp_skb_pcount(next_skb)); tcp_skb_collapse_tstamp(skb, next_skb); sk_wmem_free_skb(sk, next_skb); return true; } /* Check if coalescing SKBs is legal. */ static bool tcp_can_collapse(const struct sock *sk, const struct sk_buff *skb) { if (tcp_skb_pcount(skb) > 1) return false; if (skb_cloned(skb)) return false; if (skb == tcp_send_head(sk)) return false; /* Some heuristics for collapsing over SACK'd could be invented */ if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) return false; return true; } /* Collapse packets in the retransmit queue to make to create * less packets on the wire. This is only done on retransmission. */ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, int space) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb = to, *tmp; bool first = true; if (!sysctl_tcp_retrans_collapse) return; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN) return; tcp_for_write_queue_from_safe(skb, tmp, sk) { if (!tcp_can_collapse(sk, skb)) break; if (!tcp_skb_can_collapse_to(to)) break; space -= skb->len; if (first) { first = false; continue; } if (space < 0) break; if (after(TCP_SKB_CB(skb)->end_seq, tcp_wnd_end(tp))) break; if (!tcp_collapse_retrans(sk, to)) break; } } /* This retransmits one SKB. Policy decisions and retransmit queue * state updates are done by the caller. Returns non-zero if an * error occurred which prevented the send. */ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); unsigned int cur_mss; int diff, len, err; int avail_wnd; /* Inconclusive MTU probe */ if (icsk->icsk_mtup.probe_size) icsk->icsk_mtup.probe_size = 0; /* Do not sent more than we queued. 1/4 is reserved for possible * copying overhead: fragmentation, tunneling, mangling etc. */ if (refcount_read(&sk->sk_wmem_alloc) > min_t(u32, sk->sk_wmem_queued + (sk->sk_wmem_queued >> 2), sk->sk_sndbuf)) return -EAGAIN; if (skb_still_in_host_queue(sk, skb)) return -EBUSY; if (before(TCP_SKB_CB(skb)->seq, tp->snd_una)) { if (unlikely(before(TCP_SKB_CB(skb)->end_seq, tp->snd_una))) { WARN_ON_ONCE(1); return -EINVAL; } if (tcp_trim_head(sk, skb, tp->snd_una - TCP_SKB_CB(skb)->seq)) return -ENOMEM; } if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk)) return -EHOSTUNREACH; /* Routing failure or similar. */ cur_mss = tcp_current_mss(sk); avail_wnd = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; /* If receiver has shrunk his window, and skb is out of * new window, do not retransmit it. The exception is the * case, when window is shrunk to zero. In this case * our retransmit of one segment serves as a zero window probe. */ if (avail_wnd <= 0) { if (TCP_SKB_CB(skb)->seq != tp->snd_una) return -EAGAIN; avail_wnd = cur_mss; } len = cur_mss * segs; if (len > avail_wnd) { len = rounddown(avail_wnd, cur_mss); if (!len) len = avail_wnd; } if (skb->len > len) { if (tcp_fragment(sk, skb, len, cur_mss, GFP_ATOMIC)) return -ENOMEM; /* We'll try again later. */ } else { if (skb_unclone(skb, GFP_ATOMIC)) return -ENOMEM; diff = tcp_skb_pcount(skb); tcp_set_skb_tso_segs(skb, cur_mss); diff -= tcp_skb_pcount(skb); if (diff) tcp_adjust_pcount(sk, skb, diff); avail_wnd = min_t(int, avail_wnd, cur_mss); if (skb->len < avail_wnd) tcp_retrans_try_collapse(sk, skb, avail_wnd); } /* RFC3168, section 6.1.1.1. ECN fallback */ if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN_ECN) == TCPHDR_SYN_ECN) tcp_ecn_clear_syn(sk, skb); /* Update global and local TCP statistics. */ segs = tcp_skb_pcount(skb); TCP_ADD_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS, segs); if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN) __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); tp->total_retrans += segs; /* make sure skb->data is aligned on arches that require it * and check if ack-trimming & collapsing extended the headroom * beyond what csum_start can cover. */ if (unlikely((NET_IP_ALIGN && ((unsigned long)skb->data & 3)) || skb_headroom(skb) >= 0xFFFF)) { struct sk_buff *nskb; nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC); err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : -ENOBUFS; if (!err) { skb->skb_mstamp = tp->tcp_mstamp; tcp_rate_skb_sent(sk, skb); } } else { err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); } if (likely(!err)) { TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS; } else if (err != -EBUSY) { NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL, segs); } return err; } int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) { struct tcp_sock *tp = tcp_sk(sk); int err = __tcp_retransmit_skb(sk, skb, segs); if (err == 0) { #if FASTRETRANS_DEBUG > 0 if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) { net_dbg_ratelimited("retrans_out leaked\n"); } #endif TCP_SKB_CB(skb)->sacked |= TCPCB_RETRANS; tp->retrans_out += tcp_skb_pcount(skb); /* Save stamp of the first retransmit. */ if (!tp->retrans_stamp) tp->retrans_stamp = tcp_skb_timestamp(skb); } if (tp->undo_retrans < 0) tp->undo_retrans = 0; tp->undo_retrans += tcp_skb_pcount(skb); return err; } /* This gets called after a retransmit timeout, and the initially * retransmitted data is acknowledged. It tries to continue * resending the rest of the retransmit queue, until either * we've sent it all or the congestion window limit is reached. * If doing SACK, the first ACK which comes back for a timeout * based retransmit packet might feed us FACK information again. * If so, we use it to avoid unnecessarily retransmissions. */ void tcp_xmit_retransmit_queue(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; struct sk_buff *hole = NULL; u32 max_segs; int mib_idx; if (!tp->packets_out) return; if (tp->retransmit_skb_hint) { skb = tp->retransmit_skb_hint; } else { skb = tcp_write_queue_head(sk); } max_segs = tcp_tso_segs(sk, tcp_current_mss(sk)); tcp_for_write_queue_from(skb, sk) { __u8 sacked; int segs; if (skb == tcp_send_head(sk)) break; if (tcp_pacing_check(sk)) break; /* we could do better than to assign each time */ if (!hole) tp->retransmit_skb_hint = skb; segs = tp->snd_cwnd - tcp_packets_in_flight(tp); if (segs <= 0) return; sacked = TCP_SKB_CB(skb)->sacked; /* In case tcp_shift_skb_data() have aggregated large skbs, * we need to make sure not sending too bigs TSO packets */ segs = min_t(int, segs, max_segs); if (tp->retrans_out >= tp->lost_out) { break; } else if (!(sacked & TCPCB_LOST)) { if (!hole && !(sacked & (TCPCB_SACKED_RETRANS|TCPCB_SACKED_ACKED))) hole = skb; continue; } else { if (icsk->icsk_ca_state != TCP_CA_Loss) mib_idx = LINUX_MIB_TCPFASTRETRANS; else mib_idx = LINUX_MIB_TCPSLOWSTARTRETRANS; } if (sacked & (TCPCB_SACKED_ACKED|TCPCB_SACKED_RETRANS)) continue; if (tcp_small_queue_check(sk, skb, 1)) return; if (tcp_retransmit_skb(sk, skb, segs)) return; NET_ADD_STATS(sock_net(sk), mib_idx, tcp_skb_pcount(skb)); if (tcp_in_cwnd_reduction(sk)) tp->prr_out += tcp_skb_pcount(skb); if (skb == tcp_write_queue_head(sk) && icsk->icsk_pending != ICSK_TIME_REO_TIMEOUT) inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, inet_csk(sk)->icsk_rto, TCP_RTO_MAX); } } /* We allow to exceed memory limits for FIN packets to expedite * connection tear down and (memory) recovery. * Otherwise tcp_send_fin() could be tempted to either delay FIN * or even be forced to close flow without any FIN. * In general, we want to allow one skb per socket to avoid hangs * with edge trigger epoll() */ void sk_forced_mem_schedule(struct sock *sk, int size) { int delta, amt; delta = size - sk->sk_forward_alloc; if (delta <= 0) return; amt = sk_mem_pages(delta); sk->sk_forward_alloc += amt * SK_MEM_QUANTUM; sk_memory_allocated_add(sk, amt); if (mem_cgroup_sockets_enabled && sk->sk_memcg) mem_cgroup_charge_skmem(sk->sk_memcg, amt); } /* Send a FIN. The caller locks the socket for us. * We should try to send a FIN packet really hard, but eventually give up. */ void tcp_send_fin(struct sock *sk) { struct sk_buff *skb, *tskb = tcp_write_queue_tail(sk); struct tcp_sock *tp = tcp_sk(sk); /* Optimization, tack on the FIN if we have one skb in write queue and * this skb was not yet sent, or we are under memory pressure. * Note: in the latter case, FIN packet will be sent after a timeout, * as TCP stack thinks it has already been transmitted. */ if (tskb && (tcp_send_head(sk) || tcp_under_memory_pressure(sk))) { coalesce: TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN; TCP_SKB_CB(tskb)->end_seq++; tp->write_seq++; if (!tcp_send_head(sk)) { /* This means tskb was already sent. * Pretend we included the FIN on previous transmit. * We need to set tp->snd_nxt to the value it would have * if FIN had been sent. This is because retransmit path * does not change tp->snd_nxt. */ tp->snd_nxt++; return; } } else { skb = alloc_skb_fclone(MAX_TCP_HEADER, sk->sk_allocation); if (unlikely(!skb)) { if (tskb) goto coalesce; return; } skb_reserve(skb, MAX_TCP_HEADER); sk_forced_mem_schedule(sk, skb->truesize); /* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */ tcp_init_nondata_skb(skb, tp->write_seq, TCPHDR_ACK | TCPHDR_FIN); tcp_queue_skb(sk, skb); } __tcp_push_pending_frames(sk, tcp_current_mss(sk), TCP_NAGLE_OFF); } /* We get here when a process closes a file descriptor (either due to * an explicit close() or as a byproduct of exit()'ing) and there * was unread data in the receive queue. This behavior is recommended * by RFC 2525, section 2.17. -DaveM */ void tcp_send_active_reset(struct sock *sk, gfp_t priority) { struct sk_buff *skb; TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTRSTS); /* NOTE: No TCP options attached and we never retransmit this. */ skb = alloc_skb(MAX_TCP_HEADER, priority); if (!skb) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED); return; } /* Reserve space for headers and prepare control bits. */ skb_reserve(skb, MAX_TCP_HEADER); tcp_init_nondata_skb(skb, tcp_acceptable_seq(sk), TCPHDR_ACK | TCPHDR_RST); tcp_mstamp_refresh(tcp_sk(sk)); /* Send it off. */ if (tcp_transmit_skb(sk, skb, 0, priority)) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED); } /* Send a crossed SYN-ACK during socket establishment. * WARNING: This routine must only be called when we have already sent * a SYN packet that crossed the incoming SYN that caused this routine * to get called. If this assumption fails then the initial rcv_wnd * and rcv_wscale values will not be correct. */ int tcp_send_synack(struct sock *sk) { struct sk_buff *skb; skb = tcp_write_queue_head(sk); if (!skb || !(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { pr_debug("%s: wrong queue state\n", __func__); return -EFAULT; } if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK)) { if (skb_cloned(skb)) { struct sk_buff *nskb = skb_copy(skb, GFP_ATOMIC); if (!nskb) return -ENOMEM; tcp_unlink_write_queue(skb, sk); __skb_header_release(nskb); __tcp_add_write_queue_head(sk, nskb); sk_wmem_free_skb(sk, skb); sk->sk_wmem_queued += nskb->truesize; sk_mem_charge(sk, nskb->truesize); skb = nskb; } TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ACK; tcp_ecn_send_synack(sk, skb); } return tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); } /** * tcp_make_synack - Prepare a SYN-ACK. * sk: listener socket * dst: dst entry attached to the SYNACK * req: request_sock pointer * * Allocate one skb and build a SYNACK packet. * @dst is consumed : Caller should not use it again. */ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, struct request_sock *req, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type) { struct inet_request_sock *ireq = inet_rsk(req); const struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *md5 = NULL; struct tcp_out_options opts; struct sk_buff *skb; int tcp_header_size; struct tcphdr *th; int mss; skb = alloc_skb(MAX_TCP_HEADER, GFP_ATOMIC); if (unlikely(!skb)) { dst_release(dst); return NULL; } /* Reserve space for headers. */ skb_reserve(skb, MAX_TCP_HEADER); switch (synack_type) { case TCP_SYNACK_NORMAL: skb_set_owner_w(skb, req_to_sk(req)); break; case TCP_SYNACK_COOKIE: /* Under synflood, we do not attach skb to a socket, * to avoid false sharing. */ break; case TCP_SYNACK_FASTOPEN: /* sk is a const pointer, because we want to express multiple * cpu might call us concurrently. * sk->sk_wmem_alloc in an atomic, we can promote to rw. */ skb_set_owner_w(skb, (struct sock *)sk); break; } skb_dst_set(skb, dst); mss = tcp_mss_clamp(tp, dst_metric_advmss(dst)); memset(&opts, 0, sizeof(opts)); #ifdef CONFIG_SYN_COOKIES if (unlikely(req->cookie_ts)) skb->skb_mstamp = cookie_init_timestamp(req); else #endif skb->skb_mstamp = tcp_clock_us(); #ifdef CONFIG_TCP_MD5SIG rcu_read_lock(); md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req)); #endif skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4); tcp_header_size = tcp_synack_options(req, mss, skb, &opts, md5, foc, synack_type) + sizeof(*th); skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); th = (struct tcphdr *)skb->data; memset(th, 0, sizeof(struct tcphdr)); th->syn = 1; th->ack = 1; tcp_ecn_make_synack(req, th); th->source = htons(ireq->ir_num); th->dest = ireq->ir_rmt_port; skb->mark = ireq->ir_mark; skb->ip_summed = CHECKSUM_PARTIAL; th->seq = htonl(tcp_rsk(req)->snt_isn); /* XXX data is queued and acked as is. No buffer/window check */ th->ack_seq = htonl(tcp_rsk(req)->rcv_nxt); /* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */ th->window = htons(min(req->rsk_rcv_wnd, 65535U)); tcp_options_write((__be32 *)(th + 1), NULL, &opts); th->doff = (tcp_header_size >> 2); __TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS); #ifdef CONFIG_TCP_MD5SIG /* Okay, we have all we need - do the md5 hash if needed */ if (md5) tcp_rsk(req)->af_specific->calc_md5_hash(opts.hash_location, md5, req_to_sk(req), skb); rcu_read_unlock(); #endif /* Do not fool tcpdump (if any), clean our debris */ skb->tstamp = 0; return skb; } EXPORT_SYMBOL(tcp_make_synack); static void tcp_ca_dst_init(struct sock *sk, const struct dst_entry *dst) { struct inet_connection_sock *icsk = inet_csk(sk); const struct tcp_congestion_ops *ca; u32 ca_key = dst_metric(dst, RTAX_CC_ALGO); if (ca_key == TCP_CA_UNSPEC) return; rcu_read_lock(); ca = tcp_ca_find_key(ca_key); if (likely(ca && try_module_get(ca->owner))) { module_put(icsk->icsk_ca_ops->owner); icsk->icsk_ca_dst_locked = tcp_ca_dst_locked(dst); icsk->icsk_ca_ops = ca; } rcu_read_unlock(); } /* Do all connect socket setups that can be done AF independent. */ static void tcp_connect_init(struct sock *sk) { const struct dst_entry *dst = __sk_dst_get(sk); struct tcp_sock *tp = tcp_sk(sk); __u8 rcv_wscale; u32 rcv_wnd; /* We'll fix this up when we get a response from the other end. * See tcp_input.c:tcp_rcv_state_process case TCP_SYN_SENT. */ tp->tcp_header_len = sizeof(struct tcphdr); if (sock_net(sk)->ipv4.sysctl_tcp_timestamps) tp->tcp_header_len += TCPOLEN_TSTAMP_ALIGNED; #ifdef CONFIG_TCP_MD5SIG if (tp->af_specific->md5_lookup(sk, sk)) tp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED; #endif /* If user gave his TCP_MAXSEG, record it to clamp */ if (tp->rx_opt.user_mss) tp->rx_opt.mss_clamp = tp->rx_opt.user_mss; tp->max_window = 0; tcp_mtup_init(sk); tcp_sync_mss(sk, dst_mtu(dst)); tcp_ca_dst_init(sk, dst); if (!tp->window_clamp) tp->window_clamp = dst_metric(dst, RTAX_WINDOW); tp->advmss = tcp_mss_clamp(tp, dst_metric_advmss(dst)); tcp_initialize_rcv_mss(sk); /* limit the window selection if the user enforce a smaller rx buffer */ if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && (tp->window_clamp > tcp_full_space(sk) || tp->window_clamp == 0)) tp->window_clamp = tcp_full_space(sk); rcv_wnd = tcp_rwnd_init_bpf(sk); if (rcv_wnd == 0) rcv_wnd = dst_metric(dst, RTAX_INITRWND); tcp_select_initial_window(tcp_full_space(sk), tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0), &tp->rcv_wnd, &tp->window_clamp, sock_net(sk)->ipv4.sysctl_tcp_window_scaling, &rcv_wscale, rcv_wnd); tp->rx_opt.rcv_wscale = rcv_wscale; tp->rcv_ssthresh = tp->rcv_wnd; sk->sk_err = 0; sock_reset_flag(sk, SOCK_DONE); tp->snd_wnd = 0; tcp_init_wl(tp, 0); tcp_write_queue_purge(sk); tp->snd_una = tp->write_seq; tp->snd_sml = tp->write_seq; tp->snd_up = tp->write_seq; tp->snd_nxt = tp->write_seq; if (likely(!tp->repair)) tp->rcv_nxt = 0; else tp->rcv_tstamp = tcp_jiffies32; tp->rcv_wup = tp->rcv_nxt; tp->copied_seq = tp->rcv_nxt; inet_csk(sk)->icsk_rto = tcp_timeout_init(sk); inet_csk(sk)->icsk_retransmits = 0; tcp_clear_retrans(tp); } static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_skb_cb *tcb = TCP_SKB_CB(skb); tcb->end_seq += skb->len; __skb_header_release(skb); __tcp_add_write_queue_tail(sk, skb); sk->sk_wmem_queued += skb->truesize; sk_mem_charge(sk, skb->truesize); tp->write_seq = tcb->end_seq; tp->packets_out += tcp_skb_pcount(skb); } /* Build and send a SYN with data and (cached) Fast Open cookie. However, * queue a data-only packet after the regular SYN, such that regular SYNs * are retransmitted on timeouts. Also if the remote SYN-ACK acknowledges * only the SYN sequence, the data are retransmitted in the first ACK. * If cookie is not cached or other error occurs, falls back to send a * regular SYN with Fast Open cookie request option. */ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct tcp_fastopen_request *fo = tp->fastopen_req; int space, err = 0; struct sk_buff *syn_data; tp->rx_opt.mss_clamp = tp->advmss; /* If MSS is not cached */ if (!tcp_fastopen_cookie_check(sk, &tp->rx_opt.mss_clamp, &fo->cookie)) goto fallback; /* MSS for SYN-data is based on cached MSS and bounded by PMTU and * user-MSS. Reserve maximum option space for middleboxes that add * private TCP options. The cost is reduced data space in SYN :( */ tp->rx_opt.mss_clamp = tcp_mss_clamp(tp, tp->rx_opt.mss_clamp); /* Sync mss_cache after updating the mss_clamp */ tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); space = __tcp_mtu_to_mss(sk, icsk->icsk_pmtu_cookie) - MAX_TCP_OPTION_SPACE; space = min_t(size_t, space, fo->size); /* limit to order-0 allocations */ space = min_t(size_t, space, SKB_MAX_HEAD(MAX_TCP_HEADER)); syn_data = sk_stream_alloc_skb(sk, space, sk->sk_allocation, false); if (!syn_data) goto fallback; syn_data->ip_summed = CHECKSUM_PARTIAL; memcpy(syn_data->cb, syn->cb, sizeof(syn->cb)); if (space) { int copied = copy_from_iter(skb_put(syn_data, space), space, &fo->data->msg_iter); if (unlikely(!copied)) { kfree_skb(syn_data); goto fallback; } if (copied != space) { skb_trim(syn_data, copied); space = copied; } } /* No more data pending in inet_wait_for_connect() */ if (space == fo->size) fo->data = NULL; fo->copied = space; tcp_connect_queue_skb(sk, syn_data); if (syn_data->len) tcp_chrono_start(sk, TCP_CHRONO_BUSY); err = tcp_transmit_skb(sk, syn_data, 1, sk->sk_allocation); syn->skb_mstamp = syn_data->skb_mstamp; /* Now full SYN+DATA was cloned and sent (or not), * remove the SYN from the original skb (syn_data) * we keep in write queue in case of a retransmit, as we * also have the SYN packet (with no data) in the same queue. */ TCP_SKB_CB(syn_data)->seq++; TCP_SKB_CB(syn_data)->tcp_flags = TCPHDR_ACK | TCPHDR_PSH; if (!err) { tp->syn_data = (fo->copied > 0); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT); goto done; } /* data was not sent, this is our new send_head */ sk->sk_send_head = syn_data; tp->packets_out -= tcp_skb_pcount(syn_data); fallback: /* Send a regular SYN with Fast Open cookie request option */ if (fo->cookie.len > 0) fo->cookie.len = 0; err = tcp_transmit_skb(sk, syn, 1, sk->sk_allocation); if (err) tp->syn_fastopen = 0; done: fo->cookie.len = -1; /* Exclude Fast Open option for SYN retries */ return err; } /* Build a SYN and send it off. */ int tcp_connect(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *buff; int err; tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_CONNECT_CB); if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk)) return -EHOSTUNREACH; /* Routing failure or similar. */ tcp_connect_init(sk); if (unlikely(tp->repair)) { tcp_finish_connect(sk, NULL); return 0; } buff = sk_stream_alloc_skb(sk, 0, sk->sk_allocation, true); if (unlikely(!buff)) return -ENOBUFS; tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN); tcp_mstamp_refresh(tp); tp->retrans_stamp = tcp_time_stamp(tp); tcp_connect_queue_skb(sk, buff); tcp_ecn_send_syn(sk, buff); /* Send off SYN; include data in Fast Open. */ err = tp->fastopen_req ? tcp_send_syn_data(sk, buff) : tcp_transmit_skb(sk, buff, 1, sk->sk_allocation); if (err == -ECONNREFUSED) return err; /* We change tp->snd_nxt after the tcp_transmit_skb() call * in order to make this packet get counted in tcpOutSegs. */ tp->snd_nxt = tp->write_seq; tp->pushed_seq = tp->write_seq; buff = tcp_send_head(sk); if (unlikely(buff)) { tp->snd_nxt = TCP_SKB_CB(buff)->seq; tp->pushed_seq = TCP_SKB_CB(buff)->seq; } TCP_INC_STATS(sock_net(sk), TCP_MIB_ACTIVEOPENS); /* Timer for repeating the SYN until an answer. */ inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, inet_csk(sk)->icsk_rto, TCP_RTO_MAX); return 0; } EXPORT_SYMBOL(tcp_connect); /* Send out a delayed ack, the caller does the policy checking * to see if we should even be here. See tcp_input.c:tcp_ack_snd_check() * for details. */ void tcp_send_delayed_ack(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); int ato = icsk->icsk_ack.ato; unsigned long timeout; if (ato > TCP_DELACK_MIN) { const struct tcp_sock *tp = tcp_sk(sk); int max_ato = HZ / 2; if (icsk->icsk_ack.pingpong || (icsk->icsk_ack.pending & ICSK_ACK_PUSHED)) max_ato = TCP_DELACK_MAX; /* Slow path, intersegment interval is "high". */ /* If some rtt estimate is known, use it to bound delayed ack. * Do not use inet_csk(sk)->icsk_rto here, use results of rtt measurements * directly. */ if (tp->srtt_us) { int rtt = max_t(int, usecs_to_jiffies(tp->srtt_us >> 3), TCP_DELACK_MIN); if (rtt < max_ato) max_ato = rtt; } ato = min(ato, max_ato); } /* Stay within the limit we were given */ timeout = jiffies + ato; /* Use new timeout only if there wasn't a older one earlier. */ if (icsk->icsk_ack.pending & ICSK_ACK_TIMER) { /* If delack timer was blocked or is about to expire, * send ACK now. */ if (icsk->icsk_ack.blocked || time_before_eq(icsk->icsk_ack.timeout, jiffies + (ato >> 2))) { tcp_send_ack(sk); return; } if (!time_before(timeout, icsk->icsk_ack.timeout)) timeout = icsk->icsk_ack.timeout; } icsk->icsk_ack.pending |= ICSK_ACK_SCHED | ICSK_ACK_TIMER; icsk->icsk_ack.timeout = timeout; sk_reset_timer(sk, &icsk->icsk_delack_timer, timeout); } /* This routine sends an ack and also updates the window. */ void __tcp_send_ack(struct sock *sk, u32 rcv_nxt) { struct sk_buff *buff; /* If we have been reset, we may not send again. */ if (sk->sk_state == TCP_CLOSE) return; /* We are not putting this on the write queue, so * tcp_transmit_skb() will set the ownership to this * sock. */ buff = alloc_skb(MAX_TCP_HEADER, sk_gfp_mask(sk, GFP_ATOMIC | __GFP_NOWARN)); if (unlikely(!buff)) { inet_csk_schedule_ack(sk); inet_csk(sk)->icsk_ack.ato = TCP_ATO_MIN; inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, TCP_DELACK_MAX, TCP_RTO_MAX); return; } /* Reserve space for headers and prepare control bits. */ skb_reserve(buff, MAX_TCP_HEADER); tcp_init_nondata_skb(buff, tcp_acceptable_seq(sk), TCPHDR_ACK); /* We do not want pure acks influencing TCP Small Queues or fq/pacing * too much. * SKB_TRUESIZE(max(1 .. 66, MAX_TCP_HEADER)) is unfortunately ~784 */ skb_set_tcp_pure_ack(buff); /* Send it off, this clears delayed acks for us. */ __tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0, rcv_nxt); } EXPORT_SYMBOL_GPL(__tcp_send_ack); void tcp_send_ack(struct sock *sk) { __tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt); } /* This routine sends a packet with an out of date sequence * number. It assumes the other end will try to ack it. * * Question: what should we make while urgent mode? * 4.4BSD forces sending single byte of data. We cannot send * out of window data, because we have SND.NXT==SND.MAX... * * Current solution: to send TWO zero-length segments in urgent mode: * one is with SEG.SEQ=SND.UNA to deliver urgent pointer, another is * out-of-date with SND.UNA-1 to probe window. */ static int tcp_xmit_probe_skb(struct sock *sk, int urgent, int mib) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; /* We don't queue it, tcp_transmit_skb() sets ownership. */ skb = alloc_skb(MAX_TCP_HEADER, sk_gfp_mask(sk, GFP_ATOMIC | __GFP_NOWARN)); if (!skb) return -1; /* Reserve space for headers and set control bits. */ skb_reserve(skb, MAX_TCP_HEADER); /* Use a previous sequence. This should cause the other * end to send an ack. Don't queue or clone SKB, just * send it. */ tcp_init_nondata_skb(skb, tp->snd_una - !urgent, TCPHDR_ACK); NET_INC_STATS(sock_net(sk), mib); return tcp_transmit_skb(sk, skb, 0, (__force gfp_t)0); } /* Called from setsockopt( ... TCP_REPAIR ) */ void tcp_send_window_probe(struct sock *sk) { if (sk->sk_state == TCP_ESTABLISHED) { tcp_sk(sk)->snd_wl1 = tcp_sk(sk)->rcv_nxt - 1; tcp_mstamp_refresh(tcp_sk(sk)); tcp_xmit_probe_skb(sk, 0, LINUX_MIB_TCPWINPROBE); } } /* Initiate keepalive or window probe from timer. */ int tcp_write_wakeup(struct sock *sk, int mib) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; if (sk->sk_state == TCP_CLOSE) return -1; skb = tcp_send_head(sk); if (skb && before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp))) { int err; unsigned int mss = tcp_current_mss(sk); unsigned int seg_size = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; if (before(tp->pushed_seq, TCP_SKB_CB(skb)->end_seq)) tp->pushed_seq = TCP_SKB_CB(skb)->end_seq; /* We are probing the opening of a window * but the window size is != 0 * must have been a result SWS avoidance ( sender ) */ if (seg_size < TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq || skb->len > mss) { seg_size = min(seg_size, mss); TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH; if (tcp_fragment(sk, skb, seg_size, mss, GFP_ATOMIC)) return -1; } else if (!tcp_skb_pcount(skb)) tcp_set_skb_tso_segs(skb, mss); TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_PSH; err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); if (!err) tcp_event_new_data_sent(sk, skb); return err; } else { if (between(tp->snd_up, tp->snd_una + 1, tp->snd_una + 0xFFFF)) tcp_xmit_probe_skb(sk, 1, mib); return tcp_xmit_probe_skb(sk, 0, mib); } } /* A window probe timeout has occurred. If window is not closed send * a partial packet else a zero probe. */ void tcp_send_probe0(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); unsigned long probe_max; int err; err = tcp_write_wakeup(sk, LINUX_MIB_TCPWINPROBE); if (tp->packets_out || !tcp_send_head(sk)) { /* Cancel probe timer, if it is not required. */ icsk->icsk_probes_out = 0; icsk->icsk_backoff = 0; return; } if (err <= 0) { if (icsk->icsk_backoff < net->ipv4.sysctl_tcp_retries2) icsk->icsk_backoff++; icsk->icsk_probes_out++; probe_max = TCP_RTO_MAX; } else { /* If packet was not sent due to local congestion, * do not backoff and do not remember icsk_probes_out. * Let local senders to fight for local resources. * * Use accumulated backoff yet. */ if (!icsk->icsk_probes_out) icsk->icsk_probes_out = 1; probe_max = TCP_RESOURCE_PROBE_INTERVAL; } inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0, tcp_probe0_when(sk, probe_max), TCP_RTO_MAX); } int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) { const struct tcp_request_sock_ops *af_ops = tcp_rsk(req)->af_specific; struct flowi fl; int res; tcp_rsk(req)->txhash = net_tx_rndhash(); res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL); if (!res) { TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS); if (unlikely(tcp_passive_fastopen(sk))) tcp_sk(sk)->total_retrans++; } return res; } EXPORT_SYMBOL(tcp_rtx_synack); |
| 5 5 11 2 6 6 2 2 2 5 6 6 6 6 6 5 2 2 2 4 2 2 6 4 11 2 5 18 18 18 19 18 19 7 7 6 4 4 5 7 9 9 8 2 8 8 6 6 5 5 5 6 2 2 2 2 1 2 2 3 1 1 1 2 3 3 2 1 3 14 13 10 10 3 3 3 11 4 2 2 5 5 4 3 11 8 2 2 1 1 6 8 20 20 8 12 7 3 2 11 20 7 7 6 2 1 7 7 7 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 | /* BlueZ - Bluetooth protocol stack for Linux Copyright (C) 2000-2001 Qualcomm Incorporated Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.com> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License version 2 as published by the Free Software Foundation; 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 OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS SOFTWARE IS DISCLAIMED. */ /* Bluetooth SCO sockets. */ #include <linux/module.h> #include <linux/debugfs.h> #include <linux/seq_file.h> #include <linux/sched/signal.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include <net/bluetooth/sco.h> static bool disable_esco; static const struct proto_ops sco_sock_ops; static struct bt_sock_list sco_sk_list = { .lock = __RW_LOCK_UNLOCKED(sco_sk_list.lock) }; /* ---- SCO connections ---- */ struct sco_conn { struct hci_conn *hcon; spinlock_t lock; struct sock *sk; struct delayed_work timeout_work; unsigned int mtu; }; #define sco_conn_lock(c) spin_lock(&c->lock); #define sco_conn_unlock(c) spin_unlock(&c->lock); static void sco_sock_close(struct sock *sk); static void sco_sock_kill(struct sock *sk); /* ----- SCO socket info ----- */ #define sco_pi(sk) ((struct sco_pinfo *) sk) struct sco_pinfo { struct bt_sock bt; bdaddr_t src; bdaddr_t dst; __u32 flags; __u16 setting; struct sco_conn *conn; }; /* ---- SCO timers ---- */ #define SCO_CONN_TIMEOUT (HZ * 40) #define SCO_DISCONN_TIMEOUT (HZ * 2) static void sco_sock_timeout(struct work_struct *work) { struct sco_conn *conn = container_of(work, struct sco_conn, timeout_work.work); struct sock *sk; sco_conn_lock(conn); sk = conn->sk; if (sk) sock_hold(sk); sco_conn_unlock(conn); if (!sk) return; BT_DBG("sock %p state %d", sk, sk->sk_state); bh_lock_sock(sk); sk->sk_err = ETIMEDOUT; sk->sk_state_change(sk); bh_unlock_sock(sk); sock_put(sk); } static void sco_sock_set_timer(struct sock *sk, long timeout) { if (!sco_pi(sk)->conn) return; BT_DBG("sock %p state %d timeout %ld", sk, sk->sk_state, timeout); cancel_delayed_work(&sco_pi(sk)->conn->timeout_work); schedule_delayed_work(&sco_pi(sk)->conn->timeout_work, timeout); } static void sco_sock_clear_timer(struct sock *sk) { if (!sco_pi(sk)->conn) return; BT_DBG("sock %p state %d", sk, sk->sk_state); cancel_delayed_work(&sco_pi(sk)->conn->timeout_work); } /* ---- SCO connections ---- */ static struct sco_conn *sco_conn_add(struct hci_conn *hcon) { struct hci_dev *hdev = hcon->hdev; struct sco_conn *conn = hcon->sco_data; if (conn) return conn; conn = kzalloc(sizeof(struct sco_conn), GFP_KERNEL); if (!conn) return NULL; spin_lock_init(&conn->lock); INIT_DELAYED_WORK(&conn->timeout_work, sco_sock_timeout); hcon->sco_data = conn; conn->hcon = hcon; if (hdev->sco_mtu > 0) conn->mtu = hdev->sco_mtu; else conn->mtu = 60; BT_DBG("hcon %p conn %p", hcon, conn); return conn; } /* Delete channel. * Must be called on the locked socket. */ static void sco_chan_del(struct sock *sk, int err) { struct sco_conn *conn; conn = sco_pi(sk)->conn; BT_DBG("sk %p, conn %p, err %d", sk, conn, err); if (conn) { sco_conn_lock(conn); conn->sk = NULL; sco_pi(sk)->conn = NULL; sco_conn_unlock(conn); if (conn->hcon) hci_conn_drop(conn->hcon); } sk->sk_state = BT_CLOSED; sk->sk_err = err; sk->sk_state_change(sk); sock_set_flag(sk, SOCK_ZAPPED); } static void sco_conn_del(struct hci_conn *hcon, int err) { struct sco_conn *conn = hcon->sco_data; struct sock *sk; if (!conn) return; BT_DBG("hcon %p conn %p, err %d", hcon, conn, err); /* Kill socket */ sco_conn_lock(conn); sk = conn->sk; sco_conn_unlock(conn); if (sk) { sock_hold(sk); bh_lock_sock(sk); sco_sock_clear_timer(sk); sco_chan_del(sk, err); bh_unlock_sock(sk); sock_put(sk); } /* Ensure no more work items will run before freeing conn. */ cancel_delayed_work_sync(&conn->timeout_work); hcon->sco_data = NULL; kfree(conn); } static void __sco_chan_add(struct sco_conn *conn, struct sock *sk, struct sock *parent) { BT_DBG("conn %p", conn); sco_pi(sk)->conn = conn; conn->sk = sk; if (parent) bt_accept_enqueue(parent, sk, true); } static int sco_chan_add(struct sco_conn *conn, struct sock *sk, struct sock *parent) { int err = 0; sco_conn_lock(conn); if (conn->sk) err = -EBUSY; else __sco_chan_add(conn, sk, parent); sco_conn_unlock(conn); return err; } static int sco_connect(struct hci_dev *hdev, struct sock *sk) { struct sco_conn *conn; struct hci_conn *hcon; int err, type; BT_DBG("%pMR -> %pMR", &sco_pi(sk)->src, &sco_pi(sk)->dst); if (lmp_esco_capable(hdev) && !disable_esco) type = ESCO_LINK; else type = SCO_LINK; if (sco_pi(sk)->setting == BT_VOICE_TRANSPARENT && (!lmp_transp_capable(hdev) || !lmp_esco_capable(hdev))) return -EOPNOTSUPP; hcon = hci_connect_sco(hdev, type, &sco_pi(sk)->dst, sco_pi(sk)->setting); if (IS_ERR(hcon)) return PTR_ERR(hcon); conn = sco_conn_add(hcon); if (!conn) { hci_conn_drop(hcon); return -ENOMEM; } /* Update source addr of the socket */ bacpy(&sco_pi(sk)->src, &hcon->src); err = sco_chan_add(conn, sk, NULL); if (err) return err; if (hcon->state == BT_CONNECTED) { sco_sock_clear_timer(sk); sk->sk_state = BT_CONNECTED; } else { sk->sk_state = BT_CONNECT; sco_sock_set_timer(sk, sk->sk_sndtimeo); } return err; } static int sco_send_frame(struct sock *sk, struct sk_buff *skb) { struct sco_conn *conn = sco_pi(sk)->conn; int len = skb->len; /* Check outgoing MTU */ if (len > conn->mtu) return -EINVAL; BT_DBG("sk %p len %d", sk, len); hci_send_sco(conn->hcon, skb); return len; } static void sco_recv_frame(struct sco_conn *conn, struct sk_buff *skb) { struct sock *sk; sco_conn_lock(conn); sk = conn->sk; sco_conn_unlock(conn); if (!sk) goto drop; BT_DBG("sk %p len %d", sk, skb->len); if (sk->sk_state != BT_CONNECTED) goto drop; if (!sock_queue_rcv_skb(sk, skb)) return; drop: kfree_skb(skb); } /* -------- Socket interface ---------- */ static struct sock *__sco_get_sock_listen_by_addr(bdaddr_t *ba) { struct sock *sk; sk_for_each(sk, &sco_sk_list.head) { if (sk->sk_state != BT_LISTEN) continue; if (!bacmp(&sco_pi(sk)->src, ba)) return sk; } return NULL; } /* Find socket listening on source bdaddr. * Returns closest match. */ static struct sock *sco_get_sock_listen(bdaddr_t *src) { struct sock *sk = NULL, *sk1 = NULL; read_lock(&sco_sk_list.lock); sk_for_each(sk, &sco_sk_list.head) { if (sk->sk_state != BT_LISTEN) continue; /* Exact match. */ if (!bacmp(&sco_pi(sk)->src, src)) break; /* Closest match */ if (!bacmp(&sco_pi(sk)->src, BDADDR_ANY)) sk1 = sk; } read_unlock(&sco_sk_list.lock); return sk ? sk : sk1; } static void sco_sock_destruct(struct sock *sk) { BT_DBG("sk %p", sk); skb_queue_purge(&sk->sk_receive_queue); skb_queue_purge(&sk->sk_write_queue); } static void sco_sock_cleanup_listen(struct sock *parent) { struct sock *sk; BT_DBG("parent %p", parent); /* Close not yet accepted channels */ while ((sk = bt_accept_dequeue(parent, NULL))) { sco_sock_close(sk); sco_sock_kill(sk); } parent->sk_state = BT_CLOSED; sock_set_flag(parent, SOCK_ZAPPED); } /* Kill socket (only if zapped and orphan) * Must be called on unlocked socket. */ static void sco_sock_kill(struct sock *sk) { if (!sock_flag(sk, SOCK_ZAPPED) || sk->sk_socket) return; BT_DBG("sk %p state %d", sk, sk->sk_state); /* Kill poor orphan */ bt_sock_unlink(&sco_sk_list, sk); sock_set_flag(sk, SOCK_DEAD); sock_put(sk); } static void __sco_sock_close(struct sock *sk) { BT_DBG("sk %p state %d socket %p", sk, sk->sk_state, sk->sk_socket); switch (sk->sk_state) { case BT_LISTEN: sco_sock_cleanup_listen(sk); break; case BT_CONNECTED: case BT_CONFIG: if (sco_pi(sk)->conn->hcon) { sk->sk_state = BT_DISCONN; sco_sock_set_timer(sk, SCO_DISCONN_TIMEOUT); sco_conn_lock(sco_pi(sk)->conn); hci_conn_drop(sco_pi(sk)->conn->hcon); sco_pi(sk)->conn->hcon = NULL; sco_conn_unlock(sco_pi(sk)->conn); } else sco_chan_del(sk, ECONNRESET); break; case BT_CONNECT2: case BT_CONNECT: case BT_DISCONN: sco_chan_del(sk, ECONNRESET); break; default: sock_set_flag(sk, SOCK_ZAPPED); break; } } /* Must be called on unlocked socket. */ static void sco_sock_close(struct sock *sk) { sco_sock_clear_timer(sk); lock_sock(sk); __sco_sock_close(sk); release_sock(sk); } static void sco_sock_init(struct sock *sk, struct sock *parent) { BT_DBG("sk %p", sk); if (parent) { sk->sk_type = parent->sk_type; bt_sk(sk)->flags = bt_sk(parent)->flags; security_sk_clone(parent, sk); } } static struct proto sco_proto = { .name = "SCO", .owner = THIS_MODULE, .obj_size = sizeof(struct sco_pinfo) }; static struct sock *sco_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio, int kern) { struct sock *sk; sk = sk_alloc(net, PF_BLUETOOTH, prio, &sco_proto, kern); if (!sk) return NULL; sock_init_data(sock, sk); INIT_LIST_HEAD(&bt_sk(sk)->accept_q); sk->sk_destruct = sco_sock_destruct; sk->sk_sndtimeo = SCO_CONN_TIMEOUT; sock_reset_flag(sk, SOCK_ZAPPED); sk->sk_protocol = proto; sk->sk_state = BT_OPEN; sco_pi(sk)->setting = BT_VOICE_CVSD_16BIT; bt_sock_link(&sco_sk_list, sk); return sk; } static int sco_sock_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; BT_DBG("sock %p", sock); sock->state = SS_UNCONNECTED; if (sock->type != SOCK_SEQPACKET) return -ESOCKTNOSUPPORT; sock->ops = &sco_sock_ops; sk = sco_sock_alloc(net, sock, protocol, GFP_ATOMIC, kern); if (!sk) return -ENOMEM; sco_sock_init(sk, NULL); return 0; } static int sco_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_len) { struct sockaddr_sco *sa = (struct sockaddr_sco *) addr; struct sock *sk = sock->sk; int err = 0; BT_DBG("sk %p %pMR", sk, &sa->sco_bdaddr); if (!addr || addr_len < sizeof(struct sockaddr_sco) || addr->sa_family != AF_BLUETOOTH) return -EINVAL; lock_sock(sk); if (sk->sk_state != BT_OPEN) { err = -EBADFD; goto done; } if (sk->sk_type != SOCK_SEQPACKET) { err = -EINVAL; goto done; } bacpy(&sco_pi(sk)->src, &sa->sco_bdaddr); sk->sk_state = BT_BOUND; done: release_sock(sk); return err; } static int sco_sock_connect(struct socket *sock, struct sockaddr *addr, int alen, int flags) { struct sockaddr_sco *sa = (struct sockaddr_sco *) addr; struct sock *sk = sock->sk; struct hci_dev *hdev; int err; BT_DBG("sk %p", sk); if (alen < sizeof(struct sockaddr_sco) || addr->sa_family != AF_BLUETOOTH) return -EINVAL; lock_sock(sk); if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND) { err = -EBADFD; goto done; } if (sk->sk_type != SOCK_SEQPACKET) { err = -EINVAL; goto done; } hdev = hci_get_route(&sa->sco_bdaddr, &sco_pi(sk)->src, BDADDR_BREDR); if (!hdev) { err = -EHOSTUNREACH; goto done; } hci_dev_lock(hdev); /* Set destination address and psm */ bacpy(&sco_pi(sk)->dst, &sa->sco_bdaddr); err = sco_connect(hdev, sk); hci_dev_unlock(hdev); hci_dev_put(hdev); if (err) goto done; err = bt_sock_wait_state(sk, BT_CONNECTED, sock_sndtimeo(sk, flags & O_NONBLOCK)); done: release_sock(sk); return err; } static int sco_sock_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; bdaddr_t *src = &sco_pi(sk)->src; int err = 0; BT_DBG("sk %p backlog %d", sk, backlog); lock_sock(sk); if (sk->sk_state != BT_BOUND) { err = -EBADFD; goto done; } if (sk->sk_type != SOCK_SEQPACKET) { err = -EINVAL; goto done; } write_lock(&sco_sk_list.lock); if (__sco_get_sock_listen_by_addr(src)) { err = -EADDRINUSE; goto unlock; } sk->sk_max_ack_backlog = backlog; sk->sk_ack_backlog = 0; sk->sk_state = BT_LISTEN; unlock: write_unlock(&sco_sk_list.lock); done: release_sock(sk); return err; } static int sco_sock_accept(struct socket *sock, struct socket *newsock, int flags, bool kern) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct sock *sk = sock->sk, *ch; long timeo; int err = 0; lock_sock(sk); timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); BT_DBG("sk %p timeo %ld", sk, timeo); /* Wait for an incoming connection. (wake-one). */ add_wait_queue_exclusive(sk_sleep(sk), &wait); while (1) { if (sk->sk_state != BT_LISTEN) { err = -EBADFD; break; } ch = bt_accept_dequeue(sk, newsock); if (ch) break; if (!timeo) { err = -EAGAIN; break; } if (signal_pending(current)) { err = sock_intr_errno(timeo); break; } release_sock(sk); timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); lock_sock(sk); } remove_wait_queue(sk_sleep(sk), &wait); if (err) goto done; newsock->state = SS_CONNECTED; BT_DBG("new socket %p", ch); done: release_sock(sk); return err; } static int sco_sock_getname(struct socket *sock, struct sockaddr *addr, int *len, int peer) { struct sockaddr_sco *sa = (struct sockaddr_sco *) addr; struct sock *sk = sock->sk; BT_DBG("sock %p, sk %p", sock, sk); addr->sa_family = AF_BLUETOOTH; *len = sizeof(struct sockaddr_sco); if (peer) bacpy(&sa->sco_bdaddr, &sco_pi(sk)->dst); else bacpy(&sa->sco_bdaddr, &sco_pi(sk)->src); return 0; } static int sco_sock_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct sk_buff *skb; int err; BT_DBG("sock %p, sk %p", sock, sk); err = sock_error(sk); if (err) return err; if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; skb = bt_skb_sendmsg(sk, msg, len, len, 0, 0); if (IS_ERR(skb)) return PTR_ERR(skb); lock_sock(sk); if (sk->sk_state == BT_CONNECTED) err = sco_send_frame(sk, skb); else err = -ENOTCONN; release_sock(sk); if (err < 0) kfree_skb(skb); return err; } static void sco_conn_defer_accept(struct hci_conn *conn, u16 setting) { struct hci_dev *hdev = conn->hdev; BT_DBG("conn %p", conn); conn->state = BT_CONFIG; if (!lmp_esco_capable(hdev)) { struct hci_cp_accept_conn_req cp; bacpy(&cp.bdaddr, &conn->dst); cp.role = 0x00; /* Ignored */ hci_send_cmd(hdev, HCI_OP_ACCEPT_CONN_REQ, sizeof(cp), &cp); } else { struct hci_cp_accept_sync_conn_req cp; bacpy(&cp.bdaddr, &conn->dst); cp.pkt_type = cpu_to_le16(conn->pkt_type); cp.tx_bandwidth = cpu_to_le32(0x00001f40); cp.rx_bandwidth = cpu_to_le32(0x00001f40); cp.content_format = cpu_to_le16(setting); switch (setting & SCO_AIRMODE_MASK) { case SCO_AIRMODE_TRANSP: if (conn->pkt_type & ESCO_2EV3) cp.max_latency = cpu_to_le16(0x0008); else cp.max_latency = cpu_to_le16(0x000D); cp.retrans_effort = 0x02; break; case SCO_AIRMODE_CVSD: cp.max_latency = cpu_to_le16(0xffff); cp.retrans_effort = 0xff; break; default: /* use CVSD settings as fallback */ cp.max_latency = cpu_to_le16(0xffff); cp.retrans_effort = 0xff; break; } hci_send_cmd(hdev, HCI_OP_ACCEPT_SYNC_CONN_REQ, sizeof(cp), &cp); } } static int sco_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sock *sk = sock->sk; struct sco_pinfo *pi = sco_pi(sk); lock_sock(sk); if (sk->sk_state == BT_CONNECT2 && test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { sco_conn_defer_accept(pi->conn->hcon, pi->setting); sk->sk_state = BT_CONFIG; release_sock(sk); return 0; } release_sock(sk); return bt_sock_recvmsg(sock, msg, len, flags); } static int sco_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen) { struct sock *sk = sock->sk; int len, err = 0; struct bt_voice voice; u32 opt; BT_DBG("sk %p", sk); lock_sock(sk); switch (optname) { case BT_DEFER_SETUP: if (sk->sk_state != BT_BOUND && sk->sk_state != BT_LISTEN) { err = -EINVAL; break; } if (get_user(opt, (u32 __user *) optval)) { err = -EFAULT; break; } if (opt) set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags); else clear_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags); break; case BT_VOICE: if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND && sk->sk_state != BT_CONNECT2) { err = -EINVAL; break; } voice.setting = sco_pi(sk)->setting; len = min_t(unsigned int, sizeof(voice), optlen); if (copy_from_user((char *)&voice, optval, len)) { err = -EFAULT; break; } /* Explicitly check for these values */ if (voice.setting != BT_VOICE_TRANSPARENT && voice.setting != BT_VOICE_CVSD_16BIT) { err = -EINVAL; break; } sco_pi(sk)->setting = voice.setting; break; default: err = -ENOPROTOOPT; break; } release_sock(sk); return err; } static int sco_sock_getsockopt_old(struct socket *sock, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; struct sco_options opts; struct sco_conninfo cinfo; int len, err = 0; BT_DBG("sk %p", sk); if (get_user(len, optlen)) return -EFAULT; lock_sock(sk); switch (optname) { case SCO_OPTIONS: if (sk->sk_state != BT_CONNECTED && !(sk->sk_state == BT_CONNECT2 && test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags))) { err = -ENOTCONN; break; } opts.mtu = sco_pi(sk)->conn->mtu; BT_DBG("mtu %d", opts.mtu); len = min_t(unsigned int, len, sizeof(opts)); if (copy_to_user(optval, (char *)&opts, len)) err = -EFAULT; break; case SCO_CONNINFO: if (sk->sk_state != BT_CONNECTED && !(sk->sk_state == BT_CONNECT2 && test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags))) { err = -ENOTCONN; break; } memset(&cinfo, 0, sizeof(cinfo)); cinfo.hci_handle = sco_pi(sk)->conn->hcon->handle; memcpy(cinfo.dev_class, sco_pi(sk)->conn->hcon->dev_class, 3); len = min_t(unsigned int, len, sizeof(cinfo)); if (copy_to_user(optval, (char *)&cinfo, len)) err = -EFAULT; break; default: err = -ENOPROTOOPT; break; } release_sock(sk); return err; } static int sco_sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; int len, err = 0; struct bt_voice voice; BT_DBG("sk %p", sk); if (level == SOL_SCO) return sco_sock_getsockopt_old(sock, optname, optval, optlen); if (get_user(len, optlen)) return -EFAULT; lock_sock(sk); switch (optname) { case BT_DEFER_SETUP: if (sk->sk_state != BT_BOUND && sk->sk_state != BT_LISTEN) { err = -EINVAL; break; } if (put_user(test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags), (u32 __user *)optval)) err = -EFAULT; break; case BT_VOICE: voice.setting = sco_pi(sk)->setting; len = min_t(unsigned int, len, sizeof(voice)); if (copy_to_user(optval, (char *)&voice, len)) err = -EFAULT; break; default: err = -ENOPROTOOPT; break; } release_sock(sk); return err; } static int sco_sock_shutdown(struct socket *sock, int how) { struct sock *sk = sock->sk; int err = 0; BT_DBG("sock %p, sk %p", sock, sk); if (!sk) return 0; sock_hold(sk); lock_sock(sk); if (!sk->sk_shutdown) { sk->sk_shutdown = SHUTDOWN_MASK; sco_sock_clear_timer(sk); __sco_sock_close(sk); if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime && !(current->flags & PF_EXITING)) err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime); } release_sock(sk); sock_put(sk); return err; } static int sco_sock_release(struct socket *sock) { struct sock *sk = sock->sk; int err = 0; BT_DBG("sock %p, sk %p", sock, sk); if (!sk) return 0; sco_sock_close(sk); if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime && !(current->flags & PF_EXITING)) { lock_sock(sk); err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime); release_sock(sk); } sock_orphan(sk); sco_sock_kill(sk); return err; } static void sco_conn_ready(struct sco_conn *conn) { struct sock *parent; struct sock *sk = conn->sk; BT_DBG("conn %p", conn); if (sk) { sco_sock_clear_timer(sk); bh_lock_sock(sk); sk->sk_state = BT_CONNECTED; sk->sk_state_change(sk); bh_unlock_sock(sk); } else { sco_conn_lock(conn); if (!conn->hcon) { sco_conn_unlock(conn); return; } parent = sco_get_sock_listen(&conn->hcon->src); if (!parent) { sco_conn_unlock(conn); return; } bh_lock_sock(parent); sk = sco_sock_alloc(sock_net(parent), NULL, BTPROTO_SCO, GFP_ATOMIC, 0); if (!sk) { bh_unlock_sock(parent); sco_conn_unlock(conn); return; } sco_sock_init(sk, parent); bacpy(&sco_pi(sk)->src, &conn->hcon->src); bacpy(&sco_pi(sk)->dst, &conn->hcon->dst); hci_conn_hold(conn->hcon); __sco_chan_add(conn, sk, parent); if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags)) sk->sk_state = BT_CONNECT2; else sk->sk_state = BT_CONNECTED; /* Wake up parent */ parent->sk_data_ready(parent); bh_unlock_sock(parent); sco_conn_unlock(conn); } } /* ----- SCO interface with lower layer (HCI) ----- */ int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) { struct sock *sk; int lm = 0; BT_DBG("hdev %s, bdaddr %pMR", hdev->name, bdaddr); /* Find listening sockets */ read_lock(&sco_sk_list.lock); sk_for_each(sk, &sco_sk_list.head) { if (sk->sk_state != BT_LISTEN) continue; if (!bacmp(&sco_pi(sk)->src, &hdev->bdaddr) || !bacmp(&sco_pi(sk)->src, BDADDR_ANY)) { lm |= HCI_LM_ACCEPT; if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) *flags |= HCI_PROTO_DEFER; break; } } read_unlock(&sco_sk_list.lock); return lm; } static void sco_connect_cfm(struct hci_conn *hcon, __u8 status) { if (hcon->type != SCO_LINK && hcon->type != ESCO_LINK) return; BT_DBG("hcon %p bdaddr %pMR status %d", hcon, &hcon->dst, status); if (!status) { struct sco_conn *conn; conn = sco_conn_add(hcon); if (conn) sco_conn_ready(conn); } else sco_conn_del(hcon, bt_to_errno(status)); } static void sco_disconn_cfm(struct hci_conn *hcon, __u8 reason) { if (hcon->type != SCO_LINK && hcon->type != ESCO_LINK) return; BT_DBG("hcon %p reason %d", hcon, reason); sco_conn_del(hcon, bt_to_errno(reason)); } void sco_recv_scodata(struct hci_conn *hcon, struct sk_buff *skb) { struct sco_conn *conn = hcon->sco_data; if (!conn) goto drop; BT_DBG("conn %p len %d", conn, skb->len); if (skb->len) { sco_recv_frame(conn, skb); return; } drop: kfree_skb(skb); } static struct hci_cb sco_cb = { .name = "SCO", .connect_cfm = sco_connect_cfm, .disconn_cfm = sco_disconn_cfm, }; static int sco_debugfs_show(struct seq_file *f, void *p) { struct sock *sk; read_lock(&sco_sk_list.lock); sk_for_each(sk, &sco_sk_list.head) { seq_printf(f, "%pMR %pMR %d\n", &sco_pi(sk)->src, &sco_pi(sk)->dst, sk->sk_state); } read_unlock(&sco_sk_list.lock); return 0; } static int sco_debugfs_open(struct inode *inode, struct file *file) { return single_open(file, sco_debugfs_show, inode->i_private); } static const struct file_operations sco_debugfs_fops = { .open = sco_debugfs_open, .read = seq_read, .llseek = seq_lseek, .release = single_release, }; static struct dentry *sco_debugfs; static const struct proto_ops sco_sock_ops = { .family = PF_BLUETOOTH, .owner = THIS_MODULE, .release = sco_sock_release, .bind = sco_sock_bind, .connect = sco_sock_connect, .listen = sco_sock_listen, .accept = sco_sock_accept, .getname = sco_sock_getname, .sendmsg = sco_sock_sendmsg, .recvmsg = sco_sock_recvmsg, .poll = bt_sock_poll, .ioctl = bt_sock_ioctl, .mmap = sock_no_mmap, .socketpair = sock_no_socketpair, .shutdown = sco_sock_shutdown, .setsockopt = sco_sock_setsockopt, .getsockopt = sco_sock_getsockopt }; static const struct net_proto_family sco_sock_family_ops = { .family = PF_BLUETOOTH, .owner = THIS_MODULE, .create = sco_sock_create, }; int __init sco_init(void) { int err; BUILD_BUG_ON(sizeof(struct sockaddr_sco) > sizeof(struct sockaddr)); err = proto_register(&sco_proto, 0); if (err < 0) return err; err = bt_sock_register(BTPROTO_SCO, &sco_sock_family_ops); if (err < 0) { BT_ERR("SCO socket registration failed"); goto error; } err = bt_procfs_init(&init_net, "sco", &sco_sk_list, NULL); if (err < 0) { BT_ERR("Failed to create SCO proc file"); bt_sock_unregister(BTPROTO_SCO); goto error; } BT_INFO("SCO socket layer initialized"); hci_register_cb(&sco_cb); if (IS_ERR_OR_NULL(bt_debugfs)) return 0; sco_debugfs = debugfs_create_file("sco", 0444, bt_debugfs, NULL, &sco_debugfs_fops); return 0; error: proto_unregister(&sco_proto); return err; } void sco_exit(void) { bt_procfs_cleanup(&init_net, "sco"); debugfs_remove(sco_debugfs); hci_unregister_cb(&sco_cb); bt_sock_unregister(BTPROTO_SCO); proto_unregister(&sco_proto); } module_param(disable_esco, bool, 0644); MODULE_PARM_DESC(disable_esco, "Disable eSCO connection creation"); |
| 1254 1253 1182 290 1253 1253 553 552 139 555 2555 1077 2556 2555 2557 2556 1253 2556 1252 2556 2557 1252 555 2557 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/bug.h> #include <linux/compiler.h> #include <linux/export.h> #include <linux/string.h> #include <linux/list_sort.h> #include <linux/list.h> #define MAX_LIST_LENGTH_BITS 20 /* * Returns a list organized in an intermediate format suited * to chaining of merge() calls: null-terminated, no reserved or * sentinel head node, "prev" links not maintained. */ static struct list_head *merge(void *priv, int (*cmp)(void *priv, struct list_head *a, struct list_head *b), struct list_head *a, struct list_head *b) { struct list_head head, *tail = &head; while (a && b) { /* if equal, take 'a' -- important for sort stability */ if ((*cmp)(priv, a, b) <= 0) { tail->next = a; a = a->next; } else { tail->next = b; b = b->next; } tail = tail->next; } tail->next = a?:b; return head.next; } /* * Combine final list merge with restoration of standard doubly-linked * list structure. This approach duplicates code from merge(), but * runs faster than the tidier alternatives of either a separate final * prev-link restoration pass, or maintaining the prev links * throughout. */ static void merge_and_restore_back_links(void *priv, int (*cmp)(void *priv, struct list_head *a, struct list_head *b), struct list_head *head, struct list_head *a, struct list_head *b) { struct list_head *tail = head; u8 count = 0; while (a && b) { /* if equal, take 'a' -- important for sort stability */ if ((*cmp)(priv, a, b) <= 0) { tail->next = a; a->prev = tail; a = a->next; } else { tail->next = b; b->prev = tail; b = b->next; } tail = tail->next; } tail->next = a ? : b; do { /* * In worst cases this loop may run many iterations. * Continue callbacks to the client even though no * element comparison is needed, so the client's cmp() * routine can invoke cond_resched() periodically. */ if (unlikely(!(++count))) (*cmp)(priv, tail->next, tail->next); tail->next->prev = tail; tail = tail->next; } while (tail->next); tail->next = head; head->prev = tail; } /** * list_sort - sort a list * @priv: private data, opaque to list_sort(), passed to @cmp * @head: the list to sort * @cmp: the elements comparison function * * This function implements "merge sort", which has O(nlog(n)) * complexity. * * The comparison function @cmp must return a negative value if @a * should sort before @b, and a positive value if @a should sort after * @b. If @a and @b are equivalent, and their original relative * ordering is to be preserved, @cmp must return 0. */ void list_sort(void *priv, struct list_head *head, int (*cmp)(void *priv, struct list_head *a, struct list_head *b)) { struct list_head *part[MAX_LIST_LENGTH_BITS+1]; /* sorted partial lists -- last slot is a sentinel */ int lev; /* index into part[] */ int max_lev = 0; struct list_head *list; if (list_empty(head)) return; memset(part, 0, sizeof(part)); head->prev->next = NULL; list = head->next; while (list) { struct list_head *cur = list; list = list->next; cur->next = NULL; for (lev = 0; part[lev]; lev++) { cur = merge(priv, cmp, part[lev], cur); part[lev] = NULL; } if (lev > max_lev) { if (unlikely(lev >= ARRAY_SIZE(part)-1)) { printk_once(KERN_DEBUG "list too long for efficiency\n"); lev--; } max_lev = lev; } part[lev] = cur; } for (lev = 0; lev < max_lev; lev++) if (part[lev]) list = merge(priv, cmp, part[lev], list); merge_and_restore_back_links(priv, cmp, head, part[max_lev], list); } EXPORT_SYMBOL(list_sort); |
| 670 670 533 537 129 533 659 61 58 532 534 1 522 528 516 528 12 520 520 516 522 7 106 74 139 49 1 5 143 3 140 140 139 134 133 133 74 133 63 131 130 129 1 129 129 129 106 101 133 132 138 139 18 122 146 2 146 1 144 144 143 142 690 685 685 1 679 690 3 3 3 12 12 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 | /* Netfilter messages via netlink socket. Allows for user space * protocol helpers and general trouble making from userspace. * * (C) 2001 by Jay Schulist <jschlst@samba.org>, * (C) 2002-2005 by Harald Welte <laforge@gnumonks.org> * (C) 2005-2017 by Pablo Neira Ayuso <pablo@netfilter.org> * * Initial netfilter messages via netlink development funded and * generally made possible by Network Robots, Inc. (www.networkrobots.com) * * Further development of this code funded by Astaro AG (http://www.astaro.com) * * This software may be used and distributed according to the terms * of the GNU General Public License, incorporated herein by reference. */ #include <linux/module.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/skbuff.h> #include <linux/uaccess.h> #include <net/sock.h> #include <linux/init.h> #include <net/netlink.h> #include <linux/netfilter/nfnetlink.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_NETFILTER); #define nfnl_dereference_protected(id) \ rcu_dereference_protected(table[(id)].subsys, \ lockdep_nfnl_is_held((id))) static char __initdata nfversion[] = "0.30"; static struct { struct mutex mutex; const struct nfnetlink_subsystem __rcu *subsys; } table[NFNL_SUBSYS_COUNT]; static const int nfnl_group2type[NFNLGRP_MAX+1] = { [NFNLGRP_CONNTRACK_NEW] = NFNL_SUBSYS_CTNETLINK, [NFNLGRP_CONNTRACK_UPDATE] = NFNL_SUBSYS_CTNETLINK, [NFNLGRP_CONNTRACK_DESTROY] = NFNL_SUBSYS_CTNETLINK, [NFNLGRP_CONNTRACK_EXP_NEW] = NFNL_SUBSYS_CTNETLINK_EXP, [NFNLGRP_CONNTRACK_EXP_UPDATE] = NFNL_SUBSYS_CTNETLINK_EXP, [NFNLGRP_CONNTRACK_EXP_DESTROY] = NFNL_SUBSYS_CTNETLINK_EXP, [NFNLGRP_NFTABLES] = NFNL_SUBSYS_NFTABLES, [NFNLGRP_ACCT_QUOTA] = NFNL_SUBSYS_ACCT, [NFNLGRP_NFTRACE] = NFNL_SUBSYS_NFTABLES, }; void nfnl_lock(__u8 subsys_id) { mutex_lock(&table[subsys_id].mutex); } EXPORT_SYMBOL_GPL(nfnl_lock); void nfnl_unlock(__u8 subsys_id) { mutex_unlock(&table[subsys_id].mutex); } EXPORT_SYMBOL_GPL(nfnl_unlock); #ifdef CONFIG_PROVE_LOCKING bool lockdep_nfnl_is_held(u8 subsys_id) { return lockdep_is_held(&table[subsys_id].mutex); } EXPORT_SYMBOL_GPL(lockdep_nfnl_is_held); #endif int nfnetlink_subsys_register(const struct nfnetlink_subsystem *n) { nfnl_lock(n->subsys_id); if (table[n->subsys_id].subsys) { nfnl_unlock(n->subsys_id); return -EBUSY; } rcu_assign_pointer(table[n->subsys_id].subsys, n); nfnl_unlock(n->subsys_id); return 0; } EXPORT_SYMBOL_GPL(nfnetlink_subsys_register); int nfnetlink_subsys_unregister(const struct nfnetlink_subsystem *n) { nfnl_lock(n->subsys_id); table[n->subsys_id].subsys = NULL; nfnl_unlock(n->subsys_id); synchronize_rcu(); return 0; } EXPORT_SYMBOL_GPL(nfnetlink_subsys_unregister); static inline const struct nfnetlink_subsystem *nfnetlink_get_subsys(u16 type) { u8 subsys_id = NFNL_SUBSYS_ID(type); if (subsys_id >= NFNL_SUBSYS_COUNT) return NULL; return rcu_dereference(table[subsys_id].subsys); } static inline const struct nfnl_callback * nfnetlink_find_client(u16 type, const struct nfnetlink_subsystem *ss) { u8 cb_id = NFNL_MSG_TYPE(type); if (cb_id >= ss->cb_count) return NULL; return &ss->cb[cb_id]; } int nfnetlink_has_listeners(struct net *net, unsigned int group) { return netlink_has_listeners(net->nfnl, group); } EXPORT_SYMBOL_GPL(nfnetlink_has_listeners); int nfnetlink_send(struct sk_buff *skb, struct net *net, u32 portid, unsigned int group, int echo, gfp_t flags) { return nlmsg_notify(net->nfnl, skb, portid, group, echo, flags); } EXPORT_SYMBOL_GPL(nfnetlink_send); int nfnetlink_set_err(struct net *net, u32 portid, u32 group, int error) { return netlink_set_err(net->nfnl, portid, group, error); } EXPORT_SYMBOL_GPL(nfnetlink_set_err); int nfnetlink_unicast(struct sk_buff *skb, struct net *net, u32 portid, int flags) { return netlink_unicast(net->nfnl, skb, portid, flags); } EXPORT_SYMBOL_GPL(nfnetlink_unicast); /* Process one complete nfnetlink message. */ static int nfnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); const struct nfnl_callback *nc; const struct nfnetlink_subsystem *ss; int type, err; /* All the messages must at least contain nfgenmsg */ if (nlmsg_len(nlh) < sizeof(struct nfgenmsg)) return 0; type = nlh->nlmsg_type; replay: rcu_read_lock(); ss = nfnetlink_get_subsys(type); if (!ss) { #ifdef CONFIG_MODULES rcu_read_unlock(); request_module("nfnetlink-subsys-%d", NFNL_SUBSYS_ID(type)); rcu_read_lock(); ss = nfnetlink_get_subsys(type); if (!ss) #endif { rcu_read_unlock(); return -EINVAL; } } nc = nfnetlink_find_client(type, ss); if (!nc) { rcu_read_unlock(); return -EINVAL; } { int min_len = nlmsg_total_size(sizeof(struct nfgenmsg)); u8 cb_id = NFNL_MSG_TYPE(nlh->nlmsg_type); struct nlattr *cda[ss->cb[cb_id].attr_count + 1]; struct nlattr *attr = (void *)nlh + min_len; int attrlen = nlh->nlmsg_len - min_len; __u8 subsys_id = NFNL_SUBSYS_ID(type); err = nla_parse(cda, ss->cb[cb_id].attr_count, attr, attrlen, ss->cb[cb_id].policy, extack); if (err < 0) { rcu_read_unlock(); return err; } if (nc->call_rcu) { err = nc->call_rcu(net, net->nfnl, skb, nlh, (const struct nlattr **)cda, extack); rcu_read_unlock(); } else { rcu_read_unlock(); nfnl_lock(subsys_id); if (nfnl_dereference_protected(subsys_id) != ss || nfnetlink_find_client(type, ss) != nc) err = -EAGAIN; else if (nc->call) err = nc->call(net, net->nfnl, skb, nlh, (const struct nlattr **)cda, extack); else err = -EINVAL; nfnl_unlock(subsys_id); } if (err == -EAGAIN) goto replay; return err; } } struct nfnl_err { struct list_head head; struct nlmsghdr *nlh; int err; struct netlink_ext_ack extack; }; static int nfnl_err_add(struct list_head *list, struct nlmsghdr *nlh, int err, const struct netlink_ext_ack *extack) { struct nfnl_err *nfnl_err; nfnl_err = kmalloc(sizeof(struct nfnl_err), GFP_KERNEL); if (nfnl_err == NULL) return -ENOMEM; nfnl_err->nlh = nlh; nfnl_err->err = err; nfnl_err->extack = *extack; list_add_tail(&nfnl_err->head, list); return 0; } static void nfnl_err_del(struct nfnl_err *nfnl_err) { list_del(&nfnl_err->head); kfree(nfnl_err); } static void nfnl_err_reset(struct list_head *err_list) { struct nfnl_err *nfnl_err, *next; list_for_each_entry_safe(nfnl_err, next, err_list, head) nfnl_err_del(nfnl_err); } static void nfnl_err_deliver(struct list_head *err_list, struct sk_buff *skb) { struct nfnl_err *nfnl_err, *next; list_for_each_entry_safe(nfnl_err, next, err_list, head) { netlink_ack(skb, nfnl_err->nlh, nfnl_err->err, &nfnl_err->extack); nfnl_err_del(nfnl_err); } } enum { NFNL_BATCH_FAILURE = (1 << 0), NFNL_BATCH_DONE = (1 << 1), NFNL_BATCH_REPLAY = (1 << 2), }; static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh, u16 subsys_id, u32 genid) { struct sk_buff *oskb = skb; struct net *net = sock_net(skb->sk); const struct nfnetlink_subsystem *ss; const struct nfnl_callback *nc; struct netlink_ext_ack extack; LIST_HEAD(err_list); u32 status; int err; if (subsys_id >= NFNL_SUBSYS_COUNT) return netlink_ack(skb, nlh, -EINVAL, NULL); replay: status = 0; skb = netlink_skb_clone(oskb, GFP_KERNEL); if (!skb) return netlink_ack(oskb, nlh, -ENOMEM, NULL); nfnl_lock(subsys_id); ss = nfnl_dereference_protected(subsys_id); if (!ss) { #ifdef CONFIG_MODULES nfnl_unlock(subsys_id); request_module("nfnetlink-subsys-%d", subsys_id); nfnl_lock(subsys_id); ss = nfnl_dereference_protected(subsys_id); if (!ss) #endif { nfnl_unlock(subsys_id); netlink_ack(oskb, nlh, -EOPNOTSUPP, NULL); return kfree_skb(skb); } } if (!ss->commit || !ss->abort) { nfnl_unlock(subsys_id); netlink_ack(oskb, nlh, -EOPNOTSUPP, NULL); return kfree_skb(skb); } if (genid && ss->valid_genid && !ss->valid_genid(net, genid)) { nfnl_unlock(subsys_id); netlink_ack(oskb, nlh, -ERESTART, NULL); return kfree_skb(skb); } while (skb->len >= nlmsg_total_size(0)) { int msglen, type; memset(&extack, 0, sizeof(extack)); nlh = nlmsg_hdr(skb); err = 0; if (nlh->nlmsg_len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len || nlmsg_len(nlh) < sizeof(struct nfgenmsg)) { nfnl_err_reset(&err_list); status |= NFNL_BATCH_FAILURE; goto done; } /* Only requests are handled by the kernel */ if (!(nlh->nlmsg_flags & NLM_F_REQUEST)) { err = -EINVAL; goto ack; } type = nlh->nlmsg_type; if (type == NFNL_MSG_BATCH_BEGIN) { /* Malformed: Batch begin twice */ nfnl_err_reset(&err_list); status |= NFNL_BATCH_FAILURE; goto done; } else if (type == NFNL_MSG_BATCH_END) { status |= NFNL_BATCH_DONE; goto done; } else if (type < NLMSG_MIN_TYPE) { err = -EINVAL; goto ack; } /* We only accept a batch with messages for the same * subsystem. */ if (NFNL_SUBSYS_ID(type) != subsys_id) { err = -EINVAL; goto ack; } nc = nfnetlink_find_client(type, ss); if (!nc) { err = -EINVAL; goto ack; } { int min_len = nlmsg_total_size(sizeof(struct nfgenmsg)); u8 cb_id = NFNL_MSG_TYPE(nlh->nlmsg_type); struct nlattr *cda[ss->cb[cb_id].attr_count + 1]; struct nlattr *attr = (void *)nlh + min_len; int attrlen = nlh->nlmsg_len - min_len; err = nla_parse(cda, ss->cb[cb_id].attr_count, attr, attrlen, ss->cb[cb_id].policy, NULL); if (err < 0) goto ack; if (nc->call_batch) { err = nc->call_batch(net, net->nfnl, skb, nlh, (const struct nlattr **)cda, &extack); } /* The lock was released to autoload some module, we * have to abort and start from scratch using the * original skb. */ if (err == -EAGAIN) { status |= NFNL_BATCH_REPLAY; goto next; } } ack: if (nlh->nlmsg_flags & NLM_F_ACK || err) { /* Errors are delivered once the full batch has been * processed, this avoids that the same error is * reported several times when replaying the batch. */ if (nfnl_err_add(&err_list, nlh, err, &extack) < 0) { /* We failed to enqueue an error, reset the * list of errors and send OOM to userspace * pointing to the batch header. */ nfnl_err_reset(&err_list); netlink_ack(oskb, nlmsg_hdr(oskb), -ENOMEM, NULL); status |= NFNL_BATCH_FAILURE; goto done; } /* We don't stop processing the batch on errors, thus, * userspace gets all the errors that the batch * triggers. */ if (err) status |= NFNL_BATCH_FAILURE; } next: msglen = NLMSG_ALIGN(nlh->nlmsg_len); if (msglen > skb->len) msglen = skb->len; skb_pull(skb, msglen); } done: if (status & NFNL_BATCH_REPLAY) { ss->abort(net, oskb); nfnl_err_reset(&err_list); nfnl_unlock(subsys_id); kfree_skb(skb); goto replay; } else if (status == NFNL_BATCH_DONE) { ss->commit(net, oskb); } else { ss->abort(net, oskb); } nfnl_err_deliver(&err_list, oskb); nfnl_unlock(subsys_id); kfree_skb(skb); } static const struct nla_policy nfnl_batch_policy[NFNL_BATCH_MAX + 1] = { [NFNL_BATCH_GENID] = { .type = NLA_U32 }, }; static void nfnetlink_rcv_skb_batch(struct sk_buff *skb, struct nlmsghdr *nlh) { int min_len = nlmsg_total_size(sizeof(struct nfgenmsg)); struct nlattr *attr = (void *)nlh + min_len; struct nlattr *cda[NFNL_BATCH_MAX + 1]; int attrlen = nlh->nlmsg_len - min_len; struct nfgenmsg *nfgenmsg; int msglen, err; u32 gen_id = 0; u16 res_id; msglen = NLMSG_ALIGN(nlh->nlmsg_len); if (msglen > skb->len) msglen = skb->len; if (skb->len < NLMSG_HDRLEN + sizeof(struct nfgenmsg)) return; err = nla_parse(cda, NFNL_BATCH_MAX, attr, attrlen, nfnl_batch_policy, NULL); if (err < 0) { netlink_ack(skb, nlh, err, NULL); return; } if (cda[NFNL_BATCH_GENID]) gen_id = ntohl(nla_get_be32(cda[NFNL_BATCH_GENID])); nfgenmsg = nlmsg_data(nlh); skb_pull(skb, msglen); /* Work around old nft using host byte order */ if (nfgenmsg->res_id == NFNL_SUBSYS_NFTABLES) res_id = NFNL_SUBSYS_NFTABLES; else res_id = ntohs(nfgenmsg->res_id); nfnetlink_rcv_batch(skb, nlh, res_id, gen_id); } static void nfnetlink_rcv(struct sk_buff *skb) { struct nlmsghdr *nlh = nlmsg_hdr(skb); if (skb->len < NLMSG_HDRLEN || nlh->nlmsg_len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len) return; if (!netlink_net_capable(skb, CAP_NET_ADMIN)) { netlink_ack(skb, nlh, -EPERM, NULL); return; } if (nlh->nlmsg_type == NFNL_MSG_BATCH_BEGIN) nfnetlink_rcv_skb_batch(skb, nlh); else netlink_rcv_skb(skb, nfnetlink_rcv_msg); } #ifdef CONFIG_MODULES static int nfnetlink_bind(struct net *net, int group) { const struct nfnetlink_subsystem *ss; int type; if (group <= NFNLGRP_NONE || group > NFNLGRP_MAX) return 0; type = nfnl_group2type[group]; rcu_read_lock(); ss = nfnetlink_get_subsys(type << 8); rcu_read_unlock(); if (!ss) request_module_nowait("nfnetlink-subsys-%d", type); return 0; } #endif static int __net_init nfnetlink_net_init(struct net *net) { struct sock *nfnl; struct netlink_kernel_cfg cfg = { .groups = NFNLGRP_MAX, .input = nfnetlink_rcv, #ifdef CONFIG_MODULES .bind = nfnetlink_bind, #endif }; nfnl = netlink_kernel_create(net, NETLINK_NETFILTER, &cfg); if (!nfnl) return -ENOMEM; net->nfnl_stash = nfnl; rcu_assign_pointer(net->nfnl, nfnl); return 0; } static void __net_exit nfnetlink_net_exit_batch(struct list_head *net_exit_list) { struct net *net; list_for_each_entry(net, net_exit_list, exit_list) RCU_INIT_POINTER(net->nfnl, NULL); synchronize_net(); list_for_each_entry(net, net_exit_list, exit_list) netlink_kernel_release(net->nfnl_stash); } static struct pernet_operations nfnetlink_net_ops = { .init = nfnetlink_net_init, .exit_batch = nfnetlink_net_exit_batch, }; static int __init nfnetlink_init(void) { int i; for (i = NFNLGRP_NONE + 1; i <= NFNLGRP_MAX; i++) BUG_ON(nfnl_group2type[i] == NFNL_SUBSYS_NONE); for (i=0; i<NFNL_SUBSYS_COUNT; i++) mutex_init(&table[i].mutex); pr_info("Netfilter messages via NETLINK v%s.\n", nfversion); return register_pernet_subsys(&nfnetlink_net_ops); } static void __exit nfnetlink_exit(void) { pr_info("Removing netfilter NETLINK layer.\n"); unregister_pernet_subsys(&nfnetlink_net_ops); } module_init(nfnetlink_init); module_exit(nfnetlink_exit); |
| 20 20 20 20 20 20 20 89 89 1665 1666 1665 29 15 33 33 33 7 33 32 33 20 20 20 20 20 90 19 19 36 43 43 7 43 43 44 43 43 21 21 1 8 8 8 43 21 21 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 | /* * net/switchdev/switchdev.c - Switch device API * Copyright (c) 2014-2015 Jiri Pirko <jiri@resnulli.us> * Copyright (c) 2014-2015 Scott Feldman <sfeldma@gmail.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. */ #include <linux/kernel.h> #include <linux/types.h> #include <linux/init.h> #include <linux/mutex.h> #include <linux/notifier.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/if_bridge.h> #include <linux/list.h> #include <linux/workqueue.h> #include <linux/if_vlan.h> #include <linux/rtnetlink.h> #include <net/switchdev.h> /** * switchdev_trans_item_enqueue - Enqueue data item to transaction queue * * @trans: transaction * @data: pointer to data being queued * @destructor: data destructor * @tritem: transaction item being queued * * Enqeueue data item to transaction queue. tritem is typically placed in * cointainter pointed at by data pointer. Destructor is called on * transaction abort and after successful commit phase in case * the caller did not dequeue the item before. */ void switchdev_trans_item_enqueue(struct switchdev_trans *trans, void *data, void (*destructor)(void const *), struct switchdev_trans_item *tritem) { tritem->data = data; tritem->destructor = destructor; list_add_tail(&tritem->list, &trans->item_list); } EXPORT_SYMBOL_GPL(switchdev_trans_item_enqueue); static struct switchdev_trans_item * __switchdev_trans_item_dequeue(struct switchdev_trans *trans) { struct switchdev_trans_item *tritem; if (list_empty(&trans->item_list)) return NULL; tritem = list_first_entry(&trans->item_list, struct switchdev_trans_item, list); list_del(&tritem->list); return tritem; } /** * switchdev_trans_item_dequeue - Dequeue data item from transaction queue * * @trans: transaction */ void *switchdev_trans_item_dequeue(struct switchdev_trans *trans) { struct switchdev_trans_item *tritem; tritem = __switchdev_trans_item_dequeue(trans); BUG_ON(!tritem); return tritem->data; } EXPORT_SYMBOL_GPL(switchdev_trans_item_dequeue); static void switchdev_trans_init(struct switchdev_trans *trans) { INIT_LIST_HEAD(&trans->item_list); } static void switchdev_trans_items_destroy(struct switchdev_trans *trans) { struct switchdev_trans_item *tritem; while ((tritem = __switchdev_trans_item_dequeue(trans))) tritem->destructor(tritem->data); } static void switchdev_trans_items_warn_destroy(struct net_device *dev, struct switchdev_trans *trans) { WARN(!list_empty(&trans->item_list), "%s: transaction item queue is not empty.\n", dev->name); switchdev_trans_items_destroy(trans); } static LIST_HEAD(deferred); static DEFINE_SPINLOCK(deferred_lock); typedef void switchdev_deferred_func_t(struct net_device *dev, const void *data); struct switchdev_deferred_item { struct list_head list; struct net_device *dev; switchdev_deferred_func_t *func; unsigned long data[0]; }; static struct switchdev_deferred_item *switchdev_deferred_dequeue(void) { struct switchdev_deferred_item *dfitem; spin_lock_bh(&deferred_lock); if (list_empty(&deferred)) { dfitem = NULL; goto unlock; } dfitem = list_first_entry(&deferred, struct switchdev_deferred_item, list); list_del(&dfitem->list); unlock: spin_unlock_bh(&deferred_lock); return dfitem; } /** * switchdev_deferred_process - Process ops in deferred queue * * Called to flush the ops currently queued in deferred ops queue. * rtnl_lock must be held. */ void switchdev_deferred_process(void) { struct switchdev_deferred_item *dfitem; ASSERT_RTNL(); while ((dfitem = switchdev_deferred_dequeue())) { dfitem->func(dfitem->dev, dfitem->data); dev_put(dfitem->dev); kfree(dfitem); } } EXPORT_SYMBOL_GPL(switchdev_deferred_process); static void switchdev_deferred_process_work(struct work_struct *work) { rtnl_lock(); switchdev_deferred_process(); rtnl_unlock(); } static DECLARE_WORK(deferred_process_work, switchdev_deferred_process_work); static int switchdev_deferred_enqueue(struct net_device *dev, const void *data, size_t data_len, switchdev_deferred_func_t *func) { struct switchdev_deferred_item *dfitem; dfitem = kmalloc(sizeof(*dfitem) + data_len, GFP_ATOMIC); if (!dfitem) return -ENOMEM; dfitem->dev = dev; dfitem->func = func; memcpy(dfitem->data, data, data_len); dev_hold(dev); spin_lock_bh(&deferred_lock); list_add_tail(&dfitem->list, &deferred); spin_unlock_bh(&deferred_lock); schedule_work(&deferred_process_work); return 0; } /** * switchdev_port_attr_get - Get port attribute * * @dev: port device * @attr: attribute to get */ int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr) { const struct switchdev_ops *ops = dev->switchdev_ops; struct net_device *lower_dev; struct list_head *iter; struct switchdev_attr first = { .id = SWITCHDEV_ATTR_ID_UNDEFINED }; int err = -EOPNOTSUPP; if (ops && ops->switchdev_port_attr_get) return ops->switchdev_port_attr_get(dev, attr); if (attr->flags & SWITCHDEV_F_NO_RECURSE) return err; /* Switch device port(s) may be stacked under * bond/team/vlan dev, so recurse down to get attr on * each port. Return -ENODATA if attr values don't * compare across ports. */ netdev_for_each_lower_dev(dev, lower_dev, iter) { err = switchdev_port_attr_get(lower_dev, attr); if (err) break; if (first.id == SWITCHDEV_ATTR_ID_UNDEFINED) first = *attr; else if (memcmp(&first, attr, sizeof(*attr))) return -ENODATA; } return err; } EXPORT_SYMBOL_GPL(switchdev_port_attr_get); static int __switchdev_port_attr_set(struct net_device *dev, const struct switchdev_attr *attr, struct switchdev_trans *trans) { const struct switchdev_ops *ops = dev->switchdev_ops; struct net_device *lower_dev; struct list_head *iter; int err = -EOPNOTSUPP; if (ops && ops->switchdev_port_attr_set) { err = ops->switchdev_port_attr_set(dev, attr, trans); goto done; } if (attr->flags & SWITCHDEV_F_NO_RECURSE) goto done; /* Switch device port(s) may be stacked under * bond/team/vlan dev, so recurse down to set attr on * each port. */ netdev_for_each_lower_dev(dev, lower_dev, iter) { err = __switchdev_port_attr_set(lower_dev, attr, trans); if (err) break; } done: if (err == -EOPNOTSUPP && attr->flags & SWITCHDEV_F_SKIP_EOPNOTSUPP) err = 0; return err; } static int switchdev_port_attr_set_now(struct net_device *dev, const struct switchdev_attr *attr) { struct switchdev_trans trans; int err; switchdev_trans_init(&trans); /* Phase I: prepare for attr set. Driver/device should fail * here if there are going to be issues in the commit phase, * such as lack of resources or support. The driver/device * should reserve resources needed for the commit phase here, * but should not commit the attr. */ trans.ph_prepare = true; err = __switchdev_port_attr_set(dev, attr, &trans); if (err) { /* Prepare phase failed: abort the transaction. Any * resources reserved in the prepare phase are * released. */ if (err != -EOPNOTSUPP) switchdev_trans_items_destroy(&trans); return err; } /* Phase II: commit attr set. This cannot fail as a fault * of driver/device. If it does, it's a bug in the driver/device * because the driver said everythings was OK in phase I. */ trans.ph_prepare = false; err = __switchdev_port_attr_set(dev, attr, &trans); WARN(err, "%s: Commit of attribute (id=%d) failed.\n", dev->name, attr->id); switchdev_trans_items_warn_destroy(dev, &trans); return err; } static void switchdev_port_attr_set_deferred(struct net_device *dev, const void *data) { const struct switchdev_attr *attr = data; int err; err = switchdev_port_attr_set_now(dev, attr); if (err && err != -EOPNOTSUPP) netdev_err(dev, "failed (err=%d) to set attribute (id=%d)\n", err, attr->id); if (attr->complete) attr->complete(dev, err, attr->complete_priv); } static int switchdev_port_attr_set_defer(struct net_device *dev, const struct switchdev_attr *attr) { return switchdev_deferred_enqueue(dev, attr, sizeof(*attr), switchdev_port_attr_set_deferred); } /** * switchdev_port_attr_set - Set port attribute * * @dev: port device * @attr: attribute to set * * Use a 2-phase prepare-commit transaction model to ensure * system is not left in a partially updated state due to * failure from driver/device. * * rtnl_lock must be held and must not be in atomic section, * in case SWITCHDEV_F_DEFER flag is not set. */ int switchdev_port_attr_set(struct net_device *dev, const struct switchdev_attr *attr) { if (attr->flags & SWITCHDEV_F_DEFER) return switchdev_port_attr_set_defer(dev, attr); ASSERT_RTNL(); return switchdev_port_attr_set_now(dev, attr); } EXPORT_SYMBOL_GPL(switchdev_port_attr_set); static size_t switchdev_obj_size(const struct switchdev_obj *obj) { switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_VLAN: return sizeof(struct switchdev_obj_port_vlan); case SWITCHDEV_OBJ_ID_PORT_MDB: return sizeof(struct switchdev_obj_port_mdb); default: BUG(); } return 0; } static int __switchdev_port_obj_add(struct net_device *dev, const struct switchdev_obj *obj, struct switchdev_trans *trans) { const struct switchdev_ops *ops = dev->switchdev_ops; struct net_device *lower_dev; struct list_head *iter; int err = -EOPNOTSUPP; if (ops && ops->switchdev_port_obj_add) return ops->switchdev_port_obj_add(dev, obj, trans); /* Switch device port(s) may be stacked under * bond/team/vlan dev, so recurse down to add object on * each port. */ netdev_for_each_lower_dev(dev, lower_dev, iter) { err = __switchdev_port_obj_add(lower_dev, obj, trans); if (err) break; } return err; } static int switchdev_port_obj_add_now(struct net_device *dev, const struct switchdev_obj *obj) { struct switchdev_trans trans; int err; ASSERT_RTNL(); switchdev_trans_init(&trans); /* Phase I: prepare for obj add. Driver/device should fail * here if there are going to be issues in the commit phase, * such as lack of resources or support. The driver/device * should reserve resources needed for the commit phase here, * but should not commit the obj. */ trans.ph_prepare = true; err = __switchdev_port_obj_add(dev, obj, &trans); if (err) { /* Prepare phase failed: abort the transaction. Any * resources reserved in the prepare phase are * released. */ if (err != -EOPNOTSUPP) switchdev_trans_items_destroy(&trans); return err; } /* Phase II: commit obj add. This cannot fail as a fault * of driver/device. If it does, it's a bug in the driver/device * because the driver said everythings was OK in phase I. */ trans.ph_prepare = false; err = __switchdev_port_obj_add(dev, obj, &trans); WARN(err, "%s: Commit of object (id=%d) failed.\n", dev->name, obj->id); switchdev_trans_items_warn_destroy(dev, &trans); return err; } static void switchdev_port_obj_add_deferred(struct net_device *dev, const void *data) { const struct switchdev_obj *obj = data; int err; err = switchdev_port_obj_add_now(dev, obj); if (err && err != -EOPNOTSUPP) netdev_err(dev, "failed (err=%d) to add object (id=%d)\n", err, obj->id); if (obj->complete) obj->complete(dev, err, obj->complete_priv); } static int switchdev_port_obj_add_defer(struct net_device *dev, const struct switchdev_obj *obj) { return switchdev_deferred_enqueue(dev, obj, switchdev_obj_size(obj), switchdev_port_obj_add_deferred); } /** * switchdev_port_obj_add - Add port object * * @dev: port device * @id: object ID * @obj: object to add * * Use a 2-phase prepare-commit transaction model to ensure * system is not left in a partially updated state due to * failure from driver/device. * * rtnl_lock must be held and must not be in atomic section, * in case SWITCHDEV_F_DEFER flag is not set. */ int switchdev_port_obj_add(struct net_device *dev, const struct switchdev_obj *obj) { if (obj->flags & SWITCHDEV_F_DEFER) return switchdev_port_obj_add_defer(dev, obj); ASSERT_RTNL(); return switchdev_port_obj_add_now(dev, obj); } EXPORT_SYMBOL_GPL(switchdev_port_obj_add); static int switchdev_port_obj_del_now(struct net_device *dev, const struct switchdev_obj *obj) { const struct switchdev_ops *ops = dev->switchdev_ops; struct net_device *lower_dev; struct list_head *iter; int err = -EOPNOTSUPP; if (ops && ops->switchdev_port_obj_del) return ops->switchdev_port_obj_del(dev, obj); /* Switch device port(s) may be stacked under * bond/team/vlan dev, so recurse down to delete object on * each port. */ netdev_for_each_lower_dev(dev, lower_dev, iter) { err = switchdev_port_obj_del_now(lower_dev, obj); if (err) break; } return err; } static void switchdev_port_obj_del_deferred(struct net_device *dev, const void *data) { const struct switchdev_obj *obj = data; int err; err = switchdev_port_obj_del_now(dev, obj); if (err && err != -EOPNOTSUPP) netdev_err(dev, "failed (err=%d) to del object (id=%d)\n", err, obj->id); if (obj->complete) obj->complete(dev, err, obj->complete_priv); } static int switchdev_port_obj_del_defer(struct net_device *dev, const struct switchdev_obj *obj) { return switchdev_deferred_enqueue(dev, obj, switchdev_obj_size(obj), switchdev_port_obj_del_deferred); } /** * switchdev_port_obj_del - Delete port object * * @dev: port device * @id: object ID * @obj: object to delete * * rtnl_lock must be held and must not be in atomic section, * in case SWITCHDEV_F_DEFER flag is not set. */ int switchdev_port_obj_del(struct net_device *dev, const struct switchdev_obj *obj) { if (obj->flags & SWITCHDEV_F_DEFER) return switchdev_port_obj_del_defer(dev, obj); ASSERT_RTNL(); return switchdev_port_obj_del_now(dev, obj); } EXPORT_SYMBOL_GPL(switchdev_port_obj_del); static ATOMIC_NOTIFIER_HEAD(switchdev_notif_chain); /** * register_switchdev_notifier - Register notifier * @nb: notifier_block * * Register switch device notifier. */ int register_switchdev_notifier(struct notifier_block *nb) { return atomic_notifier_chain_register(&switchdev_notif_chain, nb); } EXPORT_SYMBOL_GPL(register_switchdev_notifier); /** * unregister_switchdev_notifier - Unregister notifier * @nb: notifier_block * * Unregister switch device notifier. */ int unregister_switchdev_notifier(struct notifier_block *nb) { return atomic_notifier_chain_unregister(&switchdev_notif_chain, nb); } EXPORT_SYMBOL_GPL(unregister_switchdev_notifier); /** * call_switchdev_notifiers - Call notifiers * @val: value passed unmodified to notifier function * @dev: port device * @info: notifier information data * * Call all network notifier blocks. */ int call_switchdev_notifiers(unsigned long val, struct net_device *dev, struct switchdev_notifier_info *info) { info->dev = dev; return atomic_notifier_call_chain(&switchdev_notif_chain, val, info); } EXPORT_SYMBOL_GPL(call_switchdev_notifiers); bool switchdev_port_same_parent_id(struct net_device *a, struct net_device *b) { struct switchdev_attr a_attr = { .orig_dev = a, .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, }; struct switchdev_attr b_attr = { .orig_dev = b, .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, }; if (switchdev_port_attr_get(a, &a_attr) || switchdev_port_attr_get(b, &b_attr)) return false; return netdev_phys_item_id_same(&a_attr.u.ppid, &b_attr.u.ppid); } EXPORT_SYMBOL_GPL(switchdev_port_same_parent_id); |
| 613 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_DEBUGREG_H #define _ASM_X86_DEBUGREG_H #include <linux/bug.h> #include <uapi/asm/debugreg.h> DECLARE_PER_CPU(unsigned long, cpu_dr7); #ifndef CONFIG_PARAVIRT /* * These special macros can be used to get or set a debugging register */ #define get_debugreg(var, register) \ (var) = native_get_debugreg(register) #define set_debugreg(value, register) \ native_set_debugreg(register, value) #endif static inline unsigned long native_get_debugreg(int regno) { unsigned long val = 0; /* Damn you, gcc! */ switch (regno) { case 0: asm("mov %%db0, %0" :"=r" (val)); break; case 1: asm("mov %%db1, %0" :"=r" (val)); break; case 2: asm("mov %%db2, %0" :"=r" (val)); break; case 3: asm("mov %%db3, %0" :"=r" (val)); break; case 6: asm("mov %%db6, %0" :"=r" (val)); break; case 7: asm("mov %%db7, %0" :"=r" (val)); break; default: BUG(); } return val; } static inline void native_set_debugreg(int regno, unsigned long value) { switch (regno) { case 0: asm("mov %0, %%db0" ::"r" (value)); break; case 1: asm("mov %0, %%db1" ::"r" (value)); break; case 2: asm("mov %0, %%db2" ::"r" (value)); break; case 3: asm("mov %0, %%db3" ::"r" (value)); break; case 6: asm("mov %0, %%db6" ::"r" (value)); break; case 7: asm("mov %0, %%db7" ::"r" (value)); break; default: BUG(); } } static inline void hw_breakpoint_disable(void) { /* Zero the control register for HW Breakpoint */ set_debugreg(0UL, 7); /* Zero-out the individual HW breakpoint address registers */ set_debugreg(0UL, 0); set_debugreg(0UL, 1); set_debugreg(0UL, 2); set_debugreg(0UL, 3); } static inline int hw_breakpoint_active(void) { return __this_cpu_read(cpu_dr7) & DR_GLOBAL_ENABLE_MASK; } extern void aout_dump_debugregs(struct user *dump); extern void hw_breakpoint_restore(void); #ifdef CONFIG_X86_64 DECLARE_PER_CPU(int, debug_stack_usage); static inline void debug_stack_usage_inc(void) { __this_cpu_inc(debug_stack_usage); } static inline void debug_stack_usage_dec(void) { __this_cpu_dec(debug_stack_usage); } int is_debug_stack(unsigned long addr); void debug_stack_set_zero(void); void debug_stack_reset(void); #else /* !X86_64 */ static inline int is_debug_stack(unsigned long addr) { return 0; } static inline void debug_stack_set_zero(void) { } static inline void debug_stack_reset(void) { } static inline void debug_stack_usage_inc(void) { } static inline void debug_stack_usage_dec(void) { } #endif /* X86_64 */ #ifdef CONFIG_CPU_SUP_AMD extern void set_dr_addr_mask(unsigned long mask, int dr); #else static inline void set_dr_addr_mask(unsigned long mask, int dr) { } #endif #endif /* _ASM_X86_DEBUGREG_H */ |
| 29 7 29 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE * Copyright 2003 Andi Kleen, SuSE Labs. * * Modified for x86 32 bit architecture by * Stefani Seibold <stefani@seibold.net> * sponsored by Rohde & Schwarz GmbH & Co. KG Munich/Germany * * Thanks to hpa@transmeta.com for some useful hint. * Special thanks to Ingo Molnar for his early experience with * a different vsyscall implementation for Linux/IA32 and for the name. * */ #include <linux/timekeeper_internal.h> #include <asm/vgtod.h> #include <asm/vvar.h> int vclocks_used __read_mostly; DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data); void update_vsyscall_tz(void) { vsyscall_gtod_data.tz_minuteswest = sys_tz.tz_minuteswest; vsyscall_gtod_data.tz_dsttime = sys_tz.tz_dsttime; } void update_vsyscall(struct timekeeper *tk) { int vclock_mode = tk->tkr_mono.clock->archdata.vclock_mode; struct vsyscall_gtod_data *vdata = &vsyscall_gtod_data; /* Mark the new vclock used. */ BUILD_BUG_ON(VCLOCK_MAX >= 32); WRITE_ONCE(vclocks_used, READ_ONCE(vclocks_used) | (1 << vclock_mode)); gtod_write_begin(vdata); /* copy vsyscall data */ vdata->vclock_mode = vclock_mode; vdata->cycle_last = tk->tkr_mono.cycle_last; vdata->mask = tk->tkr_mono.mask; vdata->mult = tk->tkr_mono.mult; vdata->shift = tk->tkr_mono.shift; vdata->wall_time_sec = tk->xtime_sec; vdata->wall_time_snsec = tk->tkr_mono.xtime_nsec; vdata->monotonic_time_sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec; vdata->monotonic_time_snsec = tk->tkr_mono.xtime_nsec + ((u64)tk->wall_to_monotonic.tv_nsec << tk->tkr_mono.shift); while (vdata->monotonic_time_snsec >= (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) { vdata->monotonic_time_snsec -= ((u64)NSEC_PER_SEC) << tk->tkr_mono.shift; vdata->monotonic_time_sec++; } vdata->wall_time_coarse_sec = tk->xtime_sec; vdata->wall_time_coarse_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); vdata->monotonic_time_coarse_sec = vdata->wall_time_coarse_sec + tk->wall_to_monotonic.tv_sec; vdata->monotonic_time_coarse_nsec = vdata->wall_time_coarse_nsec + tk->wall_to_monotonic.tv_nsec; while (vdata->monotonic_time_coarse_nsec >= NSEC_PER_SEC) { vdata->monotonic_time_coarse_nsec -= NSEC_PER_SEC; vdata->monotonic_time_coarse_sec++; } gtod_write_end(vdata); } |
| 12 12 12 12 12 12 12 12 12 11 12 8 8 8 8 8 8 8 8 8 8 8 8 8 58 58 58 58 10 10 58 10 50 50 50 50 50 49 49 49 7 50 50 50 63 63 63 63 63 63 63 63 63 63 63 63 63 63 63 10 10 10 10 87 87 1 86 1 63 85 37 38 55 87 13 13 7 13 13 13 9 13 13 13 6 6 6 1 1 4 5 5 6 6 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 | /* * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc. * All Rights Reserved. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License as * published by the Free Software Foundation. * * This program is distributed in the hope that it would be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License * along with this program; if not, write the Free Software Foundation, * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA */ #include "xfs.h" #include "xfs_fs.h" #include "xfs_format.h" #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" #include "xfs_da_format.h" #include "xfs_da_btree.h" #include "xfs_inode.h" #include "xfs_trans.h" #include "xfs_inode_item.h" #include "xfs_error.h" #include "xfs_dir2.h" #include "xfs_dir2_priv.h" #include "xfs_trace.h" /* * Prototypes for internal functions. */ static void xfs_dir2_sf_addname_easy(xfs_da_args_t *args, xfs_dir2_sf_entry_t *sfep, xfs_dir2_data_aoff_t offset, int new_isize); static void xfs_dir2_sf_addname_hard(xfs_da_args_t *args, int objchange, int new_isize); static int xfs_dir2_sf_addname_pick(xfs_da_args_t *args, int objchange, xfs_dir2_sf_entry_t **sfepp, xfs_dir2_data_aoff_t *offsetp); #ifdef DEBUG static void xfs_dir2_sf_check(xfs_da_args_t *args); #else #define xfs_dir2_sf_check(args) #endif /* DEBUG */ static void xfs_dir2_sf_toino4(xfs_da_args_t *args); static void xfs_dir2_sf_toino8(xfs_da_args_t *args); /* * Given a block directory (dp/block), calculate its size as a shortform (sf) * directory and a header for the sf directory, if it will fit it the * space currently present in the inode. If it won't fit, the output * size is too big (but not accurate). */ int /* size for sf form */ xfs_dir2_block_sfsize( xfs_inode_t *dp, /* incore inode pointer */ xfs_dir2_data_hdr_t *hdr, /* block directory data */ xfs_dir2_sf_hdr_t *sfhp) /* output: header for sf form */ { xfs_dir2_dataptr_t addr; /* data entry address */ xfs_dir2_leaf_entry_t *blp; /* leaf area of the block */ xfs_dir2_block_tail_t *btp; /* tail area of the block */ int count; /* shortform entry count */ xfs_dir2_data_entry_t *dep; /* data entry in the block */ int i; /* block entry index */ int i8count; /* count of big-inode entries */ int isdot; /* entry is "." */ int isdotdot; /* entry is ".." */ xfs_mount_t *mp; /* mount structure pointer */ int namelen; /* total name bytes */ xfs_ino_t parent = 0; /* parent inode number */ int size=0; /* total computed size */ int has_ftype; struct xfs_da_geometry *geo; mp = dp->i_mount; geo = mp->m_dir_geo; /* * if there is a filetype field, add the extra byte to the namelen * for each entry that we see. */ has_ftype = xfs_sb_version_hasftype(&mp->m_sb) ? 1 : 0; count = i8count = namelen = 0; btp = xfs_dir2_block_tail_p(geo, hdr); blp = xfs_dir2_block_leaf_p(btp); /* * Iterate over the block's data entries by using the leaf pointers. */ for (i = 0; i < be32_to_cpu(btp->count); i++) { if ((addr = be32_to_cpu(blp[i].address)) == XFS_DIR2_NULL_DATAPTR) continue; /* * Calculate the pointer to the entry at hand. */ dep = (xfs_dir2_data_entry_t *)((char *)hdr + xfs_dir2_dataptr_to_off(geo, addr)); /* * Detect . and .., so we can special-case them. * . is not included in sf directories. * .. is included by just the parent inode number. */ isdot = dep->namelen == 1 && dep->name[0] == '.'; isdotdot = dep->namelen == 2 && dep->name[0] == '.' && dep->name[1] == '.'; if (!isdot) i8count += be64_to_cpu(dep->inumber) > XFS_DIR2_MAX_SHORT_INUM; /* take into account the file type field */ if (!isdot && !isdotdot) { count++; namelen += dep->namelen + has_ftype; } else if (isdotdot) parent = be64_to_cpu(dep->inumber); /* * Calculate the new size, see if we should give up yet. */ size = xfs_dir2_sf_hdr_size(i8count) + /* header */ count * 3 * sizeof(u8) + /* namelen + offset */ namelen + /* name */ (i8count ? /* inumber */ count * XFS_INO64_SIZE : count * XFS_INO32_SIZE); if (size > XFS_IFORK_DSIZE(dp)) return size; /* size value is a failure */ } /* * Create the output header, if it worked. */ sfhp->count = count; sfhp->i8count = i8count; dp->d_ops->sf_put_parent_ino(sfhp, parent); return size; } /* * Convert a block format directory to shortform. * Caller has already checked that it will fit, and built us a header. */ int /* error */ xfs_dir2_block_to_sf( xfs_da_args_t *args, /* operation arguments */ struct xfs_buf *bp, int size, /* shortform directory size */ xfs_dir2_sf_hdr_t *sfhp) /* shortform directory hdr */ { xfs_dir2_data_hdr_t *hdr; /* block header */ xfs_dir2_block_tail_t *btp; /* block tail pointer */ xfs_dir2_data_entry_t *dep; /* data entry pointer */ xfs_inode_t *dp; /* incore directory inode */ xfs_dir2_data_unused_t *dup; /* unused data pointer */ char *endptr; /* end of data entries */ int error; /* error return value */ int logflags; /* inode logging flags */ xfs_mount_t *mp; /* filesystem mount point */ char *ptr; /* current data pointer */ xfs_dir2_sf_entry_t *sfep; /* shortform entry */ xfs_dir2_sf_hdr_t *sfp; /* shortform directory header */ xfs_dir2_sf_hdr_t *dst; /* temporary data buffer */ trace_xfs_dir2_block_to_sf(args); dp = args->dp; mp = dp->i_mount; /* * allocate a temporary destination buffer the size of the inode * to format the data into. Once we have formatted the data, we * can free the block and copy the formatted data into the inode literal * area. */ dst = kmem_alloc(mp->m_sb.sb_inodesize, KM_SLEEP); hdr = bp->b_addr; /* * Copy the header into the newly allocate local space. */ sfp = (xfs_dir2_sf_hdr_t *)dst; memcpy(sfp, sfhp, xfs_dir2_sf_hdr_size(sfhp->i8count)); /* * Set up to loop over the block's entries. */ btp = xfs_dir2_block_tail_p(args->geo, hdr); ptr = (char *)dp->d_ops->data_entry_p(hdr); endptr = (char *)xfs_dir2_block_leaf_p(btp); sfep = xfs_dir2_sf_firstentry(sfp); /* * Loop over the active and unused entries. * Stop when we reach the leaf/tail portion of the block. */ while (ptr < endptr) { /* * If it's unused, just skip over it. */ dup = (xfs_dir2_data_unused_t *)ptr; if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) { ptr += be16_to_cpu(dup->length); continue; } dep = (xfs_dir2_data_entry_t *)ptr; /* * Skip . */ if (dep->namelen == 1 && dep->name[0] == '.') ASSERT(be64_to_cpu(dep->inumber) == dp->i_ino); /* * Skip .., but make sure the inode number is right. */ else if (dep->namelen == 2 && dep->name[0] == '.' && dep->name[1] == '.') ASSERT(be64_to_cpu(dep->inumber) == dp->d_ops->sf_get_parent_ino(sfp)); /* * Normal entry, copy it into shortform. */ else { sfep->namelen = dep->namelen; xfs_dir2_sf_put_offset(sfep, (xfs_dir2_data_aoff_t) ((char *)dep - (char *)hdr)); memcpy(sfep->name, dep->name, dep->namelen); dp->d_ops->sf_put_ino(sfp, sfep, be64_to_cpu(dep->inumber)); dp->d_ops->sf_put_ftype(sfep, dp->d_ops->data_get_ftype(dep)); sfep = dp->d_ops->sf_nextentry(sfp, sfep); } ptr += dp->d_ops->data_entsize(dep->namelen); } ASSERT((char *)sfep - (char *)sfp == size); /* now we are done with the block, we can shrink the inode */ logflags = XFS_ILOG_CORE; error = xfs_dir2_shrink_inode(args, args->geo->datablk, bp); if (error) { ASSERT(error != -ENOSPC); goto out; } /* * The buffer is now unconditionally gone, whether * xfs_dir2_shrink_inode worked or not. * * Convert the inode to local format and copy the data in. */ ASSERT(dp->i_df.if_bytes == 0); xfs_init_local_fork(dp, XFS_DATA_FORK, dst, size); dp->i_d.di_format = XFS_DINODE_FMT_LOCAL; dp->i_d.di_size = size; logflags |= XFS_ILOG_DDATA; xfs_dir2_sf_check(args); out: xfs_trans_log_inode(args->trans, dp, logflags); kmem_free(dst); return error; } /* * Add a name to a shortform directory. * There are two algorithms, "easy" and "hard" which we decide on * before changing anything. * Convert to block form if necessary, if the new entry won't fit. */ int /* error */ xfs_dir2_sf_addname( xfs_da_args_t *args) /* operation arguments */ { xfs_inode_t *dp; /* incore directory inode */ int error; /* error return value */ int incr_isize; /* total change in size */ int new_isize; /* di_size after adding name */ int objchange; /* changing to 8-byte inodes */ xfs_dir2_data_aoff_t offset = 0; /* offset for new entry */ int pick; /* which algorithm to use */ xfs_dir2_sf_hdr_t *sfp; /* shortform structure */ xfs_dir2_sf_entry_t *sfep = NULL; /* shortform entry */ trace_xfs_dir2_sf_addname(args); ASSERT(xfs_dir2_sf_lookup(args) == -ENOENT); dp = args->dp; ASSERT(dp->i_df.if_flags & XFS_IFINLINE); /* * Make sure the shortform value has some of its header. */ if (dp->i_d.di_size < offsetof(xfs_dir2_sf_hdr_t, parent)) { ASSERT(XFS_FORCED_SHUTDOWN(dp->i_mount)); return -EIO; } ASSERT(dp->i_df.if_bytes == dp->i_d.di_size); ASSERT(dp->i_df.if_u1.if_data != NULL); sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; ASSERT(dp->i_d.di_size >= xfs_dir2_sf_hdr_size(sfp->i8count)); /* * Compute entry (and change in) size. */ incr_isize = dp->d_ops->sf_entsize(sfp, args->namelen); objchange = 0; /* * Do we have to change to 8 byte inodes? */ if (args->inumber > XFS_DIR2_MAX_SHORT_INUM && sfp->i8count == 0) { /* * Yes, adjust the inode size. old count + (parent + new) */ incr_isize += (sfp->count + 2) * XFS_INO64_DIFF; objchange = 1; } new_isize = (int)dp->i_d.di_size + incr_isize; /* * Won't fit as shortform any more (due to size), * or the pick routine says it won't (due to offset values). */ if (new_isize > XFS_IFORK_DSIZE(dp) || (pick = xfs_dir2_sf_addname_pick(args, objchange, &sfep, &offset)) == 0) { /* * Just checking or no space reservation, it doesn't fit. */ if ((args->op_flags & XFS_DA_OP_JUSTCHECK) || args->total == 0) return -ENOSPC; /* * Convert to block form then add the name. */ error = xfs_dir2_sf_to_block(args); if (error) return error; return xfs_dir2_block_addname(args); } /* * Just checking, it fits. */ if (args->op_flags & XFS_DA_OP_JUSTCHECK) return 0; /* * Do it the easy way - just add it at the end. */ if (pick == 1) xfs_dir2_sf_addname_easy(args, sfep, offset, new_isize); /* * Do it the hard way - look for a place to insert the new entry. * Convert to 8 byte inode numbers first if necessary. */ else { ASSERT(pick == 2); if (objchange) xfs_dir2_sf_toino8(args); xfs_dir2_sf_addname_hard(args, objchange, new_isize); } xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_DDATA); return 0; } /* * Add the new entry the "easy" way. * This is copying the old directory and adding the new entry at the end. * Since it's sorted by "offset" we need room after the last offset * that's already there, and then room to convert to a block directory. * This is already checked by the pick routine. */ static void xfs_dir2_sf_addname_easy( xfs_da_args_t *args, /* operation arguments */ xfs_dir2_sf_entry_t *sfep, /* pointer to new entry */ xfs_dir2_data_aoff_t offset, /* offset to use for new ent */ int new_isize) /* new directory size */ { int byteoff; /* byte offset in sf dir */ xfs_inode_t *dp; /* incore directory inode */ xfs_dir2_sf_hdr_t *sfp; /* shortform structure */ dp = args->dp; sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; byteoff = (int)((char *)sfep - (char *)sfp); /* * Grow the in-inode space. */ xfs_idata_realloc(dp, dp->d_ops->sf_entsize(sfp, args->namelen), XFS_DATA_FORK); /* * Need to set up again due to realloc of the inode data. */ sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; sfep = (xfs_dir2_sf_entry_t *)((char *)sfp + byteoff); /* * Fill in the new entry. */ sfep->namelen = args->namelen; xfs_dir2_sf_put_offset(sfep, offset); memcpy(sfep->name, args->name, sfep->namelen); dp->d_ops->sf_put_ino(sfp, sfep, args->inumber); dp->d_ops->sf_put_ftype(sfep, args->filetype); /* * Update the header and inode. */ sfp->count++; if (args->inumber > XFS_DIR2_MAX_SHORT_INUM) sfp->i8count++; dp->i_d.di_size = new_isize; xfs_dir2_sf_check(args); } /* * Add the new entry the "hard" way. * The caller has already converted to 8 byte inode numbers if necessary, * in which case we need to leave the i8count at 1. * Find a hole that the new entry will fit into, and copy * the first part of the entries, the new entry, and the last part of * the entries. */ /* ARGSUSED */ static void xfs_dir2_sf_addname_hard( xfs_da_args_t *args, /* operation arguments */ int objchange, /* changing inode number size */ int new_isize) /* new directory size */ { int add_datasize; /* data size need for new ent */ char *buf; /* buffer for old */ xfs_inode_t *dp; /* incore directory inode */ int eof; /* reached end of old dir */ int nbytes; /* temp for byte copies */ xfs_dir2_data_aoff_t new_offset; /* next offset value */ xfs_dir2_data_aoff_t offset; /* current offset value */ int old_isize; /* previous di_size */ xfs_dir2_sf_entry_t *oldsfep; /* entry in original dir */ xfs_dir2_sf_hdr_t *oldsfp; /* original shortform dir */ xfs_dir2_sf_entry_t *sfep; /* entry in new dir */ xfs_dir2_sf_hdr_t *sfp; /* new shortform dir */ /* * Copy the old directory to the stack buffer. */ dp = args->dp; sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; old_isize = (int)dp->i_d.di_size; buf = kmem_alloc(old_isize, KM_SLEEP); oldsfp = (xfs_dir2_sf_hdr_t *)buf; memcpy(oldsfp, sfp, old_isize); /* * Loop over the old directory finding the place we're going * to insert the new entry. * If it's going to end up at the end then oldsfep will point there. */ for (offset = dp->d_ops->data_first_offset, oldsfep = xfs_dir2_sf_firstentry(oldsfp), add_datasize = dp->d_ops->data_entsize(args->namelen), eof = (char *)oldsfep == &buf[old_isize]; !eof; offset = new_offset + dp->d_ops->data_entsize(oldsfep->namelen), oldsfep = dp->d_ops->sf_nextentry(oldsfp, oldsfep), eof = (char *)oldsfep == &buf[old_isize]) { new_offset = xfs_dir2_sf_get_offset(oldsfep); if (offset + add_datasize <= new_offset) break; } /* * Get rid of the old directory, then allocate space for * the new one. We do this so xfs_idata_realloc won't copy * the data. */ xfs_idata_realloc(dp, -old_isize, XFS_DATA_FORK); xfs_idata_realloc(dp, new_isize, XFS_DATA_FORK); /* * Reset the pointer since the buffer was reallocated. */ sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; /* * Copy the first part of the directory, including the header. */ nbytes = (int)((char *)oldsfep - (char *)oldsfp); memcpy(sfp, oldsfp, nbytes); sfep = (xfs_dir2_sf_entry_t *)((char *)sfp + nbytes); /* * Fill in the new entry, and update the header counts. */ sfep->namelen = args->namelen; xfs_dir2_sf_put_offset(sfep, offset); memcpy(sfep->name, args->name, sfep->namelen); dp->d_ops->sf_put_ino(sfp, sfep, args->inumber); dp->d_ops->sf_put_ftype(sfep, args->filetype); sfp->count++; if (args->inumber > XFS_DIR2_MAX_SHORT_INUM && !objchange) sfp->i8count++; /* * If there's more left to copy, do that. */ if (!eof) { sfep = dp->d_ops->sf_nextentry(sfp, sfep); memcpy(sfep, oldsfep, old_isize - nbytes); } kmem_free(buf); dp->i_d.di_size = new_isize; xfs_dir2_sf_check(args); } /* * Decide if the new entry will fit at all. * If it will fit, pick between adding the new entry to the end (easy) * or somewhere else (hard). * Return 0 (won't fit), 1 (easy), 2 (hard). */ /*ARGSUSED*/ static int /* pick result */ xfs_dir2_sf_addname_pick( xfs_da_args_t *args, /* operation arguments */ int objchange, /* inode # size changes */ xfs_dir2_sf_entry_t **sfepp, /* out(1): new entry ptr */ xfs_dir2_data_aoff_t *offsetp) /* out(1): new offset */ { xfs_inode_t *dp; /* incore directory inode */ int holefit; /* found hole it will fit in */ int i; /* entry number */ xfs_dir2_data_aoff_t offset; /* data block offset */ xfs_dir2_sf_entry_t *sfep; /* shortform entry */ xfs_dir2_sf_hdr_t *sfp; /* shortform structure */ int size; /* entry's data size */ int used; /* data bytes used */ dp = args->dp; sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; size = dp->d_ops->data_entsize(args->namelen); offset = dp->d_ops->data_first_offset; sfep = xfs_dir2_sf_firstentry(sfp); holefit = 0; /* * Loop over sf entries. * Keep track of data offset and whether we've seen a place * to insert the new entry. */ for (i = 0; i < sfp->count; i++) { if (!holefit) holefit = offset + size <= xfs_dir2_sf_get_offset(sfep); offset = xfs_dir2_sf_get_offset(sfep) + dp->d_ops->data_entsize(sfep->namelen); sfep = dp->d_ops->sf_nextentry(sfp, sfep); } /* * Calculate data bytes used excluding the new entry, if this * was a data block (block form directory). */ used = offset + (sfp->count + 3) * (uint)sizeof(xfs_dir2_leaf_entry_t) + (uint)sizeof(xfs_dir2_block_tail_t); /* * If it won't fit in a block form then we can't insert it, * we'll go back, convert to block, then try the insert and convert * to leaf. */ if (used + (holefit ? 0 : size) > args->geo->blksize) return 0; /* * If changing the inode number size, do it the hard way. */ if (objchange) return 2; /* * If it won't fit at the end then do it the hard way (use the hole). */ if (used + size > args->geo->blksize) return 2; /* * Do it the easy way. */ *sfepp = sfep; *offsetp = offset; return 1; } #ifdef DEBUG /* * Check consistency of shortform directory, assert if bad. */ static void xfs_dir2_sf_check( xfs_da_args_t *args) /* operation arguments */ { xfs_inode_t *dp; /* incore directory inode */ int i; /* entry number */ int i8count; /* number of big inode#s */ xfs_ino_t ino; /* entry inode number */ int offset; /* data offset */ xfs_dir2_sf_entry_t *sfep; /* shortform dir entry */ xfs_dir2_sf_hdr_t *sfp; /* shortform structure */ dp = args->dp; sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; offset = dp->d_ops->data_first_offset; ino = dp->d_ops->sf_get_parent_ino(sfp); i8count = ino > XFS_DIR2_MAX_SHORT_INUM; for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp); i < sfp->count; i++, sfep = dp->d_ops->sf_nextentry(sfp, sfep)) { ASSERT(xfs_dir2_sf_get_offset(sfep) >= offset); ino = dp->d_ops->sf_get_ino(sfp, sfep); i8count += ino > XFS_DIR2_MAX_SHORT_INUM; offset = xfs_dir2_sf_get_offset(sfep) + dp->d_ops->data_entsize(sfep->namelen); ASSERT(dp->d_ops->sf_get_ftype(sfep) < XFS_DIR3_FT_MAX); } ASSERT(i8count == sfp->i8count); ASSERT((char *)sfep - (char *)sfp == dp->i_d.di_size); ASSERT(offset + (sfp->count + 2) * (uint)sizeof(xfs_dir2_leaf_entry_t) + (uint)sizeof(xfs_dir2_block_tail_t) <= args->geo->blksize); } #endif /* DEBUG */ /* Verify the consistency of an inline directory. */ int xfs_dir2_sf_verify( struct xfs_inode *ip) { struct xfs_mount *mp = ip->i_mount; struct xfs_dir2_sf_hdr *sfp; struct xfs_dir2_sf_entry *sfep; struct xfs_dir2_sf_entry *next_sfep; char *endp; const struct xfs_dir_ops *dops; struct xfs_ifork *ifp; xfs_ino_t ino; int i; int i8count; int offset; int size; int error; uint8_t filetype; ASSERT(ip->i_d.di_format == XFS_DINODE_FMT_LOCAL); /* * xfs_iread calls us before xfs_setup_inode sets up ip->d_ops, * so we can only trust the mountpoint to have the right pointer. */ dops = xfs_dir_get_ops(mp, NULL); ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK); sfp = (struct xfs_dir2_sf_hdr *)ifp->if_u1.if_data; size = ifp->if_bytes; /* * Give up if the directory is way too short. */ if (size <= offsetof(struct xfs_dir2_sf_hdr, parent) || size < xfs_dir2_sf_hdr_size(sfp->i8count)) return -EFSCORRUPTED; endp = (char *)sfp + size; /* Check .. entry */ ino = dops->sf_get_parent_ino(sfp); i8count = ino > XFS_DIR2_MAX_SHORT_INUM; error = xfs_dir_ino_validate(mp, ino); if (error) return error; offset = dops->data_first_offset; /* Check all reported entries */ sfep = xfs_dir2_sf_firstentry(sfp); for (i = 0; i < sfp->count; i++) { /* * struct xfs_dir2_sf_entry has a variable length. * Check the fixed-offset parts of the structure are * within the data buffer. */ if (((char *)sfep + sizeof(*sfep)) >= endp) return -EFSCORRUPTED; /* Don't allow names with known bad length. */ if (sfep->namelen == 0) return -EFSCORRUPTED; /* * Check that the variable-length part of the structure is * within the data buffer. The next entry starts after the * name component, so nextentry is an acceptable test. */ next_sfep = dops->sf_nextentry(sfp, sfep); if (endp < (char *)next_sfep) return -EFSCORRUPTED; /* Check that the offsets always increase. */ if (xfs_dir2_sf_get_offset(sfep) < offset) return -EFSCORRUPTED; /* Check the inode number. */ ino = dops->sf_get_ino(sfp, sfep); i8count += ino > XFS_DIR2_MAX_SHORT_INUM; error = xfs_dir_ino_validate(mp, ino); if (error) return error; /* Check the file type. */ filetype = dops->sf_get_ftype(sfep); if (filetype >= XFS_DIR3_FT_MAX) return -EFSCORRUPTED; offset = xfs_dir2_sf_get_offset(sfep) + dops->data_entsize(sfep->namelen); sfep = next_sfep; } if (i8count != sfp->i8count) return -EFSCORRUPTED; if ((void *)sfep != (void *)endp) return -EFSCORRUPTED; /* Make sure this whole thing ought to be in local format. */ if (offset + (sfp->count + 2) * (uint)sizeof(xfs_dir2_leaf_entry_t) + (uint)sizeof(xfs_dir2_block_tail_t) > mp->m_dir_geo->blksize) return -EFSCORRUPTED; return 0; } /* * Create a new (shortform) directory. */ int /* error, always 0 */ xfs_dir2_sf_create( xfs_da_args_t *args, /* operation arguments */ xfs_ino_t pino) /* parent inode number */ { xfs_inode_t *dp; /* incore directory inode */ int i8count; /* parent inode is an 8-byte number */ xfs_dir2_sf_hdr_t *sfp; /* shortform structure */ int size; /* directory size */ trace_xfs_dir2_sf_create(args); dp = args->dp; ASSERT(dp != NULL); ASSERT(dp->i_d.di_size == 0); /* * If it's currently a zero-length extent file, * convert it to local format. */ if (dp->i_d.di_format == XFS_DINODE_FMT_EXTENTS) { dp->i_df.if_flags &= ~XFS_IFEXTENTS; /* just in case */ dp->i_d.di_format = XFS_DINODE_FMT_LOCAL; xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE); dp->i_df.if_flags |= XFS_IFINLINE; } ASSERT(dp->i_df.if_flags & XFS_IFINLINE); ASSERT(dp->i_df.if_bytes == 0); i8count = pino > XFS_DIR2_MAX_SHORT_INUM; size = xfs_dir2_sf_hdr_size(i8count); /* * Make a buffer for the data. */ xfs_idata_realloc(dp, size, XFS_DATA_FORK); /* * Fill in the header, */ sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; sfp->i8count = i8count; /* * Now can put in the inode number, since i8count is set. */ dp->d_ops->sf_put_parent_ino(sfp, pino); sfp->count = 0; dp->i_d.di_size = size; xfs_dir2_sf_check(args); xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_DDATA); return 0; } /* * Lookup an entry in a shortform directory. * Returns EEXIST if found, ENOENT if not found. */ int /* error */ xfs_dir2_sf_lookup( xfs_da_args_t *args) /* operation arguments */ { xfs_inode_t *dp; /* incore directory inode */ int i; /* entry index */ int error; xfs_dir2_sf_entry_t *sfep; /* shortform directory entry */ xfs_dir2_sf_hdr_t *sfp; /* shortform structure */ enum xfs_dacmp cmp; /* comparison result */ xfs_dir2_sf_entry_t *ci_sfep; /* case-insens. entry */ trace_xfs_dir2_sf_lookup(args); xfs_dir2_sf_check(args); dp = args->dp; ASSERT(dp->i_df.if_flags & XFS_IFINLINE); /* * Bail out if the directory is way too short. */ if (dp->i_d.di_size < offsetof(xfs_dir2_sf_hdr_t, parent)) { ASSERT(XFS_FORCED_SHUTDOWN(dp->i_mount)); return -EIO; } ASSERT(dp->i_df.if_bytes == dp->i_d.di_size); ASSERT(dp->i_df.if_u1.if_data != NULL); sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; ASSERT(dp->i_d.di_size >= xfs_dir2_sf_hdr_size(sfp->i8count)); /* * Special case for . */ if (args->namelen == 1 && args->name[0] == '.') { args->inumber = dp->i_ino; args->cmpresult = XFS_CMP_EXACT; args->filetype = XFS_DIR3_FT_DIR; return -EEXIST; } /* * Special case for .. */ if (args->namelen == 2 && args->name[0] == '.' && args->name[1] == '.') { args->inumber = dp->d_ops->sf_get_parent_ino(sfp); args->cmpresult = XFS_CMP_EXACT; args->filetype = XFS_DIR3_FT_DIR; return -EEXIST; } /* * Loop over all the entries trying to match ours. */ ci_sfep = NULL; for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp); i < sfp->count; i++, sfep = dp->d_ops->sf_nextentry(sfp, sfep)) { /* * Compare name and if it's an exact match, return the inode * number. If it's the first case-insensitive match, store the * inode number and continue looking for an exact match. */ cmp = dp->i_mount->m_dirnameops->compname(args, sfep->name, sfep->namelen); if (cmp != XFS_CMP_DIFFERENT && cmp != args->cmpresult) { args->cmpresult = cmp; args->inumber = dp->d_ops->sf_get_ino(sfp, sfep); args->filetype = dp->d_ops->sf_get_ftype(sfep); if (cmp == XFS_CMP_EXACT) return -EEXIST; ci_sfep = sfep; } } ASSERT(args->op_flags & XFS_DA_OP_OKNOENT); /* * Here, we can only be doing a lookup (not a rename or replace). * If a case-insensitive match was not found, return -ENOENT. */ if (!ci_sfep) return -ENOENT; /* otherwise process the CI match as required by the caller */ error = xfs_dir_cilookup_result(args, ci_sfep->name, ci_sfep->namelen); return error; } /* * Remove an entry from a shortform directory. */ int /* error */ xfs_dir2_sf_removename( xfs_da_args_t *args) { int byteoff; /* offset of removed entry */ xfs_inode_t *dp; /* incore directory inode */ int entsize; /* this entry's size */ int i; /* shortform entry index */ int newsize; /* new inode size */ int oldsize; /* old inode size */ xfs_dir2_sf_entry_t *sfep; /* shortform directory entry */ xfs_dir2_sf_hdr_t *sfp; /* shortform structure */ trace_xfs_dir2_sf_removename(args); dp = args->dp; ASSERT(dp->i_df.if_flags & XFS_IFINLINE); oldsize = (int)dp->i_d.di_size; /* * Bail out if the directory is way too short. */ if (oldsize < offsetof(xfs_dir2_sf_hdr_t, parent)) { ASSERT(XFS_FORCED_SHUTDOWN(dp->i_mount)); return -EIO; } ASSERT(dp->i_df.if_bytes == oldsize); ASSERT(dp->i_df.if_u1.if_data != NULL); sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; ASSERT(oldsize >= xfs_dir2_sf_hdr_size(sfp->i8count)); /* * Loop over the old directory entries. * Find the one we're deleting. */ for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp); i < sfp->count; i++, sfep = dp->d_ops->sf_nextentry(sfp, sfep)) { if (xfs_da_compname(args, sfep->name, sfep->namelen) == XFS_CMP_EXACT) { ASSERT(dp->d_ops->sf_get_ino(sfp, sfep) == args->inumber); break; } } /* * Didn't find it. */ if (i == sfp->count) return -ENOENT; /* * Calculate sizes. */ byteoff = (int)((char *)sfep - (char *)sfp); entsize = dp->d_ops->sf_entsize(sfp, args->namelen); newsize = oldsize - entsize; /* * Copy the part if any after the removed entry, sliding it down. */ if (byteoff + entsize < oldsize) memmove((char *)sfp + byteoff, (char *)sfp + byteoff + entsize, oldsize - (byteoff + entsize)); /* * Fix up the header and file size. */ sfp->count--; dp->i_d.di_size = newsize; /* * Reallocate, making it smaller. */ xfs_idata_realloc(dp, newsize - oldsize, XFS_DATA_FORK); sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; /* * Are we changing inode number size? */ if (args->inumber > XFS_DIR2_MAX_SHORT_INUM) { if (sfp->i8count == 1) xfs_dir2_sf_toino4(args); else sfp->i8count--; } xfs_dir2_sf_check(args); xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_DDATA); return 0; } /* * Replace the inode number of an entry in a shortform directory. */ int /* error */ xfs_dir2_sf_replace( xfs_da_args_t *args) /* operation arguments */ { xfs_inode_t *dp; /* incore directory inode */ int i; /* entry index */ xfs_ino_t ino=0; /* entry old inode number */ int i8elevated; /* sf_toino8 set i8count=1 */ xfs_dir2_sf_entry_t *sfep; /* shortform directory entry */ xfs_dir2_sf_hdr_t *sfp; /* shortform structure */ trace_xfs_dir2_sf_replace(args); dp = args->dp; ASSERT(dp->i_df.if_flags & XFS_IFINLINE); /* * Bail out if the shortform directory is way too small. */ if (dp->i_d.di_size < offsetof(xfs_dir2_sf_hdr_t, parent)) { ASSERT(XFS_FORCED_SHUTDOWN(dp->i_mount)); return -EIO; } ASSERT(dp->i_df.if_bytes == dp->i_d.di_size); ASSERT(dp->i_df.if_u1.if_data != NULL); sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; ASSERT(dp->i_d.di_size >= xfs_dir2_sf_hdr_size(sfp->i8count)); /* * New inode number is large, and need to convert to 8-byte inodes. */ if (args->inumber > XFS_DIR2_MAX_SHORT_INUM && sfp->i8count == 0) { int error; /* error return value */ int newsize; /* new inode size */ newsize = dp->i_df.if_bytes + (sfp->count + 1) * XFS_INO64_DIFF; /* * Won't fit as shortform, convert to block then do replace. */ if (newsize > XFS_IFORK_DSIZE(dp)) { error = xfs_dir2_sf_to_block(args); if (error) { return error; } return xfs_dir2_block_replace(args); } /* * Still fits, convert to 8-byte now. */ xfs_dir2_sf_toino8(args); i8elevated = 1; sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; } else i8elevated = 0; ASSERT(args->namelen != 1 || args->name[0] != '.'); /* * Replace ..'s entry. */ if (args->namelen == 2 && args->name[0] == '.' && args->name[1] == '.') { ino = dp->d_ops->sf_get_parent_ino(sfp); ASSERT(args->inumber != ino); dp->d_ops->sf_put_parent_ino(sfp, args->inumber); } /* * Normal entry, look for the name. */ else { for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp); i < sfp->count; i++, sfep = dp->d_ops->sf_nextentry(sfp, sfep)) { if (xfs_da_compname(args, sfep->name, sfep->namelen) == XFS_CMP_EXACT) { ino = dp->d_ops->sf_get_ino(sfp, sfep); ASSERT(args->inumber != ino); dp->d_ops->sf_put_ino(sfp, sfep, args->inumber); dp->d_ops->sf_put_ftype(sfep, args->filetype); break; } } /* * Didn't find it. */ if (i == sfp->count) { ASSERT(args->op_flags & XFS_DA_OP_OKNOENT); if (i8elevated) xfs_dir2_sf_toino4(args); return -ENOENT; } } /* * See if the old number was large, the new number is small. */ if (ino > XFS_DIR2_MAX_SHORT_INUM && args->inumber <= XFS_DIR2_MAX_SHORT_INUM) { /* * And the old count was one, so need to convert to small. */ if (sfp->i8count == 1) xfs_dir2_sf_toino4(args); else sfp->i8count--; } /* * See if the old number was small, the new number is large. */ if (ino <= XFS_DIR2_MAX_SHORT_INUM && args->inumber > XFS_DIR2_MAX_SHORT_INUM) { /* * add to the i8count unless we just converted to 8-byte * inodes (which does an implied i8count = 1) */ ASSERT(sfp->i8count != 0); if (!i8elevated) sfp->i8count++; } xfs_dir2_sf_check(args); xfs_trans_log_inode(args->trans, dp, XFS_ILOG_DDATA); return 0; } /* * Convert from 8-byte inode numbers to 4-byte inode numbers. * The last 8-byte inode number is gone, but the count is still 1. */ static void xfs_dir2_sf_toino4( xfs_da_args_t *args) /* operation arguments */ { char *buf; /* old dir's buffer */ xfs_inode_t *dp; /* incore directory inode */ int i; /* entry index */ int newsize; /* new inode size */ xfs_dir2_sf_entry_t *oldsfep; /* old sf entry */ xfs_dir2_sf_hdr_t *oldsfp; /* old sf directory */ int oldsize; /* old inode size */ xfs_dir2_sf_entry_t *sfep; /* new sf entry */ xfs_dir2_sf_hdr_t *sfp; /* new sf directory */ trace_xfs_dir2_sf_toino4(args); dp = args->dp; /* * Copy the old directory to the buffer. * Then nuke it from the inode, and add the new buffer to the inode. * Don't want xfs_idata_realloc copying the data here. */ oldsize = dp->i_df.if_bytes; buf = kmem_alloc(oldsize, KM_SLEEP); oldsfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; ASSERT(oldsfp->i8count == 1); memcpy(buf, oldsfp, oldsize); /* * Compute the new inode size. */ newsize = oldsize - (oldsfp->count + 1) * XFS_INO64_DIFF; xfs_idata_realloc(dp, -oldsize, XFS_DATA_FORK); xfs_idata_realloc(dp, newsize, XFS_DATA_FORK); /* * Reset our pointers, the data has moved. */ oldsfp = (xfs_dir2_sf_hdr_t *)buf; sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; /* * Fill in the new header. */ sfp->count = oldsfp->count; sfp->i8count = 0; dp->d_ops->sf_put_parent_ino(sfp, dp->d_ops->sf_get_parent_ino(oldsfp)); /* * Copy the entries field by field. */ for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp), oldsfep = xfs_dir2_sf_firstentry(oldsfp); i < sfp->count; i++, sfep = dp->d_ops->sf_nextentry(sfp, sfep), oldsfep = dp->d_ops->sf_nextentry(oldsfp, oldsfep)) { sfep->namelen = oldsfep->namelen; memcpy(sfep->offset, oldsfep->offset, sizeof(sfep->offset)); memcpy(sfep->name, oldsfep->name, sfep->namelen); dp->d_ops->sf_put_ino(sfp, sfep, dp->d_ops->sf_get_ino(oldsfp, oldsfep)); dp->d_ops->sf_put_ftype(sfep, dp->d_ops->sf_get_ftype(oldsfep)); } /* * Clean up the inode. */ kmem_free(buf); dp->i_d.di_size = newsize; xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_DDATA); } /* * Convert existing entries from 4-byte inode numbers to 8-byte inode numbers. * The new entry w/ an 8-byte inode number is not there yet; we leave with * i8count set to 1, but no corresponding 8-byte entry. */ static void xfs_dir2_sf_toino8( xfs_da_args_t *args) /* operation arguments */ { char *buf; /* old dir's buffer */ xfs_inode_t *dp; /* incore directory inode */ int i; /* entry index */ int newsize; /* new inode size */ xfs_dir2_sf_entry_t *oldsfep; /* old sf entry */ xfs_dir2_sf_hdr_t *oldsfp; /* old sf directory */ int oldsize; /* old inode size */ xfs_dir2_sf_entry_t *sfep; /* new sf entry */ xfs_dir2_sf_hdr_t *sfp; /* new sf directory */ trace_xfs_dir2_sf_toino8(args); dp = args->dp; /* * Copy the old directory to the buffer. * Then nuke it from the inode, and add the new buffer to the inode. * Don't want xfs_idata_realloc copying the data here. */ oldsize = dp->i_df.if_bytes; buf = kmem_alloc(oldsize, KM_SLEEP); oldsfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; ASSERT(oldsfp->i8count == 0); memcpy(buf, oldsfp, oldsize); /* * Compute the new inode size (nb: entry count + 1 for parent) */ newsize = oldsize + (oldsfp->count + 1) * XFS_INO64_DIFF; xfs_idata_realloc(dp, -oldsize, XFS_DATA_FORK); xfs_idata_realloc(dp, newsize, XFS_DATA_FORK); /* * Reset our pointers, the data has moved. */ oldsfp = (xfs_dir2_sf_hdr_t *)buf; sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data; /* * Fill in the new header. */ sfp->count = oldsfp->count; sfp->i8count = 1; dp->d_ops->sf_put_parent_ino(sfp, dp->d_ops->sf_get_parent_ino(oldsfp)); /* * Copy the entries field by field. */ for (i = 0, sfep = xfs_dir2_sf_firstentry(sfp), oldsfep = xfs_dir2_sf_firstentry(oldsfp); i < sfp->count; i++, sfep = dp->d_ops->sf_nextentry(sfp, sfep), oldsfep = dp->d_ops->sf_nextentry(oldsfp, oldsfep)) { sfep->namelen = oldsfep->namelen; memcpy(sfep->offset, oldsfep->offset, sizeof(sfep->offset)); memcpy(sfep->name, oldsfep->name, sfep->namelen); dp->d_ops->sf_put_ino(sfp, sfep, dp->d_ops->sf_get_ino(oldsfp, oldsfep)); dp->d_ops->sf_put_ftype(sfep, dp->d_ops->sf_get_ftype(oldsfep)); } /* * Clean up the inode. */ kmem_free(buf); dp->i_d.di_size = newsize; xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_DDATA); } |
| 2 1 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 | /* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* * include/uapi/linux/tipc.h: Header for TIPC socket interface * * Copyright (c) 2003-2006, 2015-2016 Ericsson AB * Copyright (c) 2005, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. */ #ifndef _LINUX_TIPC_H_ #define _LINUX_TIPC_H_ #include <linux/types.h> #include <linux/sockios.h> /* * TIPC addressing primitives */ struct tipc_portid { __u32 ref; __u32 node; }; struct tipc_name { __u32 type; __u32 instance; }; struct tipc_name_seq { __u32 type; __u32 lower; __u32 upper; }; /* TIPC Address Size, Offset, Mask specification for Z.C.N */ #define TIPC_NODE_BITS 12 #define TIPC_CLUSTER_BITS 12 #define TIPC_ZONE_BITS 8 #define TIPC_NODE_OFFSET 0 #define TIPC_CLUSTER_OFFSET TIPC_NODE_BITS #define TIPC_ZONE_OFFSET (TIPC_CLUSTER_OFFSET + TIPC_CLUSTER_BITS) #define TIPC_NODE_SIZE ((1UL << TIPC_NODE_BITS) - 1) #define TIPC_CLUSTER_SIZE ((1UL << TIPC_CLUSTER_BITS) - 1) #define TIPC_ZONE_SIZE ((1UL << TIPC_ZONE_BITS) - 1) #define TIPC_NODE_MASK (TIPC_NODE_SIZE << TIPC_NODE_OFFSET) #define TIPC_CLUSTER_MASK (TIPC_CLUSTER_SIZE << TIPC_CLUSTER_OFFSET) #define TIPC_ZONE_MASK (TIPC_ZONE_SIZE << TIPC_ZONE_OFFSET) #define TIPC_ZONE_CLUSTER_MASK (TIPC_ZONE_MASK | TIPC_CLUSTER_MASK) static inline __u32 tipc_addr(unsigned int zone, unsigned int cluster, unsigned int node) { return (zone << TIPC_ZONE_OFFSET) | (cluster << TIPC_CLUSTER_OFFSET) | node; } static inline unsigned int tipc_zone(__u32 addr) { return addr >> TIPC_ZONE_OFFSET; } static inline unsigned int tipc_cluster(__u32 addr) { return (addr & TIPC_CLUSTER_MASK) >> TIPC_CLUSTER_OFFSET; } static inline unsigned int tipc_node(__u32 addr) { return addr & TIPC_NODE_MASK; } /* * Application-accessible port name types */ #define TIPC_CFG_SRV 0 /* configuration service name type */ #define TIPC_TOP_SRV 1 /* topology service name type */ #define TIPC_LINK_STATE 2 /* link state name type */ #define TIPC_RESERVED_TYPES 64 /* lowest user-publishable name type */ /* * Publication scopes when binding port names and port name sequences */ #define TIPC_ZONE_SCOPE 1 #define TIPC_CLUSTER_SCOPE 2 #define TIPC_NODE_SCOPE 3 /* * Limiting values for messages */ #define TIPC_MAX_USER_MSG_SIZE 66000U /* * Message importance levels */ #define TIPC_LOW_IMPORTANCE 0 #define TIPC_MEDIUM_IMPORTANCE 1 #define TIPC_HIGH_IMPORTANCE 2 #define TIPC_CRITICAL_IMPORTANCE 3 /* * Msg rejection/connection shutdown reasons */ #define TIPC_OK 0 #define TIPC_ERR_NO_NAME 1 #define TIPC_ERR_NO_PORT 2 #define TIPC_ERR_NO_NODE 3 #define TIPC_ERR_OVERLOAD 4 #define TIPC_CONN_SHUTDOWN 5 /* * TIPC topology subscription service definitions */ #define TIPC_SUB_PORTS 0x01 /* filter for port availability */ #define TIPC_SUB_SERVICE 0x02 /* filter for service availability */ #define TIPC_SUB_CANCEL 0x04 /* cancel a subscription */ #define TIPC_WAIT_FOREVER (~0) /* timeout for permanent subscription */ struct tipc_subscr { struct tipc_name_seq seq; /* name sequence of interest */ __u32 timeout; /* subscription duration (in ms) */ __u32 filter; /* bitmask of filter options */ char usr_handle[8]; /* available for subscriber use */ }; #define TIPC_PUBLISHED 1 /* publication event */ #define TIPC_WITHDRAWN 2 /* withdraw event */ #define TIPC_SUBSCR_TIMEOUT 3 /* subscription timeout event */ struct tipc_event { __u32 event; /* event type */ __u32 found_lower; /* matching name seq instances */ __u32 found_upper; /* " " " " */ struct tipc_portid port; /* associated port */ struct tipc_subscr s; /* associated subscription */ }; /* * Socket API */ #ifndef AF_TIPC #define AF_TIPC 30 #endif #ifndef PF_TIPC #define PF_TIPC AF_TIPC #endif #ifndef SOL_TIPC #define SOL_TIPC 271 #endif #define TIPC_ADDR_NAMESEQ 1 #define TIPC_ADDR_MCAST 1 #define TIPC_ADDR_NAME 2 #define TIPC_ADDR_ID 3 struct sockaddr_tipc { unsigned short family; unsigned char addrtype; signed char scope; union { struct tipc_portid id; struct tipc_name_seq nameseq; struct { struct tipc_name name; __u32 domain; } name; } addr; }; /* * Ancillary data objects supported by recvmsg() */ #define TIPC_ERRINFO 1 /* error info */ #define TIPC_RETDATA 2 /* returned data */ #define TIPC_DESTNAME 3 /* destination name */ /* * TIPC-specific socket option names */ #define TIPC_IMPORTANCE 127 /* Default: TIPC_LOW_IMPORTANCE */ #define TIPC_SRC_DROPPABLE 128 /* Default: based on socket type */ #define TIPC_DEST_DROPPABLE 129 /* Default: based on socket type */ #define TIPC_CONN_TIMEOUT 130 /* Default: 8000 (ms) */ #define TIPC_NODE_RECVQ_DEPTH 131 /* Default: none (read only) */ #define TIPC_SOCK_RECVQ_DEPTH 132 /* Default: none (read only) */ #define TIPC_MCAST_BROADCAST 133 /* Default: TIPC selects. No arg */ #define TIPC_MCAST_REPLICAST 134 /* Default: TIPC selects. No arg */ /* * Maximum sizes of TIPC bearer-related names (including terminating NULL) * The string formatting for each name element is: * media: media * interface: media:interface name * link: Z.C.N:interface-Z.C.N:interface * */ #define TIPC_MAX_MEDIA_NAME 16 #define TIPC_MAX_IF_NAME 16 #define TIPC_MAX_BEARER_NAME 32 #define TIPC_MAX_LINK_NAME 60 #define SIOCGETLINKNAME SIOCPROTOPRIVATE struct tipc_sioc_ln_req { __u32 peer; __u32 bearer_id; char linkname[TIPC_MAX_LINK_NAME]; }; #endif |
| 149 154 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 | #ifndef PAGE_ACTOR_H #define PAGE_ACTOR_H /* * Copyright (c) 2013 * Phillip Lougher <phillip@squashfs.org.uk> * * This work is licensed under the terms of the GNU GPL, version 2. See * the COPYING file in the top-level directory. */ #ifndef CONFIG_SQUASHFS_FILE_DIRECT struct squashfs_page_actor { void **page; int pages; int length; int next_page; }; static inline struct squashfs_page_actor *squashfs_page_actor_init(void **page, int pages, int length) { struct squashfs_page_actor *actor = kmalloc(sizeof(*actor), GFP_KERNEL); if (actor == NULL) return NULL; actor->length = length ? : pages * PAGE_SIZE; actor->page = page; actor->pages = pages; actor->next_page = 0; return actor; } static inline void *squashfs_first_page(struct squashfs_page_actor *actor) { actor->next_page = 1; return actor->page[0]; } static inline void *squashfs_next_page(struct squashfs_page_actor *actor) { return actor->next_page == actor->pages ? NULL : actor->page[actor->next_page++]; } static inline void squashfs_finish_page(struct squashfs_page_actor *actor) { /* empty */ } #else struct squashfs_page_actor { union { void **buffer; struct page **page; }; void *pageaddr; void *(*squashfs_first_page)(struct squashfs_page_actor *); void *(*squashfs_next_page)(struct squashfs_page_actor *); void (*squashfs_finish_page)(struct squashfs_page_actor *); int pages; int length; int next_page; }; extern struct squashfs_page_actor *squashfs_page_actor_init(void **, int, int); extern struct squashfs_page_actor *squashfs_page_actor_init_special(struct page **, int, int); static inline void *squashfs_first_page(struct squashfs_page_actor *actor) { return actor->squashfs_first_page(actor); } static inline void *squashfs_next_page(struct squashfs_page_actor *actor) { return actor->squashfs_next_page(actor); } static inline void squashfs_finish_page(struct squashfs_page_actor *actor) { actor->squashfs_finish_page(actor); } #endif #endif |
| 7 63 24 74 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_FIB_RULES_H #define __NET_FIB_RULES_H #include <linux/types.h> #include <linux/slab.h> #include <linux/netdevice.h> #include <linux/fib_rules.h> #include <linux/refcount.h> #include <net/flow.h> #include <net/rtnetlink.h> #include <net/fib_notifier.h> struct fib_kuid_range { kuid_t start; kuid_t end; }; struct fib_rule { struct list_head list; int iifindex; int oifindex; u32 mark; u32 mark_mask; u32 flags; u32 table; u8 action; u8 l3mdev; /* 2 bytes hole, try to use */ u32 target; __be64 tun_id; struct fib_rule __rcu *ctarget; struct net *fr_net; refcount_t refcnt; u32 pref; int suppress_ifgroup; int suppress_prefixlen; char iifname[IFNAMSIZ]; char oifname[IFNAMSIZ]; struct fib_kuid_range uid_range; struct rcu_head rcu; }; struct fib_lookup_arg { void *lookup_ptr; void *result; struct fib_rule *rule; u32 table; int flags; #define FIB_LOOKUP_NOREF 1 #define FIB_LOOKUP_IGNORE_LINKSTATE 2 }; struct fib_rules_ops { int family; struct list_head list; int rule_size; int addr_size; int unresolved_rules; int nr_goto_rules; unsigned int fib_rules_seq; int (*action)(struct fib_rule *, struct flowi *, int, struct fib_lookup_arg *); bool (*suppress)(struct fib_rule *, struct fib_lookup_arg *); int (*match)(struct fib_rule *, struct flowi *, int); int (*configure)(struct fib_rule *, struct sk_buff *, struct fib_rule_hdr *, struct nlattr **); int (*delete)(struct fib_rule *); int (*compare)(struct fib_rule *, struct fib_rule_hdr *, struct nlattr **); int (*fill)(struct fib_rule *, struct sk_buff *, struct fib_rule_hdr *); size_t (*nlmsg_payload)(struct fib_rule *); /* Called after modifications to the rules set, must flush * the route cache if one exists. */ void (*flush_cache)(struct fib_rules_ops *ops); int nlgroup; const struct nla_policy *policy; struct list_head rules_list; struct module *owner; struct net *fro_net; struct rcu_head rcu; }; struct fib_rule_notifier_info { struct fib_notifier_info info; /* must be first */ struct fib_rule *rule; }; #define FRA_GENERIC_POLICY \ [FRA_IIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, \ [FRA_OIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, \ [FRA_PRIORITY] = { .type = NLA_U32 }, \ [FRA_FWMARK] = { .type = NLA_U32 }, \ [FRA_TUN_ID] = { .type = NLA_U64 }, \ [FRA_FWMASK] = { .type = NLA_U32 }, \ [FRA_TABLE] = { .type = NLA_U32 }, \ [FRA_SUPPRESS_PREFIXLEN] = { .type = NLA_U32 }, \ [FRA_SUPPRESS_IFGROUP] = { .type = NLA_U32 }, \ [FRA_GOTO] = { .type = NLA_U32 }, \ [FRA_L3MDEV] = { .type = NLA_U8 }, \ [FRA_UID_RANGE] = { .len = sizeof(struct fib_rule_uid_range) } static inline void fib_rule_get(struct fib_rule *rule) { refcount_inc(&rule->refcnt); } static inline void fib_rule_put(struct fib_rule *rule) { if (refcount_dec_and_test(&rule->refcnt)) kfree_rcu(rule, rcu); } #ifdef CONFIG_NET_L3_MASTER_DEV static inline u32 fib_rule_get_table(struct fib_rule *rule, struct fib_lookup_arg *arg) { return rule->l3mdev ? arg->table : rule->table; } #else static inline u32 fib_rule_get_table(struct fib_rule *rule, struct fib_lookup_arg *arg) { return rule->table; } #endif static inline u32 frh_get_table(struct fib_rule_hdr *frh, struct nlattr **nla) { if (nla[FRA_TABLE]) return nla_get_u32(nla[FRA_TABLE]); return frh->table; } struct fib_rules_ops *fib_rules_register(const struct fib_rules_ops *, struct net *); void fib_rules_unregister(struct fib_rules_ops *); int fib_rules_lookup(struct fib_rules_ops *, struct flowi *, int flags, struct fib_lookup_arg *); int fib_default_rule_add(struct fib_rules_ops *, u32 pref, u32 table, u32 flags); bool fib_rule_matchall(const struct fib_rule *rule); int fib_rules_dump(struct net *net, struct notifier_block *nb, int family); unsigned int fib_rules_seq_read(struct net *net, int family); int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack); int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack); #endif |
| 2 55 55 22 19 793 55 22 22 55 55 55 32 22 794 1 1 95 95 95 95 95 95 95 21 67 67 67 67 67 3 176 6 5 5 1 5 6 6 6 4 6 3 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 | /* * drivers/base/power/wakeup.c - System wakeup events framework * * Copyright (c) 2010 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc. * * This file is released under the GPLv2. */ #include <linux/device.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/capability.h> #include <linux/export.h> #include <linux/suspend.h> #include <linux/seq_file.h> #include <linux/debugfs.h> #include <linux/pm_wakeirq.h> #include <trace/events/power.h> #include "power.h" /* * If set, the suspend/hibernate code will abort transitions to a sleep state * if wakeup events are registered during or immediately before the transition. */ bool events_check_enabled __read_mostly; /* First wakeup IRQ seen by the kernel in the last cycle. */ unsigned int pm_wakeup_irq __read_mostly; /* If greater than 0 and the system is suspending, terminate the suspend. */ static atomic_t pm_abort_suspend __read_mostly; /* * Combined counters of registered wakeup events and wakeup events in progress. * They need to be modified together atomically, so it's better to use one * atomic variable to hold them both. */ static atomic_t combined_event_count = ATOMIC_INIT(0); #define IN_PROGRESS_BITS (sizeof(int) * 4) #define MAX_IN_PROGRESS ((1 << IN_PROGRESS_BITS) - 1) static void split_counters(unsigned int *cnt, unsigned int *inpr) { unsigned int comb = atomic_read(&combined_event_count); *cnt = (comb >> IN_PROGRESS_BITS); *inpr = comb & MAX_IN_PROGRESS; } /* A preserved old value of the events counter. */ static unsigned int saved_count; static DEFINE_SPINLOCK(events_lock); static void pm_wakeup_timer_fn(unsigned long data); static LIST_HEAD(wakeup_sources); static DECLARE_WAIT_QUEUE_HEAD(wakeup_count_wait_queue); DEFINE_STATIC_SRCU(wakeup_srcu); static struct wakeup_source deleted_ws = { .name = "deleted", .lock = __SPIN_LOCK_UNLOCKED(deleted_ws.lock), }; /** * wakeup_source_prepare - Prepare a new wakeup source for initialization. * @ws: Wakeup source to prepare. * @name: Pointer to the name of the new wakeup source. * * Callers must ensure that the @name string won't be freed when @ws is still in * use. */ void wakeup_source_prepare(struct wakeup_source *ws, const char *name) { if (ws) { memset(ws, 0, sizeof(*ws)); ws->name = name; } } EXPORT_SYMBOL_GPL(wakeup_source_prepare); /** * wakeup_source_create - Create a struct wakeup_source object. * @name: Name of the new wakeup source. */ struct wakeup_source *wakeup_source_create(const char *name) { struct wakeup_source *ws; ws = kmalloc(sizeof(*ws), GFP_KERNEL); if (!ws) return NULL; wakeup_source_prepare(ws, name ? kstrdup_const(name, GFP_KERNEL) : NULL); return ws; } EXPORT_SYMBOL_GPL(wakeup_source_create); /** * wakeup_source_drop - Prepare a struct wakeup_source object for destruction. * @ws: Wakeup source to prepare for destruction. * * Callers must ensure that __pm_stay_awake() or __pm_wakeup_event() will never * be run in parallel with this function for the same wakeup source object. */ void wakeup_source_drop(struct wakeup_source *ws) { if (!ws) return; __pm_relax(ws); } EXPORT_SYMBOL_GPL(wakeup_source_drop); /* * Record wakeup_source statistics being deleted into a dummy wakeup_source. */ static void wakeup_source_record(struct wakeup_source *ws) { unsigned long flags; spin_lock_irqsave(&deleted_ws.lock, flags); if (ws->event_count) { deleted_ws.total_time = ktime_add(deleted_ws.total_time, ws->total_time); deleted_ws.prevent_sleep_time = ktime_add(deleted_ws.prevent_sleep_time, ws->prevent_sleep_time); deleted_ws.max_time = ktime_compare(deleted_ws.max_time, ws->max_time) > 0 ? deleted_ws.max_time : ws->max_time; deleted_ws.event_count += ws->event_count; deleted_ws.active_count += ws->active_count; deleted_ws.relax_count += ws->relax_count; deleted_ws.expire_count += ws->expire_count; deleted_ws.wakeup_count += ws->wakeup_count; } spin_unlock_irqrestore(&deleted_ws.lock, flags); } /** * wakeup_source_destroy - Destroy a struct wakeup_source object. * @ws: Wakeup source to destroy. * * Use only for wakeup source objects created with wakeup_source_create(). */ void wakeup_source_destroy(struct wakeup_source *ws) { if (!ws) return; wakeup_source_drop(ws); wakeup_source_record(ws); kfree_const(ws->name); kfree(ws); } EXPORT_SYMBOL_GPL(wakeup_source_destroy); /** * wakeup_source_add - Add given object to the list of wakeup sources. * @ws: Wakeup source object to add to the list. */ void wakeup_source_add(struct wakeup_source *ws) { unsigned long flags; if (WARN_ON(!ws)) return; spin_lock_init(&ws->lock); setup_timer(&ws->timer, pm_wakeup_timer_fn, (unsigned long)ws); ws->active = false; ws->last_time = ktime_get(); spin_lock_irqsave(&events_lock, flags); list_add_rcu(&ws->entry, &wakeup_sources); spin_unlock_irqrestore(&events_lock, flags); } EXPORT_SYMBOL_GPL(wakeup_source_add); /** * wakeup_source_remove - Remove given object from the wakeup sources list. * @ws: Wakeup source object to remove from the list. */ void wakeup_source_remove(struct wakeup_source *ws) { unsigned long flags; if (WARN_ON(!ws)) return; spin_lock_irqsave(&events_lock, flags); list_del_rcu(&ws->entry); spin_unlock_irqrestore(&events_lock, flags); synchronize_srcu(&wakeup_srcu); del_timer_sync(&ws->timer); /* * Clear timer.function to make wakeup_source_not_registered() treat * this wakeup source as not registered. */ ws->timer.function = NULL; } EXPORT_SYMBOL_GPL(wakeup_source_remove); /** * wakeup_source_register - Create wakeup source and add it to the list. * @name: Name of the wakeup source to register. */ struct wakeup_source *wakeup_source_register(const char *name) { struct wakeup_source *ws; ws = wakeup_source_create(name); if (ws) wakeup_source_add(ws); return ws; } EXPORT_SYMBOL_GPL(wakeup_source_register); /** * wakeup_source_unregister - Remove wakeup source from the list and remove it. * @ws: Wakeup source object to unregister. */ void wakeup_source_unregister(struct wakeup_source *ws) { if (ws) { wakeup_source_remove(ws); wakeup_source_destroy(ws); } } EXPORT_SYMBOL_GPL(wakeup_source_unregister); /** * device_wakeup_attach - Attach a wakeup source object to a device object. * @dev: Device to handle. * @ws: Wakeup source object to attach to @dev. * * This causes @dev to be treated as a wakeup device. */ static int device_wakeup_attach(struct device *dev, struct wakeup_source *ws) { spin_lock_irq(&dev->power.lock); if (dev->power.wakeup) { spin_unlock_irq(&dev->power.lock); return -EEXIST; } dev->power.wakeup = ws; if (dev->power.wakeirq) device_wakeup_attach_irq(dev, dev->power.wakeirq); spin_unlock_irq(&dev->power.lock); return 0; } /** * device_wakeup_enable - Enable given device to be a wakeup source. * @dev: Device to handle. * * Create a wakeup source object, register it and attach it to @dev. */ int device_wakeup_enable(struct device *dev) { struct wakeup_source *ws; int ret; if (!dev || !dev->power.can_wakeup) return -EINVAL; ws = wakeup_source_register(dev_name(dev)); if (!ws) return -ENOMEM; ret = device_wakeup_attach(dev, ws); if (ret) wakeup_source_unregister(ws); return ret; } EXPORT_SYMBOL_GPL(device_wakeup_enable); /** * device_wakeup_attach_irq - Attach a wakeirq to a wakeup source * @dev: Device to handle * @wakeirq: Device specific wakeirq entry * * Attach a device wakeirq to the wakeup source so the device * wake IRQ can be configured automatically for suspend and * resume. * * Call under the device's power.lock lock. */ int device_wakeup_attach_irq(struct device *dev, struct wake_irq *wakeirq) { struct wakeup_source *ws; ws = dev->power.wakeup; if (!ws) { dev_err(dev, "forgot to call call device_init_wakeup?\n"); return -EINVAL; } if (ws->wakeirq) return -EEXIST; ws->wakeirq = wakeirq; return 0; } /** * device_wakeup_detach_irq - Detach a wakeirq from a wakeup source * @dev: Device to handle * * Removes a device wakeirq from the wakeup source. * * Call under the device's power.lock lock. */ void device_wakeup_detach_irq(struct device *dev) { struct wakeup_source *ws; ws = dev->power.wakeup; if (ws) ws->wakeirq = NULL; } /** * device_wakeup_arm_wake_irqs(void) * * Itereates over the list of device wakeirqs to arm them. */ void device_wakeup_arm_wake_irqs(void) { struct wakeup_source *ws; int srcuidx; srcuidx = srcu_read_lock(&wakeup_srcu); list_for_each_entry_rcu(ws, &wakeup_sources, entry) dev_pm_arm_wake_irq(ws->wakeirq); srcu_read_unlock(&wakeup_srcu, srcuidx); } /** * device_wakeup_disarm_wake_irqs(void) * * Itereates over the list of device wakeirqs to disarm them. */ void device_wakeup_disarm_wake_irqs(void) { struct wakeup_source *ws; int srcuidx; srcuidx = srcu_read_lock(&wakeup_srcu); list_for_each_entry_rcu(ws, &wakeup_sources, entry) dev_pm_disarm_wake_irq(ws->wakeirq); srcu_read_unlock(&wakeup_srcu, srcuidx); } /** * device_wakeup_detach - Detach a device's wakeup source object from it. * @dev: Device to detach the wakeup source object from. * * After it returns, @dev will not be treated as a wakeup device any more. */ static struct wakeup_source *device_wakeup_detach(struct device *dev) { struct wakeup_source *ws; spin_lock_irq(&dev->power.lock); ws = dev->power.wakeup; dev->power.wakeup = NULL; spin_unlock_irq(&dev->power.lock); return ws; } /** * device_wakeup_disable - Do not regard a device as a wakeup source any more. * @dev: Device to handle. * * Detach the @dev's wakeup source object from it, unregister this wakeup source * object and destroy it. */ int device_wakeup_disable(struct device *dev) { struct wakeup_source *ws; if (!dev || !dev->power.can_wakeup) return -EINVAL; ws = device_wakeup_detach(dev); wakeup_source_unregister(ws); return 0; } EXPORT_SYMBOL_GPL(device_wakeup_disable); /** * device_set_wakeup_capable - Set/reset device wakeup capability flag. * @dev: Device to handle. * @capable: Whether or not @dev is capable of waking up the system from sleep. * * If @capable is set, set the @dev's power.can_wakeup flag and add its * wakeup-related attributes to sysfs. Otherwise, unset the @dev's * power.can_wakeup flag and remove its wakeup-related attributes from sysfs. * * This function may sleep and it can't be called from any context where * sleeping is not allowed. */ void device_set_wakeup_capable(struct device *dev, bool capable) { if (!!dev->power.can_wakeup == !!capable) return; dev->power.can_wakeup = capable; if (device_is_registered(dev) && !list_empty(&dev->power.entry)) { if (capable) { int ret = wakeup_sysfs_add(dev); if (ret) dev_info(dev, "Wakeup sysfs attributes not added\n"); } else { wakeup_sysfs_remove(dev); } } } EXPORT_SYMBOL_GPL(device_set_wakeup_capable); /** * device_init_wakeup - Device wakeup initialization. * @dev: Device to handle. * @enable: Whether or not to enable @dev as a wakeup device. * * By default, most devices should leave wakeup disabled. The exceptions are * devices that everyone expects to be wakeup sources: keyboards, power buttons, * possibly network interfaces, etc. Also, devices that don't generate their * own wakeup requests but merely forward requests from one bus to another * (like PCI bridges) should have wakeup enabled by default. */ int device_init_wakeup(struct device *dev, bool enable) { int ret = 0; if (!dev) return -EINVAL; if (enable) { device_set_wakeup_capable(dev, true); ret = device_wakeup_enable(dev); } else { if (dev->power.can_wakeup) device_wakeup_disable(dev); device_set_wakeup_capable(dev, false); } return ret; } EXPORT_SYMBOL_GPL(device_init_wakeup); /** * device_set_wakeup_enable - Enable or disable a device to wake up the system. * @dev: Device to handle. */ int device_set_wakeup_enable(struct device *dev, bool enable) { if (!dev || !dev->power.can_wakeup) return -EINVAL; return enable ? device_wakeup_enable(dev) : device_wakeup_disable(dev); } EXPORT_SYMBOL_GPL(device_set_wakeup_enable); /** * wakeup_source_not_registered - validate the given wakeup source. * @ws: Wakeup source to be validated. */ static bool wakeup_source_not_registered(struct wakeup_source *ws) { /* * Use timer struct to check if the given source is initialized * by wakeup_source_add. */ return ws->timer.function != pm_wakeup_timer_fn || ws->timer.data != (unsigned long)ws; } /* * The functions below use the observation that each wakeup event starts a * period in which the system should not be suspended. The moment this period * will end depends on how the wakeup event is going to be processed after being * detected and all of the possible cases can be divided into two distinct * groups. * * First, a wakeup event may be detected by the same functional unit that will * carry out the entire processing of it and possibly will pass it to user space * for further processing. In that case the functional unit that has detected * the event may later "close" the "no suspend" period associated with it * directly as soon as it has been dealt with. The pair of pm_stay_awake() and * pm_relax(), balanced with each other, is supposed to be used in such * situations. * * Second, a wakeup event may be detected by one functional unit and processed * by another one. In that case the unit that has detected it cannot really * "close" the "no suspend" period associated with it, unless it knows in * advance what's going to happen to the event during processing. This * knowledge, however, may not be available to it, so it can simply specify time * to wait before the system can be suspended and pass it as the second * argument of pm_wakeup_event(). * * It is valid to call pm_relax() after pm_wakeup_event(), in which case the * "no suspend" period will be ended either by the pm_relax(), or by the timer * function executed when the timer expires, whichever comes first. */ /** * wakup_source_activate - Mark given wakeup source as active. * @ws: Wakeup source to handle. * * Update the @ws' statistics and, if @ws has just been activated, notify the PM * core of the event by incrementing the counter of of wakeup events being * processed. */ static void wakeup_source_activate(struct wakeup_source *ws) { unsigned int cec; if (WARN_ONCE(wakeup_source_not_registered(ws), "unregistered wakeup source\n")) return; ws->active = true; ws->active_count++; ws->last_time = ktime_get(); if (ws->autosleep_enabled) ws->start_prevent_time = ws->last_time; /* Increment the counter of events in progress. */ cec = atomic_inc_return(&combined_event_count); trace_wakeup_source_activate(ws->name, cec); } /** * wakeup_source_report_event - Report wakeup event using the given source. * @ws: Wakeup source to report the event for. * @hard: If set, abort suspends in progress and wake up from suspend-to-idle. */ static void wakeup_source_report_event(struct wakeup_source *ws, bool hard) { ws->event_count++; /* This is racy, but the counter is approximate anyway. */ if (events_check_enabled) ws->wakeup_count++; if (!ws->active) wakeup_source_activate(ws); if (hard) pm_system_wakeup(); } /** * __pm_stay_awake - Notify the PM core of a wakeup event. * @ws: Wakeup source object associated with the source of the event. * * It is safe to call this function from interrupt context. */ void __pm_stay_awake(struct wakeup_source *ws) { unsigned long flags; if (!ws) return; spin_lock_irqsave(&ws->lock, flags); wakeup_source_report_event(ws, false); del_timer(&ws->timer); ws->timer_expires = 0; spin_unlock_irqrestore(&ws->lock, flags); } EXPORT_SYMBOL_GPL(__pm_stay_awake); /** * pm_stay_awake - Notify the PM core that a wakeup event is being processed. * @dev: Device the wakeup event is related to. * * Notify the PM core of a wakeup event (signaled by @dev) by calling * __pm_stay_awake for the @dev's wakeup source object. * * Call this function after detecting of a wakeup event if pm_relax() is going * to be called directly after processing the event (and possibly passing it to * user space for further processing). */ void pm_stay_awake(struct device *dev) { unsigned long flags; if (!dev) return; spin_lock_irqsave(&dev->power.lock, flags); __pm_stay_awake(dev->power.wakeup); spin_unlock_irqrestore(&dev->power.lock, flags); } EXPORT_SYMBOL_GPL(pm_stay_awake); #ifdef CONFIG_PM_AUTOSLEEP static void update_prevent_sleep_time(struct wakeup_source *ws, ktime_t now) { ktime_t delta = ktime_sub(now, ws->start_prevent_time); ws->prevent_sleep_time = ktime_add(ws->prevent_sleep_time, delta); } #else static inline void update_prevent_sleep_time(struct wakeup_source *ws, ktime_t now) {} #endif /** * wakup_source_deactivate - Mark given wakeup source as inactive. * @ws: Wakeup source to handle. * * Update the @ws' statistics and notify the PM core that the wakeup source has * become inactive by decrementing the counter of wakeup events being processed * and incrementing the counter of registered wakeup events. */ static void wakeup_source_deactivate(struct wakeup_source *ws) { unsigned int cnt, inpr, cec; ktime_t duration; ktime_t now; ws->relax_count++; /* * __pm_relax() may be called directly or from a timer function. * If it is called directly right after the timer function has been * started, but before the timer function calls __pm_relax(), it is * possible that __pm_stay_awake() will be called in the meantime and * will set ws->active. Then, ws->active may be cleared immediately * by the __pm_relax() called from the timer function, but in such a * case ws->relax_count will be different from ws->active_count. */ if (ws->relax_count != ws->active_count) { ws->relax_count--; return; } ws->active = false; now = ktime_get(); duration = ktime_sub(now, ws->last_time); ws->total_time = ktime_add(ws->total_time, duration); if (ktime_to_ns(duration) > ktime_to_ns(ws->max_time)) ws->max_time = duration; ws->last_time = now; del_timer(&ws->timer); ws->timer_expires = 0; if (ws->autosleep_enabled) update_prevent_sleep_time(ws, now); /* * Increment the counter of registered wakeup events and decrement the * couter of wakeup events in progress simultaneously. */ cec = atomic_add_return(MAX_IN_PROGRESS, &combined_event_count); trace_wakeup_source_deactivate(ws->name, cec); split_counters(&cnt, &inpr); if (!inpr && waitqueue_active(&wakeup_count_wait_queue)) wake_up(&wakeup_count_wait_queue); } /** * __pm_relax - Notify the PM core that processing of a wakeup event has ended. * @ws: Wakeup source object associated with the source of the event. * * Call this function for wakeup events whose processing started with calling * __pm_stay_awake(). * * It is safe to call it from interrupt context. */ void __pm_relax(struct wakeup_source *ws) { unsigned long flags; if (!ws) return; spin_lock_irqsave(&ws->lock, flags); if (ws->active) wakeup_source_deactivate(ws); spin_unlock_irqrestore(&ws->lock, flags); } EXPORT_SYMBOL_GPL(__pm_relax); /** * pm_relax - Notify the PM core that processing of a wakeup event has ended. * @dev: Device that signaled the event. * * Execute __pm_relax() for the @dev's wakeup source object. */ void pm_relax(struct device *dev) { unsigned long flags; if (!dev) return; spin_lock_irqsave(&dev->power.lock, flags); __pm_relax(dev->power.wakeup); spin_unlock_irqrestore(&dev->power.lock, flags); } EXPORT_SYMBOL_GPL(pm_relax); /** * pm_wakeup_timer_fn - Delayed finalization of a wakeup event. * @data: Address of the wakeup source object associated with the event source. * * Call wakeup_source_deactivate() for the wakeup source whose address is stored * in @data if it is currently active and its timer has not been canceled and * the expiration time of the timer is not in future. */ static void pm_wakeup_timer_fn(unsigned long data) { struct wakeup_source *ws = (struct wakeup_source *)data; unsigned long flags; spin_lock_irqsave(&ws->lock, flags); if (ws->active && ws->timer_expires && time_after_eq(jiffies, ws->timer_expires)) { wakeup_source_deactivate(ws); ws->expire_count++; } spin_unlock_irqrestore(&ws->lock, flags); } /** * pm_wakeup_ws_event - Notify the PM core of a wakeup event. * @ws: Wakeup source object associated with the event source. * @msec: Anticipated event processing time (in milliseconds). * @hard: If set, abort suspends in progress and wake up from suspend-to-idle. * * Notify the PM core of a wakeup event whose source is @ws that will take * approximately @msec milliseconds to be processed by the kernel. If @ws is * not active, activate it. If @msec is nonzero, set up the @ws' timer to * execute pm_wakeup_timer_fn() in future. * * It is safe to call this function from interrupt context. */ void pm_wakeup_ws_event(struct wakeup_source *ws, unsigned int msec, bool hard) { unsigned long flags; unsigned long expires; if (!ws) return; spin_lock_irqsave(&ws->lock, flags); wakeup_source_report_event(ws, hard); if (!msec) { wakeup_source_deactivate(ws); goto unlock; } expires = jiffies + msecs_to_jiffies(msec); if (!expires) expires = 1; if (!ws->timer_expires || time_after(expires, ws->timer_expires)) { mod_timer(&ws->timer, expires); ws->timer_expires = expires; } unlock: spin_unlock_irqrestore(&ws->lock, flags); } EXPORT_SYMBOL_GPL(pm_wakeup_ws_event); /** * pm_wakeup_event - Notify the PM core of a wakeup event. * @dev: Device the wakeup event is related to. * @msec: Anticipated event processing time (in milliseconds). * @hard: If set, abort suspends in progress and wake up from suspend-to-idle. * * Call pm_wakeup_ws_event() for the @dev's wakeup source object. */ void pm_wakeup_dev_event(struct device *dev, unsigned int msec, bool hard) { unsigned long flags; if (!dev) return; spin_lock_irqsave(&dev->power.lock, flags); pm_wakeup_ws_event(dev->power.wakeup, msec, hard); spin_unlock_irqrestore(&dev->power.lock, flags); } EXPORT_SYMBOL_GPL(pm_wakeup_dev_event); void pm_print_active_wakeup_sources(void) { struct wakeup_source *ws; int srcuidx, active = 0; struct wakeup_source *last_activity_ws = NULL; srcuidx = srcu_read_lock(&wakeup_srcu); list_for_each_entry_rcu(ws, &wakeup_sources, entry) { if (ws->active) { pr_debug("active wakeup source: %s\n", ws->name); active = 1; } else if (!active && (!last_activity_ws || ktime_to_ns(ws->last_time) > ktime_to_ns(last_activity_ws->last_time))) { last_activity_ws = ws; } } if (!active && last_activity_ws) pr_debug("last active wakeup source: %s\n", last_activity_ws->name); srcu_read_unlock(&wakeup_srcu, srcuidx); } EXPORT_SYMBOL_GPL(pm_print_active_wakeup_sources); /** * pm_wakeup_pending - Check if power transition in progress should be aborted. * * Compare the current number of registered wakeup events with its preserved * value from the past and return true if new wakeup events have been registered * since the old value was stored. Also return true if the current number of * wakeup events being processed is different from zero. */ bool pm_wakeup_pending(void) { unsigned long flags; bool ret = false; spin_lock_irqsave(&events_lock, flags); if (events_check_enabled) { unsigned int cnt, inpr; split_counters(&cnt, &inpr); ret = (cnt != saved_count || inpr > 0); events_check_enabled = !ret; } spin_unlock_irqrestore(&events_lock, flags); if (ret) { pr_info("PM: Wakeup pending, aborting suspend\n"); pm_print_active_wakeup_sources(); } return ret || atomic_read(&pm_abort_suspend) > 0; } void pm_system_wakeup(void) { atomic_inc(&pm_abort_suspend); s2idle_wake(); } EXPORT_SYMBOL_GPL(pm_system_wakeup); void pm_system_cancel_wakeup(void) { atomic_dec_if_positive(&pm_abort_suspend); } void pm_wakeup_clear(bool reset) { pm_wakeup_irq = 0; if (reset) atomic_set(&pm_abort_suspend, 0); } void pm_system_irq_wakeup(unsigned int irq_number) { if (pm_wakeup_irq == 0) { pm_wakeup_irq = irq_number; pm_system_wakeup(); } } /** * pm_get_wakeup_count - Read the number of registered wakeup events. * @count: Address to store the value at. * @block: Whether or not to block. * * Store the number of registered wakeup events at the address in @count. If * @block is set, block until the current number of wakeup events being * processed is zero. * * Return 'false' if the current number of wakeup events being processed is * nonzero. Otherwise return 'true'. */ bool pm_get_wakeup_count(unsigned int *count, bool block) { unsigned int cnt, inpr; if (block) { DEFINE_WAIT(wait); for (;;) { prepare_to_wait(&wakeup_count_wait_queue, &wait, TASK_INTERRUPTIBLE); split_counters(&cnt, &inpr); if (inpr == 0 || signal_pending(current)) break; pm_print_active_wakeup_sources(); schedule(); } finish_wait(&wakeup_count_wait_queue, &wait); } split_counters(&cnt, &inpr); *count = cnt; return !inpr; } /** * pm_save_wakeup_count - Save the current number of registered wakeup events. * @count: Value to compare with the current number of registered wakeup events. * * If @count is equal to the current number of registered wakeup events and the * current number of wakeup events being processed is zero, store @count as the * old number of registered wakeup events for pm_check_wakeup_events(), enable * wakeup events detection and return 'true'. Otherwise disable wakeup events * detection and return 'false'. */ bool pm_save_wakeup_count(unsigned int count) { unsigned int cnt, inpr; unsigned long flags; events_check_enabled = false; spin_lock_irqsave(&events_lock, flags); split_counters(&cnt, &inpr); if (cnt == count && inpr == 0) { saved_count = count; events_check_enabled = true; } spin_unlock_irqrestore(&events_lock, flags); return events_check_enabled; } #ifdef CONFIG_PM_AUTOSLEEP /** * pm_wakep_autosleep_enabled - Modify autosleep_enabled for all wakeup sources. * @enabled: Whether to set or to clear the autosleep_enabled flags. */ void pm_wakep_autosleep_enabled(bool set) { struct wakeup_source *ws; ktime_t now = ktime_get(); int srcuidx; srcuidx = srcu_read_lock(&wakeup_srcu); list_for_each_entry_rcu(ws, &wakeup_sources, entry) { spin_lock_irq(&ws->lock); if (ws->autosleep_enabled != set) { ws->autosleep_enabled = set; if (ws->active) { if (set) ws->start_prevent_time = now; else update_prevent_sleep_time(ws, now); } } spin_unlock_irq(&ws->lock); } srcu_read_unlock(&wakeup_srcu, srcuidx); } #endif /* CONFIG_PM_AUTOSLEEP */ static struct dentry *wakeup_sources_stats_dentry; /** * print_wakeup_source_stats - Print wakeup source statistics information. * @m: seq_file to print the statistics into. * @ws: Wakeup source object to print the statistics for. */ static int print_wakeup_source_stats(struct seq_file *m, struct wakeup_source *ws) { unsigned long flags; ktime_t total_time; ktime_t max_time; unsigned long active_count; ktime_t active_time; ktime_t prevent_sleep_time; spin_lock_irqsave(&ws->lock, flags); total_time = ws->total_time; max_time = ws->max_time; prevent_sleep_time = ws->prevent_sleep_time; active_count = ws->active_count; if (ws->active) { ktime_t now = ktime_get(); active_time = ktime_sub(now, ws->last_time); total_time = ktime_add(total_time, active_time); if (active_time > max_time) max_time = active_time; if (ws->autosleep_enabled) prevent_sleep_time = ktime_add(prevent_sleep_time, ktime_sub(now, ws->start_prevent_time)); } else { active_time = 0; } seq_printf(m, "%-12s\t%lu\t\t%lu\t\t%lu\t\t%lu\t\t%lld\t\t%lld\t\t%lld\t\t%lld\t\t%lld\n", ws->name, active_count, ws->event_count, ws->wakeup_count, ws->expire_count, ktime_to_ms(active_time), ktime_to_ms(total_time), ktime_to_ms(max_time), ktime_to_ms(ws->last_time), ktime_to_ms(prevent_sleep_time)); spin_unlock_irqrestore(&ws->lock, flags); return 0; } /** * wakeup_sources_stats_show - Print wakeup sources statistics information. * @m: seq_file to print the statistics into. */ static int wakeup_sources_stats_show(struct seq_file *m, void *unused) { struct wakeup_source *ws; int srcuidx; seq_puts(m, "name\t\tactive_count\tevent_count\twakeup_count\t" "expire_count\tactive_since\ttotal_time\tmax_time\t" "last_change\tprevent_suspend_time\n"); srcuidx = srcu_read_lock(&wakeup_srcu); list_for_each_entry_rcu(ws, &wakeup_sources, entry) print_wakeup_source_stats(m, ws); srcu_read_unlock(&wakeup_srcu, srcuidx); print_wakeup_source_stats(m, &deleted_ws); return 0; } static int wakeup_sources_stats_open(struct inode *inode, struct file *file) { return single_open(file, wakeup_sources_stats_show, NULL); } static const struct file_operations wakeup_sources_stats_fops = { .owner = THIS_MODULE, .open = wakeup_sources_stats_open, .read = seq_read, .llseek = seq_lseek, .release = single_release, }; static int __init wakeup_sources_debugfs_init(void) { wakeup_sources_stats_dentry = debugfs_create_file("wakeup_sources", S_IRUGO, NULL, NULL, &wakeup_sources_stats_fops); return 0; } postcore_initcall(wakeup_sources_debugfs_init); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 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 | /* * Copyright (c) 1999 Andreas Gal * Copyright (c) 2000-2001 Vojtech Pavlik * Copyright (c) 2006-2007 Jiri Kosina */ /* * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA * * Should you need to contact me, the author, you can do so either by * e-mail - mail your message to <vojtech@ucw.cz>, or by paper mail: * Vojtech Pavlik, Simunkova 1594, Prague 8, 182 00 Czech Republic */ #ifndef __HID_H #define __HID_H #include <linux/types.h> #include <linux/slab.h> #include <linux/list.h> #include <linux/mod_devicetable.h> /* hid_device_id */ #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/input.h> #include <linux/semaphore.h> #include <linux/mutex.h> #include <linux/power_supply.h> #include <uapi/linux/hid.h> /* * We parse each description item into this structure. Short items data * values are expanded to 32-bit signed int, long items contain a pointer * into the data area. */ struct hid_item { unsigned format; __u8 size; __u8 type; __u8 tag; union { __u8 u8; __s8 s8; __u16 u16; __s16 s16; __u32 u32; __s32 s32; __u8 *longdata; } data; }; /* * HID report item format */ #define HID_ITEM_FORMAT_SHORT 0 #define HID_ITEM_FORMAT_LONG 1 /* * Special tag indicating long items */ #define HID_ITEM_TAG_LONG 15 /* * HID report descriptor item type (prefix bit 2,3) */ #define HID_ITEM_TYPE_MAIN 0 #define HID_ITEM_TYPE_GLOBAL 1 #define HID_ITEM_TYPE_LOCAL 2 #define HID_ITEM_TYPE_RESERVED 3 /* * HID report descriptor main item tags */ #define HID_MAIN_ITEM_TAG_INPUT 8 #define HID_MAIN_ITEM_TAG_OUTPUT 9 #define HID_MAIN_ITEM_TAG_FEATURE 11 #define HID_MAIN_ITEM_TAG_BEGIN_COLLECTION 10 #define HID_MAIN_ITEM_TAG_END_COLLECTION 12 /* * HID report descriptor main item contents */ #define HID_MAIN_ITEM_CONSTANT 0x001 #define HID_MAIN_ITEM_VARIABLE 0x002 #define HID_MAIN_ITEM_RELATIVE 0x004 #define HID_MAIN_ITEM_WRAP 0x008 #define HID_MAIN_ITEM_NONLINEAR 0x010 #define HID_MAIN_ITEM_NO_PREFERRED 0x020 #define HID_MAIN_ITEM_NULL_STATE 0x040 #define HID_MAIN_ITEM_VOLATILE 0x080 #define HID_MAIN_ITEM_BUFFERED_BYTE 0x100 /* * HID report descriptor collection item types */ #define HID_COLLECTION_PHYSICAL 0 #define HID_COLLECTION_APPLICATION 1 #define HID_COLLECTION_LOGICAL 2 /* * HID report descriptor global item tags */ #define HID_GLOBAL_ITEM_TAG_USAGE_PAGE 0 #define HID_GLOBAL_ITEM_TAG_LOGICAL_MINIMUM 1 #define HID_GLOBAL_ITEM_TAG_LOGICAL_MAXIMUM 2 #define HID_GLOBAL_ITEM_TAG_PHYSICAL_MINIMUM 3 #define HID_GLOBAL_ITEM_TAG_PHYSICAL_MAXIMUM 4 #define HID_GLOBAL_ITEM_TAG_UNIT_EXPONENT 5 #define HID_GLOBAL_ITEM_TAG_UNIT 6 #define HID_GLOBAL_ITEM_TAG_REPORT_SIZE 7 #define HID_GLOBAL_ITEM_TAG_REPORT_ID 8 #define HID_GLOBAL_ITEM_TAG_REPORT_COUNT 9 #define HID_GLOBAL_ITEM_TAG_PUSH 10 #define HID_GLOBAL_ITEM_TAG_POP 11 /* * HID report descriptor local item tags */ #define HID_LOCAL_ITEM_TAG_USAGE 0 #define HID_LOCAL_ITEM_TAG_USAGE_MINIMUM 1 #define HID_LOCAL_ITEM_TAG_USAGE_MAXIMUM 2 #define HID_LOCAL_ITEM_TAG_DESIGNATOR_INDEX 3 #define HID_LOCAL_ITEM_TAG_DESIGNATOR_MINIMUM 4 #define HID_LOCAL_ITEM_TAG_DESIGNATOR_MAXIMUM 5 #define HID_LOCAL_ITEM_TAG_STRING_INDEX 7 #define HID_LOCAL_ITEM_TAG_STRING_MINIMUM 8 #define HID_LOCAL_ITEM_TAG_STRING_MAXIMUM 9 #define HID_LOCAL_ITEM_TAG_DELIMITER 10 /* * HID usage tables */ #define HID_USAGE_PAGE 0xffff0000 #define HID_UP_UNDEFINED 0x00000000 #define HID_UP_GENDESK 0x00010000 #define HID_UP_SIMULATION 0x00020000 #define HID_UP_GENDEVCTRLS 0x00060000 #define HID_UP_KEYBOARD 0x00070000 #define HID_UP_LED 0x00080000 #define HID_UP_BUTTON 0x00090000 #define HID_UP_ORDINAL 0x000a0000 #define HID_UP_TELEPHONY 0x000b0000 #define HID_UP_CONSUMER 0x000c0000 #define HID_UP_DIGITIZER 0x000d0000 #define HID_UP_PID 0x000f0000 #define HID_UP_HPVENDOR 0xff7f0000 #define HID_UP_HPVENDOR2 0xff010000 #define HID_UP_MSVENDOR 0xff000000 #define HID_UP_CUSTOM 0x00ff0000 #define HID_UP_LOGIVENDOR 0xffbc0000 #define HID_UP_LOGIVENDOR2 0xff090000 #define HID_UP_LOGIVENDOR3 0xff430000 #define HID_UP_LNVENDOR 0xffa00000 #define HID_UP_SENSOR 0x00200000 #define HID_UP_ASUSVENDOR 0xff310000 #define HID_USAGE 0x0000ffff #define HID_GD_POINTER 0x00010001 #define HID_GD_MOUSE 0x00010002 #define HID_GD_JOYSTICK 0x00010004 #define HID_GD_GAMEPAD 0x00010005 #define HID_GD_KEYBOARD 0x00010006 #define HID_GD_KEYPAD 0x00010007 #define HID_GD_MULTIAXIS 0x00010008 /* * Microsoft Win8 Wireless Radio Controls extensions CA, see: * http://www.usb.org/developers/hidpage/HUTRR40RadioHIDUsagesFinal.pdf */ #define HID_GD_WIRELESS_RADIO_CTLS 0x0001000c #define HID_GD_X 0x00010030 #define HID_GD_Y 0x00010031 #define HID_GD_Z 0x00010032 #define HID_GD_RX 0x00010033 #define HID_GD_RY 0x00010034 #define HID_GD_RZ 0x00010035 #define HID_GD_SLIDER 0x00010036 #define HID_GD_DIAL 0x00010037 #define HID_GD_WHEEL 0x00010038 #define HID_GD_HATSWITCH 0x00010039 #define HID_GD_BUFFER 0x0001003a #define HID_GD_BYTECOUNT 0x0001003b #define HID_GD_MOTION 0x0001003c #define HID_GD_START 0x0001003d #define HID_GD_SELECT 0x0001003e #define HID_GD_VX 0x00010040 #define HID_GD_VY 0x00010041 #define HID_GD_VZ 0x00010042 #define HID_GD_VBRX 0x00010043 #define HID_GD_VBRY 0x00010044 #define HID_GD_VBRZ 0x00010045 #define HID_GD_VNO 0x00010046 #define HID_GD_FEATURE 0x00010047 #define HID_GD_SYSTEM_CONTROL 0x00010080 #define HID_GD_UP 0x00010090 #define HID_GD_DOWN 0x00010091 #define HID_GD_RIGHT 0x00010092 #define HID_GD_LEFT 0x00010093 /* Microsoft Win8 Wireless Radio Controls CA usage codes */ #define HID_GD_RFKILL_BTN 0x000100c6 #define HID_GD_RFKILL_LED 0x000100c7 #define HID_GD_RFKILL_SWITCH 0x000100c8 #define HID_DC_BATTERYSTRENGTH 0x00060020 #define HID_CP_CONSUMER_CONTROL 0x000c0001 #define HID_DG_DIGITIZER 0x000d0001 #define HID_DG_PEN 0x000d0002 #define HID_DG_LIGHTPEN 0x000d0003 #define HID_DG_TOUCHSCREEN 0x000d0004 #define HID_DG_TOUCHPAD 0x000d0005 #define HID_DG_STYLUS 0x000d0020 #define HID_DG_PUCK 0x000d0021 #define HID_DG_FINGER 0x000d0022 #define HID_DG_TIPPRESSURE 0x000d0030 #define HID_DG_BARRELPRESSURE 0x000d0031 #define HID_DG_INRANGE 0x000d0032 #define HID_DG_TOUCH 0x000d0033 #define HID_DG_UNTOUCH 0x000d0034 #define HID_DG_TAP 0x000d0035 #define HID_DG_TABLETFUNCTIONKEY 0x000d0039 #define HID_DG_PROGRAMCHANGEKEY 0x000d003a #define HID_DG_BATTERYSTRENGTH 0x000d003b #define HID_DG_INVERT 0x000d003c #define HID_DG_TILT_X 0x000d003d #define HID_DG_TILT_Y 0x000d003e #define HID_DG_TWIST 0x000d0041 #define HID_DG_TIPSWITCH 0x000d0042 #define HID_DG_TIPSWITCH2 0x000d0043 #define HID_DG_BARRELSWITCH 0x000d0044 #define HID_DG_ERASER 0x000d0045 #define HID_DG_TABLETPICK 0x000d0046 #define HID_CP_CONSUMERCONTROL 0x000c0001 #define HID_CP_NUMERICKEYPAD 0x000c0002 #define HID_CP_PROGRAMMABLEBUTTONS 0x000c0003 #define HID_CP_MICROPHONE 0x000c0004 #define HID_CP_HEADPHONE 0x000c0005 #define HID_CP_GRAPHICEQUALIZER 0x000c0006 #define HID_CP_FUNCTIONBUTTONS 0x000c0036 #define HID_CP_SELECTION 0x000c0080 #define HID_CP_MEDIASELECTION 0x000c0087 #define HID_CP_SELECTDISC 0x000c00ba #define HID_CP_VOLUMEUP 0x000c00e9 #define HID_CP_VOLUMEDOWN 0x000c00ea #define HID_CP_PLAYBACKSPEED 0x000c00f1 #define HID_CP_PROXIMITY 0x000c0109 #define HID_CP_SPEAKERSYSTEM 0x000c0160 #define HID_CP_CHANNELLEFT 0x000c0161 #define HID_CP_CHANNELRIGHT 0x000c0162 #define HID_CP_CHANNELCENTER 0x000c0163 #define HID_CP_CHANNELFRONT 0x000c0164 #define HID_CP_CHANNELCENTERFRONT 0x000c0165 #define HID_CP_CHANNELSIDE 0x000c0166 #define HID_CP_CHANNELSURROUND 0x000c0167 #define HID_CP_CHANNELLOWFREQUENCYENHANCEMENT 0x000c0168 #define HID_CP_CHANNELTOP 0x000c0169 #define HID_CP_CHANNELUNKNOWN 0x000c016a #define HID_CP_APPLICATIONLAUNCHBUTTONS 0x000c0180 #define HID_CP_GENERICGUIAPPLICATIONCONTROLS 0x000c0200 #define HID_DG_DEVICECONFIG 0x000d000e #define HID_DG_DEVICESETTINGS 0x000d0023 #define HID_DG_CONFIDENCE 0x000d0047 #define HID_DG_WIDTH 0x000d0048 #define HID_DG_HEIGHT 0x000d0049 #define HID_DG_CONTACTID 0x000d0051 #define HID_DG_INPUTMODE 0x000d0052 #define HID_DG_DEVICEINDEX 0x000d0053 #define HID_DG_CONTACTCOUNT 0x000d0054 #define HID_DG_CONTACTMAX 0x000d0055 #define HID_DG_BUTTONTYPE 0x000d0059 #define HID_DG_BARRELSWITCH2 0x000d005a #define HID_DG_TOOLSERIALNUMBER 0x000d005b #define HID_VD_ASUS_CUSTOM_MEDIA_KEYS 0xff310076 /* * HID report types --- Ouch! HID spec says 1 2 3! */ #define HID_INPUT_REPORT 0 #define HID_OUTPUT_REPORT 1 #define HID_FEATURE_REPORT 2 #define HID_REPORT_TYPES 3 /* * HID connect requests */ #define HID_CONNECT_HIDINPUT 0x01 #define HID_CONNECT_HIDINPUT_FORCE 0x02 #define HID_CONNECT_HIDRAW 0x04 #define HID_CONNECT_HIDDEV 0x08 #define HID_CONNECT_HIDDEV_FORCE 0x10 #define HID_CONNECT_FF 0x20 #define HID_CONNECT_DRIVER 0x40 #define HID_CONNECT_DEFAULT (HID_CONNECT_HIDINPUT|HID_CONNECT_HIDRAW| \ HID_CONNECT_HIDDEV|HID_CONNECT_FF) /* * HID device quirks. */ /* * Increase this if you need to configure more HID quirks at module load time */ #define MAX_USBHID_BOOT_QUIRKS 4 #define HID_QUIRK_INVERT 0x00000001 #define HID_QUIRK_NOTOUCH 0x00000002 #define HID_QUIRK_IGNORE 0x00000004 #define HID_QUIRK_NOGET 0x00000008 #define HID_QUIRK_HIDDEV_FORCE 0x00000010 #define HID_QUIRK_BADPAD 0x00000020 #define HID_QUIRK_MULTI_INPUT 0x00000040 #define HID_QUIRK_HIDINPUT_FORCE 0x00000080 #define HID_QUIRK_NO_EMPTY_INPUT 0x00000100 /* 0x00000200 reserved for backward compatibility, was NO_INIT_INPUT_REPORTS */ #define HID_QUIRK_ALWAYS_POLL 0x00000400 #define HID_QUIRK_SKIP_OUTPUT_REPORTS 0x00010000 #define HID_QUIRK_SKIP_OUTPUT_REPORT_ID 0x00020000 #define HID_QUIRK_NO_OUTPUT_REPORTS_ON_INTR_EP 0x00040000 #define HID_QUIRK_FULLSPEED_INTERVAL 0x10000000 #define HID_QUIRK_NO_INIT_REPORTS 0x20000000 #define HID_QUIRK_NO_IGNORE 0x40000000 #define HID_QUIRK_NO_INPUT_SYNC 0x80000000 /* * HID device groups * * Note: HID_GROUP_ANY is declared in linux/mod_devicetable.h * and has a value of 0x0000 */ #define HID_GROUP_GENERIC 0x0001 #define HID_GROUP_MULTITOUCH 0x0002 #define HID_GROUP_SENSOR_HUB 0x0003 #define HID_GROUP_MULTITOUCH_WIN_8 0x0004 /* * Vendor specific HID device groups */ #define HID_GROUP_RMI 0x0100 #define HID_GROUP_WACOM 0x0101 #define HID_GROUP_LOGITECH_DJ_DEVICE 0x0102 /* * HID protocol status */ #define HID_REPORT_PROTOCOL 1 #define HID_BOOT_PROTOCOL 0 /* * This is the global environment of the parser. This information is * persistent for main-items. The global environment can be saved and * restored with PUSH/POP statements. */ struct hid_global { unsigned usage_page; __s32 logical_minimum; __s32 logical_maximum; __s32 physical_minimum; __s32 physical_maximum; __s32 unit_exponent; unsigned unit; unsigned report_id; unsigned report_size; unsigned report_count; }; /* * This is the local environment. It is persistent up the next main-item. */ #define HID_MAX_USAGES 12288 #define HID_DEFAULT_NUM_COLLECTIONS 16 struct hid_local { unsigned usage[HID_MAX_USAGES]; /* usage array */ u8 usage_size[HID_MAX_USAGES]; /* usage size array */ unsigned collection_index[HID_MAX_USAGES]; /* collection index array */ unsigned usage_index; unsigned usage_minimum; unsigned delimiter_depth; unsigned delimiter_branch; }; /* * This is the collection stack. We climb up the stack to determine * application and function of each field. */ struct hid_collection { unsigned type; unsigned usage; unsigned level; }; struct hid_usage { unsigned hid; /* hid usage code */ unsigned collection_index; /* index into collection array */ unsigned usage_index; /* index into usage array */ /* hidinput data */ __u16 code; /* input driver code */ __u8 type; /* input driver type */ __s8 hat_min; /* hat switch fun */ __s8 hat_max; /* ditto */ __s8 hat_dir; /* ditto */ }; struct hid_input; struct hid_field { unsigned physical; /* physical usage for this field */ unsigned logical; /* logical usage for this field */ unsigned application; /* application usage for this field */ struct hid_usage *usage; /* usage table for this function */ unsigned maxusage; /* maximum usage index */ unsigned flags; /* main-item flags (i.e. volatile,array,constant) */ unsigned report_offset; /* bit offset in the report */ unsigned report_size; /* size of this field in the report */ unsigned report_count; /* number of this field in the report */ unsigned report_type; /* (input,output,feature) */ __s32 *value; /* last known value(s) */ __s32 logical_minimum; __s32 logical_maximum; __s32 physical_minimum; __s32 physical_maximum; __s32 unit_exponent; unsigned unit; struct hid_report *report; /* associated report */ unsigned index; /* index into report->field[] */ /* hidinput data */ struct hid_input *hidinput; /* associated input structure */ __u16 dpad; /* dpad input code */ }; #define HID_MAX_FIELDS 256 struct hid_report { struct list_head list; unsigned id; /* id of this report */ unsigned type; /* report type */ struct hid_field *field[HID_MAX_FIELDS]; /* fields of the report */ unsigned maxfield; /* maximum valid field index */ unsigned size; /* size of the report (bits) */ struct hid_device *device; /* associated device */ }; #define HID_MAX_IDS 256 struct hid_report_enum { unsigned numbered; struct list_head report_list; struct hid_report *report_id_hash[HID_MAX_IDS]; }; #define HID_MIN_BUFFER_SIZE 64 /* make sure there is at least a packet size of space */ #define HID_MAX_BUFFER_SIZE 8192 /* 8kb */ #define HID_CONTROL_FIFO_SIZE 256 /* to init devices with >100 reports */ #define HID_OUTPUT_FIFO_SIZE 64 struct hid_control_fifo { unsigned char dir; struct hid_report *report; char *raw_report; }; struct hid_output_fifo { struct hid_report *report; char *raw_report; }; #define HID_CLAIMED_INPUT 1 #define HID_CLAIMED_HIDDEV 2 #define HID_CLAIMED_HIDRAW 4 #define HID_CLAIMED_DRIVER 8 #define HID_STAT_ADDED 1 #define HID_STAT_PARSED 2 struct hid_input { struct list_head list; struct hid_report *report; struct input_dev *input; bool registered; }; enum hid_type { HID_TYPE_OTHER = 0, HID_TYPE_USBMOUSE, HID_TYPE_USBNONE }; enum hid_battery_status { HID_BATTERY_UNKNOWN = 0, HID_BATTERY_QUERIED, /* Kernel explicitly queried battery strength */ HID_BATTERY_REPORTED, /* Device sent unsolicited battery strength report */ }; struct hid_driver; struct hid_ll_driver; struct hid_device { /* device report descriptor */ __u8 *dev_rdesc; unsigned dev_rsize; __u8 *rdesc; unsigned rsize; struct hid_collection *collection; /* List of HID collections */ unsigned collection_size; /* Number of allocated hid_collections */ unsigned maxcollection; /* Number of parsed collections */ unsigned maxapplication; /* Number of applications */ __u16 bus; /* BUS ID */ __u16 group; /* Report group */ __u32 vendor; /* Vendor ID */ __u32 product; /* Product ID */ __u32 version; /* HID version */ enum hid_type type; /* device type (mouse, kbd, ...) */ unsigned country; /* HID country */ struct hid_report_enum report_enum[HID_REPORT_TYPES]; struct work_struct led_work; /* delayed LED worker */ struct semaphore driver_input_lock; /* protects the current driver */ struct device dev; /* device */ struct hid_driver *driver; struct hid_ll_driver *ll_driver; struct mutex ll_open_lock; unsigned int ll_open_count; #ifdef CONFIG_HID_BATTERY_STRENGTH /* * Power supply information for HID devices which report * battery strength. power_supply was successfully registered if * battery is non-NULL. */ struct power_supply *battery; __s32 battery_capacity; __s32 battery_min; __s32 battery_max; __s32 battery_report_type; __s32 battery_report_id; enum hid_battery_status battery_status; bool battery_avoid_query; #endif unsigned int status; /* see STAT flags above */ unsigned claimed; /* Claimed by hidinput, hiddev? */ unsigned quirks; /* Various quirks the device can pull on us */ bool io_started; /* If IO has started */ struct list_head inputs; /* The list of inputs */ void *hiddev; /* The hiddev structure */ void *hidraw; char name[128]; /* Device name */ char phys[64]; /* Device physical location */ char uniq[64]; /* Device unique identifier (serial #) */ void *driver_data; /* temporary hid_ff handling (until moved to the drivers) */ int (*ff_init)(struct hid_device *); /* hiddev event handler */ int (*hiddev_connect)(struct hid_device *, unsigned int); void (*hiddev_disconnect)(struct hid_device *); void (*hiddev_hid_event) (struct hid_device *, struct hid_field *field, struct hid_usage *, __s32); void (*hiddev_report_event) (struct hid_device *, struct hid_report *); /* debugging support via debugfs */ unsigned short debug; struct dentry *debug_dir; struct dentry *debug_rdesc; struct dentry *debug_events; struct list_head debug_list; spinlock_t debug_list_lock; wait_queue_head_t debug_wait; }; #define to_hid_device(pdev) \ container_of(pdev, struct hid_device, dev) static inline void *hid_get_drvdata(struct hid_device *hdev) { return dev_get_drvdata(&hdev->dev); } static inline void hid_set_drvdata(struct hid_device *hdev, void *data) { dev_set_drvdata(&hdev->dev, data); } #define HID_GLOBAL_STACK_SIZE 4 #define HID_COLLECTION_STACK_SIZE 4 #define HID_SCAN_FLAG_MT_WIN_8 BIT(0) #define HID_SCAN_FLAG_VENDOR_SPECIFIC BIT(1) #define HID_SCAN_FLAG_GD_POINTER BIT(2) struct hid_parser { struct hid_global global; struct hid_global global_stack[HID_GLOBAL_STACK_SIZE]; unsigned global_stack_ptr; struct hid_local local; unsigned collection_stack[HID_COLLECTION_STACK_SIZE]; unsigned collection_stack_ptr; struct hid_device *device; unsigned scan_flags; }; struct hid_class_descriptor { __u8 bDescriptorType; __le16 wDescriptorLength; } __attribute__ ((packed)); struct hid_descriptor { __u8 bLength; __u8 bDescriptorType; __le16 bcdHID; __u8 bCountryCode; __u8 bNumDescriptors; struct hid_class_descriptor desc[1]; } __attribute__ ((packed)); #define HID_DEVICE(b, g, ven, prod) \ .bus = (b), .group = (g), .vendor = (ven), .product = (prod) #define HID_USB_DEVICE(ven, prod) \ .bus = BUS_USB, .vendor = (ven), .product = (prod) #define HID_BLUETOOTH_DEVICE(ven, prod) \ .bus = BUS_BLUETOOTH, .vendor = (ven), .product = (prod) #define HID_I2C_DEVICE(ven, prod) \ .bus = BUS_I2C, .vendor = (ven), .product = (prod) #define HID_REPORT_ID(rep) \ .report_type = (rep) #define HID_USAGE_ID(uhid, utype, ucode) \ .usage_hid = (uhid), .usage_type = (utype), .usage_code = (ucode) /* we don't want to catch types and codes equal to 0 */ #define HID_TERMINATOR (HID_ANY_ID - 1) struct hid_report_id { __u32 report_type; }; struct hid_usage_id { __u32 usage_hid; __u32 usage_type; __u32 usage_code; }; /** * struct hid_driver * @name: driver name (e.g. "Footech_bar-wheel") * @id_table: which devices is this driver for (must be non-NULL for probe * to be called) * @dyn_list: list of dynamically added device ids * @dyn_lock: lock protecting @dyn_list * @probe: new device inserted * @remove: device removed (NULL if not a hot-plug capable driver) * @report_table: on which reports to call raw_event (NULL means all) * @raw_event: if report in report_table, this hook is called (NULL means nop) * @usage_table: on which events to call event (NULL means all) * @event: if usage in usage_table, this hook is called (NULL means nop) * @report: this hook is called after parsing a report (NULL means nop) * @report_fixup: called before report descriptor parsing (NULL means nop) * @input_mapping: invoked on input registering before mapping an usage * @input_mapped: invoked on input registering after mapping an usage * @input_configured: invoked just before the device is registered * @feature_mapping: invoked on feature registering * @suspend: invoked on suspend (NULL means nop) * @resume: invoked on resume if device was not reset (NULL means nop) * @reset_resume: invoked on resume if device was reset (NULL means nop) * * probe should return -errno on error, or 0 on success. During probe, * input will not be passed to raw_event unless hid_device_io_start is * called. * * raw_event and event should return 0 on no action performed, 1 when no * further processing should be done and negative on error * * input_mapping shall return a negative value to completely ignore this usage * (e.g. doubled or invalid usage), zero to continue with parsing of this * usage by generic code (no special handling needed) or positive to skip * generic parsing (needed special handling which was done in the hook already) * input_mapped shall return negative to inform the layer that this usage * should not be considered for further processing or zero to notify that * no processing was performed and should be done in a generic manner * Both these functions may be NULL which means the same behavior as returning * zero from them. */ struct hid_driver { char *name; const struct hid_device_id *id_table; struct list_head dyn_list; spinlock_t dyn_lock; int (*probe)(struct hid_device *dev, const struct hid_device_id *id); void (*remove)(struct hid_device *dev); const struct hid_report_id *report_table; int (*raw_event)(struct hid_device *hdev, struct hid_report *report, u8 *data, int size); const struct hid_usage_id *usage_table; int (*event)(struct hid_device *hdev, struct hid_field *field, struct hid_usage *usage, __s32 value); void (*report)(struct hid_device *hdev, struct hid_report *report); __u8 *(*report_fixup)(struct hid_device *hdev, __u8 *buf, unsigned int *size); int (*input_mapping)(struct hid_device *hdev, struct hid_input *hidinput, struct hid_field *field, struct hid_usage *usage, unsigned long **bit, int *max); int (*input_mapped)(struct hid_device *hdev, struct hid_input *hidinput, struct hid_field *field, struct hid_usage *usage, unsigned long **bit, int *max); int (*input_configured)(struct hid_device *hdev, struct hid_input *hidinput); void (*feature_mapping)(struct hid_device *hdev, struct hid_field *field, struct hid_usage *usage); #ifdef CONFIG_PM int (*suspend)(struct hid_device *hdev, pm_message_t message); int (*resume)(struct hid_device *hdev); int (*reset_resume)(struct hid_device *hdev); #endif /* private: */ struct device_driver driver; }; #define to_hid_driver(pdrv) \ container_of(pdrv, struct hid_driver, driver) /** * hid_ll_driver - low level driver callbacks * @start: called on probe to start the device * @stop: called on remove * @open: called by input layer on open * @close: called by input layer on close * @parse: this method is called only once to parse the device data, * shouldn't allocate anything to not leak memory * @request: send report request to device (e.g. feature report) * @wait: wait for buffered io to complete (send/recv reports) * @raw_request: send raw report request to device (e.g. feature report) * @output_report: send output report to device * @idle: send idle request to device */ struct hid_ll_driver { int (*start)(struct hid_device *hdev); void (*stop)(struct hid_device *hdev); int (*open)(struct hid_device *hdev); void (*close)(struct hid_device *hdev); int (*power)(struct hid_device *hdev, int level); int (*parse)(struct hid_device *hdev); void (*request)(struct hid_device *hdev, struct hid_report *report, int reqtype); int (*wait)(struct hid_device *hdev); int (*raw_request) (struct hid_device *hdev, unsigned char reportnum, __u8 *buf, size_t len, unsigned char rtype, int reqtype); int (*output_report) (struct hid_device *hdev, __u8 *buf, size_t len); int (*idle)(struct hid_device *hdev, int report, int idle, int reqtype); }; extern struct hid_ll_driver i2c_hid_ll_driver; extern struct hid_ll_driver hidp_hid_driver; extern struct hid_ll_driver uhid_hid_driver; extern struct hid_ll_driver usb_hid_driver; static inline bool hid_is_using_ll_driver(struct hid_device *hdev, struct hid_ll_driver *driver) { return hdev->ll_driver == driver; } static inline bool hid_is_usb(struct hid_device *hdev) { return hid_is_using_ll_driver(hdev, &usb_hid_driver); } #define PM_HINT_FULLON 1<<5 #define PM_HINT_NORMAL 1<<1 /* Applications from HID Usage Tables 4/8/99 Version 1.1 */ /* We ignore a few input applications that are not widely used */ #define IS_INPUT_APPLICATION(a) (((a >= 0x00010000) && (a <= 0x00010008)) || (a == 0x00010080) || (a == 0x000c0001) || ((a >= 0x000d0002) && (a <= 0x000d0006))) /* HID core API */ extern int hid_debug; extern bool hid_ignore(struct hid_device *); extern int hid_add_device(struct hid_device *); extern void hid_destroy_device(struct hid_device *); extern int __must_check __hid_register_driver(struct hid_driver *, struct module *, const char *mod_name); /* use a define to avoid include chaining to get THIS_MODULE & friends */ #define hid_register_driver(driver) \ __hid_register_driver(driver, THIS_MODULE, KBUILD_MODNAME) extern void hid_unregister_driver(struct hid_driver *); /** * module_hid_driver() - Helper macro for registering a HID driver * @__hid_driver: hid_driver struct * * Helper macro for HID drivers which do not do anything special in module * init/exit. This eliminates a lot of boilerplate. Each module may only * use this macro once, and calling it replaces module_init() and module_exit() */ #define module_hid_driver(__hid_driver) \ module_driver(__hid_driver, hid_register_driver, \ hid_unregister_driver) extern void hidinput_hid_event(struct hid_device *, struct hid_field *, struct hid_usage *, __s32); extern void hidinput_report_event(struct hid_device *hid, struct hid_report *report); extern int hidinput_connect(struct hid_device *hid, unsigned int force); extern void hidinput_disconnect(struct hid_device *); int hid_set_field(struct hid_field *, unsigned, __s32); int hid_input_report(struct hid_device *, int type, u8 *, u32, int); int hidinput_find_field(struct hid_device *hid, unsigned int type, unsigned int code, struct hid_field **field); struct hid_field *hidinput_get_led_field(struct hid_device *hid); unsigned int hidinput_count_leds(struct hid_device *hid); __s32 hidinput_calc_abs_res(const struct hid_field *field, __u16 code); void hid_output_report(struct hid_report *report, __u8 *data); void __hid_request(struct hid_device *hid, struct hid_report *rep, int reqtype); u8 *hid_alloc_report_buf(struct hid_report *report, gfp_t flags); struct hid_device *hid_allocate_device(void); struct hid_report *hid_register_report(struct hid_device *device, unsigned type, unsigned id); int hid_parse_report(struct hid_device *hid, __u8 *start, unsigned size); struct hid_report *hid_validate_values(struct hid_device *hid, unsigned int type, unsigned int id, unsigned int field_index, unsigned int report_counts); int hid_open_report(struct hid_device *device); int hid_check_keys_pressed(struct hid_device *hid); int hid_connect(struct hid_device *hid, unsigned int connect_mask); void hid_disconnect(struct hid_device *hid); const struct hid_device_id *hid_match_id(struct hid_device *hdev, const struct hid_device_id *id); s32 hid_snto32(__u32 value, unsigned n); __u32 hid_field_extract(const struct hid_device *hid, __u8 *report, unsigned offset, unsigned n); /** * hid_device_io_start - enable HID input during probe, remove * * @hid - the device * * This should only be called during probe or remove and only be * called by the thread calling probe or remove. It will allow * incoming packets to be delivered to the driver. */ static inline void hid_device_io_start(struct hid_device *hid) { if (hid->io_started) { dev_warn(&hid->dev, "io already started\n"); return; } hid->io_started = true; up(&hid->driver_input_lock); } /** * hid_device_io_stop - disable HID input during probe, remove * * @hid - the device * * Should only be called after hid_device_io_start. It will prevent * incoming packets from going to the driver for the duration of * probe, remove. If called during probe, packets will still go to the * driver after probe is complete. This function should only be called * by the thread calling probe or remove. */ static inline void hid_device_io_stop(struct hid_device *hid) { if (!hid->io_started) { dev_warn(&hid->dev, "io already stopped\n"); return; } hid->io_started = false; down(&hid->driver_input_lock); } /** * hid_map_usage - map usage input bits * * @hidinput: hidinput which we are interested in * @usage: usage to fill in * @bit: pointer to input->{}bit (out parameter) * @max: maximal valid usage->code to consider later (out parameter) * @type: input event type (EV_KEY, EV_REL, ...) * @c: code which corresponds to this usage and type * * The value pointed to by @bit will be set to NULL if either @type is * an unhandled event type, or if @c is out of range for @type. This * can be used as an error condition. */ static inline void hid_map_usage(struct hid_input *hidinput, struct hid_usage *usage, unsigned long **bit, int *max, __u8 type, unsigned int c) { struct input_dev *input = hidinput->input; unsigned long *bmap = NULL; unsigned int limit = 0; switch (type) { case EV_ABS: bmap = input->absbit; limit = ABS_MAX; break; case EV_REL: bmap = input->relbit; limit = REL_MAX; break; case EV_KEY: bmap = input->keybit; limit = KEY_MAX; break; case EV_LED: bmap = input->ledbit; limit = LED_MAX; break; } if (unlikely(c > limit || !bmap)) { pr_warn_ratelimited("%s: Invalid code %d type %d\n", input->name, c, type); *bit = NULL; return; } usage->type = type; usage->code = c; *max = limit; *bit = bmap; } /** * hid_map_usage_clear - map usage input bits and clear the input bit * * The same as hid_map_usage, except the @c bit is also cleared in supported * bits (@bit). */ static inline void hid_map_usage_clear(struct hid_input *hidinput, struct hid_usage *usage, unsigned long **bit, int *max, __u8 type, __u16 c) { hid_map_usage(hidinput, usage, bit, max, type, c); if (*bit) clear_bit(usage->code, *bit); } /** * hid_parse - parse HW reports * * @hdev: hid device * * Call this from probe after you set up the device (if needed). Your * report_fixup will be called (if non-NULL) after reading raw report from * device before passing it to hid layer for real parsing. */ static inline int __must_check hid_parse(struct hid_device *hdev) { return hid_open_report(hdev); } int __must_check hid_hw_start(struct hid_device *hdev, unsigned int connect_mask); void hid_hw_stop(struct hid_device *hdev); int __must_check hid_hw_open(struct hid_device *hdev); void hid_hw_close(struct hid_device *hdev); /** * hid_hw_power - requests underlying HW to go into given power mode * * @hdev: hid device * @level: requested power level (one of %PM_HINT_* defines) * * This function requests underlying hardware to enter requested power * mode. */ static inline int hid_hw_power(struct hid_device *hdev, int level) { return hdev->ll_driver->power ? hdev->ll_driver->power(hdev, level) : 0; } /** * hid_hw_request - send report request to device * * @hdev: hid device * @report: report to send * @reqtype: hid request type */ static inline void hid_hw_request(struct hid_device *hdev, struct hid_report *report, int reqtype) { if (hdev->ll_driver->request) return hdev->ll_driver->request(hdev, report, reqtype); __hid_request(hdev, report, reqtype); } /** * hid_hw_raw_request - send report request to device * * @hdev: hid device * @reportnum: report ID * @buf: in/out data to transfer * @len: length of buf * @rtype: HID report type * @reqtype: HID_REQ_GET_REPORT or HID_REQ_SET_REPORT * * @return: count of data transfered, negative if error * * Same behavior as hid_hw_request, but with raw buffers instead. */ static inline int hid_hw_raw_request(struct hid_device *hdev, unsigned char reportnum, __u8 *buf, size_t len, unsigned char rtype, int reqtype) { if (len < 1 || len > HID_MAX_BUFFER_SIZE || !buf) return -EINVAL; return hdev->ll_driver->raw_request(hdev, reportnum, buf, len, rtype, reqtype); } /** * hid_hw_output_report - send output report to device * * @hdev: hid device * @buf: raw data to transfer * @len: length of buf * * @return: count of data transfered, negative if error */ static inline int hid_hw_output_report(struct hid_device *hdev, __u8 *buf, size_t len) { if (len < 1 || len > HID_MAX_BUFFER_SIZE || !buf) return -EINVAL; if (hdev->ll_driver->output_report) return hdev->ll_driver->output_report(hdev, buf, len); return -ENOSYS; } /** * hid_hw_idle - send idle request to device * * @hdev: hid device * @report: report to control * @idle: idle state * @reqtype: hid request type */ static inline int hid_hw_idle(struct hid_device *hdev, int report, int idle, int reqtype) { if (hdev->ll_driver->idle) return hdev->ll_driver->idle(hdev, report, idle, reqtype); return 0; } /** * hid_hw_wait - wait for buffered io to complete * * @hdev: hid device */ static inline void hid_hw_wait(struct hid_device *hdev) { if (hdev->ll_driver->wait) hdev->ll_driver->wait(hdev); } /** * hid_report_len - calculate the report length * * @report: the report we want to know the length */ static inline u32 hid_report_len(struct hid_report *report) { return DIV_ROUND_UP(report->size, 8) + (report->id > 0); } int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, u32 size, int interrupt); /* HID quirks API */ u32 usbhid_lookup_quirk(const u16 idVendor, const u16 idProduct); int usbhid_quirks_init(char **quirks_param); void usbhid_quirks_exit(void); #ifdef CONFIG_HID_PID int hid_pidff_init(struct hid_device *hid); #else #define hid_pidff_init NULL #endif #define dbg_hid(format, arg...) \ do { \ if (hid_debug) \ printk(KERN_DEBUG "%s: " format, __FILE__, ##arg); \ } while (0) #define hid_printk(level, hid, fmt, arg...) \ dev_printk(level, &(hid)->dev, fmt, ##arg) #define hid_emerg(hid, fmt, arg...) \ dev_emerg(&(hid)->dev, fmt, ##arg) #define hid_crit(hid, fmt, arg...) \ dev_crit(&(hid)->dev, fmt, ##arg) #define hid_alert(hid, fmt, arg...) \ dev_alert(&(hid)->dev, fmt, ##arg) #define hid_err(hid, fmt, arg...) \ dev_err(&(hid)->dev, fmt, ##arg) #define hid_notice(hid, fmt, arg...) \ dev_notice(&(hid)->dev, fmt, ##arg) #define hid_warn(hid, fmt, arg...) \ dev_warn(&(hid)->dev, fmt, ##arg) #define hid_info(hid, fmt, arg...) \ dev_info(&(hid)->dev, fmt, ##arg) #define hid_dbg(hid, fmt, arg...) \ dev_dbg(&(hid)->dev, fmt, ##arg) #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 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 | /* * Copyright (c) 2004 Mellanox Technologies Ltd. All rights reserved. * Copyright (c) 2004 Infinicon Corporation. All rights reserved. * Copyright (c) 2004 Intel Corporation. All rights reserved. * Copyright (c) 2004 Topspin Corporation. All rights reserved. * Copyright (c) 2004 Voltaire Corporation. All rights reserved. * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved. * Copyright (c) 2005, 2006, 2007 Cisco Systems. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ #if !defined(IB_VERBS_H) #define IB_VERBS_H #include <linux/types.h> #include <linux/device.h> #include <linux/mm.h> #include <linux/dma-mapping.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/rwsem.h> #include <linux/scatterlist.h> #include <linux/workqueue.h> #include <linux/socket.h> #include <linux/irq_poll.h> #include <uapi/linux/if_ether.h> #include <net/ipv6.h> #include <net/ip.h> #include <linux/string.h> #include <linux/slab.h> #include <linux/netdevice.h> #include <linux/if_link.h> #include <linux/atomic.h> #include <linux/mmu_notifier.h> #include <linux/uaccess.h> #include <linux/cgroup_rdma.h> #include <uapi/rdma/ib_user_verbs.h> #define IB_FW_VERSION_NAME_MAX ETHTOOL_FWVERS_LEN extern struct workqueue_struct *ib_wq; extern struct workqueue_struct *ib_comp_wq; extern struct workqueue_struct *ib_comp_unbound_wq; union ib_gid { u8 raw[16]; struct { __be64 subnet_prefix; __be64 interface_id; } global; }; extern union ib_gid zgid; enum ib_gid_type { /* If link layer is Ethernet, this is RoCE V1 */ IB_GID_TYPE_IB = 0, IB_GID_TYPE_ROCE = 0, IB_GID_TYPE_ROCE_UDP_ENCAP = 1, IB_GID_TYPE_SIZE }; #define ROCE_V2_UDP_DPORT 4791 struct ib_gid_attr { enum ib_gid_type gid_type; struct net_device *ndev; }; enum rdma_node_type { /* IB values map to NodeInfo:NodeType. */ RDMA_NODE_IB_CA = 1, RDMA_NODE_IB_SWITCH, RDMA_NODE_IB_ROUTER, RDMA_NODE_RNIC, RDMA_NODE_USNIC, RDMA_NODE_USNIC_UDP, }; enum { /* set the local administered indication */ IB_SA_WELL_KNOWN_GUID = BIT_ULL(57) | 2, }; enum rdma_transport_type { RDMA_TRANSPORT_IB, RDMA_TRANSPORT_IWARP, RDMA_TRANSPORT_USNIC, RDMA_TRANSPORT_USNIC_UDP }; enum rdma_protocol_type { RDMA_PROTOCOL_IB, RDMA_PROTOCOL_IBOE, RDMA_PROTOCOL_IWARP, RDMA_PROTOCOL_USNIC_UDP }; __attribute_const__ enum rdma_transport_type rdma_node_get_transport(enum rdma_node_type node_type); enum rdma_network_type { RDMA_NETWORK_IB, RDMA_NETWORK_ROCE_V1 = RDMA_NETWORK_IB, RDMA_NETWORK_IPV4, RDMA_NETWORK_IPV6 }; static inline enum ib_gid_type ib_network_to_gid_type(enum rdma_network_type network_type) { if (network_type == RDMA_NETWORK_IPV4 || network_type == RDMA_NETWORK_IPV6) return IB_GID_TYPE_ROCE_UDP_ENCAP; /* IB_GID_TYPE_IB same as RDMA_NETWORK_ROCE_V1 */ return IB_GID_TYPE_IB; } static inline enum rdma_network_type ib_gid_to_network_type(enum ib_gid_type gid_type, union ib_gid *gid) { if (gid_type == IB_GID_TYPE_IB) return RDMA_NETWORK_IB; if (ipv6_addr_v4mapped((struct in6_addr *)gid)) return RDMA_NETWORK_IPV4; else return RDMA_NETWORK_IPV6; } enum rdma_link_layer { IB_LINK_LAYER_UNSPECIFIED, IB_LINK_LAYER_INFINIBAND, IB_LINK_LAYER_ETHERNET, }; enum ib_device_cap_flags { IB_DEVICE_RESIZE_MAX_WR = (1 << 0), IB_DEVICE_BAD_PKEY_CNTR = (1 << 1), IB_DEVICE_BAD_QKEY_CNTR = (1 << 2), IB_DEVICE_RAW_MULTI = (1 << 3), IB_DEVICE_AUTO_PATH_MIG = (1 << 4), IB_DEVICE_CHANGE_PHY_PORT = (1 << 5), IB_DEVICE_UD_AV_PORT_ENFORCE = (1 << 6), IB_DEVICE_CURR_QP_STATE_MOD = (1 << 7), IB_DEVICE_SHUTDOWN_PORT = (1 << 8), /* Not in use, former INIT_TYPE = (1 << 9),*/ IB_DEVICE_PORT_ACTIVE_EVENT = (1 << 10), IB_DEVICE_SYS_IMAGE_GUID = (1 << 11), IB_DEVICE_RC_RNR_NAK_GEN = (1 << 12), IB_DEVICE_SRQ_RESIZE = (1 << 13), IB_DEVICE_N_NOTIFY_CQ = (1 << 14), /* * This device supports a per-device lkey or stag that can be * used without performing a memory registration for the local * memory. Note that ULPs should never check this flag, but * instead of use the local_dma_lkey flag in the ib_pd structure, * which will always contain a usable lkey. */ IB_DEVICE_LOCAL_DMA_LKEY = (1 << 15), /* Reserved, old SEND_W_INV = (1 << 16),*/ IB_DEVICE_MEM_WINDOW = (1 << 17), /* * Devices should set IB_DEVICE_UD_IP_SUM if they support * insertion of UDP and TCP checksum on outgoing UD IPoIB * messages and can verify the validity of checksum for * incoming messages. Setting this flag implies that the * IPoIB driver may set NETIF_F_IP_CSUM for datagram mode. */ IB_DEVICE_UD_IP_CSUM = (1 << 18), IB_DEVICE_UD_TSO = (1 << 19), IB_DEVICE_XRC = (1 << 20), /* * This device supports the IB "base memory management extension", * which includes support for fast registrations (IB_WR_REG_MR, * IB_WR_LOCAL_INV and IB_WR_SEND_WITH_INV verbs). This flag should * also be set by any iWarp device which must support FRs to comply * to the iWarp verbs spec. iWarp devices also support the * IB_WR_RDMA_READ_WITH_INV verb for RDMA READs that invalidate the * stag. */ IB_DEVICE_MEM_MGT_EXTENSIONS = (1 << 21), IB_DEVICE_BLOCK_MULTICAST_LOOPBACK = (1 << 22), IB_DEVICE_MEM_WINDOW_TYPE_2A = (1 << 23), IB_DEVICE_MEM_WINDOW_TYPE_2B = (1 << 24), IB_DEVICE_RC_IP_CSUM = (1 << 25), /* Deprecated. Please use IB_RAW_PACKET_CAP_IP_CSUM. */ IB_DEVICE_RAW_IP_CSUM = (1 << 26), /* * Devices should set IB_DEVICE_CROSS_CHANNEL if they * support execution of WQEs that involve synchronization * of I/O operations with single completion queue managed * by hardware. */ IB_DEVICE_CROSS_CHANNEL = (1 << 27), IB_DEVICE_MANAGED_FLOW_STEERING = (1 << 29), IB_DEVICE_SIGNATURE_HANDOVER = (1 << 30), IB_DEVICE_ON_DEMAND_PAGING = (1ULL << 31), IB_DEVICE_SG_GAPS_REG = (1ULL << 32), IB_DEVICE_VIRTUAL_FUNCTION = (1ULL << 33), /* Deprecated. Please use IB_RAW_PACKET_CAP_SCATTER_FCS. */ IB_DEVICE_RAW_SCATTER_FCS = (1ULL << 34), IB_DEVICE_RDMA_NETDEV_OPA_VNIC = (1ULL << 35), }; enum ib_signature_prot_cap { IB_PROT_T10DIF_TYPE_1 = 1, IB_PROT_T10DIF_TYPE_2 = 1 << 1, IB_PROT_T10DIF_TYPE_3 = 1 << 2, }; enum ib_signature_guard_cap { IB_GUARD_T10DIF_CRC = 1, IB_GUARD_T10DIF_CSUM = 1 << 1, }; enum ib_atomic_cap { IB_ATOMIC_NONE, IB_ATOMIC_HCA, IB_ATOMIC_GLOB }; enum ib_odp_general_cap_bits { IB_ODP_SUPPORT = 1 << 0, IB_ODP_SUPPORT_IMPLICIT = 1 << 1, }; enum ib_odp_transport_cap_bits { IB_ODP_SUPPORT_SEND = 1 << 0, IB_ODP_SUPPORT_RECV = 1 << 1, IB_ODP_SUPPORT_WRITE = 1 << 2, IB_ODP_SUPPORT_READ = 1 << 3, IB_ODP_SUPPORT_ATOMIC = 1 << 4, }; struct ib_odp_caps { uint64_t general_caps; struct { uint32_t rc_odp_caps; uint32_t uc_odp_caps; uint32_t ud_odp_caps; } per_transport_caps; }; struct ib_rss_caps { /* Corresponding bit will be set if qp type from * 'enum ib_qp_type' is supported, e.g. * supported_qpts |= 1 << IB_QPT_UD */ u32 supported_qpts; u32 max_rwq_indirection_tables; u32 max_rwq_indirection_table_size; }; enum ib_tm_cap_flags { /* Support tag matching on RC transport */ IB_TM_CAP_RC = 1 << 0, }; struct ib_tm_caps { /* Max size of RNDV header */ u32 max_rndv_hdr_size; /* Max number of entries in tag matching list */ u32 max_num_tags; /* From enum ib_tm_cap_flags */ u32 flags; /* Max number of outstanding list operations */ u32 max_ops; /* Max number of SGE in tag matching entry */ u32 max_sge; }; enum ib_cq_creation_flags { IB_CQ_FLAGS_TIMESTAMP_COMPLETION = 1 << 0, IB_CQ_FLAGS_IGNORE_OVERRUN = 1 << 1, }; struct ib_cq_init_attr { unsigned int cqe; u32 comp_vector; u32 flags; }; struct ib_device_attr { u64 fw_ver; __be64 sys_image_guid; u64 max_mr_size; u64 page_size_cap; u32 vendor_id; u32 vendor_part_id; u32 hw_ver; int max_qp; int max_qp_wr; u64 device_cap_flags; int max_sge; int max_sge_rd; int max_cq; int max_cqe; int max_mr; int max_pd; int max_qp_rd_atom; int max_ee_rd_atom; int max_res_rd_atom; int max_qp_init_rd_atom; int max_ee_init_rd_atom; enum ib_atomic_cap atomic_cap; enum ib_atomic_cap masked_atomic_cap; int max_ee; int max_rdd; int max_mw; int max_raw_ipv6_qp; int max_raw_ethy_qp; int max_mcast_grp; int max_mcast_qp_attach; int max_total_mcast_qp_attach; int max_ah; int max_fmr; int max_map_per_fmr; int max_srq; int max_srq_wr; int max_srq_sge; unsigned int max_fast_reg_page_list_len; u16 max_pkeys; u8 local_ca_ack_delay; int sig_prot_cap; int sig_guard_cap; struct ib_odp_caps odp_caps; uint64_t timestamp_mask; uint64_t hca_core_clock; /* in KHZ */ struct ib_rss_caps rss_caps; u32 max_wq_type_rq; u32 raw_packet_caps; /* Use ib_raw_packet_caps enum */ struct ib_tm_caps tm_caps; }; enum ib_mtu { IB_MTU_256 = 1, IB_MTU_512 = 2, IB_MTU_1024 = 3, IB_MTU_2048 = 4, IB_MTU_4096 = 5 }; static inline int ib_mtu_enum_to_int(enum ib_mtu mtu) { switch (mtu) { case IB_MTU_256: return 256; case IB_MTU_512: return 512; case IB_MTU_1024: return 1024; case IB_MTU_2048: return 2048; case IB_MTU_4096: return 4096; default: return -1; } } static inline enum ib_mtu ib_mtu_int_to_enum(int mtu) { if (mtu >= 4096) return IB_MTU_4096; else if (mtu >= 2048) return IB_MTU_2048; else if (mtu >= 1024) return IB_MTU_1024; else if (mtu >= 512) return IB_MTU_512; else return IB_MTU_256; } enum ib_port_state { IB_PORT_NOP = 0, IB_PORT_DOWN = 1, IB_PORT_INIT = 2, IB_PORT_ARMED = 3, IB_PORT_ACTIVE = 4, IB_PORT_ACTIVE_DEFER = 5 }; enum ib_port_cap_flags { IB_PORT_SM = 1 << 1, IB_PORT_NOTICE_SUP = 1 << 2, IB_PORT_TRAP_SUP = 1 << 3, IB_PORT_OPT_IPD_SUP = 1 << 4, IB_PORT_AUTO_MIGR_SUP = 1 << 5, IB_PORT_SL_MAP_SUP = 1 << 6, IB_PORT_MKEY_NVRAM = 1 << 7, IB_PORT_PKEY_NVRAM = 1 << 8, IB_PORT_LED_INFO_SUP = 1 << 9, IB_PORT_SM_DISABLED = 1 << 10, IB_PORT_SYS_IMAGE_GUID_SUP = 1 << 11, IB_PORT_PKEY_SW_EXT_PORT_TRAP_SUP = 1 << 12, IB_PORT_EXTENDED_SPEEDS_SUP = 1 << 14, IB_PORT_CM_SUP = 1 << 16, IB_PORT_SNMP_TUNNEL_SUP = 1 << 17, IB_PORT_REINIT_SUP = 1 << 18, IB_PORT_DEVICE_MGMT_SUP = 1 << 19, IB_PORT_VENDOR_CLASS_SUP = 1 << 20, IB_PORT_DR_NOTICE_SUP = 1 << 21, IB_PORT_CAP_MASK_NOTICE_SUP = 1 << 22, IB_PORT_BOOT_MGMT_SUP = 1 << 23, IB_PORT_LINK_LATENCY_SUP = 1 << 24, IB_PORT_CLIENT_REG_SUP = 1 << 25, IB_PORT_IP_BASED_GIDS = 1 << 26, }; enum ib_port_width { IB_WIDTH_1X = 1, IB_WIDTH_4X = 2, IB_WIDTH_8X = 4, IB_WIDTH_12X = 8 }; static inline int ib_width_enum_to_int(enum ib_port_width width) { switch (width) { case IB_WIDTH_1X: return 1; case IB_WIDTH_4X: return 4; case IB_WIDTH_8X: return 8; case IB_WIDTH_12X: return 12; default: return -1; } } enum ib_port_speed { IB_SPEED_SDR = 1, IB_SPEED_DDR = 2, IB_SPEED_QDR = 4, IB_SPEED_FDR10 = 8, IB_SPEED_FDR = 16, IB_SPEED_EDR = 32, IB_SPEED_HDR = 64 }; /** * struct rdma_hw_stats * @timestamp - Used by the core code to track when the last update was * @lifespan - Used by the core code to determine how old the counters * should be before being updated again. Stored in jiffies, defaults * to 10 milliseconds, drivers can override the default be specifying * their own value during their allocation routine. * @name - Array of pointers to static names used for the counters in * directory. * @num_counters - How many hardware counters there are. If name is * shorter than this number, a kernel oops will result. Driver authors * are encouraged to leave BUILD_BUG_ON(ARRAY_SIZE(@name) < num_counters) * in their code to prevent this. * @value - Array of u64 counters that are accessed by the sysfs code and * filled in by the drivers get_stats routine */ struct rdma_hw_stats { unsigned long timestamp; unsigned long lifespan; const char * const *names; int num_counters; u64 value[]; }; #define RDMA_HW_STATS_DEFAULT_LIFESPAN 10 /** * rdma_alloc_hw_stats_struct - Helper function to allocate dynamic struct * for drivers. * @names - Array of static const char * * @num_counters - How many elements in array * @lifespan - How many milliseconds between updates */ static inline struct rdma_hw_stats *rdma_alloc_hw_stats_struct( const char * const *names, int num_counters, unsigned long lifespan) { struct rdma_hw_stats *stats; stats = kzalloc(sizeof(*stats) + num_counters * sizeof(u64), GFP_KERNEL); if (!stats) return NULL; stats->names = names; stats->num_counters = num_counters; stats->lifespan = msecs_to_jiffies(lifespan); return stats; } /* Define bits for the various functionality this port needs to be supported by * the core. */ /* Management 0x00000FFF */ #define RDMA_CORE_CAP_IB_MAD 0x00000001 #define RDMA_CORE_CAP_IB_SMI 0x00000002 #define RDMA_CORE_CAP_IB_CM 0x00000004 #define RDMA_CORE_CAP_IW_CM 0x00000008 #define RDMA_CORE_CAP_IB_SA 0x00000010 #define RDMA_CORE_CAP_OPA_MAD 0x00000020 /* Address format 0x000FF000 */ #define RDMA_CORE_CAP_AF_IB 0x00001000 #define RDMA_CORE_CAP_ETH_AH 0x00002000 #define RDMA_CORE_CAP_OPA_AH 0x00004000 /* Protocol 0xFFF00000 */ #define RDMA_CORE_CAP_PROT_IB 0x00100000 #define RDMA_CORE_CAP_PROT_ROCE 0x00200000 #define RDMA_CORE_CAP_PROT_IWARP 0x00400000 #define RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP 0x00800000 #define RDMA_CORE_CAP_PROT_RAW_PACKET 0x01000000 #define RDMA_CORE_CAP_PROT_USNIC 0x02000000 #define RDMA_CORE_PORT_IBA_IB (RDMA_CORE_CAP_PROT_IB \ | RDMA_CORE_CAP_IB_MAD \ | RDMA_CORE_CAP_IB_SMI \ | RDMA_CORE_CAP_IB_CM \ | RDMA_CORE_CAP_IB_SA \ | RDMA_CORE_CAP_AF_IB) #define RDMA_CORE_PORT_IBA_ROCE (RDMA_CORE_CAP_PROT_ROCE \ | RDMA_CORE_CAP_IB_MAD \ | RDMA_CORE_CAP_IB_CM \ | RDMA_CORE_CAP_AF_IB \ | RDMA_CORE_CAP_ETH_AH) #define RDMA_CORE_PORT_IBA_ROCE_UDP_ENCAP \ (RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP \ | RDMA_CORE_CAP_IB_MAD \ | RDMA_CORE_CAP_IB_CM \ | RDMA_CORE_CAP_AF_IB \ | RDMA_CORE_CAP_ETH_AH) #define RDMA_CORE_PORT_IWARP (RDMA_CORE_CAP_PROT_IWARP \ | RDMA_CORE_CAP_IW_CM) #define RDMA_CORE_PORT_INTEL_OPA (RDMA_CORE_PORT_IBA_IB \ | RDMA_CORE_CAP_OPA_MAD) #define RDMA_CORE_PORT_RAW_PACKET (RDMA_CORE_CAP_PROT_RAW_PACKET) #define RDMA_CORE_PORT_USNIC (RDMA_CORE_CAP_PROT_USNIC) struct ib_port_attr { u64 subnet_prefix; enum ib_port_state state; enum ib_mtu max_mtu; enum ib_mtu active_mtu; int gid_tbl_len; u32 port_cap_flags; u32 max_msg_sz; u32 bad_pkey_cntr; u32 qkey_viol_cntr; u16 pkey_tbl_len; u32 sm_lid; u32 lid; u8 lmc; u8 max_vl_num; u8 sm_sl; u8 subnet_timeout; u8 init_type_reply; u8 active_width; u8 active_speed; u8 phys_state; bool grh_required; }; enum ib_device_modify_flags { IB_DEVICE_MODIFY_SYS_IMAGE_GUID = 1 << 0, IB_DEVICE_MODIFY_NODE_DESC = 1 << 1 }; #define IB_DEVICE_NODE_DESC_MAX 64 struct ib_device_modify { u64 sys_image_guid; char node_desc[IB_DEVICE_NODE_DESC_MAX]; }; enum ib_port_modify_flags { IB_PORT_SHUTDOWN = 1, IB_PORT_INIT_TYPE = (1<<2), IB_PORT_RESET_QKEY_CNTR = (1<<3), IB_PORT_OPA_MASK_CHG = (1<<4) }; struct ib_port_modify { u32 set_port_cap_mask; u32 clr_port_cap_mask; u8 init_type; }; enum ib_event_type { IB_EVENT_CQ_ERR, IB_EVENT_QP_FATAL, IB_EVENT_QP_REQ_ERR, IB_EVENT_QP_ACCESS_ERR, IB_EVENT_COMM_EST, IB_EVENT_SQ_DRAINED, IB_EVENT_PATH_MIG, IB_EVENT_PATH_MIG_ERR, IB_EVENT_DEVICE_FATAL, IB_EVENT_PORT_ACTIVE, IB_EVENT_PORT_ERR, IB_EVENT_LID_CHANGE, IB_EVENT_PKEY_CHANGE, IB_EVENT_SM_CHANGE, IB_EVENT_SRQ_ERR, IB_EVENT_SRQ_LIMIT_REACHED, IB_EVENT_QP_LAST_WQE_REACHED, IB_EVENT_CLIENT_REREGISTER, IB_EVENT_GID_CHANGE, IB_EVENT_WQ_FATAL, }; const char *__attribute_const__ ib_event_msg(enum ib_event_type event); struct ib_event { struct ib_device *device; union { struct ib_cq *cq; struct ib_qp *qp; struct ib_srq *srq; struct ib_wq *wq; u8 port_num; } element; enum ib_event_type event; }; struct ib_event_handler { struct ib_device *device; void (*handler)(struct ib_event_handler *, struct ib_event *); struct list_head list; }; #define INIT_IB_EVENT_HANDLER(_ptr, _device, _handler) \ do { \ (_ptr)->device = _device; \ (_ptr)->handler = _handler; \ INIT_LIST_HEAD(&(_ptr)->list); \ } while (0) struct ib_global_route { union ib_gid dgid; u32 flow_label; u8 sgid_index; u8 hop_limit; u8 traffic_class; }; struct ib_grh { __be32 version_tclass_flow; __be16 paylen; u8 next_hdr; u8 hop_limit; union ib_gid sgid; union ib_gid dgid; }; union rdma_network_hdr { struct ib_grh ibgrh; struct { /* The IB spec states that if it's IPv4, the header * is located in the last 20 bytes of the header. */ u8 reserved[20]; struct iphdr roce4grh; }; }; #define IB_QPN_MASK 0xFFFFFF enum { IB_MULTICAST_QPN = 0xffffff }; #define IB_LID_PERMISSIVE cpu_to_be16(0xFFFF) #define IB_MULTICAST_LID_BASE cpu_to_be16(0xC000) enum ib_ah_flags { IB_AH_GRH = 1 }; enum ib_rate { IB_RATE_PORT_CURRENT = 0, IB_RATE_2_5_GBPS = 2, IB_RATE_5_GBPS = 5, IB_RATE_10_GBPS = 3, IB_RATE_20_GBPS = 6, IB_RATE_30_GBPS = 4, IB_RATE_40_GBPS = 7, IB_RATE_60_GBPS = 8, IB_RATE_80_GBPS = 9, IB_RATE_120_GBPS = 10, IB_RATE_14_GBPS = 11, IB_RATE_56_GBPS = 12, IB_RATE_112_GBPS = 13, IB_RATE_168_GBPS = 14, IB_RATE_25_GBPS = 15, IB_RATE_100_GBPS = 16, IB_RATE_200_GBPS = 17, IB_RATE_300_GBPS = 18 }; /** * ib_rate_to_mult - Convert the IB rate enum to a multiple of the * base rate of 2.5 Gbit/sec. For example, IB_RATE_5_GBPS will be * converted to 2, since 5 Gbit/sec is 2 * 2.5 Gbit/sec. * @rate: rate to convert. */ __attribute_const__ int ib_rate_to_mult(enum ib_rate rate); /** * ib_rate_to_mbps - Convert the IB rate enum to Mbps. * For example, IB_RATE_2_5_GBPS will be converted to 2500. * @rate: rate to convert. */ __attribute_const__ int ib_rate_to_mbps(enum ib_rate rate); /** * enum ib_mr_type - memory region type * @IB_MR_TYPE_MEM_REG: memory region that is used for * normal registration * @IB_MR_TYPE_SIGNATURE: memory region that is used for * signature operations (data-integrity * capable regions) * @IB_MR_TYPE_SG_GAPS: memory region that is capable to * register any arbitrary sg lists (without * the normal mr constraints - see * ib_map_mr_sg) */ enum ib_mr_type { IB_MR_TYPE_MEM_REG, IB_MR_TYPE_SIGNATURE, IB_MR_TYPE_SG_GAPS, }; /** * Signature types * IB_SIG_TYPE_NONE: Unprotected. * IB_SIG_TYPE_T10_DIF: Type T10-DIF */ enum ib_signature_type { IB_SIG_TYPE_NONE, IB_SIG_TYPE_T10_DIF, }; /** * Signature T10-DIF block-guard types * IB_T10DIF_CRC: Corresponds to T10-PI mandated CRC checksum rules. * IB_T10DIF_CSUM: Corresponds to IP checksum rules. */ enum ib_t10_dif_bg_type { IB_T10DIF_CRC, IB_T10DIF_CSUM }; /** * struct ib_t10_dif_domain - Parameters specific for T10-DIF * domain. * @bg_type: T10-DIF block guard type (CRC|CSUM) * @pi_interval: protection information interval. * @bg: seed of guard computation. * @app_tag: application tag of guard block * @ref_tag: initial guard block reference tag. * @ref_remap: Indicate wethear the reftag increments each block * @app_escape: Indicate to skip block check if apptag=0xffff * @ref_escape: Indicate to skip block check if reftag=0xffffffff * @apptag_check_mask: check bitmask of application tag. */ struct ib_t10_dif_domain { enum ib_t10_dif_bg_type bg_type; u16 pi_interval; u16 bg; u16 app_tag; u32 ref_tag; bool ref_remap; bool app_escape; bool ref_escape; u16 apptag_check_mask; }; /** * struct ib_sig_domain - Parameters for signature domain * @sig_type: specific signauture type * @sig: union of all signature domain attributes that may * be used to set domain layout. */ struct ib_sig_domain { enum ib_signature_type sig_type; union { struct ib_t10_dif_domain dif; } sig; }; /** * struct ib_sig_attrs - Parameters for signature handover operation * @check_mask: bitmask for signature byte check (8 bytes) * @mem: memory domain layout desciptor. * @wire: wire domain layout desciptor. */ struct ib_sig_attrs { u8 check_mask; struct ib_sig_domain mem; struct ib_sig_domain wire; }; enum ib_sig_err_type { IB_SIG_BAD_GUARD, IB_SIG_BAD_REFTAG, IB_SIG_BAD_APPTAG, }; /** * struct ib_sig_err - signature error descriptor */ struct ib_sig_err { enum ib_sig_err_type err_type; u32 expected; u32 actual; u64 sig_err_offset; u32 key; }; enum ib_mr_status_check { IB_MR_CHECK_SIG_STATUS = 1, }; /** * struct ib_mr_status - Memory region status container * * @fail_status: Bitmask of MR checks status. For each * failed check a corresponding status bit is set. * @sig_err: Additional info for IB_MR_CEHCK_SIG_STATUS * failure. */ struct ib_mr_status { u32 fail_status; struct ib_sig_err sig_err; }; /** * mult_to_ib_rate - Convert a multiple of 2.5 Gbit/sec to an IB rate * enum. * @mult: multiple to convert. */ __attribute_const__ enum ib_rate mult_to_ib_rate(int mult); enum rdma_ah_attr_type { RDMA_AH_ATTR_TYPE_UNDEFINED, RDMA_AH_ATTR_TYPE_IB, RDMA_AH_ATTR_TYPE_ROCE, RDMA_AH_ATTR_TYPE_OPA, }; struct ib_ah_attr { u16 dlid; u8 src_path_bits; }; struct roce_ah_attr { u8 dmac[ETH_ALEN]; }; struct opa_ah_attr { u32 dlid; u8 src_path_bits; bool make_grd; }; struct rdma_ah_attr { struct ib_global_route grh; u8 sl; u8 static_rate; u8 port_num; u8 ah_flags; enum rdma_ah_attr_type type; union { struct ib_ah_attr ib; struct roce_ah_attr roce; struct opa_ah_attr opa; }; }; enum ib_wc_status { IB_WC_SUCCESS, IB_WC_LOC_LEN_ERR, IB_WC_LOC_QP_OP_ERR, IB_WC_LOC_EEC_OP_ERR, IB_WC_LOC_PROT_ERR, IB_WC_WR_FLUSH_ERR, IB_WC_MW_BIND_ERR, IB_WC_BAD_RESP_ERR, IB_WC_LOC_ACCESS_ERR, IB_WC_REM_INV_REQ_ERR, IB_WC_REM_ACCESS_ERR, IB_WC_REM_OP_ERR, IB_WC_RETRY_EXC_ERR, IB_WC_RNR_RETRY_EXC_ERR, IB_WC_LOC_RDD_VIOL_ERR, IB_WC_REM_INV_RD_REQ_ERR, IB_WC_REM_ABORT_ERR, IB_WC_INV_EECN_ERR, IB_WC_INV_EEC_STATE_ERR, IB_WC_FATAL_ERR, IB_WC_RESP_TIMEOUT_ERR, IB_WC_GENERAL_ERR }; const char *__attribute_const__ ib_wc_status_msg(enum ib_wc_status status); enum ib_wc_opcode { IB_WC_SEND, IB_WC_RDMA_WRITE, IB_WC_RDMA_READ, IB_WC_COMP_SWAP, IB_WC_FETCH_ADD, IB_WC_LSO, IB_WC_LOCAL_INV, IB_WC_REG_MR, IB_WC_MASKED_COMP_SWAP, IB_WC_MASKED_FETCH_ADD, /* * Set value of IB_WC_RECV so consumers can test if a completion is a * receive by testing (opcode & IB_WC_RECV). */ IB_WC_RECV = 1 << 7, IB_WC_RECV_RDMA_WITH_IMM }; enum ib_wc_flags { IB_WC_GRH = 1, IB_WC_WITH_IMM = (1<<1), IB_WC_WITH_INVALIDATE = (1<<2), IB_WC_IP_CSUM_OK = (1<<3), IB_WC_WITH_SMAC = (1<<4), IB_WC_WITH_VLAN = (1<<5), IB_WC_WITH_NETWORK_HDR_TYPE = (1<<6), }; struct ib_wc { union { u64 wr_id; struct ib_cqe *wr_cqe; }; enum ib_wc_status status; enum ib_wc_opcode opcode; u32 vendor_err; u32 byte_len; struct ib_qp *qp; union { __be32 imm_data; u32 invalidate_rkey; } ex; u32 src_qp; u32 slid; int wc_flags; u16 pkey_index; u8 sl; u8 dlid_path_bits; u8 port_num; /* valid only for DR SMPs on switches */ u8 smac[ETH_ALEN]; u16 vlan_id; u8 network_hdr_type; }; enum ib_cq_notify_flags { IB_CQ_SOLICITED = 1 << 0, IB_CQ_NEXT_COMP = 1 << 1, IB_CQ_SOLICITED_MASK = IB_CQ_SOLICITED | IB_CQ_NEXT_COMP, IB_CQ_REPORT_MISSED_EVENTS = 1 << 2, }; enum ib_srq_type { IB_SRQT_BASIC, IB_SRQT_XRC, IB_SRQT_TM, }; static inline bool ib_srq_has_cq(enum ib_srq_type srq_type) { return srq_type == IB_SRQT_XRC || srq_type == IB_SRQT_TM; } enum ib_srq_attr_mask { IB_SRQ_MAX_WR = 1 << 0, IB_SRQ_LIMIT = 1 << 1, }; struct ib_srq_attr { u32 max_wr; u32 max_sge; u32 srq_limit; }; struct ib_srq_init_attr { void (*event_handler)(struct ib_event *, void *); void *srq_context; struct ib_srq_attr attr; enum ib_srq_type srq_type; struct { struct ib_cq *cq; union { struct { struct ib_xrcd *xrcd; } xrc; struct { u32 max_num_tags; } tag_matching; }; } ext; }; struct ib_qp_cap { u32 max_send_wr; u32 max_recv_wr; u32 max_send_sge; u32 max_recv_sge; u32 max_inline_data; /* * Maximum number of rdma_rw_ctx structures in flight at a time. * ib_create_qp() will calculate the right amount of neededed WRs * and MRs based on this. */ u32 max_rdma_ctxs; }; enum ib_sig_type { IB_SIGNAL_ALL_WR, IB_SIGNAL_REQ_WR }; enum ib_qp_type { /* * IB_QPT_SMI and IB_QPT_GSI have to be the first two entries * here (and in that order) since the MAD layer uses them as * indices into a 2-entry table. */ IB_QPT_SMI, IB_QPT_GSI, IB_QPT_RC, IB_QPT_UC, IB_QPT_UD, IB_QPT_RAW_IPV6, IB_QPT_RAW_ETHERTYPE, IB_QPT_RAW_PACKET = 8, IB_QPT_XRC_INI = 9, IB_QPT_XRC_TGT, IB_QPT_MAX, /* Reserve a range for qp types internal to the low level driver. * These qp types will not be visible at the IB core layer, so the * IB_QPT_MAX usages should not be affected in the core layer */ IB_QPT_RESERVED1 = 0x1000, IB_QPT_RESERVED2, IB_QPT_RESERVED3, IB_QPT_RESERVED4, IB_QPT_RESERVED5, IB_QPT_RESERVED6, IB_QPT_RESERVED7, IB_QPT_RESERVED8, IB_QPT_RESERVED9, IB_QPT_RESERVED10, }; enum ib_qp_create_flags { IB_QP_CREATE_IPOIB_UD_LSO = 1 << 0, IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK = 1 << 1, IB_QP_CREATE_CROSS_CHANNEL = 1 << 2, IB_QP_CREATE_MANAGED_SEND = 1 << 3, IB_QP_CREATE_MANAGED_RECV = 1 << 4, IB_QP_CREATE_NETIF_QP = 1 << 5, IB_QP_CREATE_SIGNATURE_EN = 1 << 6, /* FREE = 1 << 7, */ IB_QP_CREATE_SCATTER_FCS = 1 << 8, IB_QP_CREATE_CVLAN_STRIPPING = 1 << 9, IB_QP_CREATE_SOURCE_QPN = 1 << 10, /* reserve bits 26-31 for low level drivers' internal use */ IB_QP_CREATE_RESERVED_START = 1 << 26, IB_QP_CREATE_RESERVED_END = 1 << 31, }; /* * Note: users may not call ib_close_qp or ib_destroy_qp from the event_handler * callback to destroy the passed in QP. */ struct ib_qp_init_attr { void (*event_handler)(struct ib_event *, void *); void *qp_context; struct ib_cq *send_cq; struct ib_cq *recv_cq; struct ib_srq *srq; struct ib_xrcd *xrcd; /* XRC TGT QPs only */ struct ib_qp_cap cap; enum ib_sig_type sq_sig_type; enum ib_qp_type qp_type; u32 create_flags; /* * Only needed for special QP types, or when using the RW API. */ u8 port_num; struct ib_rwq_ind_table *rwq_ind_tbl; u32 source_qpn; }; struct ib_qp_open_attr { void (*event_handler)(struct ib_event *, void *); void *qp_context; u32 qp_num; enum ib_qp_type qp_type; }; enum ib_rnr_timeout { IB_RNR_TIMER_655_36 = 0, IB_RNR_TIMER_000_01 = 1, IB_RNR_TIMER_000_02 = 2, IB_RNR_TIMER_000_03 = 3, IB_RNR_TIMER_000_04 = 4, IB_RNR_TIMER_000_06 = 5, IB_RNR_TIMER_000_08 = 6, IB_RNR_TIMER_000_12 = 7, IB_RNR_TIMER_000_16 = 8, IB_RNR_TIMER_000_24 = 9, IB_RNR_TIMER_000_32 = 10, IB_RNR_TIMER_000_48 = 11, IB_RNR_TIMER_000_64 = 12, IB_RNR_TIMER_000_96 = 13, IB_RNR_TIMER_001_28 = 14, IB_RNR_TIMER_001_92 = 15, IB_RNR_TIMER_002_56 = 16, IB_RNR_TIMER_003_84 = 17, IB_RNR_TIMER_005_12 = 18, IB_RNR_TIMER_007_68 = 19, IB_RNR_TIMER_010_24 = 20, IB_RNR_TIMER_015_36 = 21, IB_RNR_TIMER_020_48 = 22, IB_RNR_TIMER_030_72 = 23, IB_RNR_TIMER_040_96 = 24, IB_RNR_TIMER_061_44 = 25, IB_RNR_TIMER_081_92 = 26, IB_RNR_TIMER_122_88 = 27, IB_RNR_TIMER_163_84 = 28, IB_RNR_TIMER_245_76 = 29, IB_RNR_TIMER_327_68 = 30, IB_RNR_TIMER_491_52 = 31 }; enum ib_qp_attr_mask { IB_QP_STATE = 1, IB_QP_CUR_STATE = (1<<1), IB_QP_EN_SQD_ASYNC_NOTIFY = (1<<2), IB_QP_ACCESS_FLAGS = (1<<3), IB_QP_PKEY_INDEX = (1<<4), IB_QP_PORT = (1<<5), IB_QP_QKEY = (1<<6), IB_QP_AV = (1<<7), IB_QP_PATH_MTU = (1<<8), IB_QP_TIMEOUT = (1<<9), IB_QP_RETRY_CNT = (1<<10), IB_QP_RNR_RETRY = (1<<11), IB_QP_RQ_PSN = (1<<12), IB_QP_MAX_QP_RD_ATOMIC = (1<<13), IB_QP_ALT_PATH = (1<<14), IB_QP_MIN_RNR_TIMER = (1<<15), IB_QP_SQ_PSN = (1<<16), IB_QP_MAX_DEST_RD_ATOMIC = (1<<17), IB_QP_PATH_MIG_STATE = (1<<18), IB_QP_CAP = (1<<19), IB_QP_DEST_QPN = (1<<20), IB_QP_RESERVED1 = (1<<21), IB_QP_RESERVED2 = (1<<22), IB_QP_RESERVED3 = (1<<23), IB_QP_RESERVED4 = (1<<24), IB_QP_RATE_LIMIT = (1<<25), }; enum ib_qp_state { IB_QPS_RESET, IB_QPS_INIT, IB_QPS_RTR, IB_QPS_RTS, IB_QPS_SQD, IB_QPS_SQE, IB_QPS_ERR }; enum ib_mig_state { IB_MIG_MIGRATED, IB_MIG_REARM, IB_MIG_ARMED }; enum ib_mw_type { IB_MW_TYPE_1 = 1, IB_MW_TYPE_2 = 2 }; struct ib_qp_attr { enum ib_qp_state qp_state; enum ib_qp_state cur_qp_state; enum ib_mtu path_mtu; enum ib_mig_state path_mig_state; u32 qkey; u32 rq_psn; u32 sq_psn; u32 dest_qp_num; int qp_access_flags; struct ib_qp_cap cap; struct rdma_ah_attr ah_attr; struct rdma_ah_attr alt_ah_attr; u16 pkey_index; u16 alt_pkey_index; u8 en_sqd_async_notify; u8 sq_draining; u8 max_rd_atomic; u8 max_dest_rd_atomic; u8 min_rnr_timer; u8 port_num; u8 timeout; u8 retry_cnt; u8 rnr_retry; u8 alt_port_num; u8 alt_timeout; u32 rate_limit; }; enum ib_wr_opcode { /* These are shared with userspace */ IB_WR_RDMA_WRITE = IB_UVERBS_WR_RDMA_WRITE, IB_WR_RDMA_WRITE_WITH_IMM = IB_UVERBS_WR_RDMA_WRITE_WITH_IMM, IB_WR_SEND = IB_UVERBS_WR_SEND, IB_WR_SEND_WITH_IMM = IB_UVERBS_WR_SEND_WITH_IMM, IB_WR_RDMA_READ = IB_UVERBS_WR_RDMA_READ, IB_WR_ATOMIC_CMP_AND_SWP = IB_UVERBS_WR_ATOMIC_CMP_AND_SWP, IB_WR_ATOMIC_FETCH_AND_ADD = IB_UVERBS_WR_ATOMIC_FETCH_AND_ADD, IB_WR_LSO = IB_UVERBS_WR_TSO, IB_WR_SEND_WITH_INV = IB_UVERBS_WR_SEND_WITH_INV, IB_WR_RDMA_READ_WITH_INV = IB_UVERBS_WR_RDMA_READ_WITH_INV, IB_WR_LOCAL_INV = IB_UVERBS_WR_LOCAL_INV, IB_WR_MASKED_ATOMIC_CMP_AND_SWP = IB_UVERBS_WR_MASKED_ATOMIC_CMP_AND_SWP, IB_WR_MASKED_ATOMIC_FETCH_AND_ADD = IB_UVERBS_WR_MASKED_ATOMIC_FETCH_AND_ADD, /* These are kernel only and can not be issued by userspace */ IB_WR_REG_MR = 0x20, IB_WR_REG_SIG_MR, /* reserve values for low level drivers' internal use. * These values will not be used at all in the ib core layer. */ IB_WR_RESERVED1 = 0xf0, IB_WR_RESERVED2, IB_WR_RESERVED3, IB_WR_RESERVED4, IB_WR_RESERVED5, IB_WR_RESERVED6, IB_WR_RESERVED7, IB_WR_RESERVED8, IB_WR_RESERVED9, IB_WR_RESERVED10, }; enum ib_send_flags { IB_SEND_FENCE = 1, IB_SEND_SIGNALED = (1<<1), IB_SEND_SOLICITED = (1<<2), IB_SEND_INLINE = (1<<3), IB_SEND_IP_CSUM = (1<<4), /* reserve bits 26-31 for low level drivers' internal use */ IB_SEND_RESERVED_START = (1 << 26), IB_SEND_RESERVED_END = (1 << 31), }; struct ib_sge { u64 addr; u32 length; u32 lkey; }; struct ib_cqe { void (*done)(struct ib_cq *cq, struct ib_wc *wc); }; struct ib_send_wr { struct ib_send_wr *next; union { u64 wr_id; struct ib_cqe *wr_cqe; }; struct ib_sge *sg_list; int num_sge; enum ib_wr_opcode opcode; int send_flags; union { __be32 imm_data; u32 invalidate_rkey; } ex; }; struct ib_rdma_wr { struct ib_send_wr wr; u64 remote_addr; u32 rkey; }; static inline struct ib_rdma_wr *rdma_wr(struct ib_send_wr *wr) { return container_of(wr, struct ib_rdma_wr, wr); } struct ib_atomic_wr { struct ib_send_wr wr; u64 remote_addr; u64 compare_add; u64 swap; u64 compare_add_mask; u64 swap_mask; u32 rkey; }; static inline struct ib_atomic_wr *atomic_wr(struct ib_send_wr *wr) { return container_of(wr, struct ib_atomic_wr, wr); } struct ib_ud_wr { struct ib_send_wr wr; struct ib_ah *ah; void *header; int hlen; int mss; u32 remote_qpn; u32 remote_qkey; u16 pkey_index; /* valid for GSI only */ u8 port_num; /* valid for DR SMPs on switch only */ }; static inline struct ib_ud_wr *ud_wr(struct ib_send_wr *wr) { return container_of(wr, struct ib_ud_wr, wr); } struct ib_reg_wr { struct ib_send_wr wr; struct ib_mr *mr; u32 key; int access; }; static inline struct ib_reg_wr *reg_wr(struct ib_send_wr *wr) { return container_of(wr, struct ib_reg_wr, wr); } struct ib_sig_handover_wr { struct ib_send_wr wr; struct ib_sig_attrs *sig_attrs; struct ib_mr *sig_mr; int access_flags; struct ib_sge *prot; }; static inline struct ib_sig_handover_wr *sig_handover_wr(struct ib_send_wr *wr) { return container_of(wr, struct ib_sig_handover_wr, wr); } struct ib_recv_wr { struct ib_recv_wr *next; union { u64 wr_id; struct ib_cqe *wr_cqe; }; struct ib_sge *sg_list; int num_sge; }; enum ib_access_flags { IB_ACCESS_LOCAL_WRITE = 1, IB_ACCESS_REMOTE_WRITE = (1<<1), IB_ACCESS_REMOTE_READ = (1<<2), IB_ACCESS_REMOTE_ATOMIC = (1<<3), IB_ACCESS_MW_BIND = (1<<4), IB_ZERO_BASED = (1<<5), IB_ACCESS_ON_DEMAND = (1<<6), IB_ACCESS_HUGETLB = (1<<7), }; /* * XXX: these are apparently used for ->rereg_user_mr, no idea why they * are hidden here instead of a uapi header! */ enum ib_mr_rereg_flags { IB_MR_REREG_TRANS = 1, IB_MR_REREG_PD = (1<<1), IB_MR_REREG_ACCESS = (1<<2), IB_MR_REREG_SUPPORTED = ((IB_MR_REREG_ACCESS << 1) - 1) }; struct ib_fmr_attr { int max_pages; int max_maps; u8 page_shift; }; struct ib_umem; enum rdma_remove_reason { /* Userspace requested uobject deletion. Call could fail */ RDMA_REMOVE_DESTROY, /* Context deletion. This call should delete the actual object itself */ RDMA_REMOVE_CLOSE, /* Driver is being hot-unplugged. This call should delete the actual object itself */ RDMA_REMOVE_DRIVER_REMOVE, /* Context is being cleaned-up, but commit was just completed */ RDMA_REMOVE_DURING_CLEANUP, }; struct ib_rdmacg_object { #ifdef CONFIG_CGROUP_RDMA struct rdma_cgroup *cg; /* owner rdma cgroup */ #endif }; struct ib_ucontext { struct ib_device *device; struct ib_uverbs_file *ufile; int closing; /* locking the uobjects_list */ struct mutex uobjects_lock; struct list_head uobjects; /* protects cleanup process from other actions */ struct rw_semaphore cleanup_rwsem; enum rdma_remove_reason cleanup_reason; struct pid *tgid; #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING struct rb_root_cached umem_tree; /* * Protects .umem_rbroot and tree, as well as odp_mrs_count and * mmu notifiers registration. */ struct rw_semaphore umem_rwsem; void (*invalidate_range)(struct ib_umem *umem, unsigned long start, unsigned long end); struct mmu_notifier mn; atomic_t notifier_count; /* A list of umems that don't have private mmu notifier counters yet. */ struct list_head no_private_counters; int odp_mrs_count; #endif struct ib_rdmacg_object cg_obj; }; struct ib_uobject { u64 user_handle; /* handle given to us by userspace */ struct ib_ucontext *context; /* associated user context */ void *object; /* containing object */ struct list_head list; /* link to context's list */ struct ib_rdmacg_object cg_obj; /* rdmacg object */ int id; /* index into kernel idr */ struct kref ref; atomic_t usecnt; /* protects exclusive access */ struct rcu_head rcu; /* kfree_rcu() overhead */ const struct uverbs_obj_type *type; }; struct ib_uobject_file { struct ib_uobject uobj; /* ufile contains the lock between context release and file close */ struct ib_uverbs_file *ufile; }; struct ib_udata { const void __user *inbuf; void __user *outbuf; size_t inlen; size_t outlen; }; struct ib_pd { u32 local_dma_lkey; u32 flags; struct ib_device *device; struct ib_uobject *uobject; atomic_t usecnt; /* count all resources */ u32 unsafe_global_rkey; /* * Implementation details of the RDMA core, don't use in drivers: */ struct ib_mr *__internal_mr; }; struct ib_xrcd { struct ib_device *device; atomic_t usecnt; /* count all exposed resources */ struct inode *inode; struct mutex tgt_qp_mutex; struct list_head tgt_qp_list; }; struct ib_ah { struct ib_device *device; struct ib_pd *pd; struct ib_uobject *uobject; enum rdma_ah_attr_type type; }; typedef void (*ib_comp_handler)(struct ib_cq *cq, void *cq_context); enum ib_poll_context { IB_POLL_DIRECT, /* caller context, no hw completions */ IB_POLL_SOFTIRQ, /* poll from softirq context */ IB_POLL_WORKQUEUE, /* poll from workqueue */ IB_POLL_UNBOUND_WORKQUEUE, /* poll from unbound workqueue */ }; struct ib_cq { struct ib_device *device; struct ib_uobject *uobject; ib_comp_handler comp_handler; void (*event_handler)(struct ib_event *, void *); void *cq_context; int cqe; atomic_t usecnt; /* count number of work queues */ enum ib_poll_context poll_ctx; struct ib_wc *wc; union { struct irq_poll iop; struct work_struct work; }; struct workqueue_struct *comp_wq; }; struct ib_srq { struct ib_device *device; struct ib_pd *pd; struct ib_uobject *uobject; void (*event_handler)(struct ib_event *, void *); void *srq_context; enum ib_srq_type srq_type; atomic_t usecnt; struct { struct ib_cq *cq; union { struct { struct ib_xrcd *xrcd; u32 srq_num; } xrc; }; } ext; }; enum ib_raw_packet_caps { /* Strip cvlan from incoming packet and report it in the matching work * completion is supported. */ IB_RAW_PACKET_CAP_CVLAN_STRIPPING = (1 << 0), /* Scatter FCS field of an incoming packet to host memory is supported. */ IB_RAW_PACKET_CAP_SCATTER_FCS = (1 << 1), /* Checksum offloads are supported (for both send and receive). */ IB_RAW_PACKET_CAP_IP_CSUM = (1 << 2), /* When a packet is received for an RQ with no receive WQEs, the * packet processing is delayed. */ IB_RAW_PACKET_CAP_DELAY_DROP = (1 << 3), }; enum ib_wq_type { IB_WQT_RQ }; enum ib_wq_state { IB_WQS_RESET, IB_WQS_RDY, IB_WQS_ERR }; struct ib_wq { struct ib_device *device; struct ib_uobject *uobject; void *wq_context; void (*event_handler)(struct ib_event *, void *); struct ib_pd *pd; struct ib_cq *cq; u32 wq_num; enum ib_wq_state state; enum ib_wq_type wq_type; atomic_t usecnt; }; enum ib_wq_flags { IB_WQ_FLAGS_CVLAN_STRIPPING = 1 << 0, IB_WQ_FLAGS_SCATTER_FCS = 1 << 1, IB_WQ_FLAGS_DELAY_DROP = 1 << 2, }; struct ib_wq_init_attr { void *wq_context; enum ib_wq_type wq_type; u32 max_wr; u32 max_sge; struct ib_cq *cq; void (*event_handler)(struct ib_event *, void *); u32 create_flags; /* Use enum ib_wq_flags */ }; enum ib_wq_attr_mask { IB_WQ_STATE = 1 << 0, IB_WQ_CUR_STATE = 1 << 1, IB_WQ_FLAGS = 1 << 2, }; struct ib_wq_attr { enum ib_wq_state wq_state; enum ib_wq_state curr_wq_state; u32 flags; /* Use enum ib_wq_flags */ u32 flags_mask; /* Use enum ib_wq_flags */ }; struct ib_rwq_ind_table { struct ib_device *device; struct ib_uobject *uobject; atomic_t usecnt; u32 ind_tbl_num; u32 log_ind_tbl_size; struct ib_wq **ind_tbl; }; struct ib_rwq_ind_table_init_attr { u32 log_ind_tbl_size; /* Each entry is a pointer to Receive Work Queue */ struct ib_wq **ind_tbl; }; enum port_pkey_state { IB_PORT_PKEY_NOT_VALID = 0, IB_PORT_PKEY_VALID = 1, IB_PORT_PKEY_LISTED = 2, }; struct ib_qp_security; struct ib_port_pkey { enum port_pkey_state state; u16 pkey_index; u8 port_num; struct list_head qp_list; struct list_head to_error_list; struct ib_qp_security *sec; }; struct ib_ports_pkeys { struct ib_port_pkey main; struct ib_port_pkey alt; }; struct ib_qp_security { struct ib_qp *qp; struct ib_device *dev; /* Hold this mutex when changing port and pkey settings. */ struct mutex mutex; struct ib_ports_pkeys *ports_pkeys; /* A list of all open shared QP handles. Required to enforce security * properly for all users of a shared QP. */ struct list_head shared_qp_list; void *security; bool destroying; atomic_t error_list_count; struct completion error_complete; int error_comps_pending; }; /* * @max_write_sge: Maximum SGE elements per RDMA WRITE request. * @max_read_sge: Maximum SGE elements per RDMA READ request. */ struct ib_qp { struct ib_device *device; struct ib_pd *pd; struct ib_cq *send_cq; struct ib_cq *recv_cq; spinlock_t mr_lock; int mrs_used; struct list_head rdma_mrs; struct list_head sig_mrs; struct ib_srq *srq; struct ib_xrcd *xrcd; /* XRC TGT QPs only */ struct list_head xrcd_list; /* count times opened, mcast attaches, flow attaches */ atomic_t usecnt; struct list_head open_list; struct ib_qp *real_qp; struct ib_uobject *uobject; void (*event_handler)(struct ib_event *, void *); void *qp_context; u32 qp_num; u32 max_write_sge; u32 max_read_sge; enum ib_qp_type qp_type; struct ib_rwq_ind_table *rwq_ind_tbl; struct ib_qp_security *qp_sec; u8 port; }; struct ib_mr { struct ib_device *device; struct ib_pd *pd; u32 lkey; u32 rkey; u64 iova; u64 length; unsigned int page_size; bool need_inval; union { struct ib_uobject *uobject; /* user */ struct list_head qp_entry; /* FR */ }; }; struct ib_mw { struct ib_device *device; struct ib_pd *pd; struct ib_uobject *uobject; u32 rkey; enum ib_mw_type type; }; struct ib_fmr { struct ib_device *device; struct ib_pd *pd; struct list_head list; u32 lkey; u32 rkey; }; /* Supported steering options */ enum ib_flow_attr_type { /* steering according to rule specifications */ IB_FLOW_ATTR_NORMAL = 0x0, /* default unicast and multicast rule - * receive all Eth traffic which isn't steered to any QP */ IB_FLOW_ATTR_ALL_DEFAULT = 0x1, /* default multicast rule - * receive all Eth multicast traffic which isn't steered to any QP */ IB_FLOW_ATTR_MC_DEFAULT = 0x2, /* sniffer rule - receive all port traffic */ IB_FLOW_ATTR_SNIFFER = 0x3 }; /* Supported steering header types */ enum ib_flow_spec_type { /* L2 headers*/ IB_FLOW_SPEC_ETH = 0x20, IB_FLOW_SPEC_IB = 0x22, /* L3 header*/ IB_FLOW_SPEC_IPV4 = 0x30, IB_FLOW_SPEC_IPV6 = 0x31, /* L4 headers*/ IB_FLOW_SPEC_TCP = 0x40, IB_FLOW_SPEC_UDP = 0x41, IB_FLOW_SPEC_VXLAN_TUNNEL = 0x50, IB_FLOW_SPEC_INNER = 0x100, /* Actions */ IB_FLOW_SPEC_ACTION_TAG = 0x1000, IB_FLOW_SPEC_ACTION_DROP = 0x1001, }; #define IB_FLOW_SPEC_LAYER_MASK 0xF0 #define IB_FLOW_SPEC_SUPPORT_LAYERS 8 /* Flow steering rule priority is set according to it's domain. * Lower domain value means higher priority. */ enum ib_flow_domain { IB_FLOW_DOMAIN_USER, IB_FLOW_DOMAIN_ETHTOOL, IB_FLOW_DOMAIN_RFS, IB_FLOW_DOMAIN_NIC, IB_FLOW_DOMAIN_NUM /* Must be last */ }; enum ib_flow_flags { IB_FLOW_ATTR_FLAGS_DONT_TRAP = 1UL << 1, /* Continue match, no steal */ IB_FLOW_ATTR_FLAGS_RESERVED = 1UL << 2 /* Must be last */ }; struct ib_flow_eth_filter { u8 dst_mac[6]; u8 src_mac[6]; __be16 ether_type; __be16 vlan_tag; /* Must be last */ u8 real_sz[0]; }; struct ib_flow_spec_eth { u32 type; u16 size; struct ib_flow_eth_filter val; struct ib_flow_eth_filter mask; }; struct ib_flow_ib_filter { __be16 dlid; __u8 sl; /* Must be last */ u8 real_sz[0]; }; struct ib_flow_spec_ib { u32 type; u16 size; struct ib_flow_ib_filter val; struct ib_flow_ib_filter mask; }; /* IPv4 header flags */ enum ib_ipv4_flags { IB_IPV4_DONT_FRAG = 0x2, /* Don't enable packet fragmentation */ IB_IPV4_MORE_FRAG = 0X4 /* For All fragmented packets except the last have this flag set */ }; struct ib_flow_ipv4_filter { __be32 src_ip; __be32 dst_ip; u8 proto; u8 tos; u8 ttl; u8 flags; /* Must be last */ u8 real_sz[0]; }; struct ib_flow_spec_ipv4 { u32 type; u16 size; struct ib_flow_ipv4_filter val; struct ib_flow_ipv4_filter mask; }; struct ib_flow_ipv6_filter { u8 src_ip[16]; u8 dst_ip[16]; __be32 flow_label; u8 next_hdr; u8 traffic_class; u8 hop_limit; /* Must be last */ u8 real_sz[0]; }; struct ib_flow_spec_ipv6 { u32 type; u16 size; struct ib_flow_ipv6_filter val; struct ib_flow_ipv6_filter mask; }; struct ib_flow_tcp_udp_filter { __be16 dst_port; __be16 src_port; /* Must be last */ u8 real_sz[0]; }; struct ib_flow_spec_tcp_udp { u32 type; u16 size; struct ib_flow_tcp_udp_filter val; struct ib_flow_tcp_udp_filter mask; }; struct ib_flow_tunnel_filter { __be32 tunnel_id; u8 real_sz[0]; }; /* ib_flow_spec_tunnel describes the Vxlan tunnel * the tunnel_id from val has the vni value */ struct ib_flow_spec_tunnel { u32 type; u16 size; struct ib_flow_tunnel_filter val; struct ib_flow_tunnel_filter mask; }; struct ib_flow_spec_action_tag { enum ib_flow_spec_type type; u16 size; u32 tag_id; }; struct ib_flow_spec_action_drop { enum ib_flow_spec_type type; u16 size; }; union ib_flow_spec { struct { u32 type; u16 size; }; struct ib_flow_spec_eth eth; struct ib_flow_spec_ib ib; struct ib_flow_spec_ipv4 ipv4; struct ib_flow_spec_tcp_udp tcp_udp; struct ib_flow_spec_ipv6 ipv6; struct ib_flow_spec_tunnel tunnel; struct ib_flow_spec_action_tag flow_tag; struct ib_flow_spec_action_drop drop; }; struct ib_flow_attr { enum ib_flow_attr_type type; u16 size; u16 priority; u32 flags; u8 num_of_specs; u8 port; /* Following are the optional layers according to user request * struct ib_flow_spec_xxx * struct ib_flow_spec_yyy */ }; struct ib_flow { struct ib_qp *qp; struct ib_uobject *uobject; }; struct ib_mad_hdr; struct ib_grh; enum ib_process_mad_flags { IB_MAD_IGNORE_MKEY = 1, IB_MAD_IGNORE_BKEY = 2, IB_MAD_IGNORE_ALL = IB_MAD_IGNORE_MKEY | IB_MAD_IGNORE_BKEY }; enum ib_mad_result { IB_MAD_RESULT_FAILURE = 0, /* (!SUCCESS is the important flag) */ IB_MAD_RESULT_SUCCESS = 1 << 0, /* MAD was successfully processed */ IB_MAD_RESULT_REPLY = 1 << 1, /* Reply packet needs to be sent */ IB_MAD_RESULT_CONSUMED = 1 << 2 /* Packet consumed: stop processing */ }; struct ib_port_cache { u64 subnet_prefix; struct ib_pkey_cache *pkey; struct ib_gid_table *gid; u8 lmc; enum ib_port_state port_state; }; struct ib_cache { rwlock_t lock; struct ib_event_handler event_handler; struct ib_port_cache *ports; }; struct iw_cm_verbs; struct ib_port_immutable { int pkey_tbl_len; int gid_tbl_len; u32 core_cap_flags; u32 max_mad_size; }; /* rdma netdev type - specifies protocol type */ enum rdma_netdev_t { RDMA_NETDEV_OPA_VNIC, RDMA_NETDEV_IPOIB, }; /** * struct rdma_netdev - rdma netdev * For cases where netstack interfacing is required. */ struct rdma_netdev { void *clnt_priv; struct ib_device *hca; u8 port_num; /* cleanup function must be specified */ void (*free_rdma_netdev)(struct net_device *netdev); /* control functions */ void (*set_id)(struct net_device *netdev, int id); /* send packet */ int (*send)(struct net_device *dev, struct sk_buff *skb, struct ib_ah *address, u32 dqpn); /* multicast */ int (*attach_mcast)(struct net_device *dev, struct ib_device *hca, union ib_gid *gid, u16 mlid, int set_qkey, u32 qkey); int (*detach_mcast)(struct net_device *dev, struct ib_device *hca, union ib_gid *gid, u16 mlid); }; struct ib_port_pkey_list { /* Lock to hold while modifying the list. */ spinlock_t list_lock; struct list_head pkey_list; }; struct ib_device { /* Do not access @dma_device directly from ULP nor from HW drivers. */ struct device *dma_device; char name[IB_DEVICE_NAME_MAX]; struct list_head event_handler_list; spinlock_t event_handler_lock; spinlock_t client_data_lock; struct list_head core_list; /* Access to the client_data_list is protected by the client_data_lock * spinlock and the lists_rwsem read-write semaphore */ struct list_head client_data_list; struct ib_cache cache; /** * port_immutable is indexed by port number */ struct ib_port_immutable *port_immutable; int num_comp_vectors; struct ib_port_pkey_list *port_pkey_list; struct iw_cm_verbs *iwcm; /** * alloc_hw_stats - Allocate a struct rdma_hw_stats and fill in the * driver initialized data. The struct is kfree()'ed by the sysfs * core when the device is removed. A lifespan of -1 in the return * struct tells the core to set a default lifespan. */ struct rdma_hw_stats *(*alloc_hw_stats)(struct ib_device *device, u8 port_num); /** * get_hw_stats - Fill in the counter value(s) in the stats struct. * @index - The index in the value array we wish to have updated, or * num_counters if we want all stats updated * Return codes - * < 0 - Error, no counters updated * index - Updated the single counter pointed to by index * num_counters - Updated all counters (will reset the timestamp * and prevent further calls for lifespan milliseconds) * Drivers are allowed to update all counters in leiu of just the * one given in index at their option */ int (*get_hw_stats)(struct ib_device *device, struct rdma_hw_stats *stats, u8 port, int index); int (*query_device)(struct ib_device *device, struct ib_device_attr *device_attr, struct ib_udata *udata); int (*query_port)(struct ib_device *device, u8 port_num, struct ib_port_attr *port_attr); enum rdma_link_layer (*get_link_layer)(struct ib_device *device, u8 port_num); /* When calling get_netdev, the HW vendor's driver should return the * net device of device @device at port @port_num or NULL if such * a net device doesn't exist. The vendor driver should call dev_hold * on this net device. The HW vendor's device driver must guarantee * that this function returns NULL before the net device reaches * NETDEV_UNREGISTER_FINAL state. */ struct net_device *(*get_netdev)(struct ib_device *device, u8 port_num); int (*query_gid)(struct ib_device *device, u8 port_num, int index, union ib_gid *gid); /* When calling add_gid, the HW vendor's driver should * add the gid of device @device at gid index @index of * port @port_num to be @gid. Meta-info of that gid (for example, * the network device related to this gid is available * at @attr. @context allows the HW vendor driver to store extra * information together with a GID entry. The HW vendor may allocate * memory to contain this information and store it in @context when a * new GID entry is written to. Params are consistent until the next * call of add_gid or delete_gid. The function should return 0 on * success or error otherwise. The function could be called * concurrently for different ports. This function is only called * when roce_gid_table is used. */ int (*add_gid)(struct ib_device *device, u8 port_num, unsigned int index, const union ib_gid *gid, const struct ib_gid_attr *attr, void **context); /* When calling del_gid, the HW vendor's driver should delete the * gid of device @device at gid index @index of port @port_num. * Upon the deletion of a GID entry, the HW vendor must free any * allocated memory. The caller will clear @context afterwards. * This function is only called when roce_gid_table is used. */ int (*del_gid)(struct ib_device *device, u8 port_num, unsigned int index, void **context); int (*query_pkey)(struct ib_device *device, u8 port_num, u16 index, u16 *pkey); int (*modify_device)(struct ib_device *device, int device_modify_mask, struct ib_device_modify *device_modify); int (*modify_port)(struct ib_device *device, u8 port_num, int port_modify_mask, struct ib_port_modify *port_modify); struct ib_ucontext * (*alloc_ucontext)(struct ib_device *device, struct ib_udata *udata); int (*dealloc_ucontext)(struct ib_ucontext *context); int (*mmap)(struct ib_ucontext *context, struct vm_area_struct *vma); struct ib_pd * (*alloc_pd)(struct ib_device *device, struct ib_ucontext *context, struct ib_udata *udata); int (*dealloc_pd)(struct ib_pd *pd); struct ib_ah * (*create_ah)(struct ib_pd *pd, struct rdma_ah_attr *ah_attr, struct ib_udata *udata); int (*modify_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); int (*query_ah)(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); int (*destroy_ah)(struct ib_ah *ah); struct ib_srq * (*create_srq)(struct ib_pd *pd, struct ib_srq_init_attr *srq_init_attr, struct ib_udata *udata); int (*modify_srq)(struct ib_srq *srq, struct ib_srq_attr *srq_attr, enum ib_srq_attr_mask srq_attr_mask, struct ib_udata *udata); int (*query_srq)(struct ib_srq *srq, struct ib_srq_attr *srq_attr); int (*destroy_srq)(struct ib_srq *srq); int (*post_srq_recv)(struct ib_srq *srq, struct ib_recv_wr *recv_wr, struct ib_recv_wr **bad_recv_wr); struct ib_qp * (*create_qp)(struct ib_pd *pd, struct ib_qp_init_attr *qp_init_attr, struct ib_udata *udata); int (*modify_qp)(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_udata *udata); int (*query_qp)(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr); int (*destroy_qp)(struct ib_qp *qp); int (*post_send)(struct ib_qp *qp, struct ib_send_wr *send_wr, struct ib_send_wr **bad_send_wr); int (*post_recv)(struct ib_qp *qp, struct ib_recv_wr *recv_wr, struct ib_recv_wr **bad_recv_wr); struct ib_cq * (*create_cq)(struct ib_device *device, const struct ib_cq_init_attr *attr, struct ib_ucontext *context, struct ib_udata *udata); int (*modify_cq)(struct ib_cq *cq, u16 cq_count, u16 cq_period); int (*destroy_cq)(struct ib_cq *cq); int (*resize_cq)(struct ib_cq *cq, int cqe, struct ib_udata *udata); int (*poll_cq)(struct ib_cq *cq, int num_entries, struct ib_wc *wc); int (*peek_cq)(struct ib_cq *cq, int wc_cnt); int (*req_notify_cq)(struct ib_cq *cq, enum ib_cq_notify_flags flags); int (*req_ncomp_notif)(struct ib_cq *cq, int wc_cnt); struct ib_mr * (*get_dma_mr)(struct ib_pd *pd, int mr_access_flags); struct ib_mr * (*reg_user_mr)(struct ib_pd *pd, u64 start, u64 length, u64 virt_addr, int mr_access_flags, struct ib_udata *udata); int (*rereg_user_mr)(struct ib_mr *mr, int flags, u64 start, u64 length, u64 virt_addr, int mr_access_flags, struct ib_pd *pd, struct ib_udata *udata); int (*dereg_mr)(struct ib_mr *mr); struct ib_mr * (*alloc_mr)(struct ib_pd *pd, enum ib_mr_type mr_type, u32 max_num_sg); int (*map_mr_sg)(struct ib_mr *mr, struct scatterlist *sg, int sg_nents, unsigned int *sg_offset); struct ib_mw * (*alloc_mw)(struct ib_pd *pd, enum ib_mw_type type, struct ib_udata *udata); int (*dealloc_mw)(struct ib_mw *mw); struct ib_fmr * (*alloc_fmr)(struct ib_pd *pd, int mr_access_flags, struct ib_fmr_attr *fmr_attr); int (*map_phys_fmr)(struct ib_fmr *fmr, u64 *page_list, int list_len, u64 iova); int (*unmap_fmr)(struct list_head *fmr_list); int (*dealloc_fmr)(struct ib_fmr *fmr); int (*attach_mcast)(struct ib_qp *qp, union ib_gid *gid, u16 lid); int (*detach_mcast)(struct ib_qp *qp, union ib_gid *gid, u16 lid); int (*process_mad)(struct ib_device *device, int process_mad_flags, u8 port_num, const struct ib_wc *in_wc, const struct ib_grh *in_grh, const struct ib_mad_hdr *in_mad, size_t in_mad_size, struct ib_mad_hdr *out_mad, size_t *out_mad_size, u16 *out_mad_pkey_index); struct ib_xrcd * (*alloc_xrcd)(struct ib_device *device, struct ib_ucontext *ucontext, struct ib_udata *udata); int (*dealloc_xrcd)(struct ib_xrcd *xrcd); struct ib_flow * (*create_flow)(struct ib_qp *qp, struct ib_flow_attr *flow_attr, int domain); int (*destroy_flow)(struct ib_flow *flow_id); int (*check_mr_status)(struct ib_mr *mr, u32 check_mask, struct ib_mr_status *mr_status); void (*disassociate_ucontext)(struct ib_ucontext *ibcontext); void (*drain_rq)(struct ib_qp *qp); void (*drain_sq)(struct ib_qp *qp); int (*set_vf_link_state)(struct ib_device *device, int vf, u8 port, int state); int (*get_vf_config)(struct ib_device *device, int vf, u8 port, struct ifla_vf_info *ivf); int (*get_vf_stats)(struct ib_device *device, int vf, u8 port, struct ifla_vf_stats *stats); int (*set_vf_guid)(struct ib_device *device, int vf, u8 port, u64 guid, int type); struct ib_wq * (*create_wq)(struct ib_pd *pd, struct ib_wq_init_attr *init_attr, struct ib_udata *udata); int (*destroy_wq)(struct ib_wq *wq); int (*modify_wq)(struct ib_wq *wq, struct ib_wq_attr *attr, u32 wq_attr_mask, struct ib_udata *udata); struct ib_rwq_ind_table * (*create_rwq_ind_table)(struct ib_device *device, struct ib_rwq_ind_table_init_attr *init_attr, struct ib_udata *udata); int (*destroy_rwq_ind_table)(struct ib_rwq_ind_table *wq_ind_table); /** * rdma netdev operation * * Driver implementing alloc_rdma_netdev must return -EOPNOTSUPP if it * doesn't support the specified rdma netdev type. */ struct net_device *(*alloc_rdma_netdev)( struct ib_device *device, u8 port_num, enum rdma_netdev_t type, const char *name, unsigned char name_assign_type, void (*setup)(struct net_device *)); struct module *owner; struct device dev; struct kobject *ports_parent; struct list_head port_list; enum { IB_DEV_UNINITIALIZED, IB_DEV_REGISTERED, IB_DEV_UNREGISTERED } reg_state; int uverbs_abi_ver; u64 uverbs_cmd_mask; u64 uverbs_ex_cmd_mask; char node_desc[IB_DEVICE_NODE_DESC_MAX]; __be64 node_guid; u32 local_dma_lkey; u16 is_switch:1; u8 node_type; u8 phys_port_cnt; struct ib_device_attr attrs; struct attribute_group *hw_stats_ag; struct rdma_hw_stats *hw_stats; #ifdef CONFIG_CGROUP_RDMA struct rdmacg_device cg_device; #endif u32 index; /** * The following mandatory functions are used only at device * registration. Keep functions such as these at the end of this * structure to avoid cache line misses when accessing struct ib_device * in fast paths. */ int (*get_port_immutable)(struct ib_device *, u8, struct ib_port_immutable *); void (*get_dev_fw_str)(struct ib_device *, char *str); const struct cpumask *(*get_vector_affinity)(struct ib_device *ibdev, int comp_vector); struct uverbs_root_spec *specs_root; }; struct ib_client { char *name; void (*add) (struct ib_device *); void (*remove)(struct ib_device *, void *client_data); /* Returns the net_dev belonging to this ib_client and matching the * given parameters. * @dev: An RDMA device that the net_dev use for communication. * @port: A physical port number on the RDMA device. * @pkey: P_Key that the net_dev uses if applicable. * @gid: A GID that the net_dev uses to communicate. * @addr: An IP address the net_dev is configured with. * @client_data: The device's client data set by ib_set_client_data(). * * An ib_client that implements a net_dev on top of RDMA devices * (such as IP over IB) should implement this callback, allowing the * rdma_cm module to find the right net_dev for a given request. * * The caller is responsible for calling dev_put on the returned * netdev. */ struct net_device *(*get_net_dev_by_params)( struct ib_device *dev, u8 port, u16 pkey, const union ib_gid *gid, const struct sockaddr *addr, void *client_data); struct list_head list; }; struct ib_device *ib_alloc_device(size_t size); void ib_dealloc_device(struct ib_device *device); void ib_get_device_fw_str(struct ib_device *device, char *str); int ib_register_device(struct ib_device *device, int (*port_callback)(struct ib_device *, u8, struct kobject *)); void ib_unregister_device(struct ib_device *device); int ib_register_client (struct ib_client *client); void ib_unregister_client(struct ib_client *client); void *ib_get_client_data(struct ib_device *device, struct ib_client *client); void ib_set_client_data(struct ib_device *device, struct ib_client *client, void *data); static inline int ib_copy_from_udata(void *dest, struct ib_udata *udata, size_t len) { return copy_from_user(dest, udata->inbuf, len) ? -EFAULT : 0; } static inline int ib_copy_to_udata(struct ib_udata *udata, void *src, size_t len) { return copy_to_user(udata->outbuf, src, len) ? -EFAULT : 0; } static inline bool ib_is_udata_cleared(struct ib_udata *udata, size_t offset, size_t len) { const void __user *p = udata->inbuf + offset; bool ret; u8 *buf; if (len > USHRT_MAX) return false; buf = memdup_user(p, len); if (IS_ERR(buf)) return false; ret = !memchr_inv(buf, 0, len); kfree(buf); return ret; } /** * ib_modify_qp_is_ok - Check that the supplied attribute mask * contains all required attributes and no attributes not allowed for * the given QP state transition. * @cur_state: Current QP state * @next_state: Next QP state * @type: QP type * @mask: Mask of supplied QP attributes * @ll : link layer of port * * This function is a helper function that a low-level driver's * modify_qp method can use to validate the consumer's input. It * checks that cur_state and next_state are valid QP states, that a * transition from cur_state to next_state is allowed by the IB spec, * and that the attribute mask supplied is allowed for the transition. */ int ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state, enum ib_qp_type type, enum ib_qp_attr_mask mask, enum rdma_link_layer ll); void ib_register_event_handler(struct ib_event_handler *event_handler); void ib_unregister_event_handler(struct ib_event_handler *event_handler); void ib_dispatch_event(struct ib_event *event); int ib_query_port(struct ib_device *device, u8 port_num, struct ib_port_attr *port_attr); enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device, u8 port_num); /** * rdma_cap_ib_switch - Check if the device is IB switch * @device: Device to check * * Device driver is responsible for setting is_switch bit on * in ib_device structure at init time. * * Return: true if the device is IB switch. */ static inline bool rdma_cap_ib_switch(const struct ib_device *device) { return device->is_switch; } /** * rdma_start_port - Return the first valid port number for the device * specified * * @device: Device to be checked * * Return start port number */ static inline u8 rdma_start_port(const struct ib_device *device) { return rdma_cap_ib_switch(device) ? 0 : 1; } /** * rdma_end_port - Return the last valid port number for the device * specified * * @device: Device to be checked * * Return last port number */ static inline u8 rdma_end_port(const struct ib_device *device) { return rdma_cap_ib_switch(device) ? 0 : device->phys_port_cnt; } static inline int rdma_is_port_valid(const struct ib_device *device, unsigned int port) { return (port >= rdma_start_port(device) && port <= rdma_end_port(device)); } static inline bool rdma_protocol_ib(const struct ib_device *device, u8 port_num) { return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_PROT_IB; } static inline bool rdma_protocol_roce(const struct ib_device *device, u8 port_num) { return device->port_immutable[port_num].core_cap_flags & (RDMA_CORE_CAP_PROT_ROCE | RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP); } static inline bool rdma_protocol_roce_udp_encap(const struct ib_device *device, u8 port_num) { return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP; } static inline bool rdma_protocol_roce_eth_encap(const struct ib_device *device, u8 port_num) { return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_PROT_ROCE; } static inline bool rdma_protocol_iwarp(const struct ib_device *device, u8 port_num) { return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_PROT_IWARP; } static inline bool rdma_ib_or_roce(const struct ib_device *device, u8 port_num) { return rdma_protocol_ib(device, port_num) || rdma_protocol_roce(device, port_num); } static inline bool rdma_protocol_raw_packet(const struct ib_device *device, u8 port_num) { return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_PROT_RAW_PACKET; } static inline bool rdma_protocol_usnic(const struct ib_device *device, u8 port_num) { return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_PROT_USNIC; } /** * rdma_cap_ib_mad - Check if the port of a device supports Infiniband * Management Datagrams. * @device: Device to check * @port_num: Port number to check * * Management Datagrams (MAD) are a required part of the InfiniBand * specification and are supported on all InfiniBand devices. A slightly * extended version are also supported on OPA interfaces. * * Return: true if the port supports sending/receiving of MAD packets. */ static inline bool rdma_cap_ib_mad(const struct ib_device *device, u8 port_num) { return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_IB_MAD; } /** * rdma_cap_opa_mad - Check if the port of device provides support for OPA * Management Datagrams. * @device: Device to check * @port_num: Port number to check * * Intel OmniPath devices extend and/or replace the InfiniBand Management * datagrams with their own versions. These OPA MADs share many but not all of * the characteristics of InfiniBand MADs. * * OPA MADs differ in the following ways: * * 1) MADs are variable size up to 2K * IBTA defined MADs remain fixed at 256 bytes * 2) OPA SMPs must carry valid PKeys * 3) OPA SMP packets are a different format * * Return: true if the port supports OPA MAD packet formats. */ static inline bool rdma_cap_opa_mad(struct ib_device *device, u8 port_num) { return (device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_OPA_MAD) == RDMA_CORE_CAP_OPA_MAD; } /** * rdma_cap_ib_smi - Check if the port of a device provides an Infiniband * Subnet Management Agent (SMA) on the Subnet Management Interface (SMI). * @device: Device to check * @port_num: Port number to check * * Each InfiniBand node is required to provide a Subnet Management Agent * that the subnet manager can access. Prior to the fabric being fully * configured by the subnet manager, the SMA is accessed via a well known * interface called the Subnet Management Interface (SMI). This interface * uses directed route packets to communicate with the SM to get around the * chicken and egg problem of the SM needing to know what's on the fabric * in order to configure the fabric, and needing to configure the fabric in * order to send packets to the devices on the fabric. These directed * route packets do not need the fabric fully configured in order to reach * their destination. The SMI is the only method allowed to send * directed route packets on an InfiniBand fabric. * * Return: true if the port provides an SMI. */ static inline bool rdma_cap_ib_smi(const struct ib_device *device, u8 port_num) { return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_IB_SMI; } /** * rdma_cap_ib_cm - Check if the port of device has the capability Infiniband * Communication Manager. * @device: Device to check * @port_num: Port number to check * * The InfiniBand Communication Manager is one of many pre-defined General * Service Agents (GSA) that are accessed via the General Service * Interface (GSI). It's role is to facilitate establishment of connections * between nodes as well as other management related tasks for established * connections. * * Return: true if the port supports an IB CM (this does not guarantee that * a CM is actually running however). */ static inline bool rdma_cap_ib_cm(const struct ib_device *device, u8 port_num) { return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_IB_CM; } /** * rdma_cap_iw_cm - Check if the port of device has the capability IWARP * Communication Manager. * @device: Device to check * @port_num: Port number to check * * Similar to above, but specific to iWARP connections which have a different * managment protocol than InfiniBand. * * Return: true if the port supports an iWARP CM (this does not guarantee that * a CM is actually running however). */ static inline bool rdma_cap_iw_cm(const struct ib_device *device, u8 port_num) { return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_IW_CM; } /** * rdma_cap_ib_sa - Check if the port of device has the capability Infiniband * Subnet Administration. * @device: Device to check * @port_num: Port number to check * * An InfiniBand Subnet Administration (SA) service is a pre-defined General * Service Agent (GSA) provided by the Subnet Manager (SM). On InfiniBand * fabrics, devices should resolve routes to other hosts by contacting the * SA to query the proper route. * * Return: true if the port should act as a client to the fabric Subnet * Administration interface. This does not imply that the SA service is * running locally. */ static inline bool rdma_cap_ib_sa(const struct ib_device *device, u8 port_num) { return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_IB_SA; } /** * rdma_cap_ib_mcast - Check if the port of device has the capability Infiniband * Multicast. * @device: Device to check * @port_num: Port number to check * * InfiniBand multicast registration is more complex than normal IPv4 or * IPv6 multicast registration. Each Host Channel Adapter must register * with the Subnet Manager when it wishes to join a multicast group. It * should do so only once regardless of how many queue pairs it subscribes * to this group. And it should leave the group only after all queue pairs * attached to the group have been detached. * * Return: true if the port must undertake the additional adminstrative * overhead of registering/unregistering with the SM and tracking of the * total number of queue pairs attached to the multicast group. */ static inline bool rdma_cap_ib_mcast(const struct ib_device *device, u8 port_num) { return rdma_cap_ib_sa(device, port_num); } /** * rdma_cap_af_ib - Check if the port of device has the capability * Native Infiniband Address. * @device: Device to check * @port_num: Port number to check * * InfiniBand addressing uses a port's GUID + Subnet Prefix to make a default * GID. RoCE uses a different mechanism, but still generates a GID via * a prescribed mechanism and port specific data. * * Return: true if the port uses a GID address to identify devices on the * network. */ static inline bool rdma_cap_af_ib(const struct ib_device *device, u8 port_num) { return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_AF_IB; } /** * rdma_cap_eth_ah - Check if the port of device has the capability * Ethernet Address Handle. * @device: Device to check * @port_num: Port number to check * * RoCE is InfiniBand over Ethernet, and it uses a well defined technique * to fabricate GIDs over Ethernet/IP specific addresses native to the * port. Normally, packet headers are generated by the sending host * adapter, but when sending connectionless datagrams, we must manually * inject the proper headers for the fabric we are communicating over. * * Return: true if we are running as a RoCE port and must force the * addition of a Global Route Header built from our Ethernet Address * Handle into our header list for connectionless packets. */ static inline bool rdma_cap_eth_ah(const struct ib_device *device, u8 port_num) { return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_ETH_AH; } /** * rdma_cap_opa_ah - Check if the port of device supports * OPA Address handles * @device: Device to check * @port_num: Port number to check * * Return: true if we are running on an OPA device which supports * the extended OPA addressing. */ static inline bool rdma_cap_opa_ah(struct ib_device *device, u8 port_num) { return (device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_OPA_AH) == RDMA_CORE_CAP_OPA_AH; } /** * rdma_max_mad_size - Return the max MAD size required by this RDMA Port. * * @device: Device * @port_num: Port number * * This MAD size includes the MAD headers and MAD payload. No other headers * are included. * * Return the max MAD size required by the Port. Will return 0 if the port * does not support MADs */ static inline size_t rdma_max_mad_size(const struct ib_device *device, u8 port_num) { return device->port_immutable[port_num].max_mad_size; } /** * rdma_cap_roce_gid_table - Check if the port of device uses roce_gid_table * @device: Device to check * @port_num: Port number to check * * RoCE GID table mechanism manages the various GIDs for a device. * * NOTE: if allocating the port's GID table has failed, this call will still * return true, but any RoCE GID table API will fail. * * Return: true if the port uses RoCE GID table mechanism in order to manage * its GIDs. */ static inline bool rdma_cap_roce_gid_table(const struct ib_device *device, u8 port_num) { return rdma_protocol_roce(device, port_num) && device->add_gid && device->del_gid; } /* * Check if the device supports READ W/ INVALIDATE. */ static inline bool rdma_cap_read_inv(struct ib_device *dev, u32 port_num) { /* * iWarp drivers must support READ W/ INVALIDATE. No other protocol * has support for it yet. */ return rdma_protocol_iwarp(dev, port_num); } int ib_query_gid(struct ib_device *device, u8 port_num, int index, union ib_gid *gid, struct ib_gid_attr *attr); int ib_set_vf_link_state(struct ib_device *device, int vf, u8 port, int state); int ib_get_vf_config(struct ib_device *device, int vf, u8 port, struct ifla_vf_info *info); int ib_get_vf_stats(struct ib_device *device, int vf, u8 port, struct ifla_vf_stats *stats); int ib_set_vf_guid(struct ib_device *device, int vf, u8 port, u64 guid, int type); int ib_query_pkey(struct ib_device *device, u8 port_num, u16 index, u16 *pkey); int ib_modify_device(struct ib_device *device, int device_modify_mask, struct ib_device_modify *device_modify); int ib_modify_port(struct ib_device *device, u8 port_num, int port_modify_mask, struct ib_port_modify *port_modify); int ib_find_gid(struct ib_device *device, union ib_gid *gid, enum ib_gid_type gid_type, struct net_device *ndev, u8 *port_num, u16 *index); int ib_find_pkey(struct ib_device *device, u8 port_num, u16 pkey, u16 *index); enum ib_pd_flags { /* * Create a memory registration for all memory in the system and place * the rkey for it into pd->unsafe_global_rkey. This can be used by * ULPs to avoid the overhead of dynamic MRs. * * This flag is generally considered unsafe and must only be used in * extremly trusted environments. Every use of it will log a warning * in the kernel log. */ IB_PD_UNSAFE_GLOBAL_RKEY = 0x01, }; struct ib_pd *__ib_alloc_pd(struct ib_device *device, unsigned int flags, const char *caller); #define ib_alloc_pd(device, flags) \ __ib_alloc_pd((device), (flags), __func__) void ib_dealloc_pd(struct ib_pd *pd); /** * rdma_create_ah - Creates an address handle for the given address vector. * @pd: The protection domain associated with the address handle. * @ah_attr: The attributes of the address vector. * * The address handle is used to reference a local or global destination * in all UD QP post sends. */ struct ib_ah *rdma_create_ah(struct ib_pd *pd, struct rdma_ah_attr *ah_attr); /** * ib_get_gids_from_rdma_hdr - Get sgid and dgid from GRH or IPv4 header * work completion. * @hdr: the L3 header to parse * @net_type: type of header to parse * @sgid: place to store source gid * @dgid: place to store destination gid */ int ib_get_gids_from_rdma_hdr(const union rdma_network_hdr *hdr, enum rdma_network_type net_type, union ib_gid *sgid, union ib_gid *dgid); /** * ib_get_rdma_header_version - Get the header version * @hdr: the L3 header to parse */ int ib_get_rdma_header_version(const union rdma_network_hdr *hdr); /** * ib_init_ah_from_wc - Initializes address handle attributes from a * work completion. * @device: Device on which the received message arrived. * @port_num: Port on which the received message arrived. * @wc: Work completion associated with the received message. * @grh: References the received global route header. This parameter is * ignored unless the work completion indicates that the GRH is valid. * @ah_attr: Returned attributes that can be used when creating an address * handle for replying to the message. */ int ib_init_ah_from_wc(struct ib_device *device, u8 port_num, const struct ib_wc *wc, const struct ib_grh *grh, struct rdma_ah_attr *ah_attr); /** * ib_create_ah_from_wc - Creates an address handle associated with the * sender of the specified work completion. * @pd: The protection domain associated with the address handle. * @wc: Work completion information associated with a received message. * @grh: References the received global route header. This parameter is * ignored unless the work completion indicates that the GRH is valid. * @port_num: The outbound port number to associate with the address. * * The address handle is used to reference a local or global destination * in all UD QP post sends. */ struct ib_ah *ib_create_ah_from_wc(struct ib_pd *pd, const struct ib_wc *wc, const struct ib_grh *grh, u8 port_num); /** * rdma_modify_ah - Modifies the address vector associated with an address * handle. * @ah: The address handle to modify. * @ah_attr: The new address vector attributes to associate with the * address handle. */ int rdma_modify_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); /** * rdma_query_ah - Queries the address vector associated with an address * handle. * @ah: The address handle to query. * @ah_attr: The address vector attributes associated with the address * handle. */ int rdma_query_ah(struct ib_ah *ah, struct rdma_ah_attr *ah_attr); /** * rdma_destroy_ah - Destroys an address handle. * @ah: The address handle to destroy. */ int rdma_destroy_ah(struct ib_ah *ah); /** * ib_create_srq - Creates a SRQ associated with the specified protection * domain. * @pd: The protection domain associated with the SRQ. * @srq_init_attr: A list of initial attributes required to create the * SRQ. If SRQ creation succeeds, then the attributes are updated to * the actual capabilities of the created SRQ. * * srq_attr->max_wr and srq_attr->max_sge are read the determine the * requested size of the SRQ, and set to the actual values allocated * on return. If ib_create_srq() succeeds, then max_wr and max_sge * will always be at least as large as the requested values. */ struct ib_srq *ib_create_srq(struct ib_pd *pd, struct ib_srq_init_attr *srq_init_attr); /** * ib_modify_srq - Modifies the attributes for the specified SRQ. * @srq: The SRQ to modify. * @srq_attr: On input, specifies the SRQ attributes to modify. On output, * the current values of selected SRQ attributes are returned. * @srq_attr_mask: A bit-mask used to specify which attributes of the SRQ * are being modified. * * The mask may contain IB_SRQ_MAX_WR to resize the SRQ and/or * IB_SRQ_LIMIT to set the SRQ's limit and request notification when * the number of receives queued drops below the limit. */ int ib_modify_srq(struct ib_srq *srq, struct ib_srq_attr *srq_attr, enum ib_srq_attr_mask srq_attr_mask); /** * ib_query_srq - Returns the attribute list and current values for the * specified SRQ. * @srq: The SRQ to query. * @srq_attr: The attributes of the specified SRQ. */ int ib_query_srq(struct ib_srq *srq, struct ib_srq_attr *srq_attr); /** * ib_destroy_srq - Destroys the specified SRQ. * @srq: The SRQ to destroy. */ int ib_destroy_srq(struct ib_srq *srq); /** * ib_post_srq_recv - Posts a list of work requests to the specified SRQ. * @srq: The SRQ to post the work request on. * @recv_wr: A list of work requests to post on the receive queue. * @bad_recv_wr: On an immediate failure, this parameter will reference * the work request that failed to be posted on the QP. */ static inline int ib_post_srq_recv(struct ib_srq *srq, struct ib_recv_wr *recv_wr, struct ib_recv_wr **bad_recv_wr) { return srq->device->post_srq_recv(srq, recv_wr, bad_recv_wr); } /** * ib_create_qp - Creates a QP associated with the specified protection * domain. * @pd: The protection domain associated with the QP. * @qp_init_attr: A list of initial attributes required to create the * QP. If QP creation succeeds, then the attributes are updated to * the actual capabilities of the created QP. */ struct ib_qp *ib_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *qp_init_attr); /** * ib_modify_qp_with_udata - Modifies the attributes for the specified QP. * @qp: The QP to modify. * @attr: On input, specifies the QP attributes to modify. On output, * the current values of selected QP attributes are returned. * @attr_mask: A bit-mask used to specify which attributes of the QP * are being modified. * @udata: pointer to user's input output buffer information * are being modified. * It returns 0 on success and returns appropriate error code on error. */ int ib_modify_qp_with_udata(struct ib_qp *qp, struct ib_qp_attr *attr, int attr_mask, struct ib_udata *udata); /** * ib_modify_qp - Modifies the attributes for the specified QP and then * transitions the QP to the given state. * @qp: The QP to modify. * @qp_attr: On input, specifies the QP attributes to modify. On output, * the current values of selected QP attributes are returned. * @qp_attr_mask: A bit-mask used to specify which attributes of the QP * are being modified. */ int ib_modify_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask); /** * ib_query_qp - Returns the attribute list and current values for the * specified QP. * @qp: The QP to query. * @qp_attr: The attributes of the specified QP. * @qp_attr_mask: A bit-mask used to select specific attributes to query. * @qp_init_attr: Additional attributes of the selected QP. * * The qp_attr_mask may be used to limit the query to gathering only the * selected attributes. */ int ib_query_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr, int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr); /** * ib_destroy_qp - Destroys the specified QP. * @qp: The QP to destroy. */ int ib_destroy_qp(struct ib_qp *qp); /** * ib_open_qp - Obtain a reference to an existing sharable QP. * @xrcd - XRC domain * @qp_open_attr: Attributes identifying the QP to open. * * Returns a reference to a sharable QP. */ struct ib_qp *ib_open_qp(struct ib_xrcd *xrcd, struct ib_qp_open_attr *qp_open_attr); /** * ib_close_qp - Release an external reference to a QP. * @qp: The QP handle to release * * The opened QP handle is released by the caller. The underlying * shared QP is not destroyed until all internal references are released. */ int ib_close_qp(struct ib_qp *qp); /** * ib_post_send - Posts a list of work requests to the send queue of * the specified QP. * @qp: The QP to post the work request on. * @send_wr: A list of work requests to post on the send queue. * @bad_send_wr: On an immediate failure, this parameter will reference * the work request that failed to be posted on the QP. * * While IBA Vol. 1 section 11.4.1.1 specifies that if an immediate * error is returned, the QP state shall not be affected, * ib_post_send() will return an immediate error after queueing any * earlier work requests in the list. */ static inline int ib_post_send(struct ib_qp *qp, struct ib_send_wr *send_wr, struct ib_send_wr **bad_send_wr) { return qp->device->post_send(qp, send_wr, bad_send_wr); } /** * ib_post_recv - Posts a list of work requests to the receive queue of * the specified QP. * @qp: The QP to post the work request on. * @recv_wr: A list of work requests to post on the receive queue. * @bad_recv_wr: On an immediate failure, this parameter will reference * the work request that failed to be posted on the QP. */ static inline int ib_post_recv(struct ib_qp *qp, struct ib_recv_wr *recv_wr, struct ib_recv_wr **bad_recv_wr) { return qp->device->post_recv(qp, recv_wr, bad_recv_wr); } struct ib_cq *ib_alloc_cq(struct ib_device *dev, void *private, int nr_cqe, int comp_vector, enum ib_poll_context poll_ctx); void ib_free_cq(struct ib_cq *cq); int ib_process_cq_direct(struct ib_cq *cq, int budget); /** * ib_create_cq - Creates a CQ on the specified device. * @device: The device on which to create the CQ. * @comp_handler: A user-specified callback that is invoked when a * completion event occurs on the CQ. * @event_handler: A user-specified callback that is invoked when an * asynchronous event not associated with a completion occurs on the CQ. * @cq_context: Context associated with the CQ returned to the user via * the associated completion and event handlers. * @cq_attr: The attributes the CQ should be created upon. * * Users can examine the cq structure to determine the actual CQ size. */ struct ib_cq *ib_create_cq(struct ib_device *device, ib_comp_handler comp_handler, void (*event_handler)(struct ib_event *, void *), void *cq_context, const struct ib_cq_init_attr *cq_attr); /** * ib_resize_cq - Modifies the capacity of the CQ. * @cq: The CQ to resize. * @cqe: The minimum size of the CQ. * * Users can examine the cq structure to determine the actual CQ size. */ int ib_resize_cq(struct ib_cq *cq, int cqe); /** * ib_modify_cq - Modifies moderation params of the CQ * @cq: The CQ to modify. * @cq_count: number of CQEs that will trigger an event * @cq_period: max period of time in usec before triggering an event * */ int ib_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period); /** * ib_destroy_cq - Destroys the specified CQ. * @cq: The CQ to destroy. */ int ib_destroy_cq(struct ib_cq *cq); /** * ib_poll_cq - poll a CQ for completion(s) * @cq:the CQ being polled * @num_entries:maximum number of completions to return * @wc:array of at least @num_entries &struct ib_wc where completions * will be returned * * Poll a CQ for (possibly multiple) completions. If the return value * is < 0, an error occurred. If the return value is >= 0, it is the * number of completions returned. If the return value is * non-negative and < num_entries, then the CQ was emptied. */ static inline int ib_poll_cq(struct ib_cq *cq, int num_entries, struct ib_wc *wc) { return cq->device->poll_cq(cq, num_entries, wc); } /** * ib_peek_cq - Returns the number of unreaped completions currently * on the specified CQ. * @cq: The CQ to peek. * @wc_cnt: A minimum number of unreaped completions to check for. * * If the number of unreaped completions is greater than or equal to wc_cnt, * this function returns wc_cnt, otherwise, it returns the actual number of * unreaped completions. */ int ib_peek_cq(struct ib_cq *cq, int wc_cnt); /** * ib_req_notify_cq - Request completion notification on a CQ. * @cq: The CQ to generate an event for. * @flags: * Must contain exactly one of %IB_CQ_SOLICITED or %IB_CQ_NEXT_COMP * to request an event on the next solicited event or next work * completion at any type, respectively. %IB_CQ_REPORT_MISSED_EVENTS * may also be |ed in to request a hint about missed events, as * described below. * * Return Value: * < 0 means an error occurred while requesting notification * == 0 means notification was requested successfully, and if * IB_CQ_REPORT_MISSED_EVENTS was passed in, then no events * were missed and it is safe to wait for another event. In * this case is it guaranteed that any work completions added * to the CQ since the last CQ poll will trigger a completion * notification event. * > 0 is only returned if IB_CQ_REPORT_MISSED_EVENTS was passed * in. It means that the consumer must poll the CQ again to * make sure it is empty to avoid missing an event because of a * race between requesting notification and an entry being * added to the CQ. This return value means it is possible * (but not guaranteed) that a work completion has been added * to the CQ since the last poll without triggering a * completion notification event. */ static inline int ib_req_notify_cq(struct ib_cq *cq, enum ib_cq_notify_flags flags) { return cq->device->req_notify_cq(cq, flags); } /** * ib_req_ncomp_notif - Request completion notification when there are * at least the specified number of unreaped completions on the CQ. * @cq: The CQ to generate an event for. * @wc_cnt: The number of unreaped completions that should be on the * CQ before an event is generated. */ static inline int ib_req_ncomp_notif(struct ib_cq *cq, int wc_cnt) { return cq->device->req_ncomp_notif ? cq->device->req_ncomp_notif(cq, wc_cnt) : -ENOSYS; } /** * ib_dma_mapping_error - check a DMA addr for error * @dev: The device for which the dma_addr was created * @dma_addr: The DMA address to check */ static inline int ib_dma_mapping_error(struct ib_device *dev, u64 dma_addr) { return dma_mapping_error(dev->dma_device, dma_addr); } /** * ib_dma_map_single - Map a kernel virtual address to DMA address * @dev: The device for which the dma_addr is to be created * @cpu_addr: The kernel virtual address * @size: The size of the region in bytes * @direction: The direction of the DMA */ static inline u64 ib_dma_map_single(struct ib_device *dev, void *cpu_addr, size_t size, enum dma_data_direction direction) { return dma_map_single(dev->dma_device, cpu_addr, size, direction); } /** * ib_dma_unmap_single - Destroy a mapping created by ib_dma_map_single() * @dev: The device for which the DMA address was created * @addr: The DMA address * @size: The size of the region in bytes * @direction: The direction of the DMA */ static inline void ib_dma_unmap_single(struct ib_device *dev, u64 addr, size_t size, enum dma_data_direction direction) { dma_unmap_single(dev->dma_device, addr, size, direction); } /** * ib_dma_map_page - Map a physical page to DMA address * @dev: The device for which the dma_addr is to be created * @page: The page to be mapped * @offset: The offset within the page * @size: The size of the region in bytes * @direction: The direction of the DMA */ static inline u64 ib_dma_map_page(struct ib_device *dev, struct page *page, unsigned long offset, size_t size, enum dma_data_direction direction) { return dma_map_page(dev->dma_device, page, offset, size, direction); } /** * ib_dma_unmap_page - Destroy a mapping created by ib_dma_map_page() * @dev: The device for which the DMA address was created * @addr: The DMA address * @size: The size of the region in bytes * @direction: The direction of the DMA */ static inline void ib_dma_unmap_page(struct ib_device *dev, u64 addr, size_t size, enum dma_data_direction direction) { dma_unmap_page(dev->dma_device, addr, size, direction); } /** * ib_dma_map_sg - Map a scatter/gather list to DMA addresses * @dev: The device for which the DMA addresses are to be created * @sg: The array of scatter/gather entries * @nents: The number of scatter/gather entries * @direction: The direction of the DMA */ static inline int ib_dma_map_sg(struct ib_device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction) { return dma_map_sg(dev->dma_device, sg, nents, direction); } /** * ib_dma_unmap_sg - Unmap a scatter/gather list of DMA addresses * @dev: The device for which the DMA addresses were created * @sg: The array of scatter/gather entries * @nents: The number of scatter/gather entries * @direction: The direction of the DMA */ static inline void ib_dma_unmap_sg(struct ib_device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction) { dma_unmap_sg(dev->dma_device, sg, nents, direction); } static inline int ib_dma_map_sg_attrs(struct ib_device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction, unsigned long dma_attrs) { return dma_map_sg_attrs(dev->dma_device, sg, nents, direction, dma_attrs); } static inline void ib_dma_unmap_sg_attrs(struct ib_device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction, unsigned long dma_attrs) { dma_unmap_sg_attrs(dev->dma_device, sg, nents, direction, dma_attrs); } /** * ib_sg_dma_address - Return the DMA address from a scatter/gather entry * @dev: The device for which the DMA addresses were created * @sg: The scatter/gather entry * * Note: this function is obsolete. To do: change all occurrences of * ib_sg_dma_address() into sg_dma_address(). */ static inline u64 ib_sg_dma_address(struct ib_device *dev, struct scatterlist *sg) { return sg_dma_address(sg); } /** * ib_sg_dma_len - Return the DMA length from a scatter/gather entry * @dev: The device for which the DMA addresses were created * @sg: The scatter/gather entry * * Note: this function is obsolete. To do: change all occurrences of * ib_sg_dma_len() into sg_dma_len(). */ static inline unsigned int ib_sg_dma_len(struct ib_device *dev, struct scatterlist *sg) { return sg_dma_len(sg); } /** * ib_dma_sync_single_for_cpu - Prepare DMA region to be accessed by CPU * @dev: The device for which the DMA address was created * @addr: The DMA address * @size: The size of the region in bytes * @dir: The direction of the DMA */ static inline void ib_dma_sync_single_for_cpu(struct ib_device *dev, u64 addr, size_t size, enum dma_data_direction dir) { dma_sync_single_for_cpu(dev->dma_device, addr, size, dir); } /** * ib_dma_sync_single_for_device - Prepare DMA region to be accessed by device * @dev: The device for which the DMA address was created * @addr: The DMA address * @size: The size of the region in bytes * @dir: The direction of the DMA */ static inline void ib_dma_sync_single_for_device(struct ib_device *dev, u64 addr, size_t size, enum dma_data_direction dir) { dma_sync_single_for_device(dev->dma_device, addr, size, dir); } /** * ib_dma_alloc_coherent - Allocate memory and map it for DMA * @dev: The device for which the DMA address is requested * @size: The size of the region to allocate in bytes * @dma_handle: A pointer for returning the DMA address of the region * @flag: memory allocator flags */ static inline void *ib_dma_alloc_coherent(struct ib_device *dev, size_t size, dma_addr_t *dma_handle, gfp_t flag) { return dma_alloc_coherent(dev->dma_device, size, dma_handle, flag); } /** * ib_dma_free_coherent - Free memory allocated by ib_dma_alloc_coherent() * @dev: The device for which the DMA addresses were allocated * @size: The size of the region * @cpu_addr: the address returned by ib_dma_alloc_coherent() * @dma_handle: the DMA address returned by ib_dma_alloc_coherent() */ static inline void ib_dma_free_coherent(struct ib_device *dev, size_t size, void *cpu_addr, dma_addr_t dma_handle) { dma_free_coherent(dev->dma_device, size, cpu_addr, dma_handle); } /** * ib_dereg_mr - Deregisters a memory region and removes it from the * HCA translation table. * @mr: The memory region to deregister. * * This function can fail, if the memory region has memory windows bound to it. */ int ib_dereg_mr(struct ib_mr *mr); struct ib_mr *ib_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type, u32 max_num_sg); /** * ib_update_fast_reg_key - updates the key portion of the fast_reg MR * R_Key and L_Key. * @mr - struct ib_mr pointer to be updated. * @newkey - new key to be used. */ static inline void ib_update_fast_reg_key(struct ib_mr *mr, u8 newkey) { mr->lkey = (mr->lkey & 0xffffff00) | newkey; mr->rkey = (mr->rkey & 0xffffff00) | newkey; } /** * ib_inc_rkey - increments the key portion of the given rkey. Can be used * for calculating a new rkey for type 2 memory windows. * @rkey - the rkey to increment. */ static inline u32 ib_inc_rkey(u32 rkey) { const u32 mask = 0x000000ff; return ((rkey + 1) & mask) | (rkey & ~mask); } /** * ib_alloc_fmr - Allocates a unmapped fast memory region. * @pd: The protection domain associated with the unmapped region. * @mr_access_flags: Specifies the memory access rights. * @fmr_attr: Attributes of the unmapped region. * * A fast memory region must be mapped before it can be used as part of * a work request. */ struct ib_fmr *ib_alloc_fmr(struct ib_pd *pd, int mr_access_flags, struct ib_fmr_attr *fmr_attr); /** * ib_map_phys_fmr - Maps a list of physical pages to a fast memory region. * @fmr: The fast memory region to associate with the pages. * @page_list: An array of physical pages to map to the fast memory region. * @list_len: The number of pages in page_list. * @iova: The I/O virtual address to use with the mapped region. */ static inline int ib_map_phys_fmr(struct ib_fmr *fmr, u64 *page_list, int list_len, u64 iova) { return fmr->device->map_phys_fmr(fmr, page_list, list_len, iova); } /** * ib_unmap_fmr - Removes the mapping from a list of fast memory regions. * @fmr_list: A linked list of fast memory regions to unmap. */ int ib_unmap_fmr(struct list_head *fmr_list); /** * ib_dealloc_fmr - Deallocates a fast memory region. * @fmr: The fast memory region to deallocate. */ int ib_dealloc_fmr(struct ib_fmr *fmr); /** * ib_attach_mcast - Attaches the specified QP to a multicast group. * @qp: QP to attach to the multicast group. The QP must be type * IB_QPT_UD. * @gid: Multicast group GID. * @lid: Multicast group LID in host byte order. * * In order to send and receive multicast packets, subnet * administration must have created the multicast group and configured * the fabric appropriately. The port associated with the specified * QP must also be a member of the multicast group. */ int ib_attach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid); /** * ib_detach_mcast - Detaches the specified QP from a multicast group. * @qp: QP to detach from the multicast group. * @gid: Multicast group GID. * @lid: Multicast group LID in host byte order. */ int ib_detach_mcast(struct ib_qp *qp, union ib_gid *gid, u16 lid); /** * ib_alloc_xrcd - Allocates an XRC domain. * @device: The device on which to allocate the XRC domain. */ struct ib_xrcd *ib_alloc_xrcd(struct ib_device *device); /** * ib_dealloc_xrcd - Deallocates an XRC domain. * @xrcd: The XRC domain to deallocate. */ int ib_dealloc_xrcd(struct ib_xrcd *xrcd); struct ib_flow *ib_create_flow(struct ib_qp *qp, struct ib_flow_attr *flow_attr, int domain); int ib_destroy_flow(struct ib_flow *flow_id); static inline int ib_check_mr_access(int flags) { /* * Local write permission is required if remote write or * remote atomic permission is also requested. */ if (flags & (IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_REMOTE_WRITE) && !(flags & IB_ACCESS_LOCAL_WRITE)) return -EINVAL; return 0; } static inline bool ib_access_writable(int access_flags) { /* * We have writable memory backing the MR if any of the following * access flags are set. "Local write" and "remote write" obviously * require write access. "Remote atomic" can do things like fetch and * add, which will modify memory, and "MW bind" can change permissions * by binding a window. */ return access_flags & (IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_MW_BIND); } /** * ib_check_mr_status: lightweight check of MR status. * This routine may provide status checks on a selected * ib_mr. first use is for signature status check. * * @mr: A memory region. * @check_mask: Bitmask of which checks to perform from * ib_mr_status_check enumeration. * @mr_status: The container of relevant status checks. * failed checks will be indicated in the status bitmask * and the relevant info shall be in the error item. */ int ib_check_mr_status(struct ib_mr *mr, u32 check_mask, struct ib_mr_status *mr_status); struct net_device *ib_get_net_dev_by_params(struct ib_device *dev, u8 port, u16 pkey, const union ib_gid *gid, const struct sockaddr *addr); struct ib_wq *ib_create_wq(struct ib_pd *pd, struct ib_wq_init_attr *init_attr); int ib_destroy_wq(struct ib_wq *wq); int ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *attr, u32 wq_attr_mask); struct ib_rwq_ind_table *ib_create_rwq_ind_table(struct ib_device *device, struct ib_rwq_ind_table_init_attr* wq_ind_table_init_attr); int ib_destroy_rwq_ind_table(struct ib_rwq_ind_table *wq_ind_table); int ib_map_mr_sg(struct ib_mr *mr, struct scatterlist *sg, int sg_nents, unsigned int *sg_offset, unsigned int page_size); static inline int ib_map_mr_sg_zbva(struct ib_mr *mr, struct scatterlist *sg, int sg_nents, unsigned int *sg_offset, unsigned int page_size) { int n; n = ib_map_mr_sg(mr, sg, sg_nents, sg_offset, page_size); mr->iova = 0; return n; } int ib_sg_to_pages(struct ib_mr *mr, struct scatterlist *sgl, int sg_nents, unsigned int *sg_offset, int (*set_page)(struct ib_mr *, u64)); void ib_drain_rq(struct ib_qp *qp); void ib_drain_sq(struct ib_qp *qp); void ib_drain_qp(struct ib_qp *qp); int ib_resolve_eth_dmac(struct ib_device *device, struct rdma_ah_attr *ah_attr); int ib_get_eth_speed(struct ib_device *dev, u8 port_num, u8 *speed, u8 *width); static inline u8 *rdma_ah_retrieve_dmac(struct rdma_ah_attr *attr) { if (attr->type == RDMA_AH_ATTR_TYPE_ROCE) return attr->roce.dmac; return NULL; } static inline void rdma_ah_set_dlid(struct rdma_ah_attr *attr, u32 dlid) { if (attr->type == RDMA_AH_ATTR_TYPE_IB) attr->ib.dlid = (u16)dlid; else if (attr->type == RDMA_AH_ATTR_TYPE_OPA) attr->opa.dlid = dlid; } static inline u32 rdma_ah_get_dlid(const struct rdma_ah_attr *attr) { if (attr->type == RDMA_AH_ATTR_TYPE_IB) return attr->ib.dlid; else if (attr->type == RDMA_AH_ATTR_TYPE_OPA) return attr->opa.dlid; return 0; } static inline void rdma_ah_set_sl(struct rdma_ah_attr *attr, u8 sl) { attr->sl = sl; } static inline u8 rdma_ah_get_sl(const struct rdma_ah_attr *attr) { return attr->sl; } static inline void rdma_ah_set_path_bits(struct rdma_ah_attr *attr, u8 src_path_bits) { if (attr->type == RDMA_AH_ATTR_TYPE_IB) attr->ib.src_path_bits = src_path_bits; else if (attr->type == RDMA_AH_ATTR_TYPE_OPA) attr->opa.src_path_bits = src_path_bits; } static inline u8 rdma_ah_get_path_bits(const struct rdma_ah_attr *attr) { if (attr->type == RDMA_AH_ATTR_TYPE_IB) return attr->ib.src_path_bits; else if (attr->type == RDMA_AH_ATTR_TYPE_OPA) return attr->opa.src_path_bits; return 0; } static inline void rdma_ah_set_make_grd(struct rdma_ah_attr *attr, bool make_grd) { if (attr->type == RDMA_AH_ATTR_TYPE_OPA) attr->opa.make_grd = make_grd; } static inline bool rdma_ah_get_make_grd(const struct rdma_ah_attr *attr) { if (attr->type == RDMA_AH_ATTR_TYPE_OPA) return attr->opa.make_grd; return false; } static inline void rdma_ah_set_port_num(struct rdma_ah_attr *attr, u8 port_num) { attr->port_num = port_num; } static inline u8 rdma_ah_get_port_num(const struct rdma_ah_attr *attr) { return attr->port_num; } static inline void rdma_ah_set_static_rate(struct rdma_ah_attr *attr, u8 static_rate) { attr->static_rate = static_rate; } static inline u8 rdma_ah_get_static_rate(const struct rdma_ah_attr *attr) { return attr->static_rate; } static inline void rdma_ah_set_ah_flags(struct rdma_ah_attr *attr, enum ib_ah_flags flag) { attr->ah_flags = flag; } static inline enum ib_ah_flags rdma_ah_get_ah_flags(const struct rdma_ah_attr *attr) { return attr->ah_flags; } static inline const struct ib_global_route *rdma_ah_read_grh(const struct rdma_ah_attr *attr) { return &attr->grh; } /*To retrieve and modify the grh */ static inline struct ib_global_route *rdma_ah_retrieve_grh(struct rdma_ah_attr *attr) { return &attr->grh; } static inline void rdma_ah_set_dgid_raw(struct rdma_ah_attr *attr, void *dgid) { struct ib_global_route *grh = rdma_ah_retrieve_grh(attr); memcpy(grh->dgid.raw, dgid, sizeof(grh->dgid)); } static inline void rdma_ah_set_subnet_prefix(struct rdma_ah_attr *attr, __be64 prefix) { struct ib_global_route *grh = rdma_ah_retrieve_grh(attr); grh->dgid.global.subnet_prefix = prefix; } static inline void rdma_ah_set_interface_id(struct rdma_ah_attr *attr, __be64 if_id) { struct ib_global_route *grh = rdma_ah_retrieve_grh(attr); grh->dgid.global.interface_id = if_id; } static inline void rdma_ah_set_grh(struct rdma_ah_attr *attr, union ib_gid *dgid, u32 flow_label, u8 sgid_index, u8 hop_limit, u8 traffic_class) { struct ib_global_route *grh = rdma_ah_retrieve_grh(attr); attr->ah_flags = IB_AH_GRH; if (dgid) grh->dgid = *dgid; grh->flow_label = flow_label; grh->sgid_index = sgid_index; grh->hop_limit = hop_limit; grh->traffic_class = traffic_class; } /** * rdma_ah_find_type - Return address handle type. * * @dev: Device to be checked * @port_num: Port number */ static inline enum rdma_ah_attr_type rdma_ah_find_type(struct ib_device *dev, u8 port_num) { if (rdma_protocol_roce(dev, port_num)) return RDMA_AH_ATTR_TYPE_ROCE; if (rdma_protocol_ib(dev, port_num)) { if (rdma_cap_opa_ah(dev, port_num)) return RDMA_AH_ATTR_TYPE_OPA; return RDMA_AH_ATTR_TYPE_IB; } return RDMA_AH_ATTR_TYPE_UNDEFINED; } /** * ib_lid_cpu16 - Return lid in 16bit CPU encoding. * In the current implementation the only way to get * get the 32bit lid is from other sources for OPA. * For IB, lids will always be 16bits so cast the * value accordingly. * * @lid: A 32bit LID */ static inline u16 ib_lid_cpu16(u32 lid) { WARN_ON_ONCE(lid & 0xFFFF0000); return (u16)lid; } /** * ib_lid_be16 - Return lid in 16bit BE encoding. * * @lid: A 32bit LID */ static inline __be16 ib_lid_be16(u32 lid) { WARN_ON_ONCE(lid & 0xFFFF0000); return cpu_to_be16((u16)lid); } /** * ib_get_vector_affinity - Get the affinity mappings of a given completion * vector * @device: the rdma device * @comp_vector: index of completion vector * * Returns NULL on failure, otherwise a corresponding cpu map of the * completion vector (returns all-cpus map if the device driver doesn't * implement get_vector_affinity). */ static inline const struct cpumask * ib_get_vector_affinity(struct ib_device *device, int comp_vector) { if (comp_vector < 0 || comp_vector >= device->num_comp_vectors || !device->get_vector_affinity) return NULL; return device->get_vector_affinity(device, comp_vector); } #endif /* IB_VERBS_H */ |
| 7 27 27 27 1 27 8 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 | /* * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. * * Copyright Jonathan Naylor G4KLX (g4klx@g4klx.demon.co.uk) */ #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/kernel.h> #include <linux/timer.h> #include <linux/string.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/slab.h> #include <net/ax25.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <net/sock.h> #include <net/tcp_states.h> #include <linux/uaccess.h> #include <linux/fcntl.h> #include <linux/mm.h> #include <linux/interrupt.h> #include <net/netrom.h> /* * This routine purges all of the queues of frames. */ void nr_clear_queues(struct sock *sk) { struct nr_sock *nr = nr_sk(sk); skb_queue_purge(&sk->sk_write_queue); skb_queue_purge(&nr->ack_queue); skb_queue_purge(&nr->reseq_queue); skb_queue_purge(&nr->frag_queue); } /* * This routine purges the input queue of those frames that have been * acknowledged. This replaces the boxes labelled "V(a) <- N(r)" on the * SDL diagram. */ void nr_frames_acked(struct sock *sk, unsigned short nr) { struct nr_sock *nrom = nr_sk(sk); struct sk_buff *skb; /* * Remove all the ack-ed frames from the ack queue. */ if (nrom->va != nr) { while (skb_peek(&nrom->ack_queue) != NULL && nrom->va != nr) { skb = skb_dequeue(&nrom->ack_queue); kfree_skb(skb); nrom->va = (nrom->va + 1) % NR_MODULUS; } } } /* * Requeue all the un-ack-ed frames on the output queue to be picked * up by nr_kick called from the timer. This arrangement handles the * possibility of an empty output queue. */ void nr_requeue_frames(struct sock *sk) { struct sk_buff *skb, *skb_prev = NULL; while ((skb = skb_dequeue(&nr_sk(sk)->ack_queue)) != NULL) { if (skb_prev == NULL) skb_queue_head(&sk->sk_write_queue, skb); else skb_append(skb_prev, skb, &sk->sk_write_queue); skb_prev = skb; } } /* * Validate that the value of nr is between va and vs. Return true or * false for testing. */ int nr_validate_nr(struct sock *sk, unsigned short nr) { struct nr_sock *nrom = nr_sk(sk); unsigned short vc = nrom->va; while (vc != nrom->vs) { if (nr == vc) return 1; vc = (vc + 1) % NR_MODULUS; } return nr == nrom->vs; } /* * Check that ns is within the receive window. */ int nr_in_rx_window(struct sock *sk, unsigned short ns) { struct nr_sock *nr = nr_sk(sk); unsigned short vc = nr->vr; unsigned short vt = (nr->vl + nr->window) % NR_MODULUS; while (vc != vt) { if (ns == vc) return 1; vc = (vc + 1) % NR_MODULUS; } return 0; } /* * This routine is called when the HDLC layer internally generates a * control frame. */ void nr_write_internal(struct sock *sk, int frametype) { struct nr_sock *nr = nr_sk(sk); struct sk_buff *skb; unsigned char *dptr; int len, timeout; len = NR_NETWORK_LEN + NR_TRANSPORT_LEN; switch (frametype & 0x0F) { case NR_CONNREQ: len += 17; break; case NR_CONNACK: len += (nr->bpqext) ? 2 : 1; break; case NR_DISCREQ: case NR_DISCACK: case NR_INFOACK: break; default: printk(KERN_ERR "NET/ROM: nr_write_internal - invalid frame type %d\n", frametype); return; } if ((skb = alloc_skb(len, GFP_ATOMIC)) == NULL) return; /* * Space for AX.25 and NET/ROM network header */ skb_reserve(skb, NR_NETWORK_LEN); dptr = skb_put(skb, skb_tailroom(skb)); switch (frametype & 0x0F) { case NR_CONNREQ: timeout = nr->t1 / HZ; *dptr++ = nr->my_index; *dptr++ = nr->my_id; *dptr++ = 0; *dptr++ = 0; *dptr++ = frametype; *dptr++ = nr->window; memcpy(dptr, &nr->user_addr, AX25_ADDR_LEN); dptr[6] &= ~AX25_CBIT; dptr[6] &= ~AX25_EBIT; dptr[6] |= AX25_SSSID_SPARE; dptr += AX25_ADDR_LEN; memcpy(dptr, &nr->source_addr, AX25_ADDR_LEN); dptr[6] &= ~AX25_CBIT; dptr[6] &= ~AX25_EBIT; dptr[6] |= AX25_SSSID_SPARE; dptr += AX25_ADDR_LEN; *dptr++ = timeout % 256; *dptr++ = timeout / 256; break; case NR_CONNACK: *dptr++ = nr->your_index; *dptr++ = nr->your_id; *dptr++ = nr->my_index; *dptr++ = nr->my_id; *dptr++ = frametype; *dptr++ = nr->window; if (nr->bpqext) *dptr++ = sysctl_netrom_network_ttl_initialiser; break; case NR_DISCREQ: case NR_DISCACK: *dptr++ = nr->your_index; *dptr++ = nr->your_id; *dptr++ = 0; *dptr++ = 0; *dptr++ = frametype; break; case NR_INFOACK: *dptr++ = nr->your_index; *dptr++ = nr->your_id; *dptr++ = 0; *dptr++ = nr->vr; *dptr++ = frametype; break; } nr_transmit_buffer(sk, skb); } /* * This routine is called to send an error reply. */ void __nr_transmit_reply(struct sk_buff *skb, int mine, unsigned char cmdflags) { struct sk_buff *skbn; unsigned char *dptr; int len; len = NR_NETWORK_LEN + NR_TRANSPORT_LEN + 1; if ((skbn = alloc_skb(len, GFP_ATOMIC)) == NULL) return; skb_reserve(skbn, 0); dptr = skb_put(skbn, NR_NETWORK_LEN + NR_TRANSPORT_LEN); skb_copy_from_linear_data_offset(skb, 7, dptr, AX25_ADDR_LEN); dptr[6] &= ~AX25_CBIT; dptr[6] &= ~AX25_EBIT; dptr[6] |= AX25_SSSID_SPARE; dptr += AX25_ADDR_LEN; skb_copy_from_linear_data(skb, dptr, AX25_ADDR_LEN); dptr[6] &= ~AX25_CBIT; dptr[6] |= AX25_EBIT; dptr[6] |= AX25_SSSID_SPARE; dptr += AX25_ADDR_LEN; *dptr++ = sysctl_netrom_network_ttl_initialiser; if (mine) { *dptr++ = 0; *dptr++ = 0; *dptr++ = skb->data[15]; *dptr++ = skb->data[16]; } else { *dptr++ = skb->data[15]; *dptr++ = skb->data[16]; *dptr++ = 0; *dptr++ = 0; } *dptr++ = cmdflags; *dptr++ = 0; if (!nr_route_frame(skbn, NULL)) kfree_skb(skbn); } void nr_disconnect(struct sock *sk, int reason) { nr_stop_t1timer(sk); nr_stop_t2timer(sk); nr_stop_t4timer(sk); nr_stop_idletimer(sk); nr_clear_queues(sk); nr_sk(sk)->state = NR_STATE_0; sk->sk_state = TCP_CLOSE; sk->sk_err = reason; sk->sk_shutdown |= SEND_SHUTDOWN; if (!sock_flag(sk, SOCK_DEAD)) { sk->sk_state_change(sk); sock_set_flag(sk, SOCK_DEAD); } } |
| 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 | /* Copyright (c) 2016 Facebook * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public * License as published by the Free Software Foundation. */ #ifndef __BPF_LRU_LIST_H_ #define __BPF_LRU_LIST_H_ #include <linux/list.h> #include <linux/spinlock_types.h> #define NR_BPF_LRU_LIST_T (3) #define NR_BPF_LRU_LIST_COUNT (2) #define NR_BPF_LRU_LOCAL_LIST_T (2) #define BPF_LOCAL_LIST_T_OFFSET NR_BPF_LRU_LIST_T enum bpf_lru_list_type { BPF_LRU_LIST_T_ACTIVE, BPF_LRU_LIST_T_INACTIVE, BPF_LRU_LIST_T_FREE, BPF_LRU_LOCAL_LIST_T_FREE, BPF_LRU_LOCAL_LIST_T_PENDING, }; struct bpf_lru_node { struct list_head list; u16 cpu; u8 type; u8 ref; }; struct bpf_lru_list { struct list_head lists[NR_BPF_LRU_LIST_T]; unsigned int counts[NR_BPF_LRU_LIST_COUNT]; /* The next inacitve list rotation starts from here */ struct list_head *next_inactive_rotation; raw_spinlock_t lock ____cacheline_aligned_in_smp; }; struct bpf_lru_locallist { struct list_head lists[NR_BPF_LRU_LOCAL_LIST_T]; u16 next_steal; raw_spinlock_t lock; }; struct bpf_common_lru { struct bpf_lru_list lru_list; struct bpf_lru_locallist __percpu *local_list; }; typedef bool (*del_from_htab_func)(void *arg, struct bpf_lru_node *node); struct bpf_lru { union { struct bpf_common_lru common_lru; struct bpf_lru_list __percpu *percpu_lru; }; del_from_htab_func del_from_htab; void *del_arg; unsigned int hash_offset; unsigned int nr_scans; bool percpu; }; static inline void bpf_lru_node_set_ref(struct bpf_lru_node *node) { /* ref is an approximation on access frequency. It does not * have to be very accurate. Hence, no protection is used. */ if (!node->ref) node->ref = 1; } int bpf_lru_init(struct bpf_lru *lru, bool percpu, u32 hash_offset, del_from_htab_func del_from_htab, void *delete_arg); void bpf_lru_populate(struct bpf_lru *lru, void *buf, u32 node_offset, u32 elem_size, u32 nr_elems); void bpf_lru_destroy(struct bpf_lru *lru); struct bpf_lru_node *bpf_lru_pop_free(struct bpf_lru *lru, u32 hash); void bpf_lru_push_free(struct bpf_lru *lru, struct bpf_lru_node *node); void bpf_lru_promote(struct bpf_lru *lru, struct bpf_lru_node *node); #endif |
| 9 11 11 11 3 8 5 11 12 8 8 8 6 5 1743 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 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 | #include <linux/etherdevice.h> #include <linux/if_macvlan.h> #include <linux/if_tap.h> #include <linux/if_vlan.h> #include <linux/interrupt.h> #include <linux/nsproxy.h> #include <linux/compat.h> #include <linux/if_tun.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/cache.h> #include <linux/sched/signal.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/wait.h> #include <linux/cdev.h> #include <linux/idr.h> #include <linux/fs.h> #include <linux/uio.h> #include <net/net_namespace.h> #include <net/rtnetlink.h> #include <net/sock.h> #include <linux/virtio_net.h> #include <linux/skb_array.h> struct macvtap_dev { struct macvlan_dev vlan; struct tap_dev tap; }; /* * Variables for dealing with macvtaps device numbers. */ static dev_t macvtap_major; static const void *macvtap_net_namespace(struct device *d) { struct net_device *dev = to_net_dev(d->parent); return dev_net(dev); } static struct class macvtap_class = { .name = "macvtap", .owner = THIS_MODULE, .ns_type = &net_ns_type_operations, .namespace = macvtap_net_namespace, }; static struct cdev macvtap_cdev; #define TUN_OFFLOADS (NETIF_F_HW_CSUM | NETIF_F_TSO_ECN | NETIF_F_TSO | \ NETIF_F_TSO6) static void macvtap_count_tx_dropped(struct tap_dev *tap) { struct macvtap_dev *vlantap = container_of(tap, struct macvtap_dev, tap); struct macvlan_dev *vlan = &vlantap->vlan; this_cpu_inc(vlan->pcpu_stats->tx_dropped); } static void macvtap_count_rx_dropped(struct tap_dev *tap) { struct macvtap_dev *vlantap = container_of(tap, struct macvtap_dev, tap); struct macvlan_dev *vlan = &vlantap->vlan; macvlan_count_rx(vlan, 0, 0, 0); } static void macvtap_update_features(struct tap_dev *tap, netdev_features_t features) { struct macvtap_dev *vlantap = container_of(tap, struct macvtap_dev, tap); struct macvlan_dev *vlan = &vlantap->vlan; vlan->set_features = features; netdev_update_features(vlan->dev); } static int macvtap_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct macvtap_dev *vlantap = netdev_priv(dev); int err; INIT_LIST_HEAD(&vlantap->tap.queue_list); /* Since macvlan supports all offloads by default, make * tap support all offloads also. */ vlantap->tap.tap_features = TUN_OFFLOADS; /* Register callbacks for rx/tx drops accounting and updating * net_device features */ vlantap->tap.count_tx_dropped = macvtap_count_tx_dropped; vlantap->tap.count_rx_dropped = macvtap_count_rx_dropped; vlantap->tap.update_features = macvtap_update_features; err = netdev_rx_handler_register(dev, tap_handle_frame, &vlantap->tap); if (err) return err; /* Don't put anything that may fail after macvlan_common_newlink * because we can't undo what it does. */ err = macvlan_common_newlink(src_net, dev, tb, data); if (err) { netdev_rx_handler_unregister(dev); return err; } vlantap->tap.dev = vlantap->vlan.dev; return 0; } static void macvtap_dellink(struct net_device *dev, struct list_head *head) { struct macvtap_dev *vlantap = netdev_priv(dev); netdev_rx_handler_unregister(dev); tap_del_queues(&vlantap->tap); macvlan_dellink(dev, head); } static void macvtap_setup(struct net_device *dev) { macvlan_common_setup(dev); dev->tx_queue_len = TUN_READQ_SIZE; } static struct net *macvtap_link_net(const struct net_device *dev) { return dev_net(macvlan_dev_real_dev(dev)); } static struct rtnl_link_ops macvtap_link_ops __read_mostly = { .kind = "macvtap", .setup = macvtap_setup, .newlink = macvtap_newlink, .dellink = macvtap_dellink, .get_link_net = macvtap_link_net, .priv_size = sizeof(struct macvtap_dev), }; static int macvtap_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct macvtap_dev *vlantap; struct device *classdev; dev_t devt; int err; char tap_name[IFNAMSIZ]; if (dev->rtnl_link_ops != &macvtap_link_ops) return NOTIFY_DONE; snprintf(tap_name, IFNAMSIZ, "tap%d", dev->ifindex); vlantap = netdev_priv(dev); switch (event) { case NETDEV_REGISTER: /* Create the device node here after the network device has * been registered but before register_netdevice has * finished running. */ err = tap_get_minor(macvtap_major, &vlantap->tap); if (err) return notifier_from_errno(err); devt = MKDEV(MAJOR(macvtap_major), vlantap->tap.minor); classdev = device_create(&macvtap_class, &dev->dev, devt, dev, tap_name); if (IS_ERR(classdev)) { tap_free_minor(macvtap_major, &vlantap->tap); return notifier_from_errno(PTR_ERR(classdev)); } err = sysfs_create_link(&dev->dev.kobj, &classdev->kobj, tap_name); if (err) return notifier_from_errno(err); break; case NETDEV_UNREGISTER: /* vlan->minor == 0 if NETDEV_REGISTER above failed */ if (vlantap->tap.minor == 0) break; sysfs_remove_link(&dev->dev.kobj, tap_name); devt = MKDEV(MAJOR(macvtap_major), vlantap->tap.minor); device_destroy(&macvtap_class, devt); tap_free_minor(macvtap_major, &vlantap->tap); break; case NETDEV_CHANGE_TX_QUEUE_LEN: if (tap_queue_resize(&vlantap->tap)) return NOTIFY_BAD; break; } return NOTIFY_DONE; } static struct notifier_block macvtap_notifier_block __read_mostly = { .notifier_call = macvtap_device_event, }; static int macvtap_init(void) { int err; err = tap_create_cdev(&macvtap_cdev, &macvtap_major, "macvtap", THIS_MODULE); if (err) goto out1; err = class_register(&macvtap_class); if (err) goto out2; err = register_netdevice_notifier(&macvtap_notifier_block); if (err) goto out3; err = macvlan_link_register(&macvtap_link_ops); if (err) goto out4; return 0; out4: unregister_netdevice_notifier(&macvtap_notifier_block); out3: class_unregister(&macvtap_class); out2: tap_destroy_cdev(macvtap_major, &macvtap_cdev); out1: return err; } module_init(macvtap_init); static void macvtap_exit(void) { rtnl_link_unregister(&macvtap_link_ops); unregister_netdevice_notifier(&macvtap_notifier_block); class_unregister(&macvtap_class); tap_destroy_cdev(macvtap_major, &macvtap_cdev); } module_exit(macvtap_exit); MODULE_ALIAS_RTNL_LINK("macvtap"); MODULE_AUTHOR("Arnd Bergmann <arnd@arndb.de>"); MODULE_LICENSE("GPL"); |
| 2 3 3 432 6 6 6 6 5 6 2 7 3 3 9 9 9 4 4 2 2 2 1 1 1741 1741 15 15 15 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 | // 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 <net/netlink.h> #include <net/genetlink.h> #include <uapi/linux/if.h> #include <uapi/linux/smc.h> #include <rdma/ib_verbs.h> #include "smc_pnet.h" #include "smc_ib.h" #define SMC_MAX_PNET_ID_LEN 16 /* Max. length of PNET id */ static struct nla_policy smc_pnet_policy[SMC_PNETID_MAX + 1] = { [SMC_PNETID_NAME] = { .type = NLA_NUL_STRING, .len = SMC_MAX_PNET_ID_LEN - 1 }, [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; /** * struct smc_pnettable - SMC PNET table anchor * @lock: Lock for list action * @pnetlist: List of PNETIDs */ static struct smc_pnettable { rwlock_t lock; struct list_head pnetlist; } smc_pnettable = { .pnetlist = LIST_HEAD_INIT(smc_pnettable.pnetlist), .lock = __RW_LOCK_UNLOCKED(smc_pnettable.lock) }; /** * struct smc_pnetentry - pnet identifier name entry * @list: List node. * @pnet_name: Pnet identifier name * @ndev: pointer to network device. * @smcibdev: Pointer to IB device. */ struct smc_pnetentry { struct list_head list; char pnet_name[SMC_MAX_PNET_ID_LEN + 1]; struct net_device *ndev; struct smc_ib_device *smcibdev; u8 ib_port; }; /* Check if two RDMA device entries are identical. Use device name and port * number for comparison. */ static bool smc_pnet_same_ibname(struct smc_pnetentry *pnetelem, char *ibname, u8 ibport) { return pnetelem->ib_port == ibport && !strncmp(pnetelem->smcibdev->ibdev->name, ibname, sizeof(pnetelem->smcibdev->ibdev->name)); } /* Find a pnetid in the pnet table. */ static struct smc_pnetentry *smc_pnet_find_pnetid(char *pnet_name) { struct smc_pnetentry *pnetelem, *found_pnetelem = NULL; read_lock(&smc_pnettable.lock); list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) { if (!strncmp(pnetelem->pnet_name, pnet_name, sizeof(pnetelem->pnet_name))) { found_pnetelem = pnetelem; break; } } read_unlock(&smc_pnettable.lock); return found_pnetelem; } /* Remove a pnetid from the pnet table. */ static int smc_pnet_remove_by_pnetid(char *pnet_name) { struct smc_pnetentry *pnetelem, *tmp_pe; int rc = -ENOENT; write_lock(&smc_pnettable.lock); list_for_each_entry_safe(pnetelem, tmp_pe, &smc_pnettable.pnetlist, list) { if (!strncmp(pnetelem->pnet_name, pnet_name, sizeof(pnetelem->pnet_name))) { list_del(&pnetelem->list); dev_put(pnetelem->ndev); kfree(pnetelem); rc = 0; break; } } write_unlock(&smc_pnettable.lock); return rc; } /* Remove a pnet entry mentioning 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; int rc = -ENOENT; write_lock(&smc_pnettable.lock); list_for_each_entry_safe(pnetelem, tmp_pe, &smc_pnettable.pnetlist, list) { if (pnetelem->ndev == ndev) { list_del(&pnetelem->list); dev_put(pnetelem->ndev); kfree(pnetelem); rc = 0; break; } } write_unlock(&smc_pnettable.lock); return rc; } /* Remove a pnet entry mentioning a given ib device from the pnet table. */ int smc_pnet_remove_by_ibdev(struct smc_ib_device *ibdev) { struct smc_pnetentry *pnetelem, *tmp_pe; int rc = -ENOENT; write_lock(&smc_pnettable.lock); list_for_each_entry_safe(pnetelem, tmp_pe, &smc_pnettable.pnetlist, list) { if (pnetelem->smcibdev == ibdev) { list_del(&pnetelem->list); dev_put(pnetelem->ndev); kfree(pnetelem); rc = 0; break; } } write_unlock(&smc_pnettable.lock); return rc; } /* Append a pnetid to the end of the pnet table if not already on this list. */ static int smc_pnet_enter(struct smc_pnetentry *new_pnetelem) { struct smc_pnetentry *pnetelem; int rc = -EEXIST; write_lock(&smc_pnettable.lock); list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) { if (!strncmp(pnetelem->pnet_name, new_pnetelem->pnet_name, sizeof(new_pnetelem->pnet_name)) || !strncmp(pnetelem->ndev->name, new_pnetelem->ndev->name, sizeof(new_pnetelem->ndev->name)) || smc_pnet_same_ibname(pnetelem, new_pnetelem->smcibdev->ibdev->name, new_pnetelem->ib_port)) { dev_put(pnetelem->ndev); goto found; } } list_add_tail(&new_pnetelem->list, &smc_pnettable.pnetlist); rc = 0; found: write_unlock(&smc_pnettable.lock); return rc; } /* 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_PNET_ID_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; spin_lock(&smc_ib_devices.lock); list_for_each_entry(ibdev, &smc_ib_devices.list, list) { if (!strncmp(ibdev->ibdev->name, ib_name, sizeof(ibdev->ibdev->name))) { goto out; } } ibdev = NULL; out: spin_unlock(&smc_ib_devices.lock); return ibdev; } /* Parse the supplied netlink attributes and fill a pnetentry structure. * For ethernet and infiniband device names verify that the devices exist. */ static int smc_pnet_fill_entry(struct net *net, struct smc_pnetentry *pnetelem, struct nlattr *tb[]) { char *string, *ibname; int rc; memset(pnetelem, 0, sizeof(*pnetelem)); INIT_LIST_HEAD(&pnetelem->list); rc = -EINVAL; if (!tb[SMC_PNETID_NAME]) goto error; string = (char *)nla_data(tb[SMC_PNETID_NAME]); if (!smc_pnetid_valid(string, pnetelem->pnet_name)) goto error; rc = -EINVAL; if (!tb[SMC_PNETID_ETHNAME]) goto error; rc = -ENOENT; string = (char *)nla_data(tb[SMC_PNETID_ETHNAME]); pnetelem->ndev = dev_get_by_name(net, string); if (!pnetelem->ndev) goto error; rc = -EINVAL; if (!tb[SMC_PNETID_IBNAME]) goto error; rc = -ENOENT; ibname = (char *)nla_data(tb[SMC_PNETID_IBNAME]); ibname = strim(ibname); pnetelem->smcibdev = smc_pnet_find_ib(ibname); if (!pnetelem->smcibdev) goto error; rc = -EINVAL; if (!tb[SMC_PNETID_IBPORT]) goto error; pnetelem->ib_port = nla_get_u8(tb[SMC_PNETID_IBPORT]); if (pnetelem->ib_port < 1 || pnetelem->ib_port > SMC_MAX_PORTS) goto error; return 0; error: if (pnetelem->ndev) dev_put(pnetelem->ndev); 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) || nla_put_string(msg, SMC_PNETID_ETHNAME, pnetelem->ndev->name) || nla_put_string(msg, SMC_PNETID_IBNAME, pnetelem->smcibdev->ibdev->name) || nla_put_u8(msg, SMC_PNETID_IBPORT, pnetelem->ib_port)) return -1; return 0; } /* Retrieve one PNETID entry */ static int smc_pnet_get(struct sk_buff *skb, struct genl_info *info) { struct smc_pnetentry *pnetelem; struct sk_buff *msg; void *hdr; int rc; if (!info->attrs[SMC_PNETID_NAME]) return -EINVAL; pnetelem = smc_pnet_find_pnetid( (char *)nla_data(info->attrs[SMC_PNETID_NAME])); if (!pnetelem) return -ENOENT; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &smc_pnet_nl_family, 0, SMC_PNETID_GET); if (!hdr) { rc = -EMSGSIZE; goto err_out; } if (smc_pnet_set_nla(msg, pnetelem)) { rc = -ENOBUFS; goto err_out; } genlmsg_end(msg, hdr); return genlmsg_reply(msg, info); err_out: nlmsg_free(msg); return rc; } static int smc_pnet_add(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct smc_pnetentry *pnetelem; int rc; pnetelem = kzalloc(sizeof(*pnetelem), GFP_KERNEL); if (!pnetelem) return -ENOMEM; rc = smc_pnet_fill_entry(net, pnetelem, info->attrs); if (!rc) rc = smc_pnet_enter(pnetelem); if (rc) { kfree(pnetelem); return rc; } rc = smc_ib_remember_port_attr(pnetelem->smcibdev, pnetelem->ib_port); if (rc) smc_pnet_remove_by_pnetid(pnetelem->pnet_name); return rc; } static int smc_pnet_del(struct sk_buff *skb, struct genl_info *info) { if (!info->attrs[SMC_PNETID_NAME]) return -EINVAL; return smc_pnet_remove_by_pnetid( (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 sk_buff *skb, struct netlink_callback *cb) { struct smc_pnetentry *pnetelem; int idx = 0; read_lock(&smc_pnettable.lock); list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) { if (idx++ < cb->args[0]) continue; if (smc_pnet_dumpinfo(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, pnetelem)) { --idx; break; } } cb->args[0] = idx; read_unlock(&smc_pnettable.lock); return skb->len; } /* Remove and delete all pnetids from pnet table. */ static int smc_pnet_flush(struct sk_buff *skb, struct genl_info *info) { struct smc_pnetentry *pnetelem, *tmp_pe; write_lock(&smc_pnettable.lock); list_for_each_entry_safe(pnetelem, tmp_pe, &smc_pnettable.pnetlist, list) { list_del(&pnetelem->list); dev_put(pnetelem->ndev); kfree(pnetelem); } write_unlock(&smc_pnettable.lock); return 0; } /* SMC_PNETID generic netlink operation definition */ static const struct genl_ops smc_pnet_ops[] = { { .cmd = SMC_PNETID_GET, .flags = GENL_ADMIN_PERM, .policy = smc_pnet_policy, .doit = smc_pnet_get, .dumpit = smc_pnet_dump, .start = smc_pnet_dump_start }, { .cmd = SMC_PNETID_ADD, .flags = GENL_ADMIN_PERM, .policy = smc_pnet_policy, .doit = smc_pnet_add }, { .cmd = SMC_PNETID_DEL, .flags = GENL_ADMIN_PERM, .policy = smc_pnet_policy, .doit = smc_pnet_del }, { .cmd = SMC_PNETID_FLUSH, .flags = GENL_ADMIN_PERM, .policy = smc_pnet_policy, .doit = smc_pnet_flush } }; /* SMC_PNETID family definition */ static struct genl_family smc_pnet_nl_family = { .hdrsize = 0, .name = SMCR_GENL_FAMILY_NAME, .version = SMCR_GENL_FAMILY_VERSION, .maxattr = SMC_PNETID_MAX, .netnsok = true, .module = THIS_MODULE, .ops = smc_pnet_ops, .n_ops = ARRAY_SIZE(smc_pnet_ops) }; 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); switch (event) { case NETDEV_REBOOT: case NETDEV_UNREGISTER: smc_pnet_remove_by_ndev(event_dev); default: break; } return NOTIFY_DONE; } static struct notifier_block smc_netdev_notifier = { .notifier_call = smc_pnet_netdev_event }; 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; } void smc_pnet_exit(void) { smc_pnet_flush(NULL, NULL); unregister_netdevice_notifier(&smc_netdev_notifier); genl_unregister_family(&smc_pnet_nl_family); } /* 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_ib_device **smcibdev, u8 *ibport) { struct dst_entry *dst = sk_dst_get(sk); struct smc_pnetentry *pnetelem; *smcibdev = NULL; *ibport = 0; if (!dst) return; if (!dst->dev) goto out_rel; read_lock(&smc_pnettable.lock); list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) { if (dst->dev == pnetelem->ndev) { if (smc_ib_port_active(pnetelem->smcibdev, pnetelem->ib_port)) { *smcibdev = pnetelem->smcibdev; *ibport = pnetelem->ib_port; } break; } } read_unlock(&smc_pnettable.lock); out_rel: dst_release(dst); } |
| 3 2873 2876 2876 2875 2873 190 1 189 190 190 190 190 190 190 189 334 330 334 4217 3640 3638 1312 195 194 195 190 80 80 80 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 | /* * net/core/dst.c Protocol independent destination cache. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * */ #include <linux/bitops.h> #include <linux/errno.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/workqueue.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/string.h> #include <linux/types.h> #include <net/net_namespace.h> #include <linux/sched.h> #include <linux/prefetch.h> #include <net/lwtunnel.h> #include <net/dst.h> #include <net/dst_metadata.h> /* * Theory of operations: * 1) We use a list, protected by a spinlock, to add * new entries from both BH and non-BH context. * 2) In order to keep spinlock held for a small delay, * we use a second list where are stored long lived * entries, that are handled by the garbage collect thread * fired by a workqueue. * 3) This list is guarded by a mutex, * so that the gc_task and dst_dev_event() can be synchronized. */ /* * We want to keep lock & list close together * to dirty as few cache lines as possible in __dst_free(). * As this is not a very strong hint, we dont force an alignment on SMP. */ int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb) { kfree_skb(skb); return 0; } EXPORT_SYMBOL(dst_discard_out); const struct dst_metrics dst_default_metrics = { /* This initializer is needed to force linker to place this variable * into const section. Otherwise it might end into bss section. * We really want to avoid false sharing on this variable, and catch * any writes on it. */ .refcnt = REFCOUNT_INIT(1), }; void dst_init(struct dst_entry *dst, struct dst_ops *ops, struct net_device *dev, int initial_ref, int initial_obsolete, unsigned short flags) { dst->child = NULL; dst->dev = dev; if (dev) dev_hold(dev); dst->ops = ops; dst_init_metrics(dst, dst_default_metrics.metrics, true); dst->expires = 0UL; dst->path = dst; dst->from = NULL; #ifdef CONFIG_XFRM dst->xfrm = NULL; #endif dst->input = dst_discard; dst->output = dst_discard_out; dst->error = 0; dst->obsolete = initial_obsolete; dst->header_len = 0; dst->trailer_len = 0; #ifdef CONFIG_IP_ROUTE_CLASSID dst->tclassid = 0; #endif dst->lwtstate = NULL; atomic_set(&dst->__refcnt, initial_ref); dst->__use = 0; dst->lastuse = jiffies; dst->flags = flags; dst->next = NULL; if (!(flags & DST_NOCOUNT)) dst_entries_add(ops, 1); } EXPORT_SYMBOL(dst_init); void *dst_alloc(struct dst_ops *ops, struct net_device *dev, int initial_ref, int initial_obsolete, unsigned short flags) { struct dst_entry *dst; if (ops->gc && dst_entries_get_fast(ops) > ops->gc_thresh) { if (ops->gc(ops)) return NULL; } dst = kmem_cache_alloc(ops->kmem_cachep, GFP_ATOMIC); if (!dst) return NULL; dst_init(dst, ops, dev, initial_ref, initial_obsolete, flags); return dst; } EXPORT_SYMBOL(dst_alloc); struct dst_entry *dst_destroy(struct dst_entry * dst) { struct dst_entry *child; smp_rmb(); child = dst->child; if (!(dst->flags & DST_NOCOUNT)) dst_entries_add(dst->ops, -1); if (dst->ops->destroy) dst->ops->destroy(dst); if (dst->dev) dev_put(dst->dev); lwtstate_put(dst->lwtstate); if (dst->flags & DST_METADATA) metadata_dst_free((struct metadata_dst *)dst); else kmem_cache_free(dst->ops->kmem_cachep, dst); dst = child; if (dst) dst_release_immediate(dst); return NULL; } EXPORT_SYMBOL(dst_destroy); static void dst_destroy_rcu(struct rcu_head *head) { struct dst_entry *dst = container_of(head, struct dst_entry, rcu_head); dst = dst_destroy(dst); } /* Operations to mark dst as DEAD and clean up the net device referenced * by dst: * 1. put the dst under loopback interface and discard all tx/rx packets * on this route. * 2. release the net_device * This function should be called when removing routes from the fib tree * in preparation for a NETDEV_DOWN/NETDEV_UNREGISTER event and also to * make the next dst_ops->check() fail. */ void dst_dev_put(struct dst_entry *dst) { struct net_device *dev = dst->dev; dst->obsolete = DST_OBSOLETE_DEAD; if (dst->ops->ifdown) dst->ops->ifdown(dst, dev, true); dst->input = dst_discard; dst->output = dst_discard_out; dst->dev = dev_net(dst->dev)->loopback_dev; dev_hold(dst->dev); dev_put(dev); } EXPORT_SYMBOL(dst_dev_put); void dst_release(struct dst_entry *dst) { if (dst) { int newrefcnt; newrefcnt = atomic_dec_return(&dst->__refcnt); if (unlikely(newrefcnt < 0)) net_warn_ratelimited("%s: dst:%p refcnt:%d\n", __func__, dst, newrefcnt); if (!newrefcnt) call_rcu(&dst->rcu_head, dst_destroy_rcu); } } EXPORT_SYMBOL(dst_release); void dst_release_immediate(struct dst_entry *dst) { if (dst) { int newrefcnt; newrefcnt = atomic_dec_return(&dst->__refcnt); if (unlikely(newrefcnt < 0)) net_warn_ratelimited("%s: dst:%p refcnt:%d\n", __func__, dst, newrefcnt); if (!newrefcnt) dst_destroy(dst); } } EXPORT_SYMBOL(dst_release_immediate); u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old) { struct dst_metrics *p = kmalloc(sizeof(*p), GFP_ATOMIC); if (p) { struct dst_metrics *old_p = (struct dst_metrics *)__DST_METRICS_PTR(old); unsigned long prev, new; refcount_set(&p->refcnt, 1); memcpy(p->metrics, old_p->metrics, sizeof(p->metrics)); new = (unsigned long) p; prev = cmpxchg(&dst->_metrics, old, new); if (prev != old) { kfree(p); p = (struct dst_metrics *)__DST_METRICS_PTR(prev); if (prev & DST_METRICS_READ_ONLY) p = NULL; } else if (prev & DST_METRICS_REFCOUNTED) { if (refcount_dec_and_test(&old_p->refcnt)) kfree(old_p); } } BUILD_BUG_ON(offsetof(struct dst_metrics, metrics) != 0); return (u32 *)p; } EXPORT_SYMBOL(dst_cow_metrics_generic); /* Caller asserts that dst_metrics_read_only(dst) is false. */ void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old) { unsigned long prev, new; new = ((unsigned long) &dst_default_metrics) | DST_METRICS_READ_ONLY; prev = cmpxchg(&dst->_metrics, old, new); if (prev == old) kfree(__DST_METRICS_PTR(old)); } EXPORT_SYMBOL(__dst_destroy_metrics_generic); static struct dst_ops md_dst_ops = { .family = AF_UNSPEC, }; static int dst_md_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb) { WARN_ONCE(1, "Attempting to call output on metadata dst\n"); kfree_skb(skb); return 0; } static int dst_md_discard(struct sk_buff *skb) { WARN_ONCE(1, "Attempting to call input on metadata dst\n"); kfree_skb(skb); return 0; } static void __metadata_dst_init(struct metadata_dst *md_dst, enum metadata_type type, u8 optslen) { struct dst_entry *dst; dst = &md_dst->dst; dst_init(dst, &md_dst_ops, NULL, 1, DST_OBSOLETE_NONE, DST_METADATA | DST_NOCOUNT); dst->input = dst_md_discard; dst->output = dst_md_discard_out; memset(dst + 1, 0, sizeof(*md_dst) + optslen - sizeof(*dst)); md_dst->type = type; } struct metadata_dst *metadata_dst_alloc(u8 optslen, enum metadata_type type, gfp_t flags) { struct metadata_dst *md_dst; md_dst = kmalloc(sizeof(*md_dst) + optslen, flags); if (!md_dst) return NULL; __metadata_dst_init(md_dst, type, optslen); return md_dst; } EXPORT_SYMBOL_GPL(metadata_dst_alloc); void metadata_dst_free(struct metadata_dst *md_dst) { #ifdef CONFIG_DST_CACHE if (md_dst->type == METADATA_IP_TUNNEL) dst_cache_destroy(&md_dst->u.tun_info.dst_cache); #endif kfree(md_dst); } struct metadata_dst __percpu * metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags) { int cpu; struct metadata_dst __percpu *md_dst; md_dst = __alloc_percpu_gfp(sizeof(struct metadata_dst) + optslen, __alignof__(struct metadata_dst), flags); if (!md_dst) return NULL; for_each_possible_cpu(cpu) __metadata_dst_init(per_cpu_ptr(md_dst, cpu), type, optslen); return md_dst; } EXPORT_SYMBOL_GPL(metadata_dst_alloc_percpu); |
| 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 | /* * include/net/switchdev.h - Switch device API * Copyright (c) 2014-2015 Jiri Pirko <jiri@resnulli.us> * Copyright (c) 2014-2015 Scott Feldman <sfeldma@gmail.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. */ #ifndef _LINUX_SWITCHDEV_H_ #define _LINUX_SWITCHDEV_H_ #include <linux/netdevice.h> #include <linux/notifier.h> #include <linux/list.h> #include <net/ip_fib.h> #define SWITCHDEV_F_NO_RECURSE BIT(0) #define SWITCHDEV_F_SKIP_EOPNOTSUPP BIT(1) #define SWITCHDEV_F_DEFER BIT(2) struct switchdev_trans_item { struct list_head list; void *data; void (*destructor)(const void *data); }; struct switchdev_trans { struct list_head item_list; bool ph_prepare; }; static inline bool switchdev_trans_ph_prepare(struct switchdev_trans *trans) { return trans && trans->ph_prepare; } static inline bool switchdev_trans_ph_commit(struct switchdev_trans *trans) { return trans && !trans->ph_prepare; } enum switchdev_attr_id { SWITCHDEV_ATTR_ID_UNDEFINED, SWITCHDEV_ATTR_ID_PORT_PARENT_ID, SWITCHDEV_ATTR_ID_PORT_STP_STATE, SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS, SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT, SWITCHDEV_ATTR_ID_PORT_MROUTER, SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME, SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING, SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED, }; struct switchdev_attr { struct net_device *orig_dev; enum switchdev_attr_id id; u32 flags; void *complete_priv; void (*complete)(struct net_device *dev, int err, void *priv); union { struct netdev_phys_item_id ppid; /* PORT_PARENT_ID */ u8 stp_state; /* PORT_STP_STATE */ unsigned long brport_flags; /* PORT_BRIDGE_FLAGS */ unsigned long brport_flags_support; /* PORT_BRIDGE_FLAGS_SUPPORT */ bool mrouter; /* PORT_MROUTER */ clock_t ageing_time; /* BRIDGE_AGEING_TIME */ bool vlan_filtering; /* BRIDGE_VLAN_FILTERING */ bool mc_disabled; /* MC_DISABLED */ } u; }; enum switchdev_obj_id { SWITCHDEV_OBJ_ID_UNDEFINED, SWITCHDEV_OBJ_ID_PORT_VLAN, SWITCHDEV_OBJ_ID_PORT_MDB, }; struct switchdev_obj { struct net_device *orig_dev; enum switchdev_obj_id id; u32 flags; void *complete_priv; void (*complete)(struct net_device *dev, int err, void *priv); }; /* SWITCHDEV_OBJ_ID_PORT_VLAN */ struct switchdev_obj_port_vlan { struct switchdev_obj obj; u16 flags; u16 vid_begin; u16 vid_end; }; #define SWITCHDEV_OBJ_PORT_VLAN(obj) \ container_of(obj, struct switchdev_obj_port_vlan, obj) /* SWITCHDEV_OBJ_ID_PORT_MDB */ struct switchdev_obj_port_mdb { struct switchdev_obj obj; unsigned char addr[ETH_ALEN]; u16 vid; }; #define SWITCHDEV_OBJ_PORT_MDB(obj) \ container_of(obj, struct switchdev_obj_port_mdb, obj) void switchdev_trans_item_enqueue(struct switchdev_trans *trans, void *data, void (*destructor)(void const *), struct switchdev_trans_item *tritem); void *switchdev_trans_item_dequeue(struct switchdev_trans *trans); typedef int switchdev_obj_dump_cb_t(struct switchdev_obj *obj); /** * struct switchdev_ops - switchdev operations * * @switchdev_port_attr_get: Get a port attribute (see switchdev_attr). * * @switchdev_port_attr_set: Set a port attribute (see switchdev_attr). * * @switchdev_port_obj_add: Add an object to port (see switchdev_obj_*). * * @switchdev_port_obj_del: Delete an object from port (see switchdev_obj_*). */ struct switchdev_ops { int (*switchdev_port_attr_get)(struct net_device *dev, struct switchdev_attr *attr); int (*switchdev_port_attr_set)(struct net_device *dev, const struct switchdev_attr *attr, struct switchdev_trans *trans); int (*switchdev_port_obj_add)(struct net_device *dev, const struct switchdev_obj *obj, struct switchdev_trans *trans); int (*switchdev_port_obj_del)(struct net_device *dev, const struct switchdev_obj *obj); }; enum switchdev_notifier_type { SWITCHDEV_FDB_ADD_TO_BRIDGE = 1, SWITCHDEV_FDB_DEL_TO_BRIDGE, SWITCHDEV_FDB_ADD_TO_DEVICE, SWITCHDEV_FDB_DEL_TO_DEVICE, SWITCHDEV_FDB_OFFLOADED, }; struct switchdev_notifier_info { struct net_device *dev; }; struct switchdev_notifier_fdb_info { struct switchdev_notifier_info info; /* must be first */ const unsigned char *addr; u16 vid; }; static inline struct net_device * switchdev_notifier_info_to_dev(const struct switchdev_notifier_info *info) { return info->dev; } #ifdef CONFIG_NET_SWITCHDEV void switchdev_deferred_process(void); int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr); int switchdev_port_attr_set(struct net_device *dev, const struct switchdev_attr *attr); int switchdev_port_obj_add(struct net_device *dev, const struct switchdev_obj *obj); int switchdev_port_obj_del(struct net_device *dev, const struct switchdev_obj *obj); int register_switchdev_notifier(struct notifier_block *nb); int unregister_switchdev_notifier(struct notifier_block *nb); int call_switchdev_notifiers(unsigned long val, struct net_device *dev, struct switchdev_notifier_info *info); void switchdev_port_fwd_mark_set(struct net_device *dev, struct net_device *group_dev, bool joining); bool switchdev_port_same_parent_id(struct net_device *a, struct net_device *b); #define SWITCHDEV_SET_OPS(netdev, ops) ((netdev)->switchdev_ops = (ops)) #else static inline void switchdev_deferred_process(void) { } static inline int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr) { return -EOPNOTSUPP; } static inline int switchdev_port_attr_set(struct net_device *dev, const struct switchdev_attr *attr) { return -EOPNOTSUPP; } static inline int switchdev_port_obj_add(struct net_device *dev, const struct switchdev_obj *obj) { return -EOPNOTSUPP; } static inline int switchdev_port_obj_del(struct net_device *dev, const struct switchdev_obj *obj) { return -EOPNOTSUPP; } static inline int register_switchdev_notifier(struct notifier_block *nb) { return 0; } static inline int unregister_switchdev_notifier(struct notifier_block *nb) { return 0; } static inline int call_switchdev_notifiers(unsigned long val, struct net_device *dev, struct switchdev_notifier_info *info) { return NOTIFY_DONE; } static inline bool switchdev_port_same_parent_id(struct net_device *a, struct net_device *b) { return false; } #define SWITCHDEV_SET_OPS(netdev, ops) do {} while (0) #endif #endif /* _LINUX_SWITCHDEV_H_ */ |
| 20766 20769 17724 8983 20771 17613 15742 12199 12201 12194 5904 5902 5900 2484 2462 2465 2486 208 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 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 | /* bit search implementation * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * Copyright (C) 2008 IBM Corporation * 'find_last_bit' is written by Rusty Russell <rusty@rustcorp.com.au> * (Inspired by David Howell's find_next_bit implementation) * * Rewritten by Yury Norov <yury.norov@gmail.com> to decrease * size and improve performance, 2015. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ #include <linux/bitops.h> #include <linux/bitmap.h> #include <linux/export.h> #include <linux/kernel.h> #if !defined(find_next_bit) || !defined(find_next_zero_bit) /* * This is a common helper function for find_next_bit and * find_next_zero_bit. The difference is the "invert" argument, which * is XORed with each fetched word before searching it for one bits. */ static unsigned long _find_next_bit(const unsigned long *addr, unsigned long nbits, unsigned long start, unsigned long invert) { unsigned long tmp; if (unlikely(start >= nbits)) return nbits; tmp = addr[start / BITS_PER_LONG] ^ invert; /* Handle 1st word. */ tmp &= BITMAP_FIRST_WORD_MASK(start); start = round_down(start, BITS_PER_LONG); while (!tmp) { start += BITS_PER_LONG; if (start >= nbits) return nbits; tmp = addr[start / BITS_PER_LONG] ^ invert; } return min(start + __ffs(tmp), nbits); } #endif #ifndef find_next_bit /* * Find the next set bit in a memory region. */ unsigned long find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { return _find_next_bit(addr, size, offset, 0UL); } EXPORT_SYMBOL(find_next_bit); #endif #ifndef find_next_zero_bit unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { return _find_next_bit(addr, size, offset, ~0UL); } EXPORT_SYMBOL(find_next_zero_bit); #endif #ifndef find_first_bit /* * Find the first set bit in a memory region. */ unsigned long find_first_bit(const unsigned long *addr, unsigned long size) { unsigned long idx; for (idx = 0; idx * BITS_PER_LONG < size; idx++) { if (addr[idx]) return min(idx * BITS_PER_LONG + __ffs(addr[idx]), size); } return size; } EXPORT_SYMBOL(find_first_bit); #endif #ifndef find_first_zero_bit /* * Find the first cleared bit in a memory region. */ unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) { unsigned long idx; for (idx = 0; idx * BITS_PER_LONG < size; idx++) { if (addr[idx] != ~0UL) return min(idx * BITS_PER_LONG + ffz(addr[idx]), size); } return size; } EXPORT_SYMBOL(find_first_zero_bit); #endif #ifndef find_last_bit unsigned long find_last_bit(const unsigned long *addr, unsigned long size) { if (size) { unsigned long val = BITMAP_LAST_WORD_MASK(size); unsigned long idx = (size-1) / BITS_PER_LONG; do { val &= addr[idx]; if (val) return idx * BITS_PER_LONG + __fls(val); val = ~0ul; } while (idx--); } return size; } EXPORT_SYMBOL(find_last_bit); #endif #ifdef __BIG_ENDIAN #if !defined(find_next_bit_le) || !defined(find_next_zero_bit_le) static unsigned long _find_next_bit_le(const unsigned long *addr, unsigned long nbits, unsigned long start, unsigned long invert) { unsigned long tmp; if (unlikely(start >= nbits)) return nbits; tmp = addr[start / BITS_PER_LONG] ^ invert; /* Handle 1st word. */ tmp &= swab(BITMAP_FIRST_WORD_MASK(start)); start = round_down(start, BITS_PER_LONG); while (!tmp) { start += BITS_PER_LONG; if (start >= nbits) return nbits; tmp = addr[start / BITS_PER_LONG] ^ invert; } return min(start + __ffs(swab(tmp)), nbits); } #endif #ifndef find_next_zero_bit_le unsigned long find_next_zero_bit_le(const void *addr, unsigned long size, unsigned long offset) { return _find_next_bit_le(addr, size, offset, ~0UL); } EXPORT_SYMBOL(find_next_zero_bit_le); #endif #ifndef find_next_bit_le unsigned long find_next_bit_le(const void *addr, unsigned long size, unsigned long offset) { return _find_next_bit_le(addr, size, offset, 0UL); } EXPORT_SYMBOL(find_next_bit_le); #endif #endif /* __BIG_ENDIAN */ |
| 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 | /* * IEEE802.15.4-2003 specification * * Copyright (C) 2007, 2008 Siemens AG * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 * as published by the Free Software Foundation. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * * Written by: * Pavel Smolenskiy <pavel.smolenskiy@gmail.com> * Maxim Gorbachyov <maxim.gorbachev@siemens.com> * Maxim Osipov <maxim.osipov@siemens.com> * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com> * Alexander Smirnov <alex.bluesman.smirnov@gmail.com> */ #ifndef LINUX_IEEE802154_H #define LINUX_IEEE802154_H #include <linux/types.h> #include <linux/random.h> #define IEEE802154_MTU 127 #define IEEE802154_ACK_PSDU_LEN 5 #define IEEE802154_MIN_PSDU_LEN 9 #define IEEE802154_FCS_LEN 2 #define IEEE802154_MAX_AUTH_TAG_LEN 16 #define IEEE802154_FC_LEN 2 #define IEEE802154_SEQ_LEN 1 /* General MAC frame format: * 2 bytes: Frame Control * 1 byte: Sequence Number * 20 bytes: Addressing fields * 14 bytes: Auxiliary Security Header */ #define IEEE802154_MAX_HEADER_LEN (2 + 1 + 20 + 14) #define IEEE802154_MIN_HEADER_LEN (IEEE802154_ACK_PSDU_LEN - \ IEEE802154_FCS_LEN) #define IEEE802154_PAN_ID_BROADCAST 0xffff #define IEEE802154_ADDR_SHORT_BROADCAST 0xffff #define IEEE802154_ADDR_SHORT_UNSPEC 0xfffe #define IEEE802154_EXTENDED_ADDR_LEN 8 #define IEEE802154_SHORT_ADDR_LEN 2 #define IEEE802154_PAN_ID_LEN 2 #define IEEE802154_LIFS_PERIOD 40 #define IEEE802154_SIFS_PERIOD 12 #define IEEE802154_MAX_SIFS_FRAME_SIZE 18 #define IEEE802154_MAX_CHANNEL 26 #define IEEE802154_MAX_PAGE 31 #define IEEE802154_FC_TYPE_BEACON 0x0 /* Frame is beacon */ #define IEEE802154_FC_TYPE_DATA 0x1 /* Frame is data */ #define IEEE802154_FC_TYPE_ACK 0x2 /* Frame is acknowledgment */ #define IEEE802154_FC_TYPE_MAC_CMD 0x3 /* Frame is MAC command */ #define IEEE802154_FC_TYPE_SHIFT 0 #define IEEE802154_FC_TYPE_MASK ((1 << 3) - 1) #define IEEE802154_FC_TYPE(x) ((x & IEEE802154_FC_TYPE_MASK) >> IEEE802154_FC_TYPE_SHIFT) #define IEEE802154_FC_SET_TYPE(v, x) do { \ v = (((v) & ~IEEE802154_FC_TYPE_MASK) | \ (((x) << IEEE802154_FC_TYPE_SHIFT) & IEEE802154_FC_TYPE_MASK)); \ } while (0) #define IEEE802154_FC_SECEN_SHIFT 3 #define IEEE802154_FC_SECEN (1 << IEEE802154_FC_SECEN_SHIFT) #define IEEE802154_FC_FRPEND_SHIFT 4 #define IEEE802154_FC_FRPEND (1 << IEEE802154_FC_FRPEND_SHIFT) #define IEEE802154_FC_ACK_REQ_SHIFT 5 #define IEEE802154_FC_ACK_REQ (1 << IEEE802154_FC_ACK_REQ_SHIFT) #define IEEE802154_FC_INTRA_PAN_SHIFT 6 #define IEEE802154_FC_INTRA_PAN (1 << IEEE802154_FC_INTRA_PAN_SHIFT) #define IEEE802154_FC_SAMODE_SHIFT 14 #define IEEE802154_FC_SAMODE_MASK (3 << IEEE802154_FC_SAMODE_SHIFT) #define IEEE802154_FC_DAMODE_SHIFT 10 #define IEEE802154_FC_DAMODE_MASK (3 << IEEE802154_FC_DAMODE_SHIFT) #define IEEE802154_FC_VERSION_SHIFT 12 #define IEEE802154_FC_VERSION_MASK (3 << IEEE802154_FC_VERSION_SHIFT) #define IEEE802154_FC_VERSION(x) ((x & IEEE802154_FC_VERSION_MASK) >> IEEE802154_FC_VERSION_SHIFT) #define IEEE802154_FC_SAMODE(x) \ (((x) & IEEE802154_FC_SAMODE_MASK) >> IEEE802154_FC_SAMODE_SHIFT) #define IEEE802154_FC_DAMODE(x) \ (((x) & IEEE802154_FC_DAMODE_MASK) >> IEEE802154_FC_DAMODE_SHIFT) #define IEEE802154_SCF_SECLEVEL_MASK 7 #define IEEE802154_SCF_SECLEVEL_SHIFT 0 #define IEEE802154_SCF_SECLEVEL(x) (x & IEEE802154_SCF_SECLEVEL_MASK) #define IEEE802154_SCF_KEY_ID_MODE_SHIFT 3 #define IEEE802154_SCF_KEY_ID_MODE_MASK (3 << IEEE802154_SCF_KEY_ID_MODE_SHIFT) #define IEEE802154_SCF_KEY_ID_MODE(x) \ ((x & IEEE802154_SCF_KEY_ID_MODE_MASK) >> IEEE802154_SCF_KEY_ID_MODE_SHIFT) #define IEEE802154_SCF_KEY_IMPLICIT 0 #define IEEE802154_SCF_KEY_INDEX 1 #define IEEE802154_SCF_KEY_SHORT_INDEX 2 #define IEEE802154_SCF_KEY_HW_INDEX 3 #define IEEE802154_SCF_SECLEVEL_NONE 0 #define IEEE802154_SCF_SECLEVEL_MIC32 1 #define IEEE802154_SCF_SECLEVEL_MIC64 2 #define IEEE802154_SCF_SECLEVEL_MIC128 3 #define IEEE802154_SCF_SECLEVEL_ENC 4 #define IEEE802154_SCF_SECLEVEL_ENC_MIC32 5 #define IEEE802154_SCF_SECLEVEL_ENC_MIC64 6 #define IEEE802154_SCF_SECLEVEL_ENC_MIC128 7 /* MAC footer size */ #define IEEE802154_MFR_SIZE 2 /* 2 octets */ /* MAC's Command Frames Identifiers */ #define IEEE802154_CMD_ASSOCIATION_REQ 0x01 #define IEEE802154_CMD_ASSOCIATION_RESP 0x02 #define IEEE802154_CMD_DISASSOCIATION_NOTIFY 0x03 #define IEEE802154_CMD_DATA_REQ 0x04 #define IEEE802154_CMD_PANID_CONFLICT_NOTIFY 0x05 #define IEEE802154_CMD_ORPHAN_NOTIFY 0x06 #define IEEE802154_CMD_BEACON_REQ 0x07 #define IEEE802154_CMD_COORD_REALIGN_NOTIFY 0x08 #define IEEE802154_CMD_GTS_REQ 0x09 /* * The return values of MAC operations */ enum { /* * The requested operation was completed successfully. * For a transmission request, this value indicates * a successful transmission. */ IEEE802154_SUCCESS = 0x0, /* The beacon was lost following a synchronization request. */ IEEE802154_BEACON_LOSS = 0xe0, /* * A transmission could not take place due to activity on the * channel, i.e., the CSMA-CA mechanism has failed. */ IEEE802154_CHNL_ACCESS_FAIL = 0xe1, /* The GTS request has been denied by the PAN coordinator. */ IEEE802154_DENINED = 0xe2, /* The attempt to disable the transceiver has failed. */ IEEE802154_DISABLE_TRX_FAIL = 0xe3, /* * The received frame induces a failed security check according to * the security suite. */ IEEE802154_FAILED_SECURITY_CHECK = 0xe4, /* * The frame resulting from secure processing has a length that is * greater than aMACMaxFrameSize. */ IEEE802154_FRAME_TOO_LONG = 0xe5, /* * The requested GTS transmission failed because the specified GTS * either did not have a transmit GTS direction or was not defined. */ IEEE802154_INVALID_GTS = 0xe6, /* * A request to purge an MSDU from the transaction queue was made using * an MSDU handle that was not found in the transaction table. */ IEEE802154_INVALID_HANDLE = 0xe7, /* A parameter in the primitive is out of the valid range.*/ IEEE802154_INVALID_PARAMETER = 0xe8, /* No acknowledgment was received after aMaxFrameRetries. */ IEEE802154_NO_ACK = 0xe9, /* A scan operation failed to find any network beacons.*/ IEEE802154_NO_BEACON = 0xea, /* No response data were available following a request. */ IEEE802154_NO_DATA = 0xeb, /* The operation failed because a short address was not allocated. */ IEEE802154_NO_SHORT_ADDRESS = 0xec, /* * A receiver enable request was unsuccessful because it could not be * completed within the CAP. */ IEEE802154_OUT_OF_CAP = 0xed, /* * A PAN identifier conflict has been detected and communicated to the * PAN coordinator. */ IEEE802154_PANID_CONFLICT = 0xee, /* A coordinator realignment command has been received. */ IEEE802154_REALIGMENT = 0xef, /* The transaction has expired and its information discarded. */ IEEE802154_TRANSACTION_EXPIRED = 0xf0, /* There is no capacity to store the transaction. */ IEEE802154_TRANSACTION_OVERFLOW = 0xf1, /* * The transceiver was in the transmitter enabled state when the * receiver was requested to be enabled. */ IEEE802154_TX_ACTIVE = 0xf2, /* The appropriate key is not available in the ACL. */ IEEE802154_UNAVAILABLE_KEY = 0xf3, /* * A SET/GET request was issued with the identifier of a PIB attribute * that is not supported. */ IEEE802154_UNSUPPORTED_ATTR = 0xf4, /* * A request to perform a scan operation failed because the MLME was * in the process of performing a previously initiated scan operation. */ IEEE802154_SCAN_IN_PROGRESS = 0xfc, }; /* frame control handling */ #define IEEE802154_FCTL_FTYPE 0x0003 #define IEEE802154_FCTL_ACKREQ 0x0020 #define IEEE802154_FCTL_SECEN 0x0004 #define IEEE802154_FCTL_INTRA_PAN 0x0040 #define IEEE802154_FCTL_DADDR 0x0c00 #define IEEE802154_FCTL_SADDR 0xc000 #define IEEE802154_FTYPE_DATA 0x0001 #define IEEE802154_FCTL_ADDR_NONE 0x0000 #define IEEE802154_FCTL_DADDR_SHORT 0x0800 #define IEEE802154_FCTL_DADDR_EXTENDED 0x0c00 #define IEEE802154_FCTL_SADDR_SHORT 0x8000 #define IEEE802154_FCTL_SADDR_EXTENDED 0xc000 /* * ieee802154_is_data - check if type is IEEE802154_FTYPE_DATA * @fc: frame control bytes in little-endian byteorder */ static inline int ieee802154_is_data(__le16 fc) { return (fc & cpu_to_le16(IEEE802154_FCTL_FTYPE)) == cpu_to_le16(IEEE802154_FTYPE_DATA); } /** * ieee802154_is_secen - check if Security bit is set * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee802154_is_secen(__le16 fc) { return fc & cpu_to_le16(IEEE802154_FCTL_SECEN); } /** * ieee802154_is_ackreq - check if acknowledgment request bit is set * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee802154_is_ackreq(__le16 fc) { return fc & cpu_to_le16(IEEE802154_FCTL_ACKREQ); } /** * ieee802154_is_intra_pan - check if intra pan id communication * @fc: frame control bytes in little-endian byteorder */ static inline bool ieee802154_is_intra_pan(__le16 fc) { return fc & cpu_to_le16(IEEE802154_FCTL_INTRA_PAN); } /* * ieee802154_daddr_mode - get daddr mode from fc * @fc: frame control bytes in little-endian byteorder */ static inline __le16 ieee802154_daddr_mode(__le16 fc) { return fc & cpu_to_le16(IEEE802154_FCTL_DADDR); } /* * ieee802154_saddr_mode - get saddr mode from fc * @fc: frame control bytes in little-endian byteorder */ static inline __le16 ieee802154_saddr_mode(__le16 fc) { return fc & cpu_to_le16(IEEE802154_FCTL_SADDR); } /** * ieee802154_is_valid_psdu_len - check if psdu len is valid * available lengths: * 0-4 Reserved * 5 MPDU (Acknowledgment) * 6-8 Reserved * 9-127 MPDU * * @len: psdu len with (MHR + payload + MFR) */ static inline bool ieee802154_is_valid_psdu_len(u8 len) { return (len == IEEE802154_ACK_PSDU_LEN || (len >= IEEE802154_MIN_PSDU_LEN && len <= IEEE802154_MTU)); } /** * ieee802154_is_valid_extended_unicast_addr - check if extended addr is valid * @addr: extended addr to check */ static inline bool ieee802154_is_valid_extended_unicast_addr(__le64 addr) { /* Bail out if the address is all zero, or if the group * address bit is set. */ return ((addr != cpu_to_le64(0x0000000000000000ULL)) && !(addr & cpu_to_le64(0x0100000000000000ULL))); } /** * ieee802154_is_broadcast_short_addr - check if short addr is broadcast * @addr: short addr to check */ static inline bool ieee802154_is_broadcast_short_addr(__le16 addr) { return (addr == cpu_to_le16(IEEE802154_ADDR_SHORT_BROADCAST)); } /** * ieee802154_is_unspec_short_addr - check if short addr is unspecified * @addr: short addr to check */ static inline bool ieee802154_is_unspec_short_addr(__le16 addr) { return (addr == cpu_to_le16(IEEE802154_ADDR_SHORT_UNSPEC)); } /** * ieee802154_is_valid_src_short_addr - check if source short address is valid * @addr: short addr to check */ static inline bool ieee802154_is_valid_src_short_addr(__le16 addr) { return !(ieee802154_is_broadcast_short_addr(addr) || ieee802154_is_unspec_short_addr(addr)); } /** * ieee802154_random_extended_addr - generates a random extended address * @addr: extended addr pointer to place the random address */ static inline void ieee802154_random_extended_addr(__le64 *addr) { get_random_bytes(addr, IEEE802154_EXTENDED_ADDR_LEN); /* clear the group bit, and set the locally administered bit */ ((u8 *)addr)[IEEE802154_EXTENDED_ADDR_LEN - 1] &= ~0x01; ((u8 *)addr)[IEEE802154_EXTENDED_ADDR_LEN - 1] |= 0x02; } #endif /* LINUX_IEEE802154_H */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * befs.h * * Copyright (C) 2001-2002 Will Dyson <will_dyson@pobox.com> * Copyright (C) 1999 Makoto Kato (m_kato@ga2.so-net.ne.jp) */ #ifndef _LINUX_BEFS_H #define _LINUX_BEFS_H #include "befs_fs_types.h" /* used in debug.c */ #define BEFS_VERSION "0.9.3" typedef u64 befs_blocknr_t; /* * BeFS in memory structures */ struct befs_mount_options { kgid_t gid; kuid_t uid; int use_gid; int use_uid; int debug; char *iocharset; }; struct befs_sb_info { u32 magic1; u32 block_size; u32 block_shift; int byte_order; befs_off_t num_blocks; befs_off_t used_blocks; u32 inode_size; u32 magic2; /* Allocation group information */ u32 blocks_per_ag; u32 ag_shift; u32 num_ags; /* State of the superblock */ u32 flags; /* Journal log entry */ befs_block_run log_blocks; befs_off_t log_start; befs_off_t log_end; befs_inode_addr root_dir; befs_inode_addr indices; u32 magic3; struct befs_mount_options mount_opts; struct nls_table *nls; }; struct befs_inode_info { u32 i_flags; u32 i_type; befs_inode_addr i_inode_num; befs_inode_addr i_parent; befs_inode_addr i_attribute; union { befs_data_stream ds; char symlink[BEFS_SYMLINK_LEN]; } i_data; struct inode vfs_inode; }; enum befs_err { BEFS_OK, BEFS_ERR, BEFS_BAD_INODE, BEFS_BT_END, BEFS_BT_EMPTY, BEFS_BT_MATCH, BEFS_BT_OVERFLOW, BEFS_BT_NOT_FOUND }; /****************************/ /* debug.c */ __printf(2, 3) void befs_error(const struct super_block *sb, const char *fmt, ...); __printf(2, 3) void befs_warning(const struct super_block *sb, const char *fmt, ...); __printf(2, 3) void befs_debug(const struct super_block *sb, const char *fmt, ...); void befs_dump_super_block(const struct super_block *sb, befs_super_block *); void befs_dump_inode(const struct super_block *sb, befs_inode *); void befs_dump_index_entry(const struct super_block *sb, befs_disk_btree_super *); void befs_dump_index_node(const struct super_block *sb, befs_btree_nodehead *); /****************************/ /* Gets a pointer to the private portion of the super_block * structure from the public part */ static inline struct befs_sb_info * BEFS_SB(const struct super_block *super) { return (struct befs_sb_info *) super->s_fs_info; } static inline struct befs_inode_info * BEFS_I(const struct inode *inode) { return container_of(inode, struct befs_inode_info, vfs_inode); } static inline befs_blocknr_t iaddr2blockno(struct super_block *sb, const befs_inode_addr *iaddr) { return ((iaddr->allocation_group << BEFS_SB(sb)->ag_shift) + iaddr->start); } static inline befs_inode_addr blockno2iaddr(struct super_block *sb, befs_blocknr_t blockno) { befs_inode_addr iaddr; iaddr.allocation_group = blockno >> BEFS_SB(sb)->ag_shift; iaddr.start = blockno - (iaddr.allocation_group << BEFS_SB(sb)->ag_shift); iaddr.len = 1; return iaddr; } static inline unsigned int befs_iaddrs_per_block(struct super_block *sb) { return BEFS_SB(sb)->block_size / sizeof(befs_disk_inode_addr); } #include "endian.h" #endif /* _LINUX_BEFS_H */ |
| 60 58 58 2 87 24 68 81 81 81 48 48 48 40 48 5 5 5 5 5 5 5 5 5 5 35 35 35 35 35 35 35 35 8 5 5 5 5 5 5 5 8 7 7 7 6 6 8 7 6 8 1 7 7 7 7 7 29 29 29 22 25 53 52 25 25 25 52 43 35 35 43 7 7 7 7 7 7 2 7 2 1 1 1 1 1 1 2 1 1 1 1 6 3 2 3 1 3 5 2 1 2 2 1 1 1 1 1 1 1 2 2 2 2 10 5 25 7 15 5 4 4 37 14 21 6 8 6 15 15 61 63 63 15 63 217 88 87 34 79 1 1 1 1 1 2 5 43 4 2 2 1 1 4 2 1 1 1 1 1 9 6 6 6 6 6 6 5 4 4 1 4 3 3 6 6 58 58 209 209 79 12 6 18 18 18 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 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 | /* * Bridge multicast support. * * Copyright (c) 2010 Herbert Xu <herbert@gondor.apana.org.au> * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the Free * Software Foundation; either version 2 of the License, or (at your option) * any later version. * */ #include <linux/err.h> #include <linux/export.h> #include <linux/if_ether.h> #include <linux/igmp.h> #include <linux/jhash.h> #include <linux/kernel.h> #include <linux/log2.h> #include <linux/netdevice.h> #include <linux/netfilter_bridge.h> #include <linux/random.h> #include <linux/rculist.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/timer.h> #include <linux/inetdevice.h> #include <linux/mroute.h> #include <net/ip.h> #include <net/switchdev.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> #include <net/mld.h> #include <net/ip6_checksum.h> #include <net/addrconf.h> #endif #include "br_private.h" static void br_multicast_start_querier(struct net_bridge *br, struct bridge_mcast_own_query *query); static void br_multicast_add_router(struct net_bridge *br, struct net_bridge_port *port); static void br_ip4_multicast_leave_group(struct net_bridge *br, struct net_bridge_port *port, __be32 group, __u16 vid, const unsigned char *src); static void __del_port_router(struct net_bridge_port *p); #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_leave_group(struct net_bridge *br, struct net_bridge_port *port, const struct in6_addr *group, __u16 vid, const unsigned char *src); #endif unsigned int br_mdb_rehash_seq; static inline int br_ip_equal(const struct br_ip *a, const struct br_ip *b) { if (a->proto != b->proto) return 0; if (a->vid != b->vid) return 0; switch (a->proto) { case htons(ETH_P_IP): return a->u.ip4 == b->u.ip4; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): return ipv6_addr_equal(&a->u.ip6, &b->u.ip6); #endif } return 0; } static inline int __br_ip4_hash(struct net_bridge_mdb_htable *mdb, __be32 ip, __u16 vid) { return jhash_2words((__force u32)ip, vid, mdb->secret) & (mdb->max - 1); } #if IS_ENABLED(CONFIG_IPV6) static inline int __br_ip6_hash(struct net_bridge_mdb_htable *mdb, const struct in6_addr *ip, __u16 vid) { return jhash_2words(ipv6_addr_hash(ip), vid, mdb->secret) & (mdb->max - 1); } #endif static inline int br_ip_hash(struct net_bridge_mdb_htable *mdb, struct br_ip *ip) { switch (ip->proto) { case htons(ETH_P_IP): return __br_ip4_hash(mdb, ip->u.ip4, ip->vid); #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): return __br_ip6_hash(mdb, &ip->u.ip6, ip->vid); #endif } return 0; } static struct net_bridge_mdb_entry *__br_mdb_ip_get( struct net_bridge_mdb_htable *mdb, struct br_ip *dst, int hash) { struct net_bridge_mdb_entry *mp; hlist_for_each_entry_rcu(mp, &mdb->mhash[hash], hlist[mdb->ver]) { if (br_ip_equal(&mp->addr, dst)) return mp; } return NULL; } struct net_bridge_mdb_entry *br_mdb_ip_get(struct net_bridge_mdb_htable *mdb, struct br_ip *dst) { if (!mdb) return NULL; return __br_mdb_ip_get(mdb, dst, br_ip_hash(mdb, dst)); } static struct net_bridge_mdb_entry *br_mdb_ip4_get( struct net_bridge_mdb_htable *mdb, __be32 dst, __u16 vid) { struct br_ip br_dst; br_dst.u.ip4 = dst; br_dst.proto = htons(ETH_P_IP); br_dst.vid = vid; return br_mdb_ip_get(mdb, &br_dst); } #if IS_ENABLED(CONFIG_IPV6) static struct net_bridge_mdb_entry *br_mdb_ip6_get( struct net_bridge_mdb_htable *mdb, const struct in6_addr *dst, __u16 vid) { struct br_ip br_dst; br_dst.u.ip6 = *dst; br_dst.proto = htons(ETH_P_IPV6); br_dst.vid = vid; return br_mdb_ip_get(mdb, &br_dst); } #endif struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br, struct sk_buff *skb, u16 vid) { struct net_bridge_mdb_htable *mdb = rcu_dereference(br->mdb); struct br_ip ip; if (br->multicast_disabled) return NULL; if (BR_INPUT_SKB_CB(skb)->igmp) return NULL; ip.proto = skb->protocol; ip.vid = vid; switch (skb->protocol) { case htons(ETH_P_IP): ip.u.ip4 = ip_hdr(skb)->daddr; break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): ip.u.ip6 = ipv6_hdr(skb)->daddr; break; #endif default: return NULL; } return br_mdb_ip_get(mdb, &ip); } static void br_mdb_free(struct rcu_head *head) { struct net_bridge_mdb_htable *mdb = container_of(head, struct net_bridge_mdb_htable, rcu); struct net_bridge_mdb_htable *old = mdb->old; mdb->old = NULL; kfree(old->mhash); kfree(old); } static int br_mdb_copy(struct net_bridge_mdb_htable *new, struct net_bridge_mdb_htable *old, int elasticity) { struct net_bridge_mdb_entry *mp; int maxlen; int len; int i; for (i = 0; i < old->max; i++) hlist_for_each_entry(mp, &old->mhash[i], hlist[old->ver]) hlist_add_head(&mp->hlist[new->ver], &new->mhash[br_ip_hash(new, &mp->addr)]); if (!elasticity) return 0; maxlen = 0; for (i = 0; i < new->max; i++) { len = 0; hlist_for_each_entry(mp, &new->mhash[i], hlist[new->ver]) len++; if (len > maxlen) maxlen = len; } return maxlen > elasticity ? -EINVAL : 0; } void br_multicast_free_pg(struct rcu_head *head) { struct net_bridge_port_group *p = container_of(head, struct net_bridge_port_group, rcu); kfree(p); } static void br_multicast_free_group(struct rcu_head *head) { struct net_bridge_mdb_entry *mp = container_of(head, struct net_bridge_mdb_entry, rcu); kfree(mp); } static void br_multicast_group_expired(unsigned long data) { struct net_bridge_mdb_entry *mp = (void *)data; struct net_bridge *br = mp->br; struct net_bridge_mdb_htable *mdb; spin_lock(&br->multicast_lock); if (!netif_running(br->dev) || timer_pending(&mp->timer)) goto out; mp->mglist = false; if (mp->ports) goto out; mdb = mlock_dereference(br->mdb, br); hlist_del_rcu(&mp->hlist[mdb->ver]); mdb->size--; call_rcu_bh(&mp->rcu, br_multicast_free_group); out: spin_unlock(&br->multicast_lock); } static void br_multicast_del_pg(struct net_bridge *br, struct net_bridge_port_group *pg) { struct net_bridge_mdb_htable *mdb; struct net_bridge_mdb_entry *mp; struct net_bridge_port_group *p; struct net_bridge_port_group __rcu **pp; mdb = mlock_dereference(br->mdb, br); mp = br_mdb_ip_get(mdb, &pg->addr); if (WARN_ON(!mp)) return; for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL; pp = &p->next) { if (p != pg) continue; rcu_assign_pointer(*pp, p->next); hlist_del_init(&p->mglist); del_timer(&p->timer); br_mdb_notify(br->dev, p->port, &pg->addr, RTM_DELMDB, p->flags); call_rcu_bh(&p->rcu, br_multicast_free_pg); if (!mp->ports && !mp->mglist && netif_running(br->dev)) mod_timer(&mp->timer, jiffies); return; } WARN_ON(1); } static void br_multicast_port_group_expired(unsigned long data) { struct net_bridge_port_group *pg = (void *)data; struct net_bridge *br = pg->port->br; spin_lock(&br->multicast_lock); if (!netif_running(br->dev) || timer_pending(&pg->timer) || hlist_unhashed(&pg->mglist) || pg->flags & MDB_PG_FLAGS_PERMANENT) goto out; br_multicast_del_pg(br, pg); out: spin_unlock(&br->multicast_lock); } static int br_mdb_rehash(struct net_bridge_mdb_htable __rcu **mdbp, int max, int elasticity) { struct net_bridge_mdb_htable *old = rcu_dereference_protected(*mdbp, 1); struct net_bridge_mdb_htable *mdb; int err; mdb = kmalloc(sizeof(*mdb), GFP_ATOMIC); if (!mdb) return -ENOMEM; mdb->max = max; mdb->old = old; mdb->mhash = kzalloc(max * sizeof(*mdb->mhash), GFP_ATOMIC); if (!mdb->mhash) { kfree(mdb); return -ENOMEM; } mdb->size = old ? old->size : 0; mdb->ver = old ? old->ver ^ 1 : 0; if (!old || elasticity) get_random_bytes(&mdb->secret, sizeof(mdb->secret)); else mdb->secret = old->secret; if (!old) goto out; err = br_mdb_copy(mdb, old, elasticity); if (err) { kfree(mdb->mhash); kfree(mdb); return err; } br_mdb_rehash_seq++; call_rcu_bh(&mdb->rcu, br_mdb_free); out: rcu_assign_pointer(*mdbp, mdb); return 0; } static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br, __be32 group, u8 *igmp_type) { struct igmpv3_query *ihv3; size_t igmp_hdr_size; struct sk_buff *skb; struct igmphdr *ih; struct ethhdr *eth; struct iphdr *iph; igmp_hdr_size = sizeof(*ih); if (br->multicast_igmp_version == 3) igmp_hdr_size = sizeof(*ihv3); skb = netdev_alloc_skb_ip_align(br->dev, sizeof(*eth) + sizeof(*iph) + igmp_hdr_size + 4); if (!skb) goto out; skb->protocol = htons(ETH_P_IP); skb_reset_mac_header(skb); eth = eth_hdr(skb); ether_addr_copy(eth->h_source, br->dev->dev_addr); eth->h_dest[0] = 1; eth->h_dest[1] = 0; eth->h_dest[2] = 0x5e; eth->h_dest[3] = 0; eth->h_dest[4] = 0; eth->h_dest[5] = 1; eth->h_proto = htons(ETH_P_IP); skb_put(skb, sizeof(*eth)); skb_set_network_header(skb, skb->len); iph = ip_hdr(skb); iph->version = 4; iph->ihl = 6; iph->tos = 0xc0; iph->tot_len = htons(sizeof(*iph) + igmp_hdr_size + 4); iph->id = 0; iph->frag_off = htons(IP_DF); iph->ttl = 1; iph->protocol = IPPROTO_IGMP; iph->saddr = br->multicast_query_use_ifaddr ? inet_select_addr(br->dev, 0, RT_SCOPE_LINK) : 0; iph->daddr = htonl(INADDR_ALLHOSTS_GROUP); ((u8 *)&iph[1])[0] = IPOPT_RA; ((u8 *)&iph[1])[1] = 4; ((u8 *)&iph[1])[2] = 0; ((u8 *)&iph[1])[3] = 0; ip_send_check(iph); skb_put(skb, 24); skb_set_transport_header(skb, skb->len); *igmp_type = IGMP_HOST_MEMBERSHIP_QUERY; switch (br->multicast_igmp_version) { case 2: ih = igmp_hdr(skb); ih->type = IGMP_HOST_MEMBERSHIP_QUERY; ih->code = (group ? br->multicast_last_member_interval : br->multicast_query_response_interval) / (HZ / IGMP_TIMER_SCALE); ih->group = group; ih->csum = 0; ih->csum = ip_compute_csum((void *)ih, sizeof(*ih)); break; case 3: ihv3 = igmpv3_query_hdr(skb); ihv3->type = IGMP_HOST_MEMBERSHIP_QUERY; ihv3->code = (group ? br->multicast_last_member_interval : br->multicast_query_response_interval) / (HZ / IGMP_TIMER_SCALE); ihv3->group = group; ihv3->qqic = br->multicast_query_interval / HZ; ihv3->nsrcs = 0; ihv3->resv = 0; ihv3->suppress = 0; ihv3->qrv = 2; ihv3->csum = 0; ihv3->csum = ip_compute_csum((void *)ihv3, sizeof(*ihv3)); break; } skb_put(skb, igmp_hdr_size); __skb_pull(skb, sizeof(*eth)); out: return skb; } #if IS_ENABLED(CONFIG_IPV6) static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br, const struct in6_addr *grp, u8 *igmp_type) { struct mld2_query *mld2q; unsigned long interval; struct ipv6hdr *ip6h; struct mld_msg *mldq; size_t mld_hdr_size; struct sk_buff *skb; struct ethhdr *eth; u8 *hopopt; mld_hdr_size = sizeof(*mldq); if (br->multicast_mld_version == 2) mld_hdr_size = sizeof(*mld2q); skb = netdev_alloc_skb_ip_align(br->dev, sizeof(*eth) + sizeof(*ip6h) + 8 + mld_hdr_size); if (!skb) goto out; skb->protocol = htons(ETH_P_IPV6); /* Ethernet header */ skb_reset_mac_header(skb); eth = eth_hdr(skb); ether_addr_copy(eth->h_source, br->dev->dev_addr); eth->h_proto = htons(ETH_P_IPV6); skb_put(skb, sizeof(*eth)); /* IPv6 header + HbH option */ skb_set_network_header(skb, skb->len); ip6h = ipv6_hdr(skb); *(__force __be32 *)ip6h = htonl(0x60000000); ip6h->payload_len = htons(8 + mld_hdr_size); ip6h->nexthdr = IPPROTO_HOPOPTS; ip6h->hop_limit = 1; ipv6_addr_set(&ip6h->daddr, htonl(0xff020000), 0, 0, htonl(1)); if (ipv6_dev_get_saddr(dev_net(br->dev), br->dev, &ip6h->daddr, 0, &ip6h->saddr)) { kfree_skb(skb); br->has_ipv6_addr = 0; return NULL; } br->has_ipv6_addr = 1; ipv6_eth_mc_map(&ip6h->daddr, eth->h_dest); hopopt = (u8 *)(ip6h + 1); hopopt[0] = IPPROTO_ICMPV6; /* next hdr */ hopopt[1] = 0; /* length of HbH */ hopopt[2] = IPV6_TLV_ROUTERALERT; /* Router Alert */ hopopt[3] = 2; /* Length of RA Option */ hopopt[4] = 0; /* Type = 0x0000 (MLD) */ hopopt[5] = 0; hopopt[6] = IPV6_TLV_PAD1; /* Pad1 */ hopopt[7] = IPV6_TLV_PAD1; /* Pad1 */ skb_put(skb, sizeof(*ip6h) + 8); /* ICMPv6 */ skb_set_transport_header(skb, skb->len); interval = ipv6_addr_any(grp) ? br->multicast_query_response_interval : br->multicast_last_member_interval; *igmp_type = ICMPV6_MGM_QUERY; switch (br->multicast_mld_version) { case 1: mldq = (struct mld_msg *)icmp6_hdr(skb); mldq->mld_type = ICMPV6_MGM_QUERY; mldq->mld_code = 0; mldq->mld_cksum = 0; mldq->mld_maxdelay = htons((u16)jiffies_to_msecs(interval)); mldq->mld_reserved = 0; mldq->mld_mca = *grp; mldq->mld_cksum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, sizeof(*mldq), IPPROTO_ICMPV6, csum_partial(mldq, sizeof(*mldq), 0)); break; case 2: mld2q = (struct mld2_query *)icmp6_hdr(skb); mld2q->mld2q_mrc = htons((u16)jiffies_to_msecs(interval)); mld2q->mld2q_type = ICMPV6_MGM_QUERY; mld2q->mld2q_code = 0; mld2q->mld2q_cksum = 0; mld2q->mld2q_resv1 = 0; mld2q->mld2q_resv2 = 0; mld2q->mld2q_suppress = 0; mld2q->mld2q_qrv = 2; mld2q->mld2q_nsrcs = 0; mld2q->mld2q_qqic = br->multicast_query_interval / HZ; mld2q->mld2q_mca = *grp; mld2q->mld2q_cksum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, sizeof(*mld2q), IPPROTO_ICMPV6, csum_partial(mld2q, sizeof(*mld2q), 0)); break; } skb_put(skb, mld_hdr_size); __skb_pull(skb, sizeof(*eth)); out: return skb; } #endif static struct sk_buff *br_multicast_alloc_query(struct net_bridge *br, struct br_ip *addr, u8 *igmp_type) { switch (addr->proto) { case htons(ETH_P_IP): return br_ip4_multicast_alloc_query(br, addr->u.ip4, igmp_type); #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): return br_ip6_multicast_alloc_query(br, &addr->u.ip6, igmp_type); #endif } return NULL; } static struct net_bridge_mdb_entry *br_multicast_get_group( struct net_bridge *br, struct net_bridge_port *port, struct br_ip *group, int hash) { struct net_bridge_mdb_htable *mdb; struct net_bridge_mdb_entry *mp; unsigned int count = 0; unsigned int max; int elasticity; int err; mdb = rcu_dereference_protected(br->mdb, 1); hlist_for_each_entry(mp, &mdb->mhash[hash], hlist[mdb->ver]) { count++; if (unlikely(br_ip_equal(group, &mp->addr))) return mp; } elasticity = 0; max = mdb->max; if (unlikely(count > br->hash_elasticity && count)) { if (net_ratelimit()) br_info(br, "Multicast hash table " "chain limit reached: %s\n", port ? port->dev->name : br->dev->name); elasticity = br->hash_elasticity; } if (mdb->size >= max) { max *= 2; if (unlikely(max > br->hash_max)) { br_warn(br, "Multicast hash table maximum of %d " "reached, disabling snooping: %s\n", br->hash_max, port ? port->dev->name : br->dev->name); err = -E2BIG; disable: br->multicast_disabled = 1; goto err; } } if (max > mdb->max || elasticity) { if (mdb->old) { if (net_ratelimit()) br_info(br, "Multicast hash table " "on fire: %s\n", port ? port->dev->name : br->dev->name); err = -EEXIST; goto err; } err = br_mdb_rehash(&br->mdb, max, elasticity); if (err) { br_warn(br, "Cannot rehash multicast " "hash table, disabling snooping: %s, %d, %d\n", port ? port->dev->name : br->dev->name, mdb->size, err); goto disable; } err = -EAGAIN; goto err; } return NULL; err: mp = ERR_PTR(err); return mp; } struct net_bridge_mdb_entry *br_multicast_new_group(struct net_bridge *br, struct net_bridge_port *p, struct br_ip *group) { struct net_bridge_mdb_htable *mdb; struct net_bridge_mdb_entry *mp; int hash; int err; mdb = rcu_dereference_protected(br->mdb, 1); if (!mdb) { err = br_mdb_rehash(&br->mdb, BR_HASH_SIZE, 0); if (err) return ERR_PTR(err); goto rehash; } hash = br_ip_hash(mdb, group); mp = br_multicast_get_group(br, p, group, hash); switch (PTR_ERR(mp)) { case 0: break; case -EAGAIN: rehash: mdb = rcu_dereference_protected(br->mdb, 1); hash = br_ip_hash(mdb, group); break; default: goto out; } mp = kzalloc(sizeof(*mp), GFP_ATOMIC); if (unlikely(!mp)) return ERR_PTR(-ENOMEM); mp->br = br; mp->addr = *group; setup_timer(&mp->timer, br_multicast_group_expired, (unsigned long)mp); hlist_add_head_rcu(&mp->hlist[mdb->ver], &mdb->mhash[hash]); mdb->size++; out: return mp; } struct net_bridge_port_group *br_multicast_new_port_group( struct net_bridge_port *port, struct br_ip *group, struct net_bridge_port_group __rcu *next, unsigned char flags, const unsigned char *src) { struct net_bridge_port_group *p; p = kzalloc(sizeof(*p), GFP_ATOMIC); if (unlikely(!p)) return NULL; p->addr = *group; p->port = port; p->flags = flags; rcu_assign_pointer(p->next, next); hlist_add_head(&p->mglist, &port->mglist); setup_timer(&p->timer, br_multicast_port_group_expired, (unsigned long)p); if (src) memcpy(p->eth_addr, src, ETH_ALEN); else memset(p->eth_addr, 0xff, ETH_ALEN); return p; } static bool br_port_group_equal(struct net_bridge_port_group *p, struct net_bridge_port *port, const unsigned char *src) { if (p->port != port) return false; if (!(port->flags & BR_MULTICAST_TO_UNICAST)) return true; return ether_addr_equal(src, p->eth_addr); } static int br_multicast_add_group(struct net_bridge *br, struct net_bridge_port *port, struct br_ip *group, const unsigned char *src) { struct net_bridge_port_group __rcu **pp; struct net_bridge_port_group *p; struct net_bridge_mdb_entry *mp; unsigned long now = jiffies; int err; spin_lock(&br->multicast_lock); if (!netif_running(br->dev) || (port && port->state == BR_STATE_DISABLED)) goto out; mp = br_multicast_new_group(br, port, group); err = PTR_ERR(mp); if (IS_ERR(mp)) goto err; if (!port) { mp->mglist = true; mod_timer(&mp->timer, now + br->multicast_membership_interval); goto out; } for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL; pp = &p->next) { if (br_port_group_equal(p, port, src)) goto found; if ((unsigned long)p->port < (unsigned long)port) break; } p = br_multicast_new_port_group(port, group, *pp, 0, src); if (unlikely(!p)) goto err; rcu_assign_pointer(*pp, p); br_mdb_notify(br->dev, port, group, RTM_NEWMDB, 0); found: mod_timer(&p->timer, now + br->multicast_membership_interval); out: err = 0; err: spin_unlock(&br->multicast_lock); return err; } static int br_ip4_multicast_add_group(struct net_bridge *br, struct net_bridge_port *port, __be32 group, __u16 vid, const unsigned char *src) { struct br_ip br_group; if (ipv4_is_local_multicast(group)) return 0; br_group.u.ip4 = group; br_group.proto = htons(ETH_P_IP); br_group.vid = vid; return br_multicast_add_group(br, port, &br_group, src); } #if IS_ENABLED(CONFIG_IPV6) static int br_ip6_multicast_add_group(struct net_bridge *br, struct net_bridge_port *port, const struct in6_addr *group, __u16 vid, const unsigned char *src) { struct br_ip br_group; if (ipv6_addr_is_ll_all_nodes(group)) return 0; br_group.u.ip6 = *group; br_group.proto = htons(ETH_P_IPV6); br_group.vid = vid; return br_multicast_add_group(br, port, &br_group, src); } #endif static void br_multicast_router_expired(unsigned long data) { struct net_bridge_port *port = (void *)data; struct net_bridge *br = port->br; spin_lock(&br->multicast_lock); if (port->multicast_router == MDB_RTR_TYPE_DISABLED || port->multicast_router == MDB_RTR_TYPE_PERM || timer_pending(&port->multicast_router_timer)) goto out; __del_port_router(port); out: spin_unlock(&br->multicast_lock); } static void br_multicast_local_router_expired(unsigned long data) { } static void br_multicast_querier_expired(struct net_bridge *br, struct bridge_mcast_own_query *query) { spin_lock(&br->multicast_lock); if (!netif_running(br->dev) || br->multicast_disabled) goto out; br_multicast_start_querier(br, query); out: spin_unlock(&br->multicast_lock); } static void br_ip4_multicast_querier_expired(unsigned long data) { struct net_bridge *br = (void *)data; br_multicast_querier_expired(br, &br->ip4_own_query); } #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_querier_expired(unsigned long data) { struct net_bridge *br = (void *)data; br_multicast_querier_expired(br, &br->ip6_own_query); } #endif static void br_multicast_select_own_querier(struct net_bridge *br, struct br_ip *ip, struct sk_buff *skb) { if (ip->proto == htons(ETH_P_IP)) br->ip4_querier.addr.u.ip4 = ip_hdr(skb)->saddr; #if IS_ENABLED(CONFIG_IPV6) else br->ip6_querier.addr.u.ip6 = ipv6_hdr(skb)->saddr; #endif } static void __br_multicast_send_query(struct net_bridge *br, struct net_bridge_port *port, struct br_ip *ip) { struct sk_buff *skb; u8 igmp_type; skb = br_multicast_alloc_query(br, ip, &igmp_type); if (!skb) return; if (port) { skb->dev = port->dev; br_multicast_count(br, port, skb, igmp_type, BR_MCAST_DIR_TX); NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, dev_net(port->dev), NULL, skb, NULL, skb->dev, br_dev_queue_push_xmit); } else { br_multicast_select_own_querier(br, ip, skb); br_multicast_count(br, port, skb, igmp_type, BR_MCAST_DIR_RX); netif_rx(skb); } } static void br_multicast_send_query(struct net_bridge *br, struct net_bridge_port *port, struct bridge_mcast_own_query *own_query) { struct bridge_mcast_other_query *other_query = NULL; struct br_ip br_group; unsigned long time; if (!netif_running(br->dev) || br->multicast_disabled || !br->multicast_querier) return; memset(&br_group.u, 0, sizeof(br_group.u)); if (port ? (own_query == &port->ip4_own_query) : (own_query == &br->ip4_own_query)) { other_query = &br->ip4_other_query; br_group.proto = htons(ETH_P_IP); #if IS_ENABLED(CONFIG_IPV6) } else { other_query = &br->ip6_other_query; br_group.proto = htons(ETH_P_IPV6); #endif } if (!other_query || timer_pending(&other_query->timer)) return; __br_multicast_send_query(br, port, &br_group); time = jiffies; time += own_query->startup_sent < br->multicast_startup_query_count ? br->multicast_startup_query_interval : br->multicast_query_interval; mod_timer(&own_query->timer, time); } static void br_multicast_port_query_expired(struct net_bridge_port *port, struct bridge_mcast_own_query *query) { struct net_bridge *br = port->br; spin_lock(&br->multicast_lock); if (port->state == BR_STATE_DISABLED || port->state == BR_STATE_BLOCKING) goto out; if (query->startup_sent < br->multicast_startup_query_count) query->startup_sent++; br_multicast_send_query(port->br, port, query); out: spin_unlock(&br->multicast_lock); } static void br_ip4_multicast_port_query_expired(unsigned long data) { struct net_bridge_port *port = (void *)data; br_multicast_port_query_expired(port, &port->ip4_own_query); } #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_port_query_expired(unsigned long data) { struct net_bridge_port *port = (void *)data; br_multicast_port_query_expired(port, &port->ip6_own_query); } #endif static void br_mc_disabled_update(struct net_device *dev, bool value) { struct switchdev_attr attr = { .orig_dev = dev, .id = SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED, .flags = SWITCHDEV_F_DEFER, .u.mc_disabled = value, }; switchdev_port_attr_set(dev, &attr); } int br_multicast_add_port(struct net_bridge_port *port) { port->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; setup_timer(&port->multicast_router_timer, br_multicast_router_expired, (unsigned long)port); setup_timer(&port->ip4_own_query.timer, br_ip4_multicast_port_query_expired, (unsigned long)port); #if IS_ENABLED(CONFIG_IPV6) setup_timer(&port->ip6_own_query.timer, br_ip6_multicast_port_query_expired, (unsigned long)port); #endif br_mc_disabled_update(port->dev, port->br->multicast_disabled); port->mcast_stats = netdev_alloc_pcpu_stats(struct bridge_mcast_stats); if (!port->mcast_stats) return -ENOMEM; return 0; } void br_multicast_del_port(struct net_bridge_port *port) { struct net_bridge *br = port->br; struct net_bridge_port_group *pg; struct hlist_node *n; /* Take care of the remaining groups, only perm ones should be left */ spin_lock_bh(&br->multicast_lock); hlist_for_each_entry_safe(pg, n, &port->mglist, mglist) br_multicast_del_pg(br, pg); spin_unlock_bh(&br->multicast_lock); del_timer_sync(&port->multicast_router_timer); free_percpu(port->mcast_stats); } static void br_multicast_enable(struct bridge_mcast_own_query *query) { query->startup_sent = 0; if (try_to_del_timer_sync(&query->timer) >= 0 || del_timer(&query->timer)) mod_timer(&query->timer, jiffies); } static void __br_multicast_enable_port(struct net_bridge_port *port) { struct net_bridge *br = port->br; if (br->multicast_disabled || !netif_running(br->dev)) return; br_multicast_enable(&port->ip4_own_query); #if IS_ENABLED(CONFIG_IPV6) br_multicast_enable(&port->ip6_own_query); #endif if (port->multicast_router == MDB_RTR_TYPE_PERM && hlist_unhashed(&port->rlist)) br_multicast_add_router(br, port); } void br_multicast_enable_port(struct net_bridge_port *port) { struct net_bridge *br = port->br; spin_lock(&br->multicast_lock); __br_multicast_enable_port(port); spin_unlock(&br->multicast_lock); } void br_multicast_disable_port(struct net_bridge_port *port) { struct net_bridge *br = port->br; struct net_bridge_port_group *pg; struct hlist_node *n; spin_lock(&br->multicast_lock); hlist_for_each_entry_safe(pg, n, &port->mglist, mglist) if (!(pg->flags & MDB_PG_FLAGS_PERMANENT)) br_multicast_del_pg(br, pg); __del_port_router(port); del_timer(&port->multicast_router_timer); del_timer(&port->ip4_own_query.timer); #if IS_ENABLED(CONFIG_IPV6) del_timer(&port->ip6_own_query.timer); #endif spin_unlock(&br->multicast_lock); } static int br_ip4_multicast_igmp3_report(struct net_bridge *br, struct net_bridge_port *port, struct sk_buff *skb, u16 vid) { const unsigned char *src; struct igmpv3_report *ih; struct igmpv3_grec *grec; int i; int len; int num; int type; int err = 0; __be32 group; u16 nsrcs; ih = igmpv3_report_hdr(skb); num = ntohs(ih->ngrec); len = skb_transport_offset(skb) + sizeof(*ih); for (i = 0; i < num; i++) { len += sizeof(*grec); if (!pskb_may_pull(skb, len)) return -EINVAL; grec = (void *)(skb->data + len - sizeof(*grec)); group = grec->grec_mca; type = grec->grec_type; nsrcs = ntohs(grec->grec_nsrcs); len += nsrcs * 4; if (!pskb_may_pull(skb, len)) return -EINVAL; /* We treat this as an IGMPv2 report for now. */ switch (type) { case IGMPV3_MODE_IS_INCLUDE: case IGMPV3_MODE_IS_EXCLUDE: case IGMPV3_CHANGE_TO_INCLUDE: case IGMPV3_CHANGE_TO_EXCLUDE: case IGMPV3_ALLOW_NEW_SOURCES: case IGMPV3_BLOCK_OLD_SOURCES: break; default: continue; } src = eth_hdr(skb)->h_source; if ((type == IGMPV3_CHANGE_TO_INCLUDE || type == IGMPV3_MODE_IS_INCLUDE) && nsrcs == 0) { br_ip4_multicast_leave_group(br, port, group, vid, src); } else { err = br_ip4_multicast_add_group(br, port, group, vid, src); if (err) break; } } return err; } #if IS_ENABLED(CONFIG_IPV6) static int br_ip6_multicast_mld2_report(struct net_bridge *br, struct net_bridge_port *port, struct sk_buff *skb, u16 vid) { const unsigned char *src; struct icmp6hdr *icmp6h; struct mld2_grec *grec; int i; int len; int num; int err = 0; if (!pskb_may_pull(skb, sizeof(*icmp6h))) return -EINVAL; icmp6h = icmp6_hdr(skb); num = ntohs(icmp6h->icmp6_dataun.un_data16[1]); len = skb_transport_offset(skb) + sizeof(*icmp6h); for (i = 0; i < num; i++) { __be16 *_nsrcs, __nsrcs; u16 nsrcs; _nsrcs = skb_header_pointer(skb, len + offsetof(struct mld2_grec, grec_nsrcs), sizeof(__nsrcs), &__nsrcs); if (!_nsrcs) return -EINVAL; nsrcs = ntohs(*_nsrcs); if (!pskb_may_pull(skb, len + sizeof(*grec) + sizeof(struct in6_addr) * nsrcs)) return -EINVAL; grec = (struct mld2_grec *)(skb->data + len); len += sizeof(*grec) + sizeof(struct in6_addr) * nsrcs; /* We treat these as MLDv1 reports for now. */ switch (grec->grec_type) { case MLD2_MODE_IS_INCLUDE: case MLD2_MODE_IS_EXCLUDE: case MLD2_CHANGE_TO_INCLUDE: case MLD2_CHANGE_TO_EXCLUDE: case MLD2_ALLOW_NEW_SOURCES: case MLD2_BLOCK_OLD_SOURCES: break; default: continue; } src = eth_hdr(skb)->h_source; if ((grec->grec_type == MLD2_CHANGE_TO_INCLUDE || grec->grec_type == MLD2_MODE_IS_INCLUDE) && nsrcs == 0) { br_ip6_multicast_leave_group(br, port, &grec->grec_mca, vid, src); } else { err = br_ip6_multicast_add_group(br, port, &grec->grec_mca, vid, src); if (err) break; } } return err; } #endif static bool br_ip4_multicast_select_querier(struct net_bridge *br, struct net_bridge_port *port, __be32 saddr) { if (!timer_pending(&br->ip4_own_query.timer) && !timer_pending(&br->ip4_other_query.timer)) goto update; if (!br->ip4_querier.addr.u.ip4) goto update; if (ntohl(saddr) <= ntohl(br->ip4_querier.addr.u.ip4)) goto update; return false; update: br->ip4_querier.addr.u.ip4 = saddr; /* update protected by general multicast_lock by caller */ rcu_assign_pointer(br->ip4_querier.port, port); return true; } #if IS_ENABLED(CONFIG_IPV6) static bool br_ip6_multicast_select_querier(struct net_bridge *br, struct net_bridge_port *port, struct in6_addr *saddr) { if (!timer_pending(&br->ip6_own_query.timer) && !timer_pending(&br->ip6_other_query.timer)) goto update; if (ipv6_addr_cmp(saddr, &br->ip6_querier.addr.u.ip6) <= 0) goto update; return false; update: br->ip6_querier.addr.u.ip6 = *saddr; /* update protected by general multicast_lock by caller */ rcu_assign_pointer(br->ip6_querier.port, port); return true; } #endif static bool br_multicast_select_querier(struct net_bridge *br, struct net_bridge_port *port, struct br_ip *saddr) { switch (saddr->proto) { case htons(ETH_P_IP): return br_ip4_multicast_select_querier(br, port, saddr->u.ip4); #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): return br_ip6_multicast_select_querier(br, port, &saddr->u.ip6); #endif } return false; } static void br_multicast_update_query_timer(struct net_bridge *br, struct bridge_mcast_other_query *query, unsigned long max_delay) { if (!timer_pending(&query->timer)) query->delay_time = jiffies + max_delay; mod_timer(&query->timer, jiffies + br->multicast_querier_interval); } static void br_port_mc_router_state_change(struct net_bridge_port *p, bool is_mc_router) { struct switchdev_attr attr = { .orig_dev = p->dev, .id = SWITCHDEV_ATTR_ID_PORT_MROUTER, .flags = SWITCHDEV_F_DEFER, .u.mrouter = is_mc_router, }; switchdev_port_attr_set(p->dev, &attr); } /* * Add port to router_list * list is maintained ordered by pointer value * and locked by br->multicast_lock and RCU */ static void br_multicast_add_router(struct net_bridge *br, struct net_bridge_port *port) { struct net_bridge_port *p; struct hlist_node *slot = NULL; if (!hlist_unhashed(&port->rlist)) return; hlist_for_each_entry(p, &br->router_list, rlist) { if ((unsigned long) port >= (unsigned long) p) break; slot = &p->rlist; } if (slot) hlist_add_behind_rcu(&port->rlist, slot); else hlist_add_head_rcu(&port->rlist, &br->router_list); br_rtr_notify(br->dev, port, RTM_NEWMDB); br_port_mc_router_state_change(port, true); } static void br_multicast_mark_router(struct net_bridge *br, struct net_bridge_port *port) { unsigned long now = jiffies; if (!port) { if (br->multicast_router == MDB_RTR_TYPE_TEMP_QUERY) mod_timer(&br->multicast_router_timer, now + br->multicast_querier_interval); return; } if (port->multicast_router == MDB_RTR_TYPE_DISABLED || port->multicast_router == MDB_RTR_TYPE_PERM) return; br_multicast_add_router(br, port); mod_timer(&port->multicast_router_timer, now + br->multicast_querier_interval); } static void br_multicast_query_received(struct net_bridge *br, struct net_bridge_port *port, struct bridge_mcast_other_query *query, struct br_ip *saddr, unsigned long max_delay) { if (!br_multicast_select_querier(br, port, saddr)) return; br_multicast_update_query_timer(br, query, max_delay); br_multicast_mark_router(br, port); } static int br_ip4_multicast_query(struct net_bridge *br, struct net_bridge_port *port, struct sk_buff *skb, u16 vid) { const struct iphdr *iph = ip_hdr(skb); struct igmphdr *ih = igmp_hdr(skb); struct net_bridge_mdb_entry *mp; struct igmpv3_query *ih3; struct net_bridge_port_group *p; struct net_bridge_port_group __rcu **pp; struct br_ip saddr; unsigned long max_delay; unsigned long now = jiffies; unsigned int offset = skb_transport_offset(skb); __be32 group; int err = 0; spin_lock(&br->multicast_lock); if (!netif_running(br->dev) || (port && port->state == BR_STATE_DISABLED)) goto out; group = ih->group; if (skb->len == offset + sizeof(*ih)) { max_delay = ih->code * (HZ / IGMP_TIMER_SCALE); if (!max_delay) { max_delay = 10 * HZ; group = 0; } } else if (skb->len >= offset + sizeof(*ih3)) { ih3 = igmpv3_query_hdr(skb); if (ih3->nsrcs) goto out; max_delay = ih3->code ? IGMPV3_MRC(ih3->code) * (HZ / IGMP_TIMER_SCALE) : 1; } else { goto out; } if (!group) { saddr.proto = htons(ETH_P_IP); saddr.u.ip4 = iph->saddr; br_multicast_query_received(br, port, &br->ip4_other_query, &saddr, max_delay); goto out; } mp = br_mdb_ip4_get(mlock_dereference(br->mdb, br), group, vid); if (!mp) goto out; max_delay *= br->multicast_last_member_count; if (mp->mglist && (timer_pending(&mp->timer) ? time_after(mp->timer.expires, now + max_delay) : try_to_del_timer_sync(&mp->timer) >= 0)) mod_timer(&mp->timer, now + max_delay); for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL; pp = &p->next) { if (timer_pending(&p->timer) ? time_after(p->timer.expires, now + max_delay) : try_to_del_timer_sync(&p->timer) >= 0) mod_timer(&p->timer, now + max_delay); } out: spin_unlock(&br->multicast_lock); return err; } #if IS_ENABLED(CONFIG_IPV6) static int br_ip6_multicast_query(struct net_bridge *br, struct net_bridge_port *port, struct sk_buff *skb, u16 vid) { struct mld_msg *mld; struct net_bridge_mdb_entry *mp; struct mld2_query *mld2q; struct net_bridge_port_group *p; struct net_bridge_port_group __rcu **pp; struct br_ip saddr; unsigned long max_delay; unsigned long now = jiffies; unsigned int offset = skb_transport_offset(skb); const struct in6_addr *group = NULL; bool is_general_query; int err = 0; spin_lock(&br->multicast_lock); if (!netif_running(br->dev) || (port && port->state == BR_STATE_DISABLED)) goto out; if (skb->len == offset + sizeof(*mld)) { if (!pskb_may_pull(skb, offset + sizeof(*mld))) { err = -EINVAL; goto out; } mld = (struct mld_msg *) icmp6_hdr(skb); max_delay = msecs_to_jiffies(ntohs(mld->mld_maxdelay)); if (max_delay) group = &mld->mld_mca; } else { if (!pskb_may_pull(skb, offset + sizeof(*mld2q))) { err = -EINVAL; goto out; } mld2q = (struct mld2_query *)icmp6_hdr(skb); if (!mld2q->mld2q_nsrcs) group = &mld2q->mld2q_mca; max_delay = max(msecs_to_jiffies(mldv2_mrc(mld2q)), 1UL); } is_general_query = group && ipv6_addr_any(group); if (is_general_query) { saddr.proto = htons(ETH_P_IPV6); saddr.u.ip6 = ipv6_hdr(skb)->saddr; br_multicast_query_received(br, port, &br->ip6_other_query, &saddr, max_delay); goto out; } else if (!group) { goto out; } mp = br_mdb_ip6_get(mlock_dereference(br->mdb, br), group, vid); if (!mp) goto out; max_delay *= br->multicast_last_member_count; if (mp->mglist && (timer_pending(&mp->timer) ? time_after(mp->timer.expires, now + max_delay) : try_to_del_timer_sync(&mp->timer) >= 0)) mod_timer(&mp->timer, now + max_delay); for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL; pp = &p->next) { if (timer_pending(&p->timer) ? time_after(p->timer.expires, now + max_delay) : try_to_del_timer_sync(&p->timer) >= 0) mod_timer(&p->timer, now + max_delay); } out: spin_unlock(&br->multicast_lock); return err; } #endif static void br_multicast_leave_group(struct net_bridge *br, struct net_bridge_port *port, struct br_ip *group, struct bridge_mcast_other_query *other_query, struct bridge_mcast_own_query *own_query, const unsigned char *src) { struct net_bridge_mdb_htable *mdb; struct net_bridge_mdb_entry *mp; struct net_bridge_port_group *p; unsigned long now; unsigned long time; spin_lock(&br->multicast_lock); if (!netif_running(br->dev) || (port && port->state == BR_STATE_DISABLED)) goto out; mdb = mlock_dereference(br->mdb, br); mp = br_mdb_ip_get(mdb, group); if (!mp) goto out; if (port && (port->flags & BR_MULTICAST_FAST_LEAVE)) { struct net_bridge_port_group __rcu **pp; for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL; pp = &p->next) { if (!br_port_group_equal(p, port, src)) continue; if (p->flags & MDB_PG_FLAGS_PERMANENT) break; rcu_assign_pointer(*pp, p->next); hlist_del_init(&p->mglist); del_timer(&p->timer); call_rcu_bh(&p->rcu, br_multicast_free_pg); br_mdb_notify(br->dev, port, group, RTM_DELMDB, p->flags); if (!mp->ports && !mp->mglist && netif_running(br->dev)) mod_timer(&mp->timer, jiffies); } goto out; } if (timer_pending(&other_query->timer)) goto out; if (br->multicast_querier) { __br_multicast_send_query(br, port, &mp->addr); time = jiffies + br->multicast_last_member_count * br->multicast_last_member_interval; mod_timer(&own_query->timer, time); for (p = mlock_dereference(mp->ports, br); p != NULL; p = mlock_dereference(p->next, br)) { if (!br_port_group_equal(p, port, src)) continue; if (!hlist_unhashed(&p->mglist) && (timer_pending(&p->timer) ? time_after(p->timer.expires, time) : try_to_del_timer_sync(&p->timer) >= 0)) { mod_timer(&p->timer, time); } break; } } now = jiffies; time = now + br->multicast_last_member_count * br->multicast_last_member_interval; if (!port) { if (mp->mglist && (timer_pending(&mp->timer) ? time_after(mp->timer.expires, time) : try_to_del_timer_sync(&mp->timer) >= 0)) { mod_timer(&mp->timer, time); } goto out; } for (p = mlock_dereference(mp->ports, br); p != NULL; p = mlock_dereference(p->next, br)) { if (p->port != port) continue; if (!hlist_unhashed(&p->mglist) && (timer_pending(&p->timer) ? time_after(p->timer.expires, time) : try_to_del_timer_sync(&p->timer) >= 0)) { mod_timer(&p->timer, time); } break; } out: spin_unlock(&br->multicast_lock); } static void br_ip4_multicast_leave_group(struct net_bridge *br, struct net_bridge_port *port, __be32 group, __u16 vid, const unsigned char *src) { struct br_ip br_group; struct bridge_mcast_own_query *own_query; if (ipv4_is_local_multicast(group)) return; own_query = port ? &port->ip4_own_query : &br->ip4_own_query; br_group.u.ip4 = group; br_group.proto = htons(ETH_P_IP); br_group.vid = vid; br_multicast_leave_group(br, port, &br_group, &br->ip4_other_query, own_query, src); } #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_leave_group(struct net_bridge *br, struct net_bridge_port *port, const struct in6_addr *group, __u16 vid, const unsigned char *src) { struct br_ip br_group; struct bridge_mcast_own_query *own_query; if (ipv6_addr_is_ll_all_nodes(group)) return; own_query = port ? &port->ip6_own_query : &br->ip6_own_query; br_group.u.ip6 = *group; br_group.proto = htons(ETH_P_IPV6); br_group.vid = vid; br_multicast_leave_group(br, port, &br_group, &br->ip6_other_query, own_query, src); } #endif static void br_multicast_err_count(const struct net_bridge *br, const struct net_bridge_port *p, __be16 proto) { struct bridge_mcast_stats __percpu *stats; struct bridge_mcast_stats *pstats; if (!br->multicast_stats_enabled) return; if (p) stats = p->mcast_stats; else stats = br->mcast_stats; if (WARN_ON(!stats)) return; pstats = this_cpu_ptr(stats); u64_stats_update_begin(&pstats->syncp); switch (proto) { case htons(ETH_P_IP): pstats->mstats.igmp_parse_errors++; break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): pstats->mstats.mld_parse_errors++; break; #endif } u64_stats_update_end(&pstats->syncp); } static void br_multicast_pim(struct net_bridge *br, struct net_bridge_port *port, const struct sk_buff *skb) { unsigned int offset = skb_transport_offset(skb); struct pimhdr *pimhdr, _pimhdr; pimhdr = skb_header_pointer(skb, offset, sizeof(_pimhdr), &_pimhdr); if (!pimhdr || pim_hdr_version(pimhdr) != PIM_VERSION || pim_hdr_type(pimhdr) != PIM_TYPE_HELLO) return; spin_lock(&br->multicast_lock); br_multicast_mark_router(br, port); spin_unlock(&br->multicast_lock); } static int br_multicast_ipv4_rcv(struct net_bridge *br, struct net_bridge_port *port, struct sk_buff *skb, u16 vid) { struct sk_buff *skb_trimmed = NULL; const unsigned char *src; struct igmphdr *ih; int err; err = ip_mc_check_igmp(skb, &skb_trimmed); if (err == -ENOMSG) { if (!ipv4_is_local_multicast(ip_hdr(skb)->daddr)) { BR_INPUT_SKB_CB(skb)->mrouters_only = 1; } else if (pim_ipv4_all_pim_routers(ip_hdr(skb)->daddr)) { if (ip_hdr(skb)->protocol == IPPROTO_PIM) br_multicast_pim(br, port, skb); } return 0; } else if (err < 0) { br_multicast_err_count(br, port, skb->protocol); return err; } ih = igmp_hdr(skb); src = eth_hdr(skb)->h_source; BR_INPUT_SKB_CB(skb)->igmp = ih->type; switch (ih->type) { case IGMP_HOST_MEMBERSHIP_REPORT: case IGMPV2_HOST_MEMBERSHIP_REPORT: BR_INPUT_SKB_CB(skb)->mrouters_only = 1; err = br_ip4_multicast_add_group(br, port, ih->group, vid, src); break; case IGMPV3_HOST_MEMBERSHIP_REPORT: err = br_ip4_multicast_igmp3_report(br, port, skb_trimmed, vid); break; case IGMP_HOST_MEMBERSHIP_QUERY: err = br_ip4_multicast_query(br, port, skb_trimmed, vid); break; case IGMP_HOST_LEAVE_MESSAGE: br_ip4_multicast_leave_group(br, port, ih->group, vid, src); break; } if (skb_trimmed && skb_trimmed != skb) kfree_skb(skb_trimmed); br_multicast_count(br, port, skb, BR_INPUT_SKB_CB(skb)->igmp, BR_MCAST_DIR_RX); return err; } #if IS_ENABLED(CONFIG_IPV6) static int br_multicast_ipv6_rcv(struct net_bridge *br, struct net_bridge_port *port, struct sk_buff *skb, u16 vid) { struct sk_buff *skb_trimmed = NULL; const unsigned char *src; struct mld_msg *mld; int err; err = ipv6_mc_check_mld(skb, &skb_trimmed); if (err == -ENOMSG) { if (!ipv6_addr_is_ll_all_nodes(&ipv6_hdr(skb)->daddr)) BR_INPUT_SKB_CB(skb)->mrouters_only = 1; return 0; } else if (err < 0) { br_multicast_err_count(br, port, skb->protocol); return err; } mld = (struct mld_msg *)skb_transport_header(skb); BR_INPUT_SKB_CB(skb)->igmp = mld->mld_type; switch (mld->mld_type) { case ICMPV6_MGM_REPORT: src = eth_hdr(skb)->h_source; BR_INPUT_SKB_CB(skb)->mrouters_only = 1; err = br_ip6_multicast_add_group(br, port, &mld->mld_mca, vid, src); break; case ICMPV6_MLD2_REPORT: err = br_ip6_multicast_mld2_report(br, port, skb_trimmed, vid); break; case ICMPV6_MGM_QUERY: err = br_ip6_multicast_query(br, port, skb_trimmed, vid); break; case ICMPV6_MGM_REDUCTION: src = eth_hdr(skb)->h_source; br_ip6_multicast_leave_group(br, port, &mld->mld_mca, vid, src); break; } if (skb_trimmed && skb_trimmed != skb) kfree_skb(skb_trimmed); br_multicast_count(br, port, skb, BR_INPUT_SKB_CB(skb)->igmp, BR_MCAST_DIR_RX); return err; } #endif int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port, struct sk_buff *skb, u16 vid) { int ret = 0; BR_INPUT_SKB_CB(skb)->igmp = 0; BR_INPUT_SKB_CB(skb)->mrouters_only = 0; if (br->multicast_disabled) return 0; switch (skb->protocol) { case htons(ETH_P_IP): ret = br_multicast_ipv4_rcv(br, port, skb, vid); break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): ret = br_multicast_ipv6_rcv(br, port, skb, vid); break; #endif } return ret; } static void br_multicast_query_expired(struct net_bridge *br, struct bridge_mcast_own_query *query, struct bridge_mcast_querier *querier) { spin_lock(&br->multicast_lock); if (query->startup_sent < br->multicast_startup_query_count) query->startup_sent++; RCU_INIT_POINTER(querier->port, NULL); br_multicast_send_query(br, NULL, query); spin_unlock(&br->multicast_lock); } static void br_ip4_multicast_query_expired(unsigned long data) { struct net_bridge *br = (void *)data; br_multicast_query_expired(br, &br->ip4_own_query, &br->ip4_querier); } #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_query_expired(unsigned long data) { struct net_bridge *br = (void *)data; br_multicast_query_expired(br, &br->ip6_own_query, &br->ip6_querier); } #endif void br_multicast_init(struct net_bridge *br) { br->hash_elasticity = 4; br->hash_max = 512; br->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; br->multicast_querier = 0; br->multicast_query_use_ifaddr = 0; br->multicast_last_member_count = 2; br->multicast_startup_query_count = 2; br->multicast_last_member_interval = HZ; br->multicast_query_response_interval = 10 * HZ; br->multicast_startup_query_interval = 125 * HZ / 4; br->multicast_query_interval = 125 * HZ; br->multicast_querier_interval = 255 * HZ; br->multicast_membership_interval = 260 * HZ; br->ip4_other_query.delay_time = 0; br->ip4_querier.port = NULL; br->multicast_igmp_version = 2; #if IS_ENABLED(CONFIG_IPV6) br->multicast_mld_version = 1; br->ip6_other_query.delay_time = 0; br->ip6_querier.port = NULL; #endif br->has_ipv6_addr = 1; spin_lock_init(&br->multicast_lock); setup_timer(&br->multicast_router_timer, br_multicast_local_router_expired, 0); setup_timer(&br->ip4_other_query.timer, br_ip4_multicast_querier_expired, (unsigned long)br); setup_timer(&br->ip4_own_query.timer, br_ip4_multicast_query_expired, (unsigned long)br); #if IS_ENABLED(CONFIG_IPV6) setup_timer(&br->ip6_other_query.timer, br_ip6_multicast_querier_expired, (unsigned long)br); setup_timer(&br->ip6_own_query.timer, br_ip6_multicast_query_expired, (unsigned long)br); #endif } static void __br_multicast_open(struct net_bridge *br, struct bridge_mcast_own_query *query) { query->startup_sent = 0; if (br->multicast_disabled) return; mod_timer(&query->timer, jiffies); } void br_multicast_open(struct net_bridge *br) { __br_multicast_open(br, &br->ip4_own_query); #if IS_ENABLED(CONFIG_IPV6) __br_multicast_open(br, &br->ip6_own_query); #endif } void br_multicast_stop(struct net_bridge *br) { del_timer_sync(&br->multicast_router_timer); del_timer_sync(&br->ip4_other_query.timer); del_timer_sync(&br->ip4_own_query.timer); #if IS_ENABLED(CONFIG_IPV6) del_timer_sync(&br->ip6_other_query.timer); del_timer_sync(&br->ip6_own_query.timer); #endif } void br_multicast_dev_del(struct net_bridge *br) { struct net_bridge_mdb_htable *mdb; struct net_bridge_mdb_entry *mp; struct hlist_node *n; u32 ver; int i; spin_lock_bh(&br->multicast_lock); mdb = mlock_dereference(br->mdb, br); if (!mdb) goto out; br->mdb = NULL; ver = mdb->ver; for (i = 0; i < mdb->max; i++) { hlist_for_each_entry_safe(mp, n, &mdb->mhash[i], hlist[ver]) { del_timer(&mp->timer); call_rcu_bh(&mp->rcu, br_multicast_free_group); } } if (mdb->old) { spin_unlock_bh(&br->multicast_lock); rcu_barrier_bh(); spin_lock_bh(&br->multicast_lock); WARN_ON(mdb->old); } mdb->old = mdb; call_rcu_bh(&mdb->rcu, br_mdb_free); out: spin_unlock_bh(&br->multicast_lock); } int br_multicast_set_router(struct net_bridge *br, unsigned long val) { int err = -EINVAL; spin_lock_bh(&br->multicast_lock); switch (val) { case MDB_RTR_TYPE_DISABLED: case MDB_RTR_TYPE_PERM: del_timer(&br->multicast_router_timer); /* fall through */ case MDB_RTR_TYPE_TEMP_QUERY: br->multicast_router = val; err = 0; break; } spin_unlock_bh(&br->multicast_lock); return err; } static void __del_port_router(struct net_bridge_port *p) { if (hlist_unhashed(&p->rlist)) return; hlist_del_init_rcu(&p->rlist); br_rtr_notify(p->br->dev, p, RTM_DELMDB); br_port_mc_router_state_change(p, false); /* don't allow timer refresh */ if (p->multicast_router == MDB_RTR_TYPE_TEMP) p->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; } int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val) { struct net_bridge *br = p->br; unsigned long now = jiffies; int err = -EINVAL; spin_lock(&br->multicast_lock); if (p->multicast_router == val) { /* Refresh the temp router port timer */ if (p->multicast_router == MDB_RTR_TYPE_TEMP) mod_timer(&p->multicast_router_timer, now + br->multicast_querier_interval); err = 0; goto unlock; } switch (val) { case MDB_RTR_TYPE_DISABLED: p->multicast_router = MDB_RTR_TYPE_DISABLED; __del_port_router(p); del_timer(&p->multicast_router_timer); break; case MDB_RTR_TYPE_TEMP_QUERY: p->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; __del_port_router(p); break; case MDB_RTR_TYPE_PERM: p->multicast_router = MDB_RTR_TYPE_PERM; del_timer(&p->multicast_router_timer); br_multicast_add_router(br, p); break; case MDB_RTR_TYPE_TEMP: p->multicast_router = MDB_RTR_TYPE_TEMP; br_multicast_mark_router(br, p); break; default: goto unlock; } err = 0; unlock: spin_unlock(&br->multicast_lock); return err; } static void br_multicast_start_querier(struct net_bridge *br, struct bridge_mcast_own_query *query) { struct net_bridge_port *port; __br_multicast_open(br, query); rcu_read_lock(); list_for_each_entry_rcu(port, &br->port_list, list) { if (port->state == BR_STATE_DISABLED || port->state == BR_STATE_BLOCKING) continue; if (query == &br->ip4_own_query) br_multicast_enable(&port->ip4_own_query); #if IS_ENABLED(CONFIG_IPV6) else br_multicast_enable(&port->ip6_own_query); #endif } rcu_read_unlock(); } int br_multicast_toggle(struct net_bridge *br, unsigned long val) { struct net_bridge_mdb_htable *mdb; struct net_bridge_port *port; int err = 0; spin_lock_bh(&br->multicast_lock); if (br->multicast_disabled == !val) goto unlock; br_mc_disabled_update(br->dev, !val); br->multicast_disabled = !val; if (br->multicast_disabled) goto unlock; if (!netif_running(br->dev)) goto unlock; mdb = mlock_dereference(br->mdb, br); if (mdb) { if (mdb->old) { err = -EEXIST; rollback: br->multicast_disabled = !!val; goto unlock; } err = br_mdb_rehash(&br->mdb, mdb->max, br->hash_elasticity); if (err) goto rollback; } br_multicast_open(br); list_for_each_entry(port, &br->port_list, list) __br_multicast_enable_port(port); unlock: spin_unlock_bh(&br->multicast_lock); return err; } bool br_multicast_enabled(const struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); return !br->multicast_disabled; } EXPORT_SYMBOL_GPL(br_multicast_enabled); int br_multicast_set_querier(struct net_bridge *br, unsigned long val) { unsigned long max_delay; val = !!val; spin_lock_bh(&br->multicast_lock); if (br->multicast_querier == val) goto unlock; br->multicast_querier = val; if (!val) goto unlock; max_delay = br->multicast_query_response_interval; if (!timer_pending(&br->ip4_other_query.timer)) br->ip4_other_query.delay_time = jiffies + max_delay; br_multicast_start_querier(br, &br->ip4_own_query); #if IS_ENABLED(CONFIG_IPV6) if (!timer_pending(&br->ip6_other_query.timer)) br->ip6_other_query.delay_time = jiffies + max_delay; br_multicast_start_querier(br, &br->ip6_own_query); #endif unlock: spin_unlock_bh(&br->multicast_lock); return 0; } int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val) { int err = -EINVAL; u32 old; struct net_bridge_mdb_htable *mdb; spin_lock_bh(&br->multicast_lock); if (!is_power_of_2(val)) goto unlock; mdb = mlock_dereference(br->mdb, br); if (mdb && val < mdb->size) goto unlock; err = 0; old = br->hash_max; br->hash_max = val; if (mdb) { if (mdb->old) { err = -EEXIST; rollback: br->hash_max = old; goto unlock; } err = br_mdb_rehash(&br->mdb, br->hash_max, br->hash_elasticity); if (err) goto rollback; } unlock: spin_unlock_bh(&br->multicast_lock); return err; } int br_multicast_set_igmp_version(struct net_bridge *br, unsigned long val) { /* Currently we support only version 2 and 3 */ switch (val) { case 2: case 3: break; default: return -EINVAL; } spin_lock_bh(&br->multicast_lock); br->multicast_igmp_version = val; spin_unlock_bh(&br->multicast_lock); return 0; } #if IS_ENABLED(CONFIG_IPV6) int br_multicast_set_mld_version(struct net_bridge *br, unsigned long val) { /* Currently we support version 1 and 2 */ switch (val) { case 1: case 2: break; default: return -EINVAL; } spin_lock_bh(&br->multicast_lock); br->multicast_mld_version = val; spin_unlock_bh(&br->multicast_lock); return 0; } #endif /** * br_multicast_list_adjacent - Returns snooped multicast addresses * @dev: The bridge port adjacent to which to retrieve addresses * @br_ip_list: The list to store found, snooped multicast IP addresses in * * Creates a list of IP addresses (struct br_ip_list) sensed by the multicast * snooping feature on all bridge ports of dev's bridge device, excluding * the addresses from dev itself. * * Returns the number of items added to br_ip_list. * * Notes: * - br_ip_list needs to be initialized by caller * - br_ip_list might contain duplicates in the end * (needs to be taken care of by caller) * - br_ip_list needs to be freed by caller */ int br_multicast_list_adjacent(struct net_device *dev, struct list_head *br_ip_list) { struct net_bridge *br; struct net_bridge_port *port; struct net_bridge_port_group *group; struct br_ip_list *entry; int count = 0; rcu_read_lock(); if (!br_ip_list || !br_port_exists(dev)) goto unlock; port = br_port_get_rcu(dev); if (!port || !port->br) goto unlock; br = port->br; list_for_each_entry_rcu(port, &br->port_list, list) { if (!port->dev || port->dev == dev) continue; hlist_for_each_entry_rcu(group, &port->mglist, mglist) { entry = kmalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) goto unlock; entry->addr = group->addr; list_add(&entry->list, br_ip_list); count++; } } unlock: rcu_read_unlock(); return count; } EXPORT_SYMBOL_GPL(br_multicast_list_adjacent); /** * br_multicast_has_querier_anywhere - Checks for a querier on a bridge * @dev: The bridge port providing the bridge on which to check for a querier * @proto: The protocol family to check for: IGMP -> ETH_P_IP, MLD -> ETH_P_IPV6 * * Checks whether the given interface has a bridge on top and if so returns * true if a valid querier exists anywhere on the bridged link layer. * Otherwise returns false. */ bool br_multicast_has_querier_anywhere(struct net_device *dev, int proto) { struct net_bridge *br; struct net_bridge_port *port; struct ethhdr eth; bool ret = false; rcu_read_lock(); if (!br_port_exists(dev)) goto unlock; port = br_port_get_rcu(dev); if (!port || !port->br) goto unlock; br = port->br; memset(ð, 0, sizeof(eth)); eth.h_proto = htons(proto); ret = br_multicast_querier_exists(br, ð); unlock: rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(br_multicast_has_querier_anywhere); /** * br_multicast_has_querier_adjacent - Checks for a querier behind a bridge port * @dev: The bridge port adjacent to which to check for a querier * @proto: The protocol family to check for: IGMP -> ETH_P_IP, MLD -> ETH_P_IPV6 * * Checks whether the given interface has a bridge on top and if so returns * true if a selected querier is behind one of the other ports of this * bridge. Otherwise returns false. */ bool br_multicast_has_querier_adjacent(struct net_device *dev, int proto) { struct net_bridge *br; struct net_bridge_port *port; bool ret = false; rcu_read_lock(); if (!br_port_exists(dev)) goto unlock; port = br_port_get_rcu(dev); if (!port || !port->br) goto unlock; br = port->br; switch (proto) { case ETH_P_IP: if (!timer_pending(&br->ip4_other_query.timer) || rcu_dereference(br->ip4_querier.port) == port) goto unlock; break; #if IS_ENABLED(CONFIG_IPV6) case ETH_P_IPV6: if (!timer_pending(&br->ip6_other_query.timer) || rcu_dereference(br->ip6_querier.port) == port) goto unlock; break; #endif default: goto unlock; } ret = true; unlock: rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(br_multicast_has_querier_adjacent); static void br_mcast_stats_add(struct bridge_mcast_stats __percpu *stats, const struct sk_buff *skb, u8 type, u8 dir) { struct bridge_mcast_stats *pstats = this_cpu_ptr(stats); __be16 proto = skb->protocol; unsigned int t_len; u64_stats_update_begin(&pstats->syncp); switch (proto) { case htons(ETH_P_IP): t_len = ntohs(ip_hdr(skb)->tot_len) - ip_hdrlen(skb); switch (type) { case IGMP_HOST_MEMBERSHIP_REPORT: pstats->mstats.igmp_v1reports[dir]++; break; case IGMPV2_HOST_MEMBERSHIP_REPORT: pstats->mstats.igmp_v2reports[dir]++; break; case IGMPV3_HOST_MEMBERSHIP_REPORT: pstats->mstats.igmp_v3reports[dir]++; break; case IGMP_HOST_MEMBERSHIP_QUERY: if (t_len != sizeof(struct igmphdr)) { pstats->mstats.igmp_v3queries[dir]++; } else { unsigned int offset = skb_transport_offset(skb); struct igmphdr *ih, _ihdr; ih = skb_header_pointer(skb, offset, sizeof(_ihdr), &_ihdr); if (!ih) break; if (!ih->code) pstats->mstats.igmp_v1queries[dir]++; else pstats->mstats.igmp_v2queries[dir]++; } break; case IGMP_HOST_LEAVE_MESSAGE: pstats->mstats.igmp_leaves[dir]++; break; } break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): t_len = ntohs(ipv6_hdr(skb)->payload_len) + sizeof(struct ipv6hdr); t_len -= skb_network_header_len(skb); switch (type) { case ICMPV6_MGM_REPORT: pstats->mstats.mld_v1reports[dir]++; break; case ICMPV6_MLD2_REPORT: pstats->mstats.mld_v2reports[dir]++; break; case ICMPV6_MGM_QUERY: if (t_len != sizeof(struct mld_msg)) pstats->mstats.mld_v2queries[dir]++; else pstats->mstats.mld_v1queries[dir]++; break; case ICMPV6_MGM_REDUCTION: pstats->mstats.mld_leaves[dir]++; break; } break; #endif /* CONFIG_IPV6 */ } u64_stats_update_end(&pstats->syncp); } void br_multicast_count(struct net_bridge *br, const struct net_bridge_port *p, const struct sk_buff *skb, u8 type, u8 dir) { struct bridge_mcast_stats __percpu *stats; /* if multicast_disabled is true then igmp type can't be set */ if (!type || !br->multicast_stats_enabled) return; if (p) stats = p->mcast_stats; else stats = br->mcast_stats; if (WARN_ON(!stats)) return; br_mcast_stats_add(stats, skb, type, dir); } int br_multicast_init_stats(struct net_bridge *br) { br->mcast_stats = netdev_alloc_pcpu_stats(struct bridge_mcast_stats); if (!br->mcast_stats) return -ENOMEM; return 0; } void br_multicast_uninit_stats(struct net_bridge *br) { free_percpu(br->mcast_stats); } static void mcast_stats_add_dir(u64 *dst, u64 *src) { dst[BR_MCAST_DIR_RX] += src[BR_MCAST_DIR_RX]; dst[BR_MCAST_DIR_TX] += src[BR_MCAST_DIR_TX]; } void br_multicast_get_stats(const struct net_bridge *br, const struct net_bridge_port *p, struct br_mcast_stats *dest) { struct bridge_mcast_stats __percpu *stats; struct br_mcast_stats tdst; int i; memset(dest, 0, sizeof(*dest)); if (p) stats = p->mcast_stats; else stats = br->mcast_stats; if (WARN_ON(!stats)) return; memset(&tdst, 0, sizeof(tdst)); for_each_possible_cpu(i) { struct bridge_mcast_stats *cpu_stats = per_cpu_ptr(stats, i); struct br_mcast_stats temp; unsigned int start; do { start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); memcpy(&temp, &cpu_stats->mstats, sizeof(temp)); } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); mcast_stats_add_dir(tdst.igmp_v1queries, temp.igmp_v1queries); mcast_stats_add_dir(tdst.igmp_v2queries, temp.igmp_v2queries); mcast_stats_add_dir(tdst.igmp_v3queries, temp.igmp_v3queries); mcast_stats_add_dir(tdst.igmp_leaves, temp.igmp_leaves); mcast_stats_add_dir(tdst.igmp_v1reports, temp.igmp_v1reports); mcast_stats_add_dir(tdst.igmp_v2reports, temp.igmp_v2reports); mcast_stats_add_dir(tdst.igmp_v3reports, temp.igmp_v3reports); tdst.igmp_parse_errors += temp.igmp_parse_errors; mcast_stats_add_dir(tdst.mld_v1queries, temp.mld_v1queries); mcast_stats_add_dir(tdst.mld_v2queries, temp.mld_v2queries); mcast_stats_add_dir(tdst.mld_leaves, temp.mld_leaves); mcast_stats_add_dir(tdst.mld_v1reports, temp.mld_v1reports); mcast_stats_add_dir(tdst.mld_v2reports, temp.mld_v2reports); tdst.mld_parse_errors += temp.mld_parse_errors; } memcpy(dest, &tdst, sizeof(*dest)); } |
| 788 9 8 22 11754 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_CTYPE_H #define _LINUX_CTYPE_H /* * NOTE! This ctype does not handle EOF like the standard C * library is required to. */ #define _U 0x01 /* upper */ #define _L 0x02 /* lower */ #define _D 0x04 /* digit */ #define _C 0x08 /* cntrl */ #define _P 0x10 /* punct */ #define _S 0x20 /* white space (space/lf/tab) */ #define _X 0x40 /* hex digit */ #define _SP 0x80 /* hard space (0x20) */ extern const unsigned char _ctype[]; #define __ismask(x) (_ctype[(int)(unsigned char)(x)]) #define isalnum(c) ((__ismask(c)&(_U|_L|_D)) != 0) #define isalpha(c) ((__ismask(c)&(_U|_L)) != 0) #define iscntrl(c) ((__ismask(c)&(_C)) != 0) static inline int isdigit(int c) { return '0' <= c && c <= '9'; } #define isgraph(c) ((__ismask(c)&(_P|_U|_L|_D)) != 0) #define islower(c) ((__ismask(c)&(_L)) != 0) #define isprint(c) ((__ismask(c)&(_P|_U|_L|_D|_SP)) != 0) #define ispunct(c) ((__ismask(c)&(_P)) != 0) /* Note: isspace() must return false for %NUL-terminator */ #define isspace(c) ((__ismask(c)&(_S)) != 0) #define isupper(c) ((__ismask(c)&(_U)) != 0) #define isxdigit(c) ((__ismask(c)&(_D|_X)) != 0) #define isascii(c) (((unsigned char)(c))<=0x7f) #define toascii(c) (((unsigned char)(c))&0x7f) static inline unsigned char __tolower(unsigned char c) { if (isupper(c)) c -= 'A'-'a'; return c; } static inline unsigned char __toupper(unsigned char c) { if (islower(c)) c -= 'a'-'A'; return c; } #define tolower(c) __tolower(c) #define toupper(c) __toupper(c) /* * Fast implementation of tolower() for internal usage. Do not use in your * code. */ static inline char _tolower(const char c) { return c | 0x20; } /* Fast check for octal digit */ static inline int isodigit(const char c) { return c >= '0' && c <= '7'; } #endif |
| 1 1 1 1 11 24 24 25 25 6 4 3 3 18 17 16 15 8 10 7 2 5 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 | /* Copyright (c) 2011-2015 PLUMgrid, http://plumgrid.com * Copyright (c) 2016 Facebook * * This program is free software; you can redistribute it and/or * modify it under the terms of version 2 of the GNU General Public * License as published by the Free Software Foundation. */ #include <linux/kernel.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/bpf.h> #include <linux/bpf_perf_event.h> #include <linux/filter.h> #include <linux/uaccess.h> #include <linux/ctype.h> #include "trace.h" /** * trace_call_bpf - invoke BPF program * @prog: BPF program * @ctx: opaque context pointer * * kprobe handlers execute BPF programs via this helper. * Can be used from static tracepoints in the future. * * Return: BPF programs always return an integer which is interpreted by * kprobe handler as: * 0 - return from kprobe (event is filtered out) * 1 - store kprobe event into ring buffer * Other values are reserved and currently alias to 1 */ unsigned int trace_call_bpf(struct bpf_prog *prog, void *ctx) { unsigned int ret; if (in_nmi()) /* not supported yet */ return 1; preempt_disable(); if (unlikely(__this_cpu_inc_return(bpf_prog_active) != 1)) { /* * since some bpf program is already running on this cpu, * don't call into another bpf program (same or different) * and don't send kprobe event into ring-buffer, * so return zero here */ ret = 0; goto out; } rcu_read_lock(); ret = BPF_PROG_RUN(prog, ctx); rcu_read_unlock(); out: __this_cpu_dec(bpf_prog_active); preempt_enable(); return ret; } EXPORT_SYMBOL_GPL(trace_call_bpf); BPF_CALL_3(bpf_probe_read, void *, dst, u32, size, const void *, unsafe_ptr) { int ret; ret = probe_kernel_read(dst, unsafe_ptr, size); if (unlikely(ret < 0)) memset(dst, 0, size); return ret; } static const struct bpf_func_proto bpf_probe_read_proto = { .func = bpf_probe_read, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_probe_write_user, void *, unsafe_ptr, const void *, src, u32, size) { /* * Ensure we're in user context which is safe for the helper to * run. This helper has no business in a kthread. * * access_ok() should prevent writing to non-user memory, but in * some situations (nommu, temporary switch, etc) access_ok() does * not provide enough validation, hence the check on KERNEL_DS. */ if (unlikely(in_interrupt() || current->flags & (PF_KTHREAD | PF_EXITING))) return -EPERM; if (unlikely(uaccess_kernel())) return -EPERM; if (!access_ok(VERIFY_WRITE, unsafe_ptr, size)) return -EPERM; return probe_kernel_write(unsafe_ptr, src, size); } static const struct bpf_func_proto bpf_probe_write_user_proto = { .func = bpf_probe_write_user, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, }; static const struct bpf_func_proto *bpf_get_probe_write_proto(void) { pr_warn_ratelimited("%s[%d] is installing a program with bpf_probe_write_user helper that may corrupt user memory!", current->comm, task_pid_nr(current)); return &bpf_probe_write_user_proto; } /* * Only limited trace_printk() conversion specifiers allowed: * %d %i %u %x %ld %li %lu %lx %lld %lli %llu %llx %p %s */ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, u64, arg2, u64, arg3) { bool str_seen = false; int mod[3] = {}; int fmt_cnt = 0; u64 unsafe_addr; char buf[64]; int i; /* * bpf_check()->check_func_arg()->check_stack_boundary() * guarantees that fmt points to bpf program stack, * fmt_size bytes of it were initialized and fmt_size > 0 */ if (fmt[--fmt_size] != 0) return -EINVAL; /* check format string for allowed specifiers */ for (i = 0; i < fmt_size; i++) { if ((!isprint(fmt[i]) && !isspace(fmt[i])) || !isascii(fmt[i])) return -EINVAL; if (fmt[i] != '%') continue; if (fmt_cnt >= 3) return -EINVAL; /* fmt[i] != 0 && fmt[last] == 0, so we can access fmt[i + 1] */ i++; if (fmt[i] == 'l') { mod[fmt_cnt]++; i++; } else if (fmt[i] == 'p' || fmt[i] == 's') { mod[fmt_cnt]++; /* disallow any further format extensions */ if (fmt[i + 1] != 0 && !isspace(fmt[i + 1]) && !ispunct(fmt[i + 1])) return -EINVAL; fmt_cnt++; if (fmt[i] == 's') { if (str_seen) /* allow only one '%s' per fmt string */ return -EINVAL; str_seen = true; switch (fmt_cnt) { case 1: unsafe_addr = arg1; arg1 = (long) buf; break; case 2: unsafe_addr = arg2; arg2 = (long) buf; break; case 3: unsafe_addr = arg3; arg3 = (long) buf; break; } buf[0] = 0; strncpy_from_unsafe(buf, (void *) (long) unsafe_addr, sizeof(buf)); } continue; } if (fmt[i] == 'l') { mod[fmt_cnt]++; i++; } if (fmt[i] != 'i' && fmt[i] != 'd' && fmt[i] != 'u' && fmt[i] != 'x') return -EINVAL; fmt_cnt++; } /* Horrid workaround for getting va_list handling working with different * argument type combinations generically for 32 and 64 bit archs. */ #define __BPF_TP_EMIT() __BPF_ARG3_TP() #define __BPF_TP(...) \ __trace_printk(1 /* Fake ip will not be printed. */, \ fmt, ##__VA_ARGS__) #define __BPF_ARG1_TP(...) \ ((mod[0] == 2 || (mod[0] == 1 && __BITS_PER_LONG == 64)) \ ? __BPF_TP(arg1, ##__VA_ARGS__) \ : ((mod[0] == 1 || (mod[0] == 0 && __BITS_PER_LONG == 32)) \ ? __BPF_TP((long)arg1, ##__VA_ARGS__) \ : __BPF_TP((u32)arg1, ##__VA_ARGS__))) #define __BPF_ARG2_TP(...) \ ((mod[1] == 2 || (mod[1] == 1 && __BITS_PER_LONG == 64)) \ ? __BPF_ARG1_TP(arg2, ##__VA_ARGS__) \ : ((mod[1] == 1 || (mod[1] == 0 && __BITS_PER_LONG == 32)) \ ? __BPF_ARG1_TP((long)arg2, ##__VA_ARGS__) \ : __BPF_ARG1_TP((u32)arg2, ##__VA_ARGS__))) #define __BPF_ARG3_TP(...) \ ((mod[2] == 2 || (mod[2] == 1 && __BITS_PER_LONG == 64)) \ ? __BPF_ARG2_TP(arg3, ##__VA_ARGS__) \ : ((mod[2] == 1 || (mod[2] == 0 && __BITS_PER_LONG == 32)) \ ? __BPF_ARG2_TP((long)arg3, ##__VA_ARGS__) \ : __BPF_ARG2_TP((u32)arg3, ##__VA_ARGS__))) return __BPF_TP_EMIT(); } static const struct bpf_func_proto bpf_trace_printk_proto = { .func = bpf_trace_printk, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_MEM, .arg2_type = ARG_CONST_SIZE, }; const struct bpf_func_proto *bpf_get_trace_printk_proto(void) { /* * this program might be calling bpf_trace_printk, * so allocate per-cpu printk buffers */ trace_printk_init_buffers(); return &bpf_trace_printk_proto; } BPF_CALL_2(bpf_perf_event_read, struct bpf_map *, map, u64, flags) { struct bpf_array *array = container_of(map, struct bpf_array, map); unsigned int cpu = smp_processor_id(); u64 index = flags & BPF_F_INDEX_MASK; struct bpf_event_entry *ee; u64 value = 0; int err; if (unlikely(flags & ~(BPF_F_INDEX_MASK))) return -EINVAL; if (index == BPF_F_CURRENT_CPU) index = cpu; if (unlikely(index >= array->map.max_entries)) return -E2BIG; ee = READ_ONCE(array->ptrs[index]); if (!ee) return -ENOENT; err = perf_event_read_local(ee->event, &value); /* * this api is ugly since we miss [-22..-2] range of valid * counter values, but that's uapi */ if (err) return err; return value; } static const struct bpf_func_proto bpf_perf_event_read_proto = { .func = bpf_perf_event_read, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_ANYTHING, }; static DEFINE_PER_CPU(struct perf_sample_data, bpf_trace_sd); static __always_inline u64 __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map, u64 flags, struct perf_sample_data *sd) { struct bpf_array *array = container_of(map, struct bpf_array, map); unsigned int cpu = smp_processor_id(); u64 index = flags & BPF_F_INDEX_MASK; struct bpf_event_entry *ee; struct perf_event *event; if (index == BPF_F_CURRENT_CPU) index = cpu; if (unlikely(index >= array->map.max_entries)) return -E2BIG; ee = READ_ONCE(array->ptrs[index]); if (!ee) return -ENOENT; event = ee->event; if (unlikely(event->attr.type != PERF_TYPE_SOFTWARE || event->attr.config != PERF_COUNT_SW_BPF_OUTPUT)) return -EINVAL; if (unlikely(event->oncpu != cpu)) return -EOPNOTSUPP; perf_event_output(event, sd, regs); return 0; } BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map, u64, flags, void *, data, u64, size) { struct perf_sample_data *sd = this_cpu_ptr(&bpf_trace_sd); struct perf_raw_record raw = { .frag = { .size = size, .data = data, }, }; if (unlikely(flags & ~(BPF_F_INDEX_MASK))) return -EINVAL; perf_sample_data_init(sd, 0, 0); sd->raw = &raw; return __bpf_perf_event_output(regs, map, flags, sd); } static const struct bpf_func_proto bpf_perf_event_output_proto = { .func = bpf_perf_event_output, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM, .arg5_type = ARG_CONST_SIZE, }; static DEFINE_PER_CPU(struct pt_regs, bpf_pt_regs); static DEFINE_PER_CPU(struct perf_sample_data, bpf_misc_sd); u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy) { struct perf_sample_data *sd = this_cpu_ptr(&bpf_misc_sd); struct pt_regs *regs = this_cpu_ptr(&bpf_pt_regs); struct perf_raw_frag frag = { .copy = ctx_copy, .size = ctx_size, .data = ctx, }; struct perf_raw_record raw = { .frag = { { .next = ctx_size ? &frag : NULL, }, .size = meta_size, .data = meta, }, }; perf_fetch_caller_regs(regs); perf_sample_data_init(sd, 0, 0); sd->raw = &raw; return __bpf_perf_event_output(regs, map, flags, sd); } BPF_CALL_0(bpf_get_current_task) { return (long) current; } static const struct bpf_func_proto bpf_get_current_task_proto = { .func = bpf_get_current_task, .gpl_only = true, .ret_type = RET_INTEGER, }; BPF_CALL_2(bpf_current_task_under_cgroup, struct bpf_map *, map, u32, idx) { struct bpf_array *array = container_of(map, struct bpf_array, map); struct cgroup *cgrp; if (unlikely(in_interrupt())) return -EINVAL; if (unlikely(idx >= array->map.max_entries)) return -E2BIG; cgrp = READ_ONCE(array->ptrs[idx]); if (unlikely(!cgrp)) return -EAGAIN; return task_under_cgroup_hierarchy(current, cgrp); } static const struct bpf_func_proto bpf_current_task_under_cgroup_proto = { .func = bpf_current_task_under_cgroup, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_probe_read_str, void *, dst, u32, size, const void *, unsafe_ptr) { int ret; /* * The strncpy_from_unsafe() call will likely not fill the entire * buffer, but that's okay in this circumstance as we're probing * arbitrary memory anyway similar to bpf_probe_read() and might * as well probe the stack. Thus, memory is explicitly cleared * only in error case, so that improper users ignoring return * code altogether don't copy garbage; otherwise length of string * is returned that can be used for bpf_perf_event_output() et al. */ ret = strncpy_from_unsafe(dst, unsafe_ptr, size); if (unlikely(ret < 0)) memset(dst, 0, size); return ret; } static const struct bpf_func_proto bpf_probe_read_str_proto = { .func = bpf_probe_read_str, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE, .arg3_type = ARG_ANYTHING, }; static const struct bpf_func_proto *tracing_func_proto(enum bpf_func_id func_id) { switch (func_id) { case BPF_FUNC_map_lookup_elem: return &bpf_map_lookup_elem_proto; case BPF_FUNC_map_update_elem: return &bpf_map_update_elem_proto; case BPF_FUNC_map_delete_elem: return &bpf_map_delete_elem_proto; case BPF_FUNC_probe_read: return &bpf_probe_read_proto; case BPF_FUNC_ktime_get_ns: return &bpf_ktime_get_ns_proto; case BPF_FUNC_tail_call: return &bpf_tail_call_proto; case BPF_FUNC_get_current_pid_tgid: return &bpf_get_current_pid_tgid_proto; case BPF_FUNC_get_current_task: return &bpf_get_current_task_proto; case BPF_FUNC_get_current_uid_gid: return &bpf_get_current_uid_gid_proto; case BPF_FUNC_get_current_comm: return &bpf_get_current_comm_proto; case BPF_FUNC_trace_printk: return bpf_get_trace_printk_proto(); case BPF_FUNC_get_smp_processor_id: return &bpf_get_smp_processor_id_proto; case BPF_FUNC_get_numa_node_id: return &bpf_get_numa_node_id_proto; case BPF_FUNC_perf_event_read: return &bpf_perf_event_read_proto; case BPF_FUNC_probe_write_user: return bpf_get_probe_write_proto(); case BPF_FUNC_current_task_under_cgroup: return &bpf_current_task_under_cgroup_proto; case BPF_FUNC_get_prandom_u32: return &bpf_get_prandom_u32_proto; case BPF_FUNC_probe_read_str: return &bpf_probe_read_str_proto; default: return NULL; } } static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func_id) { switch (func_id) { case BPF_FUNC_perf_event_output: return &bpf_perf_event_output_proto; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto; default: return tracing_func_proto(func_id); } } /* bpf+kprobe programs can access fields of 'struct pt_regs' */ static bool kprobe_prog_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { if (off < 0 || off >= sizeof(struct pt_regs)) return false; if (type != BPF_READ) return false; if (off % size != 0) return false; /* * Assertion for 32 bit to make sure last 8 byte access * (BPF_DW) to the last 4 byte member is disallowed. */ if (off + size > sizeof(struct pt_regs)) return false; return true; } const struct bpf_verifier_ops kprobe_prog_ops = { .get_func_proto = kprobe_prog_func_proto, .is_valid_access = kprobe_prog_is_valid_access, }; BPF_CALL_5(bpf_perf_event_output_tp, void *, tp_buff, struct bpf_map *, map, u64, flags, void *, data, u64, size) { struct pt_regs *regs = *(struct pt_regs **)tp_buff; /* * r1 points to perf tracepoint buffer where first 8 bytes are hidden * from bpf program and contain a pointer to 'struct pt_regs'. Fetch it * from there and call the same bpf_perf_event_output() helper inline. */ return ____bpf_perf_event_output(regs, map, flags, data, size); } static const struct bpf_func_proto bpf_perf_event_output_proto_tp = { .func = bpf_perf_event_output_tp, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM, .arg5_type = ARG_CONST_SIZE, }; BPF_CALL_3(bpf_get_stackid_tp, void *, tp_buff, struct bpf_map *, map, u64, flags) { struct pt_regs *regs = *(struct pt_regs **)tp_buff; /* * Same comment as in bpf_perf_event_output_tp(), only that this time * the other helper's function body cannot be inlined due to being * external, thus we need to call raw helper function. */ return bpf_get_stackid((unsigned long) regs, (unsigned long) map, flags, 0, 0); } static const struct bpf_func_proto bpf_get_stackid_proto_tp = { .func = bpf_get_stackid_tp, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, }; static const struct bpf_func_proto *tp_prog_func_proto(enum bpf_func_id func_id) { switch (func_id) { case BPF_FUNC_perf_event_output: return &bpf_perf_event_output_proto_tp; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto_tp; default: return tracing_func_proto(func_id); } } static bool tp_prog_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { if (off < sizeof(void *) || off >= PERF_MAX_TRACE_SIZE) return false; if (type != BPF_READ) return false; if (off % size != 0) return false; BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(__u64)); return true; } const struct bpf_verifier_ops tracepoint_prog_ops = { .get_func_proto = tp_prog_func_proto, .is_valid_access = tp_prog_is_valid_access, }; static bool pe_prog_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { const int size_sp = FIELD_SIZEOF(struct bpf_perf_event_data, sample_period); if (off < 0 || off >= sizeof(struct bpf_perf_event_data)) return false; if (type != BPF_READ) return false; if (off % size != 0) return false; switch (off) { case bpf_ctx_range(struct bpf_perf_event_data, sample_period): bpf_ctx_record_field_size(info, size_sp); if (!bpf_ctx_narrow_access_ok(off, size, size_sp)) return false; break; default: if (size != sizeof(long)) return false; } return true; } static u32 pe_prog_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct bpf_perf_event_data, sample_period): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_perf_event_data_kern, data), si->dst_reg, si->src_reg, offsetof(struct bpf_perf_event_data_kern, data)); *insn++ = BPF_LDX_MEM(BPF_DW, si->dst_reg, si->dst_reg, bpf_target_off(struct perf_sample_data, period, 8, target_size)); break; default: *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_perf_event_data_kern, regs), si->dst_reg, si->src_reg, offsetof(struct bpf_perf_event_data_kern, regs)); *insn++ = BPF_LDX_MEM(BPF_SIZEOF(long), si->dst_reg, si->dst_reg, si->off); break; } return insn - insn_buf; } const struct bpf_verifier_ops perf_event_prog_ops = { .get_func_proto = tp_prog_func_proto, .is_valid_access = pe_prog_is_valid_access, .convert_ctx_access = pe_prog_convert_ctx_access, }; |
| 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 | /* iptables module to match on related connections */ /* * (C) 2001 Martin Josefsson <gandalf@wlug.westbo.se> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <linux/netfilter.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/nf_conntrack_helper.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_helper.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Martin Josefsson <gandalf@netfilter.org>"); MODULE_DESCRIPTION("Xtables: Related connection matching"); MODULE_ALIAS("ipt_helper"); MODULE_ALIAS("ip6t_helper"); static bool helper_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_helper_info *info = par->matchinfo; const struct nf_conn *ct; const struct nf_conn_help *master_help; const struct nf_conntrack_helper *helper; enum ip_conntrack_info ctinfo; bool ret = info->invert; ct = nf_ct_get(skb, &ctinfo); if (!ct || !ct->master) return ret; master_help = nfct_help(ct->master); if (!master_help) return ret; /* rcu_read_lock()ed by nf_hook_thresh */ helper = rcu_dereference(master_help->helper); if (!helper) return ret; if (info->name[0] == '\0') ret = !ret; else ret ^= !strncmp(helper->name, info->name, strlen(helper->name)); return ret; } static int helper_mt_check(const struct xt_mtchk_param *par) { struct xt_helper_info *info = par->matchinfo; int ret; ret = nf_ct_netns_get(par->net, par->family); if (ret < 0) { pr_info("cannot load conntrack support for proto=%u\n", par->family); return ret; } info->name[sizeof(info->name) - 1] = '\0'; return 0; } static void helper_mt_destroy(const struct xt_mtdtor_param *par) { nf_ct_netns_put(par->net, par->family); } static struct xt_match helper_mt_reg __read_mostly = { .name = "helper", .revision = 0, .family = NFPROTO_UNSPEC, .checkentry = helper_mt_check, .match = helper_mt, .destroy = helper_mt_destroy, .matchsize = sizeof(struct xt_helper_info), .me = THIS_MODULE, }; static int __init helper_mt_init(void) { return xt_register_match(&helper_mt_reg); } static void __exit helper_mt_exit(void) { xt_unregister_match(&helper_mt_reg); } module_init(helper_mt_init); module_exit(helper_mt_exit); |
| 8 8 8 9 8 7 8 8 8 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 | /* * IP Payload Compression Protocol (IPComp) - RFC3173. * * Copyright (c) 2003 James Morris <jmorris@intercode.com.au> * Copyright (c) 2003-2008 Herbert Xu <herbert@gondor.apana.org.au> * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the Free * Software Foundation; either version 2 of the License, or (at your option) * any later version. * * Todo: * - Tunable compression parameters. * - Compression stats. * - Adaptive compression. */ #include <linux/crypto.h> #include <linux/err.h> #include <linux/list.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/percpu.h> #include <linux/slab.h> #include <linux/smp.h> #include <linux/vmalloc.h> #include <net/ip.h> #include <net/ipcomp.h> #include <net/xfrm.h> struct ipcomp_tfms { struct list_head list; struct crypto_comp * __percpu *tfms; int users; }; static DEFINE_MUTEX(ipcomp_resource_mutex); static void * __percpu *ipcomp_scratches; static int ipcomp_scratch_users; static LIST_HEAD(ipcomp_tfms_list); static int ipcomp_decompress(struct xfrm_state *x, struct sk_buff *skb) { struct ipcomp_data *ipcd = x->data; const int plen = skb->len; int dlen = IPCOMP_SCRATCH_SIZE; const u8 *start = skb->data; const int cpu = get_cpu(); u8 *scratch = *per_cpu_ptr(ipcomp_scratches, cpu); struct crypto_comp *tfm = *per_cpu_ptr(ipcd->tfms, cpu); int err = crypto_comp_decompress(tfm, start, plen, scratch, &dlen); int len; if (err) goto out; if (dlen < (plen + sizeof(struct ip_comp_hdr))) { err = -EINVAL; goto out; } len = dlen - plen; if (len > skb_tailroom(skb)) len = skb_tailroom(skb); __skb_put(skb, len); len += plen; skb_copy_to_linear_data(skb, scratch, len); while ((scratch += len, dlen -= len) > 0) { skb_frag_t *frag; struct page *page; err = -EMSGSIZE; if (WARN_ON(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS)) goto out; frag = skb_shinfo(skb)->frags + skb_shinfo(skb)->nr_frags; page = alloc_page(GFP_ATOMIC); err = -ENOMEM; if (!page) goto out; __skb_frag_set_page(frag, page); len = PAGE_SIZE; if (dlen < len) len = dlen; frag->page_offset = 0; skb_frag_size_set(frag, len); memcpy(skb_frag_address(frag), scratch, len); skb->truesize += len; skb->data_len += len; skb->len += len; skb_shinfo(skb)->nr_frags++; } err = 0; out: put_cpu(); return err; } int ipcomp_input(struct xfrm_state *x, struct sk_buff *skb) { int nexthdr; int err = -ENOMEM; struct ip_comp_hdr *ipch; if (skb_linearize_cow(skb)) goto out; skb->ip_summed = CHECKSUM_NONE; /* Remove ipcomp header and decompress original payload */ ipch = (void *)skb->data; nexthdr = ipch->nexthdr; skb->transport_header = skb->network_header + sizeof(*ipch); __skb_pull(skb, sizeof(*ipch)); err = ipcomp_decompress(x, skb); if (err) goto out; err = nexthdr; out: return err; } EXPORT_SYMBOL_GPL(ipcomp_input); static int ipcomp_compress(struct xfrm_state *x, struct sk_buff *skb) { struct ipcomp_data *ipcd = x->data; const int plen = skb->len; int dlen = IPCOMP_SCRATCH_SIZE; u8 *start = skb->data; struct crypto_comp *tfm; u8 *scratch; int err; local_bh_disable(); scratch = *this_cpu_ptr(ipcomp_scratches); tfm = *this_cpu_ptr(ipcd->tfms); err = crypto_comp_compress(tfm, start, plen, scratch, &dlen); if (err) goto out; if ((dlen + sizeof(struct ip_comp_hdr)) >= plen) { err = -EMSGSIZE; goto out; } memcpy(start + sizeof(struct ip_comp_hdr), scratch, dlen); local_bh_enable(); pskb_trim(skb, dlen + sizeof(struct ip_comp_hdr)); return 0; out: local_bh_enable(); return err; } int ipcomp_output(struct xfrm_state *x, struct sk_buff *skb) { int err; struct ip_comp_hdr *ipch; struct ipcomp_data *ipcd = x->data; if (skb->len < ipcd->threshold) { /* Don't bother compressing */ goto out_ok; } if (skb_linearize_cow(skb)) goto out_ok; err = ipcomp_compress(x, skb); if (err) { goto out_ok; } /* Install ipcomp header, convert into ipcomp datagram. */ ipch = ip_comp_hdr(skb); ipch->nexthdr = *skb_mac_header(skb); ipch->flags = 0; ipch->cpi = htons((u16 )ntohl(x->id.spi)); *skb_mac_header(skb) = IPPROTO_COMP; out_ok: skb_push(skb, -skb_network_offset(skb)); return 0; } EXPORT_SYMBOL_GPL(ipcomp_output); static void ipcomp_free_scratches(void) { int i; void * __percpu *scratches; if (--ipcomp_scratch_users) return; scratches = ipcomp_scratches; if (!scratches) return; for_each_possible_cpu(i) vfree(*per_cpu_ptr(scratches, i)); free_percpu(scratches); ipcomp_scratches = NULL; } static void * __percpu *ipcomp_alloc_scratches(void) { void * __percpu *scratches; int i; if (ipcomp_scratch_users++) return ipcomp_scratches; scratches = alloc_percpu(void *); if (!scratches) return NULL; ipcomp_scratches = scratches; for_each_possible_cpu(i) { void *scratch; scratch = vmalloc_node(IPCOMP_SCRATCH_SIZE, cpu_to_node(i)); if (!scratch) return NULL; *per_cpu_ptr(scratches, i) = scratch; } return scratches; } static void ipcomp_free_tfms(struct crypto_comp * __percpu *tfms) { struct ipcomp_tfms *pos; int cpu; list_for_each_entry(pos, &ipcomp_tfms_list, list) { if (pos->tfms == tfms) break; } WARN_ON(!pos); if (--pos->users) return; list_del(&pos->list); kfree(pos); if (!tfms) return; for_each_possible_cpu(cpu) { struct crypto_comp *tfm = *per_cpu_ptr(tfms, cpu); crypto_free_comp(tfm); } free_percpu(tfms); } static struct crypto_comp * __percpu *ipcomp_alloc_tfms(const char *alg_name) { struct ipcomp_tfms *pos; struct crypto_comp * __percpu *tfms; int cpu; list_for_each_entry(pos, &ipcomp_tfms_list, list) { struct crypto_comp *tfm; /* This can be any valid CPU ID so we don't need locking. */ tfm = this_cpu_read(*pos->tfms); if (!strcmp(crypto_comp_name(tfm), alg_name)) { pos->users++; return pos->tfms; } } pos = kmalloc(sizeof(*pos), GFP_KERNEL); if (!pos) return NULL; pos->users = 1; INIT_LIST_HEAD(&pos->list); list_add(&pos->list, &ipcomp_tfms_list); pos->tfms = tfms = alloc_percpu(struct crypto_comp *); if (!tfms) goto error; for_each_possible_cpu(cpu) { struct crypto_comp *tfm = crypto_alloc_comp(alg_name, 0, CRYPTO_ALG_ASYNC); if (IS_ERR(tfm)) goto error; *per_cpu_ptr(tfms, cpu) = tfm; } return tfms; error: ipcomp_free_tfms(tfms); return NULL; } static void ipcomp_free_data(struct ipcomp_data *ipcd) { if (ipcd->tfms) ipcomp_free_tfms(ipcd->tfms); ipcomp_free_scratches(); } void ipcomp_destroy(struct xfrm_state *x) { struct ipcomp_data *ipcd = x->data; if (!ipcd) return; xfrm_state_delete_tunnel(x); mutex_lock(&ipcomp_resource_mutex); ipcomp_free_data(ipcd); mutex_unlock(&ipcomp_resource_mutex); kfree(ipcd); } EXPORT_SYMBOL_GPL(ipcomp_destroy); int ipcomp_init_state(struct xfrm_state *x) { int err; struct ipcomp_data *ipcd; struct xfrm_algo_desc *calg_desc; err = -EINVAL; if (!x->calg) goto out; if (x->encap) goto out; err = -ENOMEM; ipcd = kzalloc(sizeof(*ipcd), GFP_KERNEL); if (!ipcd) goto out; mutex_lock(&ipcomp_resource_mutex); if (!ipcomp_alloc_scratches()) goto error; ipcd->tfms = ipcomp_alloc_tfms(x->calg->alg_name); if (!ipcd->tfms) goto error; mutex_unlock(&ipcomp_resource_mutex); calg_desc = xfrm_calg_get_byname(x->calg->alg_name, 0); BUG_ON(!calg_desc); ipcd->threshold = calg_desc->uinfo.comp.threshold; x->data = ipcd; err = 0; out: return err; error: ipcomp_free_data(ipcd); mutex_unlock(&ipcomp_resource_mutex); kfree(ipcd); goto out; } EXPORT_SYMBOL_GPL(ipcomp_init_state); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("IP Payload Compression Protocol (IPComp) - RFC3173"); MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>"); |
| 1 2 2 2 2 2 1 1 2 2 1 1 2 3 3 2 3 13 13 11 10 9 9 5 4 2 2 4 2 12 4 4 4 4 4 4 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 | /* * net/sched/sch_choke.c CHOKE scheduler * * Copyright (c) 2011 Stephen Hemminger <shemminger@vyatta.com> * Copyright (c) 2011 Eric Dumazet <eric.dumazet@gmail.com> * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * version 2 as published by the Free Software Foundation. * */ #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/vmalloc.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <net/inet_ecn.h> #include <net/red.h> #include <net/flow_dissector.h> /* CHOKe stateless AQM for fair bandwidth allocation ================================================= CHOKe (CHOose and Keep for responsive flows, CHOose and Kill for unresponsive flows) is a variant of RED that penalizes misbehaving flows but maintains no flow state. The difference from RED is an additional step during the enqueuing process. If average queue size is over the low threshold (qmin), a packet is chosen at random from the queue. If both the new and chosen packet are from the same flow, both are dropped. Unlike RED, CHOKe is not really a "classful" qdisc because it needs to access packets in queue randomly. It has a minimal class interface to allow overriding the builtin flow classifier with filters. Source: R. Pan, B. Prabhakar, and K. Psounis, "CHOKe, A Stateless Active Queue Management Scheme for Approximating Fair Bandwidth Allocation", IEEE INFOCOM, 2000. A. Tang, J. Wang, S. Low, "Understanding CHOKe: Throughput and Spatial Characteristics", IEEE/ACM Transactions on Networking, 2004 */ /* Upper bound on size of sk_buff table (packets) */ #define CHOKE_MAX_QUEUE (128*1024 - 1) struct choke_sched_data { /* Parameters */ u32 limit; unsigned char flags; struct red_parms parms; /* Variables */ struct red_vars vars; struct { u32 prob_drop; /* Early probability drops */ u32 prob_mark; /* Early probability marks */ u32 forced_drop; /* Forced drops, qavg > max_thresh */ u32 forced_mark; /* Forced marks, qavg > max_thresh */ u32 pdrop; /* Drops due to queue limits */ u32 other; /* Drops due to drop() calls */ u32 matched; /* Drops to flow match */ } stats; unsigned int head; unsigned int tail; unsigned int tab_mask; /* size - 1 */ struct sk_buff **tab; }; /* number of elements in queue including holes */ static unsigned int choke_len(const struct choke_sched_data *q) { return (q->tail - q->head) & q->tab_mask; } /* Is ECN parameter configured */ static int use_ecn(const struct choke_sched_data *q) { return q->flags & TC_RED_ECN; } /* Should packets over max just be dropped (versus marked) */ static int use_harddrop(const struct choke_sched_data *q) { return q->flags & TC_RED_HARDDROP; } /* Move head pointer forward to skip over holes */ static void choke_zap_head_holes(struct choke_sched_data *q) { do { q->head = (q->head + 1) & q->tab_mask; if (q->head == q->tail) break; } while (q->tab[q->head] == NULL); } /* Move tail pointer backwards to reuse holes */ static void choke_zap_tail_holes(struct choke_sched_data *q) { do { q->tail = (q->tail - 1) & q->tab_mask; if (q->head == q->tail) break; } while (q->tab[q->tail] == NULL); } /* Drop packet from queue array by creating a "hole" */ static void choke_drop_by_idx(struct Qdisc *sch, unsigned int idx, struct sk_buff **to_free) { struct choke_sched_data *q = qdisc_priv(sch); struct sk_buff *skb = q->tab[idx]; q->tab[idx] = NULL; if (idx == q->head) choke_zap_head_holes(q); if (idx == q->tail) choke_zap_tail_holes(q); qdisc_qstats_backlog_dec(sch, skb); qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb)); qdisc_drop(skb, sch, to_free); --sch->q.qlen; } struct choke_skb_cb { u16 classid; u8 keys_valid; struct flow_keys_digest keys; }; static inline struct choke_skb_cb *choke_skb_cb(const struct sk_buff *skb) { qdisc_cb_private_validate(skb, sizeof(struct choke_skb_cb)); return (struct choke_skb_cb *)qdisc_skb_cb(skb)->data; } static inline void choke_set_classid(struct sk_buff *skb, u16 classid) { choke_skb_cb(skb)->classid = classid; } /* * Compare flow of two packets * Returns true only if source and destination address and port match. * false for special cases */ static bool choke_match_flow(struct sk_buff *skb1, struct sk_buff *skb2) { struct flow_keys temp; if (skb1->protocol != skb2->protocol) return false; if (!choke_skb_cb(skb1)->keys_valid) { choke_skb_cb(skb1)->keys_valid = 1; skb_flow_dissect_flow_keys(skb1, &temp, 0); make_flow_keys_digest(&choke_skb_cb(skb1)->keys, &temp); } if (!choke_skb_cb(skb2)->keys_valid) { choke_skb_cb(skb2)->keys_valid = 1; skb_flow_dissect_flow_keys(skb2, &temp, 0); make_flow_keys_digest(&choke_skb_cb(skb2)->keys, &temp); } return !memcmp(&choke_skb_cb(skb1)->keys, &choke_skb_cb(skb2)->keys, sizeof(choke_skb_cb(skb1)->keys)); } /* * Select a packet at random from queue * HACK: since queue can have holes from previous deletion; retry several * times to find a random skb but then just give up and return the head * Will return NULL if queue is empty (q->head == q->tail) */ static struct sk_buff *choke_peek_random(const struct choke_sched_data *q, unsigned int *pidx) { struct sk_buff *skb; int retrys = 3; do { *pidx = (q->head + prandom_u32_max(choke_len(q))) & q->tab_mask; skb = q->tab[*pidx]; if (skb) return skb; } while (--retrys > 0); return q->tab[*pidx = q->head]; } /* * Compare new packet with random packet in queue * returns true if matched and sets *pidx */ static bool choke_match_random(const struct choke_sched_data *q, struct sk_buff *nskb, unsigned int *pidx) { struct sk_buff *oskb; if (q->head == q->tail) return false; oskb = choke_peek_random(q, pidx); return choke_match_flow(oskb, nskb); } static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { struct choke_sched_data *q = qdisc_priv(sch); const struct red_parms *p = &q->parms; choke_skb_cb(skb)->keys_valid = 0; /* Compute average queue usage (see RED) */ q->vars.qavg = red_calc_qavg(p, &q->vars, sch->q.qlen); if (red_is_idling(&q->vars)) red_end_of_idle_period(&q->vars); /* Is queue small? */ if (q->vars.qavg <= p->qth_min) q->vars.qcount = -1; else { unsigned int idx; /* Draw a packet at random from queue and compare flow */ if (choke_match_random(q, skb, &idx)) { q->stats.matched++; choke_drop_by_idx(sch, idx, to_free); goto congestion_drop; } /* Queue is large, always mark/drop */ if (q->vars.qavg > p->qth_max) { q->vars.qcount = -1; qdisc_qstats_overlimit(sch); if (use_harddrop(q) || !use_ecn(q) || !INET_ECN_set_ce(skb)) { q->stats.forced_drop++; goto congestion_drop; } q->stats.forced_mark++; } else if (++q->vars.qcount) { if (red_mark_probability(p, &q->vars, q->vars.qavg)) { q->vars.qcount = 0; q->vars.qR = red_random(p); qdisc_qstats_overlimit(sch); if (!use_ecn(q) || !INET_ECN_set_ce(skb)) { q->stats.prob_drop++; goto congestion_drop; } q->stats.prob_mark++; } } else q->vars.qR = red_random(p); } /* Admit new packet */ if (sch->q.qlen < q->limit) { q->tab[q->tail] = skb; q->tail = (q->tail + 1) & q->tab_mask; ++sch->q.qlen; qdisc_qstats_backlog_inc(sch, skb); return NET_XMIT_SUCCESS; } q->stats.pdrop++; return qdisc_drop(skb, sch, to_free); congestion_drop: qdisc_drop(skb, sch, to_free); return NET_XMIT_CN; } static struct sk_buff *choke_dequeue(struct Qdisc *sch) { struct choke_sched_data *q = qdisc_priv(sch); struct sk_buff *skb; if (q->head == q->tail) { if (!red_is_idling(&q->vars)) red_start_of_idle_period(&q->vars); return NULL; } skb = q->tab[q->head]; q->tab[q->head] = NULL; choke_zap_head_holes(q); --sch->q.qlen; qdisc_qstats_backlog_dec(sch, skb); qdisc_bstats_update(sch, skb); return skb; } static void choke_reset(struct Qdisc *sch) { struct choke_sched_data *q = qdisc_priv(sch); while (q->head != q->tail) { struct sk_buff *skb = q->tab[q->head]; q->head = (q->head + 1) & q->tab_mask; if (!skb) continue; rtnl_qdisc_drop(skb, sch); } sch->q.qlen = 0; sch->qstats.backlog = 0; if (q->tab) memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *)); q->head = q->tail = 0; red_restart(&q->vars); } static const struct nla_policy choke_policy[TCA_CHOKE_MAX + 1] = { [TCA_CHOKE_PARMS] = { .len = sizeof(struct tc_red_qopt) }, [TCA_CHOKE_STAB] = { .len = RED_STAB_SIZE }, [TCA_CHOKE_MAX_P] = { .type = NLA_U32 }, }; static void choke_free(void *addr) { kvfree(addr); } static int choke_change(struct Qdisc *sch, struct nlattr *opt) { struct choke_sched_data *q = qdisc_priv(sch); struct nlattr *tb[TCA_CHOKE_MAX + 1]; const struct tc_red_qopt *ctl; int err; struct sk_buff **old = NULL; unsigned int mask; u32 max_P; u8 *stab; if (opt == NULL) return -EINVAL; err = nla_parse_nested(tb, TCA_CHOKE_MAX, opt, choke_policy, NULL); if (err < 0) return err; if (tb[TCA_CHOKE_PARMS] == NULL || tb[TCA_CHOKE_STAB] == NULL) return -EINVAL; max_P = tb[TCA_CHOKE_MAX_P] ? nla_get_u32(tb[TCA_CHOKE_MAX_P]) : 0; ctl = nla_data(tb[TCA_CHOKE_PARMS]); stab = nla_data(tb[TCA_CHOKE_STAB]); if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log, stab)) return -EINVAL; if (ctl->limit > CHOKE_MAX_QUEUE) return -EINVAL; mask = roundup_pow_of_two(ctl->limit + 1) - 1; if (mask != q->tab_mask) { struct sk_buff **ntab; ntab = kvmalloc_array((mask + 1), sizeof(struct sk_buff *), GFP_KERNEL | __GFP_ZERO); if (!ntab) return -ENOMEM; sch_tree_lock(sch); old = q->tab; if (old) { unsigned int oqlen = sch->q.qlen, tail = 0; unsigned dropped = 0; while (q->head != q->tail) { struct sk_buff *skb = q->tab[q->head]; q->head = (q->head + 1) & q->tab_mask; if (!skb) continue; if (tail < mask) { ntab[tail++] = skb; continue; } dropped += qdisc_pkt_len(skb); qdisc_qstats_backlog_dec(sch, skb); --sch->q.qlen; rtnl_qdisc_drop(skb, sch); } qdisc_tree_reduce_backlog(sch, oqlen - sch->q.qlen, dropped); q->head = 0; q->tail = tail; } q->tab_mask = mask; q->tab = ntab; } else sch_tree_lock(sch); q->flags = ctl->flags; q->limit = ctl->limit; red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Plog, ctl->Scell_log, stab, max_P); red_set_vars(&q->vars); if (q->head == q->tail) red_end_of_idle_period(&q->vars); sch_tree_unlock(sch); choke_free(old); return 0; } static int choke_init(struct Qdisc *sch, struct nlattr *opt) { return choke_change(sch, opt); } static int choke_dump(struct Qdisc *sch, struct sk_buff *skb) { struct choke_sched_data *q = qdisc_priv(sch); struct nlattr *opts = NULL; struct tc_red_qopt opt = { .limit = q->limit, .flags = q->flags, .qth_min = q->parms.qth_min >> q->parms.Wlog, .qth_max = q->parms.qth_max >> q->parms.Wlog, .Wlog = q->parms.Wlog, .Plog = q->parms.Plog, .Scell_log = q->parms.Scell_log, }; opts = nla_nest_start(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; if (nla_put(skb, TCA_CHOKE_PARMS, sizeof(opt), &opt) || nla_put_u32(skb, TCA_CHOKE_MAX_P, q->parms.max_P)) goto nla_put_failure; return nla_nest_end(skb, opts); nla_put_failure: nla_nest_cancel(skb, opts); return -EMSGSIZE; } static int choke_dump_stats(struct Qdisc *sch, struct gnet_dump *d) { struct choke_sched_data *q = qdisc_priv(sch); struct tc_choke_xstats st = { .early = q->stats.prob_drop + q->stats.forced_drop, .marked = q->stats.prob_mark + q->stats.forced_mark, .pdrop = q->stats.pdrop, .other = q->stats.other, .matched = q->stats.matched, }; return gnet_stats_copy_app(d, &st, sizeof(st)); } static void choke_destroy(struct Qdisc *sch) { struct choke_sched_data *q = qdisc_priv(sch); choke_free(q->tab); } static struct sk_buff *choke_peek_head(struct Qdisc *sch) { struct choke_sched_data *q = qdisc_priv(sch); return (q->head != q->tail) ? q->tab[q->head] : NULL; } static struct Qdisc_ops choke_qdisc_ops __read_mostly = { .id = "choke", .priv_size = sizeof(struct choke_sched_data), .enqueue = choke_enqueue, .dequeue = choke_dequeue, .peek = choke_peek_head, .init = choke_init, .destroy = choke_destroy, .reset = choke_reset, .change = choke_change, .dump = choke_dump, .dump_stats = choke_dump_stats, .owner = THIS_MODULE, }; static int __init choke_module_init(void) { return register_qdisc(&choke_qdisc_ops); } static void __exit choke_module_exit(void) { unregister_qdisc(&choke_qdisc_ops); } module_init(choke_module_init) module_exit(choke_module_exit) MODULE_LICENSE("GPL"); |
| 165 141 193 33 135 33 149 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 | /* * Copyright (C) 2007 Oracle. All rights reserved. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public * License v2 as published by the Free Software Foundation. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * General Public License for more details. * * You should have received a copy of the GNU General Public * License along with this program; if not, write to the * Free Software Foundation, Inc., 59 Temple Place - Suite 330, * Boston, MA 021110-1307, USA. */ #ifndef __BTRFS_I__ #define __BTRFS_I__ #include <linux/hash.h> #include "extent_map.h" #include "extent_io.h" #include "ordered-data.h" #include "delayed-inode.h" /* * ordered_data_close is set by truncate when a file that used * to have good data has been truncated to zero. When it is set * the btrfs file release call will add this inode to the * ordered operations list so that we make sure to flush out any * new data the application may have written before commit. */ #define BTRFS_INODE_ORDERED_DATA_CLOSE 0 #define BTRFS_INODE_ORPHAN_META_RESERVED 1 #define BTRFS_INODE_DUMMY 2 #define BTRFS_INODE_IN_DEFRAG 3 #define BTRFS_INODE_DELALLOC_META_RESERVED 4 #define BTRFS_INODE_HAS_ORPHAN_ITEM 5 #define BTRFS_INODE_HAS_ASYNC_EXTENT 6 #define BTRFS_INODE_NEEDS_FULL_SYNC 7 #define BTRFS_INODE_COPY_EVERYTHING 8 #define BTRFS_INODE_IN_DELALLOC_LIST 9 #define BTRFS_INODE_READDIO_NEED_LOCK 10 #define BTRFS_INODE_HAS_PROPS 11 /* in memory btrfs inode */ struct btrfs_inode { /* which subvolume this inode belongs to */ struct btrfs_root *root; /* key used to find this inode on disk. This is used by the code * to read in roots of subvolumes */ struct btrfs_key location; /* * Lock for counters and all fields used to determine if the inode is in * the log or not (last_trans, last_sub_trans, last_log_commit, * logged_trans). */ spinlock_t lock; /* the extent_tree has caches of all the extent mappings to disk */ struct extent_map_tree extent_tree; /* the io_tree does range state (DIRTY, LOCKED etc) */ struct extent_io_tree io_tree; /* special utility tree used to record which mirrors have already been * tried when checksums fail for a given block */ struct extent_io_tree io_failure_tree; /* held while logging the inode in tree-log.c */ struct mutex log_mutex; /* held while doing delalloc reservations */ struct mutex delalloc_mutex; /* used to order data wrt metadata */ struct btrfs_ordered_inode_tree ordered_tree; /* list of all the delalloc inodes in the FS. There are times we need * to write all the delalloc pages to disk, and this list is used * to walk them all. */ struct list_head delalloc_inodes; /* node for the red-black tree that links inodes in subvolume root */ struct rb_node rb_node; unsigned long runtime_flags; /* Keep track of who's O_SYNC/fsyncing currently */ atomic_t sync_writers; /* full 64 bit generation number, struct vfs_inode doesn't have a big * enough field for this. */ u64 generation; /* * transid of the trans_handle that last modified this inode */ u64 last_trans; /* * transid that last logged this inode */ u64 logged_trans; /* * log transid when this inode was last modified */ int last_sub_trans; /* a local copy of root's last_log_commit */ int last_log_commit; /* total number of bytes pending delalloc, used by stat to calc the * real block usage of the file */ u64 delalloc_bytes; /* * Total number of bytes pending delalloc that fall within a file * range that is either a hole or beyond EOF (and no prealloc extent * exists in the range). This is always <= delalloc_bytes. */ u64 new_delalloc_bytes; /* * total number of bytes pending defrag, used by stat to check whether * it needs COW. */ u64 defrag_bytes; /* * the size of the file stored in the metadata on disk. data=ordered * means the in-memory i_size might be larger than the size on disk * because not all the blocks are written yet. */ u64 disk_i_size; /* * if this is a directory then index_cnt is the counter for the index * number for new files that are created */ u64 index_cnt; /* Cache the directory index number to speed the dir/file remove */ u64 dir_index; /* the fsync log has some corner cases that mean we have to check * directories to see if any unlinks have been done before * the directory was logged. See tree-log.c for all the * details */ u64 last_unlink_trans; /* * Track the transaction id of the last transaction used to create a * hard link for the inode. This is used by the log tree (fsync). */ u64 last_link_trans; /* * Number of bytes outstanding that are going to need csums. This is * used in ENOSPC accounting. */ u64 csum_bytes; /* flags field from the on disk inode */ u32 flags; /* * Counters to keep track of the number of extent item's we may use due * to delalloc and such. outstanding_extents is the number of extent * items we think we'll end up using, and reserved_extents is the number * of extent items we've reserved metadata for. */ unsigned outstanding_extents; unsigned reserved_extents; /* * Cached values of inode properties */ unsigned prop_compress; /* per-file compression algorithm */ /* * Force compression on the file using the defrag ioctl, could be * different from prop_compress and takes precedence if set */ unsigned defrag_compress; struct btrfs_delayed_node *delayed_node; /* File creation time. */ struct timespec i_otime; /* Hook into fs_info->delayed_iputs */ struct list_head delayed_iput; long delayed_iput_count; /* * To avoid races between lockless (i_mutex not held) direct IO writes * and concurrent fsync requests. Direct IO writes must acquire read * access on this semaphore for creating an extent map and its * corresponding ordered extent. The fast fsync path must acquire write * access on this semaphore before it collects ordered extents and * extent maps. */ struct rw_semaphore dio_sem; struct inode vfs_inode; }; extern unsigned char btrfs_filetype_table[]; static inline struct btrfs_inode *BTRFS_I(const struct inode *inode) { return container_of(inode, struct btrfs_inode, vfs_inode); } static inline unsigned long btrfs_inode_hash(u64 objectid, const struct btrfs_root *root) { u64 h = objectid ^ (root->objectid * GOLDEN_RATIO_PRIME); #if BITS_PER_LONG == 32 h = (h >> 32) ^ (h & 0xffffffff); #endif return (unsigned long)h; } static inline void btrfs_insert_inode_hash(struct inode *inode) { unsigned long h = btrfs_inode_hash(inode->i_ino, BTRFS_I(inode)->root); __insert_inode_hash(inode, h); } static inline u64 btrfs_ino(const struct btrfs_inode *inode) { u64 ino = inode->location.objectid; /* * !ino: btree_inode * type == BTRFS_ROOT_ITEM_KEY: subvol dir */ if (!ino || inode->location.type == BTRFS_ROOT_ITEM_KEY) ino = inode->vfs_inode.i_ino; return ino; } static inline void btrfs_i_size_write(struct btrfs_inode *inode, u64 size) { i_size_write(&inode->vfs_inode, size); inode->disk_i_size = size; } static inline bool btrfs_is_free_space_inode(struct btrfs_inode *inode) { struct btrfs_root *root = inode->root; if (root == root->fs_info->tree_root && btrfs_ino(inode) != BTRFS_BTREE_INODE_OBJECTID) return true; if (inode->location.objectid == BTRFS_FREE_INO_OBJECTID) return true; return false; } static inline int btrfs_inode_in_log(struct btrfs_inode *inode, u64 generation) { int ret = 0; spin_lock(&inode->lock); if (inode->logged_trans == generation && inode->last_sub_trans <= inode->last_log_commit && inode->last_sub_trans <= inode->root->last_log_commit) { /* * After a ranged fsync we might have left some extent maps * (that fall outside the fsync's range). So return false * here if the list isn't empty, to make sure btrfs_log_inode() * will be called and process those extent maps. */ smp_mb(); if (list_empty(&inode->extent_tree.modified_extents)) ret = 1; } spin_unlock(&inode->lock); return ret; } #define BTRFS_DIO_ORIG_BIO_SUBMITTED 0x1 struct btrfs_dio_private { struct inode *inode; unsigned long flags; u64 logical_offset; u64 disk_bytenr; u64 bytes; void *private; /* number of bios pending for this dio */ atomic_t pending_bios; /* IO errors */ int errors; /* orig_bio is our btrfs_io_bio */ struct bio *orig_bio; /* dio_bio came from fs/direct-io.c */ struct bio *dio_bio; /* * The original bio may be split to several sub-bios, this is * done during endio of sub-bios */ blk_status_t (*subio_endio)(struct inode *, struct btrfs_io_bio *, blk_status_t); }; /* * Disable DIO read nolock optimization, so new dio readers will be forced * to grab i_mutex. It is used to avoid the endless truncate due to * nonlocked dio read. */ static inline void btrfs_inode_block_unlocked_dio(struct btrfs_inode *inode) { set_bit(BTRFS_INODE_READDIO_NEED_LOCK, &inode->runtime_flags); smp_mb(); } static inline void btrfs_inode_resume_unlocked_dio(struct btrfs_inode *inode) { smp_mb__before_atomic(); clear_bit(BTRFS_INODE_READDIO_NEED_LOCK, &inode->runtime_flags); } static inline void btrfs_print_data_csum_error(struct btrfs_inode *inode, u64 logical_start, u32 csum, u32 csum_expected, int mirror_num) { struct btrfs_root *root = inode->root; /* Output minus objectid, which is more meaningful */ if (root->objectid >= BTRFS_LAST_FREE_OBJECTID) btrfs_warn_rl(root->fs_info, "csum failed root %lld ino %lld off %llu csum 0x%08x expected csum 0x%08x mirror %d", root->objectid, btrfs_ino(inode), logical_start, csum, csum_expected, mirror_num); else btrfs_warn_rl(root->fs_info, "csum failed root %llu ino %llu off %llu csum 0x%08x expected csum 0x%08x mirror %d", root->objectid, btrfs_ino(inode), logical_start, csum, csum_expected, mirror_num); } bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end); #endif |
| 105 105 71 35 37 34 34 34 34 33 2 104 105 105 105 30 1 105 105 30 30 1 34 34 34 34 32 31 30 30 30 30 30 30 30 30 2 16 34 27 27 27 27 27 17 17 17 17 17 17 17 17 17 17 17 105 105 105 103 28 16 27 17 27 17 17 10 17 77 105 27 77 104 27 27 27 27 27 27 23 27 27 27 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 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 | /************************************************************ * EFI GUID Partition Table handling * * http://www.uefi.org/specs/ * http://www.intel.com/technology/efi/ * * efi.[ch] by Matt Domsch <Matt_Domsch@dell.com> * Copyright 2000,2001,2002,2004 Dell Inc. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA * * * TODO: * * Changelog: * Mon August 5th, 2013 Davidlohr Bueso <davidlohr@hp.com> * - detect hybrid MBRs, tighter pMBR checking & cleanups. * * Mon Nov 09 2004 Matt Domsch <Matt_Domsch@dell.com> * - test for valid PMBR and valid PGPT before ever reading * AGPT, allow override with 'gpt' kernel command line option. * - check for first/last_usable_lba outside of size of disk * * Tue Mar 26 2002 Matt Domsch <Matt_Domsch@dell.com> * - Ported to 2.5.7-pre1 and 2.5.7-dj2 * - Applied patch to avoid fault in alternate header handling * - cleaned up find_valid_gpt * - On-disk structure and copy in memory is *always* LE now - * swab fields as needed * - remove print_gpt_header() * - only use first max_p partition entries, to keep the kernel minor number * and partition numbers tied. * * Mon Feb 04 2002 Matt Domsch <Matt_Domsch@dell.com> * - Removed __PRIPTR_PREFIX - not being used * * Mon Jan 14 2002 Matt Domsch <Matt_Domsch@dell.com> * - Ported to 2.5.2-pre11 + library crc32 patch Linus applied * * Thu Dec 6 2001 Matt Domsch <Matt_Domsch@dell.com> * - Added compare_gpts(). * - moved le_efi_guid_to_cpus() back into this file. GPT is the only * thing that keeps EFI GUIDs on disk. * - Changed gpt structure names and members to be simpler and more Linux-like. * * Wed Oct 17 2001 Matt Domsch <Matt_Domsch@dell.com> * - Removed CONFIG_DEVFS_VOLUMES_UUID code entirely per Martin Wilck * * Wed Oct 10 2001 Matt Domsch <Matt_Domsch@dell.com> * - Changed function comments to DocBook style per Andreas Dilger suggestion. * * Mon Oct 08 2001 Matt Domsch <Matt_Domsch@dell.com> * - Change read_lba() to use the page cache per Al Viro's work. * - print u64s properly on all architectures * - fixed debug_printk(), now Dprintk() * * Mon Oct 01 2001 Matt Domsch <Matt_Domsch@dell.com> * - Style cleanups * - made most functions static * - Endianness addition * - remove test for second alternate header, as it's not per spec, * and is unnecessary. There's now a method to read/write the last * sector of an odd-sized disk from user space. No tools have ever * been released which used this code, so it's effectively dead. * - Per Asit Mallick of Intel, added a test for a valid PMBR. * - Added kernel command line option 'gpt' to override valid PMBR test. * * Wed Jun 6 2001 Martin Wilck <Martin.Wilck@Fujitsu-Siemens.com> * - added devfs volume UUID support (/dev/volumes/uuids) for * mounting file systems by the partition GUID. * * Tue Dec 5 2000 Matt Domsch <Matt_Domsch@dell.com> * - Moved crc32() to linux/lib, added efi_crc32(). * * Thu Nov 30 2000 Matt Domsch <Matt_Domsch@dell.com> * - Replaced Intel's CRC32 function with an equivalent * non-license-restricted version. * * Wed Oct 25 2000 Matt Domsch <Matt_Domsch@dell.com> * - Fixed the last_lba() call to return the proper last block * * Thu Oct 12 2000 Matt Domsch <Matt_Domsch@dell.com> * - Thanks to Andries Brouwer for his debugging assistance. * - Code works, detects all the partitions. * ************************************************************/ #include <linux/kernel.h> #include <linux/crc32.h> #include <linux/ctype.h> #include <linux/math64.h> #include <linux/slab.h> #include "check.h" #include "efi.h" /* This allows a kernel command line option 'gpt' to override * the test for invalid PMBR. Not __initdata because reloading * the partition tables happens after init too. */ static int force_gpt; static int __init force_gpt_fn(char *str) { force_gpt = 1; return 1; } __setup("gpt", force_gpt_fn); /** * efi_crc32() - EFI version of crc32 function * @buf: buffer to calculate crc32 of * @len: length of buf * * Description: Returns EFI-style CRC32 value for @buf * * This function uses the little endian Ethernet polynomial * but seeds the function with ~0, and xor's with ~0 at the end. * Note, the EFI Specification, v1.02, has a reference to * Dr. Dobbs Journal, May 1994 (actually it's in May 1992). */ static inline u32 efi_crc32(const void *buf, unsigned long len) { return (crc32(~0L, buf, len) ^ ~0L); } /** * last_lba(): return number of last logical block of device * @bdev: block device * * Description: Returns last LBA value on success, 0 on error. * This is stored (by sd and ide-geometry) in * the part[0] entry for this disk, and is the number of * physical sectors available on the disk. */ static u64 last_lba(struct block_device *bdev) { if (!bdev || !bdev->bd_inode) return 0; return div_u64(bdev->bd_inode->i_size, bdev_logical_block_size(bdev)) - 1ULL; } static inline int pmbr_part_valid(gpt_mbr_record *part) { if (part->os_type != EFI_PMBR_OSTYPE_EFI_GPT) goto invalid; /* set to 0x00000001 (i.e., the LBA of the GPT Partition Header) */ if (le32_to_cpu(part->starting_lba) != GPT_PRIMARY_PARTITION_TABLE_LBA) goto invalid; return GPT_MBR_PROTECTIVE; invalid: return 0; } /** * is_pmbr_valid(): test Protective MBR for validity * @mbr: pointer to a legacy mbr structure * @total_sectors: amount of sectors in the device * * Description: Checks for a valid protective or hybrid * master boot record (MBR). The validity of a pMBR depends * on all of the following properties: * 1) MSDOS signature is in the last two bytes of the MBR * 2) One partition of type 0xEE is found * * In addition, a hybrid MBR will have up to three additional * primary partitions, which point to the same space that's * marked out by up to three GPT partitions. * * Returns 0 upon invalid MBR, or GPT_MBR_PROTECTIVE or * GPT_MBR_HYBRID depending on the device layout. */ static int is_pmbr_valid(legacy_mbr *mbr, sector_t total_sectors) { uint32_t sz = 0; int i, part = 0, ret = 0; /* invalid by default */ if (!mbr || le16_to_cpu(mbr->signature) != MSDOS_MBR_SIGNATURE) goto done; for (i = 0; i < 4; i++) { ret = pmbr_part_valid(&mbr->partition_record[i]); if (ret == GPT_MBR_PROTECTIVE) { part = i; /* * Ok, we at least know that there's a protective MBR, * now check if there are other partition types for * hybrid MBR. */ goto check_hybrid; } } if (ret != GPT_MBR_PROTECTIVE) goto done; check_hybrid: for (i = 0; i < 4; i++) if ((mbr->partition_record[i].os_type != EFI_PMBR_OSTYPE_EFI_GPT) && (mbr->partition_record[i].os_type != 0x00)) ret = GPT_MBR_HYBRID; /* * Protective MBRs take up the lesser of the whole disk * or 2 TiB (32bit LBA), ignoring the rest of the disk. * Some partitioning programs, nonetheless, choose to set * the size to the maximum 32-bit limitation, disregarding * the disk size. * * Hybrid MBRs do not necessarily comply with this. * * Consider a bad value here to be a warning to support dd'ing * an image from a smaller disk to a larger disk. */ if (ret == GPT_MBR_PROTECTIVE) { sz = le32_to_cpu(mbr->partition_record[part].size_in_lba); if (sz != (uint32_t) total_sectors - 1 && sz != 0xFFFFFFFF) pr_debug("GPT: mbr size in lba (%u) different than whole disk (%u).\n", sz, min_t(uint32_t, total_sectors - 1, 0xFFFFFFFF)); } done: return ret; } /** * read_lba(): Read bytes from disk, starting at given LBA * @state: disk parsed partitions * @lba: the Logical Block Address of the partition table * @buffer: destination buffer * @count: bytes to read * * Description: Reads @count bytes from @state->bdev into @buffer. * Returns number of bytes read on success, 0 on error. */ static size_t read_lba(struct parsed_partitions *state, u64 lba, u8 *buffer, size_t count) { size_t totalreadcount = 0; struct block_device *bdev = state->bdev; sector_t n = lba * (bdev_logical_block_size(bdev) / 512); if (!buffer || lba > last_lba(bdev)) return 0; while (count) { int copied = 512; Sector sect; unsigned char *data = read_part_sector(state, n++, §); if (!data) break; if (copied > count) copied = count; memcpy(buffer, data, copied); put_dev_sector(sect); buffer += copied; totalreadcount +=copied; count -= copied; } return totalreadcount; } /** * alloc_read_gpt_entries(): reads partition entries from disk * @state: disk parsed partitions * @gpt: GPT header * * Description: Returns ptes on success, NULL on error. * Allocates space for PTEs based on information found in @gpt. * Notes: remember to free pte when you're done! */ static gpt_entry *alloc_read_gpt_entries(struct parsed_partitions *state, gpt_header *gpt) { size_t count; gpt_entry *pte; if (!gpt) return NULL; count = (size_t)le32_to_cpu(gpt->num_partition_entries) * le32_to_cpu(gpt->sizeof_partition_entry); if (!count) return NULL; pte = kmalloc(count, GFP_KERNEL); if (!pte) return NULL; if (read_lba(state, le64_to_cpu(gpt->partition_entry_lba), (u8 *) pte, count) < count) { kfree(pte); pte=NULL; return NULL; } return pte; } /** * alloc_read_gpt_header(): Allocates GPT header, reads into it from disk * @state: disk parsed partitions * @lba: the Logical Block Address of the partition table * * Description: returns GPT header on success, NULL on error. Allocates * and fills a GPT header starting at @ from @state->bdev. * Note: remember to free gpt when finished with it. */ static gpt_header *alloc_read_gpt_header(struct parsed_partitions *state, u64 lba) { gpt_header *gpt; unsigned ssz = bdev_logical_block_size(state->bdev); gpt = kmalloc(ssz, GFP_KERNEL); if (!gpt) return NULL; if (read_lba(state, lba, (u8 *) gpt, ssz) < ssz) { kfree(gpt); gpt=NULL; return NULL; } return gpt; } /** * is_gpt_valid() - tests one GPT header and PTEs for validity * @state: disk parsed partitions * @lba: logical block address of the GPT header to test * @gpt: GPT header ptr, filled on return. * @ptes: PTEs ptr, filled on return. * * Description: returns 1 if valid, 0 on error. * If valid, returns pointers to newly allocated GPT header and PTEs. */ static int is_gpt_valid(struct parsed_partitions *state, u64 lba, gpt_header **gpt, gpt_entry **ptes) { u32 crc, origcrc; u64 lastlba, pt_size; if (!ptes) return 0; if (!(*gpt = alloc_read_gpt_header(state, lba))) return 0; /* Check the GUID Partition Table signature */ if (le64_to_cpu((*gpt)->signature) != GPT_HEADER_SIGNATURE) { pr_debug("GUID Partition Table Header signature is wrong:" "%lld != %lld\n", (unsigned long long)le64_to_cpu((*gpt)->signature), (unsigned long long)GPT_HEADER_SIGNATURE); goto fail; } /* Check the GUID Partition Table header size is too big */ if (le32_to_cpu((*gpt)->header_size) > bdev_logical_block_size(state->bdev)) { pr_debug("GUID Partition Table Header size is too large: %u > %u\n", le32_to_cpu((*gpt)->header_size), bdev_logical_block_size(state->bdev)); goto fail; } /* Check the GUID Partition Table header size is too small */ if (le32_to_cpu((*gpt)->header_size) < sizeof(gpt_header)) { pr_debug("GUID Partition Table Header size is too small: %u < %zu\n", le32_to_cpu((*gpt)->header_size), sizeof(gpt_header)); goto fail; } /* Check the GUID Partition Table CRC */ origcrc = le32_to_cpu((*gpt)->header_crc32); (*gpt)->header_crc32 = 0; crc = efi_crc32((const unsigned char *) (*gpt), le32_to_cpu((*gpt)->header_size)); if (crc != origcrc) { pr_debug("GUID Partition Table Header CRC is wrong: %x != %x\n", crc, origcrc); goto fail; } (*gpt)->header_crc32 = cpu_to_le32(origcrc); /* Check that the my_lba entry points to the LBA that contains * the GUID Partition Table */ if (le64_to_cpu((*gpt)->my_lba) != lba) { pr_debug("GPT my_lba incorrect: %lld != %lld\n", (unsigned long long)le64_to_cpu((*gpt)->my_lba), (unsigned long long)lba); goto fail; } /* Check the first_usable_lba and last_usable_lba are * within the disk. */ lastlba = last_lba(state->bdev); if (le64_to_cpu((*gpt)->first_usable_lba) > lastlba) { pr_debug("GPT: first_usable_lba incorrect: %lld > %lld\n", (unsigned long long)le64_to_cpu((*gpt)->first_usable_lba), (unsigned long long)lastlba); goto fail; } if (le64_to_cpu((*gpt)->last_usable_lba) > lastlba) { pr_debug("GPT: last_usable_lba incorrect: %lld > %lld\n", (unsigned long long)le64_to_cpu((*gpt)->last_usable_lba), (unsigned long long)lastlba); goto fail; } if (le64_to_cpu((*gpt)->last_usable_lba) < le64_to_cpu((*gpt)->first_usable_lba)) { pr_debug("GPT: last_usable_lba incorrect: %lld > %lld\n", (unsigned long long)le64_to_cpu((*gpt)->last_usable_lba), (unsigned long long)le64_to_cpu((*gpt)->first_usable_lba)); goto fail; } /* Check that sizeof_partition_entry has the correct value */ if (le32_to_cpu((*gpt)->sizeof_partition_entry) != sizeof(gpt_entry)) { pr_debug("GUID Partition Entry Size check failed.\n"); goto fail; } /* Sanity check partition table size */ pt_size = (u64)le32_to_cpu((*gpt)->num_partition_entries) * le32_to_cpu((*gpt)->sizeof_partition_entry); if (pt_size > KMALLOC_MAX_SIZE) { pr_debug("GUID Partition Table is too large: %llu > %lu bytes\n", (unsigned long long)pt_size, KMALLOC_MAX_SIZE); goto fail; } if (!(*ptes = alloc_read_gpt_entries(state, *gpt))) goto fail; /* Check the GUID Partition Entry Array CRC */ crc = efi_crc32((const unsigned char *) (*ptes), pt_size); if (crc != le32_to_cpu((*gpt)->partition_entry_array_crc32)) { pr_debug("GUID Partition Entry Array CRC check failed.\n"); goto fail_ptes; } /* We're done, all's well */ return 1; fail_ptes: kfree(*ptes); *ptes = NULL; fail: kfree(*gpt); *gpt = NULL; return 0; } /** * is_pte_valid() - tests one PTE for validity * @pte:pte to check * @lastlba: last lba of the disk * * Description: returns 1 if valid, 0 on error. */ static inline int is_pte_valid(const gpt_entry *pte, const u64 lastlba) { if ((!efi_guidcmp(pte->partition_type_guid, NULL_GUID)) || le64_to_cpu(pte->starting_lba) > lastlba || le64_to_cpu(pte->ending_lba) > lastlba) return 0; return 1; } /** * compare_gpts() - Search disk for valid GPT headers and PTEs * @pgpt: primary GPT header * @agpt: alternate GPT header * @lastlba: last LBA number * * Description: Returns nothing. Sanity checks pgpt and agpt fields * and prints warnings on discrepancies. * */ static void compare_gpts(gpt_header *pgpt, gpt_header *agpt, u64 lastlba) { int error_found = 0; if (!pgpt || !agpt) return; if (le64_to_cpu(pgpt->my_lba) != le64_to_cpu(agpt->alternate_lba)) { pr_warn("GPT:Primary header LBA != Alt. header alternate_lba\n"); pr_warn("GPT:%lld != %lld\n", (unsigned long long)le64_to_cpu(pgpt->my_lba), (unsigned long long)le64_to_cpu(agpt->alternate_lba)); error_found++; } if (le64_to_cpu(pgpt->alternate_lba) != le64_to_cpu(agpt->my_lba)) { pr_warn("GPT:Primary header alternate_lba != Alt. header my_lba\n"); pr_warn("GPT:%lld != %lld\n", (unsigned long long)le64_to_cpu(pgpt->alternate_lba), (unsigned long long)le64_to_cpu(agpt->my_lba)); error_found++; } if (le64_to_cpu(pgpt->first_usable_lba) != le64_to_cpu(agpt->first_usable_lba)) { pr_warn("GPT:first_usable_lbas don't match.\n"); pr_warn("GPT:%lld != %lld\n", (unsigned long long)le64_to_cpu(pgpt->first_usable_lba), (unsigned long long)le64_to_cpu(agpt->first_usable_lba)); error_found++; } if (le64_to_cpu(pgpt->last_usable_lba) != le64_to_cpu(agpt->last_usable_lba)) { pr_warn("GPT:last_usable_lbas don't match.\n"); pr_warn("GPT:%lld != %lld\n", (unsigned long long)le64_to_cpu(pgpt->last_usable_lba), (unsigned long long)le64_to_cpu(agpt->last_usable_lba)); error_found++; } if (efi_guidcmp(pgpt->disk_guid, agpt->disk_guid)) { pr_warn("GPT:disk_guids don't match.\n"); error_found++; } if (le32_to_cpu(pgpt->num_partition_entries) != le32_to_cpu(agpt->num_partition_entries)) { pr_warn("GPT:num_partition_entries don't match: " "0x%x != 0x%x\n", le32_to_cpu(pgpt->num_partition_entries), le32_to_cpu(agpt->num_partition_entries)); error_found++; } if (le32_to_cpu(pgpt->sizeof_partition_entry) != le32_to_cpu(agpt->sizeof_partition_entry)) { pr_warn("GPT:sizeof_partition_entry values don't match: " "0x%x != 0x%x\n", le32_to_cpu(pgpt->sizeof_partition_entry), le32_to_cpu(agpt->sizeof_partition_entry)); error_found++; } if (le32_to_cpu(pgpt->partition_entry_array_crc32) != le32_to_cpu(agpt->partition_entry_array_crc32)) { pr_warn("GPT:partition_entry_array_crc32 values don't match: " "0x%x != 0x%x\n", le32_to_cpu(pgpt->partition_entry_array_crc32), le32_to_cpu(agpt->partition_entry_array_crc32)); error_found++; } if (le64_to_cpu(pgpt->alternate_lba) != lastlba) { pr_warn("GPT:Primary header thinks Alt. header is not at the end of the disk.\n"); pr_warn("GPT:%lld != %lld\n", (unsigned long long)le64_to_cpu(pgpt->alternate_lba), (unsigned long long)lastlba); error_found++; } if (le64_to_cpu(agpt->my_lba) != lastlba) { pr_warn("GPT:Alternate GPT header not at the end of the disk.\n"); pr_warn("GPT:%lld != %lld\n", (unsigned long long)le64_to_cpu(agpt->my_lba), (unsigned long long)lastlba); error_found++; } if (error_found) pr_warn("GPT: Use GNU Parted to correct GPT errors.\n"); return; } /** * find_valid_gpt() - Search disk for valid GPT headers and PTEs * @state: disk parsed partitions * @gpt: GPT header ptr, filled on return. * @ptes: PTEs ptr, filled on return. * * Description: Returns 1 if valid, 0 on error. * If valid, returns pointers to newly allocated GPT header and PTEs. * Validity depends on PMBR being valid (or being overridden by the * 'gpt' kernel command line option) and finding either the Primary * GPT header and PTEs valid, or the Alternate GPT header and PTEs * valid. If the Primary GPT header is not valid, the Alternate GPT header * is not checked unless the 'gpt' kernel command line option is passed. * This protects against devices which misreport their size, and forces * the user to decide to use the Alternate GPT. */ static int find_valid_gpt(struct parsed_partitions *state, gpt_header **gpt, gpt_entry **ptes) { int good_pgpt = 0, good_agpt = 0, good_pmbr = 0; gpt_header *pgpt = NULL, *agpt = NULL; gpt_entry *pptes = NULL, *aptes = NULL; legacy_mbr *legacymbr; sector_t total_sectors = i_size_read(state->bdev->bd_inode) >> 9; u64 lastlba; if (!ptes) return 0; lastlba = last_lba(state->bdev); if (!force_gpt) { /* This will be added to the EFI Spec. per Intel after v1.02. */ legacymbr = kzalloc(sizeof(*legacymbr), GFP_KERNEL); if (!legacymbr) goto fail; read_lba(state, 0, (u8 *)legacymbr, sizeof(*legacymbr)); good_pmbr = is_pmbr_valid(legacymbr, total_sectors); kfree(legacymbr); if (!good_pmbr) goto fail; pr_debug("Device has a %s MBR\n", good_pmbr == GPT_MBR_PROTECTIVE ? "protective" : "hybrid"); } good_pgpt = is_gpt_valid(state, GPT_PRIMARY_PARTITION_TABLE_LBA, &pgpt, &pptes); if (good_pgpt) good_agpt = is_gpt_valid(state, le64_to_cpu(pgpt->alternate_lba), &agpt, &aptes); if (!good_agpt && force_gpt) good_agpt = is_gpt_valid(state, lastlba, &agpt, &aptes); /* The obviously unsuccessful case */ if (!good_pgpt && !good_agpt) goto fail; compare_gpts(pgpt, agpt, lastlba); /* The good cases */ if (good_pgpt) { *gpt = pgpt; *ptes = pptes; kfree(agpt); kfree(aptes); if (!good_agpt) pr_warn("Alternate GPT is invalid, using primary GPT.\n"); return 1; } else if (good_agpt) { *gpt = agpt; *ptes = aptes; kfree(pgpt); kfree(pptes); pr_warn("Primary GPT is invalid, using alternate GPT.\n"); return 1; } fail: kfree(pgpt); kfree(agpt); kfree(pptes); kfree(aptes); *gpt = NULL; *ptes = NULL; return 0; } /** * efi_partition(struct parsed_partitions *state) * @state: disk parsed partitions * * Description: called from check.c, if the disk contains GPT * partitions, sets up partition entries in the kernel. * * If the first block on the disk is a legacy MBR, * it will get handled by msdos_partition(). * If it's a Protective MBR, we'll handle it here. * * We do not create a Linux partition for GPT, but * only for the actual data partitions. * Returns: * -1 if unable to read the partition table * 0 if this isn't our partition table * 1 if successful * */ int efi_partition(struct parsed_partitions *state) { gpt_header *gpt = NULL; gpt_entry *ptes = NULL; u32 i; unsigned ssz = bdev_logical_block_size(state->bdev) / 512; if (!find_valid_gpt(state, &gpt, &ptes) || !gpt || !ptes) { kfree(gpt); kfree(ptes); return 0; } pr_debug("GUID Partition Table is valid! Yea!\n"); for (i = 0; i < le32_to_cpu(gpt->num_partition_entries) && i < state->limit-1; i++) { struct partition_meta_info *info; unsigned label_count = 0; unsigned label_max; u64 start = le64_to_cpu(ptes[i].starting_lba); u64 size = le64_to_cpu(ptes[i].ending_lba) - le64_to_cpu(ptes[i].starting_lba) + 1ULL; if (!is_pte_valid(&ptes[i], last_lba(state->bdev))) continue; put_partition(state, i+1, start * ssz, size * ssz); /* If this is a RAID volume, tell md */ if (!efi_guidcmp(ptes[i].partition_type_guid, PARTITION_LINUX_RAID_GUID)) state->parts[i + 1].flags = ADDPART_FLAG_RAID; info = &state->parts[i + 1].info; efi_guid_to_str(&ptes[i].unique_partition_guid, info->uuid); /* Naively convert UTF16-LE to 7 bits. */ label_max = min(ARRAY_SIZE(info->volname) - 1, ARRAY_SIZE(ptes[i].partition_name)); info->volname[label_max] = 0; while (label_count < label_max) { u8 c = ptes[i].partition_name[label_count] & 0xff; if (c && !isprint(c)) c = '!'; info->volname[label_count] = c; label_count++; } state->parts[i + 1].has_info = true; } kfree(ptes); kfree(gpt); strlcat(state->pp_buf, "\n", PAGE_SIZE); return 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* Based on net/mac80211/trace.h */ #undef TRACE_SYSTEM #define TRACE_SYSTEM mac802154 #if !defined(__MAC802154_DRIVER_TRACE) || defined(TRACE_HEADER_MULTI_READ) #define __MAC802154_DRIVER_TRACE #include <linux/tracepoint.h> #include <net/mac802154.h> #include "ieee802154_i.h" #define MAXNAME 32 #define LOCAL_ENTRY __array(char, wpan_phy_name, MAXNAME) #define LOCAL_ASSIGN strlcpy(__entry->wpan_phy_name, \ wpan_phy_name(local->hw.phy), MAXNAME) #define LOCAL_PR_FMT "%s" #define LOCAL_PR_ARG __entry->wpan_phy_name #define CCA_ENTRY __field(enum nl802154_cca_modes, cca_mode) \ __field(enum nl802154_cca_opts, cca_opt) #define CCA_ASSIGN \ do { \ (__entry->cca_mode) = cca->mode; \ (__entry->cca_opt) = cca->opt; \ } while (0) #define CCA_PR_FMT "cca_mode: %d, cca_opt: %d" #define CCA_PR_ARG __entry->cca_mode, __entry->cca_opt #define BOOL_TO_STR(bo) (bo) ? "true" : "false" /* Tracing for driver callbacks */ DECLARE_EVENT_CLASS(local_only_evt, TP_PROTO(struct ieee802154_local *local), TP_ARGS(local), TP_STRUCT__entry( LOCAL_ENTRY ), TP_fast_assign( LOCAL_ASSIGN; ), TP_printk(LOCAL_PR_FMT, LOCAL_PR_ARG) ); DEFINE_EVENT(local_only_evt, 802154_drv_return_void, TP_PROTO(struct ieee802154_local *local), TP_ARGS(local) ); TRACE_EVENT(802154_drv_return_int, TP_PROTO(struct ieee802154_local *local, int ret), TP_ARGS(local, ret), TP_STRUCT__entry( LOCAL_ENTRY __field(int, ret) ), TP_fast_assign( LOCAL_ASSIGN; __entry->ret = ret; ), TP_printk(LOCAL_PR_FMT ", returned: %d", LOCAL_PR_ARG, __entry->ret) ); DEFINE_EVENT(local_only_evt, 802154_drv_start, TP_PROTO(struct ieee802154_local *local), TP_ARGS(local) ); DEFINE_EVENT(local_only_evt, 802154_drv_stop, TP_PROTO(struct ieee802154_local *local), TP_ARGS(local) ); TRACE_EVENT(802154_drv_set_channel, TP_PROTO(struct ieee802154_local *local, u8 page, u8 channel), TP_ARGS(local, page, channel), TP_STRUCT__entry( LOCAL_ENTRY __field(u8, page) __field(u8, channel) ), TP_fast_assign( LOCAL_ASSIGN; __entry->page = page; __entry->channel = channel; ), TP_printk(LOCAL_PR_FMT ", page: %d, channel: %d", LOCAL_PR_ARG, __entry->page, __entry->channel) ); TRACE_EVENT(802154_drv_set_cca_mode, TP_PROTO(struct ieee802154_local *local, const struct wpan_phy_cca *cca), TP_ARGS(local, cca), TP_STRUCT__entry( LOCAL_ENTRY CCA_ENTRY ), TP_fast_assign( LOCAL_ASSIGN; CCA_ASSIGN; ), TP_printk(LOCAL_PR_FMT ", " CCA_PR_FMT, LOCAL_PR_ARG, CCA_PR_ARG) ); TRACE_EVENT(802154_drv_set_cca_ed_level, TP_PROTO(struct ieee802154_local *local, s32 mbm), TP_ARGS(local, mbm), TP_STRUCT__entry( LOCAL_ENTRY __field(s32, mbm) ), TP_fast_assign( LOCAL_ASSIGN; __entry->mbm = mbm; ), TP_printk(LOCAL_PR_FMT ", ed level: %d", LOCAL_PR_ARG, __entry->mbm) ); TRACE_EVENT(802154_drv_set_tx_power, TP_PROTO(struct ieee802154_local *local, s32 power), TP_ARGS(local, power), TP_STRUCT__entry( LOCAL_ENTRY __field(s32, power) ), TP_fast_assign( LOCAL_ASSIGN; __entry->power = power; ), TP_printk(LOCAL_PR_FMT ", mbm: %d", LOCAL_PR_ARG, __entry->power) ); TRACE_EVENT(802154_drv_set_lbt_mode, TP_PROTO(struct ieee802154_local *local, bool mode), TP_ARGS(local, mode), TP_STRUCT__entry( LOCAL_ENTRY __field(bool, mode) ), TP_fast_assign( LOCAL_ASSIGN; __entry->mode = mode; ), TP_printk(LOCAL_PR_FMT ", lbt mode: %s", LOCAL_PR_ARG, BOOL_TO_STR(__entry->mode)) ); TRACE_EVENT(802154_drv_set_short_addr, TP_PROTO(struct ieee802154_local *local, __le16 short_addr), TP_ARGS(local, short_addr), TP_STRUCT__entry( LOCAL_ENTRY __field(__le16, short_addr) ), TP_fast_assign( LOCAL_ASSIGN; __entry->short_addr = short_addr; ), TP_printk(LOCAL_PR_FMT ", short addr: 0x%04x", LOCAL_PR_ARG, le16_to_cpu(__entry->short_addr)) ); TRACE_EVENT(802154_drv_set_pan_id, TP_PROTO(struct ieee802154_local *local, __le16 pan_id), TP_ARGS(local, pan_id), TP_STRUCT__entry( LOCAL_ENTRY __field(__le16, pan_id) ), TP_fast_assign( LOCAL_ASSIGN; __entry->pan_id = pan_id; ), TP_printk(LOCAL_PR_FMT ", pan id: 0x%04x", LOCAL_PR_ARG, le16_to_cpu(__entry->pan_id)) ); TRACE_EVENT(802154_drv_set_extended_addr, TP_PROTO(struct ieee802154_local *local, __le64 extended_addr), TP_ARGS(local, extended_addr), TP_STRUCT__entry( LOCAL_ENTRY __field(__le64, extended_addr) ), TP_fast_assign( LOCAL_ASSIGN; __entry->extended_addr = extended_addr; ), TP_printk(LOCAL_PR_FMT ", extended addr: 0x%llx", LOCAL_PR_ARG, le64_to_cpu(__entry->extended_addr)) ); TRACE_EVENT(802154_drv_set_pan_coord, TP_PROTO(struct ieee802154_local *local, bool is_coord), TP_ARGS(local, is_coord), TP_STRUCT__entry( LOCAL_ENTRY __field(bool, is_coord) ), TP_fast_assign( LOCAL_ASSIGN; __entry->is_coord = is_coord; ), TP_printk(LOCAL_PR_FMT ", is_coord: %s", LOCAL_PR_ARG, BOOL_TO_STR(__entry->is_coord)) ); TRACE_EVENT(802154_drv_set_csma_params, TP_PROTO(struct ieee802154_local *local, u8 min_be, u8 max_be, u8 max_csma_backoffs), TP_ARGS(local, min_be, max_be, max_csma_backoffs), TP_STRUCT__entry( LOCAL_ENTRY __field(u8, min_be) __field(u8, max_be) __field(u8, max_csma_backoffs) ), TP_fast_assign( LOCAL_ASSIGN, __entry->min_be = min_be; __entry->max_be = max_be; __entry->max_csma_backoffs = max_csma_backoffs; ), TP_printk(LOCAL_PR_FMT ", min be: %d, max be: %d, max csma backoffs: %d", LOCAL_PR_ARG, __entry->min_be, __entry->max_be, __entry->max_csma_backoffs) ); TRACE_EVENT(802154_drv_set_max_frame_retries, TP_PROTO(struct ieee802154_local *local, s8 max_frame_retries), TP_ARGS(local, max_frame_retries), TP_STRUCT__entry( LOCAL_ENTRY __field(s8, max_frame_retries) ), TP_fast_assign( LOCAL_ASSIGN; __entry->max_frame_retries = max_frame_retries; ), TP_printk(LOCAL_PR_FMT ", max frame retries: %d", LOCAL_PR_ARG, __entry->max_frame_retries) ); TRACE_EVENT(802154_drv_set_promiscuous_mode, TP_PROTO(struct ieee802154_local *local, bool on), TP_ARGS(local, on), TP_STRUCT__entry( LOCAL_ENTRY __field(bool, on) ), TP_fast_assign( LOCAL_ASSIGN; __entry->on = on; ), TP_printk(LOCAL_PR_FMT ", promiscuous mode: %s", LOCAL_PR_ARG, BOOL_TO_STR(__entry->on)) ); #endif /* !__MAC802154_DRIVER_TRACE || TRACE_HEADER_MULTI_READ */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE trace #include <trace/define_trace.h> |
| 226 226 28 80 226 226 226 226 225 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 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 | /* * Sound core. This file is composed of two parts. sound_class * which is common to both OSS and ALSA and OSS sound core which * is used OSS or emulation of it. */ /* * First, the common part. */ #include <linux/module.h> #include <linux/device.h> #include <linux/err.h> #include <linux/kdev_t.h> #include <linux/major.h> #include <sound/core.h> #ifdef CONFIG_SOUND_OSS_CORE static int __init init_oss_soundcore(void); static void cleanup_oss_soundcore(void); #else static inline int init_oss_soundcore(void) { return 0; } static inline void cleanup_oss_soundcore(void) { } #endif struct class *sound_class; EXPORT_SYMBOL(sound_class); MODULE_DESCRIPTION("Core sound module"); MODULE_AUTHOR("Alan Cox"); MODULE_LICENSE("GPL"); static char *sound_devnode(struct device *dev, umode_t *mode) { if (MAJOR(dev->devt) == SOUND_MAJOR) return NULL; return kasprintf(GFP_KERNEL, "snd/%s", dev_name(dev)); } static int __init init_soundcore(void) { int rc; rc = init_oss_soundcore(); if (rc) return rc; sound_class = class_create(THIS_MODULE, "sound"); if (IS_ERR(sound_class)) { cleanup_oss_soundcore(); return PTR_ERR(sound_class); } sound_class->devnode = sound_devnode; return 0; } static void __exit cleanup_soundcore(void) { cleanup_oss_soundcore(); class_destroy(sound_class); } subsys_initcall(init_soundcore); module_exit(cleanup_soundcore); #ifdef CONFIG_SOUND_OSS_CORE /* * OSS sound core handling. Breaks out sound functions to submodules * * Author: Alan Cox <alan@lxorguk.ukuu.org.uk> * * Fixes: * * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. * * -------------------- * * Top level handler for the sound subsystem. Various devices can * plug into this. The fact they don't all go via OSS doesn't mean * they don't have to implement the OSS API. There is a lot of logic * to keeping much of the OSS weight out of the code in a compatibility * module, but it's up to the driver to rember to load it... * * The code provides a set of functions for registration of devices * by type. This is done rather than providing a single call so that * we can hide any future changes in the internals (eg when we go to * 32bit dev_t) from the modules and their interface. * * Secondly we need to allocate the dsp, dsp16 and audio devices as * one. Thus we misuse the chains a bit to simplify this. * * Thirdly to make it more fun and for 2.3.x and above we do all * of this using fine grained locking. * * FIXME: we have to resolve modules and fine grained load/unload * locking at some point in 2.3.x. */ #include <linux/init.h> #include <linux/slab.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/sound.h> #include <linux/kmod.h> #define SOUND_STEP 16 struct sound_unit { int unit_minor; const struct file_operations *unit_fops; struct sound_unit *next; char name[32]; }; #ifdef CONFIG_SOUND_MSNDCLAS extern int msnd_classic_init(void); #endif #ifdef CONFIG_SOUND_MSNDPIN extern int msnd_pinnacle_init(void); #endif /* * By default, OSS sound_core claims full legacy minor range (0-255) * of SOUND_MAJOR to trap open attempts to any sound minor and * requests modules using custom sound-slot/service-* module aliases. * The only benefit of doing this is allowing use of custom module * aliases instead of the standard char-major-* ones. This behavior * prevents alternative OSS implementation and is scheduled to be * removed. * * CONFIG_SOUND_OSS_CORE_PRECLAIM and soundcore.preclaim_oss kernel * parameter are added to allow distros and developers to try and * switch to alternative implementations without needing to rebuild * the kernel in the meantime. If preclaim_oss is non-zero, the * kernel will behave the same as before. All SOUND_MAJOR minors are * preclaimed and the custom module aliases along with standard chrdev * ones are emitted if a missing device is opened. If preclaim_oss is * zero, sound_core only grabs what's actually in use and for missing * devices only the standard chrdev aliases are requested. * * All these clutters are scheduled to be removed along with * sound-slot/service-* module aliases. */ #ifdef CONFIG_SOUND_OSS_CORE_PRECLAIM static int preclaim_oss = 1; #else static int preclaim_oss = 0; #endif module_param(preclaim_oss, int, 0444); static int soundcore_open(struct inode *, struct file *); static const struct file_operations soundcore_fops = { /* We must have an owner or the module locking fails */ .owner = THIS_MODULE, .open = soundcore_open, .llseek = noop_llseek, }; /* * Low level list operator. Scan the ordered list, find a hole and * join into it. Called with the lock asserted */ static int __sound_insert_unit(struct sound_unit * s, struct sound_unit **list, const struct file_operations *fops, int index, int low, int top) { int n=low; if (index < 0) { /* first free */ while (*list && (*list)->unit_minor<n) list=&((*list)->next); while(n<top) { /* Found a hole ? */ if(*list==NULL || (*list)->unit_minor>n) break; list=&((*list)->next); n+=SOUND_STEP; } if(n>=top) return -ENOENT; } else { n = low+(index*16); while (*list) { if ((*list)->unit_minor==n) return -EBUSY; if ((*list)->unit_minor>n) break; list=&((*list)->next); } } /* * Fill it in */ s->unit_minor=n; s->unit_fops=fops; /* * Link it */ s->next=*list; *list=s; return n; } /* * Remove a node from the chain. Called with the lock asserted */ static struct sound_unit *__sound_remove_unit(struct sound_unit **list, int unit) { while(*list) { struct sound_unit *p=*list; if(p->unit_minor==unit) { *list=p->next; return p; } list=&(p->next); } printk(KERN_ERR "Sound device %d went missing!\n", unit); return NULL; } /* * This lock guards the sound loader list. */ static DEFINE_SPINLOCK(sound_loader_lock); /* * Allocate the controlling structure and add it to the sound driver * list. Acquires locks as needed */ static int sound_insert_unit(struct sound_unit **list, const struct file_operations *fops, int index, int low, int top, const char *name, umode_t mode, struct device *dev) { struct sound_unit *s = kmalloc(sizeof(*s), GFP_KERNEL); int r; if (!s) return -ENOMEM; spin_lock(&sound_loader_lock); retry: r = __sound_insert_unit(s, list, fops, index, low, top); spin_unlock(&sound_loader_lock); if (r < 0) goto fail; else if (r < SOUND_STEP) sprintf(s->name, "sound/%s", name); else sprintf(s->name, "sound/%s%d", name, r / SOUND_STEP); if (!preclaim_oss) { /* * Something else might have grabbed the minor. If * first free slot is requested, rescan with @low set * to the next unit; otherwise, -EBUSY. */ r = __register_chrdev(SOUND_MAJOR, s->unit_minor, 1, s->name, &soundcore_fops); if (r < 0) { spin_lock(&sound_loader_lock); __sound_remove_unit(list, s->unit_minor); if (index < 0) { low = s->unit_minor + SOUND_STEP; goto retry; } spin_unlock(&sound_loader_lock); r = -EBUSY; goto fail; } } device_create(sound_class, dev, MKDEV(SOUND_MAJOR, s->unit_minor), NULL, "%s", s->name+6); return s->unit_minor; fail: kfree(s); return r; } /* * Remove a unit. Acquires locks as needed. The drivers MUST have * completed the removal before their file operations become * invalid. */ static void sound_remove_unit(struct sound_unit **list, int unit) { struct sound_unit *p; spin_lock(&sound_loader_lock); p = __sound_remove_unit(list, unit); spin_unlock(&sound_loader_lock); if (p) { if (!preclaim_oss) __unregister_chrdev(SOUND_MAJOR, p->unit_minor, 1, p->name); device_destroy(sound_class, MKDEV(SOUND_MAJOR, p->unit_minor)); kfree(p); } } /* * Allocations * * 0 *16 Mixers * 1 *8 Sequencers * 2 *16 Midi * 3 *16 DSP * 4 *16 SunDSP * 5 *16 DSP16 * 6 -- sndstat (obsolete) * 7 *16 unused * 8 -- alternate sequencer (see above) * 9 *16 raw synthesizer access * 10 *16 unused * 11 *16 unused * 12 *16 unused * 13 *16 unused * 14 *16 unused * 15 *16 unused */ static struct sound_unit *chains[SOUND_STEP]; /** * register_sound_special_device - register a special sound node * @fops: File operations for the driver * @unit: Unit number to allocate * @dev: device pointer * * Allocate a special sound device by minor number from the sound * subsystem. * * Return: The allocated number is returned on success. On failure, * a negative error code is returned. */ int register_sound_special_device(const struct file_operations *fops, int unit, struct device *dev) { const int chain = unit % SOUND_STEP; int max_unit = 256; const char *name; char _name[16]; switch (chain) { case 0: name = "mixer"; break; case 1: name = "sequencer"; if (unit >= SOUND_STEP) goto __unknown; max_unit = unit + 1; break; case 2: name = "midi"; break; case 3: name = "dsp"; break; case 4: name = "audio"; break; case 5: name = "dspW"; break; case 8: name = "sequencer2"; if (unit >= SOUND_STEP) goto __unknown; max_unit = unit + 1; break; case 9: name = "dmmidi"; break; case 10: name = "dmfm"; break; case 12: name = "adsp"; break; case 13: name = "amidi"; break; case 14: name = "admmidi"; break; default: { __unknown: sprintf(_name, "unknown%d", chain); if (unit >= SOUND_STEP) strcat(_name, "-"); name = _name; } break; } return sound_insert_unit(&chains[chain], fops, -1, unit, max_unit, name, S_IRUSR | S_IWUSR, dev); } EXPORT_SYMBOL(register_sound_special_device); int register_sound_special(const struct file_operations *fops, int unit) { return register_sound_special_device(fops, unit, NULL); } EXPORT_SYMBOL(register_sound_special); /** * register_sound_mixer - register a mixer device * @fops: File operations for the driver * @dev: Unit number to allocate * * Allocate a mixer device. Unit is the number of the mixer requested. * Pass -1 to request the next free mixer unit. * * Return: On success, the allocated number is returned. On failure, * a negative error code is returned. */ int register_sound_mixer(const struct file_operations *fops, int dev) { return sound_insert_unit(&chains[0], fops, dev, 0, 128, "mixer", S_IRUSR | S_IWUSR, NULL); } EXPORT_SYMBOL(register_sound_mixer); /** * register_sound_midi - register a midi device * @fops: File operations for the driver * @dev: Unit number to allocate * * Allocate a midi device. Unit is the number of the midi device requested. * Pass -1 to request the next free midi unit. * * Return: On success, the allocated number is returned. On failure, * a negative error code is returned. */ int register_sound_midi(const struct file_operations *fops, int dev) { return sound_insert_unit(&chains[2], fops, dev, 2, 130, "midi", S_IRUSR | S_IWUSR, NULL); } EXPORT_SYMBOL(register_sound_midi); /* * DSP's are registered as a triple. Register only one and cheat * in open - see below. */ /** * register_sound_dsp - register a DSP device * @fops: File operations for the driver * @dev: Unit number to allocate * * Allocate a DSP device. Unit is the number of the DSP requested. * Pass -1 to request the next free DSP unit. * * This function allocates both the audio and dsp device entries together * and will always allocate them as a matching pair - eg dsp3/audio3 * * Return: On success, the allocated number is returned. On failure, * a negative error code is returned. */ int register_sound_dsp(const struct file_operations *fops, int dev) { return sound_insert_unit(&chains[3], fops, dev, 3, 131, "dsp", S_IWUSR | S_IRUSR, NULL); } EXPORT_SYMBOL(register_sound_dsp); /** * unregister_sound_special - unregister a special sound device * @unit: unit number to allocate * * Release a sound device that was allocated with * register_sound_special(). The unit passed is the return value from * the register function. */ void unregister_sound_special(int unit) { sound_remove_unit(&chains[unit % SOUND_STEP], unit); } EXPORT_SYMBOL(unregister_sound_special); /** * unregister_sound_mixer - unregister a mixer * @unit: unit number to allocate * * Release a sound device that was allocated with register_sound_mixer(). * The unit passed is the return value from the register function. */ void unregister_sound_mixer(int unit) { sound_remove_unit(&chains[0], unit); } EXPORT_SYMBOL(unregister_sound_mixer); /** * unregister_sound_midi - unregister a midi device * @unit: unit number to allocate * * Release a sound device that was allocated with register_sound_midi(). * The unit passed is the return value from the register function. */ void unregister_sound_midi(int unit) { sound_remove_unit(&chains[2], unit); } EXPORT_SYMBOL(unregister_sound_midi); /** * unregister_sound_dsp - unregister a DSP device * @unit: unit number to allocate * * Release a sound device that was allocated with register_sound_dsp(). * The unit passed is the return value from the register function. * * Both of the allocated units are released together automatically. */ void unregister_sound_dsp(int unit) { sound_remove_unit(&chains[3], unit); } EXPORT_SYMBOL(unregister_sound_dsp); static struct sound_unit *__look_for_unit(int chain, int unit) { struct sound_unit *s; s=chains[chain]; while(s && s->unit_minor <= unit) { if(s->unit_minor==unit) return s; s=s->next; } return NULL; } static int soundcore_open(struct inode *inode, struct file *file) { int chain; int unit = iminor(inode); struct sound_unit *s; const struct file_operations *new_fops = NULL; chain=unit&0x0F; if(chain==4 || chain==5) /* dsp/audio/dsp16 */ { unit&=0xF0; unit|=3; chain=3; } spin_lock(&sound_loader_lock); s = __look_for_unit(chain, unit); if (s) new_fops = fops_get(s->unit_fops); if (preclaim_oss && !new_fops) { spin_unlock(&sound_loader_lock); /* * Please, don't change this order or code. * For ALSA slot means soundcard and OSS emulation code * comes as add-on modules which aren't depend on * ALSA toplevel modules for soundcards, thus we need * load them at first. [Jaroslav Kysela <perex@jcu.cz>] */ request_module("sound-slot-%i", unit>>4); request_module("sound-service-%i-%i", unit>>4, chain); /* * sound-slot/service-* module aliases are scheduled * for removal in favor of the standard char-major-* * module aliases. For the time being, generate both * the legacy and standard module aliases to ease * transition. */ if (request_module("char-major-%d-%d", SOUND_MAJOR, unit) > 0) request_module("char-major-%d", SOUND_MAJOR); spin_lock(&sound_loader_lock); s = __look_for_unit(chain, unit); if (s) new_fops = fops_get(s->unit_fops); } spin_unlock(&sound_loader_lock); if (new_fops) { /* * We rely upon the fact that we can't be unloaded while the * subdriver is there. */ int err = 0; replace_fops(file, new_fops); if (file->f_op->open) err = file->f_op->open(inode,file); return err; } return -ENODEV; } MODULE_ALIAS_CHARDEV_MAJOR(SOUND_MAJOR); static void cleanup_oss_soundcore(void) { /* We have nothing to really do here - we know the lists must be empty */ unregister_chrdev(SOUND_MAJOR, "sound"); } static int __init init_oss_soundcore(void) { if (preclaim_oss && register_chrdev(SOUND_MAJOR, "sound", &soundcore_fops) < 0) { printk(KERN_ERR "soundcore: sound device already in use.\n"); return -EBUSY; } return 0; } #endif /* CONFIG_SOUND_OSS_CORE */ |
| 18 37 31 1 7 6 37 14 35 25 4 4 15 21 22 35 354 351 17 16 15 13 7 6 5 3 6 6 6 7 14 17 12 7 5 12 6 6 6 6 6 12 49 13 13 12 49 19 1 21 21 7 21 13 21 1 12 23 22 9 13 1 9 3 9 9 9 3 3 9 4 9 1 9 22 116 29 29 29 29 20 28 4 4 4 29 29 1 29 116 109 26 1 26 26 24 24 24 23 23 23 23 2 2 28 28 2 2 68 30 30 28 30 66 68 158 157 157 156 41 40 40 2 39 39 3 2 39 2 39 37 12 8 118 115 151 147 152 14 2 13 148 2 151 123 93 142 9 117 151 3 61 151 28 150 150 151 150 148 149 148 150 147 120 5 119 114 143 151 8 4 3 2 2 3 5 4 3 2 2 5 8 8 2 2 4 3 2 1 1 180 4 3 173 180 8 8 8 2 3 2 1 5 4 46 6 5 34 46 8 52 1 1 52 20 4 20 59 21 1 59 4 4 3 4 3 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * RAW sockets for IPv6 * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Adapted from linux/net/ipv4/raw.c * * Fixes: * Hideaki YOSHIFUJI : sin6_scope_id support * YOSHIFUJI,H.@USAGI : raw checksum (RFC2292(bis) compliance) * Kazunori MIYAZAWA @USAGI: change process style to use ip6_append_data * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/slab.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/icmpv6.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> #include <linux/skbuff.h> #include <linux/compat.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ipv6.h> #include <net/ndisc.h> #include <net/protocol.h> #include <net/ip6_route.h> #include <net/ip6_checksum.h> #include <net/addrconf.h> #include <net/transp_v6.h> #include <net/udp.h> #include <net/inet_common.h> #include <net/tcp_states.h> #if IS_ENABLED(CONFIG_IPV6_MIP6) #include <net/mip6.h> #endif #include <linux/mroute6.h> #include <net/raw.h> #include <net/rawv6.h> #include <net/xfrm.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/export.h> #define ICMPV6_HDRLEN 4 /* ICMPv6 header, RFC 4443 Section 2.1 */ struct raw_hashinfo raw_v6_hashinfo = { .lock = __RW_LOCK_UNLOCKED(raw_v6_hashinfo.lock), }; EXPORT_SYMBOL_GPL(raw_v6_hashinfo); struct sock *__raw_v6_lookup(struct net *net, struct sock *sk, unsigned short num, const struct in6_addr *loc_addr, const struct in6_addr *rmt_addr, int dif, int sdif) { bool is_multicast = ipv6_addr_is_multicast(loc_addr); sk_for_each_from(sk) if (inet_sk(sk)->inet_num == num) { if (!net_eq(sock_net(sk), net)) continue; if (!ipv6_addr_any(&sk->sk_v6_daddr) && !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) continue; if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif && sk->sk_bound_dev_if != sdif) continue; if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) { if (ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr)) goto found; if (is_multicast && inet6_mc_check(sk, loc_addr, rmt_addr)) goto found; continue; } goto found; } sk = NULL; found: return sk; } EXPORT_SYMBOL_GPL(__raw_v6_lookup); /* * 0 - deliver * 1 - block */ static int icmpv6_filter(const struct sock *sk, const struct sk_buff *skb) { struct icmp6hdr _hdr; const struct icmp6hdr *hdr; /* We require only the four bytes of the ICMPv6 header, not any * additional bytes of message body in "struct icmp6hdr". */ hdr = skb_header_pointer(skb, skb_transport_offset(skb), ICMPV6_HDRLEN, &_hdr); if (hdr) { const __u32 *data = &raw6_sk(sk)->filter.data[0]; unsigned int type = hdr->icmp6_type; return (data[type >> 5] & (1U << (type & 31))) != 0; } return 1; } #if IS_ENABLED(CONFIG_IPV6_MIP6) typedef int mh_filter_t(struct sock *sock, struct sk_buff *skb); static mh_filter_t __rcu *mh_filter __read_mostly; int rawv6_mh_filter_register(mh_filter_t filter) { rcu_assign_pointer(mh_filter, filter); return 0; } EXPORT_SYMBOL(rawv6_mh_filter_register); int rawv6_mh_filter_unregister(mh_filter_t filter) { RCU_INIT_POINTER(mh_filter, NULL); synchronize_rcu(); return 0; } EXPORT_SYMBOL(rawv6_mh_filter_unregister); #endif /* * demultiplex raw sockets. * (should consider queueing the skb in the sock receive_queue * without calling rawv6.c) * * Caller owns SKB so we must make clones. */ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) { const struct in6_addr *saddr; const struct in6_addr *daddr; struct sock *sk; bool delivered = false; __u8 hash; struct net *net; saddr = &ipv6_hdr(skb)->saddr; daddr = saddr + 1; hash = nexthdr & (RAW_HTABLE_SIZE - 1); read_lock(&raw_v6_hashinfo.lock); sk = sk_head(&raw_v6_hashinfo.ht[hash]); if (!sk) goto out; net = dev_net(skb->dev); sk = __raw_v6_lookup(net, sk, nexthdr, daddr, saddr, inet6_iif(skb), inet6_sdif(skb)); while (sk) { int filtered; delivered = true; switch (nexthdr) { case IPPROTO_ICMPV6: filtered = icmpv6_filter(sk, skb); break; #if IS_ENABLED(CONFIG_IPV6_MIP6) case IPPROTO_MH: { /* XXX: To validate MH only once for each packet, * this is placed here. It should be after checking * xfrm policy, however it doesn't. The checking xfrm * policy is placed in rawv6_rcv() because it is * required for each socket. */ mh_filter_t *filter; filter = rcu_dereference(mh_filter); filtered = filter ? (*filter)(sk, skb) : 0; break; } #endif default: filtered = 0; break; } if (filtered < 0) break; if (filtered == 0) { struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC); /* Not releasing hash table! */ if (clone) { nf_reset(clone); rawv6_rcv(sk, clone); } } sk = __raw_v6_lookup(net, sk_next(sk), nexthdr, daddr, saddr, inet6_iif(skb), inet6_sdif(skb)); } out: read_unlock(&raw_v6_hashinfo.lock); return delivered; } bool raw6_local_deliver(struct sk_buff *skb, int nexthdr) { struct sock *raw_sk; raw_sk = sk_head(&raw_v6_hashinfo.ht[nexthdr & (RAW_HTABLE_SIZE - 1)]); if (raw_sk && !ipv6_raw_deliver(skb, nexthdr)) raw_sk = NULL; return raw_sk != NULL; } /* This cleans up af_inet6 a bit. -DaveM */ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct sockaddr_in6 *addr = (struct sockaddr_in6 *) uaddr; __be32 v4addr = 0; int addr_type; int err; if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; if (addr->sin6_family != AF_INET6) return -EINVAL; addr_type = ipv6_addr_type(&addr->sin6_addr); /* Raw sockets are IPv6 only */ if (addr_type == IPV6_ADDR_MAPPED) return -EADDRNOTAVAIL; lock_sock(sk); err = -EINVAL; if (sk->sk_state != TCP_CLOSE) goto out; rcu_read_lock(); /* Check if the address belongs to the host. */ if (addr_type != IPV6_ADDR_ANY) { struct net_device *dev = NULL; if (__ipv6_addr_needs_scope_id(addr_type)) { if (addr_len >= sizeof(struct sockaddr_in6) && addr->sin6_scope_id) { /* Override any existing binding, if another * one is supplied by user. */ sk->sk_bound_dev_if = addr->sin6_scope_id; } /* Binding to link-local address requires an interface */ if (!sk->sk_bound_dev_if) goto out_unlock; } if (sk->sk_bound_dev_if) { err = -ENODEV; dev = dev_get_by_index_rcu(sock_net(sk), sk->sk_bound_dev_if); if (!dev) goto out_unlock; } /* ipv4 addr of the socket is invalid. Only the * unspecified and mapped address have a v4 equivalent. */ v4addr = LOOPBACK4_IPV6; if (!(addr_type & IPV6_ADDR_MULTICAST) && !sock_net(sk)->ipv6.sysctl.ip_nonlocal_bind) { err = -EADDRNOTAVAIL; if (!ipv6_chk_addr(sock_net(sk), &addr->sin6_addr, dev, 0)) { goto out_unlock; } } } inet->inet_rcv_saddr = inet->inet_saddr = v4addr; sk->sk_v6_rcv_saddr = addr->sin6_addr; if (!(addr_type & IPV6_ADDR_MULTICAST)) np->saddr = addr->sin6_addr; err = 0; out_unlock: rcu_read_unlock(); out: release_sock(sk); return err; } static void rawv6_err(struct sock *sk, struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); int err; int harderr; /* Report error on raw socket, if: 1. User requested recverr. 2. Socket is connected (otherwise the error indication is useless without recverr and error is hard. */ if (!np->recverr && sk->sk_state != TCP_ESTABLISHED) return; harderr = icmpv6_err_convert(type, code, &err); if (type == ICMPV6_PKT_TOOBIG) { ip6_sk_update_pmtu(skb, sk, info); harderr = (np->pmtudisc == IPV6_PMTUDISC_DO); } if (type == NDISC_REDIRECT) { ip6_sk_redirect(skb, sk); return; } if (np->recverr) { u8 *payload = skb->data; if (!inet->hdrincl) payload += offset; ipv6_icmp_error(sk, skb, err, 0, ntohl(info), payload); } if (np->recverr || harderr) { sk->sk_err = err; sk->sk_error_report(sk); } } void raw6_icmp_error(struct sk_buff *skb, int nexthdr, u8 type, u8 code, int inner_offset, __be32 info) { struct sock *sk; int hash; const struct in6_addr *saddr, *daddr; struct net *net; hash = nexthdr & (RAW_HTABLE_SIZE - 1); read_lock(&raw_v6_hashinfo.lock); sk = sk_head(&raw_v6_hashinfo.ht[hash]); if (sk) { /* Note: ipv6_hdr(skb) != skb->data */ const struct ipv6hdr *ip6h = (const struct ipv6hdr *)skb->data; saddr = &ip6h->saddr; daddr = &ip6h->daddr; net = dev_net(skb->dev); while ((sk = __raw_v6_lookup(net, sk, nexthdr, saddr, daddr, inet6_iif(skb), inet6_iif(skb)))) { rawv6_err(sk, skb, NULL, type, code, inner_offset, info); sk = sk_next(sk); } } read_unlock(&raw_v6_hashinfo.lock); } static inline int rawv6_rcv_skb(struct sock *sk, struct sk_buff *skb) { if ((raw6_sk(sk)->checksum || rcu_access_pointer(sk->sk_filter)) && skb_checksum_complete(skb)) { atomic_inc(&sk->sk_drops); kfree_skb(skb); return NET_RX_DROP; } /* Charge it to the socket. */ skb_dst_drop(skb); if (sock_queue_rcv_skb(sk, skb) < 0) { kfree_skb(skb); return NET_RX_DROP; } return 0; } /* * This is next to useless... * if we demultiplex in network layer we don't need the extra call * just to queue the skb... * maybe we could have the network decide upon a hint if it * should call raw_rcv for demultiplexing */ int rawv6_rcv(struct sock *sk, struct sk_buff *skb) { struct inet_sock *inet = inet_sk(sk); struct raw6_sock *rp = raw6_sk(sk); if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) { atomic_inc(&sk->sk_drops); kfree_skb(skb); return NET_RX_DROP; } if (!rp->checksum) skb->ip_summed = CHECKSUM_UNNECESSARY; if (skb->ip_summed == CHECKSUM_COMPLETE) { skb_postpull_rcsum(skb, skb_network_header(skb), skb_network_header_len(skb)); if (!csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->len, inet->inet_num, skb->csum)) skb->ip_summed = CHECKSUM_UNNECESSARY; } if (!skb_csum_unnecessary(skb)) skb->csum = ~csum_unfold(csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->len, inet->inet_num, 0)); if (inet->hdrincl) { if (skb_checksum_complete(skb)) { atomic_inc(&sk->sk_drops); kfree_skb(skb); return NET_RX_DROP; } } rawv6_rcv_skb(sk, skb); return 0; } /* * This should be easy, if there is something there * we return it, otherwise we block. */ static int rawv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); struct sk_buff *skb; size_t copied; int err; if (flags & MSG_OOB) return -EOPNOTSUPP; if (flags & MSG_ERRQUEUE) return ipv6_recv_error(sk, msg, len, addr_len); if (np->rxpmtu && np->rxopt.bits.rxpmtu) return ipv6_recv_rxpmtu(sk, msg, len, addr_len); skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) goto out; copied = skb->len; if (copied > len) { copied = len; msg->msg_flags |= MSG_TRUNC; } if (skb_csum_unnecessary(skb)) { err = skb_copy_datagram_msg(skb, 0, msg, copied); } else if (msg->msg_flags&MSG_TRUNC) { if (__skb_checksum_complete(skb)) goto csum_copy_err; err = skb_copy_datagram_msg(skb, 0, msg, copied); } else { err = skb_copy_and_csum_datagram_msg(skb, 0, msg); if (err == -EINVAL) goto csum_copy_err; } if (err) goto out_free; /* Copy the address. */ if (sin6) { sin6->sin6_family = AF_INET6; sin6->sin6_port = 0; sin6->sin6_addr = ipv6_hdr(skb)->saddr; sin6->sin6_flowinfo = 0; sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr, inet6_iif(skb)); *addr_len = sizeof(*sin6); } sock_recv_ts_and_drops(msg, sk, skb); if (np->rxopt.all) ip6_datagram_recv_ctl(sk, msg, skb); err = copied; if (flags & MSG_TRUNC) err = skb->len; out_free: skb_free_datagram(sk, skb); out: return err; csum_copy_err: skb_kill_datagram(sk, skb, flags); /* Error for blocking case is chosen to masquerade as some normal condition. */ err = (flags&MSG_DONTWAIT) ? -EAGAIN : -EHOSTUNREACH; goto out; } static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, struct raw6_sock *rp) { struct ipv6_txoptions *opt; struct sk_buff *skb; int err = 0; int offset; int len; int total_len; __wsum tmp_csum; __sum16 csum; if (!rp->checksum) goto send; skb = skb_peek(&sk->sk_write_queue); if (!skb) goto out; offset = rp->offset; total_len = inet_sk(sk)->cork.base.length; opt = inet6_sk(sk)->cork.opt; total_len -= opt ? opt->opt_flen : 0; if (offset >= total_len - 1) { err = -EINVAL; ip6_flush_pending_frames(sk); goto out; } /* should be check HW csum miyazawa */ if (skb_queue_len(&sk->sk_write_queue) == 1) { /* * Only one fragment on the socket. */ tmp_csum = skb->csum; } else { struct sk_buff *csum_skb = NULL; tmp_csum = 0; skb_queue_walk(&sk->sk_write_queue, skb) { tmp_csum = csum_add(tmp_csum, skb->csum); if (csum_skb) continue; len = skb->len - skb_transport_offset(skb); if (offset >= len) { offset -= len; continue; } csum_skb = skb; } skb = csum_skb; } offset += skb_transport_offset(skb); err = skb_copy_bits(skb, offset, &csum, 2); if (err < 0) { ip6_flush_pending_frames(sk); goto out; } /* in case cksum was not initialized */ if (unlikely(csum)) tmp_csum = csum_sub(tmp_csum, csum_unfold(csum)); csum = csum_ipv6_magic(&fl6->saddr, &fl6->daddr, total_len, fl6->flowi6_proto, tmp_csum); if (csum == 0 && fl6->flowi6_proto == IPPROTO_UDP) csum = CSUM_MANGLED_0; BUG_ON(skb_store_bits(skb, offset, &csum, 2)); send: err = ip6_push_pending_frames(sk); out: return err; } static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, struct flowi6 *fl6, struct dst_entry **dstp, unsigned int flags, const struct sockcm_cookie *sockc) { struct ipv6_pinfo *np = inet6_sk(sk); struct net *net = sock_net(sk); struct ipv6hdr *iph; struct sk_buff *skb; int err; struct rt6_info *rt = (struct rt6_info *)*dstp; int hlen = LL_RESERVED_SPACE(rt->dst.dev); int tlen = rt->dst.dev->needed_tailroom; if (length > rt->dst.dev->mtu) { ipv6_local_error(sk, EMSGSIZE, fl6, rt->dst.dev->mtu); return -EMSGSIZE; } if (length < sizeof(struct ipv6hdr)) return -EINVAL; if (flags&MSG_PROBE) goto out; skb = sock_alloc_send_skb(sk, length + hlen + tlen + 15, flags & MSG_DONTWAIT, &err); if (!skb) goto error; skb_reserve(skb, hlen); skb->protocol = htons(ETH_P_IPV6); skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; skb_put(skb, length); skb_reset_network_header(skb); iph = ipv6_hdr(skb); skb->ip_summed = CHECKSUM_NONE; skb_setup_tx_timestamp(skb, sockc->tsflags); if (flags & MSG_CONFIRM) skb_set_dst_pending_confirm(skb, 1); skb->transport_header = skb->network_header; err = memcpy_from_msg(iph, msg, length); if (err) { err = -EFAULT; kfree_skb(skb); goto error; } skb_dst_set(skb, &rt->dst); *dstp = NULL; /* if egress device is enslaved to an L3 master device pass the * skb to its handler for processing */ skb = l3mdev_ip6_out(sk, skb); if (unlikely(!skb)) return 0; /* Acquire rcu_read_lock() in case we need to use rt->rt6i_idev * in the error path. Since skb has been freed, the dst could * have been queued for deletion. */ rcu_read_lock(); IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, rt->dst.dev, dst_output); if (err > 0) err = net_xmit_errno(err); if (err) { IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); rcu_read_unlock(); goto error_check; } rcu_read_unlock(); out: return 0; error: IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); error_check: if (err == -ENOBUFS && !np->recverr) err = 0; return err; } struct raw6_frag_vec { struct msghdr *msg; int hlen; char c[4]; }; static int rawv6_probe_proto_opt(struct raw6_frag_vec *rfv, struct flowi6 *fl6) { int err = 0; switch (fl6->flowi6_proto) { case IPPROTO_ICMPV6: rfv->hlen = 2; err = memcpy_from_msg(rfv->c, rfv->msg, rfv->hlen); if (!err) { fl6->fl6_icmp_type = rfv->c[0]; fl6->fl6_icmp_code = rfv->c[1]; } break; case IPPROTO_MH: rfv->hlen = 4; err = memcpy_from_msg(rfv->c, rfv->msg, rfv->hlen); if (!err) fl6->fl6_mh_type = rfv->c[2]; } return err; } static int raw6_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) { struct raw6_frag_vec *rfv = from; if (offset < rfv->hlen) { int copy = min(rfv->hlen - offset, len); if (skb->ip_summed == CHECKSUM_PARTIAL) memcpy(to, rfv->c + offset, copy); else skb->csum = csum_block_add( skb->csum, csum_partial_copy_nocheck(rfv->c + offset, to, copy, 0), odd); odd = 0; offset += copy; to += copy; len -= copy; if (!len) return 0; } offset -= rfv->hlen; return ip_generic_getfrag(rfv->msg, to, offset, len, odd, skb); } static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct ipv6_txoptions *opt_to_free = NULL; struct ipv6_txoptions opt_space; DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); struct in6_addr *daddr, *final_p, final; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct raw6_sock *rp = raw6_sk(sk); struct ipv6_txoptions *opt = NULL; struct ip6_flowlabel *flowlabel = NULL; struct dst_entry *dst = NULL; struct raw6_frag_vec rfv; struct flowi6 fl6; struct sockcm_cookie sockc; struct ipcm6_cookie ipc6; int addr_len = msg->msg_namelen; int hdrincl; u16 proto; int err; /* Rough check on arithmetic overflow, better check is made in ip6_append_data(). */ if (len > INT_MAX) return -EMSGSIZE; /* Mirror BSD error message compatibility */ if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; /* hdrincl should be READ_ONCE(inet->hdrincl) * but READ_ONCE() doesn't work with bit fields. * Doing this indirectly yields the same result. */ hdrincl = inet->hdrincl; hdrincl = READ_ONCE(hdrincl); /* * Get and verify the address. */ memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_mark = sk->sk_mark; fl6.flowi6_uid = sk->sk_uid; ipc6.hlimit = -1; ipc6.tclass = -1; ipc6.dontfrag = -1; ipc6.opt = NULL; if (sin6) { if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; if (sin6->sin6_family && sin6->sin6_family != AF_INET6) return -EAFNOSUPPORT; /* port is the proto value [0..255] carried in nexthdr */ proto = ntohs(sin6->sin6_port); if (!proto) proto = inet->inet_num; else if (proto != inet->inet_num) return -EINVAL; if (proto > 255) return -EINVAL; daddr = &sin6->sin6_addr; if (np->sndflow) { fl6.flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK; if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) { flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (!flowlabel) return -EINVAL; } } /* * Otherwise it will be difficult to maintain * sk->sk_dst_cache. */ if (sk->sk_state == TCP_ESTABLISHED && ipv6_addr_equal(daddr, &sk->sk_v6_daddr)) daddr = &sk->sk_v6_daddr; if (addr_len >= sizeof(struct sockaddr_in6) && sin6->sin6_scope_id && __ipv6_addr_needs_scope_id(__ipv6_addr_type(daddr))) fl6.flowi6_oif = sin6->sin6_scope_id; } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; proto = inet->inet_num; daddr = &sk->sk_v6_daddr; fl6.flowlabel = np->flow_label; } if (fl6.flowi6_oif == 0) fl6.flowi6_oif = sk->sk_bound_dev_if; sockc.tsflags = sk->sk_tsflags; if (msg->msg_controllen) { opt = &opt_space; memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(struct ipv6_txoptions); ipc6.opt = opt; err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6, &sockc); if (err < 0) { fl6_sock_release(flowlabel); return err; } if ((fl6.flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) { flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (!flowlabel) return -EINVAL; } if (!(opt->opt_nflen|opt->opt_flen)) opt = NULL; } if (!opt) { opt = txopt_get(np); opt_to_free = opt; } if (flowlabel) opt = fl6_merge_options(&opt_space, flowlabel, opt); opt = ipv6_fixup_options(&opt_space, opt); fl6.flowi6_proto = proto; if (!hdrincl) { rfv.msg = msg; rfv.hlen = 0; err = rawv6_probe_proto_opt(&rfv, &fl6); if (err) goto out; } if (!ipv6_addr_any(daddr)) fl6.daddr = *daddr; else fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr)) fl6.saddr = np->saddr; final_p = fl6_update_dst(&fl6, opt, &final); if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) fl6.flowi6_oif = np->mcast_oif; else if (!fl6.flowi6_oif) fl6.flowi6_oif = np->ucast_oif; security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); if (hdrincl) fl6.flowi6_flags |= FLOWI_FLAG_KNOWN_NH; if (ipc6.tclass < 0) ipc6.tclass = np->tclass; fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto out; } if (ipc6.hlimit < 0) ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); if (ipc6.dontfrag < 0) ipc6.dontfrag = np->dontfrag; if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; back_from_confirm: if (hdrincl) err = rawv6_send_hdrinc(sk, msg, len, &fl6, &dst, msg->msg_flags, &sockc); else { ipc6.opt = opt; lock_sock(sk); err = ip6_append_data(sk, raw6_getfrag, &rfv, len, 0, &ipc6, &fl6, (struct rt6_info *)dst, msg->msg_flags, &sockc); if (err) ip6_flush_pending_frames(sk); else if (!(msg->msg_flags & MSG_MORE)) err = rawv6_push_pending_frames(sk, &fl6, rp); release_sock(sk); } done: dst_release(dst); out: fl6_sock_release(flowlabel); txopt_put(opt_to_free); return err < 0 ? err : len; do_confirm: if (msg->msg_flags & MSG_PROBE) dst_confirm_neigh(dst, &fl6.daddr); if (!(msg->msg_flags & MSG_PROBE) || len) goto back_from_confirm; err = 0; goto done; } static int rawv6_seticmpfilter(struct sock *sk, int level, int optname, char __user *optval, int optlen) { switch (optname) { case ICMPV6_FILTER: if (optlen > sizeof(struct icmp6_filter)) optlen = sizeof(struct icmp6_filter); if (copy_from_user(&raw6_sk(sk)->filter, optval, optlen)) return -EFAULT; return 0; default: return -ENOPROTOOPT; } return 0; } static int rawv6_geticmpfilter(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { int len; switch (optname) { case ICMPV6_FILTER: if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; if (len > sizeof(struct icmp6_filter)) len = sizeof(struct icmp6_filter); if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &raw6_sk(sk)->filter, len)) return -EFAULT; return 0; default: return -ENOPROTOOPT; } return 0; } static int do_rawv6_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen) { struct raw6_sock *rp = raw6_sk(sk); int val; if (get_user(val, (int __user *)optval)) return -EFAULT; switch (optname) { case IPV6_HDRINCL: if (sk->sk_type != SOCK_RAW) return -EINVAL; inet_sk(sk)->hdrincl = !!val; return 0; case IPV6_CHECKSUM: if (inet_sk(sk)->inet_num == IPPROTO_ICMPV6 && level == IPPROTO_IPV6) { /* * RFC3542 tells that IPV6_CHECKSUM socket * option in the IPPROTO_IPV6 level is not * allowed on ICMPv6 sockets. * If you want to set it, use IPPROTO_RAW * level IPV6_CHECKSUM socket option * (Linux extension). */ return -EINVAL; } /* You may get strange result with a positive odd offset; RFC2292bis agrees with me. */ if (val > 0 && (val&1)) return -EINVAL; if (val < 0) { rp->checksum = 0; } else { rp->checksum = 1; rp->offset = val; } return 0; default: return -ENOPROTOOPT; } } static int rawv6_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen) { switch (level) { case SOL_RAW: break; case SOL_ICMPV6: if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; return rawv6_seticmpfilter(sk, level, optname, optval, optlen); case SOL_IPV6: if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; default: return ipv6_setsockopt(sk, level, optname, optval, optlen); } return do_rawv6_setsockopt(sk, level, optname, optval, optlen); } #ifdef CONFIG_COMPAT static int compat_rawv6_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen) { switch (level) { case SOL_RAW: break; case SOL_ICMPV6: if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; return rawv6_seticmpfilter(sk, level, optname, optval, optlen); case SOL_IPV6: if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; default: return compat_ipv6_setsockopt(sk, level, optname, optval, optlen); } return do_rawv6_setsockopt(sk, level, optname, optval, optlen); } #endif static int do_rawv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { struct raw6_sock *rp = raw6_sk(sk); int val, len; if (get_user(len, optlen)) return -EFAULT; switch (optname) { case IPV6_HDRINCL: val = inet_sk(sk)->hdrincl; break; case IPV6_CHECKSUM: /* * We allow getsockopt() for IPPROTO_IPV6-level * IPV6_CHECKSUM socket option on ICMPv6 sockets * since RFC3542 is silent about it. */ if (rp->checksum == 0) |