| 6 6 6 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 | // SPDX-License-Identifier: GPL-2.0-only /* * * Copyright (C) 2005 Mike Isely <isely@pobox.com> * Copyright (C) 2004 Aurelien Alleaume <slts@free.fr> */ #include <linux/kernel.h> #include <linux/errno.h> #include <linux/module.h> #include <linux/usb.h> #include <linux/videodev2.h> #include "pvrusb2-hdw.h" #include "pvrusb2-devattr.h" #include "pvrusb2-context.h" #include "pvrusb2-debug.h" #include "pvrusb2-v4l2.h" #include "pvrusb2-sysfs.h" #define DRIVER_AUTHOR "Mike Isely <isely@pobox.com>" #define DRIVER_DESC "Hauppauge WinTV-PVR-USB2 MPEG2 Encoder/Tuner" #define DRIVER_VERSION "V4L in-tree version" #define DEFAULT_DEBUG_MASK (PVR2_TRACE_ERROR_LEGS| \ PVR2_TRACE_INFO| \ PVR2_TRACE_STD| \ PVR2_TRACE_TOLERANCE| \ PVR2_TRACE_TRAP| \ 0) int pvrusb2_debug = DEFAULT_DEBUG_MASK; module_param_named(debug,pvrusb2_debug,int,S_IRUGO|S_IWUSR); MODULE_PARM_DESC(debug, "Debug trace mask"); static void pvr_setup_attach(struct pvr2_context *pvr) { /* Create association with v4l layer */ pvr2_v4l2_create(pvr); #ifdef CONFIG_VIDEO_PVRUSB2_DVB /* Create association with dvb layer */ pvr2_dvb_create(pvr); #endif pvr2_sysfs_create(pvr); } static int pvr_probe(struct usb_interface *intf, const struct usb_device_id *devid) { struct pvr2_context *pvr; /* Create underlying hardware interface */ pvr = pvr2_context_create(intf,devid,pvr_setup_attach); if (!pvr) { pvr2_trace(PVR2_TRACE_ERROR_LEGS, "Failed to create hdw handler"); return -ENOMEM; } pvr2_trace(PVR2_TRACE_INIT,"pvr_probe(pvr=%p)",pvr); usb_set_intfdata(intf, pvr); return 0; } /* * pvr_disconnect() * */ static void pvr_disconnect(struct usb_interface *intf) { struct pvr2_context *pvr = usb_get_intfdata(intf); pvr2_trace(PVR2_TRACE_INIT,"pvr_disconnect(pvr=%p) BEGIN",pvr); usb_set_intfdata (intf, NULL); pvr2_context_disconnect(pvr); pvr2_trace(PVR2_TRACE_INIT,"pvr_disconnect(pvr=%p) DONE",pvr); } static struct usb_driver pvr_driver = { .name = "pvrusb2", .id_table = pvr2_device_table, .probe = pvr_probe, .disconnect = pvr_disconnect }; /* * pvr_init() / pvr_exit() * * This code is run to initialize/exit the driver. * */ static int __init pvr_init(void) { int ret; pvr2_trace(PVR2_TRACE_INIT,"pvr_init"); ret = pvr2_context_global_init(); if (ret != 0) { pvr2_trace(PVR2_TRACE_INIT,"pvr_init failure code=%d",ret); return ret; } pvr2_sysfs_class_create(); ret = usb_register(&pvr_driver); if (ret == 0) pr_info("pvrusb2: " DRIVER_VERSION ":" DRIVER_DESC "\n"); if (pvrusb2_debug) pr_info("pvrusb2: Debug mask is %d (0x%x)\n", pvrusb2_debug,pvrusb2_debug); pvr2_trace(PVR2_TRACE_INIT,"pvr_init complete"); return ret; } static void __exit pvr_exit(void) { pvr2_trace(PVR2_TRACE_INIT,"pvr_exit"); usb_deregister(&pvr_driver); pvr2_context_global_done(); pvr2_sysfs_class_destroy(); pvr2_trace(PVR2_TRACE_INIT,"pvr_exit complete"); } module_init(pvr_init); module_exit(pvr_exit); MODULE_AUTHOR(DRIVER_AUTHOR); MODULE_DESCRIPTION(DRIVER_DESC); MODULE_LICENSE("GPL"); MODULE_VERSION("0.9.1"); |
| 11688 2308 11688 2303 305 368 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 | /* SPDX-License-Identifier: GPL-2.0 */ /* rwsem.h: R/W semaphores, public interface * * Written by David Howells (dhowells@redhat.com). * Derived from asm-i386/semaphore.h */ #ifndef _LINUX_RWSEM_H #define _LINUX_RWSEM_H #include <linux/linkage.h> #include <linux/types.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/atomic.h> #include <linux/err.h> #include <linux/cleanup.h> #ifdef CONFIG_DEBUG_LOCK_ALLOC # define __RWSEM_DEP_MAP_INIT(lockname) \ .dep_map = { \ .name = #lockname, \ .wait_type_inner = LD_WAIT_SLEEP, \ }, #else # define __RWSEM_DEP_MAP_INIT(lockname) #endif #ifndef CONFIG_PREEMPT_RT #ifdef CONFIG_RWSEM_SPIN_ON_OWNER #include <linux/osq_lock.h> #endif /* * For an uncontended rwsem, count and owner are the only fields a task * needs to touch when acquiring the rwsem. So they are put next to each * other to increase the chance that they will share the same cacheline. * * In a contended rwsem, the owner is likely the most frequently accessed * field in the structure as the optimistic waiter that holds the osq lock * will spin on owner. For an embedded rwsem, other hot fields in the * containing structure should be moved further away from the rwsem to * reduce the chance that they will share the same cacheline causing * cacheline bouncing problem. */ struct rw_semaphore { atomic_long_t count; /* * Write owner or one of the read owners as well flags regarding * the current state of the rwsem. Can be used as a speculative * check to see if the write owner is running on the cpu. */ atomic_long_t owner; #ifdef CONFIG_RWSEM_SPIN_ON_OWNER struct optimistic_spin_queue osq; /* spinner MCS lock */ #endif raw_spinlock_t wait_lock; struct list_head wait_list; #ifdef CONFIG_DEBUG_RWSEMS void *magic; #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif }; #define RWSEM_UNLOCKED_VALUE 0UL #define RWSEM_WRITER_LOCKED (1UL << 0) #define __RWSEM_COUNT_INIT(name) .count = ATOMIC_LONG_INIT(RWSEM_UNLOCKED_VALUE) static inline int rwsem_is_locked(struct rw_semaphore *sem) { return atomic_long_read(&sem->count) != RWSEM_UNLOCKED_VALUE; } static inline void rwsem_assert_held_nolockdep(const struct rw_semaphore *sem) { WARN_ON(atomic_long_read(&sem->count) == RWSEM_UNLOCKED_VALUE); } static inline void rwsem_assert_held_write_nolockdep(const struct rw_semaphore *sem) { WARN_ON(!(atomic_long_read(&sem->count) & RWSEM_WRITER_LOCKED)); } /* Common initializer macros and functions */ #ifdef CONFIG_DEBUG_RWSEMS # define __RWSEM_DEBUG_INIT(lockname) .magic = &lockname, #else # define __RWSEM_DEBUG_INIT(lockname) #endif #ifdef CONFIG_RWSEM_SPIN_ON_OWNER #define __RWSEM_OPT_INIT(lockname) .osq = OSQ_LOCK_UNLOCKED, #else #define __RWSEM_OPT_INIT(lockname) #endif #define __RWSEM_INITIALIZER(name) \ { __RWSEM_COUNT_INIT(name), \ .owner = ATOMIC_LONG_INIT(0), \ __RWSEM_OPT_INIT(name) \ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock),\ .wait_list = LIST_HEAD_INIT((name).wait_list), \ __RWSEM_DEBUG_INIT(name) \ __RWSEM_DEP_MAP_INIT(name) } #define DECLARE_RWSEM(name) \ struct rw_semaphore name = __RWSEM_INITIALIZER(name) extern void __init_rwsem(struct rw_semaphore *sem, const char *name, struct lock_class_key *key); #define init_rwsem(sem) \ do { \ static struct lock_class_key __key; \ \ __init_rwsem((sem), #sem, &__key); \ } while (0) /* * This is the same regardless of which rwsem implementation that is being used. * It is just a heuristic meant to be called by somebody already holding the * rwsem to see if somebody from an incompatible type is wanting access to the * lock. */ static inline int rwsem_is_contended(struct rw_semaphore *sem) { return !list_empty(&sem->wait_list); } #else /* !CONFIG_PREEMPT_RT */ #include <linux/rwbase_rt.h> struct rw_semaphore { struct rwbase_rt rwbase; #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif }; #define __RWSEM_INITIALIZER(name) \ { \ .rwbase = __RWBASE_INITIALIZER(name), \ __RWSEM_DEP_MAP_INIT(name) \ } #define DECLARE_RWSEM(lockname) \ struct rw_semaphore lockname = __RWSEM_INITIALIZER(lockname) extern void __init_rwsem(struct rw_semaphore *rwsem, const char *name, struct lock_class_key *key); #define init_rwsem(sem) \ do { \ static struct lock_class_key __key; \ \ __init_rwsem((sem), #sem, &__key); \ } while (0) static __always_inline int rwsem_is_locked(const struct rw_semaphore *sem) { return rw_base_is_locked(&sem->rwbase); } static __always_inline void rwsem_assert_held_nolockdep(const struct rw_semaphore *sem) { WARN_ON(!rwsem_is_locked(sem)); } static __always_inline void rwsem_assert_held_write_nolockdep(const struct rw_semaphore *sem) { WARN_ON(!rw_base_is_write_locked(&sem->rwbase)); } static __always_inline int rwsem_is_contended(struct rw_semaphore *sem) { return rw_base_is_contended(&sem->rwbase); } #endif /* CONFIG_PREEMPT_RT */ /* * The functions below are the same for all rwsem implementations including * the RT specific variant. */ static inline void rwsem_assert_held(const struct rw_semaphore *sem) { if (IS_ENABLED(CONFIG_LOCKDEP)) lockdep_assert_held(sem); else rwsem_assert_held_nolockdep(sem); } static inline void rwsem_assert_held_write(const struct rw_semaphore *sem) { if (IS_ENABLED(CONFIG_LOCKDEP)) lockdep_assert_held_write(sem); else rwsem_assert_held_write_nolockdep(sem); } /* * lock for reading */ extern void down_read(struct rw_semaphore *sem); extern int __must_check down_read_interruptible(struct rw_semaphore *sem); extern int __must_check down_read_killable(struct rw_semaphore *sem); /* * trylock for reading -- returns 1 if successful, 0 if contention */ extern int down_read_trylock(struct rw_semaphore *sem); /* * lock for writing */ extern void down_write(struct rw_semaphore *sem); extern int __must_check down_write_killable(struct rw_semaphore *sem); /* * trylock for writing -- returns 1 if successful, 0 if contention */ extern int down_write_trylock(struct rw_semaphore *sem); /* * release a read lock */ extern void up_read(struct rw_semaphore *sem); /* * release a write lock */ extern void up_write(struct rw_semaphore *sem); DEFINE_GUARD(rwsem_read, struct rw_semaphore *, down_read(_T), up_read(_T)) DEFINE_GUARD_COND(rwsem_read, _try, down_read_trylock(_T)) DEFINE_GUARD_COND(rwsem_read, _intr, down_read_interruptible(_T) == 0) DEFINE_GUARD(rwsem_write, struct rw_semaphore *, down_write(_T), up_write(_T)) DEFINE_GUARD_COND(rwsem_write, _try, down_write_trylock(_T)) /* * downgrade write lock to read lock */ extern void downgrade_write(struct rw_semaphore *sem); #ifdef CONFIG_DEBUG_LOCK_ALLOC /* * nested locking. NOTE: rwsems are not allowed to recurse * (which occurs if the same task tries to acquire the same * lock instance multiple times), but multiple locks of the * same lock class might be taken, if the order of the locks * is always the same. This ordering rule can be expressed * to lockdep via the _nested() APIs, but enumerating the * subclasses that are used. (If the nesting relationship is * static then another method for expressing nested locking is * the explicit definition of lock class keys and the use of * lockdep_set_class() at lock initialization time. * See Documentation/locking/lockdep-design.rst for more details.) */ extern void down_read_nested(struct rw_semaphore *sem, int subclass); extern int __must_check down_read_killable_nested(struct rw_semaphore *sem, int subclass); extern void down_write_nested(struct rw_semaphore *sem, int subclass); extern int down_write_killable_nested(struct rw_semaphore *sem, int subclass); extern void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map *nest_lock); # define down_write_nest_lock(sem, nest_lock) \ do { \ typecheck(struct lockdep_map *, &(nest_lock)->dep_map); \ _down_write_nest_lock(sem, &(nest_lock)->dep_map); \ } while (0) /* * Take/release a lock when not the owner will release it. * * [ This API should be avoided as much as possible - the * proper abstraction for this case is completions. ] */ extern void down_read_non_owner(struct rw_semaphore *sem); extern void up_read_non_owner(struct rw_semaphore *sem); #else # define down_read_nested(sem, subclass) down_read(sem) # define down_read_killable_nested(sem, subclass) down_read_killable(sem) # define down_write_nest_lock(sem, nest_lock) down_write(sem) # define down_write_nested(sem, subclass) down_write(sem) # define down_write_killable_nested(sem, subclass) down_write_killable(sem) # define down_read_non_owner(sem) down_read(sem) # define up_read_non_owner(sem) up_read(sem) #endif #endif /* _LINUX_RWSEM_H */ |
| 3 3 6 9 25 25 3 3 3 3 3 3 3 5 3 3 3 3 24 25 5 25 25 25 25 25 24 25 6 6 3 3 3 3 3 3 6 6 6 6 6 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 | // SPDX-License-Identifier: LGPL-2.1+ /* Copyright (C) 2022 Kent Overstreet */ #include <linux/bitmap.h> #include <linux/err.h> #include <linux/export.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/string_helpers.h> #include "printbuf.h" static inline unsigned __printbuf_linelen(struct printbuf *buf, unsigned pos) { return pos - buf->last_newline; } static inline unsigned printbuf_linelen(struct printbuf *buf) { return __printbuf_linelen(buf, buf->pos); } /* * Returns spaces from start of line, if set, or 0 if unset: */ static inline unsigned cur_tabstop(struct printbuf *buf) { return buf->cur_tabstop < buf->nr_tabstops ? buf->_tabstops[buf->cur_tabstop] : 0; } int bch2_printbuf_make_room(struct printbuf *out, unsigned extra) { /* Reserved space for terminating nul: */ extra += 1; if (out->pos + extra <= out->size) return 0; if (!out->heap_allocated) { out->overflow = true; return 0; } unsigned new_size = roundup_pow_of_two(out->size + extra); /* Sanity check... */ if (new_size > PAGE_SIZE << MAX_PAGE_ORDER) { out->allocation_failure = true; out->overflow = true; return -ENOMEM; } /* * Note: output buffer must be freeable with kfree(), it's not required * that the user use printbuf_exit(). */ char *buf = krealloc(out->buf, new_size, !out->atomic ? GFP_KERNEL : GFP_NOWAIT); if (!buf) { out->allocation_failure = true; out->overflow = true; return -ENOMEM; } out->buf = buf; out->size = new_size; return 0; } static void printbuf_advance_pos(struct printbuf *out, unsigned len) { out->pos += min(len, printbuf_remaining(out)); } static void printbuf_insert_spaces(struct printbuf *out, unsigned pos, unsigned nr) { unsigned move = out->pos - pos; bch2_printbuf_make_room(out, nr); if (pos + nr < out->size) memmove(out->buf + pos + nr, out->buf + pos, min(move, out->size - 1 - pos - nr)); if (pos < out->size) memset(out->buf + pos, ' ', min(nr, out->size - pos)); printbuf_advance_pos(out, nr); printbuf_nul_terminate_reserved(out); } static void __printbuf_do_indent(struct printbuf *out, unsigned pos) { while (true) { int pad; unsigned len = out->pos - pos; char *p = out->buf + pos; char *n = memscan(p, '\n', len); if (cur_tabstop(out)) { n = min(n, (char *) memscan(p, '\r', len)); n = min(n, (char *) memscan(p, '\t', len)); } pos = n - out->buf; if (pos == out->pos) break; switch (*n) { case '\n': pos++; out->last_newline = pos; printbuf_insert_spaces(out, pos, out->indent); pos = min(pos + out->indent, out->pos); out->last_field = pos; out->cur_tabstop = 0; break; case '\r': memmove(n, n + 1, out->pos - pos); --out->pos; pad = (int) cur_tabstop(out) - (int) __printbuf_linelen(out, pos); if (pad > 0) { printbuf_insert_spaces(out, out->last_field, pad); pos += pad; } out->last_field = pos; out->cur_tabstop++; break; case '\t': pad = (int) cur_tabstop(out) - (int) __printbuf_linelen(out, pos) - 1; if (pad > 0) { *n = ' '; printbuf_insert_spaces(out, pos, pad - 1); pos += pad; } else { memmove(n, n + 1, out->pos - pos); --out->pos; } out->last_field = pos; out->cur_tabstop++; break; } } } static inline void printbuf_do_indent(struct printbuf *out, unsigned pos) { if (out->has_indent_or_tabstops && !out->suppress_indent_tabstop_handling) __printbuf_do_indent(out, pos); } void bch2_prt_vprintf(struct printbuf *out, const char *fmt, va_list args) { int len; do { va_list args2; va_copy(args2, args); len = vsnprintf(out->buf + out->pos, printbuf_remaining_size(out), fmt, args2); va_end(args2); } while (len > printbuf_remaining(out) && !bch2_printbuf_make_room(out, len)); unsigned indent_pos = out->pos; printbuf_advance_pos(out, len); printbuf_do_indent(out, indent_pos); } void bch2_prt_printf(struct printbuf *out, const char *fmt, ...) { va_list args; int len; do { va_start(args, fmt); len = vsnprintf(out->buf + out->pos, printbuf_remaining_size(out), fmt, args); va_end(args); } while (len > printbuf_remaining(out) && !bch2_printbuf_make_room(out, len)); unsigned indent_pos = out->pos; printbuf_advance_pos(out, len); printbuf_do_indent(out, indent_pos); } /** * bch2_printbuf_str() - returns printbuf's buf as a C string, guaranteed to be * null terminated * @buf: printbuf to terminate * Returns: Printbuf contents, as a nul terminated C string */ const char *bch2_printbuf_str(const struct printbuf *buf) { /* * If we've written to a printbuf then it's guaranteed to be a null * terminated string - but if we haven't, then we might not have * allocated a buffer at all: */ return buf->pos ? buf->buf : ""; } /** * bch2_printbuf_exit() - exit a printbuf, freeing memory it owns and poisoning it * against accidental use. * @buf: printbuf to exit */ void bch2_printbuf_exit(struct printbuf *buf) { if (buf->heap_allocated) { kfree(buf->buf); buf->buf = ERR_PTR(-EINTR); /* poison value */ } } void bch2_printbuf_tabstops_reset(struct printbuf *buf) { buf->nr_tabstops = 0; } void bch2_printbuf_tabstop_pop(struct printbuf *buf) { if (buf->nr_tabstops) --buf->nr_tabstops; } /* * bch2_printbuf_tabstop_set() - add a tabstop, n spaces from the previous tabstop * * @buf: printbuf to control * @spaces: number of spaces from previous tabpstop * * In the future this function may allocate memory if setting more than * PRINTBUF_INLINE_TABSTOPS or setting tabstops more than 255 spaces from start * of line. */ int bch2_printbuf_tabstop_push(struct printbuf *buf, unsigned spaces) { unsigned prev_tabstop = buf->nr_tabstops ? buf->_tabstops[buf->nr_tabstops - 1] : 0; if (WARN_ON(buf->nr_tabstops >= ARRAY_SIZE(buf->_tabstops))) return -EINVAL; buf->_tabstops[buf->nr_tabstops++] = prev_tabstop + spaces; buf->has_indent_or_tabstops = true; return 0; } /** * bch2_printbuf_indent_add() - add to the current indent level * * @buf: printbuf to control * @spaces: number of spaces to add to the current indent level * * Subsequent lines, and the current line if the output position is at the start * of the current line, will be indented by @spaces more spaces. */ void bch2_printbuf_indent_add(struct printbuf *buf, unsigned spaces) { if (WARN_ON_ONCE(buf->indent + spaces < buf->indent)) spaces = 0; buf->indent += spaces; prt_chars(buf, ' ', spaces); buf->has_indent_or_tabstops = true; } /** * bch2_printbuf_indent_sub() - subtract from the current indent level * * @buf: printbuf to control * @spaces: number of spaces to subtract from the current indent level * * Subsequent lines, and the current line if the output position is at the start * of the current line, will be indented by @spaces less spaces. */ void bch2_printbuf_indent_sub(struct printbuf *buf, unsigned spaces) { if (WARN_ON_ONCE(spaces > buf->indent)) spaces = buf->indent; if (buf->last_newline + buf->indent == buf->pos) { buf->pos -= spaces; printbuf_nul_terminate(buf); } buf->indent -= spaces; if (!buf->indent && !buf->nr_tabstops) buf->has_indent_or_tabstops = false; } void bch2_prt_newline(struct printbuf *buf) { bch2_printbuf_make_room(buf, 1 + buf->indent); __prt_char_reserved(buf, '\n'); buf->last_newline = buf->pos; __prt_chars_reserved(buf, ' ', buf->indent); printbuf_nul_terminate_reserved(buf); buf->last_field = buf->pos; buf->cur_tabstop = 0; } void bch2_printbuf_strip_trailing_newline(struct printbuf *out) { for (int p = out->pos - 1; p >= 0; --p) { if (out->buf[p] == '\n') { out->pos = p; break; } if (out->buf[p] != ' ') break; } printbuf_nul_terminate_reserved(out); } static void __prt_tab(struct printbuf *out) { int spaces = max_t(int, 0, cur_tabstop(out) - printbuf_linelen(out)); prt_chars(out, ' ', spaces); out->last_field = out->pos; out->cur_tabstop++; } /** * bch2_prt_tab() - Advance printbuf to the next tabstop * @out: printbuf to control * * Advance output to the next tabstop by printing spaces. */ void bch2_prt_tab(struct printbuf *out) { if (WARN_ON(!cur_tabstop(out))) return; __prt_tab(out); } static void __prt_tab_rjust(struct printbuf *buf) { int pad = (int) cur_tabstop(buf) - (int) printbuf_linelen(buf); if (pad > 0) printbuf_insert_spaces(buf, buf->last_field, pad); buf->last_field = buf->pos; buf->cur_tabstop++; } /** * bch2_prt_tab_rjust - Advance printbuf to the next tabstop, right justifying * previous output * * @buf: printbuf to control * * Advance output to the next tabstop by inserting spaces immediately after the * previous tabstop, right justifying previously outputted text. */ void bch2_prt_tab_rjust(struct printbuf *buf) { if (WARN_ON(!cur_tabstop(buf))) return; __prt_tab_rjust(buf); } /** * bch2_prt_bytes_indented() - Print an array of chars, handling embedded control characters * * @out: output printbuf * @str: string to print * @count: number of bytes to print * * The following contol characters are handled as so: * \n: prt_newline newline that obeys current indent level * \t: prt_tab advance to next tabstop * \r: prt_tab_rjust advance to next tabstop, with right justification */ void bch2_prt_bytes_indented(struct printbuf *out, const char *str, unsigned count) { unsigned indent_pos = out->pos; prt_bytes(out, str, count); printbuf_do_indent(out, indent_pos); } /** * bch2_prt_human_readable_u64() - Print out a u64 in human readable units * @out: output printbuf * @v: integer to print * * Units of 2^10 (default) or 10^3 are controlled via @out->si_units */ void bch2_prt_human_readable_u64(struct printbuf *out, u64 v) { bch2_printbuf_make_room(out, 10); unsigned len = string_get_size(v, 1, !out->si_units, out->buf + out->pos, printbuf_remaining_size(out)); printbuf_advance_pos(out, len); } /** * bch2_prt_human_readable_s64() - Print out a s64 in human readable units * @out: output printbuf * @v: integer to print * * Units of 2^10 (default) or 10^3 are controlled via @out->si_units */ void bch2_prt_human_readable_s64(struct printbuf *out, s64 v) { if (v < 0) prt_char(out, '-'); bch2_prt_human_readable_u64(out, abs(v)); } /** * bch2_prt_units_u64() - Print out a u64 according to printbuf unit options * @out: output printbuf * @v: integer to print * * Units are either raw (default), or human reabable units (controlled via * @buf->human_readable_units) */ void bch2_prt_units_u64(struct printbuf *out, u64 v) { if (out->human_readable_units) bch2_prt_human_readable_u64(out, v); else bch2_prt_printf(out, "%llu", v); } /** * bch2_prt_units_s64() - Print out a s64 according to printbuf unit options * @out: output printbuf * @v: integer to print * * Units are either raw (default), or human reabable units (controlled via * @buf->human_readable_units) */ void bch2_prt_units_s64(struct printbuf *out, s64 v) { if (v < 0) prt_char(out, '-'); bch2_prt_units_u64(out, abs(v)); } void bch2_prt_string_option(struct printbuf *out, const char * const list[], size_t selected) { for (size_t i = 0; list[i]; i++) bch2_prt_printf(out, i == selected ? "[%s] " : "%s ", list[i]); } void bch2_prt_bitflags(struct printbuf *out, const char * const list[], u64 flags) { unsigned bit, nr = 0; bool first = true; while (list[nr]) nr++; while (flags && (bit = __ffs64(flags)) < nr) { if (!first) bch2_prt_printf(out, ","); first = false; bch2_prt_printf(out, "%s", list[bit]); flags ^= BIT_ULL(bit); } } void bch2_prt_bitflags_vector(struct printbuf *out, const char * const list[], unsigned long *v, unsigned nr) { bool first = true; unsigned i; for (i = 0; i < nr; i++) if (!list[i]) { nr = i - 1; break; } for_each_set_bit(i, v, nr) { if (!first) bch2_prt_printf(out, ","); first = false; bch2_prt_printf(out, "%s", list[i]); } } |
| 14 14 1 4 2 11 10 10 1 10 1 9 3 3 3 8 8 1 7 1 2 2 2 1 2 2 1 1 1 1 1 1 1 1 5 1 2 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 | // SPDX-License-Identifier: GPL-2.0-only /* * vivid-vbi-out.c - vbi output support functions. * * Copyright 2014 Cisco Systems, Inc. and/or its affiliates. All rights reserved. */ #include <linux/errno.h> #include <linux/kernel.h> #include <linux/videodev2.h> #include <media/v4l2-common.h> #include "vivid-core.h" #include "vivid-kthread-out.h" #include "vivid-vbi-out.h" #include "vivid-vbi-cap.h" static int vbi_out_queue_setup(struct vb2_queue *vq, unsigned *nbuffers, unsigned *nplanes, unsigned sizes[], struct device *alloc_devs[]) { struct vivid_dev *dev = vb2_get_drv_priv(vq); bool is_60hz = dev->std_out & V4L2_STD_525_60; unsigned size = vq->type == V4L2_BUF_TYPE_SLICED_VBI_OUTPUT ? 36 * sizeof(struct v4l2_sliced_vbi_data) : 1440 * 2 * (is_60hz ? 12 : 18); if (!vivid_is_svid_out(dev)) return -EINVAL; if (*nplanes) return sizes[0] < size ? -EINVAL : 0; sizes[0] = size; *nplanes = 1; return 0; } static int vbi_out_buf_prepare(struct vb2_buffer *vb) { struct vivid_dev *dev = vb2_get_drv_priv(vb->vb2_queue); bool is_60hz = dev->std_out & V4L2_STD_525_60; unsigned size = vb->vb2_queue->type == V4L2_BUF_TYPE_SLICED_VBI_OUTPUT ? 36 * sizeof(struct v4l2_sliced_vbi_data) : 1440 * 2 * (is_60hz ? 12 : 18); dprintk(dev, 1, "%s\n", __func__); if (dev->buf_prepare_error) { /* * Error injection: test what happens if buf_prepare() returns * an error. */ dev->buf_prepare_error = false; return -EINVAL; } if (vb2_plane_size(vb, 0) < size) { dprintk(dev, 1, "%s data will not fit into plane (%lu < %u)\n", __func__, vb2_plane_size(vb, 0), size); return -EINVAL; } vb2_set_plane_payload(vb, 0, size); return 0; } static void vbi_out_buf_queue(struct vb2_buffer *vb) { struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb); struct vivid_dev *dev = vb2_get_drv_priv(vb->vb2_queue); struct vivid_buffer *buf = container_of(vbuf, struct vivid_buffer, vb); dprintk(dev, 1, "%s\n", __func__); spin_lock(&dev->slock); list_add_tail(&buf->list, &dev->vbi_out_active); spin_unlock(&dev->slock); } static int vbi_out_start_streaming(struct vb2_queue *vq, unsigned count) { struct vivid_dev *dev = vb2_get_drv_priv(vq); int err; dprintk(dev, 1, "%s\n", __func__); dev->vbi_out_seq_count = 0; if (dev->start_streaming_error) { dev->start_streaming_error = false; err = -EINVAL; } else { err = vivid_start_generating_vid_out(dev, &dev->vbi_out_streaming); } if (err) { struct vivid_buffer *buf, *tmp; list_for_each_entry_safe(buf, tmp, &dev->vbi_out_active, list) { list_del(&buf->list); vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_QUEUED); } } return err; } /* abort streaming and wait for last buffer */ static void vbi_out_stop_streaming(struct vb2_queue *vq) { struct vivid_dev *dev = vb2_get_drv_priv(vq); dprintk(dev, 1, "%s\n", __func__); vivid_stop_generating_vid_out(dev, &dev->vbi_out_streaming); dev->vbi_out_have_wss = false; dev->vbi_out_have_cc[0] = false; dev->vbi_out_have_cc[1] = false; } static void vbi_out_buf_request_complete(struct vb2_buffer *vb) { struct vivid_dev *dev = vb2_get_drv_priv(vb->vb2_queue); v4l2_ctrl_request_complete(vb->req_obj.req, &dev->ctrl_hdl_vbi_out); } const struct vb2_ops vivid_vbi_out_qops = { .queue_setup = vbi_out_queue_setup, .buf_prepare = vbi_out_buf_prepare, .buf_queue = vbi_out_buf_queue, .start_streaming = vbi_out_start_streaming, .stop_streaming = vbi_out_stop_streaming, .buf_request_complete = vbi_out_buf_request_complete, .wait_prepare = vb2_ops_wait_prepare, .wait_finish = vb2_ops_wait_finish, }; int vidioc_g_fmt_vbi_out(struct file *file, void *priv, struct v4l2_format *f) { struct vivid_dev *dev = video_drvdata(file); struct v4l2_vbi_format *vbi = &f->fmt.vbi; bool is_60hz = dev->std_out & V4L2_STD_525_60; if (!vivid_is_svid_out(dev) || !dev->has_raw_vbi_out) return -EINVAL; vbi->sampling_rate = 25000000; vbi->offset = 24; vbi->samples_per_line = 1440; vbi->sample_format = V4L2_PIX_FMT_GREY; vbi->start[0] = is_60hz ? V4L2_VBI_ITU_525_F1_START + 9 : V4L2_VBI_ITU_625_F1_START + 5; vbi->start[1] = is_60hz ? V4L2_VBI_ITU_525_F2_START + 9 : V4L2_VBI_ITU_625_F2_START + 5; vbi->count[0] = vbi->count[1] = is_60hz ? 12 : 18; vbi->flags = dev->vbi_cap_interlaced ? V4L2_VBI_INTERLACED : 0; vbi->reserved[0] = 0; vbi->reserved[1] = 0; return 0; } int vidioc_s_fmt_vbi_out(struct file *file, void *priv, struct v4l2_format *f) { struct vivid_dev *dev = video_drvdata(file); int ret = vidioc_g_fmt_vbi_out(file, priv, f); if (ret) return ret; if (vb2_is_busy(&dev->vb_vbi_out_q)) return -EBUSY; dev->stream_sliced_vbi_out = false; dev->vbi_out_dev.queue->type = V4L2_BUF_TYPE_VBI_OUTPUT; return 0; } int vidioc_g_fmt_sliced_vbi_out(struct file *file, void *fh, struct v4l2_format *fmt) { struct vivid_dev *dev = video_drvdata(file); struct v4l2_sliced_vbi_format *vbi = &fmt->fmt.sliced; if (!vivid_is_svid_out(dev) || !dev->has_sliced_vbi_out) return -EINVAL; vivid_fill_service_lines(vbi, dev->service_set_out); return 0; } int vidioc_try_fmt_sliced_vbi_out(struct file *file, void *fh, struct v4l2_format *fmt) { struct vivid_dev *dev = video_drvdata(file); struct v4l2_sliced_vbi_format *vbi = &fmt->fmt.sliced; bool is_60hz = dev->std_out & V4L2_STD_525_60; u32 service_set = vbi->service_set; if (!vivid_is_svid_out(dev) || !dev->has_sliced_vbi_out) return -EINVAL; service_set &= is_60hz ? V4L2_SLICED_CAPTION_525 : V4L2_SLICED_WSS_625 | V4L2_SLICED_TELETEXT_B; vivid_fill_service_lines(vbi, service_set); return 0; } int vidioc_s_fmt_sliced_vbi_out(struct file *file, void *fh, struct v4l2_format *fmt) { struct vivid_dev *dev = video_drvdata(file); struct v4l2_sliced_vbi_format *vbi = &fmt->fmt.sliced; int ret = vidioc_try_fmt_sliced_vbi_out(file, fh, fmt); if (ret) return ret; if (vb2_is_busy(&dev->vb_vbi_out_q)) return -EBUSY; dev->service_set_out = vbi->service_set; dev->stream_sliced_vbi_out = true; dev->vbi_out_dev.queue->type = V4L2_BUF_TYPE_SLICED_VBI_OUTPUT; return 0; } void vivid_sliced_vbi_out_process(struct vivid_dev *dev, struct vivid_buffer *buf) { struct v4l2_sliced_vbi_data *vbi = vb2_plane_vaddr(&buf->vb.vb2_buf, 0); unsigned elems = vb2_get_plane_payload(&buf->vb.vb2_buf, 0) / sizeof(*vbi); dev->vbi_out_have_cc[0] = false; dev->vbi_out_have_cc[1] = false; dev->vbi_out_have_wss = false; while (elems--) { switch (vbi->id) { case V4L2_SLICED_CAPTION_525: if ((dev->std_out & V4L2_STD_525_60) && vbi->line == 21) { dev->vbi_out_have_cc[!!vbi->field] = true; dev->vbi_out_cc[!!vbi->field][0] = vbi->data[0]; dev->vbi_out_cc[!!vbi->field][1] = vbi->data[1]; } break; case V4L2_SLICED_WSS_625: if ((dev->std_out & V4L2_STD_625_50) && vbi->field == 0 && vbi->line == 23) { dev->vbi_out_have_wss = true; dev->vbi_out_wss[0] = vbi->data[0]; dev->vbi_out_wss[1] = vbi->data[1]; } break; } vbi++; } } |
| 12 10 1 3 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 | // SPDX-License-Identifier: GPL-2.0-only /* * This is a module which is used for rejecting packets. */ /* (C) 1999-2001 Paul `Rusty' Russell * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/ip.h> #include <linux/udp.h> #include <linux/icmp.h> #include <net/icmp.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/netfilter_ipv4/ipt_REJECT.h> #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) #include <linux/netfilter_bridge.h> #endif #include <net/netfilter/ipv4/nf_reject.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("Xtables: packet \"rejection\" target for IPv4"); static unsigned int reject_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ipt_reject_info *reject = par->targinfo; int hook = xt_hooknum(par); switch (reject->with) { case IPT_ICMP_NET_UNREACHABLE: nf_send_unreach(skb, ICMP_NET_UNREACH, hook); break; case IPT_ICMP_HOST_UNREACHABLE: nf_send_unreach(skb, ICMP_HOST_UNREACH, hook); break; case IPT_ICMP_PROT_UNREACHABLE: nf_send_unreach(skb, ICMP_PROT_UNREACH, hook); break; case IPT_ICMP_PORT_UNREACHABLE: nf_send_unreach(skb, ICMP_PORT_UNREACH, hook); break; case IPT_ICMP_NET_PROHIBITED: nf_send_unreach(skb, ICMP_NET_ANO, hook); break; case IPT_ICMP_HOST_PROHIBITED: nf_send_unreach(skb, ICMP_HOST_ANO, hook); break; case IPT_ICMP_ADMIN_PROHIBITED: nf_send_unreach(skb, ICMP_PKT_FILTERED, hook); break; case IPT_TCP_RESET: nf_send_reset(xt_net(par), par->state->sk, skb, hook); break; case IPT_ICMP_ECHOREPLY: /* Doesn't happen. */ break; } return NF_DROP; } static int reject_tg_check(const struct xt_tgchk_param *par) { const struct ipt_reject_info *rejinfo = par->targinfo; const struct ipt_entry *e = par->entryinfo; if (rejinfo->with == IPT_ICMP_ECHOREPLY) { pr_info_ratelimited("ECHOREPLY no longer supported.\n"); return -EINVAL; } else if (rejinfo->with == IPT_TCP_RESET) { /* Must specify that it's a TCP packet */ if (e->ip.proto != IPPROTO_TCP || (e->ip.invflags & XT_INV_PROTO)) { pr_info_ratelimited("TCP_RESET invalid for non-tcp\n"); return -EINVAL; } } return 0; } static struct xt_target reject_tg_reg __read_mostly = { .name = "REJECT", .family = NFPROTO_IPV4, .target = reject_tg, .targetsize = sizeof(struct ipt_reject_info), .table = "filter", .hooks = (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD) | (1 << NF_INET_LOCAL_OUT), .checkentry = reject_tg_check, .me = THIS_MODULE, }; static int __init reject_tg_init(void) { return xt_register_target(&reject_tg_reg); } static void __exit reject_tg_exit(void) { xt_unregister_target(&reject_tg_reg); } module_init(reject_tg_init); module_exit(reject_tg_exit); |
| 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright Gavin Shan, IBM Corporation 2016. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/of.h> #include <linux/platform_device.h> #include <net/ncsi.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/addrconf.h> #include <net/ipv6.h> #include <net/genetlink.h> #include "internal.h" #include "ncsi-pkt.h" #include "ncsi-netlink.h" LIST_HEAD(ncsi_dev_list); DEFINE_SPINLOCK(ncsi_dev_lock); bool ncsi_channel_has_link(struct ncsi_channel *channel) { return !!(channel->modes[NCSI_MODE_LINK].data[2] & 0x1); } bool ncsi_channel_is_last(struct ncsi_dev_priv *ndp, struct ncsi_channel *channel) { struct ncsi_package *np; struct ncsi_channel *nc; NCSI_FOR_EACH_PACKAGE(ndp, np) NCSI_FOR_EACH_CHANNEL(np, nc) { if (nc == channel) continue; if (nc->state == NCSI_CHANNEL_ACTIVE && ncsi_channel_has_link(nc)) return false; } return true; } static void ncsi_report_link(struct ncsi_dev_priv *ndp, bool force_down) { struct ncsi_dev *nd = &ndp->ndev; struct ncsi_package *np; struct ncsi_channel *nc; unsigned long flags; nd->state = ncsi_dev_state_functional; if (force_down) { nd->link_up = 0; goto report; } nd->link_up = 0; NCSI_FOR_EACH_PACKAGE(ndp, np) { NCSI_FOR_EACH_CHANNEL(np, nc) { spin_lock_irqsave(&nc->lock, flags); if (!list_empty(&nc->link) || nc->state != NCSI_CHANNEL_ACTIVE) { spin_unlock_irqrestore(&nc->lock, flags); continue; } if (ncsi_channel_has_link(nc)) { spin_unlock_irqrestore(&nc->lock, flags); nd->link_up = 1; goto report; } spin_unlock_irqrestore(&nc->lock, flags); } } report: nd->handler(nd); } static void ncsi_channel_monitor(struct timer_list *t) { struct ncsi_channel *nc = from_timer(nc, t, monitor.timer); struct ncsi_package *np = nc->package; struct ncsi_dev_priv *ndp = np->ndp; struct ncsi_channel_mode *ncm; struct ncsi_cmd_arg nca; bool enabled, chained; unsigned int monitor_state; unsigned long flags; int state, ret; spin_lock_irqsave(&nc->lock, flags); state = nc->state; chained = !list_empty(&nc->link); enabled = nc->monitor.enabled; monitor_state = nc->monitor.state; spin_unlock_irqrestore(&nc->lock, flags); if (!enabled) return; /* expected race disabling timer */ if (WARN_ON_ONCE(chained)) goto bad_state; if (state != NCSI_CHANNEL_INACTIVE && state != NCSI_CHANNEL_ACTIVE) { bad_state: netdev_warn(ndp->ndev.dev, "Bad NCSI monitor state channel %d 0x%x %s queue\n", nc->id, state, chained ? "on" : "off"); spin_lock_irqsave(&nc->lock, flags); nc->monitor.enabled = false; spin_unlock_irqrestore(&nc->lock, flags); return; } switch (monitor_state) { case NCSI_CHANNEL_MONITOR_START: case NCSI_CHANNEL_MONITOR_RETRY: nca.ndp = ndp; nca.package = np->id; nca.channel = nc->id; nca.type = NCSI_PKT_CMD_GLS; nca.req_flags = 0; ret = ncsi_xmit_cmd(&nca); if (ret) netdev_err(ndp->ndev.dev, "Error %d sending GLS\n", ret); break; case NCSI_CHANNEL_MONITOR_WAIT ... NCSI_CHANNEL_MONITOR_WAIT_MAX: break; default: netdev_err(ndp->ndev.dev, "NCSI Channel %d timed out!\n", nc->id); ncsi_report_link(ndp, true); ndp->flags |= NCSI_DEV_RESHUFFLE; ncm = &nc->modes[NCSI_MODE_LINK]; spin_lock_irqsave(&nc->lock, flags); nc->monitor.enabled = false; nc->state = NCSI_CHANNEL_INVISIBLE; ncm->data[2] &= ~0x1; spin_unlock_irqrestore(&nc->lock, flags); spin_lock_irqsave(&ndp->lock, flags); nc->state = NCSI_CHANNEL_ACTIVE; list_add_tail_rcu(&nc->link, &ndp->channel_queue); spin_unlock_irqrestore(&ndp->lock, flags); ncsi_process_next_channel(ndp); return; } spin_lock_irqsave(&nc->lock, flags); nc->monitor.state++; spin_unlock_irqrestore(&nc->lock, flags); mod_timer(&nc->monitor.timer, jiffies + HZ); } void ncsi_start_channel_monitor(struct ncsi_channel *nc) { unsigned long flags; spin_lock_irqsave(&nc->lock, flags); WARN_ON_ONCE(nc->monitor.enabled); nc->monitor.enabled = true; nc->monitor.state = NCSI_CHANNEL_MONITOR_START; spin_unlock_irqrestore(&nc->lock, flags); mod_timer(&nc->monitor.timer, jiffies + HZ); } void ncsi_stop_channel_monitor(struct ncsi_channel *nc) { unsigned long flags; spin_lock_irqsave(&nc->lock, flags); if (!nc->monitor.enabled) { spin_unlock_irqrestore(&nc->lock, flags); return; } nc->monitor.enabled = false; spin_unlock_irqrestore(&nc->lock, flags); del_timer_sync(&nc->monitor.timer); } struct ncsi_channel *ncsi_find_channel(struct ncsi_package *np, unsigned char id) { struct ncsi_channel *nc; NCSI_FOR_EACH_CHANNEL(np, nc) { if (nc->id == id) return nc; } return NULL; } struct ncsi_channel *ncsi_add_channel(struct ncsi_package *np, unsigned char id) { struct ncsi_channel *nc, *tmp; int index; unsigned long flags; nc = kzalloc(sizeof(*nc), GFP_ATOMIC); if (!nc) return NULL; nc->id = id; nc->package = np; nc->state = NCSI_CHANNEL_INACTIVE; nc->monitor.enabled = false; timer_setup(&nc->monitor.timer, ncsi_channel_monitor, 0); spin_lock_init(&nc->lock); INIT_LIST_HEAD(&nc->link); for (index = 0; index < NCSI_CAP_MAX; index++) nc->caps[index].index = index; for (index = 0; index < NCSI_MODE_MAX; index++) nc->modes[index].index = index; spin_lock_irqsave(&np->lock, flags); tmp = ncsi_find_channel(np, id); if (tmp) { spin_unlock_irqrestore(&np->lock, flags); kfree(nc); return tmp; } list_add_tail_rcu(&nc->node, &np->channels); np->channel_num++; spin_unlock_irqrestore(&np->lock, flags); return nc; } static void ncsi_remove_channel(struct ncsi_channel *nc) { struct ncsi_package *np = nc->package; unsigned long flags; spin_lock_irqsave(&nc->lock, flags); /* Release filters */ kfree(nc->mac_filter.addrs); kfree(nc->vlan_filter.vids); nc->state = NCSI_CHANNEL_INACTIVE; spin_unlock_irqrestore(&nc->lock, flags); ncsi_stop_channel_monitor(nc); /* Remove and free channel */ spin_lock_irqsave(&np->lock, flags); list_del_rcu(&nc->node); np->channel_num--; spin_unlock_irqrestore(&np->lock, flags); kfree(nc); } struct ncsi_package *ncsi_find_package(struct ncsi_dev_priv *ndp, unsigned char id) { struct ncsi_package *np; NCSI_FOR_EACH_PACKAGE(ndp, np) { if (np->id == id) return np; } return NULL; } struct ncsi_package *ncsi_add_package(struct ncsi_dev_priv *ndp, unsigned char id) { struct ncsi_package *np, *tmp; unsigned long flags; np = kzalloc(sizeof(*np), GFP_ATOMIC); if (!np) return NULL; np->id = id; np->ndp = ndp; spin_lock_init(&np->lock); INIT_LIST_HEAD(&np->channels); np->channel_whitelist = UINT_MAX; spin_lock_irqsave(&ndp->lock, flags); tmp = ncsi_find_package(ndp, id); if (tmp) { spin_unlock_irqrestore(&ndp->lock, flags); kfree(np); return tmp; } list_add_tail_rcu(&np->node, &ndp->packages); ndp->package_num++; spin_unlock_irqrestore(&ndp->lock, flags); return np; } void ncsi_remove_package(struct ncsi_package *np) { struct ncsi_dev_priv *ndp = np->ndp; struct ncsi_channel *nc, *tmp; unsigned long flags; /* Release all child channels */ list_for_each_entry_safe(nc, tmp, &np->channels, node) ncsi_remove_channel(nc); /* Remove and free package */ spin_lock_irqsave(&ndp->lock, flags); list_del_rcu(&np->node); ndp->package_num--; spin_unlock_irqrestore(&ndp->lock, flags); kfree(np); } void ncsi_find_package_and_channel(struct ncsi_dev_priv *ndp, unsigned char id, struct ncsi_package **np, struct ncsi_channel **nc) { struct ncsi_package *p; struct ncsi_channel *c; p = ncsi_find_package(ndp, NCSI_PACKAGE_INDEX(id)); c = p ? ncsi_find_channel(p, NCSI_CHANNEL_INDEX(id)) : NULL; if (np) *np = p; if (nc) *nc = c; } /* For two consecutive NCSI commands, the packet IDs shouldn't * be same. Otherwise, the bogus response might be replied. So * the available IDs are allocated in round-robin fashion. */ struct ncsi_request *ncsi_alloc_request(struct ncsi_dev_priv *ndp, unsigned int req_flags) { struct ncsi_request *nr = NULL; int i, limit = ARRAY_SIZE(ndp->requests); unsigned long flags; /* Check if there is one available request until the ceiling */ spin_lock_irqsave(&ndp->lock, flags); for (i = ndp->request_id; i < limit; i++) { if (ndp->requests[i].used) continue; nr = &ndp->requests[i]; nr->used = true; nr->flags = req_flags; ndp->request_id = i + 1; goto found; } /* Fail back to check from the starting cursor */ for (i = NCSI_REQ_START_IDX; i < ndp->request_id; i++) { if (ndp->requests[i].used) continue; nr = &ndp->requests[i]; nr->used = true; nr->flags = req_flags; ndp->request_id = i + 1; goto found; } found: spin_unlock_irqrestore(&ndp->lock, flags); return nr; } void ncsi_free_request(struct ncsi_request *nr) { struct ncsi_dev_priv *ndp = nr->ndp; struct sk_buff *cmd, *rsp; unsigned long flags; bool driven; if (nr->enabled) { nr->enabled = false; del_timer_sync(&nr->timer); } spin_lock_irqsave(&ndp->lock, flags); cmd = nr->cmd; rsp = nr->rsp; nr->cmd = NULL; nr->rsp = NULL; nr->used = false; driven = !!(nr->flags & NCSI_REQ_FLAG_EVENT_DRIVEN); spin_unlock_irqrestore(&ndp->lock, flags); if (driven && cmd && --ndp->pending_req_num == 0) schedule_work(&ndp->work); /* Release command and response */ consume_skb(cmd); consume_skb(rsp); } struct ncsi_dev *ncsi_find_dev(struct net_device *dev) { struct ncsi_dev_priv *ndp; NCSI_FOR_EACH_DEV(ndp) { if (ndp->ndev.dev == dev) return &ndp->ndev; } return NULL; } static void ncsi_request_timeout(struct timer_list *t) { struct ncsi_request *nr = from_timer(nr, t, timer); struct ncsi_dev_priv *ndp = nr->ndp; struct ncsi_cmd_pkt *cmd; struct ncsi_package *np; struct ncsi_channel *nc; unsigned long flags; /* If the request already had associated response, * let the response handler to release it. */ spin_lock_irqsave(&ndp->lock, flags); nr->enabled = false; if (nr->rsp || !nr->cmd) { spin_unlock_irqrestore(&ndp->lock, flags); return; } spin_unlock_irqrestore(&ndp->lock, flags); if (nr->flags == NCSI_REQ_FLAG_NETLINK_DRIVEN) { if (nr->cmd) { /* Find the package */ cmd = (struct ncsi_cmd_pkt *) skb_network_header(nr->cmd); ncsi_find_package_and_channel(ndp, cmd->cmd.common.channel, &np, &nc); ncsi_send_netlink_timeout(nr, np, nc); } } /* Release the request */ ncsi_free_request(nr); } static void ncsi_suspend_channel(struct ncsi_dev_priv *ndp) { struct ncsi_dev *nd = &ndp->ndev; struct ncsi_package *np; struct ncsi_channel *nc, *tmp; struct ncsi_cmd_arg nca; unsigned long flags; int ret; np = ndp->active_package; nc = ndp->active_channel; nca.ndp = ndp; nca.req_flags = NCSI_REQ_FLAG_EVENT_DRIVEN; switch (nd->state) { case ncsi_dev_state_suspend: nd->state = ncsi_dev_state_suspend_select; fallthrough; case ncsi_dev_state_suspend_select: ndp->pending_req_num = 1; nca.type = NCSI_PKT_CMD_SP; nca.package = np->id; nca.channel = NCSI_RESERVED_CHANNEL; if (ndp->flags & NCSI_DEV_HWA) nca.bytes[0] = 0; else nca.bytes[0] = 1; /* To retrieve the last link states of channels in current * package when current active channel needs fail over to * another one. It means we will possibly select another * channel as next active one. The link states of channels * are most important factor of the selection. So we need * accurate link states. Unfortunately, the link states on * inactive channels can't be updated with LSC AEN in time. */ if (ndp->flags & NCSI_DEV_RESHUFFLE) nd->state = ncsi_dev_state_suspend_gls; else nd->state = ncsi_dev_state_suspend_dcnt; ret = ncsi_xmit_cmd(&nca); if (ret) goto error; break; case ncsi_dev_state_suspend_gls: ndp->pending_req_num = 1; nca.type = NCSI_PKT_CMD_GLS; nca.package = np->id; nca.channel = ndp->channel_probe_id; ret = ncsi_xmit_cmd(&nca); if (ret) goto error; ndp->channel_probe_id++; if (ndp->channel_probe_id == ndp->channel_count) { ndp->channel_probe_id = 0; nd->state = ncsi_dev_state_suspend_dcnt; } break; case ncsi_dev_state_suspend_dcnt: ndp->pending_req_num = 1; nca.type = NCSI_PKT_CMD_DCNT; nca.package = np->id; nca.channel = nc->id; nd->state = ncsi_dev_state_suspend_dc; ret = ncsi_xmit_cmd(&nca); if (ret) goto error; break; case ncsi_dev_state_suspend_dc: ndp->pending_req_num = 1; nca.type = NCSI_PKT_CMD_DC; nca.package = np->id; nca.channel = nc->id; nca.bytes[0] = 1; nd->state = ncsi_dev_state_suspend_deselect; ret = ncsi_xmit_cmd(&nca); if (ret) goto error; NCSI_FOR_EACH_CHANNEL(np, tmp) { /* If there is another channel active on this package * do not deselect the package. */ if (tmp != nc && tmp->state == NCSI_CHANNEL_ACTIVE) { nd->state = ncsi_dev_state_suspend_done; break; } } break; case ncsi_dev_state_suspend_deselect: ndp->pending_req_num = 1; nca.type = NCSI_PKT_CMD_DP; nca.package = np->id; nca.channel = NCSI_RESERVED_CHANNEL; nd->state = ncsi_dev_state_suspend_done; ret = ncsi_xmit_cmd(&nca); if (ret) goto error; break; case ncsi_dev_state_suspend_done: spin_lock_irqsave(&nc->lock, flags); nc->state = NCSI_CHANNEL_INACTIVE; spin_unlock_irqrestore(&nc->lock, flags); if (ndp->flags & NCSI_DEV_RESET) ncsi_reset_dev(nd); else ncsi_process_next_channel(ndp); break; default: netdev_warn(nd->dev, "Wrong NCSI state 0x%x in suspend\n", nd->state); } return; error: nd->state = ncsi_dev_state_functional; } /* Check the VLAN filter bitmap for a set filter, and construct a * "Set VLAN Filter - Disable" packet if found. */ static int clear_one_vid(struct ncsi_dev_priv *ndp, struct ncsi_channel *nc, struct ncsi_cmd_arg *nca) { struct ncsi_channel_vlan_filter *ncf; unsigned long flags; void *bitmap; int index; u16 vid; ncf = &nc->vlan_filter; bitmap = &ncf->bitmap; spin_lock_irqsave(&nc->lock, flags); index = find_first_bit(bitmap, ncf->n_vids); if (index >= ncf->n_vids) { spin_unlock_irqrestore(&nc->lock, flags); return -1; } vid = ncf->vids[index]; clear_bit(index, bitmap); ncf->vids[index] = 0; spin_unlock_irqrestore(&nc->lock, flags); nca->type = NCSI_PKT_CMD_SVF; nca->words[1] = vid; /* HW filter index starts at 1 */ nca->bytes[6] = index + 1; nca->bytes[7] = 0x00; return 0; } /* Find an outstanding VLAN tag and construct a "Set VLAN Filter - Enable" * packet. */ static int set_one_vid(struct ncsi_dev_priv *ndp, struct ncsi_channel *nc, struct ncsi_cmd_arg *nca) { struct ncsi_channel_vlan_filter *ncf; struct vlan_vid *vlan = NULL; unsigned long flags; int i, index; void *bitmap; u16 vid; if (list_empty(&ndp->vlan_vids)) return -1; ncf = &nc->vlan_filter; bitmap = &ncf->bitmap; spin_lock_irqsave(&nc->lock, flags); rcu_read_lock(); list_for_each_entry_rcu(vlan, &ndp->vlan_vids, list) { vid = vlan->vid; for (i = 0; i < ncf->n_vids; i++) if (ncf->vids[i] == vid) { vid = 0; break; } if (vid) break; } rcu_read_unlock(); if (!vid) { /* No VLAN ID is not set */ spin_unlock_irqrestore(&nc->lock, flags); return -1; } index = find_first_zero_bit(bitmap, ncf->n_vids); if (index < 0 || index >= ncf->n_vids) { netdev_err(ndp->ndev.dev, "Channel %u already has all VLAN filters set\n", nc->id); spin_unlock_irqrestore(&nc->lock, flags); return -1; } ncf->vids[index] = vid; set_bit(index, bitmap); spin_unlock_irqrestore(&nc->lock, flags); nca->type = NCSI_PKT_CMD_SVF; nca->words[1] = vid; /* HW filter index starts at 1 */ nca->bytes[6] = index + 1; nca->bytes[7] = 0x01; return 0; } static int ncsi_oem_keep_phy_intel(struct ncsi_cmd_arg *nca) { unsigned char data[NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN]; int ret = 0; nca->payload = NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN; memset(data, 0, NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN); *(unsigned int *)data = ntohl((__force __be32)NCSI_OEM_MFR_INTEL_ID); data[4] = NCSI_OEM_INTEL_CMD_KEEP_PHY; /* PHY Link up attribute */ data[6] = 0x1; nca->data = data; ret = ncsi_xmit_cmd(nca); if (ret) netdev_err(nca->ndp->ndev.dev, "NCSI: Failed to transmit cmd 0x%x during configure\n", nca->type); return ret; } /* NCSI OEM Command APIs */ static int ncsi_oem_gma_handler_bcm(struct ncsi_cmd_arg *nca) { unsigned char data[NCSI_OEM_BCM_CMD_GMA_LEN]; int ret = 0; nca->payload = NCSI_OEM_BCM_CMD_GMA_LEN; memset(data, 0, NCSI_OEM_BCM_CMD_GMA_LEN); *(unsigned int *)data = ntohl((__force __be32)NCSI_OEM_MFR_BCM_ID); data[5] = NCSI_OEM_BCM_CMD_GMA; nca->data = data; ret = ncsi_xmit_cmd(nca); if (ret) netdev_err(nca->ndp->ndev.dev, "NCSI: Failed to transmit cmd 0x%x during configure\n", nca->type); return ret; } static int ncsi_oem_gma_handler_mlx(struct ncsi_cmd_arg *nca) { union { u8 data_u8[NCSI_OEM_MLX_CMD_GMA_LEN]; u32 data_u32[NCSI_OEM_MLX_CMD_GMA_LEN / sizeof(u32)]; } u; int ret = 0; nca->payload = NCSI_OEM_MLX_CMD_GMA_LEN; memset(&u, 0, sizeof(u)); u.data_u32[0] = ntohl((__force __be32)NCSI_OEM_MFR_MLX_ID); u.data_u8[5] = NCSI_OEM_MLX_CMD_GMA; u.data_u8[6] = NCSI_OEM_MLX_CMD_GMA_PARAM; nca->data = u.data_u8; ret = ncsi_xmit_cmd(nca); if (ret) netdev_err(nca->ndp->ndev.dev, "NCSI: Failed to transmit cmd 0x%x during configure\n", nca->type); return ret; } static int ncsi_oem_smaf_mlx(struct ncsi_cmd_arg *nca) { union { u8 data_u8[NCSI_OEM_MLX_CMD_SMAF_LEN]; u32 data_u32[NCSI_OEM_MLX_CMD_SMAF_LEN / sizeof(u32)]; } u; int ret = 0; memset(&u, 0, sizeof(u)); u.data_u32[0] = ntohl((__force __be32)NCSI_OEM_MFR_MLX_ID); u.data_u8[5] = NCSI_OEM_MLX_CMD_SMAF; u.data_u8[6] = NCSI_OEM_MLX_CMD_SMAF_PARAM; memcpy(&u.data_u8[MLX_SMAF_MAC_ADDR_OFFSET], nca->ndp->ndev.dev->dev_addr, ETH_ALEN); u.data_u8[MLX_SMAF_MED_SUPPORT_OFFSET] = (MLX_MC_RBT_AVL | MLX_MC_RBT_SUPPORT); nca->payload = NCSI_OEM_MLX_CMD_SMAF_LEN; nca->data = u.data_u8; ret = ncsi_xmit_cmd(nca); if (ret) netdev_err(nca->ndp->ndev.dev, "NCSI: Failed to transmit cmd 0x%x during probe\n", nca->type); return ret; } static int ncsi_oem_gma_handler_intel(struct ncsi_cmd_arg *nca) { unsigned char data[NCSI_OEM_INTEL_CMD_GMA_LEN]; int ret = 0; nca->payload = NCSI_OEM_INTEL_CMD_GMA_LEN; memset(data, 0, NCSI_OEM_INTEL_CMD_GMA_LEN); *(unsigned int *)data = ntohl((__force __be32)NCSI_OEM_MFR_INTEL_ID); data[4] = NCSI_OEM_INTEL_CMD_GMA; nca->data = data; ret = ncsi_xmit_cmd(nca); if (ret) netdev_err(nca->ndp->ndev.dev, "NCSI: Failed to transmit cmd 0x%x during configure\n", nca->type); return ret; } /* OEM Command handlers initialization */ static struct ncsi_oem_gma_handler { unsigned int mfr_id; int (*handler)(struct ncsi_cmd_arg *nca); } ncsi_oem_gma_handlers[] = { { NCSI_OEM_MFR_BCM_ID, ncsi_oem_gma_handler_bcm }, { NCSI_OEM_MFR_MLX_ID, ncsi_oem_gma_handler_mlx }, { NCSI_OEM_MFR_INTEL_ID, ncsi_oem_gma_handler_intel } }; static int ncsi_gma_handler(struct ncsi_cmd_arg *nca, unsigned int mf_id) { struct ncsi_oem_gma_handler *nch = NULL; int i; /* This function should only be called once, return if flag set */ if (nca->ndp->gma_flag == 1) return -1; /* Find gma handler for given manufacturer id */ for (i = 0; i < ARRAY_SIZE(ncsi_oem_gma_handlers); i++) { if (ncsi_oem_gma_handlers[i].mfr_id == mf_id) { if (ncsi_oem_gma_handlers[i].handler) nch = &ncsi_oem_gma_handlers[i]; break; } } if (!nch) { netdev_err(nca->ndp->ndev.dev, "NCSI: No GMA handler available for MFR-ID (0x%x)\n", mf_id); return -1; } /* Get Mac address from NCSI device */ return nch->handler(nca); } /* Determine if a given channel from the channel_queue should be used for Tx */ static bool ncsi_channel_is_tx(struct ncsi_dev_priv *ndp, struct ncsi_channel *nc) { struct ncsi_channel_mode *ncm; struct ncsi_channel *channel; struct ncsi_package *np; /* Check if any other channel has Tx enabled; a channel may have already * been configured and removed from the channel queue. */ NCSI_FOR_EACH_PACKAGE(ndp, np) { if (!ndp->multi_package && np != nc->package) continue; NCSI_FOR_EACH_CHANNEL(np, channel) { ncm = &channel->modes[NCSI_MODE_TX_ENABLE]; if (ncm->enable) return false; } } /* This channel is the preferred channel and has link */ list_for_each_entry_rcu(channel, &ndp->channel_queue, link) { np = channel->package; if (np->preferred_channel && ncsi_channel_has_link(np->preferred_channel)) { return np->preferred_channel == nc; } } /* This channel has link */ if (ncsi_channel_has_link(nc)) return true; list_for_each_entry_rcu(channel, &ndp->channel_queue, link) if (ncsi_channel_has_link(channel)) return false; /* No other channel has link; default to this one */ return true; } /* Change the active Tx channel in a multi-channel setup */ int ncsi_update_tx_channel(struct ncsi_dev_priv *ndp, struct ncsi_package *package, struct ncsi_channel *disable, struct ncsi_channel *enable) { struct ncsi_cmd_arg nca; struct ncsi_channel *nc; struct ncsi_package *np; int ret = 0; if (!package->multi_channel && !ndp->multi_package) netdev_warn(ndp->ndev.dev, "NCSI: Trying to update Tx channel in single-channel mode\n"); nca.ndp = ndp; nca.req_flags = 0; /* Find current channel with Tx enabled */ NCSI_FOR_EACH_PACKAGE(ndp, np) { if (disable) break; if (!ndp->multi_package && np != package) continue; NCSI_FOR_EACH_CHANNEL(np, nc) if (nc->modes[NCSI_MODE_TX_ENABLE].enable) { disable = nc; break; } } /* Find a suitable channel for Tx */ NCSI_FOR_EACH_PACKAGE(ndp, np) { if (enable) break; if (!ndp->multi_package && np != package) continue; if (!(ndp->package_whitelist & (0x1 << np->id))) continue; if (np->preferred_channel && ncsi_channel_has_link(np->preferred_channel)) { enable = np->preferred_channel; break; } NCSI_FOR_EACH_CHANNEL(np, nc) { if (!(np->channel_whitelist & 0x1 << nc->id)) continue; if (nc->state != NCSI_CHANNEL_ACTIVE) continue; if (ncsi_channel_has_link(nc)) { enable = nc; break; } } } if (disable == enable) return -1; if (!enable) return -1; if (disable) { nca.channel = disable->id; nca.package = disable->package->id; nca.type = NCSI_PKT_CMD_DCNT; ret = ncsi_xmit_cmd(&nca); if (ret) netdev_err(ndp->ndev.dev, "Error %d sending DCNT\n", ret); } netdev_info(ndp->ndev.dev, "NCSI: channel %u enables Tx\n", enable->id); nca.channel = enable->id; nca.package = enable->package->id; nca.type = NCSI_PKT_CMD_ECNT; ret = ncsi_xmit_cmd(&nca); if (ret) netdev_err(ndp->ndev.dev, "Error %d sending ECNT\n", ret); return ret; } static void ncsi_configure_channel(struct ncsi_dev_priv *ndp) { struct ncsi_package *np = ndp->active_package; struct ncsi_channel *nc = ndp->active_channel; struct ncsi_channel *hot_nc = NULL; struct ncsi_dev *nd = &ndp->ndev; struct net_device *dev = nd->dev; struct ncsi_cmd_arg nca; unsigned char index; unsigned long flags; int ret; nca.ndp = ndp; nca.req_flags = NCSI_REQ_FLAG_EVENT_DRIVEN; switch (nd->state) { case ncsi_dev_state_config: case ncsi_dev_state_config_sp: ndp->pending_req_num = 1; /* Select the specific package */ nca.type = NCSI_PKT_CMD_SP; if (ndp->flags & NCSI_DEV_HWA) nca.bytes[0] = 0; else nca.bytes[0] = 1; nca.package = np->id; nca.channel = NCSI_RESERVED_CHANNEL; ret = ncsi_xmit_cmd(&nca); if (ret) { netdev_err(ndp->ndev.dev, "NCSI: Failed to transmit CMD_SP\n"); goto error; } nd->state = ncsi_dev_state_config_cis; break; case ncsi_dev_state_config_cis: ndp->pending_req_num = 1; /* Clear initial state */ nca.type = NCSI_PKT_CMD_CIS; nca.package = np->id; nca.channel = nc->id; ret = ncsi_xmit_cmd(&nca); if (ret) { netdev_err(ndp->ndev.dev, "NCSI: Failed to transmit CMD_CIS\n"); goto error; } nd->state = IS_ENABLED(CONFIG_NCSI_OEM_CMD_GET_MAC) ? ncsi_dev_state_config_oem_gma : ncsi_dev_state_config_clear_vids; break; case ncsi_dev_state_config_oem_gma: nd->state = ncsi_dev_state_config_clear_vids; nca.package = np->id; nca.channel = nc->id; ndp->pending_req_num = 1; if (nc->version.major >= 1 && nc->version.minor >= 2) { nca.type = NCSI_PKT_CMD_GMCMA; ret = ncsi_xmit_cmd(&nca); } else { nca.type = NCSI_PKT_CMD_OEM; ret = ncsi_gma_handler(&nca, nc->version.mf_id); } if (ret < 0) schedule_work(&ndp->work); break; case ncsi_dev_state_config_clear_vids: case ncsi_dev_state_config_svf: case ncsi_dev_state_config_ev: case ncsi_dev_state_config_sma: case ncsi_dev_state_config_ebf: case ncsi_dev_state_config_dgmf: case ncsi_dev_state_config_ecnt: case ncsi_dev_state_config_ec: case ncsi_dev_state_config_ae: case ncsi_dev_state_config_gls: ndp->pending_req_num = 1; nca.package = np->id; nca.channel = nc->id; /* Clear any active filters on the channel before setting */ if (nd->state == ncsi_dev_state_config_clear_vids) { ret = clear_one_vid(ndp, nc, &nca); if (ret) { nd->state = ncsi_dev_state_config_svf; schedule_work(&ndp->work); break; } /* Repeat */ nd->state = ncsi_dev_state_config_clear_vids; /* Add known VLAN tags to the filter */ } else if (nd->state == ncsi_dev_state_config_svf) { ret = set_one_vid(ndp, nc, &nca); if (ret) { nd->state = ncsi_dev_state_config_ev; schedule_work(&ndp->work); break; } /* Repeat */ nd->state = ncsi_dev_state_config_svf; /* Enable/Disable the VLAN filter */ } else if (nd->state == ncsi_dev_state_config_ev) { if (list_empty(&ndp->vlan_vids)) { nca.type = NCSI_PKT_CMD_DV; } else { nca.type = NCSI_PKT_CMD_EV; nca.bytes[3] = NCSI_CAP_VLAN_NO; } nd->state = ncsi_dev_state_config_sma; } else if (nd->state == ncsi_dev_state_config_sma) { /* Use first entry in unicast filter table. Note that * the MAC filter table starts from entry 1 instead of * 0. */ nca.type = NCSI_PKT_CMD_SMA; for (index = 0; index < 6; index++) nca.bytes[index] = dev->dev_addr[index]; nca.bytes[6] = 0x1; nca.bytes[7] = 0x1; nd->state = ncsi_dev_state_config_ebf; } else if (nd->state == ncsi_dev_state_config_ebf) { nca.type = NCSI_PKT_CMD_EBF; nca.dwords[0] = nc->caps[NCSI_CAP_BC].cap; /* if multicast global filtering is supported then * disable it so that all multicast packet will be * forwarded to management controller */ if (nc->caps[NCSI_CAP_GENERIC].cap & NCSI_CAP_GENERIC_MC) nd->state = ncsi_dev_state_config_dgmf; else if (ncsi_channel_is_tx(ndp, nc)) nd->state = ncsi_dev_state_config_ecnt; else nd->state = ncsi_dev_state_config_ec; } else if (nd->state == ncsi_dev_state_config_dgmf) { nca.type = NCSI_PKT_CMD_DGMF; if (ncsi_channel_is_tx(ndp, nc)) nd->state = ncsi_dev_state_config_ecnt; else nd->state = ncsi_dev_state_config_ec; } else if (nd->state == ncsi_dev_state_config_ecnt) { if (np->preferred_channel && nc != np->preferred_channel) netdev_info(ndp->ndev.dev, "NCSI: Tx failed over to channel %u\n", nc->id); nca.type = NCSI_PKT_CMD_ECNT; nd->state = ncsi_dev_state_config_ec; } else if (nd->state == ncsi_dev_state_config_ec) { /* Enable AEN if it's supported */ nca.type = NCSI_PKT_CMD_EC; nd->state = ncsi_dev_state_config_ae; if (!(nc->caps[NCSI_CAP_AEN].cap & NCSI_CAP_AEN_MASK)) nd->state = ncsi_dev_state_config_gls; } else if (nd->state == ncsi_dev_state_config_ae) { nca.type = NCSI_PKT_CMD_AE; nca.bytes[0] = 0; nca.dwords[1] = nc->caps[NCSI_CAP_AEN].cap; nd->state = ncsi_dev_state_config_gls; } else if (nd->state == ncsi_dev_state_config_gls) { nca.type = NCSI_PKT_CMD_GLS; nd->state = ncsi_dev_state_config_done; } ret = ncsi_xmit_cmd(&nca); if (ret) { netdev_err(ndp->ndev.dev, "NCSI: Failed to transmit CMD %x\n", nca.type); goto error; } break; case ncsi_dev_state_config_done: netdev_dbg(ndp->ndev.dev, "NCSI: channel %u config done\n", nc->id); spin_lock_irqsave(&nc->lock, flags); nc->state = NCSI_CHANNEL_ACTIVE; if (ndp->flags & NCSI_DEV_RESET) { /* A reset event happened during config, start it now */ nc->reconfigure_needed = false; spin_unlock_irqrestore(&nc->lock, flags); ncsi_reset_dev(nd); break; } if (nc->reconfigure_needed) { /* This channel's configuration has been updated * part-way during the config state - start the * channel configuration over */ nc->reconfigure_needed = false; nc->state = NCSI_CHANNEL_INACTIVE; spin_unlock_irqrestore(&nc->lock, flags); spin_lock_irqsave(&ndp->lock, flags); list_add_tail_rcu(&nc->link, &ndp->channel_queue); spin_unlock_irqrestore(&ndp->lock, flags); netdev_dbg(dev, "Dirty NCSI channel state reset\n"); ncsi_process_next_channel(ndp); break; } if (nc->modes[NCSI_MODE_LINK].data[2] & 0x1) { hot_nc = nc; } else { hot_nc = NULL; netdev_dbg(ndp->ndev.dev, "NCSI: channel %u link down after config\n", nc->id); } spin_unlock_irqrestore(&nc->lock, flags); /* Update the hot channel */ spin_lock_irqsave(&ndp->lock, flags); ndp->hot_channel = hot_nc; spin_unlock_irqrestore(&ndp->lock, flags); ncsi_start_channel_monitor(nc); ncsi_process_next_channel(ndp); break; default: netdev_alert(dev, "Wrong NCSI state 0x%x in config\n", nd->state); } return; error: ncsi_report_link(ndp, true); } static int ncsi_choose_active_channel(struct ncsi_dev_priv *ndp) { struct ncsi_channel *nc, *found, *hot_nc; struct ncsi_channel_mode *ncm; unsigned long flags, cflags; struct ncsi_package *np; bool with_link; spin_lock_irqsave(&ndp->lock, flags); hot_nc = ndp->hot_channel; spin_unlock_irqrestore(&ndp->lock, flags); /* By default the search is done once an inactive channel with up * link is found, unless a preferred channel is set. * If multi_package or multi_channel are configured all channels in the * whitelist are added to the channel queue. */ found = NULL; with_link = false; NCSI_FOR_EACH_PACKAGE(ndp, np) { if (!(ndp->package_whitelist & (0x1 << np->id))) continue; NCSI_FOR_EACH_CHANNEL(np, nc) { if (!(np->channel_whitelist & (0x1 << nc->id))) continue; spin_lock_irqsave(&nc->lock, cflags); if (!list_empty(&nc->link) || nc->state != NCSI_CHANNEL_INACTIVE) { spin_unlock_irqrestore(&nc->lock, cflags); continue; } if (!found) found = nc; if (nc == hot_nc) found = nc; ncm = &nc->modes[NCSI_MODE_LINK]; if (ncm->data[2] & 0x1) { found = nc; with_link = true; } /* If multi_channel is enabled configure all valid * channels whether or not they currently have link * so they will have AENs enabled. */ if (with_link || np->multi_channel) { spin_lock_irqsave(&ndp->lock, flags); list_add_tail_rcu(&nc->link, &ndp->channel_queue); spin_unlock_irqrestore(&ndp->lock, flags); netdev_dbg(ndp->ndev.dev, "NCSI: Channel %u added to queue (link %s)\n", nc->id, ncm->data[2] & 0x1 ? "up" : "down"); } spin_unlock_irqrestore(&nc->lock, cflags); if (with_link && !np->multi_channel) break; } if (with_link && !ndp->multi_package) break; } if (list_empty(&ndp->channel_queue) && found) { netdev_info(ndp->ndev.dev, "NCSI: No channel with link found, configuring channel %u\n", found->id); spin_lock_irqsave(&ndp->lock, flags); list_add_tail_rcu(&found->link, &ndp->channel_queue); spin_unlock_irqrestore(&ndp->lock, flags); } else if (!found) { netdev_warn(ndp->ndev.dev, "NCSI: No channel found to configure!\n"); ncsi_report_link(ndp, true); return -ENODEV; } return ncsi_process_next_channel(ndp); } static bool ncsi_check_hwa(struct ncsi_dev_priv *ndp) { struct ncsi_package *np; struct ncsi_channel *nc; unsigned int cap; bool has_channel = false; /* The hardware arbitration is disabled if any one channel * doesn't support explicitly. */ NCSI_FOR_EACH_PACKAGE(ndp, np) { NCSI_FOR_EACH_CHANNEL(np, nc) { has_channel = true; cap = nc->caps[NCSI_CAP_GENERIC].cap; if (!(cap & NCSI_CAP_GENERIC_HWA) || (cap & NCSI_CAP_GENERIC_HWA_MASK) != NCSI_CAP_GENERIC_HWA_SUPPORT) { ndp->flags &= ~NCSI_DEV_HWA; return false; } } } if (has_channel) { ndp->flags |= NCSI_DEV_HWA; return true; } ndp->flags &= ~NCSI_DEV_HWA; return false; } static void ncsi_probe_channel(struct ncsi_dev_priv *ndp) { struct ncsi_dev *nd = &ndp->ndev; struct ncsi_package *np; struct ncsi_cmd_arg nca; unsigned char index; int ret; nca.ndp = ndp; nca.req_flags = NCSI_REQ_FLAG_EVENT_DRIVEN; switch (nd->state) { case ncsi_dev_state_probe: nd->state = ncsi_dev_state_probe_deselect; fallthrough; case ncsi_dev_state_probe_deselect: ndp->pending_req_num = 8; /* Deselect all possible packages */ nca.type = NCSI_PKT_CMD_DP; nca.channel = NCSI_RESERVED_CHANNEL; for (index = 0; index < 8; index++) { nca.package = index; ret = ncsi_xmit_cmd(&nca); if (ret) goto error; } nd->state = ncsi_dev_state_probe_package; break; case ncsi_dev_state_probe_package: ndp->pending_req_num = 1; nca.type = NCSI_PKT_CMD_SP; nca.bytes[0] = 1; nca.package = ndp->package_probe_id; nca.channel = NCSI_RESERVED_CHANNEL; ret = ncsi_xmit_cmd(&nca); if (ret) goto error; nd->state = ncsi_dev_state_probe_channel; break; case ncsi_dev_state_probe_channel: ndp->active_package = ncsi_find_package(ndp, ndp->package_probe_id); if (!ndp->active_package) { /* No response */ nd->state = ncsi_dev_state_probe_dp; schedule_work(&ndp->work); break; } nd->state = ncsi_dev_state_probe_cis; if (IS_ENABLED(CONFIG_NCSI_OEM_CMD_GET_MAC) && ndp->mlx_multi_host) nd->state = ncsi_dev_state_probe_mlx_gma; schedule_work(&ndp->work); break; case ncsi_dev_state_probe_mlx_gma: ndp->pending_req_num = 1; nca.type = NCSI_PKT_CMD_OEM; nca.package = ndp->active_package->id; nca.channel = 0; ret = ncsi_oem_gma_handler_mlx(&nca); if (ret) goto error; nd->state = ncsi_dev_state_probe_mlx_smaf; break; case ncsi_dev_state_probe_mlx_smaf: ndp->pending_req_num = 1; nca.type = NCSI_PKT_CMD_OEM; nca.package = ndp->active_package->id; nca.channel = 0; ret = ncsi_oem_smaf_mlx(&nca); if (ret) goto error; nd->state = ncsi_dev_state_probe_cis; break; case ncsi_dev_state_probe_keep_phy: ndp->pending_req_num = 1; nca.type = NCSI_PKT_CMD_OEM; nca.package = ndp->active_package->id; nca.channel = 0; ret = ncsi_oem_keep_phy_intel(&nca); if (ret) goto error; nd->state = ncsi_dev_state_probe_gvi; break; case ncsi_dev_state_probe_cis: case ncsi_dev_state_probe_gvi: case ncsi_dev_state_probe_gc: case ncsi_dev_state_probe_gls: np = ndp->active_package; ndp->pending_req_num = 1; /* Clear initial state Retrieve version, capability or link status */ if (nd->state == ncsi_dev_state_probe_cis) nca.type = NCSI_PKT_CMD_CIS; else if (nd->state == ncsi_dev_state_probe_gvi) nca.type = NCSI_PKT_CMD_GVI; else if (nd->state == ncsi_dev_state_probe_gc) nca.type = NCSI_PKT_CMD_GC; else nca.type = NCSI_PKT_CMD_GLS; nca.package = np->id; nca.channel = ndp->channel_probe_id; ret = ncsi_xmit_cmd(&nca); if (ret) goto error; if (nd->state == ncsi_dev_state_probe_cis) { nd->state = ncsi_dev_state_probe_gvi; if (IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY) && ndp->channel_probe_id == 0) nd->state = ncsi_dev_state_probe_keep_phy; } else if (nd->state == ncsi_dev_state_probe_gvi) { nd->state = ncsi_dev_state_probe_gc; } else if (nd->state == ncsi_dev_state_probe_gc) { nd->state = ncsi_dev_state_probe_gls; } else { nd->state = ncsi_dev_state_probe_cis; ndp->channel_probe_id++; } if (ndp->channel_probe_id == ndp->channel_count) { ndp->channel_probe_id = 0; nd->state = ncsi_dev_state_probe_dp; } break; case ncsi_dev_state_probe_dp: ndp->pending_req_num = 1; /* Deselect the current package */ nca.type = NCSI_PKT_CMD_DP; nca.package = ndp->package_probe_id; nca.channel = NCSI_RESERVED_CHANNEL; ret = ncsi_xmit_cmd(&nca); if (ret) goto error; /* Probe next package */ ndp->package_probe_id++; if (ndp->package_probe_id >= 8) { /* Probe finished */ ndp->flags |= NCSI_DEV_PROBED; break; } nd->state = ncsi_dev_state_probe_package; ndp->active_package = NULL; break; default: netdev_warn(nd->dev, "Wrong NCSI state 0x%0x in enumeration\n", nd->state); } if (ndp->flags & NCSI_DEV_PROBED) { /* Check if all packages have HWA support */ ncsi_check_hwa(ndp); ncsi_choose_active_channel(ndp); } return; error: netdev_err(ndp->ndev.dev, "NCSI: Failed to transmit cmd 0x%x during probe\n", nca.type); ncsi_report_link(ndp, true); } static void ncsi_dev_work(struct work_struct *work) { struct ncsi_dev_priv *ndp = container_of(work, struct ncsi_dev_priv, work); struct ncsi_dev *nd = &ndp->ndev; switch (nd->state & ncsi_dev_state_major) { case ncsi_dev_state_probe: ncsi_probe_channel(ndp); break; case ncsi_dev_state_suspend: ncsi_suspend_channel(ndp); break; case ncsi_dev_state_config: ncsi_configure_channel(ndp); break; default: netdev_warn(nd->dev, "Wrong NCSI state 0x%x in workqueue\n", nd->state); } } int ncsi_process_next_channel(struct ncsi_dev_priv *ndp) { struct ncsi_channel *nc; int old_state; unsigned long flags; spin_lock_irqsave(&ndp->lock, flags); nc = list_first_or_null_rcu(&ndp->channel_queue, struct ncsi_channel, link); if (!nc) { spin_unlock_irqrestore(&ndp->lock, flags); goto out; } list_del_init(&nc->link); spin_unlock_irqrestore(&ndp->lock, flags); spin_lock_irqsave(&nc->lock, flags); old_state = nc->state; nc->state = NCSI_CHANNEL_INVISIBLE; spin_unlock_irqrestore(&nc->lock, flags); ndp->active_channel = nc; ndp->active_package = nc->package; switch (old_state) { case NCSI_CHANNEL_INACTIVE: ndp->ndev.state = ncsi_dev_state_config; netdev_dbg(ndp->ndev.dev, "NCSI: configuring channel %u\n", nc->id); ncsi_configure_channel(ndp); break; case NCSI_CHANNEL_ACTIVE: ndp->ndev.state = ncsi_dev_state_suspend; netdev_dbg(ndp->ndev.dev, "NCSI: suspending channel %u\n", nc->id); ncsi_suspend_channel(ndp); break; default: netdev_err(ndp->ndev.dev, "Invalid state 0x%x on %d:%d\n", old_state, nc->package->id, nc->id); ncsi_report_link(ndp, false); return -EINVAL; } return 0; out: ndp->active_channel = NULL; ndp->active_package = NULL; if (ndp->flags & NCSI_DEV_RESHUFFLE) { ndp->flags &= ~NCSI_DEV_RESHUFFLE; return ncsi_choose_active_channel(ndp); } ncsi_report_link(ndp, false); return -ENODEV; } static int ncsi_kick_channels(struct ncsi_dev_priv *ndp) { struct ncsi_dev *nd = &ndp->ndev; struct ncsi_channel *nc; struct ncsi_package *np; unsigned long flags; unsigned int n = 0; NCSI_FOR_EACH_PACKAGE(ndp, np) { NCSI_FOR_EACH_CHANNEL(np, nc) { spin_lock_irqsave(&nc->lock, flags); /* Channels may be busy, mark dirty instead of * kicking if; * a) not ACTIVE (configured) * b) in the channel_queue (to be configured) * c) it's ndev is in the config state */ if (nc->state != NCSI_CHANNEL_ACTIVE) { if ((ndp->ndev.state & 0xff00) == ncsi_dev_state_config || !list_empty(&nc->link)) { netdev_dbg(nd->dev, "NCSI: channel %p marked dirty\n", nc); nc->reconfigure_needed = true; } spin_unlock_irqrestore(&nc->lock, flags); continue; } spin_unlock_irqrestore(&nc->lock, flags); ncsi_stop_channel_monitor(nc); spin_lock_irqsave(&nc->lock, flags); nc->state = NCSI_CHANNEL_INACTIVE; spin_unlock_irqrestore(&nc->lock, flags); spin_lock_irqsave(&ndp->lock, flags); list_add_tail_rcu(&nc->link, &ndp->channel_queue); spin_unlock_irqrestore(&ndp->lock, flags); netdev_dbg(nd->dev, "NCSI: kicked channel %p\n", nc); n++; } } return n; } int ncsi_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { struct ncsi_dev_priv *ndp; unsigned int n_vids = 0; struct vlan_vid *vlan; struct ncsi_dev *nd; bool found = false; if (vid == 0) return 0; nd = ncsi_find_dev(dev); if (!nd) { netdev_warn(dev, "NCSI: No net_device?\n"); return 0; } ndp = TO_NCSI_DEV_PRIV(nd); /* Add the VLAN id to our internal list */ list_for_each_entry_rcu(vlan, &ndp->vlan_vids, list) { n_vids++; if (vlan->vid == vid) { netdev_dbg(dev, "NCSI: vid %u already registered\n", vid); return 0; } } if (n_vids >= NCSI_MAX_VLAN_VIDS) { netdev_warn(dev, "tried to add vlan id %u but NCSI max already registered (%u)\n", vid, NCSI_MAX_VLAN_VIDS); return -ENOSPC; } vlan = kzalloc(sizeof(*vlan), GFP_KERNEL); if (!vlan) return -ENOMEM; vlan->proto = proto; vlan->vid = vid; list_add_rcu(&vlan->list, &ndp->vlan_vids); netdev_dbg(dev, "NCSI: Added new vid %u\n", vid); found = ncsi_kick_channels(ndp) != 0; return found ? ncsi_process_next_channel(ndp) : 0; } EXPORT_SYMBOL_GPL(ncsi_vlan_rx_add_vid); int ncsi_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) { struct vlan_vid *vlan, *tmp; struct ncsi_dev_priv *ndp; struct ncsi_dev *nd; bool found = false; if (vid == 0) return 0; nd = ncsi_find_dev(dev); if (!nd) { netdev_warn(dev, "NCSI: no net_device?\n"); return 0; } ndp = TO_NCSI_DEV_PRIV(nd); /* Remove the VLAN id from our internal list */ list_for_each_entry_safe(vlan, tmp, &ndp->vlan_vids, list) if (vlan->vid == vid) { netdev_dbg(dev, "NCSI: vid %u found, removing\n", vid); list_del_rcu(&vlan->list); found = true; kfree(vlan); } if (!found) { netdev_err(dev, "NCSI: vid %u wasn't registered!\n", vid); return -EINVAL; } found = ncsi_kick_channels(ndp) != 0; return found ? ncsi_process_next_channel(ndp) : 0; } EXPORT_SYMBOL_GPL(ncsi_vlan_rx_kill_vid); struct ncsi_dev *ncsi_register_dev(struct net_device *dev, void (*handler)(struct ncsi_dev *ndev)) { struct ncsi_dev_priv *ndp; struct ncsi_dev *nd; struct platform_device *pdev; struct device_node *np; unsigned long flags; int i; /* Check if the device has been registered or not */ nd = ncsi_find_dev(dev); if (nd) return nd; /* Create NCSI device */ ndp = kzalloc(sizeof(*ndp), GFP_ATOMIC); if (!ndp) return NULL; nd = &ndp->ndev; nd->state = ncsi_dev_state_registered; nd->dev = dev; nd->handler = handler; ndp->pending_req_num = 0; INIT_LIST_HEAD(&ndp->channel_queue); INIT_LIST_HEAD(&ndp->vlan_vids); INIT_WORK(&ndp->work, ncsi_dev_work); ndp->package_whitelist = UINT_MAX; /* Initialize private NCSI device */ spin_lock_init(&ndp->lock); INIT_LIST_HEAD(&ndp->packages); ndp->request_id = NCSI_REQ_START_IDX; for (i = 0; i < ARRAY_SIZE(ndp->requests); i++) { ndp->requests[i].id = i; ndp->requests[i].ndp = ndp; timer_setup(&ndp->requests[i].timer, ncsi_request_timeout, 0); } ndp->channel_count = NCSI_RESERVED_CHANNEL; spin_lock_irqsave(&ncsi_dev_lock, flags); list_add_tail_rcu(&ndp->node, &ncsi_dev_list); spin_unlock_irqrestore(&ncsi_dev_lock, flags); /* Register NCSI packet Rx handler */ ndp->ptype.type = cpu_to_be16(ETH_P_NCSI); ndp->ptype.func = ncsi_rcv_rsp; ndp->ptype.dev = dev; dev_add_pack(&ndp->ptype); pdev = to_platform_device(dev->dev.parent); if (pdev) { np = pdev->dev.of_node; if (np && (of_property_read_bool(np, "mellanox,multi-host") || of_property_read_bool(np, "mlx,multi-host"))) ndp->mlx_multi_host = true; } return nd; } EXPORT_SYMBOL_GPL(ncsi_register_dev); int ncsi_start_dev(struct ncsi_dev *nd) { struct ncsi_dev_priv *ndp = TO_NCSI_DEV_PRIV(nd); if (nd->state != ncsi_dev_state_registered && nd->state != ncsi_dev_state_functional) return -ENOTTY; if (!(ndp->flags & NCSI_DEV_PROBED)) { ndp->package_probe_id = 0; ndp->channel_probe_id = 0; nd->state = ncsi_dev_state_probe; schedule_work(&ndp->work); return 0; } return ncsi_reset_dev(nd); } EXPORT_SYMBOL_GPL(ncsi_start_dev); void ncsi_stop_dev(struct ncsi_dev *nd) { struct ncsi_dev_priv *ndp = TO_NCSI_DEV_PRIV(nd); struct ncsi_package *np; struct ncsi_channel *nc; bool chained; int old_state; unsigned long flags; /* Stop the channel monitor on any active channels. Don't reset the * channel state so we know which were active when ncsi_start_dev() * is next called. */ NCSI_FOR_EACH_PACKAGE(ndp, np) { NCSI_FOR_EACH_CHANNEL(np, nc) { ncsi_stop_channel_monitor(nc); spin_lock_irqsave(&nc->lock, flags); chained = !list_empty(&nc->link); old_state = nc->state; spin_unlock_irqrestore(&nc->lock, flags); WARN_ON_ONCE(chained || old_state == NCSI_CHANNEL_INVISIBLE); } } netdev_dbg(ndp->ndev.dev, "NCSI: Stopping device\n"); ncsi_report_link(ndp, true); } EXPORT_SYMBOL_GPL(ncsi_stop_dev); int ncsi_reset_dev(struct ncsi_dev *nd) { struct ncsi_dev_priv *ndp = TO_NCSI_DEV_PRIV(nd); struct ncsi_channel *nc, *active, *tmp; struct ncsi_package *np; unsigned long flags; spin_lock_irqsave(&ndp->lock, flags); if (!(ndp->flags & NCSI_DEV_RESET)) { /* Haven't been called yet, check states */ switch (nd->state & ncsi_dev_state_major) { case ncsi_dev_state_registered: case ncsi_dev_state_probe: /* Not even probed yet - do nothing */ spin_unlock_irqrestore(&ndp->lock, flags); return 0; case ncsi_dev_state_suspend: case ncsi_dev_state_config: /* Wait for the channel to finish its suspend/config * operation; once it finishes it will check for * NCSI_DEV_RESET and reset the state. */ ndp->flags |= NCSI_DEV_RESET; spin_unlock_irqrestore(&ndp->lock, flags); return 0; } } else { switch (nd->state) { case ncsi_dev_state_suspend_done: case ncsi_dev_state_config_done: case ncsi_dev_state_functional: /* Ok */ break; default: /* Current reset operation happening */ spin_unlock_irqrestore(&ndp->lock, flags); return 0; } } if (!list_empty(&ndp->channel_queue)) { /* Clear any channel queue we may have interrupted */ list_for_each_entry_safe(nc, tmp, &ndp->channel_queue, link) list_del_init(&nc->link); } spin_unlock_irqrestore(&ndp->lock, flags); active = NULL; NCSI_FOR_EACH_PACKAGE(ndp, np) { NCSI_FOR_EACH_CHANNEL(np, nc) { spin_lock_irqsave(&nc->lock, flags); if (nc->state == NCSI_CHANNEL_ACTIVE) { active = nc; nc->state = NCSI_CHANNEL_INVISIBLE; spin_unlock_irqrestore(&nc->lock, flags); ncsi_stop_channel_monitor(nc); break; } spin_unlock_irqrestore(&nc->lock, flags); } if (active) break; } if (!active) { /* Done */ spin_lock_irqsave(&ndp->lock, flags); ndp->flags &= ~NCSI_DEV_RESET; spin_unlock_irqrestore(&ndp->lock, flags); return ncsi_choose_active_channel(ndp); } spin_lock_irqsave(&ndp->lock, flags); ndp->flags |= NCSI_DEV_RESET; ndp->active_channel = active; ndp->active_package = active->package; spin_unlock_irqrestore(&ndp->lock, flags); nd->state = ncsi_dev_state_suspend; schedule_work(&ndp->work); return 0; } void ncsi_unregister_dev(struct ncsi_dev *nd) { struct ncsi_dev_priv *ndp = TO_NCSI_DEV_PRIV(nd); struct ncsi_package *np, *tmp; unsigned long flags; dev_remove_pack(&ndp->ptype); list_for_each_entry_safe(np, tmp, &ndp->packages, node) ncsi_remove_package(np); spin_lock_irqsave(&ncsi_dev_lock, flags); list_del_rcu(&ndp->node); spin_unlock_irqrestore(&ncsi_dev_lock, flags); disable_work_sync(&ndp->work); kfree(ndp); } EXPORT_SYMBOL_GPL(ncsi_unregister_dev); |
| 31 20 42 43 43 113 113 43 113 113 113 273 231 43 43 18 18 1 18 18 3420 3419 221 2825 2829 259 7 14 12 1 90 90 90 90 90 2 3 90 90 82 87 6 6 47 4 45 47 42 6 138 92 58 44 123 123 2 123 123 10 10 8 10 2 8 2 10 1 9 9 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 | // SPDX-License-Identifier: GPL-2.0 /* * drivers/base/power/wakeup.c - System wakeup events framework * * Copyright (c) 2010 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc. */ #define pr_fmt(fmt) "PM: " fmt #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" #define list_for_each_entry_rcu_locked(pos, head, member) \ list_for_each_entry_rcu(pos, head, member, \ srcu_read_lock_held(&wakeup_srcu)) /* * 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. */ static unsigned int wakeup_irq[2] __read_mostly; static DEFINE_RAW_SPINLOCK(wakeup_irq_lock); /* 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_RAW_SPINLOCK(events_lock); static void pm_wakeup_timer_fn(struct timer_list *t); 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), }; static DEFINE_IDA(wakeup_ida); /** * 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; const char *ws_name; int id; ws = kzalloc(sizeof(*ws), GFP_KERNEL); if (!ws) goto err_ws; ws_name = kstrdup_const(name, GFP_KERNEL); if (!ws_name) goto err_name; ws->name = ws_name; id = ida_alloc(&wakeup_ida, GFP_KERNEL); if (id < 0) goto err_id; ws->id = id; return ws; err_id: kfree_const(ws->name); err_name: kfree(ws); err_ws: return NULL; } EXPORT_SYMBOL_GPL(wakeup_source_create); /* * 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); } static void wakeup_source_free(struct wakeup_source *ws) { ida_free(&wakeup_ida, ws->id); kfree_const(ws->name); kfree(ws); } /** * 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; __pm_relax(ws); wakeup_source_record(ws); wakeup_source_free(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); timer_setup(&ws->timer, pm_wakeup_timer_fn, 0); ws->active = false; raw_spin_lock_irqsave(&events_lock, flags); list_add_rcu(&ws->entry, &wakeup_sources); raw_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; raw_spin_lock_irqsave(&events_lock, flags); list_del_rcu(&ws->entry); raw_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. * @dev: Device this wakeup source is associated with (or NULL if virtual). * @name: Name of the wakeup source to register. */ struct wakeup_source *wakeup_source_register(struct device *dev, const char *name) { struct wakeup_source *ws; int ret; ws = wakeup_source_create(name); if (ws) { if (!dev || device_is_registered(dev)) { ret = wakeup_source_sysfs_add(dev, ws); if (ret) { wakeup_source_free(ws); return NULL; } } 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); if (ws->dev) wakeup_source_sysfs_remove(ws); wakeup_source_destroy(ws); } } EXPORT_SYMBOL_GPL(wakeup_source_unregister); /** * wakeup_sources_read_lock - Lock wakeup source list for read. * * Returns an index of srcu lock for struct wakeup_srcu. * This index must be passed to the matching wakeup_sources_read_unlock(). */ int wakeup_sources_read_lock(void) { return srcu_read_lock(&wakeup_srcu); } EXPORT_SYMBOL_GPL(wakeup_sources_read_lock); /** * wakeup_sources_read_unlock - Unlock wakeup source list. * @idx: return value from corresponding wakeup_sources_read_lock() */ void wakeup_sources_read_unlock(int idx) { srcu_read_unlock(&wakeup_srcu, idx); } EXPORT_SYMBOL_GPL(wakeup_sources_read_unlock); /** * wakeup_sources_walk_start - Begin a walk on wakeup source list * * Returns first object of the list of wakeup sources. * * Note that to be safe, wakeup sources list needs to be locked by calling * wakeup_source_read_lock() for this. */ struct wakeup_source *wakeup_sources_walk_start(void) { struct list_head *ws_head = &wakeup_sources; return list_entry_rcu(ws_head->next, struct wakeup_source, entry); } EXPORT_SYMBOL_GPL(wakeup_sources_walk_start); /** * wakeup_sources_walk_next - Get next wakeup source from the list * @ws: Previous wakeup source object * * Note that to be safe, wakeup sources list needs to be locked by calling * wakeup_source_read_lock() for this. */ struct wakeup_source *wakeup_sources_walk_next(struct wakeup_source *ws) { struct list_head *ws_head = &wakeup_sources; return list_next_or_null_rcu(ws_head, &ws->entry, struct wakeup_source, entry); } EXPORT_SYMBOL_GPL(wakeup_sources_walk_next); /** * 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; if (pm_suspend_target_state != PM_SUSPEND_ON) dev_dbg(dev, "Suspicious %s() during system transition!\n", __func__); ws = wakeup_source_register(dev, 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. */ void device_wakeup_attach_irq(struct device *dev, struct wake_irq *wakeirq) { struct wakeup_source *ws; ws = dev->power.wakeup; if (!ws) return; if (ws->wakeirq) dev_err(dev, "Leftover wakeup IRQ found, overriding\n"); ws->wakeirq = wakeirq; } /** * 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 - * * Iterates 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_locked(ws, &wakeup_sources, entry) dev_pm_arm_wake_irq(ws->wakeirq); srcu_read_unlock(&wakeup_srcu, srcuidx); } /** * device_wakeup_disarm_wake_irqs - * * Iterates 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_locked(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. */ void device_wakeup_disable(struct device *dev) { struct wakeup_source *ws; if (!dev || !dev->power.can_wakeup) return; ws = device_wakeup_detach(dev); wakeup_source_unregister(ws); } 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_set_wakeup_enable - Enable or disable a device to wake up the system. * @dev: Device to handle. * @enable: enable/disable flag */ int device_set_wakeup_enable(struct device *dev, bool enable) { if (enable) return device_wakeup_enable(dev); device_wakeup_disable(dev); return 0; } 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; } /* * 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. */ /** * wakeup_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 the 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 /** * wakeup_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 * counter 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. * @t: timer list * * 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(struct timer_list *t) { struct wakeup_source *ws = from_timer(ws, t, timer); 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_dev_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_locked(ws, &wakeup_sources, entry) { if (ws->active) { pm_pr_dbg("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) pm_pr_dbg("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; raw_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; } raw_spin_unlock_irqrestore(&events_lock, flags); if (ret) { pm_pr_dbg("Wakeup pending, aborting suspend\n"); pm_print_active_wakeup_sources(); } return ret || atomic_read(&pm_abort_suspend) > 0; } EXPORT_SYMBOL_GPL(pm_wakeup_pending); 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(unsigned int irq_number) { raw_spin_lock_irq(&wakeup_irq_lock); if (irq_number && wakeup_irq[0] == irq_number) wakeup_irq[0] = wakeup_irq[1]; else wakeup_irq[0] = 0; wakeup_irq[1] = 0; raw_spin_unlock_irq(&wakeup_irq_lock); if (!irq_number) atomic_set(&pm_abort_suspend, 0); } void pm_system_irq_wakeup(unsigned int irq_number) { unsigned long flags; raw_spin_lock_irqsave(&wakeup_irq_lock, flags); if (wakeup_irq[0] == 0) wakeup_irq[0] = irq_number; else if (wakeup_irq[1] == 0) wakeup_irq[1] = irq_number; else irq_number = 0; pm_pr_dbg("Triggering wakeup from IRQ %d\n", irq_number); raw_spin_unlock_irqrestore(&wakeup_irq_lock, flags); if (irq_number) pm_system_wakeup(); } unsigned int pm_wakeup_irq(void) { return wakeup_irq[0]; } /** * 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; raw_spin_lock_irqsave(&events_lock, flags); split_counters(&cnt, &inpr); if (cnt == count && inpr == 0) { saved_count = count; events_check_enabled = true; } raw_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. * @set: 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_locked(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 */ /** * 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; } static void *wakeup_sources_stats_seq_start(struct seq_file *m, loff_t *pos) { struct wakeup_source *ws; loff_t n = *pos; int *srcuidx = m->private; if (n == 0) { 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_locked(ws, &wakeup_sources, entry) { if (n-- <= 0) return ws; } return NULL; } static void *wakeup_sources_stats_seq_next(struct seq_file *m, void *v, loff_t *pos) { struct wakeup_source *ws = v; struct wakeup_source *next_ws = NULL; ++(*pos); list_for_each_entry_continue_rcu(ws, &wakeup_sources, entry) { next_ws = ws; break; } if (!next_ws) print_wakeup_source_stats(m, &deleted_ws); return next_ws; } static void wakeup_sources_stats_seq_stop(struct seq_file *m, void *v) { int *srcuidx = m->private; srcu_read_unlock(&wakeup_srcu, *srcuidx); } /** * wakeup_sources_stats_seq_show - Print wakeup sources statistics information. * @m: seq_file to print the statistics into. * @v: wakeup_source of each iteration */ static int wakeup_sources_stats_seq_show(struct seq_file *m, void *v) { struct wakeup_source *ws = v; print_wakeup_source_stats(m, ws); return 0; } static const struct seq_operations wakeup_sources_stats_seq_ops = { .start = wakeup_sources_stats_seq_start, .next = wakeup_sources_stats_seq_next, .stop = wakeup_sources_stats_seq_stop, .show = wakeup_sources_stats_seq_show, }; static int wakeup_sources_stats_open(struct inode *inode, struct file *file) { return seq_open_private(file, &wakeup_sources_stats_seq_ops, sizeof(int)); } static const struct file_operations wakeup_sources_stats_fops = { .owner = THIS_MODULE, .open = wakeup_sources_stats_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release_private, }; static int __init wakeup_sources_debugfs_init(void) { debugfs_create_file("wakeup_sources", 0444, NULL, NULL, &wakeup_sources_stats_fops); return 0; } postcore_initcall(wakeup_sources_debugfs_init); |
| 43 43 245 12 58 233 233 233 233 12 232 186 187 185 187 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Advanced Linux Sound Architecture * Copyright (c) by Jaroslav Kysela <perex@perex.cz> */ #include <linux/init.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/time.h> #include <sound/core.h> #include <sound/minors.h> #include <sound/info.h> #include <linux/sound.h> #include <linux/mutex.h> #define SNDRV_OSS_MINORS 256 static struct snd_minor *snd_oss_minors[SNDRV_OSS_MINORS]; static DEFINE_MUTEX(sound_oss_mutex); /* NOTE: This function increments the refcount of the associated card like * snd_lookup_minor_data(); the caller must call snd_card_unref() appropriately */ void *snd_lookup_oss_minor_data(unsigned int minor, int type) { struct snd_minor *mreg; void *private_data; if (minor >= ARRAY_SIZE(snd_oss_minors)) return NULL; guard(mutex)(&sound_oss_mutex); mreg = snd_oss_minors[minor]; if (mreg && mreg->type == type) { private_data = mreg->private_data; if (private_data && mreg->card_ptr) get_device(&mreg->card_ptr->card_dev); } else private_data = NULL; return private_data; } EXPORT_SYMBOL(snd_lookup_oss_minor_data); static int snd_oss_kernel_minor(int type, struct snd_card *card, int dev) { int minor; switch (type) { case SNDRV_OSS_DEVICE_TYPE_MIXER: if (snd_BUG_ON(!card || dev < 0 || dev > 1)) return -EINVAL; minor = SNDRV_MINOR_OSS(card->number, (dev ? SNDRV_MINOR_OSS_MIXER1 : SNDRV_MINOR_OSS_MIXER)); break; case SNDRV_OSS_DEVICE_TYPE_SEQUENCER: minor = SNDRV_MINOR_OSS_SEQUENCER; break; case SNDRV_OSS_DEVICE_TYPE_MUSIC: minor = SNDRV_MINOR_OSS_MUSIC; break; case SNDRV_OSS_DEVICE_TYPE_PCM: if (snd_BUG_ON(!card || dev < 0 || dev > 1)) return -EINVAL; minor = SNDRV_MINOR_OSS(card->number, (dev ? SNDRV_MINOR_OSS_PCM1 : SNDRV_MINOR_OSS_PCM)); break; case SNDRV_OSS_DEVICE_TYPE_MIDI: if (snd_BUG_ON(!card || dev < 0 || dev > 1)) return -EINVAL; minor = SNDRV_MINOR_OSS(card->number, (dev ? SNDRV_MINOR_OSS_MIDI1 : SNDRV_MINOR_OSS_MIDI)); break; case SNDRV_OSS_DEVICE_TYPE_DMFM: minor = SNDRV_MINOR_OSS(card->number, SNDRV_MINOR_OSS_DMFM); break; case SNDRV_OSS_DEVICE_TYPE_SNDSTAT: minor = SNDRV_MINOR_OSS_SNDSTAT; break; default: return -EINVAL; } if (minor < 0 || minor >= SNDRV_OSS_MINORS) return -EINVAL; return minor; } int snd_register_oss_device(int type, struct snd_card *card, int dev, const struct file_operations *f_ops, void *private_data) { int minor = snd_oss_kernel_minor(type, card, dev); int minor_unit; struct snd_minor *preg; int cidx = SNDRV_MINOR_OSS_CARD(minor); int track2 = -1; int register1 = -1, register2 = -1; struct device *carddev = snd_card_get_device_link(card); if (card && card->number >= SNDRV_MINOR_OSS_DEVICES) return 0; /* ignore silently */ if (minor < 0) return minor; preg = kmalloc(sizeof(struct snd_minor), GFP_KERNEL); if (preg == NULL) return -ENOMEM; preg->type = type; preg->card = card ? card->number : -1; preg->device = dev; preg->f_ops = f_ops; preg->private_data = private_data; preg->card_ptr = card; guard(mutex)(&sound_oss_mutex); snd_oss_minors[minor] = preg; minor_unit = SNDRV_MINOR_OSS_DEVICE(minor); switch (minor_unit) { case SNDRV_MINOR_OSS_PCM: track2 = SNDRV_MINOR_OSS(cidx, SNDRV_MINOR_OSS_AUDIO); break; case SNDRV_MINOR_OSS_MIDI: track2 = SNDRV_MINOR_OSS(cidx, SNDRV_MINOR_OSS_DMMIDI); break; case SNDRV_MINOR_OSS_MIDI1: track2 = SNDRV_MINOR_OSS(cidx, SNDRV_MINOR_OSS_DMMIDI1); break; } register1 = register_sound_special_device(f_ops, minor, carddev); if (register1 != minor) goto __end; if (track2 >= 0) { register2 = register_sound_special_device(f_ops, track2, carddev); if (register2 != track2) goto __end; snd_oss_minors[track2] = preg; } return 0; __end: if (register2 >= 0) unregister_sound_special(register2); if (register1 >= 0) unregister_sound_special(register1); snd_oss_minors[minor] = NULL; kfree(preg); return -EBUSY; } EXPORT_SYMBOL(snd_register_oss_device); int snd_unregister_oss_device(int type, struct snd_card *card, int dev) { int minor = snd_oss_kernel_minor(type, card, dev); int cidx = SNDRV_MINOR_OSS_CARD(minor); int track2 = -1; struct snd_minor *mptr; if (card && card->number >= SNDRV_MINOR_OSS_DEVICES) return 0; if (minor < 0) return minor; guard(mutex)(&sound_oss_mutex); mptr = snd_oss_minors[minor]; if (mptr == NULL) return -ENOENT; switch (SNDRV_MINOR_OSS_DEVICE(minor)) { case SNDRV_MINOR_OSS_PCM: track2 = SNDRV_MINOR_OSS(cidx, SNDRV_MINOR_OSS_AUDIO); break; case SNDRV_MINOR_OSS_MIDI: track2 = SNDRV_MINOR_OSS(cidx, SNDRV_MINOR_OSS_DMMIDI); break; case SNDRV_MINOR_OSS_MIDI1: track2 = SNDRV_MINOR_OSS(cidx, SNDRV_MINOR_OSS_DMMIDI1); break; } if (track2 >= 0) snd_oss_minors[track2] = NULL; snd_oss_minors[minor] = NULL; /* call unregister_sound_special() outside sound_oss_mutex; * otherwise may deadlock, as it can trigger the release of a card */ unregister_sound_special(minor); if (track2 >= 0) unregister_sound_special(track2); kfree(mptr); return 0; } EXPORT_SYMBOL(snd_unregister_oss_device); /* * INFO PART */ #ifdef CONFIG_SND_PROC_FS static const char *snd_oss_device_type_name(int type) { switch (type) { case SNDRV_OSS_DEVICE_TYPE_MIXER: return "mixer"; case SNDRV_OSS_DEVICE_TYPE_SEQUENCER: case SNDRV_OSS_DEVICE_TYPE_MUSIC: return "sequencer"; case SNDRV_OSS_DEVICE_TYPE_PCM: return "digital audio"; case SNDRV_OSS_DEVICE_TYPE_MIDI: return "raw midi"; case SNDRV_OSS_DEVICE_TYPE_DMFM: return "hardware dependent"; default: return "?"; } } static void snd_minor_info_oss_read(struct snd_info_entry *entry, struct snd_info_buffer *buffer) { int minor; struct snd_minor *mptr; guard(mutex)(&sound_oss_mutex); for (minor = 0; minor < SNDRV_OSS_MINORS; ++minor) { mptr = snd_oss_minors[minor]; if (!mptr) continue; if (mptr->card >= 0) snd_iprintf(buffer, "%3i: [%i-%2i]: %s\n", minor, mptr->card, mptr->device, snd_oss_device_type_name(mptr->type)); else snd_iprintf(buffer, "%3i: : %s\n", minor, snd_oss_device_type_name(mptr->type)); } } int __init snd_minor_info_oss_init(void) { struct snd_info_entry *entry; entry = snd_info_create_module_entry(THIS_MODULE, "devices", snd_oss_root); if (!entry) return -ENOMEM; entry->c.text.read = snd_minor_info_oss_read; return snd_info_register(entry); /* freed in error path */ } #endif /* CONFIG_SND_PROC_FS */ |
| 6910 750 3268 117 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM timestamp #if !defined(_TRACE_TIMESTAMP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_TIMESTAMP_H #include <linux/tracepoint.h> #include <linux/fs.h> #define CTIME_QUERIED_FLAGS \ { I_CTIME_QUERIED, "Q" } DECLARE_EVENT_CLASS(ctime, TP_PROTO(struct inode *inode, struct timespec64 *ctime), TP_ARGS(inode, ctime), TP_STRUCT__entry( __field(dev_t, dev) __field(ino_t, ino) __field(time64_t, ctime_s) __field(u32, ctime_ns) __field(u32, gen) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->gen = inode->i_generation; __entry->ctime_s = ctime->tv_sec; __entry->ctime_ns = ctime->tv_nsec; ), TP_printk("ino=%d:%d:%ld:%u ctime=%lld.%u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->gen, __entry->ctime_s, __entry->ctime_ns ) ); DEFINE_EVENT(ctime, inode_set_ctime_to_ts, TP_PROTO(struct inode *inode, struct timespec64 *ctime), TP_ARGS(inode, ctime)); DEFINE_EVENT(ctime, ctime_xchg_skip, TP_PROTO(struct inode *inode, struct timespec64 *ctime), TP_ARGS(inode, ctime)); TRACE_EVENT(ctime_ns_xchg, TP_PROTO(struct inode *inode, u32 old, u32 new, u32 cur), TP_ARGS(inode, old, new, cur), TP_STRUCT__entry( __field(dev_t, dev) __field(ino_t, ino) __field(u32, gen) __field(u32, old) __field(u32, new) __field(u32, cur) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->gen = inode->i_generation; __entry->old = old; __entry->new = new; __entry->cur = cur; ), TP_printk("ino=%d:%d:%ld:%u old=%u:%s new=%u cur=%u:%s", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->gen, __entry->old & ~I_CTIME_QUERIED, __print_flags(__entry->old & I_CTIME_QUERIED, "|", CTIME_QUERIED_FLAGS), __entry->new, __entry->cur & ~I_CTIME_QUERIED, __print_flags(__entry->cur & I_CTIME_QUERIED, "|", CTIME_QUERIED_FLAGS) ) ); TRACE_EVENT(fill_mg_cmtime, TP_PROTO(struct inode *inode, struct timespec64 *ctime, struct timespec64 *mtime), TP_ARGS(inode, ctime, mtime), TP_STRUCT__entry( __field(dev_t, dev) __field(ino_t, ino) __field(time64_t, ctime_s) __field(time64_t, mtime_s) __field(u32, ctime_ns) __field(u32, mtime_ns) __field(u32, gen) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->gen = inode->i_generation; __entry->ctime_s = ctime->tv_sec; __entry->mtime_s = mtime->tv_sec; __entry->ctime_ns = ctime->tv_nsec; __entry->mtime_ns = mtime->tv_nsec; ), TP_printk("ino=%d:%d:%ld:%u ctime=%lld.%u mtime=%lld.%u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->gen, __entry->ctime_s, __entry->ctime_ns, __entry->mtime_s, __entry->mtime_ns ) ); #endif /* _TRACE_TIMESTAMP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 41 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * NET An implementation of the SOCKET network access protocol. * This is the master header file for the Linux NET layer, * or, in plain English: the networking handling part of the * kernel. * * Version: @(#)net.h 1.0.3 05/25/93 * * Authors: Orest Zborowski, <obz@Kodak.COM> * Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> */ #ifndef _LINUX_NET_H #define _LINUX_NET_H #include <linux/stringify.h> #include <linux/random.h> #include <linux/wait.h> #include <linux/fcntl.h> /* For O_CLOEXEC and O_NONBLOCK */ #include <linux/rcupdate.h> #include <linux/once.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/sockptr.h> #include <uapi/linux/net.h> struct poll_table_struct; struct pipe_inode_info; struct inode; struct file; struct net; /* Historically, SOCKWQ_ASYNC_NOSPACE & SOCKWQ_ASYNC_WAITDATA were located * in sock->flags, but moved into sk->sk_wq->flags to be RCU protected. * Eventually all flags will be in sk->sk_wq->flags. */ #define SOCKWQ_ASYNC_NOSPACE 0 #define SOCKWQ_ASYNC_WAITDATA 1 #define SOCK_NOSPACE 2 #define SOCK_PASSCRED 3 #define SOCK_PASSSEC 4 #define SOCK_SUPPORT_ZC 5 #define SOCK_CUSTOM_SOCKOPT 6 #define SOCK_PASSPIDFD 7 #ifndef ARCH_HAS_SOCKET_TYPES /** * enum sock_type - Socket types * @SOCK_STREAM: stream (connection) socket * @SOCK_DGRAM: datagram (conn.less) socket * @SOCK_RAW: raw socket * @SOCK_RDM: reliably-delivered message * @SOCK_SEQPACKET: sequential packet socket * @SOCK_DCCP: Datagram Congestion Control Protocol socket * @SOCK_PACKET: linux specific way of getting packets at the dev level. * For writing rarp and other similar things on the user level. * * When adding some new socket type please * grep ARCH_HAS_SOCKET_TYPE include/asm-* /socket.h, at least MIPS * overrides this enum for binary compat reasons. */ enum sock_type { SOCK_STREAM = 1, SOCK_DGRAM = 2, SOCK_RAW = 3, SOCK_RDM = 4, SOCK_SEQPACKET = 5, SOCK_DCCP = 6, SOCK_PACKET = 10, }; #define SOCK_MAX (SOCK_PACKET + 1) /* Mask which covers at least up to SOCK_MASK-1. The * remaining bits are used as flags. */ #define SOCK_TYPE_MASK 0xf /* Flags for socket, socketpair, accept4 */ #define SOCK_CLOEXEC O_CLOEXEC #ifndef SOCK_NONBLOCK #define SOCK_NONBLOCK O_NONBLOCK #endif #endif /* ARCH_HAS_SOCKET_TYPES */ /** * enum sock_shutdown_cmd - Shutdown types * @SHUT_RD: shutdown receptions * @SHUT_WR: shutdown transmissions * @SHUT_RDWR: shutdown receptions/transmissions */ enum sock_shutdown_cmd { SHUT_RD, SHUT_WR, SHUT_RDWR, }; struct socket_wq { /* Note: wait MUST be first field of socket_wq */ wait_queue_head_t wait; struct fasync_struct *fasync_list; unsigned long flags; /* %SOCKWQ_ASYNC_NOSPACE, etc */ struct rcu_head rcu; } ____cacheline_aligned_in_smp; /** * struct socket - general BSD socket * @state: socket state (%SS_CONNECTED, etc) * @type: socket type (%SOCK_STREAM, etc) * @flags: socket flags (%SOCK_NOSPACE, etc) * @ops: protocol specific socket operations * @file: File back pointer for gc * @sk: internal networking protocol agnostic socket representation * @wq: wait queue for several uses */ struct socket { socket_state state; short type; unsigned long flags; struct file *file; struct sock *sk; const struct proto_ops *ops; /* Might change with IPV6_ADDRFORM or MPTCP. */ struct socket_wq wq; }; /* * "descriptor" for what we're up to with a read. * This allows us to use the same read code yet * have multiple different users of the data that * we read from a file. * * The simplest case just copies the data to user * mode. */ typedef struct { size_t written; size_t count; union { char __user *buf; void *data; } arg; int error; } read_descriptor_t; struct vm_area_struct; struct page; struct sockaddr; struct msghdr; struct module; struct sk_buff; struct proto_accept_arg; typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *, unsigned int, size_t); typedef int (*skb_read_actor_t)(struct sock *, struct sk_buff *); struct proto_ops { int family; struct module *owner; int (*release) (struct socket *sock); int (*bind) (struct socket *sock, struct sockaddr *myaddr, int sockaddr_len); int (*connect) (struct socket *sock, struct sockaddr *vaddr, int sockaddr_len, int flags); int (*socketpair)(struct socket *sock1, struct socket *sock2); int (*accept) (struct socket *sock, struct socket *newsock, struct proto_accept_arg *arg); int (*getname) (struct socket *sock, struct sockaddr *addr, int peer); __poll_t (*poll) (struct file *file, struct socket *sock, struct poll_table_struct *wait); int (*ioctl) (struct socket *sock, unsigned int cmd, unsigned long arg); #ifdef CONFIG_COMPAT int (*compat_ioctl) (struct socket *sock, unsigned int cmd, unsigned long arg); #endif int (*gettstamp) (struct socket *sock, void __user *userstamp, bool timeval, bool time32); int (*listen) (struct socket *sock, int len); int (*shutdown) (struct socket *sock, int flags); int (*setsockopt)(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen); int (*getsockopt)(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen); void (*show_fdinfo)(struct seq_file *m, struct socket *sock); int (*sendmsg) (struct socket *sock, struct msghdr *m, size_t total_len); /* Notes for implementing recvmsg: * =============================== * msg->msg_namelen should get updated by the recvmsg handlers * iff msg_name != NULL. It is by default 0 to prevent * returning uninitialized memory to user space. The recvfrom * handlers can assume that msg.msg_name is either NULL or has * a minimum size of sizeof(struct sockaddr_storage). */ int (*recvmsg) (struct socket *sock, struct msghdr *m, size_t total_len, int flags); int (*mmap) (struct file *file, struct socket *sock, struct vm_area_struct * vma); ssize_t (*splice_read)(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); void (*splice_eof)(struct socket *sock); int (*set_peek_off)(struct sock *sk, int val); int (*peek_len)(struct socket *sock); /* The following functions are called internally by kernel with * sock lock already held. */ int (*read_sock)(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor); /* This is different from read_sock(), it reads an entire skb at a time. */ int (*read_skb)(struct sock *sk, skb_read_actor_t recv_actor); int (*sendmsg_locked)(struct sock *sk, struct msghdr *msg, size_t size); int (*set_rcvlowat)(struct sock *sk, int val); }; #define DECLARE_SOCKADDR(type, dst, src) \ type dst = ({ __sockaddr_check_size(sizeof(*dst)); (type) src; }) struct net_proto_family { int family; int (*create)(struct net *net, struct socket *sock, int protocol, int kern); struct module *owner; }; struct iovec; struct kvec; enum { SOCK_WAKE_IO, SOCK_WAKE_WAITD, SOCK_WAKE_SPACE, SOCK_WAKE_URG, }; int sock_wake_async(struct socket_wq *sk_wq, int how, int band); int sock_register(const struct net_proto_family *fam); void sock_unregister(int family); bool sock_is_registered(int family); int __sock_create(struct net *net, int family, int type, int proto, struct socket **res, int kern); int sock_create(int family, int type, int proto, struct socket **res); int sock_create_kern(struct net *net, int family, int type, int proto, struct socket **res); int sock_create_lite(int family, int type, int proto, struct socket **res); struct socket *sock_alloc(void); void sock_release(struct socket *sock); int sock_sendmsg(struct socket *sock, struct msghdr *msg); int sock_recvmsg(struct socket *sock, struct msghdr *msg, int flags); struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname); struct socket *sockfd_lookup(int fd, int *err); struct socket *sock_from_file(struct file *file); #define sockfd_put(sock) fput(sock->file) int net_ratelimit(void); #define net_ratelimited_function(function, ...) \ do { \ if (net_ratelimit()) \ function(__VA_ARGS__); \ } while (0) #define net_emerg_ratelimited(fmt, ...) \ net_ratelimited_function(pr_emerg, fmt, ##__VA_ARGS__) #define net_alert_ratelimited(fmt, ...) \ net_ratelimited_function(pr_alert, fmt, ##__VA_ARGS__) #define net_crit_ratelimited(fmt, ...) \ net_ratelimited_function(pr_crit, fmt, ##__VA_ARGS__) #define net_err_ratelimited(fmt, ...) \ net_ratelimited_function(pr_err, fmt, ##__VA_ARGS__) #define net_notice_ratelimited(fmt, ...) \ net_ratelimited_function(pr_notice, fmt, ##__VA_ARGS__) #define net_warn_ratelimited(fmt, ...) \ net_ratelimited_function(pr_warn, fmt, ##__VA_ARGS__) #define net_info_ratelimited(fmt, ...) \ net_ratelimited_function(pr_info, fmt, ##__VA_ARGS__) #if defined(CONFIG_DYNAMIC_DEBUG) || \ (defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE)) #define net_dbg_ratelimited(fmt, ...) \ do { \ DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \ if (DYNAMIC_DEBUG_BRANCH(descriptor) && \ net_ratelimit()) \ __dynamic_pr_debug(&descriptor, pr_fmt(fmt), \ ##__VA_ARGS__); \ } while (0) #elif defined(DEBUG) #define net_dbg_ratelimited(fmt, ...) \ net_ratelimited_function(pr_debug, fmt, ##__VA_ARGS__) #else #define net_dbg_ratelimited(fmt, ...) \ no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__) #endif #define net_get_random_once(buf, nbytes) \ get_random_once((buf), (nbytes)) /* * E.g. XFS meta- & log-data is in slab pages, or bcache meta * data pages, or other high order pages allocated by * __get_free_pages() without __GFP_COMP, which have a page_count * of 0 and/or have PageSlab() set. We cannot use send_page for * those, as that does get_page(); put_page(); and would cause * either a VM_BUG directly, or __page_cache_release a page that * would actually still be referenced by someone, leading to some * obscure delayed Oops somewhere else. */ static inline bool sendpage_ok(struct page *page) { return !PageSlab(page) && page_count(page) >= 1; } /* * Check sendpage_ok on contiguous pages. */ static inline bool sendpages_ok(struct page *page, size_t len, size_t offset) { struct page *p = page + (offset >> PAGE_SHIFT); size_t count = 0; while (count < len) { if (!sendpage_ok(p)) return false; p++; count += PAGE_SIZE; } return true; } int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len); int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg, struct kvec *vec, size_t num, size_t len); int kernel_recvmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len, int flags); int kernel_bind(struct socket *sock, struct sockaddr *addr, int addrlen); int kernel_listen(struct socket *sock, int backlog); int kernel_accept(struct socket *sock, struct socket **newsock, int flags); int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen, int flags); int kernel_getsockname(struct socket *sock, struct sockaddr *addr); int kernel_getpeername(struct socket *sock, struct sockaddr *addr); int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how); /* Routine returns the IP overhead imposed by a (caller-protected) socket. */ u32 kernel_sock_ip_overhead(struct sock *sk); #define MODULE_ALIAS_NETPROTO(proto) \ MODULE_ALIAS("net-pf-" __stringify(proto)) #define MODULE_ALIAS_NET_PF_PROTO(pf, proto) \ MODULE_ALIAS("net-pf-" __stringify(pf) "-proto-" __stringify(proto)) #define MODULE_ALIAS_NET_PF_PROTO_TYPE(pf, proto, type) \ MODULE_ALIAS("net-pf-" __stringify(pf) "-proto-" __stringify(proto) \ "-type-" __stringify(type)) #define MODULE_ALIAS_NET_PF_PROTO_NAME(pf, proto, name) \ MODULE_ALIAS("net-pf-" __stringify(pf) "-proto-" __stringify(proto) \ name) #endif /* _LINUX_NET_H */ |
| 17 1 117 3 57 10 65 18 2 11 5 5 1 3 2 5 1 1 3 3 1 2 15 1 1 1 1 11 3 14 1 13 13 13 9 8 1 8 5 5 18 2 1 1 4 4 4 2 2 5 1 6 3 9 2 7 1 1 2 5 1 4 6 3 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 | // SPDX-License-Identifier: GPL-2.0+ /* * NILFS pathname lookup operations. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * * Modified for NILFS by Amagai Yoshiji and Ryusuke Konishi. */ /* * linux/fs/ext2/namei.c * * Copyright (C) 1992, 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) * Laboratoire MASI - Institut Blaise Pascal * Universite Pierre et Marie Curie (Paris VI) * * from * * linux/fs/minix/namei.c * * Copyright (C) 1991, 1992 Linus Torvalds * * Big-endian to little-endian byte-swapping/bitmaps by * David S. Miller (davem@caip.rutgers.edu), 1995 */ #include <linux/pagemap.h> #include "nilfs.h" #include "export.h" #define NILFS_FID_SIZE_NON_CONNECTABLE \ (offsetof(struct nilfs_fid, parent_gen) / 4) #define NILFS_FID_SIZE_CONNECTABLE (sizeof(struct nilfs_fid) / 4) static inline int nilfs_add_nondir(struct dentry *dentry, struct inode *inode) { int err = nilfs_add_link(dentry, inode); if (!err) { d_instantiate_new(dentry, inode); return 0; } inode_dec_link_count(inode); unlock_new_inode(inode); iput(inode); return err; } /* * Methods themselves. */ static struct dentry * nilfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct inode *inode; ino_t ino; int res; if (dentry->d_name.len > NILFS_NAME_LEN) return ERR_PTR(-ENAMETOOLONG); res = nilfs_inode_by_name(dir, &dentry->d_name, &ino); if (res) { if (res != -ENOENT) return ERR_PTR(res); inode = NULL; } else { inode = nilfs_iget(dir->i_sb, NILFS_I(dir)->i_root, ino); } return d_splice_alias(inode, dentry); } /* * By the time this is called, we already have created * the directory cache entry for the new file, but it * is so far negative - it has no inode. * * If the create succeeds, we fill in the inode information * with d_instantiate(). */ static int nilfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { struct inode *inode; struct nilfs_transaction_info ti; int err; err = nilfs_transaction_begin(dir->i_sb, &ti, 1); if (err) return err; inode = nilfs_new_inode(dir, mode); err = PTR_ERR(inode); if (!IS_ERR(inode)) { inode->i_op = &nilfs_file_inode_operations; inode->i_fop = &nilfs_file_operations; inode->i_mapping->a_ops = &nilfs_aops; nilfs_mark_inode_dirty(inode); err = nilfs_add_nondir(dentry, inode); } if (!err) err = nilfs_transaction_commit(dir->i_sb); else nilfs_transaction_abort(dir->i_sb); return err; } static int nilfs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { struct inode *inode; struct nilfs_transaction_info ti; int err; err = nilfs_transaction_begin(dir->i_sb, &ti, 1); if (err) return err; inode = nilfs_new_inode(dir, mode); err = PTR_ERR(inode); if (!IS_ERR(inode)) { init_special_inode(inode, inode->i_mode, rdev); nilfs_mark_inode_dirty(inode); err = nilfs_add_nondir(dentry, inode); } if (!err) err = nilfs_transaction_commit(dir->i_sb); else nilfs_transaction_abort(dir->i_sb); return err; } static int nilfs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { struct nilfs_transaction_info ti; struct super_block *sb = dir->i_sb; unsigned int l = strlen(symname) + 1; struct inode *inode; int err; if (l > sb->s_blocksize) return -ENAMETOOLONG; err = nilfs_transaction_begin(dir->i_sb, &ti, 1); if (err) return err; inode = nilfs_new_inode(dir, S_IFLNK | 0777); err = PTR_ERR(inode); if (IS_ERR(inode)) goto out; /* slow symlink */ inode->i_op = &nilfs_symlink_inode_operations; inode_nohighmem(inode); mapping_set_gfp_mask(inode->i_mapping, mapping_gfp_constraint(inode->i_mapping, ~__GFP_FS)); inode->i_mapping->a_ops = &nilfs_aops; err = page_symlink(inode, symname, l); if (err) goto out_fail; /* mark_inode_dirty(inode); */ /* page_symlink() do this */ err = nilfs_add_nondir(dentry, inode); out: if (!err) err = nilfs_transaction_commit(dir->i_sb); else nilfs_transaction_abort(dir->i_sb); return err; out_fail: drop_nlink(inode); nilfs_mark_inode_dirty(inode); unlock_new_inode(inode); iput(inode); goto out; } static int nilfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(old_dentry); struct nilfs_transaction_info ti; int err; err = nilfs_transaction_begin(dir->i_sb, &ti, 1); if (err) return err; inode_set_ctime_current(inode); inode_inc_link_count(inode); ihold(inode); err = nilfs_add_link(dentry, inode); if (!err) { d_instantiate(dentry, inode); err = nilfs_transaction_commit(dir->i_sb); } else { inode_dec_link_count(inode); iput(inode); nilfs_transaction_abort(dir->i_sb); } return err; } static int nilfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct inode *inode; struct nilfs_transaction_info ti; int err; err = nilfs_transaction_begin(dir->i_sb, &ti, 1); if (err) return err; inc_nlink(dir); inode = nilfs_new_inode(dir, S_IFDIR | mode); err = PTR_ERR(inode); if (IS_ERR(inode)) goto out_dir; inode->i_op = &nilfs_dir_inode_operations; inode->i_fop = &nilfs_dir_operations; inode->i_mapping->a_ops = &nilfs_aops; inc_nlink(inode); err = nilfs_make_empty(inode, dir); if (err) goto out_fail; err = nilfs_add_link(dentry, inode); if (err) goto out_fail; nilfs_mark_inode_dirty(inode); d_instantiate_new(dentry, inode); out: if (!err) err = nilfs_transaction_commit(dir->i_sb); else nilfs_transaction_abort(dir->i_sb); return err; out_fail: drop_nlink(inode); drop_nlink(inode); nilfs_mark_inode_dirty(inode); unlock_new_inode(inode); iput(inode); out_dir: drop_nlink(dir); nilfs_mark_inode_dirty(dir); goto out; } static int nilfs_do_unlink(struct inode *dir, struct dentry *dentry) { struct inode *inode; struct nilfs_dir_entry *de; struct folio *folio; int err; de = nilfs_find_entry(dir, &dentry->d_name, &folio); if (IS_ERR(de)) { err = PTR_ERR(de); goto out; } inode = d_inode(dentry); err = -EIO; if (le64_to_cpu(de->inode) != inode->i_ino) goto out; if (!inode->i_nlink) { nilfs_warn(inode->i_sb, "deleting nonexistent file (ino=%lu), %d", inode->i_ino, inode->i_nlink); set_nlink(inode, 1); } err = nilfs_delete_entry(de, folio); folio_release_kmap(folio, de); if (err) goto out; inode_set_ctime_to_ts(inode, inode_get_ctime(dir)); drop_nlink(inode); err = 0; out: return err; } static int nilfs_unlink(struct inode *dir, struct dentry *dentry) { struct nilfs_transaction_info ti; int err; err = nilfs_transaction_begin(dir->i_sb, &ti, 0); if (err) return err; err = nilfs_do_unlink(dir, dentry); if (!err) { nilfs_mark_inode_dirty(dir); nilfs_mark_inode_dirty(d_inode(dentry)); err = nilfs_transaction_commit(dir->i_sb); } else nilfs_transaction_abort(dir->i_sb); return err; } static int nilfs_rmdir(struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(dentry); struct nilfs_transaction_info ti; int err; err = nilfs_transaction_begin(dir->i_sb, &ti, 0); if (err) return err; err = -ENOTEMPTY; if (nilfs_empty_dir(inode)) { err = nilfs_do_unlink(dir, dentry); if (!err) { inode->i_size = 0; drop_nlink(inode); nilfs_mark_inode_dirty(inode); drop_nlink(dir); nilfs_mark_inode_dirty(dir); } } if (!err) err = nilfs_transaction_commit(dir->i_sb); else nilfs_transaction_abort(dir->i_sb); return err; } static int nilfs_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { struct inode *old_inode = d_inode(old_dentry); struct inode *new_inode = d_inode(new_dentry); struct folio *dir_folio = NULL; struct nilfs_dir_entry *dir_de = NULL; struct folio *old_folio; struct nilfs_dir_entry *old_de; struct nilfs_transaction_info ti; int err; if (flags & ~RENAME_NOREPLACE) return -EINVAL; err = nilfs_transaction_begin(old_dir->i_sb, &ti, 1); if (unlikely(err)) return err; old_de = nilfs_find_entry(old_dir, &old_dentry->d_name, &old_folio); if (IS_ERR(old_de)) { err = PTR_ERR(old_de); goto out; } if (S_ISDIR(old_inode->i_mode)) { err = -EIO; dir_de = nilfs_dotdot(old_inode, &dir_folio); if (!dir_de) goto out_old; } if (new_inode) { struct folio *new_folio; struct nilfs_dir_entry *new_de; err = -ENOTEMPTY; if (dir_de && !nilfs_empty_dir(new_inode)) goto out_dir; new_de = nilfs_find_entry(new_dir, &new_dentry->d_name, &new_folio); if (IS_ERR(new_de)) { err = PTR_ERR(new_de); goto out_dir; } nilfs_set_link(new_dir, new_de, new_folio, old_inode); folio_release_kmap(new_folio, new_de); nilfs_mark_inode_dirty(new_dir); inode_set_ctime_current(new_inode); if (dir_de) drop_nlink(new_inode); drop_nlink(new_inode); nilfs_mark_inode_dirty(new_inode); } else { err = nilfs_add_link(new_dentry, old_inode); if (err) goto out_dir; if (dir_de) { inc_nlink(new_dir); nilfs_mark_inode_dirty(new_dir); } } /* * Like most other Unix systems, set the ctime for inodes on a * rename. */ inode_set_ctime_current(old_inode); nilfs_delete_entry(old_de, old_folio); if (dir_de) { nilfs_set_link(old_inode, dir_de, dir_folio, new_dir); folio_release_kmap(dir_folio, dir_de); drop_nlink(old_dir); } folio_release_kmap(old_folio, old_de); nilfs_mark_inode_dirty(old_dir); nilfs_mark_inode_dirty(old_inode); err = nilfs_transaction_commit(old_dir->i_sb); return err; out_dir: if (dir_de) folio_release_kmap(dir_folio, dir_de); out_old: folio_release_kmap(old_folio, old_de); out: nilfs_transaction_abort(old_dir->i_sb); return err; } /* * Export operations */ static struct dentry *nilfs_get_parent(struct dentry *child) { ino_t ino; int res; struct nilfs_root *root; res = nilfs_inode_by_name(d_inode(child), &dotdot_name, &ino); if (res) return ERR_PTR(res); root = NILFS_I(d_inode(child))->i_root; return d_obtain_alias(nilfs_iget(child->d_sb, root, ino)); } static struct dentry *nilfs_get_dentry(struct super_block *sb, u64 cno, u64 ino, u32 gen) { struct nilfs_root *root; struct inode *inode; if (ino < NILFS_FIRST_INO(sb) && ino != NILFS_ROOT_INO) return ERR_PTR(-ESTALE); root = nilfs_lookup_root(sb->s_fs_info, cno); if (!root) return ERR_PTR(-ESTALE); inode = nilfs_iget(sb, root, ino); nilfs_put_root(root); if (IS_ERR(inode)) return ERR_CAST(inode); if (gen && inode->i_generation != gen) { iput(inode); return ERR_PTR(-ESTALE); } return d_obtain_alias(inode); } static struct dentry *nilfs_fh_to_dentry(struct super_block *sb, struct fid *fh, int fh_len, int fh_type) { struct nilfs_fid *fid = (struct nilfs_fid *)fh; if (fh_len < NILFS_FID_SIZE_NON_CONNECTABLE || (fh_type != FILEID_NILFS_WITH_PARENT && fh_type != FILEID_NILFS_WITHOUT_PARENT)) return NULL; return nilfs_get_dentry(sb, fid->cno, fid->ino, fid->gen); } static struct dentry *nilfs_fh_to_parent(struct super_block *sb, struct fid *fh, int fh_len, int fh_type) { struct nilfs_fid *fid = (struct nilfs_fid *)fh; if (fh_len < NILFS_FID_SIZE_CONNECTABLE || fh_type != FILEID_NILFS_WITH_PARENT) return NULL; return nilfs_get_dentry(sb, fid->cno, fid->parent_ino, fid->parent_gen); } static int nilfs_encode_fh(struct inode *inode, __u32 *fh, int *lenp, struct inode *parent) { struct nilfs_fid *fid = (struct nilfs_fid *)fh; struct nilfs_root *root = NILFS_I(inode)->i_root; int type; if (parent && *lenp < NILFS_FID_SIZE_CONNECTABLE) { *lenp = NILFS_FID_SIZE_CONNECTABLE; return FILEID_INVALID; } if (*lenp < NILFS_FID_SIZE_NON_CONNECTABLE) { *lenp = NILFS_FID_SIZE_NON_CONNECTABLE; return FILEID_INVALID; } fid->cno = root->cno; fid->ino = inode->i_ino; fid->gen = inode->i_generation; if (parent) { fid->parent_ino = parent->i_ino; fid->parent_gen = parent->i_generation; type = FILEID_NILFS_WITH_PARENT; *lenp = NILFS_FID_SIZE_CONNECTABLE; } else { type = FILEID_NILFS_WITHOUT_PARENT; *lenp = NILFS_FID_SIZE_NON_CONNECTABLE; } return type; } const struct inode_operations nilfs_dir_inode_operations = { .create = nilfs_create, .lookup = nilfs_lookup, .link = nilfs_link, .unlink = nilfs_unlink, .symlink = nilfs_symlink, .mkdir = nilfs_mkdir, .rmdir = nilfs_rmdir, .mknod = nilfs_mknod, .rename = nilfs_rename, .setattr = nilfs_setattr, .permission = nilfs_permission, .fiemap = nilfs_fiemap, .fileattr_get = nilfs_fileattr_get, .fileattr_set = nilfs_fileattr_set, }; const struct inode_operations nilfs_special_inode_operations = { .setattr = nilfs_setattr, .permission = nilfs_permission, }; const struct inode_operations nilfs_symlink_inode_operations = { .get_link = page_get_link, .permission = nilfs_permission, }; const struct export_operations nilfs_export_ops = { .encode_fh = nilfs_encode_fh, .fh_to_dentry = nilfs_fh_to_dentry, .fh_to_parent = nilfs_fh_to_parent, .get_parent = nilfs_get_parent, }; |
| 1 1 1 1 1 1 1 1 1 1 1 1 2 2 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 | /* * Copyright 2017 Red Hat * Parts ported from amdgpu (fence wait code). * Copyright 2016 Advanced Micro Devices, Inc. * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the "Software"), * to deal in the Software without restriction, including without limitation * the rights to use, copy, modify, merge, publish, distribute, sublicense, * and/or sell copies of the Software, and to permit persons to whom the * Software is furnished to do so, subject to the following conditions: * * The above copyright notice and this permission notice (including the next * paragraph) shall be included in all copies or substantial portions of the * Software. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL * THE 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. * * Authors: * */ /** * DOC: Overview * * DRM synchronisation objects (syncobj, see struct &drm_syncobj) provide a * container for a synchronization primitive which can be used by userspace * to explicitly synchronize GPU commands, can be shared between userspace * processes, and can be shared between different DRM drivers. * Their primary use-case is to implement Vulkan fences and semaphores. * The syncobj userspace API provides ioctls for several operations: * * - Creation and destruction of syncobjs * - Import and export of syncobjs to/from a syncobj file descriptor * - Import and export a syncobj's underlying fence to/from a sync file * - Reset a syncobj (set its fence to NULL) * - Signal a syncobj (set a trivially signaled fence) * - Wait for a syncobj's fence to appear and be signaled * * The syncobj userspace API also provides operations to manipulate a syncobj * in terms of a timeline of struct &dma_fence_chain rather than a single * struct &dma_fence, through the following operations: * * - Signal a given point on the timeline * - Wait for a given point to appear and/or be signaled * - Import and export from/to a given point of a timeline * * At it's core, a syncobj is simply a wrapper around a pointer to a struct * &dma_fence which may be NULL. * When a syncobj is first created, its pointer is either NULL or a pointer * to an already signaled fence depending on whether the * &DRM_SYNCOBJ_CREATE_SIGNALED flag is passed to * &DRM_IOCTL_SYNCOBJ_CREATE. * * If the syncobj is considered as a binary (its state is either signaled or * unsignaled) primitive, when GPU work is enqueued in a DRM driver to signal * the syncobj, the syncobj's fence is replaced with a fence which will be * signaled by the completion of that work. * If the syncobj is considered as a timeline primitive, when GPU work is * enqueued in a DRM driver to signal the a given point of the syncobj, a new * struct &dma_fence_chain pointing to the DRM driver's fence and also * pointing to the previous fence that was in the syncobj. The new struct * &dma_fence_chain fence replace the syncobj's fence and will be signaled by * completion of the DRM driver's work and also any work associated with the * fence previously in the syncobj. * * When GPU work which waits on a syncobj is enqueued in a DRM driver, at the * time the work is enqueued, it waits on the syncobj's fence before * submitting the work to hardware. That fence is either : * * - The syncobj's current fence if the syncobj is considered as a binary * primitive. * - The struct &dma_fence associated with a given point if the syncobj is * considered as a timeline primitive. * * If the syncobj's fence is NULL or not present in the syncobj's timeline, * the enqueue operation is expected to fail. * * With binary syncobj, all manipulation of the syncobjs's fence happens in * terms of the current fence at the time the ioctl is called by userspace * regardless of whether that operation is an immediate host-side operation * (signal or reset) or or an operation which is enqueued in some driver * queue. &DRM_IOCTL_SYNCOBJ_RESET and &DRM_IOCTL_SYNCOBJ_SIGNAL can be used * to manipulate a syncobj from the host by resetting its pointer to NULL or * setting its pointer to a fence which is already signaled. * * With a timeline syncobj, all manipulation of the synobj's fence happens in * terms of a u64 value referring to point in the timeline. See * dma_fence_chain_find_seqno() to see how a given point is found in the * timeline. * * Note that applications should be careful to always use timeline set of * ioctl() when dealing with syncobj considered as timeline. Using a binary * set of ioctl() with a syncobj considered as timeline could result incorrect * synchronization. The use of binary syncobj is supported through the * timeline set of ioctl() by using a point value of 0, this will reproduce * the behavior of the binary set of ioctl() (for example replace the * syncobj's fence when signaling). * * * Host-side wait on syncobjs * -------------------------- * * &DRM_IOCTL_SYNCOBJ_WAIT takes an array of syncobj handles and does a * host-side wait on all of the syncobj fences simultaneously. * If &DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL is set, the wait ioctl will wait on * all of the syncobj fences to be signaled before it returns. * Otherwise, it returns once at least one syncobj fence has been signaled * and the index of a signaled fence is written back to the client. * * Unlike the enqueued GPU work dependencies which fail if they see a NULL * fence in a syncobj, if &DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT is set, * the host-side wait will first wait for the syncobj to receive a non-NULL * fence and then wait on that fence. * If &DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT is not set and any one of the * syncobjs in the array has a NULL fence, -EINVAL will be returned. * Assuming the syncobj starts off with a NULL fence, this allows a client * to do a host wait in one thread (or process) which waits on GPU work * submitted in another thread (or process) without having to manually * synchronize between the two. * This requirement is inherited from the Vulkan fence API. * * If &DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE is set, the ioctl will also set * a fence deadline hint on the backing fences before waiting, to provide the * fence signaler with an appropriate sense of urgency. The deadline is * specified as an absolute &CLOCK_MONOTONIC value in units of ns. * * Similarly, &DRM_IOCTL_SYNCOBJ_TIMELINE_WAIT takes an array of syncobj * handles as well as an array of u64 points and does a host-side wait on all * of syncobj fences at the given points simultaneously. * * &DRM_IOCTL_SYNCOBJ_TIMELINE_WAIT also adds the ability to wait for a given * fence to materialize on the timeline without waiting for the fence to be * signaled by using the &DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE flag. This * requirement is inherited from the wait-before-signal behavior required by * the Vulkan timeline semaphore API. * * Alternatively, &DRM_IOCTL_SYNCOBJ_EVENTFD can be used to wait without * blocking: an eventfd will be signaled when the syncobj is. This is useful to * integrate the wait in an event loop. * * * Import/export of syncobjs * ------------------------- * * &DRM_IOCTL_SYNCOBJ_FD_TO_HANDLE and &DRM_IOCTL_SYNCOBJ_HANDLE_TO_FD * provide two mechanisms for import/export of syncobjs. * * The first lets the client import or export an entire syncobj to a file * descriptor. * These fd's are opaque and have no other use case, except passing the * syncobj between processes. * All exported file descriptors and any syncobj handles created as a * result of importing those file descriptors own a reference to the * same underlying struct &drm_syncobj and the syncobj can be used * persistently across all the processes with which it is shared. * The syncobj is freed only once the last reference is dropped. * Unlike dma-buf, importing a syncobj creates a new handle (with its own * reference) for every import instead of de-duplicating. * The primary use-case of this persistent import/export is for shared * Vulkan fences and semaphores. * * The second import/export mechanism, which is indicated by * &DRM_SYNCOBJ_FD_TO_HANDLE_FLAGS_IMPORT_SYNC_FILE or * &DRM_SYNCOBJ_HANDLE_TO_FD_FLAGS_EXPORT_SYNC_FILE lets the client * import/export the syncobj's current fence from/to a &sync_file. * When a syncobj is exported to a sync file, that sync file wraps the * sycnobj's fence at the time of export and any later signal or reset * operations on the syncobj will not affect the exported sync file. * When a sync file is imported into a syncobj, the syncobj's fence is set * to the fence wrapped by that sync file. * Because sync files are immutable, resetting or signaling the syncobj * will not affect any sync files whose fences have been imported into the * syncobj. * * * Import/export of timeline points in timeline syncobjs * ----------------------------------------------------- * * &DRM_IOCTL_SYNCOBJ_TRANSFER provides a mechanism to transfer a struct * &dma_fence_chain of a syncobj at a given u64 point to another u64 point * into another syncobj. * * Note that if you want to transfer a struct &dma_fence_chain from a given * point on a timeline syncobj from/into a binary syncobj, you can use the * point 0 to mean take/replace the fence in the syncobj. */ #include <linux/anon_inodes.h> #include <linux/dma-fence-unwrap.h> #include <linux/eventfd.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/sched/signal.h> #include <linux/sync_file.h> #include <linux/uaccess.h> #include <drm/drm.h> #include <drm/drm_drv.h> #include <drm/drm_file.h> #include <drm/drm_gem.h> #include <drm/drm_print.h> #include <drm/drm_syncobj.h> #include <drm/drm_utils.h> #include "drm_internal.h" struct syncobj_wait_entry { struct list_head node; struct task_struct *task; struct dma_fence *fence; struct dma_fence_cb fence_cb; u64 point; }; static void syncobj_wait_syncobj_func(struct drm_syncobj *syncobj, struct syncobj_wait_entry *wait); struct syncobj_eventfd_entry { struct list_head node; struct dma_fence *fence; struct dma_fence_cb fence_cb; struct drm_syncobj *syncobj; struct eventfd_ctx *ev_fd_ctx; u64 point; u32 flags; }; static void syncobj_eventfd_entry_func(struct drm_syncobj *syncobj, struct syncobj_eventfd_entry *entry); /** * drm_syncobj_find - lookup and reference a sync object. * @file_private: drm file private pointer * @handle: sync object handle to lookup. * * Returns a reference to the syncobj pointed to by handle or NULL. The * reference must be released by calling drm_syncobj_put(). */ struct drm_syncobj *drm_syncobj_find(struct drm_file *file_private, u32 handle) { struct drm_syncobj *syncobj; spin_lock(&file_private->syncobj_table_lock); /* Check if we currently have a reference on the object */ syncobj = idr_find(&file_private->syncobj_idr, handle); if (syncobj) drm_syncobj_get(syncobj); spin_unlock(&file_private->syncobj_table_lock); return syncobj; } EXPORT_SYMBOL(drm_syncobj_find); static void drm_syncobj_fence_add_wait(struct drm_syncobj *syncobj, struct syncobj_wait_entry *wait) { struct dma_fence *fence; if (wait->fence) return; spin_lock(&syncobj->lock); /* We've already tried once to get a fence and failed. Now that we * have the lock, try one more time just to be sure we don't add a * callback when a fence has already been set. */ fence = dma_fence_get(rcu_dereference_protected(syncobj->fence, 1)); if (!fence || dma_fence_chain_find_seqno(&fence, wait->point)) { dma_fence_put(fence); list_add_tail(&wait->node, &syncobj->cb_list); } else if (!fence) { wait->fence = dma_fence_get_stub(); } else { wait->fence = fence; } spin_unlock(&syncobj->lock); } static void drm_syncobj_remove_wait(struct drm_syncobj *syncobj, struct syncobj_wait_entry *wait) { if (!wait->node.next) return; spin_lock(&syncobj->lock); list_del_init(&wait->node); spin_unlock(&syncobj->lock); } static void syncobj_eventfd_entry_free(struct syncobj_eventfd_entry *entry) { eventfd_ctx_put(entry->ev_fd_ctx); dma_fence_put(entry->fence); /* This happens either inside the syncobj lock, or after the node has * already been removed from the list. */ list_del(&entry->node); kfree(entry); } static void drm_syncobj_add_eventfd(struct drm_syncobj *syncobj, struct syncobj_eventfd_entry *entry) { spin_lock(&syncobj->lock); list_add_tail(&entry->node, &syncobj->ev_fd_list); syncobj_eventfd_entry_func(syncobj, entry); spin_unlock(&syncobj->lock); } /** * drm_syncobj_add_point - add new timeline point to the syncobj * @syncobj: sync object to add timeline point do * @chain: chain node to use to add the point * @fence: fence to encapsulate in the chain node * @point: sequence number to use for the point * * Add the chain node as new timeline point to the syncobj. */ void drm_syncobj_add_point(struct drm_syncobj *syncobj, struct dma_fence_chain *chain, struct dma_fence *fence, uint64_t point) { struct syncobj_wait_entry *wait_cur, *wait_tmp; struct syncobj_eventfd_entry *ev_fd_cur, *ev_fd_tmp; struct dma_fence *prev; dma_fence_get(fence); spin_lock(&syncobj->lock); prev = drm_syncobj_fence_get(syncobj); /* You are adding an unorder point to timeline, which could cause payload returned from query_ioctl is 0! */ if (prev && prev->seqno >= point) DRM_DEBUG("You are adding an unorder point to timeline!\n"); dma_fence_chain_init(chain, prev, fence, point); rcu_assign_pointer(syncobj->fence, &chain->base); list_for_each_entry_safe(wait_cur, wait_tmp, &syncobj->cb_list, node) syncobj_wait_syncobj_func(syncobj, wait_cur); list_for_each_entry_safe(ev_fd_cur, ev_fd_tmp, &syncobj->ev_fd_list, node) syncobj_eventfd_entry_func(syncobj, ev_fd_cur); spin_unlock(&syncobj->lock); /* Walk the chain once to trigger garbage collection */ dma_fence_chain_for_each(fence, prev); dma_fence_put(prev); } EXPORT_SYMBOL(drm_syncobj_add_point); /** * drm_syncobj_replace_fence - replace fence in a sync object. * @syncobj: Sync object to replace fence in * @fence: fence to install in sync file. * * This replaces the fence on a sync object. */ void drm_syncobj_replace_fence(struct drm_syncobj *syncobj, struct dma_fence *fence) { struct dma_fence *old_fence; struct syncobj_wait_entry *wait_cur, *wait_tmp; struct syncobj_eventfd_entry *ev_fd_cur, *ev_fd_tmp; if (fence) dma_fence_get(fence); spin_lock(&syncobj->lock); old_fence = rcu_dereference_protected(syncobj->fence, lockdep_is_held(&syncobj->lock)); rcu_assign_pointer(syncobj->fence, fence); if (fence != old_fence) { list_for_each_entry_safe(wait_cur, wait_tmp, &syncobj->cb_list, node) syncobj_wait_syncobj_func(syncobj, wait_cur); list_for_each_entry_safe(ev_fd_cur, ev_fd_tmp, &syncobj->ev_fd_list, node) syncobj_eventfd_entry_func(syncobj, ev_fd_cur); } spin_unlock(&syncobj->lock); dma_fence_put(old_fence); } EXPORT_SYMBOL(drm_syncobj_replace_fence); /** * drm_syncobj_assign_null_handle - assign a stub fence to the sync object * @syncobj: sync object to assign the fence on * * Assign a already signaled stub fence to the sync object. */ static int drm_syncobj_assign_null_handle(struct drm_syncobj *syncobj) { struct dma_fence *fence = dma_fence_allocate_private_stub(ktime_get()); if (!fence) return -ENOMEM; drm_syncobj_replace_fence(syncobj, fence); dma_fence_put(fence); return 0; } /* 5s default for wait submission */ #define DRM_SYNCOBJ_WAIT_FOR_SUBMIT_TIMEOUT 5000000000ULL /** * drm_syncobj_find_fence - lookup and reference the fence in a sync object * @file_private: drm file private pointer * @handle: sync object handle to lookup. * @point: timeline point * @flags: DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT or not * @fence: out parameter for the fence * * This is just a convenience function that combines drm_syncobj_find() and * drm_syncobj_fence_get(). * * Returns 0 on success or a negative error value on failure. On success @fence * contains a reference to the fence, which must be released by calling * dma_fence_put(). */ int drm_syncobj_find_fence(struct drm_file *file_private, u32 handle, u64 point, u64 flags, struct dma_fence **fence) { struct drm_syncobj *syncobj = drm_syncobj_find(file_private, handle); struct syncobj_wait_entry wait; u64 timeout = nsecs_to_jiffies64(DRM_SYNCOBJ_WAIT_FOR_SUBMIT_TIMEOUT); int ret; if (flags & ~DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT) return -EINVAL; if (!syncobj) return -ENOENT; /* Waiting for userspace with locks help is illegal cause that can * trivial deadlock with page faults for example. Make lockdep complain * about it early on. */ if (flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT) { might_sleep(); lockdep_assert_none_held_once(); } *fence = drm_syncobj_fence_get(syncobj); if (*fence) { ret = dma_fence_chain_find_seqno(fence, point); if (!ret) { /* If the requested seqno is already signaled * drm_syncobj_find_fence may return a NULL * fence. To make sure the recipient gets * signalled, use a new fence instead. */ if (!*fence) *fence = dma_fence_get_stub(); goto out; } dma_fence_put(*fence); } else { ret = -EINVAL; } if (!(flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT)) goto out; memset(&wait, 0, sizeof(wait)); wait.task = current; wait.point = point; drm_syncobj_fence_add_wait(syncobj, &wait); do { set_current_state(TASK_INTERRUPTIBLE); if (wait.fence) { ret = 0; break; } if (timeout == 0) { ret = -ETIME; break; } if (signal_pending(current)) { ret = -ERESTARTSYS; break; } timeout = schedule_timeout(timeout); } while (1); __set_current_state(TASK_RUNNING); *fence = wait.fence; if (wait.node.next) drm_syncobj_remove_wait(syncobj, &wait); out: drm_syncobj_put(syncobj); return ret; } EXPORT_SYMBOL(drm_syncobj_find_fence); /** * drm_syncobj_free - free a sync object. * @kref: kref to free. * * Only to be called from kref_put in drm_syncobj_put. */ void drm_syncobj_free(struct kref *kref) { struct drm_syncobj *syncobj = container_of(kref, struct drm_syncobj, refcount); struct syncobj_eventfd_entry *ev_fd_cur, *ev_fd_tmp; drm_syncobj_replace_fence(syncobj, NULL); list_for_each_entry_safe(ev_fd_cur, ev_fd_tmp, &syncobj->ev_fd_list, node) syncobj_eventfd_entry_free(ev_fd_cur); kfree(syncobj); } EXPORT_SYMBOL(drm_syncobj_free); /** * drm_syncobj_create - create a new syncobj * @out_syncobj: returned syncobj * @flags: DRM_SYNCOBJ_* flags * @fence: if non-NULL, the syncobj will represent this fence * * This is the first function to create a sync object. After creating, drivers * probably want to make it available to userspace, either through * drm_syncobj_get_handle() or drm_syncobj_get_fd(). * * Returns 0 on success or a negative error value on failure. */ int drm_syncobj_create(struct drm_syncobj **out_syncobj, uint32_t flags, struct dma_fence *fence) { int ret; struct drm_syncobj *syncobj; syncobj = kzalloc(sizeof(struct drm_syncobj), GFP_KERNEL); if (!syncobj) return -ENOMEM; kref_init(&syncobj->refcount); INIT_LIST_HEAD(&syncobj->cb_list); INIT_LIST_HEAD(&syncobj->ev_fd_list); spin_lock_init(&syncobj->lock); if (flags & DRM_SYNCOBJ_CREATE_SIGNALED) { ret = drm_syncobj_assign_null_handle(syncobj); if (ret < 0) { drm_syncobj_put(syncobj); return ret; } } if (fence) drm_syncobj_replace_fence(syncobj, fence); *out_syncobj = syncobj; return 0; } EXPORT_SYMBOL(drm_syncobj_create); /** * drm_syncobj_get_handle - get a handle from a syncobj * @file_private: drm file private pointer * @syncobj: Sync object to export * @handle: out parameter with the new handle * * Exports a sync object created with drm_syncobj_create() as a handle on * @file_private to userspace. * * Returns 0 on success or a negative error value on failure. */ int drm_syncobj_get_handle(struct drm_file *file_private, struct drm_syncobj *syncobj, u32 *handle) { int ret; /* take a reference to put in the idr */ drm_syncobj_get(syncobj); idr_preload(GFP_KERNEL); spin_lock(&file_private->syncobj_table_lock); ret = idr_alloc(&file_private->syncobj_idr, syncobj, 1, 0, GFP_NOWAIT); spin_unlock(&file_private->syncobj_table_lock); idr_preload_end(); if (ret < 0) { drm_syncobj_put(syncobj); return ret; } *handle = ret; return 0; } EXPORT_SYMBOL(drm_syncobj_get_handle); static int drm_syncobj_create_as_handle(struct drm_file *file_private, u32 *handle, uint32_t flags) { int ret; struct drm_syncobj *syncobj; ret = drm_syncobj_create(&syncobj, flags, NULL); if (ret) return ret; ret = drm_syncobj_get_handle(file_private, syncobj, handle); drm_syncobj_put(syncobj); return ret; } static int drm_syncobj_destroy(struct drm_file *file_private, u32 handle) { struct drm_syncobj *syncobj; spin_lock(&file_private->syncobj_table_lock); syncobj = idr_remove(&file_private->syncobj_idr, handle); spin_unlock(&file_private->syncobj_table_lock); if (!syncobj) return -EINVAL; drm_syncobj_put(syncobj); return 0; } static int drm_syncobj_file_release(struct inode *inode, struct file *file) { struct drm_syncobj *syncobj = file->private_data; drm_syncobj_put(syncobj); return 0; } static const struct file_operations drm_syncobj_file_fops = { .release = drm_syncobj_file_release, }; /** * drm_syncobj_get_fd - get a file descriptor from a syncobj * @syncobj: Sync object to export * @p_fd: out parameter with the new file descriptor * * Exports a sync object created with drm_syncobj_create() as a file descriptor. * * Returns 0 on success or a negative error value on failure. */ int drm_syncobj_get_fd(struct drm_syncobj *syncobj, int *p_fd) { struct file *file; int fd; fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) return fd; file = anon_inode_getfile("syncobj_file", &drm_syncobj_file_fops, syncobj, 0); if (IS_ERR(file)) { put_unused_fd(fd); return PTR_ERR(file); } drm_syncobj_get(syncobj); fd_install(fd, file); *p_fd = fd; return 0; } EXPORT_SYMBOL(drm_syncobj_get_fd); static int drm_syncobj_handle_to_fd(struct drm_file *file_private, u32 handle, int *p_fd) { struct drm_syncobj *syncobj = drm_syncobj_find(file_private, handle); int ret; if (!syncobj) return -EINVAL; ret = drm_syncobj_get_fd(syncobj, p_fd); drm_syncobj_put(syncobj); return ret; } static int drm_syncobj_fd_to_handle(struct drm_file *file_private, int fd, u32 *handle) { struct drm_syncobj *syncobj; CLASS(fd, f)(fd); int ret; if (fd_empty(f)) return -EINVAL; if (fd_file(f)->f_op != &drm_syncobj_file_fops) return -EINVAL; /* take a reference to put in the idr */ syncobj = fd_file(f)->private_data; drm_syncobj_get(syncobj); idr_preload(GFP_KERNEL); spin_lock(&file_private->syncobj_table_lock); ret = idr_alloc(&file_private->syncobj_idr, syncobj, 1, 0, GFP_NOWAIT); spin_unlock(&file_private->syncobj_table_lock); idr_preload_end(); if (ret > 0) { *handle = ret; ret = 0; } else drm_syncobj_put(syncobj); return ret; } static int drm_syncobj_import_sync_file_fence(struct drm_file *file_private, int fd, int handle) { struct dma_fence *fence = sync_file_get_fence(fd); struct drm_syncobj *syncobj; if (!fence) return -EINVAL; syncobj = drm_syncobj_find(file_private, handle); if (!syncobj) { dma_fence_put(fence); return -ENOENT; } drm_syncobj_replace_fence(syncobj, fence); dma_fence_put(fence); drm_syncobj_put(syncobj); return 0; } static int drm_syncobj_export_sync_file(struct drm_file *file_private, int handle, int *p_fd) { int ret; struct dma_fence *fence; struct sync_file *sync_file; int fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) return fd; ret = drm_syncobj_find_fence(file_private, handle, 0, 0, &fence); if (ret) goto err_put_fd; sync_file = sync_file_create(fence); dma_fence_put(fence); if (!sync_file) { ret = -EINVAL; goto err_put_fd; } fd_install(fd, sync_file->file); *p_fd = fd; return 0; err_put_fd: put_unused_fd(fd); return ret; } /** * drm_syncobj_open - initializes syncobj file-private structures at devnode open time * @file_private: drm file-private structure to set up * * Called at device open time, sets up the structure for handling refcounting * of sync objects. */ void drm_syncobj_open(struct drm_file *file_private) { idr_init_base(&file_private->syncobj_idr, 1); spin_lock_init(&file_private->syncobj_table_lock); } static int drm_syncobj_release_handle(int id, void *ptr, void *data) { struct drm_syncobj *syncobj = ptr; drm_syncobj_put(syncobj); return 0; } /** * drm_syncobj_release - release file-private sync object resources * @file_private: drm file-private structure to clean up * * Called at close time when the filp is going away. * * Releases any remaining references on objects by this filp. */ void drm_syncobj_release(struct drm_file *file_private) { idr_for_each(&file_private->syncobj_idr, &drm_syncobj_release_handle, file_private); idr_destroy(&file_private->syncobj_idr); } int drm_syncobj_create_ioctl(struct drm_device *dev, void *data, struct drm_file *file_private) { struct drm_syncobj_create *args = data; if (!drm_core_check_feature(dev, DRIVER_SYNCOBJ)) return -EOPNOTSUPP; /* no valid flags yet */ if (args->flags & ~DRM_SYNCOBJ_CREATE_SIGNALED) return -EINVAL; return drm_syncobj_create_as_handle(file_private, &args->handle, args->flags); } int drm_syncobj_destroy_ioctl(struct drm_device *dev, void *data, struct drm_file *file_private) { struct drm_syncobj_destroy *args = data; if (!drm_core_check_feature(dev, DRIVER_SYNCOBJ)) return -EOPNOTSUPP; /* make sure padding is empty */ if (args->pad) return -EINVAL; return drm_syncobj_destroy(file_private, args->handle); } int drm_syncobj_handle_to_fd_ioctl(struct drm_device *dev, void *data, struct drm_file *file_private) { struct drm_syncobj_handle *args = data; if (!drm_core_check_feature(dev, DRIVER_SYNCOBJ)) return -EOPNOTSUPP; if (args->pad) return -EINVAL; if (args->flags != 0 && args->flags != DRM_SYNCOBJ_HANDLE_TO_FD_FLAGS_EXPORT_SYNC_FILE) return -EINVAL; if (args->flags & DRM_SYNCOBJ_HANDLE_TO_FD_FLAGS_EXPORT_SYNC_FILE) return drm_syncobj_export_sync_file(file_private, args->handle, &args->fd); return drm_syncobj_handle_to_fd(file_private, args->handle, &args->fd); } int drm_syncobj_fd_to_handle_ioctl(struct drm_device *dev, void *data, struct drm_file *file_private) { struct drm_syncobj_handle *args = data; if (!drm_core_check_feature(dev, DRIVER_SYNCOBJ)) return -EOPNOTSUPP; if (args->pad) return -EINVAL; if (args->flags != 0 && args->flags != DRM_SYNCOBJ_FD_TO_HANDLE_FLAGS_IMPORT_SYNC_FILE) return -EINVAL; if (args->flags & DRM_SYNCOBJ_FD_TO_HANDLE_FLAGS_IMPORT_SYNC_FILE) return drm_syncobj_import_sync_file_fence(file_private, args->fd, args->handle); return drm_syncobj_fd_to_handle(file_private, args->fd, &args->handle); } static int drm_syncobj_transfer_to_timeline(struct drm_file *file_private, struct drm_syncobj_transfer *args) { struct drm_syncobj *timeline_syncobj = NULL; struct dma_fence *fence, *tmp; struct dma_fence_chain *chain; int ret; timeline_syncobj = drm_syncobj_find(file_private, args->dst_handle); if (!timeline_syncobj) { return -ENOENT; } ret = drm_syncobj_find_fence(file_private, args->src_handle, args->src_point, args->flags, &tmp); if (ret) goto err_put_timeline; fence = dma_fence_unwrap_merge(tmp); dma_fence_put(tmp); if (!fence) { ret = -ENOMEM; goto err_put_timeline; } chain = dma_fence_chain_alloc(); if (!chain) { ret = -ENOMEM; goto err_free_fence; } drm_syncobj_add_point(timeline_syncobj, chain, fence, args->dst_point); err_free_fence: dma_fence_put(fence); err_put_timeline: drm_syncobj_put(timeline_syncobj); return ret; } static int drm_syncobj_transfer_to_binary(struct drm_file *file_private, struct drm_syncobj_transfer *args) { struct drm_syncobj *binary_syncobj = NULL; struct dma_fence *fence; int ret; binary_syncobj = drm_syncobj_find(file_private, args->dst_handle); if (!binary_syncobj) return -ENOENT; ret = drm_syncobj_find_fence(file_private, args->src_handle, args->src_point, args->flags, &fence); if (ret) goto err; drm_syncobj_replace_fence(binary_syncobj, fence); dma_fence_put(fence); err: drm_syncobj_put(binary_syncobj); return ret; } int drm_syncobj_transfer_ioctl(struct drm_device *dev, void *data, struct drm_file *file_private) { struct drm_syncobj_transfer *args = data; int ret; if (!drm_core_check_feature(dev, DRIVER_SYNCOBJ_TIMELINE)) return -EOPNOTSUPP; if (args->pad) return -EINVAL; if (args->dst_point) ret = drm_syncobj_transfer_to_timeline(file_private, args); else ret = drm_syncobj_transfer_to_binary(file_private, args); return ret; } static void syncobj_wait_fence_func(struct dma_fence *fence, struct dma_fence_cb *cb) { struct syncobj_wait_entry *wait = container_of(cb, struct syncobj_wait_entry, fence_cb); wake_up_process(wait->task); } static void syncobj_wait_syncobj_func(struct drm_syncobj *syncobj, struct syncobj_wait_entry *wait) { struct dma_fence *fence; /* This happens inside the syncobj lock */ fence = rcu_dereference_protected(syncobj->fence, lockdep_is_held(&syncobj->lock)); dma_fence_get(fence); if (!fence || dma_fence_chain_find_seqno(&fence, wait->point)) { dma_fence_put(fence); return; } else if (!fence) { wait->fence = dma_fence_get_stub(); } else { wait->fence = fence; } wake_up_process(wait->task); list_del_init(&wait->node); } static signed long drm_syncobj_array_wait_timeout(struct drm_syncobj **syncobjs, void __user *user_points, uint32_t count, uint32_t flags, signed long timeout, uint32_t *idx, ktime_t *deadline) { struct syncobj_wait_entry *entries; struct dma_fence *fence; uint64_t *points; uint32_t signaled_count, i; if (flags & (DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT | DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE)) { might_sleep(); lockdep_assert_none_held_once(); } points = kmalloc_array(count, sizeof(*points), GFP_KERNEL); if (points == NULL) return -ENOMEM; if (!user_points) { memset(points, 0, count * sizeof(uint64_t)); } else if (copy_from_user(points, user_points, sizeof(uint64_t) * count)) { timeout = -EFAULT; goto err_free_points; } entries = kcalloc(count, sizeof(*entries), GFP_KERNEL); if (!entries) { timeout = -ENOMEM; goto err_free_points; } /* Walk the list of sync objects and initialize entries. We do * this up-front so that we can properly return -EINVAL if there is * a syncobj with a missing fence and then never have the chance of * returning -EINVAL again. */ signaled_count = 0; for (i = 0; i < count; ++i) { struct dma_fence *fence; entries[i].task = current; entries[i].point = points[i]; fence = drm_syncobj_fence_get(syncobjs[i]); if (!fence || dma_fence_chain_find_seqno(&fence, points[i])) { dma_fence_put(fence); if (flags & (DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT | DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE)) { continue; } else { timeout = -EINVAL; goto cleanup_entries; } } if (fence) entries[i].fence = fence; else entries[i].fence = dma_fence_get_stub(); if ((flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE) || dma_fence_is_signaled(entries[i].fence)) { if (signaled_count == 0 && idx) *idx = i; signaled_count++; } } if (signaled_count == count || (signaled_count > 0 && !(flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL))) goto cleanup_entries; /* There's a very annoying laxness in the dma_fence API here, in * that backends are not required to automatically report when a * fence is signaled prior to fence->ops->enable_signaling() being * called. So here if we fail to match signaled_count, we need to * fallthough and try a 0 timeout wait! */ if (flags & (DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT | DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE)) { for (i = 0; i < count; ++i) drm_syncobj_fence_add_wait(syncobjs[i], &entries[i]); } if (deadline) { for (i = 0; i < count; ++i) { fence = entries[i].fence; if (!fence) continue; dma_fence_set_deadline(fence, *deadline); } } do { set_current_state(TASK_INTERRUPTIBLE); signaled_count = 0; for (i = 0; i < count; ++i) { fence = entries[i].fence; if (!fence) continue; if ((flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE) || dma_fence_is_signaled(fence) || (!entries[i].fence_cb.func && dma_fence_add_callback(fence, &entries[i].fence_cb, syncobj_wait_fence_func))) { /* The fence has been signaled */ if (flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL) { signaled_count++; } else { if (idx) *idx = i; goto done_waiting; } } } if (signaled_count == count) goto done_waiting; if (timeout == 0) { timeout = -ETIME; goto done_waiting; } if (signal_pending(current)) { timeout = -ERESTARTSYS; goto done_waiting; } timeout = schedule_timeout(timeout); } while (1); done_waiting: __set_current_state(TASK_RUNNING); cleanup_entries: for (i = 0; i < count; ++i) { drm_syncobj_remove_wait(syncobjs[i], &entries[i]); if (entries[i].fence_cb.func) dma_fence_remove_callback(entries[i].fence, &entries[i].fence_cb); dma_fence_put(entries[i].fence); } kfree(entries); err_free_points: kfree(points); return timeout; } /** * drm_timeout_abs_to_jiffies - calculate jiffies timeout from absolute value * * @timeout_nsec: timeout nsec component in ns, 0 for poll * * Calculate the timeout in jiffies from an absolute time in sec/nsec. */ signed long drm_timeout_abs_to_jiffies(int64_t timeout_nsec) { ktime_t abs_timeout, now; u64 timeout_ns, timeout_jiffies64; /* make 0 timeout means poll - absolute 0 doesn't seem valid */ if (timeout_nsec == 0) return 0; abs_timeout = ns_to_ktime(timeout_nsec); now = ktime_get(); if (!ktime_after(abs_timeout, now)) return 0; timeout_ns = ktime_to_ns(ktime_sub(abs_timeout, now)); timeout_jiffies64 = nsecs_to_jiffies64(timeout_ns); /* clamp timeout to avoid infinite timeout */ if (timeout_jiffies64 >= MAX_SCHEDULE_TIMEOUT - 1) return MAX_SCHEDULE_TIMEOUT - 1; return timeout_jiffies64 + 1; } EXPORT_SYMBOL(drm_timeout_abs_to_jiffies); static int drm_syncobj_array_wait(struct drm_device *dev, struct drm_file *file_private, struct drm_syncobj_wait *wait, struct drm_syncobj_timeline_wait *timeline_wait, struct drm_syncobj **syncobjs, bool timeline, ktime_t *deadline) { signed long timeout = 0; uint32_t first = ~0; if (!timeline) { timeout = drm_timeout_abs_to_jiffies(wait->timeout_nsec); timeout = drm_syncobj_array_wait_timeout(syncobjs, NULL, wait->count_handles, wait->flags, timeout, &first, deadline); if (timeout < 0) return timeout; wait->first_signaled = first; } else { timeout = drm_timeout_abs_to_jiffies(timeline_wait->timeout_nsec); timeout = drm_syncobj_array_wait_timeout(syncobjs, u64_to_user_ptr(timeline_wait->points), timeline_wait->count_handles, timeline_wait->flags, timeout, &first, deadline); if (timeout < 0) return timeout; timeline_wait->first_signaled = first; } return 0; } static int drm_syncobj_array_find(struct drm_file *file_private, void __user *user_handles, uint32_t count_handles, struct drm_syncobj ***syncobjs_out) { uint32_t i, *handles; struct drm_syncobj **syncobjs; int ret; handles = kmalloc_array(count_handles, sizeof(*handles), GFP_KERNEL); if (handles == NULL) return -ENOMEM; if (copy_from_user(handles, user_handles, sizeof(uint32_t) * count_handles)) { ret = -EFAULT; goto err_free_handles; } syncobjs = kmalloc_array(count_handles, sizeof(*syncobjs), GFP_KERNEL); if (syncobjs == NULL) { ret = -ENOMEM; goto err_free_handles; } for (i = 0; i < count_handles; i++) { syncobjs[i] = drm_syncobj_find(file_private, handles[i]); if (!syncobjs[i]) { ret = -ENOENT; goto err_put_syncobjs; } } kfree(handles); *syncobjs_out = syncobjs; return 0; err_put_syncobjs: while (i-- > 0) drm_syncobj_put(syncobjs[i]); kfree(syncobjs); err_free_handles: kfree(handles); return ret; } static void drm_syncobj_array_free(struct drm_syncobj **syncobjs, uint32_t count) { uint32_t i; for (i = 0; i < count; i++) drm_syncobj_put(syncobjs[i]); kfree(syncobjs); } int drm_syncobj_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file_private) { struct drm_syncobj_wait *args = data; struct drm_syncobj **syncobjs; unsigned int possible_flags; ktime_t t, *tp = NULL; int ret = 0; if (!drm_core_check_feature(dev, DRIVER_SYNCOBJ)) return -EOPNOTSUPP; possible_flags = DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL | DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT | DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE; if (args->flags & ~possible_flags) return -EINVAL; if (args->count_handles == 0) return 0; ret = drm_syncobj_array_find(file_private, u64_to_user_ptr(args->handles), args->count_handles, &syncobjs); if (ret < 0) return ret; if (args->flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE) { t = ns_to_ktime(args->deadline_nsec); tp = &t; } ret = drm_syncobj_array_wait(dev, file_private, args, NULL, syncobjs, false, tp); drm_syncobj_array_free(syncobjs, args->count_handles); return ret; } int drm_syncobj_timeline_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file_private) { struct drm_syncobj_timeline_wait *args = data; struct drm_syncobj **syncobjs; unsigned int possible_flags; ktime_t t, *tp = NULL; int ret = 0; if (!drm_core_check_feature(dev, DRIVER_SYNCOBJ_TIMELINE)) return -EOPNOTSUPP; possible_flags = DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL | DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT | DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE | DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE; if (args->flags & ~possible_flags) return -EINVAL; if (args->count_handles == 0) return 0; ret = drm_syncobj_array_find(file_private, u64_to_user_ptr(args->handles), args->count_handles, &syncobjs); if (ret < 0) return ret; if (args->flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE) { t = ns_to_ktime(args->deadline_nsec); tp = &t; } ret = drm_syncobj_array_wait(dev, file_private, NULL, args, syncobjs, true, tp); drm_syncobj_array_free(syncobjs, args->count_handles); return ret; } static void syncobj_eventfd_entry_fence_func(struct dma_fence *fence, struct dma_fence_cb *cb) { struct syncobj_eventfd_entry *entry = container_of(cb, struct syncobj_eventfd_entry, fence_cb); eventfd_signal(entry->ev_fd_ctx); syncobj_eventfd_entry_free(entry); } static void syncobj_eventfd_entry_func(struct drm_syncobj *syncobj, struct syncobj_eventfd_entry *entry) { int ret; struct dma_fence *fence; /* This happens inside the syncobj lock */ fence = dma_fence_get(rcu_dereference_protected(syncobj->fence, 1)); if (!fence) return; ret = dma_fence_chain_find_seqno(&fence, entry->point); if (ret != 0) { /* The given seqno has not been submitted yet. */ dma_fence_put(fence); return; } else if (!fence) { /* If dma_fence_chain_find_seqno returns 0 but sets the fence * to NULL, it implies that the given seqno is signaled and a * later seqno has already been submitted. Assign a stub fence * so that the eventfd still gets signaled below. */ fence = dma_fence_get_stub(); } list_del_init(&entry->node); entry->fence = fence; if (entry->flags & DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE) { eventfd_signal(entry->ev_fd_ctx); syncobj_eventfd_entry_free(entry); } else { ret = dma_fence_add_callback(fence, &entry->fence_cb, syncobj_eventfd_entry_fence_func); if (ret == -ENOENT) { eventfd_signal(entry->ev_fd_ctx); syncobj_eventfd_entry_free(entry); } } } int drm_syncobj_eventfd_ioctl(struct drm_device *dev, void *data, struct drm_file *file_private) { struct drm_syncobj_eventfd *args = data; struct drm_syncobj *syncobj; struct eventfd_ctx *ev_fd_ctx; struct syncobj_eventfd_entry *entry; int ret; if (!drm_core_check_feature(dev, DRIVER_SYNCOBJ_TIMELINE)) return -EOPNOTSUPP; if (args->flags & ~DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE) return -EINVAL; if (args->pad) return -EINVAL; syncobj = drm_syncobj_find(file_private, args->handle); if (!syncobj) return -ENOENT; ev_fd_ctx = eventfd_ctx_fdget(args->fd); if (IS_ERR(ev_fd_ctx)) { ret = PTR_ERR(ev_fd_ctx); goto err_fdget; } entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (!entry) { ret = -ENOMEM; goto err_kzalloc; } entry->syncobj = syncobj; entry->ev_fd_ctx = ev_fd_ctx; entry->point = args->point; entry->flags = args->flags; drm_syncobj_add_eventfd(syncobj, entry); drm_syncobj_put(syncobj); return 0; err_kzalloc: eventfd_ctx_put(ev_fd_ctx); err_fdget: drm_syncobj_put(syncobj); return ret; } int drm_syncobj_reset_ioctl(struct drm_device *dev, void *data, struct drm_file *file_private) { struct drm_syncobj_array *args = data; struct drm_syncobj **syncobjs; uint32_t i; int ret; if (!drm_core_check_feature(dev, DRIVER_SYNCOBJ)) return -EOPNOTSUPP; if (args->pad != 0) return -EINVAL; if (args->count_handles == 0) return -EINVAL; ret = drm_syncobj_array_find(file_private, u64_to_user_ptr(args->handles), args->count_handles, &syncobjs); if (ret < 0) return ret; for (i = 0; i < args->count_handles; i++) drm_syncobj_replace_fence(syncobjs[i], NULL); drm_syncobj_array_free(syncobjs, args->count_handles); return 0; } int drm_syncobj_signal_ioctl(struct drm_device *dev, void *data, struct drm_file *file_private) { struct drm_syncobj_array *args = data; struct drm_syncobj **syncobjs; uint32_t i; int ret; if (!drm_core_check_feature(dev, DRIVER_SYNCOBJ)) return -EOPNOTSUPP; if (args->pad != 0) return -EINVAL; if (args->count_handles == 0) return -EINVAL; ret = drm_syncobj_array_find(file_private, u64_to_user_ptr(args->handles), args->count_handles, &syncobjs); if (ret < 0) return ret; for (i = 0; i < args->count_handles; i++) { ret = drm_syncobj_assign_null_handle(syncobjs[i]); if (ret < 0) break; } drm_syncobj_array_free(syncobjs, args->count_handles); return ret; } int drm_syncobj_timeline_signal_ioctl(struct drm_device *dev, void *data, struct drm_file *file_private) { struct drm_syncobj_timeline_array *args = data; struct drm_syncobj **syncobjs; struct dma_fence_chain **chains; uint64_t *points; uint32_t i, j; int ret; if (!drm_core_check_feature(dev, DRIVER_SYNCOBJ_TIMELINE)) return -EOPNOTSUPP; if (args->flags != 0) return -EINVAL; if (args->count_handles == 0) return -EINVAL; ret = drm_syncobj_array_find(file_private, u64_to_user_ptr(args->handles), args->count_handles, &syncobjs); if (ret < 0) return ret; points = kmalloc_array(args->count_handles, sizeof(*points), GFP_KERNEL); if (!points) { ret = -ENOMEM; goto out; } if (!u64_to_user_ptr(args->points)) { memset(points, 0, args->count_handles * sizeof(uint64_t)); } else if (copy_from_user(points, u64_to_user_ptr(args->points), sizeof(uint64_t) * args->count_handles)) { ret = -EFAULT; goto err_points; } chains = kmalloc_array(args->count_handles, sizeof(void *), GFP_KERNEL); if (!chains) { ret = -ENOMEM; goto err_points; } for (i = 0; i < args->count_handles; i++) { chains[i] = dma_fence_chain_alloc(); if (!chains[i]) { for (j = 0; j < i; j++) dma_fence_chain_free(chains[j]); ret = -ENOMEM; goto err_chains; } } for (i = 0; i < args->count_handles; i++) { struct dma_fence *fence = dma_fence_get_stub(); drm_syncobj_add_point(syncobjs[i], chains[i], fence, points[i]); dma_fence_put(fence); } err_chains: kfree(chains); err_points: kfree(points); out: drm_syncobj_array_free(syncobjs, args->count_handles); return ret; } int drm_syncobj_query_ioctl(struct drm_device *dev, void *data, struct drm_file *file_private) { struct drm_syncobj_timeline_array *args = data; struct drm_syncobj **syncobjs; uint64_t __user *points = u64_to_user_ptr(args->points); uint32_t i; int ret; if (!drm_core_check_feature(dev, DRIVER_SYNCOBJ_TIMELINE)) return -EOPNOTSUPP; if (args->flags & ~DRM_SYNCOBJ_QUERY_FLAGS_LAST_SUBMITTED) return -EINVAL; if (args->count_handles == 0) return -EINVAL; ret = drm_syncobj_array_find(file_private, u64_to_user_ptr(args->handles), args->count_handles, &syncobjs); if (ret < 0) return ret; for (i = 0; i < args->count_handles; i++) { struct dma_fence_chain *chain; struct dma_fence *fence; uint64_t point; fence = drm_syncobj_fence_get(syncobjs[i]); chain = to_dma_fence_chain(fence); if (chain) { struct dma_fence *iter, *last_signaled = dma_fence_get(fence); if (args->flags & DRM_SYNCOBJ_QUERY_FLAGS_LAST_SUBMITTED) { point = fence->seqno; } else { dma_fence_chain_for_each(iter, fence) { if (iter->context != fence->context) { dma_fence_put(iter); /* It is most likely that timeline has * unorder points. */ break; } dma_fence_put(last_signaled); last_signaled = dma_fence_get(iter); } point = dma_fence_is_signaled(last_signaled) ? last_signaled->seqno : to_dma_fence_chain(last_signaled)->prev_seqno; } dma_fence_put(last_signaled); } else { point = 0; } dma_fence_put(fence); ret = copy_to_user(&points[i], &point, sizeof(uint64_t)); ret = ret ? -EFAULT : 0; if (ret) break; } drm_syncobj_array_free(syncobjs, args->count_handles); return ret; } |
| 7 1 3 1 1 1 4 20 7 5 1 15 7 13 1 13 8 8 2 1 8 2 1 2 7 1 1 1 62 33 3 3 1 1 32 25 27 23 15 3 2 1 12 2 1 5 8 8 4 4 2 2 2 29 29 1 1 119 63 4 1 1 2 4 2 16 17 2 1 3 1 4 1 3 1 14 1 2 2 1 1 1 8 3 1 2 5 2 5 1 1 24 1 23 2 4 4 1 13 9 34 5 2 19 24 24 1 26 26 26 11 1 1 9 8 2 2 4 1 33 33 33 34 24 24 16 16 16 30 31 32 32 32 32 1 31 32 11 18 6 2 2 18 3 11 2 8 8 29 3 26 32 32 25 1 25 24 24 1 1 1 25 25 2 1 4 3 3 1 1 6 1 2 4 3 1 2 1 16 35 35 35 9 1 8 6 6 31 3 29 29 2 2 14 1 1 1 11 2 9 8 8 3 1 4 2 1 14 14 13 1 1 10 10 2 13 12 1 13 12 1 6 10 10 11 3 3 1 1 1 1 1 2 2 30 29 3 3 3 27 28 28 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Generic PPP layer for Linux. * * Copyright 1999-2002 Paul Mackerras. * * The generic PPP layer handles the PPP network interfaces, the * /dev/ppp device, packet and VJ compression, and multilink. * It talks to PPP `channels' via the interface defined in * include/linux/ppp_channel.h. Channels provide the basic means for * sending and receiving PPP frames on some kind of communications * channel. * * Part of the code in this driver was inspired by the old async-only * PPP driver, written by Michael Callahan and Al Longyear, and * subsequently hacked by Paul Mackerras. * * ==FILEVERSION 20041108== */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/kmod.h> #include <linux/init.h> #include <linux/list.h> #include <linux/idr.h> #include <linux/netdevice.h> #include <linux/poll.h> #include <linux/ppp_defs.h> #include <linux/filter.h> #include <linux/ppp-ioctl.h> #include <linux/ppp_channel.h> #include <linux/ppp-comp.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/if_arp.h> #include <linux/ip.h> #include <linux/tcp.h> #include <linux/spinlock.h> #include <linux/rwsem.h> #include <linux/stddef.h> #include <linux/device.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/unaligned.h> #include <net/slhc_vj.h> #include <linux/atomic.h> #include <linux/refcount.h> #include <linux/nsproxy.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #define PPP_VERSION "2.4.2" /* * Network protocols we support. */ #define NP_IP 0 /* Internet Protocol V4 */ #define NP_IPV6 1 /* Internet Protocol V6 */ #define NP_IPX 2 /* IPX protocol */ #define NP_AT 3 /* Appletalk protocol */ #define NP_MPLS_UC 4 /* MPLS unicast */ #define NP_MPLS_MC 5 /* MPLS multicast */ #define NUM_NP 6 /* Number of NPs. */ #define MPHDRLEN 6 /* multilink protocol header length */ #define MPHDRLEN_SSN 4 /* ditto with short sequence numbers */ #define PPP_PROTO_LEN 2 #define PPP_LCP_HDRLEN 4 /* * An instance of /dev/ppp can be associated with either a ppp * interface unit or a ppp channel. In both cases, file->private_data * points to one of these. */ struct ppp_file { enum { INTERFACE=1, CHANNEL } kind; struct sk_buff_head xq; /* pppd transmit queue */ struct sk_buff_head rq; /* receive queue for pppd */ wait_queue_head_t rwait; /* for poll on reading /dev/ppp */ refcount_t refcnt; /* # refs (incl /dev/ppp attached) */ int hdrlen; /* space to leave for headers */ int index; /* interface unit / channel number */ int dead; /* unit/channel has been shut down */ }; #define PF_TO_X(pf, X) container_of(pf, X, file) #define PF_TO_PPP(pf) PF_TO_X(pf, struct ppp) #define PF_TO_CHANNEL(pf) PF_TO_X(pf, struct channel) /* * Data structure to hold primary network stats for which * we want to use 64 bit storage. Other network stats * are stored in dev->stats of the ppp strucute. */ struct ppp_link_stats { u64 rx_packets; u64 tx_packets; u64 rx_bytes; u64 tx_bytes; }; /* * Data structure describing one ppp unit. * A ppp unit corresponds to a ppp network interface device * and represents a multilink bundle. * It can have 0 or more ppp channels connected to it. */ struct ppp { struct ppp_file file; /* stuff for read/write/poll 0 */ struct file *owner; /* file that owns this unit 48 */ struct list_head channels; /* list of attached channels 4c */ int n_channels; /* how many channels are attached 54 */ spinlock_t rlock; /* lock for receive side 58 */ spinlock_t wlock; /* lock for transmit side 5c */ int __percpu *xmit_recursion; /* xmit recursion detect */ int mru; /* max receive unit 60 */ unsigned int flags; /* control bits 64 */ unsigned int xstate; /* transmit state bits 68 */ unsigned int rstate; /* receive state bits 6c */ int debug; /* debug flags 70 */ struct slcompress *vj; /* state for VJ header compression */ enum NPmode npmode[NUM_NP]; /* what to do with each net proto 78 */ struct sk_buff *xmit_pending; /* a packet ready to go out 88 */ struct compressor *xcomp; /* transmit packet compressor 8c */ void *xc_state; /* its internal state 90 */ struct compressor *rcomp; /* receive decompressor 94 */ void *rc_state; /* its internal state 98 */ unsigned long last_xmit; /* jiffies when last pkt sent 9c */ unsigned long last_recv; /* jiffies when last pkt rcvd a0 */ struct net_device *dev; /* network interface device a4 */ int closing; /* is device closing down? a8 */ #ifdef CONFIG_PPP_MULTILINK int nxchan; /* next channel to send something on */ u32 nxseq; /* next sequence number to send */ int mrru; /* MP: max reconst. receive unit */ u32 nextseq; /* MP: seq no of next packet */ u32 minseq; /* MP: min of most recent seqnos */ struct sk_buff_head mrq; /* MP: receive reconstruction queue */ #endif /* CONFIG_PPP_MULTILINK */ #ifdef CONFIG_PPP_FILTER struct bpf_prog *pass_filter; /* filter for packets to pass */ struct bpf_prog *active_filter; /* filter for pkts to reset idle */ #endif /* CONFIG_PPP_FILTER */ struct net *ppp_net; /* the net we belong to */ struct ppp_link_stats stats64; /* 64 bit network stats */ }; /* * Bits in flags: SC_NO_TCP_CCID, SC_CCP_OPEN, SC_CCP_UP, SC_LOOP_TRAFFIC, * SC_MULTILINK, SC_MP_SHORTSEQ, SC_MP_XSHORTSEQ, SC_COMP_TCP, SC_REJ_COMP_TCP, * SC_MUST_COMP * Bits in rstate: SC_DECOMP_RUN, SC_DC_ERROR, SC_DC_FERROR. * Bits in xstate: SC_COMP_RUN */ #define SC_FLAG_BITS (SC_NO_TCP_CCID|SC_CCP_OPEN|SC_CCP_UP|SC_LOOP_TRAFFIC \ |SC_MULTILINK|SC_MP_SHORTSEQ|SC_MP_XSHORTSEQ \ |SC_COMP_TCP|SC_REJ_COMP_TCP|SC_MUST_COMP) /* * Private data structure for each channel. * This includes the data structure used for multilink. */ struct channel { struct ppp_file file; /* stuff for read/write/poll */ struct list_head list; /* link in all/new_channels list */ struct ppp_channel *chan; /* public channel data structure */ struct rw_semaphore chan_sem; /* protects `chan' during chan ioctl */ spinlock_t downl; /* protects `chan', file.xq dequeue */ struct ppp *ppp; /* ppp unit we're connected to */ struct net *chan_net; /* the net channel belongs to */ netns_tracker ns_tracker; struct list_head clist; /* link in list of channels per unit */ rwlock_t upl; /* protects `ppp' and 'bridge' */ struct channel __rcu *bridge; /* "bridged" ppp channel */ #ifdef CONFIG_PPP_MULTILINK u8 avail; /* flag used in multilink stuff */ u8 had_frag; /* >= 1 fragments have been sent */ u32 lastseq; /* MP: last sequence # received */ int speed; /* speed of the corresponding ppp channel*/ #endif /* CONFIG_PPP_MULTILINK */ }; struct ppp_config { struct file *file; s32 unit; bool ifname_is_set; }; /* * SMP locking issues: * Both the ppp.rlock and ppp.wlock locks protect the ppp.channels * list and the ppp.n_channels field, you need to take both locks * before you modify them. * The lock ordering is: channel.upl -> ppp.wlock -> ppp.rlock -> * channel.downl. */ static DEFINE_MUTEX(ppp_mutex); static atomic_t ppp_unit_count = ATOMIC_INIT(0); static atomic_t channel_count = ATOMIC_INIT(0); /* per-net private data for this module */ static unsigned int ppp_net_id __read_mostly; struct ppp_net { /* units to ppp mapping */ struct idr units_idr; /* * all_ppp_mutex protects the units_idr mapping. * It also ensures that finding a ppp unit in the units_idr * map and updating its file.refcnt field is atomic. */ struct mutex all_ppp_mutex; /* channels */ struct list_head all_channels; struct list_head new_channels; int last_channel_index; /* * all_channels_lock protects all_channels and * last_channel_index, and the atomicity of find * a channel and updating its file.refcnt field. */ spinlock_t all_channels_lock; }; /* Get the PPP protocol number from a skb */ #define PPP_PROTO(skb) get_unaligned_be16((skb)->data) /* We limit the length of ppp->file.rq to this (arbitrary) value */ #define PPP_MAX_RQLEN 32 /* * Maximum number of multilink fragments queued up. * This has to be large enough to cope with the maximum latency of * the slowest channel relative to the others. Strictly it should * depend on the number of channels and their characteristics. */ #define PPP_MP_MAX_QLEN 128 /* Multilink header bits. */ #define B 0x80 /* this fragment begins a packet */ #define E 0x40 /* this fragment ends a packet */ /* Compare multilink sequence numbers (assumed to be 32 bits wide) */ #define seq_before(a, b) ((s32)((a) - (b)) < 0) #define seq_after(a, b) ((s32)((a) - (b)) > 0) /* Prototypes. */ static int ppp_unattached_ioctl(struct net *net, struct ppp_file *pf, struct file *file, unsigned int cmd, unsigned long arg); static void ppp_xmit_process(struct ppp *ppp, struct sk_buff *skb); static void ppp_send_frame(struct ppp *ppp, struct sk_buff *skb); static void ppp_push(struct ppp *ppp); static void ppp_channel_push(struct channel *pch); static void ppp_receive_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch); static void ppp_receive_error(struct ppp *ppp); static void ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb); static struct sk_buff *ppp_decompress_frame(struct ppp *ppp, struct sk_buff *skb); #ifdef CONFIG_PPP_MULTILINK static void ppp_receive_mp_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch); static void ppp_mp_insert(struct ppp *ppp, struct sk_buff *skb); static struct sk_buff *ppp_mp_reconstruct(struct ppp *ppp); static int ppp_mp_explode(struct ppp *ppp, struct sk_buff *skb); #endif /* CONFIG_PPP_MULTILINK */ static int ppp_set_compress(struct ppp *ppp, struct ppp_option_data *data); static void ppp_ccp_peek(struct ppp *ppp, struct sk_buff *skb, int inbound); static void ppp_ccp_closed(struct ppp *ppp); static struct compressor *find_compressor(int type); static void ppp_get_stats(struct ppp *ppp, struct ppp_stats *st); static int ppp_create_interface(struct net *net, struct file *file, int *unit); static void init_ppp_file(struct ppp_file *pf, int kind); static void ppp_destroy_interface(struct ppp *ppp); static struct ppp *ppp_find_unit(struct ppp_net *pn, int unit); static struct channel *ppp_find_channel(struct ppp_net *pn, int unit); static int ppp_connect_channel(struct channel *pch, int unit); static int ppp_disconnect_channel(struct channel *pch); static void ppp_destroy_channel(struct channel *pch); static int unit_get(struct idr *p, void *ptr, int min); static int unit_set(struct idr *p, void *ptr, int n); static void unit_put(struct idr *p, int n); static void *unit_find(struct idr *p, int n); static void ppp_setup(struct net_device *dev); static const struct net_device_ops ppp_netdev_ops; static const struct class ppp_class = { .name = "ppp", }; /* per net-namespace data */ static inline struct ppp_net *ppp_pernet(struct net *net) { return net_generic(net, ppp_net_id); } /* Translates a PPP protocol number to a NP index (NP == network protocol) */ static inline int proto_to_npindex(int proto) { switch (proto) { case PPP_IP: return NP_IP; case PPP_IPV6: return NP_IPV6; case PPP_IPX: return NP_IPX; case PPP_AT: return NP_AT; case PPP_MPLS_UC: return NP_MPLS_UC; case PPP_MPLS_MC: return NP_MPLS_MC; } return -EINVAL; } /* Translates an NP index into a PPP protocol number */ static const int npindex_to_proto[NUM_NP] = { PPP_IP, PPP_IPV6, PPP_IPX, PPP_AT, PPP_MPLS_UC, PPP_MPLS_MC, }; /* Translates an ethertype into an NP index */ static inline int ethertype_to_npindex(int ethertype) { switch (ethertype) { case ETH_P_IP: return NP_IP; case ETH_P_IPV6: return NP_IPV6; case ETH_P_IPX: return NP_IPX; case ETH_P_PPPTALK: case ETH_P_ATALK: return NP_AT; case ETH_P_MPLS_UC: return NP_MPLS_UC; case ETH_P_MPLS_MC: return NP_MPLS_MC; } return -1; } /* Translates an NP index into an ethertype */ static const int npindex_to_ethertype[NUM_NP] = { ETH_P_IP, ETH_P_IPV6, ETH_P_IPX, ETH_P_PPPTALK, ETH_P_MPLS_UC, ETH_P_MPLS_MC, }; /* * Locking shorthand. */ #define ppp_xmit_lock(ppp) spin_lock_bh(&(ppp)->wlock) #define ppp_xmit_unlock(ppp) spin_unlock_bh(&(ppp)->wlock) #define ppp_recv_lock(ppp) spin_lock_bh(&(ppp)->rlock) #define ppp_recv_unlock(ppp) spin_unlock_bh(&(ppp)->rlock) #define ppp_lock(ppp) do { ppp_xmit_lock(ppp); \ ppp_recv_lock(ppp); } while (0) #define ppp_unlock(ppp) do { ppp_recv_unlock(ppp); \ ppp_xmit_unlock(ppp); } while (0) /* * /dev/ppp device routines. * The /dev/ppp device is used by pppd to control the ppp unit. * It supports the read, write, ioctl and poll functions. * Open instances of /dev/ppp can be in one of three states: * unattached, attached to a ppp unit, or attached to a ppp channel. */ static int ppp_open(struct inode *inode, struct file *file) { /* * This could (should?) be enforced by the permissions on /dev/ppp. */ if (!ns_capable(file->f_cred->user_ns, CAP_NET_ADMIN)) return -EPERM; return 0; } static int ppp_release(struct inode *unused, struct file *file) { struct ppp_file *pf = file->private_data; struct ppp *ppp; if (pf) { file->private_data = NULL; if (pf->kind == INTERFACE) { ppp = PF_TO_PPP(pf); rtnl_lock(); if (file == ppp->owner) unregister_netdevice(ppp->dev); rtnl_unlock(); } if (refcount_dec_and_test(&pf->refcnt)) { switch (pf->kind) { case INTERFACE: ppp_destroy_interface(PF_TO_PPP(pf)); break; case CHANNEL: ppp_destroy_channel(PF_TO_CHANNEL(pf)); break; } } } return 0; } static ssize_t ppp_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct ppp_file *pf = file->private_data; DECLARE_WAITQUEUE(wait, current); ssize_t ret; struct sk_buff *skb = NULL; struct iovec iov; struct iov_iter to; ret = count; if (!pf) return -ENXIO; add_wait_queue(&pf->rwait, &wait); for (;;) { set_current_state(TASK_INTERRUPTIBLE); skb = skb_dequeue(&pf->rq); if (skb) break; ret = 0; if (pf->dead) break; if (pf->kind == INTERFACE) { /* * Return 0 (EOF) on an interface that has no * channels connected, unless it is looping * network traffic (demand mode). */ struct ppp *ppp = PF_TO_PPP(pf); ppp_recv_lock(ppp); if (ppp->n_channels == 0 && (ppp->flags & SC_LOOP_TRAFFIC) == 0) { ppp_recv_unlock(ppp); break; } ppp_recv_unlock(ppp); } ret = -EAGAIN; if (file->f_flags & O_NONBLOCK) break; ret = -ERESTARTSYS; if (signal_pending(current)) break; schedule(); } set_current_state(TASK_RUNNING); remove_wait_queue(&pf->rwait, &wait); if (!skb) goto out; ret = -EOVERFLOW; if (skb->len > count) goto outf; ret = -EFAULT; iov.iov_base = buf; iov.iov_len = count; iov_iter_init(&to, ITER_DEST, &iov, 1, count); if (skb_copy_datagram_iter(skb, 0, &to, skb->len)) goto outf; ret = skb->len; outf: kfree_skb(skb); out: return ret; } static bool ppp_check_packet(struct sk_buff *skb, size_t count) { /* LCP packets must include LCP header which 4 bytes long: * 1-byte code, 1-byte identifier, and 2-byte length. */ return get_unaligned_be16(skb->data) != PPP_LCP || count >= PPP_PROTO_LEN + PPP_LCP_HDRLEN; } static ssize_t ppp_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct ppp_file *pf = file->private_data; struct sk_buff *skb; ssize_t ret; if (!pf) return -ENXIO; /* All PPP packets should start with the 2-byte protocol */ if (count < PPP_PROTO_LEN) return -EINVAL; ret = -ENOMEM; skb = alloc_skb(count + pf->hdrlen, GFP_KERNEL); if (!skb) goto out; skb_reserve(skb, pf->hdrlen); ret = -EFAULT; if (copy_from_user(skb_put(skb, count), buf, count)) { kfree_skb(skb); goto out; } ret = -EINVAL; if (unlikely(!ppp_check_packet(skb, count))) { kfree_skb(skb); goto out; } switch (pf->kind) { case INTERFACE: ppp_xmit_process(PF_TO_PPP(pf), skb); break; case CHANNEL: skb_queue_tail(&pf->xq, skb); ppp_channel_push(PF_TO_CHANNEL(pf)); break; } ret = count; out: return ret; } /* No kernel lock - fine */ static __poll_t ppp_poll(struct file *file, poll_table *wait) { struct ppp_file *pf = file->private_data; __poll_t mask; if (!pf) return 0; poll_wait(file, &pf->rwait, wait); mask = EPOLLOUT | EPOLLWRNORM; if (skb_peek(&pf->rq)) mask |= EPOLLIN | EPOLLRDNORM; if (pf->dead) mask |= EPOLLHUP; else if (pf->kind == INTERFACE) { /* see comment in ppp_read */ struct ppp *ppp = PF_TO_PPP(pf); ppp_recv_lock(ppp); if (ppp->n_channels == 0 && (ppp->flags & SC_LOOP_TRAFFIC) == 0) mask |= EPOLLIN | EPOLLRDNORM; ppp_recv_unlock(ppp); } return mask; } #ifdef CONFIG_PPP_FILTER static struct bpf_prog *get_filter(struct sock_fprog *uprog) { struct sock_fprog_kern fprog; struct bpf_prog *res = NULL; int err; if (!uprog->len) return NULL; /* uprog->len is unsigned short, so no overflow here */ fprog.len = uprog->len; fprog.filter = memdup_array_user(uprog->filter, uprog->len, sizeof(struct sock_filter)); if (IS_ERR(fprog.filter)) return ERR_CAST(fprog.filter); err = bpf_prog_create(&res, &fprog); kfree(fprog.filter); return err ? ERR_PTR(err) : res; } static struct bpf_prog *ppp_get_filter(struct sock_fprog __user *p) { struct sock_fprog uprog; if (copy_from_user(&uprog, p, sizeof(struct sock_fprog))) return ERR_PTR(-EFAULT); return get_filter(&uprog); } #ifdef CONFIG_COMPAT struct sock_fprog32 { unsigned short len; compat_caddr_t filter; }; #define PPPIOCSPASS32 _IOW('t', 71, struct sock_fprog32) #define PPPIOCSACTIVE32 _IOW('t', 70, struct sock_fprog32) static struct bpf_prog *compat_ppp_get_filter(struct sock_fprog32 __user *p) { struct sock_fprog32 uprog32; struct sock_fprog uprog; if (copy_from_user(&uprog32, p, sizeof(struct sock_fprog32))) return ERR_PTR(-EFAULT); uprog.len = uprog32.len; uprog.filter = compat_ptr(uprog32.filter); return get_filter(&uprog); } #endif #endif /* Bridge one PPP channel to another. * When two channels are bridged, ppp_input on one channel is redirected to * the other's ops->start_xmit handler. * In order to safely bridge channels we must reject channels which are already * part of a bridge instance, or which form part of an existing unit. * Once successfully bridged, each channel holds a reference on the other * to prevent it being freed while the bridge is extant. */ static int ppp_bridge_channels(struct channel *pch, struct channel *pchb) { write_lock_bh(&pch->upl); if (pch->ppp || rcu_dereference_protected(pch->bridge, lockdep_is_held(&pch->upl))) { write_unlock_bh(&pch->upl); return -EALREADY; } refcount_inc(&pchb->file.refcnt); rcu_assign_pointer(pch->bridge, pchb); write_unlock_bh(&pch->upl); write_lock_bh(&pchb->upl); if (pchb->ppp || rcu_dereference_protected(pchb->bridge, lockdep_is_held(&pchb->upl))) { write_unlock_bh(&pchb->upl); goto err_unset; } refcount_inc(&pch->file.refcnt); rcu_assign_pointer(pchb->bridge, pch); write_unlock_bh(&pchb->upl); return 0; err_unset: write_lock_bh(&pch->upl); /* Re-read pch->bridge with upl held in case it was modified concurrently */ pchb = rcu_dereference_protected(pch->bridge, lockdep_is_held(&pch->upl)); RCU_INIT_POINTER(pch->bridge, NULL); write_unlock_bh(&pch->upl); synchronize_rcu(); if (pchb) if (refcount_dec_and_test(&pchb->file.refcnt)) ppp_destroy_channel(pchb); return -EALREADY; } static int ppp_unbridge_channels(struct channel *pch) { struct channel *pchb, *pchbb; write_lock_bh(&pch->upl); pchb = rcu_dereference_protected(pch->bridge, lockdep_is_held(&pch->upl)); if (!pchb) { write_unlock_bh(&pch->upl); return -EINVAL; } RCU_INIT_POINTER(pch->bridge, NULL); write_unlock_bh(&pch->upl); /* Only modify pchb if phcb->bridge points back to pch. * If not, it implies that there has been a race unbridging (and possibly * even rebridging) pchb. We should leave pchb alone to avoid either a * refcount underflow, or breaking another established bridge instance. */ write_lock_bh(&pchb->upl); pchbb = rcu_dereference_protected(pchb->bridge, lockdep_is_held(&pchb->upl)); if (pchbb == pch) RCU_INIT_POINTER(pchb->bridge, NULL); write_unlock_bh(&pchb->upl); synchronize_rcu(); if (pchbb == pch) if (refcount_dec_and_test(&pch->file.refcnt)) ppp_destroy_channel(pch); if (refcount_dec_and_test(&pchb->file.refcnt)) ppp_destroy_channel(pchb); return 0; } static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct ppp_file *pf; struct ppp *ppp; int err = -EFAULT, val, val2, i; struct ppp_idle32 idle32; struct ppp_idle64 idle64; struct npioctl npi; int unit, cflags; struct slcompress *vj; void __user *argp = (void __user *)arg; int __user *p = argp; mutex_lock(&ppp_mutex); pf = file->private_data; if (!pf) { err = ppp_unattached_ioctl(current->nsproxy->net_ns, pf, file, cmd, arg); goto out; } if (cmd == PPPIOCDETACH) { /* * PPPIOCDETACH is no longer supported as it was heavily broken, * and is only known to have been used by pppd older than * ppp-2.4.2 (released November 2003). */ pr_warn_once("%s (%d) used obsolete PPPIOCDETACH ioctl\n", current->comm, current->pid); err = -EINVAL; goto out; } if (pf->kind == CHANNEL) { struct channel *pch, *pchb; struct ppp_channel *chan; struct ppp_net *pn; pch = PF_TO_CHANNEL(pf); switch (cmd) { case PPPIOCCONNECT: if (get_user(unit, p)) break; err = ppp_connect_channel(pch, unit); break; case PPPIOCDISCONN: err = ppp_disconnect_channel(pch); break; case PPPIOCBRIDGECHAN: if (get_user(unit, p)) break; err = -ENXIO; pn = ppp_pernet(current->nsproxy->net_ns); spin_lock_bh(&pn->all_channels_lock); pchb = ppp_find_channel(pn, unit); /* Hold a reference to prevent pchb being freed while * we establish the bridge. */ if (pchb) refcount_inc(&pchb->file.refcnt); spin_unlock_bh(&pn->all_channels_lock); if (!pchb) break; err = ppp_bridge_channels(pch, pchb); /* Drop earlier refcount now bridge establishment is complete */ if (refcount_dec_and_test(&pchb->file.refcnt)) ppp_destroy_channel(pchb); break; case PPPIOCUNBRIDGECHAN: err = ppp_unbridge_channels(pch); break; default: down_read(&pch->chan_sem); chan = pch->chan; err = -ENOTTY; if (chan && chan->ops->ioctl) err = chan->ops->ioctl(chan, cmd, arg); up_read(&pch->chan_sem); } goto out; } if (pf->kind != INTERFACE) { /* can't happen */ pr_err("PPP: not interface or channel??\n"); err = -EINVAL; goto out; } ppp = PF_TO_PPP(pf); switch (cmd) { case PPPIOCSMRU: if (get_user(val, p)) break; ppp->mru = val; err = 0; break; case PPPIOCSFLAGS: if (get_user(val, p)) break; ppp_lock(ppp); cflags = ppp->flags & ~val; #ifdef CONFIG_PPP_MULTILINK if (!(ppp->flags & SC_MULTILINK) && (val & SC_MULTILINK)) ppp->nextseq = 0; #endif ppp->flags = val & SC_FLAG_BITS; ppp_unlock(ppp); if (cflags & SC_CCP_OPEN) ppp_ccp_closed(ppp); err = 0; break; case PPPIOCGFLAGS: val = ppp->flags | ppp->xstate | ppp->rstate; if (put_user(val, p)) break; err = 0; break; case PPPIOCSCOMPRESS: { struct ppp_option_data data; if (copy_from_user(&data, argp, sizeof(data))) err = -EFAULT; else err = ppp_set_compress(ppp, &data); break; } case PPPIOCGUNIT: if (put_user(ppp->file.index, p)) break; err = 0; break; case PPPIOCSDEBUG: if (get_user(val, p)) break; ppp->debug = val; err = 0; break; case PPPIOCGDEBUG: if (put_user(ppp->debug, p)) break; err = 0; break; case PPPIOCGIDLE32: idle32.xmit_idle = (jiffies - ppp->last_xmit) / HZ; idle32.recv_idle = (jiffies - ppp->last_recv) / HZ; if (copy_to_user(argp, &idle32, sizeof(idle32))) break; err = 0; break; case PPPIOCGIDLE64: idle64.xmit_idle = (jiffies - ppp->last_xmit) / HZ; idle64.recv_idle = (jiffies - ppp->last_recv) / HZ; if (copy_to_user(argp, &idle64, sizeof(idle64))) break; err = 0; break; case PPPIOCSMAXCID: if (get_user(val, p)) break; val2 = 15; if ((val >> 16) != 0) { val2 = val >> 16; val &= 0xffff; } vj = slhc_init(val2+1, val+1); if (IS_ERR(vj)) { err = PTR_ERR(vj); break; } ppp_lock(ppp); if (ppp->vj) slhc_free(ppp->vj); ppp->vj = vj; ppp_unlock(ppp); err = 0; break; case PPPIOCGNPMODE: case PPPIOCSNPMODE: if (copy_from_user(&npi, argp, sizeof(npi))) break; err = proto_to_npindex(npi.protocol); if (err < 0) break; i = err; if (cmd == PPPIOCGNPMODE) { err = -EFAULT; npi.mode = ppp->npmode[i]; if (copy_to_user(argp, &npi, sizeof(npi))) break; } else { ppp->npmode[i] = npi.mode; /* we may be able to transmit more packets now (??) */ netif_wake_queue(ppp->dev); } err = 0; break; #ifdef CONFIG_PPP_FILTER case PPPIOCSPASS: case PPPIOCSACTIVE: { struct bpf_prog *filter = ppp_get_filter(argp); struct bpf_prog **which; if (IS_ERR(filter)) { err = PTR_ERR(filter); break; } if (cmd == PPPIOCSPASS) which = &ppp->pass_filter; else which = &ppp->active_filter; ppp_lock(ppp); if (*which) bpf_prog_destroy(*which); *which = filter; ppp_unlock(ppp); err = 0; break; } #endif /* CONFIG_PPP_FILTER */ #ifdef CONFIG_PPP_MULTILINK case PPPIOCSMRRU: if (get_user(val, p)) break; ppp_recv_lock(ppp); ppp->mrru = val; ppp_recv_unlock(ppp); err = 0; break; #endif /* CONFIG_PPP_MULTILINK */ default: err = -ENOTTY; } out: mutex_unlock(&ppp_mutex); return err; } #ifdef CONFIG_COMPAT struct ppp_option_data32 { compat_uptr_t ptr; u32 length; compat_int_t transmit; }; #define PPPIOCSCOMPRESS32 _IOW('t', 77, struct ppp_option_data32) static long ppp_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct ppp_file *pf; int err = -ENOIOCTLCMD; void __user *argp = (void __user *)arg; mutex_lock(&ppp_mutex); pf = file->private_data; if (pf && pf->kind == INTERFACE) { struct ppp *ppp = PF_TO_PPP(pf); switch (cmd) { #ifdef CONFIG_PPP_FILTER case PPPIOCSPASS32: case PPPIOCSACTIVE32: { struct bpf_prog *filter = compat_ppp_get_filter(argp); struct bpf_prog **which; if (IS_ERR(filter)) { err = PTR_ERR(filter); break; } if (cmd == PPPIOCSPASS32) which = &ppp->pass_filter; else which = &ppp->active_filter; ppp_lock(ppp); if (*which) bpf_prog_destroy(*which); *which = filter; ppp_unlock(ppp); err = 0; break; } #endif /* CONFIG_PPP_FILTER */ case PPPIOCSCOMPRESS32: { struct ppp_option_data32 data32; if (copy_from_user(&data32, argp, sizeof(data32))) { err = -EFAULT; } else { struct ppp_option_data data = { .ptr = compat_ptr(data32.ptr), .length = data32.length, .transmit = data32.transmit }; err = ppp_set_compress(ppp, &data); } break; } } } mutex_unlock(&ppp_mutex); /* all other commands have compatible arguments */ if (err == -ENOIOCTLCMD) err = ppp_ioctl(file, cmd, (unsigned long)compat_ptr(arg)); return err; } #endif static int ppp_unattached_ioctl(struct net *net, struct ppp_file *pf, struct file *file, unsigned int cmd, unsigned long arg) { int unit, err = -EFAULT; struct ppp *ppp; struct channel *chan; struct ppp_net *pn; int __user *p = (int __user *)arg; switch (cmd) { case PPPIOCNEWUNIT: /* Create a new ppp unit */ if (get_user(unit, p)) break; err = ppp_create_interface(net, file, &unit); if (err < 0) break; err = -EFAULT; if (put_user(unit, p)) break; err = 0; break; case PPPIOCATTACH: /* Attach to an existing ppp unit */ if (get_user(unit, p)) break; err = -ENXIO; pn = ppp_pernet(net); mutex_lock(&pn->all_ppp_mutex); ppp = ppp_find_unit(pn, unit); if (ppp) { refcount_inc(&ppp->file.refcnt); file->private_data = &ppp->file; err = 0; } mutex_unlock(&pn->all_ppp_mutex); break; case PPPIOCATTCHAN: if (get_user(unit, p)) break; err = -ENXIO; pn = ppp_pernet(net); spin_lock_bh(&pn->all_channels_lock); chan = ppp_find_channel(pn, unit); if (chan) { refcount_inc(&chan->file.refcnt); file->private_data = &chan->file; err = 0; } spin_unlock_bh(&pn->all_channels_lock); break; default: err = -ENOTTY; } return err; } static const struct file_operations ppp_device_fops = { .owner = THIS_MODULE, .read = ppp_read, .write = ppp_write, .poll = ppp_poll, .unlocked_ioctl = ppp_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = ppp_compat_ioctl, #endif .open = ppp_open, .release = ppp_release, .llseek = noop_llseek, }; static __net_init int ppp_init_net(struct net *net) { struct ppp_net *pn = net_generic(net, ppp_net_id); idr_init(&pn->units_idr); mutex_init(&pn->all_ppp_mutex); INIT_LIST_HEAD(&pn->all_channels); INIT_LIST_HEAD(&pn->new_channels); spin_lock_init(&pn->all_channels_lock); return 0; } static __net_exit void ppp_exit_net(struct net *net) { struct ppp_net *pn = net_generic(net, ppp_net_id); struct net_device *dev; struct net_device *aux; struct ppp *ppp; LIST_HEAD(list); int id; rtnl_lock(); for_each_netdev_safe(net, dev, aux) { if (dev->netdev_ops == &ppp_netdev_ops) unregister_netdevice_queue(dev, &list); } idr_for_each_entry(&pn->units_idr, ppp, id) /* Skip devices already unregistered by previous loop */ if (!net_eq(dev_net(ppp->dev), net)) unregister_netdevice_queue(ppp->dev, &list); unregister_netdevice_many(&list); rtnl_unlock(); mutex_destroy(&pn->all_ppp_mutex); idr_destroy(&pn->units_idr); WARN_ON_ONCE(!list_empty(&pn->all_channels)); WARN_ON_ONCE(!list_empty(&pn->new_channels)); } static struct pernet_operations ppp_net_ops = { .init = ppp_init_net, .exit = ppp_exit_net, .id = &ppp_net_id, .size = sizeof(struct ppp_net), }; static int ppp_unit_register(struct ppp *ppp, int unit, bool ifname_is_set) { struct ppp_net *pn = ppp_pernet(ppp->ppp_net); int ret; mutex_lock(&pn->all_ppp_mutex); if (unit < 0) { ret = unit_get(&pn->units_idr, ppp, 0); if (ret < 0) goto err; if (!ifname_is_set) { while (1) { snprintf(ppp->dev->name, IFNAMSIZ, "ppp%i", ret); if (!netdev_name_in_use(ppp->ppp_net, ppp->dev->name)) break; unit_put(&pn->units_idr, ret); ret = unit_get(&pn->units_idr, ppp, ret + 1); if (ret < 0) goto err; } } } else { /* Caller asked for a specific unit number. Fail with -EEXIST * if unavailable. For backward compatibility, return -EEXIST * too if idr allocation fails; this makes pppd retry without * requesting a specific unit number. */ if (unit_find(&pn->units_idr, unit)) { ret = -EEXIST; goto err; } ret = unit_set(&pn->units_idr, ppp, unit); if (ret < 0) { /* Rewrite error for backward compatibility */ ret = -EEXIST; goto err; } } ppp->file.index = ret; if (!ifname_is_set) snprintf(ppp->dev->name, IFNAMSIZ, "ppp%i", ppp->file.index); mutex_unlock(&pn->all_ppp_mutex); ret = register_netdevice(ppp->dev); if (ret < 0) goto err_unit; atomic_inc(&ppp_unit_count); return 0; err_unit: mutex_lock(&pn->all_ppp_mutex); unit_put(&pn->units_idr, ppp->file.index); err: mutex_unlock(&pn->all_ppp_mutex); return ret; } static int ppp_dev_configure(struct net *src_net, struct net_device *dev, const struct ppp_config *conf) { struct ppp *ppp = netdev_priv(dev); int indx; int err; int cpu; ppp->dev = dev; ppp->ppp_net = src_net; ppp->mru = PPP_MRU; ppp->owner = conf->file; init_ppp_file(&ppp->file, INTERFACE); ppp->file.hdrlen = PPP_HDRLEN - 2; /* don't count proto bytes */ for (indx = 0; indx < NUM_NP; ++indx) ppp->npmode[indx] = NPMODE_PASS; INIT_LIST_HEAD(&ppp->channels); spin_lock_init(&ppp->rlock); spin_lock_init(&ppp->wlock); ppp->xmit_recursion = alloc_percpu(int); if (!ppp->xmit_recursion) { err = -ENOMEM; goto err1; } for_each_possible_cpu(cpu) (*per_cpu_ptr(ppp->xmit_recursion, cpu)) = 0; #ifdef CONFIG_PPP_MULTILINK ppp->minseq = -1; skb_queue_head_init(&ppp->mrq); #endif /* CONFIG_PPP_MULTILINK */ #ifdef CONFIG_PPP_FILTER ppp->pass_filter = NULL; ppp->active_filter = NULL; #endif /* CONFIG_PPP_FILTER */ err = ppp_unit_register(ppp, conf->unit, conf->ifname_is_set); if (err < 0) goto err2; conf->file->private_data = &ppp->file; return 0; err2: free_percpu(ppp->xmit_recursion); err1: return err; } static const struct nla_policy ppp_nl_policy[IFLA_PPP_MAX + 1] = { [IFLA_PPP_DEV_FD] = { .type = NLA_S32 }, }; static int ppp_nl_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (!data) return -EINVAL; if (!data[IFLA_PPP_DEV_FD]) return -EINVAL; if (nla_get_s32(data[IFLA_PPP_DEV_FD]) < 0) return -EBADF; return 0; } static int ppp_nl_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ppp_config conf = { .unit = -1, .ifname_is_set = true, }; struct file *file; int err; file = fget(nla_get_s32(data[IFLA_PPP_DEV_FD])); if (!file) return -EBADF; /* rtnl_lock is already held here, but ppp_create_interface() locks * ppp_mutex before holding rtnl_lock. Using mutex_trylock() avoids * possible deadlock due to lock order inversion, at the cost of * pushing the problem back to userspace. */ if (!mutex_trylock(&ppp_mutex)) { err = -EBUSY; goto out; } if (file->f_op != &ppp_device_fops || file->private_data) { err = -EBADF; goto out_unlock; } conf.file = file; /* Don't use device name generated by the rtnetlink layer when ifname * isn't specified. Let ppp_dev_configure() set the device name using * the PPP unit identifer as suffix (i.e. ppp<unit_id>). This allows * userspace to infer the device name using to the PPPIOCGUNIT ioctl. */ if (!tb[IFLA_IFNAME] || !nla_len(tb[IFLA_IFNAME]) || !*(char *)nla_data(tb[IFLA_IFNAME])) conf.ifname_is_set = false; err = ppp_dev_configure(src_net, dev, &conf); out_unlock: mutex_unlock(&ppp_mutex); out: fput(file); return err; } static void ppp_nl_dellink(struct net_device *dev, struct list_head *head) { unregister_netdevice_queue(dev, head); } static size_t ppp_nl_get_size(const struct net_device *dev) { return 0; } static int ppp_nl_fill_info(struct sk_buff *skb, const struct net_device *dev) { return 0; } static struct net *ppp_nl_get_link_net(const struct net_device *dev) { struct ppp *ppp = netdev_priv(dev); return READ_ONCE(ppp->ppp_net); } static struct rtnl_link_ops ppp_link_ops __read_mostly = { .kind = "ppp", .maxtype = IFLA_PPP_MAX, .policy = ppp_nl_policy, .priv_size = sizeof(struct ppp), .setup = ppp_setup, .validate = ppp_nl_validate, .newlink = ppp_nl_newlink, .dellink = ppp_nl_dellink, .get_size = ppp_nl_get_size, .fill_info = ppp_nl_fill_info, .get_link_net = ppp_nl_get_link_net, }; #define PPP_MAJOR 108 /* Called at boot time if ppp is compiled into the kernel, or at module load time (from init_module) if compiled as a module. */ static int __init ppp_init(void) { int err; pr_info("PPP generic driver version " PPP_VERSION "\n"); err = register_pernet_device(&ppp_net_ops); if (err) { pr_err("failed to register PPP pernet device (%d)\n", err); goto out; } err = register_chrdev(PPP_MAJOR, "ppp", &ppp_device_fops); if (err) { pr_err("failed to register PPP device (%d)\n", err); goto out_net; } err = class_register(&ppp_class); if (err) goto out_chrdev; err = rtnl_link_register(&ppp_link_ops); if (err) { pr_err("failed to register rtnetlink PPP handler\n"); goto out_class; } /* not a big deal if we fail here :-) */ device_create(&ppp_class, NULL, MKDEV(PPP_MAJOR, 0), NULL, "ppp"); return 0; out_class: class_unregister(&ppp_class); out_chrdev: unregister_chrdev(PPP_MAJOR, "ppp"); out_net: unregister_pernet_device(&ppp_net_ops); out: return err; } /* * Network interface unit routines. */ static netdev_tx_t ppp_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct ppp *ppp = netdev_priv(dev); int npi, proto; unsigned char *pp; npi = ethertype_to_npindex(ntohs(skb->protocol)); if (npi < 0) goto outf; /* Drop, accept or reject the packet */ switch (ppp->npmode[npi]) { case NPMODE_PASS: break; case NPMODE_QUEUE: /* it would be nice to have a way to tell the network system to queue this one up for later. */ goto outf; case NPMODE_DROP: case NPMODE_ERROR: goto outf; } /* Put the 2-byte PPP protocol number on the front, making sure there is room for the address and control fields. */ if (skb_cow_head(skb, PPP_HDRLEN)) goto outf; pp = skb_push(skb, 2); proto = npindex_to_proto[npi]; put_unaligned_be16(proto, pp); skb_scrub_packet(skb, !net_eq(ppp->ppp_net, dev_net(dev))); ppp_xmit_process(ppp, skb); return NETDEV_TX_OK; outf: kfree_skb(skb); ++dev->stats.tx_dropped; return NETDEV_TX_OK; } static int ppp_net_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *addr, int cmd) { struct ppp *ppp = netdev_priv(dev); int err = -EFAULT; struct ppp_stats stats; struct ppp_comp_stats cstats; char *vers; switch (cmd) { case SIOCGPPPSTATS: ppp_get_stats(ppp, &stats); if (copy_to_user(addr, &stats, sizeof(stats))) break; err = 0; break; case SIOCGPPPCSTATS: memset(&cstats, 0, sizeof(cstats)); if (ppp->xc_state) ppp->xcomp->comp_stat(ppp->xc_state, &cstats.c); if (ppp->rc_state) ppp->rcomp->decomp_stat(ppp->rc_state, &cstats.d); if (copy_to_user(addr, &cstats, sizeof(cstats))) break; err = 0; break; case SIOCGPPPVER: vers = PPP_VERSION; if (copy_to_user(addr, vers, strlen(vers) + 1)) break; err = 0; break; default: err = -EINVAL; } return err; } static void ppp_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats64) { struct ppp *ppp = netdev_priv(dev); ppp_recv_lock(ppp); stats64->rx_packets = ppp->stats64.rx_packets; stats64->rx_bytes = ppp->stats64.rx_bytes; ppp_recv_unlock(ppp); ppp_xmit_lock(ppp); stats64->tx_packets = ppp->stats64.tx_packets; stats64->tx_bytes = ppp->stats64.tx_bytes; ppp_xmit_unlock(ppp); stats64->rx_errors = dev->stats.rx_errors; stats64->tx_errors = dev->stats.tx_errors; stats64->rx_dropped = dev->stats.rx_dropped; stats64->tx_dropped = dev->stats.tx_dropped; stats64->rx_length_errors = dev->stats.rx_length_errors; } static int ppp_dev_init(struct net_device *dev) { struct ppp *ppp; netdev_lockdep_set_classes(dev); ppp = netdev_priv(dev); /* Let the netdevice take a reference on the ppp file. This ensures * that ppp_destroy_interface() won't run before the device gets * unregistered. */ refcount_inc(&ppp->file.refcnt); return 0; } static void ppp_dev_uninit(struct net_device *dev) { struct ppp *ppp = netdev_priv(dev); struct ppp_net *pn = ppp_pernet(ppp->ppp_net); ppp_lock(ppp); ppp->closing = 1; ppp_unlock(ppp); mutex_lock(&pn->all_ppp_mutex); unit_put(&pn->units_idr, ppp->file.index); mutex_unlock(&pn->all_ppp_mutex); ppp->owner = NULL; ppp->file.dead = 1; wake_up_interruptible(&ppp->file.rwait); } static void ppp_dev_priv_destructor(struct net_device *dev) { struct ppp *ppp; ppp = netdev_priv(dev); if (refcount_dec_and_test(&ppp->file.refcnt)) ppp_destroy_interface(ppp); } static int ppp_fill_forward_path(struct net_device_path_ctx *ctx, struct net_device_path *path) { struct ppp *ppp = netdev_priv(ctx->dev); struct ppp_channel *chan; struct channel *pch; if (ppp->flags & SC_MULTILINK) return -EOPNOTSUPP; if (list_empty(&ppp->channels)) return -ENODEV; pch = list_first_entry(&ppp->channels, struct channel, clist); chan = pch->chan; if (!chan->ops->fill_forward_path) return -EOPNOTSUPP; return chan->ops->fill_forward_path(ctx, path, chan); } static const struct net_device_ops ppp_netdev_ops = { .ndo_init = ppp_dev_init, .ndo_uninit = ppp_dev_uninit, .ndo_start_xmit = ppp_start_xmit, .ndo_siocdevprivate = ppp_net_siocdevprivate, .ndo_get_stats64 = ppp_get_stats64, .ndo_fill_forward_path = ppp_fill_forward_path, }; static const struct device_type ppp_type = { .name = "ppp", }; static void ppp_setup(struct net_device *dev) { dev->netdev_ops = &ppp_netdev_ops; SET_NETDEV_DEVTYPE(dev, &ppp_type); dev->lltx = true; dev->hard_header_len = PPP_HDRLEN; dev->mtu = PPP_MRU; dev->addr_len = 0; dev->tx_queue_len = 3; dev->type = ARPHRD_PPP; dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; dev->priv_destructor = ppp_dev_priv_destructor; netif_keep_dst(dev); } /* * Transmit-side routines. */ /* Called to do any work queued up on the transmit side that can now be done */ static void __ppp_xmit_process(struct ppp *ppp, struct sk_buff *skb) { ppp_xmit_lock(ppp); if (!ppp->closing) { ppp_push(ppp); if (skb) skb_queue_tail(&ppp->file.xq, skb); while (!ppp->xmit_pending && (skb = skb_dequeue(&ppp->file.xq))) ppp_send_frame(ppp, skb); /* If there's no work left to do, tell the core net code that we can accept some more. */ if (!ppp->xmit_pending && !skb_peek(&ppp->file.xq)) netif_wake_queue(ppp->dev); else netif_stop_queue(ppp->dev); } else { kfree_skb(skb); } ppp_xmit_unlock(ppp); } static void ppp_xmit_process(struct ppp *ppp, struct sk_buff *skb) { local_bh_disable(); if (unlikely(*this_cpu_ptr(ppp->xmit_recursion))) goto err; (*this_cpu_ptr(ppp->xmit_recursion))++; __ppp_xmit_process(ppp, skb); (*this_cpu_ptr(ppp->xmit_recursion))--; local_bh_enable(); return; err: local_bh_enable(); kfree_skb(skb); if (net_ratelimit()) netdev_err(ppp->dev, "recursion detected\n"); } static inline struct sk_buff * pad_compress_skb(struct ppp *ppp, struct sk_buff *skb) { struct sk_buff *new_skb; int len; int new_skb_size = ppp->dev->mtu + ppp->xcomp->comp_extra + ppp->dev->hard_header_len; int compressor_skb_size = ppp->dev->mtu + ppp->xcomp->comp_extra + PPP_HDRLEN; new_skb = alloc_skb(new_skb_size, GFP_ATOMIC); if (!new_skb) { if (net_ratelimit()) netdev_err(ppp->dev, "PPP: no memory (comp pkt)\n"); return NULL; } if (ppp->dev->hard_header_len > PPP_HDRLEN) skb_reserve(new_skb, ppp->dev->hard_header_len - PPP_HDRLEN); /* compressor still expects A/C bytes in hdr */ len = ppp->xcomp->compress(ppp->xc_state, skb->data - 2, new_skb->data, skb->len + 2, compressor_skb_size); if (len > 0 && (ppp->flags & SC_CCP_UP)) { consume_skb(skb); skb = new_skb; skb_put(skb, len); skb_pull(skb, 2); /* pull off A/C bytes */ } else if (len == 0) { /* didn't compress, or CCP not up yet */ consume_skb(new_skb); new_skb = skb; } else { /* * (len < 0) * MPPE requires that we do not send unencrypted * frames. The compressor will return -1 if we * should drop the frame. We cannot simply test * the compress_proto because MPPE and MPPC share * the same number. */ if (net_ratelimit()) netdev_err(ppp->dev, "ppp: compressor dropped pkt\n"); kfree_skb(skb); consume_skb(new_skb); new_skb = NULL; } return new_skb; } /* * Compress and send a frame. * The caller should have locked the xmit path, * and xmit_pending should be 0. */ static void ppp_send_frame(struct ppp *ppp, struct sk_buff *skb) { int proto = PPP_PROTO(skb); struct sk_buff *new_skb; int len; unsigned char *cp; skb->dev = ppp->dev; if (proto < 0x8000) { #ifdef CONFIG_PPP_FILTER /* check if we should pass this packet */ /* the filter instructions are constructed assuming a four-byte PPP header on each packet */ *(u8 *)skb_push(skb, 2) = 1; if (ppp->pass_filter && bpf_prog_run(ppp->pass_filter, skb) == 0) { if (ppp->debug & 1) netdev_printk(KERN_DEBUG, ppp->dev, "PPP: outbound frame " "not passed\n"); kfree_skb(skb); return; } /* if this packet passes the active filter, record the time */ if (!(ppp->active_filter && bpf_prog_run(ppp->active_filter, skb) == 0)) ppp->last_xmit = jiffies; skb_pull(skb, 2); #else /* for data packets, record the time */ ppp->last_xmit = jiffies; #endif /* CONFIG_PPP_FILTER */ } ++ppp->stats64.tx_packets; ppp->stats64.tx_bytes += skb->len - PPP_PROTO_LEN; switch (proto) { case PPP_IP: if (!ppp->vj || (ppp->flags & SC_COMP_TCP) == 0) break; /* try to do VJ TCP header compression */ new_skb = alloc_skb(skb->len + ppp->dev->hard_header_len - 2, GFP_ATOMIC); if (!new_skb) { netdev_err(ppp->dev, "PPP: no memory (VJ comp pkt)\n"); goto drop; } skb_reserve(new_skb, ppp->dev->hard_header_len - 2); cp = skb->data + 2; len = slhc_compress(ppp->vj, cp, skb->len - 2, new_skb->data + 2, &cp, !(ppp->flags & SC_NO_TCP_CCID)); if (cp == skb->data + 2) { /* didn't compress */ consume_skb(new_skb); } else { if (cp[0] & SL_TYPE_COMPRESSED_TCP) { proto = PPP_VJC_COMP; cp[0] &= ~SL_TYPE_COMPRESSED_TCP; } else { proto = PPP_VJC_UNCOMP; cp[0] = skb->data[2]; } consume_skb(skb); skb = new_skb; cp = skb_put(skb, len + 2); cp[0] = 0; cp[1] = proto; } break; case PPP_CCP: /* peek at outbound CCP frames */ ppp_ccp_peek(ppp, skb, 0); break; } /* try to do packet compression */ if ((ppp->xstate & SC_COMP_RUN) && ppp->xc_state && proto != PPP_LCP && proto != PPP_CCP) { if (!(ppp->flags & SC_CCP_UP) && (ppp->flags & SC_MUST_COMP)) { if (net_ratelimit()) netdev_err(ppp->dev, "ppp: compression required but " "down - pkt dropped.\n"); goto drop; } skb = pad_compress_skb(ppp, skb); if (!skb) goto drop; } /* * If we are waiting for traffic (demand dialling), * queue it up for pppd to receive. */ if (ppp->flags & SC_LOOP_TRAFFIC) { if (ppp->file.rq.qlen > PPP_MAX_RQLEN) goto drop; skb_queue_tail(&ppp->file.rq, skb); wake_up_interruptible(&ppp->file.rwait); return; } ppp->xmit_pending = skb; ppp_push(ppp); return; drop: kfree_skb(skb); ++ppp->dev->stats.tx_errors; } /* * Try to send the frame in xmit_pending. * The caller should have the xmit path locked. */ static void ppp_push(struct ppp *ppp) { struct list_head *list; struct channel *pch; struct sk_buff *skb = ppp->xmit_pending; if (!skb) return; list = &ppp->channels; if (list_empty(list)) { /* nowhere to send the packet, just drop it */ ppp->xmit_pending = NULL; kfree_skb(skb); return; } if ((ppp->flags & SC_MULTILINK) == 0) { /* not doing multilink: send it down the first channel */ list = list->next; pch = list_entry(list, struct channel, clist); spin_lock(&pch->downl); if (pch->chan) { if (pch->chan->ops->start_xmit(pch->chan, skb)) ppp->xmit_pending = NULL; } else { /* channel got unregistered */ kfree_skb(skb); ppp->xmit_pending = NULL; } spin_unlock(&pch->downl); return; } #ifdef CONFIG_PPP_MULTILINK /* Multilink: fragment the packet over as many links as can take the packet at the moment. */ if (!ppp_mp_explode(ppp, skb)) return; #endif /* CONFIG_PPP_MULTILINK */ ppp->xmit_pending = NULL; kfree_skb(skb); } #ifdef CONFIG_PPP_MULTILINK static bool mp_protocol_compress __read_mostly = true; module_param(mp_protocol_compress, bool, 0644); MODULE_PARM_DESC(mp_protocol_compress, "compress protocol id in multilink fragments"); /* * Divide a packet to be transmitted into fragments and * send them out the individual links. */ static int ppp_mp_explode(struct ppp *ppp, struct sk_buff *skb) { int len, totlen; int i, bits, hdrlen, mtu; int flen; int navail, nfree, nzero; int nbigger; int totspeed; int totfree; unsigned char *p, *q; struct list_head *list; struct channel *pch; struct sk_buff *frag; struct ppp_channel *chan; totspeed = 0; /*total bitrate of the bundle*/ nfree = 0; /* # channels which have no packet already queued */ navail = 0; /* total # of usable channels (not deregistered) */ nzero = 0; /* number of channels with zero speed associated*/ totfree = 0; /*total # of channels available and *having no queued packets before *starting the fragmentation*/ hdrlen = (ppp->flags & SC_MP_XSHORTSEQ)? MPHDRLEN_SSN: MPHDRLEN; i = 0; list_for_each_entry(pch, &ppp->channels, clist) { if (pch->chan) { pch->avail = 1; navail++; pch->speed = pch->chan->speed; } else { pch->avail = 0; } if (pch->avail) { if (skb_queue_empty(&pch->file.xq) || !pch->had_frag) { if (pch->speed == 0) nzero++; else totspeed += pch->speed; pch->avail = 2; ++nfree; ++totfree; } if (!pch->had_frag && i < ppp->nxchan) ppp->nxchan = i; } ++i; } /* * Don't start sending this packet unless at least half of * the channels are free. This gives much better TCP * performance if we have a lot of channels. */ if (nfree == 0 || nfree < navail / 2) return 0; /* can't take now, leave it in xmit_pending */ /* Do protocol field compression */ p = skb->data; len = skb->len; if (*p == 0 && mp_protocol_compress) { ++p; --len; } totlen = len; nbigger = len % nfree; /* skip to the channel after the one we last used and start at that one */ list = &ppp->channels; for (i = 0; i < ppp->nxchan; ++i) { list = list->next; if (list == &ppp->channels) { i = 0; break; } } /* create a fragment for each channel */ bits = B; while (len > 0) { list = list->next; if (list == &ppp->channels) { i = 0; continue; } pch = list_entry(list, struct channel, clist); ++i; if (!pch->avail) continue; /* * Skip this channel if it has a fragment pending already and * we haven't given a fragment to all of the free channels. */ if (pch->avail == 1) { if (nfree > 0) continue; } else { pch->avail = 1; } /* check the channel's mtu and whether it is still attached. */ spin_lock(&pch->downl); if (pch->chan == NULL) { /* can't use this channel, it's being deregistered */ if (pch->speed == 0) nzero--; else totspeed -= pch->speed; spin_unlock(&pch->downl); pch->avail = 0; totlen = len; totfree--; nfree--; if (--navail == 0) break; continue; } /* *if the channel speed is not set divide *the packet evenly among the free channels; *otherwise divide it according to the speed *of the channel we are going to transmit on */ flen = len; if (nfree > 0) { if (pch->speed == 0) { flen = len/nfree; if (nbigger > 0) { flen++; nbigger--; } } else { flen = (((totfree - nzero)*(totlen + hdrlen*totfree)) / ((totspeed*totfree)/pch->speed)) - hdrlen; if (nbigger > 0) { flen += ((totfree - nzero)*pch->speed)/totspeed; nbigger -= ((totfree - nzero)*pch->speed)/ totspeed; } } nfree--; } /* *check if we are on the last channel or *we exceded the length of the data to *fragment */ if ((nfree <= 0) || (flen > len)) flen = len; /* *it is not worth to tx on slow channels: *in that case from the resulting flen according to the *above formula will be equal or less than zero. *Skip the channel in this case */ if (flen <= 0) { pch->avail = 2; spin_unlock(&pch->downl); continue; } /* * hdrlen includes the 2-byte PPP protocol field, but the * MTU counts only the payload excluding the protocol field. * (RFC1661 Section 2) */ mtu = pch->chan->mtu - (hdrlen - 2); if (mtu < 4) mtu = 4; if (flen > mtu) flen = mtu; if (flen == len) bits |= E; frag = alloc_skb(flen + hdrlen + (flen == 0), GFP_ATOMIC); if (!frag) goto noskb; q = skb_put(frag, flen + hdrlen); /* make the MP header */ put_unaligned_be16(PPP_MP, q); if (ppp->flags & SC_MP_XSHORTSEQ) { q[2] = bits + ((ppp->nxseq >> 8) & 0xf); q[3] = ppp->nxseq; } else { q[2] = bits; q[3] = ppp->nxseq >> 16; q[4] = ppp->nxseq >> 8; q[5] = ppp->nxseq; } memcpy(q + hdrlen, p, flen); /* try to send it down the channel */ chan = pch->chan; if (!skb_queue_empty(&pch->file.xq) || !chan->ops->start_xmit(chan, frag)) skb_queue_tail(&pch->file.xq, frag); pch->had_frag = 1; p += flen; len -= flen; ++ppp->nxseq; bits = 0; spin_unlock(&pch->downl); } ppp->nxchan = i; return 1; noskb: spin_unlock(&pch->downl); if (ppp->debug & 1) netdev_err(ppp->dev, "PPP: no memory (fragment)\n"); ++ppp->dev->stats.tx_errors; ++ppp->nxseq; return 1; /* abandon the frame */ } #endif /* CONFIG_PPP_MULTILINK */ /* Try to send data out on a channel */ static void __ppp_channel_push(struct channel *pch) { struct sk_buff *skb; struct ppp *ppp; spin_lock(&pch->downl); if (pch->chan) { while (!skb_queue_empty(&pch->file.xq)) { skb = skb_dequeue(&pch->file.xq); if (!pch->chan->ops->start_xmit(pch->chan, skb)) { /* put the packet back and try again later */ skb_queue_head(&pch->file.xq, skb); break; } } } else { /* channel got deregistered */ skb_queue_purge(&pch->file.xq); } spin_unlock(&pch->downl); /* see if there is anything from the attached unit to be sent */ if (skb_queue_empty(&pch->file.xq)) { ppp = pch->ppp; if (ppp) __ppp_xmit_process(ppp, NULL); } } static void ppp_channel_push(struct channel *pch) { read_lock_bh(&pch->upl); if (pch->ppp) { (*this_cpu_ptr(pch->ppp->xmit_recursion))++; __ppp_channel_push(pch); (*this_cpu_ptr(pch->ppp->xmit_recursion))--; } else { __ppp_channel_push(pch); } read_unlock_bh(&pch->upl); } /* * Receive-side routines. */ struct ppp_mp_skb_parm { u32 sequence; u8 BEbits; }; #define PPP_MP_CB(skb) ((struct ppp_mp_skb_parm *)((skb)->cb)) static inline void ppp_do_recv(struct ppp *ppp, struct sk_buff *skb, struct channel *pch) { ppp_recv_lock(ppp); if (!ppp->closing) ppp_receive_frame(ppp, skb, pch); else kfree_skb(skb); ppp_recv_unlock(ppp); } /** * __ppp_decompress_proto - Decompress protocol field, slim version. * @skb: Socket buffer where protocol field should be decompressed. It must have * at least 1 byte of head room and 1 byte of linear data. First byte of * data must be a protocol field byte. * * Decompress protocol field in PPP header if it's compressed, e.g. when * Protocol-Field-Compression (PFC) was negotiated. No checks w.r.t. skb data * length are done in this function. */ static void __ppp_decompress_proto(struct sk_buff *skb) { if (skb->data[0] & 0x01) *(u8 *)skb_push(skb, 1) = 0x00; } /** * ppp_decompress_proto - Check skb data room and decompress protocol field. * @skb: Socket buffer where protocol field should be decompressed. First byte * of data must be a protocol field byte. * * Decompress protocol field in PPP header if it's compressed, e.g. when * Protocol-Field-Compression (PFC) was negotiated. This function also makes * sure that skb data room is sufficient for Protocol field, before and after * decompression. * * Return: true - decompressed successfully, false - not enough room in skb. */ static bool ppp_decompress_proto(struct sk_buff *skb) { /* At least one byte should be present (if protocol is compressed) */ if (!pskb_may_pull(skb, 1)) return false; __ppp_decompress_proto(skb); /* Protocol field should occupy 2 bytes when not compressed */ return pskb_may_pull(skb, 2); } /* Attempt to handle a frame via. a bridged channel, if one exists. * If the channel is bridged, the frame is consumed by the bridge. * If not, the caller must handle the frame by normal recv mechanisms. * Returns true if the frame is consumed, false otherwise. */ static bool ppp_channel_bridge_input(struct channel *pch, struct sk_buff *skb) { struct channel *pchb; rcu_read_lock(); pchb = rcu_dereference(pch->bridge); if (!pchb) goto out_rcu; spin_lock_bh(&pchb->downl); if (!pchb->chan) { /* channel got unregistered */ kfree_skb(skb); goto outl; } skb_scrub_packet(skb, !net_eq(pch->chan_net, pchb->chan_net)); if (!pchb->chan->ops->start_xmit(pchb->chan, skb)) kfree_skb(skb); outl: spin_unlock_bh(&pchb->downl); out_rcu: rcu_read_unlock(); /* If pchb is set then we've consumed the packet */ return !!pchb; } void ppp_input(struct ppp_channel *chan, struct sk_buff *skb) { struct channel *pch = chan->ppp; int proto; if (!pch) { kfree_skb(skb); return; } /* If the channel is bridged, transmit via. bridge */ if (ppp_channel_bridge_input(pch, skb)) return; read_lock_bh(&pch->upl); if (!ppp_decompress_proto(skb)) { kfree_skb(skb); if (pch->ppp) { ++pch->ppp->dev->stats.rx_length_errors; ppp_receive_error(pch->ppp); } goto done; } proto = PPP_PROTO(skb); if (!pch->ppp || proto >= 0xc000 || proto == PPP_CCPFRAG) { /* put it on the channel queue */ skb_queue_tail(&pch->file.rq, skb); /* drop old frames if queue too long */ while (pch->file.rq.qlen > PPP_MAX_RQLEN && (skb = skb_dequeue(&pch->file.rq))) kfree_skb(skb); wake_up_interruptible(&pch->file.rwait); } else { ppp_do_recv(pch->ppp, skb, pch); } done: read_unlock_bh(&pch->upl); } /* Put a 0-length skb in the receive queue as an error indication */ void ppp_input_error(struct ppp_channel *chan, int code) { struct channel *pch = chan->ppp; struct sk_buff *skb; if (!pch) return; read_lock_bh(&pch->upl); if (pch->ppp) { skb = alloc_skb(0, GFP_ATOMIC); if (skb) { skb->len = 0; /* probably unnecessary */ skb->cb[0] = code; ppp_do_recv(pch->ppp, skb, pch); } } read_unlock_bh(&pch->upl); } /* * We come in here to process a received frame. * The receive side of the ppp unit is locked. */ static void ppp_receive_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch) { /* note: a 0-length skb is used as an error indication */ if (skb->len > 0) { skb_checksum_complete_unset(skb); #ifdef CONFIG_PPP_MULTILINK /* XXX do channel-level decompression here */ if (PPP_PROTO(skb) == PPP_MP) ppp_receive_mp_frame(ppp, skb, pch); else #endif /* CONFIG_PPP_MULTILINK */ ppp_receive_nonmp_frame(ppp, skb); } else { kfree_skb(skb); ppp_receive_error(ppp); } } static void ppp_receive_error(struct ppp *ppp) { ++ppp->dev->stats.rx_errors; if (ppp->vj) slhc_toss(ppp->vj); } static void ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb) { struct sk_buff *ns; int proto, len, npi; /* * Decompress the frame, if compressed. * Note that some decompressors need to see uncompressed frames * that come in as well as compressed frames. */ if (ppp->rc_state && (ppp->rstate & SC_DECOMP_RUN) && (ppp->rstate & (SC_DC_FERROR | SC_DC_ERROR)) == 0) skb = ppp_decompress_frame(ppp, skb); if (ppp->flags & SC_MUST_COMP && ppp->rstate & SC_DC_FERROR) goto err; /* At this point the "Protocol" field MUST be decompressed, either in * ppp_input(), ppp_decompress_frame() or in ppp_receive_mp_frame(). */ proto = PPP_PROTO(skb); switch (proto) { case PPP_VJC_COMP: /* decompress VJ compressed packets */ if (!ppp->vj || (ppp->flags & SC_REJ_COMP_TCP)) goto err; if (skb_tailroom(skb) < 124 || skb_cloned(skb)) { /* copy to a new sk_buff with more tailroom */ ns = dev_alloc_skb(skb->len + 128); if (!ns) { netdev_err(ppp->dev, "PPP: no memory " "(VJ decomp)\n"); goto err; } skb_reserve(ns, 2); skb_copy_bits(skb, 0, skb_put(ns, skb->len), skb->len); consume_skb(skb); skb = ns; } else skb->ip_summed = CHECKSUM_NONE; len = slhc_uncompress(ppp->vj, skb->data + 2, skb->len - 2); if (len <= 0) { netdev_printk(KERN_DEBUG, ppp->dev, "PPP: VJ decompression error\n"); goto err; } len += 2; if (len > skb->len) skb_put(skb, len - skb->len); else if (len < skb->len) skb_trim(skb, len); proto = PPP_IP; break; case PPP_VJC_UNCOMP: if (!ppp->vj || (ppp->flags & SC_REJ_COMP_TCP)) goto err; /* Until we fix the decompressor need to make sure * data portion is linear. */ if (!pskb_may_pull(skb, skb->len)) goto err; if (slhc_remember(ppp->vj, skb->data + 2, skb->len - 2) <= 0) { netdev_err(ppp->dev, "PPP: VJ uncompressed error\n"); goto err; } proto = PPP_IP; break; case PPP_CCP: ppp_ccp_peek(ppp, skb, 1); break; } ++ppp->stats64.rx_packets; ppp->stats64.rx_bytes += skb->len - 2; npi = proto_to_npindex(proto); if (npi < 0) { /* control or unknown frame - pass it to pppd */ skb_queue_tail(&ppp->file.rq, skb); /* limit queue length by dropping old frames */ while (ppp->file.rq.qlen > PPP_MAX_RQLEN && (skb = skb_dequeue(&ppp->file.rq))) kfree_skb(skb); /* wake up any process polling or blocking on read */ wake_up_interruptible(&ppp->file.rwait); } else { /* network protocol frame - give it to the kernel */ #ifdef CONFIG_PPP_FILTER /* check if the packet passes the pass and active filters */ /* the filter instructions are constructed assuming a four-byte PPP header on each packet */ if (ppp->pass_filter || ppp->active_filter) { if (skb_unclone(skb, GFP_ATOMIC)) goto err; *(u8 *)skb_push(skb, 2) = 0; if (ppp->pass_filter && bpf_prog_run(ppp->pass_filter, skb) == 0) { if (ppp->debug & 1) netdev_printk(KERN_DEBUG, ppp->dev, "PPP: inbound frame " "not passed\n"); kfree_skb(skb); return; } if (!(ppp->active_filter && bpf_prog_run(ppp->active_filter, skb) == 0)) ppp->last_recv = jiffies; __skb_pull(skb, 2); } else #endif /* CONFIG_PPP_FILTER */ ppp->last_recv = jiffies; if ((ppp->dev->flags & IFF_UP) == 0 || ppp->npmode[npi] != NPMODE_PASS) { kfree_skb(skb); } else { /* chop off protocol */ skb_pull_rcsum(skb, 2); skb->dev = ppp->dev; skb->protocol = htons(npindex_to_ethertype[npi]); skb_reset_mac_header(skb); skb_scrub_packet(skb, !net_eq(ppp->ppp_net, dev_net(ppp->dev))); netif_rx(skb); } } return; err: kfree_skb(skb); ppp_receive_error(ppp); } static struct sk_buff * ppp_decompress_frame(struct ppp *ppp, struct sk_buff *skb) { int proto = PPP_PROTO(skb); struct sk_buff *ns; int len; /* Until we fix all the decompressor's need to make sure * data portion is linear. */ if (!pskb_may_pull(skb, skb->len)) goto err; if (proto == PPP_COMP) { int obuff_size; switch(ppp->rcomp->compress_proto) { case CI_MPPE: obuff_size = ppp->mru + PPP_HDRLEN + 1; break; default: obuff_size = ppp->mru + PPP_HDRLEN; break; } ns = dev_alloc_skb(obuff_size); if (!ns) { netdev_err(ppp->dev, "ppp_decompress_frame: " "no memory\n"); goto err; } /* the decompressor still expects the A/C bytes in the hdr */ len = ppp->rcomp->decompress(ppp->rc_state, skb->data - 2, skb->len + 2, ns->data, obuff_size); if (len < 0) { /* Pass the compressed frame to pppd as an error indication. */ if (len == DECOMP_FATALERROR) ppp->rstate |= SC_DC_FERROR; kfree_skb(ns); goto err; } consume_skb(skb); skb = ns; skb_put(skb, len); skb_pull(skb, 2); /* pull off the A/C bytes */ /* Don't call __ppp_decompress_proto() here, but instead rely on * corresponding algo (mppe/bsd/deflate) to decompress it. */ } else { /* Uncompressed frame - pass to decompressor so it can update its dictionary if necessary. */ if (ppp->rcomp->incomp) ppp->rcomp->incomp(ppp->rc_state, skb->data - 2, skb->len + 2); } return skb; err: ppp->rstate |= SC_DC_ERROR; ppp_receive_error(ppp); return skb; } #ifdef CONFIG_PPP_MULTILINK /* * Receive a multilink frame. * We put it on the reconstruction queue and then pull off * as many completed frames as we can. */ static void ppp_receive_mp_frame(struct ppp *ppp, struct sk_buff *skb, struct channel *pch) { u32 mask, seq; struct channel *ch; int mphdrlen = (ppp->flags & SC_MP_SHORTSEQ)? MPHDRLEN_SSN: MPHDRLEN; if (!pskb_may_pull(skb, mphdrlen + 1) || ppp->mrru == 0) goto err; /* no good, throw it away */ /* Decode sequence number and begin/end bits */ if (ppp->flags & SC_MP_SHORTSEQ) { seq = ((skb->data[2] & 0x0f) << 8) | skb->data[3]; mask = 0xfff; } else { seq = (skb->data[3] << 16) | (skb->data[4] << 8)| skb->data[5]; mask = 0xffffff; } PPP_MP_CB(skb)->BEbits = skb->data[2]; skb_pull(skb, mphdrlen); /* pull off PPP and MP headers */ /* * Do protocol ID decompression on the first fragment of each packet. * We have to do that here, because ppp_receive_nonmp_frame() expects * decompressed protocol field. */ if (PPP_MP_CB(skb)->BEbits & B) __ppp_decompress_proto(skb); /* * Expand sequence number to 32 bits, making it as close * as possible to ppp->minseq. */ seq |= ppp->minseq & ~mask; if ((int)(ppp->minseq - seq) > (int)(mask >> 1)) seq += mask + 1; else if ((int)(seq - ppp->minseq) > (int)(mask >> 1)) seq -= mask + 1; /* should never happen */ PPP_MP_CB(skb)->sequence = seq; pch->lastseq = seq; /* * If this packet comes before the next one we were expecting, * drop it. */ if (seq_before(seq, ppp->nextseq)) { kfree_skb(skb); ++ppp->dev->stats.rx_dropped; ppp_receive_error(ppp); return; } /* * Reevaluate minseq, the minimum over all channels of the * last sequence number received on each channel. Because of * the increasing sequence number rule, we know that any fragment * before `minseq' which hasn't arrived is never going to arrive. * The list of channels can't change because we have the receive * side of the ppp unit locked. */ list_for_each_entry(ch, &ppp->channels, clist) { if (seq_before(ch->lastseq, seq)) seq = ch->lastseq; } if (seq_before(ppp->minseq, seq)) ppp->minseq = seq; /* Put the fragment on the reconstruction queue */ ppp_mp_insert(ppp, skb); /* If the queue is getting long, don't wait any longer for packets before the start of the queue. */ if (skb_queue_len(&ppp->mrq) >= PPP_MP_MAX_QLEN) { struct sk_buff *mskb = skb_peek(&ppp->mrq); if (seq_before(ppp->minseq, PPP_MP_CB(mskb)->sequence)) ppp->minseq = PPP_MP_CB(mskb)->sequence; } /* Pull completed packets off the queue and receive them. */ while ((skb = ppp_mp_reconstruct(ppp))) { if (pskb_may_pull(skb, 2)) ppp_receive_nonmp_frame(ppp, skb); else { ++ppp->dev->stats.rx_length_errors; kfree_skb(skb); ppp_receive_error(ppp); } } return; err: kfree_skb(skb); ppp_receive_error(ppp); } /* * Insert a fragment on the MP reconstruction queue. * The queue is ordered by increasing sequence number. */ static void ppp_mp_insert(struct ppp *ppp, struct sk_buff *skb) { struct sk_buff *p; struct sk_buff_head *list = &ppp->mrq; u32 seq = PPP_MP_CB(skb)->sequence; /* N.B. we don't need to lock the list lock because we have the ppp unit receive-side lock. */ skb_queue_walk(list, p) { if (seq_before(seq, PPP_MP_CB(p)->sequence)) break; } __skb_queue_before(list, p, skb); } /* * Reconstruct a packet from the MP fragment queue. * We go through increasing sequence numbers until we find a * complete packet, or we get to the sequence number for a fragment * which hasn't arrived but might still do so. */ static struct sk_buff * ppp_mp_reconstruct(struct ppp *ppp) { u32 seq = ppp->nextseq; u32 minseq = ppp->minseq; struct sk_buff_head *list = &ppp->mrq; struct sk_buff *p, *tmp; struct sk_buff *head, *tail; struct sk_buff *skb = NULL; int lost = 0, len = 0; if (ppp->mrru == 0) /* do nothing until mrru is set */ return NULL; head = __skb_peek(list); tail = NULL; skb_queue_walk_safe(list, p, tmp) { again: if (seq_before(PPP_MP_CB(p)->sequence, seq)) { /* this can't happen, anyway ignore the skb */ netdev_err(ppp->dev, "ppp_mp_reconstruct bad " "seq %u < %u\n", PPP_MP_CB(p)->sequence, seq); __skb_unlink(p, list); kfree_skb(p); continue; } if (PPP_MP_CB(p)->sequence != seq) { u32 oldseq; /* Fragment `seq' is missing. If it is after minseq, it might arrive later, so stop here. */ if (seq_after(seq, minseq)) break; /* Fragment `seq' is lost, keep going. */ lost = 1; oldseq = seq; seq = seq_before(minseq, PPP_MP_CB(p)->sequence)? minseq + 1: PPP_MP_CB(p)->sequence; if (ppp->debug & 1) netdev_printk(KERN_DEBUG, ppp->dev, "lost frag %u..%u\n", oldseq, seq-1); goto again; } /* * At this point we know that all the fragments from * ppp->nextseq to seq are either present or lost. * Also, there are no complete packets in the queue * that have no missing fragments and end before this * fragment. */ /* B bit set indicates this fragment starts a packet */ if (PPP_MP_CB(p)->BEbits & B) { head = p; lost = 0; len = 0; } len += p->len; /* Got a complete packet yet? */ if (lost == 0 && (PPP_MP_CB(p)->BEbits & E) && (PPP_MP_CB(head)->BEbits & B)) { if (len > ppp->mrru + 2) { ++ppp->dev->stats.rx_length_errors; netdev_printk(KERN_DEBUG, ppp->dev, "PPP: reconstructed packet" " is too long (%d)\n", len); } else { tail = p; break; } ppp->nextseq = seq + 1; } /* * If this is the ending fragment of a packet, * and we haven't found a complete valid packet yet, * we can discard up to and including this fragment. */ if (PPP_MP_CB(p)->BEbits & E) { struct sk_buff *tmp2; skb_queue_reverse_walk_from_safe(list, p, tmp2) { if (ppp->debug & 1) netdev_printk(KERN_DEBUG, ppp->dev, "discarding frag %u\n", PPP_MP_CB(p)->sequence); __skb_unlink(p, list); kfree_skb(p); } head = skb_peek(list); if (!head) break; } ++seq; } /* If we have a complete packet, copy it all into one skb. */ if (tail != NULL) { /* If we have discarded any fragments, signal a receive error. */ if (PPP_MP_CB(head)->sequence != ppp->nextseq) { skb_queue_walk_safe(list, p, tmp) { if (p == head) break; if (ppp->debug & 1) netdev_printk(KERN_DEBUG, ppp->dev, "discarding frag %u\n", PPP_MP_CB(p)->sequence); __skb_unlink(p, list); kfree_skb(p); } if (ppp->debug & 1) netdev_printk(KERN_DEBUG, ppp->dev, " missed pkts %u..%u\n", ppp->nextseq, PPP_MP_CB(head)->sequence-1); ++ppp->dev->stats.rx_dropped; ppp_receive_error(ppp); } skb = head; if (head != tail) { struct sk_buff **fragpp = &skb_shinfo(skb)->frag_list; p = skb_queue_next(list, head); __skb_unlink(skb, list); skb_queue_walk_from_safe(list, p, tmp) { __skb_unlink(p, list); *fragpp = p; p->next = NULL; fragpp = &p->next; skb->len += p->len; skb->data_len += p->len; skb->truesize += p->truesize; if (p == tail) break; } } else { __skb_unlink(skb, list); } ppp->nextseq = PPP_MP_CB(tail)->sequence + 1; } return skb; } #endif /* CONFIG_PPP_MULTILINK */ /* * Channel interface. */ /* Create a new, unattached ppp channel. */ int ppp_register_channel(struct ppp_channel *chan) { return ppp_register_net_channel(current->nsproxy->net_ns, chan); } /* Create a new, unattached ppp channel for specified net. */ int ppp_register_net_channel(struct net *net, struct ppp_channel *chan) { struct channel *pch; struct ppp_net *pn; pch = kzalloc(sizeof(struct channel), GFP_KERNEL); if (!pch) return -ENOMEM; pn = ppp_pernet(net); pch->ppp = NULL; pch->chan = chan; pch->chan_net = get_net_track(net, &pch->ns_tracker, GFP_KERNEL); chan->ppp = pch; init_ppp_file(&pch->file, CHANNEL); pch->file.hdrlen = chan->hdrlen; #ifdef CONFIG_PPP_MULTILINK pch->lastseq = -1; #endif /* CONFIG_PPP_MULTILINK */ init_rwsem(&pch->chan_sem); spin_lock_init(&pch->downl); rwlock_init(&pch->upl); spin_lock_bh(&pn->all_channels_lock); pch->file.index = ++pn->last_channel_index; list_add(&pch->list, &pn->new_channels); atomic_inc(&channel_count); spin_unlock_bh(&pn->all_channels_lock); return 0; } /* * Return the index of a channel. */ int ppp_channel_index(struct ppp_channel *chan) { struct channel *pch = chan->ppp; if (pch) return pch->file.index; return -1; } /* * Return the PPP unit number to which a channel is connected. */ int ppp_unit_number(struct ppp_channel *chan) { struct channel *pch = chan->ppp; int unit = -1; if (pch) { read_lock_bh(&pch->upl); if (pch->ppp) unit = pch->ppp->file.index; read_unlock_bh(&pch->upl); } return unit; } /* * Return the PPP device interface name of a channel. */ char *ppp_dev_name(struct ppp_channel *chan) { struct channel *pch = chan->ppp; char *name = NULL; if (pch) { read_lock_bh(&pch->upl); if (pch->ppp && pch->ppp->dev) name = pch->ppp->dev->name; read_unlock_bh(&pch->upl); } return name; } /* * Disconnect a channel from the generic layer. * This must be called in process context. */ void ppp_unregister_channel(struct ppp_channel *chan) { struct channel *pch = chan->ppp; struct ppp_net *pn; if (!pch) return; /* should never happen */ chan->ppp = NULL; /* * This ensures that we have returned from any calls into * the channel's start_xmit or ioctl routine before we proceed. */ down_write(&pch->chan_sem); spin_lock_bh(&pch->downl); pch->chan = NULL; spin_unlock_bh(&pch->downl); up_write(&pch->chan_sem); ppp_disconnect_channel(pch); pn = ppp_pernet(pch->chan_net); spin_lock_bh(&pn->all_channels_lock); list_del(&pch->list); spin_unlock_bh(&pn->all_channels_lock); ppp_unbridge_channels(pch); pch->file.dead = 1; wake_up_interruptible(&pch->file.rwait); if (refcount_dec_and_test(&pch->file.refcnt)) ppp_destroy_channel(pch); } /* * Callback from a channel when it can accept more to transmit. * This should be called at BH/softirq level, not interrupt level. */ void ppp_output_wakeup(struct ppp_channel *chan) { struct channel *pch = chan->ppp; if (!pch) return; ppp_channel_push(pch); } /* * Compression control. */ /* Process the PPPIOCSCOMPRESS ioctl. */ static int ppp_set_compress(struct ppp *ppp, struct ppp_option_data *data) { int err = -EFAULT; struct compressor *cp, *ocomp; void *state, *ostate; unsigned char ccp_option[CCP_MAX_OPTION_LENGTH]; if (data->length > CCP_MAX_OPTION_LENGTH) goto out; if (copy_from_user(ccp_option, data->ptr, data->length)) goto out; err = -EINVAL; if (data->length < 2 || ccp_option[1] < 2 || ccp_option[1] > data->length) goto out; cp = try_then_request_module( find_compressor(ccp_option[0]), "ppp-compress-%d", ccp_option[0]); if (!cp) goto out; err = -ENOBUFS; if (data->transmit) { state = cp->comp_alloc(ccp_option, data->length); if (state) { ppp_xmit_lock(ppp); ppp->xstate &= ~SC_COMP_RUN; ocomp = ppp->xcomp; ostate = ppp->xc_state; ppp->xcomp = cp; ppp->xc_state = state; ppp_xmit_unlock(ppp); if (ostate) { ocomp->comp_free(ostate); module_put(ocomp->owner); } err = 0; } else module_put(cp->owner); } else { state = cp->decomp_alloc(ccp_option, data->length); if (state) { ppp_recv_lock(ppp); ppp->rstate &= ~SC_DECOMP_RUN; ocomp = ppp->rcomp; ostate = ppp->rc_state; ppp->rcomp = cp; ppp->rc_state = state; ppp_recv_unlock(ppp); if (ostate) { ocomp->decomp_free(ostate); module_put(ocomp->owner); } err = 0; } else module_put(cp->owner); } out: return err; } /* * Look at a CCP packet and update our state accordingly. * We assume the caller has the xmit or recv path locked. */ static void ppp_ccp_peek(struct ppp *ppp, struct sk_buff *skb, int inbound) { unsigned char *dp; int len; if (!pskb_may_pull(skb, CCP_HDRLEN + 2)) return; /* no header */ dp = skb->data + 2; switch (CCP_CODE(dp)) { case CCP_CONFREQ: /* A ConfReq starts negotiation of compression * in one direction of transmission, * and hence brings it down...but which way? * * Remember: * A ConfReq indicates what the sender would like to receive */ if(inbound) /* He is proposing what I should send */ ppp->xstate &= ~SC_COMP_RUN; else /* I am proposing to what he should send */ ppp->rstate &= ~SC_DECOMP_RUN; break; case CCP_TERMREQ: case CCP_TERMACK: /* * CCP is going down, both directions of transmission */ ppp->rstate &= ~SC_DECOMP_RUN; ppp->xstate &= ~SC_COMP_RUN; break; case CCP_CONFACK: if ((ppp->flags & (SC_CCP_OPEN | SC_CCP_UP)) != SC_CCP_OPEN) break; len = CCP_LENGTH(dp); if (!pskb_may_pull(skb, len + 2)) return; /* too short */ dp += CCP_HDRLEN; len -= CCP_HDRLEN; if (len < CCP_OPT_MINLEN || len < CCP_OPT_LENGTH(dp)) break; if (inbound) { /* we will start receiving compressed packets */ if (!ppp->rc_state) break; if (ppp->rcomp->decomp_init(ppp->rc_state, dp, len, ppp->file.index, 0, ppp->mru, ppp->debug)) { ppp->rstate |= SC_DECOMP_RUN; ppp->rstate &= ~(SC_DC_ERROR | SC_DC_FERROR); } } else { /* we will soon start sending compressed packets */ if (!ppp->xc_state) break; if (ppp->xcomp->comp_init(ppp->xc_state, dp, len, ppp->file.index, 0, ppp->debug)) ppp->xstate |= SC_COMP_RUN; } break; case CCP_RESETACK: /* reset the [de]compressor */ if ((ppp->flags & SC_CCP_UP) == 0) break; if (inbound) { if (ppp->rc_state && (ppp->rstate & SC_DECOMP_RUN)) { ppp->rcomp->decomp_reset(ppp->rc_state); ppp->rstate &= ~SC_DC_ERROR; } } else { if (ppp->xc_state && (ppp->xstate & SC_COMP_RUN)) ppp->xcomp->comp_reset(ppp->xc_state); } break; } } /* Free up compression resources. */ static void ppp_ccp_closed(struct ppp *ppp) { void *xstate, *rstate; struct compressor *xcomp, *rcomp; ppp_lock(ppp); ppp->flags &= ~(SC_CCP_OPEN | SC_CCP_UP); ppp->xstate = 0; xcomp = ppp->xcomp; xstate = ppp->xc_state; ppp->xc_state = NULL; ppp->rstate = 0; rcomp = ppp->rcomp; rstate = ppp->rc_state; ppp->rc_state = NULL; ppp_unlock(ppp); if (xstate) { xcomp->comp_free(xstate); module_put(xcomp->owner); } if (rstate) { rcomp->decomp_free(rstate); module_put(rcomp->owner); } } /* List of compressors. */ static LIST_HEAD(compressor_list); static DEFINE_SPINLOCK(compressor_list_lock); struct compressor_entry { struct list_head list; struct compressor *comp; }; static struct compressor_entry * find_comp_entry(int proto) { struct compressor_entry *ce; list_for_each_entry(ce, &compressor_list, list) { if (ce->comp->compress_proto == proto) return ce; } return NULL; } /* Register a compressor */ int ppp_register_compressor(struct compressor *cp) { struct compressor_entry *ce; int ret; spin_lock(&compressor_list_lock); ret = -EEXIST; if (find_comp_entry(cp->compress_proto)) goto out; ret = -ENOMEM; ce = kmalloc(sizeof(struct compressor_entry), GFP_ATOMIC); if (!ce) goto out; ret = 0; ce->comp = cp; list_add(&ce->list, &compressor_list); out: spin_unlock(&compressor_list_lock); return ret; } /* Unregister a compressor */ void ppp_unregister_compressor(struct compressor *cp) { struct compressor_entry *ce; spin_lock(&compressor_list_lock); ce = find_comp_entry(cp->compress_proto); if (ce && ce->comp == cp) { list_del(&ce->list); kfree(ce); } spin_unlock(&compressor_list_lock); } /* Find a compressor. */ static struct compressor * find_compressor(int type) { struct compressor_entry *ce; struct compressor *cp = NULL; spin_lock(&compressor_list_lock); ce = find_comp_entry(type); if (ce) { cp = ce->comp; if (!try_module_get(cp->owner)) cp = NULL; } spin_unlock(&compressor_list_lock); return cp; } /* * Miscelleneous stuff. */ static void ppp_get_stats(struct ppp *ppp, struct ppp_stats *st) { struct slcompress *vj = ppp->vj; memset(st, 0, sizeof(*st)); st->p.ppp_ipackets = ppp->stats64.rx_packets; st->p.ppp_ierrors = ppp->dev->stats.rx_errors; st->p.ppp_ibytes = ppp->stats64.rx_bytes; st->p.ppp_opackets = ppp->stats64.tx_packets; st->p.ppp_oerrors = ppp->dev->stats.tx_errors; st->p.ppp_obytes = ppp->stats64.tx_bytes; if (!vj) return; st->vj.vjs_packets = vj->sls_o_compressed + vj->sls_o_uncompressed; st->vj.vjs_compressed = vj->sls_o_compressed; st->vj.vjs_searches = vj->sls_o_searches; st->vj.vjs_misses = vj->sls_o_misses; st->vj.vjs_errorin = vj->sls_i_error; st->vj.vjs_tossed = vj->sls_i_tossed; st->vj.vjs_uncompressedin = vj->sls_i_uncompressed; st->vj.vjs_compressedin = vj->sls_i_compressed; } /* * Stuff for handling the lists of ppp units and channels * and for initialization. */ /* * Create a new ppp interface unit. Fails if it can't allocate memory * or if there is already a unit with the requested number. * unit == -1 means allocate a new number. */ static int ppp_create_interface(struct net *net, struct file *file, int *unit) { struct ppp_config conf = { .file = file, .unit = *unit, .ifname_is_set = false, }; struct net_device *dev; struct ppp *ppp; int err; dev = alloc_netdev(sizeof(struct ppp), "", NET_NAME_ENUM, ppp_setup); if (!dev) { err = -ENOMEM; goto err; } dev_net_set(dev, net); dev->rtnl_link_ops = &ppp_link_ops; rtnl_lock(); err = ppp_dev_configure(net, dev, &conf); if (err < 0) goto err_dev; ppp = netdev_priv(dev); *unit = ppp->file.index; rtnl_unlock(); return 0; err_dev: rtnl_unlock(); free_netdev(dev); err: return err; } /* * Initialize a ppp_file structure. */ static void init_ppp_file(struct ppp_file *pf, int kind) { pf->kind = kind; skb_queue_head_init(&pf->xq); skb_queue_head_init(&pf->rq); refcount_set(&pf->refcnt, 1); init_waitqueue_head(&pf->rwait); } /* * Free the memory used by a ppp unit. This is only called once * there are no channels connected to the unit and no file structs * that reference the unit. */ static void ppp_destroy_interface(struct ppp *ppp) { atomic_dec(&ppp_unit_count); if (!ppp->file.dead || ppp->n_channels) { /* "can't happen" */ netdev_err(ppp->dev, "ppp: destroying ppp struct %p " "but dead=%d n_channels=%d !\n", ppp, ppp->file.dead, ppp->n_channels); return; } ppp_ccp_closed(ppp); if (ppp->vj) { slhc_free(ppp->vj); ppp->vj = NULL; } skb_queue_purge(&ppp->file.xq); skb_queue_purge(&ppp->file.rq); #ifdef CONFIG_PPP_MULTILINK skb_queue_purge(&ppp->mrq); #endif /* CONFIG_PPP_MULTILINK */ #ifdef CONFIG_PPP_FILTER if (ppp->pass_filter) { bpf_prog_destroy(ppp->pass_filter); ppp->pass_filter = NULL; } if (ppp->active_filter) { bpf_prog_destroy(ppp->active_filter); ppp->active_filter = NULL; } #endif /* CONFIG_PPP_FILTER */ kfree_skb(ppp->xmit_pending); free_percpu(ppp->xmit_recursion); free_netdev(ppp->dev); } /* * Locate an existing ppp unit. * The caller should have locked the all_ppp_mutex. */ static struct ppp * ppp_find_unit(struct ppp_net *pn, int unit) { return unit_find(&pn->units_idr, unit); } /* * Locate an existing ppp channel. * The caller should have locked the all_channels_lock. * First we look in the new_channels list, then in the * all_channels list. If found in the new_channels list, * we move it to the all_channels list. This is for speed * when we have a lot of channels in use. */ static struct channel * ppp_find_channel(struct ppp_net *pn, int unit) { struct channel *pch; list_for_each_entry(pch, &pn->new_channels, list) { if (pch->file.index == unit) { list_move(&pch->list, &pn->all_channels); return pch; } } list_for_each_entry(pch, &pn->all_channels, list) { if (pch->file.index == unit) return pch; } return NULL; } /* * Connect a PPP channel to a PPP interface unit. */ static int ppp_connect_channel(struct channel *pch, int unit) { struct ppp *ppp; struct ppp_net *pn; int ret = -ENXIO; int hdrlen; pn = ppp_pernet(pch->chan_net); mutex_lock(&pn->all_ppp_mutex); ppp = ppp_find_unit(pn, unit); if (!ppp) goto out; write_lock_bh(&pch->upl); ret = -EINVAL; if (pch->ppp || rcu_dereference_protected(pch->bridge, lockdep_is_held(&pch->upl))) goto outl; ppp_lock(ppp); spin_lock_bh(&pch->downl); if (!pch->chan) { /* Don't connect unregistered channels */ spin_unlock_bh(&pch->downl); ppp_unlock(ppp); ret = -ENOTCONN; goto outl; } spin_unlock_bh(&pch->downl); if (pch->file.hdrlen > ppp->file.hdrlen) ppp->file.hdrlen = pch->file.hdrlen; hdrlen = pch->file.hdrlen + 2; /* for protocol bytes */ if (hdrlen > ppp->dev->hard_header_len) ppp->dev->hard_header_len = hdrlen; list_add_tail(&pch->clist, &ppp->channels); ++ppp->n_channels; pch->ppp = ppp; refcount_inc(&ppp->file.refcnt); ppp_unlock(ppp); ret = 0; outl: write_unlock_bh(&pch->upl); out: mutex_unlock(&pn->all_ppp_mutex); return ret; } /* * Disconnect a channel from its ppp unit. */ static int ppp_disconnect_channel(struct channel *pch) { struct ppp *ppp; int err = -EINVAL; write_lock_bh(&pch->upl); ppp = pch->ppp; pch->ppp = NULL; write_unlock_bh(&pch->upl); if (ppp) { /* remove it from the ppp unit's list */ ppp_lock(ppp); list_del(&pch->clist); if (--ppp->n_channels == 0) wake_up_interruptible(&ppp->file.rwait); ppp_unlock(ppp); if (refcount_dec_and_test(&ppp->file.refcnt)) ppp_destroy_interface(ppp); err = 0; } return err; } /* * Free up the resources used by a ppp channel. */ static void ppp_destroy_channel(struct channel *pch) { put_net_track(pch->chan_net, &pch->ns_tracker); pch->chan_net = NULL; atomic_dec(&channel_count); if (!pch->file.dead) { /* "can't happen" */ pr_err("ppp: destroying undead channel %p !\n", pch); return; } skb_queue_purge(&pch->file.xq); skb_queue_purge(&pch->file.rq); kfree(pch); } static void __exit ppp_cleanup(void) { /* should never happen */ if (atomic_read(&ppp_unit_count) || atomic_read(&channel_count)) pr_err("PPP: removing module but units remain!\n"); rtnl_link_unregister(&ppp_link_ops); unregister_chrdev(PPP_MAJOR, "ppp"); device_destroy(&ppp_class, MKDEV(PPP_MAJOR, 0)); class_unregister(&ppp_class); unregister_pernet_device(&ppp_net_ops); } /* * Units handling. Caller must protect concurrent access * by holding all_ppp_mutex */ /* associate pointer with specified number */ static int unit_set(struct idr *p, void *ptr, int n) { int unit; unit = idr_alloc(p, ptr, n, n + 1, GFP_KERNEL); if (unit == -ENOSPC) unit = -EINVAL; return unit; } /* get new free unit number and associate pointer with it */ static int unit_get(struct idr *p, void *ptr, int min) { return idr_alloc(p, ptr, min, 0, GFP_KERNEL); } /* put unit number back to a pool */ static void unit_put(struct idr *p, int n) { idr_remove(p, n); } /* get pointer associated with the number */ static void *unit_find(struct idr *p, int n) { return idr_find(p, n); } /* Module/initialization stuff */ module_init(ppp_init); module_exit(ppp_cleanup); EXPORT_SYMBOL(ppp_register_net_channel); EXPORT_SYMBOL(ppp_register_channel); EXPORT_SYMBOL(ppp_unregister_channel); EXPORT_SYMBOL(ppp_channel_index); EXPORT_SYMBOL(ppp_unit_number); EXPORT_SYMBOL(ppp_dev_name); EXPORT_SYMBOL(ppp_input); EXPORT_SYMBOL(ppp_input_error); EXPORT_SYMBOL(ppp_output_wakeup); EXPORT_SYMBOL(ppp_register_compressor); EXPORT_SYMBOL(ppp_unregister_compressor); MODULE_DESCRIPTION("Generic PPP layer driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS_CHARDEV(PPP_MAJOR, 0); MODULE_ALIAS_RTNL_LINK("ppp"); MODULE_ALIAS("devname:ppp"); |
| 34 34 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 | // SPDX-License-Identifier: GPL-2.0 /* * sysctl_net_ipv6.c: sysctl interface to net IPV6 subsystem. * * Changes: * YOSHIFUJI Hideaki @USAGI: added icmp sysctl table. */ #include <linux/mm.h> #include <linux/sysctl.h> #include <linux/in6.h> #include <linux/ipv6.h> #include <linux/slab.h> #include <linux/export.h> #include <net/ndisc.h> #include <net/ipv6.h> #include <net/addrconf.h> #include <net/inet_frag.h> #include <net/netevent.h> #include <net/ip_fib.h> #ifdef CONFIG_NETLABEL #include <net/calipso.h> #endif #include <linux/ioam6.h> static int flowlabel_reflect_max = 0x7; static int auto_flowlabels_max = IP6_AUTO_FLOW_LABEL_MAX; static u32 rt6_multipath_hash_fields_all_mask = FIB_MULTIPATH_HASH_FIELD_ALL_MASK; static u32 ioam6_id_max = IOAM6_DEFAULT_ID; static u64 ioam6_id_wide_max = IOAM6_DEFAULT_ID_WIDE; static int proc_rt6_multipath_hash_policy(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net; int ret; net = container_of(table->data, struct net, ipv6.sysctl.multipath_hash_policy); ret = proc_dou8vec_minmax(table, write, buffer, lenp, ppos); if (write && ret == 0) call_netevent_notifiers(NETEVENT_IPV6_MPATH_HASH_UPDATE, net); return ret; } static int proc_rt6_multipath_hash_fields(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net; int ret; net = container_of(table->data, struct net, ipv6.sysctl.multipath_hash_fields); ret = proc_douintvec_minmax(table, write, buffer, lenp, ppos); if (write && ret == 0) call_netevent_notifiers(NETEVENT_IPV6_MPATH_HASH_UPDATE, net); return ret; } static struct ctl_table ipv6_table_template[] = { { .procname = "bindv6only", .data = &init_net.ipv6.sysctl.bindv6only, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "anycast_src_echo_reply", .data = &init_net.ipv6.sysctl.anycast_src_echo_reply, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "flowlabel_consistency", .data = &init_net.ipv6.sysctl.flowlabel_consistency, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "auto_flowlabels", .data = &init_net.ipv6.sysctl.auto_flowlabels, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra2 = &auto_flowlabels_max }, { .procname = "fwmark_reflect", .data = &init_net.ipv6.sysctl.fwmark_reflect, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "idgen_retries", .data = &init_net.ipv6.sysctl.idgen_retries, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "idgen_delay", .data = &init_net.ipv6.sysctl.idgen_delay, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "flowlabel_state_ranges", .data = &init_net.ipv6.sysctl.flowlabel_state_ranges, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "ip_nonlocal_bind", .data = &init_net.ipv6.sysctl.ip_nonlocal_bind, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, }, { .procname = "flowlabel_reflect", .data = &init_net.ipv6.sysctl.flowlabel_reflect, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = &flowlabel_reflect_max, }, { .procname = "max_dst_opts_number", .data = &init_net.ipv6.sysctl.max_dst_opts_cnt, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "max_hbh_opts_number", .data = &init_net.ipv6.sysctl.max_hbh_opts_cnt, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "max_dst_opts_length", .data = &init_net.ipv6.sysctl.max_dst_opts_len, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "max_hbh_length", .data = &init_net.ipv6.sysctl.max_hbh_opts_len, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "fib_multipath_hash_policy", .data = &init_net.ipv6.sysctl.multipath_hash_policy, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_rt6_multipath_hash_policy, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_THREE, }, { .procname = "fib_multipath_hash_fields", .data = &init_net.ipv6.sysctl.multipath_hash_fields, .maxlen = sizeof(u32), .mode = 0644, .proc_handler = proc_rt6_multipath_hash_fields, .extra1 = SYSCTL_ONE, .extra2 = &rt6_multipath_hash_fields_all_mask, }, { .procname = "seg6_flowlabel", .data = &init_net.ipv6.sysctl.seg6_flowlabel, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "fib_notify_on_flag_change", .data = &init_net.ipv6.sysctl.fib_notify_on_flag_change, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, { .procname = "ioam6_id", .data = &init_net.ipv6.sysctl.ioam6_id, .maxlen = sizeof(u32), .mode = 0644, .proc_handler = proc_douintvec_minmax, .extra2 = &ioam6_id_max, }, { .procname = "ioam6_id_wide", .data = &init_net.ipv6.sysctl.ioam6_id_wide, .maxlen = sizeof(u64), .mode = 0644, .proc_handler = proc_doulongvec_minmax, .extra2 = &ioam6_id_wide_max, }, }; static struct ctl_table ipv6_rotable[] = { { .procname = "mld_max_msf", .data = &sysctl_mld_max_msf, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, { .procname = "mld_qrv", .data = &sysctl_mld_qrv, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ONE }, #ifdef CONFIG_NETLABEL { .procname = "calipso_cache_enable", .data = &calipso_cache_enabled, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "calipso_cache_bucket_size", .data = &calipso_cache_bucketsize, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, #endif /* CONFIG_NETLABEL */ }; static int __net_init ipv6_sysctl_net_init(struct net *net) { size_t table_size = ARRAY_SIZE(ipv6_table_template); struct ctl_table *ipv6_table; struct ctl_table *ipv6_route_table; struct ctl_table *ipv6_icmp_table; int err, i; err = -ENOMEM; ipv6_table = kmemdup(ipv6_table_template, sizeof(ipv6_table_template), GFP_KERNEL); if (!ipv6_table) goto out; /* Update the variables to point into the current struct net */ for (i = 0; i < table_size; i++) ipv6_table[i].data += (void *)net - (void *)&init_net; ipv6_route_table = ipv6_route_sysctl_init(net); if (!ipv6_route_table) goto out_ipv6_table; ipv6_icmp_table = ipv6_icmp_sysctl_init(net); if (!ipv6_icmp_table) goto out_ipv6_route_table; net->ipv6.sysctl.hdr = register_net_sysctl_sz(net, "net/ipv6", ipv6_table, table_size); if (!net->ipv6.sysctl.hdr) goto out_ipv6_icmp_table; net->ipv6.sysctl.route_hdr = register_net_sysctl_sz(net, "net/ipv6/route", ipv6_route_table, ipv6_route_sysctl_table_size(net)); if (!net->ipv6.sysctl.route_hdr) goto out_unregister_ipv6_table; net->ipv6.sysctl.icmp_hdr = register_net_sysctl_sz(net, "net/ipv6/icmp", ipv6_icmp_table, ipv6_icmp_sysctl_table_size()); if (!net->ipv6.sysctl.icmp_hdr) goto out_unregister_route_table; err = 0; out: return err; out_unregister_route_table: unregister_net_sysctl_table(net->ipv6.sysctl.route_hdr); out_unregister_ipv6_table: unregister_net_sysctl_table(net->ipv6.sysctl.hdr); out_ipv6_icmp_table: kfree(ipv6_icmp_table); out_ipv6_route_table: kfree(ipv6_route_table); out_ipv6_table: kfree(ipv6_table); goto out; } static void __net_exit ipv6_sysctl_net_exit(struct net *net) { const struct ctl_table *ipv6_table; const struct ctl_table *ipv6_route_table; const struct ctl_table *ipv6_icmp_table; ipv6_table = net->ipv6.sysctl.hdr->ctl_table_arg; ipv6_route_table = net->ipv6.sysctl.route_hdr->ctl_table_arg; ipv6_icmp_table = net->ipv6.sysctl.icmp_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv6.sysctl.icmp_hdr); unregister_net_sysctl_table(net->ipv6.sysctl.route_hdr); unregister_net_sysctl_table(net->ipv6.sysctl.hdr); kfree(ipv6_table); kfree(ipv6_route_table); kfree(ipv6_icmp_table); } static struct pernet_operations ipv6_sysctl_net_ops = { .init = ipv6_sysctl_net_init, .exit = ipv6_sysctl_net_exit, }; static struct ctl_table_header *ip6_header; int ipv6_sysctl_register(void) { int err = -ENOMEM; ip6_header = register_net_sysctl(&init_net, "net/ipv6", ipv6_rotable); if (!ip6_header) goto out; err = register_pernet_subsys(&ipv6_sysctl_net_ops); if (err) goto err_pernet; out: return err; err_pernet: unregister_net_sysctl_table(ip6_header); goto out; } void ipv6_sysctl_unregister(void) { unregister_net_sysctl_table(ip6_header); unregister_pernet_subsys(&ipv6_sysctl_net_ops); } |
| 31 32 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 | // SPDX-License-Identifier: GPL-2.0-or-later /* RxRPC security handling * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/module.h> #include <linux/net.h> #include <linux/skbuff.h> #include <linux/udp.h> #include <linux/crypto.h> #include <net/sock.h> #include <net/af_rxrpc.h> #include <keys/rxrpc-type.h> #include "ar-internal.h" static const struct rxrpc_security *rxrpc_security_types[] = { [RXRPC_SECURITY_NONE] = &rxrpc_no_security, #ifdef CONFIG_RXKAD [RXRPC_SECURITY_RXKAD] = &rxkad, #endif }; int __init rxrpc_init_security(void) { int i, ret; for (i = 0; i < ARRAY_SIZE(rxrpc_security_types); i++) { if (rxrpc_security_types[i]) { ret = rxrpc_security_types[i]->init(); if (ret < 0) goto failed; } } return 0; failed: for (i--; i >= 0; i--) if (rxrpc_security_types[i]) rxrpc_security_types[i]->exit(); return ret; } void rxrpc_exit_security(void) { int i; for (i = 0; i < ARRAY_SIZE(rxrpc_security_types); i++) if (rxrpc_security_types[i]) rxrpc_security_types[i]->exit(); } /* * look up an rxrpc security module */ const struct rxrpc_security *rxrpc_security_lookup(u8 security_index) { if (security_index >= ARRAY_SIZE(rxrpc_security_types)) return NULL; return rxrpc_security_types[security_index]; } /* * Initialise the security on a client call. */ int rxrpc_init_client_call_security(struct rxrpc_call *call) { const struct rxrpc_security *sec = &rxrpc_no_security; struct rxrpc_key_token *token; struct key *key = call->key; int ret; if (!key) goto found; ret = key_validate(key); if (ret < 0) return ret; for (token = key->payload.data[0]; token; token = token->next) { sec = rxrpc_security_lookup(token->security_index); if (sec) goto found; } return -EKEYREJECTED; found: call->security = sec; call->security_ix = sec->security_index; return 0; } /* * initialise the security on a client connection */ int rxrpc_init_client_conn_security(struct rxrpc_connection *conn) { struct rxrpc_key_token *token; struct key *key = conn->key; int ret = 0; _enter("{%d},{%x}", conn->debug_id, key_serial(key)); for (token = key->payload.data[0]; token; token = token->next) { if (token->security_index == conn->security->security_index) goto found; } return -EKEYREJECTED; found: mutex_lock(&conn->security_lock); if (conn->state == RXRPC_CONN_CLIENT_UNSECURED) { ret = conn->security->init_connection_security(conn, token); if (ret == 0) { spin_lock(&conn->state_lock); if (conn->state == RXRPC_CONN_CLIENT_UNSECURED) conn->state = RXRPC_CONN_CLIENT; spin_unlock(&conn->state_lock); } } mutex_unlock(&conn->security_lock); return ret; } /* * Set the ops a server connection. */ const struct rxrpc_security *rxrpc_get_incoming_security(struct rxrpc_sock *rx, struct sk_buff *skb) { const struct rxrpc_security *sec; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); _enter(""); sec = rxrpc_security_lookup(sp->hdr.securityIndex); if (!sec) { rxrpc_direct_abort(skb, rxrpc_abort_unsupported_security, RX_INVALID_OPERATION, -EKEYREJECTED); return NULL; } if (sp->hdr.securityIndex != RXRPC_SECURITY_NONE && !rx->securities) { rxrpc_direct_abort(skb, rxrpc_abort_no_service_key, sec->no_key_abort, -EKEYREJECTED); return NULL; } return sec; } /* * Find the security key for a server connection. */ struct key *rxrpc_look_up_server_security(struct rxrpc_connection *conn, struct sk_buff *skb, u32 kvno, u32 enctype) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_sock *rx; struct key *key = ERR_PTR(-EKEYREJECTED); key_ref_t kref = NULL; char kdesc[5 + 1 + 3 + 1 + 12 + 1 + 12 + 1]; int ret; _enter(""); if (enctype) sprintf(kdesc, "%u:%u:%u:%u", sp->hdr.serviceId, sp->hdr.securityIndex, kvno, enctype); else if (kvno) sprintf(kdesc, "%u:%u:%u", sp->hdr.serviceId, sp->hdr.securityIndex, kvno); else sprintf(kdesc, "%u:%u", sp->hdr.serviceId, sp->hdr.securityIndex); read_lock(&conn->local->services_lock); rx = conn->local->service; if (!rx) goto out; /* look through the service's keyring */ kref = keyring_search(make_key_ref(rx->securities, 1UL), &key_type_rxrpc_s, kdesc, true); if (IS_ERR(kref)) { key = ERR_CAST(kref); goto out; } key = key_ref_to_ptr(kref); ret = key_validate(key); if (ret < 0) { key_put(key); key = ERR_PTR(ret); goto out; } out: read_unlock(&conn->local->services_lock); return key; } |
| 34 34 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 | /* * Mapping of UID/GIDs to name and vice versa. * * Copyright (c) 2002, 2003 The Regents of the University of * Michigan. All rights reserved. * * Marius Aamodt Eriksen <marius@umich.edu> * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the name of the University 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 ``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 REGENTS OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ #include <linux/module.h> #include <linux/seq_file.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/sunrpc/svc_xprt.h> #include <net/net_namespace.h> #include "idmap.h" #include "nfsd.h" #include "netns.h" #include "vfs.h" /* * Turn off idmapping when using AUTH_SYS. */ static bool nfs4_disable_idmapping = true; module_param(nfs4_disable_idmapping, bool, 0644); MODULE_PARM_DESC(nfs4_disable_idmapping, "Turn off server's NFSv4 idmapping when using 'sec=sys'"); /* * Cache entry */ /* * XXX we know that IDMAP_NAMESZ < PAGE_SIZE, but it's ugly to rely on * that. */ struct ent { struct cache_head h; int type; /* User / Group */ u32 id; char name[IDMAP_NAMESZ]; char authname[IDMAP_NAMESZ]; struct rcu_head rcu_head; }; /* Common entry handling */ #define ENT_HASHBITS 8 #define ENT_HASHMAX (1 << ENT_HASHBITS) static void ent_init(struct cache_head *cnew, struct cache_head *citm) { struct ent *new = container_of(cnew, struct ent, h); struct ent *itm = container_of(citm, struct ent, h); new->id = itm->id; new->type = itm->type; strscpy(new->name, itm->name, sizeof(new->name)); strscpy(new->authname, itm->authname, sizeof(new->authname)); } static void ent_put(struct kref *ref) { struct ent *map = container_of(ref, struct ent, h.ref); kfree_rcu(map, rcu_head); } static struct cache_head * ent_alloc(void) { struct ent *e = kmalloc(sizeof(*e), GFP_KERNEL); if (e) return &e->h; else return NULL; } /* * ID -> Name cache */ static uint32_t idtoname_hash(struct ent *ent) { uint32_t hash; hash = hash_str(ent->authname, ENT_HASHBITS); hash = hash_long(hash ^ ent->id, ENT_HASHBITS); /* Flip LSB for user/group */ if (ent->type == IDMAP_TYPE_GROUP) hash ^= 1; return hash; } static int idtoname_upcall(struct cache_detail *cd, struct cache_head *h) { return sunrpc_cache_pipe_upcall_timeout(cd, h); } static void idtoname_request(struct cache_detail *cd, struct cache_head *ch, char **bpp, int *blen) { struct ent *ent = container_of(ch, struct ent, h); char idstr[11]; qword_add(bpp, blen, ent->authname); snprintf(idstr, sizeof(idstr), "%u", ent->id); qword_add(bpp, blen, ent->type == IDMAP_TYPE_GROUP ? "group" : "user"); qword_add(bpp, blen, idstr); (*bpp)[-1] = '\n'; } static int idtoname_match(struct cache_head *ca, struct cache_head *cb) { struct ent *a = container_of(ca, struct ent, h); struct ent *b = container_of(cb, struct ent, h); return (a->id == b->id && a->type == b->type && strcmp(a->authname, b->authname) == 0); } static int idtoname_show(struct seq_file *m, struct cache_detail *cd, struct cache_head *h) { struct ent *ent; if (h == NULL) { seq_puts(m, "#domain type id [name]\n"); return 0; } ent = container_of(h, struct ent, h); seq_printf(m, "%s %s %u", ent->authname, ent->type == IDMAP_TYPE_GROUP ? "group" : "user", ent->id); if (test_bit(CACHE_VALID, &h->flags)) seq_printf(m, " %s", ent->name); seq_putc(m, '\n'); return 0; } static void warn_no_idmapd(struct cache_detail *detail, int has_died) { printk("nfsd: nfsv4 idmapping failing: has idmapd %s?\n", has_died ? "died" : "not been started"); } static int idtoname_parse(struct cache_detail *, char *, int); static struct ent *idtoname_lookup(struct cache_detail *, struct ent *); static struct ent *idtoname_update(struct cache_detail *, struct ent *, struct ent *); static const struct cache_detail idtoname_cache_template = { .owner = THIS_MODULE, .hash_size = ENT_HASHMAX, .name = "nfs4.idtoname", .cache_put = ent_put, .cache_upcall = idtoname_upcall, .cache_request = idtoname_request, .cache_parse = idtoname_parse, .cache_show = idtoname_show, .warn_no_listener = warn_no_idmapd, .match = idtoname_match, .init = ent_init, .update = ent_init, .alloc = ent_alloc, }; static int idtoname_parse(struct cache_detail *cd, char *buf, int buflen) { struct ent ent, *res; char *buf1, *bp; int len; int error = -EINVAL; if (buf[buflen - 1] != '\n') return (-EINVAL); buf[buflen - 1]= '\0'; buf1 = kmalloc(PAGE_SIZE, GFP_KERNEL); if (buf1 == NULL) return (-ENOMEM); memset(&ent, 0, sizeof(ent)); /* Authentication name */ len = qword_get(&buf, buf1, PAGE_SIZE); if (len <= 0 || len >= IDMAP_NAMESZ) goto out; memcpy(ent.authname, buf1, sizeof(ent.authname)); /* Type */ if (qword_get(&buf, buf1, PAGE_SIZE) <= 0) goto out; ent.type = strcmp(buf1, "user") == 0 ? IDMAP_TYPE_USER : IDMAP_TYPE_GROUP; /* ID */ if (qword_get(&buf, buf1, PAGE_SIZE) <= 0) goto out; ent.id = simple_strtoul(buf1, &bp, 10); if (bp == buf1) goto out; /* expiry */ error = get_expiry(&buf, &ent.h.expiry_time); if (error) goto out; error = -ENOMEM; res = idtoname_lookup(cd, &ent); if (!res) goto out; /* Name */ error = -EINVAL; len = qword_get(&buf, buf1, PAGE_SIZE); if (len < 0 || len >= IDMAP_NAMESZ) goto out; if (len == 0) set_bit(CACHE_NEGATIVE, &ent.h.flags); else memcpy(ent.name, buf1, sizeof(ent.name)); error = -ENOMEM; res = idtoname_update(cd, &ent, res); if (res == NULL) goto out; cache_put(&res->h, cd); error = 0; out: kfree(buf1); return error; } static struct ent * idtoname_lookup(struct cache_detail *cd, struct ent *item) { struct cache_head *ch = sunrpc_cache_lookup_rcu(cd, &item->h, idtoname_hash(item)); if (ch) return container_of(ch, struct ent, h); else return NULL; } static struct ent * idtoname_update(struct cache_detail *cd, struct ent *new, struct ent *old) { struct cache_head *ch = sunrpc_cache_update(cd, &new->h, &old->h, idtoname_hash(new)); if (ch) return container_of(ch, struct ent, h); else return NULL; } /* * Name -> ID cache */ static inline int nametoid_hash(struct ent *ent) { return hash_str(ent->name, ENT_HASHBITS); } static int nametoid_upcall(struct cache_detail *cd, struct cache_head *h) { return sunrpc_cache_pipe_upcall_timeout(cd, h); } static void nametoid_request(struct cache_detail *cd, struct cache_head *ch, char **bpp, int *blen) { struct ent *ent = container_of(ch, struct ent, h); qword_add(bpp, blen, ent->authname); qword_add(bpp, blen, ent->type == IDMAP_TYPE_GROUP ? "group" : "user"); qword_add(bpp, blen, ent->name); (*bpp)[-1] = '\n'; } static int nametoid_match(struct cache_head *ca, struct cache_head *cb) { struct ent *a = container_of(ca, struct ent, h); struct ent *b = container_of(cb, struct ent, h); return (a->type == b->type && strcmp(a->name, b->name) == 0 && strcmp(a->authname, b->authname) == 0); } static int nametoid_show(struct seq_file *m, struct cache_detail *cd, struct cache_head *h) { struct ent *ent; if (h == NULL) { seq_puts(m, "#domain type name [id]\n"); return 0; } ent = container_of(h, struct ent, h); seq_printf(m, "%s %s %s", ent->authname, ent->type == IDMAP_TYPE_GROUP ? "group" : "user", ent->name); if (test_bit(CACHE_VALID, &h->flags)) seq_printf(m, " %u", ent->id); seq_putc(m, '\n'); return 0; } static struct ent *nametoid_lookup(struct cache_detail *, struct ent *); static struct ent *nametoid_update(struct cache_detail *, struct ent *, struct ent *); static int nametoid_parse(struct cache_detail *, char *, int); static const struct cache_detail nametoid_cache_template = { .owner = THIS_MODULE, .hash_size = ENT_HASHMAX, .name = "nfs4.nametoid", .cache_put = ent_put, .cache_upcall = nametoid_upcall, .cache_request = nametoid_request, .cache_parse = nametoid_parse, .cache_show = nametoid_show, .warn_no_listener = warn_no_idmapd, .match = nametoid_match, .init = ent_init, .update = ent_init, .alloc = ent_alloc, }; static int nametoid_parse(struct cache_detail *cd, char *buf, int buflen) { struct ent ent, *res; char *buf1; int len, error = -EINVAL; if (buf[buflen - 1] != '\n') return (-EINVAL); buf[buflen - 1]= '\0'; buf1 = kmalloc(PAGE_SIZE, GFP_KERNEL); if (buf1 == NULL) return (-ENOMEM); memset(&ent, 0, sizeof(ent)); /* Authentication name */ len = qword_get(&buf, buf1, PAGE_SIZE); if (len <= 0 || len >= IDMAP_NAMESZ) goto out; memcpy(ent.authname, buf1, sizeof(ent.authname)); /* Type */ if (qword_get(&buf, buf1, PAGE_SIZE) <= 0) goto out; ent.type = strcmp(buf1, "user") == 0 ? IDMAP_TYPE_USER : IDMAP_TYPE_GROUP; /* Name */ len = qword_get(&buf, buf1, PAGE_SIZE); if (len <= 0 || len >= IDMAP_NAMESZ) goto out; memcpy(ent.name, buf1, sizeof(ent.name)); /* expiry */ error = get_expiry(&buf, &ent.h.expiry_time); if (error) goto out; /* ID */ error = get_int(&buf, &ent.id); if (error == -EINVAL) goto out; if (error == -ENOENT) set_bit(CACHE_NEGATIVE, &ent.h.flags); error = -ENOMEM; res = nametoid_lookup(cd, &ent); if (res == NULL) goto out; res = nametoid_update(cd, &ent, res); if (res == NULL) goto out; cache_put(&res->h, cd); error = 0; out: kfree(buf1); return (error); } static struct ent * nametoid_lookup(struct cache_detail *cd, struct ent *item) { struct cache_head *ch = sunrpc_cache_lookup_rcu(cd, &item->h, nametoid_hash(item)); if (ch) return container_of(ch, struct ent, h); else return NULL; } static struct ent * nametoid_update(struct cache_detail *cd, struct ent *new, struct ent *old) { struct cache_head *ch = sunrpc_cache_update(cd, &new->h, &old->h, nametoid_hash(new)); if (ch) return container_of(ch, struct ent, h); else return NULL; } /* * Exported API */ int nfsd_idmap_init(struct net *net) { int rv; struct nfsd_net *nn = net_generic(net, nfsd_net_id); nn->idtoname_cache = cache_create_net(&idtoname_cache_template, net); if (IS_ERR(nn->idtoname_cache)) return PTR_ERR(nn->idtoname_cache); rv = cache_register_net(nn->idtoname_cache, net); if (rv) goto destroy_idtoname_cache; nn->nametoid_cache = cache_create_net(&nametoid_cache_template, net); if (IS_ERR(nn->nametoid_cache)) { rv = PTR_ERR(nn->nametoid_cache); goto unregister_idtoname_cache; } rv = cache_register_net(nn->nametoid_cache, net); if (rv) goto destroy_nametoid_cache; return 0; destroy_nametoid_cache: cache_destroy_net(nn->nametoid_cache, net); unregister_idtoname_cache: cache_unregister_net(nn->idtoname_cache, net); destroy_idtoname_cache: cache_destroy_net(nn->idtoname_cache, net); return rv; } void nfsd_idmap_shutdown(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); cache_unregister_net(nn->idtoname_cache, net); cache_unregister_net(nn->nametoid_cache, net); cache_destroy_net(nn->idtoname_cache, net); cache_destroy_net(nn->nametoid_cache, net); } static int idmap_lookup(struct svc_rqst *rqstp, struct ent *(*lookup_fn)(struct cache_detail *, struct ent *), struct ent *key, struct cache_detail *detail, struct ent **item) { int ret; *item = lookup_fn(detail, key); if (!*item) return -ENOMEM; retry: ret = cache_check(detail, &(*item)->h, &rqstp->rq_chandle); if (ret == -ETIMEDOUT) { struct ent *prev_item = *item; *item = lookup_fn(detail, key); if (*item != prev_item) goto retry; cache_put(&(*item)->h, detail); } return ret; } static char * rqst_authname(struct svc_rqst *rqstp) { struct auth_domain *clp; clp = rqstp->rq_gssclient ? rqstp->rq_gssclient : rqstp->rq_client; return clp->name; } static __be32 idmap_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen, u32 *id) { struct ent *item, key = { .type = type, }; int ret; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); if (namelen + 1 > sizeof(key.name)) return nfserr_badowner; memcpy(key.name, name, namelen); key.name[namelen] = '\0'; strscpy(key.authname, rqst_authname(rqstp), sizeof(key.authname)); ret = idmap_lookup(rqstp, nametoid_lookup, &key, nn->nametoid_cache, &item); if (ret == -ENOENT) return nfserr_badowner; if (ret) return nfserrno(ret); *id = item->id; cache_put(&item->h, nn->nametoid_cache); return 0; } static __be32 encode_ascii_id(struct xdr_stream *xdr, u32 id) { char buf[11]; int len; __be32 *p; len = sprintf(buf, "%u", id); p = xdr_reserve_space(xdr, len + 4); if (!p) return nfserr_resource; p = xdr_encode_opaque(p, buf, len); return 0; } static __be32 idmap_id_to_name(struct xdr_stream *xdr, struct svc_rqst *rqstp, int type, u32 id) { struct ent *item, key = { .id = id, .type = type, }; __be32 status = nfs_ok; __be32 *p; int ret; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); strscpy(key.authname, rqst_authname(rqstp), sizeof(key.authname)); ret = idmap_lookup(rqstp, idtoname_lookup, &key, nn->idtoname_cache, &item); if (ret == -ENOENT) return encode_ascii_id(xdr, id); if (ret) return nfserrno(ret); ret = strlen(item->name); WARN_ON_ONCE(ret > IDMAP_NAMESZ); p = xdr_reserve_space(xdr, ret + 4); if (unlikely(!p)) { status = nfserr_resource; goto out_put; } xdr_encode_opaque(p, item->name, ret); out_put: cache_put(&item->h, nn->idtoname_cache); return status; } static bool numeric_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen, u32 *id) { int ret; char buf[11]; if (namelen + 1 > sizeof(buf)) /* too long to represent a 32-bit id: */ return false; /* Just to make sure it's null-terminated: */ memcpy(buf, name, namelen); buf[namelen] = '\0'; ret = kstrtouint(buf, 10, id); return ret == 0; } static __be32 do_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen, u32 *id) { if (nfs4_disable_idmapping && rqstp->rq_cred.cr_flavor < RPC_AUTH_GSS) if (numeric_name_to_id(rqstp, type, name, namelen, id)) return 0; /* * otherwise, fall through and try idmapping, for * backwards compatibility with clients sending names: */ return idmap_name_to_id(rqstp, type, name, namelen, id); } static __be32 encode_name_from_id(struct xdr_stream *xdr, struct svc_rqst *rqstp, int type, u32 id) { if (nfs4_disable_idmapping && rqstp->rq_cred.cr_flavor < RPC_AUTH_GSS) return encode_ascii_id(xdr, id); return idmap_id_to_name(xdr, rqstp, type, id); } __be32 nfsd_map_name_to_uid(struct svc_rqst *rqstp, const char *name, size_t namelen, kuid_t *uid) { __be32 status; u32 id = -1; if (name == NULL || namelen == 0) return nfserr_inval; status = do_name_to_id(rqstp, IDMAP_TYPE_USER, name, namelen, &id); *uid = make_kuid(nfsd_user_namespace(rqstp), id); if (!uid_valid(*uid)) status = nfserr_badowner; return status; } __be32 nfsd_map_name_to_gid(struct svc_rqst *rqstp, const char *name, size_t namelen, kgid_t *gid) { __be32 status; u32 id = -1; if (name == NULL || namelen == 0) return nfserr_inval; status = do_name_to_id(rqstp, IDMAP_TYPE_GROUP, name, namelen, &id); *gid = make_kgid(nfsd_user_namespace(rqstp), id); if (!gid_valid(*gid)) status = nfserr_badowner; return status; } __be32 nfsd4_encode_user(struct xdr_stream *xdr, struct svc_rqst *rqstp, kuid_t uid) { u32 id = from_kuid_munged(nfsd_user_namespace(rqstp), uid); return encode_name_from_id(xdr, rqstp, IDMAP_TYPE_USER, id); } __be32 nfsd4_encode_group(struct xdr_stream *xdr, struct svc_rqst *rqstp, kgid_t gid) { u32 id = from_kgid_munged(nfsd_user_namespace(rqstp), gid); return encode_name_from_id(xdr, rqstp, IDMAP_TYPE_GROUP, id); } |
| 48 58 54 12 55 58 58 11 2 5 5 5 4 5 5 5 10 22 9 1 1 1 1 1 8 8 7 1 8 8 8 8 8 2 8 8 8 8 5 5 5 5 5 62 14 2 6 31 8 9 6 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 | // SPDX-License-Identifier: GPL-2.0 /* * file.c - part of debugfs, a tiny little debug file system * * Copyright (C) 2004 Greg Kroah-Hartman <greg@kroah.com> * Copyright (C) 2004 IBM Inc. * * debugfs is for people to use instead of /proc or /sys. * See Documentation/filesystems/ for more details. */ #include <linux/module.h> #include <linux/fs.h> #include <linux/seq_file.h> #include <linux/pagemap.h> #include <linux/debugfs.h> #include <linux/io.h> #include <linux/slab.h> #include <linux/atomic.h> #include <linux/device.h> #include <linux/pm_runtime.h> #include <linux/poll.h> #include <linux/security.h> #include "internal.h" struct poll_table_struct; static ssize_t default_read_file(struct file *file, char __user *buf, size_t count, loff_t *ppos) { return 0; } static ssize_t default_write_file(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { return count; } const struct file_operations debugfs_noop_file_operations = { .read = default_read_file, .write = default_write_file, .open = simple_open, .llseek = noop_llseek, }; #define F_DENTRY(filp) ((filp)->f_path.dentry) const struct file_operations *debugfs_real_fops(const struct file *filp) { struct debugfs_fsdata *fsd = F_DENTRY(filp)->d_fsdata; if ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT) { /* * Urgh, we've been called w/o a protecting * debugfs_file_get(). */ WARN_ON(1); return NULL; } return fsd->real_fops; } EXPORT_SYMBOL_GPL(debugfs_real_fops); /** * debugfs_file_get - mark the beginning of file data access * @dentry: the dentry object whose data is being accessed. * * Up to a matching call to debugfs_file_put(), any successive call * into the file removing functions debugfs_remove() and * debugfs_remove_recursive() will block. Since associated private * file data may only get freed after a successful return of any of * the removal functions, you may safely access it after a successful * call to debugfs_file_get() without worrying about lifetime issues. * * If -%EIO is returned, the file has already been removed and thus, * it is not safe to access any of its data. If, on the other hand, * it is allowed to access the file data, zero is returned. */ int debugfs_file_get(struct dentry *dentry) { struct debugfs_fsdata *fsd; void *d_fsd; /* * This could only happen if some debugfs user erroneously calls * debugfs_file_get() on a dentry that isn't even a file, let * them know about it. */ if (WARN_ON(!d_is_reg(dentry))) return -EINVAL; d_fsd = READ_ONCE(dentry->d_fsdata); if (!((unsigned long)d_fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)) { fsd = d_fsd; } else { fsd = kmalloc(sizeof(*fsd), GFP_KERNEL); if (!fsd) return -ENOMEM; fsd->real_fops = (void *)((unsigned long)d_fsd & ~DEBUGFS_FSDATA_IS_REAL_FOPS_BIT); refcount_set(&fsd->active_users, 1); init_completion(&fsd->active_users_drained); INIT_LIST_HEAD(&fsd->cancellations); mutex_init(&fsd->cancellations_mtx); if (cmpxchg(&dentry->d_fsdata, d_fsd, fsd) != d_fsd) { mutex_destroy(&fsd->cancellations_mtx); kfree(fsd); fsd = READ_ONCE(dentry->d_fsdata); } } /* * In case of a successful cmpxchg() above, this check is * strictly necessary and must follow it, see the comment in * __debugfs_remove_file(). * OTOH, if the cmpxchg() hasn't been executed or wasn't * successful, this serves the purpose of not starving * removers. */ if (d_unlinked(dentry)) return -EIO; if (!refcount_inc_not_zero(&fsd->active_users)) return -EIO; return 0; } EXPORT_SYMBOL_GPL(debugfs_file_get); /** * debugfs_file_put - mark the end of file data access * @dentry: the dentry object formerly passed to * debugfs_file_get(). * * Allow any ongoing concurrent call into debugfs_remove() or * debugfs_remove_recursive() blocked by a former call to * debugfs_file_get() to proceed and return to its caller. */ void debugfs_file_put(struct dentry *dentry) { struct debugfs_fsdata *fsd = READ_ONCE(dentry->d_fsdata); if (refcount_dec_and_test(&fsd->active_users)) complete(&fsd->active_users_drained); } EXPORT_SYMBOL_GPL(debugfs_file_put); /** * debugfs_enter_cancellation - enter a debugfs cancellation * @file: the file being accessed * @cancellation: the cancellation object, the cancel callback * inside of it must be initialized * * When a debugfs file is removed it needs to wait for all active * operations to complete. However, the operation itself may need * to wait for hardware or completion of some asynchronous process * or similar. As such, it may need to be cancelled to avoid long * waits or even deadlocks. * * This function can be used inside a debugfs handler that may * need to be cancelled. As soon as this function is called, the * cancellation's 'cancel' callback may be called, at which point * the caller should proceed to call debugfs_leave_cancellation() * and leave the debugfs handler function as soon as possible. * Note that the 'cancel' callback is only ever called in the * context of some kind of debugfs_remove(). * * This function must be paired with debugfs_leave_cancellation(). */ void debugfs_enter_cancellation(struct file *file, struct debugfs_cancellation *cancellation) { struct debugfs_fsdata *fsd; struct dentry *dentry = F_DENTRY(file); INIT_LIST_HEAD(&cancellation->list); if (WARN_ON(!d_is_reg(dentry))) return; if (WARN_ON(!cancellation->cancel)) return; fsd = READ_ONCE(dentry->d_fsdata); if (WARN_ON(!fsd || ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT))) return; mutex_lock(&fsd->cancellations_mtx); list_add(&cancellation->list, &fsd->cancellations); mutex_unlock(&fsd->cancellations_mtx); /* if we're already removing wake it up to cancel */ if (d_unlinked(dentry)) complete(&fsd->active_users_drained); } EXPORT_SYMBOL_GPL(debugfs_enter_cancellation); /** * debugfs_leave_cancellation - leave cancellation section * @file: the file being accessed * @cancellation: the cancellation previously registered with * debugfs_enter_cancellation() * * See the documentation of debugfs_enter_cancellation(). */ void debugfs_leave_cancellation(struct file *file, struct debugfs_cancellation *cancellation) { struct debugfs_fsdata *fsd; struct dentry *dentry = F_DENTRY(file); if (WARN_ON(!d_is_reg(dentry))) return; fsd = READ_ONCE(dentry->d_fsdata); if (WARN_ON(!fsd || ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT))) return; mutex_lock(&fsd->cancellations_mtx); if (!list_empty(&cancellation->list)) list_del(&cancellation->list); mutex_unlock(&fsd->cancellations_mtx); } EXPORT_SYMBOL_GPL(debugfs_leave_cancellation); /* * Only permit access to world-readable files when the kernel is locked down. * We also need to exclude any file that has ways to write or alter it as root * can bypass the permissions check. */ static int debugfs_locked_down(struct inode *inode, struct file *filp, const struct file_operations *real_fops) { if ((inode->i_mode & 07777 & ~0444) == 0 && !(filp->f_mode & FMODE_WRITE) && !real_fops->unlocked_ioctl && !real_fops->compat_ioctl && !real_fops->mmap) return 0; if (security_locked_down(LOCKDOWN_DEBUGFS)) return -EPERM; return 0; } static int open_proxy_open(struct inode *inode, struct file *filp) { struct dentry *dentry = F_DENTRY(filp); const struct file_operations *real_fops = NULL; int r; r = debugfs_file_get(dentry); if (r) return r == -EIO ? -ENOENT : r; real_fops = debugfs_real_fops(filp); r = debugfs_locked_down(inode, filp, real_fops); if (r) goto out; if (!fops_get(real_fops)) { #ifdef CONFIG_MODULES if (real_fops->owner && real_fops->owner->state == MODULE_STATE_GOING) { r = -ENXIO; goto out; } #endif /* Huh? Module did not clean up after itself at exit? */ WARN(1, "debugfs file owner did not clean up at exit: %pd", dentry); r = -ENXIO; goto out; } replace_fops(filp, real_fops); if (real_fops->open) r = real_fops->open(inode, filp); out: debugfs_file_put(dentry); return r; } const struct file_operations debugfs_open_proxy_file_operations = { .open = open_proxy_open, }; #define PROTO(args...) args #define ARGS(args...) args #define FULL_PROXY_FUNC(name, ret_type, filp, proto, args) \ static ret_type full_proxy_ ## name(proto) \ { \ struct dentry *dentry = F_DENTRY(filp); \ const struct file_operations *real_fops; \ ret_type r; \ \ r = debugfs_file_get(dentry); \ if (unlikely(r)) \ return r; \ real_fops = debugfs_real_fops(filp); \ r = real_fops->name(args); \ debugfs_file_put(dentry); \ return r; \ } FULL_PROXY_FUNC(llseek, loff_t, filp, PROTO(struct file *filp, loff_t offset, int whence), ARGS(filp, offset, whence)); FULL_PROXY_FUNC(read, ssize_t, filp, PROTO(struct file *filp, char __user *buf, size_t size, loff_t *ppos), ARGS(filp, buf, size, ppos)); FULL_PROXY_FUNC(write, ssize_t, filp, PROTO(struct file *filp, const char __user *buf, size_t size, loff_t *ppos), ARGS(filp, buf, size, ppos)); FULL_PROXY_FUNC(unlocked_ioctl, long, filp, PROTO(struct file *filp, unsigned int cmd, unsigned long arg), ARGS(filp, cmd, arg)); static __poll_t full_proxy_poll(struct file *filp, struct poll_table_struct *wait) { struct dentry *dentry = F_DENTRY(filp); __poll_t r = 0; const struct file_operations *real_fops; if (debugfs_file_get(dentry)) return EPOLLHUP; real_fops = debugfs_real_fops(filp); r = real_fops->poll(filp, wait); debugfs_file_put(dentry); return r; } static int full_proxy_release(struct inode *inode, struct file *filp) { const struct dentry *dentry = F_DENTRY(filp); const struct file_operations *real_fops = debugfs_real_fops(filp); const struct file_operations *proxy_fops = filp->f_op; int r = 0; /* * We must not protect this against removal races here: the * original releaser should be called unconditionally in order * not to leak any resources. Releasers must not assume that * ->i_private is still being meaningful here. */ if (real_fops->release) r = real_fops->release(inode, filp); replace_fops(filp, d_inode(dentry)->i_fop); kfree(proxy_fops); fops_put(real_fops); return r; } static void __full_proxy_fops_init(struct file_operations *proxy_fops, const struct file_operations *real_fops) { proxy_fops->release = full_proxy_release; if (real_fops->llseek) proxy_fops->llseek = full_proxy_llseek; if (real_fops->read) proxy_fops->read = full_proxy_read; if (real_fops->write) proxy_fops->write = full_proxy_write; if (real_fops->poll) proxy_fops->poll = full_proxy_poll; if (real_fops->unlocked_ioctl) proxy_fops->unlocked_ioctl = full_proxy_unlocked_ioctl; } static int full_proxy_open(struct inode *inode, struct file *filp) { struct dentry *dentry = F_DENTRY(filp); const struct file_operations *real_fops = NULL; struct file_operations *proxy_fops = NULL; int r; r = debugfs_file_get(dentry); if (r) return r == -EIO ? -ENOENT : r; real_fops = debugfs_real_fops(filp); r = debugfs_locked_down(inode, filp, real_fops); if (r) goto out; if (!fops_get(real_fops)) { #ifdef CONFIG_MODULES if (real_fops->owner && real_fops->owner->state == MODULE_STATE_GOING) { r = -ENXIO; goto out; } #endif /* Huh? Module did not cleanup after itself at exit? */ WARN(1, "debugfs file owner did not clean up at exit: %pd", dentry); r = -ENXIO; goto out; } proxy_fops = kzalloc(sizeof(*proxy_fops), GFP_KERNEL); if (!proxy_fops) { r = -ENOMEM; goto free_proxy; } __full_proxy_fops_init(proxy_fops, real_fops); replace_fops(filp, proxy_fops); if (real_fops->open) { r = real_fops->open(inode, filp); if (r) { replace_fops(filp, d_inode(dentry)->i_fop); goto free_proxy; } else if (filp->f_op != proxy_fops) { /* No protection against file removal anymore. */ WARN(1, "debugfs file owner replaced proxy fops: %pd", dentry); goto free_proxy; } } goto out; free_proxy: kfree(proxy_fops); fops_put(real_fops); out: debugfs_file_put(dentry); return r; } const struct file_operations debugfs_full_proxy_file_operations = { .open = full_proxy_open, }; ssize_t debugfs_attr_read(struct file *file, char __user *buf, size_t len, loff_t *ppos) { struct dentry *dentry = F_DENTRY(file); ssize_t ret; ret = debugfs_file_get(dentry); if (unlikely(ret)) return ret; ret = simple_attr_read(file, buf, len, ppos); debugfs_file_put(dentry); return ret; } EXPORT_SYMBOL_GPL(debugfs_attr_read); static ssize_t debugfs_attr_write_xsigned(struct file *file, const char __user *buf, size_t len, loff_t *ppos, bool is_signed) { struct dentry *dentry = F_DENTRY(file); ssize_t ret; ret = debugfs_file_get(dentry); if (unlikely(ret)) return ret; if (is_signed) ret = simple_attr_write_signed(file, buf, len, ppos); else ret = simple_attr_write(file, buf, len, ppos); debugfs_file_put(dentry); return ret; } ssize_t debugfs_attr_write(struct file *file, const char __user *buf, size_t len, loff_t *ppos) { return debugfs_attr_write_xsigned(file, buf, len, ppos, false); } EXPORT_SYMBOL_GPL(debugfs_attr_write); ssize_t debugfs_attr_write_signed(struct file *file, const char __user *buf, size_t len, loff_t *ppos) { return debugfs_attr_write_xsigned(file, buf, len, ppos, true); } EXPORT_SYMBOL_GPL(debugfs_attr_write_signed); static struct dentry *debugfs_create_mode_unsafe(const char *name, umode_t mode, struct dentry *parent, void *value, const struct file_operations *fops, const struct file_operations *fops_ro, const struct file_operations *fops_wo) { /* if there are no write bits set, make read only */ if (!(mode & S_IWUGO)) return debugfs_create_file_unsafe(name, mode, parent, value, fops_ro); /* if there are no read bits set, make write only */ if (!(mode & S_IRUGO)) return debugfs_create_file_unsafe(name, mode, parent, value, fops_wo); return debugfs_create_file_unsafe(name, mode, parent, value, fops); } static int debugfs_u8_set(void *data, u64 val) { *(u8 *)data = val; return 0; } static int debugfs_u8_get(void *data, u64 *val) { *val = *(u8 *)data; return 0; } DEFINE_DEBUGFS_ATTRIBUTE(fops_u8, debugfs_u8_get, debugfs_u8_set, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_u8_ro, debugfs_u8_get, NULL, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_u8_wo, NULL, debugfs_u8_set, "%llu\n"); /** * debugfs_create_u8 - create a debugfs file that is used to read and write an unsigned 8-bit value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. * * This function creates a file in debugfs with the given name that * contains the value of the variable @value. If the @mode variable is so * set, it can be read from, and written to. */ void debugfs_create_u8(const char *name, umode_t mode, struct dentry *parent, u8 *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u8, &fops_u8_ro, &fops_u8_wo); } EXPORT_SYMBOL_GPL(debugfs_create_u8); static int debugfs_u16_set(void *data, u64 val) { *(u16 *)data = val; return 0; } static int debugfs_u16_get(void *data, u64 *val) { *val = *(u16 *)data; return 0; } DEFINE_DEBUGFS_ATTRIBUTE(fops_u16, debugfs_u16_get, debugfs_u16_set, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_u16_ro, debugfs_u16_get, NULL, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_u16_wo, NULL, debugfs_u16_set, "%llu\n"); /** * debugfs_create_u16 - create a debugfs file that is used to read and write an unsigned 16-bit value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. * * This function creates a file in debugfs with the given name that * contains the value of the variable @value. If the @mode variable is so * set, it can be read from, and written to. */ void debugfs_create_u16(const char *name, umode_t mode, struct dentry *parent, u16 *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u16, &fops_u16_ro, &fops_u16_wo); } EXPORT_SYMBOL_GPL(debugfs_create_u16); static int debugfs_u32_set(void *data, u64 val) { *(u32 *)data = val; return 0; } static int debugfs_u32_get(void *data, u64 *val) { *val = *(u32 *)data; return 0; } DEFINE_DEBUGFS_ATTRIBUTE(fops_u32, debugfs_u32_get, debugfs_u32_set, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_u32_ro, debugfs_u32_get, NULL, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_u32_wo, NULL, debugfs_u32_set, "%llu\n"); /** * debugfs_create_u32 - create a debugfs file that is used to read and write an unsigned 32-bit value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. * * This function creates a file in debugfs with the given name that * contains the value of the variable @value. If the @mode variable is so * set, it can be read from, and written to. */ void debugfs_create_u32(const char *name, umode_t mode, struct dentry *parent, u32 *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u32, &fops_u32_ro, &fops_u32_wo); } EXPORT_SYMBOL_GPL(debugfs_create_u32); static int debugfs_u64_set(void *data, u64 val) { *(u64 *)data = val; return 0; } static int debugfs_u64_get(void *data, u64 *val) { *val = *(u64 *)data; return 0; } DEFINE_DEBUGFS_ATTRIBUTE(fops_u64, debugfs_u64_get, debugfs_u64_set, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_u64_ro, debugfs_u64_get, NULL, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_u64_wo, NULL, debugfs_u64_set, "%llu\n"); /** * debugfs_create_u64 - create a debugfs file that is used to read and write an unsigned 64-bit value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. * * This function creates a file in debugfs with the given name that * contains the value of the variable @value. If the @mode variable is so * set, it can be read from, and written to. */ void debugfs_create_u64(const char *name, umode_t mode, struct dentry *parent, u64 *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_u64, &fops_u64_ro, &fops_u64_wo); } EXPORT_SYMBOL_GPL(debugfs_create_u64); static int debugfs_ulong_set(void *data, u64 val) { *(unsigned long *)data = val; return 0; } static int debugfs_ulong_get(void *data, u64 *val) { *val = *(unsigned long *)data; return 0; } DEFINE_DEBUGFS_ATTRIBUTE(fops_ulong, debugfs_ulong_get, debugfs_ulong_set, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_ulong_ro, debugfs_ulong_get, NULL, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_ulong_wo, NULL, debugfs_ulong_set, "%llu\n"); /** * debugfs_create_ulong - create a debugfs file that is used to read and write * an unsigned long value. * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. * * This function creates a file in debugfs with the given name that * contains the value of the variable @value. If the @mode variable is so * set, it can be read from, and written to. */ void debugfs_create_ulong(const char *name, umode_t mode, struct dentry *parent, unsigned long *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_ulong, &fops_ulong_ro, &fops_ulong_wo); } EXPORT_SYMBOL_GPL(debugfs_create_ulong); DEFINE_DEBUGFS_ATTRIBUTE(fops_x8, debugfs_u8_get, debugfs_u8_set, "0x%02llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x8_ro, debugfs_u8_get, NULL, "0x%02llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x8_wo, NULL, debugfs_u8_set, "0x%02llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x16, debugfs_u16_get, debugfs_u16_set, "0x%04llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x16_ro, debugfs_u16_get, NULL, "0x%04llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x16_wo, NULL, debugfs_u16_set, "0x%04llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x32, debugfs_u32_get, debugfs_u32_set, "0x%08llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x32_ro, debugfs_u32_get, NULL, "0x%08llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x32_wo, NULL, debugfs_u32_set, "0x%08llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x64, debugfs_u64_get, debugfs_u64_set, "0x%016llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x64_ro, debugfs_u64_get, NULL, "0x%016llx\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_x64_wo, NULL, debugfs_u64_set, "0x%016llx\n"); /* * debugfs_create_x{8,16,32,64} - create a debugfs file that is used to read and write an unsigned {8,16,32,64}-bit value * * These functions are exactly the same as the above functions (but use a hex * output for the decimal challenged). For details look at the above unsigned * decimal functions. */ /** * debugfs_create_x8 - create a debugfs file that is used to read and write an unsigned 8-bit value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. */ void debugfs_create_x8(const char *name, umode_t mode, struct dentry *parent, u8 *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_x8, &fops_x8_ro, &fops_x8_wo); } EXPORT_SYMBOL_GPL(debugfs_create_x8); /** * debugfs_create_x16 - create a debugfs file that is used to read and write an unsigned 16-bit value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. */ void debugfs_create_x16(const char *name, umode_t mode, struct dentry *parent, u16 *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_x16, &fops_x16_ro, &fops_x16_wo); } EXPORT_SYMBOL_GPL(debugfs_create_x16); /** * debugfs_create_x32 - create a debugfs file that is used to read and write an unsigned 32-bit value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. */ void debugfs_create_x32(const char *name, umode_t mode, struct dentry *parent, u32 *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_x32, &fops_x32_ro, &fops_x32_wo); } EXPORT_SYMBOL_GPL(debugfs_create_x32); /** * debugfs_create_x64 - create a debugfs file that is used to read and write an unsigned 64-bit value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. */ void debugfs_create_x64(const char *name, umode_t mode, struct dentry *parent, u64 *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_x64, &fops_x64_ro, &fops_x64_wo); } EXPORT_SYMBOL_GPL(debugfs_create_x64); static int debugfs_size_t_set(void *data, u64 val) { *(size_t *)data = val; return 0; } static int debugfs_size_t_get(void *data, u64 *val) { *val = *(size_t *)data; return 0; } DEFINE_DEBUGFS_ATTRIBUTE(fops_size_t, debugfs_size_t_get, debugfs_size_t_set, "%llu\n"); /* %llu and %zu are more or less the same */ DEFINE_DEBUGFS_ATTRIBUTE(fops_size_t_ro, debugfs_size_t_get, NULL, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_size_t_wo, NULL, debugfs_size_t_set, "%llu\n"); /** * debugfs_create_size_t - create a debugfs file that is used to read and write an size_t value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. */ void debugfs_create_size_t(const char *name, umode_t mode, struct dentry *parent, size_t *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_size_t, &fops_size_t_ro, &fops_size_t_wo); } EXPORT_SYMBOL_GPL(debugfs_create_size_t); static int debugfs_atomic_t_set(void *data, u64 val) { atomic_set((atomic_t *)data, val); return 0; } static int debugfs_atomic_t_get(void *data, u64 *val) { *val = atomic_read((atomic_t *)data); return 0; } DEFINE_DEBUGFS_ATTRIBUTE_SIGNED(fops_atomic_t, debugfs_atomic_t_get, debugfs_atomic_t_set, "%lld\n"); DEFINE_DEBUGFS_ATTRIBUTE_SIGNED(fops_atomic_t_ro, debugfs_atomic_t_get, NULL, "%lld\n"); DEFINE_DEBUGFS_ATTRIBUTE_SIGNED(fops_atomic_t_wo, NULL, debugfs_atomic_t_set, "%lld\n"); /** * debugfs_create_atomic_t - create a debugfs file that is used to read and * write an atomic_t value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. */ void debugfs_create_atomic_t(const char *name, umode_t mode, struct dentry *parent, atomic_t *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_atomic_t, &fops_atomic_t_ro, &fops_atomic_t_wo); } EXPORT_SYMBOL_GPL(debugfs_create_atomic_t); ssize_t debugfs_read_file_bool(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { char buf[2]; bool val; int r; struct dentry *dentry = F_DENTRY(file); r = debugfs_file_get(dentry); if (unlikely(r)) return r; val = *(bool *)file->private_data; debugfs_file_put(dentry); if (val) buf[0] = 'Y'; else buf[0] = 'N'; buf[1] = '\n'; return simple_read_from_buffer(user_buf, count, ppos, buf, 2); } EXPORT_SYMBOL_GPL(debugfs_read_file_bool); ssize_t debugfs_write_file_bool(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { bool bv; int r; bool *val = file->private_data; struct dentry *dentry = F_DENTRY(file); r = kstrtobool_from_user(user_buf, count, &bv); if (!r) { r = debugfs_file_get(dentry); if (unlikely(r)) return r; *val = bv; debugfs_file_put(dentry); } return count; } EXPORT_SYMBOL_GPL(debugfs_write_file_bool); static const struct file_operations fops_bool = { .read = debugfs_read_file_bool, .write = debugfs_write_file_bool, .open = simple_open, .llseek = default_llseek, }; static const struct file_operations fops_bool_ro = { .read = debugfs_read_file_bool, .open = simple_open, .llseek = default_llseek, }; static const struct file_operations fops_bool_wo = { .write = debugfs_write_file_bool, .open = simple_open, .llseek = default_llseek, }; /** * debugfs_create_bool - create a debugfs file that is used to read and write a boolean value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. * * This function creates a file in debugfs with the given name that * contains the value of the variable @value. If the @mode variable is so * set, it can be read from, and written to. */ void debugfs_create_bool(const char *name, umode_t mode, struct dentry *parent, bool *value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_bool, &fops_bool_ro, &fops_bool_wo); } EXPORT_SYMBOL_GPL(debugfs_create_bool); ssize_t debugfs_read_file_str(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { struct dentry *dentry = F_DENTRY(file); char *str, *copy = NULL; int copy_len, len; ssize_t ret; ret = debugfs_file_get(dentry); if (unlikely(ret)) return ret; str = *(char **)file->private_data; len = strlen(str) + 1; copy = kmalloc(len, GFP_KERNEL); if (!copy) { debugfs_file_put(dentry); return -ENOMEM; } copy_len = strscpy(copy, str, len); debugfs_file_put(dentry); if (copy_len < 0) { kfree(copy); return copy_len; } copy[copy_len] = '\n'; ret = simple_read_from_buffer(user_buf, count, ppos, copy, len); kfree(copy); return ret; } EXPORT_SYMBOL_GPL(debugfs_create_str); static ssize_t debugfs_write_file_str(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { struct dentry *dentry = F_DENTRY(file); char *old, *new = NULL; int pos = *ppos; int r; r = debugfs_file_get(dentry); if (unlikely(r)) return r; old = *(char **)file->private_data; /* only allow strict concatenation */ r = -EINVAL; if (pos && pos != strlen(old)) goto error; r = -E2BIG; if (pos + count + 1 > PAGE_SIZE) goto error; r = -ENOMEM; new = kmalloc(pos + count + 1, GFP_KERNEL); if (!new) goto error; if (pos) memcpy(new, old, pos); r = -EFAULT; if (copy_from_user(new + pos, user_buf, count)) goto error; new[pos + count] = '\0'; strim(new); rcu_assign_pointer(*(char __rcu **)file->private_data, new); synchronize_rcu(); kfree(old); debugfs_file_put(dentry); return count; error: kfree(new); debugfs_file_put(dentry); return r; } static const struct file_operations fops_str = { .read = debugfs_read_file_str, .write = debugfs_write_file_str, .open = simple_open, .llseek = default_llseek, }; static const struct file_operations fops_str_ro = { .read = debugfs_read_file_str, .open = simple_open, .llseek = default_llseek, }; static const struct file_operations fops_str_wo = { .write = debugfs_write_file_str, .open = simple_open, .llseek = default_llseek, }; /** * debugfs_create_str - create a debugfs file that is used to read and write a string value * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @value: a pointer to the variable that the file should read to and write * from. * * This function creates a file in debugfs with the given name that * contains the value of the variable @value. If the @mode variable is so * set, it can be read from, and written to. */ void debugfs_create_str(const char *name, umode_t mode, struct dentry *parent, char **value) { debugfs_create_mode_unsafe(name, mode, parent, value, &fops_str, &fops_str_ro, &fops_str_wo); } static ssize_t read_file_blob(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { struct debugfs_blob_wrapper *blob = file->private_data; struct dentry *dentry = F_DENTRY(file); ssize_t r; r = debugfs_file_get(dentry); if (unlikely(r)) return r; r = simple_read_from_buffer(user_buf, count, ppos, blob->data, blob->size); debugfs_file_put(dentry); return r; } static ssize_t write_file_blob(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { struct debugfs_blob_wrapper *blob = file->private_data; struct dentry *dentry = F_DENTRY(file); ssize_t r; r = debugfs_file_get(dentry); if (unlikely(r)) return r; r = simple_write_to_buffer(blob->data, blob->size, ppos, user_buf, count); debugfs_file_put(dentry); return r; } static const struct file_operations fops_blob = { .read = read_file_blob, .write = write_file_blob, .open = simple_open, .llseek = default_llseek, }; /** * debugfs_create_blob - create a debugfs file that is used to read and write * a binary blob * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @blob: a pointer to a struct debugfs_blob_wrapper which contains a pointer * to the blob data and the size of the data. * * This function creates a file in debugfs with the given name that exports * @blob->data as a binary blob. If the @mode variable is so set it can be * read from and written to. * * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, * you are responsible here.) If an error occurs, ERR_PTR(-ERROR) will be * returned. * * If debugfs is not enabled in the kernel, the value ERR_PTR(-ENODEV) will * be returned. */ struct dentry *debugfs_create_blob(const char *name, umode_t mode, struct dentry *parent, struct debugfs_blob_wrapper *blob) { return debugfs_create_file_unsafe(name, mode & 0644, parent, blob, &fops_blob); } EXPORT_SYMBOL_GPL(debugfs_create_blob); static size_t u32_format_array(char *buf, size_t bufsize, u32 *array, int array_size) { size_t ret = 0; while (--array_size >= 0) { size_t len; char term = array_size ? ' ' : '\n'; len = snprintf(buf, bufsize, "%u%c", *array++, term); ret += len; buf += len; bufsize -= len; } return ret; } static int u32_array_open(struct inode *inode, struct file *file) { struct debugfs_u32_array *data = inode->i_private; int size, elements = data->n_elements; char *buf; /* * Max size: * - 10 digits + ' '/'\n' = 11 bytes per number * - terminating NUL character */ size = elements*11; buf = kmalloc(size+1, GFP_KERNEL); if (!buf) return -ENOMEM; buf[size] = 0; file->private_data = buf; u32_format_array(buf, size, data->array, data->n_elements); return nonseekable_open(inode, file); } static ssize_t u32_array_read(struct file *file, char __user *buf, size_t len, loff_t *ppos) { size_t size = strlen(file->private_data); return simple_read_from_buffer(buf, len, ppos, file->private_data, size); } static int u32_array_release(struct inode *inode, struct file *file) { kfree(file->private_data); return 0; } static const struct file_operations u32_array_fops = { .owner = THIS_MODULE, .open = u32_array_open, .release = u32_array_release, .read = u32_array_read, }; /** * debugfs_create_u32_array - create a debugfs file that is used to read u32 * array. * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have. * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @array: wrapper struct containing data pointer and size of the array. * * This function creates a file in debugfs with the given name that exports * @array as data. If the @mode variable is so set it can be read from. * Writing is not supported. Seek within the file is also not supported. * Once array is created its size can not be changed. */ void debugfs_create_u32_array(const char *name, umode_t mode, struct dentry *parent, struct debugfs_u32_array *array) { debugfs_create_file_unsafe(name, mode, parent, array, &u32_array_fops); } EXPORT_SYMBOL_GPL(debugfs_create_u32_array); #ifdef CONFIG_HAS_IOMEM /* * The regset32 stuff is used to print 32-bit registers using the * seq_file utilities. We offer printing a register set in an already-opened * sequential file or create a debugfs file that only prints a regset32. */ /** * debugfs_print_regs32 - use seq_print to describe a set of registers * @s: the seq_file structure being used to generate output * @regs: an array if struct debugfs_reg32 structures * @nregs: the length of the above array * @base: the base address to be used in reading the registers * @prefix: a string to be prefixed to every output line * * This function outputs a text block describing the current values of * some 32-bit hardware registers. It is meant to be used within debugfs * files based on seq_file that need to show registers, intermixed with other * information. The prefix argument may be used to specify a leading string, * because some peripherals have several blocks of identical registers, * for example configuration of dma channels */ void debugfs_print_regs32(struct seq_file *s, const struct debugfs_reg32 *regs, int nregs, void __iomem *base, char *prefix) { int i; for (i = 0; i < nregs; i++, regs++) { if (prefix) seq_printf(s, "%s", prefix); seq_printf(s, "%s = 0x%08x\n", regs->name, readl(base + regs->offset)); if (seq_has_overflowed(s)) break; } } EXPORT_SYMBOL_GPL(debugfs_print_regs32); static int debugfs_regset32_show(struct seq_file *s, void *data) { struct debugfs_regset32 *regset = s->private; if (regset->dev) pm_runtime_get_sync(regset->dev); debugfs_print_regs32(s, regset->regs, regset->nregs, regset->base, ""); if (regset->dev) pm_runtime_put(regset->dev); return 0; } DEFINE_SHOW_ATTRIBUTE(debugfs_regset32); /** * debugfs_create_regset32 - create a debugfs file that returns register values * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @regset: a pointer to a struct debugfs_regset32, which contains a pointer * to an array of register definitions, the array size and the base * address where the register bank is to be found. * * This function creates a file in debugfs with the given name that reports * the names and values of a set of 32-bit registers. If the @mode variable * is so set it can be read from. Writing is not supported. */ void debugfs_create_regset32(const char *name, umode_t mode, struct dentry *parent, struct debugfs_regset32 *regset) { debugfs_create_file(name, mode, parent, regset, &debugfs_regset32_fops); } EXPORT_SYMBOL_GPL(debugfs_create_regset32); #endif /* CONFIG_HAS_IOMEM */ struct debugfs_devm_entry { int (*read)(struct seq_file *seq, void *data); struct device *dev; }; static int debugfs_devm_entry_open(struct inode *inode, struct file *f) { struct debugfs_devm_entry *entry = inode->i_private; return single_open(f, entry->read, entry->dev); } static const struct file_operations debugfs_devm_entry_ops = { .owner = THIS_MODULE, .open = debugfs_devm_entry_open, .release = single_release, .read = seq_read, .llseek = seq_lseek }; /** * debugfs_create_devm_seqfile - create a debugfs file that is bound to device. * * @dev: device related to this debugfs file. * @name: name of the debugfs file. * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is %NULL, then the * file will be created in the root of the debugfs filesystem. * @read_fn: function pointer called to print the seq_file content. */ void debugfs_create_devm_seqfile(struct device *dev, const char *name, struct dentry *parent, int (*read_fn)(struct seq_file *s, void *data)) { struct debugfs_devm_entry *entry; if (IS_ERR(parent)) return; entry = devm_kzalloc(dev, sizeof(*entry), GFP_KERNEL); if (!entry) return; entry->read = read_fn; entry->dev = dev; debugfs_create_file(name, S_IRUGO, parent, entry, &debugfs_devm_entry_ops); } EXPORT_SYMBOL_GPL(debugfs_create_devm_seqfile); |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright 2019, 2020 Amazon.com, Inc. or its affiliates. All rights reserved. * * User extended attribute client side cache functions. * * Author: Frank van der Linden <fllinden@amazon.com> */ #include <linux/errno.h> #include <linux/nfs_fs.h> #include <linux/hashtable.h> #include <linux/refcount.h> #include <uapi/linux/xattr.h> #include "nfs4_fs.h" #include "internal.h" /* * User extended attributes client side caching is implemented by having * a cache structure attached to NFS inodes. This structure is allocated * when needed, and freed when the cache is zapped. * * The cache structure contains as hash table of entries, and a pointer * to a special-cased entry for the listxattr cache. * * Accessing and allocating / freeing the caches is done via reference * counting. The cache entries use a similar refcounting scheme. * * This makes freeing a cache, both from the shrinker and from the * zap cache path, easy. It also means that, in current use cases, * the large majority of inodes will not waste any memory, as they * will never have any user extended attributes assigned to them. * * Attribute entries are hashed in to a simple hash table. They are * also part of an LRU. * * There are three shrinkers. * * Two shrinkers deal with the cache entries themselves: one for * large entries (> PAGE_SIZE), and one for smaller entries. The * shrinker for the larger entries works more aggressively than * those for the smaller entries. * * The other shrinker frees the cache structures themselves. */ /* * 64 buckets is a good default. There is likely no reasonable * workload that uses more than even 64 user extended attributes. * You can certainly add a lot more - but you get what you ask for * in those circumstances. */ #define NFS4_XATTR_HASH_SIZE 64 #define NFSDBG_FACILITY NFSDBG_XATTRCACHE struct nfs4_xattr_cache; struct nfs4_xattr_entry; struct nfs4_xattr_bucket { spinlock_t lock; struct hlist_head hlist; struct nfs4_xattr_cache *cache; bool draining; }; struct nfs4_xattr_cache { struct kref ref; struct nfs4_xattr_bucket buckets[NFS4_XATTR_HASH_SIZE]; struct list_head lru; struct list_head dispose; atomic_long_t nent; spinlock_t listxattr_lock; struct inode *inode; struct nfs4_xattr_entry *listxattr; }; struct nfs4_xattr_entry { struct kref ref; struct hlist_node hnode; struct list_head lru; struct list_head dispose; char *xattr_name; void *xattr_value; size_t xattr_size; struct nfs4_xattr_bucket *bucket; uint32_t flags; }; #define NFS4_XATTR_ENTRY_EXTVAL 0x0001 /* * LRU list of NFS inodes that have xattr caches. */ static struct list_lru nfs4_xattr_cache_lru; static struct list_lru nfs4_xattr_entry_lru; static struct list_lru nfs4_xattr_large_entry_lru; static struct kmem_cache *nfs4_xattr_cache_cachep; /* * Hashing helper functions. */ static void nfs4_xattr_hash_init(struct nfs4_xattr_cache *cache) { unsigned int i; for (i = 0; i < NFS4_XATTR_HASH_SIZE; i++) { INIT_HLIST_HEAD(&cache->buckets[i].hlist); spin_lock_init(&cache->buckets[i].lock); cache->buckets[i].cache = cache; cache->buckets[i].draining = false; } } /* * Locking order: * 1. inode i_lock or bucket lock * 2. list_lru lock (taken by list_lru_* functions) */ /* * Wrapper functions to add a cache entry to the right LRU. */ static bool nfs4_xattr_entry_lru_add(struct nfs4_xattr_entry *entry) { struct list_lru *lru; lru = (entry->flags & NFS4_XATTR_ENTRY_EXTVAL) ? &nfs4_xattr_large_entry_lru : &nfs4_xattr_entry_lru; return list_lru_add_obj(lru, &entry->lru); } static bool nfs4_xattr_entry_lru_del(struct nfs4_xattr_entry *entry) { struct list_lru *lru; lru = (entry->flags & NFS4_XATTR_ENTRY_EXTVAL) ? &nfs4_xattr_large_entry_lru : &nfs4_xattr_entry_lru; return list_lru_del_obj(lru, &entry->lru); } /* * This function allocates cache entries. They are the normal * extended attribute name/value pairs, but may also be a listxattr * cache. Those allocations use the same entry so that they can be * treated as one by the memory shrinker. * * xattr cache entries are allocated together with names. If the * value fits in to one page with the entry structure and the name, * it will also be part of the same allocation (kmalloc). This is * expected to be the vast majority of cases. Larger allocations * have a value pointer that is allocated separately by kvmalloc. * * Parameters: * * @name: Name of the extended attribute. NULL for listxattr cache * entry. * @value: Value of attribute, or listxattr cache. NULL if the * value is to be copied from pages instead. * @pages: Pages to copy the value from, if not NULL. Passed in to * make it easier to copy the value after an RPC, even if * the value will not be passed up to application (e.g. * for a 'query' getxattr with NULL buffer). * @len: Length of the value. Can be 0 for zero-length attributes. * @value and @pages will be NULL if @len is 0. */ static struct nfs4_xattr_entry * nfs4_xattr_alloc_entry(const char *name, const void *value, struct page **pages, size_t len) { struct nfs4_xattr_entry *entry; void *valp; char *namep; size_t alloclen, slen; char *buf; uint32_t flags; BUILD_BUG_ON(sizeof(struct nfs4_xattr_entry) + XATTR_NAME_MAX + 1 > PAGE_SIZE); alloclen = sizeof(struct nfs4_xattr_entry); if (name != NULL) { slen = strlen(name) + 1; alloclen += slen; } else slen = 0; if (alloclen + len <= PAGE_SIZE) { alloclen += len; flags = 0; } else { flags = NFS4_XATTR_ENTRY_EXTVAL; } buf = kmalloc(alloclen, GFP_KERNEL); if (buf == NULL) return NULL; entry = (struct nfs4_xattr_entry *)buf; if (name != NULL) { namep = buf + sizeof(struct nfs4_xattr_entry); memcpy(namep, name, slen); } else { namep = NULL; } if (flags & NFS4_XATTR_ENTRY_EXTVAL) { valp = kvmalloc(len, GFP_KERNEL); if (valp == NULL) { kfree(buf); return NULL; } } else if (len != 0) { valp = buf + sizeof(struct nfs4_xattr_entry) + slen; } else valp = NULL; if (valp != NULL) { if (value != NULL) memcpy(valp, value, len); else _copy_from_pages(valp, pages, 0, len); } entry->flags = flags; entry->xattr_value = valp; kref_init(&entry->ref); entry->xattr_name = namep; entry->xattr_size = len; entry->bucket = NULL; INIT_LIST_HEAD(&entry->lru); INIT_LIST_HEAD(&entry->dispose); INIT_HLIST_NODE(&entry->hnode); return entry; } static void nfs4_xattr_free_entry(struct nfs4_xattr_entry *entry) { if (entry->flags & NFS4_XATTR_ENTRY_EXTVAL) kvfree(entry->xattr_value); kfree(entry); } static void nfs4_xattr_free_entry_cb(struct kref *kref) { struct nfs4_xattr_entry *entry; entry = container_of(kref, struct nfs4_xattr_entry, ref); if (WARN_ON(!list_empty(&entry->lru))) return; nfs4_xattr_free_entry(entry); } static void nfs4_xattr_free_cache_cb(struct kref *kref) { struct nfs4_xattr_cache *cache; int i; cache = container_of(kref, struct nfs4_xattr_cache, ref); for (i = 0; i < NFS4_XATTR_HASH_SIZE; i++) { if (WARN_ON(!hlist_empty(&cache->buckets[i].hlist))) return; cache->buckets[i].draining = false; } cache->listxattr = NULL; kmem_cache_free(nfs4_xattr_cache_cachep, cache); } static struct nfs4_xattr_cache * nfs4_xattr_alloc_cache(void) { struct nfs4_xattr_cache *cache; cache = kmem_cache_alloc(nfs4_xattr_cache_cachep, GFP_KERNEL); if (cache == NULL) return NULL; kref_init(&cache->ref); atomic_long_set(&cache->nent, 0); return cache; } /* * Set the listxattr cache, which is a special-cased cache entry. * The special value ERR_PTR(-ESTALE) is used to indicate that * the cache is being drained - this prevents a new listxattr * cache from being added to what is now a stale cache. */ static int nfs4_xattr_set_listcache(struct nfs4_xattr_cache *cache, struct nfs4_xattr_entry *new) { struct nfs4_xattr_entry *old; int ret = 1; spin_lock(&cache->listxattr_lock); old = cache->listxattr; if (old == ERR_PTR(-ESTALE)) { ret = 0; goto out; } cache->listxattr = new; if (new != NULL && new != ERR_PTR(-ESTALE)) nfs4_xattr_entry_lru_add(new); if (old != NULL) { nfs4_xattr_entry_lru_del(old); kref_put(&old->ref, nfs4_xattr_free_entry_cb); } out: spin_unlock(&cache->listxattr_lock); return ret; } /* * Unlink a cache from its parent inode, clearing out an invalid * cache. Must be called with i_lock held. */ static struct nfs4_xattr_cache * nfs4_xattr_cache_unlink(struct inode *inode) { struct nfs_inode *nfsi; struct nfs4_xattr_cache *oldcache; nfsi = NFS_I(inode); oldcache = nfsi->xattr_cache; if (oldcache != NULL) { list_lru_del_obj(&nfs4_xattr_cache_lru, &oldcache->lru); oldcache->inode = NULL; } nfsi->xattr_cache = NULL; nfsi->cache_validity &= ~NFS_INO_INVALID_XATTR; return oldcache; } /* * Discard a cache. Called by get_cache() if there was an old, * invalid cache. Can also be called from a shrinker callback. * * The cache is dead, it has already been unlinked from its inode, * and no longer appears on the cache LRU list. * * Mark all buckets as draining, so that no new entries are added. This * could still happen in the unlikely, but possible case that another * thread had grabbed a reference before it was unlinked from the inode, * and is still holding it for an add operation. * * Remove all entries from the LRU lists, so that there is no longer * any way to 'find' this cache. Then, remove the entries from the hash * table. * * At that point, the cache will remain empty and can be freed when the final * reference drops, which is very likely the kref_put at the end of * this function, or the one called immediately afterwards in the * shrinker callback. */ static void nfs4_xattr_discard_cache(struct nfs4_xattr_cache *cache) { unsigned int i; struct nfs4_xattr_entry *entry; struct nfs4_xattr_bucket *bucket; struct hlist_node *n; nfs4_xattr_set_listcache(cache, ERR_PTR(-ESTALE)); for (i = 0; i < NFS4_XATTR_HASH_SIZE; i++) { bucket = &cache->buckets[i]; spin_lock(&bucket->lock); bucket->draining = true; hlist_for_each_entry_safe(entry, n, &bucket->hlist, hnode) { nfs4_xattr_entry_lru_del(entry); hlist_del_init(&entry->hnode); kref_put(&entry->ref, nfs4_xattr_free_entry_cb); } spin_unlock(&bucket->lock); } atomic_long_set(&cache->nent, 0); kref_put(&cache->ref, nfs4_xattr_free_cache_cb); } /* * Get a referenced copy of the cache structure. Avoid doing allocs * while holding i_lock. Which means that we do some optimistic allocation, * and might have to free the result in rare cases. * * This function only checks the NFS_INO_INVALID_XATTR cache validity bit * and acts accordingly, replacing the cache when needed. For the read case * (!add), this means that the caller must make sure that the cache * is valid before caling this function. getxattr and listxattr call * revalidate_inode to do this. The attribute cache timeout (for the * non-delegated case) is expected to be dealt with in the revalidate * call. */ static struct nfs4_xattr_cache * nfs4_xattr_get_cache(struct inode *inode, int add) { struct nfs_inode *nfsi; struct nfs4_xattr_cache *cache, *oldcache, *newcache; nfsi = NFS_I(inode); cache = oldcache = NULL; spin_lock(&inode->i_lock); if (nfsi->cache_validity & NFS_INO_INVALID_XATTR) oldcache = nfs4_xattr_cache_unlink(inode); else cache = nfsi->xattr_cache; if (cache != NULL) kref_get(&cache->ref); spin_unlock(&inode->i_lock); if (add && cache == NULL) { newcache = NULL; cache = nfs4_xattr_alloc_cache(); if (cache == NULL) goto out; spin_lock(&inode->i_lock); if (nfsi->cache_validity & NFS_INO_INVALID_XATTR) { /* * The cache was invalidated again. Give up, * since what we want to enter is now likely * outdated anyway. */ spin_unlock(&inode->i_lock); kref_put(&cache->ref, nfs4_xattr_free_cache_cb); cache = NULL; goto out; } /* * Check if someone beat us to it. */ if (nfsi->xattr_cache != NULL) { newcache = nfsi->xattr_cache; kref_get(&newcache->ref); } else { kref_get(&cache->ref); nfsi->xattr_cache = cache; cache->inode = inode; list_lru_add_obj(&nfs4_xattr_cache_lru, &cache->lru); } spin_unlock(&inode->i_lock); /* * If there was a race, throw away the cache we just * allocated, and use the new one allocated by someone * else. */ if (newcache != NULL) { kref_put(&cache->ref, nfs4_xattr_free_cache_cb); cache = newcache; } } out: /* * Discard the now orphaned old cache. */ if (oldcache != NULL) nfs4_xattr_discard_cache(oldcache); return cache; } static inline struct nfs4_xattr_bucket * nfs4_xattr_hash_bucket(struct nfs4_xattr_cache *cache, const char *name) { return &cache->buckets[jhash(name, strlen(name), 0) & (ARRAY_SIZE(cache->buckets) - 1)]; } static struct nfs4_xattr_entry * nfs4_xattr_get_entry(struct nfs4_xattr_bucket *bucket, const char *name) { struct nfs4_xattr_entry *entry; entry = NULL; hlist_for_each_entry(entry, &bucket->hlist, hnode) { if (!strcmp(entry->xattr_name, name)) break; } return entry; } static int nfs4_xattr_hash_add(struct nfs4_xattr_cache *cache, struct nfs4_xattr_entry *entry) { struct nfs4_xattr_bucket *bucket; struct nfs4_xattr_entry *oldentry = NULL; int ret = 1; bucket = nfs4_xattr_hash_bucket(cache, entry->xattr_name); entry->bucket = bucket; spin_lock(&bucket->lock); if (bucket->draining) { ret = 0; goto out; } oldentry = nfs4_xattr_get_entry(bucket, entry->xattr_name); if (oldentry != NULL) { hlist_del_init(&oldentry->hnode); nfs4_xattr_entry_lru_del(oldentry); } else { atomic_long_inc(&cache->nent); } hlist_add_head(&entry->hnode, &bucket->hlist); nfs4_xattr_entry_lru_add(entry); out: spin_unlock(&bucket->lock); if (oldentry != NULL) kref_put(&oldentry->ref, nfs4_xattr_free_entry_cb); return ret; } static void nfs4_xattr_hash_remove(struct nfs4_xattr_cache *cache, const char *name) { struct nfs4_xattr_bucket *bucket; struct nfs4_xattr_entry *entry; bucket = nfs4_xattr_hash_bucket(cache, name); spin_lock(&bucket->lock); entry = nfs4_xattr_get_entry(bucket, name); if (entry != NULL) { hlist_del_init(&entry->hnode); nfs4_xattr_entry_lru_del(entry); atomic_long_dec(&cache->nent); } spin_unlock(&bucket->lock); if (entry != NULL) kref_put(&entry->ref, nfs4_xattr_free_entry_cb); } static struct nfs4_xattr_entry * nfs4_xattr_hash_find(struct nfs4_xattr_cache *cache, const char *name) { struct nfs4_xattr_bucket *bucket; struct nfs4_xattr_entry *entry; bucket = nfs4_xattr_hash_bucket(cache, name); spin_lock(&bucket->lock); entry = nfs4_xattr_get_entry(bucket, name); if (entry != NULL) kref_get(&entry->ref); spin_unlock(&bucket->lock); return entry; } /* * Entry point to retrieve an entry from the cache. */ ssize_t nfs4_xattr_cache_get(struct inode *inode, const char *name, char *buf, ssize_t buflen) { struct nfs4_xattr_cache *cache; struct nfs4_xattr_entry *entry; ssize_t ret; cache = nfs4_xattr_get_cache(inode, 0); if (cache == NULL) return -ENOENT; ret = 0; entry = nfs4_xattr_hash_find(cache, name); if (entry != NULL) { dprintk("%s: cache hit '%s', len %lu\n", __func__, entry->xattr_name, (unsigned long)entry->xattr_size); if (buflen == 0) { /* Length probe only */ ret = entry->xattr_size; } else if (buflen < entry->xattr_size) ret = -ERANGE; else { memcpy(buf, entry->xattr_value, entry->xattr_size); ret = entry->xattr_size; } kref_put(&entry->ref, nfs4_xattr_free_entry_cb); } else { dprintk("%s: cache miss '%s'\n", __func__, name); ret = -ENOENT; } kref_put(&cache->ref, nfs4_xattr_free_cache_cb); return ret; } /* * Retrieve a cached list of xattrs from the cache. */ ssize_t nfs4_xattr_cache_list(struct inode *inode, char *buf, ssize_t buflen) { struct nfs4_xattr_cache *cache; struct nfs4_xattr_entry *entry; ssize_t ret; cache = nfs4_xattr_get_cache(inode, 0); if (cache == NULL) return -ENOENT; spin_lock(&cache->listxattr_lock); entry = cache->listxattr; if (entry != NULL && entry != ERR_PTR(-ESTALE)) { if (buflen == 0) { /* Length probe only */ ret = entry->xattr_size; } else if (entry->xattr_size > buflen) ret = -ERANGE; else { memcpy(buf, entry->xattr_value, entry->xattr_size); ret = entry->xattr_size; } } else { ret = -ENOENT; } spin_unlock(&cache->listxattr_lock); kref_put(&cache->ref, nfs4_xattr_free_cache_cb); return ret; } /* * Add an xattr to the cache. * * This also invalidates the xattr list cache. */ void nfs4_xattr_cache_add(struct inode *inode, const char *name, const char *buf, struct page **pages, ssize_t buflen) { struct nfs4_xattr_cache *cache; struct nfs4_xattr_entry *entry; dprintk("%s: add '%s' len %lu\n", __func__, name, (unsigned long)buflen); cache = nfs4_xattr_get_cache(inode, 1); if (cache == NULL) return; entry = nfs4_xattr_alloc_entry(name, buf, pages, buflen); if (entry == NULL) goto out; (void)nfs4_xattr_set_listcache(cache, NULL); if (!nfs4_xattr_hash_add(cache, entry)) kref_put(&entry->ref, nfs4_xattr_free_entry_cb); out: kref_put(&cache->ref, nfs4_xattr_free_cache_cb); } /* * Remove an xattr from the cache. * * This also invalidates the xattr list cache. */ void nfs4_xattr_cache_remove(struct inode *inode, const char *name) { struct nfs4_xattr_cache *cache; dprintk("%s: remove '%s'\n", __func__, name); cache = nfs4_xattr_get_cache(inode, 0); if (cache == NULL) return; (void)nfs4_xattr_set_listcache(cache, NULL); nfs4_xattr_hash_remove(cache, name); kref_put(&cache->ref, nfs4_xattr_free_cache_cb); } /* * Cache listxattr output, replacing any possible old one. */ void nfs4_xattr_cache_set_list(struct inode *inode, const char *buf, ssize_t buflen) { struct nfs4_xattr_cache *cache; struct nfs4_xattr_entry *entry; cache = nfs4_xattr_get_cache(inode, 1); if (cache == NULL) return; entry = nfs4_xattr_alloc_entry(NULL, buf, NULL, buflen); if (entry == NULL) goto out; /* * This is just there to be able to get to bucket->cache, * which is obviously the same for all buckets, so just * use bucket 0. */ entry->bucket = &cache->buckets[0]; if (!nfs4_xattr_set_listcache(cache, entry)) kref_put(&entry->ref, nfs4_xattr_free_entry_cb); out: kref_put(&cache->ref, nfs4_xattr_free_cache_cb); } /* * Zap the entire cache. Called when an inode is evicted. */ void nfs4_xattr_cache_zap(struct inode *inode) { struct nfs4_xattr_cache *oldcache; spin_lock(&inode->i_lock); oldcache = nfs4_xattr_cache_unlink(inode); spin_unlock(&inode->i_lock); if (oldcache) nfs4_xattr_discard_cache(oldcache); } /* * The entry LRU is shrunk more aggressively than the cache LRU, * by settings @seeks to 1. * * Cache structures are freed only when they've become empty, after * pruning all but one entry. */ static unsigned long nfs4_xattr_cache_count(struct shrinker *shrink, struct shrink_control *sc); static unsigned long nfs4_xattr_entry_count(struct shrinker *shrink, struct shrink_control *sc); static unsigned long nfs4_xattr_cache_scan(struct shrinker *shrink, struct shrink_control *sc); static unsigned long nfs4_xattr_entry_scan(struct shrinker *shrink, struct shrink_control *sc); static struct shrinker *nfs4_xattr_cache_shrinker; static struct shrinker *nfs4_xattr_entry_shrinker; static struct shrinker *nfs4_xattr_large_entry_shrinker; static enum lru_status cache_lru_isolate(struct list_head *item, struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) { struct list_head *dispose = arg; struct inode *inode; struct nfs4_xattr_cache *cache = container_of(item, struct nfs4_xattr_cache, lru); if (atomic_long_read(&cache->nent) > 1) return LRU_SKIP; /* * If a cache structure is on the LRU list, we know that * its inode is valid. Try to lock it to break the link. * Since we're inverting the lock order here, only try. */ inode = cache->inode; if (!spin_trylock(&inode->i_lock)) return LRU_SKIP; kref_get(&cache->ref); cache->inode = NULL; NFS_I(inode)->xattr_cache = NULL; NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_XATTR; list_lru_isolate(lru, &cache->lru); spin_unlock(&inode->i_lock); list_add_tail(&cache->dispose, dispose); return LRU_REMOVED; } static unsigned long nfs4_xattr_cache_scan(struct shrinker *shrink, struct shrink_control *sc) { LIST_HEAD(dispose); unsigned long freed; struct nfs4_xattr_cache *cache; freed = list_lru_shrink_walk(&nfs4_xattr_cache_lru, sc, cache_lru_isolate, &dispose); while (!list_empty(&dispose)) { cache = list_first_entry(&dispose, struct nfs4_xattr_cache, dispose); list_del_init(&cache->dispose); nfs4_xattr_discard_cache(cache); kref_put(&cache->ref, nfs4_xattr_free_cache_cb); } return freed; } static unsigned long nfs4_xattr_cache_count(struct shrinker *shrink, struct shrink_control *sc) { unsigned long count; count = list_lru_shrink_count(&nfs4_xattr_cache_lru, sc); return vfs_pressure_ratio(count); } static enum lru_status entry_lru_isolate(struct list_head *item, struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) { struct list_head *dispose = arg; struct nfs4_xattr_bucket *bucket; struct nfs4_xattr_cache *cache; struct nfs4_xattr_entry *entry = container_of(item, struct nfs4_xattr_entry, lru); bucket = entry->bucket; cache = bucket->cache; /* * Unhook the entry from its parent (either a cache bucket * or a cache structure if it's a listxattr buf), so that * it's no longer found. Then add it to the isolate list, * to be freed later. * * In both cases, we're reverting lock order, so use * trylock and skip the entry if we can't get the lock. */ if (entry->xattr_name != NULL) { /* Regular cache entry */ if (!spin_trylock(&bucket->lock)) return LRU_SKIP; kref_get(&entry->ref); hlist_del_init(&entry->hnode); atomic_long_dec(&cache->nent); list_lru_isolate(lru, &entry->lru); spin_unlock(&bucket->lock); } else { /* Listxattr cache entry */ if (!spin_trylock(&cache->listxattr_lock)) return LRU_SKIP; kref_get(&entry->ref); cache->listxattr = NULL; list_lru_isolate(lru, &entry->lru); spin_unlock(&cache->listxattr_lock); } list_add_tail(&entry->dispose, dispose); return LRU_REMOVED; } static unsigned long nfs4_xattr_entry_scan(struct shrinker *shrink, struct shrink_control *sc) { LIST_HEAD(dispose); unsigned long freed; struct nfs4_xattr_entry *entry; struct list_lru *lru; lru = (shrink == nfs4_xattr_large_entry_shrinker) ? &nfs4_xattr_large_entry_lru : &nfs4_xattr_entry_lru; freed = list_lru_shrink_walk(lru, sc, entry_lru_isolate, &dispose); while (!list_empty(&dispose)) { entry = list_first_entry(&dispose, struct nfs4_xattr_entry, dispose); list_del_init(&entry->dispose); /* * Drop two references: the one that we just grabbed * in entry_lru_isolate, and the one that was set * when the entry was first allocated. */ kref_put(&entry->ref, nfs4_xattr_free_entry_cb); kref_put(&entry->ref, nfs4_xattr_free_entry_cb); } return freed; } static unsigned long nfs4_xattr_entry_count(struct shrinker *shrink, struct shrink_control *sc) { unsigned long count; struct list_lru *lru; lru = (shrink == nfs4_xattr_large_entry_shrinker) ? &nfs4_xattr_large_entry_lru : &nfs4_xattr_entry_lru; count = list_lru_shrink_count(lru, sc); return vfs_pressure_ratio(count); } static void nfs4_xattr_cache_init_once(void *p) { struct nfs4_xattr_cache *cache = p; spin_lock_init(&cache->listxattr_lock); atomic_long_set(&cache->nent, 0); nfs4_xattr_hash_init(cache); cache->listxattr = NULL; INIT_LIST_HEAD(&cache->lru); INIT_LIST_HEAD(&cache->dispose); } typedef unsigned long (*count_objects_cb)(struct shrinker *s, struct shrink_control *sc); typedef unsigned long (*scan_objects_cb)(struct shrinker *s, struct shrink_control *sc); static int __init nfs4_xattr_shrinker_init(struct shrinker **shrinker, struct list_lru *lru, const char *name, count_objects_cb count, scan_objects_cb scan, long batch, int seeks) { int ret; *shrinker = shrinker_alloc(SHRINKER_MEMCG_AWARE, name); if (!*shrinker) return -ENOMEM; ret = list_lru_init_memcg(lru, *shrinker); if (ret) { shrinker_free(*shrinker); return ret; } (*shrinker)->count_objects = count; (*shrinker)->scan_objects = scan; (*shrinker)->batch = batch; (*shrinker)->seeks = seeks; shrinker_register(*shrinker); return ret; } static void nfs4_xattr_shrinker_destroy(struct shrinker *shrinker, struct list_lru *lru) { shrinker_free(shrinker); list_lru_destroy(lru); } int __init nfs4_xattr_cache_init(void) { int ret = 0; nfs4_xattr_cache_cachep = kmem_cache_create("nfs4_xattr_cache_cache", sizeof(struct nfs4_xattr_cache), 0, (SLAB_RECLAIM_ACCOUNT), nfs4_xattr_cache_init_once); if (nfs4_xattr_cache_cachep == NULL) return -ENOMEM; ret = nfs4_xattr_shrinker_init(&nfs4_xattr_cache_shrinker, &nfs4_xattr_cache_lru, "nfs-xattr_cache", nfs4_xattr_cache_count, nfs4_xattr_cache_scan, 0, DEFAULT_SEEKS); if (ret) goto out1; ret = nfs4_xattr_shrinker_init(&nfs4_xattr_entry_shrinker, &nfs4_xattr_entry_lru, "nfs-xattr_entry", nfs4_xattr_entry_count, nfs4_xattr_entry_scan, 512, DEFAULT_SEEKS); if (ret) goto out2; ret = nfs4_xattr_shrinker_init(&nfs4_xattr_large_entry_shrinker, &nfs4_xattr_large_entry_lru, "nfs-xattr_large_entry", nfs4_xattr_entry_count, nfs4_xattr_entry_scan, 512, 1); if (!ret) return 0; nfs4_xattr_shrinker_destroy(nfs4_xattr_entry_shrinker, &nfs4_xattr_entry_lru); out2: nfs4_xattr_shrinker_destroy(nfs4_xattr_cache_shrinker, &nfs4_xattr_cache_lru); out1: kmem_cache_destroy(nfs4_xattr_cache_cachep); return ret; } void nfs4_xattr_cache_exit(void) { nfs4_xattr_shrinker_destroy(nfs4_xattr_large_entry_shrinker, &nfs4_xattr_large_entry_lru); nfs4_xattr_shrinker_destroy(nfs4_xattr_entry_shrinker, &nfs4_xattr_entry_lru); nfs4_xattr_shrinker_destroy(nfs4_xattr_cache_shrinker, &nfs4_xattr_cache_lru); kmem_cache_destroy(nfs4_xattr_cache_cachep); } |
| 34 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 8073 8074 8075 8076 8077 8078 8079 8080 8081 8082 8083 8084 8085 8086 8087 8088 8089 8090 8091 8092 8093 8094 8095 8096 8097 8098 8099 8100 8101 8102 8103 8104 8105 8106 8107 8108 8109 8110 8111 8112 8113 8114 8115 8116 8117 8118 8119 8120 8121 8122 8123 8124 8125 8126 8127 8128 8129 8130 8131 8132 8133 8134 8135 8136 8137 8138 8139 8140 8141 8142 8143 8144 8145 8146 8147 8148 8149 8150 8151 8152 8153 8154 8155 8156 8157 8158 8159 8160 8161 8162 8163 8164 8165 8166 8167 8168 8169 8170 8171 8172 8173 8174 8175 8176 8177 8178 8179 8180 8181 8182 8183 8184 8185 8186 8187 8188 8189 8190 8191 8192 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 8209 8210 8211 8212 8213 8214 8215 8216 8217 8218 8219 8220 8221 8222 8223 8224 8225 8226 8227 8228 8229 8230 8231 8232 8233 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 8262 8263 8264 8265 8266 8267 8268 8269 8270 8271 8272 8273 8274 8275 8276 8277 8278 8279 8280 8281 8282 8283 8284 8285 8286 8287 8288 8289 8290 8291 8292 8293 8294 8295 8296 8297 8298 8299 8300 8301 8302 8303 8304 8305 8306 8307 8308 8309 8310 8311 8312 8313 8314 8315 8316 8317 8318 8319 8320 8321 8322 8323 8324 8325 8326 8327 8328 8329 8330 8331 8332 8333 8334 8335 8336 8337 8338 8339 8340 8341 8342 8343 8344 8345 8346 8347 8348 8349 8350 8351 8352 8353 8354 8355 8356 8357 8358 8359 8360 8361 8362 8363 8364 8365 8366 8367 8368 8369 8370 8371 8372 8373 8374 8375 8376 8377 8378 8379 8380 8381 8382 8383 8384 8385 8386 8387 8388 8389 8390 8391 8392 8393 8394 8395 8396 8397 8398 8399 8400 8401 8402 8403 8404 8405 8406 8407 8408 8409 8410 8411 8412 8413 8414 8415 8416 8417 8418 8419 8420 8421 8422 8423 8424 8425 8426 8427 8428 8429 8430 8431 8432 8433 8434 8435 8436 8437 8438 8439 8440 8441 8442 8443 8444 8445 8446 8447 8448 8449 8450 8451 8452 8453 8454 8455 8456 8457 8458 8459 8460 8461 8462 8463 8464 8465 8466 8467 8468 8469 8470 8471 8472 8473 8474 8475 8476 8477 8478 8479 8480 8481 8482 8483 8484 8485 8486 8487 8488 8489 8490 8491 8492 8493 8494 8495 8496 8497 8498 8499 8500 8501 8502 8503 8504 8505 8506 8507 8508 8509 8510 8511 8512 8513 8514 8515 8516 8517 8518 8519 8520 8521 8522 8523 8524 8525 8526 8527 8528 8529 8530 8531 8532 8533 8534 8535 8536 8537 8538 8539 8540 8541 8542 8543 8544 8545 8546 8547 8548 8549 8550 8551 8552 8553 8554 8555 8556 8557 8558 8559 8560 8561 8562 8563 8564 8565 8566 8567 8568 8569 8570 8571 8572 8573 8574 8575 8576 8577 8578 8579 8580 8581 8582 8583 8584 8585 8586 8587 8588 8589 8590 8591 8592 8593 8594 8595 8596 8597 8598 8599 8600 8601 8602 8603 8604 8605 8606 8607 8608 8609 8610 8611 8612 8613 8614 8615 8616 8617 8618 8619 8620 8621 8622 8623 8624 8625 8626 8627 8628 8629 8630 8631 8632 8633 8634 8635 8636 8637 8638 8639 8640 8641 8642 8643 8644 8645 8646 8647 8648 8649 8650 8651 8652 8653 8654 8655 8656 8657 8658 8659 8660 8661 8662 8663 8664 8665 8666 8667 8668 8669 8670 8671 8672 8673 8674 8675 8676 8677 8678 8679 8680 8681 8682 8683 8684 8685 8686 8687 8688 8689 8690 8691 8692 8693 8694 8695 8696 8697 8698 8699 8700 8701 8702 8703 8704 8705 8706 8707 8708 8709 8710 8711 8712 8713 8714 8715 8716 8717 8718 8719 8720 8721 8722 8723 8724 8725 8726 8727 8728 8729 8730 8731 8732 8733 8734 8735 8736 8737 8738 8739 8740 8741 8742 8743 8744 8745 8746 8747 8748 8749 8750 8751 8752 8753 8754 8755 8756 8757 8758 8759 8760 8761 8762 8763 8764 8765 8766 8767 8768 8769 8770 8771 8772 8773 8774 8775 8776 8777 8778 8779 8780 8781 8782 8783 8784 8785 8786 8787 8788 8789 8790 8791 8792 8793 8794 8795 8796 8797 8798 8799 8800 8801 8802 8803 8804 8805 8806 8807 8808 8809 8810 8811 8812 8813 8814 8815 8816 8817 8818 8819 8820 8821 8822 8823 8824 8825 8826 8827 8828 8829 8830 8831 8832 8833 8834 8835 8836 8837 8838 8839 8840 8841 8842 8843 8844 8845 8846 8847 8848 8849 8850 8851 8852 8853 8854 8855 8856 8857 8858 8859 8860 8861 8862 8863 8864 8865 8866 8867 8868 8869 8870 8871 8872 8873 8874 8875 8876 8877 8878 8879 8880 8881 8882 8883 8884 8885 8886 8887 8888 8889 8890 8891 8892 8893 8894 8895 8896 8897 8898 8899 8900 8901 8902 8903 8904 8905 8906 8907 8908 8909 8910 8911 8912 8913 8914 8915 8916 8917 8918 8919 8920 8921 8922 8923 8924 8925 8926 8927 8928 8929 8930 8931 8932 8933 8934 8935 8936 8937 8938 8939 8940 8941 8942 8943 8944 8945 8946 8947 8948 8949 8950 8951 8952 8953 8954 8955 8956 8957 8958 8959 | /* * Copyright (c) 2001 The Regents of the University of Michigan. * All rights reserved. * * Kendrick Smith <kmsmith@umich.edu> * Andy Adamson <kandros@umich.edu> * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the name of the University 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 ``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 REGENTS OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. * */ #include <linux/file.h> #include <linux/fs.h> #include <linux/slab.h> #include <linux/namei.h> #include <linux/swap.h> #include <linux/pagemap.h> #include <linux/ratelimit.h> #include <linux/sunrpc/svcauth_gss.h> #include <linux/sunrpc/addr.h> #include <linux/jhash.h> #include <linux/string_helpers.h> #include <linux/fsnotify.h> #include <linux/rhashtable.h> #include <linux/nfs_ssc.h> #include "xdr4.h" #include "xdr4cb.h" #include "vfs.h" #include "current_stateid.h" #include "netns.h" #include "pnfs.h" #include "filecache.h" #include "trace.h" #define NFSDDBG_FACILITY NFSDDBG_PROC #define all_ones {{ ~0, ~0}, ~0} static const stateid_t one_stateid = { .si_generation = ~0, .si_opaque = all_ones, }; static const stateid_t zero_stateid = { /* all fields zero */ }; static const stateid_t currentstateid = { .si_generation = 1, }; static const stateid_t close_stateid = { .si_generation = 0xffffffffU, }; static u64 current_sessionid = 1; #define ZERO_STATEID(stateid) (!memcmp((stateid), &zero_stateid, sizeof(stateid_t))) #define ONE_STATEID(stateid) (!memcmp((stateid), &one_stateid, sizeof(stateid_t))) #define CURRENT_STATEID(stateid) (!memcmp((stateid), ¤tstateid, sizeof(stateid_t))) #define CLOSE_STATEID(stateid) (!memcmp((stateid), &close_stateid, sizeof(stateid_t))) /* forward declarations */ static bool check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner); static void nfs4_free_ol_stateid(struct nfs4_stid *stid); void nfsd4_end_grace(struct nfsd_net *nn); static void _free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps); static void nfsd4_file_hash_remove(struct nfs4_file *fi); static void deleg_reaper(struct nfsd_net *nn); /* Locking: */ /* * Currently used for the del_recall_lru and file hash table. In an * effort to decrease the scope of the client_mutex, this spinlock may * eventually cover more: */ static DEFINE_SPINLOCK(state_lock); enum nfsd4_st_mutex_lock_subclass { OPEN_STATEID_MUTEX = 0, LOCK_STATEID_MUTEX = 1, }; /* * A waitqueue for all in-progress 4.0 CLOSE operations that are waiting for * the refcount on the open stateid to drop. */ static DECLARE_WAIT_QUEUE_HEAD(close_wq); /* * A waitqueue where a writer to clients/#/ctl destroying a client can * wait for cl_rpc_users to drop to 0 and then for the client to be * unhashed. */ static DECLARE_WAIT_QUEUE_HEAD(expiry_wq); static struct kmem_cache *client_slab; static struct kmem_cache *openowner_slab; static struct kmem_cache *lockowner_slab; static struct kmem_cache *file_slab; static struct kmem_cache *stateid_slab; static struct kmem_cache *deleg_slab; static struct kmem_cache *odstate_slab; static void free_session(struct nfsd4_session *); static const struct nfsd4_callback_ops nfsd4_cb_recall_ops; static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops; static const struct nfsd4_callback_ops nfsd4_cb_getattr_ops; static struct workqueue_struct *laundry_wq; int nfsd4_create_laundry_wq(void) { int rc = 0; laundry_wq = alloc_workqueue("%s", WQ_UNBOUND, 0, "nfsd4"); if (laundry_wq == NULL) rc = -ENOMEM; return rc; } void nfsd4_destroy_laundry_wq(void) { destroy_workqueue(laundry_wq); } static bool is_session_dead(struct nfsd4_session *ses) { return ses->se_flags & NFS4_SESSION_DEAD; } static __be32 mark_session_dead_locked(struct nfsd4_session *ses, int ref_held_by_me) { if (atomic_read(&ses->se_ref) > ref_held_by_me) return nfserr_jukebox; ses->se_flags |= NFS4_SESSION_DEAD; return nfs_ok; } static bool is_client_expired(struct nfs4_client *clp) { return clp->cl_time == 0; } static void nfsd4_dec_courtesy_client_count(struct nfsd_net *nn, struct nfs4_client *clp) { if (clp->cl_state != NFSD4_ACTIVE) atomic_add_unless(&nn->nfsd_courtesy_clients, -1, 0); } static __be32 get_client_locked(struct nfs4_client *clp) { struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); lockdep_assert_held(&nn->client_lock); if (is_client_expired(clp)) return nfserr_expired; atomic_inc(&clp->cl_rpc_users); nfsd4_dec_courtesy_client_count(nn, clp); clp->cl_state = NFSD4_ACTIVE; return nfs_ok; } /* must be called under the client_lock */ static inline void renew_client_locked(struct nfs4_client *clp) { struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); if (is_client_expired(clp)) { WARN_ON(1); printk("%s: client (clientid %08x/%08x) already expired\n", __func__, clp->cl_clientid.cl_boot, clp->cl_clientid.cl_id); return; } list_move_tail(&clp->cl_lru, &nn->client_lru); clp->cl_time = ktime_get_boottime_seconds(); nfsd4_dec_courtesy_client_count(nn, clp); clp->cl_state = NFSD4_ACTIVE; } static void put_client_renew_locked(struct nfs4_client *clp) { struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); lockdep_assert_held(&nn->client_lock); if (!atomic_dec_and_test(&clp->cl_rpc_users)) return; if (!is_client_expired(clp)) renew_client_locked(clp); else wake_up_all(&expiry_wq); } static void put_client_renew(struct nfs4_client *clp) { struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); if (!atomic_dec_and_lock(&clp->cl_rpc_users, &nn->client_lock)) return; if (!is_client_expired(clp)) renew_client_locked(clp); else wake_up_all(&expiry_wq); spin_unlock(&nn->client_lock); } static __be32 nfsd4_get_session_locked(struct nfsd4_session *ses) { __be32 status; if (is_session_dead(ses)) return nfserr_badsession; status = get_client_locked(ses->se_client); if (status) return status; atomic_inc(&ses->se_ref); return nfs_ok; } static void nfsd4_put_session_locked(struct nfsd4_session *ses) { struct nfs4_client *clp = ses->se_client; struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); lockdep_assert_held(&nn->client_lock); if (atomic_dec_and_test(&ses->se_ref) && is_session_dead(ses)) free_session(ses); put_client_renew_locked(clp); } static void nfsd4_put_session(struct nfsd4_session *ses) { struct nfs4_client *clp = ses->se_client; struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); spin_lock(&nn->client_lock); nfsd4_put_session_locked(ses); spin_unlock(&nn->client_lock); } static struct nfsd4_blocked_lock * find_blocked_lock(struct nfs4_lockowner *lo, struct knfsd_fh *fh, struct nfsd_net *nn) { struct nfsd4_blocked_lock *cur, *found = NULL; spin_lock(&nn->blocked_locks_lock); list_for_each_entry(cur, &lo->lo_blocked, nbl_list) { if (fh_match(fh, &cur->nbl_fh)) { list_del_init(&cur->nbl_list); WARN_ON(list_empty(&cur->nbl_lru)); list_del_init(&cur->nbl_lru); found = cur; break; } } spin_unlock(&nn->blocked_locks_lock); if (found) locks_delete_block(&found->nbl_lock); return found; } static struct nfsd4_blocked_lock * find_or_allocate_block(struct nfs4_lockowner *lo, struct knfsd_fh *fh, struct nfsd_net *nn) { struct nfsd4_blocked_lock *nbl; nbl = find_blocked_lock(lo, fh, nn); if (!nbl) { nbl = kmalloc(sizeof(*nbl), GFP_KERNEL); if (nbl) { INIT_LIST_HEAD(&nbl->nbl_list); INIT_LIST_HEAD(&nbl->nbl_lru); fh_copy_shallow(&nbl->nbl_fh, fh); locks_init_lock(&nbl->nbl_lock); kref_init(&nbl->nbl_kref); nfsd4_init_cb(&nbl->nbl_cb, lo->lo_owner.so_client, &nfsd4_cb_notify_lock_ops, NFSPROC4_CLNT_CB_NOTIFY_LOCK); } } return nbl; } static void free_nbl(struct kref *kref) { struct nfsd4_blocked_lock *nbl; nbl = container_of(kref, struct nfsd4_blocked_lock, nbl_kref); locks_release_private(&nbl->nbl_lock); kfree(nbl); } static void free_blocked_lock(struct nfsd4_blocked_lock *nbl) { locks_delete_block(&nbl->nbl_lock); kref_put(&nbl->nbl_kref, free_nbl); } static void remove_blocked_locks(struct nfs4_lockowner *lo) { struct nfs4_client *clp = lo->lo_owner.so_client; struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); struct nfsd4_blocked_lock *nbl; LIST_HEAD(reaplist); /* Dequeue all blocked locks */ spin_lock(&nn->blocked_locks_lock); while (!list_empty(&lo->lo_blocked)) { nbl = list_first_entry(&lo->lo_blocked, struct nfsd4_blocked_lock, nbl_list); list_del_init(&nbl->nbl_list); WARN_ON(list_empty(&nbl->nbl_lru)); list_move(&nbl->nbl_lru, &reaplist); } spin_unlock(&nn->blocked_locks_lock); /* Now free them */ while (!list_empty(&reaplist)) { nbl = list_first_entry(&reaplist, struct nfsd4_blocked_lock, nbl_lru); list_del_init(&nbl->nbl_lru); free_blocked_lock(nbl); } } static void nfsd4_cb_notify_lock_prepare(struct nfsd4_callback *cb) { struct nfsd4_blocked_lock *nbl = container_of(cb, struct nfsd4_blocked_lock, nbl_cb); locks_delete_block(&nbl->nbl_lock); } static int nfsd4_cb_notify_lock_done(struct nfsd4_callback *cb, struct rpc_task *task) { trace_nfsd_cb_notify_lock_done(&zero_stateid, task); /* * Since this is just an optimization, we don't try very hard if it * turns out not to succeed. We'll requeue it on NFS4ERR_DELAY, and * just quit trying on anything else. */ switch (task->tk_status) { case -NFS4ERR_DELAY: rpc_delay(task, 1 * HZ); return 0; default: return 1; } } static void nfsd4_cb_notify_lock_release(struct nfsd4_callback *cb) { struct nfsd4_blocked_lock *nbl = container_of(cb, struct nfsd4_blocked_lock, nbl_cb); free_blocked_lock(nbl); } static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops = { .prepare = nfsd4_cb_notify_lock_prepare, .done = nfsd4_cb_notify_lock_done, .release = nfsd4_cb_notify_lock_release, .opcode = OP_CB_NOTIFY_LOCK, }; /* * We store the NONE, READ, WRITE, and BOTH bits separately in the * st_{access,deny}_bmap field of the stateid, in order to track not * only what share bits are currently in force, but also what * combinations of share bits previous opens have used. This allows us * to enforce the recommendation in * https://datatracker.ietf.org/doc/html/rfc7530#section-16.19.4 that * the server return an error if the client attempt to downgrade to a * combination of share bits not explicable by closing some of its * previous opens. * * This enforcement is arguably incomplete, since we don't keep * track of access/deny bit combinations; so, e.g., we allow: * * OPEN allow read, deny write * OPEN allow both, deny none * DOWNGRADE allow read, deny none * * which we should reject. * * But you could also argue that our current code is already overkill, * since it only exists to return NFS4ERR_INVAL on incorrect client * behavior. */ static unsigned int bmap_to_share_mode(unsigned long bmap) { int i; unsigned int access = 0; for (i = 1; i < 4; i++) { if (test_bit(i, &bmap)) access |= i; } return access; } /* set share access for a given stateid */ static inline void set_access(u32 access, struct nfs4_ol_stateid *stp) { unsigned char mask = 1 << access; WARN_ON_ONCE(access > NFS4_SHARE_ACCESS_BOTH); stp->st_access_bmap |= mask; } /* clear share access for a given stateid */ static inline void clear_access(u32 access, struct nfs4_ol_stateid *stp) { unsigned char mask = 1 << access; WARN_ON_ONCE(access > NFS4_SHARE_ACCESS_BOTH); stp->st_access_bmap &= ~mask; } /* test whether a given stateid has access */ static inline bool test_access(u32 access, struct nfs4_ol_stateid *stp) { unsigned char mask = 1 << access; return (bool)(stp->st_access_bmap & mask); } /* set share deny for a given stateid */ static inline void set_deny(u32 deny, struct nfs4_ol_stateid *stp) { unsigned char mask = 1 << deny; WARN_ON_ONCE(deny > NFS4_SHARE_DENY_BOTH); stp->st_deny_bmap |= mask; } /* clear share deny for a given stateid */ static inline void clear_deny(u32 deny, struct nfs4_ol_stateid *stp) { unsigned char mask = 1 << deny; WARN_ON_ONCE(deny > NFS4_SHARE_DENY_BOTH); stp->st_deny_bmap &= ~mask; } /* test whether a given stateid is denying specific access */ static inline bool test_deny(u32 deny, struct nfs4_ol_stateid *stp) { unsigned char mask = 1 << deny; return (bool)(stp->st_deny_bmap & mask); } static int nfs4_access_to_omode(u32 access) { switch (access & NFS4_SHARE_ACCESS_BOTH) { case NFS4_SHARE_ACCESS_READ: return O_RDONLY; case NFS4_SHARE_ACCESS_WRITE: return O_WRONLY; case NFS4_SHARE_ACCESS_BOTH: return O_RDWR; } WARN_ON_ONCE(1); return O_RDONLY; } static inline int access_permit_read(struct nfs4_ol_stateid *stp) { return test_access(NFS4_SHARE_ACCESS_READ, stp) || test_access(NFS4_SHARE_ACCESS_BOTH, stp) || test_access(NFS4_SHARE_ACCESS_WRITE, stp); } static inline int access_permit_write(struct nfs4_ol_stateid *stp) { return test_access(NFS4_SHARE_ACCESS_WRITE, stp) || test_access(NFS4_SHARE_ACCESS_BOTH, stp); } static inline struct nfs4_stateowner * nfs4_get_stateowner(struct nfs4_stateowner *sop) { atomic_inc(&sop->so_count); return sop; } static int same_owner_str(struct nfs4_stateowner *sop, struct xdr_netobj *owner) { return (sop->so_owner.len == owner->len) && 0 == memcmp(sop->so_owner.data, owner->data, owner->len); } static struct nfs4_openowner * find_openstateowner_str(unsigned int hashval, struct nfsd4_open *open, struct nfs4_client *clp) { struct nfs4_stateowner *so; lockdep_assert_held(&clp->cl_lock); list_for_each_entry(so, &clp->cl_ownerstr_hashtbl[hashval], so_strhash) { if (!so->so_is_open_owner) continue; if (same_owner_str(so, &open->op_owner)) return openowner(nfs4_get_stateowner(so)); } return NULL; } static inline u32 opaque_hashval(const void *ptr, int nbytes) { unsigned char *cptr = (unsigned char *) ptr; u32 x = 0; while (nbytes--) { x *= 37; x += *cptr++; } return x; } static void nfsd4_free_file_rcu(struct rcu_head *rcu) { struct nfs4_file *fp = container_of(rcu, struct nfs4_file, fi_rcu); kmem_cache_free(file_slab, fp); } void put_nfs4_file(struct nfs4_file *fi) { if (refcount_dec_and_test(&fi->fi_ref)) { nfsd4_file_hash_remove(fi); WARN_ON_ONCE(!list_empty(&fi->fi_clnt_odstate)); WARN_ON_ONCE(!list_empty(&fi->fi_delegations)); call_rcu(&fi->fi_rcu, nfsd4_free_file_rcu); } } static struct nfsd_file * find_writeable_file_locked(struct nfs4_file *f) { struct nfsd_file *ret; lockdep_assert_held(&f->fi_lock); ret = nfsd_file_get(f->fi_fds[O_WRONLY]); if (!ret) ret = nfsd_file_get(f->fi_fds[O_RDWR]); return ret; } static struct nfsd_file * find_writeable_file(struct nfs4_file *f) { struct nfsd_file *ret; spin_lock(&f->fi_lock); ret = find_writeable_file_locked(f); spin_unlock(&f->fi_lock); return ret; } static struct nfsd_file * find_readable_file_locked(struct nfs4_file *f) { struct nfsd_file *ret; lockdep_assert_held(&f->fi_lock); ret = nfsd_file_get(f->fi_fds[O_RDONLY]); if (!ret) ret = nfsd_file_get(f->fi_fds[O_RDWR]); return ret; } static struct nfsd_file * find_readable_file(struct nfs4_file *f) { struct nfsd_file *ret; spin_lock(&f->fi_lock); ret = find_readable_file_locked(f); spin_unlock(&f->fi_lock); return ret; } static struct nfsd_file * find_rw_file(struct nfs4_file *f) { struct nfsd_file *ret; spin_lock(&f->fi_lock); ret = nfsd_file_get(f->fi_fds[O_RDWR]); spin_unlock(&f->fi_lock); return ret; } struct nfsd_file * find_any_file(struct nfs4_file *f) { struct nfsd_file *ret; if (!f) return NULL; spin_lock(&f->fi_lock); ret = nfsd_file_get(f->fi_fds[O_RDWR]); if (!ret) { ret = nfsd_file_get(f->fi_fds[O_WRONLY]); if (!ret) ret = nfsd_file_get(f->fi_fds[O_RDONLY]); } spin_unlock(&f->fi_lock); return ret; } static struct nfsd_file *find_any_file_locked(struct nfs4_file *f) { lockdep_assert_held(&f->fi_lock); if (f->fi_fds[O_RDWR]) return f->fi_fds[O_RDWR]; if (f->fi_fds[O_WRONLY]) return f->fi_fds[O_WRONLY]; if (f->fi_fds[O_RDONLY]) return f->fi_fds[O_RDONLY]; return NULL; } static atomic_long_t num_delegations; unsigned long max_delegations; /* * Open owner state (share locks) */ /* hash tables for lock and open owners */ #define OWNER_HASH_BITS 8 #define OWNER_HASH_SIZE (1 << OWNER_HASH_BITS) #define OWNER_HASH_MASK (OWNER_HASH_SIZE - 1) static unsigned int ownerstr_hashval(struct xdr_netobj *ownername) { unsigned int ret; ret = opaque_hashval(ownername->data, ownername->len); return ret & OWNER_HASH_MASK; } static struct rhltable nfs4_file_rhltable ____cacheline_aligned_in_smp; static const struct rhashtable_params nfs4_file_rhash_params = { .key_len = sizeof_field(struct nfs4_file, fi_inode), .key_offset = offsetof(struct nfs4_file, fi_inode), .head_offset = offsetof(struct nfs4_file, fi_rlist), /* * Start with a single page hash table to reduce resizing churn * on light workloads. */ .min_size = 256, .automatic_shrinking = true, }; /* * Check if courtesy clients have conflicting access and resolve it if possible * * access: is op_share_access if share_access is true. * Check if access mode, op_share_access, would conflict with * the current deny mode of the file 'fp'. * access: is op_share_deny if share_access is false. * Check if the deny mode, op_share_deny, would conflict with * current access of the file 'fp'. * stp: skip checking this entry. * new_stp: normal open, not open upgrade. * * Function returns: * false - access/deny mode conflict with normal client. * true - no conflict or conflict with courtesy client(s) is resolved. */ static bool nfs4_resolve_deny_conflicts_locked(struct nfs4_file *fp, bool new_stp, struct nfs4_ol_stateid *stp, u32 access, bool share_access) { struct nfs4_ol_stateid *st; bool resolvable = true; unsigned char bmap; struct nfsd_net *nn; struct nfs4_client *clp; lockdep_assert_held(&fp->fi_lock); list_for_each_entry(st, &fp->fi_stateids, st_perfile) { /* ignore lock stateid */ if (st->st_openstp) continue; if (st == stp && new_stp) continue; /* check file access against deny mode or vice versa */ bmap = share_access ? st->st_deny_bmap : st->st_access_bmap; if (!(access & bmap_to_share_mode(bmap))) continue; clp = st->st_stid.sc_client; if (try_to_expire_client(clp)) continue; resolvable = false; break; } if (resolvable) { clp = stp->st_stid.sc_client; nn = net_generic(clp->net, nfsd_net_id); mod_delayed_work(laundry_wq, &nn->laundromat_work, 0); } return resolvable; } static void __nfs4_file_get_access(struct nfs4_file *fp, u32 access) { lockdep_assert_held(&fp->fi_lock); if (access & NFS4_SHARE_ACCESS_WRITE) atomic_inc(&fp->fi_access[O_WRONLY]); if (access & NFS4_SHARE_ACCESS_READ) atomic_inc(&fp->fi_access[O_RDONLY]); } static __be32 nfs4_file_get_access(struct nfs4_file *fp, u32 access) { lockdep_assert_held(&fp->fi_lock); /* Does this access mode make sense? */ if (access & ~NFS4_SHARE_ACCESS_BOTH) return nfserr_inval; /* Does it conflict with a deny mode already set? */ if ((access & fp->fi_share_deny) != 0) return nfserr_share_denied; __nfs4_file_get_access(fp, access); return nfs_ok; } static __be32 nfs4_file_check_deny(struct nfs4_file *fp, u32 deny) { /* Common case is that there is no deny mode. */ if (deny) { /* Does this deny mode make sense? */ if (deny & ~NFS4_SHARE_DENY_BOTH) return nfserr_inval; if ((deny & NFS4_SHARE_DENY_READ) && atomic_read(&fp->fi_access[O_RDONLY])) return nfserr_share_denied; if ((deny & NFS4_SHARE_DENY_WRITE) && atomic_read(&fp->fi_access[O_WRONLY])) return nfserr_share_denied; } return nfs_ok; } static void __nfs4_file_put_access(struct nfs4_file *fp, int oflag) { might_lock(&fp->fi_lock); if (atomic_dec_and_lock(&fp->fi_access[oflag], &fp->fi_lock)) { struct nfsd_file *f1 = NULL; struct nfsd_file *f2 = NULL; swap(f1, fp->fi_fds[oflag]); if (atomic_read(&fp->fi_access[1 - oflag]) == 0) swap(f2, fp->fi_fds[O_RDWR]); spin_unlock(&fp->fi_lock); if (f1) nfsd_file_put(f1); if (f2) nfsd_file_put(f2); } } static void nfs4_file_put_access(struct nfs4_file *fp, u32 access) { WARN_ON_ONCE(access & ~NFS4_SHARE_ACCESS_BOTH); if (access & NFS4_SHARE_ACCESS_WRITE) __nfs4_file_put_access(fp, O_WRONLY); if (access & NFS4_SHARE_ACCESS_READ) __nfs4_file_put_access(fp, O_RDONLY); } /* * Allocate a new open/delegation state counter. This is needed for * pNFS for proper return on close semantics. * * Note that we only allocate it for pNFS-enabled exports, otherwise * all pointers to struct nfs4_clnt_odstate are always NULL. */ static struct nfs4_clnt_odstate * alloc_clnt_odstate(struct nfs4_client *clp) { struct nfs4_clnt_odstate *co; co = kmem_cache_zalloc(odstate_slab, GFP_KERNEL); if (co) { co->co_client = clp; refcount_set(&co->co_odcount, 1); } return co; } static void hash_clnt_odstate_locked(struct nfs4_clnt_odstate *co) { struct nfs4_file *fp = co->co_file; lockdep_assert_held(&fp->fi_lock); list_add(&co->co_perfile, &fp->fi_clnt_odstate); } static inline void get_clnt_odstate(struct nfs4_clnt_odstate *co) { if (co) refcount_inc(&co->co_odcount); } static void put_clnt_odstate(struct nfs4_clnt_odstate *co) { struct nfs4_file *fp; if (!co) return; fp = co->co_file; if (refcount_dec_and_lock(&co->co_odcount, &fp->fi_lock)) { list_del(&co->co_perfile); spin_unlock(&fp->fi_lock); nfsd4_return_all_file_layouts(co->co_client, fp); kmem_cache_free(odstate_slab, co); } } static struct nfs4_clnt_odstate * find_or_hash_clnt_odstate(struct nfs4_file *fp, struct nfs4_clnt_odstate *new) { struct nfs4_clnt_odstate *co; struct nfs4_client *cl; if (!new) return NULL; cl = new->co_client; spin_lock(&fp->fi_lock); list_for_each_entry(co, &fp->fi_clnt_odstate, co_perfile) { if (co->co_client == cl) { get_clnt_odstate(co); goto out; } } co = new; co->co_file = fp; hash_clnt_odstate_locked(new); out: spin_unlock(&fp->fi_lock); return co; } struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab, void (*sc_free)(struct nfs4_stid *)) { struct nfs4_stid *stid; int new_id; stid = kmem_cache_zalloc(slab, GFP_KERNEL); if (!stid) return NULL; idr_preload(GFP_KERNEL); spin_lock(&cl->cl_lock); /* Reserving 0 for start of file in nfsdfs "states" file: */ new_id = idr_alloc_cyclic(&cl->cl_stateids, stid, 1, 0, GFP_NOWAIT); spin_unlock(&cl->cl_lock); idr_preload_end(); if (new_id < 0) goto out_free; stid->sc_free = sc_free; stid->sc_client = cl; stid->sc_stateid.si_opaque.so_id = new_id; stid->sc_stateid.si_opaque.so_clid = cl->cl_clientid; /* Will be incremented before return to client: */ refcount_set(&stid->sc_count, 1); spin_lock_init(&stid->sc_lock); INIT_LIST_HEAD(&stid->sc_cp_list); /* * It shouldn't be a problem to reuse an opaque stateid value. * I don't think it is for 4.1. But with 4.0 I worry that, for * example, a stray write retransmission could be accepted by * the server when it should have been rejected. Therefore, * adopt a trick from the sctp code to attempt to maximize the * amount of time until an id is reused, by ensuring they always * "increase" (mod INT_MAX): */ return stid; out_free: kmem_cache_free(slab, stid); return NULL; } /* * Create a unique stateid_t to represent each COPY. */ static int nfs4_init_cp_state(struct nfsd_net *nn, copy_stateid_t *stid, unsigned char cs_type) { int new_id; stid->cs_stid.si_opaque.so_clid.cl_boot = (u32)nn->boot_time; stid->cs_stid.si_opaque.so_clid.cl_id = nn->s2s_cp_cl_id; idr_preload(GFP_KERNEL); spin_lock(&nn->s2s_cp_lock); new_id = idr_alloc_cyclic(&nn->s2s_cp_stateids, stid, 0, 0, GFP_NOWAIT); stid->cs_stid.si_opaque.so_id = new_id; stid->cs_stid.si_generation = 1; spin_unlock(&nn->s2s_cp_lock); idr_preload_end(); if (new_id < 0) return 0; stid->cs_type = cs_type; return 1; } int nfs4_init_copy_state(struct nfsd_net *nn, struct nfsd4_copy *copy) { return nfs4_init_cp_state(nn, ©->cp_stateid, NFS4_COPY_STID); } struct nfs4_cpntf_state *nfs4_alloc_init_cpntf_state(struct nfsd_net *nn, struct nfs4_stid *p_stid) { struct nfs4_cpntf_state *cps; cps = kzalloc(sizeof(struct nfs4_cpntf_state), GFP_KERNEL); if (!cps) return NULL; cps->cpntf_time = ktime_get_boottime_seconds(); refcount_set(&cps->cp_stateid.cs_count, 1); if (!nfs4_init_cp_state(nn, &cps->cp_stateid, NFS4_COPYNOTIFY_STID)) goto out_free; spin_lock(&nn->s2s_cp_lock); list_add(&cps->cp_list, &p_stid->sc_cp_list); spin_unlock(&nn->s2s_cp_lock); return cps; out_free: kfree(cps); return NULL; } void nfs4_free_copy_state(struct nfsd4_copy *copy) { struct nfsd_net *nn; if (copy->cp_stateid.cs_type != NFS4_COPY_STID) return; nn = net_generic(copy->cp_clp->net, nfsd_net_id); spin_lock(&nn->s2s_cp_lock); idr_remove(&nn->s2s_cp_stateids, copy->cp_stateid.cs_stid.si_opaque.so_id); spin_unlock(&nn->s2s_cp_lock); } static void nfs4_free_cpntf_statelist(struct net *net, struct nfs4_stid *stid) { struct nfs4_cpntf_state *cps; struct nfsd_net *nn; nn = net_generic(net, nfsd_net_id); spin_lock(&nn->s2s_cp_lock); while (!list_empty(&stid->sc_cp_list)) { cps = list_first_entry(&stid->sc_cp_list, struct nfs4_cpntf_state, cp_list); _free_cpntf_state_locked(nn, cps); } spin_unlock(&nn->s2s_cp_lock); } static struct nfs4_ol_stateid * nfs4_alloc_open_stateid(struct nfs4_client *clp) { struct nfs4_stid *stid; stid = nfs4_alloc_stid(clp, stateid_slab, nfs4_free_ol_stateid); if (!stid) return NULL; return openlockstateid(stid); } static void nfs4_free_deleg(struct nfs4_stid *stid) { struct nfs4_delegation *dp = delegstateid(stid); WARN_ON_ONCE(!list_empty(&stid->sc_cp_list)); WARN_ON_ONCE(!list_empty(&dp->dl_perfile)); WARN_ON_ONCE(!list_empty(&dp->dl_perclnt)); WARN_ON_ONCE(!list_empty(&dp->dl_recall_lru)); kmem_cache_free(deleg_slab, stid); atomic_long_dec(&num_delegations); } /* * When we recall a delegation, we should be careful not to hand it * out again straight away. * To ensure this we keep a pair of bloom filters ('new' and 'old') * in which the filehandles of recalled delegations are "stored". * If a filehandle appear in either filter, a delegation is blocked. * When a delegation is recalled, the filehandle is stored in the "new" * filter. * Every 30 seconds we swap the filters and clear the "new" one, * unless both are empty of course. This results in delegations for a * given filehandle being blocked for between 30 and 60 seconds. * * Each filter is 256 bits. We hash the filehandle to 32bit and use the * low 3 bytes as hash-table indices. * * 'blocked_delegations_lock', which is always taken in block_delegations(), * is used to manage concurrent access. Testing does not need the lock * except when swapping the two filters. */ static DEFINE_SPINLOCK(blocked_delegations_lock); static struct bloom_pair { int entries, old_entries; time64_t swap_time; int new; /* index into 'set' */ DECLARE_BITMAP(set[2], 256); } blocked_delegations; static int delegation_blocked(struct knfsd_fh *fh) { u32 hash; struct bloom_pair *bd = &blocked_delegations; if (bd->entries == 0) return 0; if (ktime_get_seconds() - bd->swap_time > 30) { spin_lock(&blocked_delegations_lock); if (ktime_get_seconds() - bd->swap_time > 30) { bd->entries -= bd->old_entries; bd->old_entries = bd->entries; bd->new = 1-bd->new; memset(bd->set[bd->new], 0, sizeof(bd->set[0])); bd->swap_time = ktime_get_seconds(); } spin_unlock(&blocked_delegations_lock); } hash = jhash(&fh->fh_raw, fh->fh_size, 0); if (test_bit(hash&255, bd->set[0]) && test_bit((hash>>8)&255, bd->set[0]) && test_bit((hash>>16)&255, bd->set[0])) return 1; if (test_bit(hash&255, bd->set[1]) && test_bit((hash>>8)&255, bd->set[1]) && test_bit((hash>>16)&255, bd->set[1])) return 1; return 0; } static void block_delegations(struct knfsd_fh *fh) { u32 hash; struct bloom_pair *bd = &blocked_delegations; hash = jhash(&fh->fh_raw, fh->fh_size, 0); spin_lock(&blocked_delegations_lock); __set_bit(hash&255, bd->set[bd->new]); __set_bit((hash>>8)&255, bd->set[bd->new]); __set_bit((hash>>16)&255, bd->set[bd->new]); if (bd->entries == 0) bd->swap_time = ktime_get_seconds(); bd->entries += 1; spin_unlock(&blocked_delegations_lock); } static struct nfs4_delegation * alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp, struct nfs4_clnt_odstate *odstate, u32 dl_type) { struct nfs4_delegation *dp; struct nfs4_stid *stid; long n; dprintk("NFSD alloc_init_deleg\n"); n = atomic_long_inc_return(&num_delegations); if (n < 0 || n > max_delegations) goto out_dec; if (delegation_blocked(&fp->fi_fhandle)) goto out_dec; stid = nfs4_alloc_stid(clp, deleg_slab, nfs4_free_deleg); if (stid == NULL) goto out_dec; dp = delegstateid(stid); /* * delegation seqid's are never incremented. The 4.1 special * meaning of seqid 0 isn't meaningful, really, but let's avoid * 0 anyway just for consistency and use 1: */ dp->dl_stid.sc_stateid.si_generation = 1; INIT_LIST_HEAD(&dp->dl_perfile); INIT_LIST_HEAD(&dp->dl_perclnt); INIT_LIST_HEAD(&dp->dl_recall_lru); dp->dl_clnt_odstate = odstate; get_clnt_odstate(odstate); dp->dl_type = dl_type; dp->dl_retries = 1; dp->dl_recalled = false; nfsd4_init_cb(&dp->dl_recall, dp->dl_stid.sc_client, &nfsd4_cb_recall_ops, NFSPROC4_CLNT_CB_RECALL); nfsd4_init_cb(&dp->dl_cb_fattr.ncf_getattr, dp->dl_stid.sc_client, &nfsd4_cb_getattr_ops, NFSPROC4_CLNT_CB_GETATTR); dp->dl_cb_fattr.ncf_file_modified = false; dp->dl_cb_fattr.ncf_cb_bmap[0] = FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE; get_nfs4_file(fp); dp->dl_stid.sc_file = fp; return dp; out_dec: atomic_long_dec(&num_delegations); return NULL; } void nfs4_put_stid(struct nfs4_stid *s) { struct nfs4_file *fp = s->sc_file; struct nfs4_client *clp = s->sc_client; might_lock(&clp->cl_lock); if (!refcount_dec_and_lock(&s->sc_count, &clp->cl_lock)) { wake_up_all(&close_wq); return; } idr_remove(&clp->cl_stateids, s->sc_stateid.si_opaque.so_id); if (s->sc_status & SC_STATUS_ADMIN_REVOKED) atomic_dec(&s->sc_client->cl_admin_revoked); nfs4_free_cpntf_statelist(clp->net, s); spin_unlock(&clp->cl_lock); s->sc_free(s); if (fp) put_nfs4_file(fp); } void nfs4_inc_and_copy_stateid(stateid_t *dst, struct nfs4_stid *stid) { stateid_t *src = &stid->sc_stateid; spin_lock(&stid->sc_lock); if (unlikely(++src->si_generation == 0)) src->si_generation = 1; memcpy(dst, src, sizeof(*dst)); spin_unlock(&stid->sc_lock); } static void put_deleg_file(struct nfs4_file *fp) { struct nfsd_file *nf = NULL; spin_lock(&fp->fi_lock); if (--fp->fi_delegees == 0) swap(nf, fp->fi_deleg_file); spin_unlock(&fp->fi_lock); if (nf) nfsd_file_put(nf); } static void nfs4_unlock_deleg_lease(struct nfs4_delegation *dp) { struct nfs4_file *fp = dp->dl_stid.sc_file; struct nfsd_file *nf = fp->fi_deleg_file; WARN_ON_ONCE(!fp->fi_delegees); kernel_setlease(nf->nf_file, F_UNLCK, NULL, (void **)&dp); put_deleg_file(fp); } static void destroy_unhashed_deleg(struct nfs4_delegation *dp) { put_clnt_odstate(dp->dl_clnt_odstate); nfs4_unlock_deleg_lease(dp); nfs4_put_stid(&dp->dl_stid); } /** * nfs4_delegation_exists - Discover if this delegation already exists * @clp: a pointer to the nfs4_client we're granting a delegation to * @fp: a pointer to the nfs4_file we're granting a delegation on * * Return: * On success: true iff an existing delegation is found */ static bool nfs4_delegation_exists(struct nfs4_client *clp, struct nfs4_file *fp) { struct nfs4_delegation *searchdp = NULL; struct nfs4_client *searchclp = NULL; lockdep_assert_held(&state_lock); lockdep_assert_held(&fp->fi_lock); list_for_each_entry(searchdp, &fp->fi_delegations, dl_perfile) { searchclp = searchdp->dl_stid.sc_client; if (clp == searchclp) { return true; } } return false; } /** * hash_delegation_locked - Add a delegation to the appropriate lists * @dp: a pointer to the nfs4_delegation we are adding. * @fp: a pointer to the nfs4_file we're granting a delegation on * * Return: * On success: NULL if the delegation was successfully hashed. * * On error: -EAGAIN if one was previously granted to this * nfs4_client for this nfs4_file. Delegation is not hashed. * */ static int hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp) { struct nfs4_client *clp = dp->dl_stid.sc_client; lockdep_assert_held(&state_lock); lockdep_assert_held(&fp->fi_lock); lockdep_assert_held(&clp->cl_lock); if (nfs4_delegation_exists(clp, fp)) return -EAGAIN; refcount_inc(&dp->dl_stid.sc_count); dp->dl_stid.sc_type = SC_TYPE_DELEG; list_add(&dp->dl_perfile, &fp->fi_delegations); list_add(&dp->dl_perclnt, &clp->cl_delegations); return 0; } static bool delegation_hashed(struct nfs4_delegation *dp) { return !(list_empty(&dp->dl_perfile)); } static bool unhash_delegation_locked(struct nfs4_delegation *dp, unsigned short statusmask) { struct nfs4_file *fp = dp->dl_stid.sc_file; lockdep_assert_held(&state_lock); if (!delegation_hashed(dp)) return false; if (statusmask == SC_STATUS_REVOKED && dp->dl_stid.sc_client->cl_minorversion == 0) statusmask = SC_STATUS_CLOSED; dp->dl_stid.sc_status |= statusmask; if (statusmask & SC_STATUS_ADMIN_REVOKED) atomic_inc(&dp->dl_stid.sc_client->cl_admin_revoked); /* Ensure that deleg break won't try to requeue it */ ++dp->dl_time; spin_lock(&fp->fi_lock); list_del_init(&dp->dl_perclnt); list_del_init(&dp->dl_recall_lru); list_del_init(&dp->dl_perfile); spin_unlock(&fp->fi_lock); return true; } static void destroy_delegation(struct nfs4_delegation *dp) { bool unhashed; spin_lock(&state_lock); unhashed = unhash_delegation_locked(dp, SC_STATUS_CLOSED); spin_unlock(&state_lock); if (unhashed) destroy_unhashed_deleg(dp); } /** * revoke_delegation - perform nfs4 delegation structure cleanup * @dp: pointer to the delegation * * This function assumes that it's called either from the administrative * interface (nfsd4_revoke_states()) that's revoking a specific delegation * stateid or it's called from a laundromat thread (nfsd4_landromat()) that * determined that this specific state has expired and needs to be revoked * (both mark state with the appropriate stid sc_status mode). It is also * assumed that a reference was taken on the @dp state. * * If this function finds that the @dp state is SC_STATUS_FREED it means * that a FREE_STATEID operation for this stateid has been processed and * we can proceed to removing it from recalled list. However, if @dp state * isn't marked SC_STATUS_FREED, it means we need place it on the cl_revoked * list and wait for the FREE_STATEID to arrive from the client. At the same * time, we need to mark it as SC_STATUS_FREEABLE to indicate to the * nfsd4_free_stateid() function that this stateid has already been added * to the cl_revoked list and that nfsd4_free_stateid() is now responsible * for removing it from the list. Inspection of where the delegation state * in the revocation process is protected by the clp->cl_lock. */ static void revoke_delegation(struct nfs4_delegation *dp) { struct nfs4_client *clp = dp->dl_stid.sc_client; WARN_ON(!list_empty(&dp->dl_recall_lru)); WARN_ON_ONCE(!(dp->dl_stid.sc_status & (SC_STATUS_REVOKED | SC_STATUS_ADMIN_REVOKED))); trace_nfsd_stid_revoke(&dp->dl_stid); spin_lock(&clp->cl_lock); if (dp->dl_stid.sc_status & SC_STATUS_FREED) { list_del_init(&dp->dl_recall_lru); goto out; } list_add(&dp->dl_recall_lru, &clp->cl_revoked); dp->dl_stid.sc_status |= SC_STATUS_FREEABLE; out: spin_unlock(&clp->cl_lock); destroy_unhashed_deleg(dp); } /* * SETCLIENTID state */ static unsigned int clientid_hashval(u32 id) { return id & CLIENT_HASH_MASK; } static unsigned int clientstr_hashval(struct xdr_netobj name) { return opaque_hashval(name.data, 8) & CLIENT_HASH_MASK; } /* * A stateid that had a deny mode associated with it is being released * or downgraded. Recalculate the deny mode on the file. */ static void recalculate_deny_mode(struct nfs4_file *fp) { struct nfs4_ol_stateid *stp; u32 old_deny; spin_lock(&fp->fi_lock); old_deny = fp->fi_share_deny; fp->fi_share_deny = 0; list_for_each_entry(stp, &fp->fi_stateids, st_perfile) { fp->fi_share_deny |= bmap_to_share_mode(stp->st_deny_bmap); if (fp->fi_share_deny == old_deny) break; } spin_unlock(&fp->fi_lock); } static void reset_union_bmap_deny(u32 deny, struct nfs4_ol_stateid *stp) { int i; bool change = false; for (i = 1; i < 4; i++) { if ((i & deny) != i) { change = true; clear_deny(i, stp); } } /* Recalculate per-file deny mode if there was a change */ if (change) recalculate_deny_mode(stp->st_stid.sc_file); } /* release all access and file references for a given stateid */ static void release_all_access(struct nfs4_ol_stateid *stp) { int i; struct nfs4_file *fp = stp->st_stid.sc_file; if (fp && stp->st_deny_bmap != 0) recalculate_deny_mode(fp); for (i = 1; i < 4; i++) { if (test_access(i, stp)) nfs4_file_put_access(stp->st_stid.sc_file, i); clear_access(i, stp); } } static inline void nfs4_free_stateowner(struct nfs4_stateowner *sop) { kfree(sop->so_owner.data); sop->so_ops->so_free(sop); } static void nfs4_put_stateowner(struct nfs4_stateowner *sop) { struct nfs4_client *clp = sop->so_client; might_lock(&clp->cl_lock); if (!atomic_dec_and_lock(&sop->so_count, &clp->cl_lock)) return; sop->so_ops->so_unhash(sop); spin_unlock(&clp->cl_lock); nfs4_free_stateowner(sop); } static bool nfs4_ol_stateid_unhashed(const struct nfs4_ol_stateid *stp) { return list_empty(&stp->st_perfile); } static bool unhash_ol_stateid(struct nfs4_ol_stateid *stp) { struct nfs4_file *fp = stp->st_stid.sc_file; lockdep_assert_held(&stp->st_stateowner->so_client->cl_lock); if (list_empty(&stp->st_perfile)) return false; spin_lock(&fp->fi_lock); list_del_init(&stp->st_perfile); spin_unlock(&fp->fi_lock); list_del(&stp->st_perstateowner); return true; } static void nfs4_free_ol_stateid(struct nfs4_stid *stid) { struct nfs4_ol_stateid *stp = openlockstateid(stid); put_clnt_odstate(stp->st_clnt_odstate); release_all_access(stp); if (stp->st_stateowner) nfs4_put_stateowner(stp->st_stateowner); WARN_ON(!list_empty(&stid->sc_cp_list)); kmem_cache_free(stateid_slab, stid); } static void nfs4_free_lock_stateid(struct nfs4_stid *stid) { struct nfs4_ol_stateid *stp = openlockstateid(stid); struct nfs4_lockowner *lo = lockowner(stp->st_stateowner); struct nfsd_file *nf; nf = find_any_file(stp->st_stid.sc_file); if (nf) { get_file(nf->nf_file); filp_close(nf->nf_file, (fl_owner_t)lo); nfsd_file_put(nf); } nfs4_free_ol_stateid(stid); } /* * Put the persistent reference to an already unhashed generic stateid, while * holding the cl_lock. If it's the last reference, then put it onto the * reaplist for later destruction. */ static void put_ol_stateid_locked(struct nfs4_ol_stateid *stp, struct list_head *reaplist) { struct nfs4_stid *s = &stp->st_stid; struct nfs4_client *clp = s->sc_client; lockdep_assert_held(&clp->cl_lock); WARN_ON_ONCE(!list_empty(&stp->st_locks)); if (!refcount_dec_and_test(&s->sc_count)) { wake_up_all(&close_wq); return; } idr_remove(&clp->cl_stateids, s->sc_stateid.si_opaque.so_id); if (s->sc_status & SC_STATUS_ADMIN_REVOKED) atomic_dec(&s->sc_client->cl_admin_revoked); list_add(&stp->st_locks, reaplist); } static bool unhash_lock_stateid(struct nfs4_ol_stateid *stp) { lockdep_assert_held(&stp->st_stid.sc_client->cl_lock); if (!unhash_ol_stateid(stp)) return false; list_del_init(&stp->st_locks); stp->st_stid.sc_status |= SC_STATUS_CLOSED; return true; } static void release_lock_stateid(struct nfs4_ol_stateid *stp) { struct nfs4_client *clp = stp->st_stid.sc_client; bool unhashed; spin_lock(&clp->cl_lock); unhashed = unhash_lock_stateid(stp); spin_unlock(&clp->cl_lock); if (unhashed) nfs4_put_stid(&stp->st_stid); } static void unhash_lockowner_locked(struct nfs4_lockowner *lo) { struct nfs4_client *clp = lo->lo_owner.so_client; lockdep_assert_held(&clp->cl_lock); list_del_init(&lo->lo_owner.so_strhash); } /* * Free a list of generic stateids that were collected earlier after being * fully unhashed. */ static void free_ol_stateid_reaplist(struct list_head *reaplist) { struct nfs4_ol_stateid *stp; struct nfs4_file *fp; might_sleep(); while (!list_empty(reaplist)) { stp = list_first_entry(reaplist, struct nfs4_ol_stateid, st_locks); list_del(&stp->st_locks); fp = stp->st_stid.sc_file; stp->st_stid.sc_free(&stp->st_stid); if (fp) put_nfs4_file(fp); } } static void release_open_stateid_locks(struct nfs4_ol_stateid *open_stp, struct list_head *reaplist) { struct nfs4_ol_stateid *stp; lockdep_assert_held(&open_stp->st_stid.sc_client->cl_lock); while (!list_empty(&open_stp->st_locks)) { stp = list_entry(open_stp->st_locks.next, struct nfs4_ol_stateid, st_locks); unhash_lock_stateid(stp); put_ol_stateid_locked(stp, reaplist); } } static bool unhash_open_stateid(struct nfs4_ol_stateid *stp, struct list_head *reaplist) { lockdep_assert_held(&stp->st_stid.sc_client->cl_lock); if (!unhash_ol_stateid(stp)) return false; release_open_stateid_locks(stp, reaplist); return true; } static void release_open_stateid(struct nfs4_ol_stateid *stp) { LIST_HEAD(reaplist); spin_lock(&stp->st_stid.sc_client->cl_lock); stp->st_stid.sc_status |= SC_STATUS_CLOSED; if (unhash_open_stateid(stp, &reaplist)) put_ol_stateid_locked(stp, &reaplist); spin_unlock(&stp->st_stid.sc_client->cl_lock); free_ol_stateid_reaplist(&reaplist); } static void unhash_openowner_locked(struct nfs4_openowner *oo) { struct nfs4_client *clp = oo->oo_owner.so_client; lockdep_assert_held(&clp->cl_lock); list_del_init(&oo->oo_owner.so_strhash); list_del_init(&oo->oo_perclient); } static void release_last_closed_stateid(struct nfs4_openowner *oo) { struct nfsd_net *nn = net_generic(oo->oo_owner.so_client->net, nfsd_net_id); struct nfs4_ol_stateid *s; spin_lock(&nn->client_lock); s = oo->oo_last_closed_stid; if (s) { list_del_init(&oo->oo_close_lru); oo->oo_last_closed_stid = NULL; } spin_unlock(&nn->client_lock); if (s) nfs4_put_stid(&s->st_stid); } static void release_openowner(struct nfs4_openowner *oo) { struct nfs4_ol_stateid *stp; struct nfs4_client *clp = oo->oo_owner.so_client; LIST_HEAD(reaplist); spin_lock(&clp->cl_lock); unhash_openowner_locked(oo); while (!list_empty(&oo->oo_owner.so_stateids)) { stp = list_first_entry(&oo->oo_owner.so_stateids, struct nfs4_ol_stateid, st_perstateowner); if (unhash_open_stateid(stp, &reaplist)) put_ol_stateid_locked(stp, &reaplist); } spin_unlock(&clp->cl_lock); free_ol_stateid_reaplist(&reaplist); release_last_closed_stateid(oo); nfs4_put_stateowner(&oo->oo_owner); } static struct nfs4_stid *find_one_sb_stid(struct nfs4_client *clp, struct super_block *sb, unsigned int sc_types) { unsigned long id, tmp; struct nfs4_stid *stid; spin_lock(&clp->cl_lock); idr_for_each_entry_ul(&clp->cl_stateids, stid, tmp, id) if ((stid->sc_type & sc_types) && stid->sc_status == 0 && stid->sc_file->fi_inode->i_sb == sb) { refcount_inc(&stid->sc_count); break; } spin_unlock(&clp->cl_lock); return stid; } /** * nfsd4_revoke_states - revoke all nfsv4 states associated with given filesystem * @net: used to identify instance of nfsd (there is one per net namespace) * @sb: super_block used to identify target filesystem * * All nfs4 states (open, lock, delegation, layout) held by the server instance * and associated with a file on the given filesystem will be revoked resulting * in any files being closed and so all references from nfsd to the filesystem * being released. Thus nfsd will no longer prevent the filesystem from being * unmounted. * * The clients which own the states will subsequently being notified that the * states have been "admin-revoked". */ void nfsd4_revoke_states(struct net *net, struct super_block *sb) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); unsigned int idhashval; unsigned int sc_types; sc_types = SC_TYPE_OPEN | SC_TYPE_LOCK | SC_TYPE_DELEG | SC_TYPE_LAYOUT; spin_lock(&nn->client_lock); for (idhashval = 0; idhashval < CLIENT_HASH_MASK; idhashval++) { struct list_head *head = &nn->conf_id_hashtbl[idhashval]; struct nfs4_client *clp; retry: list_for_each_entry(clp, head, cl_idhash) { struct nfs4_stid *stid = find_one_sb_stid(clp, sb, sc_types); if (stid) { struct nfs4_ol_stateid *stp; struct nfs4_delegation *dp; struct nfs4_layout_stateid *ls; spin_unlock(&nn->client_lock); switch (stid->sc_type) { case SC_TYPE_OPEN: stp = openlockstateid(stid); mutex_lock_nested(&stp->st_mutex, OPEN_STATEID_MUTEX); spin_lock(&clp->cl_lock); if (stid->sc_status == 0) { stid->sc_status |= SC_STATUS_ADMIN_REVOKED; atomic_inc(&clp->cl_admin_revoked); spin_unlock(&clp->cl_lock); release_all_access(stp); } else spin_unlock(&clp->cl_lock); mutex_unlock(&stp->st_mutex); break; case SC_TYPE_LOCK: stp = openlockstateid(stid); mutex_lock_nested(&stp->st_mutex, LOCK_STATEID_MUTEX); spin_lock(&clp->cl_lock); if (stid->sc_status == 0) { struct nfs4_lockowner *lo = lockowner(stp->st_stateowner); struct nfsd_file *nf; stid->sc_status |= SC_STATUS_ADMIN_REVOKED; atomic_inc(&clp->cl_admin_revoked); spin_unlock(&clp->cl_lock); nf = find_any_file(stp->st_stid.sc_file); if (nf) { get_file(nf->nf_file); filp_close(nf->nf_file, (fl_owner_t)lo); nfsd_file_put(nf); } release_all_access(stp); } else spin_unlock(&clp->cl_lock); mutex_unlock(&stp->st_mutex); break; case SC_TYPE_DELEG: refcount_inc(&stid->sc_count); dp = delegstateid(stid); spin_lock(&state_lock); if (!unhash_delegation_locked( dp, SC_STATUS_ADMIN_REVOKED)) dp = NULL; spin_unlock(&state_lock); if (dp) revoke_delegation(dp); break; case SC_TYPE_LAYOUT: ls = layoutstateid(stid); nfsd4_close_layout(ls); break; } nfs4_put_stid(stid); spin_lock(&nn->client_lock); if (clp->cl_minorversion == 0) /* Allow cleanup after a lease period. * store_release ensures cleanup will * see any newly revoked states if it * sees the time updated. */ nn->nfs40_last_revoke = ktime_get_boottime_seconds(); goto retry; } } } spin_unlock(&nn->client_lock); } static inline int hash_sessionid(struct nfs4_sessionid *sessionid) { struct nfsd4_sessionid *sid = (struct nfsd4_sessionid *)sessionid; return sid->sequence % SESSION_HASH_SIZE; } #ifdef CONFIG_SUNRPC_DEBUG static inline void dump_sessionid(const char *fn, struct nfs4_sessionid *sessionid) { u32 *ptr = (u32 *)(&sessionid->data[0]); dprintk("%s: %u:%u:%u:%u\n", fn, ptr[0], ptr[1], ptr[2], ptr[3]); } #else static inline void dump_sessionid(const char *fn, struct nfs4_sessionid *sessionid) { } #endif /* * Bump the seqid on cstate->replay_owner, and clear replay_owner if it * won't be used for replay. */ void nfsd4_bump_seqid(struct nfsd4_compound_state *cstate, __be32 nfserr) { struct nfs4_stateowner *so = cstate->replay_owner; if (nfserr == nfserr_replay_me) return; if (!seqid_mutating_err(ntohl(nfserr))) { nfsd4_cstate_clear_replay(cstate); return; } if (!so) return; if (so->so_is_open_owner) release_last_closed_stateid(openowner(so)); so->so_seqid++; return; } static void gen_sessionid(struct nfsd4_session *ses) { struct nfs4_client *clp = ses->se_client; struct nfsd4_sessionid *sid; sid = (struct nfsd4_sessionid *)ses->se_sessionid.data; sid->clientid = clp->cl_clientid; sid->sequence = current_sessionid++; sid->reserved = 0; } /* * The protocol defines ca_maxresponssize_cached to include the size of * the rpc header, but all we need to cache is the data starting after * the end of the initial SEQUENCE operation--the rest we regenerate * each time. Therefore we can advertise a ca_maxresponssize_cached * value that is the number of bytes in our cache plus a few additional * bytes. In order to stay on the safe side, and not promise more than * we can cache, those additional bytes must be the minimum possible: 24 * bytes of rpc header (xid through accept state, with AUTH_NULL * verifier), 12 for the compound header (with zero-length tag), and 44 * for the SEQUENCE op response: */ #define NFSD_MIN_HDR_SEQ_SZ (24 + 12 + 44) static void free_session_slots(struct nfsd4_session *ses) { int i; for (i = 0; i < ses->se_fchannel.maxreqs; i++) { free_svc_cred(&ses->se_slots[i]->sl_cred); kfree(ses->se_slots[i]); } } /* * We don't actually need to cache the rpc and session headers, so we * can allocate a little less for each slot: */ static inline u32 slot_bytes(struct nfsd4_channel_attrs *ca) { u32 size; if (ca->maxresp_cached < NFSD_MIN_HDR_SEQ_SZ) size = 0; else size = ca->maxresp_cached - NFSD_MIN_HDR_SEQ_SZ; return size + sizeof(struct nfsd4_slot); } /* * XXX: If we run out of reserved DRC memory we could (up to a point) * re-negotiate active sessions and reduce their slot usage to make * room for new connections. For now we just fail the create session. */ static u32 nfsd4_get_drc_mem(struct nfsd4_channel_attrs *ca, struct nfsd_net *nn) { u32 slotsize = slot_bytes(ca); u32 num = ca->maxreqs; unsigned long avail, total_avail; unsigned int scale_factor; spin_lock(&nfsd_drc_lock); if (nfsd_drc_max_mem > nfsd_drc_mem_used) total_avail = nfsd_drc_max_mem - nfsd_drc_mem_used; else /* We have handed out more space than we chose in * set_max_drc() to allow. That isn't really a * problem as long as that doesn't make us think we * have lots more due to integer overflow. */ total_avail = 0; avail = min((unsigned long)NFSD_MAX_MEM_PER_SESSION, total_avail); /* * Never use more than a fraction of the remaining memory, * unless it's the only way to give this client a slot. * The chosen fraction is either 1/8 or 1/number of threads, * whichever is smaller. This ensures there are adequate * slots to support multiple clients per thread. * Give the client one slot even if that would require * over-allocation--it is better than failure. */ scale_factor = max_t(unsigned int, 8, nn->nfsd_serv->sv_nrthreads); avail = clamp_t(unsigned long, avail, slotsize, total_avail/scale_factor); num = min_t(int, num, avail / slotsize); num = max_t(int, num, 1); nfsd_drc_mem_used += num * slotsize; spin_unlock(&nfsd_drc_lock); return num; } static void nfsd4_put_drc_mem(struct nfsd4_channel_attrs *ca) { int slotsize = slot_bytes(ca); spin_lock(&nfsd_drc_lock); nfsd_drc_mem_used -= slotsize * ca->maxreqs; spin_unlock(&nfsd_drc_lock); } static struct nfsd4_session *alloc_session(struct nfsd4_channel_attrs *fattrs, struct nfsd4_channel_attrs *battrs) { int numslots = fattrs->maxreqs; int slotsize = slot_bytes(fattrs); struct nfsd4_session *new; int i; BUILD_BUG_ON(struct_size(new, se_slots, NFSD_MAX_SLOTS_PER_SESSION) > PAGE_SIZE); new = kzalloc(struct_size(new, se_slots, numslots), GFP_KERNEL); if (!new) return NULL; /* allocate each struct nfsd4_slot and data cache in one piece */ for (i = 0; i < numslots; i++) { new->se_slots[i] = kzalloc(slotsize, GFP_KERNEL); if (!new->se_slots[i]) goto out_free; } memcpy(&new->se_fchannel, fattrs, sizeof(struct nfsd4_channel_attrs)); memcpy(&new->se_bchannel, battrs, sizeof(struct nfsd4_channel_attrs)); return new; out_free: while (i--) kfree(new->se_slots[i]); kfree(new); return NULL; } static void free_conn(struct nfsd4_conn *c) { svc_xprt_put(c->cn_xprt); kfree(c); } static void nfsd4_conn_lost(struct svc_xpt_user *u) { struct nfsd4_conn *c = container_of(u, struct nfsd4_conn, cn_xpt_user); struct nfs4_client *clp = c->cn_session->se_client; trace_nfsd_cb_lost(clp); spin_lock(&clp->cl_lock); if (!list_empty(&c->cn_persession)) { list_del(&c->cn_persession); free_conn(c); } nfsd4_probe_callback(clp); spin_unlock(&clp->cl_lock); } static struct nfsd4_conn *alloc_conn(struct svc_rqst *rqstp, u32 flags) { struct nfsd4_conn *conn; conn = kmalloc(sizeof(struct nfsd4_conn), GFP_KERNEL); if (!conn) return NULL; svc_xprt_get(rqstp->rq_xprt); conn->cn_xprt = rqstp->rq_xprt; conn->cn_flags = flags; INIT_LIST_HEAD(&conn->cn_xpt_user.list); return conn; } static void __nfsd4_hash_conn(struct nfsd4_conn *conn, struct nfsd4_session *ses) { conn->cn_session = ses; list_add(&conn->cn_persession, &ses->se_conns); } static void nfsd4_hash_conn(struct nfsd4_conn *conn, struct nfsd4_session *ses) { struct nfs4_client *clp = ses->se_client; spin_lock(&clp->cl_lock); __nfsd4_hash_conn(conn, ses); spin_unlock(&clp->cl_lock); } static int nfsd4_register_conn(struct nfsd4_conn *conn) { conn->cn_xpt_user.callback = nfsd4_conn_lost; return register_xpt_user(conn->cn_xprt, &conn->cn_xpt_user); } static void nfsd4_init_conn(struct svc_rqst *rqstp, struct nfsd4_conn *conn, struct nfsd4_session *ses) { int ret; nfsd4_hash_conn(conn, ses); ret = nfsd4_register_conn(conn); if (ret) /* oops; xprt is already down: */ nfsd4_conn_lost(&conn->cn_xpt_user); /* We may have gained or lost a callback channel: */ nfsd4_probe_callback_sync(ses->se_client); } static struct nfsd4_conn *alloc_conn_from_crses(struct svc_rqst *rqstp, struct nfsd4_create_session *cses) { u32 dir = NFS4_CDFC4_FORE; if (cses->flags & SESSION4_BACK_CHAN) dir |= NFS4_CDFC4_BACK; return alloc_conn(rqstp, dir); } /* must be called under client_lock */ static void nfsd4_del_conns(struct nfsd4_session *s) { struct nfs4_client *clp = s->se_client; struct nfsd4_conn *c; spin_lock(&clp->cl_lock); while (!list_empty(&s->se_conns)) { c = list_first_entry(&s->se_conns, struct nfsd4_conn, cn_persession); list_del_init(&c->cn_persession); spin_unlock(&clp->cl_lock); unregister_xpt_user(c->cn_xprt, &c->cn_xpt_user); free_conn(c); spin_lock(&clp->cl_lock); } spin_unlock(&clp->cl_lock); } static void __free_session(struct nfsd4_session *ses) { free_session_slots(ses); kfree(ses); } static void free_session(struct nfsd4_session *ses) { nfsd4_del_conns(ses); nfsd4_put_drc_mem(&ses->se_fchannel); __free_session(ses); } static void init_session(struct svc_rqst *rqstp, struct nfsd4_session *new, struct nfs4_client *clp, struct nfsd4_create_session *cses) { int idx; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); new->se_client = clp; gen_sessionid(new); INIT_LIST_HEAD(&new->se_conns); new->se_cb_seq_nr = 1; new->se_flags = cses->flags; new->se_cb_prog = cses->callback_prog; new->se_cb_sec = cses->cb_sec; atomic_set(&new->se_ref, 0); idx = hash_sessionid(&new->se_sessionid); list_add(&new->se_hash, &nn->sessionid_hashtbl[idx]); spin_lock(&clp->cl_lock); list_add(&new->se_perclnt, &clp->cl_sessions); spin_unlock(&clp->cl_lock); { struct sockaddr *sa = svc_addr(rqstp); /* * This is a little silly; with sessions there's no real * use for the callback address. Use the peer address * as a reasonable default for now, but consider fixing * the rpc client not to require an address in the * future: */ rpc_copy_addr((struct sockaddr *)&clp->cl_cb_conn.cb_addr, sa); clp->cl_cb_conn.cb_addrlen = svc_addr_len(sa); } } /* caller must hold client_lock */ static struct nfsd4_session * __find_in_sessionid_hashtbl(struct nfs4_sessionid *sessionid, struct net *net) { struct nfsd4_session *elem; int idx; struct nfsd_net *nn = net_generic(net, nfsd_net_id); lockdep_assert_held(&nn->client_lock); dump_sessionid(__func__, sessionid); idx = hash_sessionid(sessionid); /* Search in the appropriate list */ list_for_each_entry(elem, &nn->sessionid_hashtbl[idx], se_hash) { if (!memcmp(elem->se_sessionid.data, sessionid->data, NFS4_MAX_SESSIONID_LEN)) { return elem; } } dprintk("%s: session not found\n", __func__); return NULL; } static struct nfsd4_session * find_in_sessionid_hashtbl(struct nfs4_sessionid *sessionid, struct net *net, __be32 *ret) { struct nfsd4_session *session; __be32 status = nfserr_badsession; session = __find_in_sessionid_hashtbl(sessionid, net); if (!session) goto out; status = nfsd4_get_session_locked(session); if (status) session = NULL; out: *ret = status; return session; } /* caller must hold client_lock */ static void unhash_session(struct nfsd4_session *ses) { struct nfs4_client *clp = ses->se_client; struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); lockdep_assert_held(&nn->client_lock); list_del(&ses->se_hash); spin_lock(&ses->se_client->cl_lock); list_del(&ses->se_perclnt); spin_unlock(&ses->se_client->cl_lock); } /* SETCLIENTID and SETCLIENTID_CONFIRM Helper functions */ static int STALE_CLIENTID(clientid_t *clid, struct nfsd_net *nn) { /* * We're assuming the clid was not given out from a boot * precisely 2^32 (about 136 years) before this one. That seems * a safe assumption: */ if (clid->cl_boot == (u32)nn->boot_time) return 0; trace_nfsd_clid_stale(clid); return 1; } /* * XXX Should we use a slab cache ? * This type of memory management is somewhat inefficient, but we use it * anyway since SETCLIENTID is not a common operation. */ static struct nfs4_client *alloc_client(struct xdr_netobj name, struct nfsd_net *nn) { struct nfs4_client *clp; int i; if (atomic_read(&nn->nfs4_client_count) >= nn->nfs4_max_clients) { mod_delayed_work(laundry_wq, &nn->laundromat_work, 0); return NULL; } clp = kmem_cache_zalloc(client_slab, GFP_KERNEL); if (clp == NULL) return NULL; xdr_netobj_dup(&clp->cl_name, &name, GFP_KERNEL); if (clp->cl_name.data == NULL) goto err_no_name; clp->cl_ownerstr_hashtbl = kmalloc_array(OWNER_HASH_SIZE, sizeof(struct list_head), GFP_KERNEL); if (!clp->cl_ownerstr_hashtbl) goto err_no_hashtbl; clp->cl_callback_wq = alloc_ordered_workqueue("nfsd4_callbacks", 0); if (!clp->cl_callback_wq) goto err_no_callback_wq; for (i = 0; i < OWNER_HASH_SIZE; i++) INIT_LIST_HEAD(&clp->cl_ownerstr_hashtbl[i]); INIT_LIST_HEAD(&clp->cl_sessions); idr_init(&clp->cl_stateids); atomic_set(&clp->cl_rpc_users, 0); clp->cl_cb_state = NFSD4_CB_UNKNOWN; clp->cl_state = NFSD4_ACTIVE; atomic_inc(&nn->nfs4_client_count); atomic_set(&clp->cl_delegs_in_recall, 0); INIT_LIST_HEAD(&clp->cl_idhash); INIT_LIST_HEAD(&clp->cl_openowners); INIT_LIST_HEAD(&clp->cl_delegations); INIT_LIST_HEAD(&clp->cl_lru); INIT_LIST_HEAD(&clp->cl_revoked); #ifdef CONFIG_NFSD_PNFS INIT_LIST_HEAD(&clp->cl_lo_states); #endif INIT_LIST_HEAD(&clp->async_copies); spin_lock_init(&clp->async_lock); spin_lock_init(&clp->cl_lock); rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table"); return clp; err_no_callback_wq: kfree(clp->cl_ownerstr_hashtbl); err_no_hashtbl: kfree(clp->cl_name.data); err_no_name: kmem_cache_free(client_slab, clp); return NULL; } static void __free_client(struct kref *k) { struct nfsdfs_client *c = container_of(k, struct nfsdfs_client, cl_ref); struct nfs4_client *clp = container_of(c, struct nfs4_client, cl_nfsdfs); free_svc_cred(&clp->cl_cred); destroy_workqueue(clp->cl_callback_wq); kfree(clp->cl_ownerstr_hashtbl); kfree(clp->cl_name.data); kfree(clp->cl_nii_domain.data); kfree(clp->cl_nii_name.data); idr_destroy(&clp->cl_stateids); kfree(clp->cl_ra); kmem_cache_free(client_slab, clp); } static void drop_client(struct nfs4_client *clp) { kref_put(&clp->cl_nfsdfs.cl_ref, __free_client); } static void free_client(struct nfs4_client *clp) { while (!list_empty(&clp->cl_sessions)) { struct nfsd4_session *ses; ses = list_entry(clp->cl_sessions.next, struct nfsd4_session, se_perclnt); list_del(&ses->se_perclnt); WARN_ON_ONCE(atomic_read(&ses->se_ref)); free_session(ses); } rpc_destroy_wait_queue(&clp->cl_cb_waitq); if (clp->cl_nfsd_dentry) { nfsd_client_rmdir(clp->cl_nfsd_dentry); clp->cl_nfsd_dentry = NULL; wake_up_all(&expiry_wq); } drop_client(clp); } /* must be called under the client_lock */ static void unhash_client_locked(struct nfs4_client *clp) { struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); struct nfsd4_session *ses; lockdep_assert_held(&nn->client_lock); /* Mark the client as expired! */ clp->cl_time = 0; /* Make it invisible */ if (!list_empty(&clp->cl_idhash)) { list_del_init(&clp->cl_idhash); if (test_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags)) rb_erase(&clp->cl_namenode, &nn->conf_name_tree); else rb_erase(&clp->cl_namenode, &nn->unconf_name_tree); } list_del_init(&clp->cl_lru); spin_lock(&clp->cl_lock); list_for_each_entry(ses, &clp->cl_sessions, se_perclnt) list_del_init(&ses->se_hash); spin_unlock(&clp->cl_lock); } static void unhash_client(struct nfs4_client *clp) { struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); spin_lock(&nn->client_lock); unhash_client_locked(clp); spin_unlock(&nn->client_lock); } static __be32 mark_client_expired_locked(struct nfs4_client *clp) { int users = atomic_read(&clp->cl_rpc_users); trace_nfsd_mark_client_expired(clp, users); if (users) return nfserr_jukebox; unhash_client_locked(clp); return nfs_ok; } static void __destroy_client(struct nfs4_client *clp) { struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); int i; struct nfs4_openowner *oo; struct nfs4_delegation *dp; LIST_HEAD(reaplist); spin_lock(&state_lock); while (!list_empty(&clp->cl_delegations)) { dp = list_entry(clp->cl_delegations.next, struct nfs4_delegation, dl_perclnt); unhash_delegation_locked(dp, SC_STATUS_CLOSED); list_add(&dp->dl_recall_lru, &reaplist); } spin_unlock(&state_lock); while (!list_empty(&reaplist)) { dp = list_entry(reaplist.next, struct nfs4_delegation, dl_recall_lru); list_del_init(&dp->dl_recall_lru); destroy_unhashed_deleg(dp); } while (!list_empty(&clp->cl_revoked)) { dp = list_entry(clp->cl_revoked.next, struct nfs4_delegation, dl_recall_lru); list_del_init(&dp->dl_recall_lru); nfs4_put_stid(&dp->dl_stid); } while (!list_empty(&clp->cl_openowners)) { oo = list_entry(clp->cl_openowners.next, struct nfs4_openowner, oo_perclient); nfs4_get_stateowner(&oo->oo_owner); release_openowner(oo); } for (i = 0; i < OWNER_HASH_SIZE; i++) { struct nfs4_stateowner *so, *tmp; list_for_each_entry_safe(so, tmp, &clp->cl_ownerstr_hashtbl[i], so_strhash) { /* Should be no openowners at this point */ WARN_ON_ONCE(so->so_is_open_owner); remove_blocked_locks(lockowner(so)); } } nfsd4_return_all_client_layouts(clp); nfsd4_shutdown_copy(clp); nfsd4_shutdown_callback(clp); if (clp->cl_cb_conn.cb_xprt) svc_xprt_put(clp->cl_cb_conn.cb_xprt); atomic_add_unless(&nn->nfs4_client_count, -1, 0); nfsd4_dec_courtesy_client_count(nn, clp); free_client(clp); wake_up_all(&expiry_wq); } static void destroy_client(struct nfs4_client *clp) { unhash_client(clp); __destroy_client(clp); } static void inc_reclaim_complete(struct nfs4_client *clp) { struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); if (!nn->track_reclaim_completes) return; if (!nfsd4_find_reclaim_client(clp->cl_name, nn)) return; if (atomic_inc_return(&nn->nr_reclaim_complete) == nn->reclaim_str_hashtbl_size) { printk(KERN_INFO "NFSD: all clients done reclaiming, ending NFSv4 grace period (net %x)\n", clp->net->ns.inum); nfsd4_end_grace(nn); } } static void expire_client(struct nfs4_client *clp) { unhash_client(clp); nfsd4_client_record_remove(clp); __destroy_client(clp); } static void copy_verf(struct nfs4_client *target, nfs4_verifier *source) { memcpy(target->cl_verifier.data, source->data, sizeof(target->cl_verifier.data)); } static void copy_clid(struct nfs4_client *target, struct nfs4_client *source) { target->cl_clientid.cl_boot = source->cl_clientid.cl_boot; target->cl_clientid.cl_id = source->cl_clientid.cl_id; } static int copy_cred(struct svc_cred *target, struct svc_cred *source) { target->cr_principal = kstrdup(source->cr_principal, GFP_KERNEL); target->cr_raw_principal = kstrdup(source->cr_raw_principal, GFP_KERNEL); target->cr_targ_princ = kstrdup(source->cr_targ_princ, GFP_KERNEL); if ((source->cr_principal && !target->cr_principal) || (source->cr_raw_principal && !target->cr_raw_principal) || (source->cr_targ_princ && !target->cr_targ_princ)) return -ENOMEM; target->cr_flavor = source->cr_flavor; target->cr_uid = source->cr_uid; target->cr_gid = source->cr_gid; target->cr_group_info = source->cr_group_info; get_group_info(target->cr_group_info); target->cr_gss_mech = source->cr_gss_mech; if (source->cr_gss_mech) gss_mech_get(source->cr_gss_mech); return 0; } static int compare_blob(const struct xdr_netobj *o1, const struct xdr_netobj *o2) { if (o1->len < o2->len) return -1; if (o1->len > o2->len) return 1; return memcmp(o1->data, o2->data, o1->len); } static int same_verf(nfs4_verifier *v1, nfs4_verifier *v2) { return 0 == memcmp(v1->data, v2->data, sizeof(v1->data)); } static int same_clid(clientid_t *cl1, clientid_t *cl2) { return (cl1->cl_boot == cl2->cl_boot) && (cl1->cl_id == cl2->cl_id); } static bool groups_equal(struct group_info *g1, struct group_info *g2) { int i; if (g1->ngroups != g2->ngroups) return false; for (i=0; i<g1->ngroups; i++) if (!gid_eq(g1->gid[i], g2->gid[i])) return false; return true; } /* * RFC 3530 language requires clid_inuse be returned when the * "principal" associated with a requests differs from that previously * used. We use uid, gid's, and gss principal string as our best * approximation. We also don't want to allow non-gss use of a client * established using gss: in theory cr_principal should catch that * change, but in practice cr_principal can be null even in the gss case * since gssd doesn't always pass down a principal string. */ static bool is_gss_cred(struct svc_cred *cr) { /* Is cr_flavor one of the gss "pseudoflavors"?: */ return (cr->cr_flavor > RPC_AUTH_MAXFLAVOR); } static bool same_creds(struct svc_cred *cr1, struct svc_cred *cr2) { if ((is_gss_cred(cr1) != is_gss_cred(cr2)) || (!uid_eq(cr1->cr_uid, cr2->cr_uid)) || (!gid_eq(cr1->cr_gid, cr2->cr_gid)) || !groups_equal(cr1->cr_group_info, cr2->cr_group_info)) return false; /* XXX: check that cr_targ_princ fields match ? */ if (cr1->cr_principal == cr2->cr_principal) return true; if (!cr1->cr_principal || !cr2->cr_principal) return false; return 0 == strcmp(cr1->cr_principal, cr2->cr_principal); } static bool svc_rqst_integrity_protected(struct svc_rqst *rqstp) { struct svc_cred *cr = &rqstp->rq_cred; u32 service; if (!cr->cr_gss_mech) return false; service = gss_pseudoflavor_to_service(cr->cr_gss_mech, cr->cr_flavor); return service == RPC_GSS_SVC_INTEGRITY || service == RPC_GSS_SVC_PRIVACY; } bool nfsd4_mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp) { struct svc_cred *cr = &rqstp->rq_cred; if (!cl->cl_mach_cred) return true; if (cl->cl_cred.cr_gss_mech != cr->cr_gss_mech) return false; if (!svc_rqst_integrity_protected(rqstp)) return false; if (cl->cl_cred.cr_raw_principal) return 0 == strcmp(cl->cl_cred.cr_raw_principal, cr->cr_raw_principal); if (!cr->cr_principal) return false; return 0 == strcmp(cl->cl_cred.cr_principal, cr->cr_principal); } static void gen_confirm(struct nfs4_client *clp, struct nfsd_net *nn) { __be32 verf[2]; /* * This is opaque to client, so no need to byte-swap. Use * __force to keep sparse happy */ verf[0] = (__force __be32)(u32)ktime_get_real_seconds(); verf[1] = (__force __be32)nn->clverifier_counter++; memcpy(clp->cl_confirm.data, verf, sizeof(clp->cl_confirm.data)); } static void gen_clid(struct nfs4_client *clp, struct nfsd_net *nn) { clp->cl_clientid.cl_boot = (u32)nn->boot_time; clp->cl_clientid.cl_id = nn->clientid_counter++; gen_confirm(clp, nn); } static struct nfs4_stid * find_stateid_locked(struct nfs4_client *cl, stateid_t *t) { struct nfs4_stid *ret; ret = idr_find(&cl->cl_stateids, t->si_opaque.so_id); if (!ret || !ret->sc_type) return NULL; return ret; } static struct nfs4_stid * find_stateid_by_type(struct nfs4_client *cl, stateid_t *t, unsigned short typemask, unsigned short ok_states) { struct nfs4_stid *s; spin_lock(&cl->cl_lock); s = find_stateid_locked(cl, t); if (s != NULL) { if ((s->sc_status & ~ok_states) == 0 && (typemask & s->sc_type)) refcount_inc(&s->sc_count); else s = NULL; } spin_unlock(&cl->cl_lock); return s; } static struct nfs4_client *get_nfsdfs_clp(struct inode *inode) { struct nfsdfs_client *nc; nc = get_nfsdfs_client(inode); if (!nc) return NULL; return container_of(nc, struct nfs4_client, cl_nfsdfs); } static void seq_quote_mem(struct seq_file *m, char *data, int len) { seq_puts(m, "\""); seq_escape_mem(m, data, len, ESCAPE_HEX | ESCAPE_NAP | ESCAPE_APPEND, "\"\\"); seq_puts(m, "\""); } static const char *cb_state2str(int state) { switch (state) { case NFSD4_CB_UP: return "UP"; case NFSD4_CB_UNKNOWN: return "UNKNOWN"; case NFSD4_CB_DOWN: return "DOWN"; case NFSD4_CB_FAULT: return "FAULT"; } return "UNDEFINED"; } static int client_info_show(struct seq_file *m, void *v) { struct inode *inode = file_inode(m->file); struct nfs4_client *clp; u64 clid; clp = get_nfsdfs_clp(inode); if (!clp) return -ENXIO; memcpy(&clid, &clp->cl_clientid, sizeof(clid)); seq_printf(m, "clientid: 0x%llx\n", clid); seq_printf(m, "address: \"%pISpc\"\n", (struct sockaddr *)&clp->cl_addr); if (clp->cl_state == NFSD4_COURTESY) seq_puts(m, "status: courtesy\n"); else if (clp->cl_state == NFSD4_EXPIRABLE) seq_puts(m, "status: expirable\n"); else if (test_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags)) seq_puts(m, "status: confirmed\n"); else seq_puts(m, "status: unconfirmed\n"); seq_printf(m, "seconds from last renew: %lld\n", ktime_get_boottime_seconds() - clp->cl_time); seq_puts(m, "name: "); seq_quote_mem(m, clp->cl_name.data, clp->cl_name.len); seq_printf(m, "\nminor version: %d\n", clp->cl_minorversion); if (clp->cl_nii_domain.data) { seq_puts(m, "Implementation domain: "); seq_quote_mem(m, clp->cl_nii_domain.data, clp->cl_nii_domain.len); seq_puts(m, "\nImplementation name: "); seq_quote_mem(m, clp->cl_nii_name.data, clp->cl_nii_name.len); seq_printf(m, "\nImplementation time: [%lld, %ld]\n", clp->cl_nii_time.tv_sec, clp->cl_nii_time.tv_nsec); } seq_printf(m, "callback state: %s\n", cb_state2str(clp->cl_cb_state)); seq_printf(m, "callback address: \"%pISpc\"\n", &clp->cl_cb_conn.cb_addr); seq_printf(m, "admin-revoked states: %d\n", atomic_read(&clp->cl_admin_revoked)); drop_client(clp); return 0; } DEFINE_SHOW_ATTRIBUTE(client_info); static void *states_start(struct seq_file *s, loff_t *pos) __acquires(&clp->cl_lock) { struct nfs4_client *clp = s->private; unsigned long id = *pos; void *ret; spin_lock(&clp->cl_lock); ret = idr_get_next_ul(&clp->cl_stateids, &id); *pos = id; return ret; } static void *states_next(struct seq_file *s, void *v, loff_t *pos) { struct nfs4_client *clp = s->private; unsigned long id = *pos; void *ret; id = *pos; id++; ret = idr_get_next_ul(&clp->cl_stateids, &id); *pos = id; return ret; } static void states_stop(struct seq_file *s, void *v) __releases(&clp->cl_lock) { struct nfs4_client *clp = s->private; spin_unlock(&clp->cl_lock); } static void nfs4_show_fname(struct seq_file *s, struct nfsd_file *f) { seq_printf(s, "filename: \"%pD2\"", f->nf_file); } static void nfs4_show_superblock(struct seq_file *s, struct nfsd_file *f) { struct inode *inode = file_inode(f->nf_file); seq_printf(s, "superblock: \"%02x:%02x:%ld\"", MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), inode->i_ino); } static void nfs4_show_owner(struct seq_file *s, struct nfs4_stateowner *oo) { seq_puts(s, "owner: "); seq_quote_mem(s, oo->so_owner.data, oo->so_owner.len); } static void nfs4_show_stateid(struct seq_file *s, stateid_t *stid) { seq_printf(s, "0x%.8x", stid->si_generation); seq_printf(s, "%12phN", &stid->si_opaque); } static int nfs4_show_open(struct seq_file *s, struct nfs4_stid *st) { struct nfs4_ol_stateid *ols; struct nfs4_file *nf; struct nfsd_file *file; struct nfs4_stateowner *oo; unsigned int access, deny; ols = openlockstateid(st); oo = ols->st_stateowner; nf = st->sc_file; seq_puts(s, "- "); nfs4_show_stateid(s, &st->sc_stateid); seq_puts(s, ": { type: open, "); access = bmap_to_share_mode(ols->st_access_bmap); deny = bmap_to_share_mode(ols->st_deny_bmap); seq_printf(s, "access: %s%s, ", access & NFS4_SHARE_ACCESS_READ ? "r" : "-", access & NFS4_SHARE_ACCESS_WRITE ? "w" : "-"); seq_printf(s, "deny: %s%s, ", deny & NFS4_SHARE_ACCESS_READ ? "r" : "-", deny & NFS4_SHARE_ACCESS_WRITE ? "w" : "-"); if (nf) { spin_lock(&nf->fi_lock); file = find_any_file_locked(nf); if (file) { nfs4_show_superblock(s, file); seq_puts(s, ", "); nfs4_show_fname(s, file); seq_puts(s, ", "); } spin_unlock(&nf->fi_lock); } else seq_puts(s, "closed, "); nfs4_show_owner(s, oo); if (st->sc_status & SC_STATUS_ADMIN_REVOKED) seq_puts(s, ", admin-revoked"); seq_puts(s, " }\n"); return 0; } static int nfs4_show_lock(struct seq_file *s, struct nfs4_stid *st) { struct nfs4_ol_stateid *ols; struct nfs4_file *nf; struct nfsd_file *file; struct nfs4_stateowner *oo; ols = openlockstateid(st); oo = ols->st_stateowner; nf = st->sc_file; seq_puts(s, "- "); nfs4_show_stateid(s, &st->sc_stateid); seq_puts(s, ": { type: lock, "); spin_lock(&nf->fi_lock); file = find_any_file_locked(nf); if (file) { /* * Note: a lock stateid isn't really the same thing as a lock, * it's the locking state held by one owner on a file, and there * may be multiple (or no) lock ranges associated with it. * (Same for the matter is true of open stateids.) */ nfs4_show_superblock(s, file); /* XXX: open stateid? */ seq_puts(s, ", "); nfs4_show_fname(s, file); seq_puts(s, ", "); } nfs4_show_owner(s, oo); if (st->sc_status & SC_STATUS_ADMIN_REVOKED) seq_puts(s, ", admin-revoked"); seq_puts(s, " }\n"); spin_unlock(&nf->fi_lock); return 0; } static int nfs4_show_deleg(struct seq_file *s, struct nfs4_stid *st) { struct nfs4_delegation *ds; struct nfs4_file *nf; struct nfsd_file *file; ds = delegstateid(st); nf = st->sc_file; seq_puts(s, "- "); nfs4_show_stateid(s, &st->sc_stateid); seq_puts(s, ": { type: deleg, "); seq_printf(s, "access: %s", ds->dl_type == NFS4_OPEN_DELEGATE_READ ? "r" : "w"); /* XXX: lease time, whether it's being recalled. */ spin_lock(&nf->fi_lock); file = nf->fi_deleg_file; if (file) { seq_puts(s, ", "); nfs4_show_superblock(s, file); seq_puts(s, ", "); nfs4_show_fname(s, file); } spin_unlock(&nf->fi_lock); if (st->sc_status & SC_STATUS_ADMIN_REVOKED) seq_puts(s, ", admin-revoked"); seq_puts(s, " }\n"); return 0; } static int nfs4_show_layout(struct seq_file *s, struct nfs4_stid *st) { struct nfs4_layout_stateid *ls; struct nfsd_file *file; ls = container_of(st, struct nfs4_layout_stateid, ls_stid); seq_puts(s, "- "); nfs4_show_stateid(s, &st->sc_stateid); seq_puts(s, ": { type: layout"); /* XXX: What else would be useful? */ spin_lock(&ls->ls_stid.sc_file->fi_lock); file = ls->ls_file; if (file) { seq_puts(s, ", "); nfs4_show_superblock(s, file); seq_puts(s, ", "); nfs4_show_fname(s, file); } spin_unlock(&ls->ls_stid.sc_file->fi_lock); if (st->sc_status & SC_STATUS_ADMIN_REVOKED) seq_puts(s, ", admin-revoked"); seq_puts(s, " }\n"); return 0; } static int states_show(struct seq_file *s, void *v) { struct nfs4_stid *st = v; switch (st->sc_type) { case SC_TYPE_OPEN: return nfs4_show_open(s, st); case SC_TYPE_LOCK: return nfs4_show_lock(s, st); case SC_TYPE_DELEG: return nfs4_show_deleg(s, st); case SC_TYPE_LAYOUT: return nfs4_show_layout(s, st); default: return 0; /* XXX: or SEQ_SKIP? */ } /* XXX: copy stateids? */ } static struct seq_operations states_seq_ops = { .start = states_start, .next = states_next, .stop = states_stop, .show = states_show }; static int client_states_open(struct inode *inode, struct file *file) { struct seq_file *s; struct nfs4_client *clp; int ret; clp = get_nfsdfs_clp(inode); if (!clp) return -ENXIO; ret = seq_open(file, &states_seq_ops); if (ret) return ret; s = file->private_data; s->private = clp; return 0; } static int client_opens_release(struct inode *inode, struct file *file) { struct seq_file *m = file->private_data; struct nfs4_client *clp = m->private; /* XXX: alternatively, we could get/drop in seq start/stop */ drop_client(clp); return seq_release(inode, file); } static const struct file_operations client_states_fops = { .open = client_states_open, .read = seq_read, .llseek = seq_lseek, .release = client_opens_release, }; /* * Normally we refuse to destroy clients that are in use, but here the * administrator is telling us to just do it. We also want to wait * so the caller has a guarantee that the client's locks are gone by * the time the write returns: */ static void force_expire_client(struct nfs4_client *clp) { struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); bool already_expired; trace_nfsd_clid_admin_expired(&clp->cl_clientid); spin_lock(&nn->client_lock); clp->cl_time = 0; spin_unlock(&nn->client_lock); wait_event(expiry_wq, atomic_read(&clp->cl_rpc_users) == 0); spin_lock(&nn->client_lock); already_expired = list_empty(&clp->cl_lru); if (!already_expired) unhash_client_locked(clp); spin_unlock(&nn->client_lock); if (!already_expired) expire_client(clp); else wait_event(expiry_wq, clp->cl_nfsd_dentry == NULL); } static ssize_t client_ctl_write(struct file *file, const char __user *buf, size_t size, loff_t *pos) { char *data; struct nfs4_client *clp; data = simple_transaction_get(file, buf, size); if (IS_ERR(data)) return PTR_ERR(data); if (size != 7 || 0 != memcmp(data, "expire\n", 7)) return -EINVAL; clp = get_nfsdfs_clp(file_inode(file)); if (!clp) return -ENXIO; force_expire_client(clp); drop_client(clp); return 7; } static const struct file_operations client_ctl_fops = { .write = client_ctl_write, .release = simple_transaction_release, }; static const struct tree_descr client_files[] = { [0] = {"info", &client_info_fops, S_IRUSR}, [1] = {"states", &client_states_fops, S_IRUSR}, [2] = {"ctl", &client_ctl_fops, S_IWUSR}, [3] = {""}, }; static int nfsd4_cb_recall_any_done(struct nfsd4_callback *cb, struct rpc_task *task) { trace_nfsd_cb_recall_any_done(cb, task); switch (task->tk_status) { case -NFS4ERR_DELAY: rpc_delay(task, 2 * HZ); return 0; default: return 1; } } static void nfsd4_cb_recall_any_release(struct nfsd4_callback *cb) { struct nfs4_client *clp = cb->cb_clp; clear_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags); drop_client(clp); } static int nfsd4_cb_getattr_done(struct nfsd4_callback *cb, struct rpc_task *task) { struct nfs4_cb_fattr *ncf = container_of(cb, struct nfs4_cb_fattr, ncf_getattr); struct nfs4_delegation *dp = container_of(ncf, struct nfs4_delegation, dl_cb_fattr); trace_nfsd_cb_getattr_done(&dp->dl_stid.sc_stateid, task); ncf->ncf_cb_status = task->tk_status; switch (task->tk_status) { case -NFS4ERR_DELAY: rpc_delay(task, 2 * HZ); return 0; default: return 1; } } static void nfsd4_cb_getattr_release(struct nfsd4_callback *cb) { struct nfs4_cb_fattr *ncf = container_of(cb, struct nfs4_cb_fattr, ncf_getattr); struct nfs4_delegation *dp = container_of(ncf, struct nfs4_delegation, dl_cb_fattr); clear_and_wake_up_bit(CB_GETATTR_BUSY, &ncf->ncf_cb_flags); nfs4_put_stid(&dp->dl_stid); } static const struct nfsd4_callback_ops nfsd4_cb_recall_any_ops = { .done = nfsd4_cb_recall_any_done, .release = nfsd4_cb_recall_any_release, .opcode = OP_CB_RECALL_ANY, }; static const struct nfsd4_callback_ops nfsd4_cb_getattr_ops = { .done = nfsd4_cb_getattr_done, .release = nfsd4_cb_getattr_release, .opcode = OP_CB_GETATTR, }; static void nfs4_cb_getattr(struct nfs4_cb_fattr *ncf) { struct nfs4_delegation *dp = container_of(ncf, struct nfs4_delegation, dl_cb_fattr); if (test_and_set_bit(CB_GETATTR_BUSY, &ncf->ncf_cb_flags)) return; /* set to proper status when nfsd4_cb_getattr_done runs */ ncf->ncf_cb_status = NFS4ERR_IO; refcount_inc(&dp->dl_stid.sc_count); nfsd4_run_cb(&ncf->ncf_getattr); } static struct nfs4_client *create_client(struct xdr_netobj name, struct svc_rqst *rqstp, nfs4_verifier *verf) { struct nfs4_client *clp; struct sockaddr *sa = svc_addr(rqstp); int ret; struct net *net = SVC_NET(rqstp); struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct dentry *dentries[ARRAY_SIZE(client_files)]; clp = alloc_client(name, nn); if (clp == NULL) return NULL; ret = copy_cred(&clp->cl_cred, &rqstp->rq_cred); if (ret) { free_client(clp); return NULL; } gen_clid(clp, nn); kref_init(&clp->cl_nfsdfs.cl_ref); nfsd4_init_cb(&clp->cl_cb_null, clp, NULL, NFSPROC4_CLNT_CB_NULL); clp->cl_time = ktime_get_boottime_seconds(); clear_bit(0, &clp->cl_cb_slot_busy); copy_verf(clp, verf); memcpy(&clp->cl_addr, sa, sizeof(struct sockaddr_storage)); clp->cl_cb_session = NULL; clp->net = net; clp->cl_nfsd_dentry = nfsd_client_mkdir( nn, &clp->cl_nfsdfs, clp->cl_clientid.cl_id - nn->clientid_base, client_files, dentries); clp->cl_nfsd_info_dentry = dentries[0]; if (!clp->cl_nfsd_dentry) { free_client(clp); return NULL; } clp->cl_ra = kzalloc(sizeof(*clp->cl_ra), GFP_KERNEL); if (!clp->cl_ra) { free_client(clp); return NULL; } clp->cl_ra_time = 0; nfsd4_init_cb(&clp->cl_ra->ra_cb, clp, &nfsd4_cb_recall_any_ops, NFSPROC4_CLNT_CB_RECALL_ANY); return clp; } static void add_clp_to_name_tree(struct nfs4_client *new_clp, struct rb_root *root) { struct rb_node **new = &(root->rb_node), *parent = NULL; struct nfs4_client *clp; while (*new) { clp = rb_entry(*new, struct nfs4_client, cl_namenode); parent = *new; if (compare_blob(&clp->cl_name, &new_clp->cl_name) > 0) new = &((*new)->rb_left); else new = &((*new)->rb_right); } rb_link_node(&new_clp->cl_namenode, parent, new); rb_insert_color(&new_clp->cl_namenode, root); } static struct nfs4_client * find_clp_in_name_tree(struct xdr_netobj *name, struct rb_root *root) { int cmp; struct rb_node *node = root->rb_node; struct nfs4_client *clp; while (node) { clp = rb_entry(node, struct nfs4_client, cl_namenode); cmp = compare_blob(&clp->cl_name, name); if (cmp > 0) node = node->rb_left; else if (cmp < 0) node = node->rb_right; else return clp; } return NULL; } static void add_to_unconfirmed(struct nfs4_client *clp) { unsigned int idhashval; struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); lockdep_assert_held(&nn->client_lock); clear_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags); add_clp_to_name_tree(clp, &nn->unconf_name_tree); idhashval = clientid_hashval(clp->cl_clientid.cl_id); list_add(&clp->cl_idhash, &nn->unconf_id_hashtbl[idhashval]); renew_client_locked(clp); } static void move_to_confirmed(struct nfs4_client *clp) { unsigned int idhashval = clientid_hashval(clp->cl_clientid.cl_id); struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); lockdep_assert_held(&nn->client_lock); list_move(&clp->cl_idhash, &nn->conf_id_hashtbl[idhashval]); rb_erase(&clp->cl_namenode, &nn->unconf_name_tree); add_clp_to_name_tree(clp, &nn->conf_name_tree); set_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags); trace_nfsd_clid_confirmed(&clp->cl_clientid); renew_client_locked(clp); } static struct nfs4_client * find_client_in_id_table(struct list_head *tbl, clientid_t *clid, bool sessions) { struct nfs4_client *clp; unsigned int idhashval = clientid_hashval(clid->cl_id); list_for_each_entry(clp, &tbl[idhashval], cl_idhash) { if (same_clid(&clp->cl_clientid, clid)) { if ((bool)clp->cl_minorversion != sessions) return NULL; renew_client_locked(clp); return clp; } } return NULL; } static struct nfs4_client * find_confirmed_client(clientid_t *clid, bool sessions, struct nfsd_net *nn) { struct list_head *tbl = nn->conf_id_hashtbl; lockdep_assert_held(&nn->client_lock); return find_client_in_id_table(tbl, clid, sessions); } static struct nfs4_client * find_unconfirmed_client(clientid_t *clid, bool sessions, struct nfsd_net *nn) { struct list_head *tbl = nn->unconf_id_hashtbl; lockdep_assert_held(&nn->client_lock); return find_client_in_id_table(tbl, clid, sessions); } static bool clp_used_exchangeid(struct nfs4_client *clp) { return clp->cl_exchange_flags != 0; } static struct nfs4_client * find_confirmed_client_by_name(struct xdr_netobj *name, struct nfsd_net *nn) { lockdep_assert_held(&nn->client_lock); return find_clp_in_name_tree(name, &nn->conf_name_tree); } static struct nfs4_client * find_unconfirmed_client_by_name(struct xdr_netobj *name, struct nfsd_net *nn) { lockdep_assert_held(&nn->client_lock); return find_clp_in_name_tree(name, &nn->unconf_name_tree); } static void gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se, struct svc_rqst *rqstp) { struct nfs4_cb_conn *conn = &clp->cl_cb_conn; struct sockaddr *sa = svc_addr(rqstp); u32 scopeid = rpc_get_scope_id(sa); unsigned short expected_family; /* Currently, we only support tcp and tcp6 for the callback channel */ if (se->se_callback_netid_len == 3 && !memcmp(se->se_callback_netid_val, "tcp", 3)) expected_family = AF_INET; else if (se->se_callback_netid_len == 4 && !memcmp(se->se_callback_netid_val, "tcp6", 4)) expected_family = AF_INET6; else goto out_err; conn->cb_addrlen = rpc_uaddr2sockaddr(clp->net, se->se_callback_addr_val, se->se_callback_addr_len, (struct sockaddr *)&conn->cb_addr, sizeof(conn->cb_addr)); if (!conn->cb_addrlen || conn->cb_addr.ss_family != expected_family) goto out_err; if (conn->cb_addr.ss_family == AF_INET6) ((struct sockaddr_in6 *)&conn->cb_addr)->sin6_scope_id = scopeid; conn->cb_prog = se->se_callback_prog; conn->cb_ident = se->se_callback_ident; memcpy(&conn->cb_saddr, &rqstp->rq_daddr, rqstp->rq_daddrlen); trace_nfsd_cb_args(clp, conn); return; out_err: conn->cb_addr.ss_family = AF_UNSPEC; conn->cb_addrlen = 0; trace_nfsd_cb_nodelegs(clp); return; } /* * Cache a reply. nfsd4_check_resp_size() has bounded the cache size. */ static void nfsd4_store_cache_entry(struct nfsd4_compoundres *resp) { struct xdr_buf *buf = resp->xdr->buf; struct nfsd4_slot *slot = resp->cstate.slot; unsigned int base; dprintk("--> %s slot %p\n", __func__, slot); slot->sl_flags |= NFSD4_SLOT_INITIALIZED; slot->sl_opcnt = resp->opcnt; slot->sl_status = resp->cstate.status; free_svc_cred(&slot->sl_cred); copy_cred(&slot->sl_cred, &resp->rqstp->rq_cred); if (!nfsd4_cache_this(resp)) { slot->sl_flags &= ~NFSD4_SLOT_CACHED; return; } slot->sl_flags |= NFSD4_SLOT_CACHED; base = resp->cstate.data_offset; slot->sl_datalen = buf->len - base; if (read_bytes_from_xdr_buf(buf, base, slot->sl_data, slot->sl_datalen)) WARN(1, "%s: sessions DRC could not cache compound\n", __func__); return; } /* * Encode the replay sequence operation from the slot values. * If cachethis is FALSE encode the uncached rep error on the next * operation which sets resp->p and increments resp->opcnt for * nfs4svc_encode_compoundres. * */ static __be32 nfsd4_enc_sequence_replay(struct nfsd4_compoundargs *args, struct nfsd4_compoundres *resp) { struct nfsd4_op *op; struct nfsd4_slot *slot = resp->cstate.slot; /* Encode the replayed sequence operation */ op = &args->ops[resp->opcnt - 1]; nfsd4_encode_operation(resp, op); if (slot->sl_flags & NFSD4_SLOT_CACHED) return op->status; if (args->opcnt == 1) { /* * The original operation wasn't a solo sequence--we * always cache those--so this retry must not match the * original: */ op->status = nfserr_seq_false_retry; } else { op = &args->ops[resp->opcnt++]; op->status = nfserr_retry_uncached_rep; nfsd4_encode_operation(resp, op); } return op->status; } /* * The sequence operation is not cached because we can use the slot and * session values. */ static __be32 nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp, struct nfsd4_sequence *seq) { struct nfsd4_slot *slot = resp->cstate.slot; struct xdr_stream *xdr = resp->xdr; __be32 *p; __be32 status; dprintk("--> %s slot %p\n", __func__, slot); status = nfsd4_enc_sequence_replay(resp->rqstp->rq_argp, resp); if (status) return status; p = xdr_reserve_space(xdr, slot->sl_datalen); if (!p) { WARN_ON_ONCE(1); return nfserr_serverfault; } xdr_encode_opaque_fixed(p, slot->sl_data, slot->sl_datalen); xdr_commit_encode(xdr); resp->opcnt = slot->sl_opcnt; return slot->sl_status; } /* * Set the exchange_id flags returned by the server. */ static void nfsd4_set_ex_flags(struct nfs4_client *new, struct nfsd4_exchange_id *clid) { #ifdef CONFIG_NFSD_PNFS new->cl_exchange_flags |= EXCHGID4_FLAG_USE_PNFS_MDS; #else new->cl_exchange_flags |= EXCHGID4_FLAG_USE_NON_PNFS; #endif /* Referrals are supported, Migration is not. */ new->cl_exchange_flags |= EXCHGID4_FLAG_SUPP_MOVED_REFER; /* set the wire flags to return to client. */ clid->flags = new->cl_exchange_flags; } static bool client_has_openowners(struct nfs4_client *clp) { struct nfs4_openowner *oo; list_for_each_entry(oo, &clp->cl_openowners, oo_perclient) { if (!list_empty(&oo->oo_owner.so_stateids)) return true; } return false; } static bool client_has_state(struct nfs4_client *clp) { return client_has_openowners(clp) #ifdef CONFIG_NFSD_PNFS || !list_empty(&clp->cl_lo_states) #endif || !list_empty(&clp->cl_delegations) || !list_empty(&clp->cl_sessions) || !list_empty(&clp->async_copies); } static __be32 copy_impl_id(struct nfs4_client *clp, struct nfsd4_exchange_id *exid) { if (!exid->nii_domain.data) return 0; xdr_netobj_dup(&clp->cl_nii_domain, &exid->nii_domain, GFP_KERNEL); if (!clp->cl_nii_domain.data) return nfserr_jukebox; xdr_netobj_dup(&clp->cl_nii_name, &exid->nii_name, GFP_KERNEL); if (!clp->cl_nii_name.data) return nfserr_jukebox; clp->cl_nii_time = exid->nii_time; return 0; } __be32 nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_exchange_id *exid = &u->exchange_id; struct nfs4_client *conf, *new; struct nfs4_client *unconf = NULL; __be32 status; char addr_str[INET6_ADDRSTRLEN]; nfs4_verifier verf = exid->verifier; struct sockaddr *sa = svc_addr(rqstp); bool update = exid->flags & EXCHGID4_FLAG_UPD_CONFIRMED_REC_A; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); rpc_ntop(sa, addr_str, sizeof(addr_str)); dprintk("%s rqstp=%p exid=%p clname.len=%u clname.data=%p " "ip_addr=%s flags %x, spa_how %u\n", __func__, rqstp, exid, exid->clname.len, exid->clname.data, addr_str, exid->flags, exid->spa_how); if (exid->flags & ~EXCHGID4_FLAG_MASK_A) return nfserr_inval; new = create_client(exid->clname, rqstp, &verf); if (new == NULL) return nfserr_jukebox; status = copy_impl_id(new, exid); if (status) goto out_nolock; switch (exid->spa_how) { case SP4_MACH_CRED: exid->spo_must_enforce[0] = 0; exid->spo_must_enforce[1] = ( 1 << (OP_BIND_CONN_TO_SESSION - 32) | 1 << (OP_EXCHANGE_ID - 32) | 1 << (OP_CREATE_SESSION - 32) | 1 << (OP_DESTROY_SESSION - 32) | 1 << (OP_DESTROY_CLIENTID - 32)); exid->spo_must_allow[0] &= (1 << (OP_CLOSE) | 1 << (OP_OPEN_DOWNGRADE) | 1 << (OP_LOCKU) | 1 << (OP_DELEGRETURN)); exid->spo_must_allow[1] &= ( 1 << (OP_TEST_STATEID - 32) | 1 << (OP_FREE_STATEID - 32)); if (!svc_rqst_integrity_protected(rqstp)) { status = nfserr_inval; goto out_nolock; } /* * Sometimes userspace doesn't give us a principal. * Which is a bug, really. Anyway, we can't enforce * MACH_CRED in that case, better to give up now: */ if (!new->cl_cred.cr_principal && !new->cl_cred.cr_raw_principal) { status = nfserr_serverfault; goto out_nolock; } new->cl_mach_cred = true; break; case SP4_NONE: break; default: /* checked by xdr code */ WARN_ON_ONCE(1); fallthrough; case SP4_SSV: status = nfserr_encr_alg_unsupp; goto out_nolock; } /* Cases below refer to rfc 5661 section 18.35.4: */ spin_lock(&nn->client_lock); conf = find_confirmed_client_by_name(&exid->clname, nn); if (conf) { bool creds_match = same_creds(&conf->cl_cred, &rqstp->rq_cred); bool verfs_match = same_verf(&verf, &conf->cl_verifier); if (update) { if (!clp_used_exchangeid(conf)) { /* buggy client */ status = nfserr_inval; goto out; } if (!nfsd4_mach_creds_match(conf, rqstp)) { status = nfserr_wrong_cred; goto out; } if (!creds_match) { /* case 9 */ status = nfserr_perm; goto out; } if (!verfs_match) { /* case 8 */ status = nfserr_not_same; goto out; } /* case 6 */ exid->flags |= EXCHGID4_FLAG_CONFIRMED_R; trace_nfsd_clid_confirmed_r(conf); goto out_copy; } if (!creds_match) { /* case 3 */ if (client_has_state(conf)) { status = nfserr_clid_inuse; trace_nfsd_clid_cred_mismatch(conf, rqstp); goto out; } goto out_new; } if (verfs_match) { /* case 2 */ conf->cl_exchange_flags |= EXCHGID4_FLAG_CONFIRMED_R; trace_nfsd_clid_confirmed_r(conf); goto out_copy; } /* case 5, client reboot */ trace_nfsd_clid_verf_mismatch(conf, rqstp, &verf); conf = NULL; goto out_new; } if (update) { /* case 7 */ status = nfserr_noent; goto out; } unconf = find_unconfirmed_client_by_name(&exid->clname, nn); if (unconf) /* case 4, possible retry or client restart */ unhash_client_locked(unconf); /* case 1, new owner ID */ trace_nfsd_clid_fresh(new); out_new: if (conf) { status = mark_client_expired_locked(conf); if (status) goto out; trace_nfsd_clid_replaced(&conf->cl_clientid); } new->cl_minorversion = cstate->minorversion; new->cl_spo_must_allow.u.words[0] = exid->spo_must_allow[0]; new->cl_spo_must_allow.u.words[1] = exid->spo_must_allow[1]; /* Contrived initial CREATE_SESSION response */ new->cl_cs_slot.sl_status = nfserr_seq_misordered; add_to_unconfirmed(new); swap(new, conf); out_copy: exid->clientid.cl_boot = conf->cl_clientid.cl_boot; exid->clientid.cl_id = conf->cl_clientid.cl_id; exid->seqid = conf->cl_cs_slot.sl_seqid + 1; nfsd4_set_ex_flags(conf, exid); dprintk("nfsd4_exchange_id seqid %d flags %x\n", conf->cl_cs_slot.sl_seqid, conf->cl_exchange_flags); status = nfs_ok; out: spin_unlock(&nn->client_lock); out_nolock: if (new) expire_client(new); if (unconf) { trace_nfsd_clid_expire_unconf(&unconf->cl_clientid); expire_client(unconf); } return status; } static __be32 check_slot_seqid(u32 seqid, u32 slot_seqid, bool slot_inuse) { /* The slot is in use, and no response has been sent. */ if (slot_inuse) { if (seqid == slot_seqid) return nfserr_jukebox; else return nfserr_seq_misordered; } /* Note unsigned 32-bit arithmetic handles wraparound: */ if (likely(seqid == slot_seqid + 1)) return nfs_ok; if (seqid == slot_seqid) return nfserr_replay_cache; return nfserr_seq_misordered; } /* * Cache the create session result into the create session single DRC * slot cache by saving the xdr structure. sl_seqid has been set. * Do this for solo or embedded create session operations. */ static void nfsd4_cache_create_session(struct nfsd4_create_session *cr_ses, struct nfsd4_clid_slot *slot, __be32 nfserr) { slot->sl_status = nfserr; memcpy(&slot->sl_cr_ses, cr_ses, sizeof(*cr_ses)); } static __be32 nfsd4_replay_create_session(struct nfsd4_create_session *cr_ses, struct nfsd4_clid_slot *slot) { memcpy(cr_ses, &slot->sl_cr_ses, sizeof(*cr_ses)); return slot->sl_status; } #define NFSD_MIN_REQ_HDR_SEQ_SZ ((\ 2 * 2 + /* credential,verifier: AUTH_NULL, length 0 */ \ 1 + /* MIN tag is length with zero, only length */ \ 3 + /* version, opcount, opcode */ \ XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + \ /* seqid, slotID, slotID, cache */ \ 4 ) * sizeof(__be32)) #define NFSD_MIN_RESP_HDR_SEQ_SZ ((\ 2 + /* verifier: AUTH_NULL, length 0 */\ 1 + /* status */ \ 1 + /* MIN tag is length with zero, only length */ \ 3 + /* opcount, opcode, opstatus*/ \ XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + \ /* seqid, slotID, slotID, slotID, status */ \ 5 ) * sizeof(__be32)) static __be32 check_forechannel_attrs(struct nfsd4_channel_attrs *ca, struct nfsd_net *nn) { u32 maxrpc = nn->nfsd_serv->sv_max_mesg; if (ca->maxreq_sz < NFSD_MIN_REQ_HDR_SEQ_SZ) return nfserr_toosmall; if (ca->maxresp_sz < NFSD_MIN_RESP_HDR_SEQ_SZ) return nfserr_toosmall; ca->headerpadsz = 0; ca->maxreq_sz = min_t(u32, ca->maxreq_sz, maxrpc); ca->maxresp_sz = min_t(u32, ca->maxresp_sz, maxrpc); ca->maxops = min_t(u32, ca->maxops, NFSD_MAX_OPS_PER_COMPOUND); ca->maxresp_cached = min_t(u32, ca->maxresp_cached, NFSD_SLOT_CACHE_SIZE + NFSD_MIN_HDR_SEQ_SZ); ca->maxreqs = min_t(u32, ca->maxreqs, NFSD_MAX_SLOTS_PER_SESSION); /* * Note decreasing slot size below client's request may make it * difficult for client to function correctly, whereas * decreasing the number of slots will (just?) affect * performance. When short on memory we therefore prefer to * decrease number of slots instead of their size. Clients that * request larger slots than they need will get poor results: * Note that we always allow at least one slot, because our * accounting is soft and provides no guarantees either way. */ ca->maxreqs = nfsd4_get_drc_mem(ca, nn); return nfs_ok; } /* * Server's NFSv4.1 backchannel support is AUTH_SYS-only for now. * These are based on similar macros in linux/sunrpc/msg_prot.h . */ #define RPC_MAX_HEADER_WITH_AUTH_SYS \ (RPC_CALLHDRSIZE + 2 * (2 + UNX_CALLSLACK)) #define RPC_MAX_REPHEADER_WITH_AUTH_SYS \ (RPC_REPHDRSIZE + (2 + NUL_REPLYSLACK)) #define NFSD_CB_MAX_REQ_SZ ((NFS4_enc_cb_recall_sz + \ RPC_MAX_HEADER_WITH_AUTH_SYS) * sizeof(__be32)) #define NFSD_CB_MAX_RESP_SZ ((NFS4_dec_cb_recall_sz + \ RPC_MAX_REPHEADER_WITH_AUTH_SYS) * \ sizeof(__be32)) static __be32 check_backchannel_attrs(struct nfsd4_channel_attrs *ca) { ca->headerpadsz = 0; if (ca->maxreq_sz < NFSD_CB_MAX_REQ_SZ) return nfserr_toosmall; if (ca->maxresp_sz < NFSD_CB_MAX_RESP_SZ) return nfserr_toosmall; ca->maxresp_cached = 0; if (ca->maxops < 2) return nfserr_toosmall; return nfs_ok; } static __be32 nfsd4_check_cb_sec(struct nfsd4_cb_sec *cbs) { switch (cbs->flavor) { case RPC_AUTH_NULL: case RPC_AUTH_UNIX: return nfs_ok; default: /* * GSS case: the spec doesn't allow us to return this * error. But it also doesn't allow us not to support * GSS. * I'd rather this fail hard than return some error the * client might think it can already handle: */ return nfserr_encr_alg_unsupp; } } __be32 nfsd4_create_session(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_create_session *cr_ses = &u->create_session; struct sockaddr *sa = svc_addr(rqstp); struct nfs4_client *conf, *unconf; struct nfsd4_clid_slot *cs_slot; struct nfs4_client *old = NULL; struct nfsd4_session *new; struct nfsd4_conn *conn; __be32 status = 0; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); if (cr_ses->flags & ~SESSION4_FLAG_MASK_A) return nfserr_inval; status = nfsd4_check_cb_sec(&cr_ses->cb_sec); if (status) return status; status = check_forechannel_attrs(&cr_ses->fore_channel, nn); if (status) return status; status = check_backchannel_attrs(&cr_ses->back_channel); if (status) goto out_release_drc_mem; status = nfserr_jukebox; new = alloc_session(&cr_ses->fore_channel, &cr_ses->back_channel); if (!new) goto out_release_drc_mem; conn = alloc_conn_from_crses(rqstp, cr_ses); if (!conn) goto out_free_session; spin_lock(&nn->client_lock); /* RFC 8881 Section 18.36.4 Phase 1: Client record look-up. */ unconf = find_unconfirmed_client(&cr_ses->clientid, true, nn); conf = find_confirmed_client(&cr_ses->clientid, true, nn); if (!conf && !unconf) { status = nfserr_stale_clientid; goto out_free_conn; } /* RFC 8881 Section 18.36.4 Phase 2: Sequence ID processing. */ if (conf) { cs_slot = &conf->cl_cs_slot; trace_nfsd_slot_seqid_conf(conf, cr_ses); } else { cs_slot = &unconf->cl_cs_slot; trace_nfsd_slot_seqid_unconf(unconf, cr_ses); } status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0); switch (status) { case nfs_ok: cs_slot->sl_seqid++; cr_ses->seqid = cs_slot->sl_seqid; break; case nfserr_replay_cache: status = nfsd4_replay_create_session(cr_ses, cs_slot); fallthrough; case nfserr_jukebox: /* The server MUST NOT cache NFS4ERR_DELAY */ goto out_free_conn; default: goto out_cache_error; } /* RFC 8881 Section 18.36.4 Phase 3: Client ID confirmation. */ if (conf) { status = nfserr_wrong_cred; if (!nfsd4_mach_creds_match(conf, rqstp)) goto out_cache_error; } else { status = nfserr_clid_inuse; if (!same_creds(&unconf->cl_cred, &rqstp->rq_cred) || !rpc_cmp_addr(sa, (struct sockaddr *) &unconf->cl_addr)) { trace_nfsd_clid_cred_mismatch(unconf, rqstp); goto out_cache_error; } status = nfserr_wrong_cred; if (!nfsd4_mach_creds_match(unconf, rqstp)) goto out_cache_error; old = find_confirmed_client_by_name(&unconf->cl_name, nn); if (old) { status = mark_client_expired_locked(old); if (status) goto out_expired_error; trace_nfsd_clid_replaced(&old->cl_clientid); } move_to_confirmed(unconf); conf = unconf; } /* RFC 8881 Section 18.36.4 Phase 4: Session creation. */ status = nfs_ok; /* Persistent sessions are not supported */ cr_ses->flags &= ~SESSION4_PERSIST; /* Upshifting from TCP to RDMA is not supported */ cr_ses->flags &= ~SESSION4_RDMA; init_session(rqstp, new, conf, cr_ses); nfsd4_get_session_locked(new); memcpy(cr_ses->sessionid.data, new->se_sessionid.data, NFS4_MAX_SESSIONID_LEN); /* cache solo and embedded create sessions under the client_lock */ nfsd4_cache_create_session(cr_ses, cs_slot, status); spin_unlock(&nn->client_lock); if (conf == unconf) fsnotify_dentry(conf->cl_nfsd_info_dentry, FS_MODIFY); /* init connection and backchannel */ nfsd4_init_conn(rqstp, conn, new); nfsd4_put_session(new); if (old) expire_client(old); return status; out_expired_error: old = NULL; /* * Revert the slot seq_nr change so the server will process * the client's resend instead of returning a cached response. */ if (status == nfserr_jukebox) { cs_slot->sl_seqid--; cr_ses->seqid = cs_slot->sl_seqid; goto out_free_conn; } out_cache_error: nfsd4_cache_create_session(cr_ses, cs_slot, status); out_free_conn: spin_unlock(&nn->client_lock); free_conn(conn); if (old) expire_client(old); out_free_session: __free_session(new); out_release_drc_mem: nfsd4_put_drc_mem(&cr_ses->fore_channel); return status; } static __be32 nfsd4_map_bcts_dir(u32 *dir) { switch (*dir) { case NFS4_CDFC4_FORE: case NFS4_CDFC4_BACK: return nfs_ok; case NFS4_CDFC4_FORE_OR_BOTH: case NFS4_CDFC4_BACK_OR_BOTH: *dir = NFS4_CDFC4_BOTH; return nfs_ok; } return nfserr_inval; } __be32 nfsd4_backchannel_ctl(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_backchannel_ctl *bc = &u->backchannel_ctl; struct nfsd4_session *session = cstate->session; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); __be32 status; status = nfsd4_check_cb_sec(&bc->bc_cb_sec); if (status) return status; spin_lock(&nn->client_lock); session->se_cb_prog = bc->bc_cb_program; session->se_cb_sec = bc->bc_cb_sec; spin_unlock(&nn->client_lock); nfsd4_probe_callback(session->se_client); return nfs_ok; } static struct nfsd4_conn *__nfsd4_find_conn(struct svc_xprt *xpt, struct nfsd4_session *s) { struct nfsd4_conn *c; list_for_each_entry(c, &s->se_conns, cn_persession) { if (c->cn_xprt == xpt) { return c; } } return NULL; } static __be32 nfsd4_match_existing_connection(struct svc_rqst *rqst, struct nfsd4_session *session, u32 req, struct nfsd4_conn **conn) { struct nfs4_client *clp = session->se_client; struct svc_xprt *xpt = rqst->rq_xprt; struct nfsd4_conn *c; __be32 status; /* Following the last paragraph of RFC 5661 Section 18.34.3: */ spin_lock(&clp->cl_lock); c = __nfsd4_find_conn(xpt, session); if (!c) status = nfserr_noent; else if (req == c->cn_flags) status = nfs_ok; else if (req == NFS4_CDFC4_FORE_OR_BOTH && c->cn_flags != NFS4_CDFC4_BACK) status = nfs_ok; else if (req == NFS4_CDFC4_BACK_OR_BOTH && c->cn_flags != NFS4_CDFC4_FORE) status = nfs_ok; else status = nfserr_inval; spin_unlock(&clp->cl_lock); if (status == nfs_ok && conn) *conn = c; return status; } __be32 nfsd4_bind_conn_to_session(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_bind_conn_to_session *bcts = &u->bind_conn_to_session; __be32 status; struct nfsd4_conn *conn; struct nfsd4_session *session; struct net *net = SVC_NET(rqstp); struct nfsd_net *nn = net_generic(net, nfsd_net_id); if (!nfsd4_last_compound_op(rqstp)) return nfserr_not_only_op; spin_lock(&nn->client_lock); session = find_in_sessionid_hashtbl(&bcts->sessionid, net, &status); spin_unlock(&nn->client_lock); if (!session) goto out_no_session; status = nfserr_wrong_cred; if (!nfsd4_mach_creds_match(session->se_client, rqstp)) goto out; status = nfsd4_match_existing_connection(rqstp, session, bcts->dir, &conn); if (status == nfs_ok) { if (bcts->dir == NFS4_CDFC4_FORE_OR_BOTH || bcts->dir == NFS4_CDFC4_BACK) conn->cn_flags |= NFS4_CDFC4_BACK; nfsd4_probe_callback(session->se_client); goto out; } if (status == nfserr_inval) goto out; status = nfsd4_map_bcts_dir(&bcts->dir); if (status) goto out; conn = alloc_conn(rqstp, bcts->dir); status = nfserr_jukebox; if (!conn) goto out; nfsd4_init_conn(rqstp, conn, session); status = nfs_ok; out: nfsd4_put_session(session); out_no_session: return status; } static bool nfsd4_compound_in_session(struct nfsd4_compound_state *cstate, struct nfs4_sessionid *sid) { if (!cstate->session) return false; return !memcmp(sid, &cstate->session->se_sessionid, sizeof(*sid)); } __be32 nfsd4_destroy_session(struct svc_rqst *r, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfs4_sessionid *sessionid = &u->destroy_session.sessionid; struct nfsd4_session *ses; __be32 status; int ref_held_by_me = 0; struct net *net = SVC_NET(r); struct nfsd_net *nn = net_generic(net, nfsd_net_id); status = nfserr_not_only_op; if (nfsd4_compound_in_session(cstate, sessionid)) { if (!nfsd4_last_compound_op(r)) goto out; ref_held_by_me++; } dump_sessionid(__func__, sessionid); spin_lock(&nn->client_lock); ses = find_in_sessionid_hashtbl(sessionid, net, &status); if (!ses) goto out_client_lock; status = nfserr_wrong_cred; if (!nfsd4_mach_creds_match(ses->se_client, r)) goto out_put_session; status = mark_session_dead_locked(ses, 1 + ref_held_by_me); if (status) goto out_put_session; unhash_session(ses); spin_unlock(&nn->client_lock); nfsd4_probe_callback_sync(ses->se_client); spin_lock(&nn->client_lock); status = nfs_ok; out_put_session: nfsd4_put_session_locked(ses); out_client_lock: spin_unlock(&nn->client_lock); out: return status; } static __be32 nfsd4_sequence_check_conn(struct nfsd4_conn *new, struct nfsd4_session *ses) { struct nfs4_client *clp = ses->se_client; struct nfsd4_conn *c; __be32 status = nfs_ok; int ret; spin_lock(&clp->cl_lock); c = __nfsd4_find_conn(new->cn_xprt, ses); if (c) goto out_free; status = nfserr_conn_not_bound_to_session; if (clp->cl_mach_cred) goto out_free; __nfsd4_hash_conn(new, ses); spin_unlock(&clp->cl_lock); ret = nfsd4_register_conn(new); if (ret) /* oops; xprt is already down: */ nfsd4_conn_lost(&new->cn_xpt_user); return nfs_ok; out_free: spin_unlock(&clp->cl_lock); free_conn(new); return status; } static bool nfsd4_session_too_many_ops(struct svc_rqst *rqstp, struct nfsd4_session *session) { struct nfsd4_compoundargs *args = rqstp->rq_argp; return args->opcnt > session->se_fchannel.maxops; } static bool nfsd4_request_too_big(struct svc_rqst *rqstp, struct nfsd4_session *session) { struct xdr_buf *xb = &rqstp->rq_arg; return xb->len > session->se_fchannel.maxreq_sz; } static bool replay_matches_cache(struct svc_rqst *rqstp, struct nfsd4_sequence *seq, struct nfsd4_slot *slot) { struct nfsd4_compoundargs *argp = rqstp->rq_argp; if ((bool)(slot->sl_flags & NFSD4_SLOT_CACHETHIS) != (bool)seq->cachethis) return false; /* * If there's an error then the reply can have fewer ops than * the call. */ if (slot->sl_opcnt < argp->opcnt && !slot->sl_status) return false; /* * But if we cached a reply with *more* ops than the call you're * sending us now, then this new call is clearly not really a * replay of the old one: */ if (slot->sl_opcnt > argp->opcnt) return false; /* This is the only check explicitly called by spec: */ if (!same_creds(&rqstp->rq_cred, &slot->sl_cred)) return false; /* * There may be more comparisons we could actually do, but the * spec doesn't require us to catch every case where the calls * don't match (that would require caching the call as well as * the reply), so we don't bother. */ return true; } __be32 nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_sequence *seq = &u->sequence; struct nfsd4_compoundres *resp = rqstp->rq_resp; struct xdr_stream *xdr = resp->xdr; struct nfsd4_session *session; struct nfs4_client *clp; struct nfsd4_slot *slot; struct nfsd4_conn *conn; __be32 status; int buflen; struct net *net = SVC_NET(rqstp); struct nfsd_net *nn = net_generic(net, nfsd_net_id); if (resp->opcnt != 1) return nfserr_sequence_pos; /* * Will be either used or freed by nfsd4_sequence_check_conn * below. */ conn = alloc_conn(rqstp, NFS4_CDFC4_FORE); if (!conn) return nfserr_jukebox; spin_lock(&nn->client_lock); session = find_in_sessionid_hashtbl(&seq->sessionid, net, &status); if (!session) goto out_no_session; clp = session->se_client; status = nfserr_too_many_ops; if (nfsd4_session_too_many_ops(rqstp, session)) goto out_put_session; status = nfserr_req_too_big; if (nfsd4_request_too_big(rqstp, session)) goto out_put_session; status = nfserr_badslot; if (seq->slotid >= session->se_fchannel.maxreqs) goto out_put_session; slot = session->se_slots[seq->slotid]; dprintk("%s: slotid %d\n", __func__, seq->slotid); /* We do not negotiate the number of slots yet, so set the * maxslots to the session maxreqs which is used to encode * sr_highest_slotid and the sr_target_slot id to maxslots */ seq->maxslots = session->se_fchannel.maxreqs; trace_nfsd_slot_seqid_sequence(clp, seq, slot); status = check_slot_seqid(seq->seqid, slot->sl_seqid, slot->sl_flags & NFSD4_SLOT_INUSE); if (status == nfserr_replay_cache) { status = nfserr_seq_misordered; if (!(slot->sl_flags & NFSD4_SLOT_INITIALIZED)) goto out_put_session; status = nfserr_seq_false_retry; if (!replay_matches_cache(rqstp, seq, slot)) goto out_put_session; cstate->slot = slot; cstate->session = session; cstate->clp = clp; /* Return the cached reply status and set cstate->status * for nfsd4_proc_compound processing */ status = nfsd4_replay_cache_entry(resp, seq); cstate->status = nfserr_replay_cache; goto out; } if (status) goto out_put_session; status = nfsd4_sequence_check_conn(conn, session); conn = NULL; if (status) goto out_put_session; buflen = (seq->cachethis) ? session->se_fchannel.maxresp_cached : session->se_fchannel.maxresp_sz; status = (seq->cachethis) ? nfserr_rep_too_big_to_cache : nfserr_rep_too_big; if (xdr_restrict_buflen(xdr, buflen - rqstp->rq_auth_slack)) goto out_put_session; svc_reserve(rqstp, buflen); status = nfs_ok; /* Success! bump slot seqid */ slot->sl_seqid = seq->seqid; slot->sl_flags |= NFSD4_SLOT_INUSE; if (seq->cachethis) slot->sl_flags |= NFSD4_SLOT_CACHETHIS; else slot->sl_flags &= ~NFSD4_SLOT_CACHETHIS; cstate->slot = slot; cstate->session = session; cstate->clp = clp; out: switch (clp->cl_cb_state) { case NFSD4_CB_DOWN: seq->status_flags = SEQ4_STATUS_CB_PATH_DOWN; break; case NFSD4_CB_FAULT: seq->status_flags = SEQ4_STATUS_BACKCHANNEL_FAULT; break; default: seq->status_flags = 0; } if (!list_empty(&clp->cl_revoked)) seq->status_flags |= SEQ4_STATUS_RECALLABLE_STATE_REVOKED; if (atomic_read(&clp->cl_admin_revoked)) seq->status_flags |= SEQ4_STATUS_ADMIN_STATE_REVOKED; trace_nfsd_seq4_status(rqstp, seq); out_no_session: if (conn) free_conn(conn); spin_unlock(&nn->client_lock); return status; out_put_session: nfsd4_put_session_locked(session); goto out_no_session; } void nfsd4_sequence_done(struct nfsd4_compoundres *resp) { struct nfsd4_compound_state *cs = &resp->cstate; if (nfsd4_has_session(cs)) { if (cs->status != nfserr_replay_cache) { nfsd4_store_cache_entry(resp); cs->slot->sl_flags &= ~NFSD4_SLOT_INUSE; } /* Drop session reference that was taken in nfsd4_sequence() */ nfsd4_put_session(cs->session); } else if (cs->clp) put_client_renew(cs->clp); } __be32 nfsd4_destroy_clientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_destroy_clientid *dc = &u->destroy_clientid; struct nfs4_client *conf, *unconf; struct nfs4_client *clp = NULL; __be32 status = 0; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); spin_lock(&nn->client_lock); unconf = find_unconfirmed_client(&dc->clientid, true, nn); conf = find_confirmed_client(&dc->clientid, true, nn); WARN_ON_ONCE(conf && unconf); if (conf) { if (client_has_state(conf)) { status = nfserr_clientid_busy; goto out; } status = mark_client_expired_locked(conf); if (status) goto out; clp = conf; } else if (unconf) clp = unconf; else { status = nfserr_stale_clientid; goto out; } if (!nfsd4_mach_creds_match(clp, rqstp)) { clp = NULL; status = nfserr_wrong_cred; goto out; } trace_nfsd_clid_destroyed(&clp->cl_clientid); unhash_client_locked(clp); out: spin_unlock(&nn->client_lock); if (clp) expire_client(clp); return status; } __be32 nfsd4_reclaim_complete(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_reclaim_complete *rc = &u->reclaim_complete; struct nfs4_client *clp = cstate->clp; __be32 status = 0; if (rc->rca_one_fs) { if (!cstate->current_fh.fh_dentry) return nfserr_nofilehandle; /* * We don't take advantage of the rca_one_fs case. * That's OK, it's optional, we can safely ignore it. */ return nfs_ok; } status = nfserr_complete_already; if (test_and_set_bit(NFSD4_CLIENT_RECLAIM_COMPLETE, &clp->cl_flags)) goto out; status = nfserr_stale_clientid; if (is_client_expired(clp)) /* * The following error isn't really legal. * But we only get here if the client just explicitly * destroyed the client. Surely it no longer cares what * error it gets back on an operation for the dead * client. */ goto out; status = nfs_ok; trace_nfsd_clid_reclaim_complete(&clp->cl_clientid); nfsd4_client_record_create(clp); inc_reclaim_complete(clp); out: return status; } __be32 nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_setclientid *setclid = &u->setclientid; struct xdr_netobj clname = setclid->se_name; nfs4_verifier clverifier = setclid->se_verf; struct nfs4_client *conf, *new; struct nfs4_client *unconf = NULL; __be32 status; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); new = create_client(clname, rqstp, &clverifier); if (new == NULL) return nfserr_jukebox; spin_lock(&nn->client_lock); conf = find_confirmed_client_by_name(&clname, nn); if (conf && client_has_state(conf)) { status = nfserr_clid_inuse; if (clp_used_exchangeid(conf)) goto out; if (!same_creds(&conf->cl_cred, &rqstp->rq_cred)) { trace_nfsd_clid_cred_mismatch(conf, rqstp); goto out; } } unconf = find_unconfirmed_client_by_name(&clname, nn); if (unconf) unhash_client_locked(unconf); if (conf) { if (same_verf(&conf->cl_verifier, &clverifier)) { copy_clid(new, conf); gen_confirm(new, nn); } else trace_nfsd_clid_verf_mismatch(conf, rqstp, &clverifier); } else trace_nfsd_clid_fresh(new); new->cl_minorversion = 0; gen_callback(new, setclid, rqstp); add_to_unconfirmed(new); setclid->se_clientid.cl_boot = new->cl_clientid.cl_boot; setclid->se_clientid.cl_id = new->cl_clientid.cl_id; memcpy(setclid->se_confirm.data, new->cl_confirm.data, sizeof(setclid->se_confirm.data)); new = NULL; status = nfs_ok; out: spin_unlock(&nn->client_lock); if (new) free_client(new); if (unconf) { trace_nfsd_clid_expire_unconf(&unconf->cl_clientid); expire_client(unconf); } return status; } __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_setclientid_confirm *setclientid_confirm = &u->setclientid_confirm; struct nfs4_client *conf, *unconf; struct nfs4_client *old = NULL; nfs4_verifier confirm = setclientid_confirm->sc_confirm; clientid_t * clid = &setclientid_confirm->sc_clientid; __be32 status; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); if (STALE_CLIENTID(clid, nn)) return nfserr_stale_clientid; spin_lock(&nn->client_lock); conf = find_confirmed_client(clid, false, nn); unconf = find_unconfirmed_client(clid, false, nn); /* * We try hard to give out unique clientid's, so if we get an * attempt to confirm the same clientid with a different cred, * the client may be buggy; this should never happen. * * Nevertheless, RFC 7530 recommends INUSE for this case: */ status = nfserr_clid_inuse; if (unconf && !same_creds(&unconf->cl_cred, &rqstp->rq_cred)) { trace_nfsd_clid_cred_mismatch(unconf, rqstp); goto out; } if (conf && !same_creds(&conf->cl_cred, &rqstp->rq_cred)) { trace_nfsd_clid_cred_mismatch(conf, rqstp); goto out; } if (!unconf || !same_verf(&confirm, &unconf->cl_confirm)) { if (conf && same_verf(&confirm, &conf->cl_confirm)) { status = nfs_ok; } else status = nfserr_stale_clientid; goto out; } status = nfs_ok; if (conf) { old = unconf; unhash_client_locked(old); nfsd4_change_callback(conf, &unconf->cl_cb_conn); } else { old = find_confirmed_client_by_name(&unconf->cl_name, nn); if (old) { status = nfserr_clid_inuse; if (client_has_state(old) && !same_creds(&unconf->cl_cred, &old->cl_cred)) { old = NULL; goto out; } status = mark_client_expired_locked(old); if (status) { old = NULL; goto out; } trace_nfsd_clid_replaced(&old->cl_clientid); } move_to_confirmed(unconf); conf = unconf; } get_client_locked(conf); spin_unlock(&nn->client_lock); if (conf == unconf) fsnotify_dentry(conf->cl_nfsd_info_dentry, FS_MODIFY); nfsd4_probe_callback(conf); spin_lock(&nn->client_lock); put_client_renew_locked(conf); out: spin_unlock(&nn->client_lock); if (old) expire_client(old); return status; } static struct nfs4_file *nfsd4_alloc_file(void) { return kmem_cache_alloc(file_slab, GFP_KERNEL); } /* OPEN Share state helper functions */ static void nfsd4_file_init(const struct svc_fh *fh, struct nfs4_file *fp) { refcount_set(&fp->fi_ref, 1); spin_lock_init(&fp->fi_lock); INIT_LIST_HEAD(&fp->fi_stateids); INIT_LIST_HEAD(&fp->fi_delegations); INIT_LIST_HEAD(&fp->fi_clnt_odstate); fh_copy_shallow(&fp->fi_fhandle, &fh->fh_handle); fp->fi_deleg_file = NULL; fp->fi_had_conflict = false; fp->fi_share_deny = 0; memset(fp->fi_fds, 0, sizeof(fp->fi_fds)); memset(fp->fi_access, 0, sizeof(fp->fi_access)); fp->fi_aliased = false; fp->fi_inode = d_inode(fh->fh_dentry); #ifdef CONFIG_NFSD_PNFS INIT_LIST_HEAD(&fp->fi_lo_states); atomic_set(&fp->fi_lo_recalls, 0); #endif } void nfsd4_free_slabs(void) { kmem_cache_destroy(client_slab); kmem_cache_destroy(openowner_slab); kmem_cache_destroy(lockowner_slab); kmem_cache_destroy(file_slab); kmem_cache_destroy(stateid_slab); kmem_cache_destroy(deleg_slab); kmem_cache_destroy(odstate_slab); } int nfsd4_init_slabs(void) { client_slab = KMEM_CACHE(nfs4_client, 0); if (client_slab == NULL) goto out; openowner_slab = KMEM_CACHE(nfs4_openowner, 0); if (openowner_slab == NULL) goto out_free_client_slab; lockowner_slab = KMEM_CACHE(nfs4_lockowner, 0); if (lockowner_slab == NULL) goto out_free_openowner_slab; file_slab = KMEM_CACHE(nfs4_file, 0); if (file_slab == NULL) goto out_free_lockowner_slab; stateid_slab = KMEM_CACHE(nfs4_ol_stateid, 0); if (stateid_slab == NULL) goto out_free_file_slab; deleg_slab = KMEM_CACHE(nfs4_delegation, 0); if (deleg_slab == NULL) goto out_free_stateid_slab; odstate_slab = KMEM_CACHE(nfs4_clnt_odstate, 0); if (odstate_slab == NULL) goto out_free_deleg_slab; return 0; out_free_deleg_slab: kmem_cache_destroy(deleg_slab); out_free_stateid_slab: kmem_cache_destroy(stateid_slab); out_free_file_slab: kmem_cache_destroy(file_slab); out_free_lockowner_slab: kmem_cache_destroy(lockowner_slab); out_free_openowner_slab: kmem_cache_destroy(openowner_slab); out_free_client_slab: kmem_cache_destroy(client_slab); out: return -ENOMEM; } static unsigned long nfsd4_state_shrinker_count(struct shrinker *shrink, struct shrink_control *sc) { int count; struct nfsd_net *nn = shrink->private_data; count = atomic_read(&nn->nfsd_courtesy_clients); if (!count) count = atomic_long_read(&num_delegations); if (count) queue_work(laundry_wq, &nn->nfsd_shrinker_work); return (unsigned long)count; } static unsigned long nfsd4_state_shrinker_scan(struct shrinker *shrink, struct shrink_control *sc) { return SHRINK_STOP; } void nfsd4_init_leases_net(struct nfsd_net *nn) { struct sysinfo si; u64 max_clients; nn->nfsd4_lease = 90; /* default lease time */ nn->nfsd4_grace = 90; nn->somebody_reclaimed = false; nn->track_reclaim_completes = false; nn->clverifier_counter = get_random_u32(); nn->clientid_base = get_random_u32(); nn->clientid_counter = nn->clientid_base + 1; nn->s2s_cp_cl_id = nn->clientid_counter++; atomic_set(&nn->nfs4_client_count, 0); si_meminfo(&si); max_clients = (u64)si.totalram * si.mem_unit / (1024 * 1024 * 1024); max_clients *= NFS4_CLIENTS_PER_GB; nn->nfs4_max_clients = max_t(int, max_clients, NFS4_CLIENTS_PER_GB); atomic_set(&nn->nfsd_courtesy_clients, 0); } enum rp_lock { RP_UNLOCKED, RP_LOCKED, RP_UNHASHED, }; static void init_nfs4_replay(struct nfs4_replay *rp) { rp->rp_status = nfserr_serverfault; rp->rp_buflen = 0; rp->rp_buf = rp->rp_ibuf; atomic_set(&rp->rp_locked, RP_UNLOCKED); } static int nfsd4_cstate_assign_replay(struct nfsd4_compound_state *cstate, struct nfs4_stateowner *so) { if (!nfsd4_has_session(cstate)) { wait_var_event(&so->so_replay.rp_locked, atomic_cmpxchg(&so->so_replay.rp_locked, RP_UNLOCKED, RP_LOCKED) != RP_LOCKED); if (atomic_read(&so->so_replay.rp_locked) == RP_UNHASHED) return -EAGAIN; cstate->replay_owner = nfs4_get_stateowner(so); } return 0; } void nfsd4_cstate_clear_replay(struct nfsd4_compound_state *cstate) { struct nfs4_stateowner *so = cstate->replay_owner; if (so != NULL) { cstate->replay_owner = NULL; atomic_set(&so->so_replay.rp_locked, RP_UNLOCKED); smp_mb__after_atomic(); wake_up_var(&so->so_replay.rp_locked); nfs4_put_stateowner(so); } } static inline void *alloc_stateowner(struct kmem_cache *slab, struct xdr_netobj *owner, struct nfs4_client *clp) { struct nfs4_stateowner *sop; sop = kmem_cache_alloc(slab, GFP_KERNEL); if (!sop) return NULL; xdr_netobj_dup(&sop->so_owner, owner, GFP_KERNEL); if (!sop->so_owner.data) { kmem_cache_free(slab, sop); return NULL; } INIT_LIST_HEAD(&sop->so_stateids); sop->so_client = clp; init_nfs4_replay(&sop->so_replay); atomic_set(&sop->so_count, 1); return sop; } static void hash_openowner(struct nfs4_openowner *oo, struct nfs4_client *clp, unsigned int strhashval) { lockdep_assert_held(&clp->cl_lock); list_add(&oo->oo_owner.so_strhash, &clp->cl_ownerstr_hashtbl[strhashval]); list_add(&oo->oo_perclient, &clp->cl_openowners); } static void nfs4_unhash_openowner(struct nfs4_stateowner *so) { unhash_openowner_locked(openowner(so)); } static void nfs4_free_openowner(struct nfs4_stateowner *so) { struct nfs4_openowner *oo = openowner(so); kmem_cache_free(openowner_slab, oo); } static const struct nfs4_stateowner_operations openowner_ops = { .so_unhash = nfs4_unhash_openowner, .so_free = nfs4_free_openowner, }; static struct nfs4_ol_stateid * nfsd4_find_existing_open(struct nfs4_file *fp, struct nfsd4_open *open) { struct nfs4_ol_stateid *local, *ret = NULL; struct nfs4_openowner *oo = open->op_openowner; lockdep_assert_held(&fp->fi_lock); list_for_each_entry(local, &fp->fi_stateids, st_perfile) { /* ignore lock owners */ if (local->st_stateowner->so_is_open_owner == 0) continue; if (local->st_stateowner != &oo->oo_owner) continue; if (local->st_stid.sc_type == SC_TYPE_OPEN && !local->st_stid.sc_status) { ret = local; refcount_inc(&ret->st_stid.sc_count); break; } } return ret; } static void nfsd4_drop_revoked_stid(struct nfs4_stid *s) __releases(&s->sc_client->cl_lock) { struct nfs4_client *cl = s->sc_client; LIST_HEAD(reaplist); struct nfs4_ol_stateid *stp; struct nfs4_delegation *dp; bool unhashed; switch (s->sc_type) { case SC_TYPE_OPEN: stp = openlockstateid(s); if (unhash_open_stateid(stp, &reaplist)) put_ol_stateid_locked(stp, &reaplist); spin_unlock(&cl->cl_lock); free_ol_stateid_reaplist(&reaplist); break; case SC_TYPE_LOCK: stp = openlockstateid(s); unhashed = unhash_lock_stateid(stp); spin_unlock(&cl->cl_lock); if (unhashed) nfs4_put_stid(s); break; case SC_TYPE_DELEG: dp = delegstateid(s); list_del_init(&dp->dl_recall_lru); spin_unlock(&cl->cl_lock); nfs4_put_stid(s); break; default: spin_unlock(&cl->cl_lock); } } static void nfsd40_drop_revoked_stid(struct nfs4_client *cl, stateid_t *stid) { /* NFSv4.0 has no way for the client to tell the server * that it can forget an admin-revoked stateid. * So we keep it around until the first time that the * client uses it, and drop it the first time * nfserr_admin_revoked is returned. * For v4.1 and later we wait until explicitly told * to free the stateid. */ if (cl->cl_minorversion == 0) { struct nfs4_stid *st; spin_lock(&cl->cl_lock); st = find_stateid_locked(cl, stid); if (st) nfsd4_drop_revoked_stid(st); else spin_unlock(&cl->cl_lock); } } static __be32 nfsd4_verify_open_stid(struct nfs4_stid *s) { __be32 ret = nfs_ok; if (s->sc_status & SC_STATUS_ADMIN_REVOKED) ret = nfserr_admin_revoked; else if (s->sc_status & SC_STATUS_REVOKED) ret = nfserr_deleg_revoked; else if (s->sc_status & SC_STATUS_CLOSED) ret = nfserr_bad_stateid; return ret; } /* Lock the stateid st_mutex, and deal with races with CLOSE */ static __be32 nfsd4_lock_ol_stateid(struct nfs4_ol_stateid *stp) { __be32 ret; mutex_lock_nested(&stp->st_mutex, LOCK_STATEID_MUTEX); ret = nfsd4_verify_open_stid(&stp->st_stid); if (ret == nfserr_admin_revoked) nfsd40_drop_revoked_stid(stp->st_stid.sc_client, &stp->st_stid.sc_stateid); if (ret != nfs_ok) mutex_unlock(&stp->st_mutex); return ret; } static struct nfs4_ol_stateid * nfsd4_find_and_lock_existing_open(struct nfs4_file *fp, struct nfsd4_open *open) { struct nfs4_ol_stateid *stp; for (;;) { spin_lock(&fp->fi_lock); stp = nfsd4_find_existing_open(fp, open); spin_unlock(&fp->fi_lock); if (!stp || nfsd4_lock_ol_stateid(stp) == nfs_ok) break; nfs4_put_stid(&stp->st_stid); } return stp; } static struct nfs4_openowner * find_or_alloc_open_stateowner(unsigned int strhashval, struct nfsd4_open *open, struct nfsd4_compound_state *cstate) { struct nfs4_client *clp = cstate->clp; struct nfs4_openowner *oo, *new = NULL; retry: spin_lock(&clp->cl_lock); oo = find_openstateowner_str(strhashval, open, clp); if (!oo && new) { hash_openowner(new, clp, strhashval); spin_unlock(&clp->cl_lock); return new; } spin_unlock(&clp->cl_lock); if (oo && !(oo->oo_flags & NFS4_OO_CONFIRMED)) { /* Replace unconfirmed owners without checking for replay. */ release_openowner(oo); oo = NULL; } if (oo) { if (new) nfs4_free_stateowner(&new->oo_owner); return oo; } new = alloc_stateowner(openowner_slab, &open->op_owner, clp); if (!new) return NULL; new->oo_owner.so_ops = &openowner_ops; new->oo_owner.so_is_open_owner = 1; new->oo_owner.so_seqid = open->op_seqid; new->oo_flags = 0; if (nfsd4_has_session(cstate)) new->oo_flags |= NFS4_OO_CONFIRMED; new->oo_time = 0; new->oo_last_closed_stid = NULL; INIT_LIST_HEAD(&new->oo_close_lru); goto retry; } static struct nfs4_ol_stateid * init_open_stateid(struct nfs4_file *fp, struct nfsd4_open *open) { struct nfs4_openowner *oo = open->op_openowner; struct nfs4_ol_stateid *retstp = NULL; struct nfs4_ol_stateid *stp; stp = open->op_stp; /* We are moving these outside of the spinlocks to avoid the warnings */ mutex_init(&stp->st_mutex); mutex_lock_nested(&stp->st_mutex, OPEN_STATEID_MUTEX); retry: spin_lock(&oo->oo_owner.so_client->cl_lock); spin_lock(&fp->fi_lock); retstp = nfsd4_find_existing_open(fp, open); if (retstp) goto out_unlock; open->op_stp = NULL; refcount_inc(&stp->st_stid.sc_count); stp->st_stid.sc_type = SC_TYPE_OPEN; INIT_LIST_HEAD(&stp->st_locks); stp->st_stateowner = nfs4_get_stateowner(&oo->oo_owner); get_nfs4_file(fp); stp->st_stid.sc_file = fp; stp->st_access_bmap = 0; stp->st_deny_bmap = 0; stp->st_openstp = NULL; list_add(&stp->st_perstateowner, &oo->oo_owner.so_stateids); list_add(&stp->st_perfile, &fp->fi_stateids); out_unlock: spin_unlock(&fp->fi_lock); spin_unlock(&oo->oo_owner.so_client->cl_lock); if (retstp) { /* Handle races with CLOSE */ if (nfsd4_lock_ol_stateid(retstp) != nfs_ok) { nfs4_put_stid(&retstp->st_stid); goto retry; } /* To keep mutex tracking happy */ mutex_unlock(&stp->st_mutex); stp = retstp; } return stp; } /* * In the 4.0 case we need to keep the owners around a little while to handle * CLOSE replay. We still do need to release any file access that is held by * them before returning however. */ static void move_to_close_lru(struct nfs4_ol_stateid *s, struct net *net) { struct nfs4_ol_stateid *last; struct nfs4_openowner *oo = openowner(s->st_stateowner); struct nfsd_net *nn = net_generic(s->st_stid.sc_client->net, nfsd_net_id); dprintk("NFSD: move_to_close_lru nfs4_openowner %p\n", oo); /* * We know that we hold one reference via nfsd4_close, and another * "persistent" reference for the client. If the refcount is higher * than 2, then there are still calls in progress that are using this * stateid. We can't put the sc_file reference until they are finished. * Wait for the refcount to drop to 2. Since it has been unhashed, * there should be no danger of the refcount going back up again at * this point. * Some threads with a reference might be waiting for rp_locked, * so tell them to stop waiting. */ atomic_set(&oo->oo_owner.so_replay.rp_locked, RP_UNHASHED); smp_mb__after_atomic(); wake_up_var(&oo->oo_owner.so_replay.rp_locked); wait_event(close_wq, refcount_read(&s->st_stid.sc_count) == 2); release_all_access(s); if (s->st_stid.sc_file) { put_nfs4_file(s->st_stid.sc_file); s->st_stid.sc_file = NULL; } spin_lock(&nn->client_lock); last = oo->oo_last_closed_stid; oo->oo_last_closed_stid = s; list_move_tail(&oo->oo_close_lru, &nn->close_lru); oo->oo_time = ktime_get_boottime_seconds(); spin_unlock(&nn->client_lock); if (last) nfs4_put_stid(&last->st_stid); } static noinline_for_stack struct nfs4_file * nfsd4_file_hash_lookup(const struct svc_fh *fhp) { struct inode *inode = d_inode(fhp->fh_dentry); struct rhlist_head *tmp, *list; struct nfs4_file *fi; rcu_read_lock(); list = rhltable_lookup(&nfs4_file_rhltable, &inode, nfs4_file_rhash_params); rhl_for_each_entry_rcu(fi, tmp, list, fi_rlist) { if (fh_match(&fi->fi_fhandle, &fhp->fh_handle)) { if (refcount_inc_not_zero(&fi->fi_ref)) { rcu_read_unlock(); return fi; } } } rcu_read_unlock(); return NULL; } /* * On hash insertion, identify entries with the same inode but * distinct filehandles. They will all be on the list returned * by rhltable_lookup(). * * inode->i_lock prevents racing insertions from adding an entry * for the same inode/fhp pair twice. */ static noinline_for_stack struct nfs4_file * nfsd4_file_hash_insert(struct nfs4_file *new, const struct svc_fh *fhp) { struct inode *inode = d_inode(fhp->fh_dentry); struct rhlist_head *tmp, *list; struct nfs4_file *ret = NULL; bool alias_found = false; struct nfs4_file *fi; int err; rcu_read_lock(); spin_lock(&inode->i_lock); list = rhltable_lookup(&nfs4_file_rhltable, &inode, nfs4_file_rhash_params); rhl_for_each_entry_rcu(fi, tmp, list, fi_rlist) { if (fh_match(&fi->fi_fhandle, &fhp->fh_handle)) { if (refcount_inc_not_zero(&fi->fi_ref)) ret = fi; } else fi->fi_aliased = alias_found = true; } if (ret) goto out_unlock; nfsd4_file_init(fhp, new); err = rhltable_insert(&nfs4_file_rhltable, &new->fi_rlist, nfs4_file_rhash_params); if (err) goto out_unlock; new->fi_aliased = alias_found; ret = new; out_unlock: spin_unlock(&inode->i_lock); rcu_read_unlock(); return ret; } static noinline_for_stack void nfsd4_file_hash_remove(struct nfs4_file *fi) { rhltable_remove(&nfs4_file_rhltable, &fi->fi_rlist, nfs4_file_rhash_params); } /* * Called to check deny when READ with all zero stateid or * WRITE with all zero or all one stateid */ static __be32 nfs4_share_conflict(struct svc_fh *current_fh, unsigned int deny_type) { struct nfs4_file *fp; __be32 ret = nfs_ok; fp = nfsd4_file_hash_lookup(current_fh); if (!fp) return ret; /* Check for conflicting share reservations */ spin_lock(&fp->fi_lock); if (fp->fi_share_deny & deny_type) ret = nfserr_locked; spin_unlock(&fp->fi_lock); put_nfs4_file(fp); return ret; } static bool nfsd4_deleg_present(const struct inode *inode) { struct file_lock_context *ctx = locks_inode_context(inode); return ctx && !list_empty_careful(&ctx->flc_lease); } /** * nfsd_wait_for_delegreturn - wait for delegations to be returned * @rqstp: the RPC transaction being executed * @inode: in-core inode of the file being waited for * * The timeout prevents deadlock if all nfsd threads happen to be * tied up waiting for returning delegations. * * Return values: * %true: delegation was returned * %false: timed out waiting for delegreturn */ bool nfsd_wait_for_delegreturn(struct svc_rqst *rqstp, struct inode *inode) { long __maybe_unused timeo; timeo = wait_var_event_timeout(inode, !nfsd4_deleg_present(inode), NFSD_DELEGRETURN_TIMEOUT); trace_nfsd_delegret_wakeup(rqstp, inode, timeo); return timeo > 0; } static void nfsd4_cb_recall_prepare(struct nfsd4_callback *cb) { struct nfs4_delegation *dp = cb_to_delegation(cb); struct nfsd_net *nn = net_generic(dp->dl_stid.sc_client->net, nfsd_net_id); block_delegations(&dp->dl_stid.sc_file->fi_fhandle); /* * We can't do this in nfsd_break_deleg_cb because it is * already holding inode->i_lock. * * If the dl_time != 0, then we know that it has already been * queued for a lease break. Don't queue it again. */ spin_lock(&state_lock); if (delegation_hashed(dp) && dp->dl_time == 0) { dp->dl_time = ktime_get_boottime_seconds(); list_add_tail(&dp->dl_recall_lru, &nn->del_recall_lru); } spin_unlock(&state_lock); } static int nfsd4_cb_recall_done(struct nfsd4_callback *cb, struct rpc_task *task) { struct nfs4_delegation *dp = cb_to_delegation(cb); trace_nfsd_cb_recall_done(&dp->dl_stid.sc_stateid, task); if (dp->dl_stid.sc_status) /* CLOSED or REVOKED */ return 1; switch (task->tk_status) { case 0: return 1; case -NFS4ERR_DELAY: rpc_delay(task, 2 * HZ); return 0; case -EBADHANDLE: case -NFS4ERR_BAD_STATEID: /* * Race: client probably got cb_recall before open reply * granting delegation. */ if (dp->dl_retries--) { rpc_delay(task, 2 * HZ); return 0; } fallthrough; default: return 1; } } static void nfsd4_cb_recall_release(struct nfsd4_callback *cb) { struct nfs4_delegation *dp = cb_to_delegation(cb); nfs4_put_stid(&dp->dl_stid); } static const struct nfsd4_callback_ops nfsd4_cb_recall_ops = { .prepare = nfsd4_cb_recall_prepare, .done = nfsd4_cb_recall_done, .release = nfsd4_cb_recall_release, .opcode = OP_CB_RECALL, }; static void nfsd_break_one_deleg(struct nfs4_delegation *dp) { /* * We're assuming the state code never drops its reference * without first removing the lease. Since we're in this lease * callback (and since the lease code is serialized by the * flc_lock) we know the server hasn't removed the lease yet, and * we know it's safe to take a reference. */ refcount_inc(&dp->dl_stid.sc_count); WARN_ON_ONCE(!nfsd4_run_cb(&dp->dl_recall)); } /* Called from break_lease() with flc_lock held. */ static bool nfsd_break_deleg_cb(struct file_lease *fl) { struct nfs4_delegation *dp = (struct nfs4_delegation *) fl->c.flc_owner; struct nfs4_file *fp = dp->dl_stid.sc_file; struct nfs4_client *clp = dp->dl_stid.sc_client; struct nfsd_net *nn; trace_nfsd_cb_recall(&dp->dl_stid); dp->dl_recalled = true; atomic_inc(&clp->cl_delegs_in_recall); if (try_to_expire_client(clp)) { nn = net_generic(clp->net, nfsd_net_id); mod_delayed_work(laundry_wq, &nn->laundromat_work, 0); } /* * We don't want the locks code to timeout the lease for us; * we'll remove it ourself if a delegation isn't returned * in time: */ fl->fl_break_time = 0; fp->fi_had_conflict = true; nfsd_break_one_deleg(dp); return false; } /** * nfsd_breaker_owns_lease - Check if lease conflict was resolved * @fl: Lock state to check * * Return values: * %true: Lease conflict was resolved * %false: Lease conflict was not resolved. */ static bool nfsd_breaker_owns_lease(struct file_lease *fl) { struct nfs4_delegation *dl = fl->c.flc_owner; struct svc_rqst *rqst; struct nfs4_client *clp; rqst = nfsd_current_rqst(); if (!nfsd_v4client(rqst)) return false; clp = *(rqst->rq_lease_breaker); return dl->dl_stid.sc_client == clp; } static int nfsd_change_deleg_cb(struct file_lease *onlist, int arg, struct list_head *dispose) { struct nfs4_delegation *dp = (struct nfs4_delegation *) onlist->c.flc_owner; struct nfs4_client *clp = dp->dl_stid.sc_client; if (arg & F_UNLCK) { if (dp->dl_recalled) atomic_dec(&clp->cl_delegs_in_recall); return lease_modify(onlist, arg, dispose); } else return -EAGAIN; } static const struct lease_manager_operations nfsd_lease_mng_ops = { .lm_breaker_owns_lease = nfsd_breaker_owns_lease, .lm_break = nfsd_break_deleg_cb, .lm_change = nfsd_change_deleg_cb, }; static __be32 nfsd4_check_seqid(struct nfsd4_compound_state *cstate, struct nfs4_stateowner *so, u32 seqid) { if (nfsd4_has_session(cstate)) return nfs_ok; if (seqid == so->so_seqid - 1) return nfserr_replay_me; if (seqid == so->so_seqid) return nfs_ok; return nfserr_bad_seqid; } static struct nfs4_client *lookup_clientid(clientid_t *clid, bool sessions, struct nfsd_net *nn) { struct nfs4_client *found; spin_lock(&nn->client_lock); found = find_confirmed_client(clid, sessions, nn); if (found) atomic_inc(&found->cl_rpc_users); spin_unlock(&nn->client_lock); return found; } static __be32 set_client(clientid_t *clid, struct nfsd4_compound_state *cstate, struct nfsd_net *nn) { if (cstate->clp) { if (!same_clid(&cstate->clp->cl_clientid, clid)) return nfserr_stale_clientid; return nfs_ok; } if (STALE_CLIENTID(clid, nn)) return nfserr_stale_clientid; /* * We're in the 4.0 case (otherwise the SEQUENCE op would have * set cstate->clp), so session = false: */ cstate->clp = lookup_clientid(clid, false, nn); if (!cstate->clp) return nfserr_expired; return nfs_ok; } __be32 nfsd4_process_open1(struct nfsd4_compound_state *cstate, struct nfsd4_open *open, struct nfsd_net *nn) { clientid_t *clientid = &open->op_clientid; struct nfs4_client *clp = NULL; unsigned int strhashval; struct nfs4_openowner *oo = NULL; __be32 status; /* * In case we need it later, after we've already created the * file and don't want to risk a further failure: */ open->op_file = nfsd4_alloc_file(); if (open->op_file == NULL) return nfserr_jukebox; status = set_client(clientid, cstate, nn); if (status) return status; clp = cstate->clp; strhashval = ownerstr_hashval(&open->op_owner); retry: oo = find_or_alloc_open_stateowner(strhashval, open, cstate); open->op_openowner = oo; if (!oo) return nfserr_jukebox; if (nfsd4_cstate_assign_replay(cstate, &oo->oo_owner) == -EAGAIN) { nfs4_put_stateowner(&oo->oo_owner); goto retry; } status = nfsd4_check_seqid(cstate, &oo->oo_owner, open->op_seqid); if (status) return status; open->op_stp = nfs4_alloc_open_stateid(clp); if (!open->op_stp) return nfserr_jukebox; if (nfsd4_has_session(cstate) && (cstate->current_fh.fh_export->ex_flags & NFSEXP_PNFS)) { open->op_odstate = alloc_clnt_odstate(clp); if (!open->op_odstate) return nfserr_jukebox; } return nfs_ok; } static inline __be32 nfs4_check_delegmode(struct nfs4_delegation *dp, int flags) { if ((flags & WR_STATE) && (dp->dl_type == NFS4_OPEN_DELEGATE_READ)) return nfserr_openmode; else return nfs_ok; } static int share_access_to_flags(u32 share_access) { return share_access == NFS4_SHARE_ACCESS_READ ? RD_STATE : WR_STATE; } static struct nfs4_delegation *find_deleg_stateid(struct nfs4_client *cl, stateid_t *s) { struct nfs4_stid *ret; ret = find_stateid_by_type(cl, s, SC_TYPE_DELEG, SC_STATUS_REVOKED); if (!ret) return NULL; return delegstateid(ret); } static bool nfsd4_is_deleg_cur(struct nfsd4_open *open) { return open->op_claim_type == NFS4_OPEN_CLAIM_DELEGATE_CUR || open->op_claim_type == NFS4_OPEN_CLAIM_DELEG_CUR_FH; } static __be32 nfs4_check_deleg(struct nfs4_client *cl, struct nfsd4_open *open, struct nfs4_delegation **dp) { int flags; __be32 status = nfserr_bad_stateid; struct nfs4_delegation *deleg; deleg = find_deleg_stateid(cl, &open->op_delegate_stateid); if (deleg == NULL) goto out; if (deleg->dl_stid.sc_status & SC_STATUS_ADMIN_REVOKED) { nfs4_put_stid(&deleg->dl_stid); status = nfserr_admin_revoked; goto out; } if (deleg->dl_stid.sc_status & SC_STATUS_REVOKED) { nfs4_put_stid(&deleg->dl_stid); nfsd40_drop_revoked_stid(cl, &open->op_delegate_stateid); status = nfserr_deleg_revoked; goto out; } flags = share_access_to_flags(open->op_share_access); status = nfs4_check_delegmode(deleg, flags); if (status) { nfs4_put_stid(&deleg->dl_stid); goto out; } *dp = deleg; out: if (!nfsd4_is_deleg_cur(open)) return nfs_ok; if (status) return status; open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED; return nfs_ok; } static inline int nfs4_access_to_access(u32 nfs4_access) { int flags = 0; if (nfs4_access & NFS4_SHARE_ACCESS_READ) flags |= NFSD_MAY_READ; if (nfs4_access & NFS4_SHARE_ACCESS_WRITE) flags |= NFSD_MAY_WRITE; return flags; } static inline __be32 nfsd4_truncate(struct svc_rqst *rqstp, struct svc_fh *fh, struct nfsd4_open *open) { struct iattr iattr = { .ia_valid = ATTR_SIZE, .ia_size = 0, }; struct nfsd_attrs attrs = { .na_iattr = &iattr, }; if (!open->op_truncate) return 0; if (!(open->op_share_access & NFS4_SHARE_ACCESS_WRITE)) return nfserr_inval; return nfsd_setattr(rqstp, fh, &attrs, NULL); } static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp, struct svc_fh *cur_fh, struct nfs4_ol_stateid *stp, struct nfsd4_open *open, bool new_stp) { struct nfsd_file *nf = NULL; __be32 status; int oflag = nfs4_access_to_omode(open->op_share_access); int access = nfs4_access_to_access(open->op_share_access); unsigned char old_access_bmap, old_deny_bmap; spin_lock(&fp->fi_lock); /* * Are we trying to set a deny mode that would conflict with * current access? */ status = nfs4_file_check_deny(fp, open->op_share_deny); if (status != nfs_ok) { if (status != nfserr_share_denied) { spin_unlock(&fp->fi_lock); goto out; } if (nfs4_resolve_deny_conflicts_locked(fp, new_stp, stp, open->op_share_deny, false)) status = nfserr_jukebox; spin_unlock(&fp->fi_lock); goto out; } /* set access to the file */ status = nfs4_file_get_access(fp, open->op_share_access); if (status != nfs_ok) { if (status != nfserr_share_denied) { spin_unlock(&fp->fi_lock); goto out; } if (nfs4_resolve_deny_conflicts_locked(fp, new_stp, stp, open->op_share_access, true)) status = nfserr_jukebox; spin_unlock(&fp->fi_lock); goto out; } /* Set access bits in stateid */ old_access_bmap = stp->st_access_bmap; set_access(open->op_share_access, stp); /* Set new deny mask */ old_deny_bmap = stp->st_deny_bmap; set_deny(open->op_share_deny, stp); fp->fi_share_deny |= (open->op_share_deny & NFS4_SHARE_DENY_BOTH); if (!fp->fi_fds[oflag]) { spin_unlock(&fp->fi_lock); status = nfsd_file_acquire_opened(rqstp, cur_fh, access, open->op_filp, &nf); if (status != nfs_ok) goto out_put_access; spin_lock(&fp->fi_lock); if (!fp->fi_fds[oflag]) { fp->fi_fds[oflag] = nf; nf = NULL; } } spin_unlock(&fp->fi_lock); if (nf) nfsd_file_put(nf); status = nfserrno(nfsd_open_break_lease(cur_fh->fh_dentry->d_inode, access)); if (status) goto out_put_access; status = nfsd4_truncate(rqstp, cur_fh, open); if (status) goto out_put_access; out: return status; out_put_access: stp->st_access_bmap = old_access_bmap; nfs4_file_put_access(fp, open->op_share_access); reset_union_bmap_deny(bmap_to_share_mode(old_deny_bmap), stp); goto out; } static __be32 nfs4_upgrade_open(struct svc_rqst *rqstp, struct nfs4_file *fp, struct svc_fh *cur_fh, struct nfs4_ol_stateid *stp, struct nfsd4_open *open) { __be32 status; unsigned char old_deny_bmap = stp->st_deny_bmap; if (!test_access(open->op_share_access, stp)) return nfs4_get_vfs_file(rqstp, fp, cur_fh, stp, open, false); /* test and set deny mode */ spin_lock(&fp->fi_lock); status = nfs4_file_check_deny(fp, open->op_share_deny); switch (status) { case nfs_ok: set_deny(open->op_share_deny, stp); fp->fi_share_deny |= (open->op_share_deny & NFS4_SHARE_DENY_BOTH); break; case nfserr_share_denied: if (nfs4_resolve_deny_conflicts_locked(fp, false, stp, open->op_share_deny, false)) status = nfserr_jukebox; break; } spin_unlock(&fp->fi_lock); if (status != nfs_ok) return status; status = nfsd4_truncate(rqstp, cur_fh, open); if (status != nfs_ok) reset_union_bmap_deny(old_deny_bmap, stp); return status; } /* Should we give out recallable state?: */ static bool nfsd4_cb_channel_good(struct nfs4_client *clp) { if (clp->cl_cb_state == NFSD4_CB_UP) return true; /* * In the sessions case, since we don't have to establish a * separate connection for callbacks, we assume it's OK * until we hear otherwise: */ return clp->cl_minorversion && clp->cl_cb_state == NFSD4_CB_UNKNOWN; } static struct file_lease *nfs4_alloc_init_lease(struct nfs4_delegation *dp, int flag) { struct file_lease *fl; fl = locks_alloc_lease(); if (!fl) return NULL; fl->fl_lmops = &nfsd_lease_mng_ops; fl->c.flc_flags = FL_DELEG; fl->c.flc_type = flag == NFS4_OPEN_DELEGATE_READ? F_RDLCK: F_WRLCK; fl->c.flc_owner = (fl_owner_t)dp; fl->c.flc_pid = current->tgid; fl->c.flc_file = dp->dl_stid.sc_file->fi_deleg_file->nf_file; return fl; } static int nfsd4_check_conflicting_opens(struct nfs4_client *clp, struct nfs4_file *fp) { struct nfs4_ol_stateid *st; struct file *f = fp->fi_deleg_file->nf_file; struct inode *ino = file_inode(f); int writes; writes = atomic_read(&ino->i_writecount); if (!writes) return 0; /* * There could be multiple filehandles (hence multiple * nfs4_files) referencing this file, but that's not too * common; let's just give up in that case rather than * trying to go look up all the clients using that other * nfs4_file as well: */ if (fp->fi_aliased) return -EAGAIN; /* * If there's a close in progress, make sure that we see it * clear any fi_fds[] entries before we see it decrement * i_writecount: */ smp_mb__after_atomic(); if (fp->fi_fds[O_WRONLY]) writes--; if (fp->fi_fds[O_RDWR]) writes--; if (writes > 0) return -EAGAIN; /* There may be non-NFSv4 writers */ /* * It's possible there are non-NFSv4 write opens in progress, * but if they haven't incremented i_writecount yet then they * also haven't called break lease yet; so, they'll break this * lease soon enough. So, all that's left to check for is NFSv4 * opens: */ spin_lock(&fp->fi_lock); list_for_each_entry(st, &fp->fi_stateids, st_perfile) { if (st->st_openstp == NULL /* it's an open */ && access_permit_write(st) && st->st_stid.sc_client != clp) { spin_unlock(&fp->fi_lock); return -EAGAIN; } } spin_unlock(&fp->fi_lock); /* * There's a small chance that we could be racing with another * NFSv4 open. However, any open that hasn't added itself to * the fi_stateids list also hasn't called break_lease yet; so, * they'll break this lease soon enough. */ return 0; } /* * It's possible that between opening the dentry and setting the delegation, * that it has been renamed or unlinked. Redo the lookup to verify that this * hasn't happened. */ static int nfsd4_verify_deleg_dentry(struct nfsd4_open *open, struct nfs4_file *fp, struct svc_fh *parent) { struct svc_export *exp; struct dentry *child; __be32 err; err = nfsd_lookup_dentry(open->op_rqstp, parent, open->op_fname, open->op_fnamelen, &exp, &child); if (err) return -EAGAIN; exp_put(exp); dput(child); if (child != file_dentry(fp->fi_deleg_file->nf_file)) return -EAGAIN; return 0; } /* * We avoid breaking delegations held by a client due to its own activity, but * clearing setuid/setgid bits on a write is an implicit activity and the client * may not notice and continue using the old mode. Avoid giving out a delegation * on setuid/setgid files when the client is requesting an open for write. */ static int nfsd4_verify_setuid_write(struct nfsd4_open *open, struct nfsd_file *nf) { struct inode *inode = file_inode(nf->nf_file); if ((open->op_share_access & NFS4_SHARE_ACCESS_WRITE) && (inode->i_mode & (S_ISUID|S_ISGID))) return -EAGAIN; return 0; } static struct nfs4_delegation * nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, struct svc_fh *parent) { int status = 0; struct nfs4_client *clp = stp->st_stid.sc_client; struct nfs4_file *fp = stp->st_stid.sc_file; struct nfs4_clnt_odstate *odstate = stp->st_clnt_odstate; struct nfs4_delegation *dp; struct nfsd_file *nf = NULL; struct file_lease *fl; u32 dl_type; /* * The fi_had_conflict and nfs_get_existing_delegation checks * here are just optimizations; we'll need to recheck them at * the end: */ if (fp->fi_had_conflict) return ERR_PTR(-EAGAIN); /* * Try for a write delegation first. RFC8881 section 10.4 says: * * "An OPEN_DELEGATE_WRITE delegation allows the client to handle, * on its own, all opens." * * Furthermore the client can use a write delegation for most READ * operations as well, so we require a O_RDWR file here. * * Offer a write delegation in the case of a BOTH open, and ensure * we get the O_RDWR descriptor. */ if ((open->op_share_access & NFS4_SHARE_ACCESS_BOTH) == NFS4_SHARE_ACCESS_BOTH) { nf = find_rw_file(fp); dl_type = NFS4_OPEN_DELEGATE_WRITE; } /* * If the file is being opened O_RDONLY or we couldn't get a O_RDWR * file for some reason, then try for a read delegation instead. */ if (!nf && (open->op_share_access & NFS4_SHARE_ACCESS_READ)) { nf = find_readable_file(fp); dl_type = NFS4_OPEN_DELEGATE_READ; } if (!nf) return ERR_PTR(-EAGAIN); spin_lock(&state_lock); spin_lock(&fp->fi_lock); if (nfs4_delegation_exists(clp, fp)) status = -EAGAIN; else if (nfsd4_verify_setuid_write(open, nf)) status = -EAGAIN; else if (!fp->fi_deleg_file) { fp->fi_deleg_file = nf; /* increment early to prevent fi_deleg_file from being * cleared */ fp->fi_delegees = 1; nf = NULL; } else fp->fi_delegees++; spin_unlock(&fp->fi_lock); spin_unlock(&state_lock); if (nf) nfsd_file_put(nf); if (status) return ERR_PTR(status); status = -ENOMEM; dp = alloc_init_deleg(clp, fp, odstate, dl_type); if (!dp) goto out_delegees; fl = nfs4_alloc_init_lease(dp, dl_type); if (!fl) goto out_clnt_odstate; status = kernel_setlease(fp->fi_deleg_file->nf_file, fl->c.flc_type, &fl, NULL); if (fl) locks_free_lease(fl); if (status) goto out_clnt_odstate; if (parent) { status = nfsd4_verify_deleg_dentry(open, fp, parent); if (status) goto out_unlock; } status = nfsd4_check_conflicting_opens(clp, fp); if (status) goto out_unlock; /* * Now that the deleg is set, check again to ensure that nothing * raced in and changed the mode while we weren't looking. */ status = nfsd4_verify_setuid_write(open, fp->fi_deleg_file); if (status) goto out_unlock; status = -EAGAIN; if (fp->fi_had_conflict) goto out_unlock; spin_lock(&state_lock); spin_lock(&clp->cl_lock); spin_lock(&fp->fi_lock); status = hash_delegation_locked(dp, fp); spin_unlock(&fp->fi_lock); spin_unlock(&clp->cl_lock); spin_unlock(&state_lock); if (status) goto out_unlock; return dp; out_unlock: kernel_setlease(fp->fi_deleg_file->nf_file, F_UNLCK, NULL, (void **)&dp); out_clnt_odstate: put_clnt_odstate(dp->dl_clnt_odstate); nfs4_put_stid(&dp->dl_stid); out_delegees: put_deleg_file(fp); return ERR_PTR(status); } static void nfsd4_open_deleg_none_ext(struct nfsd4_open *open, int status) { open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT; if (status == -EAGAIN) open->op_why_no_deleg = WND4_CONTENTION; else { open->op_why_no_deleg = WND4_RESOURCE; switch (open->op_deleg_want) { case NFS4_SHARE_WANT_READ_DELEG: case NFS4_SHARE_WANT_WRITE_DELEG: case NFS4_SHARE_WANT_ANY_DELEG: break; case NFS4_SHARE_WANT_CANCEL: open->op_why_no_deleg = WND4_CANCELLED; break; case NFS4_SHARE_WANT_NO_DELEG: WARN_ON_ONCE(1); } } } static bool nfs4_delegation_stat(struct nfs4_delegation *dp, struct svc_fh *currentfh, struct kstat *stat) { struct nfsd_file *nf = find_rw_file(dp->dl_stid.sc_file); struct path path; int rc; if (!nf) return false; path.mnt = currentfh->fh_export->ex_path.mnt; path.dentry = file_dentry(nf->nf_file); rc = vfs_getattr(&path, stat, (STATX_SIZE | STATX_CTIME | STATX_CHANGE_COOKIE), AT_STATX_SYNC_AS_STAT); nfsd_file_put(nf); return rc == 0; } /* * The Linux NFS server does not offer write delegations to NFSv4.0 * clients in order to avoid conflicts between write delegations and * GETATTRs requesting CHANGE or SIZE attributes. * * With NFSv4.1 and later minorversions, the SEQUENCE operation that * begins each COMPOUND contains a client ID. Delegation recall can * be avoided when the server recognizes the client sending a * GETATTR also holds write delegation it conflicts with. * * However, the NFSv4.0 protocol does not enable a server to * determine that a GETATTR originated from the client holding the * conflicting delegation versus coming from some other client. Per * RFC 7530 Section 16.7.5, the server must recall or send a * CB_GETATTR even when the GETATTR originates from the client that * holds the conflicting delegation. * * An NFSv4.0 client can trigger a pathological situation if it * always sends a DELEGRETURN preceded by a conflicting GETATTR in * the same COMPOUND. COMPOUND execution will always stop at the * GETATTR and the DELEGRETURN will never get executed. The server * eventually revokes the delegation, which can result in loss of * open or lock state. */ static void nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, struct svc_fh *currentfh) { struct nfs4_delegation *dp; struct nfs4_openowner *oo = openowner(stp->st_stateowner); struct nfs4_client *clp = stp->st_stid.sc_client; struct svc_fh *parent = NULL; int cb_up; int status = 0; struct kstat stat; cb_up = nfsd4_cb_channel_good(oo->oo_owner.so_client); open->op_recall = false; switch (open->op_claim_type) { case NFS4_OPEN_CLAIM_PREVIOUS: if (!cb_up) open->op_recall = true; break; case NFS4_OPEN_CLAIM_NULL: parent = currentfh; fallthrough; case NFS4_OPEN_CLAIM_FH: /* * Let's not give out any delegations till everyone's * had the chance to reclaim theirs, *and* until * NLM locks have all been reclaimed: */ if (locks_in_grace(clp->net)) goto out_no_deleg; if (!cb_up || !(oo->oo_flags & NFS4_OO_CONFIRMED)) goto out_no_deleg; if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE && !clp->cl_minorversion) goto out_no_deleg; break; default: goto out_no_deleg; } dp = nfs4_set_delegation(open, stp, parent); if (IS_ERR(dp)) goto out_no_deleg; memcpy(&open->op_delegate_stateid, &dp->dl_stid.sc_stateid, sizeof(dp->dl_stid.sc_stateid)); if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE) { if (!nfs4_delegation_stat(dp, currentfh, &stat)) { nfs4_put_stid(&dp->dl_stid); destroy_delegation(dp); goto out_no_deleg; } open->op_delegate_type = NFS4_OPEN_DELEGATE_WRITE; dp->dl_cb_fattr.ncf_cur_fsize = stat.size; dp->dl_cb_fattr.ncf_initial_cinfo = nfsd4_change_attribute(&stat, d_inode(currentfh->fh_dentry)); trace_nfsd_deleg_write(&dp->dl_stid.sc_stateid); } else { open->op_delegate_type = NFS4_OPEN_DELEGATE_READ; trace_nfsd_deleg_read(&dp->dl_stid.sc_stateid); } nfs4_put_stid(&dp->dl_stid); return; out_no_deleg: open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE; if (open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS && open->op_delegate_type != NFS4_OPEN_DELEGATE_NONE) { dprintk("NFSD: WARNING: refusing delegation reclaim\n"); open->op_recall = true; } /* 4.1 client asking for a delegation? */ if (open->op_deleg_want) nfsd4_open_deleg_none_ext(open, status); return; } static void nfsd4_deleg_xgrade_none_ext(struct nfsd4_open *open, struct nfs4_delegation *dp) { if (open->op_deleg_want == NFS4_SHARE_WANT_READ_DELEG && dp->dl_type == NFS4_OPEN_DELEGATE_WRITE) { open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT; open->op_why_no_deleg = WND4_NOT_SUPP_DOWNGRADE; } else if (open->op_deleg_want == NFS4_SHARE_WANT_WRITE_DELEG && dp->dl_type == NFS4_OPEN_DELEGATE_WRITE) { open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT; open->op_why_no_deleg = WND4_NOT_SUPP_UPGRADE; } /* Otherwise the client must be confused wanting a delegation * it already has, therefore we don't return * NFS4_OPEN_DELEGATE_NONE_EXT and reason. */ } /** * nfsd4_process_open2 - finish open processing * @rqstp: the RPC transaction being executed * @current_fh: NFSv4 COMPOUND's current filehandle * @open: OPEN arguments * * If successful, (1) truncate the file if open->op_truncate was * set, (2) set open->op_stateid, (3) set open->op_delegation. * * Returns %nfs_ok on success; otherwise an nfs4stat value in * network byte order is returned. */ __be32 nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open) { struct nfsd4_compoundres *resp = rqstp->rq_resp; struct nfs4_client *cl = open->op_openowner->oo_owner.so_client; struct nfs4_file *fp = NULL; struct nfs4_ol_stateid *stp = NULL; struct nfs4_delegation *dp = NULL; __be32 status; bool new_stp = false; /* * Lookup file; if found, lookup stateid and check open request, * and check for delegations in the process of being recalled. * If not found, create the nfs4_file struct */ fp = nfsd4_file_hash_insert(open->op_file, current_fh); if (unlikely(!fp)) return nfserr_jukebox; if (fp != open->op_file) { status = nfs4_check_deleg(cl, open, &dp); if (status) goto out; stp = nfsd4_find_and_lock_existing_open(fp, open); } else { open->op_file = NULL; status = nfserr_bad_stateid; if (nfsd4_is_deleg_cur(open)) goto out; } if (!stp) { stp = init_open_stateid(fp, open); if (!open->op_stp) new_stp = true; } /* * OPEN the file, or upgrade an existing OPEN. * If truncate fails, the OPEN fails. * * stp is already locked. */ if (!new_stp) { /* Stateid was found, this is an OPEN upgrade */ status = nfs4_upgrade_open(rqstp, fp, current_fh, stp, open); if (status) { mutex_unlock(&stp->st_mutex); goto out; } } else { status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open, true); if (status) { release_open_stateid(stp); mutex_unlock(&stp->st_mutex); goto out; } stp->st_clnt_odstate = find_or_hash_clnt_odstate(fp, open->op_odstate); if (stp->st_clnt_odstate == open->op_odstate) open->op_odstate = NULL; } nfs4_inc_and_copy_stateid(&open->op_stateid, &stp->st_stid); mutex_unlock(&stp->st_mutex); if (nfsd4_has_session(&resp->cstate)) { if (open->op_deleg_want & NFS4_SHARE_WANT_NO_DELEG) { open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT; open->op_why_no_deleg = WND4_NOT_WANTED; goto nodeleg; } } /* * Attempt to hand out a delegation. No error return, because the * OPEN succeeds even if we fail. */ nfs4_open_delegation(open, stp, &resp->cstate.current_fh); nodeleg: status = nfs_ok; trace_nfsd_open(&stp->st_stid.sc_stateid); out: /* 4.1 client trying to upgrade/downgrade delegation? */ if (open->op_delegate_type == NFS4_OPEN_DELEGATE_NONE && dp && open->op_deleg_want) nfsd4_deleg_xgrade_none_ext(open, dp); if (fp) put_nfs4_file(fp); if (status == 0 && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS) open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED; /* * To finish the open response, we just need to set the rflags. */ open->op_rflags = NFS4_OPEN_RESULT_LOCKTYPE_POSIX; if (nfsd4_has_session(&resp->cstate)) open->op_rflags |= NFS4_OPEN_RESULT_MAY_NOTIFY_LOCK; else if (!(open->op_openowner->oo_flags & NFS4_OO_CONFIRMED)) open->op_rflags |= NFS4_OPEN_RESULT_CONFIRM; if (dp) nfs4_put_stid(&dp->dl_stid); if (stp) nfs4_put_stid(&stp->st_stid); return status; } void nfsd4_cleanup_open_state(struct nfsd4_compound_state *cstate, struct nfsd4_open *open) { if (open->op_openowner) nfs4_put_stateowner(&open->op_openowner->oo_owner); if (open->op_file) kmem_cache_free(file_slab, open->op_file); if (open->op_stp) nfs4_put_stid(&open->op_stp->st_stid); if (open->op_odstate) kmem_cache_free(odstate_slab, open->op_odstate); } __be32 nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { clientid_t *clid = &u->renew; struct nfs4_client *clp; __be32 status; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); trace_nfsd_clid_renew(clid); status = set_client(clid, cstate, nn); if (status) return status; clp = cstate->clp; if (!list_empty(&clp->cl_delegations) && clp->cl_cb_state != NFSD4_CB_UP) return nfserr_cb_path_down; return nfs_ok; } void nfsd4_end_grace(struct nfsd_net *nn) { /* do nothing if grace period already ended */ if (nn->grace_ended) return; trace_nfsd_grace_complete(nn); nn->grace_ended = true; /* * If the server goes down again right now, an NFSv4 * client will still be allowed to reclaim after it comes back up, * even if it hasn't yet had a chance to reclaim state this time. * */ nfsd4_record_grace_done(nn); /* * At this point, NFSv4 clients can still reclaim. But if the * server crashes, any that have not yet reclaimed will be out * of luck on the next boot. * * (NFSv4.1+ clients are considered to have reclaimed once they * call RECLAIM_COMPLETE. NFSv4.0 clients are considered to * have reclaimed after their first OPEN.) */ locks_end_grace(&nn->nfsd4_manager); /* * At this point, and once lockd and/or any other containers * exit their grace period, further reclaims will fail and * regular locking can resume. */ } /* * If we've waited a lease period but there are still clients trying to * reclaim, wait a little longer to give them a chance to finish. */ static bool clients_still_reclaiming(struct nfsd_net *nn) { time64_t double_grace_period_end = nn->boot_time + 2 * nn->nfsd4_lease; if (nn->track_reclaim_completes && atomic_read(&nn->nr_reclaim_complete) == nn->reclaim_str_hashtbl_size) return false; if (!nn->somebody_reclaimed) return false; nn->somebody_reclaimed = false; /* * If we've given them *two* lease times to reclaim, and they're * still not done, give up: */ if (ktime_get_boottime_seconds() > double_grace_period_end) return false; return true; } struct laundry_time { time64_t cutoff; time64_t new_timeo; }; static bool state_expired(struct laundry_time *lt, time64_t last_refresh) { time64_t time_remaining; if (last_refresh < lt->cutoff) return true; time_remaining = last_refresh - lt->cutoff; lt->new_timeo = min(lt->new_timeo, time_remaining); return false; } #ifdef CONFIG_NFSD_V4_2_INTER_SSC void nfsd4_ssc_init_umount_work(struct nfsd_net *nn) { spin_lock_init(&nn->nfsd_ssc_lock); INIT_LIST_HEAD(&nn->nfsd_ssc_mount_list); init_waitqueue_head(&nn->nfsd_ssc_waitq); } /* * This is called when nfsd is being shutdown, after all inter_ssc * cleanup were done, to destroy the ssc delayed unmount list. */ static void nfsd4_ssc_shutdown_umount(struct nfsd_net *nn) { struct nfsd4_ssc_umount_item *ni = NULL; struct nfsd4_ssc_umount_item *tmp; spin_lock(&nn->nfsd_ssc_lock); list_for_each_entry_safe(ni, tmp, &nn->nfsd_ssc_mount_list, nsui_list) { list_del(&ni->nsui_list); spin_unlock(&nn->nfsd_ssc_lock); mntput(ni->nsui_vfsmount); kfree(ni); spin_lock(&nn->nfsd_ssc_lock); } spin_unlock(&nn->nfsd_ssc_lock); } static void nfsd4_ssc_expire_umount(struct nfsd_net *nn) { bool do_wakeup = false; struct nfsd4_ssc_umount_item *ni = NULL; struct nfsd4_ssc_umount_item *tmp; spin_lock(&nn->nfsd_ssc_lock); list_for_each_entry_safe(ni, tmp, &nn->nfsd_ssc_mount_list, nsui_list) { if (time_after(jiffies, ni->nsui_expire)) { if (refcount_read(&ni->nsui_refcnt) > 1) continue; /* mark being unmount */ ni->nsui_busy = true; spin_unlock(&nn->nfsd_ssc_lock); mntput(ni->nsui_vfsmount); spin_lock(&nn->nfsd_ssc_lock); /* waiters need to start from begin of list */ list_del(&ni->nsui_list); kfree(ni); /* wakeup ssc_connect waiters */ do_wakeup = true; continue; } break; } if (do_wakeup) wake_up_all(&nn->nfsd_ssc_waitq); spin_unlock(&nn->nfsd_ssc_lock); } #endif /* Check if any lock belonging to this lockowner has any blockers */ static bool nfs4_lockowner_has_blockers(struct nfs4_lockowner *lo) { struct file_lock_context *ctx; struct nfs4_ol_stateid *stp; struct nfs4_file *nf; list_for_each_entry(stp, &lo->lo_owner.so_stateids, st_perstateowner) { nf = stp->st_stid.sc_file; ctx = locks_inode_context(nf->fi_inode); if (!ctx) continue; if (locks_owner_has_blockers(ctx, lo)) return true; } return false; } static bool nfs4_anylock_blockers(struct nfs4_client *clp) { int i; struct nfs4_stateowner *so; struct nfs4_lockowner *lo; if (atomic_read(&clp->cl_delegs_in_recall)) return true; spin_lock(&clp->cl_lock); for (i = 0; i < OWNER_HASH_SIZE; i++) { list_for_each_entry(so, &clp->cl_ownerstr_hashtbl[i], so_strhash) { if (so->so_is_open_owner) continue; lo = lockowner(so); if (nfs4_lockowner_has_blockers(lo)) { spin_unlock(&clp->cl_lock); return true; } } } spin_unlock(&clp->cl_lock); return false; } static void nfs4_get_client_reaplist(struct nfsd_net *nn, struct list_head *reaplist, struct laundry_time *lt) { unsigned int maxreap, reapcnt = 0; struct list_head *pos, *next; struct nfs4_client *clp; maxreap = (atomic_read(&nn->nfs4_client_count) >= nn->nfs4_max_clients) ? NFSD_CLIENT_MAX_TRIM_PER_RUN : 0; INIT_LIST_HEAD(reaplist); spin_lock(&nn->client_lock); list_for_each_safe(pos, next, &nn->client_lru) { clp = list_entry(pos, struct nfs4_client, cl_lru); if (clp->cl_state == NFSD4_EXPIRABLE) goto exp_client; if (!state_expired(lt, clp->cl_time)) break; if (!atomic_read(&clp->cl_rpc_users)) { if (clp->cl_state == NFSD4_ACTIVE) atomic_inc(&nn->nfsd_courtesy_clients); clp->cl_state = NFSD4_COURTESY; } if (!client_has_state(clp)) goto exp_client; if (!nfs4_anylock_blockers(clp)) if (reapcnt >= maxreap) continue; exp_client: if (!mark_client_expired_locked(clp)) { list_add(&clp->cl_lru, reaplist); reapcnt++; } } spin_unlock(&nn->client_lock); } static void nfs4_get_courtesy_client_reaplist(struct nfsd_net *nn, struct list_head *reaplist) { unsigned int maxreap = 0, reapcnt = 0; struct list_head *pos, *next; struct nfs4_client *clp; maxreap = NFSD_CLIENT_MAX_TRIM_PER_RUN; INIT_LIST_HEAD(reaplist); spin_lock(&nn->client_lock); list_for_each_safe(pos, next, &nn->client_lru) { clp = list_entry(pos, struct nfs4_client, cl_lru); if (clp->cl_state == NFSD4_ACTIVE) break; if (reapcnt >= maxreap) break; if (!mark_client_expired_locked(clp)) { list_add(&clp->cl_lru, reaplist); reapcnt++; } } spin_unlock(&nn->client_lock); } static void nfs4_process_client_reaplist(struct list_head *reaplist) { struct list_head *pos, *next; struct nfs4_client *clp; list_for_each_safe(pos, next, reaplist) { clp = list_entry(pos, struct nfs4_client, cl_lru); trace_nfsd_clid_purged(&clp->cl_clientid); list_del_init(&clp->cl_lru); expire_client(clp); } } static void nfs40_clean_admin_revoked(struct nfsd_net *nn, struct laundry_time *lt) { struct nfs4_client *clp; spin_lock(&nn->client_lock); if (nn->nfs40_last_revoke == 0 || nn->nfs40_last_revoke > lt->cutoff) { spin_unlock(&nn->client_lock); return; } nn->nfs40_last_revoke = 0; retry: list_for_each_entry(clp, &nn->client_lru, cl_lru) { unsigned long id, tmp; struct nfs4_stid *stid; if (atomic_read(&clp->cl_admin_revoked) == 0) continue; spin_lock(&clp->cl_lock); idr_for_each_entry_ul(&clp->cl_stateids, stid, tmp, id) if (stid->sc_status & SC_STATUS_ADMIN_REVOKED) { refcount_inc(&stid->sc_count); spin_unlock(&nn->client_lock); /* this function drops ->cl_lock */ nfsd4_drop_revoked_stid(stid); nfs4_put_stid(stid); spin_lock(&nn->client_lock); goto retry; } spin_unlock(&clp->cl_lock); } spin_unlock(&nn->client_lock); } static time64_t nfs4_laundromat(struct nfsd_net *nn) { struct nfs4_openowner *oo; struct nfs4_delegation *dp; struct nfs4_ol_stateid *stp; struct nfsd4_blocked_lock *nbl; struct list_head *pos, *next, reaplist; struct laundry_time lt = { .cutoff = ktime_get_boottime_seconds() - nn->nfsd4_lease, .new_timeo = nn->nfsd4_lease }; struct nfs4_cpntf_state *cps; copy_stateid_t *cps_t; int i; if (clients_still_reclaiming(nn)) { lt.new_timeo = 0; goto out; } nfsd4_end_grace(nn); spin_lock(&nn->s2s_cp_lock); idr_for_each_entry(&nn->s2s_cp_stateids, cps_t, i) { cps = container_of(cps_t, struct nfs4_cpntf_state, cp_stateid); if (cps->cp_stateid.cs_type == NFS4_COPYNOTIFY_STID && state_expired(<, cps->cpntf_time)) _free_cpntf_state_locked(nn, cps); } spin_unlock(&nn->s2s_cp_lock); nfs4_get_client_reaplist(nn, &reaplist, <); nfs4_process_client_reaplist(&reaplist); nfs40_clean_admin_revoked(nn, <); spin_lock(&state_lock); list_for_each_safe(pos, next, &nn->del_recall_lru) { dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru); if (!state_expired(<, dp->dl_time)) break; refcount_inc(&dp->dl_stid.sc_count); unhash_delegation_locked(dp, SC_STATUS_REVOKED); list_add(&dp->dl_recall_lru, &reaplist); } spin_unlock(&state_lock); while (!list_empty(&reaplist)) { dp = list_first_entry(&reaplist, struct nfs4_delegation, dl_recall_lru); list_del_init(&dp->dl_recall_lru); revoke_delegation(dp); } spin_lock(&nn->client_lock); while (!list_empty(&nn->close_lru)) { oo = list_first_entry(&nn->close_lru, struct nfs4_openowner, oo_close_lru); if (!state_expired(<, oo->oo_time)) break; list_del_init(&oo->oo_close_lru); stp = oo->oo_last_closed_stid; oo->oo_last_closed_stid = NULL; spin_unlock(&nn->client_lock); nfs4_put_stid(&stp->st_stid); spin_lock(&nn->client_lock); } spin_unlock(&nn->client_lock); /* * It's possible for a client to try and acquire an already held lock * that is being held for a long time, and then lose interest in it. * So, we clean out any un-revisited request after a lease period * under the assumption that the client is no longer interested. * * RFC5661, sec. 9.6 states that the client must not rely on getting * notifications and must continue to poll for locks, even when the * server supports them. Thus this shouldn't lead to clients blocking * indefinitely once the lock does become free. */ BUG_ON(!list_empty(&reaplist)); spin_lock(&nn->blocked_locks_lock); while (!list_empty(&nn->blocked_locks_lru)) { nbl = list_first_entry(&nn->blocked_locks_lru, struct nfsd4_blocked_lock, nbl_lru); if (!state_expired(<, nbl->nbl_time)) break; list_move(&nbl->nbl_lru, &reaplist); list_del_init(&nbl->nbl_list); } spin_unlock(&nn->blocked_locks_lock); while (!list_empty(&reaplist)) { nbl = list_first_entry(&reaplist, struct nfsd4_blocked_lock, nbl_lru); list_del_init(&nbl->nbl_lru); free_blocked_lock(nbl); } #ifdef CONFIG_NFSD_V4_2_INTER_SSC /* service the server-to-server copy delayed unmount list */ nfsd4_ssc_expire_umount(nn); #endif if (atomic_long_read(&num_delegations) >= max_delegations) deleg_reaper(nn); out: return max_t(time64_t, lt.new_timeo, NFSD_LAUNDROMAT_MINTIMEOUT); } static void laundromat_main(struct work_struct *); static void laundromat_main(struct work_struct *laundry) { time64_t t; struct delayed_work *dwork = to_delayed_work(laundry); struct nfsd_net *nn = container_of(dwork, struct nfsd_net, laundromat_work); t = nfs4_laundromat(nn); queue_delayed_work(laundry_wq, &nn->laundromat_work, t*HZ); } static void courtesy_client_reaper(struct nfsd_net *nn) { struct list_head reaplist; nfs4_get_courtesy_client_reaplist(nn, &reaplist); nfs4_process_client_reaplist(&reaplist); } static void deleg_reaper(struct nfsd_net *nn) { struct list_head *pos, *next; struct nfs4_client *clp; LIST_HEAD(cblist); spin_lock(&nn->client_lock); list_for_each_safe(pos, next, &nn->client_lru) { clp = list_entry(pos, struct nfs4_client, cl_lru); if (clp->cl_state != NFSD4_ACTIVE || list_empty(&clp->cl_delegations) || atomic_read(&clp->cl_delegs_in_recall) || test_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags) || (ktime_get_boottime_seconds() - clp->cl_ra_time < 5)) { continue; } list_add(&clp->cl_ra_cblist, &cblist); /* release in nfsd4_cb_recall_any_release */ kref_get(&clp->cl_nfsdfs.cl_ref); set_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags); clp->cl_ra_time = ktime_get_boottime_seconds(); } spin_unlock(&nn->client_lock); while (!list_empty(&cblist)) { clp = list_first_entry(&cblist, struct nfs4_client, cl_ra_cblist); list_del_init(&clp->cl_ra_cblist); clp->cl_ra->ra_keep = 0; clp->cl_ra->ra_bmval[0] = BIT(RCA4_TYPE_MASK_RDATA_DLG) | BIT(RCA4_TYPE_MASK_WDATA_DLG); trace_nfsd_cb_recall_any(clp->cl_ra); nfsd4_run_cb(&clp->cl_ra->ra_cb); } } static void nfsd4_state_shrinker_worker(struct work_struct *work) { struct nfsd_net *nn = container_of(work, struct nfsd_net, nfsd_shrinker_work); courtesy_client_reaper(nn); deleg_reaper(nn); } static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_stid *stp) { if (!fh_match(&fhp->fh_handle, &stp->sc_file->fi_fhandle)) return nfserr_bad_stateid; return nfs_ok; } static __be32 nfs4_check_openmode(struct nfs4_ol_stateid *stp, int flags) { __be32 status = nfserr_openmode; /* For lock stateid's, we test the parent open, not the lock: */ if (stp->st_openstp) stp = stp->st_openstp; if ((flags & WR_STATE) && !access_permit_write(stp)) goto out; if ((flags & RD_STATE) && !access_permit_read(stp)) goto out; status = nfs_ok; out: return status; } static inline __be32 check_special_stateids(struct net *net, svc_fh *current_fh, stateid_t *stateid, int flags) { if (ONE_STATEID(stateid) && (flags & RD_STATE)) return nfs_ok; else if (opens_in_grace(net)) { /* Answer in remaining cases depends on existence of * conflicting state; so we must wait out the grace period. */ return nfserr_grace; } else if (flags & WR_STATE) return nfs4_share_conflict(current_fh, NFS4_SHARE_DENY_WRITE); else /* (flags & RD_STATE) && ZERO_STATEID(stateid) */ return nfs4_share_conflict(current_fh, NFS4_SHARE_DENY_READ); } static __be32 check_stateid_generation(stateid_t *in, stateid_t *ref, bool has_session) { /* * When sessions are used the stateid generation number is ignored * when it is zero. */ if (has_session && in->si_generation == 0) return nfs_ok; if (in->si_generation == ref->si_generation) return nfs_ok; /* If the client sends us a stateid from the future, it's buggy: */ if (nfsd4_stateid_generation_after(in, ref)) return nfserr_bad_stateid; /* * However, we could see a stateid from the past, even from a * non-buggy client. For example, if the client sends a lock * while some IO is outstanding, the lock may bump si_generation * while the IO is still in flight. The client could avoid that * situation by waiting for responses on all the IO requests, * but better performance may result in retrying IO that * receives an old_stateid error if requests are rarely * reordered in flight: */ return nfserr_old_stateid; } static __be32 nfsd4_stid_check_stateid_generation(stateid_t *in, struct nfs4_stid *s, bool has_session) { __be32 ret; spin_lock(&s->sc_lock); ret = nfsd4_verify_open_stid(s); if (ret == nfs_ok) ret = check_stateid_generation(in, &s->sc_stateid, has_session); spin_unlock(&s->sc_lock); if (ret == nfserr_admin_revoked) nfsd40_drop_revoked_stid(s->sc_client, &s->sc_stateid); return ret; } static __be32 nfsd4_check_openowner_confirmed(struct nfs4_ol_stateid *ols) { if (ols->st_stateowner->so_is_open_owner && !(openowner(ols->st_stateowner)->oo_flags & NFS4_OO_CONFIRMED)) return nfserr_bad_stateid; return nfs_ok; } static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid) { struct nfs4_stid *s; __be32 status = nfserr_bad_stateid; if (ZERO_STATEID(stateid) || ONE_STATEID(stateid) || CLOSE_STATEID(stateid)) return status; spin_lock(&cl->cl_lock); s = find_stateid_locked(cl, stateid); if (!s) goto out_unlock; status = nfsd4_stid_check_stateid_generation(stateid, s, 1); if (status) goto out_unlock; status = nfsd4_verify_open_stid(s); if (status) goto out_unlock; switch (s->sc_type) { case SC_TYPE_DELEG: status = nfs_ok; break; case SC_TYPE_OPEN: case SC_TYPE_LOCK: status = nfsd4_check_openowner_confirmed(openlockstateid(s)); break; default: printk("unknown stateid type %x\n", s->sc_type); status = nfserr_bad_stateid; } out_unlock: spin_unlock(&cl->cl_lock); if (status == nfserr_admin_revoked) nfsd40_drop_revoked_stid(cl, stateid); return status; } __be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, stateid_t *stateid, unsigned short typemask, unsigned short statusmask, struct nfs4_stid **s, struct nfsd_net *nn) { __be32 status; struct nfs4_stid *stid; bool return_revoked = false; /* * only return revoked delegations if explicitly asked. * otherwise we report revoked or bad_stateid status. */ if (statusmask & SC_STATUS_REVOKED) return_revoked = true; if (typemask & SC_TYPE_DELEG) /* Always allow REVOKED for DELEG so we can * retturn the appropriate error. */ statusmask |= SC_STATUS_REVOKED; statusmask |= SC_STATUS_ADMIN_REVOKED; if (ZERO_STATEID(stateid) || ONE_STATEID(stateid) || CLOSE_STATEID(stateid)) return nfserr_bad_stateid; status = set_client(&stateid->si_opaque.so_clid, cstate, nn); if (status == nfserr_stale_clientid) { if (cstate->session) return nfserr_bad_stateid; return nfserr_stale_stateid; } if (status) return status; stid = find_stateid_by_type(cstate->clp, stateid, typemask, statusmask); if (!stid) return nfserr_bad_stateid; if ((stid->sc_status & SC_STATUS_REVOKED) && !return_revoked) { nfs4_put_stid(stid); return nfserr_deleg_revoked; } if (stid->sc_status & SC_STATUS_ADMIN_REVOKED) { nfsd40_drop_revoked_stid(cstate->clp, stateid); nfs4_put_stid(stid); return nfserr_admin_revoked; } *s = stid; return nfs_ok; } static struct nfsd_file * nfs4_find_file(struct nfs4_stid *s, int flags) { struct nfsd_file *ret = NULL; if (!s || s->sc_status) return NULL; switch (s->sc_type) { case SC_TYPE_DELEG: spin_lock(&s->sc_file->fi_lock); ret = nfsd_file_get(s->sc_file->fi_deleg_file); spin_unlock(&s->sc_file->fi_lock); break; case SC_TYPE_OPEN: case SC_TYPE_LOCK: if (flags & RD_STATE) ret = find_readable_file(s->sc_file); else ret = find_writeable_file(s->sc_file); } return ret; } static __be32 nfs4_check_olstateid(struct nfs4_ol_stateid *ols, int flags) { __be32 status; status = nfsd4_check_openowner_confirmed(ols); if (status) return status; return nfs4_check_openmode(ols, flags); } static __be32 nfs4_check_file(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfs4_stid *s, struct nfsd_file **nfp, int flags) { int acc = (flags & RD_STATE) ? NFSD_MAY_READ : NFSD_MAY_WRITE; struct nfsd_file *nf; __be32 status; nf = nfs4_find_file(s, flags); if (nf) { status = nfsd_permission(&rqstp->rq_cred, fhp->fh_export, fhp->fh_dentry, acc | NFSD_MAY_OWNER_OVERRIDE); if (status) { nfsd_file_put(nf); goto out; } } else { status = nfsd_file_acquire(rqstp, fhp, acc, &nf); if (status) return status; } *nfp = nf; out: return status; } static void _free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps) { WARN_ON_ONCE(cps->cp_stateid.cs_type != NFS4_COPYNOTIFY_STID); if (!refcount_dec_and_test(&cps->cp_stateid.cs_count)) return; list_del(&cps->cp_list); idr_remove(&nn->s2s_cp_stateids, cps->cp_stateid.cs_stid.si_opaque.so_id); kfree(cps); } /* * A READ from an inter server to server COPY will have a * copy stateid. Look up the copy notify stateid from the * idr structure and take a reference on it. */ __be32 manage_cpntf_state(struct nfsd_net *nn, stateid_t *st, struct nfs4_client *clp, struct nfs4_cpntf_state **cps) { copy_stateid_t *cps_t; struct nfs4_cpntf_state *state = NULL; if (st->si_opaque.so_clid.cl_id != nn->s2s_cp_cl_id) return nfserr_bad_stateid; spin_lock(&nn->s2s_cp_lock); cps_t = idr_find(&nn->s2s_cp_stateids, st->si_opaque.so_id); if (cps_t) { state = container_of(cps_t, struct nfs4_cpntf_state, cp_stateid); if (state->cp_stateid.cs_type != NFS4_COPYNOTIFY_STID) { state = NULL; goto unlock; } if (!clp) refcount_inc(&state->cp_stateid.cs_count); else _free_cpntf_state_locked(nn, state); } unlock: spin_unlock(&nn->s2s_cp_lock); if (!state) return nfserr_bad_stateid; if (!clp) *cps = state; return 0; } static __be32 find_cpntf_state(struct nfsd_net *nn, stateid_t *st, struct nfs4_stid **stid) { __be32 status; struct nfs4_cpntf_state *cps = NULL; struct nfs4_client *found; status = manage_cpntf_state(nn, st, NULL, &cps); if (status) return status; cps->cpntf_time = ktime_get_boottime_seconds(); status = nfserr_expired; found = lookup_clientid(&cps->cp_p_clid, true, nn); if (!found) goto out; *stid = find_stateid_by_type(found, &cps->cp_p_stateid, SC_TYPE_DELEG|SC_TYPE_OPEN|SC_TYPE_LOCK, 0); if (*stid) status = nfs_ok; else status = nfserr_bad_stateid; put_client_renew(found); out: nfs4_put_cpntf_state(nn, cps); return status; } void nfs4_put_cpntf_state(struct nfsd_net *nn, struct nfs4_cpntf_state *cps) { spin_lock(&nn->s2s_cp_lock); _free_cpntf_state_locked(nn, cps); spin_unlock(&nn->s2s_cp_lock); } /** * nfs4_preprocess_stateid_op - find and prep stateid for an operation * @rqstp: incoming request from client * @cstate: current compound state * @fhp: filehandle associated with requested stateid * @stateid: stateid (provided by client) * @flags: flags describing type of operation to be done * @nfp: optional nfsd_file return pointer (may be NULL) * @cstid: optional returned nfs4_stid pointer (may be NULL) * * Given info from the client, look up a nfs4_stid for the operation. On * success, it returns a reference to the nfs4_stid and/or the nfsd_file * associated with it. */ __be32 nfs4_preprocess_stateid_op(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct svc_fh *fhp, stateid_t *stateid, int flags, struct nfsd_file **nfp, struct nfs4_stid **cstid) { struct net *net = SVC_NET(rqstp); struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct nfs4_stid *s = NULL; __be32 status; if (nfp) *nfp = NULL; if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) { status = check_special_stateids(net, fhp, stateid, flags); goto done; } status = nfsd4_lookup_stateid(cstate, stateid, SC_TYPE_DELEG|SC_TYPE_OPEN|SC_TYPE_LOCK, 0, &s, nn); if (status == nfserr_bad_stateid) status = find_cpntf_state(nn, stateid, &s); if (status) return status; status = nfsd4_stid_check_stateid_generation(stateid, s, nfsd4_has_session(cstate)); if (status) goto out; switch (s->sc_type) { case SC_TYPE_DELEG: status = nfs4_check_delegmode(delegstateid(s), flags); break; case SC_TYPE_OPEN: case SC_TYPE_LOCK: status = nfs4_check_olstateid(openlockstateid(s), flags); break; } if (status) goto out; status = nfs4_check_fh(fhp, s); done: if (status == nfs_ok && nfp) status = nfs4_check_file(rqstp, fhp, s, nfp, flags); out: if (s) { if (!status && cstid) *cstid = s; else nfs4_put_stid(s); } return status; } /* * Test if the stateid is valid */ __be32 nfsd4_test_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_test_stateid *test_stateid = &u->test_stateid; struct nfsd4_test_stateid_id *stateid; struct nfs4_client *cl = cstate->clp; list_for_each_entry(stateid, &test_stateid->ts_stateid_list, ts_id_list) stateid->ts_id_status = nfsd4_validate_stateid(cl, &stateid->ts_id_stateid); return nfs_ok; } static __be32 nfsd4_free_lock_stateid(stateid_t *stateid, struct nfs4_stid *s) { struct nfs4_ol_stateid *stp = openlockstateid(s); __be32 ret; ret = nfsd4_lock_ol_stateid(stp); if (ret) goto out_put_stid; ret = check_stateid_generation(stateid, &s->sc_stateid, 1); if (ret) goto out; ret = nfserr_locks_held; if (check_for_locks(stp->st_stid.sc_file, lockowner(stp->st_stateowner))) goto out; release_lock_stateid(stp); ret = nfs_ok; out: mutex_unlock(&stp->st_mutex); out_put_stid: nfs4_put_stid(s); return ret; } __be32 nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_free_stateid *free_stateid = &u->free_stateid; stateid_t *stateid = &free_stateid->fr_stateid; struct nfs4_stid *s; struct nfs4_delegation *dp; struct nfs4_client *cl = cstate->clp; __be32 ret = nfserr_bad_stateid; spin_lock(&cl->cl_lock); s = find_stateid_locked(cl, stateid); if (!s || s->sc_status & SC_STATUS_CLOSED) goto out_unlock; if (s->sc_status & SC_STATUS_ADMIN_REVOKED) { nfsd4_drop_revoked_stid(s); ret = nfs_ok; goto out; } spin_lock(&s->sc_lock); switch (s->sc_type) { case SC_TYPE_DELEG: if (s->sc_status & SC_STATUS_REVOKED) { s->sc_status |= SC_STATUS_CLOSED; spin_unlock(&s->sc_lock); dp = delegstateid(s); if (s->sc_status & SC_STATUS_FREEABLE) list_del_init(&dp->dl_recall_lru); s->sc_status |= SC_STATUS_FREED; spin_unlock(&cl->cl_lock); nfs4_put_stid(s); ret = nfs_ok; goto out; } ret = nfserr_locks_held; break; case SC_TYPE_OPEN: ret = check_stateid_generation(stateid, &s->sc_stateid, 1); if (ret) break; ret = nfserr_locks_held; break; case SC_TYPE_LOCK: spin_unlock(&s->sc_lock); refcount_inc(&s->sc_count); spin_unlock(&cl->cl_lock); ret = nfsd4_free_lock_stateid(stateid, s); goto out; } spin_unlock(&s->sc_lock); out_unlock: spin_unlock(&cl->cl_lock); out: return ret; } static inline int setlkflg (int type) { return (type == NFS4_READW_LT || type == NFS4_READ_LT) ? RD_STATE : WR_STATE; } static __be32 nfs4_seqid_op_checks(struct nfsd4_compound_state *cstate, stateid_t *stateid, u32 seqid, struct nfs4_ol_stateid *stp) { struct svc_fh *current_fh = &cstate->current_fh; struct nfs4_stateowner *sop = stp->st_stateowner; __be32 status; status = nfsd4_check_seqid(cstate, sop, seqid); if (status) return status; status = nfsd4_lock_ol_stateid(stp); if (status != nfs_ok) return status; status = check_stateid_generation(stateid, &stp->st_stid.sc_stateid, nfsd4_has_session(cstate)); if (status == nfs_ok) status = nfs4_check_fh(current_fh, &stp->st_stid); if (status != nfs_ok) mutex_unlock(&stp->st_mutex); return status; } /** * nfs4_preprocess_seqid_op - find and prep an ol_stateid for a seqid-morphing op * @cstate: compund state * @seqid: seqid (provided by client) * @stateid: stateid (provided by client) * @typemask: mask of allowable types for this operation * @statusmask: mask of allowed states: 0 or STID_CLOSED * @stpp: return pointer for the stateid found * @nn: net namespace for request * * Given a stateid+seqid from a client, look up an nfs4_ol_stateid and * return it in @stpp. On a nfs_ok return, the returned stateid will * have its st_mutex locked. */ static __be32 nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid, stateid_t *stateid, unsigned short typemask, unsigned short statusmask, struct nfs4_ol_stateid **stpp, struct nfsd_net *nn) { __be32 status; struct nfs4_stid *s; struct nfs4_ol_stateid *stp = NULL; trace_nfsd_preprocess(seqid, stateid); *stpp = NULL; retry: status = nfsd4_lookup_stateid(cstate, stateid, typemask, statusmask, &s, nn); if (status) return status; stp = openlockstateid(s); if (nfsd4_cstate_assign_replay(cstate, stp->st_stateowner) == -EAGAIN) { nfs4_put_stateowner(stp->st_stateowner); goto retry; } status = nfs4_seqid_op_checks(cstate, stateid, seqid, stp); if (!status) *stpp = stp; else nfs4_put_stid(&stp->st_stid); return status; } static __be32 nfs4_preprocess_confirmed_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid, stateid_t *stateid, struct nfs4_ol_stateid **stpp, struct nfsd_net *nn) { __be32 status; struct nfs4_openowner *oo; struct nfs4_ol_stateid *stp; status = nfs4_preprocess_seqid_op(cstate, seqid, stateid, SC_TYPE_OPEN, 0, &stp, nn); if (status) return status; oo = openowner(stp->st_stateowner); if (!(oo->oo_flags & NFS4_OO_CONFIRMED)) { mutex_unlock(&stp->st_mutex); nfs4_put_stid(&stp->st_stid); return nfserr_bad_stateid; } *stpp = stp; return nfs_ok; } __be32 nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_open_confirm *oc = &u->open_confirm; __be32 status; struct nfs4_openowner *oo; struct nfs4_ol_stateid *stp; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); dprintk("NFSD: nfsd4_open_confirm on file %pd\n", cstate->current_fh.fh_dentry); status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0); if (status) return status; status = nfs4_preprocess_seqid_op(cstate, oc->oc_seqid, &oc->oc_req_stateid, SC_TYPE_OPEN, 0, &stp, nn); if (status) goto out; oo = openowner(stp->st_stateowner); status = nfserr_bad_stateid; if (oo->oo_flags & NFS4_OO_CONFIRMED) { mutex_unlock(&stp->st_mutex); goto put_stateid; } oo->oo_flags |= NFS4_OO_CONFIRMED; nfs4_inc_and_copy_stateid(&oc->oc_resp_stateid, &stp->st_stid); mutex_unlock(&stp->st_mutex); trace_nfsd_open_confirm(oc->oc_seqid, &stp->st_stid.sc_stateid); nfsd4_client_record_create(oo->oo_owner.so_client); status = nfs_ok; put_stateid: nfs4_put_stid(&stp->st_stid); out: nfsd4_bump_seqid(cstate, status); return status; } static inline void nfs4_stateid_downgrade_bit(struct nfs4_ol_stateid *stp, u32 access) { if (!test_access(access, stp)) return; nfs4_file_put_access(stp->st_stid.sc_file, access); clear_access(access, stp); } static inline void nfs4_stateid_downgrade(struct nfs4_ol_stateid *stp, u32 to_access) { switch (to_access) { case NFS4_SHARE_ACCESS_READ: nfs4_stateid_downgrade_bit(stp, NFS4_SHARE_ACCESS_WRITE); nfs4_stateid_downgrade_bit(stp, NFS4_SHARE_ACCESS_BOTH); break; case NFS4_SHARE_ACCESS_WRITE: nfs4_stateid_downgrade_bit(stp, NFS4_SHARE_ACCESS_READ); nfs4_stateid_downgrade_bit(stp, NFS4_SHARE_ACCESS_BOTH); break; case NFS4_SHARE_ACCESS_BOTH: break; default: WARN_ON_ONCE(1); } } __be32 nfsd4_open_downgrade(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_open_downgrade *od = &u->open_downgrade; __be32 status; struct nfs4_ol_stateid *stp; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); dprintk("NFSD: nfsd4_open_downgrade on file %pd\n", cstate->current_fh.fh_dentry); /* We don't yet support WANT bits: */ if (od->od_deleg_want) dprintk("NFSD: %s: od_deleg_want=0x%x ignored\n", __func__, od->od_deleg_want); status = nfs4_preprocess_confirmed_seqid_op(cstate, od->od_seqid, &od->od_stateid, &stp, nn); if (status) goto out; status = nfserr_inval; if (!test_access(od->od_share_access, stp)) { dprintk("NFSD: access not a subset of current bitmap: 0x%hhx, input access=%08x\n", stp->st_access_bmap, od->od_share_access); goto put_stateid; } if (!test_deny(od->od_share_deny, stp)) { dprintk("NFSD: deny not a subset of current bitmap: 0x%hhx, input deny=%08x\n", stp->st_deny_bmap, od->od_share_deny); goto put_stateid; } nfs4_stateid_downgrade(stp, od->od_share_access); reset_union_bmap_deny(od->od_share_deny, stp); nfs4_inc_and_copy_stateid(&od->od_stateid, &stp->st_stid); status = nfs_ok; put_stateid: mutex_unlock(&stp->st_mutex); nfs4_put_stid(&stp->st_stid); out: nfsd4_bump_seqid(cstate, status); return status; } static bool nfsd4_close_open_stateid(struct nfs4_ol_stateid *s) { struct nfs4_client *clp = s->st_stid.sc_client; bool unhashed; LIST_HEAD(reaplist); struct nfs4_ol_stateid *stp; spin_lock(&clp->cl_lock); unhashed = unhash_open_stateid(s, &reaplist); if (clp->cl_minorversion) { if (unhashed) put_ol_stateid_locked(s, &reaplist); spin_unlock(&clp->cl_lock); list_for_each_entry(stp, &reaplist, st_locks) nfs4_free_cpntf_statelist(clp->net, &stp->st_stid); free_ol_stateid_reaplist(&reaplist); return false; } else { spin_unlock(&clp->cl_lock); free_ol_stateid_reaplist(&reaplist); return unhashed; } } /* * nfs4_unlock_state() called after encode */ __be32 nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_close *close = &u->close; __be32 status; struct nfs4_ol_stateid *stp; struct net *net = SVC_NET(rqstp); struct nfsd_net *nn = net_generic(net, nfsd_net_id); bool need_move_to_close_list; dprintk("NFSD: nfsd4_close on file %pd\n", cstate->current_fh.fh_dentry); status = nfs4_preprocess_seqid_op(cstate, close->cl_seqid, &close->cl_stateid, SC_TYPE_OPEN, SC_STATUS_CLOSED, &stp, nn); nfsd4_bump_seqid(cstate, status); if (status) goto out; spin_lock(&stp->st_stid.sc_client->cl_lock); stp->st_stid.sc_status |= SC_STATUS_CLOSED; spin_unlock(&stp->st_stid.sc_client->cl_lock); /* * Technically we don't _really_ have to increment or copy it, since * it should just be gone after this operation and we clobber the * copied value below, but we continue to do so here just to ensure * that racing ops see that there was a state change. */ nfs4_inc_and_copy_stateid(&close->cl_stateid, &stp->st_stid); need_move_to_close_list = nfsd4_close_open_stateid(stp); mutex_unlock(&stp->st_mutex); if (need_move_to_close_list) move_to_close_lru(stp, net); /* v4.1+ suggests that we send a special stateid in here, since the * clients should just ignore this anyway. Since this is not useful * for v4.0 clients either, we set it to the special close_stateid * universally. * * See RFC5661 section 18.2.4, and RFC7530 section 16.2.5 */ memcpy(&close->cl_stateid, &close_stateid, sizeof(close->cl_stateid)); /* put reference from nfs4_preprocess_seqid_op */ nfs4_put_stid(&stp->st_stid); out: return status; } __be32 nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_delegreturn *dr = &u->delegreturn; struct nfs4_delegation *dp; stateid_t *stateid = &dr->dr_stateid; struct nfs4_stid *s; __be32 status; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); if ((status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0))) return status; status = nfsd4_lookup_stateid(cstate, stateid, SC_TYPE_DELEG, SC_STATUS_REVOKED | SC_STATUS_FREEABLE, &s, nn); if (status) goto out; dp = delegstateid(s); status = nfsd4_stid_check_stateid_generation(stateid, &dp->dl_stid, nfsd4_has_session(cstate)); if (status) goto put_stateid; trace_nfsd_deleg_return(stateid); destroy_delegation(dp); smp_mb__after_atomic(); wake_up_var(d_inode(cstate->current_fh.fh_dentry)); put_stateid: nfs4_put_stid(&dp->dl_stid); out: return status; } /* last octet in a range */ static inline u64 last_byte_offset(u64 start, u64 len) { u64 end; WARN_ON_ONCE(!len); end = start + len; return end > start ? end - 1: NFS4_MAX_UINT64; } /* * TODO: Linux file offsets are _signed_ 64-bit quantities, which means that * we can't properly handle lock requests that go beyond the (2^63 - 1)-th * byte, because of sign extension problems. Since NFSv4 calls for 64-bit * locking, this prevents us from being completely protocol-compliant. The * real solution to this problem is to start using unsigned file offsets in * the VFS, but this is a very deep change! */ static inline void nfs4_transform_lock_offset(struct file_lock *lock) { if (lock->fl_start < 0) lock->fl_start = OFFSET_MAX; if (lock->fl_end < 0) lock->fl_end = OFFSET_MAX; } static fl_owner_t nfsd4_lm_get_owner(fl_owner_t owner) { struct nfs4_lockowner *lo = (struct nfs4_lockowner *)owner; nfs4_get_stateowner(&lo->lo_owner); return owner; } static void nfsd4_lm_put_owner(fl_owner_t owner) { struct nfs4_lockowner *lo = (struct nfs4_lockowner *)owner; if (lo) nfs4_put_stateowner(&lo->lo_owner); } /* return pointer to struct nfs4_client if client is expirable */ static bool nfsd4_lm_lock_expirable(struct file_lock *cfl) { struct nfs4_lockowner *lo = (struct nfs4_lockowner *) cfl->c.flc_owner; struct nfs4_client *clp = lo->lo_owner.so_client; struct nfsd_net *nn; if (try_to_expire_client(clp)) { nn = net_generic(clp->net, nfsd_net_id); mod_delayed_work(laundry_wq, &nn->laundromat_work, 0); return true; } return false; } /* schedule laundromat to run immediately and wait for it to complete */ static void nfsd4_lm_expire_lock(void) { flush_workqueue(laundry_wq); } static void nfsd4_lm_notify(struct file_lock *fl) { struct nfs4_lockowner *lo = (struct nfs4_lockowner *) fl->c.flc_owner; struct net *net = lo->lo_owner.so_client->net; struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct nfsd4_blocked_lock *nbl = container_of(fl, struct nfsd4_blocked_lock, nbl_lock); bool queue = false; /* An empty list means that something else is going to be using it */ spin_lock(&nn->blocked_locks_lock); if (!list_empty(&nbl->nbl_list)) { list_del_init(&nbl->nbl_list); list_del_init(&nbl->nbl_lru); queue = true; } spin_unlock(&nn->blocked_locks_lock); if (queue) { trace_nfsd_cb_notify_lock(lo, nbl); nfsd4_run_cb(&nbl->nbl_cb); } } static const struct lock_manager_operations nfsd_posix_mng_ops = { .lm_mod_owner = THIS_MODULE, .lm_notify = nfsd4_lm_notify, .lm_get_owner = nfsd4_lm_get_owner, .lm_put_owner = nfsd4_lm_put_owner, .lm_lock_expirable = nfsd4_lm_lock_expirable, .lm_expire_lock = nfsd4_lm_expire_lock, }; static inline void nfs4_set_lock_denied(struct file_lock *fl, struct nfsd4_lock_denied *deny) { struct nfs4_lockowner *lo; if (fl->fl_lmops == &nfsd_posix_mng_ops) { lo = (struct nfs4_lockowner *) fl->c.flc_owner; xdr_netobj_dup(&deny->ld_owner, &lo->lo_owner.so_owner, GFP_KERNEL); if (!deny->ld_owner.data) /* We just don't care that much */ goto nevermind; deny->ld_clientid = lo->lo_owner.so_client->cl_clientid; } else { nevermind: deny->ld_owner.len = 0; deny->ld_owner.data = NULL; deny->ld_clientid.cl_boot = 0; deny->ld_clientid.cl_id = 0; } deny->ld_start = fl->fl_start; deny->ld_length = NFS4_MAX_UINT64; if (fl->fl_end != NFS4_MAX_UINT64) deny->ld_length = fl->fl_end - fl->fl_start + 1; deny->ld_type = NFS4_READ_LT; if (fl->c.flc_type != F_RDLCK) deny->ld_type = NFS4_WRITE_LT; } static struct nfs4_lockowner * find_lockowner_str_locked(struct nfs4_client *clp, struct xdr_netobj *owner) { unsigned int strhashval = ownerstr_hashval(owner); struct nfs4_stateowner *so; lockdep_assert_held(&clp->cl_lock); list_for_each_entry(so, &clp->cl_ownerstr_hashtbl[strhashval], so_strhash) { if (so->so_is_open_owner) continue; if (same_owner_str(so, owner)) return lockowner(nfs4_get_stateowner(so)); } return NULL; } static struct nfs4_lockowner * find_lockowner_str(struct nfs4_client *clp, struct xdr_netobj *owner) { struct nfs4_lockowner *lo; spin_lock(&clp->cl_lock); lo = find_lockowner_str_locked(clp, owner); spin_unlock(&clp->cl_lock); return lo; } static void nfs4_unhash_lockowner(struct nfs4_stateowner *sop) { unhash_lockowner_locked(lockowner(sop)); } static void nfs4_free_lockowner(struct nfs4_stateowner *sop) { struct nfs4_lockowner *lo = lockowner(sop); kmem_cache_free(lockowner_slab, lo); } static const struct nfs4_stateowner_operations lockowner_ops = { .so_unhash = nfs4_unhash_lockowner, .so_free = nfs4_free_lockowner, }; /* * Alloc a lock owner structure. * Called in nfsd4_lock - therefore, OPEN and OPEN_CONFIRM (if needed) has * occurred. * * strhashval = ownerstr_hashval */ static struct nfs4_lockowner * alloc_init_lock_stateowner(unsigned int strhashval, struct nfs4_client *clp, struct nfs4_ol_stateid *open_stp, struct nfsd4_lock *lock) { struct nfs4_lockowner *lo, *ret; lo = alloc_stateowner(lockowner_slab, &lock->lk_new_owner, clp); if (!lo) return NULL; INIT_LIST_HEAD(&lo->lo_blocked); INIT_LIST_HEAD(&lo->lo_owner.so_stateids); lo->lo_owner.so_is_open_owner = 0; lo->lo_owner.so_seqid = lock->lk_new_lock_seqid; lo->lo_owner.so_ops = &lockowner_ops; spin_lock(&clp->cl_lock); ret = find_lockowner_str_locked(clp, &lock->lk_new_owner); if (ret == NULL) { list_add(&lo->lo_owner.so_strhash, &clp->cl_ownerstr_hashtbl[strhashval]); ret = lo; } else nfs4_free_stateowner(&lo->lo_owner); spin_unlock(&clp->cl_lock); return ret; } static struct nfs4_ol_stateid * find_lock_stateid(const struct nfs4_lockowner *lo, const struct nfs4_ol_stateid *ost) { struct nfs4_ol_stateid *lst; lockdep_assert_held(&ost->st_stid.sc_client->cl_lock); /* If ost is not hashed, ost->st_locks will not be valid */ if (!nfs4_ol_stateid_unhashed(ost)) list_for_each_entry(lst, &ost->st_locks, st_locks) { if (lst->st_stateowner == &lo->lo_owner) { refcount_inc(&lst->st_stid.sc_count); return lst; } } return NULL; } static struct nfs4_ol_stateid * init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo, struct nfs4_file *fp, struct inode *inode, struct nfs4_ol_stateid *open_stp) { struct nfs4_client *clp = lo->lo_owner.so_client; struct nfs4_ol_stateid *retstp; mutex_init(&stp->st_mutex); mutex_lock_nested(&stp->st_mutex, OPEN_STATEID_MUTEX); retry: spin_lock(&clp->cl_lock); if (nfs4_ol_stateid_unhashed(open_stp)) goto out_close; retstp = find_lock_stateid(lo, open_stp); if (retstp) goto out_found; refcount_inc(&stp->st_stid.sc_count); stp->st_stid.sc_type = SC_TYPE_LOCK; stp->st_stateowner = nfs4_get_stateowner(&lo->lo_owner); get_nfs4_file(fp); stp->st_stid.sc_file = fp; stp->st_access_bmap = 0; stp->st_deny_bmap = open_stp->st_deny_bmap; stp->st_openstp = open_stp; spin_lock(&fp->fi_lock); list_add(&stp->st_locks, &open_stp->st_locks); list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids); list_add(&stp->st_perfile, &fp->fi_stateids); spin_unlock(&fp->fi_lock); spin_unlock(&clp->cl_lock); return stp; out_found: spin_unlock(&clp->cl_lock); if (nfsd4_lock_ol_stateid(retstp) != nfs_ok) { nfs4_put_stid(&retstp->st_stid); goto retry; } /* To keep mutex tracking happy */ mutex_unlock(&stp->st_mutex); return retstp; out_close: spin_unlock(&clp->cl_lock); mutex_unlock(&stp->st_mutex); return NULL; } static struct nfs4_ol_stateid * find_or_create_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fi, struct inode *inode, struct nfs4_ol_stateid *ost, bool *new) { struct nfs4_stid *ns = NULL; struct nfs4_ol_stateid *lst; struct nfs4_openowner *oo = openowner(ost->st_stateowner); struct nfs4_client *clp = oo->oo_owner.so_client; *new = false; spin_lock(&clp->cl_lock); lst = find_lock_stateid(lo, ost); spin_unlock(&clp->cl_lock); if (lst != NULL) { if (nfsd4_lock_ol_stateid(lst) == nfs_ok) goto out; nfs4_put_stid(&lst->st_stid); } ns = nfs4_alloc_stid(clp, stateid_slab, nfs4_free_lock_stateid); if (ns == NULL) return NULL; lst = init_lock_stateid(openlockstateid(ns), lo, fi, inode, ost); if (lst == openlockstateid(ns)) *new = true; else nfs4_put_stid(ns); out: return lst; } static int check_lock_length(u64 offset, u64 length) { return ((length == 0) || ((length != NFS4_MAX_UINT64) && (length > ~offset))); } static void get_lock_access(struct nfs4_ol_stateid *lock_stp, u32 access) { struct nfs4_file *fp = lock_stp->st_stid.sc_file; lockdep_assert_held(&fp->fi_lock); if (test_access(access, lock_stp)) return; __nfs4_file_get_access(fp, access); set_access(access, lock_stp); } static __be32 lookup_or_create_lock_state(struct nfsd4_compound_state *cstate, struct nfs4_ol_stateid *ost, struct nfsd4_lock *lock, struct nfs4_ol_stateid **plst, bool *new) { __be32 status; struct nfs4_file *fi = ost->st_stid.sc_file; struct nfs4_openowner *oo = openowner(ost->st_stateowner); struct nfs4_client *cl = oo->oo_owner.so_client; struct inode *inode = d_inode(cstate->current_fh.fh_dentry); struct nfs4_lockowner *lo; struct nfs4_ol_stateid *lst; unsigned int strhashval; lo = find_lockowner_str(cl, &lock->lk_new_owner); if (!lo) { strhashval = ownerstr_hashval(&lock->lk_new_owner); lo = alloc_init_lock_stateowner(strhashval, cl, ost, lock); if (lo == NULL) return nfserr_jukebox; } else { /* with an existing lockowner, seqids must be the same */ status = nfserr_bad_seqid; if (!cstate->minorversion && lock->lk_new_lock_seqid != lo->lo_owner.so_seqid) goto out; } lst = find_or_create_lock_stateid(lo, fi, inode, ost, new); if (lst == NULL) { status = nfserr_jukebox; goto out; } status = nfs_ok; *plst = lst; out: nfs4_put_stateowner(&lo->lo_owner); return status; } /* * LOCK operation */ __be32 nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_lock *lock = &u->lock; struct nfs4_openowner *open_sop = NULL; struct nfs4_lockowner *lock_sop = NULL; struct nfs4_ol_stateid *lock_stp = NULL; struct nfs4_ol_stateid *open_stp = NULL; struct nfs4_file *fp; struct nfsd_file *nf = NULL; struct nfsd4_blocked_lock *nbl = NULL; struct file_lock *file_lock = NULL; struct file_lock *conflock = NULL; struct super_block *sb; __be32 status = 0; int lkflg; int err; bool new = false; unsigned char type; unsigned int flags = FL_POSIX; struct net *net = SVC_NET(rqstp); struct nfsd_net *nn = net_generic(net, nfsd_net_id); dprintk("NFSD: nfsd4_lock: start=%Ld length=%Ld\n", (long long) lock->lk_offset, (long long) lock->lk_length); if (check_lock_length(lock->lk_offset, lock->lk_length)) return nfserr_inval; if ((status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, NFSD_MAY_LOCK))) { dprintk("NFSD: nfsd4_lock: permission denied!\n"); return status; } sb = cstate->current_fh.fh_dentry->d_sb; if (lock->lk_is_new) { if (nfsd4_has_session(cstate)) /* See rfc 5661 18.10.3: given clientid is ignored: */ memcpy(&lock->lk_new_clientid, &cstate->clp->cl_clientid, sizeof(clientid_t)); /* validate and update open stateid and open seqid */ status = nfs4_preprocess_confirmed_seqid_op(cstate, lock->lk_new_open_seqid, &lock->lk_new_open_stateid, &open_stp, nn); if (status) goto out; mutex_unlock(&open_stp->st_mutex); open_sop = openowner(open_stp->st_stateowner); status = nfserr_bad_stateid; if (!same_clid(&open_sop->oo_owner.so_client->cl_clientid, &lock->lk_new_clientid)) goto out; status = lookup_or_create_lock_state(cstate, open_stp, lock, &lock_stp, &new); } else { status = nfs4_preprocess_seqid_op(cstate, lock->lk_old_lock_seqid, &lock->lk_old_lock_stateid, SC_TYPE_LOCK, 0, &lock_stp, nn); } if (status) goto out; lock_sop = lockowner(lock_stp->st_stateowner); lkflg = setlkflg(lock->lk_type); status = nfs4_check_openmode(lock_stp, lkflg); if (status) goto out; status = nfserr_grace; if (locks_in_grace(net) && !lock->lk_reclaim) goto out; status = nfserr_no_grace; if (!locks_in_grace(net) && lock->lk_reclaim) goto out; if (lock->lk_reclaim) flags |= FL_RECLAIM; fp = lock_stp->st_stid.sc_file; switch (lock->lk_type) { case NFS4_READW_LT: fallthrough; case NFS4_READ_LT: spin_lock(&fp->fi_lock); nf = find_readable_file_locked(fp); if (nf) get_lock_access(lock_stp, NFS4_SHARE_ACCESS_READ); spin_unlock(&fp->fi_lock); type = F_RDLCK; break; case NFS4_WRITEW_LT: fallthrough; case NFS4_WRITE_LT: spin_lock(&fp->fi_lock); nf = find_writeable_file_locked(fp); if (nf) get_lock_access(lock_stp, NFS4_SHARE_ACCESS_WRITE); spin_unlock(&fp->fi_lock); type = F_WRLCK; break; default: status = nfserr_inval; goto out; } if (!nf) { status = nfserr_openmode; goto out; } if (lock->lk_type & (NFS4_READW_LT | NFS4_WRITEW_LT) && nfsd4_has_session(cstate) && locks_can_async_lock(nf->nf_file->f_op)) flags |= FL_SLEEP; nbl = find_or_allocate_block(lock_sop, &fp->fi_fhandle, nn); if (!nbl) { dprintk("NFSD: %s: unable to allocate block!\n", __func__); status = nfserr_jukebox; goto out; } file_lock = &nbl->nbl_lock; file_lock->c.flc_type = type; file_lock->c.flc_owner = (fl_owner_t)lockowner(nfs4_get_stateowner(&lock_sop->lo_owner)); file_lock->c.flc_pid = current->tgid; file_lock->c.flc_file = nf->nf_file; file_lock->c.flc_flags = flags; file_lock->fl_lmops = &nfsd_posix_mng_ops; file_lock->fl_start = lock->lk_offset; file_lock->fl_end = last_byte_offset(lock->lk_offset, lock->lk_length); nfs4_transform_lock_offset(file_lock); conflock = locks_alloc_lock(); if (!conflock) { dprintk("NFSD: %s: unable to allocate lock!\n", __func__); status = nfserr_jukebox; goto out; } if (flags & FL_SLEEP) { nbl->nbl_time = ktime_get_boottime_seconds(); spin_lock(&nn->blocked_locks_lock); list_add_tail(&nbl->nbl_list, &lock_sop->lo_blocked); list_add_tail(&nbl->nbl_lru, &nn->blocked_locks_lru); kref_get(&nbl->nbl_kref); spin_unlock(&nn->blocked_locks_lock); } err = vfs_lock_file(nf->nf_file, F_SETLK, file_lock, conflock); switch (err) { case 0: /* success! */ nfs4_inc_and_copy_stateid(&lock->lk_resp_stateid, &lock_stp->st_stid); status = 0; if (lock->lk_reclaim) nn->somebody_reclaimed = true; break; case FILE_LOCK_DEFERRED: kref_put(&nbl->nbl_kref, free_nbl); nbl = NULL; fallthrough; case -EAGAIN: /* conflock holds conflicting lock */ status = nfserr_denied; dprintk("NFSD: nfsd4_lock: conflicting lock found!\n"); nfs4_set_lock_denied(conflock, &lock->lk_denied); break; case -EDEADLK: status = nfserr_deadlock; break; default: dprintk("NFSD: nfsd4_lock: vfs_lock_file() failed! status %d\n",err); status = nfserrno(err); break; } out: if (nbl) { /* dequeue it if we queued it before */ if (flags & FL_SLEEP) { spin_lock(&nn->blocked_locks_lock); if (!list_empty(&nbl->nbl_list) && !list_empty(&nbl->nbl_lru)) { list_del_init(&nbl->nbl_list); list_del_init(&nbl->nbl_lru); kref_put(&nbl->nbl_kref, free_nbl); } /* nbl can use one of lists to be linked to reaplist */ spin_unlock(&nn->blocked_locks_lock); } free_blocked_lock(nbl); } if (nf) nfsd_file_put(nf); if (lock_stp) { /* Bump seqid manually if the 4.0 replay owner is openowner */ if (cstate->replay_owner && cstate->replay_owner != &lock_sop->lo_owner && seqid_mutating_err(ntohl(status))) lock_sop->lo_owner.so_seqid++; /* * If this is a new, never-before-used stateid, and we are * returning an error, then just go ahead and release it. */ if (status && new) release_lock_stateid(lock_stp); mutex_unlock(&lock_stp->st_mutex); nfs4_put_stid(&lock_stp->st_stid); } if (open_stp) nfs4_put_stid(&open_stp->st_stid); nfsd4_bump_seqid(cstate, status); if (conflock) locks_free_lock(conflock); return status; } void nfsd4_lock_release(union nfsd4_op_u *u) { struct nfsd4_lock *lock = &u->lock; struct nfsd4_lock_denied *deny = &lock->lk_denied; kfree(deny->ld_owner.data); } /* * The NFSv4 spec allows a client to do a LOCKT without holding an OPEN, * so we do a temporary open here just to get an open file to pass to * vfs_test_lock. */ static __be32 nfsd_test_lock(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file_lock *lock) { struct nfsd_file *nf; struct inode *inode; __be32 err; err = nfsd_file_acquire(rqstp, fhp, NFSD_MAY_READ, &nf); if (err) return err; inode = fhp->fh_dentry->d_inode; inode_lock(inode); /* to block new leases till after test_lock: */ err = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ)); if (err) goto out; lock->c.flc_file = nf->nf_file; err = nfserrno(vfs_test_lock(nf->nf_file, lock)); lock->c.flc_file = NULL; out: inode_unlock(inode); nfsd_file_put(nf); return err; } /* * LOCKT operation */ __be32 nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_lockt *lockt = &u->lockt; struct file_lock *file_lock = NULL; struct nfs4_lockowner *lo = NULL; __be32 status; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); if (locks_in_grace(SVC_NET(rqstp))) return nfserr_grace; if (check_lock_length(lockt->lt_offset, lockt->lt_length)) return nfserr_inval; if (!nfsd4_has_session(cstate)) { status = set_client(&lockt->lt_clientid, cstate, nn); if (status) goto out; } if ((status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0))) goto out; file_lock = locks_alloc_lock(); if (!file_lock) { dprintk("NFSD: %s: unable to allocate lock!\n", __func__); status = nfserr_jukebox; goto out; } switch (lockt->lt_type) { case NFS4_READ_LT: case NFS4_READW_LT: file_lock->c.flc_type = F_RDLCK; break; case NFS4_WRITE_LT: case NFS4_WRITEW_LT: file_lock->c.flc_type = F_WRLCK; break; default: dprintk("NFSD: nfs4_lockt: bad lock type!\n"); status = nfserr_inval; goto out; } lo = find_lockowner_str(cstate->clp, &lockt->lt_owner); if (lo) file_lock->c.flc_owner = (fl_owner_t)lo; file_lock->c.flc_pid = current->tgid; file_lock->c.flc_flags = FL_POSIX; file_lock->fl_start = lockt->lt_offset; file_lock->fl_end = last_byte_offset(lockt->lt_offset, lockt->lt_length); nfs4_transform_lock_offset(file_lock); status = nfsd_test_lock(rqstp, &cstate->current_fh, file_lock); if (status) goto out; if (file_lock->c.flc_type != F_UNLCK) { status = nfserr_denied; nfs4_set_lock_denied(file_lock, &lockt->lt_denied); } out: if (lo) nfs4_put_stateowner(&lo->lo_owner); if (file_lock) locks_free_lock(file_lock); return status; } void nfsd4_lockt_release(union nfsd4_op_u *u) { struct nfsd4_lockt *lockt = &u->lockt; struct nfsd4_lock_denied *deny = &lockt->lt_denied; kfree(deny->ld_owner.data); } __be32 nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_locku *locku = &u->locku; struct nfs4_ol_stateid *stp; struct nfsd_file *nf = NULL; struct file_lock *file_lock = NULL; __be32 status; int err; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); dprintk("NFSD: nfsd4_locku: start=%Ld length=%Ld\n", (long long) locku->lu_offset, (long long) locku->lu_length); if (check_lock_length(locku->lu_offset, locku->lu_length)) return nfserr_inval; status = nfs4_preprocess_seqid_op(cstate, locku->lu_seqid, &locku->lu_stateid, SC_TYPE_LOCK, 0, &stp, nn); if (status) goto out; nf = find_any_file(stp->st_stid.sc_file); if (!nf) { status = nfserr_lock_range; goto put_stateid; } file_lock = locks_alloc_lock(); if (!file_lock) { dprintk("NFSD: %s: unable to allocate lock!\n", __func__); status = nfserr_jukebox; goto put_file; } file_lock->c.flc_type = F_UNLCK; file_lock->c.flc_owner = (fl_owner_t)lockowner(nfs4_get_stateowner(stp->st_stateowner)); file_lock->c.flc_pid = current->tgid; file_lock->c.flc_file = nf->nf_file; file_lock->c.flc_flags = FL_POSIX; file_lock->fl_lmops = &nfsd_posix_mng_ops; file_lock->fl_start = locku->lu_offset; file_lock->fl_end = last_byte_offset(locku->lu_offset, locku->lu_length); nfs4_transform_lock_offset(file_lock); err = vfs_lock_file(nf->nf_file, F_SETLK, file_lock, NULL); if (err) { dprintk("NFSD: nfs4_locku: vfs_lock_file failed!\n"); goto out_nfserr; } nfs4_inc_and_copy_stateid(&locku->lu_stateid, &stp->st_stid); put_file: nfsd_file_put(nf); put_stateid: mutex_unlock(&stp->st_mutex); nfs4_put_stid(&stp->st_stid); out: nfsd4_bump_seqid(cstate, status); if (file_lock) locks_free_lock(file_lock); return status; out_nfserr: status = nfserrno(err); goto put_file; } /* * returns * true: locks held by lockowner * false: no locks held by lockowner */ static bool check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) { struct file_lock *fl; int status = false; struct nfsd_file *nf; struct inode *inode; struct file_lock_context *flctx; spin_lock(&fp->fi_lock); nf = find_any_file_locked(fp); if (!nf) { /* Any valid lock stateid should have some sort of access */ WARN_ON_ONCE(1); goto out; } inode = file_inode(nf->nf_file); flctx = locks_inode_context(inode); if (flctx && !list_empty_careful(&flctx->flc_posix)) { spin_lock(&flctx->flc_lock); for_each_file_lock(fl, &flctx->flc_posix) { if (fl->c.flc_owner == (fl_owner_t)lowner) { status = true; break; } } spin_unlock(&flctx->flc_lock); } out: spin_unlock(&fp->fi_lock); return status; } /** * nfsd4_release_lockowner - process NFSv4.0 RELEASE_LOCKOWNER operations * @rqstp: RPC transaction * @cstate: NFSv4 COMPOUND state * @u: RELEASE_LOCKOWNER arguments * * Check if there are any locks still held and if not, free the lockowner * and any lock state that is owned. * * Return values: * %nfs_ok: lockowner released or not found * %nfserr_locks_held: lockowner still in use * %nfserr_stale_clientid: clientid no longer active * %nfserr_expired: clientid not recognized */ __be32 nfsd4_release_lockowner(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_release_lockowner *rlockowner = &u->release_lockowner; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); clientid_t *clid = &rlockowner->rl_clientid; struct nfs4_ol_stateid *stp; struct nfs4_lockowner *lo; struct nfs4_client *clp; LIST_HEAD(reaplist); __be32 status; dprintk("nfsd4_release_lockowner clientid: (%08x/%08x):\n", clid->cl_boot, clid->cl_id); status = set_client(clid, cstate, nn); if (status) return status; clp = cstate->clp; spin_lock(&clp->cl_lock); lo = find_lockowner_str_locked(clp, &rlockowner->rl_owner); if (!lo) { spin_unlock(&clp->cl_lock); return nfs_ok; } list_for_each_entry(stp, &lo->lo_owner.so_stateids, st_perstateowner) { if (check_for_locks(stp->st_stid.sc_file, lo)) { spin_unlock(&clp->cl_lock); nfs4_put_stateowner(&lo->lo_owner); return nfserr_locks_held; } } unhash_lockowner_locked(lo); while (!list_empty(&lo->lo_owner.so_stateids)) { stp = list_first_entry(&lo->lo_owner.so_stateids, struct nfs4_ol_stateid, st_perstateowner); unhash_lock_stateid(stp); put_ol_stateid_locked(stp, &reaplist); } spin_unlock(&clp->cl_lock); free_ol_stateid_reaplist(&reaplist); remove_blocked_locks(lo); nfs4_put_stateowner(&lo->lo_owner); return nfs_ok; } static inline struct nfs4_client_reclaim * alloc_reclaim(void) { return kmalloc(sizeof(struct nfs4_client_reclaim), GFP_KERNEL); } bool nfs4_has_reclaimed_state(struct xdr_netobj name, struct nfsd_net *nn) { struct nfs4_client_reclaim *crp; crp = nfsd4_find_reclaim_client(name, nn); return (crp && crp->cr_clp); } /* * failure => all reset bets are off, nfserr_no_grace... * * The caller is responsible for freeing name.data if NULL is returned (it * will be freed in nfs4_remove_reclaim_record in the normal case). */ struct nfs4_client_reclaim * nfs4_client_to_reclaim(struct xdr_netobj name, struct xdr_netobj princhash, struct nfsd_net *nn) { unsigned int strhashval; struct nfs4_client_reclaim *crp; crp = alloc_reclaim(); if (crp) { strhashval = clientstr_hashval(name); INIT_LIST_HEAD(&crp->cr_strhash); list_add(&crp->cr_strhash, &nn->reclaim_str_hashtbl[strhashval]); crp->cr_name.data = name.data; crp->cr_name.len = name.len; crp->cr_princhash.data = princhash.data; crp->cr_princhash.len = princhash.len; crp->cr_clp = NULL; nn->reclaim_str_hashtbl_size++; } return crp; } void nfs4_remove_reclaim_record(struct nfs4_client_reclaim *crp, struct nfsd_net *nn) { list_del(&crp->cr_strhash); kfree(crp->cr_name.data); kfree(crp->cr_princhash.data); kfree(crp); nn->reclaim_str_hashtbl_size--; } void nfs4_release_reclaim(struct nfsd_net *nn) { struct nfs4_client_reclaim *crp = NULL; int i; for (i = 0; i < CLIENT_HASH_SIZE; i++) { while (!list_empty(&nn->reclaim_str_hashtbl[i])) { crp = list_entry(nn->reclaim_str_hashtbl[i].next, struct nfs4_client_reclaim, cr_strhash); nfs4_remove_reclaim_record(crp, nn); } } WARN_ON_ONCE(nn->reclaim_str_hashtbl_size); } /* * called from OPEN, CLAIM_PREVIOUS with a new clientid. */ struct nfs4_client_reclaim * nfsd4_find_reclaim_client(struct xdr_netobj name, struct nfsd_net *nn) { unsigned int strhashval; struct nfs4_client_reclaim *crp = NULL; strhashval = clientstr_hashval(name); list_for_each_entry(crp, &nn->reclaim_str_hashtbl[strhashval], cr_strhash) { if (compare_blob(&crp->cr_name, &name) == 0) { return crp; } } return NULL; } __be32 nfs4_check_open_reclaim(struct nfs4_client *clp) { if (test_bit(NFSD4_CLIENT_RECLAIM_COMPLETE, &clp->cl_flags)) return nfserr_no_grace; if (nfsd4_client_record_check(clp)) return nfserr_reclaim_bad; return nfs_ok; } /* * Since the lifetime of a delegation isn't limited to that of an open, a * client may quite reasonably hang on to a delegation as long as it has * the inode cached. This becomes an obvious problem the first time a * client's inode cache approaches the size of the server's total memory. * * For now we avoid this problem by imposing a hard limit on the number * of delegations, which varies according to the server's memory size. */ static void set_max_delegations(void) { /* * Allow at most 4 delegations per megabyte of RAM. Quick * estimates suggest that in the worst case (where every delegation * is for a different inode), a delegation could take about 1.5K, * giving a worst case usage of about 6% of memory. */ max_delegations = nr_free_buffer_pages() >> (20 - 2 - PAGE_SHIFT); } static int nfs4_state_create_net(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); int i; nn->conf_id_hashtbl = kmalloc_array(CLIENT_HASH_SIZE, sizeof(struct list_head), GFP_KERNEL); if (!nn->conf_id_hashtbl) goto err; nn->unconf_id_hashtbl = kmalloc_array(CLIENT_HASH_SIZE, sizeof(struct list_head), GFP_KERNEL); if (!nn->unconf_id_hashtbl) goto err_unconf_id; nn->sessionid_hashtbl = kmalloc_array(SESSION_HASH_SIZE, sizeof(struct list_head), GFP_KERNEL); if (!nn->sessionid_hashtbl) goto err_sessionid; for (i = 0; i < CLIENT_HASH_SIZE; i++) { INIT_LIST_HEAD(&nn->conf_id_hashtbl[i]); INIT_LIST_HEAD(&nn->unconf_id_hashtbl[i]); } for (i = 0; i < SESSION_HASH_SIZE; i++) INIT_LIST_HEAD(&nn->sessionid_hashtbl[i]); nn->conf_name_tree = RB_ROOT; nn->unconf_name_tree = RB_ROOT; nn->boot_time = ktime_get_real_seconds(); nn->grace_ended = false; nn->nfsd4_manager.block_opens = true; INIT_LIST_HEAD(&nn->nfsd4_manager.list); INIT_LIST_HEAD(&nn->client_lru); INIT_LIST_HEAD(&nn->close_lru); INIT_LIST_HEAD(&nn->del_recall_lru); spin_lock_init(&nn->client_lock); spin_lock_init(&nn->s2s_cp_lock); idr_init(&nn->s2s_cp_stateids); atomic_set(&nn->pending_async_copies, 0); spin_lock_init(&nn->blocked_locks_lock); INIT_LIST_HEAD(&nn->blocked_locks_lru); INIT_DELAYED_WORK(&nn->laundromat_work, laundromat_main); INIT_WORK(&nn->nfsd_shrinker_work, nfsd4_state_shrinker_worker); get_net(net); nn->nfsd_client_shrinker = shrinker_alloc(0, "nfsd-client"); if (!nn->nfsd_client_shrinker) goto err_shrinker; nn->nfsd_client_shrinker->scan_objects = nfsd4_state_shrinker_scan; nn->nfsd_client_shrinker->count_objects = nfsd4_state_shrinker_count; nn->nfsd_client_shrinker->private_data = nn; shrinker_register(nn->nfsd_client_shrinker); return 0; err_shrinker: put_net(net); kfree(nn->sessionid_hashtbl); err_sessionid: kfree(nn->unconf_id_hashtbl); err_unconf_id: kfree(nn->conf_id_hashtbl); err: return -ENOMEM; } static void nfs4_state_destroy_net(struct net *net) { int i; struct nfs4_client *clp = NULL; struct nfsd_net *nn = net_generic(net, nfsd_net_id); for (i = 0; i < CLIENT_HASH_SIZE; i++) { while (!list_empty(&nn->conf_id_hashtbl[i])) { clp = list_entry(nn->conf_id_hashtbl[i].next, struct nfs4_client, cl_idhash); destroy_client(clp); } } WARN_ON(!list_empty(&nn->blocked_locks_lru)); for (i = 0; i < CLIENT_HASH_SIZE; i++) { while (!list_empty(&nn->unconf_id_hashtbl[i])) { clp = list_entry(nn->unconf_id_hashtbl[i].next, struct nfs4_client, cl_idhash); destroy_client(clp); } } kfree(nn->sessionid_hashtbl); kfree(nn->unconf_id_hashtbl); kfree(nn->conf_id_hashtbl); put_net(net); } int nfs4_state_start_net(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); int ret; ret = nfs4_state_create_net(net); if (ret) return ret; locks_start_grace(net, &nn->nfsd4_manager); nfsd4_client_tracking_init(net); if (nn->track_reclaim_completes && nn->reclaim_str_hashtbl_size == 0) goto skip_grace; printk(KERN_INFO "NFSD: starting %lld-second grace period (net %x)\n", nn->nfsd4_grace, net->ns.inum); trace_nfsd_grace_start(nn); queue_delayed_work(laundry_wq, &nn->laundromat_work, nn->nfsd4_grace * HZ); return 0; skip_grace: printk(KERN_INFO "NFSD: no clients to reclaim, skipping NFSv4 grace period (net %x)\n", net->ns.inum); queue_delayed_work(laundry_wq, &nn->laundromat_work, nn->nfsd4_lease * HZ); nfsd4_end_grace(nn); return 0; } /* initialization to perform when the nfsd service is started: */ int nfs4_state_start(void) { int ret; ret = rhltable_init(&nfs4_file_rhltable, &nfs4_file_rhash_params); if (ret) return ret; set_max_delegations(); return 0; } void nfs4_state_shutdown_net(struct net *net) { struct nfs4_delegation *dp = NULL; struct list_head *pos, *next, reaplist; struct nfsd_net *nn = net_generic(net, nfsd_net_id); shrinker_free(nn->nfsd_client_shrinker); cancel_work_sync(&nn->nfsd_shrinker_work); cancel_delayed_work_sync(&nn->laundromat_work); locks_end_grace(&nn->nfsd4_manager); INIT_LIST_HEAD(&reaplist); spin_lock(&state_lock); list_for_each_safe(pos, next, &nn->del_recall_lru) { dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru); unhash_delegation_locked(dp, SC_STATUS_CLOSED); list_add(&dp->dl_recall_lru, &reaplist); } spin_unlock(&state_lock); list_for_each_safe(pos, next, &reaplist) { dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru); list_del_init(&dp->dl_recall_lru); destroy_unhashed_deleg(dp); } nfsd4_client_tracking_exit(net); nfs4_state_destroy_net(net); #ifdef CONFIG_NFSD_V4_2_INTER_SSC nfsd4_ssc_shutdown_umount(nn); #endif } void nfs4_state_shutdown(void) { rhltable_destroy(&nfs4_file_rhltable); } static void get_stateid(struct nfsd4_compound_state *cstate, stateid_t *stateid) { if (HAS_CSTATE_FLAG(cstate, CURRENT_STATE_ID_FLAG) && CURRENT_STATEID(stateid)) memcpy(stateid, &cstate->current_stateid, sizeof(stateid_t)); } static void put_stateid(struct nfsd4_compound_state *cstate, stateid_t *stateid) { if (cstate->minorversion) { memcpy(&cstate->current_stateid, stateid, sizeof(stateid_t)); SET_CSTATE_FLAG(cstate, CURRENT_STATE_ID_FLAG); } } void clear_current_stateid(struct nfsd4_compound_state *cstate) { CLEAR_CSTATE_FLAG(cstate, CURRENT_STATE_ID_FLAG); } /* * functions to set current state id */ void nfsd4_set_opendowngradestateid(struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { put_stateid(cstate, &u->open_downgrade.od_stateid); } void nfsd4_set_openstateid(struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { put_stateid(cstate, &u->open.op_stateid); } void nfsd4_set_closestateid(struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { put_stateid(cstate, &u->close.cl_stateid); } void nfsd4_set_lockstateid(struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { put_stateid(cstate, &u->lock.lk_resp_stateid); } /* * functions to consume current state id */ void nfsd4_get_opendowngradestateid(struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { get_stateid(cstate, &u->open_downgrade.od_stateid); } void nfsd4_get_delegreturnstateid(struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { get_stateid(cstate, &u->delegreturn.dr_stateid); } void nfsd4_get_freestateid(struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { get_stateid(cstate, &u->free_stateid.fr_stateid); } void nfsd4_get_setattrstateid(struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { get_stateid(cstate, &u->setattr.sa_stateid); } void nfsd4_get_closestateid(struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { get_stateid(cstate, &u->close.cl_stateid); } void nfsd4_get_lockustateid(struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { get_stateid(cstate, &u->locku.lu_stateid); } void nfsd4_get_readstateid(struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { get_stateid(cstate, &u->read.rd_stateid); } void nfsd4_get_writestateid(struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { get_stateid(cstate, &u->write.wr_stateid); } /** * nfsd4_deleg_getattr_conflict - Recall if GETATTR causes conflict * @rqstp: RPC transaction context * @dentry: dentry of inode to be checked for a conflict * @modified: return true if file was modified * @size: new size of file if modified is true * * This function is called when there is a conflict between a write * delegation and a change/size GETATTR from another client. The server * must either use the CB_GETATTR to get the current values of the * attributes from the client that holds the delegation or recall the * delegation before replying to the GETATTR. See RFC 8881 section * 18.7.4. * * Returns 0 if there is no conflict; otherwise an nfs_stat * code is returned. */ __be32 nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct dentry *dentry, bool *modified, u64 *size) { __be32 status; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); struct file_lock_context *ctx; struct nfs4_delegation *dp = NULL; struct file_lease *fl; struct iattr attrs; struct nfs4_cb_fattr *ncf; struct inode *inode = d_inode(dentry); *modified = false; ctx = locks_inode_context(inode); if (!ctx) return 0; #define NON_NFSD_LEASE ((void *)1) spin_lock(&ctx->flc_lock); for_each_file_lock(fl, &ctx->flc_lease) { if (fl->c.flc_flags == FL_LAYOUT) continue; if (fl->c.flc_type == F_WRLCK) { if (fl->fl_lmops == &nfsd_lease_mng_ops) dp = fl->c.flc_owner; else dp = NON_NFSD_LEASE; } break; } if (dp == NULL || dp == NON_NFSD_LEASE || dp->dl_recall.cb_clp == *(rqstp->rq_lease_breaker)) { spin_unlock(&ctx->flc_lock); if (dp == NON_NFSD_LEASE) { status = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ)); if (status != nfserr_jukebox || !nfsd_wait_for_delegreturn(rqstp, inode)) return status; } return 0; } nfsd_stats_wdeleg_getattr_inc(nn); refcount_inc(&dp->dl_stid.sc_count); ncf = &dp->dl_cb_fattr; nfs4_cb_getattr(&dp->dl_cb_fattr); spin_unlock(&ctx->flc_lock); wait_on_bit_timeout(&ncf->ncf_cb_flags, CB_GETATTR_BUSY, TASK_INTERRUPTIBLE, NFSD_CB_GETATTR_TIMEOUT); if (ncf->ncf_cb_status) { /* Recall delegation only if client didn't respond */ status = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ)); if (status != nfserr_jukebox || !nfsd_wait_for_delegreturn(rqstp, inode)) goto out_status; } if (!ncf->ncf_file_modified && (ncf->ncf_initial_cinfo != ncf->ncf_cb_change || ncf->ncf_cur_fsize != ncf->ncf_cb_fsize)) ncf->ncf_file_modified = true; if (ncf->ncf_file_modified) { int err; /* * Per section 10.4.3 of RFC 8881, the server would * not update the file's metadata with the client's * modified size */ attrs.ia_mtime = attrs.ia_ctime = current_time(inode); attrs.ia_valid = ATTR_MTIME | ATTR_CTIME | ATTR_DELEG; inode_lock(inode); err = notify_change(&nop_mnt_idmap, dentry, &attrs, NULL); inode_unlock(inode); if (err) { status = nfserrno(err); goto out_status; } ncf->ncf_cur_fsize = ncf->ncf_cb_fsize; *size = ncf->ncf_cur_fsize; *modified = true; } status = 0; out_status: nfs4_put_stid(&dp->dl_stid); return status; } |
| 39 37 40 37 31 23 31 29 32 31 1 3 31 23 23 23 26 30 32 4 12 37 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 | /* inffast.c -- fast decoding * Copyright (C) 1995-2004 Mark Adler * For conditions of distribution and use, see copyright notice in zlib.h */ #include <linux/zutil.h> #include "inftrees.h" #include "inflate.h" #include "inffast.h" #ifndef ASMINF union uu { unsigned short us; unsigned char b[2]; }; /* Endian independent version */ static inline unsigned short get_unaligned16(const unsigned short *p) { union uu mm; unsigned char *b = (unsigned char *)p; mm.b[0] = b[0]; mm.b[1] = b[1]; return mm.us; } /* Decode literal, length, and distance codes and write out the resulting literal and match bytes until either not enough input or output is available, an end-of-block is encountered, or a data error is encountered. When large enough input and output buffers are supplied to inflate(), for example, a 16K input buffer and a 64K output buffer, more than 95% of the inflate execution time is spent in this routine. Entry assumptions: state->mode == LEN strm->avail_in >= 6 strm->avail_out >= 258 start >= strm->avail_out state->bits < 8 On return, state->mode is one of: LEN -- ran out of enough output space or enough available input TYPE -- reached end of block code, inflate() to interpret next block BAD -- error in block data Notes: - The maximum input bits used by a length/distance pair is 15 bits for the length code, 5 bits for the length extra, 15 bits for the distance code, and 13 bits for the distance extra. This totals 48 bits, or six bytes. Therefore if strm->avail_in >= 6, then there is enough input to avoid checking for available input while decoding. - The maximum bytes that a single length/distance pair can output is 258 bytes, which is the maximum length that can be coded. inflate_fast() requires strm->avail_out >= 258 for each loop to avoid checking for output space. - @start: inflate()'s starting value for strm->avail_out */ void inflate_fast(z_streamp strm, unsigned start) { struct inflate_state *state; const unsigned char *in; /* local strm->next_in */ const unsigned char *last; /* while in < last, enough input available */ unsigned char *out; /* local strm->next_out */ unsigned char *beg; /* inflate()'s initial strm->next_out */ unsigned char *end; /* while out < end, enough space available */ #ifdef INFLATE_STRICT unsigned dmax; /* maximum distance from zlib header */ #endif unsigned wsize; /* window size or zero if not using window */ unsigned whave; /* valid bytes in the window */ unsigned write; /* window write index */ unsigned char *window; /* allocated sliding window, if wsize != 0 */ unsigned long hold; /* local strm->hold */ unsigned bits; /* local strm->bits */ code const *lcode; /* local strm->lencode */ code const *dcode; /* local strm->distcode */ unsigned lmask; /* mask for first level of length codes */ unsigned dmask; /* mask for first level of distance codes */ code this; /* retrieved table entry */ unsigned op; /* code bits, operation, extra bits, or */ /* window position, window bytes to copy */ unsigned len; /* match length, unused bytes */ unsigned dist; /* match distance */ unsigned char *from; /* where to copy match from */ /* copy state to local variables */ state = (struct inflate_state *)strm->state; in = strm->next_in; last = in + (strm->avail_in - 5); out = strm->next_out; beg = out - (start - strm->avail_out); end = out + (strm->avail_out - 257); #ifdef INFLATE_STRICT dmax = state->dmax; #endif wsize = state->wsize; whave = state->whave; write = state->write; window = state->window; hold = state->hold; bits = state->bits; lcode = state->lencode; dcode = state->distcode; lmask = (1U << state->lenbits) - 1; dmask = (1U << state->distbits) - 1; /* decode literals and length/distances until end-of-block or not enough input data or output space */ do { if (bits < 15) { hold += (unsigned long)(*in++) << bits; bits += 8; hold += (unsigned long)(*in++) << bits; bits += 8; } this = lcode[hold & lmask]; dolen: op = (unsigned)(this.bits); hold >>= op; bits -= op; op = (unsigned)(this.op); if (op == 0) { /* literal */ *out++ = (unsigned char)(this.val); } else if (op & 16) { /* length base */ len = (unsigned)(this.val); op &= 15; /* number of extra bits */ if (op) { if (bits < op) { hold += (unsigned long)(*in++) << bits; bits += 8; } len += (unsigned)hold & ((1U << op) - 1); hold >>= op; bits -= op; } if (bits < 15) { hold += (unsigned long)(*in++) << bits; bits += 8; hold += (unsigned long)(*in++) << bits; bits += 8; } this = dcode[hold & dmask]; dodist: op = (unsigned)(this.bits); hold >>= op; bits -= op; op = (unsigned)(this.op); if (op & 16) { /* distance base */ dist = (unsigned)(this.val); op &= 15; /* number of extra bits */ if (bits < op) { hold += (unsigned long)(*in++) << bits; bits += 8; if (bits < op) { hold += (unsigned long)(*in++) << bits; bits += 8; } } dist += (unsigned)hold & ((1U << op) - 1); #ifdef INFLATE_STRICT if (dist > dmax) { strm->msg = (char *)"invalid distance too far back"; state->mode = BAD; break; } #endif hold >>= op; bits -= op; op = (unsigned)(out - beg); /* max distance in output */ if (dist > op) { /* see if copy from window */ op = dist - op; /* distance back in window */ if (op > whave) { strm->msg = (char *)"invalid distance too far back"; state->mode = BAD; break; } from = window; if (write == 0) { /* very common case */ from += wsize - op; if (op < len) { /* some from window */ len -= op; do { *out++ = *from++; } while (--op); from = out - dist; /* rest from output */ } } else if (write < op) { /* wrap around window */ from += wsize + write - op; op -= write; if (op < len) { /* some from end of window */ len -= op; do { *out++ = *from++; } while (--op); from = window; if (write < len) { /* some from start of window */ op = write; len -= op; do { *out++ = *from++; } while (--op); from = out - dist; /* rest from output */ } } } else { /* contiguous in window */ from += write - op; if (op < len) { /* some from window */ len -= op; do { *out++ = *from++; } while (--op); from = out - dist; /* rest from output */ } } while (len > 2) { *out++ = *from++; *out++ = *from++; *out++ = *from++; len -= 3; } if (len) { *out++ = *from++; if (len > 1) *out++ = *from++; } } else { unsigned short *sout; unsigned long loops; from = out - dist; /* copy direct from output */ /* minimum length is three */ /* Align out addr */ if (!((long)(out - 1) & 1)) { *out++ = *from++; len--; } sout = (unsigned short *)(out); if (dist > 2) { unsigned short *sfrom; sfrom = (unsigned short *)(from); loops = len >> 1; do { if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) *sout++ = *sfrom++; else *sout++ = get_unaligned16(sfrom++); } while (--loops); out = (unsigned char *)sout; from = (unsigned char *)sfrom; } else { /* dist == 1 or dist == 2 */ unsigned short pat16; pat16 = *(sout-1); if (dist == 1) { union uu mm; /* copy one char pattern to both bytes */ mm.us = pat16; mm.b[0] = mm.b[1]; pat16 = mm.us; } loops = len >> 1; do *sout++ = pat16; while (--loops); out = (unsigned char *)sout; } if (len & 1) *out++ = *from++; } } else if ((op & 64) == 0) { /* 2nd level distance code */ this = dcode[this.val + (hold & ((1U << op) - 1))]; goto dodist; } else { strm->msg = (char *)"invalid distance code"; state->mode = BAD; break; } } else if ((op & 64) == 0) { /* 2nd level length code */ this = lcode[this.val + (hold & ((1U << op) - 1))]; goto dolen; } else if (op & 32) { /* end-of-block */ state->mode = TYPE; break; } else { strm->msg = (char *)"invalid literal/length code"; state->mode = BAD; break; } } while (in < last && out < end); /* return unused bytes (on entry, bits < 8, so in won't go too far back) */ len = bits >> 3; in -= len; bits -= len << 3; hold &= (1U << bits) - 1; /* update state and return */ strm->next_in = in; strm->next_out = out; strm->avail_in = (unsigned)(in < last ? 5 + (last - in) : 5 - (in - last)); strm->avail_out = (unsigned)(out < end ? 257 + (end - out) : 257 - (out - end)); state->hold = hold; state->bits = bits; return; } /* inflate_fast() speedups that turned out slower (on a PowerPC G3 750CXe): - Using bit fields for code structure - Different op definition to avoid & for extra bits (do & for table bits) - Three separate decoding do-loops for direct, window, and write == 0 - Special case for distance > 1 copies to do overlapped load and store copy - Explicit branch predictions (based on measured branch probabilities) - Deferring match copy and interspersed it with decoding subsequent codes - Swapping literal/length else - Swapping window/direct else - Larger unrolled copy loops (three is about right) - Moving len -= 3 statement into middle of loop */ #endif /* !ASMINF */ |
| 1 1 29 88 13 49 7 56 3 3 14 14 14 12 2 11 7 10 29 136 21 4 69 73 73 88 90 57 20 16 16 16 37 23 24 21 6 6 6 55 7 16 11 26 22 33 33 22 16 4 15 15 14 3 16 1 16 16 15 4 4 4 4 4 33 33 31 3 33 39 39 2 39 2 33 33 33 4 33 3 33 2 33 33 33 33 1 1 52 1 4 13 9 16 14 16 8 10 8 39 9 9 9 3 8 87 8 25 25 71 71 59 62 41 11 2 42 2 39 4 4 1 1 1 6 6 25 1 1 7 5 5 4 3 15 15 25 39 5 12 22 4 3 25 19 19 17 5 2 10 12 8 2 2 6 2 10 6 1 5 11 11 11 12 2 1 30 3 3 3 73 71 3 7 2 40 1 16 50 49 44 48 7 43 2 2 2 1 11 2 2 7 1 2 1 1 2 1 3 2 4 7 53 6 11 11 1 1 1 1 2 1 11 2 2 2 1 2 2 2 1 4 9 3 1 9 8 4 7 7 94 11 10 54 18 2 3 3 2 2 2 4 4 4 48 2 50 50 2 50 50 85 87 71 48 3 1 28 1 29 12 19 44 45 32 16 1 8 1 2 2 3 3 2 2 1 5 5 58 40 39 2 11 42 1 5 38 4 1 3 39 6 6 13 7 4 5 25 28 2 8 8 8 2 6 6 1 8 7 8 2 6 2 2 8 8 66 63 10 3 71 40 3 68 13 13 10 6 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (C) 2009 Red Hat, Inc. * Copyright (C) 2006 Rusty Russell IBM Corporation * * Author: Michael S. Tsirkin <mst@redhat.com> * * Inspiration, some code, and most witty comments come from * Documentation/virtual/lguest/lguest.c, by Rusty Russell * * Generic code for virtio server in host kernel. */ #include <linux/eventfd.h> #include <linux/vhost.h> #include <linux/uio.h> #include <linux/mm.h> #include <linux/miscdevice.h> #include <linux/mutex.h> #include <linux/poll.h> #include <linux/file.h> #include <linux/highmem.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/kthread.h> #include <linux/module.h> #include <linux/sort.h> #include <linux/sched/mm.h> #include <linux/sched/signal.h> #include <linux/sched/vhost_task.h> #include <linux/interval_tree_generic.h> #include <linux/nospec.h> #include <linux/kcov.h> #include "vhost.h" static ushort max_mem_regions = 64; module_param(max_mem_regions, ushort, 0444); MODULE_PARM_DESC(max_mem_regions, "Maximum number of memory regions in memory map. (default: 64)"); static int max_iotlb_entries = 2048; module_param(max_iotlb_entries, int, 0444); MODULE_PARM_DESC(max_iotlb_entries, "Maximum number of iotlb entries. (default: 2048)"); enum { VHOST_MEMORY_F_LOG = 0x1, }; #define vhost_used_event(vq) ((__virtio16 __user *)&vq->avail->ring[vq->num]) #define vhost_avail_event(vq) ((__virtio16 __user *)&vq->used->ring[vq->num]) #ifdef CONFIG_VHOST_CROSS_ENDIAN_LEGACY static void vhost_disable_cross_endian(struct vhost_virtqueue *vq) { vq->user_be = !virtio_legacy_is_little_endian(); } static void vhost_enable_cross_endian_big(struct vhost_virtqueue *vq) { vq->user_be = true; } static void vhost_enable_cross_endian_little(struct vhost_virtqueue *vq) { vq->user_be = false; } static long vhost_set_vring_endian(struct vhost_virtqueue *vq, int __user *argp) { struct vhost_vring_state s; if (vq->private_data) return -EBUSY; if (copy_from_user(&s, argp, sizeof(s))) return -EFAULT; if (s.num != VHOST_VRING_LITTLE_ENDIAN && s.num != VHOST_VRING_BIG_ENDIAN) return -EINVAL; if (s.num == VHOST_VRING_BIG_ENDIAN) vhost_enable_cross_endian_big(vq); else vhost_enable_cross_endian_little(vq); return 0; } static long vhost_get_vring_endian(struct vhost_virtqueue *vq, u32 idx, int __user *argp) { struct vhost_vring_state s = { .index = idx, .num = vq->user_be }; if (copy_to_user(argp, &s, sizeof(s))) return -EFAULT; return 0; } static void vhost_init_is_le(struct vhost_virtqueue *vq) { /* Note for legacy virtio: user_be is initialized at reset time * according to the host endianness. If userspace does not set an * explicit endianness, the default behavior is native endian, as * expected by legacy virtio. */ vq->is_le = vhost_has_feature(vq, VIRTIO_F_VERSION_1) || !vq->user_be; } #else static void vhost_disable_cross_endian(struct vhost_virtqueue *vq) { } static long vhost_set_vring_endian(struct vhost_virtqueue *vq, int __user *argp) { return -ENOIOCTLCMD; } static long vhost_get_vring_endian(struct vhost_virtqueue *vq, u32 idx, int __user *argp) { return -ENOIOCTLCMD; } static void vhost_init_is_le(struct vhost_virtqueue *vq) { vq->is_le = vhost_has_feature(vq, VIRTIO_F_VERSION_1) || virtio_legacy_is_little_endian(); } #endif /* CONFIG_VHOST_CROSS_ENDIAN_LEGACY */ static void vhost_reset_is_le(struct vhost_virtqueue *vq) { vhost_init_is_le(vq); } struct vhost_flush_struct { struct vhost_work work; struct completion wait_event; }; static void vhost_flush_work(struct vhost_work *work) { struct vhost_flush_struct *s; s = container_of(work, struct vhost_flush_struct, work); complete(&s->wait_event); } static void vhost_poll_func(struct file *file, wait_queue_head_t *wqh, poll_table *pt) { struct vhost_poll *poll; poll = container_of(pt, struct vhost_poll, table); poll->wqh = wqh; add_wait_queue(wqh, &poll->wait); } static int vhost_poll_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct vhost_poll *poll = container_of(wait, struct vhost_poll, wait); struct vhost_work *work = &poll->work; if (!(key_to_poll(key) & poll->mask)) return 0; if (!poll->dev->use_worker) work->fn(work); else vhost_poll_queue(poll); return 0; } void vhost_work_init(struct vhost_work *work, vhost_work_fn_t fn) { clear_bit(VHOST_WORK_QUEUED, &work->flags); work->fn = fn; } EXPORT_SYMBOL_GPL(vhost_work_init); /* Init poll structure */ void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn, __poll_t mask, struct vhost_dev *dev, struct vhost_virtqueue *vq) { init_waitqueue_func_entry(&poll->wait, vhost_poll_wakeup); init_poll_funcptr(&poll->table, vhost_poll_func); poll->mask = mask; poll->dev = dev; poll->wqh = NULL; poll->vq = vq; vhost_work_init(&poll->work, fn); } EXPORT_SYMBOL_GPL(vhost_poll_init); /* Start polling a file. We add ourselves to file's wait queue. The caller must * keep a reference to a file until after vhost_poll_stop is called. */ int vhost_poll_start(struct vhost_poll *poll, struct file *file) { __poll_t mask; if (poll->wqh) return 0; mask = vfs_poll(file, &poll->table); if (mask) vhost_poll_wakeup(&poll->wait, 0, 0, poll_to_key(mask)); if (mask & EPOLLERR) { vhost_poll_stop(poll); return -EINVAL; } return 0; } EXPORT_SYMBOL_GPL(vhost_poll_start); /* Stop polling a file. After this function returns, it becomes safe to drop the * file reference. You must also flush afterwards. */ void vhost_poll_stop(struct vhost_poll *poll) { if (poll->wqh) { remove_wait_queue(poll->wqh, &poll->wait); poll->wqh = NULL; } } EXPORT_SYMBOL_GPL(vhost_poll_stop); static void vhost_worker_queue(struct vhost_worker *worker, struct vhost_work *work) { if (!test_and_set_bit(VHOST_WORK_QUEUED, &work->flags)) { /* We can only add the work to the list after we're * sure it was not in the list. * test_and_set_bit() implies a memory barrier. */ llist_add(&work->node, &worker->work_list); vhost_task_wake(worker->vtsk); } } bool vhost_vq_work_queue(struct vhost_virtqueue *vq, struct vhost_work *work) { struct vhost_worker *worker; bool queued = false; rcu_read_lock(); worker = rcu_dereference(vq->worker); if (worker) { queued = true; vhost_worker_queue(worker, work); } rcu_read_unlock(); return queued; } EXPORT_SYMBOL_GPL(vhost_vq_work_queue); /** * __vhost_worker_flush - flush a worker * @worker: worker to flush * * The worker's flush_mutex must be held. */ static void __vhost_worker_flush(struct vhost_worker *worker) { struct vhost_flush_struct flush; if (!worker->attachment_cnt || worker->killed) return; init_completion(&flush.wait_event); vhost_work_init(&flush.work, vhost_flush_work); vhost_worker_queue(worker, &flush.work); /* * Drop mutex in case our worker is killed and it needs to take the * mutex to force cleanup. */ mutex_unlock(&worker->mutex); wait_for_completion(&flush.wait_event); mutex_lock(&worker->mutex); } static void vhost_worker_flush(struct vhost_worker *worker) { mutex_lock(&worker->mutex); __vhost_worker_flush(worker); mutex_unlock(&worker->mutex); } void vhost_dev_flush(struct vhost_dev *dev) { struct vhost_worker *worker; unsigned long i; xa_for_each(&dev->worker_xa, i, worker) vhost_worker_flush(worker); } EXPORT_SYMBOL_GPL(vhost_dev_flush); /* A lockless hint for busy polling code to exit the loop */ bool vhost_vq_has_work(struct vhost_virtqueue *vq) { struct vhost_worker *worker; bool has_work = false; rcu_read_lock(); worker = rcu_dereference(vq->worker); if (worker && !llist_empty(&worker->work_list)) has_work = true; rcu_read_unlock(); return has_work; } EXPORT_SYMBOL_GPL(vhost_vq_has_work); void vhost_poll_queue(struct vhost_poll *poll) { vhost_vq_work_queue(poll->vq, &poll->work); } EXPORT_SYMBOL_GPL(vhost_poll_queue); static void __vhost_vq_meta_reset(struct vhost_virtqueue *vq) { int j; for (j = 0; j < VHOST_NUM_ADDRS; j++) vq->meta_iotlb[j] = NULL; } static void vhost_vq_meta_reset(struct vhost_dev *d) { int i; for (i = 0; i < d->nvqs; ++i) __vhost_vq_meta_reset(d->vqs[i]); } static void vhost_vring_call_reset(struct vhost_vring_call *call_ctx) { call_ctx->ctx = NULL; memset(&call_ctx->producer, 0x0, sizeof(struct irq_bypass_producer)); } bool vhost_vq_is_setup(struct vhost_virtqueue *vq) { return vq->avail && vq->desc && vq->used && vhost_vq_access_ok(vq); } EXPORT_SYMBOL_GPL(vhost_vq_is_setup); static void vhost_vq_reset(struct vhost_dev *dev, struct vhost_virtqueue *vq) { vq->num = 1; vq->desc = NULL; vq->avail = NULL; vq->used = NULL; vq->last_avail_idx = 0; vq->avail_idx = 0; vq->last_used_idx = 0; vq->signalled_used = 0; vq->signalled_used_valid = false; vq->used_flags = 0; vq->log_used = false; vq->log_addr = -1ull; vq->private_data = NULL; vq->acked_features = 0; vq->acked_backend_features = 0; vq->log_base = NULL; vq->error_ctx = NULL; vq->kick = NULL; vq->log_ctx = NULL; vhost_disable_cross_endian(vq); vhost_reset_is_le(vq); vq->busyloop_timeout = 0; vq->umem = NULL; vq->iotlb = NULL; rcu_assign_pointer(vq->worker, NULL); vhost_vring_call_reset(&vq->call_ctx); __vhost_vq_meta_reset(vq); } static bool vhost_run_work_list(void *data) { struct vhost_worker *worker = data; struct vhost_work *work, *work_next; struct llist_node *node; node = llist_del_all(&worker->work_list); if (node) { __set_current_state(TASK_RUNNING); node = llist_reverse_order(node); /* make sure flag is seen after deletion */ smp_wmb(); llist_for_each_entry_safe(work, work_next, node, node) { clear_bit(VHOST_WORK_QUEUED, &work->flags); kcov_remote_start_common(worker->kcov_handle); work->fn(work); kcov_remote_stop(); cond_resched(); } } return !!node; } static void vhost_worker_killed(void *data) { struct vhost_worker *worker = data; struct vhost_dev *dev = worker->dev; struct vhost_virtqueue *vq; int i, attach_cnt = 0; mutex_lock(&worker->mutex); worker->killed = true; for (i = 0; i < dev->nvqs; i++) { vq = dev->vqs[i]; mutex_lock(&vq->mutex); if (worker == rcu_dereference_check(vq->worker, lockdep_is_held(&vq->mutex))) { rcu_assign_pointer(vq->worker, NULL); attach_cnt++; } mutex_unlock(&vq->mutex); } worker->attachment_cnt -= attach_cnt; if (attach_cnt) synchronize_rcu(); /* * Finish vhost_worker_flush calls and any other works that snuck in * before the synchronize_rcu. */ vhost_run_work_list(worker); mutex_unlock(&worker->mutex); } static void vhost_vq_free_iovecs(struct vhost_virtqueue *vq) { kfree(vq->indirect); vq->indirect = NULL; kfree(vq->log); vq->log = NULL; kfree(vq->heads); vq->heads = NULL; } /* Helper to allocate iovec buffers for all vqs. */ static long vhost_dev_alloc_iovecs(struct vhost_dev *dev) { struct vhost_virtqueue *vq; int i; for (i = 0; i < dev->nvqs; ++i) { vq = dev->vqs[i]; vq->indirect = kmalloc_array(UIO_MAXIOV, sizeof(*vq->indirect), GFP_KERNEL); vq->log = kmalloc_array(dev->iov_limit, sizeof(*vq->log), GFP_KERNEL); vq->heads = kmalloc_array(dev->iov_limit, sizeof(*vq->heads), GFP_KERNEL); if (!vq->indirect || !vq->log || !vq->heads) goto err_nomem; } return 0; err_nomem: for (; i >= 0; --i) vhost_vq_free_iovecs(dev->vqs[i]); return -ENOMEM; } static void vhost_dev_free_iovecs(struct vhost_dev *dev) { int i; for (i = 0; i < dev->nvqs; ++i) vhost_vq_free_iovecs(dev->vqs[i]); } bool vhost_exceeds_weight(struct vhost_virtqueue *vq, int pkts, int total_len) { struct vhost_dev *dev = vq->dev; if ((dev->byte_weight && total_len >= dev->byte_weight) || pkts >= dev->weight) { vhost_poll_queue(&vq->poll); return true; } return false; } EXPORT_SYMBOL_GPL(vhost_exceeds_weight); static size_t vhost_get_avail_size(struct vhost_virtqueue *vq, unsigned int num) { size_t event __maybe_unused = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0; return size_add(struct_size(vq->avail, ring, num), event); } static size_t vhost_get_used_size(struct vhost_virtqueue *vq, unsigned int num) { size_t event __maybe_unused = vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX) ? 2 : 0; return size_add(struct_size(vq->used, ring, num), event); } static size_t vhost_get_desc_size(struct vhost_virtqueue *vq, unsigned int num) { return sizeof(*vq->desc) * num; } void vhost_dev_init(struct vhost_dev *dev, struct vhost_virtqueue **vqs, int nvqs, int iov_limit, int weight, int byte_weight, bool use_worker, int (*msg_handler)(struct vhost_dev *dev, u32 asid, struct vhost_iotlb_msg *msg)) { struct vhost_virtqueue *vq; int i; dev->vqs = vqs; dev->nvqs = nvqs; mutex_init(&dev->mutex); dev->log_ctx = NULL; dev->umem = NULL; dev->iotlb = NULL; dev->mm = NULL; dev->iov_limit = iov_limit; dev->weight = weight; dev->byte_weight = byte_weight; dev->use_worker = use_worker; dev->msg_handler = msg_handler; init_waitqueue_head(&dev->wait); INIT_LIST_HEAD(&dev->read_list); INIT_LIST_HEAD(&dev->pending_list); spin_lock_init(&dev->iotlb_lock); xa_init_flags(&dev->worker_xa, XA_FLAGS_ALLOC); for (i = 0; i < dev->nvqs; ++i) { vq = dev->vqs[i]; vq->log = NULL; vq->indirect = NULL; vq->heads = NULL; vq->dev = dev; mutex_init(&vq->mutex); vhost_vq_reset(dev, vq); if (vq->handle_kick) vhost_poll_init(&vq->poll, vq->handle_kick, EPOLLIN, dev, vq); } } EXPORT_SYMBOL_GPL(vhost_dev_init); /* Caller should have device mutex */ long vhost_dev_check_owner(struct vhost_dev *dev) { /* Are you the owner? If not, I don't think you mean to do that */ return dev->mm == current->mm ? 0 : -EPERM; } EXPORT_SYMBOL_GPL(vhost_dev_check_owner); /* Caller should have device mutex */ bool vhost_dev_has_owner(struct vhost_dev *dev) { return dev->mm; } EXPORT_SYMBOL_GPL(vhost_dev_has_owner); static void vhost_attach_mm(struct vhost_dev *dev) { /* No owner, become one */ if (dev->use_worker) { dev->mm = get_task_mm(current); } else { /* vDPA device does not use worker thead, so there's * no need to hold the address space for mm. This help * to avoid deadlock in the case of mmap() which may * held the refcnt of the file and depends on release * method to remove vma. */ dev->mm = current->mm; mmgrab(dev->mm); } } static void vhost_detach_mm(struct vhost_dev *dev) { if (!dev->mm) return; if (dev->use_worker) mmput(dev->mm); else mmdrop(dev->mm); dev->mm = NULL; } static void vhost_worker_destroy(struct vhost_dev *dev, struct vhost_worker *worker) { if (!worker) return; WARN_ON(!llist_empty(&worker->work_list)); xa_erase(&dev->worker_xa, worker->id); vhost_task_stop(worker->vtsk); kfree(worker); } static void vhost_workers_free(struct vhost_dev *dev) { struct vhost_worker *worker; unsigned long i; if (!dev->use_worker) return; for (i = 0; i < dev->nvqs; i++) rcu_assign_pointer(dev->vqs[i]->worker, NULL); /* * Free the default worker we created and cleanup workers userspace * created but couldn't clean up (it forgot or crashed). */ xa_for_each(&dev->worker_xa, i, worker) vhost_worker_destroy(dev, worker); xa_destroy(&dev->worker_xa); } static struct vhost_worker *vhost_worker_create(struct vhost_dev *dev) { struct vhost_worker *worker; struct vhost_task *vtsk; char name[TASK_COMM_LEN]; int ret; u32 id; worker = kzalloc(sizeof(*worker), GFP_KERNEL_ACCOUNT); if (!worker) return NULL; worker->dev = dev; snprintf(name, sizeof(name), "vhost-%d", current->pid); vtsk = vhost_task_create(vhost_run_work_list, vhost_worker_killed, worker, name); if (!vtsk) goto free_worker; mutex_init(&worker->mutex); init_llist_head(&worker->work_list); worker->kcov_handle = kcov_common_handle(); worker->vtsk = vtsk; vhost_task_start(vtsk); ret = xa_alloc(&dev->worker_xa, &id, worker, xa_limit_32b, GFP_KERNEL); if (ret < 0) goto stop_worker; worker->id = id; return worker; stop_worker: vhost_task_stop(vtsk); free_worker: kfree(worker); return NULL; } /* Caller must have device mutex */ static void __vhost_vq_attach_worker(struct vhost_virtqueue *vq, struct vhost_worker *worker) { struct vhost_worker *old_worker; mutex_lock(&worker->mutex); if (worker->killed) { mutex_unlock(&worker->mutex); return; } mutex_lock(&vq->mutex); old_worker = rcu_dereference_check(vq->worker, lockdep_is_held(&vq->mutex)); rcu_assign_pointer(vq->worker, worker); worker->attachment_cnt++; if (!old_worker) { mutex_unlock(&vq->mutex); mutex_unlock(&worker->mutex); return; } mutex_unlock(&vq->mutex); mutex_unlock(&worker->mutex); /* * Take the worker mutex to make sure we see the work queued from * device wide flushes which doesn't use RCU for execution. */ mutex_lock(&old_worker->mutex); if (old_worker->killed) { mutex_unlock(&old_worker->mutex); return; } /* * We don't want to call synchronize_rcu for every vq during setup * because it will slow down VM startup. If we haven't done * VHOST_SET_VRING_KICK and not done the driver specific * SET_ENDPOINT/RUNNUNG then we can skip the sync since there will * not be any works queued for scsi and net. */ mutex_lock(&vq->mutex); if (!vhost_vq_get_backend(vq) && !vq->kick) { mutex_unlock(&vq->mutex); old_worker->attachment_cnt--; mutex_unlock(&old_worker->mutex); /* * vsock can queue anytime after VHOST_VSOCK_SET_GUEST_CID. * Warn if it adds support for multiple workers but forgets to * handle the early queueing case. */ WARN_ON(!old_worker->attachment_cnt && !llist_empty(&old_worker->work_list)); return; } mutex_unlock(&vq->mutex); /* Make sure new vq queue/flush/poll calls see the new worker */ synchronize_rcu(); /* Make sure whatever was queued gets run */ __vhost_worker_flush(old_worker); old_worker->attachment_cnt--; mutex_unlock(&old_worker->mutex); } /* Caller must have device mutex */ static int vhost_vq_attach_worker(struct vhost_virtqueue *vq, struct vhost_vring_worker *info) { unsigned long index = info->worker_id; struct vhost_dev *dev = vq->dev; struct vhost_worker *worker; if (!dev->use_worker) return -EINVAL; worker = xa_find(&dev->worker_xa, &index, UINT_MAX, XA_PRESENT); if (!worker || worker->id != info->worker_id) return -ENODEV; __vhost_vq_attach_worker(vq, worker); return 0; } /* Caller must have device mutex */ static int vhost_new_worker(struct vhost_dev *dev, struct vhost_worker_state *info) { struct vhost_worker *worker; worker = vhost_worker_create(dev); if (!worker) return -ENOMEM; info->worker_id = worker->id; return 0; } /* Caller must have device mutex */ static int vhost_free_worker(struct vhost_dev *dev, struct vhost_worker_state *info) { unsigned long index = info->worker_id; struct vhost_worker *worker; worker = xa_find(&dev->worker_xa, &index, UINT_MAX, XA_PRESENT); if (!worker || worker->id != info->worker_id) return -ENODEV; mutex_lock(&worker->mutex); if (worker->attachment_cnt || worker->killed) { mutex_unlock(&worker->mutex); return -EBUSY; } /* * A flush might have raced and snuck in before attachment_cnt was set * to zero. Make sure flushes are flushed from the queue before * freeing. */ __vhost_worker_flush(worker); mutex_unlock(&worker->mutex); vhost_worker_destroy(dev, worker); return 0; } static int vhost_get_vq_from_user(struct vhost_dev *dev, void __user *argp, struct vhost_virtqueue **vq, u32 *id) { u32 __user *idxp = argp; u32 idx; long r; r = get_user(idx, idxp); if (r < 0) return r; if (idx >= dev->nvqs) return -ENOBUFS; idx = array_index_nospec(idx, dev->nvqs); *vq = dev->vqs[idx]; *id = idx; return 0; } /* Caller must have device mutex */ long vhost_worker_ioctl(struct vhost_dev *dev, unsigned int ioctl, void __user *argp) { struct vhost_vring_worker ring_worker; struct vhost_worker_state state; struct vhost_worker *worker; struct vhost_virtqueue *vq; long ret; u32 idx; if (!dev->use_worker) return -EINVAL; if (!vhost_dev_has_owner(dev)) return -EINVAL; ret = vhost_dev_check_owner(dev); if (ret) return ret; switch (ioctl) { /* dev worker ioctls */ case VHOST_NEW_WORKER: ret = vhost_new_worker(dev, &state); if (!ret && copy_to_user(argp, &state, sizeof(state))) ret = -EFAULT; return ret; case VHOST_FREE_WORKER: if (copy_from_user(&state, argp, sizeof(state))) return -EFAULT; return vhost_free_worker(dev, &state); /* vring worker ioctls */ case VHOST_ATTACH_VRING_WORKER: case VHOST_GET_VRING_WORKER: break; default: return -ENOIOCTLCMD; } ret = vhost_get_vq_from_user(dev, argp, &vq, &idx); if (ret) return ret; switch (ioctl) { case VHOST_ATTACH_VRING_WORKER: if (copy_from_user(&ring_worker, argp, sizeof(ring_worker))) { ret = -EFAULT; break; } ret = vhost_vq_attach_worker(vq, &ring_worker); break; case VHOST_GET_VRING_WORKER: worker = rcu_dereference_check(vq->worker, lockdep_is_held(&dev->mutex)); if (!worker) { ret = -EINVAL; break; } ring_worker.index = idx; ring_worker.worker_id = worker->id; if (copy_to_user(argp, &ring_worker, sizeof(ring_worker))) ret = -EFAULT; break; default: ret = -ENOIOCTLCMD; break; } return ret; } EXPORT_SYMBOL_GPL(vhost_worker_ioctl); /* Caller should have device mutex */ long vhost_dev_set_owner(struct vhost_dev *dev) { struct vhost_worker *worker; int err, i; /* Is there an owner already? */ if (vhost_dev_has_owner(dev)) { err = -EBUSY; goto err_mm; } vhost_attach_mm(dev); err = vhost_dev_alloc_iovecs(dev); if (err) goto err_iovecs; if (dev->use_worker) { /* * This should be done last, because vsock can queue work * before VHOST_SET_OWNER so it simplifies the failure path * below since we don't have to worry about vsock queueing * while we free the worker. */ worker = vhost_worker_create(dev); if (!worker) { err = -ENOMEM; goto err_worker; } for (i = 0; i < dev->nvqs; i++) __vhost_vq_attach_worker(dev->vqs[i], worker); } return 0; err_worker: vhost_dev_free_iovecs(dev); err_iovecs: vhost_detach_mm(dev); err_mm: return err; } EXPORT_SYMBOL_GPL(vhost_dev_set_owner); static struct vhost_iotlb *iotlb_alloc(void) { return vhost_iotlb_alloc(max_iotlb_entries, VHOST_IOTLB_FLAG_RETIRE); } struct vhost_iotlb *vhost_dev_reset_owner_prepare(void) { return iotlb_alloc(); } EXPORT_SYMBOL_GPL(vhost_dev_reset_owner_prepare); /* Caller should have device mutex */ void vhost_dev_reset_owner(struct vhost_dev *dev, struct vhost_iotlb *umem) { int i; vhost_dev_cleanup(dev); dev->umem = umem; /* We don't need VQ locks below since vhost_dev_cleanup makes sure * VQs aren't running. */ for (i = 0; i < dev->nvqs; ++i) dev->vqs[i]->umem = umem; } EXPORT_SYMBOL_GPL(vhost_dev_reset_owner); void vhost_dev_stop(struct vhost_dev *dev) { int i; for (i = 0; i < dev->nvqs; ++i) { if (dev->vqs[i]->kick && dev->vqs[i]->handle_kick) vhost_poll_stop(&dev->vqs[i]->poll); } vhost_dev_flush(dev); } EXPORT_SYMBOL_GPL(vhost_dev_stop); void vhost_clear_msg(struct vhost_dev *dev) { struct vhost_msg_node *node, *n; spin_lock(&dev->iotlb_lock); list_for_each_entry_safe(node, n, &dev->read_list, node) { list_del(&node->node); kfree(node); } list_for_each_entry_safe(node, n, &dev->pending_list, node) { list_del(&node->node); kfree(node); } spin_unlock(&dev->iotlb_lock); } EXPORT_SYMBOL_GPL(vhost_clear_msg); void vhost_dev_cleanup(struct vhost_dev *dev) { int i; for (i = 0; i < dev->nvqs; ++i) { if (dev->vqs[i]->error_ctx) eventfd_ctx_put(dev->vqs[i]->error_ctx); if (dev->vqs[i]->kick) fput(dev->vqs[i]->kick); if (dev->vqs[i]->call_ctx.ctx) eventfd_ctx_put(dev->vqs[i]->call_ctx.ctx); vhost_vq_reset(dev, dev->vqs[i]); } vhost_dev_free_iovecs(dev); if (dev->log_ctx) eventfd_ctx_put(dev->log_ctx); dev->log_ctx = NULL; /* No one will access memory at this point */ vhost_iotlb_free(dev->umem); dev->umem = NULL; vhost_iotlb_free(dev->iotlb); dev->iotlb = NULL; vhost_clear_msg(dev); wake_up_interruptible_poll(&dev->wait, EPOLLIN | EPOLLRDNORM); vhost_workers_free(dev); vhost_detach_mm(dev); } EXPORT_SYMBOL_GPL(vhost_dev_cleanup); static bool log_access_ok(void __user *log_base, u64 addr, unsigned long sz) { u64 a = addr / VHOST_PAGE_SIZE / 8; /* Make sure 64 bit math will not overflow. */ if (a > ULONG_MAX - (unsigned long)log_base || a + (unsigned long)log_base > ULONG_MAX) return false; return access_ok(log_base + a, (sz + VHOST_PAGE_SIZE * 8 - 1) / VHOST_PAGE_SIZE / 8); } /* Make sure 64 bit math will not overflow. */ static bool vhost_overflow(u64 uaddr, u64 size) { if (uaddr > ULONG_MAX || size > ULONG_MAX) return true; if (!size) return false; return uaddr > ULONG_MAX - size + 1; } /* Caller should have vq mutex and device mutex. */ static bool vq_memory_access_ok(void __user *log_base, struct vhost_iotlb *umem, int log_all) { struct vhost_iotlb_map *map; if (!umem) return false; list_for_each_entry(map, &umem->list, link) { unsigned long a = map->addr; if (vhost_overflow(map->addr, map->size)) return false; if (!access_ok((void __user *)a, map->size)) return false; else if (log_all && !log_access_ok(log_base, map->start, map->size)) return false; } return true; } static inline void __user *vhost_vq_meta_fetch(struct vhost_virtqueue *vq, u64 addr, unsigned int size, int type) { const struct vhost_iotlb_map *map = vq->meta_iotlb[type]; if (!map) return NULL; return (void __user *)(uintptr_t)(map->addr + addr - map->start); } /* Can we switch to this memory table? */ /* Caller should have device mutex but not vq mutex */ static bool memory_access_ok(struct vhost_dev *d, struct vhost_iotlb *umem, int log_all) { int i; for (i = 0; i < d->nvqs; ++i) { bool ok; bool log; mutex_lock(&d->vqs[i]->mutex); log = log_all || vhost_has_feature(d->vqs[i], VHOST_F_LOG_ALL); /* If ring is inactive, will check when it's enabled. */ if (d->vqs[i]->private_data) ok = vq_memory_access_ok(d->vqs[i]->log_base, umem, log); else ok = true; mutex_unlock(&d->vqs[i]->mutex); if (!ok) return false; } return true; } static int translate_desc(struct vhost_virtqueue *vq, u64 addr, u32 len, struct iovec iov[], int iov_size, int access); static int vhost_copy_to_user(struct vhost_virtqueue *vq, void __user *to, const void *from, unsigned size) { int ret; if (!vq->iotlb) return __copy_to_user(to, from, size); else { /* This function should be called after iotlb * prefetch, which means we're sure that all vq * could be access through iotlb. So -EAGAIN should * not happen in this case. */ struct iov_iter t; void __user *uaddr = vhost_vq_meta_fetch(vq, (u64)(uintptr_t)to, size, VHOST_ADDR_USED); if (uaddr) return __copy_to_user(uaddr, from, size); ret = translate_desc(vq, (u64)(uintptr_t)to, size, vq->iotlb_iov, ARRAY_SIZE(vq->iotlb_iov), VHOST_ACCESS_WO); if (ret < 0) goto out; iov_iter_init(&t, ITER_DEST, vq->iotlb_iov, ret, size); ret = copy_to_iter(from, size, &t); if (ret == size) ret = 0; } out: return ret; } static int vhost_copy_from_user(struct vhost_virtqueue *vq, void *to, void __user *from, unsigned size) { int ret; if (!vq->iotlb) return __copy_from_user(to, from, size); else { /* This function should be called after iotlb * prefetch, which means we're sure that vq * could be access through iotlb. So -EAGAIN should * not happen in this case. */ void __user *uaddr = vhost_vq_meta_fetch(vq, (u64)(uintptr_t)from, size, VHOST_ADDR_DESC); struct iov_iter f; if (uaddr) return __copy_from_user(to, uaddr, size); ret = translate_desc(vq, (u64)(uintptr_t)from, size, vq->iotlb_iov, ARRAY_SIZE(vq->iotlb_iov), VHOST_ACCESS_RO); if (ret < 0) { vq_err(vq, "IOTLB translation failure: uaddr " "%p size 0x%llx\n", from, (unsigned long long) size); goto out; } iov_iter_init(&f, ITER_SOURCE, vq->iotlb_iov, ret, size); ret = copy_from_iter(to, size, &f); if (ret == size) ret = 0; } out: return ret; } static void __user *__vhost_get_user_slow(struct vhost_virtqueue *vq, void __user *addr, unsigned int size, int type) { int ret; ret = translate_desc(vq, (u64)(uintptr_t)addr, size, vq->iotlb_iov, ARRAY_SIZE(vq->iotlb_iov), VHOST_ACCESS_RO); if (ret < 0) { vq_err(vq, "IOTLB translation failure: uaddr " "%p size 0x%llx\n", addr, (unsigned long long) size); return NULL; } if (ret != 1 || vq->iotlb_iov[0].iov_len != size) { vq_err(vq, "Non atomic userspace memory access: uaddr " "%p size 0x%llx\n", addr, (unsigned long long) size); return NULL; } return vq->iotlb_iov[0].iov_base; } /* This function should be called after iotlb * prefetch, which means we're sure that vq * could be access through iotlb. So -EAGAIN should * not happen in this case. */ static inline void __user *__vhost_get_user(struct vhost_virtqueue *vq, void __user *addr, unsigned int size, int type) { void __user *uaddr = vhost_vq_meta_fetch(vq, (u64)(uintptr_t)addr, size, type); if (uaddr) return uaddr; return __vhost_get_user_slow(vq, addr, size, type); } #define vhost_put_user(vq, x, ptr) \ ({ \ int ret; \ if (!vq->iotlb) { \ ret = __put_user(x, ptr); \ } else { \ __typeof__(ptr) to = \ (__typeof__(ptr)) __vhost_get_user(vq, ptr, \ sizeof(*ptr), VHOST_ADDR_USED); \ if (to != NULL) \ ret = __put_user(x, to); \ else \ ret = -EFAULT; \ } \ ret; \ }) static inline int vhost_put_avail_event(struct vhost_virtqueue *vq) { return vhost_put_user(vq, cpu_to_vhost16(vq, vq->avail_idx), vhost_avail_event(vq)); } static inline int vhost_put_used(struct vhost_virtqueue *vq, struct vring_used_elem *head, int idx, int count) { return vhost_copy_to_user(vq, vq->used->ring + idx, head, count * sizeof(*head)); } static inline int vhost_put_used_flags(struct vhost_virtqueue *vq) { return vhost_put_user(vq, cpu_to_vhost16(vq, vq->used_flags), &vq->used->flags); } static inline int vhost_put_used_idx(struct vhost_virtqueue *vq) { return vhost_put_user(vq, cpu_to_vhost16(vq, vq->last_used_idx), &vq->used->idx); } #define vhost_get_user(vq, x, ptr, type) \ ({ \ int ret; \ if (!vq->iotlb) { \ ret = __get_user(x, ptr); \ } else { \ __typeof__(ptr) from = \ (__typeof__(ptr)) __vhost_get_user(vq, ptr, \ sizeof(*ptr), \ type); \ if (from != NULL) \ ret = __get_user(x, from); \ else \ ret = -EFAULT; \ } \ ret; \ }) #define vhost_get_avail(vq, x, ptr) \ vhost_get_user(vq, x, ptr, VHOST_ADDR_AVAIL) #define vhost_get_used(vq, x, ptr) \ vhost_get_user(vq, x, ptr, VHOST_ADDR_USED) static void vhost_dev_lock_vqs(struct vhost_dev *d) { int i = 0; for (i = 0; i < d->nvqs; ++i) mutex_lock_nested(&d->vqs[i]->mutex, i); } static void vhost_dev_unlock_vqs(struct vhost_dev *d) { int i = 0; for (i = 0; i < d->nvqs; ++i) mutex_unlock(&d->vqs[i]->mutex); } static inline int vhost_get_avail_idx(struct vhost_virtqueue *vq) { __virtio16 idx; int r; r = vhost_get_avail(vq, idx, &vq->avail->idx); if (unlikely(r < 0)) { vq_err(vq, "Failed to access available index at %p (%d)\n", &vq->avail->idx, r); return r; } /* Check it isn't doing very strange thing with available indexes */ vq->avail_idx = vhost16_to_cpu(vq, idx); if (unlikely((u16)(vq->avail_idx - vq->last_avail_idx) > vq->num)) { vq_err(vq, "Invalid available index change from %u to %u", vq->last_avail_idx, vq->avail_idx); return -EINVAL; } /* We're done if there is nothing new */ if (vq->avail_idx == vq->last_avail_idx) return 0; /* * We updated vq->avail_idx so we need a memory barrier between * the index read above and the caller reading avail ring entries. */ smp_rmb(); return 1; } static inline int vhost_get_avail_head(struct vhost_virtqueue *vq, __virtio16 *head, int idx) { return vhost_get_avail(vq, *head, &vq->avail->ring[idx & (vq->num - 1)]); } static inline int vhost_get_avail_flags(struct vhost_virtqueue *vq, __virtio16 *flags) { return vhost_get_avail(vq, *flags, &vq->avail->flags); } static inline int vhost_get_used_event(struct vhost_virtqueue *vq, __virtio16 *event) { return vhost_get_avail(vq, *event, vhost_used_event(vq)); } static inline int vhost_get_used_idx(struct vhost_virtqueue *vq, __virtio16 *idx) { return vhost_get_used(vq, *idx, &vq->used->idx); } static inline int vhost_get_desc(struct vhost_virtqueue *vq, struct vring_desc *desc, int idx) { return vhost_copy_from_user(vq, desc, vq->desc + idx, sizeof(*desc)); } static void vhost_iotlb_notify_vq(struct vhost_dev *d, struct vhost_iotlb_msg *msg) { struct vhost_msg_node *node, *n; spin_lock(&d->iotlb_lock); list_for_each_entry_safe(node, n, &d->pending_list, node) { struct vhost_iotlb_msg *vq_msg = &node->msg.iotlb; if (msg->iova <= vq_msg->iova && msg->iova + msg->size - 1 >= vq_msg->iova && vq_msg->type == VHOST_IOTLB_MISS) { vhost_poll_queue(&node->vq->poll); list_del(&node->node); kfree(node); } } spin_unlock(&d->iotlb_lock); } static bool umem_access_ok(u64 uaddr, u64 size, int access) { unsigned long a = uaddr; /* Make sure 64 bit math will not overflow. */ if (vhost_overflow(uaddr, size)) return false; if ((access & VHOST_ACCESS_RO) && !access_ok((void __user *)a, size)) return false; if ((access & VHOST_ACCESS_WO) && !access_ok((void __user *)a, size)) return false; return true; } static int vhost_process_iotlb_msg(struct vhost_dev *dev, u32 asid, struct vhost_iotlb_msg *msg) { int ret = 0; if (asid != 0) return -EINVAL; mutex_lock(&dev->mutex); vhost_dev_lock_vqs(dev); switch (msg->type) { case VHOST_IOTLB_UPDATE: if (!dev->iotlb) { ret = -EFAULT; break; } if (!umem_access_ok(msg->uaddr, msg->size, msg->perm)) { ret = -EFAULT; break; } vhost_vq_meta_reset(dev); if (vhost_iotlb_add_range(dev->iotlb, msg->iova, msg->iova + msg->size - 1, msg->uaddr, msg->perm)) { ret = -ENOMEM; break; } vhost_iotlb_notify_vq(dev, msg); break; case VHOST_IOTLB_INVALIDATE: if (!dev->iotlb) { ret = -EFAULT; break; } vhost_vq_meta_reset(dev); vhost_iotlb_del_range(dev->iotlb, msg->iova, msg->iova + msg->size - 1); break; default: ret = -EINVAL; break; } vhost_dev_unlock_vqs(dev); mutex_unlock(&dev->mutex); return ret; } ssize_t vhost_chr_write_iter(struct vhost_dev *dev, struct iov_iter *from) { struct vhost_iotlb_msg msg; size_t offset; int type, ret; u32 asid = 0; ret = copy_from_iter(&type, sizeof(type), from); if (ret != sizeof(type)) { ret = -EINVAL; goto done; } switch (type) { case VHOST_IOTLB_MSG: /* There maybe a hole after type for V1 message type, * so skip it here. */ offset = offsetof(struct vhost_msg, iotlb) - sizeof(int); break; case VHOST_IOTLB_MSG_V2: if (vhost_backend_has_feature(dev->vqs[0], VHOST_BACKEND_F_IOTLB_ASID)) { ret = copy_from_iter(&asid, sizeof(asid), from); if (ret != sizeof(asid)) { ret = -EINVAL; goto done; } offset = 0; } else offset = sizeof(__u32); break; default: ret = -EINVAL; goto done; } iov_iter_advance(from, offset); ret = copy_from_iter(&msg, sizeof(msg), from); if (ret != sizeof(msg)) { ret = -EINVAL; goto done; } if (msg.type == VHOST_IOTLB_UPDATE && msg.size == 0) { ret = -EINVAL; goto done; } if (dev->msg_handler) ret = dev->msg_handler(dev, asid, &msg); else ret = vhost_process_iotlb_msg(dev, asid, &msg); if (ret) { ret = -EFAULT; goto done; } ret = (type == VHOST_IOTLB_MSG) ? sizeof(struct vhost_msg) : sizeof(struct vhost_msg_v2); done: return ret; } EXPORT_SYMBOL(vhost_chr_write_iter); __poll_t vhost_chr_poll(struct file *file, struct vhost_dev *dev, poll_table *wait) { __poll_t mask = 0; poll_wait(file, &dev->wait, wait); if (!list_empty(&dev->read_list)) mask |= EPOLLIN | EPOLLRDNORM; return mask; } EXPORT_SYMBOL(vhost_chr_poll); ssize_t vhost_chr_read_iter(struct vhost_dev *dev, struct iov_iter *to, int noblock) { DEFINE_WAIT(wait); struct vhost_msg_node *node; ssize_t ret = 0; unsigned size = sizeof(struct vhost_msg); if (iov_iter_count(to) < size) return 0; while (1) { if (!noblock) prepare_to_wait(&dev->wait, &wait, TASK_INTERRUPTIBLE); node = vhost_dequeue_msg(dev, &dev->read_list); if (node) break; if (noblock) { ret = -EAGAIN; break; } if (signal_pending(current)) { ret = -ERESTARTSYS; break; } if (!dev->iotlb) { ret = -EBADFD; break; } schedule(); } if (!noblock) finish_wait(&dev->wait, &wait); if (node) { struct vhost_iotlb_msg *msg; void *start = &node->msg; switch (node->msg.type) { case VHOST_IOTLB_MSG: size = sizeof(node->msg); msg = &node->msg.iotlb; break; case VHOST_IOTLB_MSG_V2: size = sizeof(node->msg_v2); msg = &node->msg_v2.iotlb; break; default: BUG(); break; } ret = copy_to_iter(start, size, to); if (ret != size || msg->type != VHOST_IOTLB_MISS) { kfree(node); return ret; } vhost_enqueue_msg(dev, &dev->pending_list, node); } return ret; } EXPORT_SYMBOL_GPL(vhost_chr_read_iter); static int vhost_iotlb_miss(struct vhost_virtqueue *vq, u64 iova, int access) { struct vhost_dev *dev = vq->dev; struct vhost_msg_node *node; struct vhost_iotlb_msg *msg; bool v2 = vhost_backend_has_feature(vq, VHOST_BACKEND_F_IOTLB_MSG_V2); node = vhost_new_msg(vq, v2 ? VHOST_IOTLB_MSG_V2 : VHOST_IOTLB_MSG); if (!node) return -ENOMEM; if (v2) { node->msg_v2.type = VHOST_IOTLB_MSG_V2; msg = &node->msg_v2.iotlb; } else { msg = &node->msg.iotlb; } msg->type = VHOST_IOTLB_MISS; msg->iova = iova; msg->perm = access; vhost_enqueue_msg(dev, &dev->read_list, node); return 0; } static bool vq_access_ok(struct vhost_virtqueue *vq, unsigned int num, vring_desc_t __user *desc, vring_avail_t __user *avail, vring_used_t __user *used) { /* If an IOTLB device is present, the vring addresses are * GIOVAs. Access validation occurs at prefetch time. */ if (vq->iotlb) return true; return access_ok(desc, vhost_get_desc_size(vq, num)) && access_ok(avail, vhost_get_avail_size(vq, num)) && access_ok(used, vhost_get_used_size(vq, num)); } static void vhost_vq_meta_update(struct vhost_virtqueue *vq, const struct vhost_iotlb_map *map, int type) { int access = (type == VHOST_ADDR_USED) ? VHOST_ACCESS_WO : VHOST_ACCESS_RO; if (likely(map->perm & access)) vq->meta_iotlb[type] = map; } static bool iotlb_access_ok(struct vhost_virtqueue *vq, int access, u64 addr, u64 len, int type) { const struct vhost_iotlb_map *map; struct vhost_iotlb *umem = vq->iotlb; u64 s = 0, size, orig_addr = addr, last = addr + len - 1; if (vhost_vq_meta_fetch(vq, addr, len, type)) return true; while (len > s) { map = vhost_iotlb_itree_first(umem, addr, last); if (map == NULL || map->start > addr) { vhost_iotlb_miss(vq, addr, access); return false; } else if (!(map->perm & access)) { /* Report the possible access violation by * request another translation from userspace. */ return false; } size = map->size - addr + map->start; if (orig_addr == addr && size >= len) vhost_vq_meta_update(vq, map, type); s += size; addr += size; } return true; } int vq_meta_prefetch(struct vhost_virtqueue *vq) { unsigned int num = vq->num; if (!vq->iotlb) return 1; return iotlb_access_ok(vq, VHOST_MAP_RO, (u64)(uintptr_t)vq->desc, vhost_get_desc_size(vq, num), VHOST_ADDR_DESC) && iotlb_access_ok(vq, VHOST_MAP_RO, (u64)(uintptr_t)vq->avail, vhost_get_avail_size(vq, num), VHOST_ADDR_AVAIL) && iotlb_access_ok(vq, VHOST_MAP_WO, (u64)(uintptr_t)vq->used, vhost_get_used_size(vq, num), VHOST_ADDR_USED); } EXPORT_SYMBOL_GPL(vq_meta_prefetch); /* Can we log writes? */ /* Caller should have device mutex but not vq mutex */ bool vhost_log_access_ok(struct vhost_dev *dev) { return memory_access_ok(dev, dev->umem, 1); } EXPORT_SYMBOL_GPL(vhost_log_access_ok); static bool vq_log_used_access_ok(struct vhost_virtqueue *vq, void __user *log_base, bool log_used, u64 log_addr) { /* If an IOTLB device is present, log_addr is a GIOVA that * will never be logged by log_used(). */ if (vq->iotlb) return true; return !log_used || log_access_ok(log_base, log_addr, vhost_get_used_size(vq, vq->num)); } /* Verify access for write logging. */ /* Caller should have vq mutex and device mutex */ static bool vq_log_access_ok(struct vhost_virtqueue *vq, void __user *log_base) { return vq_memory_access_ok(log_base, vq->umem, vhost_has_feature(vq, VHOST_F_LOG_ALL)) && vq_log_used_access_ok(vq, log_base, vq->log_used, vq->log_addr); } /* Can we start vq? */ /* Caller should have vq mutex and device mutex */ bool vhost_vq_access_ok(struct vhost_virtqueue *vq) { if (!vq_log_access_ok(vq, vq->log_base)) return false; return vq_access_ok(vq, vq->num, vq->desc, vq->avail, vq->used); } EXPORT_SYMBOL_GPL(vhost_vq_access_ok); static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m) { struct vhost_memory mem, *newmem; struct vhost_memory_region *region; struct vhost_iotlb *newumem, *oldumem; unsigned long size = offsetof(struct vhost_memory, regions); int i; if (copy_from_user(&mem, m, size)) return -EFAULT; if (mem.padding) return -EOPNOTSUPP; if (mem.nregions > max_mem_regions) return -E2BIG; newmem = kvzalloc(struct_size(newmem, regions, mem.nregions), GFP_KERNEL); if (!newmem) return -ENOMEM; memcpy(newmem, &mem, size); if (copy_from_user(newmem->regions, m->regions, flex_array_size(newmem, regions, mem.nregions))) { kvfree(newmem); return -EFAULT; } newumem = iotlb_alloc(); if (!newumem) { kvfree(newmem); return -ENOMEM; } for (region = newmem->regions; region < newmem->regions + mem.nregions; region++) { if (vhost_iotlb_add_range(newumem, region->guest_phys_addr, region->guest_phys_addr + region->memory_size - 1, region->userspace_addr, VHOST_MAP_RW)) goto err; } if (!memory_access_ok(d, newumem, 0)) goto err; oldumem = d->umem; d->umem = newumem; /* All memory accesses are done under some VQ mutex. */ for (i = 0; i < d->nvqs; ++i) { mutex_lock(&d->vqs[i]->mutex); d->vqs[i]->umem = newumem; mutex_unlock(&d->vqs[i]->mutex); } kvfree(newmem); vhost_iotlb_free(oldumem); return 0; err: vhost_iotlb_free(newumem); kvfree(newmem); return -EFAULT; } static long vhost_vring_set_num(struct vhost_dev *d, struct vhost_virtqueue *vq, void __user *argp) { struct vhost_vring_state s; /* Resizing ring with an active backend? * You don't want to do that. */ if (vq->private_data) return -EBUSY; if (copy_from_user(&s, argp, sizeof s)) return -EFAULT; if (!s.num || s.num > 0xffff || (s.num & (s.num - 1))) return -EINVAL; vq->num = s.num; return 0; } static long vhost_vring_set_addr(struct vhost_dev *d, struct vhost_virtqueue *vq, void __user *argp) { struct vhost_vring_addr a; if (copy_from_user(&a, argp, sizeof a)) return -EFAULT; if (a.flags & ~(0x1 << VHOST_VRING_F_LOG)) return -EOPNOTSUPP; /* For 32bit, verify that the top 32bits of the user data are set to zero. */ if ((u64)(unsigned long)a.desc_user_addr != a.desc_user_addr || (u64)(unsigned long)a.used_user_addr != a.used_user_addr || (u64)(unsigned long)a.avail_user_addr != a.avail_user_addr) return -EFAULT; /* Make sure it's safe to cast pointers to vring types. */ BUILD_BUG_ON(__alignof__ *vq->avail > VRING_AVAIL_ALIGN_SIZE); BUILD_BUG_ON(__alignof__ *vq->used > VRING_USED_ALIGN_SIZE); if ((a.avail_user_addr & (VRING_AVAIL_ALIGN_SIZE - 1)) || (a.used_user_addr & (VRING_USED_ALIGN_SIZE - 1)) || (a.log_guest_addr & (VRING_USED_ALIGN_SIZE - 1))) return -EINVAL; /* We only verify access here if backend is configured. * If it is not, we don't as size might not have been setup. * We will verify when backend is configured. */ if (vq->private_data) { if (!vq_access_ok(vq, vq->num, (void __user *)(unsigned long)a.desc_user_addr, (void __user *)(unsigned long)a.avail_user_addr, (void __user *)(unsigned long)a.used_user_addr)) return -EINVAL; /* Also validate log access for used ring if enabled. */ if (!vq_log_used_access_ok(vq, vq->log_base, a.flags & (0x1 << VHOST_VRING_F_LOG), a.log_guest_addr)) return -EINVAL; } vq->log_used = !!(a.flags & (0x1 << VHOST_VRING_F_LOG)); vq->desc = (void __user *)(unsigned long)a.desc_user_addr; vq->avail = (void __user *)(unsigned long)a.avail_user_addr; vq->log_addr = a.log_guest_addr; vq->used = (void __user *)(unsigned long)a.used_user_addr; return 0; } static long vhost_vring_set_num_addr(struct vhost_dev *d, struct vhost_virtqueue *vq, unsigned int ioctl, void __user *argp) { long r; mutex_lock(&vq->mutex); switch (ioctl) { case VHOST_SET_VRING_NUM: r = vhost_vring_set_num(d, vq, argp); break; case VHOST_SET_VRING_ADDR: r = vhost_vring_set_addr(d, vq, argp); break; default: BUG(); } mutex_unlock(&vq->mutex); return r; } long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *argp) { struct file *eventfp, *filep = NULL; bool pollstart = false, pollstop = false; struct eventfd_ctx *ctx = NULL; struct vhost_virtqueue *vq; struct vhost_vring_state s; struct vhost_vring_file f; u32 idx; long r; r = vhost_get_vq_from_user(d, argp, &vq, &idx); if (r < 0) return r; if (ioctl == VHOST_SET_VRING_NUM || ioctl == VHOST_SET_VRING_ADDR) { return vhost_vring_set_num_addr(d, vq, ioctl, argp); } mutex_lock(&vq->mutex); switch (ioctl) { case VHOST_SET_VRING_BASE: /* Moving base with an active backend? * You don't want to do that. */ if (vq->private_data) { r = -EBUSY; break; } if (copy_from_user(&s, argp, sizeof s)) { r = -EFAULT; break; } if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED)) { vq->last_avail_idx = s.num & 0xffff; vq->last_used_idx = (s.num >> 16) & 0xffff; } else { if (s.num > 0xffff) { r = -EINVAL; break; } vq->last_avail_idx = s.num; } /* Forget the cached index value. */ vq->avail_idx = vq->last_avail_idx; break; case VHOST_GET_VRING_BASE: s.index = idx; if (vhost_has_feature(vq, VIRTIO_F_RING_PACKED)) s.num = (u32)vq->last_avail_idx | ((u32)vq->last_used_idx << 16); else s.num = vq->last_avail_idx; if (copy_to_user(argp, &s, sizeof s)) r = -EFAULT; break; case VHOST_SET_VRING_KICK: if (copy_from_user(&f, argp, sizeof f)) { r = -EFAULT; break; } eventfp = f.fd == VHOST_FILE_UNBIND ? NULL : eventfd_fget(f.fd); if (IS_ERR(eventfp)) { r = PTR_ERR(eventfp); break; } if (eventfp != vq->kick) { pollstop = (filep = vq->kick) != NULL; pollstart = (vq->kick = eventfp) != NULL; } else filep = eventfp; break; case VHOST_SET_VRING_CALL: if (copy_from_user(&f, argp, sizeof f)) { r = -EFAULT; break; } ctx = f.fd == VHOST_FILE_UNBIND ? NULL : eventfd_ctx_fdget(f.fd); if (IS_ERR(ctx)) { r = PTR_ERR(ctx); break; } swap(ctx, vq->call_ctx.ctx); break; case VHOST_SET_VRING_ERR: if (copy_from_user(&f, argp, sizeof f)) { r = -EFAULT; break; } ctx = f.fd == VHOST_FILE_UNBIND ? NULL : eventfd_ctx_fdget(f.fd); if (IS_ERR(ctx)) { r = PTR_ERR(ctx); break; } swap(ctx, vq->error_ctx); break; case VHOST_SET_VRING_ENDIAN: r = vhost_set_vring_endian(vq, argp); break; case VHOST_GET_VRING_ENDIAN: r = vhost_get_vring_endian(vq, idx, argp); break; case VHOST_SET_VRING_BUSYLOOP_TIMEOUT: if (copy_from_user(&s, argp, sizeof(s))) { r = -EFAULT; break; } vq->busyloop_timeout = s.num; break; case VHOST_GET_VRING_BUSYLOOP_TIMEOUT: s.index = idx; s.num = vq->busyloop_timeout; if (copy_to_user(argp, &s, sizeof(s))) r = -EFAULT; break; default: r = -ENOIOCTLCMD; } if (pollstop && vq->handle_kick) vhost_poll_stop(&vq->poll); if (!IS_ERR_OR_NULL(ctx)) eventfd_ctx_put(ctx); if (filep) fput(filep); if (pollstart && vq->handle_kick) r = vhost_poll_start(&vq->poll, vq->kick); mutex_unlock(&vq->mutex); if (pollstop && vq->handle_kick) vhost_dev_flush(vq->poll.dev); return r; } EXPORT_SYMBOL_GPL(vhost_vring_ioctl); int vhost_init_device_iotlb(struct vhost_dev *d) { struct vhost_iotlb *niotlb, *oiotlb; int i; niotlb = iotlb_alloc(); if (!niotlb) return -ENOMEM; oiotlb = d->iotlb; d->iotlb = niotlb; for (i = 0; i < d->nvqs; ++i) { struct vhost_virtqueue *vq = d->vqs[i]; mutex_lock(&vq->mutex); vq->iotlb = niotlb; __vhost_vq_meta_reset(vq); mutex_unlock(&vq->mutex); } vhost_iotlb_free(oiotlb); return 0; } EXPORT_SYMBOL_GPL(vhost_init_device_iotlb); /* Caller must have device mutex */ long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *argp) { struct eventfd_ctx *ctx; u64 p; long r; int i, fd; /* If you are not the owner, you can become one */ if (ioctl == VHOST_SET_OWNER) { r = vhost_dev_set_owner(d); goto done; } /* You must be the owner to do anything else */ r = vhost_dev_check_owner(d); if (r) goto done; switch (ioctl) { case VHOST_SET_MEM_TABLE: r = vhost_set_memory(d, argp); break; case VHOST_SET_LOG_BASE: if (copy_from_user(&p, argp, sizeof p)) { r = -EFAULT; break; } if ((u64)(unsigned long)p != p) { r = -EFAULT; break; } for (i = 0; i < d->nvqs; ++i) { struct vhost_virtqueue *vq; void __user *base = (void __user *)(unsigned long)p; vq = d->vqs[i]; mutex_lock(&vq->mutex); /* If ring is inactive, will check when it's enabled. */ if (vq->private_data && !vq_log_access_ok(vq, base)) r = -EFAULT; else vq->log_base = base; mutex_unlock(&vq->mutex); } break; case VHOST_SET_LOG_FD: r = get_user(fd, (int __user *)argp); if (r < 0) break; ctx = fd == VHOST_FILE_UNBIND ? NULL : eventfd_ctx_fdget(fd); if (IS_ERR(ctx)) { r = PTR_ERR(ctx); break; } swap(ctx, d->log_ctx); for (i = 0; i < d->nvqs; ++i) { mutex_lock(&d->vqs[i]->mutex); d->vqs[i]->log_ctx = d->log_ctx; mutex_unlock(&d->vqs[i]->mutex); } if (ctx) eventfd_ctx_put(ctx); break; default: r = -ENOIOCTLCMD; break; } done: return r; } EXPORT_SYMBOL_GPL(vhost_dev_ioctl); /* TODO: This is really inefficient. We need something like get_user() * (instruction directly accesses the data, with an exception table entry * returning -EFAULT). See Documentation/arch/x86/exception-tables.rst. */ static int set_bit_to_user(int nr, void __user *addr) { unsigned long log = (unsigned long)addr; struct page *page; void *base; int bit = nr + (log % PAGE_SIZE) * 8; int r; r = pin_user_pages_fast(log, 1, FOLL_WRITE, &page); if (r < 0) return r; BUG_ON(r != 1); base = kmap_atomic(page); set_bit(bit, base); kunmap_atomic(base); unpin_user_pages_dirty_lock(&page, 1, true); return 0; } static int log_write(void __user *log_base, u64 write_address, u64 write_length) { u64 write_page = write_address / VHOST_PAGE_SIZE; int r; if (!write_length) return 0; write_length += write_address % VHOST_PAGE_SIZE; for (;;) { u64 base = (u64)(unsigned long)log_base; u64 log = base + write_page / 8; int bit = write_page % 8; if ((u64)(unsigned long)log != log) return -EFAULT; r = set_bit_to_user(bit, (void __user *)(unsigned long)log); if (r < 0) return r; if (write_length <= VHOST_PAGE_SIZE) break; write_length -= VHOST_PAGE_SIZE; write_page += 1; } return r; } static int log_write_hva(struct vhost_virtqueue *vq, u64 hva, u64 len) { struct vhost_iotlb *umem = vq->umem; struct vhost_iotlb_map *u; u64 start, end, l, min; int r; bool hit = false; while (len) { min = len; /* More than one GPAs can be mapped into a single HVA. So * iterate all possible umems here to be safe. */ list_for_each_entry(u, &umem->list, link) { if (u->addr > hva - 1 + len || u->addr - 1 + u->size < hva) continue; start = max(u->addr, hva); end = min(u->addr - 1 + u->size, hva - 1 + len); l = end - start + 1; r = log_write(vq->log_base, u->start + start - u->addr, l); if (r < 0) return r; hit = true; min = min(l, min); } if (!hit) return -EFAULT; len -= min; hva += min; } return 0; } static int log_used(struct vhost_virtqueue *vq, u64 used_offset, u64 len) { struct iovec *iov = vq->log_iov; int i, ret; if (!vq->iotlb) return log_write(vq->log_base, vq->log_addr + used_offset, len); ret = translate_desc(vq, (uintptr_t)vq->used + used_offset, len, iov, 64, VHOST_ACCESS_WO); if (ret < 0) return ret; for (i = 0; i < ret; i++) { ret = log_write_hva(vq, (uintptr_t)iov[i].iov_base, iov[i].iov_len); if (ret) return ret; } return 0; } int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log, unsigned int log_num, u64 len, struct iovec *iov, int count) { int i, r; /* Make sure data written is seen before log. */ smp_wmb(); if (vq->iotlb) { for (i = 0; i < count; i++) { r = log_write_hva(vq, (uintptr_t)iov[i].iov_base, iov[i].iov_len); if (r < 0) return r; } return 0; } for (i = 0; i < log_num; ++i) { u64 l = min(log[i].len, len); r = log_write(vq->log_base, log[i].addr, l); if (r < 0) return r; len -= l; if (!len) { if (vq->log_ctx) eventfd_signal(vq->log_ctx); return 0; } } /* Length written exceeds what we have stored. This is a bug. */ BUG(); return 0; } EXPORT_SYMBOL_GPL(vhost_log_write); static int vhost_update_used_flags(struct vhost_virtqueue *vq) { void __user *used; if (vhost_put_used_flags(vq)) return -EFAULT; if (unlikely(vq->log_used)) { /* Make sure the flag is seen before log. */ smp_wmb(); /* Log used flag write. */ used = &vq->used->flags; log_used(vq, (used - (void __user *)vq->used), sizeof vq->used->flags); if (vq->log_ctx) eventfd_signal(vq->log_ctx); } return 0; } static int vhost_update_avail_event(struct vhost_virtqueue *vq) { if (vhost_put_avail_event(vq)) return -EFAULT; if (unlikely(vq->log_used)) { void __user *used; /* Make sure the event is seen before log. */ smp_wmb(); /* Log avail event write */ used = vhost_avail_event(vq); log_used(vq, (used - (void __user *)vq->used), sizeof *vhost_avail_event(vq)); if (vq->log_ctx) eventfd_signal(vq->log_ctx); } return 0; } int vhost_vq_init_access(struct vhost_virtqueue *vq) { __virtio16 last_used_idx; int r; bool is_le = vq->is_le; if (!vq->private_data) return 0; vhost_init_is_le(vq); r = vhost_update_used_flags(vq); if (r) goto err; vq->signalled_used_valid = false; if (!vq->iotlb && !access_ok(&vq->used->idx, sizeof vq->used->idx)) { r = -EFAULT; goto err; } r = vhost_get_used_idx(vq, &last_used_idx); if (r) { vq_err(vq, "Can't access used idx at %p\n", &vq->used->idx); goto err; } vq->last_used_idx = vhost16_to_cpu(vq, last_used_idx); return 0; err: vq->is_le = is_le; return r; } EXPORT_SYMBOL_GPL(vhost_vq_init_access); static int translate_desc(struct vhost_virtqueue *vq, u64 addr, u32 len, struct iovec iov[], int iov_size, int access) { const struct vhost_iotlb_map *map; struct vhost_dev *dev = vq->dev; struct vhost_iotlb *umem = dev->iotlb ? dev->iotlb : dev->umem; struct iovec *_iov; u64 s = 0, last = addr + len - 1; int ret = 0; while ((u64)len > s) { u64 size; if (unlikely(ret >= iov_size)) { ret = -ENOBUFS; break; } map = vhost_iotlb_itree_first(umem, addr, last); if (map == NULL || map->start > addr) { if (umem != dev->iotlb) { ret = -EFAULT; break; } ret = -EAGAIN; break; } else if (!(map->perm & access)) { ret = -EPERM; break; } _iov = iov + ret; size = map->size - addr + map->start; _iov->iov_len = min((u64)len - s, size); _iov->iov_base = (void __user *)(unsigned long) (map->addr + addr - map->start); s += size; addr += size; ++ret; } if (ret == -EAGAIN) vhost_iotlb_miss(vq, addr, access); return ret; } /* Each buffer in the virtqueues is actually a chain of descriptors. This * function returns the next descriptor in the chain, * or -1U if we're at the end. */ static unsigned next_desc(struct vhost_virtqueue *vq, struct vring_desc *desc) { unsigned int next; /* If this descriptor says it doesn't chain, we're done. */ if (!(desc->flags & cpu_to_vhost16(vq, VRING_DESC_F_NEXT))) return -1U; /* Check they're not leading us off end of descriptors. */ next = vhost16_to_cpu(vq, READ_ONCE(desc->next)); return next; } static int get_indirect(struct vhost_virtqueue *vq, struct iovec iov[], unsigned int iov_size, unsigned int *out_num, unsigned int *in_num, struct vhost_log *log, unsigned int *log_num, struct vring_desc *indirect) { struct vring_desc desc; unsigned int i = 0, count, found = 0; u32 len = vhost32_to_cpu(vq, indirect->len); struct iov_iter from; int ret, access; /* Sanity check */ if (unlikely(len % sizeof desc)) { vq_err(vq, "Invalid length in indirect descriptor: " "len 0x%llx not multiple of 0x%zx\n", (unsigned long long)len, sizeof desc); return -EINVAL; } ret = translate_desc(vq, vhost64_to_cpu(vq, indirect->addr), len, vq->indirect, UIO_MAXIOV, VHOST_ACCESS_RO); if (unlikely(ret < 0)) { if (ret != -EAGAIN) vq_err(vq, "Translation failure %d in indirect.\n", ret); return ret; } iov_iter_init(&from, ITER_SOURCE, vq->indirect, ret, len); count = len / sizeof desc; /* Buffers are chained via a 16 bit next field, so * we can have at most 2^16 of these. */ if (unlikely(count > USHRT_MAX + 1)) { vq_err(vq, "Indirect buffer length too big: %d\n", indirect->len); return -E2BIG; } do { unsigned iov_count = *in_num + *out_num; if (unlikely(++found > count)) { vq_err(vq, "Loop detected: last one at %u " "indirect size %u\n", i, count); return -EINVAL; } if (unlikely(!copy_from_iter_full(&desc, sizeof(desc), &from))) { vq_err(vq, "Failed indirect descriptor: idx %d, %zx\n", i, (size_t)vhost64_to_cpu(vq, indirect->addr) + i * sizeof desc); return -EINVAL; } if (unlikely(desc.flags & cpu_to_vhost16(vq, VRING_DESC_F_INDIRECT))) { vq_err(vq, "Nested indirect descriptor: idx %d, %zx\n", i, (size_t)vhost64_to_cpu(vq, indirect->addr) + i * sizeof desc); return -EINVAL; } if (desc.flags & cpu_to_vhost16(vq, VRING_DESC_F_WRITE)) access = VHOST_ACCESS_WO; else access = VHOST_ACCESS_RO; ret = translate_desc(vq, vhost64_to_cpu(vq, desc.addr), vhost32_to_cpu(vq, desc.len), iov + iov_count, iov_size - iov_count, access); if (unlikely(ret < 0)) { if (ret != -EAGAIN) vq_err(vq, "Translation failure %d indirect idx %d\n", ret, i); return ret; } /* If this is an input descriptor, increment that count. */ if (access == VHOST_ACCESS_WO) { *in_num += ret; if (unlikely(log && ret)) { log[*log_num].addr = vhost64_to_cpu(vq, desc.addr); log[*log_num].len = vhost32_to_cpu(vq, desc.len); ++*log_num; } } else { /* If it's an output descriptor, they're all supposed * to come before any input descriptors. */ if (unlikely(*in_num)) { vq_err(vq, "Indirect descriptor " "has out after in: idx %d\n", i); return -EINVAL; } *out_num += ret; } } while ((i = next_desc(vq, &desc)) != -1); return 0; } /* This looks in the virtqueue and for the first available buffer, and converts * it to an iovec for convenient access. Since descriptors consist of some * number of output then some number of input descriptors, it's actually two * iovecs, but we pack them into one and note how many of each there were. * * This function returns the descriptor number found, or vq->num (which is * never a valid descriptor number) if none was found. A negative code is * returned on error. */ int vhost_get_vq_desc(struct vhost_virtqueue *vq, struct iovec iov[], unsigned int iov_size, unsigned int *out_num, unsigned int *in_num, struct vhost_log *log, unsigned int *log_num) { struct vring_desc desc; unsigned int i, head, found = 0; u16 last_avail_idx = vq->last_avail_idx; __virtio16 ring_head; int ret, access; if (vq->avail_idx == vq->last_avail_idx) { ret = vhost_get_avail_idx(vq); if (unlikely(ret < 0)) return ret; if (!ret) return vq->num; } /* Grab the next descriptor number they're advertising, and increment * the index we've seen. */ if (unlikely(vhost_get_avail_head(vq, &ring_head, last_avail_idx))) { vq_err(vq, "Failed to read head: idx %d address %p\n", last_avail_idx, &vq->avail->ring[last_avail_idx % vq->num]); return -EFAULT; } head = vhost16_to_cpu(vq, ring_head); /* If their number is silly, that's an error. */ if (unlikely(head >= vq->num)) { vq_err(vq, "Guest says index %u > %u is available", head, vq->num); return -EINVAL; } /* When we start there are none of either input nor output. */ *out_num = *in_num = 0; if (unlikely(log)) *log_num = 0; i = head; do { unsigned iov_count = *in_num + *out_num; if (unlikely(i >= vq->num)) { vq_err(vq, "Desc index is %u > %u, head = %u", i, vq->num, head); return -EINVAL; } if (unlikely(++found > vq->num)) { vq_err(vq, "Loop detected: last one at %u " "vq size %u head %u\n", i, vq->num, head); return -EINVAL; } ret = vhost_get_desc(vq, &desc, i); if (unlikely(ret)) { vq_err(vq, "Failed to get descriptor: idx %d addr %p\n", i, vq->desc + i); return -EFAULT; } if (desc.flags & cpu_to_vhost16(vq, VRING_DESC_F_INDIRECT)) { ret = get_indirect(vq, iov, iov_size, out_num, in_num, log, log_num, &desc); if (unlikely(ret < 0)) { if (ret != -EAGAIN) vq_err(vq, "Failure detected " "in indirect descriptor at idx %d\n", i); return ret; } continue; } if (desc.flags & cpu_to_vhost16(vq, VRING_DESC_F_WRITE)) access = VHOST_ACCESS_WO; else access = VHOST_ACCESS_RO; ret = translate_desc(vq, vhost64_to_cpu(vq, desc.addr), vhost32_to_cpu(vq, desc.len), iov + iov_count, iov_size - iov_count, access); if (unlikely(ret < 0)) { if (ret != -EAGAIN) vq_err(vq, "Translation failure %d descriptor idx %d\n", ret, i); return ret; } if (access == VHOST_ACCESS_WO) { /* If this is an input descriptor, * increment that count. */ *in_num += ret; if (unlikely(log && ret)) { log[*log_num].addr = vhost64_to_cpu(vq, desc.addr); log[*log_num].len = vhost32_to_cpu(vq, desc.len); ++*log_num; } } else { /* If it's an output descriptor, they're all supposed * to come before any input descriptors. */ if (unlikely(*in_num)) { vq_err(vq, "Descriptor has out after in: " "idx %d\n", i); return -EINVAL; } *out_num += ret; } } while ((i = next_desc(vq, &desc)) != -1); /* On success, increment avail index. */ vq->last_avail_idx++; /* Assume notifications from guest are disabled at this point, * if they aren't we would need to update avail_event index. */ BUG_ON(!(vq->used_flags & VRING_USED_F_NO_NOTIFY)); return head; } EXPORT_SYMBOL_GPL(vhost_get_vq_desc); /* Reverse the effect of vhost_get_vq_desc. Useful for error handling. */ void vhost_discard_vq_desc(struct vhost_virtqueue *vq, int n) { vq->last_avail_idx -= n; } EXPORT_SYMBOL_GPL(vhost_discard_vq_desc); /* After we've used one of their buffers, we tell them about it. We'll then * want to notify the guest, using eventfd. */ int vhost_add_used(struct vhost_virtqueue *vq, unsigned int head, int len) { struct vring_used_elem heads = { cpu_to_vhost32(vq, head), cpu_to_vhost32(vq, len) }; return vhost_add_used_n(vq, &heads, 1); } EXPORT_SYMBOL_GPL(vhost_add_used); static int __vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads, unsigned count) { vring_used_elem_t __user *used; u16 old, new; int start; start = vq->last_used_idx & (vq->num - 1); used = vq->used->ring + start; if (vhost_put_used(vq, heads, start, count)) { vq_err(vq, "Failed to write used"); return -EFAULT; } if (unlikely(vq->log_used)) { /* Make sure data is seen before log. */ smp_wmb(); /* Log used ring entry write. */ log_used(vq, ((void __user *)used - (void __user *)vq->used), count * sizeof *used); } old = vq->last_used_idx; new = (vq->last_used_idx += count); /* If the driver never bothers to signal in a very long while, * used index might wrap around. If that happens, invalidate * signalled_used index we stored. TODO: make sure driver * signals at least once in 2^16 and remove this. */ if (unlikely((u16)(new - vq->signalled_used) < (u16)(new - old))) vq->signalled_used_valid = false; return 0; } /* After we've used one of their buffers, we tell them about it. We'll then * want to notify the guest, using eventfd. */ int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads, unsigned count) { int start, n, r; start = vq->last_used_idx & (vq->num - 1); n = vq->num - start; if (n < count) { r = __vhost_add_used_n(vq, heads, n); if (r < 0) return r; heads += n; count -= n; } r = __vhost_add_used_n(vq, heads, count); /* Make sure buffer is written before we update index. */ smp_wmb(); if (vhost_put_used_idx(vq)) { vq_err(vq, "Failed to increment used idx"); return -EFAULT; } if (unlikely(vq->log_used)) { /* Make sure used idx is seen before log. */ smp_wmb(); /* Log used index update. */ log_used(vq, offsetof(struct vring_used, idx), sizeof vq->used->idx); if (vq->log_ctx) eventfd_signal(vq->log_ctx); } return r; } EXPORT_SYMBOL_GPL(vhost_add_used_n); static bool vhost_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq) { __u16 old, new; __virtio16 event; bool v; /* Flush out used index updates. This is paired * with the barrier that the Guest executes when enabling * interrupts. */ smp_mb(); if (vhost_has_feature(vq, VIRTIO_F_NOTIFY_ON_EMPTY) && unlikely(vq->avail_idx == vq->last_avail_idx)) return true; if (!vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX)) { __virtio16 flags; if (vhost_get_avail_flags(vq, &flags)) { vq_err(vq, "Failed to get flags"); return true; } return !(flags & cpu_to_vhost16(vq, VRING_AVAIL_F_NO_INTERRUPT)); } old = vq->signalled_used; v = vq->signalled_used_valid; new = vq->signalled_used = vq->last_used_idx; vq->signalled_used_valid = true; if (unlikely(!v)) return true; if (vhost_get_used_event(vq, &event)) { vq_err(vq, "Failed to get used event idx"); return true; } return vring_need_event(vhost16_to_cpu(vq, event), new, old); } /* This actually signals the guest, using eventfd. */ void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq) { /* Signal the Guest tell them we used something up. */ if (vq->call_ctx.ctx && vhost_notify(dev, vq)) eventfd_signal(vq->call_ctx.ctx); } EXPORT_SYMBOL_GPL(vhost_signal); /* And here's the combo meal deal. Supersize me! */ void vhost_add_used_and_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq, unsigned int head, int len) { vhost_add_used(vq, head, len); vhost_signal(dev, vq); } EXPORT_SYMBOL_GPL(vhost_add_used_and_signal); /* multi-buffer version of vhost_add_used_and_signal */ void vhost_add_used_and_signal_n(struct vhost_dev *dev, struct vhost_virtqueue *vq, struct vring_used_elem *heads, unsigned count) { vhost_add_used_n(vq, heads, count); vhost_signal(dev, vq); } EXPORT_SYMBOL_GPL(vhost_add_used_and_signal_n); /* return true if we're sure that avaiable ring is empty */ bool vhost_vq_avail_empty(struct vhost_dev *dev, struct vhost_virtqueue *vq) { int r; if (vq->avail_idx != vq->last_avail_idx) return false; r = vhost_get_avail_idx(vq); /* Note: we treat error as non-empty here */ return r == 0; } EXPORT_SYMBOL_GPL(vhost_vq_avail_empty); /* OK, now we need to know about added descriptors. */ bool vhost_enable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq) { int r; if (!(vq->used_flags & VRING_USED_F_NO_NOTIFY)) return false; vq->used_flags &= ~VRING_USED_F_NO_NOTIFY; if (!vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX)) { r = vhost_update_used_flags(vq); if (r) { vq_err(vq, "Failed to enable notification at %p: %d\n", &vq->used->flags, r); return false; } } else { r = vhost_update_avail_event(vq); if (r) { vq_err(vq, "Failed to update avail event index at %p: %d\n", vhost_avail_event(vq), r); return false; } } /* They could have slipped one in as we were doing that: make * sure it's written, then check again. */ smp_mb(); r = vhost_get_avail_idx(vq); /* Note: we treat error as empty here */ if (unlikely(r < 0)) return false; return r; } EXPORT_SYMBOL_GPL(vhost_enable_notify); /* We don't need to be notified again. */ void vhost_disable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq) { int r; if (vq->used_flags & VRING_USED_F_NO_NOTIFY) return; vq->used_flags |= VRING_USED_F_NO_NOTIFY; if (!vhost_has_feature(vq, VIRTIO_RING_F_EVENT_IDX)) { r = vhost_update_used_flags(vq); if (r) vq_err(vq, "Failed to disable notification at %p: %d\n", &vq->used->flags, r); } } EXPORT_SYMBOL_GPL(vhost_disable_notify); /* Create a new message. */ struct vhost_msg_node *vhost_new_msg(struct vhost_virtqueue *vq, int type) { /* Make sure all padding within the structure is initialized. */ struct vhost_msg_node *node = kzalloc(sizeof(*node), GFP_KERNEL); if (!node) return NULL; node->vq = vq; node->msg.type = type; return node; } EXPORT_SYMBOL_GPL(vhost_new_msg); void vhost_enqueue_msg(struct vhost_dev *dev, struct list_head *head, struct vhost_msg_node *node) { spin_lock(&dev->iotlb_lock); list_add_tail(&node->node, head); spin_unlock(&dev->iotlb_lock); wake_up_interruptible_poll(&dev->wait, EPOLLIN | EPOLLRDNORM); } EXPORT_SYMBOL_GPL(vhost_enqueue_msg); struct vhost_msg_node *vhost_dequeue_msg(struct vhost_dev *dev, struct list_head *head) { struct vhost_msg_node *node = NULL; spin_lock(&dev->iotlb_lock); if (!list_empty(head)) { node = list_first_entry(head, struct vhost_msg_node, node); list_del(&node->node); } spin_unlock(&dev->iotlb_lock); return node; } EXPORT_SYMBOL_GPL(vhost_dequeue_msg); void vhost_set_backend_features(struct vhost_dev *dev, u64 features) { struct vhost_virtqueue *vq; int i; mutex_lock(&dev->mutex); for (i = 0; i < dev->nvqs; ++i) { vq = dev->vqs[i]; mutex_lock(&vq->mutex); vq->acked_backend_features = features; mutex_unlock(&vq->mutex); } mutex_unlock(&dev->mutex); } EXPORT_SYMBOL_GPL(vhost_set_backend_features); static int __init vhost_init(void) { return 0; } static void __exit vhost_exit(void) { } module_init(vhost_init); module_exit(vhost_exit); MODULE_VERSION("0.0.1"); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Michael S. Tsirkin"); MODULE_DESCRIPTION("Host kernel accelerator for virtio"); |
| 308 302 311 305 305 297 302 42 42 42 42 116 120 14 37 37 101 102 122 122 9 5 4 2 1 6 3 4 3 4 22 16 243 242 16 238 237 2 7 317 240 300 303 15 2 48 48 191 47 3 216 211 2 1 213 192 192 25 25 2 23 40 40 2 39 27 27 325 82 49 311 2 311 7 312 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/hfs/bnode.c * * Copyright (C) 2001 * Brad Boyer (flar@allandria.com) * (C) 2003 Ardis Technologies <roman@ardistech.com> * * Handle basic btree node operations */ #include <linux/pagemap.h> #include <linux/slab.h> #include <linux/swap.h> #include "btree.h" void hfs_bnode_read(struct hfs_bnode *node, void *buf, int off, int len) { struct page *page; int pagenum; int bytes_read; int bytes_to_read; off += node->page_offset; pagenum = off >> PAGE_SHIFT; off &= ~PAGE_MASK; /* compute page offset for the first page */ for (bytes_read = 0; bytes_read < len; bytes_read += bytes_to_read) { if (pagenum >= node->tree->pages_per_bnode) break; page = node->page[pagenum]; bytes_to_read = min_t(int, len - bytes_read, PAGE_SIZE - off); memcpy_from_page(buf + bytes_read, page, off, bytes_to_read); pagenum++; off = 0; /* page offset only applies to the first page */ } } u16 hfs_bnode_read_u16(struct hfs_bnode *node, int off) { __be16 data; // optimize later... hfs_bnode_read(node, &data, off, 2); return be16_to_cpu(data); } u8 hfs_bnode_read_u8(struct hfs_bnode *node, int off) { u8 data; // optimize later... hfs_bnode_read(node, &data, off, 1); return data; } void hfs_bnode_read_key(struct hfs_bnode *node, void *key, int off) { struct hfs_btree *tree; int key_len; tree = node->tree; if (node->type == HFS_NODE_LEAF || tree->attributes & HFS_TREE_VARIDXKEYS) key_len = hfs_bnode_read_u8(node, off) + 1; else key_len = tree->max_key_len + 1; hfs_bnode_read(node, key, off, key_len); } void hfs_bnode_write(struct hfs_bnode *node, void *buf, int off, int len) { struct page *page; off += node->page_offset; page = node->page[0]; memcpy_to_page(page, off, buf, len); set_page_dirty(page); } void hfs_bnode_write_u16(struct hfs_bnode *node, int off, u16 data) { __be16 v = cpu_to_be16(data); // optimize later... hfs_bnode_write(node, &v, off, 2); } void hfs_bnode_write_u8(struct hfs_bnode *node, int off, u8 data) { // optimize later... hfs_bnode_write(node, &data, off, 1); } void hfs_bnode_clear(struct hfs_bnode *node, int off, int len) { struct page *page; off += node->page_offset; page = node->page[0]; memzero_page(page, off, len); set_page_dirty(page); } void hfs_bnode_copy(struct hfs_bnode *dst_node, int dst, struct hfs_bnode *src_node, int src, int len) { struct page *src_page, *dst_page; hfs_dbg(BNODE_MOD, "copybytes: %u,%u,%u\n", dst, src, len); if (!len) return; src += src_node->page_offset; dst += dst_node->page_offset; src_page = src_node->page[0]; dst_page = dst_node->page[0]; memcpy_page(dst_page, dst, src_page, src, len); set_page_dirty(dst_page); } void hfs_bnode_move(struct hfs_bnode *node, int dst, int src, int len) { struct page *page; void *ptr; hfs_dbg(BNODE_MOD, "movebytes: %u,%u,%u\n", dst, src, len); if (!len) return; src += node->page_offset; dst += node->page_offset; page = node->page[0]; ptr = kmap_local_page(page); memmove(ptr + dst, ptr + src, len); kunmap_local(ptr); set_page_dirty(page); } void hfs_bnode_dump(struct hfs_bnode *node) { struct hfs_bnode_desc desc; __be32 cnid; int i, off, key_off; hfs_dbg(BNODE_MOD, "bnode: %d\n", node->this); hfs_bnode_read(node, &desc, 0, sizeof(desc)); hfs_dbg(BNODE_MOD, "%d, %d, %d, %d, %d\n", be32_to_cpu(desc.next), be32_to_cpu(desc.prev), desc.type, desc.height, be16_to_cpu(desc.num_recs)); off = node->tree->node_size - 2; for (i = be16_to_cpu(desc.num_recs); i >= 0; off -= 2, i--) { key_off = hfs_bnode_read_u16(node, off); hfs_dbg_cont(BNODE_MOD, " %d", key_off); if (i && node->type == HFS_NODE_INDEX) { int tmp; if (node->tree->attributes & HFS_TREE_VARIDXKEYS) tmp = (hfs_bnode_read_u8(node, key_off) | 1) + 1; else tmp = node->tree->max_key_len + 1; hfs_dbg_cont(BNODE_MOD, " (%d,%d", tmp, hfs_bnode_read_u8(node, key_off)); hfs_bnode_read(node, &cnid, key_off + tmp, 4); hfs_dbg_cont(BNODE_MOD, ",%d)", be32_to_cpu(cnid)); } else if (i && node->type == HFS_NODE_LEAF) { int tmp; tmp = hfs_bnode_read_u8(node, key_off); hfs_dbg_cont(BNODE_MOD, " (%d)", tmp); } } hfs_dbg_cont(BNODE_MOD, "\n"); } void hfs_bnode_unlink(struct hfs_bnode *node) { struct hfs_btree *tree; struct hfs_bnode *tmp; __be32 cnid; tree = node->tree; if (node->prev) { tmp = hfs_bnode_find(tree, node->prev); if (IS_ERR(tmp)) return; tmp->next = node->next; cnid = cpu_to_be32(tmp->next); hfs_bnode_write(tmp, &cnid, offsetof(struct hfs_bnode_desc, next), 4); hfs_bnode_put(tmp); } else if (node->type == HFS_NODE_LEAF) tree->leaf_head = node->next; if (node->next) { tmp = hfs_bnode_find(tree, node->next); if (IS_ERR(tmp)) return; tmp->prev = node->prev; cnid = cpu_to_be32(tmp->prev); hfs_bnode_write(tmp, &cnid, offsetof(struct hfs_bnode_desc, prev), 4); hfs_bnode_put(tmp); } else if (node->type == HFS_NODE_LEAF) tree->leaf_tail = node->prev; // move down? if (!node->prev && !node->next) { printk(KERN_DEBUG "hfs_btree_del_level\n"); } if (!node->parent) { tree->root = 0; tree->depth = 0; } set_bit(HFS_BNODE_DELETED, &node->flags); } static inline int hfs_bnode_hash(u32 num) { num = (num >> 16) + num; num += num >> 8; return num & (NODE_HASH_SIZE - 1); } struct hfs_bnode *hfs_bnode_findhash(struct hfs_btree *tree, u32 cnid) { struct hfs_bnode *node; if (cnid >= tree->node_count) { pr_err("request for non-existent node %d in B*Tree\n", cnid); return NULL; } for (node = tree->node_hash[hfs_bnode_hash(cnid)]; node; node = node->next_hash) { if (node->this == cnid) { return node; } } return NULL; } static struct hfs_bnode *__hfs_bnode_create(struct hfs_btree *tree, u32 cnid) { struct hfs_bnode *node, *node2; struct address_space *mapping; struct page *page; int size, block, i, hash; loff_t off; if (cnid >= tree->node_count) { pr_err("request for non-existent node %d in B*Tree\n", cnid); return NULL; } size = sizeof(struct hfs_bnode) + tree->pages_per_bnode * sizeof(struct page *); node = kzalloc(size, GFP_KERNEL); if (!node) return NULL; node->tree = tree; node->this = cnid; set_bit(HFS_BNODE_NEW, &node->flags); atomic_set(&node->refcnt, 1); hfs_dbg(BNODE_REFS, "new_node(%d:%d): 1\n", node->tree->cnid, node->this); init_waitqueue_head(&node->lock_wq); spin_lock(&tree->hash_lock); node2 = hfs_bnode_findhash(tree, cnid); if (!node2) { hash = hfs_bnode_hash(cnid); node->next_hash = tree->node_hash[hash]; tree->node_hash[hash] = node; tree->node_hash_cnt++; } else { hfs_bnode_get(node2); spin_unlock(&tree->hash_lock); kfree(node); wait_event(node2->lock_wq, !test_bit(HFS_BNODE_NEW, &node2->flags)); return node2; } spin_unlock(&tree->hash_lock); mapping = tree->inode->i_mapping; off = (loff_t)cnid * tree->node_size; block = off >> PAGE_SHIFT; node->page_offset = off & ~PAGE_MASK; for (i = 0; i < tree->pages_per_bnode; i++) { page = read_mapping_page(mapping, block++, NULL); if (IS_ERR(page)) goto fail; node->page[i] = page; } return node; fail: set_bit(HFS_BNODE_ERROR, &node->flags); return node; } void hfs_bnode_unhash(struct hfs_bnode *node) { struct hfs_bnode **p; hfs_dbg(BNODE_REFS, "remove_node(%d:%d): %d\n", node->tree->cnid, node->this, atomic_read(&node->refcnt)); for (p = &node->tree->node_hash[hfs_bnode_hash(node->this)]; *p && *p != node; p = &(*p)->next_hash) ; BUG_ON(!*p); *p = node->next_hash; node->tree->node_hash_cnt--; } /* Load a particular node out of a tree */ struct hfs_bnode *hfs_bnode_find(struct hfs_btree *tree, u32 num) { struct hfs_bnode *node; struct hfs_bnode_desc *desc; int i, rec_off, off, next_off; int entry_size, key_size; spin_lock(&tree->hash_lock); node = hfs_bnode_findhash(tree, num); if (node) { hfs_bnode_get(node); spin_unlock(&tree->hash_lock); wait_event(node->lock_wq, !test_bit(HFS_BNODE_NEW, &node->flags)); if (test_bit(HFS_BNODE_ERROR, &node->flags)) goto node_error; return node; } spin_unlock(&tree->hash_lock); node = __hfs_bnode_create(tree, num); if (!node) return ERR_PTR(-ENOMEM); if (test_bit(HFS_BNODE_ERROR, &node->flags)) goto node_error; if (!test_bit(HFS_BNODE_NEW, &node->flags)) return node; desc = (struct hfs_bnode_desc *)(kmap_local_page(node->page[0]) + node->page_offset); node->prev = be32_to_cpu(desc->prev); node->next = be32_to_cpu(desc->next); node->num_recs = be16_to_cpu(desc->num_recs); node->type = desc->type; node->height = desc->height; kunmap_local(desc); switch (node->type) { case HFS_NODE_HEADER: case HFS_NODE_MAP: if (node->height != 0) goto node_error; break; case HFS_NODE_LEAF: if (node->height != 1) goto node_error; break; case HFS_NODE_INDEX: if (node->height <= 1 || node->height > tree->depth) goto node_error; break; default: goto node_error; } rec_off = tree->node_size - 2; off = hfs_bnode_read_u16(node, rec_off); if (off != sizeof(struct hfs_bnode_desc)) goto node_error; for (i = 1; i <= node->num_recs; off = next_off, i++) { rec_off -= 2; next_off = hfs_bnode_read_u16(node, rec_off); if (next_off <= off || next_off > tree->node_size || next_off & 1) goto node_error; entry_size = next_off - off; if (node->type != HFS_NODE_INDEX && node->type != HFS_NODE_LEAF) continue; key_size = hfs_bnode_read_u8(node, off) + 1; if (key_size >= entry_size /*|| key_size & 1*/) goto node_error; } clear_bit(HFS_BNODE_NEW, &node->flags); wake_up(&node->lock_wq); return node; node_error: set_bit(HFS_BNODE_ERROR, &node->flags); clear_bit(HFS_BNODE_NEW, &node->flags); wake_up(&node->lock_wq); hfs_bnode_put(node); return ERR_PTR(-EIO); } void hfs_bnode_free(struct hfs_bnode *node) { int i; for (i = 0; i < node->tree->pages_per_bnode; i++) if (node->page[i]) put_page(node->page[i]); kfree(node); } struct hfs_bnode *hfs_bnode_create(struct hfs_btree *tree, u32 num) { struct hfs_bnode *node; struct page **pagep; int i; spin_lock(&tree->hash_lock); node = hfs_bnode_findhash(tree, num); spin_unlock(&tree->hash_lock); if (node) { pr_crit("new node %u already hashed?\n", num); WARN_ON(1); return node; } node = __hfs_bnode_create(tree, num); if (!node) return ERR_PTR(-ENOMEM); if (test_bit(HFS_BNODE_ERROR, &node->flags)) { hfs_bnode_put(node); return ERR_PTR(-EIO); } pagep = node->page; memzero_page(*pagep, node->page_offset, min((int)PAGE_SIZE, (int)tree->node_size)); set_page_dirty(*pagep); for (i = 1; i < tree->pages_per_bnode; i++) { memzero_page(*++pagep, 0, PAGE_SIZE); set_page_dirty(*pagep); } clear_bit(HFS_BNODE_NEW, &node->flags); wake_up(&node->lock_wq); return node; } void hfs_bnode_get(struct hfs_bnode *node) { if (node) { atomic_inc(&node->refcnt); hfs_dbg(BNODE_REFS, "get_node(%d:%d): %d\n", node->tree->cnid, node->this, atomic_read(&node->refcnt)); } } /* Dispose of resources used by a node */ void hfs_bnode_put(struct hfs_bnode *node) { if (node) { struct hfs_btree *tree = node->tree; int i; hfs_dbg(BNODE_REFS, "put_node(%d:%d): %d\n", node->tree->cnid, node->this, atomic_read(&node->refcnt)); BUG_ON(!atomic_read(&node->refcnt)); if (!atomic_dec_and_lock(&node->refcnt, &tree->hash_lock)) return; for (i = 0; i < tree->pages_per_bnode; i++) { if (!node->page[i]) continue; mark_page_accessed(node->page[i]); } if (test_bit(HFS_BNODE_DELETED, &node->flags)) { hfs_bnode_unhash(node); spin_unlock(&tree->hash_lock); hfs_bmap_free(node); hfs_bnode_free(node); return; } spin_unlock(&tree->hash_lock); } } |
| 1 2 2 1 5 2 3 4 1 5 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * HID driver for some cypress "special" devices * * Copyright (c) 1999 Andreas Gal * Copyright (c) 2000-2005 Vojtech Pavlik <vojtech@suse.cz> * Copyright (c) 2005 Michael Haboustak <mike-@cinci.rr.com> for Concept2, Inc * Copyright (c) 2006-2007 Jiri Kosina * Copyright (c) 2008 Jiri Slaby */ /* */ #include <linux/device.h> #include <linux/hid.h> #include <linux/input.h> #include <linux/module.h> #include "hid-ids.h" #define CP_RDESC_SWAPPED_MIN_MAX 0x01 #define CP_2WHEEL_MOUSE_HACK 0x02 #define CP_2WHEEL_MOUSE_HACK_ON 0x04 #define VA_INVAL_LOGICAL_BOUNDARY 0x08 /* * Some USB barcode readers from cypress have usage min and usage max in * the wrong order */ static __u8 *cp_rdesc_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { unsigned int i; if (*rsize < 4) return rdesc; for (i = 0; i < *rsize - 4; i++) if (rdesc[i] == 0x29 && rdesc[i + 2] == 0x19) { rdesc[i] = 0x19; rdesc[i + 2] = 0x29; swap(rdesc[i + 3], rdesc[i + 1]); } return rdesc; } static __u8 *va_logical_boundary_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { /* * Varmilo VA104M (with VID Cypress and device ID 07B1) incorrectly * reports Logical Minimum of its Consumer Control device as 572 * (0x02 0x3c). Fix this by setting its Logical Minimum to zero. */ if (*rsize == 25 && rdesc[0] == 0x05 && rdesc[1] == 0x0c && rdesc[2] == 0x09 && rdesc[3] == 0x01 && rdesc[6] == 0x19 && rdesc[7] == 0x00 && rdesc[11] == 0x16 && rdesc[12] == 0x3c && rdesc[13] == 0x02) { hid_info(hdev, "fixing up varmilo VA104M consumer control report descriptor\n"); rdesc[12] = 0x00; rdesc[13] = 0x00; } return rdesc; } static const __u8 *cp_report_fixup(struct hid_device *hdev, __u8 *rdesc, unsigned int *rsize) { unsigned long quirks = (unsigned long)hid_get_drvdata(hdev); if (quirks & CP_RDESC_SWAPPED_MIN_MAX) rdesc = cp_rdesc_fixup(hdev, rdesc, rsize); if (quirks & VA_INVAL_LOGICAL_BOUNDARY) rdesc = va_logical_boundary_fixup(hdev, rdesc, rsize); return rdesc; } static int cp_input_mapped(struct hid_device *hdev, struct hid_input *hi, struct hid_field *field, struct hid_usage *usage, unsigned long **bit, int *max) { unsigned long quirks = (unsigned long)hid_get_drvdata(hdev); if (!(quirks & CP_2WHEEL_MOUSE_HACK)) return 0; if (usage->type == EV_REL && usage->code == REL_WHEEL) set_bit(REL_HWHEEL, *bit); if (usage->hid == 0x00090005) return -1; return 0; } static int cp_event(struct hid_device *hdev, struct hid_field *field, struct hid_usage *usage, __s32 value) { unsigned long quirks = (unsigned long)hid_get_drvdata(hdev); if (!(hdev->claimed & HID_CLAIMED_INPUT) || !field->hidinput || !usage->type || !(quirks & CP_2WHEEL_MOUSE_HACK)) return 0; if (usage->hid == 0x00090005) { if (value) quirks |= CP_2WHEEL_MOUSE_HACK_ON; else quirks &= ~CP_2WHEEL_MOUSE_HACK_ON; hid_set_drvdata(hdev, (void *)quirks); return 1; } if (usage->code == REL_WHEEL && (quirks & CP_2WHEEL_MOUSE_HACK_ON)) { struct input_dev *input = field->hidinput->input; input_event(input, usage->type, REL_HWHEEL, value); return 1; } return 0; } static int cp_probe(struct hid_device *hdev, const struct hid_device_id *id) { unsigned long quirks = id->driver_data; int ret; hid_set_drvdata(hdev, (void *)quirks); ret = hid_parse(hdev); if (ret) { hid_err(hdev, "parse failed\n"); goto err_free; } ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT); if (ret) { hid_err(hdev, "hw start failed\n"); goto err_free; } return 0; err_free: return ret; } static const struct hid_device_id cp_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_BARCODE_1), .driver_data = CP_RDESC_SWAPPED_MIN_MAX }, { HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_BARCODE_2), .driver_data = CP_RDESC_SWAPPED_MIN_MAX }, { HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_BARCODE_3), .driver_data = CP_RDESC_SWAPPED_MIN_MAX }, { HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_BARCODE_4), .driver_data = CP_RDESC_SWAPPED_MIN_MAX }, { HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_MOUSE), .driver_data = CP_2WHEEL_MOUSE_HACK }, { HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_VARMILO_VA104M_07B1), .driver_data = VA_INVAL_LOGICAL_BOUNDARY }, { } }; MODULE_DEVICE_TABLE(hid, cp_devices); static struct hid_driver cp_driver = { .name = "cypress", .id_table = cp_devices, .report_fixup = cp_report_fixup, .input_mapped = cp_input_mapped, .event = cp_event, .probe = cp_probe, }; module_hid_driver(cp_driver); MODULE_DESCRIPTION("HID driver for some cypress \"special\" devices"); MODULE_LICENSE("GPL"); |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* * Symbol USB barcode to serial driver * * Copyright (C) 2013 Johan Hovold <jhovold@gmail.com> * Copyright (C) 2009 Greg Kroah-Hartman <gregkh@suse.de> * Copyright (C) 2009 Novell Inc. */ #include <linux/kernel.h> #include <linux/tty.h> #include <linux/slab.h> #include <linux/tty_driver.h> #include <linux/tty_flip.h> #include <linux/module.h> #include <linux/usb.h> #include <linux/usb/serial.h> #include <linux/uaccess.h> static const struct usb_device_id id_table[] = { { USB_DEVICE(0x05e0, 0x0600) }, { }, }; MODULE_DEVICE_TABLE(usb, id_table); struct symbol_private { spinlock_t lock; /* protects the following flags */ bool throttled; bool actually_throttled; }; static void symbol_int_callback(struct urb *urb) { struct usb_serial_port *port = urb->context; struct symbol_private *priv = usb_get_serial_port_data(port); unsigned char *data = urb->transfer_buffer; int status = urb->status; unsigned long flags; int result; int data_length; switch (status) { case 0: /* success */ break; case -ECONNRESET: case -ENOENT: case -ESHUTDOWN: /* this urb is terminated, clean up */ dev_dbg(&port->dev, "%s - urb shutting down with status: %d\n", __func__, status); return; default: dev_dbg(&port->dev, "%s - nonzero urb status received: %d\n", __func__, status); goto exit; } usb_serial_debug_data(&port->dev, __func__, urb->actual_length, data); /* * Data from the device comes with a 1 byte header: * * <size of data> <data>... */ if (urb->actual_length > 1) { data_length = data[0]; if (data_length > (urb->actual_length - 1)) data_length = urb->actual_length - 1; tty_insert_flip_string(&port->port, &data[1], data_length); tty_flip_buffer_push(&port->port); } else { dev_dbg(&port->dev, "%s - short packet\n", __func__); } exit: spin_lock_irqsave(&priv->lock, flags); /* Continue trying to always read if we should */ if (!priv->throttled) { result = usb_submit_urb(port->interrupt_in_urb, GFP_ATOMIC); if (result) dev_err(&port->dev, "%s - failed resubmitting read urb, error %d\n", __func__, result); } else priv->actually_throttled = true; spin_unlock_irqrestore(&priv->lock, flags); } static int symbol_open(struct tty_struct *tty, struct usb_serial_port *port) { struct symbol_private *priv = usb_get_serial_port_data(port); unsigned long flags; int result = 0; spin_lock_irqsave(&priv->lock, flags); priv->throttled = false; priv->actually_throttled = false; spin_unlock_irqrestore(&priv->lock, flags); /* Start reading from the device */ result = usb_submit_urb(port->interrupt_in_urb, GFP_KERNEL); if (result) dev_err(&port->dev, "%s - failed resubmitting read urb, error %d\n", __func__, result); return result; } static void symbol_close(struct usb_serial_port *port) { usb_kill_urb(port->interrupt_in_urb); } static void symbol_throttle(struct tty_struct *tty) { struct usb_serial_port *port = tty->driver_data; struct symbol_private *priv = usb_get_serial_port_data(port); spin_lock_irq(&priv->lock); priv->throttled = true; spin_unlock_irq(&priv->lock); } static void symbol_unthrottle(struct tty_struct *tty) { struct usb_serial_port *port = tty->driver_data; struct symbol_private *priv = usb_get_serial_port_data(port); int result; bool was_throttled; spin_lock_irq(&priv->lock); priv->throttled = false; was_throttled = priv->actually_throttled; priv->actually_throttled = false; spin_unlock_irq(&priv->lock); if (was_throttled) { result = usb_submit_urb(port->interrupt_in_urb, GFP_KERNEL); if (result) dev_err(&port->dev, "%s - failed submitting read urb, error %d\n", __func__, result); } } static int symbol_port_probe(struct usb_serial_port *port) { struct symbol_private *priv; priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; spin_lock_init(&priv->lock); usb_set_serial_port_data(port, priv); return 0; } static void symbol_port_remove(struct usb_serial_port *port) { struct symbol_private *priv = usb_get_serial_port_data(port); kfree(priv); } static struct usb_serial_driver symbol_device = { .driver = { .name = "symbol", }, .id_table = id_table, .num_ports = 1, .num_interrupt_in = 1, .port_probe = symbol_port_probe, .port_remove = symbol_port_remove, .open = symbol_open, .close = symbol_close, .throttle = symbol_throttle, .unthrottle = symbol_unthrottle, .read_int_callback = symbol_int_callback, }; static struct usb_serial_driver * const serial_drivers[] = { &symbol_device, NULL }; module_usb_serial_driver(serial_drivers, id_table); MODULE_DESCRIPTION("Symbol USB barcode to serial driver"); MODULE_LICENSE("GPL v2"); |
| 3 2 2 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * s2255drv.c - a driver for the Sensoray 2255 USB video capture device * * Copyright (C) 2007-2014 by Sensoray Company Inc. * Dean Anderson * * Some video buffer code based on vivi driver: * * Sensoray 2255 device supports 4 simultaneous channels. * The channels are not "crossbar" inputs, they are physically * attached to separate video decoders. * * Because of USB2.0 bandwidth limitations. There is only a * certain amount of data which may be transferred at one time. * * Example maximum bandwidth utilization: * * -full size, color mode YUYV or YUV422P: 2 channels at once * -full or half size Grey scale: all 4 channels at once * -half size, color mode YUYV or YUV422P: all 4 channels at once * -full size, color mode YUYV or YUV422P 1/2 frame rate: all 4 channels * at once. */ #include <linux/module.h> #include <linux/firmware.h> #include <linux/kernel.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/videodev2.h> #include <linux/mm.h> #include <linux/vmalloc.h> #include <linux/usb.h> #include <media/videobuf2-v4l2.h> #include <media/videobuf2-vmalloc.h> #include <media/v4l2-common.h> #include <media/v4l2-device.h> #include <media/v4l2-ioctl.h> #include <media/v4l2-ctrls.h> #include <media/v4l2-event.h> #define S2255_VERSION "1.25.1" #define FIRMWARE_FILE_NAME "f2255usb.bin" /* default JPEG quality */ #define S2255_DEF_JPEG_QUAL 50 /* vendor request in */ #define S2255_VR_IN 0 /* vendor request out */ #define S2255_VR_OUT 1 /* firmware query */ #define S2255_VR_FW 0x30 /* USB endpoint number for configuring the device */ #define S2255_CONFIG_EP 2 /* maximum time for DSP to start responding after last FW word loaded(ms) */ #define S2255_DSP_BOOTTIME 800 /* maximum time to wait for firmware to load (ms) */ #define S2255_LOAD_TIMEOUT (5000 + S2255_DSP_BOOTTIME) #define S2255_MIN_BUFS 2 #define S2255_SETMODE_TIMEOUT 500 #define S2255_VIDSTATUS_TIMEOUT 350 #define S2255_MARKER_FRAME cpu_to_le32(0x2255DA4AL) #define S2255_MARKER_RESPONSE cpu_to_le32(0x2255ACACL) #define S2255_RESPONSE_SETMODE cpu_to_le32(0x01) #define S2255_RESPONSE_FW cpu_to_le32(0x10) #define S2255_RESPONSE_STATUS cpu_to_le32(0x20) #define S2255_USB_XFER_SIZE (16 * 1024) #define MAX_CHANNELS 4 #define SYS_FRAMES 4 /* maximum size is PAL full size plus room for the marker header(s) */ #define SYS_FRAMES_MAXSIZE (720*288*2*2 + 4096) #define DEF_USB_BLOCK S2255_USB_XFER_SIZE #define LINE_SZ_4CIFS_NTSC 640 #define LINE_SZ_2CIFS_NTSC 640 #define LINE_SZ_1CIFS_NTSC 320 #define LINE_SZ_4CIFS_PAL 704 #define LINE_SZ_2CIFS_PAL 704 #define LINE_SZ_1CIFS_PAL 352 #define NUM_LINES_4CIFS_NTSC 240 #define NUM_LINES_2CIFS_NTSC 240 #define NUM_LINES_1CIFS_NTSC 240 #define NUM_LINES_4CIFS_PAL 288 #define NUM_LINES_2CIFS_PAL 288 #define NUM_LINES_1CIFS_PAL 288 #define LINE_SZ_DEF 640 #define NUM_LINES_DEF 240 /* predefined settings */ #define FORMAT_NTSC 1 #define FORMAT_PAL 2 #define SCALE_4CIFS 1 /* 640x480(NTSC) or 704x576(PAL) */ #define SCALE_2CIFS 2 /* 640x240(NTSC) or 704x288(PAL) */ #define SCALE_1CIFS 3 /* 320x240(NTSC) or 352x288(PAL) */ /* SCALE_4CIFSI is the 2 fields interpolated into one */ #define SCALE_4CIFSI 4 /* 640x480(NTSC) or 704x576(PAL) high quality */ #define COLOR_YUVPL 1 /* YUV planar */ #define COLOR_YUVPK 2 /* YUV packed */ #define COLOR_Y8 4 /* monochrome */ #define COLOR_JPG 5 /* JPEG */ #define MASK_COLOR 0x000000ff #define MASK_JPG_QUALITY 0x0000ff00 #define MASK_INPUT_TYPE 0x000f0000 /* frame decimation. */ #define FDEC_1 1 /* capture every frame. default */ #define FDEC_2 2 /* capture every 2nd frame */ #define FDEC_3 3 /* capture every 3rd frame */ #define FDEC_5 5 /* capture every 5th frame */ /*------------------------------------------------------- * Default mode parameters. *-------------------------------------------------------*/ #define DEF_SCALE SCALE_4CIFS #define DEF_COLOR COLOR_YUVPL #define DEF_FDEC FDEC_1 #define DEF_BRIGHT 0 #define DEF_CONTRAST 0x5c #define DEF_SATURATION 0x80 #define DEF_HUE 0 /* usb config commands */ #define IN_DATA_TOKEN cpu_to_le32(0x2255c0de) #define CMD_2255 0xc2255000 #define CMD_SET_MODE cpu_to_le32((CMD_2255 | 0x10)) #define CMD_START cpu_to_le32((CMD_2255 | 0x20)) #define CMD_STOP cpu_to_le32((CMD_2255 | 0x30)) #define CMD_STATUS cpu_to_le32((CMD_2255 | 0x40)) struct s2255_mode { u32 format; /* input video format (NTSC, PAL) */ u32 scale; /* output video scale */ u32 color; /* output video color format */ u32 fdec; /* frame decimation */ u32 bright; /* brightness */ u32 contrast; /* contrast */ u32 saturation; /* saturation */ u32 hue; /* hue (NTSC only)*/ u32 single; /* capture 1 frame at a time (!=0), continuously (==0)*/ u32 usb_block; /* block size. should be 4096 of DEF_USB_BLOCK */ u32 restart; /* if DSP requires restart */ }; #define S2255_READ_IDLE 0 #define S2255_READ_FRAME 1 /* frame structure */ struct s2255_framei { unsigned long size; unsigned long ulState; /* ulState:S2255_READ_IDLE, S2255_READ_FRAME*/ void *lpvbits; /* image data */ unsigned long cur_size; /* current data copied to it */ }; /* image buffer structure */ struct s2255_bufferi { unsigned long dwFrames; /* number of frames in buffer */ struct s2255_framei frame[SYS_FRAMES]; /* array of FRAME structures */ }; #define DEF_MODEI_NTSC_CONT {FORMAT_NTSC, DEF_SCALE, DEF_COLOR, \ DEF_FDEC, DEF_BRIGHT, DEF_CONTRAST, DEF_SATURATION, \ DEF_HUE, 0, DEF_USB_BLOCK, 0} /* for firmware loading, fw_state */ #define S2255_FW_NOTLOADED 0 #define S2255_FW_LOADED_DSPWAIT 1 #define S2255_FW_SUCCESS 2 #define S2255_FW_FAILED 3 #define S2255_FW_DISCONNECTING 4 #define S2255_FW_MARKER cpu_to_le32(0x22552f2f) /* 2255 read states */ #define S2255_READ_IDLE 0 #define S2255_READ_FRAME 1 struct s2255_fw { int fw_loaded; int fw_size; struct urb *fw_urb; atomic_t fw_state; void *pfw_data; wait_queue_head_t wait_fw; const struct firmware *fw; }; struct s2255_pipeinfo { u32 max_transfer_size; u32 cur_transfer_size; u8 *transfer_buffer; u32 state; void *stream_urb; void *dev; /* back pointer to s2255_dev struct*/ u32 err_count; u32 idx; }; struct s2255_fmt; /*forward declaration */ struct s2255_dev; /* 2255 video channel */ struct s2255_vc { struct s2255_dev *dev; struct video_device vdev; struct v4l2_ctrl_handler hdl; struct v4l2_ctrl *jpegqual_ctrl; int resources; struct list_head buf_list; struct s2255_bufferi buffer; struct s2255_mode mode; v4l2_std_id std; /* jpeg compression */ unsigned jpegqual; /* capture parameters (for high quality mode full size) */ struct v4l2_captureparm cap_parm; int cur_frame; int last_frame; /* allocated image size */ unsigned long req_image_size; /* received packet size */ unsigned long pkt_size; int bad_payload; unsigned long frame_count; /* if JPEG image */ int jpg_size; /* if channel configured to default state */ int configured; wait_queue_head_t wait_setmode; int setmode_ready; /* video status items */ int vidstatus; wait_queue_head_t wait_vidstatus; int vidstatus_ready; unsigned int width; unsigned int height; enum v4l2_field field; const struct s2255_fmt *fmt; int idx; /* channel number on device, 0-3 */ struct vb2_queue vb_vidq; struct mutex vb_lock; /* streaming lock */ spinlock_t qlock; }; struct s2255_dev { struct s2255_vc vc[MAX_CHANNELS]; struct v4l2_device v4l2_dev; refcount_t num_channels; int frames; struct mutex lock; /* channels[].vdev.lock */ struct mutex cmdlock; /* protects cmdbuf */ struct usb_device *udev; struct usb_interface *interface; u8 read_endpoint; struct timer_list timer; struct s2255_fw *fw_data; struct s2255_pipeinfo pipe; u32 cc; /* current channel */ int frame_ready; int chn_ready; /* dsp firmware version (f2255usb.bin) */ int dsp_fw_ver; u16 pid; /* product id */ #define S2255_CMDBUF_SIZE 512 __le32 *cmdbuf; }; static inline struct s2255_dev *to_s2255_dev(struct v4l2_device *v4l2_dev) { return container_of(v4l2_dev, struct s2255_dev, v4l2_dev); } struct s2255_fmt { u32 fourcc; int depth; }; /* buffer for one video frame */ struct s2255_buffer { /* common v4l buffer stuff -- must be first */ struct vb2_v4l2_buffer vb; struct list_head list; }; /* current cypress EEPROM firmware version */ #define S2255_CUR_USB_FWVER ((3 << 8) | 12) /* current DSP FW version */ #define S2255_CUR_DSP_FWVER 10104 /* Need DSP version 5+ for video status feature */ #define S2255_MIN_DSP_STATUS 5 #define S2255_MIN_DSP_COLORFILTER 8 #define S2255_NORMS (V4L2_STD_ALL) /* private V4L2 controls */ /* * The following chart displays how COLORFILTER should be set * ========================================================= * = fourcc = COLORFILTER = * = =============================== * = = 0 = 1 = * ========================================================= * = V4L2_PIX_FMT_GREY(Y8) = monochrome from = monochrome= * = = s-video or = composite = * = = B/W camera = input = * ========================================================= * = other = color, svideo = color, = * = = = composite = * ========================================================= * * Notes: * channels 0-3 on 2255 are composite * channels 0-1 on 2257 are composite, 2-3 are s-video * If COLORFILTER is 0 with a composite color camera connected, * the output will appear monochrome but hatching * will occur. * COLORFILTER is different from "color killer" and "color effects" * for reasons above. */ #define S2255_V4L2_YC_ON 1 #define S2255_V4L2_YC_OFF 0 #define V4L2_CID_S2255_COLORFILTER (V4L2_CID_USER_S2255_BASE + 0) /* frame prefix size (sent once every frame) */ #define PREFIX_SIZE 512 /* Channels on box are in reverse order */ static unsigned long G_chnmap[MAX_CHANNELS] = {3, 2, 1, 0}; static int debug; static int s2255_start_readpipe(struct s2255_dev *dev); static void s2255_stop_readpipe(struct s2255_dev *dev); static int s2255_start_acquire(struct s2255_vc *vc); static int s2255_stop_acquire(struct s2255_vc *vc); static void s2255_fillbuff(struct s2255_vc *vc, struct s2255_buffer *buf, int jpgsize); static int s2255_set_mode(struct s2255_vc *vc, struct s2255_mode *mode); static int s2255_board_shutdown(struct s2255_dev *dev); static void s2255_fwload_start(struct s2255_dev *dev); static void s2255_destroy(struct s2255_dev *dev); static long s2255_vendor_req(struct s2255_dev *dev, unsigned char req, u16 index, u16 value, void *buf, s32 buf_len, int bOut); /* dev_err macro with driver name */ #define S2255_DRIVER_NAME "s2255" #define s2255_dev_err(dev, fmt, arg...) \ dev_err(dev, S2255_DRIVER_NAME " - " fmt, ##arg) #define dprintk(dev, level, fmt, arg...) \ v4l2_dbg(level, debug, &dev->v4l2_dev, fmt, ## arg) static struct usb_driver s2255_driver; /* start video number */ static int video_nr = -1; /* /dev/videoN, -1 for autodetect */ /* Enable jpeg capture. */ static int jpeg_enable = 1; module_param(debug, int, 0644); MODULE_PARM_DESC(debug, "Debug level(0-100) default 0"); module_param(video_nr, int, 0644); MODULE_PARM_DESC(video_nr, "start video minor(-1 default autodetect)"); module_param(jpeg_enable, int, 0644); MODULE_PARM_DESC(jpeg_enable, "Jpeg enable(1-on 0-off) default 1"); /* USB device table */ #define USB_SENSORAY_VID 0x1943 static const struct usb_device_id s2255_table[] = { {USB_DEVICE(USB_SENSORAY_VID, 0x2255)}, {USB_DEVICE(USB_SENSORAY_VID, 0x2257)}, /*same family as 2255*/ { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, s2255_table); #define BUFFER_TIMEOUT msecs_to_jiffies(400) /* image formats. */ /* JPEG formats must be defined last to support jpeg_enable parameter */ static const struct s2255_fmt formats[] = { { .fourcc = V4L2_PIX_FMT_YUYV, .depth = 16 }, { .fourcc = V4L2_PIX_FMT_UYVY, .depth = 16 }, { .fourcc = V4L2_PIX_FMT_YUV422P, .depth = 16 }, { .fourcc = V4L2_PIX_FMT_GREY, .depth = 8 }, { .fourcc = V4L2_PIX_FMT_JPEG, .depth = 24 }, { .fourcc = V4L2_PIX_FMT_MJPEG, .depth = 24 } }; static int norm_maxw(struct s2255_vc *vc) { return (vc->std & V4L2_STD_525_60) ? LINE_SZ_4CIFS_NTSC : LINE_SZ_4CIFS_PAL; } static int norm_maxh(struct s2255_vc *vc) { return (vc->std & V4L2_STD_525_60) ? (NUM_LINES_1CIFS_NTSC * 2) : (NUM_LINES_1CIFS_PAL * 2); } static int norm_minw(struct s2255_vc *vc) { return (vc->std & V4L2_STD_525_60) ? LINE_SZ_1CIFS_NTSC : LINE_SZ_1CIFS_PAL; } static int norm_minh(struct s2255_vc *vc) { return (vc->std & V4L2_STD_525_60) ? (NUM_LINES_1CIFS_NTSC) : (NUM_LINES_1CIFS_PAL); } /* * TODO: fixme: move YUV reordering to hardware * converts 2255 planar format to yuyv or uyvy */ static void planar422p_to_yuv_packed(const unsigned char *in, unsigned char *out, int width, int height, int fmt) { unsigned char *pY; unsigned char *pCb; unsigned char *pCr; unsigned long size = height * width; unsigned int i; pY = (unsigned char *)in; pCr = (unsigned char *)in + height * width; pCb = (unsigned char *)in + height * width + (height * width / 2); for (i = 0; i < size * 2; i += 4) { out[i] = (fmt == V4L2_PIX_FMT_YUYV) ? *pY++ : *pCr++; out[i + 1] = (fmt == V4L2_PIX_FMT_YUYV) ? *pCr++ : *pY++; out[i + 2] = (fmt == V4L2_PIX_FMT_YUYV) ? *pY++ : *pCb++; out[i + 3] = (fmt == V4L2_PIX_FMT_YUYV) ? *pCb++ : *pY++; } return; } static void s2255_reset_dsppower(struct s2255_dev *dev) { s2255_vendor_req(dev, 0x40, 0x0000, 0x0001, NULL, 0, 1); msleep(50); s2255_vendor_req(dev, 0x50, 0x0000, 0x0000, NULL, 0, 1); msleep(600); s2255_vendor_req(dev, 0x10, 0x0000, 0x0000, NULL, 0, 1); return; } /* kickstarts the firmware loading. from probe */ static void s2255_timer(struct timer_list *t) { struct s2255_dev *dev = from_timer(dev, t, timer); struct s2255_fw *data = dev->fw_data; if (usb_submit_urb(data->fw_urb, GFP_ATOMIC) < 0) { pr_err("s2255: can't submit urb\n"); atomic_set(&data->fw_state, S2255_FW_FAILED); /* wake up anything waiting for the firmware */ wake_up(&data->wait_fw); return; } } /* this loads the firmware asynchronously. Originally this was done synchronously in probe. But it is better to load it asynchronously here than block inside the probe function. Blocking inside probe affects boot time. FW loading is triggered by the timer in the probe function */ static void s2255_fwchunk_complete(struct urb *urb) { struct s2255_fw *data = urb->context; struct usb_device *udev = urb->dev; int len; if (urb->status) { dev_err(&udev->dev, "URB failed with status %d\n", urb->status); atomic_set(&data->fw_state, S2255_FW_FAILED); /* wake up anything waiting for the firmware */ wake_up(&data->wait_fw); return; } if (data->fw_urb == NULL) { s2255_dev_err(&udev->dev, "disconnected\n"); atomic_set(&data->fw_state, S2255_FW_FAILED); /* wake up anything waiting for the firmware */ wake_up(&data->wait_fw); return; } #define CHUNK_SIZE 512 /* all USB transfers must be done with continuous kernel memory. can't allocate more than 128k in current linux kernel, so upload the firmware in chunks */ if (data->fw_loaded < data->fw_size) { len = (data->fw_loaded + CHUNK_SIZE) > data->fw_size ? data->fw_size % CHUNK_SIZE : CHUNK_SIZE; if (len < CHUNK_SIZE) memset(data->pfw_data, 0, CHUNK_SIZE); memcpy(data->pfw_data, (char *) data->fw->data + data->fw_loaded, len); usb_fill_bulk_urb(data->fw_urb, udev, usb_sndbulkpipe(udev, 2), data->pfw_data, CHUNK_SIZE, s2255_fwchunk_complete, data); if (usb_submit_urb(data->fw_urb, GFP_ATOMIC) < 0) { dev_err(&udev->dev, "failed submit URB\n"); atomic_set(&data->fw_state, S2255_FW_FAILED); /* wake up anything waiting for the firmware */ wake_up(&data->wait_fw); return; } data->fw_loaded += len; } else atomic_set(&data->fw_state, S2255_FW_LOADED_DSPWAIT); return; } static void s2255_got_frame(struct s2255_vc *vc, int jpgsize) { struct s2255_buffer *buf; struct s2255_dev *dev = to_s2255_dev(vc->vdev.v4l2_dev); unsigned long flags = 0; spin_lock_irqsave(&vc->qlock, flags); if (list_empty(&vc->buf_list)) { dprintk(dev, 1, "No active queue to serve\n"); spin_unlock_irqrestore(&vc->qlock, flags); return; } buf = list_entry(vc->buf_list.next, struct s2255_buffer, list); list_del(&buf->list); buf->vb.vb2_buf.timestamp = ktime_get_ns(); buf->vb.field = vc->field; buf->vb.sequence = vc->frame_count; spin_unlock_irqrestore(&vc->qlock, flags); s2255_fillbuff(vc, buf, jpgsize); /* tell v4l buffer was filled */ vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_DONE); dprintk(dev, 2, "%s: [buf] [%p]\n", __func__, buf); } static const struct s2255_fmt *format_by_fourcc(int fourcc) { unsigned int i; for (i = 0; i < ARRAY_SIZE(formats); i++) { if (-1 == formats[i].fourcc) continue; if (!jpeg_enable && ((formats[i].fourcc == V4L2_PIX_FMT_JPEG) || (formats[i].fourcc == V4L2_PIX_FMT_MJPEG))) continue; if (formats[i].fourcc == fourcc) return formats + i; } return NULL; } /* video buffer vmalloc implementation based partly on VIVI driver which is * Copyright (c) 2006 by * Mauro Carvalho Chehab <mchehab--a.t--infradead.org> * Ted Walther <ted--a.t--enumera.com> * John Sokol <sokol--a.t--videotechnology.com> * http://v4l.videotechnology.com/ * */ static void s2255_fillbuff(struct s2255_vc *vc, struct s2255_buffer *buf, int jpgsize) { int pos = 0; const char *tmpbuf; char *vbuf = vb2_plane_vaddr(&buf->vb.vb2_buf, 0); unsigned long last_frame; struct s2255_dev *dev = vc->dev; if (!vbuf) return; last_frame = vc->last_frame; if (last_frame != -1) { tmpbuf = (const char *)vc->buffer.frame[last_frame].lpvbits; switch (vc->fmt->fourcc) { case V4L2_PIX_FMT_YUYV: case V4L2_PIX_FMT_UYVY: planar422p_to_yuv_packed((const unsigned char *)tmpbuf, vbuf, vc->width, vc->height, vc->fmt->fourcc); break; case V4L2_PIX_FMT_GREY: memcpy(vbuf, tmpbuf, vc->width * vc->height); break; case V4L2_PIX_FMT_JPEG: case V4L2_PIX_FMT_MJPEG: vb2_set_plane_payload(&buf->vb.vb2_buf, 0, jpgsize); memcpy(vbuf, tmpbuf, jpgsize); break; case V4L2_PIX_FMT_YUV422P: memcpy(vbuf, tmpbuf, vc->width * vc->height * 2); break; default: pr_info("s2255: unknown format?\n"); } vc->last_frame = -1; } else { pr_err("s2255: =======no frame\n"); return; } dprintk(dev, 2, "s2255fill at : Buffer %p size= %d\n", vbuf, pos); } /* ------------------------------------------------------------------ Videobuf operations ------------------------------------------------------------------*/ static int queue_setup(struct vb2_queue *vq, unsigned int *nbuffers, unsigned int *nplanes, unsigned int sizes[], struct device *alloc_devs[]) { struct s2255_vc *vc = vb2_get_drv_priv(vq); if (*nbuffers < S2255_MIN_BUFS) *nbuffers = S2255_MIN_BUFS; *nplanes = 1; sizes[0] = vc->width * vc->height * (vc->fmt->depth >> 3); return 0; } static int buffer_prepare(struct vb2_buffer *vb) { struct s2255_vc *vc = vb2_get_drv_priv(vb->vb2_queue); struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb); struct s2255_buffer *buf = container_of(vbuf, struct s2255_buffer, vb); int w = vc->width; int h = vc->height; unsigned long size; dprintk(vc->dev, 4, "%s\n", __func__); if (vc->fmt == NULL) return -EINVAL; if ((w < norm_minw(vc)) || (w > norm_maxw(vc)) || (h < norm_minh(vc)) || (h > norm_maxh(vc))) { dprintk(vc->dev, 4, "invalid buffer prepare\n"); return -EINVAL; } size = w * h * (vc->fmt->depth >> 3); if (vb2_plane_size(vb, 0) < size) { dprintk(vc->dev, 4, "invalid buffer prepare\n"); return -EINVAL; } vb2_set_plane_payload(&buf->vb.vb2_buf, 0, size); return 0; } static void buffer_queue(struct vb2_buffer *vb) { struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb); struct s2255_buffer *buf = container_of(vbuf, struct s2255_buffer, vb); struct s2255_vc *vc = vb2_get_drv_priv(vb->vb2_queue); unsigned long flags = 0; dprintk(vc->dev, 1, "%s\n", __func__); spin_lock_irqsave(&vc->qlock, flags); list_add_tail(&buf->list, &vc->buf_list); spin_unlock_irqrestore(&vc->qlock, flags); } static int start_streaming(struct vb2_queue *vq, unsigned int count); static void stop_streaming(struct vb2_queue *vq); static const struct vb2_ops s2255_video_qops = { .queue_setup = queue_setup, .buf_prepare = buffer_prepare, .buf_queue = buffer_queue, .start_streaming = start_streaming, .stop_streaming = stop_streaming, .wait_prepare = vb2_ops_wait_prepare, .wait_finish = vb2_ops_wait_finish, }; static int vidioc_querycap(struct file *file, void *priv, struct v4l2_capability *cap) { struct s2255_vc *vc = video_drvdata(file); struct s2255_dev *dev = vc->dev; strscpy(cap->driver, "s2255", sizeof(cap->driver)); strscpy(cap->card, "s2255", sizeof(cap->card)); usb_make_path(dev->udev, cap->bus_info, sizeof(cap->bus_info)); return 0; } static int vidioc_enum_fmt_vid_cap(struct file *file, void *priv, struct v4l2_fmtdesc *f) { int index = f->index; if (index >= ARRAY_SIZE(formats)) return -EINVAL; if (!jpeg_enable && ((formats[index].fourcc == V4L2_PIX_FMT_JPEG) || (formats[index].fourcc == V4L2_PIX_FMT_MJPEG))) return -EINVAL; f->pixelformat = formats[index].fourcc; return 0; } static int vidioc_g_fmt_vid_cap(struct file *file, void *priv, struct v4l2_format *f) { struct s2255_vc *vc = video_drvdata(file); int is_ntsc = vc->std & V4L2_STD_525_60; f->fmt.pix.width = vc->width; f->fmt.pix.height = vc->height; if (f->fmt.pix.height >= (is_ntsc ? NUM_LINES_1CIFS_NTSC : NUM_LINES_1CIFS_PAL) * 2) f->fmt.pix.field = V4L2_FIELD_INTERLACED; else f->fmt.pix.field = V4L2_FIELD_TOP; f->fmt.pix.pixelformat = vc->fmt->fourcc; f->fmt.pix.bytesperline = f->fmt.pix.width * (vc->fmt->depth >> 3); f->fmt.pix.sizeimage = f->fmt.pix.height * f->fmt.pix.bytesperline; f->fmt.pix.colorspace = V4L2_COLORSPACE_SMPTE170M; return 0; } static int vidioc_try_fmt_vid_cap(struct file *file, void *priv, struct v4l2_format *f) { const struct s2255_fmt *fmt; enum v4l2_field field; struct s2255_vc *vc = video_drvdata(file); int is_ntsc = vc->std & V4L2_STD_525_60; fmt = format_by_fourcc(f->fmt.pix.pixelformat); if (fmt == NULL) return -EINVAL; dprintk(vc->dev, 50, "%s NTSC: %d suggested width: %d, height: %d\n", __func__, is_ntsc, f->fmt.pix.width, f->fmt.pix.height); if (is_ntsc) { /* NTSC */ if (f->fmt.pix.height >= NUM_LINES_1CIFS_NTSC * 2) { f->fmt.pix.height = NUM_LINES_1CIFS_NTSC * 2; field = V4L2_FIELD_INTERLACED; } else { f->fmt.pix.height = NUM_LINES_1CIFS_NTSC; field = V4L2_FIELD_TOP; } if (f->fmt.pix.width >= LINE_SZ_4CIFS_NTSC) f->fmt.pix.width = LINE_SZ_4CIFS_NTSC; else f->fmt.pix.width = LINE_SZ_1CIFS_NTSC; } else { /* PAL */ if (f->fmt.pix.height >= NUM_LINES_1CIFS_PAL * 2) { f->fmt.pix.height = NUM_LINES_1CIFS_PAL * 2; field = V4L2_FIELD_INTERLACED; } else { f->fmt.pix.height = NUM_LINES_1CIFS_PAL; field = V4L2_FIELD_TOP; } if (f->fmt.pix.width >= LINE_SZ_4CIFS_PAL) f->fmt.pix.width = LINE_SZ_4CIFS_PAL; else f->fmt.pix.width = LINE_SZ_1CIFS_PAL; } f->fmt.pix.field = field; f->fmt.pix.bytesperline = (f->fmt.pix.width * fmt->depth) >> 3; f->fmt.pix.sizeimage = f->fmt.pix.height * f->fmt.pix.bytesperline; f->fmt.pix.colorspace = V4L2_COLORSPACE_SMPTE170M; dprintk(vc->dev, 50, "%s: set width %d height %d field %d\n", __func__, f->fmt.pix.width, f->fmt.pix.height, f->fmt.pix.field); return 0; } static int vidioc_s_fmt_vid_cap(struct file *file, void *priv, struct v4l2_format *f) { struct s2255_vc *vc = video_drvdata(file); const struct s2255_fmt *fmt; struct vb2_queue *q = &vc->vb_vidq; struct s2255_mode mode; int ret; ret = vidioc_try_fmt_vid_cap(file, vc, f); if (ret < 0) return ret; fmt = format_by_fourcc(f->fmt.pix.pixelformat); if (fmt == NULL) return -EINVAL; if (vb2_is_busy(q)) { dprintk(vc->dev, 1, "queue busy\n"); return -EBUSY; } mode = vc->mode; vc->fmt = fmt; vc->width = f->fmt.pix.width; vc->height = f->fmt.pix.height; vc->field = f->fmt.pix.field; if (vc->width > norm_minw(vc)) { if (vc->height > norm_minh(vc)) { if (vc->cap_parm.capturemode & V4L2_MODE_HIGHQUALITY) mode.scale = SCALE_4CIFSI; else mode.scale = SCALE_4CIFS; } else mode.scale = SCALE_2CIFS; } else { mode.scale = SCALE_1CIFS; } /* color mode */ switch (vc->fmt->fourcc) { case V4L2_PIX_FMT_GREY: mode.color &= ~MASK_COLOR; mode.color |= COLOR_Y8; break; case V4L2_PIX_FMT_JPEG: case V4L2_PIX_FMT_MJPEG: mode.color &= ~MASK_COLOR; mode.color |= COLOR_JPG; mode.color |= (vc->jpegqual << 8); break; case V4L2_PIX_FMT_YUV422P: mode.color &= ~MASK_COLOR; mode.color |= COLOR_YUVPL; break; case V4L2_PIX_FMT_YUYV: case V4L2_PIX_FMT_UYVY: default: mode.color &= ~MASK_COLOR; mode.color |= COLOR_YUVPK; break; } if ((mode.color & MASK_COLOR) != (vc->mode.color & MASK_COLOR)) mode.restart = 1; else if (mode.scale != vc->mode.scale) mode.restart = 1; else if (mode.format != vc->mode.format) mode.restart = 1; vc->mode = mode; (void) s2255_set_mode(vc, &mode); return 0; } /* write to the configuration pipe, synchronously */ static int s2255_write_config(struct usb_device *udev, unsigned char *pbuf, int size) { int pipe; int done; long retval = -1; if (udev) { pipe = usb_sndbulkpipe(udev, S2255_CONFIG_EP); retval = usb_bulk_msg(udev, pipe, pbuf, size, &done, 500); } return retval; } static u32 get_transfer_size(struct s2255_mode *mode) { int linesPerFrame = LINE_SZ_DEF; int pixelsPerLine = NUM_LINES_DEF; u32 outImageSize; u32 usbInSize; unsigned int mask_mult; if (mode == NULL) return 0; if (mode->format == FORMAT_NTSC) { switch (mode->scale) { case SCALE_4CIFS: case SCALE_4CIFSI: linesPerFrame = NUM_LINES_4CIFS_NTSC * 2; pixelsPerLine = LINE_SZ_4CIFS_NTSC; break; case SCALE_2CIFS: linesPerFrame = NUM_LINES_2CIFS_NTSC; pixelsPerLine = LINE_SZ_2CIFS_NTSC; break; case SCALE_1CIFS: linesPerFrame = NUM_LINES_1CIFS_NTSC; pixelsPerLine = LINE_SZ_1CIFS_NTSC; break; default: break; } } else if (mode->format == FORMAT_PAL) { switch (mode->scale) { case SCALE_4CIFS: case SCALE_4CIFSI: linesPerFrame = NUM_LINES_4CIFS_PAL * 2; pixelsPerLine = LINE_SZ_4CIFS_PAL; break; case SCALE_2CIFS: linesPerFrame = NUM_LINES_2CIFS_PAL; pixelsPerLine = LINE_SZ_2CIFS_PAL; break; case SCALE_1CIFS: linesPerFrame = NUM_LINES_1CIFS_PAL; pixelsPerLine = LINE_SZ_1CIFS_PAL; break; default: break; } } outImageSize = linesPerFrame * pixelsPerLine; if ((mode->color & MASK_COLOR) != COLOR_Y8) { /* 2 bytes/pixel if not monochrome */ outImageSize *= 2; } /* total bytes to send including prefix and 4K padding; must be a multiple of USB_READ_SIZE */ usbInSize = outImageSize + PREFIX_SIZE; /* always send prefix */ mask_mult = 0xffffffffUL - DEF_USB_BLOCK + 1; /* if size not a multiple of USB_READ_SIZE */ if (usbInSize & ~mask_mult) usbInSize = (usbInSize & mask_mult) + (DEF_USB_BLOCK); return usbInSize; } static void s2255_print_cfg(struct s2255_dev *sdev, struct s2255_mode *mode) { struct device *dev = &sdev->udev->dev; dev_info(dev, "------------------------------------------------\n"); dev_info(dev, "format: %d\nscale %d\n", mode->format, mode->scale); dev_info(dev, "fdec: %d\ncolor %d\n", mode->fdec, mode->color); dev_info(dev, "bright: 0x%x\n", mode->bright); dev_info(dev, "------------------------------------------------\n"); } /* * set mode is the function which controls the DSP. * the restart parameter in struct s2255_mode should be set whenever * the image size could change via color format, video system or image * size. * When the restart parameter is set, we sleep for ONE frame to allow the * DSP time to get the new frame */ static int s2255_set_mode(struct s2255_vc *vc, struct s2255_mode *mode) { int res; unsigned long chn_rev; struct s2255_dev *dev = to_s2255_dev(vc->vdev.v4l2_dev); int i; __le32 *buffer = dev->cmdbuf; mutex_lock(&dev->cmdlock); chn_rev = G_chnmap[vc->idx]; dprintk(dev, 3, "%s channel: %d\n", __func__, vc->idx); /* if JPEG, set the quality */ if ((mode->color & MASK_COLOR) == COLOR_JPG) { mode->color &= ~MASK_COLOR; mode->color |= COLOR_JPG; mode->color &= ~MASK_JPG_QUALITY; mode->color |= (vc->jpegqual << 8); } /* save the mode */ vc->mode = *mode; vc->req_image_size = get_transfer_size(mode); dprintk(dev, 1, "%s: reqsize %ld\n", __func__, vc->req_image_size); /* set the mode */ buffer[0] = IN_DATA_TOKEN; buffer[1] = (__le32) cpu_to_le32(chn_rev); buffer[2] = CMD_SET_MODE; for (i = 0; i < sizeof(struct s2255_mode) / sizeof(u32); i++) buffer[3 + i] = cpu_to_le32(((u32 *)&vc->mode)[i]); vc->setmode_ready = 0; res = s2255_write_config(dev->udev, (unsigned char *)buffer, 512); if (debug) s2255_print_cfg(dev, mode); /* wait at least 3 frames before continuing */ if (mode->restart) { wait_event_timeout(vc->wait_setmode, (vc->setmode_ready != 0), msecs_to_jiffies(S2255_SETMODE_TIMEOUT)); if (vc->setmode_ready != 1) { dprintk(dev, 0, "s2255: no set mode response\n"); res = -EFAULT; } } /* clear the restart flag */ vc->mode.restart = 0; dprintk(dev, 1, "%s chn %d, result: %d\n", __func__, vc->idx, res); mutex_unlock(&dev->cmdlock); return res; } static int s2255_cmd_status(struct s2255_vc *vc, u32 *pstatus) { int res; u32 chn_rev; struct s2255_dev *dev = to_s2255_dev(vc->vdev.v4l2_dev); __le32 *buffer = dev->cmdbuf; mutex_lock(&dev->cmdlock); chn_rev = G_chnmap[vc->idx]; dprintk(dev, 4, "%s chan %d\n", __func__, vc->idx); /* form the get vid status command */ buffer[0] = IN_DATA_TOKEN; buffer[1] = (__le32) cpu_to_le32(chn_rev); buffer[2] = CMD_STATUS; *pstatus = 0; vc->vidstatus_ready = 0; res = s2255_write_config(dev->udev, (unsigned char *)buffer, 512); wait_event_timeout(vc->wait_vidstatus, (vc->vidstatus_ready != 0), msecs_to_jiffies(S2255_VIDSTATUS_TIMEOUT)); if (vc->vidstatus_ready != 1) { dprintk(dev, 0, "s2255: no vidstatus response\n"); res = -EFAULT; } *pstatus = vc->vidstatus; dprintk(dev, 4, "%s, vid status %d\n", __func__, *pstatus); mutex_unlock(&dev->cmdlock); return res; } static int start_streaming(struct vb2_queue *vq, unsigned int count) { struct s2255_vc *vc = vb2_get_drv_priv(vq); int j; vc->last_frame = -1; vc->bad_payload = 0; vc->cur_frame = 0; vc->frame_count = 0; for (j = 0; j < SYS_FRAMES; j++) { vc->buffer.frame[j].ulState = S2255_READ_IDLE; vc->buffer.frame[j].cur_size = 0; } return s2255_start_acquire(vc); } /* abort streaming and wait for last buffer */ static void stop_streaming(struct vb2_queue *vq) { struct s2255_vc *vc = vb2_get_drv_priv(vq); struct s2255_buffer *buf, *node; unsigned long flags; (void) s2255_stop_acquire(vc); spin_lock_irqsave(&vc->qlock, flags); list_for_each_entry_safe(buf, node, &vc->buf_list, list) { list_del(&buf->list); vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_ERROR); dprintk(vc->dev, 2, "[%p/%d] done\n", buf, buf->vb.vb2_buf.index); } spin_unlock_irqrestore(&vc->qlock, flags); } static int vidioc_s_std(struct file *file, void *priv, v4l2_std_id i) { struct s2255_vc *vc = video_drvdata(file); struct s2255_mode mode; struct vb2_queue *q = &vc->vb_vidq; /* * Changing the standard implies a format change, which is not allowed * while buffers for use with streaming have already been allocated. */ if (vb2_is_busy(q)) return -EBUSY; mode = vc->mode; if (i & V4L2_STD_525_60) { dprintk(vc->dev, 4, "%s 60 Hz\n", __func__); /* if changing format, reset frame decimation/intervals */ if (mode.format != FORMAT_NTSC) { mode.restart = 1; mode.format = FORMAT_NTSC; mode.fdec = FDEC_1; vc->width = LINE_SZ_4CIFS_NTSC; vc->height = NUM_LINES_4CIFS_NTSC * 2; } } else if (i & V4L2_STD_625_50) { dprintk(vc->dev, 4, "%s 50 Hz\n", __func__); if (mode.format != FORMAT_PAL) { mode.restart = 1; mode.format = FORMAT_PAL; mode.fdec = FDEC_1; vc->width = LINE_SZ_4CIFS_PAL; vc->height = NUM_LINES_4CIFS_PAL * 2; } } else return -EINVAL; vc->std = i; if (mode.restart) s2255_set_mode(vc, &mode); return 0; } static int vidioc_g_std(struct file *file, void *priv, v4l2_std_id *i) { struct s2255_vc *vc = video_drvdata(file); *i = vc->std; return 0; } /* Sensoray 2255 is a multiple channel capture device. It does not have a "crossbar" of inputs. We use one V4L device per channel. The user must be aware that certain combinations are not allowed. For instance, you cannot do full FPS on more than 2 channels(2 videodevs) at once in color(you can do full fps on 4 channels with greyscale. */ static int vidioc_enum_input(struct file *file, void *priv, struct v4l2_input *inp) { struct s2255_vc *vc = video_drvdata(file); struct s2255_dev *dev = vc->dev; u32 status = 0; if (inp->index != 0) return -EINVAL; inp->type = V4L2_INPUT_TYPE_CAMERA; inp->std = S2255_NORMS; inp->status = 0; if (dev->dsp_fw_ver >= S2255_MIN_DSP_STATUS) { int rc; rc = s2255_cmd_status(vc, &status); dprintk(dev, 4, "s2255_cmd_status rc: %d status %x\n", rc, status); if (rc == 0) inp->status = (status & 0x01) ? 0 : V4L2_IN_ST_NO_SIGNAL; } switch (dev->pid) { case 0x2255: default: strscpy(inp->name, "Composite", sizeof(inp->name)); break; case 0x2257: strscpy(inp->name, (vc->idx < 2) ? "Composite" : "S-Video", sizeof(inp->name)); break; } return 0; } static int vidioc_g_input(struct file *file, void *priv, unsigned int *i) { *i = 0; return 0; } static int vidioc_s_input(struct file *file, void *priv, unsigned int i) { if (i > 0) return -EINVAL; return 0; } static int s2255_s_ctrl(struct v4l2_ctrl *ctrl) { struct s2255_vc *vc = container_of(ctrl->handler, struct s2255_vc, hdl); struct s2255_mode mode; mode = vc->mode; /* update the mode to the corresponding value */ switch (ctrl->id) { case V4L2_CID_BRIGHTNESS: mode.bright = ctrl->val; break; case V4L2_CID_CONTRAST: mode.contrast = ctrl->val; break; case V4L2_CID_HUE: mode.hue = ctrl->val; break; case V4L2_CID_SATURATION: mode.saturation = ctrl->val; break; case V4L2_CID_S2255_COLORFILTER: mode.color &= ~MASK_INPUT_TYPE; mode.color |= !ctrl->val << 16; break; case V4L2_CID_JPEG_COMPRESSION_QUALITY: vc->jpegqual = ctrl->val; return 0; default: return -EINVAL; } mode.restart = 0; /* set mode here. Note: stream does not need restarted. some V4L programs restart stream unnecessarily after a s_crtl. */ s2255_set_mode(vc, &mode); return 0; } static int vidioc_g_jpegcomp(struct file *file, void *priv, struct v4l2_jpegcompression *jc) { struct s2255_vc *vc = video_drvdata(file); memset(jc, 0, sizeof(*jc)); jc->quality = vc->jpegqual; dprintk(vc->dev, 2, "%s: quality %d\n", __func__, jc->quality); return 0; } static int vidioc_s_jpegcomp(struct file *file, void *priv, const struct v4l2_jpegcompression *jc) { struct s2255_vc *vc = video_drvdata(file); if (jc->quality < 0 || jc->quality > 100) return -EINVAL; v4l2_ctrl_s_ctrl(vc->jpegqual_ctrl, jc->quality); dprintk(vc->dev, 2, "%s: quality %d\n", __func__, jc->quality); return 0; } static int vidioc_g_parm(struct file *file, void *priv, struct v4l2_streamparm *sp) { __u32 def_num, def_dem; struct s2255_vc *vc = video_drvdata(file); if (sp->type != V4L2_BUF_TYPE_VIDEO_CAPTURE) return -EINVAL; sp->parm.capture.capability = V4L2_CAP_TIMEPERFRAME; sp->parm.capture.capturemode = vc->cap_parm.capturemode; sp->parm.capture.readbuffers = S2255_MIN_BUFS; def_num = (vc->mode.format == FORMAT_NTSC) ? 1001 : 1000; def_dem = (vc->mode.format == FORMAT_NTSC) ? 30000 : 25000; sp->parm.capture.timeperframe.denominator = def_dem; switch (vc->mode.fdec) { default: case FDEC_1: sp->parm.capture.timeperframe.numerator = def_num; break; case FDEC_2: sp->parm.capture.timeperframe.numerator = def_num * 2; break; case FDEC_3: sp->parm.capture.timeperframe.numerator = def_num * 3; break; case FDEC_5: sp->parm.capture.timeperframe.numerator = def_num * 5; break; } dprintk(vc->dev, 4, "%s capture mode, %d timeperframe %d/%d\n", __func__, sp->parm.capture.capturemode, sp->parm.capture.timeperframe.numerator, sp->parm.capture.timeperframe.denominator); return 0; } static int vidioc_s_parm(struct file *file, void *priv, struct v4l2_streamparm *sp) { struct s2255_vc *vc = video_drvdata(file); struct s2255_mode mode; int fdec = FDEC_1; __u32 def_num, def_dem; if (sp->type != V4L2_BUF_TYPE_VIDEO_CAPTURE) return -EINVAL; mode = vc->mode; /* high quality capture mode requires a stream restart */ if ((vc->cap_parm.capturemode != sp->parm.capture.capturemode) && vb2_is_streaming(&vc->vb_vidq)) return -EBUSY; def_num = (mode.format == FORMAT_NTSC) ? 1001 : 1000; def_dem = (mode.format == FORMAT_NTSC) ? 30000 : 25000; if (def_dem != sp->parm.capture.timeperframe.denominator) sp->parm.capture.timeperframe.numerator = def_num; else if (sp->parm.capture.timeperframe.numerator <= def_num) sp->parm.capture.timeperframe.numerator = def_num; else if (sp->parm.capture.timeperframe.numerator <= (def_num * 2)) { sp->parm.capture.timeperframe.numerator = def_num * 2; fdec = FDEC_2; } else if (sp->parm.capture.timeperframe.numerator <= (def_num * 3)) { sp->parm.capture.timeperframe.numerator = def_num * 3; fdec = FDEC_3; } else { sp->parm.capture.timeperframe.numerator = def_num * 5; fdec = FDEC_5; } mode.fdec = fdec; sp->parm.capture.timeperframe.denominator = def_dem; sp->parm.capture.readbuffers = S2255_MIN_BUFS; s2255_set_mode(vc, &mode); dprintk(vc->dev, 4, "%s capture mode, %d timeperframe %d/%d, fdec %d\n", __func__, sp->parm.capture.capturemode, sp->parm.capture.timeperframe.numerator, sp->parm.capture.timeperframe.denominator, fdec); return 0; } #define NUM_SIZE_ENUMS 3 static const struct v4l2_frmsize_discrete ntsc_sizes[] = { { 640, 480 }, { 640, 240 }, { 320, 240 }, }; static const struct v4l2_frmsize_discrete pal_sizes[] = { { 704, 576 }, { 704, 288 }, { 352, 288 }, }; static int vidioc_enum_framesizes(struct file *file, void *priv, struct v4l2_frmsizeenum *fe) { struct s2255_vc *vc = video_drvdata(file); int is_ntsc = vc->std & V4L2_STD_525_60; const struct s2255_fmt *fmt; if (fe->index >= NUM_SIZE_ENUMS) return -EINVAL; fmt = format_by_fourcc(fe->pixel_format); if (fmt == NULL) return -EINVAL; fe->type = V4L2_FRMSIZE_TYPE_DISCRETE; fe->discrete = is_ntsc ? ntsc_sizes[fe->index] : pal_sizes[fe->index]; return 0; } static int vidioc_enum_frameintervals(struct file *file, void *priv, struct v4l2_frmivalenum *fe) { struct s2255_vc *vc = video_drvdata(file); const struct s2255_fmt *fmt; const struct v4l2_frmsize_discrete *sizes; int is_ntsc = vc->std & V4L2_STD_525_60; #define NUM_FRAME_ENUMS 4 int frm_dec[NUM_FRAME_ENUMS] = {1, 2, 3, 5}; int i; if (fe->index >= NUM_FRAME_ENUMS) return -EINVAL; fmt = format_by_fourcc(fe->pixel_format); if (fmt == NULL) return -EINVAL; sizes = is_ntsc ? ntsc_sizes : pal_sizes; for (i = 0; i < NUM_SIZE_ENUMS; i++, sizes++) if (fe->width == sizes->width && fe->height == sizes->height) break; if (i == NUM_SIZE_ENUMS) return -EINVAL; fe->type = V4L2_FRMIVAL_TYPE_DISCRETE; fe->discrete.denominator = is_ntsc ? 30000 : 25000; fe->discrete.numerator = (is_ntsc ? 1001 : 1000) * frm_dec[fe->index]; dprintk(vc->dev, 4, "%s discrete %d/%d\n", __func__, fe->discrete.numerator, fe->discrete.denominator); return 0; } static int s2255_open(struct file *file) { struct s2255_vc *vc = video_drvdata(file); struct s2255_dev *dev = vc->dev; int state; int rc = 0; rc = v4l2_fh_open(file); if (rc != 0) return rc; dprintk(dev, 1, "s2255: %s\n", __func__); state = atomic_read(&dev->fw_data->fw_state); switch (state) { case S2255_FW_DISCONNECTING: return -ENODEV; case S2255_FW_FAILED: s2255_dev_err(&dev->udev->dev, "firmware load failed. retrying.\n"); s2255_fwload_start(dev); wait_event_timeout(dev->fw_data->wait_fw, ((atomic_read(&dev->fw_data->fw_state) == S2255_FW_SUCCESS) || (atomic_read(&dev->fw_data->fw_state) == S2255_FW_DISCONNECTING)), msecs_to_jiffies(S2255_LOAD_TIMEOUT)); /* state may have changed, re-read */ state = atomic_read(&dev->fw_data->fw_state); break; case S2255_FW_NOTLOADED: case S2255_FW_LOADED_DSPWAIT: /* give S2255_LOAD_TIMEOUT time for firmware to load in case driver loaded and then device immediately opened */ pr_info("%s waiting for firmware load\n", __func__); wait_event_timeout(dev->fw_data->wait_fw, ((atomic_read(&dev->fw_data->fw_state) == S2255_FW_SUCCESS) || (atomic_read(&dev->fw_data->fw_state) == S2255_FW_DISCONNECTING)), msecs_to_jiffies(S2255_LOAD_TIMEOUT)); /* state may have changed, re-read */ state = atomic_read(&dev->fw_data->fw_state); break; case S2255_FW_SUCCESS: default: break; } /* state may have changed in above switch statement */ switch (state) { case S2255_FW_SUCCESS: break; case S2255_FW_FAILED: pr_info("2255 firmware load failed.\n"); return -ENODEV; case S2255_FW_DISCONNECTING: pr_info("%s: disconnecting\n", __func__); return -ENODEV; case S2255_FW_LOADED_DSPWAIT: case S2255_FW_NOTLOADED: pr_info("%s: firmware not loaded, please retry\n", __func__); /* * Timeout on firmware load means device unusable. * Set firmware failure state. * On next s2255_open the firmware will be reloaded. */ atomic_set(&dev->fw_data->fw_state, S2255_FW_FAILED); return -EAGAIN; default: pr_info("%s: unknown state\n", __func__); return -EFAULT; } if (!vc->configured) { /* configure channel to default state */ vc->fmt = &formats[0]; s2255_set_mode(vc, &vc->mode); vc->configured = 1; } return 0; } static void s2255_destroy(struct s2255_dev *dev) { dprintk(dev, 1, "%s", __func__); /* board shutdown stops the read pipe if it is running */ s2255_board_shutdown(dev); /* make sure firmware still not trying to load */ timer_shutdown_sync(&dev->timer); /* only started in .probe and .open */ if (dev->fw_data->fw_urb) { usb_kill_urb(dev->fw_data->fw_urb); usb_free_urb(dev->fw_data->fw_urb); dev->fw_data->fw_urb = NULL; } release_firmware(dev->fw_data->fw); kfree(dev->fw_data->pfw_data); kfree(dev->fw_data); /* reset the DSP so firmware can be reloaded next time */ s2255_reset_dsppower(dev); mutex_destroy(&dev->lock); usb_put_dev(dev->udev); v4l2_device_unregister(&dev->v4l2_dev); kfree(dev->cmdbuf); kfree(dev); } static const struct v4l2_file_operations s2255_fops_v4l = { .owner = THIS_MODULE, .open = s2255_open, .release = vb2_fop_release, .poll = vb2_fop_poll, .unlocked_ioctl = video_ioctl2, /* V4L2 ioctl handler */ .mmap = vb2_fop_mmap, .read = vb2_fop_read, }; static const struct v4l2_ioctl_ops s2255_ioctl_ops = { .vidioc_querycap = vidioc_querycap, .vidioc_enum_fmt_vid_cap = vidioc_enum_fmt_vid_cap, .vidioc_g_fmt_vid_cap = vidioc_g_fmt_vid_cap, .vidioc_try_fmt_vid_cap = vidioc_try_fmt_vid_cap, .vidioc_s_fmt_vid_cap = vidioc_s_fmt_vid_cap, .vidioc_reqbufs = vb2_ioctl_reqbufs, .vidioc_querybuf = vb2_ioctl_querybuf, .vidioc_qbuf = vb2_ioctl_qbuf, .vidioc_dqbuf = vb2_ioctl_dqbuf, .vidioc_s_std = vidioc_s_std, .vidioc_g_std = vidioc_g_std, .vidioc_enum_input = vidioc_enum_input, .vidioc_g_input = vidioc_g_input, .vidioc_s_input = vidioc_s_input, .vidioc_streamon = vb2_ioctl_streamon, .vidioc_streamoff = vb2_ioctl_streamoff, .vidioc_s_jpegcomp = vidioc_s_jpegcomp, .vidioc_g_jpegcomp = vidioc_g_jpegcomp, .vidioc_s_parm = vidioc_s_parm, .vidioc_g_parm = vidioc_g_parm, .vidioc_enum_framesizes = vidioc_enum_framesizes, .vidioc_enum_frameintervals = vidioc_enum_frameintervals, .vidioc_log_status = v4l2_ctrl_log_status, .vidioc_subscribe_event = v4l2_ctrl_subscribe_event, .vidioc_unsubscribe_event = v4l2_event_unsubscribe, }; static void s2255_video_device_release(struct video_device *vdev) { struct s2255_dev *dev = to_s2255_dev(vdev->v4l2_dev); struct s2255_vc *vc = container_of(vdev, struct s2255_vc, vdev); dprintk(dev, 4, "%s, chnls: %d\n", __func__, refcount_read(&dev->num_channels)); v4l2_ctrl_handler_free(&vc->hdl); if (refcount_dec_and_test(&dev->num_channels)) s2255_destroy(dev); return; } static const struct video_device template = { .name = "s2255v", .fops = &s2255_fops_v4l, .ioctl_ops = &s2255_ioctl_ops, .release = s2255_video_device_release, .tvnorms = S2255_NORMS, }; static const struct v4l2_ctrl_ops s2255_ctrl_ops = { .s_ctrl = s2255_s_ctrl, }; static const struct v4l2_ctrl_config color_filter_ctrl = { .ops = &s2255_ctrl_ops, .name = "Color Filter", .id = V4L2_CID_S2255_COLORFILTER, .type = V4L2_CTRL_TYPE_BOOLEAN, .max = 1, .step = 1, .def = 1, }; static int s2255_probe_v4l(struct s2255_dev *dev) { int ret; int i; int cur_nr = video_nr; struct s2255_vc *vc; struct vb2_queue *q; ret = v4l2_device_register(&dev->interface->dev, &dev->v4l2_dev); if (ret) return ret; /* initialize all video 4 linux */ /* register 4 video devices */ for (i = 0; i < MAX_CHANNELS; i++) { vc = &dev->vc[i]; INIT_LIST_HEAD(&vc->buf_list); v4l2_ctrl_handler_init(&vc->hdl, 6); v4l2_ctrl_new_std(&vc->hdl, &s2255_ctrl_ops, V4L2_CID_BRIGHTNESS, -127, 127, 1, DEF_BRIGHT); v4l2_ctrl_new_std(&vc->hdl, &s2255_ctrl_ops, V4L2_CID_CONTRAST, 0, 255, 1, DEF_CONTRAST); v4l2_ctrl_new_std(&vc->hdl, &s2255_ctrl_ops, V4L2_CID_SATURATION, 0, 255, 1, DEF_SATURATION); v4l2_ctrl_new_std(&vc->hdl, &s2255_ctrl_ops, V4L2_CID_HUE, 0, 255, 1, DEF_HUE); vc->jpegqual_ctrl = v4l2_ctrl_new_std(&vc->hdl, &s2255_ctrl_ops, V4L2_CID_JPEG_COMPRESSION_QUALITY, 0, 100, 1, S2255_DEF_JPEG_QUAL); if (dev->dsp_fw_ver >= S2255_MIN_DSP_COLORFILTER && (dev->pid != 0x2257 || vc->idx <= 1)) v4l2_ctrl_new_custom(&vc->hdl, &color_filter_ctrl, NULL); if (vc->hdl.error) { ret = vc->hdl.error; v4l2_ctrl_handler_free(&vc->hdl); dev_err(&dev->udev->dev, "couldn't register control\n"); break; } q = &vc->vb_vidq; q->type = V4L2_BUF_TYPE_VIDEO_CAPTURE; q->io_modes = VB2_MMAP | VB2_READ | VB2_USERPTR; q->drv_priv = vc; q->lock = &vc->vb_lock; q->buf_struct_size = sizeof(struct s2255_buffer); q->mem_ops = &vb2_vmalloc_memops; q->ops = &s2255_video_qops; q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC; ret = vb2_queue_init(q); if (ret != 0) { dev_err(&dev->udev->dev, "%s vb2_queue_init 0x%x\n", __func__, ret); break; } /* register video devices */ vc->vdev = template; vc->vdev.queue = q; vc->vdev.ctrl_handler = &vc->hdl; vc->vdev.lock = &dev->lock; vc->vdev.v4l2_dev = &dev->v4l2_dev; vc->vdev.device_caps = V4L2_CAP_VIDEO_CAPTURE | V4L2_CAP_STREAMING | V4L2_CAP_READWRITE; video_set_drvdata(&vc->vdev, vc); if (video_nr == -1) ret = video_register_device(&vc->vdev, VFL_TYPE_VIDEO, video_nr); else ret = video_register_device(&vc->vdev, VFL_TYPE_VIDEO, cur_nr + i); if (ret) { dev_err(&dev->udev->dev, "failed to register video device!\n"); break; } refcount_inc(&dev->num_channels); v4l2_info(&dev->v4l2_dev, "V4L2 device registered as %s\n", video_device_node_name(&vc->vdev)); } pr_info("Sensoray 2255 V4L driver Revision: %s\n", S2255_VERSION); /* if no channels registered, return error and probe will fail*/ if (refcount_read(&dev->num_channels) == 0) { v4l2_device_unregister(&dev->v4l2_dev); return ret; } if (refcount_read(&dev->num_channels) != MAX_CHANNELS) pr_warn("s2255: Not all channels available.\n"); return 0; } /* this function moves the usb stream read pipe data * into the system buffers. * returns 0 on success, EAGAIN if more data to process( call this * function again). * * Received frame structure: * bytes 0-3: marker : 0x2255DA4AL (S2255_MARKER_FRAME) * bytes 4-7: channel: 0-3 * bytes 8-11: payload size: size of the frame * bytes 12-payloadsize+12: frame data */ static int save_frame(struct s2255_dev *dev, struct s2255_pipeinfo *pipe_info) { char *pdest; u32 offset = 0; int bframe = 0; char *psrc; unsigned long copy_size; unsigned long size; s32 idx = -1; struct s2255_framei *frm; unsigned char *pdata; struct s2255_vc *vc; dprintk(dev, 100, "buffer to user\n"); vc = &dev->vc[dev->cc]; idx = vc->cur_frame; frm = &vc->buffer.frame[idx]; if (frm->ulState == S2255_READ_IDLE) { int jj; unsigned int cc; __le32 *pdword; /*data from dsp is little endian */ int payload; /* search for marker codes */ pdata = (unsigned char *)pipe_info->transfer_buffer; pdword = (__le32 *)pdata; for (jj = 0; jj < (pipe_info->cur_transfer_size - 12); jj++) { switch (*pdword) { case S2255_MARKER_FRAME: dprintk(dev, 4, "marker @ offset: %d [%x %x]\n", jj, pdata[0], pdata[1]); offset = jj + PREFIX_SIZE; bframe = 1; cc = le32_to_cpu(pdword[1]); if (cc >= MAX_CHANNELS) { dprintk(dev, 0, "bad channel\n"); return -EINVAL; } /* reverse it */ dev->cc = G_chnmap[cc]; vc = &dev->vc[dev->cc]; payload = le32_to_cpu(pdword[3]); if (payload > vc->req_image_size) { vc->bad_payload++; /* discard the bad frame */ return -EINVAL; } vc->pkt_size = payload; vc->jpg_size = le32_to_cpu(pdword[4]); break; case S2255_MARKER_RESPONSE: pdata += DEF_USB_BLOCK; jj += DEF_USB_BLOCK; if (le32_to_cpu(pdword[1]) >= MAX_CHANNELS) break; cc = G_chnmap[le32_to_cpu(pdword[1])]; if (cc >= MAX_CHANNELS) break; vc = &dev->vc[cc]; switch (pdword[2]) { case S2255_RESPONSE_SETMODE: /* check if channel valid */ /* set mode ready */ vc->setmode_ready = 1; wake_up(&vc->wait_setmode); dprintk(dev, 5, "setmode rdy %d\n", cc); break; case S2255_RESPONSE_FW: dev->chn_ready |= (1 << cc); if ((dev->chn_ready & 0x0f) != 0x0f) break; /* all channels ready */ pr_info("s2255: fw loaded\n"); atomic_set(&dev->fw_data->fw_state, S2255_FW_SUCCESS); wake_up(&dev->fw_data->wait_fw); break; case S2255_RESPONSE_STATUS: vc->vidstatus = le32_to_cpu(pdword[3]); vc->vidstatus_ready = 1; wake_up(&vc->wait_vidstatus); dprintk(dev, 5, "vstat %x chan %d\n", le32_to_cpu(pdword[3]), cc); break; default: pr_info("s2255 unknown resp\n"); } pdata++; break; default: pdata++; break; } if (bframe) break; } /* for */ if (!bframe) return -EINVAL; } vc = &dev->vc[dev->cc]; idx = vc->cur_frame; frm = &vc->buffer.frame[idx]; /* search done. now find out if should be acquiring on this channel */ if (!vb2_is_streaming(&vc->vb_vidq)) { /* we found a frame, but this channel is turned off */ frm->ulState = S2255_READ_IDLE; return -EINVAL; } if (frm->ulState == S2255_READ_IDLE) { frm->ulState = S2255_READ_FRAME; frm->cur_size = 0; } /* skip the marker 512 bytes (and offset if out of sync) */ psrc = (u8 *)pipe_info->transfer_buffer + offset; if (frm->lpvbits == NULL) { dprintk(dev, 1, "s2255 frame buffer == NULL.%p %p %d %d", frm, dev, dev->cc, idx); return -ENOMEM; } pdest = frm->lpvbits + frm->cur_size; copy_size = (pipe_info->cur_transfer_size - offset); size = vc->pkt_size - PREFIX_SIZE; /* sanity check on pdest */ if ((copy_size + frm->cur_size) < vc->req_image_size) memcpy(pdest, psrc, copy_size); frm->cur_size += copy_size; dprintk(dev, 4, "cur_size: %lu, size: %lu\n", frm->cur_size, size); if (frm->cur_size >= size) { dprintk(dev, 2, "******[%d]Buffer[%d]full*******\n", dev->cc, idx); vc->last_frame = vc->cur_frame; vc->cur_frame++; /* end of system frame ring buffer, start at zero */ if ((vc->cur_frame == SYS_FRAMES) || (vc->cur_frame == vc->buffer.dwFrames)) vc->cur_frame = 0; /* frame ready */ if (vb2_is_streaming(&vc->vb_vidq)) s2255_got_frame(vc, vc->jpg_size); vc->frame_count++; frm->ulState = S2255_READ_IDLE; frm->cur_size = 0; } /* done successfully */ return 0; } static void s2255_read_video_callback(struct s2255_dev *dev, struct s2255_pipeinfo *pipe_info) { int res; dprintk(dev, 50, "callback read video\n"); if (dev->cc >= MAX_CHANNELS) { dev->cc = 0; dev_err(&dev->udev->dev, "invalid channel\n"); return; } /* otherwise copy to the system buffers */ res = save_frame(dev, pipe_info); if (res != 0) dprintk(dev, 4, "s2255: read callback failed\n"); dprintk(dev, 50, "callback read video done\n"); return; } static long s2255_vendor_req(struct s2255_dev *dev, unsigned char Request, u16 Index, u16 Value, void *TransferBuffer, s32 TransferBufferLength, int bOut) { int r; unsigned char *buf; buf = kmalloc(TransferBufferLength, GFP_KERNEL); if (!buf) return -ENOMEM; if (!bOut) { r = usb_control_msg(dev->udev, usb_rcvctrlpipe(dev->udev, 0), Request, USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_IN, Value, Index, buf, TransferBufferLength, USB_CTRL_SET_TIMEOUT); if (r >= 0) memcpy(TransferBuffer, buf, TransferBufferLength); } else { memcpy(buf, TransferBuffer, TransferBufferLength); r = usb_control_msg(dev->udev, usb_sndctrlpipe(dev->udev, 0), Request, USB_TYPE_VENDOR | USB_RECIP_DEVICE, Value, Index, buf, TransferBufferLength, USB_CTRL_SET_TIMEOUT); } kfree(buf); return r; } /* * retrieve FX2 firmware version. future use. * @param dev pointer to device extension * @return -1 for fail, else returns firmware version as an int(16 bits) */ static int s2255_get_fx2fw(struct s2255_dev *dev) { int fw; int ret; u8 transBuffer[2] = {}; ret = s2255_vendor_req(dev, S2255_VR_FW, 0, 0, transBuffer, sizeof(transBuffer), S2255_VR_IN); if (ret < 0) dprintk(dev, 2, "get fw error: %x\n", ret); fw = transBuffer[0] + (transBuffer[1] << 8); dprintk(dev, 2, "Get FW %x %x\n", transBuffer[0], transBuffer[1]); return fw; } /* * Create the system ring buffer to copy frames into from the * usb read pipe. */ static int s2255_create_sys_buffers(struct s2255_vc *vc) { unsigned long i; unsigned long reqsize; vc->buffer.dwFrames = SYS_FRAMES; /* always allocate maximum size(PAL) for system buffers */ reqsize = SYS_FRAMES_MAXSIZE; if (reqsize > SYS_FRAMES_MAXSIZE) reqsize = SYS_FRAMES_MAXSIZE; for (i = 0; i < SYS_FRAMES; i++) { /* allocate the frames */ vc->buffer.frame[i].lpvbits = vmalloc(reqsize); vc->buffer.frame[i].size = reqsize; if (vc->buffer.frame[i].lpvbits == NULL) { pr_info("out of memory. using less frames\n"); vc->buffer.dwFrames = i; break; } } /* make sure internal states are set */ for (i = 0; i < SYS_FRAMES; i++) { vc->buffer.frame[i].ulState = 0; vc->buffer.frame[i].cur_size = 0; } vc->cur_frame = 0; vc->last_frame = -1; return 0; } static int s2255_release_sys_buffers(struct s2255_vc *vc) { unsigned long i; for (i = 0; i < SYS_FRAMES; i++) { vfree(vc->buffer.frame[i].lpvbits); vc->buffer.frame[i].lpvbits = NULL; } return 0; } static int s2255_board_init(struct s2255_dev *dev) { struct s2255_mode mode_def = DEF_MODEI_NTSC_CONT; int fw_ver; int j; struct s2255_pipeinfo *pipe = &dev->pipe; dprintk(dev, 4, "board init: %p", dev); memset(pipe, 0, sizeof(*pipe)); pipe->dev = dev; pipe->cur_transfer_size = S2255_USB_XFER_SIZE; pipe->max_transfer_size = S2255_USB_XFER_SIZE; pipe->transfer_buffer = kzalloc(pipe->max_transfer_size, GFP_KERNEL); if (pipe->transfer_buffer == NULL) { dprintk(dev, 1, "out of memory!\n"); return -ENOMEM; } /* query the firmware */ fw_ver = s2255_get_fx2fw(dev); pr_info("s2255: usb firmware version %d.%d\n", (fw_ver >> 8) & 0xff, fw_ver & 0xff); if (fw_ver < S2255_CUR_USB_FWVER) pr_info("s2255: newer USB firmware available\n"); for (j = 0; j < MAX_CHANNELS; j++) { struct s2255_vc *vc = &dev->vc[j]; vc->mode = mode_def; if (dev->pid == 0x2257 && j > 1) vc->mode.color |= (1 << 16); vc->jpegqual = S2255_DEF_JPEG_QUAL; vc->width = LINE_SZ_4CIFS_NTSC; vc->height = NUM_LINES_4CIFS_NTSC * 2; vc->std = V4L2_STD_NTSC_M; vc->fmt = &formats[0]; vc->mode.restart = 1; vc->req_image_size = get_transfer_size(&mode_def); vc->frame_count = 0; /* create the system buffers */ s2255_create_sys_buffers(vc); } /* start read pipe */ s2255_start_readpipe(dev); dprintk(dev, 1, "%s: success\n", __func__); return 0; } static int s2255_board_shutdown(struct s2255_dev *dev) { u32 i; dprintk(dev, 1, "%s: dev: %p", __func__, dev); for (i = 0; i < MAX_CHANNELS; i++) { if (vb2_is_streaming(&dev->vc[i].vb_vidq)) s2255_stop_acquire(&dev->vc[i]); } s2255_stop_readpipe(dev); for (i = 0; i < MAX_CHANNELS; i++) s2255_release_sys_buffers(&dev->vc[i]); /* release transfer buffer */ kfree(dev->pipe.transfer_buffer); return 0; } static void read_pipe_completion(struct urb *purb) { struct s2255_pipeinfo *pipe_info; struct s2255_dev *dev; int status; int pipe; pipe_info = purb->context; if (pipe_info == NULL) { dev_err(&purb->dev->dev, "no context!\n"); return; } dev = pipe_info->dev; if (dev == NULL) { dev_err(&purb->dev->dev, "no context!\n"); return; } status = purb->status; /* if shutting down, do not resubmit, exit immediately */ if (status == -ESHUTDOWN) { dprintk(dev, 2, "%s: err shutdown\n", __func__); pipe_info->err_count++; return; } if (pipe_info->state == 0) { dprintk(dev, 2, "%s: exiting USB pipe", __func__); return; } if (status == 0) s2255_read_video_callback(dev, pipe_info); else { pipe_info->err_count++; dprintk(dev, 1, "%s: failed URB %d\n", __func__, status); } pipe = usb_rcvbulkpipe(dev->udev, dev->read_endpoint); /* reuse urb */ usb_fill_bulk_urb(pipe_info->stream_urb, dev->udev, pipe, pipe_info->transfer_buffer, pipe_info->cur_transfer_size, read_pipe_completion, pipe_info); if (pipe_info->state != 0) { if (usb_submit_urb(pipe_info->stream_urb, GFP_ATOMIC)) dev_err(&dev->udev->dev, "error submitting urb\n"); } else { dprintk(dev, 2, "%s :complete state 0\n", __func__); } return; } static int s2255_start_readpipe(struct s2255_dev *dev) { int pipe; int retval; struct s2255_pipeinfo *pipe_info = &dev->pipe; pipe = usb_rcvbulkpipe(dev->udev, dev->read_endpoint); dprintk(dev, 2, "%s: IN %d\n", __func__, dev->read_endpoint); pipe_info->state = 1; pipe_info->err_count = 0; pipe_info->stream_urb = usb_alloc_urb(0, GFP_KERNEL); if (!pipe_info->stream_urb) return -ENOMEM; /* transfer buffer allocated in board_init */ usb_fill_bulk_urb(pipe_info->stream_urb, dev->udev, pipe, pipe_info->transfer_buffer, pipe_info->cur_transfer_size, read_pipe_completion, pipe_info); retval = usb_submit_urb(pipe_info->stream_urb, GFP_KERNEL); if (retval) { pr_err("s2255: start read pipe failed\n"); return retval; } return 0; } /* starts acquisition process */ static int s2255_start_acquire(struct s2255_vc *vc) { int res; unsigned long chn_rev; int j; struct s2255_dev *dev = to_s2255_dev(vc->vdev.v4l2_dev); __le32 *buffer = dev->cmdbuf; mutex_lock(&dev->cmdlock); chn_rev = G_chnmap[vc->idx]; vc->last_frame = -1; vc->bad_payload = 0; vc->cur_frame = 0; for (j = 0; j < SYS_FRAMES; j++) { vc->buffer.frame[j].ulState = 0; vc->buffer.frame[j].cur_size = 0; } /* send the start command */ buffer[0] = IN_DATA_TOKEN; buffer[1] = (__le32) cpu_to_le32(chn_rev); buffer[2] = CMD_START; res = s2255_write_config(dev->udev, (unsigned char *)buffer, 512); if (res != 0) dev_err(&dev->udev->dev, "CMD_START error\n"); dprintk(dev, 2, "start acquire exit[%d] %d\n", vc->idx, res); mutex_unlock(&dev->cmdlock); return res; } static int s2255_stop_acquire(struct s2255_vc *vc) { int res; unsigned long chn_rev; struct s2255_dev *dev = to_s2255_dev(vc->vdev.v4l2_dev); __le32 *buffer = dev->cmdbuf; mutex_lock(&dev->cmdlock); chn_rev = G_chnmap[vc->idx]; /* send the stop command */ buffer[0] = IN_DATA_TOKEN; buffer[1] = (__le32) cpu_to_le32(chn_rev); buffer[2] = CMD_STOP; res = s2255_write_config(dev->udev, (unsigned char *)buffer, 512); if (res != 0) dev_err(&dev->udev->dev, "CMD_STOP error\n"); dprintk(dev, 4, "%s: chn %d, res %d\n", __func__, vc->idx, res); mutex_unlock(&dev->cmdlock); return res; } static void s2255_stop_readpipe(struct s2255_dev *dev) { struct s2255_pipeinfo *pipe = &dev->pipe; pipe->state = 0; if (pipe->stream_urb) { /* cancel urb */ usb_kill_urb(pipe->stream_urb); usb_free_urb(pipe->stream_urb); pipe->stream_urb = NULL; } dprintk(dev, 4, "%s", __func__); return; } static void s2255_fwload_start(struct s2255_dev *dev) { s2255_reset_dsppower(dev); dev->fw_data->fw_size = dev->fw_data->fw->size; atomic_set(&dev->fw_data->fw_state, S2255_FW_NOTLOADED); memcpy(dev->fw_data->pfw_data, dev->fw_data->fw->data, CHUNK_SIZE); dev->fw_data->fw_loaded = CHUNK_SIZE; usb_fill_bulk_urb(dev->fw_data->fw_urb, dev->udev, usb_sndbulkpipe(dev->udev, 2), dev->fw_data->pfw_data, CHUNK_SIZE, s2255_fwchunk_complete, dev->fw_data); mod_timer(&dev->timer, jiffies + HZ); } /* standard usb probe function */ static int s2255_probe(struct usb_interface *interface, const struct usb_device_id *id) { struct s2255_dev *dev = NULL; struct usb_host_interface *iface_desc; struct usb_endpoint_descriptor *endpoint; int i; int retval = -ENOMEM; __le32 *pdata; int fw_size; /* allocate memory for our device state and initialize it to zero */ dev = kzalloc(sizeof(struct s2255_dev), GFP_KERNEL); if (dev == NULL) { s2255_dev_err(&interface->dev, "out of memory\n"); return -ENOMEM; } dev->cmdbuf = kzalloc(S2255_CMDBUF_SIZE, GFP_KERNEL); if (dev->cmdbuf == NULL) { s2255_dev_err(&interface->dev, "out of memory\n"); goto errorFWDATA1; } refcount_set(&dev->num_channels, 0); dev->pid = id->idProduct; dev->fw_data = kzalloc(sizeof(struct s2255_fw), GFP_KERNEL); if (!dev->fw_data) goto errorFWDATA1; mutex_init(&dev->lock); mutex_init(&dev->cmdlock); /* grab usb_device and save it */ dev->udev = usb_get_dev(interface_to_usbdev(interface)); if (dev->udev == NULL) { dev_err(&interface->dev, "null usb device\n"); retval = -ENODEV; goto errorUDEV; } dev_dbg(&interface->dev, "dev: %p, udev %p interface %p\n", dev, dev->udev, interface); dev->interface = interface; /* set up the endpoint information */ iface_desc = interface->cur_altsetting; dev_dbg(&interface->dev, "num EP: %d\n", iface_desc->desc.bNumEndpoints); for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) { endpoint = &iface_desc->endpoint[i].desc; if (!dev->read_endpoint && usb_endpoint_is_bulk_in(endpoint)) { /* we found the bulk in endpoint */ dev->read_endpoint = endpoint->bEndpointAddress; } } if (!dev->read_endpoint) { dev_err(&interface->dev, "Could not find bulk-in endpoint\n"); goto errorEP; } timer_setup(&dev->timer, s2255_timer, 0); init_waitqueue_head(&dev->fw_data->wait_fw); for (i = 0; i < MAX_CHANNELS; i++) { struct s2255_vc *vc = &dev->vc[i]; vc->idx = i; vc->dev = dev; init_waitqueue_head(&vc->wait_setmode); init_waitqueue_head(&vc->wait_vidstatus); spin_lock_init(&vc->qlock); mutex_init(&vc->vb_lock); } dev->fw_data->fw_urb = usb_alloc_urb(0, GFP_KERNEL); if (!dev->fw_data->fw_urb) goto errorFWURB; dev->fw_data->pfw_data = kzalloc(CHUNK_SIZE, GFP_KERNEL); if (!dev->fw_data->pfw_data) { dev_err(&interface->dev, "out of memory!\n"); goto errorFWDATA2; } /* load the first chunk */ if (request_firmware(&dev->fw_data->fw, FIRMWARE_FILE_NAME, &dev->udev->dev)) { dev_err(&interface->dev, "sensoray 2255 failed to get firmware\n"); goto errorREQFW; } /* check the firmware is valid */ fw_size = dev->fw_data->fw->size; pdata = (__le32 *) &dev->fw_data->fw->data[fw_size - 8]; if (*pdata != S2255_FW_MARKER) { dev_err(&interface->dev, "Firmware invalid.\n"); retval = -ENODEV; goto errorFWMARKER; } else { /* make sure firmware is the latest */ __le32 *pRel; pRel = (__le32 *) &dev->fw_data->fw->data[fw_size - 4]; pr_info("s2255 dsp fw version %x\n", le32_to_cpu(*pRel)); dev->dsp_fw_ver = le32_to_cpu(*pRel); if (dev->dsp_fw_ver < S2255_CUR_DSP_FWVER) pr_info("s2255: f2255usb.bin out of date.\n"); if (dev->pid == 0x2257 && dev->dsp_fw_ver < S2255_MIN_DSP_COLORFILTER) pr_warn("2257 needs firmware %d or above.\n", S2255_MIN_DSP_COLORFILTER); } usb_reset_device(dev->udev); /* load 2255 board specific */ retval = s2255_board_init(dev); if (retval) goto errorBOARDINIT; s2255_fwload_start(dev); /* loads v4l specific */ retval = s2255_probe_v4l(dev); if (retval) goto errorBOARDINIT; dev_info(&interface->dev, "Sensoray 2255 detected\n"); return 0; errorBOARDINIT: s2255_board_shutdown(dev); errorFWMARKER: release_firmware(dev->fw_data->fw); errorREQFW: kfree(dev->fw_data->pfw_data); errorFWDATA2: usb_free_urb(dev->fw_data->fw_urb); errorFWURB: timer_shutdown_sync(&dev->timer); errorEP: usb_put_dev(dev->udev); errorUDEV: kfree(dev->fw_data); mutex_destroy(&dev->lock); errorFWDATA1: kfree(dev->cmdbuf); kfree(dev); pr_warn("Sensoray 2255 driver load failed: 0x%x\n", retval); return retval; } /* disconnect routine. when board is removed physically or with rmmod */ static void s2255_disconnect(struct usb_interface *interface) { struct s2255_dev *dev = to_s2255_dev(usb_get_intfdata(interface)); int i; int channels = refcount_read(&dev->num_channels); mutex_lock(&dev->lock); v4l2_device_disconnect(&dev->v4l2_dev); mutex_unlock(&dev->lock); /*see comments in the uvc_driver.c usb disconnect function */ refcount_inc(&dev->num_channels); /* unregister each video device. */ for (i = 0; i < channels; i++) video_unregister_device(&dev->vc[i].vdev); /* wake up any of our timers */ atomic_set(&dev->fw_data->fw_state, S2255_FW_DISCONNECTING); wake_up(&dev->fw_data->wait_fw); for (i = 0; i < MAX_CHANNELS; i++) { dev->vc[i].setmode_ready = 1; wake_up(&dev->vc[i].wait_setmode); dev->vc[i].vidstatus_ready = 1; wake_up(&dev->vc[i].wait_vidstatus); } if (refcount_dec_and_test(&dev->num_channels)) s2255_destroy(dev); dev_info(&interface->dev, "%s\n", __func__); } static struct usb_driver s2255_driver = { .name = S2255_DRIVER_NAME, .probe = s2255_probe, .disconnect = s2255_disconnect, .id_table = s2255_table, }; module_usb_driver(s2255_driver); MODULE_DESCRIPTION("Sensoray 2255 Video for Linux driver"); MODULE_AUTHOR("Dean Anderson (Sensoray Company Inc.)"); MODULE_LICENSE("GPL"); MODULE_VERSION(S2255_VERSION); MODULE_FIRMWARE(FIRMWARE_FILE_NAME); |
| 4 1 2 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2015 Pablo Neira Ayuso <pablo@netfilter.org> */ #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/ipv4/nf_dup_ipv4.h> struct nft_dup_ipv4 { u8 sreg_addr; u8 sreg_dev; }; static void nft_dup_ipv4_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_dup_ipv4 *priv = nft_expr_priv(expr); struct in_addr gw = { .s_addr = (__force __be32)regs->data[priv->sreg_addr], }; int oif = priv->sreg_dev ? regs->data[priv->sreg_dev] : -1; nf_dup_ipv4(nft_net(pkt), pkt->skb, nft_hook(pkt), &gw, oif); } static int nft_dup_ipv4_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_dup_ipv4 *priv = nft_expr_priv(expr); int err; if (tb[NFTA_DUP_SREG_ADDR] == NULL) return -EINVAL; err = nft_parse_register_load(ctx, tb[NFTA_DUP_SREG_ADDR], &priv->sreg_addr, sizeof(struct in_addr)); if (err < 0) return err; if (tb[NFTA_DUP_SREG_DEV]) err = nft_parse_register_load(ctx, tb[NFTA_DUP_SREG_DEV], &priv->sreg_dev, sizeof(int)); return err; } static int nft_dup_ipv4_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { struct nft_dup_ipv4 *priv = nft_expr_priv(expr); if (nft_dump_register(skb, NFTA_DUP_SREG_ADDR, priv->sreg_addr)) goto nla_put_failure; if (priv->sreg_dev && nft_dump_register(skb, NFTA_DUP_SREG_DEV, priv->sreg_dev)) goto nla_put_failure; return 0; nla_put_failure: return -1; } static struct nft_expr_type nft_dup_ipv4_type; static const struct nft_expr_ops nft_dup_ipv4_ops = { .type = &nft_dup_ipv4_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_dup_ipv4)), .eval = nft_dup_ipv4_eval, .init = nft_dup_ipv4_init, .dump = nft_dup_ipv4_dump, .reduce = NFT_REDUCE_READONLY, }; static const struct nla_policy nft_dup_ipv4_policy[NFTA_DUP_MAX + 1] = { [NFTA_DUP_SREG_ADDR] = { .type = NLA_U32 }, [NFTA_DUP_SREG_DEV] = { .type = NLA_U32 }, }; static struct nft_expr_type nft_dup_ipv4_type __read_mostly = { .family = NFPROTO_IPV4, .name = "dup", .ops = &nft_dup_ipv4_ops, .policy = nft_dup_ipv4_policy, .maxattr = NFTA_DUP_MAX, .owner = THIS_MODULE, }; static int __init nft_dup_ipv4_module_init(void) { return nft_register_expr(&nft_dup_ipv4_type); } static void __exit nft_dup_ipv4_module_exit(void) { nft_unregister_expr(&nft_dup_ipv4_type); } module_init(nft_dup_ipv4_module_init); module_exit(nft_dup_ipv4_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "dup"); MODULE_DESCRIPTION("IPv4 nftables packet duplication support"); |
| 29 30 1 31 29 27 32 1 1 29 29 29 3 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 | // SPDX-License-Identifier: GPL-2.0-only /* * net/dccp/qpolicy.c * * Policy-based packet dequeueing interface for DCCP. * * Copyright (c) 2008 Tomasz Grobelny <tomasz@grobelny.oswiecenia.net> */ #include "dccp.h" /* * Simple Dequeueing Policy: * If tx_qlen is different from 0, enqueue up to tx_qlen elements. */ static void qpolicy_simple_push(struct sock *sk, struct sk_buff *skb) { skb_queue_tail(&sk->sk_write_queue, skb); } static bool qpolicy_simple_full(struct sock *sk) { return dccp_sk(sk)->dccps_tx_qlen && sk->sk_write_queue.qlen >= dccp_sk(sk)->dccps_tx_qlen; } static struct sk_buff *qpolicy_simple_top(struct sock *sk) { return skb_peek(&sk->sk_write_queue); } /* * Priority-based Dequeueing Policy: * If tx_qlen is different from 0 and the queue has reached its upper bound * of tx_qlen elements, replace older packets lowest-priority-first. */ static struct sk_buff *qpolicy_prio_best_skb(struct sock *sk) { struct sk_buff *skb, *best = NULL; skb_queue_walk(&sk->sk_write_queue, skb) if (best == NULL || skb->priority > best->priority) best = skb; return best; } static struct sk_buff *qpolicy_prio_worst_skb(struct sock *sk) { struct sk_buff *skb, *worst = NULL; skb_queue_walk(&sk->sk_write_queue, skb) if (worst == NULL || skb->priority < worst->priority) worst = skb; return worst; } static bool qpolicy_prio_full(struct sock *sk) { if (qpolicy_simple_full(sk)) dccp_qpolicy_drop(sk, qpolicy_prio_worst_skb(sk)); return false; } /** * struct dccp_qpolicy_operations - TX Packet Dequeueing Interface * @push: add a new @skb to the write queue * @full: indicates that no more packets will be admitted * @top: peeks at whatever the queueing policy defines as its `top' * @params: parameter passed to policy operation */ struct dccp_qpolicy_operations { void (*push) (struct sock *sk, struct sk_buff *skb); bool (*full) (struct sock *sk); struct sk_buff* (*top) (struct sock *sk); __be32 params; }; static struct dccp_qpolicy_operations qpol_table[DCCPQ_POLICY_MAX] = { [DCCPQ_POLICY_SIMPLE] = { .push = qpolicy_simple_push, .full = qpolicy_simple_full, .top = qpolicy_simple_top, .params = 0, }, [DCCPQ_POLICY_PRIO] = { .push = qpolicy_simple_push, .full = qpolicy_prio_full, .top = qpolicy_prio_best_skb, .params = DCCP_SCM_PRIORITY, }, }; /* * Externally visible interface */ void dccp_qpolicy_push(struct sock *sk, struct sk_buff *skb) { qpol_table[dccp_sk(sk)->dccps_qpolicy].push(sk, skb); } bool dccp_qpolicy_full(struct sock *sk) { return qpol_table[dccp_sk(sk)->dccps_qpolicy].full(sk); } void dccp_qpolicy_drop(struct sock *sk, struct sk_buff *skb) { if (skb != NULL) { skb_unlink(skb, &sk->sk_write_queue); kfree_skb(skb); } } struct sk_buff *dccp_qpolicy_top(struct sock *sk) { return qpol_table[dccp_sk(sk)->dccps_qpolicy].top(sk); } struct sk_buff *dccp_qpolicy_pop(struct sock *sk) { struct sk_buff *skb = dccp_qpolicy_top(sk); if (skb != NULL) { /* Clear any skb fields that we used internally */ skb->priority = 0; skb_unlink(skb, &sk->sk_write_queue); } return skb; } bool dccp_qpolicy_param_ok(struct sock *sk, __be32 param) { /* check if exactly one bit is set */ if (!param || (param & (param - 1))) return false; return (qpol_table[dccp_sk(sk)->dccps_qpolicy].params & param) == param; } |
| 10 6 4 2 9 8 8 3 8 4 4 1 6 6 6 6 2 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 | // SPDX-License-Identifier: GPL-2.0-or-later /* DataCenter TCP (DCTCP) congestion control. * * http://simula.stanford.edu/~alizade/Site/DCTCP.html * * This is an implementation of DCTCP over Reno, an enhancement to the * TCP congestion control algorithm designed for data centers. DCTCP * leverages Explicit Congestion Notification (ECN) in the network to * provide multi-bit feedback to the end hosts. DCTCP's goal is to meet * the following three data center transport requirements: * * - High burst tolerance (incast due to partition/aggregate) * - Low latency (short flows, queries) * - High throughput (continuous data updates, large file transfers) * with commodity shallow buffered switches * * The algorithm is described in detail in the following two papers: * * 1) Mohammad Alizadeh, Albert Greenberg, David A. Maltz, Jitendra Padhye, * Parveen Patel, Balaji Prabhakar, Sudipta Sengupta, and Murari Sridharan: * "Data Center TCP (DCTCP)", Data Center Networks session * Proc. ACM SIGCOMM, New Delhi, 2010. * http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp-final.pdf * * 2) Mohammad Alizadeh, Adel Javanmard, and Balaji Prabhakar: * "Analysis of DCTCP: Stability, Convergence, and Fairness" * Proc. ACM SIGMETRICS, San Jose, 2011. * http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp_analysis-full.pdf * * Initial prototype from Abdul Kabbani, Masato Yasuda and Mohammad Alizadeh. * * Authors: * * Daniel Borkmann <dborkman@redhat.com> * Florian Westphal <fw@strlen.de> * Glenn Judd <glenn.judd@morganstanley.com> */ #include <linux/btf.h> #include <linux/btf_ids.h> #include <linux/module.h> #include <linux/mm.h> #include <net/tcp.h> #include <linux/inet_diag.h> #include "tcp_dctcp.h" #define DCTCP_MAX_ALPHA 1024U struct dctcp { u32 old_delivered; u32 old_delivered_ce; u32 prior_rcv_nxt; u32 dctcp_alpha; u32 next_seq; u32 ce_state; u32 loss_cwnd; struct tcp_plb_state plb; }; static unsigned int dctcp_shift_g __read_mostly = 4; /* g = 1/2^4 */ static int dctcp_shift_g_set(const char *val, const struct kernel_param *kp) { return param_set_uint_minmax(val, kp, 0, 10); } static const struct kernel_param_ops dctcp_shift_g_ops = { .set = dctcp_shift_g_set, .get = param_get_uint, }; module_param_cb(dctcp_shift_g, &dctcp_shift_g_ops, &dctcp_shift_g, 0644); MODULE_PARM_DESC(dctcp_shift_g, "parameter g for updating dctcp_alpha"); static unsigned int dctcp_alpha_on_init __read_mostly = DCTCP_MAX_ALPHA; module_param(dctcp_alpha_on_init, uint, 0644); MODULE_PARM_DESC(dctcp_alpha_on_init, "parameter for initial alpha value"); static struct tcp_congestion_ops dctcp_reno; static void dctcp_reset(const struct tcp_sock *tp, struct dctcp *ca) { ca->next_seq = tp->snd_nxt; ca->old_delivered = tp->delivered; ca->old_delivered_ce = tp->delivered_ce; } __bpf_kfunc static void dctcp_init(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); if ((tp->ecn_flags & TCP_ECN_OK) || (sk->sk_state == TCP_LISTEN || sk->sk_state == TCP_CLOSE)) { struct dctcp *ca = inet_csk_ca(sk); ca->prior_rcv_nxt = tp->rcv_nxt; ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA); ca->loss_cwnd = 0; ca->ce_state = 0; dctcp_reset(tp, ca); tcp_plb_init(sk, &ca->plb); return; } /* No ECN support? Fall back to Reno. Also need to clear * ECT from sk since it is set during 3WHS for DCTCP. */ inet_csk(sk)->icsk_ca_ops = &dctcp_reno; INET_ECN_dontxmit(sk); } __bpf_kfunc static u32 dctcp_ssthresh(struct sock *sk) { struct dctcp *ca = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); ca->loss_cwnd = tcp_snd_cwnd(tp); return max(tcp_snd_cwnd(tp) - ((tcp_snd_cwnd(tp) * ca->dctcp_alpha) >> 11U), 2U); } __bpf_kfunc static void dctcp_update_alpha(struct sock *sk, u32 flags) { const struct tcp_sock *tp = tcp_sk(sk); struct dctcp *ca = inet_csk_ca(sk); /* Expired RTT */ if (!before(tp->snd_una, ca->next_seq)) { u32 delivered = tp->delivered - ca->old_delivered; u32 delivered_ce = tp->delivered_ce - ca->old_delivered_ce; u32 alpha = ca->dctcp_alpha; u32 ce_ratio = 0; if (delivered > 0) { /* dctcp_alpha keeps EWMA of fraction of ECN marked * packets. Because of EWMA smoothing, PLB reaction can * be slow so we use ce_ratio which is an instantaneous * measure of congestion. ce_ratio is the fraction of * ECN marked packets in the previous RTT. */ if (delivered_ce > 0) ce_ratio = (delivered_ce << TCP_PLB_SCALE) / delivered; tcp_plb_update_state(sk, &ca->plb, (int)ce_ratio); tcp_plb_check_rehash(sk, &ca->plb); } /* alpha = (1 - g) * alpha + g * F */ alpha -= min_not_zero(alpha, alpha >> dctcp_shift_g); if (delivered_ce) { /* If dctcp_shift_g == 1, a 32bit value would overflow * after 8 M packets. */ delivered_ce <<= (10 - dctcp_shift_g); delivered_ce /= max(1U, delivered); alpha = min(alpha + delivered_ce, DCTCP_MAX_ALPHA); } /* dctcp_alpha can be read from dctcp_get_info() without * synchro, so we ask compiler to not use dctcp_alpha * as a temporary variable in prior operations. */ WRITE_ONCE(ca->dctcp_alpha, alpha); dctcp_reset(tp, ca); } } static void dctcp_react_to_loss(struct sock *sk) { struct dctcp *ca = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); ca->loss_cwnd = tcp_snd_cwnd(tp); tp->snd_ssthresh = max(tcp_snd_cwnd(tp) >> 1U, 2U); } __bpf_kfunc static void dctcp_state(struct sock *sk, u8 new_state) { if (new_state == TCP_CA_Recovery && new_state != inet_csk(sk)->icsk_ca_state) dctcp_react_to_loss(sk); /* We handle RTO in dctcp_cwnd_event to ensure that we perform only * one loss-adjustment per RTT. */ } __bpf_kfunc static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev) { struct dctcp *ca = inet_csk_ca(sk); switch (ev) { case CA_EVENT_ECN_IS_CE: case CA_EVENT_ECN_NO_CE: dctcp_ece_ack_update(sk, ev, &ca->prior_rcv_nxt, &ca->ce_state); break; case CA_EVENT_LOSS: tcp_plb_update_state_upon_rto(sk, &ca->plb); dctcp_react_to_loss(sk); break; case CA_EVENT_TX_START: tcp_plb_check_rehash(sk, &ca->plb); /* Maybe rehash when inflight is 0 */ break; default: /* Don't care for the rest. */ break; } } static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr, union tcp_cc_info *info) { const struct dctcp *ca = inet_csk_ca(sk); const struct tcp_sock *tp = tcp_sk(sk); /* Fill it also in case of VEGASINFO due to req struct limits. * We can still correctly retrieve it later. */ if (ext & (1 << (INET_DIAG_DCTCPINFO - 1)) || ext & (1 << (INET_DIAG_VEGASINFO - 1))) { memset(&info->dctcp, 0, sizeof(info->dctcp)); if (inet_csk(sk)->icsk_ca_ops != &dctcp_reno) { info->dctcp.dctcp_enabled = 1; info->dctcp.dctcp_ce_state = (u16) ca->ce_state; info->dctcp.dctcp_alpha = ca->dctcp_alpha; info->dctcp.dctcp_ab_ecn = tp->mss_cache * (tp->delivered_ce - ca->old_delivered_ce); info->dctcp.dctcp_ab_tot = tp->mss_cache * (tp->delivered - ca->old_delivered); } *attr = INET_DIAG_DCTCPINFO; return sizeof(info->dctcp); } return 0; } __bpf_kfunc static u32 dctcp_cwnd_undo(struct sock *sk) { const struct dctcp *ca = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); return max(tcp_snd_cwnd(tp), ca->loss_cwnd); } static struct tcp_congestion_ops dctcp __read_mostly = { .init = dctcp_init, .in_ack_event = dctcp_update_alpha, .cwnd_event = dctcp_cwnd_event, .ssthresh = dctcp_ssthresh, .cong_avoid = tcp_reno_cong_avoid, .undo_cwnd = dctcp_cwnd_undo, .set_state = dctcp_state, .get_info = dctcp_get_info, .flags = TCP_CONG_NEEDS_ECN, .owner = THIS_MODULE, .name = "dctcp", }; static struct tcp_congestion_ops dctcp_reno __read_mostly = { .ssthresh = tcp_reno_ssthresh, .cong_avoid = tcp_reno_cong_avoid, .undo_cwnd = tcp_reno_undo_cwnd, .get_info = dctcp_get_info, .owner = THIS_MODULE, .name = "dctcp-reno", }; BTF_KFUNCS_START(tcp_dctcp_check_kfunc_ids) BTF_ID_FLAGS(func, dctcp_init) BTF_ID_FLAGS(func, dctcp_update_alpha) BTF_ID_FLAGS(func, dctcp_cwnd_event) BTF_ID_FLAGS(func, dctcp_ssthresh) BTF_ID_FLAGS(func, dctcp_cwnd_undo) BTF_ID_FLAGS(func, dctcp_state) BTF_KFUNCS_END(tcp_dctcp_check_kfunc_ids) static const struct btf_kfunc_id_set tcp_dctcp_kfunc_set = { .owner = THIS_MODULE, .set = &tcp_dctcp_check_kfunc_ids, }; static int __init dctcp_register(void) { int ret; BUILD_BUG_ON(sizeof(struct dctcp) > ICSK_CA_PRIV_SIZE); ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &tcp_dctcp_kfunc_set); if (ret < 0) return ret; return tcp_register_congestion_control(&dctcp); } static void __exit dctcp_unregister(void) { tcp_unregister_congestion_control(&dctcp); } module_init(dctcp_register); module_exit(dctcp_unregister); MODULE_AUTHOR("Daniel Borkmann <dborkman@redhat.com>"); MODULE_AUTHOR("Florian Westphal <fw@strlen.de>"); MODULE_AUTHOR("Glenn Judd <glenn.judd@morganstanley.com>"); MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("DataCenter TCP (DCTCP)"); |
| 9 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __KVM_X86_PMU_H #define __KVM_X86_PMU_H #include <linux/nospec.h> #include <asm/kvm_host.h> #define vcpu_to_pmu(vcpu) (&(vcpu)->arch.pmu) #define pmu_to_vcpu(pmu) (container_of((pmu), struct kvm_vcpu, arch.pmu)) #define pmc_to_pmu(pmc) (&(pmc)->vcpu->arch.pmu) #define MSR_IA32_MISC_ENABLE_PMU_RO_MASK (MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL | \ MSR_IA32_MISC_ENABLE_BTS_UNAVAIL) /* retrieve the 4 bits for EN and PMI out of IA32_FIXED_CTR_CTRL */ #define fixed_ctrl_field(ctrl_reg, idx) \ (((ctrl_reg) >> ((idx) * INTEL_FIXED_BITS_STRIDE)) & INTEL_FIXED_BITS_MASK) #define VMWARE_BACKDOOR_PMC_HOST_TSC 0x10000 #define VMWARE_BACKDOOR_PMC_REAL_TIME 0x10001 #define VMWARE_BACKDOOR_PMC_APPARENT_TIME 0x10002 #define KVM_FIXED_PMC_BASE_IDX INTEL_PMC_IDX_FIXED struct kvm_pmu_emulated_event_selectors { u64 INSTRUCTIONS_RETIRED; u64 BRANCH_INSTRUCTIONS_RETIRED; }; struct kvm_pmu_ops { struct kvm_pmc *(*rdpmc_ecx_to_pmc)(struct kvm_vcpu *vcpu, unsigned int idx, u64 *mask); struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, u32 msr); int (*check_rdpmc_early)(struct kvm_vcpu *vcpu, unsigned int idx); bool (*is_valid_msr)(struct kvm_vcpu *vcpu, u32 msr); int (*get_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info); int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info); void (*refresh)(struct kvm_vcpu *vcpu); void (*init)(struct kvm_vcpu *vcpu); void (*reset)(struct kvm_vcpu *vcpu); void (*deliver_pmi)(struct kvm_vcpu *vcpu); void (*cleanup)(struct kvm_vcpu *vcpu); const u64 EVENTSEL_EVENT; const int MAX_NR_GP_COUNTERS; const int MIN_NR_GP_COUNTERS; }; void kvm_pmu_ops_update(const struct kvm_pmu_ops *pmu_ops); static inline bool kvm_pmu_has_perf_global_ctrl(struct kvm_pmu *pmu) { /* * Architecturally, Intel's SDM states that IA32_PERF_GLOBAL_CTRL is * supported if "CPUID.0AH: EAX[7:0] > 0", i.e. if the PMU version is * greater than zero. However, KVM only exposes and emulates the MSR * to/for the guest if the guest PMU supports at least "Architectural * Performance Monitoring Version 2". * * AMD's version of PERF_GLOBAL_CTRL conveniently shows up with v2. */ return pmu->version > 1; } /* * KVM tracks all counters in 64-bit bitmaps, with general purpose counters * mapped to bits 31:0 and fixed counters mapped to 63:32, e.g. fixed counter 0 * is tracked internally via index 32. On Intel, (AMD doesn't support fixed * counters), this mirrors how fixed counters are mapped to PERF_GLOBAL_CTRL * and similar MSRs, i.e. tracking fixed counters at base index 32 reduces the * amounter of boilerplate needed to iterate over PMCs *and* simplifies common * enabling/disable/reset operations. * * WARNING! This helper is only for lookups that are initiated by KVM, it is * NOT safe for guest lookups, e.g. will do the wrong thing if passed a raw * ECX value from RDPMC (fixed counters are accessed by setting bit 30 in ECX * for RDPMC, not by adding 32 to the fixed counter index). */ static inline struct kvm_pmc *kvm_pmc_idx_to_pmc(struct kvm_pmu *pmu, int idx) { if (idx < pmu->nr_arch_gp_counters) return &pmu->gp_counters[idx]; idx -= KVM_FIXED_PMC_BASE_IDX; if (idx >= 0 && idx < pmu->nr_arch_fixed_counters) return &pmu->fixed_counters[idx]; return NULL; } #define kvm_for_each_pmc(pmu, pmc, i, bitmap) \ for_each_set_bit(i, bitmap, X86_PMC_IDX_MAX) \ if (!(pmc = kvm_pmc_idx_to_pmc(pmu, i))) \ continue; \ else \ static inline u64 pmc_bitmask(struct kvm_pmc *pmc) { struct kvm_pmu *pmu = pmc_to_pmu(pmc); return pmu->counter_bitmask[pmc->type]; } static inline u64 pmc_read_counter(struct kvm_pmc *pmc) { u64 counter, enabled, running; counter = pmc->counter + pmc->emulated_counter; if (pmc->perf_event && !pmc->is_paused) counter += perf_event_read_value(pmc->perf_event, &enabled, &running); /* FIXME: Scaling needed? */ return counter & pmc_bitmask(pmc); } void pmc_write_counter(struct kvm_pmc *pmc, u64 val); static inline bool pmc_is_gp(struct kvm_pmc *pmc) { return pmc->type == KVM_PMC_GP; } static inline bool pmc_is_fixed(struct kvm_pmc *pmc) { return pmc->type == KVM_PMC_FIXED; } static inline bool kvm_valid_perf_global_ctrl(struct kvm_pmu *pmu, u64 data) { return !(pmu->global_ctrl_rsvd & data); } /* returns general purpose PMC with the specified MSR. Note that it can be * used for both PERFCTRn and EVNTSELn; that is why it accepts base as a * parameter to tell them apart. */ static inline struct kvm_pmc *get_gp_pmc(struct kvm_pmu *pmu, u32 msr, u32 base) { if (msr >= base && msr < base + pmu->nr_arch_gp_counters) { u32 index = array_index_nospec(msr - base, pmu->nr_arch_gp_counters); return &pmu->gp_counters[index]; } return NULL; } /* returns fixed PMC with the specified MSR */ static inline struct kvm_pmc *get_fixed_pmc(struct kvm_pmu *pmu, u32 msr) { int base = MSR_CORE_PERF_FIXED_CTR0; if (msr >= base && msr < base + pmu->nr_arch_fixed_counters) { u32 index = array_index_nospec(msr - base, pmu->nr_arch_fixed_counters); return &pmu->fixed_counters[index]; } return NULL; } static inline bool pmc_speculative_in_use(struct kvm_pmc *pmc) { struct kvm_pmu *pmu = pmc_to_pmu(pmc); if (pmc_is_fixed(pmc)) return fixed_ctrl_field(pmu->fixed_ctr_ctrl, pmc->idx - KVM_FIXED_PMC_BASE_IDX) & (INTEL_FIXED_0_KERNEL | INTEL_FIXED_0_USER); return pmc->eventsel & ARCH_PERFMON_EVENTSEL_ENABLE; } extern struct x86_pmu_capability kvm_pmu_cap; extern struct kvm_pmu_emulated_event_selectors kvm_pmu_eventsel; static inline void kvm_init_pmu_capability(const struct kvm_pmu_ops *pmu_ops) { bool is_intel = boot_cpu_data.x86_vendor == X86_VENDOR_INTEL; int min_nr_gp_ctrs = pmu_ops->MIN_NR_GP_COUNTERS; /* * Hybrid PMUs don't play nice with virtualization without careful * configuration by userspace, and KVM's APIs for reporting supported * vPMU features do not account for hybrid PMUs. Disable vPMU support * for hybrid PMUs until KVM gains a way to let userspace opt-in. */ if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) enable_pmu = false; if (enable_pmu) { perf_get_x86_pmu_capability(&kvm_pmu_cap); /* * WARN if perf did NOT disable hardware PMU if the number of * architecturally required GP counters aren't present, i.e. if * there are a non-zero number of counters, but fewer than what * is architecturally required. */ if (!kvm_pmu_cap.num_counters_gp || WARN_ON_ONCE(kvm_pmu_cap.num_counters_gp < min_nr_gp_ctrs)) enable_pmu = false; else if (is_intel && !kvm_pmu_cap.version) enable_pmu = false; } if (!enable_pmu) { memset(&kvm_pmu_cap, 0, sizeof(kvm_pmu_cap)); return; } kvm_pmu_cap.version = min(kvm_pmu_cap.version, 2); kvm_pmu_cap.num_counters_gp = min(kvm_pmu_cap.num_counters_gp, pmu_ops->MAX_NR_GP_COUNTERS); kvm_pmu_cap.num_counters_fixed = min(kvm_pmu_cap.num_counters_fixed, KVM_MAX_NR_FIXED_COUNTERS); kvm_pmu_eventsel.INSTRUCTIONS_RETIRED = perf_get_hw_event_config(PERF_COUNT_HW_INSTRUCTIONS); kvm_pmu_eventsel.BRANCH_INSTRUCTIONS_RETIRED = perf_get_hw_event_config(PERF_COUNT_HW_BRANCH_INSTRUCTIONS); } static inline void kvm_pmu_request_counter_reprogram(struct kvm_pmc *pmc) { set_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi); kvm_make_request(KVM_REQ_PMU, pmc->vcpu); } static inline void reprogram_counters(struct kvm_pmu *pmu, u64 diff) { int bit; if (!diff) return; for_each_set_bit(bit, (unsigned long *)&diff, X86_PMC_IDX_MAX) set_bit(bit, pmu->reprogram_pmi); kvm_make_request(KVM_REQ_PMU, pmu_to_vcpu(pmu)); } /* * Check if a PMC is enabled by comparing it against global_ctrl bits. * * If the vPMU doesn't have global_ctrl MSR, all vPMCs are enabled. */ static inline bool pmc_is_globally_enabled(struct kvm_pmc *pmc) { struct kvm_pmu *pmu = pmc_to_pmu(pmc); if (!kvm_pmu_has_perf_global_ctrl(pmu)) return true; return test_bit(pmc->idx, (unsigned long *)&pmu->global_ctrl); } void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu); void kvm_pmu_handle_event(struct kvm_vcpu *vcpu); int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data); int kvm_pmu_check_rdpmc_early(struct kvm_vcpu *vcpu, unsigned int idx); bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr); int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); void kvm_pmu_refresh(struct kvm_vcpu *vcpu); void kvm_pmu_init(struct kvm_vcpu *vcpu); void kvm_pmu_cleanup(struct kvm_vcpu *vcpu); void kvm_pmu_destroy(struct kvm_vcpu *vcpu); int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp); void kvm_pmu_trigger_event(struct kvm_vcpu *vcpu, u64 eventsel); bool is_vmware_backdoor_pmc(u32 pmc_idx); extern struct kvm_pmu_ops intel_pmu_ops; extern struct kvm_pmu_ops amd_pmu_ops; #endif /* __KVM_X86_PMU_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2008 ioogle, Inc. All rights reserved. * * Libata transport class. * * The ATA transport class contains common code to deal with ATA HBAs, * an approximated representation of ATA topologies in the driver model, * and various sysfs attributes to expose these topologies and management * interfaces to user-space. * * There are 3 objects defined in this class: * - ata_port * - ata_link * - ata_device * Each port has a link object. Each link can have up to two devices for PATA * and generally one for SATA. * If there is SATA port multiplier [PMP], 15 additional ata_link object are * created. * * These objects are created when the ata host is initialized and when a PMP is * found. They are removed only when the HBA is removed, cleaned before the * error handler runs. */ #include <linux/kernel.h> #include <linux/blkdev.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <scsi/scsi_transport.h> #include <linux/libata.h> #include <linux/hdreg.h> #include <linux/uaccess.h> #include <linux/pm_runtime.h> #include "libata.h" #include "libata-transport.h" #define ATA_PORT_ATTRS 3 #define ATA_LINK_ATTRS 3 #define ATA_DEV_ATTRS 9 struct scsi_transport_template; struct scsi_transport_template *ata_scsi_transport_template; struct ata_internal { struct scsi_transport_template t; struct device_attribute private_port_attrs[ATA_PORT_ATTRS]; struct device_attribute private_link_attrs[ATA_LINK_ATTRS]; struct device_attribute private_dev_attrs[ATA_DEV_ATTRS]; struct transport_container link_attr_cont; struct transport_container dev_attr_cont; /* * The array of null terminated pointers to attributes * needed by scsi_sysfs.c */ struct device_attribute *link_attrs[ATA_LINK_ATTRS + 1]; struct device_attribute *port_attrs[ATA_PORT_ATTRS + 1]; struct device_attribute *dev_attrs[ATA_DEV_ATTRS + 1]; }; #define to_ata_internal(tmpl) container_of(tmpl, struct ata_internal, t) #define tdev_to_device(d) \ container_of((d), struct ata_device, tdev) #define transport_class_to_dev(dev) \ tdev_to_device((dev)->parent) #define tdev_to_link(d) \ container_of((d), struct ata_link, tdev) #define transport_class_to_link(dev) \ tdev_to_link((dev)->parent) #define tdev_to_port(d) \ container_of((d), struct ata_port, tdev) #define transport_class_to_port(dev) \ tdev_to_port((dev)->parent) /* * Hack to allow attributes of the same name in different objects. */ #define ATA_DEVICE_ATTR(_prefix,_name,_mode,_show,_store) \ struct device_attribute device_attr_##_prefix##_##_name = \ __ATTR(_name,_mode,_show,_store) #define ata_bitfield_name_match(title, table) \ static ssize_t \ get_ata_##title##_names(u32 table_key, char *buf) \ { \ char *prefix = ""; \ ssize_t len = 0; \ int i; \ \ for (i = 0; i < ARRAY_SIZE(table); i++) { \ if (table[i].value & table_key) { \ len += sprintf(buf + len, "%s%s", \ prefix, table[i].name); \ prefix = ", "; \ } \ } \ len += sprintf(buf + len, "\n"); \ return len; \ } #define ata_bitfield_name_search(title, table) \ static ssize_t \ get_ata_##title##_names(u32 table_key, char *buf) \ { \ ssize_t len = 0; \ int i; \ \ for (i = 0; i < ARRAY_SIZE(table); i++) { \ if (table[i].value == table_key) { \ len += sprintf(buf + len, "%s", \ table[i].name); \ break; \ } \ } \ len += sprintf(buf + len, "\n"); \ return len; \ } static struct { u32 value; char *name; } ata_class_names[] = { { ATA_DEV_UNKNOWN, "unknown" }, { ATA_DEV_ATA, "ata" }, { ATA_DEV_ATA_UNSUP, "ata" }, { ATA_DEV_ATAPI, "atapi" }, { ATA_DEV_ATAPI_UNSUP, "atapi" }, { ATA_DEV_PMP, "pmp" }, { ATA_DEV_PMP_UNSUP, "pmp" }, { ATA_DEV_SEMB, "semb" }, { ATA_DEV_SEMB_UNSUP, "semb" }, { ATA_DEV_ZAC, "zac" }, { ATA_DEV_NONE, "none" } }; ata_bitfield_name_search(class, ata_class_names) static struct { u32 value; char *name; } ata_err_names[] = { { AC_ERR_DEV, "DeviceError" }, { AC_ERR_HSM, "HostStateMachineError" }, { AC_ERR_TIMEOUT, "Timeout" }, { AC_ERR_MEDIA, "MediaError" }, { AC_ERR_ATA_BUS, "BusError" }, { AC_ERR_HOST_BUS, "HostBusError" }, { AC_ERR_SYSTEM, "SystemError" }, { AC_ERR_INVALID, "InvalidArg" }, { AC_ERR_OTHER, "Unknown" }, { AC_ERR_NODEV_HINT, "NoDeviceHint" }, { AC_ERR_NCQ, "NCQError" } }; ata_bitfield_name_match(err, ata_err_names) static struct { u32 value; char *name; } ata_xfer_names[] = { { XFER_UDMA_7, "XFER_UDMA_7" }, { XFER_UDMA_6, "XFER_UDMA_6" }, { XFER_UDMA_5, "XFER_UDMA_5" }, { XFER_UDMA_4, "XFER_UDMA_4" }, { XFER_UDMA_3, "XFER_UDMA_3" }, { XFER_UDMA_2, "XFER_UDMA_2" }, { XFER_UDMA_1, "XFER_UDMA_1" }, { XFER_UDMA_0, "XFER_UDMA_0" }, { XFER_MW_DMA_4, "XFER_MW_DMA_4" }, { XFER_MW_DMA_3, "XFER_MW_DMA_3" }, { XFER_MW_DMA_2, "XFER_MW_DMA_2" }, { XFER_MW_DMA_1, "XFER_MW_DMA_1" }, { XFER_MW_DMA_0, "XFER_MW_DMA_0" }, { XFER_SW_DMA_2, "XFER_SW_DMA_2" }, { XFER_SW_DMA_1, "XFER_SW_DMA_1" }, { XFER_SW_DMA_0, "XFER_SW_DMA_0" }, { XFER_PIO_6, "XFER_PIO_6" }, { XFER_PIO_5, "XFER_PIO_5" }, { XFER_PIO_4, "XFER_PIO_4" }, { XFER_PIO_3, "XFER_PIO_3" }, { XFER_PIO_2, "XFER_PIO_2" }, { XFER_PIO_1, "XFER_PIO_1" }, { XFER_PIO_0, "XFER_PIO_0" }, { XFER_PIO_SLOW, "XFER_PIO_SLOW" } }; ata_bitfield_name_search(xfer, ata_xfer_names) /* * ATA Port attributes */ #define ata_port_show_simple(field, name, format_string, cast) \ static ssize_t \ show_ata_port_##name(struct device *dev, \ struct device_attribute *attr, char *buf) \ { \ struct ata_port *ap = transport_class_to_port(dev); \ \ return scnprintf(buf, 20, format_string, cast ap->field); \ } #define ata_port_simple_attr(field, name, format_string, type) \ ata_port_show_simple(field, name, format_string, (type)) \ static DEVICE_ATTR(name, S_IRUGO, show_ata_port_##name, NULL) ata_port_simple_attr(nr_pmp_links, nr_pmp_links, "%d\n", int); ata_port_simple_attr(stats.idle_irq, idle_irq, "%ld\n", unsigned long); /* We want the port_no sysfs attibute to start at 1 (ap->port_no starts at 0) */ ata_port_simple_attr(port_no + 1, port_no, "%u\n", unsigned int); static DECLARE_TRANSPORT_CLASS(ata_port_class, "ata_port", NULL, NULL, NULL); static void ata_tport_release(struct device *dev) { struct ata_port *ap = tdev_to_port(dev); ata_host_put(ap->host); } /** * ata_is_port -- check if a struct device represents a ATA port * @dev: device to check * * Returns: * %1 if the device represents a ATA Port, %0 else */ static int ata_is_port(const struct device *dev) { return dev->release == ata_tport_release; } static int ata_tport_match(struct attribute_container *cont, struct device *dev) { if (!ata_is_port(dev)) return 0; return &ata_scsi_transport_template->host_attrs.ac == cont; } /** * ata_tport_delete -- remove ATA PORT * @ap: ATA PORT to remove * * Removes the specified ATA PORT. Remove the associated link as well. */ void ata_tport_delete(struct ata_port *ap) { struct device *dev = &ap->tdev; ata_tlink_delete(&ap->link); transport_remove_device(dev); device_del(dev); transport_destroy_device(dev); put_device(dev); } EXPORT_SYMBOL_GPL(ata_tport_delete); static const struct device_type ata_port_sas_type = { .name = ATA_PORT_TYPE_NAME, }; /** ata_tport_add - initialize a transport ATA port structure * * @parent: parent device * @ap: existing ata_port structure * * Initialize a ATA port structure for sysfs. It will be added to the device * tree below the device specified by @parent which could be a PCI device. * * Returns %0 on success */ int ata_tport_add(struct device *parent, struct ata_port *ap) { int error; struct device *dev = &ap->tdev; device_initialize(dev); if (ap->flags & ATA_FLAG_SAS_HOST) dev->type = &ata_port_sas_type; else dev->type = &ata_port_type; dev->parent = parent; ata_host_get(ap->host); dev->release = ata_tport_release; dev_set_name(dev, "ata%d", ap->print_id); transport_setup_device(dev); ata_acpi_bind_port(ap); error = device_add(dev); if (error) { goto tport_err; } device_enable_async_suspend(dev); pm_runtime_set_active(dev); pm_runtime_enable(dev); pm_runtime_forbid(dev); error = transport_add_device(dev); if (error) goto tport_transport_add_err; transport_configure_device(dev); error = ata_tlink_add(&ap->link); if (error) { goto tport_link_err; } return 0; tport_link_err: transport_remove_device(dev); tport_transport_add_err: device_del(dev); tport_err: transport_destroy_device(dev); put_device(dev); return error; } EXPORT_SYMBOL_GPL(ata_tport_add); /** * ata_port_classify - determine device type based on ATA-spec signature * @ap: ATA port device on which the classification should be run * @tf: ATA taskfile register set for device to be identified * * A wrapper around ata_dev_classify() to provide additional logging * * RETURNS: * Device type, %ATA_DEV_ATA, %ATA_DEV_ATAPI, %ATA_DEV_PMP, * %ATA_DEV_ZAC, or %ATA_DEV_UNKNOWN the event of failure. */ unsigned int ata_port_classify(struct ata_port *ap, const struct ata_taskfile *tf) { int i; unsigned int class = ata_dev_classify(tf); /* Start with index '1' to skip the 'unknown' entry */ for (i = 1; i < ARRAY_SIZE(ata_class_names); i++) { if (ata_class_names[i].value == class) { ata_port_dbg(ap, "found %s device by sig\n", ata_class_names[i].name); return class; } } ata_port_info(ap, "found unknown device (class %u)\n", class); return class; } EXPORT_SYMBOL_GPL(ata_port_classify); /* * ATA device attributes */ #define ata_dev_show_class(title, field) \ static ssize_t \ show_ata_dev_##field(struct device *dev, \ struct device_attribute *attr, char *buf) \ { \ struct ata_device *ata_dev = transport_class_to_dev(dev); \ \ return get_ata_##title##_names(ata_dev->field, buf); \ } #define ata_dev_attr(title, field) \ ata_dev_show_class(title, field) \ static DEVICE_ATTR(field, S_IRUGO, show_ata_dev_##field, NULL) ata_dev_attr(class, class); ata_dev_attr(xfer, pio_mode); ata_dev_attr(xfer, dma_mode); ata_dev_attr(xfer, xfer_mode); #define ata_dev_show_simple(field, format_string, cast) \ static ssize_t \ show_ata_dev_##field(struct device *dev, \ struct device_attribute *attr, char *buf) \ { \ struct ata_device *ata_dev = transport_class_to_dev(dev); \ \ return scnprintf(buf, 20, format_string, cast ata_dev->field); \ } #define ata_dev_simple_attr(field, format_string, type) \ ata_dev_show_simple(field, format_string, (type)) \ static DEVICE_ATTR(field, S_IRUGO, \ show_ata_dev_##field, NULL) ata_dev_simple_attr(spdn_cnt, "%d\n", int); struct ata_show_ering_arg { char* buf; int written; }; static int ata_show_ering(struct ata_ering_entry *ent, void *void_arg) { struct ata_show_ering_arg* arg = void_arg; u64 seconds; u32 rem; seconds = div_u64_rem(ent->timestamp, HZ, &rem); arg->written += sprintf(arg->buf + arg->written, "[%5llu.%09lu]", seconds, rem * NSEC_PER_SEC / HZ); arg->written += get_ata_err_names(ent->err_mask, arg->buf + arg->written); return 0; } static ssize_t show_ata_dev_ering(struct device *dev, struct device_attribute *attr, char *buf) { struct ata_device *ata_dev = transport_class_to_dev(dev); struct ata_show_ering_arg arg = { buf, 0 }; ata_ering_map(&ata_dev->ering, ata_show_ering, &arg); return arg.written; } static DEVICE_ATTR(ering, S_IRUGO, show_ata_dev_ering, NULL); static ssize_t show_ata_dev_id(struct device *dev, struct device_attribute *attr, char *buf) { struct ata_device *ata_dev = transport_class_to_dev(dev); int written = 0, i = 0; if (ata_dev->class == ATA_DEV_PMP) return 0; for(i=0;i<ATA_ID_WORDS;i++) { written += scnprintf(buf+written, 20, "%04x%c", ata_dev->id[i], ((i+1) & 7) ? ' ' : '\n'); } return written; } static DEVICE_ATTR(id, S_IRUGO, show_ata_dev_id, NULL); static ssize_t show_ata_dev_gscr(struct device *dev, struct device_attribute *attr, char *buf) { struct ata_device *ata_dev = transport_class_to_dev(dev); int written = 0, i = 0; if (ata_dev->class != ATA_DEV_PMP) return 0; for(i=0;i<SATA_PMP_GSCR_DWORDS;i++) { written += scnprintf(buf+written, 20, "%08x%c", ata_dev->gscr[i], ((i+1) & 3) ? ' ' : '\n'); } if (SATA_PMP_GSCR_DWORDS & 3) buf[written-1] = '\n'; return written; } static DEVICE_ATTR(gscr, S_IRUGO, show_ata_dev_gscr, NULL); static ssize_t show_ata_dev_trim(struct device *dev, struct device_attribute *attr, char *buf) { struct ata_device *ata_dev = transport_class_to_dev(dev); unsigned char *mode; if (!ata_id_has_trim(ata_dev->id)) mode = "unsupported"; else if (ata_dev->quirks & ATA_QUIRK_NOTRIM) mode = "forced_unsupported"; else if (ata_dev->quirks & ATA_QUIRK_NO_NCQ_TRIM) mode = "forced_unqueued"; else if (ata_fpdma_dsm_supported(ata_dev)) mode = "queued"; else mode = "unqueued"; return scnprintf(buf, 20, "%s\n", mode); } static DEVICE_ATTR(trim, S_IRUGO, show_ata_dev_trim, NULL); static DECLARE_TRANSPORT_CLASS(ata_dev_class, "ata_device", NULL, NULL, NULL); static void ata_tdev_release(struct device *dev) { } /** * ata_is_ata_dev -- check if a struct device represents a ATA device * @dev: device to check * * Returns: * true if the device represents a ATA device, false otherwise */ static bool ata_is_ata_dev(const struct device *dev) { return dev->release == ata_tdev_release; } static int ata_tdev_match(struct attribute_container *cont, struct device *dev) { struct ata_internal *i = to_ata_internal(ata_scsi_transport_template); if (!ata_is_ata_dev(dev)) return 0; return &i->dev_attr_cont.ac == cont; } /** * ata_tdev_free -- free an ATA transport device * @dev: struct ata_device owning the transport device to free * * Free the ATA transport device for the specified ATA device. * * Note: * This function must only be called for a ATA transport device that has not * yet successfully been added using ata_tdev_add(). */ static void ata_tdev_free(struct ata_device *dev) { transport_destroy_device(&dev->tdev); put_device(&dev->tdev); } /** * ata_tdev_delete -- remove an ATA transport device * @ata_dev: struct ata_device owning the transport device to delete * * Removes the ATA transport device for the specified ATA device. */ static void ata_tdev_delete(struct ata_device *ata_dev) { struct device *dev = &ata_dev->tdev; transport_remove_device(dev); device_del(dev); ata_tdev_free(ata_dev); } /** * ata_tdev_add -- initialize an ATA transport device * @ata_dev: struct ata_device owning the transport device to add * * Initialize an ATA transport device for sysfs. It will be added in the * device tree below the ATA link device it belongs to. * * Returns %0 on success and a negative error code on error. */ static int ata_tdev_add(struct ata_device *ata_dev) { struct device *dev = &ata_dev->tdev; struct ata_link *link = ata_dev->link; struct ata_port *ap = link->ap; int error; device_initialize(dev); dev->parent = &link->tdev; dev->release = ata_tdev_release; if (ata_is_host_link(link)) dev_set_name(dev, "dev%d.%d", ap->print_id,ata_dev->devno); else dev_set_name(dev, "dev%d.%d.0", ap->print_id, link->pmp); transport_setup_device(dev); ata_acpi_bind_dev(ata_dev); error = device_add(dev); if (error) { ata_tdev_free(ata_dev); return error; } error = transport_add_device(dev); if (error) { device_del(dev); ata_tdev_free(ata_dev); return error; } transport_configure_device(dev); return 0; } /* * ATA link attributes */ static int noop(int x) { return x; } #define ata_link_show_linkspeed(field, format) \ static ssize_t \ show_ata_link_##field(struct device *dev, \ struct device_attribute *attr, char *buf) \ { \ struct ata_link *link = transport_class_to_link(dev); \ \ return sprintf(buf, "%s\n", \ sata_spd_string(format(link->field))); \ } #define ata_link_linkspeed_attr(field, format) \ ata_link_show_linkspeed(field, format) \ static DEVICE_ATTR(field, 0444, show_ata_link_##field, NULL) ata_link_linkspeed_attr(hw_sata_spd_limit, fls); ata_link_linkspeed_attr(sata_spd_limit, fls); ata_link_linkspeed_attr(sata_spd, noop); static DECLARE_TRANSPORT_CLASS(ata_link_class, "ata_link", NULL, NULL, NULL); static void ata_tlink_release(struct device *dev) { } /** * ata_is_link -- check if a struct device represents a ATA link * @dev: device to check * * Returns: * true if the device represents a ATA link, false otherwise */ static bool ata_is_link(const struct device *dev) { return dev->release == ata_tlink_release; } static int ata_tlink_match(struct attribute_container *cont, struct device *dev) { struct ata_internal *i = to_ata_internal(ata_scsi_transport_template); if (!ata_is_link(dev)) return 0; return &i->link_attr_cont.ac == cont; } /** * ata_tlink_delete -- remove an ATA link transport device * @link: struct ata_link owning the link transport device to remove * * Removes the link transport device of the specified ATA link. This also * removes the ATA device(s) associated with the link as well. */ void ata_tlink_delete(struct ata_link *link) { struct device *dev = &link->tdev; struct ata_device *ata_dev; ata_for_each_dev(ata_dev, link, ALL) { ata_tdev_delete(ata_dev); } transport_remove_device(dev); device_del(dev); transport_destroy_device(dev); put_device(dev); } /** * ata_tlink_add -- initialize an ATA link transport device * @link: struct ata_link owning the link transport device to initialize * * Initialize an ATA link transport device for sysfs. It will be added in the * device tree below the ATA port it belongs to. * * Returns %0 on success and a negative error code on error. */ int ata_tlink_add(struct ata_link *link) { struct device *dev = &link->tdev; struct ata_port *ap = link->ap; struct ata_device *ata_dev; int error; device_initialize(dev); dev->parent = &ap->tdev; dev->release = ata_tlink_release; if (ata_is_host_link(link)) dev_set_name(dev, "link%d", ap->print_id); else dev_set_name(dev, "link%d.%d", ap->print_id, link->pmp); transport_setup_device(dev); error = device_add(dev); if (error) goto tlink_err; error = transport_add_device(dev); if (error) goto tlink_transport_err; transport_configure_device(dev); ata_for_each_dev(ata_dev, link, ALL) { error = ata_tdev_add(ata_dev); if (error) goto tlink_dev_err; } return 0; tlink_dev_err: while (--ata_dev >= link->device) ata_tdev_delete(ata_dev); transport_remove_device(dev); tlink_transport_err: device_del(dev); tlink_err: transport_destroy_device(dev); put_device(dev); return error; } /* * Setup / Teardown code */ #define SETUP_TEMPLATE(attrb, field, perm, test) \ i->private_##attrb[count] = dev_attr_##field; \ i->private_##attrb[count].attr.mode = perm; \ i->attrb[count] = &i->private_##attrb[count]; \ if (test) \ count++ #define SETUP_LINK_ATTRIBUTE(field) \ SETUP_TEMPLATE(link_attrs, field, S_IRUGO, 1) #define SETUP_PORT_ATTRIBUTE(field) \ SETUP_TEMPLATE(port_attrs, field, S_IRUGO, 1) #define SETUP_DEV_ATTRIBUTE(field) \ SETUP_TEMPLATE(dev_attrs, field, S_IRUGO, 1) /** * ata_attach_transport -- instantiate ATA transport template */ struct scsi_transport_template *ata_attach_transport(void) { struct ata_internal *i; int count; i = kzalloc(sizeof(struct ata_internal), GFP_KERNEL); if (!i) return NULL; i->t.eh_strategy_handler = ata_scsi_error; i->t.user_scan = ata_scsi_user_scan; i->t.host_attrs.ac.attrs = &i->port_attrs[0]; i->t.host_attrs.ac.class = &ata_port_class.class; i->t.host_attrs.ac.match = ata_tport_match; transport_container_register(&i->t.host_attrs); i->link_attr_cont.ac.class = &ata_link_class.class; i->link_attr_cont.ac.attrs = &i->link_attrs[0]; i->link_attr_cont.ac.match = ata_tlink_match; transport_container_register(&i->link_attr_cont); i->dev_attr_cont.ac.class = &ata_dev_class.class; i->dev_attr_cont.ac.attrs = &i->dev_attrs[0]; i->dev_attr_cont.ac.match = ata_tdev_match; transport_container_register(&i->dev_attr_cont); count = 0; SETUP_PORT_ATTRIBUTE(nr_pmp_links); SETUP_PORT_ATTRIBUTE(idle_irq); SETUP_PORT_ATTRIBUTE(port_no); BUG_ON(count > ATA_PORT_ATTRS); i->port_attrs[count] = NULL; count = 0; SETUP_LINK_ATTRIBUTE(hw_sata_spd_limit); SETUP_LINK_ATTRIBUTE(sata_spd_limit); SETUP_LINK_ATTRIBUTE(sata_spd); BUG_ON(count > ATA_LINK_ATTRS); i->link_attrs[count] = NULL; count = 0; SETUP_DEV_ATTRIBUTE(class); SETUP_DEV_ATTRIBUTE(pio_mode); SETUP_DEV_ATTRIBUTE(dma_mode); SETUP_DEV_ATTRIBUTE(xfer_mode); SETUP_DEV_ATTRIBUTE(spdn_cnt); SETUP_DEV_ATTRIBUTE(ering); SETUP_DEV_ATTRIBUTE(id); SETUP_DEV_ATTRIBUTE(gscr); SETUP_DEV_ATTRIBUTE(trim); BUG_ON(count > ATA_DEV_ATTRS); i->dev_attrs[count] = NULL; return &i->t; } /** * ata_release_transport -- release ATA transport template instance * @t: transport template instance */ void ata_release_transport(struct scsi_transport_template *t) { struct ata_internal *i = to_ata_internal(t); transport_container_unregister(&i->t.host_attrs); transport_container_unregister(&i->link_attr_cont); transport_container_unregister(&i->dev_attr_cont); kfree(i); } __init int libata_transport_init(void) { int error; error = transport_class_register(&ata_link_class); if (error) goto out_unregister_transport; error = transport_class_register(&ata_port_class); if (error) goto out_unregister_link; error = transport_class_register(&ata_dev_class); if (error) goto out_unregister_port; return 0; out_unregister_port: transport_class_unregister(&ata_port_class); out_unregister_link: transport_class_unregister(&ata_link_class); out_unregister_transport: return error; } void __exit libata_transport_exit(void) { transport_class_unregister(&ata_link_class); transport_class_unregister(&ata_port_class); transport_class_unregister(&ata_dev_class); } |
| 342 23 8 22 5 22 9 1 18 22 20 18 3 12 9 6 1 20 31 19 12 31 16 12 19 12 10 1 3 17 14 14 14 1 1 30 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Generic address resolution entity * * Authors: * net_random Alan Cox * net_ratelimit Andi Kleen * in{4,6}_pton YOSHIFUJI Hideaki, Copyright (C)2006 USAGI/WIDE Project * * Created by Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> */ #include <linux/module.h> #include <linux/jiffies.h> #include <linux/kernel.h> #include <linux/ctype.h> #include <linux/inet.h> #include <linux/mm.h> #include <linux/net.h> #include <linux/string.h> #include <linux/types.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/ratelimit.h> #include <linux/socket.h> #include <net/sock.h> #include <net/net_ratelimit.h> #include <net/ipv6.h> #include <asm/byteorder.h> #include <linux/uaccess.h> DEFINE_RATELIMIT_STATE(net_ratelimit_state, 5 * HZ, 10); /* * All net warning printk()s should be guarded by this function. */ int net_ratelimit(void) { return __ratelimit(&net_ratelimit_state); } EXPORT_SYMBOL(net_ratelimit); /* * Convert an ASCII string to binary IP. * This is outside of net/ipv4/ because various code that uses IP addresses * is otherwise not dependent on the TCP/IP stack. */ __be32 in_aton(const char *str) { unsigned int l; unsigned int val; int i; l = 0; for (i = 0; i < 4; i++) { l <<= 8; if (*str != '\0') { val = 0; while (*str != '\0' && *str != '.' && *str != '\n') { val *= 10; val += *str - '0'; str++; } l |= val; if (*str != '\0') str++; } } return htonl(l); } EXPORT_SYMBOL(in_aton); #define IN6PTON_XDIGIT 0x00010000 #define IN6PTON_DIGIT 0x00020000 #define IN6PTON_COLON_MASK 0x00700000 #define IN6PTON_COLON_1 0x00100000 /* single : requested */ #define IN6PTON_COLON_2 0x00200000 /* second : requested */ #define IN6PTON_COLON_1_2 0x00400000 /* :: requested */ #define IN6PTON_DOT 0x00800000 /* . */ #define IN6PTON_DELIM 0x10000000 #define IN6PTON_NULL 0x20000000 /* first/tail */ #define IN6PTON_UNKNOWN 0x40000000 static inline int xdigit2bin(char c, int delim) { int val; if (c == delim || c == '\0') return IN6PTON_DELIM; if (c == ':') return IN6PTON_COLON_MASK; if (c == '.') return IN6PTON_DOT; val = hex_to_bin(c); if (val >= 0) return val | IN6PTON_XDIGIT | (val < 10 ? IN6PTON_DIGIT : 0); if (delim == -1) return IN6PTON_DELIM; return IN6PTON_UNKNOWN; } /** * in4_pton - convert an IPv4 address from literal to binary representation * @src: the start of the IPv4 address string * @srclen: the length of the string, -1 means strlen(src) * @dst: the binary (u8[4] array) representation of the IPv4 address * @delim: the delimiter of the IPv4 address in @src, -1 means no delimiter * @end: A pointer to the end of the parsed string will be placed here * * Return one on success, return zero when any error occurs * and @end will point to the end of the parsed string. * */ int in4_pton(const char *src, int srclen, u8 *dst, int delim, const char **end) { const char *s; u8 *d; u8 dbuf[4]; int ret = 0; int i; int w = 0; if (srclen < 0) srclen = strlen(src); s = src; d = dbuf; i = 0; while (1) { int c; c = xdigit2bin(srclen > 0 ? *s : '\0', delim); if (!(c & (IN6PTON_DIGIT | IN6PTON_DOT | IN6PTON_DELIM | IN6PTON_COLON_MASK))) { goto out; } if (c & (IN6PTON_DOT | IN6PTON_DELIM | IN6PTON_COLON_MASK)) { if (w == 0) goto out; *d++ = w & 0xff; w = 0; i++; if (c & (IN6PTON_DELIM | IN6PTON_COLON_MASK)) { if (i != 4) goto out; break; } goto cont; } w = (w * 10) + c; if ((w & 0xffff) > 255) { goto out; } cont: if (i >= 4) goto out; s++; srclen--; } ret = 1; memcpy(dst, dbuf, sizeof(dbuf)); out: if (end) *end = s; return ret; } EXPORT_SYMBOL(in4_pton); /** * in6_pton - convert an IPv6 address from literal to binary representation * @src: the start of the IPv6 address string * @srclen: the length of the string, -1 means strlen(src) * @dst: the binary (u8[16] array) representation of the IPv6 address * @delim: the delimiter of the IPv6 address in @src, -1 means no delimiter * @end: A pointer to the end of the parsed string will be placed here * * Return one on success, return zero when any error occurs * and @end will point to the end of the parsed string. * */ int in6_pton(const char *src, int srclen, u8 *dst, int delim, const char **end) { const char *s, *tok = NULL; u8 *d, *dc = NULL; u8 dbuf[16]; int ret = 0; int i; int state = IN6PTON_COLON_1_2 | IN6PTON_XDIGIT | IN6PTON_NULL; int w = 0; memset(dbuf, 0, sizeof(dbuf)); s = src; d = dbuf; if (srclen < 0) srclen = strlen(src); while (1) { int c; c = xdigit2bin(srclen > 0 ? *s : '\0', delim); if (!(c & state)) goto out; if (c & (IN6PTON_DELIM | IN6PTON_COLON_MASK)) { /* process one 16-bit word */ if (!(state & IN6PTON_NULL)) { *d++ = (w >> 8) & 0xff; *d++ = w & 0xff; } w = 0; if (c & IN6PTON_DELIM) { /* We've processed last word */ break; } /* * COLON_1 => XDIGIT * COLON_2 => XDIGIT|DELIM * COLON_1_2 => COLON_2 */ switch (state & IN6PTON_COLON_MASK) { case IN6PTON_COLON_2: dc = d; state = IN6PTON_XDIGIT | IN6PTON_DELIM; if (dc - dbuf >= sizeof(dbuf)) state |= IN6PTON_NULL; break; case IN6PTON_COLON_1|IN6PTON_COLON_1_2: state = IN6PTON_XDIGIT | IN6PTON_COLON_2; break; case IN6PTON_COLON_1: state = IN6PTON_XDIGIT; break; case IN6PTON_COLON_1_2: state = IN6PTON_COLON_2; break; default: state = 0; } tok = s + 1; goto cont; } if (c & IN6PTON_DOT) { ret = in4_pton(tok ? tok : s, srclen + (int)(s - tok), d, delim, &s); if (ret > 0) { d += 4; break; } goto out; } w = (w << 4) | (0xff & c); state = IN6PTON_COLON_1 | IN6PTON_DELIM; if (!(w & 0xf000)) { state |= IN6PTON_XDIGIT; } if (!dc && d + 2 < dbuf + sizeof(dbuf)) { state |= IN6PTON_COLON_1_2; state &= ~IN6PTON_DELIM; } if (d + 2 >= dbuf + sizeof(dbuf)) { state &= ~(IN6PTON_COLON_1|IN6PTON_COLON_1_2); } cont: if ((dc && d + 4 < dbuf + sizeof(dbuf)) || d + 4 == dbuf + sizeof(dbuf)) { state |= IN6PTON_DOT; } if (d >= dbuf + sizeof(dbuf)) { state &= ~(IN6PTON_XDIGIT|IN6PTON_COLON_MASK); } s++; srclen--; } i = 15; d--; if (dc) { while (d >= dc) dst[i--] = *d--; while (i >= dc - dbuf) dst[i--] = 0; while (i >= 0) dst[i--] = *d--; } else memcpy(dst, dbuf, sizeof(dbuf)); ret = 1; out: if (end) *end = s; return ret; } EXPORT_SYMBOL(in6_pton); static int inet4_pton(const char *src, u16 port_num, struct sockaddr_storage *addr) { struct sockaddr_in *addr4 = (struct sockaddr_in *)addr; size_t srclen = strlen(src); if (srclen > INET_ADDRSTRLEN) return -EINVAL; if (in4_pton(src, srclen, (u8 *)&addr4->sin_addr.s_addr, '\n', NULL) == 0) return -EINVAL; addr4->sin_family = AF_INET; addr4->sin_port = htons(port_num); return 0; } static int inet6_pton(struct net *net, const char *src, u16 port_num, struct sockaddr_storage *addr) { struct sockaddr_in6 *addr6 = (struct sockaddr_in6 *)addr; const char *scope_delim; size_t srclen = strlen(src); if (srclen > INET6_ADDRSTRLEN) return -EINVAL; if (in6_pton(src, srclen, (u8 *)&addr6->sin6_addr.s6_addr, '%', &scope_delim) == 0) return -EINVAL; if (ipv6_addr_type(&addr6->sin6_addr) & IPV6_ADDR_LINKLOCAL && src + srclen != scope_delim && *scope_delim == '%') { struct net_device *dev; char scope_id[16]; size_t scope_len = min_t(size_t, sizeof(scope_id) - 1, src + srclen - scope_delim - 1); memcpy(scope_id, scope_delim + 1, scope_len); scope_id[scope_len] = '\0'; dev = dev_get_by_name(net, scope_id); if (dev) { addr6->sin6_scope_id = dev->ifindex; dev_put(dev); } else if (kstrtouint(scope_id, 0, &addr6->sin6_scope_id)) { return -EINVAL; } } addr6->sin6_family = AF_INET6; addr6->sin6_port = htons(port_num); return 0; } /** * inet_pton_with_scope - convert an IPv4/IPv6 and port to socket address * @net: net namespace (used for scope handling) * @af: address family, AF_INET, AF_INET6 or AF_UNSPEC for either * @src: the start of the address string * @port: the start of the port string (or NULL for none) * @addr: output socket address * * Return zero on success, return errno when any error occurs. */ int inet_pton_with_scope(struct net *net, __kernel_sa_family_t af, const char *src, const char *port, struct sockaddr_storage *addr) { u16 port_num; int ret = -EINVAL; if (port) { if (kstrtou16(port, 0, &port_num)) return -EINVAL; } else { port_num = 0; } switch (af) { case AF_INET: ret = inet4_pton(src, port_num, addr); break; case AF_INET6: ret = inet6_pton(net, src, port_num, addr); break; case AF_UNSPEC: ret = inet4_pton(src, port_num, addr); if (ret) ret = inet6_pton(net, src, port_num, addr); break; default: pr_err("unexpected address family %d\n", af); } return ret; } EXPORT_SYMBOL(inet_pton_with_scope); bool inet_addr_is_any(struct sockaddr *addr) { if (addr->sa_family == AF_INET6) { struct sockaddr_in6 *in6 = (struct sockaddr_in6 *)addr; const struct sockaddr_in6 in6_any = { .sin6_addr = IN6ADDR_ANY_INIT }; if (!memcmp(in6->sin6_addr.s6_addr, in6_any.sin6_addr.s6_addr, 16)) return true; } else if (addr->sa_family == AF_INET) { struct sockaddr_in *in = (struct sockaddr_in *)addr; if (in->sin_addr.s_addr == htonl(INADDR_ANY)) return true; } else { pr_warn("unexpected address family %u\n", addr->sa_family); } return false; } EXPORT_SYMBOL(inet_addr_is_any); void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb, __be32 from, __be32 to, bool pseudohdr) { if (skb->ip_summed != CHECKSUM_PARTIAL) { csum_replace4(sum, from, to); if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr) skb->csum = ~csum_add(csum_sub(~(skb->csum), (__force __wsum)from), (__force __wsum)to); } else if (pseudohdr) *sum = ~csum_fold(csum_add(csum_sub(csum_unfold(*sum), (__force __wsum)from), (__force __wsum)to)); } EXPORT_SYMBOL(inet_proto_csum_replace4); /** * inet_proto_csum_replace16 - update layer 4 header checksum field * @sum: Layer 4 header checksum field * @skb: sk_buff for the packet * @from: old IPv6 address * @to: new IPv6 address * @pseudohdr: True if layer 4 header checksum includes pseudoheader * * Update layer 4 header as per the update in IPv6 src/dst address. * * There is no need to update skb->csum in this function, because update in two * fields a.) IPv6 src/dst address and b.) L4 header checksum cancels each other * for skb->csum calculation. Whereas inet_proto_csum_replace4 function needs to * update skb->csum, because update in 3 fields a.) IPv4 src/dst address, * b.) IPv4 Header checksum and c.) L4 header checksum results in same diff as * L4 Header checksum for skb->csum calculation. */ void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb, const __be32 *from, const __be32 *to, bool pseudohdr) { __be32 diff[] = { ~from[0], ~from[1], ~from[2], ~from[3], to[0], to[1], to[2], to[3], }; if (skb->ip_summed != CHECKSUM_PARTIAL) { *sum = csum_fold(csum_partial(diff, sizeof(diff), ~csum_unfold(*sum))); } else if (pseudohdr) *sum = ~csum_fold(csum_partial(diff, sizeof(diff), csum_unfold(*sum))); } EXPORT_SYMBOL(inet_proto_csum_replace16); void inet_proto_csum_replace_by_diff(__sum16 *sum, struct sk_buff *skb, __wsum diff, bool pseudohdr) { if (skb->ip_summed != CHECKSUM_PARTIAL) { csum_replace_by_diff(sum, diff); if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr) skb->csum = ~csum_sub(diff, skb->csum); } else if (pseudohdr) { *sum = ~csum_fold(csum_add(diff, csum_unfold(*sum))); } } EXPORT_SYMBOL(inet_proto_csum_replace_by_diff); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_TASK_STACK_H #define _LINUX_SCHED_TASK_STACK_H /* * task->stack (kernel stack) handling interfaces: */ #include <linux/sched.h> #include <linux/magic.h> #include <linux/refcount.h> #include <linux/kasan.h> #ifdef CONFIG_THREAD_INFO_IN_TASK /* * When accessing the stack of a non-current task that might exit, use * try_get_task_stack() instead. task_stack_page will return a pointer * that could get freed out from under you. */ static __always_inline void *task_stack_page(const struct task_struct *task) { return task->stack; } #define setup_thread_stack(new,old) do { } while(0) static __always_inline unsigned long *end_of_stack(const struct task_struct *task) { #ifdef CONFIG_STACK_GROWSUP return (unsigned long *)((unsigned long)task->stack + THREAD_SIZE) - 1; #else return task->stack; #endif } #else #define task_stack_page(task) ((void *)(task)->stack) static inline void setup_thread_stack(struct task_struct *p, struct task_struct *org) { *task_thread_info(p) = *task_thread_info(org); task_thread_info(p)->task = p; } /* * Return the address of the last usable long on the stack. * * When the stack grows down, this is just above the thread * info struct. Going any lower will corrupt the threadinfo. * * When the stack grows up, this is the highest address. * Beyond that position, we corrupt data on the next page. */ static inline unsigned long *end_of_stack(struct task_struct *p) { #ifdef CONFIG_STACK_GROWSUP return (unsigned long *)((unsigned long)task_thread_info(p) + THREAD_SIZE) - 1; #else return (unsigned long *)(task_thread_info(p) + 1); #endif } #endif #ifdef CONFIG_THREAD_INFO_IN_TASK static inline void *try_get_task_stack(struct task_struct *tsk) { return refcount_inc_not_zero(&tsk->stack_refcount) ? task_stack_page(tsk) : NULL; } extern void put_task_stack(struct task_struct *tsk); #else static inline void *try_get_task_stack(struct task_struct *tsk) { return task_stack_page(tsk); } static inline void put_task_stack(struct task_struct *tsk) {} #endif void exit_task_stack_account(struct task_struct *tsk); #define task_stack_end_corrupted(task) \ (*(end_of_stack(task)) != STACK_END_MAGIC) static inline int object_is_on_stack(const void *obj) { void *stack = task_stack_page(current); obj = kasan_reset_tag(obj); return (obj >= stack) && (obj < (stack + THREAD_SIZE)); } extern void thread_stack_cache_init(void); #ifdef CONFIG_DEBUG_STACK_USAGE unsigned long stack_not_used(struct task_struct *p); #else static inline unsigned long stack_not_used(struct task_struct *p) { return 0; } #endif extern void set_task_stack_end_magic(struct task_struct *tsk); #ifndef __HAVE_ARCH_KSTACK_END static inline int kstack_end(void *addr) { /* Reliable end of stack detection: * Some APM bios versions misalign the stack */ return !(((unsigned long)addr+sizeof(void*)-1) & (THREAD_SIZE-sizeof(void*))); } #endif #endif /* _LINUX_SCHED_TASK_STACK_H */ |
| 87 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _FB_DRAW_H #define _FB_DRAW_H #include <asm/types.h> #include <linux/fb.h> #include <linux/bug.h> /* * Compose two values, using a bitmask as decision value * This is equivalent to (a & mask) | (b & ~mask) */ static inline unsigned long comp(unsigned long a, unsigned long b, unsigned long mask) { return ((a ^ b) & mask) ^ b; } /* * Create a pattern with the given pixel's color */ #if BITS_PER_LONG == 64 static inline unsigned long pixel_to_pat( u32 bpp, u32 pixel) { switch (bpp) { case 1: return 0xfffffffffffffffful*pixel; case 2: return 0x5555555555555555ul*pixel; case 4: return 0x1111111111111111ul*pixel; case 8: return 0x0101010101010101ul*pixel; case 12: return 0x1001001001001001ul*pixel; case 16: return 0x0001000100010001ul*pixel; case 24: return 0x0001000001000001ul*pixel; case 32: return 0x0000000100000001ul*pixel; default: WARN(1, "pixel_to_pat(): unsupported pixelformat %d\n", bpp); return 0; } } #else static inline unsigned long pixel_to_pat( u32 bpp, u32 pixel) { switch (bpp) { case 1: return 0xfffffffful*pixel; case 2: return 0x55555555ul*pixel; case 4: return 0x11111111ul*pixel; case 8: return 0x01010101ul*pixel; case 12: return 0x01001001ul*pixel; case 16: return 0x00010001ul*pixel; case 24: return 0x01000001ul*pixel; case 32: return 0x00000001ul*pixel; default: WARN(1, "pixel_to_pat(): unsupported pixelformat %d\n", bpp); return 0; } } #endif #ifdef CONFIG_FB_CFB_REV_PIXELS_IN_BYTE #if BITS_PER_LONG == 64 #define REV_PIXELS_MASK1 0x5555555555555555ul #define REV_PIXELS_MASK2 0x3333333333333333ul #define REV_PIXELS_MASK4 0x0f0f0f0f0f0f0f0ful #else #define REV_PIXELS_MASK1 0x55555555ul #define REV_PIXELS_MASK2 0x33333333ul #define REV_PIXELS_MASK4 0x0f0f0f0ful #endif static inline unsigned long fb_rev_pixels_in_long(unsigned long val, u32 bswapmask) { if (bswapmask & 1) val = comp(val >> 1, val << 1, REV_PIXELS_MASK1); if (bswapmask & 2) val = comp(val >> 2, val << 2, REV_PIXELS_MASK2); if (bswapmask & 3) val = comp(val >> 4, val << 4, REV_PIXELS_MASK4); return val; } static inline u32 fb_shifted_pixels_mask_u32(struct fb_info *p, u32 index, u32 bswapmask) { u32 mask; if (!bswapmask) { mask = FB_SHIFT_HIGH(p, ~(u32)0, index); } else { mask = 0xff << FB_LEFT_POS(p, 8); mask = FB_SHIFT_LOW(p, mask, index & (bswapmask)) & mask; mask = FB_SHIFT_HIGH(p, mask, index & ~(bswapmask)); #if defined(__i386__) || defined(__x86_64__) /* Shift argument is limited to 0 - 31 on x86 based CPU's */ if(index + bswapmask < 32) #endif mask |= FB_SHIFT_HIGH(p, ~(u32)0, (index + bswapmask) & ~(bswapmask)); } return mask; } static inline unsigned long fb_shifted_pixels_mask_long(struct fb_info *p, u32 index, u32 bswapmask) { unsigned long mask; if (!bswapmask) { mask = FB_SHIFT_HIGH(p, ~0UL, index); } else { mask = 0xff << FB_LEFT_POS(p, 8); mask = FB_SHIFT_LOW(p, mask, index & (bswapmask)) & mask; mask = FB_SHIFT_HIGH(p, mask, index & ~(bswapmask)); #if defined(__i386__) || defined(__x86_64__) /* Shift argument is limited to 0 - 31 on x86 based CPU's */ if(index + bswapmask < BITS_PER_LONG) #endif mask |= FB_SHIFT_HIGH(p, ~0UL, (index + bswapmask) & ~(bswapmask)); } return mask; } static inline u32 fb_compute_bswapmask(struct fb_info *info) { u32 bswapmask = 0; unsigned bpp = info->var.bits_per_pixel; if ((bpp < 8) && (info->var.nonstd & FB_NONSTD_REV_PIX_IN_B)) { /* * Reversed order of pixel layout in bytes * works only for 1, 2 and 4 bpp */ bswapmask = 7 - bpp + 1; } return bswapmask; } #else /* CONFIG_FB_CFB_REV_PIXELS_IN_BYTE */ static inline unsigned long fb_rev_pixels_in_long(unsigned long val, u32 bswapmask) { return val; } #define fb_shifted_pixels_mask_u32(p, i, b) FB_SHIFT_HIGH((p), ~(u32)0, (i)) #define fb_shifted_pixels_mask_long(p, i, b) FB_SHIFT_HIGH((p), ~0UL, (i)) #define fb_compute_bswapmask(...) 0 #endif /* CONFIG_FB_CFB_REV_PIXELS_IN_BYTE */ #define cpu_to_le_long _cpu_to_le_long(BITS_PER_LONG) #define _cpu_to_le_long(x) __cpu_to_le_long(x) #define __cpu_to_le_long(x) cpu_to_le##x #define le_long_to_cpu _le_long_to_cpu(BITS_PER_LONG) #define _le_long_to_cpu(x) __le_long_to_cpu(x) #define __le_long_to_cpu(x) le##x##_to_cpu static inline unsigned long rolx(unsigned long word, unsigned int shift, unsigned int x) { return (word << shift) | (word >> (x - shift)); } #endif /* FB_DRAW_H */ |
| 19 3 8 8 8 11 11 3 3 1 3 3 3 13 14 1 3 18 19 19 19 18 1 12 14 14 14 11 11 1 11 11 1 1 11 1 3 11 11 11 3 11 11 11 11 1 3 3 11 11 11 14 14 14 14 14 14 14 27 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2008 Red Hat. All rights reserved. */ #include <linux/pagemap.h> #include <linux/sched.h> #include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/math64.h> #include <linux/ratelimit.h> #include <linux/error-injection.h> #include <linux/sched/mm.h> #include <linux/string_choices.h> #include "ctree.h" #include "fs.h" #include "messages.h" #include "misc.h" #include "free-space-cache.h" #include "transaction.h" #include "disk-io.h" #include "extent_io.h" #include "space-info.h" #include "block-group.h" #include "discard.h" #include "subpage.h" #include "inode-item.h" #include "accessors.h" #include "file-item.h" #include "file.h" #include "super.h" #define BITS_PER_BITMAP (PAGE_SIZE * 8UL) #define MAX_CACHE_BYTES_PER_GIG SZ_64K #define FORCE_EXTENT_THRESHOLD SZ_1M static struct kmem_cache *btrfs_free_space_cachep; static struct kmem_cache *btrfs_free_space_bitmap_cachep; struct btrfs_trim_range { u64 start; u64 bytes; struct list_head list; }; static int link_free_space(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *info); static void unlink_free_space(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *info, bool update_stat); static int search_bitmap(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *bitmap_info, u64 *offset, u64 *bytes, bool for_alloc); static void free_bitmap(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *bitmap_info); static void bitmap_clear_bits(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *info, u64 offset, u64 bytes, bool update_stats); static void btrfs_crc32c_final(u32 crc, u8 *result) { put_unaligned_le32(~crc, result); } static void __btrfs_remove_free_space_cache(struct btrfs_free_space_ctl *ctl) { struct btrfs_free_space *info; struct rb_node *node; while ((node = rb_last(&ctl->free_space_offset)) != NULL) { info = rb_entry(node, struct btrfs_free_space, offset_index); if (!info->bitmap) { unlink_free_space(ctl, info, true); kmem_cache_free(btrfs_free_space_cachep, info); } else { free_bitmap(ctl, info); } cond_resched_lock(&ctl->tree_lock); } } static struct inode *__lookup_free_space_inode(struct btrfs_root *root, struct btrfs_path *path, u64 offset) { struct btrfs_key key; struct btrfs_key location; struct btrfs_disk_key disk_key; struct btrfs_free_space_header *header; struct extent_buffer *leaf; struct inode *inode = NULL; unsigned nofs_flag; int ret; key.objectid = BTRFS_FREE_SPACE_OBJECTID; key.offset = offset; key.type = 0; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) return ERR_PTR(ret); if (ret > 0) { btrfs_release_path(path); return ERR_PTR(-ENOENT); } leaf = path->nodes[0]; header = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_free_space_header); btrfs_free_space_key(leaf, header, &disk_key); btrfs_disk_key_to_cpu(&location, &disk_key); btrfs_release_path(path); /* * We are often under a trans handle at this point, so we need to make * sure NOFS is set to keep us from deadlocking. */ nofs_flag = memalloc_nofs_save(); inode = btrfs_iget_path(location.objectid, root, path); btrfs_release_path(path); memalloc_nofs_restore(nofs_flag); if (IS_ERR(inode)) return inode; mapping_set_gfp_mask(inode->i_mapping, mapping_gfp_constraint(inode->i_mapping, ~(__GFP_FS | __GFP_HIGHMEM))); return inode; } struct inode *lookup_free_space_inode(struct btrfs_block_group *block_group, struct btrfs_path *path) { struct btrfs_fs_info *fs_info = block_group->fs_info; struct inode *inode = NULL; u32 flags = BTRFS_INODE_NODATASUM | BTRFS_INODE_NODATACOW; spin_lock(&block_group->lock); if (block_group->inode) inode = igrab(&block_group->inode->vfs_inode); spin_unlock(&block_group->lock); if (inode) return inode; inode = __lookup_free_space_inode(fs_info->tree_root, path, block_group->start); if (IS_ERR(inode)) return inode; spin_lock(&block_group->lock); if (!((BTRFS_I(inode)->flags & flags) == flags)) { btrfs_info(fs_info, "Old style space inode found, converting."); BTRFS_I(inode)->flags |= BTRFS_INODE_NODATASUM | BTRFS_INODE_NODATACOW; block_group->disk_cache_state = BTRFS_DC_CLEAR; } if (!test_and_set_bit(BLOCK_GROUP_FLAG_IREF, &block_group->runtime_flags)) block_group->inode = BTRFS_I(igrab(inode)); spin_unlock(&block_group->lock); return inode; } static int __create_free_space_inode(struct btrfs_root *root, struct btrfs_trans_handle *trans, struct btrfs_path *path, u64 ino, u64 offset) { struct btrfs_key key; struct btrfs_disk_key disk_key; struct btrfs_free_space_header *header; struct btrfs_inode_item *inode_item; struct extent_buffer *leaf; /* We inline CRCs for the free disk space cache */ const u64 flags = BTRFS_INODE_NOCOMPRESS | BTRFS_INODE_PREALLOC | BTRFS_INODE_NODATASUM | BTRFS_INODE_NODATACOW; int ret; ret = btrfs_insert_empty_inode(trans, root, path, ino); if (ret) return ret; leaf = path->nodes[0]; inode_item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_inode_item); btrfs_item_key(leaf, &disk_key, path->slots[0]); memzero_extent_buffer(leaf, (unsigned long)inode_item, sizeof(*inode_item)); btrfs_set_inode_generation(leaf, inode_item, trans->transid); btrfs_set_inode_size(leaf, inode_item, 0); btrfs_set_inode_nbytes(leaf, inode_item, 0); btrfs_set_inode_uid(leaf, inode_item, 0); btrfs_set_inode_gid(leaf, inode_item, 0); btrfs_set_inode_mode(leaf, inode_item, S_IFREG | 0600); btrfs_set_inode_flags(leaf, inode_item, flags); btrfs_set_inode_nlink(leaf, inode_item, 1); btrfs_set_inode_transid(leaf, inode_item, trans->transid); btrfs_set_inode_block_group(leaf, inode_item, offset); btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); key.objectid = BTRFS_FREE_SPACE_OBJECTID; key.offset = offset; key.type = 0; ret = btrfs_insert_empty_item(trans, root, path, &key, sizeof(struct btrfs_free_space_header)); if (ret < 0) { btrfs_release_path(path); return ret; } leaf = path->nodes[0]; header = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_free_space_header); memzero_extent_buffer(leaf, (unsigned long)header, sizeof(*header)); btrfs_set_free_space_key(leaf, header, &disk_key); btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); return 0; } int create_free_space_inode(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path) { int ret; u64 ino; ret = btrfs_get_free_objectid(trans->fs_info->tree_root, &ino); if (ret < 0) return ret; return __create_free_space_inode(trans->fs_info->tree_root, trans, path, ino, block_group->start); } /* * inode is an optional sink: if it is NULL, btrfs_remove_free_space_inode * handles lookup, otherwise it takes ownership and iputs the inode. * Don't reuse an inode pointer after passing it into this function. */ int btrfs_remove_free_space_inode(struct btrfs_trans_handle *trans, struct inode *inode, struct btrfs_block_group *block_group) { struct btrfs_path *path; struct btrfs_key key; int ret = 0; path = btrfs_alloc_path(); if (!path) return -ENOMEM; if (!inode) inode = lookup_free_space_inode(block_group, path); if (IS_ERR(inode)) { if (PTR_ERR(inode) != -ENOENT) ret = PTR_ERR(inode); goto out; } ret = btrfs_orphan_add(trans, BTRFS_I(inode)); if (ret) { btrfs_add_delayed_iput(BTRFS_I(inode)); goto out; } clear_nlink(inode); /* One for the block groups ref */ spin_lock(&block_group->lock); if (test_and_clear_bit(BLOCK_GROUP_FLAG_IREF, &block_group->runtime_flags)) { block_group->inode = NULL; spin_unlock(&block_group->lock); iput(inode); } else { spin_unlock(&block_group->lock); } /* One for the lookup ref */ btrfs_add_delayed_iput(BTRFS_I(inode)); key.objectid = BTRFS_FREE_SPACE_OBJECTID; key.type = 0; key.offset = block_group->start; ret = btrfs_search_slot(trans, trans->fs_info->tree_root, &key, path, -1, 1); if (ret) { if (ret > 0) ret = 0; goto out; } ret = btrfs_del_item(trans, trans->fs_info->tree_root, path); out: btrfs_free_path(path); return ret; } int btrfs_truncate_free_space_cache(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct inode *vfs_inode) { struct btrfs_truncate_control control = { .inode = BTRFS_I(vfs_inode), .new_size = 0, .ino = btrfs_ino(BTRFS_I(vfs_inode)), .min_type = BTRFS_EXTENT_DATA_KEY, .clear_extent_range = true, }; struct btrfs_inode *inode = BTRFS_I(vfs_inode); struct btrfs_root *root = inode->root; struct extent_state *cached_state = NULL; int ret = 0; bool locked = false; if (block_group) { struct btrfs_path *path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; goto fail; } locked = true; mutex_lock(&trans->transaction->cache_write_mutex); if (!list_empty(&block_group->io_list)) { list_del_init(&block_group->io_list); btrfs_wait_cache_io(trans, block_group, path); btrfs_put_block_group(block_group); } /* * now that we've truncated the cache away, its no longer * setup or written */ spin_lock(&block_group->lock); block_group->disk_cache_state = BTRFS_DC_CLEAR; spin_unlock(&block_group->lock); btrfs_free_path(path); } btrfs_i_size_write(inode, 0); truncate_pagecache(vfs_inode, 0); lock_extent(&inode->io_tree, 0, (u64)-1, &cached_state); btrfs_drop_extent_map_range(inode, 0, (u64)-1, false); /* * We skip the throttling logic for free space cache inodes, so we don't * need to check for -EAGAIN. */ ret = btrfs_truncate_inode_items(trans, root, &control); inode_sub_bytes(&inode->vfs_inode, control.sub_bytes); btrfs_inode_safe_disk_i_size_write(inode, control.last_size); unlock_extent(&inode->io_tree, 0, (u64)-1, &cached_state); if (ret) goto fail; ret = btrfs_update_inode(trans, inode); fail: if (locked) mutex_unlock(&trans->transaction->cache_write_mutex); if (ret) btrfs_abort_transaction(trans, ret); return ret; } static void readahead_cache(struct inode *inode) { struct file_ra_state ra; unsigned long last_index; file_ra_state_init(&ra, inode->i_mapping); last_index = (i_size_read(inode) - 1) >> PAGE_SHIFT; page_cache_sync_readahead(inode->i_mapping, &ra, NULL, 0, last_index); } static int io_ctl_init(struct btrfs_io_ctl *io_ctl, struct inode *inode, int write) { int num_pages; num_pages = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); /* Make sure we can fit our crcs and generation into the first page */ if (write && (num_pages * sizeof(u32) + sizeof(u64)) > PAGE_SIZE) return -ENOSPC; memset(io_ctl, 0, sizeof(struct btrfs_io_ctl)); io_ctl->pages = kcalloc(num_pages, sizeof(struct page *), GFP_NOFS); if (!io_ctl->pages) return -ENOMEM; io_ctl->num_pages = num_pages; io_ctl->fs_info = inode_to_fs_info(inode); io_ctl->inode = inode; return 0; } ALLOW_ERROR_INJECTION(io_ctl_init, ERRNO); static void io_ctl_free(struct btrfs_io_ctl *io_ctl) { kfree(io_ctl->pages); io_ctl->pages = NULL; } static void io_ctl_unmap_page(struct btrfs_io_ctl *io_ctl) { if (io_ctl->cur) { io_ctl->cur = NULL; io_ctl->orig = NULL; } } static void io_ctl_map_page(struct btrfs_io_ctl *io_ctl, int clear) { ASSERT(io_ctl->index < io_ctl->num_pages); io_ctl->page = io_ctl->pages[io_ctl->index++]; io_ctl->cur = page_address(io_ctl->page); io_ctl->orig = io_ctl->cur; io_ctl->size = PAGE_SIZE; if (clear) clear_page(io_ctl->cur); } static void io_ctl_drop_pages(struct btrfs_io_ctl *io_ctl) { int i; io_ctl_unmap_page(io_ctl); for (i = 0; i < io_ctl->num_pages; i++) { if (io_ctl->pages[i]) { btrfs_folio_clear_checked(io_ctl->fs_info, page_folio(io_ctl->pages[i]), page_offset(io_ctl->pages[i]), PAGE_SIZE); unlock_page(io_ctl->pages[i]); put_page(io_ctl->pages[i]); } } } static int io_ctl_prepare_pages(struct btrfs_io_ctl *io_ctl, bool uptodate) { struct page *page; struct inode *inode = io_ctl->inode; gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping); int i; for (i = 0; i < io_ctl->num_pages; i++) { int ret; page = find_or_create_page(inode->i_mapping, i, mask); if (!page) { io_ctl_drop_pages(io_ctl); return -ENOMEM; } ret = set_page_extent_mapped(page); if (ret < 0) { unlock_page(page); put_page(page); io_ctl_drop_pages(io_ctl); return ret; } io_ctl->pages[i] = page; if (uptodate && !PageUptodate(page)) { btrfs_read_folio(NULL, page_folio(page)); lock_page(page); if (page->mapping != inode->i_mapping) { btrfs_err(BTRFS_I(inode)->root->fs_info, "free space cache page truncated"); io_ctl_drop_pages(io_ctl); return -EIO; } if (!PageUptodate(page)) { btrfs_err(BTRFS_I(inode)->root->fs_info, "error reading free space cache"); io_ctl_drop_pages(io_ctl); return -EIO; } } } for (i = 0; i < io_ctl->num_pages; i++) clear_page_dirty_for_io(io_ctl->pages[i]); return 0; } static void io_ctl_set_generation(struct btrfs_io_ctl *io_ctl, u64 generation) { io_ctl_map_page(io_ctl, 1); /* * Skip the csum areas. If we don't check crcs then we just have a * 64bit chunk at the front of the first page. */ io_ctl->cur += (sizeof(u32) * io_ctl->num_pages); io_ctl->size -= sizeof(u64) + (sizeof(u32) * io_ctl->num_pages); put_unaligned_le64(generation, io_ctl->cur); io_ctl->cur += sizeof(u64); } static int io_ctl_check_generation(struct btrfs_io_ctl *io_ctl, u64 generation) { u64 cache_gen; /* * Skip the crc area. If we don't check crcs then we just have a 64bit * chunk at the front of the first page. */ io_ctl->cur += sizeof(u32) * io_ctl->num_pages; io_ctl->size -= sizeof(u64) + (sizeof(u32) * io_ctl->num_pages); cache_gen = get_unaligned_le64(io_ctl->cur); if (cache_gen != generation) { btrfs_err_rl(io_ctl->fs_info, "space cache generation (%llu) does not match inode (%llu)", cache_gen, generation); io_ctl_unmap_page(io_ctl); return -EIO; } io_ctl->cur += sizeof(u64); return 0; } static void io_ctl_set_crc(struct btrfs_io_ctl *io_ctl, int index) { u32 *tmp; u32 crc = ~(u32)0; unsigned offset = 0; if (index == 0) offset = sizeof(u32) * io_ctl->num_pages; crc = crc32c(crc, io_ctl->orig + offset, PAGE_SIZE - offset); btrfs_crc32c_final(crc, (u8 *)&crc); io_ctl_unmap_page(io_ctl); tmp = page_address(io_ctl->pages[0]); tmp += index; *tmp = crc; } static int io_ctl_check_crc(struct btrfs_io_ctl *io_ctl, int index) { u32 *tmp, val; u32 crc = ~(u32)0; unsigned offset = 0; if (index == 0) offset = sizeof(u32) * io_ctl->num_pages; tmp = page_address(io_ctl->pages[0]); tmp += index; val = *tmp; io_ctl_map_page(io_ctl, 0); crc = crc32c(crc, io_ctl->orig + offset, PAGE_SIZE - offset); btrfs_crc32c_final(crc, (u8 *)&crc); if (val != crc) { btrfs_err_rl(io_ctl->fs_info, "csum mismatch on free space cache"); io_ctl_unmap_page(io_ctl); return -EIO; } return 0; } static int io_ctl_add_entry(struct btrfs_io_ctl *io_ctl, u64 offset, u64 bytes, void *bitmap) { struct btrfs_free_space_entry *entry; if (!io_ctl->cur) return -ENOSPC; entry = io_ctl->cur; put_unaligned_le64(offset, &entry->offset); put_unaligned_le64(bytes, &entry->bytes); entry->type = (bitmap) ? BTRFS_FREE_SPACE_BITMAP : BTRFS_FREE_SPACE_EXTENT; io_ctl->cur += sizeof(struct btrfs_free_space_entry); io_ctl->size -= sizeof(struct btrfs_free_space_entry); if (io_ctl->size >= sizeof(struct btrfs_free_space_entry)) return 0; io_ctl_set_crc(io_ctl, io_ctl->index - 1); /* No more pages to map */ if (io_ctl->index >= io_ctl->num_pages) return 0; /* map the next page */ io_ctl_map_page(io_ctl, 1); return 0; } static int io_ctl_add_bitmap(struct btrfs_io_ctl *io_ctl, void *bitmap) { if (!io_ctl->cur) return -ENOSPC; /* * If we aren't at the start of the current page, unmap this one and * map the next one if there is any left. */ if (io_ctl->cur != io_ctl->orig) { io_ctl_set_crc(io_ctl, io_ctl->index - 1); if (io_ctl->index >= io_ctl->num_pages) return -ENOSPC; io_ctl_map_page(io_ctl, 0); } copy_page(io_ctl->cur, bitmap); io_ctl_set_crc(io_ctl, io_ctl->index - 1); if (io_ctl->index < io_ctl->num_pages) io_ctl_map_page(io_ctl, 0); return 0; } static void io_ctl_zero_remaining_pages(struct btrfs_io_ctl *io_ctl) { /* * If we're not on the boundary we know we've modified the page and we * need to crc the page. */ if (io_ctl->cur != io_ctl->orig) io_ctl_set_crc(io_ctl, io_ctl->index - 1); else io_ctl_unmap_page(io_ctl); while (io_ctl->index < io_ctl->num_pages) { io_ctl_map_page(io_ctl, 1); io_ctl_set_crc(io_ctl, io_ctl->index - 1); } } static int io_ctl_read_entry(struct btrfs_io_ctl *io_ctl, struct btrfs_free_space *entry, u8 *type) { struct btrfs_free_space_entry *e; int ret; if (!io_ctl->cur) { ret = io_ctl_check_crc(io_ctl, io_ctl->index); if (ret) return ret; } e = io_ctl->cur; entry->offset = get_unaligned_le64(&e->offset); entry->bytes = get_unaligned_le64(&e->bytes); *type = e->type; io_ctl->cur += sizeof(struct btrfs_free_space_entry); io_ctl->size -= sizeof(struct btrfs_free_space_entry); if (io_ctl->size >= sizeof(struct btrfs_free_space_entry)) return 0; io_ctl_unmap_page(io_ctl); return 0; } static int io_ctl_read_bitmap(struct btrfs_io_ctl *io_ctl, struct btrfs_free_space *entry) { int ret; ret = io_ctl_check_crc(io_ctl, io_ctl->index); if (ret) return ret; copy_page(entry->bitmap, io_ctl->cur); io_ctl_unmap_page(io_ctl); return 0; } static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl) { struct btrfs_block_group *block_group = ctl->block_group; u64 max_bytes; u64 bitmap_bytes; u64 extent_bytes; u64 size = block_group->length; u64 bytes_per_bg = BITS_PER_BITMAP * ctl->unit; u64 max_bitmaps = div64_u64(size + bytes_per_bg - 1, bytes_per_bg); max_bitmaps = max_t(u64, max_bitmaps, 1); if (ctl->total_bitmaps > max_bitmaps) btrfs_err(block_group->fs_info, "invalid free space control: bg start=%llu len=%llu total_bitmaps=%u unit=%u max_bitmaps=%llu bytes_per_bg=%llu", block_group->start, block_group->length, ctl->total_bitmaps, ctl->unit, max_bitmaps, bytes_per_bg); ASSERT(ctl->total_bitmaps <= max_bitmaps); /* * We are trying to keep the total amount of memory used per 1GiB of * space to be MAX_CACHE_BYTES_PER_GIG. However, with a reclamation * mechanism of pulling extents >= FORCE_EXTENT_THRESHOLD out of * bitmaps, we may end up using more memory than this. */ if (size < SZ_1G) max_bytes = MAX_CACHE_BYTES_PER_GIG; else max_bytes = MAX_CACHE_BYTES_PER_GIG * div_u64(size, SZ_1G); bitmap_bytes = ctl->total_bitmaps * ctl->unit; /* * we want the extent entry threshold to always be at most 1/2 the max * bytes we can have, or whatever is less than that. */ extent_bytes = max_bytes - bitmap_bytes; extent_bytes = min_t(u64, extent_bytes, max_bytes >> 1); ctl->extents_thresh = div_u64(extent_bytes, sizeof(struct btrfs_free_space)); } static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode, struct btrfs_free_space_ctl *ctl, struct btrfs_path *path, u64 offset) { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_free_space_header *header; struct extent_buffer *leaf; struct btrfs_io_ctl io_ctl; struct btrfs_key key; struct btrfs_free_space *e, *n; LIST_HEAD(bitmaps); u64 num_entries; u64 num_bitmaps; u64 generation; u8 type; int ret = 0; /* Nothing in the space cache, goodbye */ if (!i_size_read(inode)) return 0; key.objectid = BTRFS_FREE_SPACE_OBJECTID; key.offset = offset; key.type = 0; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) return 0; else if (ret > 0) { btrfs_release_path(path); return 0; } ret = -1; leaf = path->nodes[0]; header = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_free_space_header); num_entries = btrfs_free_space_entries(leaf, header); num_bitmaps = btrfs_free_space_bitmaps(leaf, header); generation = btrfs_free_space_generation(leaf, header); btrfs_release_path(path); if (!BTRFS_I(inode)->generation) { btrfs_info(fs_info, "the free space cache file (%llu) is invalid, skip it", offset); return 0; } if (BTRFS_I(inode)->generation != generation) { btrfs_err(fs_info, "free space inode generation (%llu) did not match free space cache generation (%llu)", BTRFS_I(inode)->generation, generation); return 0; } if (!num_entries) return 0; ret = io_ctl_init(&io_ctl, inode, 0); if (ret) return ret; readahead_cache(inode); ret = io_ctl_prepare_pages(&io_ctl, true); if (ret) goto out; ret = io_ctl_check_crc(&io_ctl, 0); if (ret) goto free_cache; ret = io_ctl_check_generation(&io_ctl, generation); if (ret) goto free_cache; while (num_entries) { e = kmem_cache_zalloc(btrfs_free_space_cachep, GFP_NOFS); if (!e) { ret = -ENOMEM; goto free_cache; } ret = io_ctl_read_entry(&io_ctl, e, &type); if (ret) { kmem_cache_free(btrfs_free_space_cachep, e); goto free_cache; } if (!e->bytes) { ret = -1; kmem_cache_free(btrfs_free_space_cachep, e); goto free_cache; } if (type == BTRFS_FREE_SPACE_EXTENT) { spin_lock(&ctl->tree_lock); ret = link_free_space(ctl, e); spin_unlock(&ctl->tree_lock); if (ret) { btrfs_err(fs_info, "Duplicate entries in free space cache, dumping"); kmem_cache_free(btrfs_free_space_cachep, e); goto free_cache; } } else { ASSERT(num_bitmaps); num_bitmaps--; e->bitmap = kmem_cache_zalloc( btrfs_free_space_bitmap_cachep, GFP_NOFS); if (!e->bitmap) { ret = -ENOMEM; kmem_cache_free( btrfs_free_space_cachep, e); goto free_cache; } spin_lock(&ctl->tree_lock); ret = link_free_space(ctl, e); if (ret) { spin_unlock(&ctl->tree_lock); btrfs_err(fs_info, "Duplicate entries in free space cache, dumping"); kmem_cache_free(btrfs_free_space_bitmap_cachep, e->bitmap); kmem_cache_free(btrfs_free_space_cachep, e); goto free_cache; } ctl->total_bitmaps++; recalculate_thresholds(ctl); spin_unlock(&ctl->tree_lock); list_add_tail(&e->list, &bitmaps); } num_entries--; } io_ctl_unmap_page(&io_ctl); /* * We add the bitmaps at the end of the entries in order that * the bitmap entries are added to the cache. */ list_for_each_entry_safe(e, n, &bitmaps, list) { list_del_init(&e->list); ret = io_ctl_read_bitmap(&io_ctl, e); if (ret) goto free_cache; } io_ctl_drop_pages(&io_ctl); ret = 1; out: io_ctl_free(&io_ctl); return ret; free_cache: io_ctl_drop_pages(&io_ctl); spin_lock(&ctl->tree_lock); __btrfs_remove_free_space_cache(ctl); spin_unlock(&ctl->tree_lock); goto out; } static int copy_free_space_cache(struct btrfs_block_group *block_group, struct btrfs_free_space_ctl *ctl) { struct btrfs_free_space *info; struct rb_node *n; int ret = 0; while (!ret && (n = rb_first(&ctl->free_space_offset)) != NULL) { info = rb_entry(n, struct btrfs_free_space, offset_index); if (!info->bitmap) { const u64 offset = info->offset; const u64 bytes = info->bytes; unlink_free_space(ctl, info, true); spin_unlock(&ctl->tree_lock); kmem_cache_free(btrfs_free_space_cachep, info); ret = btrfs_add_free_space(block_group, offset, bytes); spin_lock(&ctl->tree_lock); } else { u64 offset = info->offset; u64 bytes = ctl->unit; ret = search_bitmap(ctl, info, &offset, &bytes, false); if (ret == 0) { bitmap_clear_bits(ctl, info, offset, bytes, true); spin_unlock(&ctl->tree_lock); ret = btrfs_add_free_space(block_group, offset, bytes); spin_lock(&ctl->tree_lock); } else { free_bitmap(ctl, info); ret = 0; } } cond_resched_lock(&ctl->tree_lock); } return ret; } static struct lock_class_key btrfs_free_space_inode_key; int load_free_space_cache(struct btrfs_block_group *block_group) { struct btrfs_fs_info *fs_info = block_group->fs_info; struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; struct btrfs_free_space_ctl tmp_ctl = {}; struct inode *inode; struct btrfs_path *path; int ret = 0; bool matched; u64 used = block_group->used; /* * Because we could potentially discard our loaded free space, we want * to load everything into a temporary structure first, and then if it's * valid copy it all into the actual free space ctl. */ btrfs_init_free_space_ctl(block_group, &tmp_ctl); /* * If this block group has been marked to be cleared for one reason or * another then we can't trust the on disk cache, so just return. */ spin_lock(&block_group->lock); if (block_group->disk_cache_state != BTRFS_DC_WRITTEN) { spin_unlock(&block_group->lock); return 0; } spin_unlock(&block_group->lock); path = btrfs_alloc_path(); if (!path) return 0; path->search_commit_root = 1; path->skip_locking = 1; /* * We must pass a path with search_commit_root set to btrfs_iget in * order to avoid a deadlock when allocating extents for the tree root. * * When we are COWing an extent buffer from the tree root, when looking * for a free extent, at extent-tree.c:find_free_extent(), we can find * block group without its free space cache loaded. When we find one * we must load its space cache which requires reading its free space * cache's inode item from the root tree. If this inode item is located * in the same leaf that we started COWing before, then we end up in * deadlock on the extent buffer (trying to read lock it when we * previously write locked it). * * It's safe to read the inode item using the commit root because * block groups, once loaded, stay in memory forever (until they are * removed) as well as their space caches once loaded. New block groups * once created get their ->cached field set to BTRFS_CACHE_FINISHED so * we will never try to read their inode item while the fs is mounted. */ inode = lookup_free_space_inode(block_group, path); if (IS_ERR(inode)) { btrfs_free_path(path); return 0; } /* We may have converted the inode and made the cache invalid. */ spin_lock(&block_group->lock); if (block_group->disk_cache_state != BTRFS_DC_WRITTEN) { spin_unlock(&block_group->lock); btrfs_free_path(path); goto out; } spin_unlock(&block_group->lock); /* * Reinitialize the class of struct inode's mapping->invalidate_lock for * free space inodes to prevent false positives related to locks for normal * inodes. */ lockdep_set_class(&(&inode->i_data)->invalidate_lock, &btrfs_free_space_inode_key); ret = __load_free_space_cache(fs_info->tree_root, inode, &tmp_ctl, path, block_group->start); btrfs_free_path(path); if (ret <= 0) goto out; matched = (tmp_ctl.free_space == (block_group->length - used - block_group->bytes_super)); if (matched) { spin_lock(&tmp_ctl.tree_lock); ret = copy_free_space_cache(block_group, &tmp_ctl); spin_unlock(&tmp_ctl.tree_lock); /* * ret == 1 means we successfully loaded the free space cache, * so we need to re-set it here. */ if (ret == 0) ret = 1; } else { /* * We need to call the _locked variant so we don't try to update * the discard counters. */ spin_lock(&tmp_ctl.tree_lock); __btrfs_remove_free_space_cache(&tmp_ctl); spin_unlock(&tmp_ctl.tree_lock); btrfs_warn(fs_info, "block group %llu has wrong amount of free space", block_group->start); ret = -1; } out: if (ret < 0) { /* This cache is bogus, make sure it gets cleared */ spin_lock(&block_group->lock); block_group->disk_cache_state = BTRFS_DC_CLEAR; spin_unlock(&block_group->lock); ret = 0; btrfs_warn(fs_info, "failed to load free space cache for block group %llu, rebuilding it now", block_group->start); } spin_lock(&ctl->tree_lock); btrfs_discard_update_discardable(block_group); spin_unlock(&ctl->tree_lock); iput(inode); return ret; } static noinline_for_stack int write_cache_extent_entries(struct btrfs_io_ctl *io_ctl, struct btrfs_free_space_ctl *ctl, struct btrfs_block_group *block_group, int *entries, int *bitmaps, struct list_head *bitmap_list) { int ret; struct btrfs_free_cluster *cluster = NULL; struct btrfs_free_cluster *cluster_locked = NULL; struct rb_node *node = rb_first(&ctl->free_space_offset); struct btrfs_trim_range *trim_entry; /* Get the cluster for this block_group if it exists */ if (block_group && !list_empty(&block_group->cluster_list)) { cluster = list_entry(block_group->cluster_list.next, struct btrfs_free_cluster, block_group_list); } if (!node && cluster) { cluster_locked = cluster; spin_lock(&cluster_locked->lock); node = rb_first(&cluster->root); cluster = NULL; } /* Write out the extent entries */ while (node) { struct btrfs_free_space *e; e = rb_entry(node, struct btrfs_free_space, offset_index); *entries += 1; ret = io_ctl_add_entry(io_ctl, e->offset, e->bytes, e->bitmap); if (ret) goto fail; if (e->bitmap) { list_add_tail(&e->list, bitmap_list); *bitmaps += 1; } node = rb_next(node); if (!node && cluster) { node = rb_first(&cluster->root); cluster_locked = cluster; spin_lock(&cluster_locked->lock); cluster = NULL; } } if (cluster_locked) { spin_unlock(&cluster_locked->lock); cluster_locked = NULL; } /* * Make sure we don't miss any range that was removed from our rbtree * because trimming is running. Otherwise after a umount+mount (or crash * after committing the transaction) we would leak free space and get * an inconsistent free space cache report from fsck. */ list_for_each_entry(trim_entry, &ctl->trimming_ranges, list) { ret = io_ctl_add_entry(io_ctl, trim_entry->start, trim_entry->bytes, NULL); if (ret) goto fail; *entries += 1; } return 0; fail: if (cluster_locked) spin_unlock(&cluster_locked->lock); return -ENOSPC; } static noinline_for_stack int update_cache_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct inode *inode, struct btrfs_path *path, u64 offset, int entries, int bitmaps) { struct btrfs_key key; struct btrfs_free_space_header *header; struct extent_buffer *leaf; int ret; key.objectid = BTRFS_FREE_SPACE_OBJECTID; key.offset = offset; key.type = 0; ret = btrfs_search_slot(trans, root, &key, path, 0, 1); if (ret < 0) { clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, inode->i_size - 1, EXTENT_DELALLOC, NULL); goto fail; } leaf = path->nodes[0]; if (ret > 0) { struct btrfs_key found_key; ASSERT(path->slots[0]); path->slots[0]--; btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]); if (found_key.objectid != BTRFS_FREE_SPACE_OBJECTID || found_key.offset != offset) { clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, inode->i_size - 1, EXTENT_DELALLOC, NULL); btrfs_release_path(path); goto fail; } } BTRFS_I(inode)->generation = trans->transid; header = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_free_space_header); btrfs_set_free_space_entries(leaf, header, entries); btrfs_set_free_space_bitmaps(leaf, header, bitmaps); btrfs_set_free_space_generation(leaf, header, trans->transid); btrfs_mark_buffer_dirty(trans, leaf); btrfs_release_path(path); return 0; fail: return -1; } static noinline_for_stack int write_pinned_extent_entries( struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_io_ctl *io_ctl, int *entries) { u64 start, extent_start, extent_end, len; struct extent_io_tree *unpin = NULL; int ret; if (!block_group) return 0; /* * We want to add any pinned extents to our free space cache * so we don't leak the space * * We shouldn't have switched the pinned extents yet so this is the * right one */ unpin = &trans->transaction->pinned_extents; start = block_group->start; while (start < block_group->start + block_group->length) { if (!find_first_extent_bit(unpin, start, &extent_start, &extent_end, EXTENT_DIRTY, NULL)) return 0; /* This pinned extent is out of our range */ if (extent_start >= block_group->start + block_group->length) return 0; extent_start = max(extent_start, start); extent_end = min(block_group->start + block_group->length, extent_end + 1); len = extent_end - extent_start; *entries += 1; ret = io_ctl_add_entry(io_ctl, extent_start, len, NULL); if (ret) return -ENOSPC; start = extent_end; } return 0; } static noinline_for_stack int write_bitmap_entries(struct btrfs_io_ctl *io_ctl, struct list_head *bitmap_list) { struct btrfs_free_space *entry, *next; int ret; /* Write out the bitmaps */ list_for_each_entry_safe(entry, next, bitmap_list, list) { ret = io_ctl_add_bitmap(io_ctl, entry->bitmap); if (ret) return -ENOSPC; list_del_init(&entry->list); } return 0; } static int flush_dirty_cache(struct inode *inode) { int ret; ret = btrfs_wait_ordered_range(BTRFS_I(inode), 0, (u64)-1); if (ret) clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, inode->i_size - 1, EXTENT_DELALLOC, NULL); return ret; } static void noinline_for_stack cleanup_bitmap_list(struct list_head *bitmap_list) { struct btrfs_free_space *entry, *next; list_for_each_entry_safe(entry, next, bitmap_list, list) list_del_init(&entry->list); } static void noinline_for_stack cleanup_write_cache_enospc(struct inode *inode, struct btrfs_io_ctl *io_ctl, struct extent_state **cached_state) { io_ctl_drop_pages(io_ctl); unlock_extent(&BTRFS_I(inode)->io_tree, 0, i_size_read(inode) - 1, cached_state); } static int __btrfs_wait_cache_io(struct btrfs_root *root, struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_io_ctl *io_ctl, struct btrfs_path *path, u64 offset) { int ret; struct inode *inode = io_ctl->inode; if (!inode) return 0; /* Flush the dirty pages in the cache file. */ ret = flush_dirty_cache(inode); if (ret) goto out; /* Update the cache item to tell everyone this cache file is valid. */ ret = update_cache_item(trans, root, inode, path, offset, io_ctl->entries, io_ctl->bitmaps); out: if (ret) { invalidate_inode_pages2(inode->i_mapping); BTRFS_I(inode)->generation = 0; if (block_group) btrfs_debug(root->fs_info, "failed to write free space cache for block group %llu error %d", block_group->start, ret); } btrfs_update_inode(trans, BTRFS_I(inode)); if (block_group) { /* the dirty list is protected by the dirty_bgs_lock */ spin_lock(&trans->transaction->dirty_bgs_lock); /* the disk_cache_state is protected by the block group lock */ spin_lock(&block_group->lock); /* * only mark this as written if we didn't get put back on * the dirty list while waiting for IO. Otherwise our * cache state won't be right, and we won't get written again */ if (!ret && list_empty(&block_group->dirty_list)) block_group->disk_cache_state = BTRFS_DC_WRITTEN; else if (ret) block_group->disk_cache_state = BTRFS_DC_ERROR; spin_unlock(&block_group->lock); spin_unlock(&trans->transaction->dirty_bgs_lock); io_ctl->inode = NULL; iput(inode); } return ret; } int btrfs_wait_cache_io(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path) { return __btrfs_wait_cache_io(block_group->fs_info->tree_root, trans, block_group, &block_group->io_ctl, path, block_group->start); } /* * Write out cached info to an inode. * * @inode: freespace inode we are writing out * @ctl: free space cache we are going to write out * @block_group: block_group for this cache if it belongs to a block_group * @io_ctl: holds context for the io * @trans: the trans handle * * This function writes out a free space cache struct to disk for quick recovery * on mount. This will return 0 if it was successful in writing the cache out, * or an errno if it was not. */ static int __btrfs_write_out_cache(struct inode *inode, struct btrfs_free_space_ctl *ctl, struct btrfs_block_group *block_group, struct btrfs_io_ctl *io_ctl, struct btrfs_trans_handle *trans) { struct extent_state *cached_state = NULL; LIST_HEAD(bitmap_list); int entries = 0; int bitmaps = 0; int ret; int must_iput = 0; int i_size; if (!i_size_read(inode)) return -EIO; WARN_ON(io_ctl->pages); ret = io_ctl_init(io_ctl, inode, 1); if (ret) return ret; if (block_group && (block_group->flags & BTRFS_BLOCK_GROUP_DATA)) { down_write(&block_group->data_rwsem); spin_lock(&block_group->lock); if (block_group->delalloc_bytes) { block_group->disk_cache_state = BTRFS_DC_WRITTEN; spin_unlock(&block_group->lock); up_write(&block_group->data_rwsem); BTRFS_I(inode)->generation = 0; ret = 0; must_iput = 1; goto out; } spin_unlock(&block_group->lock); } /* Lock all pages first so we can lock the extent safely. */ ret = io_ctl_prepare_pages(io_ctl, false); if (ret) goto out_unlock; lock_extent(&BTRFS_I(inode)->io_tree, 0, i_size_read(inode) - 1, &cached_state); io_ctl_set_generation(io_ctl, trans->transid); mutex_lock(&ctl->cache_writeout_mutex); /* Write out the extent entries in the free space cache */ spin_lock(&ctl->tree_lock); ret = write_cache_extent_entries(io_ctl, ctl, block_group, &entries, &bitmaps, &bitmap_list); if (ret) goto out_nospc_locked; /* * Some spaces that are freed in the current transaction are pinned, * they will be added into free space cache after the transaction is * committed, we shouldn't lose them. * * If this changes while we are working we'll get added back to * the dirty list and redo it. No locking needed */ ret = write_pinned_extent_entries(trans, block_group, io_ctl, &entries); if (ret) goto out_nospc_locked; /* * At last, we write out all the bitmaps and keep cache_writeout_mutex * locked while doing it because a concurrent trim can be manipulating * or freeing the bitmap. */ ret = write_bitmap_entries(io_ctl, &bitmap_list); spin_unlock(&ctl->tree_lock); mutex_unlock(&ctl->cache_writeout_mutex); if (ret) goto out_nospc; /* Zero out the rest of the pages just to make sure */ io_ctl_zero_remaining_pages(io_ctl); /* Everything is written out, now we dirty the pages in the file. */ i_size = i_size_read(inode); for (int i = 0; i < round_up(i_size, PAGE_SIZE) / PAGE_SIZE; i++) { u64 dirty_start = i * PAGE_SIZE; u64 dirty_len = min_t(u64, dirty_start + PAGE_SIZE, i_size) - dirty_start; ret = btrfs_dirty_folio(BTRFS_I(inode), page_folio(io_ctl->pages[i]), dirty_start, dirty_len, &cached_state, false); if (ret < 0) goto out_nospc; } if (block_group && (block_group->flags & BTRFS_BLOCK_GROUP_DATA)) up_write(&block_group->data_rwsem); /* * Release the pages and unlock the extent, we will flush * them out later */ io_ctl_drop_pages(io_ctl); io_ctl_free(io_ctl); unlock_extent(&BTRFS_I(inode)->io_tree, 0, i_size_read(inode) - 1, &cached_state); /* * at this point the pages are under IO and we're happy, * The caller is responsible for waiting on them and updating * the cache and the inode */ io_ctl->entries = entries; io_ctl->bitmaps = bitmaps; ret = btrfs_fdatawrite_range(BTRFS_I(inode), 0, (u64)-1); if (ret) goto out; return 0; out_nospc_locked: cleanup_bitmap_list(&bitmap_list); spin_unlock(&ctl->tree_lock); mutex_unlock(&ctl->cache_writeout_mutex); out_nospc: cleanup_write_cache_enospc(inode, io_ctl, &cached_state); out_unlock: if (block_group && (block_group->flags & BTRFS_BLOCK_GROUP_DATA)) up_write(&block_group->data_rwsem); out: io_ctl->inode = NULL; io_ctl_free(io_ctl); if (ret) { invalidate_inode_pages2(inode->i_mapping); BTRFS_I(inode)->generation = 0; } btrfs_update_inode(trans, BTRFS_I(inode)); if (must_iput) iput(inode); return ret; } int btrfs_write_out_cache(struct btrfs_trans_handle *trans, struct btrfs_block_group *block_group, struct btrfs_path *path) { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; struct inode *inode; int ret = 0; spin_lock(&block_group->lock); if (block_group->disk_cache_state < BTRFS_DC_SETUP) { spin_unlock(&block_group->lock); return 0; } spin_unlock(&block_group->lock); inode = lookup_free_space_inode(block_group, path); if (IS_ERR(inode)) return 0; ret = __btrfs_write_out_cache(inode, ctl, block_group, &block_group->io_ctl, trans); if (ret) { btrfs_debug(fs_info, "failed to write free space cache for block group %llu error %d", block_group->start, ret); spin_lock(&block_group->lock); block_group->disk_cache_state = BTRFS_DC_ERROR; spin_unlock(&block_group->lock); block_group->io_ctl.inode = NULL; iput(inode); } /* * if ret == 0 the caller is expected to call btrfs_wait_cache_io * to wait for IO and put the inode */ return ret; } static inline unsigned long offset_to_bit(u64 bitmap_start, u32 unit, u64 offset) { ASSERT(offset >= bitmap_start); offset -= bitmap_start; return (unsigned long)(div_u64(offset, unit)); } static inline unsigned long bytes_to_bits(u64 bytes, u32 unit) { return (unsigned long)(div_u64(bytes, unit)); } static inline u64 offset_to_bitmap(struct btrfs_free_space_ctl *ctl, u64 offset) { u64 bitmap_start; u64 bytes_per_bitmap; bytes_per_bitmap = BITS_PER_BITMAP * ctl->unit; bitmap_start = offset - ctl->start; bitmap_start = div64_u64(bitmap_start, bytes_per_bitmap); bitmap_start *= bytes_per_bitmap; bitmap_start += ctl->start; return bitmap_start; } static int tree_insert_offset(struct btrfs_free_space_ctl *ctl, struct btrfs_free_cluster *cluster, struct btrfs_free_space *new_entry) { struct rb_root *root; struct rb_node **p; struct rb_node *parent = NULL; lockdep_assert_held(&ctl->tree_lock); if (cluster) { lockdep_assert_held(&cluster->lock); root = &cluster->root; } else { root = &ctl->free_space_offset; } p = &root->rb_node; while (*p) { struct btrfs_free_space *info; parent = *p; info = rb_entry(parent, struct btrfs_free_space, offset_index); if (new_entry->offset < info->offset) { p = &(*p)->rb_left; } else if (new_entry->offset > info->offset) { p = &(*p)->rb_right; } else { /* * we could have a bitmap entry and an extent entry * share the same offset. If this is the case, we want * the extent entry to always be found first if we do a * linear search through the tree, since we want to have * the quickest allocation time, and allocating from an * extent is faster than allocating from a bitmap. So * if we're inserting a bitmap and we find an entry at * this offset, we want to go right, or after this entry * logically. If we are inserting an extent and we've * found a bitmap, we want to go left, or before * logically. */ if (new_entry->bitmap) { if (info->bitmap) { WARN_ON_ONCE(1); return -EEXIST; } p = &(*p)->rb_right; } else { if (!info->bitmap) { WARN_ON_ONCE(1); return -EEXIST; } p = &(*p)->rb_left; } } } rb_link_node(&new_entry->offset_index, parent, p); rb_insert_color(&new_entry->offset_index, root); return 0; } /* * This is a little subtle. We *only* have ->max_extent_size set if we actually * searched through the bitmap and figured out the largest ->max_extent_size, * otherwise it's 0. In the case that it's 0 we don't want to tell the * allocator the wrong thing, we want to use the actual real max_extent_size * we've found already if it's larger, or we want to use ->bytes. * * This matters because find_free_space() will skip entries who's ->bytes is * less than the required bytes. So if we didn't search down this bitmap, we * may pick some previous entry that has a smaller ->max_extent_size than we * have. For example, assume we have two entries, one that has * ->max_extent_size set to 4K and ->bytes set to 1M. A second entry hasn't set * ->max_extent_size yet, has ->bytes set to 8K and it's contiguous. We will * call into find_free_space(), and return with max_extent_size == 4K, because * that first bitmap entry had ->max_extent_size set, but the second one did * not. If instead we returned 8K we'd come in searching for 8K, and find the * 8K contiguous range. * * Consider the other case, we have 2 8K chunks in that second entry and still * don't have ->max_extent_size set. We'll return 16K, and the next time the * allocator comes in it'll fully search our second bitmap, and this time it'll * get an uptodate value of 8K as the maximum chunk size. Then we'll get the * right allocation the next loop through. */ static inline u64 get_max_extent_size(const struct btrfs_free_space *entry) { if (entry->bitmap && entry->max_extent_size) return entry->max_extent_size; return entry->bytes; } /* * We want the largest entry to be leftmost, so this is inverted from what you'd * normally expect. */ static bool entry_less(struct rb_node *node, const struct rb_node *parent) { const struct btrfs_free_space *entry, *exist; entry = rb_entry(node, struct btrfs_free_space, bytes_index); exist = rb_entry(parent, struct btrfs_free_space, bytes_index); return get_max_extent_size(exist) < get_max_extent_size(entry); } /* * searches the tree for the given offset. * * fuzzy - If this is set, then we are trying to make an allocation, and we just * want a section that has at least bytes size and comes at or after the given * offset. */ static struct btrfs_free_space * tree_search_offset(struct btrfs_free_space_ctl *ctl, u64 offset, int bitmap_only, int fuzzy) { struct rb_node *n = ctl->free_space_offset.rb_node; struct btrfs_free_space *entry = NULL, *prev = NULL; lockdep_assert_held(&ctl->tree_lock); /* find entry that is closest to the 'offset' */ while (n) { entry = rb_entry(n, struct btrfs_free_space, offset_index); prev = entry; if (offset < entry->offset) n = n->rb_left; else if (offset > entry->offset) n = n->rb_right; else break; entry = NULL; } if (bitmap_only) { if (!entry) return NULL; if (entry->bitmap) return entry; /* * bitmap entry and extent entry may share same offset, * in that case, bitmap entry comes after extent entry. */ n = rb_next(n); if (!n) return NULL; entry = rb_entry(n, struct btrfs_free_space, offset_index); if (entry->offset != offset) return NULL; WARN_ON(!entry->bitmap); return entry; } else if (entry) { if (entry->bitmap) { /* * if previous extent entry covers the offset, * we should return it instead of the bitmap entry */ n = rb_prev(&entry->offset_index); if (n) { prev = rb_entry(n, struct btrfs_free_space, offset_index); if (!prev->bitmap && prev->offset + prev->bytes > offset) entry = prev; } } return entry; } if (!prev) return NULL; /* find last entry before the 'offset' */ entry = prev; if (entry->offset > offset) { n = rb_prev(&entry->offset_index); if (n) { entry = rb_entry(n, struct btrfs_free_space, offset_index); ASSERT(entry->offset <= offset); } else { if (fuzzy) return entry; else return NULL; } } if (entry->bitmap) { n = rb_prev(&entry->offset_index); if (n) { prev = rb_entry(n, struct btrfs_free_space, offset_index); if (!prev->bitmap && prev->offset + prev->bytes > offset) return prev; } if (entry->offset + BITS_PER_BITMAP * ctl->unit > offset) return entry; } else if (entry->offset + entry->bytes > offset) return entry; if (!fuzzy) return NULL; while (1) { n = rb_next(&entry->offset_index); if (!n) return NULL; entry = rb_entry(n, struct btrfs_free_space, offset_index); if (entry->bitmap) { if (entry->offset + BITS_PER_BITMAP * ctl->unit > offset) break; } else { if (entry->offset + entry->bytes > offset) break; } } return entry; } static inline void unlink_free_space(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *info, bool update_stat) { lockdep_assert_held(&ctl->tree_lock); rb_erase(&info->offset_index, &ctl->free_space_offset); rb_erase_cached(&info->bytes_index, &ctl->free_space_bytes); ctl->free_extents--; if (!info->bitmap && !btrfs_free_space_trimmed(info)) { ctl->discardable_extents[BTRFS_STAT_CURR]--; ctl->discardable_bytes[BTRFS_STAT_CURR] -= info->bytes; } if (update_stat) ctl->free_space -= info->bytes; } static int link_free_space(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *info) { int ret = 0; lockdep_assert_held(&ctl->tree_lock); ASSERT(info->bytes || info->bitmap); ret = tree_insert_offset(ctl, NULL, info); if (ret) return ret; rb_add_cached(&info->bytes_index, &ctl->free_space_bytes, entry_less); if (!info->bitmap && !btrfs_free_space_trimmed(info)) { ctl->discardable_extents[BTRFS_STAT_CURR]++; ctl->discardable_bytes[BTRFS_STAT_CURR] += info->bytes; } ctl->free_space += info->bytes; ctl->free_extents++; return ret; } static void relink_bitmap_entry(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *info) { ASSERT(info->bitmap); /* * If our entry is empty it's because we're on a cluster and we don't * want to re-link it into our ctl bytes index. */ if (RB_EMPTY_NODE(&info->bytes_index)) return; lockdep_assert_held(&ctl->tree_lock); rb_erase_cached(&info->bytes_index, &ctl->free_space_bytes); rb_add_cached(&info->bytes_index, &ctl->free_space_bytes, entry_less); } static inline void bitmap_clear_bits(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *info, u64 offset, u64 bytes, bool update_stat) { unsigned long start, count, end; int extent_delta = -1; start = offset_to_bit(info->offset, ctl->unit, offset); count = bytes_to_bits(bytes, ctl->unit); end = start + count; ASSERT(end <= BITS_PER_BITMAP); bitmap_clear(info->bitmap, start, count); info->bytes -= bytes; if (info->max_extent_size > ctl->unit) info->max_extent_size = 0; relink_bitmap_entry(ctl, info); if (start && test_bit(start - 1, info->bitmap)) extent_delta++; if (end < BITS_PER_BITMAP && test_bit(end, info->bitmap)) extent_delta++; info->bitmap_extents += extent_delta; if (!btrfs_free_space_trimmed(info)) { ctl->discardable_extents[BTRFS_STAT_CURR] += extent_delta; ctl->discardable_bytes[BTRFS_STAT_CURR] -= bytes; } if (update_stat) ctl->free_space -= bytes; } static void btrfs_bitmap_set_bits(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *info, u64 offset, u64 bytes) { unsigned long start, count, end; int extent_delta = 1; start = offset_to_bit(info->offset, ctl->unit, offset); count = bytes_to_bits(bytes, ctl->unit); end = start + count; ASSERT(end <= BITS_PER_BITMAP); bitmap_set(info->bitmap, start, count); /* * We set some bytes, we have no idea what the max extent size is * anymore. */ info->max_extent_size = 0; info->bytes += bytes; ctl->free_space += bytes; relink_bitmap_entry(ctl, info); if (start && test_bit(start - 1, info->bitmap)) extent_delta--; if (end < BITS_PER_BITMAP && test_bit(end, info->bitmap)) extent_delta--; info->bitmap_extents += extent_delta; if (!btrfs_free_space_trimmed(info)) { ctl->discardable_extents[BTRFS_STAT_CURR] += extent_delta; ctl->discardable_bytes[BTRFS_STAT_CURR] += bytes; } } /* * If we can not find suitable extent, we will use bytes to record * the size of the max extent. */ static int search_bitmap(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *bitmap_info, u64 *offset, u64 *bytes, bool for_alloc) { unsigned long found_bits = 0; unsigned long max_bits = 0; unsigned long bits, i; unsigned long next_zero; unsigned long extent_bits; /* * Skip searching the bitmap if we don't have a contiguous section that * is large enough for this allocation. */ if (for_alloc && bitmap_info->max_extent_size && bitmap_info->max_extent_size < *bytes) { *bytes = bitmap_info->max_extent_size; return -1; } i = offset_to_bit(bitmap_info->offset, ctl->unit, max_t(u64, *offset, bitmap_info->offset)); bits = bytes_to_bits(*bytes, ctl->unit); for_each_set_bit_from(i, bitmap_info->bitmap, BITS_PER_BITMAP) { if (for_alloc && bits == 1) { found_bits = 1; break; } next_zero = find_next_zero_bit(bitmap_info->bitmap, BITS_PER_BITMAP, i); extent_bits = next_zero - i; if (extent_bits >= bits) { found_bits = extent_bits; break; } else if (extent_bits > max_bits) { max_bits = extent_bits; } i = next_zero; } if (found_bits) { *offset = (u64)(i * ctl->unit) + bitmap_info->offset; *bytes = (u64)(found_bits) * ctl->unit; return 0; } *bytes = (u64)(max_bits) * ctl->unit; bitmap_info->max_extent_size = *bytes; relink_bitmap_entry(ctl, bitmap_info); return -1; } /* Cache the size of the max extent in bytes */ static struct btrfs_free_space * find_free_space(struct btrfs_free_space_ctl *ctl, u64 *offset, u64 *bytes, unsigned long align, u64 *max_extent_size, bool use_bytes_index) { struct btrfs_free_space *entry; struct rb_node *node; u64 tmp; u64 align_off; int ret; if (!ctl->free_space_offset.rb_node) goto out; again: if (use_bytes_index) { node = rb_first_cached(&ctl->free_space_bytes); } else { entry = tree_search_offset(ctl, offset_to_bitmap(ctl, *offset), 0, 1); if (!entry) goto out; node = &entry->offset_index; } for (; node; node = rb_next(node)) { if (use_bytes_index) entry = rb_entry(node, struct btrfs_free_space, bytes_index); else entry = rb_entry(node, struct btrfs_free_space, offset_index); /* * If we are using the bytes index then all subsequent entries * in this tree are going to be < bytes, so simply set the max * extent size and exit the loop. * * If we're using the offset index then we need to keep going * through the rest of the tree. */ if (entry->bytes < *bytes) { *max_extent_size = max(get_max_extent_size(entry), *max_extent_size); if (use_bytes_index) break; continue; } /* make sure the space returned is big enough * to match our requested alignment */ if (*bytes >= align) { tmp = entry->offset - ctl->start + align - 1; tmp = div64_u64(tmp, align); tmp = tmp * align + ctl->start; align_off = tmp - entry->offset; } else { align_off = 0; tmp = entry->offset; } /* * We don't break here if we're using the bytes index because we * may have another entry that has the correct alignment that is * the right size, so we don't want to miss that possibility. * At worst this adds another loop through the logic, but if we * broke here we could prematurely ENOSPC. */ if (entry->bytes < *bytes + align_off) { *max_extent_size = max(get_max_extent_size(entry), *max_extent_size); continue; } if (entry->bitmap) { struct rb_node *old_next = rb_next(node); u64 size = *bytes; ret = search_bitmap(ctl, entry, &tmp, &size, true); if (!ret) { *offset = tmp; *bytes = size; return entry; } else { *max_extent_size = max(get_max_extent_size(entry), *max_extent_size); } /* * The bitmap may have gotten re-arranged in the space * index here because the max_extent_size may have been * updated. Start from the beginning again if this * happened. */ if (use_bytes_index && old_next != rb_next(node)) goto again; continue; } *offset = tmp; *bytes = entry->bytes - align_off; return entry; } out: return NULL; } static void add_new_bitmap(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *info, u64 offset) { info->offset = offset_to_bitmap(ctl, offset); info->bytes = 0; info->bitmap_extents = 0; INIT_LIST_HEAD(&info->list); link_free_space(ctl, info); ctl->total_bitmaps++; recalculate_thresholds(ctl); } static void free_bitmap(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *bitmap_info) { /* * Normally when this is called, the bitmap is completely empty. However, * if we are blowing up the free space cache for one reason or another * via __btrfs_remove_free_space_cache(), then it may not be freed and * we may leave stats on the table. */ if (bitmap_info->bytes && !btrfs_free_space_trimmed(bitmap_info)) { ctl->discardable_extents[BTRFS_STAT_CURR] -= bitmap_info->bitmap_extents; ctl->discardable_bytes[BTRFS_STAT_CURR] -= bitmap_info->bytes; } unlink_free_space(ctl, bitmap_info, true); kmem_cache_free(btrfs_free_space_bitmap_cachep, bitmap_info->bitmap); kmem_cache_free(btrfs_free_space_cachep, bitmap_info); ctl->total_bitmaps--; recalculate_thresholds(ctl); } static noinline int remove_from_bitmap(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *bitmap_info, u64 *offset, u64 *bytes) { u64 end; u64 search_start, search_bytes; int ret; again: end = bitmap_info->offset + (u64)(BITS_PER_BITMAP * ctl->unit) - 1; /* * We need to search for bits in this bitmap. We could only cover some * of the extent in this bitmap thanks to how we add space, so we need * to search for as much as it as we can and clear that amount, and then * go searching for the next bit. */ search_start = *offset; search_bytes = ctl->unit; search_bytes = min(search_bytes, end - search_start + 1); ret = search_bitmap(ctl, bitmap_info, &search_start, &search_bytes, false); if (ret < 0 || search_start != *offset) return -EINVAL; /* We may have found more bits than what we need */ search_bytes = min(search_bytes, *bytes); /* Cannot clear past the end of the bitmap */ search_bytes = min(search_bytes, end - search_start + 1); bitmap_clear_bits(ctl, bitmap_info, search_start, search_bytes, true); *offset += search_bytes; *bytes -= search_bytes; if (*bytes) { struct rb_node *next = rb_next(&bitmap_info->offset_index); if (!bitmap_info->bytes) free_bitmap(ctl, bitmap_info); /* * no entry after this bitmap, but we still have bytes to * remove, so something has gone wrong. */ if (!next) return -EINVAL; bitmap_info = rb_entry(next, struct btrfs_free_space, offset_index); /* * if the next entry isn't a bitmap we need to return to let the * extent stuff do its work. */ if (!bitmap_info->bitmap) return -EAGAIN; /* * Ok the next item is a bitmap, but it may not actually hold * the information for the rest of this free space stuff, so * look for it, and if we don't find it return so we can try * everything over again. */ search_start = *offset; search_bytes = ctl->unit; ret = search_bitmap(ctl, bitmap_info, &search_start, &search_bytes, false); if (ret < 0 || search_start != *offset) return -EAGAIN; goto again; } else if (!bitmap_info->bytes) free_bitmap(ctl, bitmap_info); return 0; } static u64 add_bytes_to_bitmap(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *info, u64 offset, u64 bytes, enum btrfs_trim_state trim_state) { u64 bytes_to_set = 0; u64 end; /* * This is a tradeoff to make bitmap trim state minimal. We mark the * whole bitmap untrimmed if at any point we add untrimmed regions. */ if (trim_state == BTRFS_TRIM_STATE_UNTRIMMED) { if (btrfs_free_space_trimmed(info)) { ctl->discardable_extents[BTRFS_STAT_CURR] += info->bitmap_extents; ctl->discardable_bytes[BTRFS_STAT_CURR] += info->bytes; } info->trim_state = BTRFS_TRIM_STATE_UNTRIMMED; } end = info->offset + (u64)(BITS_PER_BITMAP * ctl->unit); bytes_to_set = min(end - offset, bytes); btrfs_bitmap_set_bits(ctl, info, offset, bytes_to_set); return bytes_to_set; } static bool use_bitmap(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *info) { struct btrfs_block_group *block_group = ctl->block_group; struct btrfs_fs_info *fs_info = block_group->fs_info; bool forced = false; #ifdef CONFIG_BTRFS_DEBUG if (btrfs_should_fragment_free_space(block_group)) forced = true; #endif /* This is a way to reclaim large regions from the bitmaps. */ if (!forced && info->bytes >= FORCE_EXTENT_THRESHOLD) return false; /* * If we are below the extents threshold then we can add this as an * extent, and don't have to deal with the bitmap */ if (!forced && ctl->free_extents < ctl->extents_thresh) { /* * If this block group has some small extents we don't want to * use up all of our free slots in the cache with them, we want * to reserve them to larger extents, however if we have plenty * of cache left then go ahead an dadd them, no sense in adding * the overhead of a bitmap if we don't have to. */ if (info->bytes <= fs_info->sectorsize * 8) { if (ctl->free_extents * 3 <= ctl->extents_thresh) return false; } else { return false; } } /* * The original block groups from mkfs can be really small, like 8 * megabytes, so don't bother with a bitmap for those entries. However * some block groups can be smaller than what a bitmap would cover but * are still large enough that they could overflow the 32k memory limit, * so allow those block groups to still be allowed to have a bitmap * entry. */ if (((BITS_PER_BITMAP * ctl->unit) >> 1) > block_group->length) return false; return true; } static const struct btrfs_free_space_op free_space_op = { .use_bitmap = use_bitmap, }; static int insert_into_bitmap(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *info) { struct btrfs_free_space *bitmap_info; struct btrfs_block_group *block_group = NULL; int added = 0; u64 bytes, offset, bytes_added; enum btrfs_trim_state trim_state; int ret; bytes = info->bytes; offset = info->offset; trim_state = info->trim_state; if (!ctl->op->use_bitmap(ctl, info)) return 0; if (ctl->op == &free_space_op) block_group = ctl->block_group; again: /* * Since we link bitmaps right into the cluster we need to see if we * have a cluster here, and if so and it has our bitmap we need to add * the free space to that bitmap. */ if (block_group && !list_empty(&block_group->cluster_list)) { struct btrfs_free_cluster *cluster; struct rb_node *node; struct btrfs_free_space *entry; cluster = list_entry(block_group->cluster_list.next, struct btrfs_free_cluster, block_group_list); spin_lock(&cluster->lock); node = rb_first(&cluster->root); if (!node) { spin_unlock(&cluster->lock); goto no_cluster_bitmap; } entry = rb_entry(node, struct btrfs_free_space, offset_index); if (!entry->bitmap) { spin_unlock(&cluster->lock); goto no_cluster_bitmap; } if (entry->offset == offset_to_bitmap(ctl, offset)) { bytes_added = add_bytes_to_bitmap(ctl, entry, offset, bytes, trim_state); bytes -= bytes_added; offset += bytes_added; } spin_unlock(&cluster->lock); if (!bytes) { ret = 1; goto out; } } no_cluster_bitmap: bitmap_info = tree_search_offset(ctl, offset_to_bitmap(ctl, offset), 1, 0); if (!bitmap_info) { ASSERT(added == 0); goto new_bitmap; } bytes_added = add_bytes_to_bitmap(ctl, bitmap_info, offset, bytes, trim_state); bytes -= bytes_added; offset += bytes_added; added = 0; if (!bytes) { ret = 1; goto out; } else goto again; new_bitmap: if (info && info->bitmap) { add_new_bitmap(ctl, info, offset); added = 1; info = NULL; goto again; } else { spin_unlock(&ctl->tree_lock); /* no pre-allocated info, allocate a new one */ if (!info) { info = kmem_cache_zalloc(btrfs_free_space_cachep, GFP_NOFS); if (!info) { spin_lock(&ctl->tree_lock); ret = -ENOMEM; goto out; } } /* allocate the bitmap */ info->bitmap = kmem_cache_zalloc(btrfs_free_space_bitmap_cachep, GFP_NOFS); info->trim_state = BTRFS_TRIM_STATE_TRIMMED; spin_lock(&ctl->tree_lock); if (!info->bitmap) { ret = -ENOMEM; goto out; } goto again; } out: if (info) { if (info->bitmap) kmem_cache_free(btrfs_free_space_bitmap_cachep, info->bitmap); kmem_cache_free(btrfs_free_space_cachep, info); } return ret; } /* * Free space merging rules: * 1) Merge trimmed areas together * 2) Let untrimmed areas coalesce with trimmed areas * 3) Always pull neighboring regions from bitmaps * * The above rules are for when we merge free space based on btrfs_trim_state. * Rules 2 and 3 are subtle because they are suboptimal, but are done for the * same reason: to promote larger extent regions which makes life easier for * find_free_extent(). Rule 2 enables coalescing based on the common path * being returning free space from btrfs_finish_extent_commit(). So when free * space is trimmed, it will prevent aggregating trimmed new region and * untrimmed regions in the rb_tree. Rule 3 is purely to obtain larger extents * and provide find_free_extent() with the largest extents possible hoping for * the reuse path. */ static bool try_merge_free_space(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *info, bool update_stat) { struct btrfs_free_space *left_info = NULL; struct btrfs_free_space *right_info; bool merged = false; u64 offset = info->offset; u64 bytes = info->bytes; const bool is_trimmed = btrfs_free_space_trimmed(info); struct rb_node *right_prev = NULL; /* * first we want to see if there is free space adjacent to the range we * are adding, if there is remove that struct and add a new one to * cover the entire range */ right_info = tree_search_offset(ctl, offset + bytes, 0, 0); if (right_info) right_prev = rb_prev(&right_info->offset_index); if (right_prev) left_info = rb_entry(right_prev, struct btrfs_free_space, offset_index); else if (!right_info) left_info = tree_search_offset(ctl, offset - 1, 0, 0); /* See try_merge_free_space() comment. */ if (right_info && !right_info->bitmap && (!is_trimmed || btrfs_free_space_trimmed(right_info))) { unlink_free_space(ctl, right_info, update_stat); info->bytes += right_info->bytes; kmem_cache_free(btrfs_free_space_cachep, right_info); merged = true; } /* See try_merge_free_space() comment. */ if (left_info && !left_info->bitmap && left_info->offset + left_info->bytes == offset && (!is_trimmed || btrfs_free_space_trimmed(left_info))) { unlink_free_space(ctl, left_info, update_stat); info->offset = left_info->offset; info->bytes += left_info->bytes; kmem_cache_free(btrfs_free_space_cachep, left_info); merged = true; } return merged; } static bool steal_from_bitmap_to_end(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *info, bool update_stat) { struct btrfs_free_space *bitmap; unsigned long i; unsigned long j; const u64 end = info->offset + info->bytes; const u64 bitmap_offset = offset_to_bitmap(ctl, end); u64 bytes; bitmap = tree_search_offset(ctl, bitmap_offset, 1, 0); if (!bitmap) return false; i = offset_to_bit(bitmap->offset, ctl->unit, end); j = find_next_zero_bit(bitmap->bitmap, BITS_PER_BITMAP, i); if (j == i) return false; bytes = (j - i) * ctl->unit; info->bytes += bytes; /* See try_merge_free_space() comment. */ if (!btrfs_free_space_trimmed(bitmap)) info->trim_state = BTRFS_TRIM_STATE_UNTRIMMED; bitmap_clear_bits(ctl, bitmap, end, bytes, update_stat); if (!bitmap->bytes) free_bitmap(ctl, bitmap); return true; } static bool steal_from_bitmap_to_front(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *info, bool update_stat) { struct btrfs_free_space *bitmap; u64 bitmap_offset; unsigned long i; unsigned long j; unsigned long prev_j; u64 bytes; bitmap_offset = offset_to_bitmap(ctl, info->offset); /* If we're on a boundary, try the previous logical bitmap. */ if (bitmap_offset == info->offset) { if (info->offset == 0) return false; bitmap_offset = offset_to_bitmap(ctl, info->offset - 1); } bitmap = tree_search_offset(ctl, bitmap_offset, 1, 0); if (!bitmap) return false; i = offset_to_bit(bitmap->offset, ctl->unit, info->offset) - 1; j = 0; prev_j = (unsigned long)-1; for_each_clear_bit_from(j, bitmap->bitmap, BITS_PER_BITMAP) { if (j > i) break; prev_j = j; } if (prev_j == i) return false; if (prev_j == (unsigned long)-1) bytes = (i + 1) * ctl->unit; else bytes = (i - prev_j) * ctl->unit; info->offset -= bytes; info->bytes += bytes; /* See try_merge_free_space() comment. */ if (!btrfs_free_space_trimmed(bitmap)) info->trim_state = BTRFS_TRIM_STATE_UNTRIMMED; bitmap_clear_bits(ctl, bitmap, info->offset, bytes, update_stat); if (!bitmap->bytes) free_bitmap(ctl, bitmap); return true; } /* * We prefer always to allocate from extent entries, both for clustered and * non-clustered allocation requests. So when attempting to add a new extent * entry, try to see if there's adjacent free space in bitmap entries, and if * there is, migrate that space from the bitmaps to the extent. * Like this we get better chances of satisfying space allocation requests * because we attempt to satisfy them based on a single cache entry, and never * on 2 or more entries - even if the entries represent a contiguous free space * region (e.g. 1 extent entry + 1 bitmap entry starting where the extent entry * ends). */ static void steal_from_bitmap(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *info, bool update_stat) { /* * Only work with disconnected entries, as we can change their offset, * and must be extent entries. */ ASSERT(!info->bitmap); ASSERT(RB_EMPTY_NODE(&info->offset_index)); if (ctl->total_bitmaps > 0) { bool stole_end; bool stole_front = false; stole_end = steal_from_bitmap_to_end(ctl, info, update_stat); if (ctl->total_bitmaps > 0) stole_front = steal_from_bitmap_to_front(ctl, info, update_stat); if (stole_end || stole_front) try_merge_free_space(ctl, info, update_stat); } } static int __btrfs_add_free_space(struct btrfs_block_group *block_group, u64 offset, u64 bytes, enum btrfs_trim_state trim_state) { struct btrfs_fs_info *fs_info = block_group->fs_info; struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; struct btrfs_free_space *info; int ret = 0; u64 filter_bytes = bytes; ASSERT(!btrfs_is_zoned(fs_info)); info = kmem_cache_zalloc(btrfs_free_space_cachep, GFP_NOFS); if (!info) return -ENOMEM; info->offset = offset; info->bytes = bytes; info->trim_state = trim_state; RB_CLEAR_NODE(&info->offset_index); RB_CLEAR_NODE(&info->bytes_index); spin_lock(&ctl->tree_lock); if (try_merge_free_space(ctl, info, true)) goto link; /* * There was no extent directly to the left or right of this new * extent then we know we're going to have to allocate a new extent, so * before we do that see if we need to drop this into a bitmap */ ret = insert_into_bitmap(ctl, info); if (ret < 0) { goto out; } else if (ret) { ret = 0; goto out; } link: /* * Only steal free space from adjacent bitmaps if we're sure we're not * going to add the new free space to existing bitmap entries - because * that would mean unnecessary work that would be reverted. Therefore * attempt to steal space from bitmaps if we're adding an extent entry. */ steal_from_bitmap(ctl, info, true); filter_bytes = max(filter_bytes, info->bytes); ret = link_free_space(ctl, info); if (ret) kmem_cache_free(btrfs_free_space_cachep, info); out: btrfs_discard_update_discardable(block_group); spin_unlock(&ctl->tree_lock); if (ret) { btrfs_crit(fs_info, "unable to add free space :%d", ret); ASSERT(ret != -EEXIST); } if (trim_state != BTRFS_TRIM_STATE_TRIMMED) { btrfs_discard_check_filter(block_group, filter_bytes); btrfs_discard_queue_work(&fs_info->discard_ctl, block_group); } return ret; } static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group, u64 bytenr, u64 size, bool used) { struct btrfs_space_info *sinfo = block_group->space_info; struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; u64 offset = bytenr - block_group->start; u64 to_free, to_unusable; int bg_reclaim_threshold = 0; bool initial; u64 reclaimable_unusable; spin_lock(&block_group->lock); initial = ((size == block_group->length) && (block_group->alloc_offset == 0)); WARN_ON(!initial && offset + size > block_group->zone_capacity); if (!initial) bg_reclaim_threshold = READ_ONCE(sinfo->bg_reclaim_threshold); if (!used) to_free = size; else if (initial) to_free = block_group->zone_capacity; else if (offset >= block_group->alloc_offset) to_free = size; else if (offset + size <= block_group->alloc_offset) to_free = 0; else to_free = offset + size - block_group->alloc_offset; to_unusable = size - to_free; spin_lock(&ctl->tree_lock); ctl->free_space += to_free; spin_unlock(&ctl->tree_lock); /* * If the block group is read-only, we should account freed space into * bytes_readonly. */ if (!block_group->ro) { block_group->zone_unusable += to_unusable; WARN_ON(block_group->zone_unusable > block_group->length); } if (!used) { block_group->alloc_offset -= size; } reclaimable_unusable = block_group->zone_unusable - (block_group->length - block_group->zone_capacity); /* All the region is now unusable. Mark it as unused and reclaim */ if (block_group->zone_unusable == block_group->length) { btrfs_mark_bg_unused(block_group); } else if (bg_reclaim_threshold && reclaimable_unusable >= mult_perc(block_group->zone_capacity, bg_reclaim_threshold)) { btrfs_mark_bg_to_reclaim(block_group); } spin_unlock(&block_group->lock); return 0; } int btrfs_add_free_space(struct btrfs_block_group *block_group, u64 bytenr, u64 size) { enum btrfs_trim_state trim_state = BTRFS_TRIM_STATE_UNTRIMMED; if (btrfs_is_zoned(block_group->fs_info)) return __btrfs_add_free_space_zoned(block_group, bytenr, size, true); if (btrfs_test_opt(block_group->fs_info, DISCARD_SYNC)) trim_state = BTRFS_TRIM_STATE_TRIMMED; return __btrfs_add_free_space(block_group, bytenr, size, trim_state); } int btrfs_add_free_space_unused(struct btrfs_block_group *block_group, u64 bytenr, u64 size) { if (btrfs_is_zoned(block_group->fs_info)) return __btrfs_add_free_space_zoned(block_group, bytenr, size, false); return btrfs_add_free_space(block_group, bytenr, size); } /* * This is a subtle distinction because when adding free space back in general, * we want it to be added as untrimmed for async. But in the case where we add * it on loading of a block group, we want to consider it trimmed. */ int btrfs_add_free_space_async_trimmed(struct btrfs_block_group *block_group, u64 bytenr, u64 size) { enum btrfs_trim_state trim_state = BTRFS_TRIM_STATE_UNTRIMMED; if (btrfs_is_zoned(block_group->fs_info)) return __btrfs_add_free_space_zoned(block_group, bytenr, size, true); if (btrfs_test_opt(block_group->fs_info, DISCARD_SYNC) || btrfs_test_opt(block_group->fs_info, DISCARD_ASYNC)) trim_state = BTRFS_TRIM_STATE_TRIMMED; return __btrfs_add_free_space(block_group, bytenr, size, trim_state); } int btrfs_remove_free_space(struct btrfs_block_group *block_group, u64 offset, u64 bytes) { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; struct btrfs_free_space *info; int ret; bool re_search = false; if (btrfs_is_zoned(block_group->fs_info)) { /* * This can happen with conventional zones when replaying log. * Since the allocation info of tree-log nodes are not recorded * to the extent-tree, calculate_alloc_pointer() failed to * advance the allocation pointer after last allocated tree log * node blocks. * * This function is called from * btrfs_pin_extent_for_log_replay() when replaying the log. * Advance the pointer not to overwrite the tree-log nodes. */ if (block_group->start + block_group->alloc_offset < offset + bytes) { block_group->alloc_offset = offset + bytes - block_group->start; } return 0; } spin_lock(&ctl->tree_lock); again: ret = 0; if (!bytes) goto out_lock; info = tree_search_offset(ctl, offset, 0, 0); if (!info) { /* * oops didn't find an extent that matched the space we wanted * to remove, look for a bitmap instead */ info = tree_search_offset(ctl, offset_to_bitmap(ctl, offset), 1, 0); if (!info) { /* * If we found a partial bit of our free space in a * bitmap but then couldn't find the other part this may * be a problem, so WARN about it. */ WARN_ON(re_search); goto out_lock; } } re_search = false; if (!info->bitmap) { unlink_free_space(ctl, info, true); if (offset == info->offset) { u64 to_free = min(bytes, info->bytes); info->bytes -= to_free; info->offset += to_free; if (info->bytes) { ret = link_free_space(ctl, info); WARN_ON(ret); } else { kmem_cache_free(btrfs_free_space_cachep, info); } offset += to_free; bytes -= to_free; goto again; } else { u64 old_end = info->bytes + info->offset; info->bytes = offset - info->offset; ret = link_free_space(ctl, info); WARN_ON(ret); if (ret) goto out_lock; /* Not enough bytes in this entry to satisfy us */ if (old_end < offset + bytes) { bytes -= old_end - offset; offset = old_end; goto again; } else if (old_end == offset + bytes) { /* all done */ goto out_lock; } spin_unlock(&ctl->tree_lock); ret = __btrfs_add_free_space(block_group, offset + bytes, old_end - (offset + bytes), info->trim_state); WARN_ON(ret); goto out; } } ret = remove_from_bitmap(ctl, info, &offset, &bytes); if (ret == -EAGAIN) { re_search = true; goto again; } out_lock: btrfs_discard_update_discardable(block_group); spin_unlock(&ctl->tree_lock); out: return ret; } void btrfs_dump_free_space(struct btrfs_block_group *block_group, u64 bytes) { struct btrfs_fs_info *fs_info = block_group->fs_info; struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; struct btrfs_free_space *info; struct rb_node *n; int count = 0; /* * Zoned btrfs does not use free space tree and cluster. Just print * out the free space after the allocation offset. */ if (btrfs_is_zoned(fs_info)) { btrfs_info(fs_info, "free space %llu active %d", block_group->zone_capacity - block_group->alloc_offset, test_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &block_group->runtime_flags)); return; } spin_lock(&ctl->tree_lock); for (n = rb_first(&ctl->free_space_offset); n; n = rb_next(n)) { info = rb_entry(n, struct btrfs_free_space, offset_index); if (info->bytes >= bytes && !block_group->ro) count++; btrfs_crit(fs_info, "entry offset %llu, bytes %llu, bitmap %s", info->offset, info->bytes, str_yes_no(info->bitmap)); } spin_unlock(&ctl->tree_lock); btrfs_info(fs_info, "block group has cluster?: %s", str_no_yes(list_empty(&block_group->cluster_list))); btrfs_info(fs_info, "%d free space entries at or bigger than %llu bytes", count, bytes); } void btrfs_init_free_space_ctl(struct btrfs_block_group *block_group, struct btrfs_free_space_ctl *ctl) { struct btrfs_fs_info *fs_info = block_group->fs_info; spin_lock_init(&ctl->tree_lock); ctl->unit = fs_info->sectorsize; ctl->start = block_group->start; ctl->block_group = block_group; ctl->op = &free_space_op; ctl->free_space_bytes = RB_ROOT_CACHED; INIT_LIST_HEAD(&ctl->trimming_ranges); mutex_init(&ctl->cache_writeout_mutex); /* * we only want to have 32k of ram per block group for keeping * track of free space, and if we pass 1/2 of that we want to * start converting things over to using bitmaps */ ctl->extents_thresh = (SZ_32K / 2) / sizeof(struct btrfs_free_space); } /* * for a given cluster, put all of its extents back into the free * space cache. If the block group passed doesn't match the block group * pointed to by the cluster, someone else raced in and freed the * cluster already. In that case, we just return without changing anything */ static void __btrfs_return_cluster_to_free_space( struct btrfs_block_group *block_group, struct btrfs_free_cluster *cluster) { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; struct rb_node *node; lockdep_assert_held(&ctl->tree_lock); spin_lock(&cluster->lock); if (cluster->block_group != block_group) { spin_unlock(&cluster->lock); return; } cluster->block_group = NULL; cluster->window_start = 0; list_del_init(&cluster->block_group_list); node = rb_first(&cluster->root); while (node) { struct btrfs_free_space *entry; entry = rb_entry(node, struct btrfs_free_space, offset_index); node = rb_next(&entry->offset_index); rb_erase(&entry->offset_index, &cluster->root); RB_CLEAR_NODE(&entry->offset_index); if (!entry->bitmap) { /* Merging treats extents as if they were new */ if (!btrfs_free_space_trimmed(entry)) { ctl->discardable_extents[BTRFS_STAT_CURR]--; ctl->discardable_bytes[BTRFS_STAT_CURR] -= entry->bytes; } try_merge_free_space(ctl, entry, false); steal_from_bitmap(ctl, entry, false); /* As we insert directly, update these statistics */ if (!btrfs_free_space_trimmed(entry)) { ctl->discardable_extents[BTRFS_STAT_CURR]++; ctl->discardable_bytes[BTRFS_STAT_CURR] += entry->bytes; } } tree_insert_offset(ctl, NULL, entry); rb_add_cached(&entry->bytes_index, &ctl->free_space_bytes, entry_less); } cluster->root = RB_ROOT; spin_unlock(&cluster->lock); btrfs_put_block_group(block_group); } void btrfs_remove_free_space_cache(struct btrfs_block_group *block_group) { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; struct btrfs_free_cluster *cluster; struct list_head *head; spin_lock(&ctl->tree_lock); while ((head = block_group->cluster_list.next) != &block_group->cluster_list) { cluster = list_entry(head, struct btrfs_free_cluster, block_group_list); WARN_ON(cluster->block_group != block_group); __btrfs_return_cluster_to_free_space(block_group, cluster); cond_resched_lock(&ctl->tree_lock); } __btrfs_remove_free_space_cache(ctl); btrfs_discard_update_discardable(block_group); spin_unlock(&ctl->tree_lock); } /* * Walk @block_group's free space rb_tree to determine if everything is trimmed. */ bool btrfs_is_free_space_trimmed(struct btrfs_block_group *block_group) { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; struct btrfs_free_space *info; struct rb_node *node; bool ret = true; spin_lock(&ctl->tree_lock); node = rb_first(&ctl->free_space_offset); while (node) { info = rb_entry(node, struct btrfs_free_space, offset_index); if (!btrfs_free_space_trimmed(info)) { ret = false; break; } node = rb_next(node); } spin_unlock(&ctl->tree_lock); return ret; } u64 btrfs_find_space_for_alloc(struct btrfs_block_group *block_group, u64 offset, u64 bytes, u64 empty_size, u64 *max_extent_size) { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; struct btrfs_discard_ctl *discard_ctl = &block_group->fs_info->discard_ctl; struct btrfs_free_space *entry = NULL; u64 bytes_search = bytes + empty_size; u64 ret = 0; u64 align_gap = 0; u64 align_gap_len = 0; enum btrfs_trim_state align_gap_trim_state = BTRFS_TRIM_STATE_UNTRIMMED; bool use_bytes_index = (offset == block_group->start); ASSERT(!btrfs_is_zoned(block_group->fs_info)); spin_lock(&ctl->tree_lock); entry = find_free_space(ctl, &offset, &bytes_search, block_group->full_stripe_len, max_extent_size, use_bytes_index); if (!entry) goto out; ret = offset; if (entry->bitmap) { bitmap_clear_bits(ctl, entry, offset, bytes, true); if (!btrfs_free_space_trimmed(entry)) atomic64_add(bytes, &discard_ctl->discard_bytes_saved); if (!entry->bytes) free_bitmap(ctl, entry); } else { unlink_free_space(ctl, entry, true); align_gap_len = offset - entry->offset; align_gap = entry->offset; align_gap_trim_state = entry->trim_state; if (!btrfs_free_space_trimmed(entry)) atomic64_add(bytes, &discard_ctl->discard_bytes_saved); entry->offset = offset + bytes; WARN_ON(entry->bytes < bytes + align_gap_len); entry->bytes -= bytes + align_gap_len; if (!entry->bytes) kmem_cache_free(btrfs_free_space_cachep, entry); else link_free_space(ctl, entry); } out: btrfs_discard_update_discardable(block_group); spin_unlock(&ctl->tree_lock); if (align_gap_len) __btrfs_add_free_space(block_group, align_gap, align_gap_len, align_gap_trim_state); return ret; } /* * given a cluster, put all of its extents back into the free space * cache. If a block group is passed, this function will only free * a cluster that belongs to the passed block group. * * Otherwise, it'll get a reference on the block group pointed to by the * cluster and remove the cluster from it. */ void btrfs_return_cluster_to_free_space( struct btrfs_block_group *block_group, struct btrfs_free_cluster *cluster) { struct btrfs_free_space_ctl *ctl; /* first, get a safe pointer to the block group */ spin_lock(&cluster->lock); if (!block_group) { block_group = cluster->block_group; if (!block_group) { spin_unlock(&cluster->lock); return; } } else if (cluster->block_group != block_group) { /* someone else has already freed it don't redo their work */ spin_unlock(&cluster->lock); return; } btrfs_get_block_group(block_group); spin_unlock(&cluster->lock); ctl = block_group->free_space_ctl; /* now return any extents the cluster had on it */ spin_lock(&ctl->tree_lock); __btrfs_return_cluster_to_free_space(block_group, cluster); spin_unlock(&ctl->tree_lock); btrfs_discard_queue_work(&block_group->fs_info->discard_ctl, block_group); /* finally drop our ref */ btrfs_put_block_group(block_group); } static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group *block_group, struct btrfs_free_cluster *cluster, struct btrfs_free_space *entry, u64 bytes, u64 min_start, u64 *max_extent_size) { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; int err; u64 search_start = cluster->window_start; u64 search_bytes = bytes; u64 ret = 0; search_start = min_start; search_bytes = bytes; err = search_bitmap(ctl, entry, &search_start, &search_bytes, true); if (err) { *max_extent_size = max(get_max_extent_size(entry), *max_extent_size); return 0; } ret = search_start; bitmap_clear_bits(ctl, entry, ret, bytes, false); return ret; } /* * given a cluster, try to allocate 'bytes' from it, returns 0 * if it couldn't find anything suitably large, or a logical disk offset * if things worked out */ u64 btrfs_alloc_from_cluster(struct btrfs_block_group *block_group, struct btrfs_free_cluster *cluster, u64 bytes, u64 min_start, u64 *max_extent_size) { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; struct btrfs_discard_ctl *discard_ctl = &block_group->fs_info->discard_ctl; struct btrfs_free_space *entry = NULL; struct rb_node *node; u64 ret = 0; ASSERT(!btrfs_is_zoned(block_group->fs_info)); spin_lock(&cluster->lock); if (bytes > cluster->max_size) goto out; if (cluster->block_group != block_group) goto out; node = rb_first(&cluster->root); if (!node) goto out; entry = rb_entry(node, struct btrfs_free_space, offset_index); while (1) { if (entry->bytes < bytes) *max_extent_size = max(get_max_extent_size(entry), *max_extent_size); if (entry->bytes < bytes || (!entry->bitmap && entry->offset < min_start)) { node = rb_next(&entry->offset_index); if (!node) break; entry = rb_entry(node, struct btrfs_free_space, offset_index); continue; } if (entry->bitmap) { ret = btrfs_alloc_from_bitmap(block_group, cluster, entry, bytes, cluster->window_start, max_extent_size); if (ret == 0) { node = rb_next(&entry->offset_index); if (!node) break; entry = rb_entry(node, struct btrfs_free_space, offset_index); continue; } cluster->window_start += bytes; } else { ret = entry->offset; entry->offset += bytes; entry->bytes -= bytes; } break; } out: spin_unlock(&cluster->lock); if (!ret) return 0; spin_lock(&ctl->tree_lock); if (!btrfs_free_space_trimmed(entry)) atomic64_add(bytes, &discard_ctl->discard_bytes_saved); ctl->free_space -= bytes; if (!entry->bitmap && !btrfs_free_space_trimmed(entry)) ctl->discardable_bytes[BTRFS_STAT_CURR] -= bytes; spin_lock(&cluster->lock); if (entry->bytes == 0) { rb_erase(&entry->offset_index, &cluster->root); ctl->free_extents--; if (entry->bitmap) { kmem_cache_free(btrfs_free_space_bitmap_cachep, entry->bitmap); ctl->total_bitmaps--; recalculate_thresholds(ctl); } else if (!btrfs_free_space_trimmed(entry)) { ctl->discardable_extents[BTRFS_STAT_CURR]--; } kmem_cache_free(btrfs_free_space_cachep, entry); } spin_unlock(&cluster->lock); spin_unlock(&ctl->tree_lock); return ret; } static int btrfs_bitmap_cluster(struct btrfs_block_group *block_group, struct btrfs_free_space *entry, struct btrfs_free_cluster *cluster, u64 offset, u64 bytes, u64 cont1_bytes, u64 min_bytes) { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; unsigned long next_zero; unsigned long i; unsigned long want_bits; unsigned long min_bits; unsigned long found_bits; unsigned long max_bits = 0; unsigned long start = 0; unsigned long total_found = 0; int ret; lockdep_assert_held(&ctl->tree_lock); i = offset_to_bit(entry->offset, ctl->unit, max_t(u64, offset, entry->offset)); want_bits = bytes_to_bits(bytes, ctl->unit); min_bits = bytes_to_bits(min_bytes, ctl->unit); /* * Don't bother looking for a cluster in this bitmap if it's heavily * fragmented. */ if (entry->max_extent_size && entry->max_extent_size < cont1_bytes) return -ENOSPC; again: found_bits = 0; for_each_set_bit_from(i, entry->bitmap, BITS_PER_BITMAP) { next_zero = find_next_zero_bit(entry->bitmap, BITS_PER_BITMAP, i); if (next_zero - i >= min_bits) { found_bits = next_zero - i; if (found_bits > max_bits) max_bits = found_bits; break; } if (next_zero - i > max_bits) max_bits = next_zero - i; i = next_zero; } if (!found_bits) { entry->max_extent_size = (u64)max_bits * ctl->unit; return -ENOSPC; } if (!total_found) { start = i; cluster->max_size = 0; } total_found += found_bits; if (cluster->max_size < found_bits * ctl->unit) cluster->max_size = found_bits * ctl->unit; if (total_found < want_bits || cluster->max_size < cont1_bytes) { i = next_zero + 1; goto again; } cluster->window_start = start * ctl->unit + entry->offset; rb_erase(&entry->offset_index, &ctl->free_space_offset); rb_erase_cached(&entry->bytes_index, &ctl->free_space_bytes); /* * We need to know if we're currently on the normal space index when we * manipulate the bitmap so that we know we need to remove and re-insert * it into the space_index tree. Clear the bytes_index node here so the * bitmap manipulation helpers know not to mess with the space_index * until this bitmap entry is added back into the normal cache. */ RB_CLEAR_NODE(&entry->bytes_index); ret = tree_insert_offset(ctl, cluster, entry); ASSERT(!ret); /* -EEXIST; Logic error */ trace_btrfs_setup_cluster(block_group, cluster, total_found * ctl->unit, 1); return 0; } /* * This searches the block group for just extents to fill the cluster with. * Try to find a cluster with at least bytes total bytes, at least one * extent of cont1_bytes, and other clusters of at least min_bytes. */ static noinline int setup_cluster_no_bitmap(struct btrfs_block_group *block_group, struct btrfs_free_cluster *cluster, struct list_head *bitmaps, u64 offset, u64 bytes, u64 cont1_bytes, u64 min_bytes) { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; struct btrfs_free_space *first = NULL; struct btrfs_free_space *entry = NULL; struct btrfs_free_space *last; struct rb_node *node; u64 window_free; u64 max_extent; u64 total_size = 0; lockdep_assert_held(&ctl->tree_lock); entry = tree_search_offset(ctl, offset, 0, 1); if (!entry) return -ENOSPC; /* * We don't want bitmaps, so just move along until we find a normal * extent entry. */ while (entry->bitmap || entry->bytes < min_bytes) { if (entry->bitmap && list_empty(&entry->list)) list_add_tail(&entry->list, bitmaps); node = rb_next(&entry->offset_index); if (!node) return -ENOSPC; entry = rb_entry(node, struct btrfs_free_space, offset_index); } window_free = entry->bytes; max_extent = entry->bytes; first = entry; last = entry; for (node = rb_next(&entry->offset_index); node; node = rb_next(&entry->offset_index)) { entry = rb_entry(node, struct btrfs_free_space, offset_index); if (entry->bitmap) { if (list_empty(&entry->list)) list_add_tail(&entry->list, bitmaps); continue; } if (entry->bytes < min_bytes) continue; last = entry; window_free += entry->bytes; if (entry->bytes > max_extent) max_extent = entry->bytes; } if (window_free < bytes || max_extent < cont1_bytes) return -ENOSPC; cluster->window_start = first->offset; node = &first->offset_index; /* * now we've found our entries, pull them out of the free space * cache and put them into the cluster rbtree */ do { int ret; entry = rb_entry(node, struct btrfs_free_space, offset_index); node = rb_next(&entry->offset_index); if (entry->bitmap || entry->bytes < min_bytes) continue; rb_erase(&entry->offset_index, &ctl->free_space_offset); rb_erase_cached(&entry->bytes_index, &ctl->free_space_bytes); ret = tree_insert_offset(ctl, cluster, entry); total_size += entry->bytes; ASSERT(!ret); /* -EEXIST; Logic error */ } while (node && entry != last); cluster->max_size = max_extent; trace_btrfs_setup_cluster(block_group, cluster, total_size, 0); return 0; } /* * This specifically looks for bitmaps that may work in the cluster, we assume * that we have already failed to find extents that will work. */ static noinline int setup_cluster_bitmap(struct btrfs_block_group *block_group, struct btrfs_free_cluster *cluster, struct list_head *bitmaps, u64 offset, u64 bytes, u64 cont1_bytes, u64 min_bytes) { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; struct btrfs_free_space *entry = NULL; int ret = -ENOSPC; u64 bitmap_offset = offset_to_bitmap(ctl, offset); if (ctl->total_bitmaps == 0) return -ENOSPC; /* * The bitmap that covers offset won't be in the list unless offset * is just its start offset. */ if (!list_empty(bitmaps)) entry = list_first_entry(bitmaps, struct btrfs_free_space, list); if (!entry || entry->offset != bitmap_offset) { entry = tree_search_offset(ctl, bitmap_offset, 1, 0); if (entry && list_empty(&entry->list)) list_add(&entry->list, bitmaps); } list_for_each_entry(entry, bitmaps, list) { if (entry->bytes < bytes) continue; ret = btrfs_bitmap_cluster(block_group, entry, cluster, offset, bytes, cont1_bytes, min_bytes); if (!ret) return 0; } /* * The bitmaps list has all the bitmaps that record free space * starting after offset, so no more search is required. */ return -ENOSPC; } /* * here we try to find a cluster of blocks in a block group. The goal * is to find at least bytes+empty_size. * We might not find them all in one contiguous area. * * returns zero and sets up cluster if things worked out, otherwise * it returns -enospc */ int btrfs_find_space_cluster(struct btrfs_block_group *block_group, struct btrfs_free_cluster *cluster, u64 offset, u64 bytes, u64 empty_size) { struct btrfs_fs_info *fs_info = block_group->fs_info; struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; struct btrfs_free_space *entry, *tmp; LIST_HEAD(bitmaps); u64 min_bytes; u64 cont1_bytes; int ret; /* * Choose the minimum extent size we'll require for this * cluster. For SSD_SPREAD, don't allow any fragmentation. * For metadata, allow allocates with smaller extents. For * data, keep it dense. */ if (btrfs_test_opt(fs_info, SSD_SPREAD)) { cont1_bytes = bytes + empty_size; min_bytes = cont1_bytes; } else if (block_group->flags & BTRFS_BLOCK_GROUP_METADATA) { cont1_bytes = bytes; min_bytes = fs_info->sectorsize; } else { cont1_bytes = max(bytes, (bytes + empty_size) >> 2); min_bytes = fs_info->sectorsize; } spin_lock(&ctl->tree_lock); /* * If we know we don't have enough space to make a cluster don't even * bother doing all the work to try and find one. */ if (ctl->free_space < bytes) { spin_unlock(&ctl->tree_lock); return -ENOSPC; } spin_lock(&cluster->lock); /* someone already found a cluster, hooray */ if (cluster->block_group) { ret = 0; goto out; } trace_btrfs_find_cluster(block_group, offset, bytes, empty_size, min_bytes); ret = setup_cluster_no_bitmap(block_group, cluster, &bitmaps, offset, bytes + empty_size, cont1_bytes, min_bytes); if (ret) ret = setup_cluster_bitmap(block_group, cluster, &bitmaps, offset, bytes + empty_size, cont1_bytes, min_bytes); /* Clear our temporary list */ list_for_each_entry_safe(entry, tmp, &bitmaps, list) list_del_init(&entry->list); if (!ret) { btrfs_get_block_group(block_group); list_add_tail(&cluster->block_group_list, &block_group->cluster_list); cluster->block_group = block_group; } else { trace_btrfs_failed_cluster_setup(block_group); } out: spin_unlock(&cluster->lock); spin_unlock(&ctl->tree_lock); return ret; } /* * simple code to zero out a cluster */ void btrfs_init_free_cluster(struct btrfs_free_cluster *cluster) { spin_lock_init(&cluster->lock); spin_lock_init(&cluster->refill_lock); cluster->root = RB_ROOT; cluster->max_size = 0; cluster->fragmented = false; INIT_LIST_HEAD(&cluster->block_group_list); cluster->block_group = NULL; } static int do_trimming(struct btrfs_block_group *block_group, u64 *total_trimmed, u64 start, u64 bytes, u64 reserved_start, u64 reserved_bytes, enum btrfs_trim_state reserved_trim_state, struct btrfs_trim_range *trim_entry) { struct btrfs_space_info *space_info = block_group->space_info; struct btrfs_fs_info *fs_info = block_group->fs_info; struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; int ret; int update = 0; const u64 end = start + bytes; const u64 reserved_end = reserved_start + reserved_bytes; enum btrfs_trim_state trim_state = BTRFS_TRIM_STATE_UNTRIMMED; u64 trimmed = 0; spin_lock(&space_info->lock); spin_lock(&block_group->lock); if (!block_group->ro) { block_group->reserved += reserved_bytes; space_info->bytes_reserved += reserved_bytes; update = 1; } spin_unlock(&block_group->lock); spin_unlock(&space_info->lock); ret = btrfs_discard_extent(fs_info, start, bytes, &trimmed); if (!ret) { *total_trimmed += trimmed; trim_state = BTRFS_TRIM_STATE_TRIMMED; } mutex_lock(&ctl->cache_writeout_mutex); if (reserved_start < start) __btrfs_add_free_space(block_group, reserved_start, start - reserved_start, reserved_trim_state); if (end < reserved_end) __btrfs_add_free_space(block_group, end, reserved_end - end, reserved_trim_state); __btrfs_add_free_space(block_group, start, bytes, trim_state); list_del(&trim_entry->list); mutex_unlock(&ctl->cache_writeout_mutex); if (update) { spin_lock(&space_info->lock); spin_lock(&block_group->lock); if (block_group->ro) space_info->bytes_readonly += reserved_bytes; block_group->reserved -= reserved_bytes; space_info->bytes_reserved -= reserved_bytes; spin_unlock(&block_group->lock); spin_unlock(&space_info->lock); } return ret; } /* * If @async is set, then we will trim 1 region and return. */ static int trim_no_bitmap(struct btrfs_block_group *block_group, u64 *total_trimmed, u64 start, u64 end, u64 minlen, bool async) { struct btrfs_discard_ctl *discard_ctl = &block_group->fs_info->discard_ctl; struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; struct btrfs_free_space *entry; struct rb_node *node; int ret = 0; u64 extent_start; u64 extent_bytes; enum btrfs_trim_state extent_trim_state; u64 bytes; const u64 max_discard_size = READ_ONCE(discard_ctl->max_discard_size); while (start < end) { struct btrfs_trim_range trim_entry; mutex_lock(&ctl->cache_writeout_mutex); spin_lock(&ctl->tree_lock); if (ctl->free_space < minlen) goto out_unlock; entry = tree_search_offset(ctl, start, 0, 1); if (!entry) goto out_unlock; /* Skip bitmaps and if async, already trimmed entries */ while (entry->bitmap || (async && btrfs_free_space_trimmed(entry))) { node = rb_next(&entry->offset_index); if (!node) goto out_unlock; entry = rb_entry(node, struct btrfs_free_space, offset_index); } if (entry->offset >= end) goto out_unlock; extent_start = entry->offset; extent_bytes = entry->bytes; extent_trim_state = entry->trim_state; if (async) { start = entry->offset; bytes = entry->bytes; if (bytes < minlen) { spin_unlock(&ctl->tree_lock); mutex_unlock(&ctl->cache_writeout_mutex); goto next; } unlink_free_space(ctl, entry, true); /* * Let bytes = BTRFS_MAX_DISCARD_SIZE + X. * If X < BTRFS_ASYNC_DISCARD_MIN_FILTER, we won't trim * X when we come back around. So trim it now. */ if (max_discard_size && bytes >= (max_discard_size + BTRFS_ASYNC_DISCARD_MIN_FILTER)) { bytes = max_discard_size; extent_bytes = max_discard_size; entry->offset += max_discard_size; entry->bytes -= max_discard_size; link_free_space(ctl, entry); } else { kmem_cache_free(btrfs_free_space_cachep, entry); } } else { start = max(start, extent_start); bytes = min(extent_start + extent_bytes, end) - start; if (bytes < minlen) { spin_unlock(&ctl->tree_lock); mutex_unlock(&ctl->cache_writeout_mutex); goto next; } unlink_free_space(ctl, entry, true); kmem_cache_free(btrfs_free_space_cachep, entry); } spin_unlock(&ctl->tree_lock); trim_entry.start = extent_start; trim_entry.bytes = extent_bytes; list_add_tail(&trim_entry.list, &ctl->trimming_ranges); mutex_unlock(&ctl->cache_writeout_mutex); ret = do_trimming(block_group, total_trimmed, start, bytes, extent_start, extent_bytes, extent_trim_state, &trim_entry); if (ret) { block_group->discard_cursor = start + bytes; break; } next: start += bytes; block_group->discard_cursor = start; if (async && *total_trimmed) break; if (btrfs_trim_interrupted()) { ret = -ERESTARTSYS; break; } cond_resched(); } return ret; out_unlock: block_group->discard_cursor = btrfs_block_group_end(block_group); spin_unlock(&ctl->tree_lock); mutex_unlock(&ctl->cache_writeout_mutex); return ret; } /* * If we break out of trimming a bitmap prematurely, we should reset the * trimming bit. In a rather contrieved case, it's possible to race here so * reset the state to BTRFS_TRIM_STATE_UNTRIMMED. * * start = start of bitmap * end = near end of bitmap * * Thread 1: Thread 2: * trim_bitmaps(start) * trim_bitmaps(end) * end_trimming_bitmap() * reset_trimming_bitmap() */ static void reset_trimming_bitmap(struct btrfs_free_space_ctl *ctl, u64 offset) { struct btrfs_free_space *entry; spin_lock(&ctl->tree_lock); entry = tree_search_offset(ctl, offset, 1, 0); if (entry) { if (btrfs_free_space_trimmed(entry)) { ctl->discardable_extents[BTRFS_STAT_CURR] += entry->bitmap_extents; ctl->discardable_bytes[BTRFS_STAT_CURR] += entry->bytes; } entry->trim_state = BTRFS_TRIM_STATE_UNTRIMMED; } spin_unlock(&ctl->tree_lock); } static void end_trimming_bitmap(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *entry) { if (btrfs_free_space_trimming_bitmap(entry)) { entry->trim_state = BTRFS_TRIM_STATE_TRIMMED; ctl->discardable_extents[BTRFS_STAT_CURR] -= entry->bitmap_extents; ctl->discardable_bytes[BTRFS_STAT_CURR] -= entry->bytes; } } /* * If @async is set, then we will trim 1 region and return. */ static int trim_bitmaps(struct btrfs_block_group *block_group, u64 *total_trimmed, u64 start, u64 end, u64 minlen, u64 maxlen, bool async) { struct btrfs_discard_ctl *discard_ctl = &block_group->fs_info->discard_ctl; struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; struct btrfs_free_space *entry; int ret = 0; int ret2; u64 bytes; u64 offset = offset_to_bitmap(ctl, start); const u64 max_discard_size = READ_ONCE(discard_ctl->max_discard_size); while (offset < end) { bool next_bitmap = false; struct btrfs_trim_range trim_entry; mutex_lock(&ctl->cache_writeout_mutex); spin_lock(&ctl->tree_lock); if (ctl->free_space < minlen) { block_group->discard_cursor = btrfs_block_group_end(block_group); spin_unlock(&ctl->tree_lock); mutex_unlock(&ctl->cache_writeout_mutex); break; } entry = tree_search_offset(ctl, offset, 1, 0); /* * Bitmaps are marked trimmed lossily now to prevent constant * discarding of the same bitmap (the reason why we are bound * by the filters). So, retrim the block group bitmaps when we * are preparing to punt to the unused_bgs list. This uses * @minlen to determine if we are in BTRFS_DISCARD_INDEX_UNUSED * which is the only discard index which sets minlen to 0. */ if (!entry || (async && minlen && start == offset && btrfs_free_space_trimmed(entry))) { spin_unlock(&ctl->tree_lock); mutex_unlock(&ctl->cache_writeout_mutex); next_bitmap = true; goto next; } /* * Async discard bitmap trimming begins at by setting the start * to be key.objectid and the offset_to_bitmap() aligns to the * start of the bitmap. This lets us know we are fully * scanning the bitmap rather than only some portion of it. */ if (start == offset) entry->trim_state = BTRFS_TRIM_STATE_TRIMMING; bytes = minlen; ret2 = search_bitmap(ctl, entry, &start, &bytes, false); if (ret2 || start >= end) { /* * We lossily consider a bitmap trimmed if we only skip * over regions <= BTRFS_ASYNC_DISCARD_MIN_FILTER. */ if (ret2 && minlen <= BTRFS_ASYNC_DISCARD_MIN_FILTER) end_trimming_bitmap(ctl, entry); else entry->trim_state = BTRFS_TRIM_STATE_UNTRIMMED; spin_unlock(&ctl->tree_lock); mutex_unlock(&ctl->cache_writeout_mutex); next_bitmap = true; goto next; } /* * We already trimmed a region, but are using the locking above * to reset the trim_state. */ if (async && *total_trimmed) { spin_unlock(&ctl->tree_lock); mutex_unlock(&ctl->cache_writeout_mutex); goto out; } bytes = min(bytes, end - start); if (bytes < minlen || (async && maxlen && bytes > maxlen)) { spin_unlock(&ctl->tree_lock); mutex_unlock(&ctl->cache_writeout_mutex); goto next; } /* * Let bytes = BTRFS_MAX_DISCARD_SIZE + X. * If X < @minlen, we won't trim X when we come back around. * So trim it now. We differ here from trimming extents as we * don't keep individual state per bit. */ if (async && max_discard_size && bytes > (max_discard_size + minlen)) bytes = max_discard_size; bitmap_clear_bits(ctl, entry, start, bytes, true); if (entry->bytes == 0) free_bitmap(ctl, entry); spin_unlock(&ctl->tree_lock); trim_entry.start = start; trim_entry.bytes = bytes; list_add_tail(&trim_entry.list, &ctl->trimming_ranges); mutex_unlock(&ctl->cache_writeout_mutex); ret = do_trimming(block_group, total_trimmed, start, bytes, start, bytes, 0, &trim_entry); if (ret) { reset_trimming_bitmap(ctl, offset); block_group->discard_cursor = btrfs_block_group_end(block_group); break; } next: if (next_bitmap) { offset += BITS_PER_BITMAP * ctl->unit; start = offset; } else { start += bytes; } block_group->discard_cursor = start; if (btrfs_trim_interrupted()) { if (start != offset) reset_trimming_bitmap(ctl, offset); ret = -ERESTARTSYS; break; } cond_resched(); } if (offset >= end) block_group->discard_cursor = end; out: return ret; } int btrfs_trim_block_group(struct btrfs_block_group *block_group, u64 *trimmed, u64 start, u64 end, u64 minlen) { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; int ret; u64 rem = 0; ASSERT(!btrfs_is_zoned(block_group->fs_info)); *trimmed = 0; spin_lock(&block_group->lock); if (test_bit(BLOCK_GROUP_FLAG_REMOVED, &block_group->runtime_flags)) { spin_unlock(&block_group->lock); return 0; } btrfs_freeze_block_group(block_group); spin_unlock(&block_group->lock); ret = trim_no_bitmap(block_group, trimmed, start, end, minlen, false); if (ret) goto out; ret = trim_bitmaps(block_group, trimmed, start, end, minlen, 0, false); div64_u64_rem(end, BITS_PER_BITMAP * ctl->unit, &rem); /* If we ended in the middle of a bitmap, reset the trimming flag */ if (rem) reset_trimming_bitmap(ctl, offset_to_bitmap(ctl, end)); out: btrfs_unfreeze_block_group(block_group); return ret; } int btrfs_trim_block_group_extents(struct btrfs_block_group *block_group, u64 *trimmed, u64 start, u64 end, u64 minlen, bool async) { int ret; *trimmed = 0; spin_lock(&block_group->lock); if (test_bit(BLOCK_GROUP_FLAG_REMOVED, &block_group->runtime_flags)) { spin_unlock(&block_group->lock); return 0; } btrfs_freeze_block_group(block_group); spin_unlock(&block_group->lock); ret = trim_no_bitmap(block_group, trimmed, start, end, minlen, async); btrfs_unfreeze_block_group(block_group); return ret; } int btrfs_trim_block_group_bitmaps(struct btrfs_block_group *block_group, u64 *trimmed, u64 start, u64 end, u64 minlen, u64 maxlen, bool async) { int ret; *trimmed = 0; spin_lock(&block_group->lock); if (test_bit(BLOCK_GROUP_FLAG_REMOVED, &block_group->runtime_flags)) { spin_unlock(&block_group->lock); return 0; } btrfs_freeze_block_group(block_group); spin_unlock(&block_group->lock); ret = trim_bitmaps(block_group, trimmed, start, end, minlen, maxlen, async); btrfs_unfreeze_block_group(block_group); return ret; } bool btrfs_free_space_cache_v1_active(struct btrfs_fs_info *fs_info) { return btrfs_super_cache_generation(fs_info->super_copy); } static int cleanup_free_space_cache_v1(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans) { struct btrfs_block_group *block_group; struct rb_node *node; int ret = 0; btrfs_info(fs_info, "cleaning free space cache v1"); node = rb_first_cached(&fs_info->block_group_cache_tree); while (node) { block_group = rb_entry(node, struct btrfs_block_group, cache_node); ret = btrfs_remove_free_space_inode(trans, NULL, block_group); if (ret) goto out; node = rb_next(node); } out: return ret; } int btrfs_set_free_space_cache_v1_active(struct btrfs_fs_info *fs_info, bool active) { struct btrfs_trans_handle *trans; int ret; /* * update_super_roots will appropriately set or unset * super_copy->cache_generation based on SPACE_CACHE and * BTRFS_FS_CLEANUP_SPACE_CACHE_V1. For this reason, we need a * transaction commit whether we are enabling space cache v1 and don't * have any other work to do, or are disabling it and removing free * space inodes. */ trans = btrfs_start_transaction(fs_info->tree_root, 0); if (IS_ERR(trans)) return PTR_ERR(trans); if (!active) { set_bit(BTRFS_FS_CLEANUP_SPACE_CACHE_V1, &fs_info->flags); ret = cleanup_free_space_cache_v1(fs_info, trans); if (ret) { btrfs_abort_transaction(trans, ret); btrfs_end_transaction(trans); goto out; } } ret = btrfs_commit_transaction(trans); out: clear_bit(BTRFS_FS_CLEANUP_SPACE_CACHE_V1, &fs_info->flags); return ret; } int __init btrfs_free_space_init(void) { btrfs_free_space_cachep = KMEM_CACHE(btrfs_free_space, 0); if (!btrfs_free_space_cachep) return -ENOMEM; btrfs_free_space_bitmap_cachep = kmem_cache_create("btrfs_free_space_bitmap", PAGE_SIZE, PAGE_SIZE, 0, NULL); if (!btrfs_free_space_bitmap_cachep) { kmem_cache_destroy(btrfs_free_space_cachep); return -ENOMEM; } return 0; } void __cold btrfs_free_space_exit(void) { kmem_cache_destroy(btrfs_free_space_cachep); kmem_cache_destroy(btrfs_free_space_bitmap_cachep); } #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS /* * Use this if you need to make a bitmap or extent entry specifically, it * doesn't do any of the merging that add_free_space does, this acts a lot like * how the free space cache loading stuff works, so you can get really weird * configurations. */ int test_add_free_space_entry(struct btrfs_block_group *cache, u64 offset, u64 bytes, bool bitmap) { struct btrfs_free_space_ctl *ctl = cache->free_space_ctl; struct btrfs_free_space *info = NULL, *bitmap_info; void *map = NULL; enum btrfs_trim_state trim_state = BTRFS_TRIM_STATE_TRIMMED; u64 bytes_added; int ret; again: if (!info) { info = kmem_cache_zalloc(btrfs_free_space_cachep, GFP_NOFS); if (!info) return -ENOMEM; } if (!bitmap) { spin_lock(&ctl->tree_lock); info->offset = offset; info->bytes = bytes; info->max_extent_size = 0; ret = link_free_space(ctl, info); spin_unlock(&ctl->tree_lock); if (ret) kmem_cache_free(btrfs_free_space_cachep, info); return ret; } if (!map) { map = kmem_cache_zalloc(btrfs_free_space_bitmap_cachep, GFP_NOFS); if (!map) { kmem_cache_free(btrfs_free_space_cachep, info); return -ENOMEM; } } spin_lock(&ctl->tree_lock); bitmap_info = tree_search_offset(ctl, offset_to_bitmap(ctl, offset), 1, 0); if (!bitmap_info) { info->bitmap = map; map = NULL; add_new_bitmap(ctl, info, offset); bitmap_info = info; info = NULL; } bytes_added = add_bytes_to_bitmap(ctl, bitmap_info, offset, bytes, trim_state); bytes -= bytes_added; offset += bytes_added; spin_unlock(&ctl->tree_lock); if (bytes) goto again; if (info) kmem_cache_free(btrfs_free_space_cachep, info); if (map) kmem_cache_free(btrfs_free_space_bitmap_cachep, map); return 0; } /* * Checks to see if the given range is in the free space cache. This is really * just used to check the absence of space, so if there is free space in the * range at all we will return 1. */ int test_check_exists(struct btrfs_block_group *cache, u64 offset, u64 bytes) { struct btrfs_free_space_ctl *ctl = cache->free_space_ctl; struct btrfs_free_space *info; int ret = 0; spin_lock(&ctl->tree_lock); info = tree_search_offset(ctl, offset, 0, 0); if (!info) { info = tree_search_offset(ctl, offset_to_bitmap(ctl, offset), 1, 0); if (!info) goto out; } have_info: if (info->bitmap) { u64 bit_off, bit_bytes; struct rb_node *n; struct btrfs_free_space *tmp; bit_off = offset; bit_bytes = ctl->unit; ret = search_bitmap(ctl, info, &bit_off, &bit_bytes, false); if (!ret) { if (bit_off == offset) { ret = 1; goto out; } else if (bit_off > offset && offset + bytes > bit_off) { ret = 1; goto out; } } n = rb_prev(&info->offset_index); while (n) { tmp = rb_entry(n, struct btrfs_free_space, offset_index); if (tmp->offset + tmp->bytes < offset) break; if (offset + bytes < tmp->offset) { n = rb_prev(&tmp->offset_index); continue; } info = tmp; goto have_info; } n = rb_next(&info->offset_index); while (n) { tmp = rb_entry(n, struct btrfs_free_space, offset_index); if (offset + bytes < tmp->offset) break; if (tmp->offset + tmp->bytes < offset) { n = rb_next(&tmp->offset_index); continue; } info = tmp; goto have_info; } ret = 0; goto out; } if (info->offset == offset) { ret = 1; goto out; } if (offset > info->offset && offset < info->offset + info->bytes) ret = 1; out: spin_unlock(&ctl->tree_lock); return ret; } #endif /* CONFIG_BTRFS_FS_RUN_SANITY_TESTS */ |
| 10 10 9 9 2 1 1 1 10 10 10 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/gc.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ */ #include <linux/fs.h> #include <linux/module.h> #include <linux/init.h> #include <linux/f2fs_fs.h> #include <linux/kthread.h> #include <linux/delay.h> #include <linux/freezer.h> #include <linux/sched/signal.h> #include <linux/random.h> #include <linux/sched/mm.h> #include "f2fs.h" #include "node.h" #include "segment.h" #include "gc.h" #include "iostat.h" #include <trace/events/f2fs.h> static struct kmem_cache *victim_entry_slab; static unsigned int count_bits(const unsigned long *addr, unsigned int offset, unsigned int len); static int gc_thread_func(void *data) { struct f2fs_sb_info *sbi = data; struct f2fs_gc_kthread *gc_th = sbi->gc_thread; wait_queue_head_t *wq = &sbi->gc_thread->gc_wait_queue_head; wait_queue_head_t *fggc_wq = &sbi->gc_thread->fggc_wq; unsigned int wait_ms; struct f2fs_gc_control gc_control = { .victim_segno = NULL_SEGNO, .should_migrate_blocks = false, .err_gc_skipped = false }; wait_ms = gc_th->min_sleep_time; set_freezable(); do { bool sync_mode, foreground = false; wait_event_freezable_timeout(*wq, kthread_should_stop() || waitqueue_active(fggc_wq) || gc_th->gc_wake, msecs_to_jiffies(wait_ms)); if (test_opt(sbi, GC_MERGE) && waitqueue_active(fggc_wq)) foreground = true; /* give it a try one time */ if (gc_th->gc_wake) gc_th->gc_wake = false; if (f2fs_readonly(sbi->sb)) { stat_other_skip_bggc_count(sbi); continue; } if (kthread_should_stop()) break; if (sbi->sb->s_writers.frozen >= SB_FREEZE_WRITE) { increase_sleep_time(gc_th, &wait_ms); stat_other_skip_bggc_count(sbi); continue; } if (time_to_inject(sbi, FAULT_CHECKPOINT)) f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_FAULT_INJECT); if (!sb_start_write_trylock(sbi->sb)) { stat_other_skip_bggc_count(sbi); continue; } gc_control.one_time = false; /* * [GC triggering condition] * 0. GC is not conducted currently. * 1. There are enough dirty segments. * 2. IO subsystem is idle by checking the # of writeback pages. * 3. IO subsystem is idle by checking the # of requests in * bdev's request list. * * Note) We have to avoid triggering GCs frequently. * Because it is possible that some segments can be * invalidated soon after by user update or deletion. * So, I'd like to wait some time to collect dirty segments. */ if (sbi->gc_mode == GC_URGENT_HIGH || sbi->gc_mode == GC_URGENT_MID) { wait_ms = gc_th->urgent_sleep_time; f2fs_down_write(&sbi->gc_lock); goto do_gc; } if (foreground) { f2fs_down_write(&sbi->gc_lock); goto do_gc; } else if (!f2fs_down_write_trylock(&sbi->gc_lock)) { stat_other_skip_bggc_count(sbi); goto next; } if (!is_idle(sbi, GC_TIME)) { increase_sleep_time(gc_th, &wait_ms); f2fs_up_write(&sbi->gc_lock); stat_io_skip_bggc_count(sbi); goto next; } if (f2fs_sb_has_blkzoned(sbi)) { if (has_enough_free_blocks(sbi, gc_th->no_zoned_gc_percent)) { wait_ms = gc_th->no_gc_sleep_time; f2fs_up_write(&sbi->gc_lock); goto next; } if (wait_ms == gc_th->no_gc_sleep_time) wait_ms = gc_th->max_sleep_time; } if (need_to_boost_gc(sbi)) { decrease_sleep_time(gc_th, &wait_ms); if (f2fs_sb_has_blkzoned(sbi)) gc_control.one_time = true; } else { increase_sleep_time(gc_th, &wait_ms); } do_gc: stat_inc_gc_call_count(sbi, foreground ? FOREGROUND : BACKGROUND); sync_mode = (F2FS_OPTION(sbi).bggc_mode == BGGC_MODE_SYNC) || gc_control.one_time; /* foreground GC was been triggered via f2fs_balance_fs() */ if (foreground) sync_mode = false; gc_control.init_gc_type = sync_mode ? FG_GC : BG_GC; gc_control.no_bg_gc = foreground; gc_control.nr_free_secs = foreground ? 1 : 0; /* if return value is not zero, no victim was selected */ if (f2fs_gc(sbi, &gc_control)) { /* don't bother wait_ms by foreground gc */ if (!foreground) wait_ms = gc_th->no_gc_sleep_time; } else { /* reset wait_ms to default sleep time */ if (wait_ms == gc_th->no_gc_sleep_time) wait_ms = gc_th->min_sleep_time; } if (foreground) wake_up_all(&gc_th->fggc_wq); trace_f2fs_background_gc(sbi->sb, wait_ms, prefree_segments(sbi), free_segments(sbi)); /* balancing f2fs's metadata periodically */ f2fs_balance_fs_bg(sbi, true); next: if (sbi->gc_mode != GC_NORMAL) { spin_lock(&sbi->gc_remaining_trials_lock); if (sbi->gc_remaining_trials) { sbi->gc_remaining_trials--; if (!sbi->gc_remaining_trials) sbi->gc_mode = GC_NORMAL; } spin_unlock(&sbi->gc_remaining_trials_lock); } sb_end_write(sbi->sb); } while (!kthread_should_stop()); return 0; } int f2fs_start_gc_thread(struct f2fs_sb_info *sbi) { struct f2fs_gc_kthread *gc_th; dev_t dev = sbi->sb->s_bdev->bd_dev; gc_th = f2fs_kmalloc(sbi, sizeof(struct f2fs_gc_kthread), GFP_KERNEL); if (!gc_th) return -ENOMEM; gc_th->urgent_sleep_time = DEF_GC_THREAD_URGENT_SLEEP_TIME; gc_th->valid_thresh_ratio = DEF_GC_THREAD_VALID_THRESH_RATIO; if (f2fs_sb_has_blkzoned(sbi)) { gc_th->min_sleep_time = DEF_GC_THREAD_MIN_SLEEP_TIME_ZONED; gc_th->max_sleep_time = DEF_GC_THREAD_MAX_SLEEP_TIME_ZONED; gc_th->no_gc_sleep_time = DEF_GC_THREAD_NOGC_SLEEP_TIME_ZONED; gc_th->no_zoned_gc_percent = LIMIT_NO_ZONED_GC; gc_th->boost_zoned_gc_percent = LIMIT_BOOST_ZONED_GC; } else { gc_th->min_sleep_time = DEF_GC_THREAD_MIN_SLEEP_TIME; gc_th->max_sleep_time = DEF_GC_THREAD_MAX_SLEEP_TIME; gc_th->no_gc_sleep_time = DEF_GC_THREAD_NOGC_SLEEP_TIME; gc_th->no_zoned_gc_percent = 0; gc_th->boost_zoned_gc_percent = 0; } gc_th->gc_wake = false; sbi->gc_thread = gc_th; init_waitqueue_head(&sbi->gc_thread->gc_wait_queue_head); init_waitqueue_head(&sbi->gc_thread->fggc_wq); sbi->gc_thread->f2fs_gc_task = kthread_run(gc_thread_func, sbi, "f2fs_gc-%u:%u", MAJOR(dev), MINOR(dev)); if (IS_ERR(gc_th->f2fs_gc_task)) { int err = PTR_ERR(gc_th->f2fs_gc_task); kfree(gc_th); sbi->gc_thread = NULL; return err; } return 0; } void f2fs_stop_gc_thread(struct f2fs_sb_info *sbi) { struct f2fs_gc_kthread *gc_th = sbi->gc_thread; if (!gc_th) return; kthread_stop(gc_th->f2fs_gc_task); wake_up_all(&gc_th->fggc_wq); kfree(gc_th); sbi->gc_thread = NULL; } static int select_gc_type(struct f2fs_sb_info *sbi, int gc_type) { int gc_mode; if (gc_type == BG_GC) { if (sbi->am.atgc_enabled) gc_mode = GC_AT; else gc_mode = GC_CB; } else { gc_mode = GC_GREEDY; } switch (sbi->gc_mode) { case GC_IDLE_CB: gc_mode = GC_CB; break; case GC_IDLE_GREEDY: case GC_URGENT_HIGH: gc_mode = GC_GREEDY; break; case GC_IDLE_AT: gc_mode = GC_AT; break; } return gc_mode; } static void select_policy(struct f2fs_sb_info *sbi, int gc_type, int type, struct victim_sel_policy *p) { struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); if (p->alloc_mode == SSR) { p->gc_mode = GC_GREEDY; p->dirty_bitmap = dirty_i->dirty_segmap[type]; p->max_search = dirty_i->nr_dirty[type]; p->ofs_unit = 1; } else if (p->alloc_mode == AT_SSR) { p->gc_mode = GC_GREEDY; p->dirty_bitmap = dirty_i->dirty_segmap[type]; p->max_search = dirty_i->nr_dirty[type]; p->ofs_unit = 1; } else { p->gc_mode = select_gc_type(sbi, gc_type); p->ofs_unit = SEGS_PER_SEC(sbi); if (__is_large_section(sbi)) { p->dirty_bitmap = dirty_i->dirty_secmap; p->max_search = count_bits(p->dirty_bitmap, 0, MAIN_SECS(sbi)); } else { p->dirty_bitmap = dirty_i->dirty_segmap[DIRTY]; p->max_search = dirty_i->nr_dirty[DIRTY]; } } /* * adjust candidates range, should select all dirty segments for * foreground GC and urgent GC cases. */ if (gc_type != FG_GC && (sbi->gc_mode != GC_URGENT_HIGH) && (p->gc_mode != GC_AT && p->alloc_mode != AT_SSR) && p->max_search > sbi->max_victim_search) p->max_search = sbi->max_victim_search; /* let's select beginning hot/small space first. */ if (f2fs_need_rand_seg(sbi)) p->offset = get_random_u32_below(MAIN_SECS(sbi) * SEGS_PER_SEC(sbi)); else if (type == CURSEG_HOT_DATA || IS_NODESEG(type)) p->offset = 0; else p->offset = SIT_I(sbi)->last_victim[p->gc_mode]; } static unsigned int get_max_cost(struct f2fs_sb_info *sbi, struct victim_sel_policy *p) { /* SSR allocates in a segment unit */ if (p->alloc_mode == SSR) return BLKS_PER_SEG(sbi); else if (p->alloc_mode == AT_SSR) return UINT_MAX; /* LFS */ if (p->gc_mode == GC_GREEDY) return SEGS_TO_BLKS(sbi, 2 * p->ofs_unit); else if (p->gc_mode == GC_CB) return UINT_MAX; else if (p->gc_mode == GC_AT) return UINT_MAX; else /* No other gc_mode */ return 0; } static unsigned int check_bg_victims(struct f2fs_sb_info *sbi) { struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); unsigned int secno; /* * If the gc_type is FG_GC, we can select victim segments * selected by background GC before. * Those segments guarantee they have small valid blocks. */ for_each_set_bit(secno, dirty_i->victim_secmap, MAIN_SECS(sbi)) { if (sec_usage_check(sbi, secno)) continue; clear_bit(secno, dirty_i->victim_secmap); return GET_SEG_FROM_SEC(sbi, secno); } return NULL_SEGNO; } static unsigned int get_cb_cost(struct f2fs_sb_info *sbi, unsigned int segno) { struct sit_info *sit_i = SIT_I(sbi); unsigned int secno = GET_SEC_FROM_SEG(sbi, segno); unsigned int start = GET_SEG_FROM_SEC(sbi, secno); unsigned long long mtime = 0; unsigned int vblocks; unsigned char age = 0; unsigned char u; unsigned int i; unsigned int usable_segs_per_sec = f2fs_usable_segs_in_sec(sbi); for (i = 0; i < usable_segs_per_sec; i++) mtime += get_seg_entry(sbi, start + i)->mtime; vblocks = get_valid_blocks(sbi, segno, true); mtime = div_u64(mtime, usable_segs_per_sec); vblocks = div_u64(vblocks, usable_segs_per_sec); u = BLKS_TO_SEGS(sbi, vblocks * 100); /* Handle if the system time has changed by the user */ if (mtime < sit_i->min_mtime) sit_i->min_mtime = mtime; if (mtime > sit_i->max_mtime) sit_i->max_mtime = mtime; if (sit_i->max_mtime != sit_i->min_mtime) age = 100 - div64_u64(100 * (mtime - sit_i->min_mtime), sit_i->max_mtime - sit_i->min_mtime); return UINT_MAX - ((100 * (100 - u) * age) / (100 + u)); } static inline unsigned int get_gc_cost(struct f2fs_sb_info *sbi, unsigned int segno, struct victim_sel_policy *p) { if (p->alloc_mode == SSR) return get_seg_entry(sbi, segno)->ckpt_valid_blocks; if (p->one_time_gc && (get_valid_blocks(sbi, segno, true) >= CAP_BLKS_PER_SEC(sbi) * sbi->gc_thread->valid_thresh_ratio / 100)) return UINT_MAX; /* alloc_mode == LFS */ if (p->gc_mode == GC_GREEDY) return get_valid_blocks(sbi, segno, true); else if (p->gc_mode == GC_CB) return get_cb_cost(sbi, segno); f2fs_bug_on(sbi, 1); return 0; } static unsigned int count_bits(const unsigned long *addr, unsigned int offset, unsigned int len) { unsigned int end = offset + len, sum = 0; while (offset < end) { if (test_bit(offset++, addr)) ++sum; } return sum; } static bool f2fs_check_victim_tree(struct f2fs_sb_info *sbi, struct rb_root_cached *root) { #ifdef CONFIG_F2FS_CHECK_FS struct rb_node *cur = rb_first_cached(root), *next; struct victim_entry *cur_ve, *next_ve; while (cur) { next = rb_next(cur); if (!next) return true; cur_ve = rb_entry(cur, struct victim_entry, rb_node); next_ve = rb_entry(next, struct victim_entry, rb_node); if (cur_ve->mtime > next_ve->mtime) { f2fs_info(sbi, "broken victim_rbtree, " "cur_mtime(%llu) next_mtime(%llu)", cur_ve->mtime, next_ve->mtime); return false; } cur = next; } #endif return true; } static struct victim_entry *__lookup_victim_entry(struct f2fs_sb_info *sbi, unsigned long long mtime) { struct atgc_management *am = &sbi->am; struct rb_node *node = am->root.rb_root.rb_node; struct victim_entry *ve = NULL; while (node) { ve = rb_entry(node, struct victim_entry, rb_node); if (mtime < ve->mtime) node = node->rb_left; else node = node->rb_right; } return ve; } static struct victim_entry *__create_victim_entry(struct f2fs_sb_info *sbi, unsigned long long mtime, unsigned int segno) { struct atgc_management *am = &sbi->am; struct victim_entry *ve; ve = f2fs_kmem_cache_alloc(victim_entry_slab, GFP_NOFS, true, NULL); ve->mtime = mtime; ve->segno = segno; list_add_tail(&ve->list, &am->victim_list); am->victim_count++; return ve; } static void __insert_victim_entry(struct f2fs_sb_info *sbi, unsigned long long mtime, unsigned int segno) { struct atgc_management *am = &sbi->am; struct rb_root_cached *root = &am->root; struct rb_node **p = &root->rb_root.rb_node; struct rb_node *parent = NULL; struct victim_entry *ve; bool left_most = true; /* look up rb tree to find parent node */ while (*p) { parent = *p; ve = rb_entry(parent, struct victim_entry, rb_node); if (mtime < ve->mtime) { p = &(*p)->rb_left; } else { p = &(*p)->rb_right; left_most = false; } } ve = __create_victim_entry(sbi, mtime, segno); rb_link_node(&ve->rb_node, parent, p); rb_insert_color_cached(&ve->rb_node, root, left_most); } static void add_victim_entry(struct f2fs_sb_info *sbi, struct victim_sel_policy *p, unsigned int segno) { struct sit_info *sit_i = SIT_I(sbi); unsigned int secno = GET_SEC_FROM_SEG(sbi, segno); unsigned int start = GET_SEG_FROM_SEC(sbi, secno); unsigned long long mtime = 0; unsigned int i; if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { if (p->gc_mode == GC_AT && get_valid_blocks(sbi, segno, true) == 0) return; } for (i = 0; i < SEGS_PER_SEC(sbi); i++) mtime += get_seg_entry(sbi, start + i)->mtime; mtime = div_u64(mtime, SEGS_PER_SEC(sbi)); /* Handle if the system time has changed by the user */ if (mtime < sit_i->min_mtime) sit_i->min_mtime = mtime; if (mtime > sit_i->max_mtime) sit_i->max_mtime = mtime; if (mtime < sit_i->dirty_min_mtime) sit_i->dirty_min_mtime = mtime; if (mtime > sit_i->dirty_max_mtime) sit_i->dirty_max_mtime = mtime; /* don't choose young section as candidate */ if (sit_i->dirty_max_mtime - mtime < p->age_threshold) return; __insert_victim_entry(sbi, mtime, segno); } static void atgc_lookup_victim(struct f2fs_sb_info *sbi, struct victim_sel_policy *p) { struct sit_info *sit_i = SIT_I(sbi); struct atgc_management *am = &sbi->am; struct rb_root_cached *root = &am->root; struct rb_node *node; struct victim_entry *ve; unsigned long long total_time; unsigned long long age, u, accu; unsigned long long max_mtime = sit_i->dirty_max_mtime; unsigned long long min_mtime = sit_i->dirty_min_mtime; unsigned int sec_blocks = CAP_BLKS_PER_SEC(sbi); unsigned int vblocks; unsigned int dirty_threshold = max(am->max_candidate_count, am->candidate_ratio * am->victim_count / 100); unsigned int age_weight = am->age_weight; unsigned int cost; unsigned int iter = 0; if (max_mtime < min_mtime) return; max_mtime += 1; total_time = max_mtime - min_mtime; accu = div64_u64(ULLONG_MAX, total_time); accu = min_t(unsigned long long, div_u64(accu, 100), DEFAULT_ACCURACY_CLASS); node = rb_first_cached(root); next: ve = rb_entry_safe(node, struct victim_entry, rb_node); if (!ve) return; if (ve->mtime >= max_mtime || ve->mtime < min_mtime) goto skip; /* age = 10000 * x% * 60 */ age = div64_u64(accu * (max_mtime - ve->mtime), total_time) * age_weight; vblocks = get_valid_blocks(sbi, ve->segno, true); f2fs_bug_on(sbi, !vblocks || vblocks == sec_blocks); /* u = 10000 * x% * 40 */ u = div64_u64(accu * (sec_blocks - vblocks), sec_blocks) * (100 - age_weight); f2fs_bug_on(sbi, age + u >= UINT_MAX); cost = UINT_MAX - (age + u); iter++; if (cost < p->min_cost || (cost == p->min_cost && age > p->oldest_age)) { p->min_cost = cost; p->oldest_age = age; p->min_segno = ve->segno; } skip: if (iter < dirty_threshold) { node = rb_next(node); goto next; } } /* * select candidates around source section in range of * [target - dirty_threshold, target + dirty_threshold] */ static void atssr_lookup_victim(struct f2fs_sb_info *sbi, struct victim_sel_policy *p) { struct sit_info *sit_i = SIT_I(sbi); struct atgc_management *am = &sbi->am; struct victim_entry *ve; unsigned long long age; unsigned long long max_mtime = sit_i->dirty_max_mtime; unsigned long long min_mtime = sit_i->dirty_min_mtime; unsigned int vblocks; unsigned int dirty_threshold = max(am->max_candidate_count, am->candidate_ratio * am->victim_count / 100); unsigned int cost, iter; int stage = 0; if (max_mtime < min_mtime) return; max_mtime += 1; next_stage: iter = 0; ve = __lookup_victim_entry(sbi, p->age); next_node: if (!ve) { if (stage++ == 0) goto next_stage; return; } if (ve->mtime >= max_mtime || ve->mtime < min_mtime) goto skip_node; age = max_mtime - ve->mtime; vblocks = get_seg_entry(sbi, ve->segno)->ckpt_valid_blocks; f2fs_bug_on(sbi, !vblocks); /* rare case */ if (vblocks == BLKS_PER_SEG(sbi)) goto skip_node; iter++; age = max_mtime - abs(p->age - age); cost = UINT_MAX - vblocks; if (cost < p->min_cost || (cost == p->min_cost && age > p->oldest_age)) { p->min_cost = cost; p->oldest_age = age; p->min_segno = ve->segno; } skip_node: if (iter < dirty_threshold) { ve = rb_entry(stage == 0 ? rb_prev(&ve->rb_node) : rb_next(&ve->rb_node), struct victim_entry, rb_node); goto next_node; } if (stage++ == 0) goto next_stage; } static void lookup_victim_by_age(struct f2fs_sb_info *sbi, struct victim_sel_policy *p) { f2fs_bug_on(sbi, !f2fs_check_victim_tree(sbi, &sbi->am.root)); if (p->gc_mode == GC_AT) atgc_lookup_victim(sbi, p); else if (p->alloc_mode == AT_SSR) atssr_lookup_victim(sbi, p); else f2fs_bug_on(sbi, 1); } static void release_victim_entry(struct f2fs_sb_info *sbi) { struct atgc_management *am = &sbi->am; struct victim_entry *ve, *tmp; list_for_each_entry_safe(ve, tmp, &am->victim_list, list) { list_del(&ve->list); kmem_cache_free(victim_entry_slab, ve); am->victim_count--; } am->root = RB_ROOT_CACHED; f2fs_bug_on(sbi, am->victim_count); f2fs_bug_on(sbi, !list_empty(&am->victim_list)); } static bool f2fs_pin_section(struct f2fs_sb_info *sbi, unsigned int segno) { struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); unsigned int secno = GET_SEC_FROM_SEG(sbi, segno); if (!dirty_i->enable_pin_section) return false; if (!test_and_set_bit(secno, dirty_i->pinned_secmap)) dirty_i->pinned_secmap_cnt++; return true; } static bool f2fs_pinned_section_exists(struct dirty_seglist_info *dirty_i) { return dirty_i->pinned_secmap_cnt; } static bool f2fs_section_is_pinned(struct dirty_seglist_info *dirty_i, unsigned int secno) { return dirty_i->enable_pin_section && f2fs_pinned_section_exists(dirty_i) && test_bit(secno, dirty_i->pinned_secmap); } static void f2fs_unpin_all_sections(struct f2fs_sb_info *sbi, bool enable) { unsigned int bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi)); if (f2fs_pinned_section_exists(DIRTY_I(sbi))) { memset(DIRTY_I(sbi)->pinned_secmap, 0, bitmap_size); DIRTY_I(sbi)->pinned_secmap_cnt = 0; } DIRTY_I(sbi)->enable_pin_section = enable; } static int f2fs_gc_pinned_control(struct inode *inode, int gc_type, unsigned int segno) { if (!f2fs_is_pinned_file(inode)) return 0; if (gc_type != FG_GC) return -EBUSY; if (!f2fs_pin_section(F2FS_I_SB(inode), segno)) f2fs_pin_file_control(inode, true); return -EAGAIN; } /* * This function is called from two paths. * One is garbage collection and the other is SSR segment selection. * When it is called during GC, it just gets a victim segment * and it does not remove it from dirty seglist. * When it is called from SSR segment selection, it finds a segment * which has minimum valid blocks and removes it from dirty seglist. */ int f2fs_get_victim(struct f2fs_sb_info *sbi, unsigned int *result, int gc_type, int type, char alloc_mode, unsigned long long age, bool one_time) { struct dirty_seglist_info *dirty_i = DIRTY_I(sbi); struct sit_info *sm = SIT_I(sbi); struct victim_sel_policy p; unsigned int secno, last_victim; unsigned int last_segment; unsigned int nsearched; bool is_atgc; int ret = 0; mutex_lock(&dirty_i->seglist_lock); last_segment = MAIN_SECS(sbi) * SEGS_PER_SEC(sbi); p.alloc_mode = alloc_mode; p.age = age; p.age_threshold = sbi->am.age_threshold; p.one_time_gc = one_time; retry: select_policy(sbi, gc_type, type, &p); p.min_segno = NULL_SEGNO; p.oldest_age = 0; p.min_cost = get_max_cost(sbi, &p); is_atgc = (p.gc_mode == GC_AT || p.alloc_mode == AT_SSR); nsearched = 0; if (is_atgc) SIT_I(sbi)->dirty_min_mtime = ULLONG_MAX; if (*result != NULL_SEGNO) { if (!get_valid_blocks(sbi, *result, false)) { ret = -ENODATA; goto out; } if (sec_usage_check(sbi, GET_SEC_FROM_SEG(sbi, *result))) ret = -EBUSY; else p.min_segno = *result; goto out; } ret = -ENODATA; if (p.max_search == 0) goto out; if (__is_large_section(sbi) && p.alloc_mode == LFS) { if (sbi->next_victim_seg[BG_GC] != NULL_SEGNO) { p.min_segno = sbi->next_victim_seg[BG_GC]; *result = p.min_segno; sbi->next_victim_seg[BG_GC] = NULL_SEGNO; goto got_result; } if (gc_type == FG_GC && sbi->next_victim_seg[FG_GC] != NULL_SEGNO) { p.min_segno = sbi->next_victim_seg[FG_GC]; *result = p.min_segno; sbi->next_victim_seg[FG_GC] = NULL_SEGNO; goto got_result; } } last_victim = sm->last_victim[p.gc_mode]; if (p.alloc_mode == LFS && gc_type == FG_GC) { p.min_segno = check_bg_victims(sbi); if (p.min_segno != NULL_SEGNO) goto got_it; } while (1) { unsigned long cost, *dirty_bitmap; unsigned int unit_no, segno; dirty_bitmap = p.dirty_bitmap; unit_no = find_next_bit(dirty_bitmap, last_segment / p.ofs_unit, p.offset / p.ofs_unit); segno = unit_no * p.ofs_unit; if (segno >= last_segment) { if (sm->last_victim[p.gc_mode]) { last_segment = sm->last_victim[p.gc_mode]; sm->last_victim[p.gc_mode] = 0; p.offset = 0; continue; } break; } p.offset = segno + p.ofs_unit; nsearched++; #ifdef CONFIG_F2FS_CHECK_FS /* * skip selecting the invalid segno (that is failed due to block * validity check failure during GC) to avoid endless GC loop in * such cases. */ if (test_bit(segno, sm->invalid_segmap)) goto next; #endif secno = GET_SEC_FROM_SEG(sbi, segno); if (sec_usage_check(sbi, secno)) goto next; /* Don't touch checkpointed data */ if (unlikely(is_sbi_flag_set(sbi, SBI_CP_DISABLED))) { if (p.alloc_mode == LFS) { /* * LFS is set to find source section during GC. * The victim should have no checkpointed data. */ if (get_ckpt_valid_blocks(sbi, segno, true)) goto next; } else { /* * SSR | AT_SSR are set to find target segment * for writes which can be full by checkpointed * and newly written blocks. */ if (!f2fs_segment_has_free_slot(sbi, segno)) goto next; } } if (gc_type == BG_GC && test_bit(secno, dirty_i->victim_secmap)) goto next; if (gc_type == FG_GC && f2fs_section_is_pinned(dirty_i, secno)) goto next; if (is_atgc) { add_victim_entry(sbi, &p, segno); goto next; } cost = get_gc_cost(sbi, segno, &p); if (p.min_cost > cost) { p.min_segno = segno; p.min_cost = cost; } next: if (nsearched >= p.max_search) { if (!sm->last_victim[p.gc_mode] && segno <= last_victim) sm->last_victim[p.gc_mode] = last_victim + p.ofs_unit; else sm->last_victim[p.gc_mode] = segno + p.ofs_unit; sm->last_victim[p.gc_mode] %= (MAIN_SECS(sbi) * SEGS_PER_SEC(sbi)); break; } } /* get victim for GC_AT/AT_SSR */ if (is_atgc) { lookup_victim_by_age(sbi, &p); release_victim_entry(sbi); } if (is_atgc && p.min_segno == NULL_SEGNO && sm->elapsed_time < p.age_threshold) { p.age_threshold = 0; goto retry; } if (p.min_segno != NULL_SEGNO) { got_it: *result = (p.min_segno / p.ofs_unit) * p.ofs_unit; got_result: if (p.alloc_mode == LFS) { secno = GET_SEC_FROM_SEG(sbi, p.min_segno); if (gc_type == FG_GC) sbi->cur_victim_sec = secno; else set_bit(secno, dirty_i->victim_secmap); } ret = 0; } out: if (p.min_segno != NULL_SEGNO) trace_f2fs_get_victim(sbi->sb, type, gc_type, &p, sbi->cur_victim_sec, prefree_segments(sbi), free_segments(sbi)); mutex_unlock(&dirty_i->seglist_lock); return ret; } static struct inode *find_gc_inode(struct gc_inode_list *gc_list, nid_t ino) { struct inode_entry *ie; ie = radix_tree_lookup(&gc_list->iroot, ino); if (ie) return ie->inode; return NULL; } static void add_gc_inode(struct gc_inode_list *gc_list, struct inode *inode) { struct inode_entry *new_ie; if (inode == find_gc_inode(gc_list, inode->i_ino)) { iput(inode); return; } new_ie = f2fs_kmem_cache_alloc(f2fs_inode_entry_slab, GFP_NOFS, true, NULL); new_ie->inode = inode; f2fs_radix_tree_insert(&gc_list->iroot, inode->i_ino, new_ie); list_add_tail(&new_ie->list, &gc_list->ilist); } static void put_gc_inode(struct gc_inode_list *gc_list) { struct inode_entry *ie, *next_ie; list_for_each_entry_safe(ie, next_ie, &gc_list->ilist, list) { radix_tree_delete(&gc_list->iroot, ie->inode->i_ino); iput(ie->inode); list_del(&ie->list); kmem_cache_free(f2fs_inode_entry_slab, ie); } } static int check_valid_map(struct f2fs_sb_info *sbi, unsigned int segno, int offset) { struct sit_info *sit_i = SIT_I(sbi); struct seg_entry *sentry; int ret; down_read(&sit_i->sentry_lock); sentry = get_seg_entry(sbi, segno); ret = f2fs_test_bit(offset, sentry->cur_valid_map); up_read(&sit_i->sentry_lock); return ret; } /* * This function compares node address got in summary with that in NAT. * On validity, copy that node with cold status, otherwise (invalid node) * ignore that. */ static int gc_node_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, unsigned int segno, int gc_type) { struct f2fs_summary *entry; block_t start_addr; int off; int phase = 0; bool fggc = (gc_type == FG_GC); int submitted = 0; unsigned int usable_blks_in_seg = f2fs_usable_blks_in_seg(sbi, segno); start_addr = START_BLOCK(sbi, segno); next_step: entry = sum; if (fggc && phase == 2) atomic_inc(&sbi->wb_sync_req[NODE]); for (off = 0; off < usable_blks_in_seg; off++, entry++) { nid_t nid = le32_to_cpu(entry->nid); struct page *node_page; struct node_info ni; int err; /* stop BG_GC if there is not enough free sections. */ if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0)) return submitted; if (check_valid_map(sbi, segno, off) == 0) continue; if (phase == 0) { f2fs_ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), 1, META_NAT, true); continue; } if (phase == 1) { f2fs_ra_node_page(sbi, nid); continue; } /* phase == 2 */ node_page = f2fs_get_node_page(sbi, nid); if (IS_ERR(node_page)) continue; /* block may become invalid during f2fs_get_node_page */ if (check_valid_map(sbi, segno, off) == 0) { f2fs_put_page(node_page, 1); continue; } if (f2fs_get_node_info(sbi, nid, &ni, false)) { f2fs_put_page(node_page, 1); continue; } if (ni.blk_addr != start_addr + off) { f2fs_put_page(node_page, 1); continue; } err = f2fs_move_node_page(node_page, gc_type); if (!err && gc_type == FG_GC) submitted++; stat_inc_node_blk_count(sbi, 1, gc_type); } if (++phase < 3) goto next_step; if (fggc) atomic_dec(&sbi->wb_sync_req[NODE]); return submitted; } /* * Calculate start block index indicating the given node offset. * Be careful, caller should give this node offset only indicating direct node * blocks. If any node offsets, which point the other types of node blocks such * as indirect or double indirect node blocks, are given, it must be a caller's * bug. */ block_t f2fs_start_bidx_of_node(unsigned int node_ofs, struct inode *inode) { unsigned int indirect_blks = 2 * NIDS_PER_BLOCK + 4; unsigned int bidx; if (node_ofs == 0) return 0; if (node_ofs <= 2) { bidx = node_ofs - 1; } else if (node_ofs <= indirect_blks) { int dec = (node_ofs - 4) / (NIDS_PER_BLOCK + 1); bidx = node_ofs - 2 - dec; } else { int dec = (node_ofs - indirect_blks - 3) / (NIDS_PER_BLOCK + 1); bidx = node_ofs - 5 - dec; } return bidx * ADDRS_PER_BLOCK(inode) + ADDRS_PER_INODE(inode); } static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, struct node_info *dni, block_t blkaddr, unsigned int *nofs) { struct page *node_page; nid_t nid; unsigned int ofs_in_node, max_addrs, base; block_t source_blkaddr; nid = le32_to_cpu(sum->nid); ofs_in_node = le16_to_cpu(sum->ofs_in_node); node_page = f2fs_get_node_page(sbi, nid); if (IS_ERR(node_page)) return false; if (f2fs_get_node_info(sbi, nid, dni, false)) { f2fs_put_page(node_page, 1); return false; } if (sum->version != dni->version) { f2fs_warn(sbi, "%s: valid data with mismatched node version.", __func__); set_sbi_flag(sbi, SBI_NEED_FSCK); } if (f2fs_check_nid_range(sbi, dni->ino)) { f2fs_put_page(node_page, 1); return false; } if (IS_INODE(node_page)) { base = offset_in_addr(F2FS_INODE(node_page)); max_addrs = DEF_ADDRS_PER_INODE; } else { base = 0; max_addrs = DEF_ADDRS_PER_BLOCK; } if (base + ofs_in_node >= max_addrs) { f2fs_err(sbi, "Inconsistent blkaddr offset: base:%u, ofs_in_node:%u, max:%u, ino:%u, nid:%u", base, ofs_in_node, max_addrs, dni->ino, dni->nid); f2fs_put_page(node_page, 1); return false; } *nofs = ofs_of_node(node_page); source_blkaddr = data_blkaddr(NULL, node_page, ofs_in_node); f2fs_put_page(node_page, 1); if (source_blkaddr != blkaddr) { #ifdef CONFIG_F2FS_CHECK_FS unsigned int segno = GET_SEGNO(sbi, blkaddr); unsigned long offset = GET_BLKOFF_FROM_SEG0(sbi, blkaddr); if (unlikely(check_valid_map(sbi, segno, offset))) { if (!test_and_set_bit(segno, SIT_I(sbi)->invalid_segmap)) { f2fs_err(sbi, "mismatched blkaddr %u (source_blkaddr %u) in seg %u", blkaddr, source_blkaddr, segno); set_sbi_flag(sbi, SBI_NEED_FSCK); } } #endif return false; } return true; } static int ra_data_block(struct inode *inode, pgoff_t index) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct address_space *mapping = f2fs_is_cow_file(inode) ? F2FS_I(inode)->atomic_inode->i_mapping : inode->i_mapping; struct dnode_of_data dn; struct page *page; struct f2fs_io_info fio = { .sbi = sbi, .ino = inode->i_ino, .type = DATA, .temp = COLD, .op = REQ_OP_READ, .op_flags = 0, .encrypted_page = NULL, .in_list = 0, }; int err; page = f2fs_grab_cache_page(mapping, index, true); if (!page) return -ENOMEM; if (f2fs_lookup_read_extent_cache_block(inode, index, &dn.data_blkaddr)) { if (unlikely(!f2fs_is_valid_blkaddr(sbi, dn.data_blkaddr, DATA_GENERIC_ENHANCE_READ))) { err = -EFSCORRUPTED; goto put_page; } goto got_it; } set_new_dnode(&dn, inode, NULL, NULL, 0); err = f2fs_get_dnode_of_data(&dn, index, LOOKUP_NODE); if (err) goto put_page; f2fs_put_dnode(&dn); if (!__is_valid_data_blkaddr(dn.data_blkaddr)) { err = -ENOENT; goto put_page; } if (unlikely(!f2fs_is_valid_blkaddr(sbi, dn.data_blkaddr, DATA_GENERIC_ENHANCE))) { err = -EFSCORRUPTED; goto put_page; } got_it: /* read page */ fio.page = page; fio.new_blkaddr = fio.old_blkaddr = dn.data_blkaddr; /* * don't cache encrypted data into meta inode until previous dirty * data were writebacked to avoid racing between GC and flush. */ f2fs_wait_on_page_writeback(page, DATA, true, true); f2fs_wait_on_block_writeback(inode, dn.data_blkaddr); fio.encrypted_page = f2fs_pagecache_get_page(META_MAPPING(sbi), dn.data_blkaddr, FGP_LOCK | FGP_CREAT, GFP_NOFS); if (!fio.encrypted_page) { err = -ENOMEM; goto put_page; } err = f2fs_submit_page_bio(&fio); if (err) goto put_encrypted_page; f2fs_put_page(fio.encrypted_page, 0); f2fs_put_page(page, 1); f2fs_update_iostat(sbi, inode, FS_DATA_READ_IO, F2FS_BLKSIZE); f2fs_update_iostat(sbi, NULL, FS_GDATA_READ_IO, F2FS_BLKSIZE); return 0; put_encrypted_page: f2fs_put_page(fio.encrypted_page, 1); put_page: f2fs_put_page(page, 1); return err; } /* * Move data block via META_MAPPING while keeping locked data page. * This can be used to move blocks, aka LBAs, directly on disk. */ static int move_data_block(struct inode *inode, block_t bidx, int gc_type, unsigned int segno, int off) { struct address_space *mapping = f2fs_is_cow_file(inode) ? F2FS_I(inode)->atomic_inode->i_mapping : inode->i_mapping; struct f2fs_io_info fio = { .sbi = F2FS_I_SB(inode), .ino = inode->i_ino, .type = DATA, .temp = COLD, .op = REQ_OP_READ, .op_flags = 0, .encrypted_page = NULL, .in_list = 0, }; struct dnode_of_data dn; struct f2fs_summary sum; struct node_info ni; struct page *page, *mpage; block_t newaddr; int err = 0; bool lfs_mode = f2fs_lfs_mode(fio.sbi); int type = fio.sbi->am.atgc_enabled && (gc_type == BG_GC) && (fio.sbi->gc_mode != GC_URGENT_HIGH) ? CURSEG_ALL_DATA_ATGC : CURSEG_COLD_DATA; /* do not read out */ page = f2fs_grab_cache_page(mapping, bidx, false); if (!page) return -ENOMEM; if (!check_valid_map(F2FS_I_SB(inode), segno, off)) { err = -ENOENT; goto out; } err = f2fs_gc_pinned_control(inode, gc_type, segno); if (err) goto out; set_new_dnode(&dn, inode, NULL, NULL, 0); err = f2fs_get_dnode_of_data(&dn, bidx, LOOKUP_NODE); if (err) goto out; if (unlikely(dn.data_blkaddr == NULL_ADDR)) { ClearPageUptodate(page); err = -ENOENT; goto put_out; } /* * don't cache encrypted data into meta inode until previous dirty * data were writebacked to avoid racing between GC and flush. */ f2fs_wait_on_page_writeback(page, DATA, true, true); f2fs_wait_on_block_writeback(inode, dn.data_blkaddr); err = f2fs_get_node_info(fio.sbi, dn.nid, &ni, false); if (err) goto put_out; /* read page */ fio.page = page; fio.new_blkaddr = fio.old_blkaddr = dn.data_blkaddr; if (lfs_mode) f2fs_down_write(&fio.sbi->io_order_lock); mpage = f2fs_grab_cache_page(META_MAPPING(fio.sbi), fio.old_blkaddr, false); if (!mpage) { err = -ENOMEM; goto up_out; } fio.encrypted_page = mpage; /* read source block in mpage */ if (!PageUptodate(mpage)) { err = f2fs_submit_page_bio(&fio); if (err) { f2fs_put_page(mpage, 1); goto up_out; } f2fs_update_iostat(fio.sbi, inode, FS_DATA_READ_IO, F2FS_BLKSIZE); f2fs_update_iostat(fio.sbi, NULL, FS_GDATA_READ_IO, F2FS_BLKSIZE); lock_page(mpage); if (unlikely(mpage->mapping != META_MAPPING(fio.sbi) || !PageUptodate(mpage))) { err = -EIO; f2fs_put_page(mpage, 1); goto up_out; } } set_summary(&sum, dn.nid, dn.ofs_in_node, ni.version); /* allocate block address */ err = f2fs_allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr, &sum, type, NULL); if (err) { f2fs_put_page(mpage, 1); /* filesystem should shutdown, no need to recovery block */ goto up_out; } fio.encrypted_page = f2fs_pagecache_get_page(META_MAPPING(fio.sbi), newaddr, FGP_LOCK | FGP_CREAT, GFP_NOFS); if (!fio.encrypted_page) { err = -ENOMEM; f2fs_put_page(mpage, 1); goto recover_block; } /* write target block */ f2fs_wait_on_page_writeback(fio.encrypted_page, DATA, true, true); memcpy(page_address(fio.encrypted_page), page_address(mpage), PAGE_SIZE); f2fs_put_page(mpage, 1); f2fs_invalidate_internal_cache(fio.sbi, fio.old_blkaddr); set_page_dirty(fio.encrypted_page); if (clear_page_dirty_for_io(fio.encrypted_page)) dec_page_count(fio.sbi, F2FS_DIRTY_META); set_page_writeback(fio.encrypted_page); fio.op = REQ_OP_WRITE; fio.op_flags = REQ_SYNC; fio.new_blkaddr = newaddr; f2fs_submit_page_write(&fio); f2fs_update_iostat(fio.sbi, NULL, FS_GC_DATA_IO, F2FS_BLKSIZE); f2fs_update_data_blkaddr(&dn, newaddr); set_inode_flag(inode, FI_APPEND_WRITE); f2fs_put_page(fio.encrypted_page, 1); recover_block: if (err) f2fs_do_replace_block(fio.sbi, &sum, newaddr, fio.old_blkaddr, true, true, true); up_out: if (lfs_mode) f2fs_up_write(&fio.sbi->io_order_lock); put_out: f2fs_put_dnode(&dn); out: f2fs_put_page(page, 1); return err; } static int move_data_page(struct inode *inode, block_t bidx, int gc_type, unsigned int segno, int off) { struct page *page; int err = 0; page = f2fs_get_lock_data_page(inode, bidx, true); if (IS_ERR(page)) return PTR_ERR(page); if (!check_valid_map(F2FS_I_SB(inode), segno, off)) { err = -ENOENT; goto out; } err = f2fs_gc_pinned_control(inode, gc_type, segno); if (err) goto out; if (gc_type == BG_GC) { if (folio_test_writeback(page_folio(page))) { err = -EAGAIN; goto out; } set_page_dirty(page); set_page_private_gcing(page); } else { struct f2fs_io_info fio = { .sbi = F2FS_I_SB(inode), .ino = inode->i_ino, .type = DATA, .temp = COLD, .op = REQ_OP_WRITE, .op_flags = REQ_SYNC, .old_blkaddr = NULL_ADDR, .page = page, .encrypted_page = NULL, .need_lock = LOCK_REQ, .io_type = FS_GC_DATA_IO, }; bool is_dirty = PageDirty(page); retry: f2fs_wait_on_page_writeback(page, DATA, true, true); set_page_dirty(page); if (clear_page_dirty_for_io(page)) { inode_dec_dirty_pages(inode); f2fs_remove_dirty_inode(inode); } set_page_private_gcing(page); err = f2fs_do_write_data_page(&fio); if (err) { clear_page_private_gcing(page); if (err == -ENOMEM) { memalloc_retry_wait(GFP_NOFS); goto retry; } if (is_dirty) set_page_dirty(page); } } out: f2fs_put_page(page, 1); return err; } /* * This function tries to get parent node of victim data block, and identifies * data block validity. If the block is valid, copy that with cold status and * modify parent node. * If the parent node is not valid or the data block address is different, * the victim data block is ignored. */ static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, struct gc_inode_list *gc_list, unsigned int segno, int gc_type, bool force_migrate) { struct super_block *sb = sbi->sb; struct f2fs_summary *entry; block_t start_addr; int off; int phase = 0; int submitted = 0; unsigned int usable_blks_in_seg = f2fs_usable_blks_in_seg(sbi, segno); start_addr = START_BLOCK(sbi, segno); next_step: entry = sum; for (off = 0; off < usable_blks_in_seg; off++, entry++) { struct page *data_page; struct inode *inode; struct node_info dni; /* dnode info for the data */ unsigned int ofs_in_node, nofs; block_t start_bidx; nid_t nid = le32_to_cpu(entry->nid); /* * stop BG_GC if there is not enough free sections. * Or, stop GC if the segment becomes fully valid caused by * race condition along with SSR block allocation. */ if ((gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0)) || (!force_migrate && get_valid_blocks(sbi, segno, true) == CAP_BLKS_PER_SEC(sbi))) return submitted; if (check_valid_map(sbi, segno, off) == 0) continue; if (phase == 0) { f2fs_ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), 1, META_NAT, true); continue; } if (phase == 1) { f2fs_ra_node_page(sbi, nid); continue; } /* Get an inode by ino with checking validity */ if (!is_alive(sbi, entry, &dni, start_addr + off, &nofs)) continue; if (phase == 2) { f2fs_ra_node_page(sbi, dni.ino); continue; } ofs_in_node = le16_to_cpu(entry->ofs_in_node); if (phase == 3) { int err; inode = f2fs_iget(sb, dni.ino); if (IS_ERR(inode)) continue; if (is_bad_inode(inode) || special_file(inode->i_mode)) { iput(inode); continue; } if (f2fs_has_inline_data(inode)) { iput(inode); set_sbi_flag(sbi, SBI_NEED_FSCK); f2fs_err_ratelimited(sbi, "inode %lx has both inline_data flag and " "data block, nid=%u, ofs_in_node=%u", inode->i_ino, dni.nid, ofs_in_node); continue; } err = f2fs_gc_pinned_control(inode, gc_type, segno); if (err == -EAGAIN) { iput(inode); return submitted; } if (!f2fs_down_write_trylock( &F2FS_I(inode)->i_gc_rwsem[WRITE])) { iput(inode); sbi->skipped_gc_rwsem++; continue; } start_bidx = f2fs_start_bidx_of_node(nofs, inode) + ofs_in_node; if (f2fs_meta_inode_gc_required(inode)) { int err = ra_data_block(inode, start_bidx); f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); if (err) { iput(inode); continue; } add_gc_inode(gc_list, inode); continue; } data_page = f2fs_get_read_data_page(inode, start_bidx, REQ_RAHEAD, true, NULL); f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]); if (IS_ERR(data_page)) { iput(inode); continue; } f2fs_put_page(data_page, 0); add_gc_inode(gc_list, inode); continue; } /* phase 4 */ inode = find_gc_inode(gc_list, dni.ino); if (inode) { struct f2fs_inode_info *fi = F2FS_I(inode); bool locked = false; int err; if (S_ISREG(inode->i_mode)) { if (!f2fs_down_write_trylock(&fi->i_gc_rwsem[WRITE])) { sbi->skipped_gc_rwsem++; continue; } if (!f2fs_down_write_trylock( &fi->i_gc_rwsem[READ])) { sbi->skipped_gc_rwsem++; f2fs_up_write(&fi->i_gc_rwsem[WRITE]); continue; } locked = true; /* wait for all inflight aio data */ inode_dio_wait(inode); } start_bidx = f2fs_start_bidx_of_node(nofs, inode) + ofs_in_node; if (f2fs_meta_inode_gc_required(inode)) err = move_data_block(inode, start_bidx, gc_type, segno, off); else err = move_data_page(inode, start_bidx, gc_type, segno, off); if (!err && (gc_type == FG_GC || f2fs_meta_inode_gc_required(inode))) submitted++; if (locked) { f2fs_up_write(&fi->i_gc_rwsem[READ]); f2fs_up_write(&fi->i_gc_rwsem[WRITE]); } stat_inc_data_blk_count(sbi, 1, gc_type); } } if (++phase < 5) goto next_step; return submitted; } static int __get_victim(struct f2fs_sb_info *sbi, unsigned int *victim, int gc_type, bool one_time) { struct sit_info *sit_i = SIT_I(sbi); int ret; down_write(&sit_i->sentry_lock); ret = f2fs_get_victim(sbi, victim, gc_type, NO_CHECK_TYPE, LFS, 0, one_time); up_write(&sit_i->sentry_lock); return ret; } static int do_garbage_collect(struct f2fs_sb_info *sbi, unsigned int start_segno, struct gc_inode_list *gc_list, int gc_type, bool force_migrate, bool one_time) { struct page *sum_page; struct f2fs_summary_block *sum; struct blk_plug plug; unsigned int segno = start_segno; unsigned int end_segno = start_segno + SEGS_PER_SEC(sbi); unsigned int sec_end_segno; int seg_freed = 0, migrated = 0; unsigned char type = IS_DATASEG(get_seg_entry(sbi, segno)->type) ? SUM_TYPE_DATA : SUM_TYPE_NODE; unsigned char data_type = (type == SUM_TYPE_DATA) ? DATA : NODE; int submitted = 0; if (__is_large_section(sbi)) { sec_end_segno = rounddown(end_segno, SEGS_PER_SEC(sbi)); /* * zone-capacity can be less than zone-size in zoned devices, * resulting in less than expected usable segments in the zone, * calculate the end segno in the zone which can be garbage * collected */ if (f2fs_sb_has_blkzoned(sbi)) sec_end_segno -= SEGS_PER_SEC(sbi) - f2fs_usable_segs_in_sec(sbi); if (gc_type == BG_GC || one_time) { unsigned int window_granularity = sbi->migration_window_granularity; if (f2fs_sb_has_blkzoned(sbi) && !has_enough_free_blocks(sbi, sbi->gc_thread->boost_zoned_gc_percent)) window_granularity *= BOOST_GC_MULTIPLE; end_segno = start_segno + window_granularity; } if (end_segno > sec_end_segno) end_segno = sec_end_segno; } sanity_check_seg_type(sbi, get_seg_entry(sbi, segno)->type); /* readahead multi ssa blocks those have contiguous address */ if (__is_large_section(sbi)) f2fs_ra_meta_pages(sbi, GET_SUM_BLOCK(sbi, segno), end_segno - segno, META_SSA, true); /* reference all summary page */ while (segno < end_segno) { sum_page = f2fs_get_sum_page(sbi, segno++); if (IS_ERR(sum_page)) { int err = PTR_ERR(sum_page); end_segno = segno - 1; for (segno = start_segno; segno < end_segno; segno++) { sum_page = find_get_page(META_MAPPING(sbi), GET_SUM_BLOCK(sbi, segno)); f2fs_put_page(sum_page, 0); f2fs_put_page(sum_page, 0); } return err; } unlock_page(sum_page); } blk_start_plug(&plug); for (segno = start_segno; segno < end_segno; segno++) { /* find segment summary of victim */ sum_page = find_get_page(META_MAPPING(sbi), GET_SUM_BLOCK(sbi, segno)); f2fs_put_page(sum_page, 0); if (get_valid_blocks(sbi, segno, false) == 0) goto freed; if (gc_type == BG_GC && __is_large_section(sbi) && migrated >= sbi->migration_granularity) goto skip; if (!PageUptodate(sum_page) || unlikely(f2fs_cp_error(sbi))) goto skip; sum = page_address(sum_page); if (type != GET_SUM_TYPE((&sum->footer))) { f2fs_err(sbi, "Inconsistent segment (%u) type [%d, %d] in SSA and SIT", segno, type, GET_SUM_TYPE((&sum->footer))); f2fs_stop_checkpoint(sbi, false, STOP_CP_REASON_CORRUPTED_SUMMARY); goto skip; } /* * this is to avoid deadlock: * - lock_page(sum_page) - f2fs_replace_block * - check_valid_map() - down_write(sentry_lock) * - down_read(sentry_lock) - change_curseg() * - lock_page(sum_page) */ if (type == SUM_TYPE_NODE) submitted += gc_node_segment(sbi, sum->entries, segno, gc_type); else submitted += gc_data_segment(sbi, sum->entries, gc_list, segno, gc_type, force_migrate); stat_inc_gc_seg_count(sbi, data_type, gc_type); sbi->gc_reclaimed_segs[sbi->gc_mode]++; migrated++; freed: if (gc_type == FG_GC && get_valid_blocks(sbi, segno, false) == 0) seg_freed++; if (__is_large_section(sbi)) sbi->next_victim_seg[gc_type] = (segno + 1 < sec_end_segno) ? segno + 1 : NULL_SEGNO; skip: f2fs_put_page(sum_page, 0); } if (submitted) f2fs_submit_merged_write(sbi, data_type); blk_finish_plug(&plug); if (migrated) stat_inc_gc_sec_count(sbi, data_type, gc_type); return seg_freed; } int f2fs_gc(struct f2fs_sb_info *sbi, struct f2fs_gc_control *gc_control) { int gc_type = gc_control->init_gc_type; unsigned int segno = gc_control->victim_segno; int sec_freed = 0, seg_freed = 0, total_freed = 0, total_sec_freed = 0; int ret = 0; struct cp_control cpc; struct gc_inode_list gc_list = { .ilist = LIST_HEAD_INIT(gc_list.ilist), .iroot = RADIX_TREE_INIT(gc_list.iroot, GFP_NOFS), }; unsigned int skipped_round = 0, round = 0; unsigned int upper_secs; trace_f2fs_gc_begin(sbi->sb, gc_type, gc_control->no_bg_gc, gc_control->nr_free_secs, get_pages(sbi, F2FS_DIRTY_NODES), get_pages(sbi, F2FS_DIRTY_DENTS), get_pages(sbi, F2FS_DIRTY_IMETA), free_sections(sbi), free_segments(sbi), reserved_segments(sbi), prefree_segments(sbi)); cpc.reason = __get_cp_reason(sbi); gc_more: sbi->skipped_gc_rwsem = 0; if (unlikely(!(sbi->sb->s_flags & SB_ACTIVE))) { ret = -EINVAL; goto stop; } if (unlikely(f2fs_cp_error(sbi))) { ret = -EIO; goto stop; } /* Let's run FG_GC, if we don't have enough space. */ if (has_not_enough_free_secs(sbi, 0, 0)) { gc_type = FG_GC; /* * For example, if there are many prefree_segments below given * threshold, we can make them free by checkpoint. Then, we * secure free segments which doesn't need fggc any more. */ if (prefree_segments(sbi)) { stat_inc_cp_call_count(sbi, TOTAL_CALL); ret = f2fs_write_checkpoint(sbi, &cpc); if (ret) goto stop; /* Reset due to checkpoint */ sec_freed = 0; } } /* f2fs_balance_fs doesn't need to do BG_GC in critical path. */ if (gc_type == BG_GC && gc_control->no_bg_gc) { ret = -EINVAL; goto stop; } retry: ret = __get_victim(sbi, &segno, gc_type, gc_control->one_time); if (ret) { /* allow to search victim from sections has pinned data */ if (ret == -ENODATA && gc_type == FG_GC && f2fs_pinned_section_exists(DIRTY_I(sbi))) { f2fs_unpin_all_sections(sbi, false); goto retry; } goto stop; } seg_freed = do_garbage_collect(sbi, segno, &gc_list, gc_type, gc_control->should_migrate_blocks, gc_control->one_time); if (seg_freed < 0) goto stop; total_freed += seg_freed; if (seg_freed == f2fs_usable_segs_in_sec(sbi)) { sec_freed++; total_sec_freed++; } if (gc_control->one_time) goto stop; if (gc_type == FG_GC) { sbi->cur_victim_sec = NULL_SEGNO; if (has_enough_free_secs(sbi, sec_freed, 0)) { if (!gc_control->no_bg_gc && total_sec_freed < gc_control->nr_free_secs) goto go_gc_more; goto stop; } if (sbi->skipped_gc_rwsem) skipped_round++; round++; if (skipped_round > MAX_SKIP_GC_COUNT && skipped_round * 2 >= round) { stat_inc_cp_call_count(sbi, TOTAL_CALL); ret = f2fs_write_checkpoint(sbi, &cpc); goto stop; } } else if (has_enough_free_secs(sbi, 0, 0)) { goto stop; } __get_secs_required(sbi, NULL, &upper_secs, NULL); /* * Write checkpoint to reclaim prefree segments. * We need more three extra sections for writer's data/node/dentry. */ if (free_sections(sbi) <= upper_secs + NR_GC_CHECKPOINT_SECS && prefree_segments(sbi)) { stat_inc_cp_call_count(sbi, TOTAL_CALL); ret = f2fs_write_checkpoint(sbi, &cpc); if (ret) goto stop; /* Reset due to checkpoint */ sec_freed = 0; } go_gc_more: segno = NULL_SEGNO; goto gc_more; stop: SIT_I(sbi)->last_victim[ALLOC_NEXT] = 0; SIT_I(sbi)->last_victim[FLUSH_DEVICE] = gc_control->victim_segno; if (gc_type == FG_GC) f2fs_unpin_all_sections(sbi, true); trace_f2fs_gc_end(sbi->sb, ret, total_freed, total_sec_freed, get_pages(sbi, F2FS_DIRTY_NODES), get_pages(sbi, F2FS_DIRTY_DENTS), get_pages(sbi, F2FS_DIRTY_IMETA), free_sections(sbi), free_segments(sbi), reserved_segments(sbi), prefree_segments(sbi)); f2fs_up_write(&sbi->gc_lock); put_gc_inode(&gc_list); if (gc_control->err_gc_skipped && !ret) ret = total_sec_freed ? 0 : -EAGAIN; return ret; } int __init f2fs_create_garbage_collection_cache(void) { victim_entry_slab = f2fs_kmem_cache_create("f2fs_victim_entry", sizeof(struct victim_entry)); return victim_entry_slab ? 0 : -ENOMEM; } void f2fs_destroy_garbage_collection_cache(void) { kmem_cache_destroy(victim_entry_slab); } static void init_atgc_management(struct f2fs_sb_info *sbi) { struct atgc_management *am = &sbi->am; if (test_opt(sbi, ATGC) && SIT_I(sbi)->elapsed_time >= DEF_GC_THREAD_AGE_THRESHOLD) am->atgc_enabled = true; am->root = RB_ROOT_CACHED; INIT_LIST_HEAD(&am->victim_list); am->victim_count = 0; am->candidate_ratio = DEF_GC_THREAD_CANDIDATE_RATIO; am->max_candidate_count = DEF_GC_THREAD_MAX_CANDIDATE_COUNT; am->age_weight = DEF_GC_THREAD_AGE_WEIGHT; am->age_threshold = DEF_GC_THREAD_AGE_THRESHOLD; } void f2fs_build_gc_manager(struct f2fs_sb_info *sbi) { sbi->gc_pin_file_threshold = DEF_GC_FAILED_PINNED_FILES; /* give warm/cold data area from slower device */ if (f2fs_is_multi_device(sbi) && !__is_large_section(sbi)) SIT_I(sbi)->last_victim[ALLOC_NEXT] = GET_SEGNO(sbi, FDEV(0).end_blk) + 1; init_atgc_management(sbi); } int f2fs_gc_range(struct f2fs_sb_info *sbi, unsigned int start_seg, unsigned int end_seg, bool dry_run, unsigned int dry_run_sections) { unsigned int segno; unsigned int gc_secs = dry_run_sections; if (unlikely(f2fs_cp_error(sbi))) return -EIO; for (segno = start_seg; segno <= end_seg; segno += SEGS_PER_SEC(sbi)) { struct gc_inode_list gc_list = { .ilist = LIST_HEAD_INIT(gc_list.ilist), .iroot = RADIX_TREE_INIT(gc_list.iroot, GFP_NOFS), }; do_garbage_collect(sbi, segno, &gc_list, FG_GC, true, false); put_gc_inode(&gc_list); if (!dry_run && get_valid_blocks(sbi, segno, true)) return -EAGAIN; if (dry_run && dry_run_sections && !get_valid_blocks(sbi, segno, true) && --gc_secs == 0) break; if (fatal_signal_pending(current)) return -ERESTARTSYS; } return 0; } static int free_segment_range(struct f2fs_sb_info *sbi, unsigned int secs, bool dry_run) { unsigned int next_inuse, start, end; struct cp_control cpc = { CP_RESIZE, 0, 0, 0 }; int gc_mode, gc_type; int err = 0; int type; /* Force block allocation for GC */ MAIN_SECS(sbi) -= secs; start = MAIN_SECS(sbi) * SEGS_PER_SEC(sbi); end = MAIN_SEGS(sbi) - 1; mutex_lock(&DIRTY_I(sbi)->seglist_lock); for (gc_mode = 0; gc_mode < MAX_GC_POLICY; gc_mode++) if (SIT_I(sbi)->last_victim[gc_mode] >= start) SIT_I(sbi)->last_victim[gc_mode] = 0; for (gc_type = BG_GC; gc_type <= FG_GC; gc_type++) if (sbi->next_victim_seg[gc_type] >= start) sbi->next_victim_seg[gc_type] = NULL_SEGNO; mutex_unlock(&DIRTY_I(sbi)->seglist_lock); /* Move out cursegs from the target range */ for (type = CURSEG_HOT_DATA; type < NR_CURSEG_PERSIST_TYPE; type++) { err = f2fs_allocate_segment_for_resize(sbi, type, start, end); if (err) goto out; } /* do GC to move out valid blocks in the range */ err = f2fs_gc_range(sbi, start, end, dry_run, 0); if (err || dry_run) goto out; stat_inc_cp_call_count(sbi, TOTAL_CALL); err = f2fs_write_checkpoint(sbi, &cpc); if (err) goto out; next_inuse = find_next_inuse(FREE_I(sbi), end + 1, start); if (next_inuse <= end) { f2fs_err(sbi, "segno %u should be free but still inuse!", next_inuse); f2fs_bug_on(sbi, 1); } out: MAIN_SECS(sbi) += secs; return err; } static void update_sb_metadata(struct f2fs_sb_info *sbi, int secs) { struct f2fs_super_block *raw_sb = F2FS_RAW_SUPER(sbi); int section_count; int segment_count; int segment_count_main; long long block_count; int segs = secs * SEGS_PER_SEC(sbi); f2fs_down_write(&sbi->sb_lock); section_count = le32_to_cpu(raw_sb->section_count); segment_count = le32_to_cpu(raw_sb->segment_count); segment_count_main = le32_to_cpu(raw_sb->segment_count_main); block_count = le64_to_cpu(raw_sb->block_count); raw_sb->section_count = cpu_to_le32(section_count + secs); raw_sb->segment_count = cpu_to_le32(segment_count + segs); raw_sb->segment_count_main = cpu_to_le32(segment_count_main + segs); raw_sb->block_count = cpu_to_le64(block_count + (long long)SEGS_TO_BLKS(sbi, segs)); if (f2fs_is_multi_device(sbi)) { int last_dev = sbi->s_ndevs - 1; int dev_segs = le32_to_cpu(raw_sb->devs[last_dev].total_segments); raw_sb->devs[last_dev].total_segments = cpu_to_le32(dev_segs + segs); } f2fs_up_write(&sbi->sb_lock); } static void update_fs_metadata(struct f2fs_sb_info *sbi, int secs) { int segs = secs * SEGS_PER_SEC(sbi); long long blks = SEGS_TO_BLKS(sbi, segs); long long user_block_count = le64_to_cpu(F2FS_CKPT(sbi)->user_block_count); SM_I(sbi)->segment_count = (int)SM_I(sbi)->segment_count + segs; MAIN_SEGS(sbi) = (int)MAIN_SEGS(sbi) + segs; MAIN_SECS(sbi) += secs; FREE_I(sbi)->free_sections = (int)FREE_I(sbi)->free_sections + secs; FREE_I(sbi)->free_segments = (int)FREE_I(sbi)->free_segments + segs; F2FS_CKPT(sbi)->user_block_count = cpu_to_le64(user_block_count + blks); if (f2fs_is_multi_device(sbi)) { int last_dev = sbi->s_ndevs - 1; FDEV(last_dev).total_segments = (int)FDEV(last_dev).total_segments + segs; FDEV(last_dev).end_blk = (long long)FDEV(last_dev).end_blk + blks; #ifdef CONFIG_BLK_DEV_ZONED FDEV(last_dev).nr_blkz = FDEV(last_dev).nr_blkz + div_u64(blks, sbi->blocks_per_blkz); #endif } } int f2fs_resize_fs(struct file *filp, __u64 block_count) { struct f2fs_sb_info *sbi = F2FS_I_SB(file_inode(filp)); __u64 old_block_count, shrunk_blocks; struct cp_control cpc = { CP_RESIZE, 0, 0, 0 }; unsigned int secs; int err = 0; __u32 rem; old_block_count = le64_to_cpu(F2FS_RAW_SUPER(sbi)->block_count); if (block_count > old_block_count) return -EINVAL; if (f2fs_is_multi_device(sbi)) { int last_dev = sbi->s_ndevs - 1; __u64 last_segs = FDEV(last_dev).total_segments; if (block_count + SEGS_TO_BLKS(sbi, last_segs) <= old_block_count) return -EINVAL; } /* new fs size should align to section size */ div_u64_rem(block_count, BLKS_PER_SEC(sbi), &rem); if (rem) return -EINVAL; if (block_count == old_block_count) return 0; if (is_sbi_flag_set(sbi, SBI_NEED_FSCK)) { f2fs_err(sbi, "Should run fsck to repair first."); return -EFSCORRUPTED; } if (test_opt(sbi, DISABLE_CHECKPOINT)) { f2fs_err(sbi, "Checkpoint should be enabled."); return -EINVAL; } err = mnt_want_write_file(filp); if (err) return err; shrunk_blocks = old_block_count - block_count; secs = div_u64(shrunk_blocks, BLKS_PER_SEC(sbi)); /* stop other GC */ if (!f2fs_down_write_trylock(&sbi->gc_lock)) { err = -EAGAIN; goto out_drop_write; } /* stop CP to protect MAIN_SEC in free_segment_range */ f2fs_lock_op(sbi); spin_lock(&sbi->stat_lock); if (shrunk_blocks + valid_user_blocks(sbi) + sbi->current_reserved_blocks + sbi->unusable_block_count + F2FS_OPTION(sbi).root_reserved_blocks > sbi->user_block_count) err = -ENOSPC; spin_unlock(&sbi->stat_lock); if (err) goto out_unlock; err = free_segment_range(sbi, secs, true); out_unlock: f2fs_unlock_op(sbi); f2fs_up_write(&sbi->gc_lock); out_drop_write: mnt_drop_write_file(filp); if (err) return err; err = freeze_super(sbi->sb, FREEZE_HOLDER_USERSPACE); if (err) return err; if (f2fs_readonly(sbi->sb)) { err = thaw_super(sbi->sb, FREEZE_HOLDER_USERSPACE); if (err) return err; return -EROFS; } f2fs_down_write(&sbi->gc_lock); f2fs_down_write(&sbi->cp_global_sem); spin_lock(&sbi->stat_lock); if (shrunk_blocks + valid_user_blocks(sbi) + sbi->current_reserved_blocks + sbi->unusable_block_count + F2FS_OPTION(sbi).root_reserved_blocks > sbi->user_block_count) err = -ENOSPC; else sbi->user_block_count -= shrunk_blocks; spin_unlock(&sbi->stat_lock); if (err) goto out_err; set_sbi_flag(sbi, SBI_IS_RESIZEFS); err = free_segment_range(sbi, secs, false); if (err) goto recover_out; update_sb_metadata(sbi, -secs); err = f2fs_commit_super(sbi, false); if (err) { update_sb_metadata(sbi, secs); goto recover_out; } update_fs_metadata(sbi, -secs); clear_sbi_flag(sbi, SBI_IS_RESIZEFS); set_sbi_flag(sbi, SBI_IS_DIRTY); stat_inc_cp_call_count(sbi, TOTAL_CALL); err = f2fs_write_checkpoint(sbi, &cpc); if (err) { update_fs_metadata(sbi, secs); update_sb_metadata(sbi, secs); f2fs_commit_super(sbi, false); } recover_out: clear_sbi_flag(sbi, SBI_IS_RESIZEFS); if (err) { set_sbi_flag(sbi, SBI_NEED_FSCK); f2fs_err(sbi, "resize_fs failed, should run fsck to repair!"); spin_lock(&sbi->stat_lock); sbi->user_block_count += shrunk_blocks; spin_unlock(&sbi->stat_lock); } out_err: f2fs_up_write(&sbi->cp_global_sem); f2fs_up_write(&sbi->gc_lock); thaw_super(sbi->sb, FREEZE_HOLDER_USERSPACE); return err; } |
| 7 15 14 10 10 10 10 20 20 17 2 19 17 5 21 21 21 21 19 21 6 4 2 5 5 1 1 2 27 27 5 23 27 26 17 20 12 12 12 12 12 12 12 6 6 6 6 6 6 6 3 6 6 5 15 14 23 1 1 4 4 1 1 2 3 3 26 44 17 4 15 17 3 17 2 2 3 3 4 4 1 3 1 10 4 7 3 4 9 3 9 9 3 3 128 131 131 129 128 131 131 17 17 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 | /* * Copyright © 2008 Intel Corporation * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the "Software"), * to deal in the Software without restriction, including without limitation * the rights to use, copy, modify, merge, publish, distribute, sublicense, * and/or sell copies of the Software, and to permit persons to whom the * Software is furnished to do so, subject to the following conditions: * * The above copyright notice and this permission notice (including the next * paragraph) shall be included in all copies or substantial portions of the * Software. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL * THE 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. * * Authors: * Eric Anholt <eric@anholt.net> * */ #include <linux/dma-buf.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/iosys-map.h> #include <linux/mem_encrypt.h> #include <linux/mm.h> #include <linux/mman.h> #include <linux/module.h> #include <linux/pagemap.h> #include <linux/pagevec.h> #include <linux/shmem_fs.h> #include <linux/slab.h> #include <linux/string_helpers.h> #include <linux/types.h> #include <linux/uaccess.h> #include <drm/drm.h> #include <drm/drm_device.h> #include <drm/drm_drv.h> #include <drm/drm_file.h> #include <drm/drm_gem.h> #include <drm/drm_managed.h> #include <drm/drm_print.h> #include <drm/drm_vma_manager.h> #include "drm_internal.h" /** @file drm_gem.c * * This file provides some of the base ioctls and library routines for * the graphics memory manager implemented by each device driver. * * Because various devices have different requirements in terms of * synchronization and migration strategies, implementing that is left up to * the driver, and all that the general API provides should be generic -- * allocating objects, reading/writing data with the cpu, freeing objects. * Even there, platform-dependent optimizations for reading/writing data with * the CPU mean we'll likely hook those out to driver-specific calls. However, * the DRI2 implementation wants to have at least allocate/mmap be generic. * * The goal was to have swap-backed object allocation managed through * struct file. However, file descriptors as handles to a struct file have * two major failings: * - Process limits prevent more than 1024 or so being used at a time by * default. * - Inability to allocate high fds will aggravate the X Server's select() * handling, and likely that of many GL client applications as well. * * This led to a plan of using our own integer IDs (called handles, following * DRM terminology) to mimic fds, and implement the fd syscalls we need as * ioctls. The objects themselves will still include the struct file so * that we can transition to fds if the required kernel infrastructure shows * up at a later date, and as our interface with shmfs for memory allocation. */ static void drm_gem_init_release(struct drm_device *dev, void *ptr) { drm_vma_offset_manager_destroy(dev->vma_offset_manager); } /** * drm_gem_init - Initialize the GEM device fields * @dev: drm_devic structure to initialize */ int drm_gem_init(struct drm_device *dev) { struct drm_vma_offset_manager *vma_offset_manager; mutex_init(&dev->object_name_lock); idr_init_base(&dev->object_name_idr, 1); vma_offset_manager = drmm_kzalloc(dev, sizeof(*vma_offset_manager), GFP_KERNEL); if (!vma_offset_manager) { DRM_ERROR("out of memory\n"); return -ENOMEM; } dev->vma_offset_manager = vma_offset_manager; drm_vma_offset_manager_init(vma_offset_manager, DRM_FILE_PAGE_OFFSET_START, DRM_FILE_PAGE_OFFSET_SIZE); return drmm_add_action(dev, drm_gem_init_release, NULL); } /** * drm_gem_object_init - initialize an allocated shmem-backed GEM object * @dev: drm_device the object should be initialized for * @obj: drm_gem_object to initialize * @size: object size * * Initialize an already allocated GEM object of the specified size with * shmfs backing store. */ int drm_gem_object_init(struct drm_device *dev, struct drm_gem_object *obj, size_t size) { struct file *filp; drm_gem_private_object_init(dev, obj, size); filp = shmem_file_setup("drm mm object", size, VM_NORESERVE); if (IS_ERR(filp)) return PTR_ERR(filp); obj->filp = filp; return 0; } EXPORT_SYMBOL(drm_gem_object_init); /** * drm_gem_private_object_init - initialize an allocated private GEM object * @dev: drm_device the object should be initialized for * @obj: drm_gem_object to initialize * @size: object size * * Initialize an already allocated GEM object of the specified size with * no GEM provided backing store. Instead the caller is responsible for * backing the object and handling it. */ void drm_gem_private_object_init(struct drm_device *dev, struct drm_gem_object *obj, size_t size) { BUG_ON((size & (PAGE_SIZE - 1)) != 0); obj->dev = dev; obj->filp = NULL; kref_init(&obj->refcount); obj->handle_count = 0; obj->size = size; dma_resv_init(&obj->_resv); if (!obj->resv) obj->resv = &obj->_resv; if (drm_core_check_feature(dev, DRIVER_GEM_GPUVA)) drm_gem_gpuva_init(obj); drm_vma_node_reset(&obj->vma_node); INIT_LIST_HEAD(&obj->lru_node); } EXPORT_SYMBOL(drm_gem_private_object_init); /** * drm_gem_private_object_fini - Finalize a failed drm_gem_object * @obj: drm_gem_object * * Uninitialize an already allocated GEM object when it initialized failed */ void drm_gem_private_object_fini(struct drm_gem_object *obj) { WARN_ON(obj->dma_buf); dma_resv_fini(&obj->_resv); } EXPORT_SYMBOL(drm_gem_private_object_fini); /** * drm_gem_object_handle_free - release resources bound to userspace handles * @obj: GEM object to clean up. * * Called after the last handle to the object has been closed * * Removes any name for the object. Note that this must be * called before drm_gem_object_free or we'll be touching * freed memory */ static void drm_gem_object_handle_free(struct drm_gem_object *obj) { struct drm_device *dev = obj->dev; /* Remove any name for this object */ if (obj->name) { idr_remove(&dev->object_name_idr, obj->name); obj->name = 0; } } static void drm_gem_object_exported_dma_buf_free(struct drm_gem_object *obj) { /* Unbreak the reference cycle if we have an exported dma_buf. */ if (obj->dma_buf) { dma_buf_put(obj->dma_buf); obj->dma_buf = NULL; } } static void drm_gem_object_handle_put_unlocked(struct drm_gem_object *obj) { struct drm_device *dev = obj->dev; bool final = false; if (WARN_ON(READ_ONCE(obj->handle_count) == 0)) return; /* * Must bump handle count first as this may be the last * ref, in which case the object would disappear before we * checked for a name */ mutex_lock(&dev->object_name_lock); if (--obj->handle_count == 0) { drm_gem_object_handle_free(obj); drm_gem_object_exported_dma_buf_free(obj); final = true; } mutex_unlock(&dev->object_name_lock); if (final) drm_gem_object_put(obj); } /* * Called at device or object close to release the file's * handle references on objects. */ static int drm_gem_object_release_handle(int id, void *ptr, void *data) { struct drm_file *file_priv = data; struct drm_gem_object *obj = ptr; if (obj->funcs->close) obj->funcs->close(obj, file_priv); drm_prime_remove_buf_handle(&file_priv->prime, id); drm_vma_node_revoke(&obj->vma_node, file_priv); drm_gem_object_handle_put_unlocked(obj); return 0; } /** * drm_gem_handle_delete - deletes the given file-private handle * @filp: drm file-private structure to use for the handle look up * @handle: userspace handle to delete * * Removes the GEM handle from the @filp lookup table which has been added with * drm_gem_handle_create(). If this is the last handle also cleans up linked * resources like GEM names. */ int drm_gem_handle_delete(struct drm_file *filp, u32 handle) { struct drm_gem_object *obj; spin_lock(&filp->table_lock); /* Check if we currently have a reference on the object */ obj = idr_replace(&filp->object_idr, NULL, handle); spin_unlock(&filp->table_lock); if (IS_ERR_OR_NULL(obj)) return -EINVAL; /* Release driver's reference and decrement refcount. */ drm_gem_object_release_handle(handle, obj, filp); /* And finally make the handle available for future allocations. */ spin_lock(&filp->table_lock); idr_remove(&filp->object_idr, handle); spin_unlock(&filp->table_lock); return 0; } EXPORT_SYMBOL(drm_gem_handle_delete); /** * drm_gem_dumb_map_offset - return the fake mmap offset for a gem object * @file: drm file-private structure containing the gem object * @dev: corresponding drm_device * @handle: gem object handle * @offset: return location for the fake mmap offset * * This implements the &drm_driver.dumb_map_offset kms driver callback for * drivers which use gem to manage their backing storage. * * Returns: * 0 on success or a negative error code on failure. */ int drm_gem_dumb_map_offset(struct drm_file *file, struct drm_device *dev, u32 handle, u64 *offset) { struct drm_gem_object *obj; int ret; obj = drm_gem_object_lookup(file, handle); if (!obj) return -ENOENT; /* Don't allow imported objects to be mapped */ if (obj->import_attach) { ret = -EINVAL; goto out; } ret = drm_gem_create_mmap_offset(obj); if (ret) goto out; *offset = drm_vma_node_offset_addr(&obj->vma_node); out: drm_gem_object_put(obj); return ret; } EXPORT_SYMBOL_GPL(drm_gem_dumb_map_offset); /** * drm_gem_handle_create_tail - internal functions to create a handle * @file_priv: drm file-private structure to register the handle for * @obj: object to register * @handlep: pointer to return the created handle to the caller * * This expects the &drm_device.object_name_lock to be held already and will * drop it before returning. Used to avoid races in establishing new handles * when importing an object from either an flink name or a dma-buf. * * Handles must be release again through drm_gem_handle_delete(). This is done * when userspace closes @file_priv for all attached handles, or through the * GEM_CLOSE ioctl for individual handles. */ int drm_gem_handle_create_tail(struct drm_file *file_priv, struct drm_gem_object *obj, u32 *handlep) { struct drm_device *dev = obj->dev; u32 handle; int ret; WARN_ON(!mutex_is_locked(&dev->object_name_lock)); if (obj->handle_count++ == 0) drm_gem_object_get(obj); /* * Get the user-visible handle using idr. Preload and perform * allocation under our spinlock. */ idr_preload(GFP_KERNEL); spin_lock(&file_priv->table_lock); ret = idr_alloc(&file_priv->object_idr, obj, 1, 0, GFP_NOWAIT); spin_unlock(&file_priv->table_lock); idr_preload_end(); mutex_unlock(&dev->object_name_lock); if (ret < 0) goto err_unref; handle = ret; ret = drm_vma_node_allow(&obj->vma_node, file_priv); if (ret) goto err_remove; if (obj->funcs->open) { ret = obj->funcs->open(obj, file_priv); if (ret) goto err_revoke; } *handlep = handle; return 0; err_revoke: drm_vma_node_revoke(&obj->vma_node, file_priv); err_remove: spin_lock(&file_priv->table_lock); idr_remove(&file_priv->object_idr, handle); spin_unlock(&file_priv->table_lock); err_unref: drm_gem_object_handle_put_unlocked(obj); return ret; } /** * drm_gem_handle_create - create a gem handle for an object * @file_priv: drm file-private structure to register the handle for * @obj: object to register * @handlep: pointer to return the created handle to the caller * * Create a handle for this object. This adds a handle reference to the object, * which includes a regular reference count. Callers will likely want to * dereference the object afterwards. * * Since this publishes @obj to userspace it must be fully set up by this point, * drivers must call this last in their buffer object creation callbacks. */ int drm_gem_handle_create(struct drm_file *file_priv, struct drm_gem_object *obj, u32 *handlep) { mutex_lock(&obj->dev->object_name_lock); return drm_gem_handle_create_tail(file_priv, obj, handlep); } EXPORT_SYMBOL(drm_gem_handle_create); /** * drm_gem_free_mmap_offset - release a fake mmap offset for an object * @obj: obj in question * * This routine frees fake offsets allocated by drm_gem_create_mmap_offset(). * * Note that drm_gem_object_release() already calls this function, so drivers * don't have to take care of releasing the mmap offset themselves when freeing * the GEM object. */ void drm_gem_free_mmap_offset(struct drm_gem_object *obj) { struct drm_device *dev = obj->dev; drm_vma_offset_remove(dev->vma_offset_manager, &obj->vma_node); } EXPORT_SYMBOL(drm_gem_free_mmap_offset); /** * drm_gem_create_mmap_offset_size - create a fake mmap offset for an object * @obj: obj in question * @size: the virtual size * * GEM memory mapping works by handing back to userspace a fake mmap offset * it can use in a subsequent mmap(2) call. The DRM core code then looks * up the object based on the offset and sets up the various memory mapping * structures. * * This routine allocates and attaches a fake offset for @obj, in cases where * the virtual size differs from the physical size (ie. &drm_gem_object.size). * Otherwise just use drm_gem_create_mmap_offset(). * * This function is idempotent and handles an already allocated mmap offset * transparently. Drivers do not need to check for this case. */ int drm_gem_create_mmap_offset_size(struct drm_gem_object *obj, size_t size) { struct drm_device *dev = obj->dev; return drm_vma_offset_add(dev->vma_offset_manager, &obj->vma_node, size / PAGE_SIZE); } EXPORT_SYMBOL(drm_gem_create_mmap_offset_size); /** * drm_gem_create_mmap_offset - create a fake mmap offset for an object * @obj: obj in question * * GEM memory mapping works by handing back to userspace a fake mmap offset * it can use in a subsequent mmap(2) call. The DRM core code then looks * up the object based on the offset and sets up the various memory mapping * structures. * * This routine allocates and attaches a fake offset for @obj. * * Drivers can call drm_gem_free_mmap_offset() before freeing @obj to release * the fake offset again. */ int drm_gem_create_mmap_offset(struct drm_gem_object *obj) { return drm_gem_create_mmap_offset_size(obj, obj->size); } EXPORT_SYMBOL(drm_gem_create_mmap_offset); /* * Move folios to appropriate lru and release the folios, decrementing the * ref count of those folios. */ static void drm_gem_check_release_batch(struct folio_batch *fbatch) { check_move_unevictable_folios(fbatch); __folio_batch_release(fbatch); cond_resched(); } /** * drm_gem_get_pages - helper to allocate backing pages for a GEM object * from shmem * @obj: obj in question * * This reads the page-array of the shmem-backing storage of the given gem * object. An array of pages is returned. If a page is not allocated or * swapped-out, this will allocate/swap-in the required pages. Note that the * whole object is covered by the page-array and pinned in memory. * * Use drm_gem_put_pages() to release the array and unpin all pages. * * This uses the GFP-mask set on the shmem-mapping (see mapping_set_gfp_mask()). * If you require other GFP-masks, you have to do those allocations yourself. * * Note that you are not allowed to change gfp-zones during runtime. That is, * shmem_read_mapping_page_gfp() must be called with the same gfp_zone(gfp) as * set during initialization. If you have special zone constraints, set them * after drm_gem_object_init() via mapping_set_gfp_mask(). shmem-core takes care * to keep pages in the required zone during swap-in. * * This function is only valid on objects initialized with * drm_gem_object_init(), but not for those initialized with * drm_gem_private_object_init() only. */ struct page **drm_gem_get_pages(struct drm_gem_object *obj) { struct address_space *mapping; struct page **pages; struct folio *folio; struct folio_batch fbatch; long i, j, npages; if (WARN_ON(!obj->filp)) return ERR_PTR(-EINVAL); /* This is the shared memory object that backs the GEM resource */ mapping = obj->filp->f_mapping; /* We already BUG_ON() for non-page-aligned sizes in * drm_gem_object_init(), so we should never hit this unless * driver author is doing something really wrong: */ WARN_ON((obj->size & (PAGE_SIZE - 1)) != 0); npages = obj->size >> PAGE_SHIFT; pages = kvmalloc_array(npages, sizeof(struct page *), GFP_KERNEL); if (pages == NULL) return ERR_PTR(-ENOMEM); mapping_set_unevictable(mapping); i = 0; while (i < npages) { long nr; folio = shmem_read_folio_gfp(mapping, i, mapping_gfp_mask(mapping)); if (IS_ERR(folio)) goto fail; nr = min(npages - i, folio_nr_pages(folio)); for (j = 0; j < nr; j++, i++) pages[i] = folio_file_page(folio, i); /* Make sure shmem keeps __GFP_DMA32 allocated pages in the * correct region during swapin. Note that this requires * __GFP_DMA32 to be set in mapping_gfp_mask(inode->i_mapping) * so shmem can relocate pages during swapin if required. */ BUG_ON(mapping_gfp_constraint(mapping, __GFP_DMA32) && (folio_pfn(folio) >= 0x00100000UL)); } return pages; fail: mapping_clear_unevictable(mapping); folio_batch_init(&fbatch); j = 0; while (j < i) { struct folio *f = page_folio(pages[j]); if (!folio_batch_add(&fbatch, f)) drm_gem_check_release_batch(&fbatch); j += folio_nr_pages(f); } if (fbatch.nr) drm_gem_check_release_batch(&fbatch); kvfree(pages); return ERR_CAST(folio); } EXPORT_SYMBOL(drm_gem_get_pages); /** * drm_gem_put_pages - helper to free backing pages for a GEM object * @obj: obj in question * @pages: pages to free * @dirty: if true, pages will be marked as dirty * @accessed: if true, the pages will be marked as accessed */ void drm_gem_put_pages(struct drm_gem_object *obj, struct page **pages, bool dirty, bool accessed) { int i, npages; struct address_space *mapping; struct folio_batch fbatch; mapping = file_inode(obj->filp)->i_mapping; mapping_clear_unevictable(mapping); /* We already BUG_ON() for non-page-aligned sizes in * drm_gem_object_init(), so we should never hit this unless * driver author is doing something really wrong: */ WARN_ON((obj->size & (PAGE_SIZE - 1)) != 0); npages = obj->size >> PAGE_SHIFT; folio_batch_init(&fbatch); for (i = 0; i < npages; i++) { struct folio *folio; if (!pages[i]) continue; folio = page_folio(pages[i]); if (dirty) folio_mark_dirty(folio); if (accessed) folio_mark_accessed(folio); /* Undo the reference we took when populating the table */ if (!folio_batch_add(&fbatch, folio)) drm_gem_check_release_batch(&fbatch); i += folio_nr_pages(folio) - 1; } if (folio_batch_count(&fbatch)) drm_gem_check_release_batch(&fbatch); kvfree(pages); } EXPORT_SYMBOL(drm_gem_put_pages); static int objects_lookup(struct drm_file *filp, u32 *handle, int count, struct drm_gem_object **objs) { int i, ret = 0; struct drm_gem_object *obj; spin_lock(&filp->table_lock); for (i = 0; i < count; i++) { /* Check if we currently have a reference on the object */ obj = idr_find(&filp->object_idr, handle[i]); if (!obj) { ret = -ENOENT; break; } drm_gem_object_get(obj); objs[i] = obj; } spin_unlock(&filp->table_lock); return ret; } /** * drm_gem_objects_lookup - look up GEM objects from an array of handles * @filp: DRM file private date * @bo_handles: user pointer to array of userspace handle * @count: size of handle array * @objs_out: returned pointer to array of drm_gem_object pointers * * Takes an array of userspace handles and returns a newly allocated array of * GEM objects. * * For a single handle lookup, use drm_gem_object_lookup(). * * Returns: * @objs filled in with GEM object pointers. Returned GEM objects need to be * released with drm_gem_object_put(). -ENOENT is returned on a lookup * failure. 0 is returned on success. * */ int drm_gem_objects_lookup(struct drm_file *filp, void __user *bo_handles, int count, struct drm_gem_object ***objs_out) { int ret; u32 *handles; struct drm_gem_object **objs; if (!count) return 0; objs = kvmalloc_array(count, sizeof(struct drm_gem_object *), GFP_KERNEL | __GFP_ZERO); if (!objs) return -ENOMEM; *objs_out = objs; handles = kvmalloc_array(count, sizeof(u32), GFP_KERNEL); if (!handles) { ret = -ENOMEM; goto out; } if (copy_from_user(handles, bo_handles, count * sizeof(u32))) { ret = -EFAULT; DRM_DEBUG("Failed to copy in GEM handles\n"); goto out; } ret = objects_lookup(filp, handles, count, objs); out: kvfree(handles); return ret; } EXPORT_SYMBOL(drm_gem_objects_lookup); /** * drm_gem_object_lookup - look up a GEM object from its handle * @filp: DRM file private date * @handle: userspace handle * * If looking up an array of handles, use drm_gem_objects_lookup(). * * Returns: * A reference to the object named by the handle if such exists on @filp, NULL * otherwise. */ struct drm_gem_object * drm_gem_object_lookup(struct drm_file *filp, u32 handle) { struct drm_gem_object *obj = NULL; objects_lookup(filp, &handle, 1, &obj); return obj; } EXPORT_SYMBOL(drm_gem_object_lookup); /** * drm_gem_dma_resv_wait - Wait on GEM object's reservation's objects * shared and/or exclusive fences. * @filep: DRM file private date * @handle: userspace handle * @wait_all: if true, wait on all fences, else wait on just exclusive fence * @timeout: timeout value in jiffies or zero to return immediately * * Returns: * Returns -ERESTARTSYS if interrupted, 0 if the wait timed out, or * greater than 0 on success. */ long drm_gem_dma_resv_wait(struct drm_file *filep, u32 handle, bool wait_all, unsigned long timeout) { long ret; struct drm_gem_object *obj; obj = drm_gem_object_lookup(filep, handle); if (!obj) { DRM_DEBUG("Failed to look up GEM BO %d\n", handle); return -EINVAL; } ret = dma_resv_wait_timeout(obj->resv, dma_resv_usage_rw(wait_all), true, timeout); if (ret == 0) ret = -ETIME; else if (ret > 0) ret = 0; drm_gem_object_put(obj); return ret; } EXPORT_SYMBOL(drm_gem_dma_resv_wait); /** * drm_gem_close_ioctl - implementation of the GEM_CLOSE ioctl * @dev: drm_device * @data: ioctl data * @file_priv: drm file-private structure * * Releases the handle to an mm object. */ int drm_gem_close_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_gem_close *args = data; int ret; if (!drm_core_check_feature(dev, DRIVER_GEM)) return -EOPNOTSUPP; ret = drm_gem_handle_delete(file_priv, args->handle); return ret; } /** * drm_gem_flink_ioctl - implementation of the GEM_FLINK ioctl * @dev: drm_device * @data: ioctl data * @file_priv: drm file-private structure * * Create a global name for an object, returning the name. * * Note that the name does not hold a reference; when the object * is freed, the name goes away. */ int drm_gem_flink_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_gem_flink *args = data; struct drm_gem_object *obj; int ret; if (!drm_core_check_feature(dev, DRIVER_GEM)) return -EOPNOTSUPP; obj = drm_gem_object_lookup(file_priv, args->handle); if (obj == NULL) return -ENOENT; mutex_lock(&dev->object_name_lock); /* prevent races with concurrent gem_close. */ if (obj->handle_count == 0) { ret = -ENOENT; goto err; } if (!obj->name) { ret = idr_alloc(&dev->object_name_idr, obj, 1, 0, GFP_KERNEL); if (ret < 0) goto err; obj->name = ret; } args->name = (uint64_t) obj->name; ret = 0; err: mutex_unlock(&dev->object_name_lock); drm_gem_object_put(obj); return ret; } /** * drm_gem_open_ioctl - implementation of the GEM_OPEN ioctl * @dev: drm_device * @data: ioctl data * @file_priv: drm file-private structure * * Open an object using the global name, returning a handle and the size. * * This handle (of course) holds a reference to the object, so the object * will not go away until the handle is deleted. */ int drm_gem_open_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { struct drm_gem_open *args = data; struct drm_gem_object *obj; int ret; u32 handle; if (!drm_core_check_feature(dev, DRIVER_GEM)) return -EOPNOTSUPP; mutex_lock(&dev->object_name_lock); obj = idr_find(&dev->object_name_idr, (int) args->name); if (obj) { drm_gem_object_get(obj); } else { mutex_unlock(&dev->object_name_lock); return -ENOENT; } /* drm_gem_handle_create_tail unlocks dev->object_name_lock. */ ret = drm_gem_handle_create_tail(file_priv, obj, &handle); if (ret) goto err; args->handle = handle; args->size = obj->size; err: drm_gem_object_put(obj); return ret; } /** * drm_gem_open - initializes GEM file-private structures at devnode open time * @dev: drm_device which is being opened by userspace * @file_private: drm file-private structure to set up * * Called at device open time, sets up the structure for handling refcounting * of mm objects. */ void drm_gem_open(struct drm_device *dev, struct drm_file *file_private) { idr_init_base(&file_private->object_idr, 1); spin_lock_init(&file_private->table_lock); } /** * drm_gem_release - release file-private GEM resources * @dev: drm_device which is being closed by userspace * @file_private: drm file-private structure to clean up * * Called at close time when the filp is going away. * * Releases any remaining references on objects by this filp. */ void drm_gem_release(struct drm_device *dev, struct drm_file *file_private) { idr_for_each(&file_private->object_idr, &drm_gem_object_release_handle, file_private); idr_destroy(&file_private->object_idr); } /** * drm_gem_object_release - release GEM buffer object resources * @obj: GEM buffer object * * This releases any structures and resources used by @obj and is the inverse of * drm_gem_object_init(). */ void drm_gem_object_release(struct drm_gem_object *obj) { if (obj->filp) fput(obj->filp); drm_gem_private_object_fini(obj); drm_gem_free_mmap_offset(obj); drm_gem_lru_remove(obj); } EXPORT_SYMBOL(drm_gem_object_release); /** * drm_gem_object_free - free a GEM object * @kref: kref of the object to free * * Called after the last reference to the object has been lost. * * Frees the object */ void drm_gem_object_free(struct kref *kref) { struct drm_gem_object *obj = container_of(kref, struct drm_gem_object, refcount); if (WARN_ON(!obj->funcs->free)) return; obj->funcs->free(obj); } EXPORT_SYMBOL(drm_gem_object_free); /** * drm_gem_vm_open - vma->ops->open implementation for GEM * @vma: VM area structure * * This function implements the #vm_operations_struct open() callback for GEM * drivers. This must be used together with drm_gem_vm_close(). */ void drm_gem_vm_open(struct vm_area_struct *vma) { struct drm_gem_object *obj = vma->vm_private_data; drm_gem_object_get(obj); } EXPORT_SYMBOL(drm_gem_vm_open); /** * drm_gem_vm_close - vma->ops->close implementation for GEM * @vma: VM area structure * * This function implements the #vm_operations_struct close() callback for GEM * drivers. This must be used together with drm_gem_vm_open(). */ void drm_gem_vm_close(struct vm_area_struct *vma) { struct drm_gem_object *obj = vma->vm_private_data; drm_gem_object_put(obj); } EXPORT_SYMBOL(drm_gem_vm_close); /** * drm_gem_mmap_obj - memory map a GEM object * @obj: the GEM object to map * @obj_size: the object size to be mapped, in bytes * @vma: VMA for the area to be mapped * * Set up the VMA to prepare mapping of the GEM object using the GEM object's * vm_ops. Depending on their requirements, GEM objects can either * provide a fault handler in their vm_ops (in which case any accesses to * the object will be trapped, to perform migration, GTT binding, surface * register allocation, or performance monitoring), or mmap the buffer memory * synchronously after calling drm_gem_mmap_obj. * * This function is mainly intended to implement the DMABUF mmap operation, when * the GEM object is not looked up based on its fake offset. To implement the * DRM mmap operation, drivers should use the drm_gem_mmap() function. * * drm_gem_mmap_obj() assumes the user is granted access to the buffer while * drm_gem_mmap() prevents unprivileged users from mapping random objects. So * callers must verify access restrictions before calling this helper. * * Return 0 or success or -EINVAL if the object size is smaller than the VMA * size, or if no vm_ops are provided. */ int drm_gem_mmap_obj(struct drm_gem_object *obj, unsigned long obj_size, struct vm_area_struct *vma) { int ret; /* Check for valid size. */ if (obj_size < vma->vm_end - vma->vm_start) return -EINVAL; /* Take a ref for this mapping of the object, so that the fault * handler can dereference the mmap offset's pointer to the object. * This reference is cleaned up by the corresponding vm_close * (which should happen whether the vma was created by this call, or * by a vm_open due to mremap or partial unmap or whatever). */ drm_gem_object_get(obj); vma->vm_private_data = obj; vma->vm_ops = obj->funcs->vm_ops; if (obj->funcs->mmap) { ret = obj->funcs->mmap(obj, vma); if (ret) goto err_drm_gem_object_put; WARN_ON(!(vma->vm_flags & VM_DONTEXPAND)); } else { if (!vma->vm_ops) { ret = -EINVAL; goto err_drm_gem_object_put; } vm_flags_set(vma, VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP); vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags)); vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot); } return 0; err_drm_gem_object_put: drm_gem_object_put(obj); return ret; } EXPORT_SYMBOL(drm_gem_mmap_obj); /** * drm_gem_mmap - memory map routine for GEM objects * @filp: DRM file pointer * @vma: VMA for the area to be mapped * * If a driver supports GEM object mapping, mmap calls on the DRM file * descriptor will end up here. * * Look up the GEM object based on the offset passed in (vma->vm_pgoff will * contain the fake offset we created when the GTT map ioctl was called on * the object) and map it with a call to drm_gem_mmap_obj(). * * If the caller is not granted access to the buffer object, the mmap will fail * with EACCES. Please see the vma manager for more information. */ int drm_gem_mmap(struct file *filp, struct vm_area_struct *vma) { struct drm_file *priv = filp->private_data; struct drm_device *dev = priv->minor->dev; struct drm_gem_object *obj = NULL; struct drm_vma_offset_node *node; int ret; if (drm_dev_is_unplugged(dev)) return -ENODEV; drm_vma_offset_lock_lookup(dev->vma_offset_manager); node = drm_vma_offset_exact_lookup_locked(dev->vma_offset_manager, vma->vm_pgoff, vma_pages(vma)); if (likely(node)) { obj = container_of(node, struct drm_gem_object, vma_node); /* * When the object is being freed, after it hits 0-refcnt it * proceeds to tear down the object. In the process it will * attempt to remove the VMA offset and so acquire this * mgr->vm_lock. Therefore if we find an object with a 0-refcnt * that matches our range, we know it is in the process of being * destroyed and will be freed as soon as we release the lock - * so we have to check for the 0-refcnted object and treat it as * invalid. */ if (!kref_get_unless_zero(&obj->refcount)) obj = NULL; } drm_vma_offset_unlock_lookup(dev->vma_offset_manager); if (!obj) return -EINVAL; if (!drm_vma_node_is_allowed(node, priv)) { drm_gem_object_put(obj); return -EACCES; } ret = drm_gem_mmap_obj(obj, drm_vma_node_size(node) << PAGE_SHIFT, vma); drm_gem_object_put(obj); return ret; } EXPORT_SYMBOL(drm_gem_mmap); void drm_gem_print_info(struct drm_printer *p, unsigned int indent, const struct drm_gem_object *obj) { drm_printf_indent(p, indent, "name=%d\n", obj->name); drm_printf_indent(p, indent, "refcount=%u\n", kref_read(&obj->refcount)); drm_printf_indent(p, indent, "start=%08lx\n", drm_vma_node_start(&obj->vma_node)); drm_printf_indent(p, indent, "size=%zu\n", obj->size); drm_printf_indent(p, indent, "imported=%s\n", str_yes_no(obj->import_attach)); if (obj->funcs->print_info) obj->funcs->print_info(p, indent, obj); } int drm_gem_pin_locked(struct drm_gem_object *obj) { if (obj->funcs->pin) return obj->funcs->pin(obj); return 0; } void drm_gem_unpin_locked(struct drm_gem_object *obj) { if (obj->funcs->unpin) obj->funcs->unpin(obj); } int drm_gem_pin(struct drm_gem_object *obj) { int ret; dma_resv_lock(obj->resv, NULL); ret = drm_gem_pin_locked(obj); dma_resv_unlock(obj->resv); return ret; } void drm_gem_unpin(struct drm_gem_object *obj) { dma_resv_lock(obj->resv, NULL); drm_gem_unpin_locked(obj); dma_resv_unlock(obj->resv); } int drm_gem_vmap(struct drm_gem_object *obj, struct iosys_map *map) { int ret; dma_resv_assert_held(obj->resv); if (!obj->funcs->vmap) return -EOPNOTSUPP; ret = obj->funcs->vmap(obj, map); if (ret) return ret; else if (iosys_map_is_null(map)) return -ENOMEM; return 0; } EXPORT_SYMBOL(drm_gem_vmap); void drm_gem_vunmap(struct drm_gem_object *obj, struct iosys_map *map) { dma_resv_assert_held(obj->resv); if (iosys_map_is_null(map)) return; if (obj->funcs->vunmap) obj->funcs->vunmap(obj, map); /* Always set the mapping to NULL. Callers may rely on this. */ iosys_map_clear(map); } EXPORT_SYMBOL(drm_gem_vunmap); void drm_gem_lock(struct drm_gem_object *obj) { dma_resv_lock(obj->resv, NULL); } EXPORT_SYMBOL(drm_gem_lock); void drm_gem_unlock(struct drm_gem_object *obj) { dma_resv_unlock(obj->resv); } EXPORT_SYMBOL(drm_gem_unlock); int drm_gem_vmap_unlocked(struct drm_gem_object *obj, struct iosys_map *map) { int ret; dma_resv_lock(obj->resv, NULL); ret = drm_gem_vmap(obj, map); dma_resv_unlock(obj->resv); return ret; } EXPORT_SYMBOL(drm_gem_vmap_unlocked); void drm_gem_vunmap_unlocked(struct drm_gem_object *obj, struct iosys_map *map) { dma_resv_lock(obj->resv, NULL); drm_gem_vunmap(obj, map); dma_resv_unlock(obj->resv); } EXPORT_SYMBOL(drm_gem_vunmap_unlocked); /** * drm_gem_lock_reservations - Sets up the ww context and acquires * the lock on an array of GEM objects. * * Once you've locked your reservations, you'll want to set up space * for your shared fences (if applicable), submit your job, then * drm_gem_unlock_reservations(). * * @objs: drm_gem_objects to lock * @count: Number of objects in @objs * @acquire_ctx: struct ww_acquire_ctx that will be initialized as * part of tracking this set of locked reservations. */ int drm_gem_lock_reservations(struct drm_gem_object **objs, int count, struct ww_acquire_ctx *acquire_ctx) { int contended = -1; int i, ret; ww_acquire_init(acquire_ctx, &reservation_ww_class); retry: if (contended != -1) { struct drm_gem_object *obj = objs[contended]; ret = dma_resv_lock_slow_interruptible(obj->resv, acquire_ctx); if (ret) { ww_acquire_fini(acquire_ctx); return ret; } } for (i = 0; i < count; i++) { if (i == contended) continue; ret = dma_resv_lock_interruptible(objs[i]->resv, acquire_ctx); if (ret) { int j; for (j = 0; j < i; j++) dma_resv_unlock(objs[j]->resv); if (contended != -1 && contended >= i) dma_resv_unlock(objs[contended]->resv); if (ret == -EDEADLK) { contended = i; goto retry; } ww_acquire_fini(acquire_ctx); return ret; } } ww_acquire_done(acquire_ctx); return 0; } EXPORT_SYMBOL(drm_gem_lock_reservations); void drm_gem_unlock_reservations(struct drm_gem_object **objs, int count, struct ww_acquire_ctx *acquire_ctx) { int i; for (i = 0; i < count; i++) dma_resv_unlock(objs[i]->resv); ww_acquire_fini(acquire_ctx); } EXPORT_SYMBOL(drm_gem_unlock_reservations); /** * drm_gem_lru_init - initialize a LRU * * @lru: The LRU to initialize * @lock: The lock protecting the LRU */ void drm_gem_lru_init(struct drm_gem_lru *lru, struct mutex *lock) { lru->lock = lock; lru->count = 0; INIT_LIST_HEAD(&lru->list); } EXPORT_SYMBOL(drm_gem_lru_init); static void drm_gem_lru_remove_locked(struct drm_gem_object *obj) { obj->lru->count -= obj->size >> PAGE_SHIFT; WARN_ON(obj->lru->count < 0); list_del(&obj->lru_node); obj->lru = NULL; } /** * drm_gem_lru_remove - remove object from whatever LRU it is in * * If the object is currently in any LRU, remove it. * * @obj: The GEM object to remove from current LRU */ void drm_gem_lru_remove(struct drm_gem_object *obj) { struct drm_gem_lru *lru = obj->lru; if (!lru) return; mutex_lock(lru->lock); drm_gem_lru_remove_locked(obj); mutex_unlock(lru->lock); } EXPORT_SYMBOL(drm_gem_lru_remove); /** * drm_gem_lru_move_tail_locked - move the object to the tail of the LRU * * Like &drm_gem_lru_move_tail but lru lock must be held * * @lru: The LRU to move the object into. * @obj: The GEM object to move into this LRU */ void drm_gem_lru_move_tail_locked(struct drm_gem_lru *lru, struct drm_gem_object *obj) { lockdep_assert_held_once(lru->lock); if (obj->lru) drm_gem_lru_remove_locked(obj); lru->count += obj->size >> PAGE_SHIFT; list_add_tail(&obj->lru_node, &lru->list); obj->lru = lru; } EXPORT_SYMBOL(drm_gem_lru_move_tail_locked); /** * drm_gem_lru_move_tail - move the object to the tail of the LRU * * If the object is already in this LRU it will be moved to the * tail. Otherwise it will be removed from whichever other LRU * it is in (if any) and moved into this LRU. * * @lru: The LRU to move the object into. * @obj: The GEM object to move into this LRU */ void drm_gem_lru_move_tail(struct drm_gem_lru *lru, struct drm_gem_object *obj) { mutex_lock(lru->lock); drm_gem_lru_move_tail_locked(lru, obj); mutex_unlock(lru->lock); } EXPORT_SYMBOL(drm_gem_lru_move_tail); /** * drm_gem_lru_scan - helper to implement shrinker.scan_objects * * If the shrink callback succeeds, it is expected that the driver * move the object out of this LRU. * * If the LRU possibly contain active buffers, it is the responsibility * of the shrink callback to check for this (ie. dma_resv_test_signaled()) * or if necessary block until the buffer becomes idle. * * @lru: The LRU to scan * @nr_to_scan: The number of pages to try to reclaim * @remaining: The number of pages left to reclaim, should be initialized by caller * @shrink: Callback to try to shrink/reclaim the object. */ unsigned long drm_gem_lru_scan(struct drm_gem_lru *lru, unsigned int nr_to_scan, unsigned long *remaining, bool (*shrink)(struct drm_gem_object *obj)) { struct drm_gem_lru still_in_lru; struct drm_gem_object *obj; unsigned freed = 0; drm_gem_lru_init(&still_in_lru, lru->lock); mutex_lock(lru->lock); while (freed < nr_to_scan) { obj = list_first_entry_or_null(&lru->list, typeof(*obj), lru_node); if (!obj) break; drm_gem_lru_move_tail_locked(&still_in_lru, obj); /* * If it's in the process of being freed, gem_object->free() * may be blocked on lock waiting to remove it. So just * skip it. */ if (!kref_get_unless_zero(&obj->refcount)) continue; /* * Now that we own a reference, we can drop the lock for the * rest of the loop body, to reduce contention with other * code paths that need the LRU lock */ mutex_unlock(lru->lock); /* * Note that this still needs to be trylock, since we can * hit shrinker in response to trying to get backing pages * for this obj (ie. while it's lock is already held) */ if (!dma_resv_trylock(obj->resv)) { *remaining += obj->size >> PAGE_SHIFT; goto tail; } if (shrink(obj)) { freed += obj->size >> PAGE_SHIFT; /* * If we succeeded in releasing the object's backing * pages, we expect the driver to have moved the object * out of this LRU */ WARN_ON(obj->lru == &still_in_lru); WARN_ON(obj->lru == lru); } dma_resv_unlock(obj->resv); tail: drm_gem_object_put(obj); mutex_lock(lru->lock); } /* * Move objects we've skipped over out of the temporary still_in_lru * back into this LRU */ list_for_each_entry (obj, &still_in_lru.list, lru_node) obj->lru = lru; list_splice_tail(&still_in_lru.list, &lru->list); lru->count += still_in_lru.count; mutex_unlock(lru->lock); return freed; } EXPORT_SYMBOL(drm_gem_lru_scan); /** * drm_gem_evict - helper to evict backing pages for a GEM object * @obj: obj in question */ int drm_gem_evict(struct drm_gem_object *obj) { dma_resv_assert_held(obj->resv); if (!dma_resv_test_signaled(obj->resv, DMA_RESV_USAGE_READ)) return -EBUSY; if (obj->funcs->evict) return obj->funcs->evict(obj); return 0; } EXPORT_SYMBOL(drm_gem_evict); |
| 8 4 32 2 35 34 35 35 32 32 6 35 35 35 35 36 38 38 32 21 21 1 20 7 7 7 7 7 5 5 2 2 35 35 35 10 10 21 8 13 17 4 20 20 32 32 32 32 12 12 12 5 41 1750 25 24 1 25 1 7 9 8 1 1 1 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright 2011-2014 Autronica Fire and Security AS * * Author(s): * 2011-2014 Arvid Brodin, arvid.brodin@alten.se * This file contains device methods for creating, using and destroying * virtual HSR or PRP devices. */ #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> #include <linux/pkt_sched.h> #include "hsr_device.h" #include "hsr_slave.h" #include "hsr_framereg.h" #include "hsr_main.h" #include "hsr_forward.h" static bool is_admin_up(struct net_device *dev) { return dev && (dev->flags & IFF_UP); } static bool is_slave_up(struct net_device *dev) { return dev && is_admin_up(dev) && netif_oper_up(dev); } static void hsr_set_operstate(struct hsr_port *master, bool has_carrier) { struct net_device *dev = master->dev; if (!is_admin_up(dev)) { netdev_set_operstate(dev, IF_OPER_DOWN); return; } if (has_carrier) netdev_set_operstate(dev, IF_OPER_UP); else netdev_set_operstate(dev, IF_OPER_LOWERLAYERDOWN); } static bool hsr_check_carrier(struct hsr_port *master) { struct hsr_port *port; ASSERT_RTNL(); hsr_for_each_port(master->hsr, port) { if (port->type != HSR_PT_MASTER && is_slave_up(port->dev)) { netif_carrier_on(master->dev); return true; } } netif_carrier_off(master->dev); return false; } static void hsr_check_announce(struct net_device *hsr_dev) { struct hsr_priv *hsr; hsr = netdev_priv(hsr_dev); if (netif_running(hsr_dev) && netif_oper_up(hsr_dev)) { /* Enable announce timer and start sending supervisory frames */ if (!timer_pending(&hsr->announce_timer)) { hsr->announce_count = 0; mod_timer(&hsr->announce_timer, jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL)); } if (hsr->redbox && !timer_pending(&hsr->announce_proxy_timer)) mod_timer(&hsr->announce_proxy_timer, jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL) / 2); } else { /* Deactivate the announce timer */ timer_delete(&hsr->announce_timer); if (hsr->redbox) timer_delete(&hsr->announce_proxy_timer); } } void hsr_check_carrier_and_operstate(struct hsr_priv *hsr) { struct hsr_port *master; bool has_carrier; master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); /* netif_stacked_transfer_operstate() cannot be used here since * it doesn't set IF_OPER_LOWERLAYERDOWN (?) */ has_carrier = hsr_check_carrier(master); hsr_set_operstate(master, has_carrier); hsr_check_announce(master->dev); } int hsr_get_max_mtu(struct hsr_priv *hsr) { unsigned int mtu_max; struct hsr_port *port; mtu_max = ETH_DATA_LEN; hsr_for_each_port(hsr, port) if (port->type != HSR_PT_MASTER) mtu_max = min(port->dev->mtu, mtu_max); if (mtu_max < HSR_HLEN) return 0; return mtu_max - HSR_HLEN; } static int hsr_dev_change_mtu(struct net_device *dev, int new_mtu) { struct hsr_priv *hsr; hsr = netdev_priv(dev); if (new_mtu > hsr_get_max_mtu(hsr)) { netdev_info(dev, "A HSR master's MTU cannot be greater than the smallest MTU of its slaves minus the HSR Tag length (%d octets).\n", HSR_HLEN); return -EINVAL; } WRITE_ONCE(dev->mtu, new_mtu); return 0; } static int hsr_dev_open(struct net_device *dev) { struct hsr_priv *hsr; struct hsr_port *port; const char *designation = NULL; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: designation = "Slave A"; break; case HSR_PT_SLAVE_B: designation = "Slave B"; break; case HSR_PT_INTERLINK: designation = "Interlink"; break; default: designation = "Unknown"; } if (!is_slave_up(port->dev)) netdev_warn(dev, "%s (%s) is not up; please bring it up to get a fully working HSR network\n", designation, port->dev->name); } if (!designation) netdev_warn(dev, "No slave devices configured\n"); return 0; } static int hsr_dev_close(struct net_device *dev) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: dev_uc_unsync(port->dev, dev); dev_mc_unsync(port->dev, dev); break; default: break; } } return 0; } static netdev_features_t hsr_features_recompute(struct hsr_priv *hsr, netdev_features_t features) { netdev_features_t mask; struct hsr_port *port; mask = features; /* Mask out all features that, if supported by one device, should be * enabled for all devices (see NETIF_F_ONE_FOR_ALL). * * Anything that's off in mask will not be enabled - so only things * that were in features originally, and also is in NETIF_F_ONE_FOR_ALL, * may become enabled. */ features &= ~NETIF_F_ONE_FOR_ALL; hsr_for_each_port(hsr, port) features = netdev_increment_features(features, port->dev->features, mask); return features; } static netdev_features_t hsr_fix_features(struct net_device *dev, netdev_features_t features) { struct hsr_priv *hsr = netdev_priv(dev); return hsr_features_recompute(hsr, features); } static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev) { struct hsr_priv *hsr = netdev_priv(dev); struct hsr_port *master; master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (master) { skb->dev = master->dev; skb_reset_mac_header(skb); skb_reset_mac_len(skb); spin_lock_bh(&hsr->seqnr_lock); hsr_forward_skb(skb, master); spin_unlock_bh(&hsr->seqnr_lock); } else { dev_core_stats_tx_dropped_inc(dev); dev_kfree_skb_any(skb); } return NETDEV_TX_OK; } static const struct header_ops hsr_header_ops = { .create = eth_header, .parse = eth_header_parse, }; static struct sk_buff *hsr_init_skb(struct hsr_port *master) { struct hsr_priv *hsr = master->hsr; struct sk_buff *skb; int hlen, tlen; hlen = LL_RESERVED_SPACE(master->dev); tlen = master->dev->needed_tailroom; /* skb size is same for PRP/HSR frames, only difference * being, for PRP it is a trailer and for HSR it is a * header */ skb = dev_alloc_skb(sizeof(struct hsr_sup_tag) + sizeof(struct hsr_sup_payload) + hlen + tlen); if (!skb) return skb; skb_reserve(skb, hlen); skb->dev = master->dev; skb->priority = TC_PRIO_CONTROL; if (dev_hard_header(skb, skb->dev, ETH_P_PRP, hsr->sup_multicast_addr, skb->dev->dev_addr, skb->len) <= 0) goto out; skb_reset_mac_header(skb); skb_reset_mac_len(skb); skb_reset_network_header(skb); skb_reset_transport_header(skb); return skb; out: kfree_skb(skb); return NULL; } static void send_hsr_supervision_frame(struct hsr_port *port, unsigned long *interval, const unsigned char *addr) { struct hsr_priv *hsr = port->hsr; __u8 type = HSR_TLV_LIFE_CHECK; struct hsr_sup_payload *hsr_sp; struct hsr_sup_tlv *hsr_stlv; struct hsr_sup_tag *hsr_stag; struct sk_buff *skb; *interval = msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL); if (hsr->announce_count < 3 && hsr->prot_version == 0) { type = HSR_TLV_ANNOUNCE; *interval = msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL); hsr->announce_count++; } skb = hsr_init_skb(port); if (!skb) { netdev_warn_once(port->dev, "HSR: Could not send supervision frame\n"); return; } hsr_stag = skb_put(skb, sizeof(struct hsr_sup_tag)); set_hsr_stag_path(hsr_stag, (hsr->prot_version ? 0x0 : 0xf)); set_hsr_stag_HSR_ver(hsr_stag, hsr->prot_version); /* From HSRv1 on we have separate supervision sequence numbers. */ spin_lock_bh(&hsr->seqnr_lock); if (hsr->prot_version > 0) { hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr); hsr->sup_sequence_nr++; } else { hsr_stag->sequence_nr = htons(hsr->sequence_nr); hsr->sequence_nr++; } hsr_stag->tlv.HSR_TLV_type = type; /* TODO: Why 12 in HSRv0? */ hsr_stag->tlv.HSR_TLV_length = hsr->prot_version ? sizeof(struct hsr_sup_payload) : 12; /* Payload: MacAddressA / SAN MAC from ProxyNodeTable */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, addr); if (hsr->redbox && hsr_is_node_in_db(&hsr->proxy_node_db, addr)) { hsr_stlv = skb_put(skb, sizeof(struct hsr_sup_tlv)); hsr_stlv->HSR_TLV_type = PRP_TLV_REDBOX_MAC; hsr_stlv->HSR_TLV_length = sizeof(struct hsr_sup_payload); /* Payload: MacAddressRedBox */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, hsr->macaddress_redbox); } if (skb_put_padto(skb, ETH_ZLEN)) { spin_unlock_bh(&hsr->seqnr_lock); return; } hsr_forward_skb(skb, port); spin_unlock_bh(&hsr->seqnr_lock); return; } static void send_prp_supervision_frame(struct hsr_port *master, unsigned long *interval, const unsigned char *addr) { struct hsr_priv *hsr = master->hsr; struct hsr_sup_payload *hsr_sp; struct hsr_sup_tag *hsr_stag; struct sk_buff *skb; skb = hsr_init_skb(master); if (!skb) { netdev_warn_once(master->dev, "PRP: Could not send supervision frame\n"); return; } *interval = msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL); hsr_stag = skb_put(skb, sizeof(struct hsr_sup_tag)); set_hsr_stag_path(hsr_stag, (hsr->prot_version ? 0x0 : 0xf)); set_hsr_stag_HSR_ver(hsr_stag, (hsr->prot_version ? 1 : 0)); /* From HSRv1 on we have separate supervision sequence numbers. */ spin_lock_bh(&hsr->seqnr_lock); hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr); hsr->sup_sequence_nr++; hsr_stag->tlv.HSR_TLV_type = PRP_TLV_LIFE_CHECK_DD; hsr_stag->tlv.HSR_TLV_length = sizeof(struct hsr_sup_payload); /* Payload: MacAddressA */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, master->dev->dev_addr); if (skb_put_padto(skb, ETH_ZLEN)) { spin_unlock_bh(&hsr->seqnr_lock); return; } hsr_forward_skb(skb, master); spin_unlock_bh(&hsr->seqnr_lock); } /* Announce (supervision frame) timer function */ static void hsr_announce(struct timer_list *t) { struct hsr_priv *hsr; struct hsr_port *master; unsigned long interval; hsr = from_timer(hsr, t, announce_timer); rcu_read_lock(); master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); hsr->proto_ops->send_sv_frame(master, &interval, master->dev->dev_addr); if (is_admin_up(master->dev)) mod_timer(&hsr->announce_timer, jiffies + interval); rcu_read_unlock(); } /* Announce (supervision frame) timer function for RedBox */ static void hsr_proxy_announce(struct timer_list *t) { struct hsr_priv *hsr = from_timer(hsr, t, announce_proxy_timer); struct hsr_port *interlink; unsigned long interval = 0; struct hsr_node *node; rcu_read_lock(); /* RedBOX sends supervisory frames to HSR network with MAC addresses * of SAN nodes stored in ProxyNodeTable. */ interlink = hsr_port_get_hsr(hsr, HSR_PT_INTERLINK); if (!interlink) goto done; list_for_each_entry_rcu(node, &hsr->proxy_node_db, mac_list) { if (hsr_addr_is_redbox(hsr, node->macaddress_A)) continue; hsr->proto_ops->send_sv_frame(interlink, &interval, node->macaddress_A); } if (is_admin_up(interlink->dev)) { if (!interval) interval = msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL); mod_timer(&hsr->announce_proxy_timer, jiffies + interval); } done: rcu_read_unlock(); } void hsr_del_ports(struct hsr_priv *hsr) { struct hsr_port *port; port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_A); if (port) hsr_del_port(port); port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); if (port) hsr_del_port(port); port = hsr_port_get_hsr(hsr, HSR_PT_INTERLINK); if (port) hsr_del_port(port); port = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (port) hsr_del_port(port); } static void hsr_set_rx_mode(struct net_device *dev) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: dev_mc_sync_multiple(port->dev, dev); dev_uc_sync_multiple(port->dev, dev); break; default: break; } } } static void hsr_change_rx_flags(struct net_device *dev, int change) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: if (change & IFF_ALLMULTI) dev_set_allmulti(port->dev, dev->flags & IFF_ALLMULTI ? 1 : -1); break; default: break; } } } static const struct net_device_ops hsr_device_ops = { .ndo_change_mtu = hsr_dev_change_mtu, .ndo_open = hsr_dev_open, .ndo_stop = hsr_dev_close, .ndo_start_xmit = hsr_dev_xmit, .ndo_change_rx_flags = hsr_change_rx_flags, .ndo_fix_features = hsr_fix_features, .ndo_set_rx_mode = hsr_set_rx_mode, }; static const struct device_type hsr_type = { .name = "hsr", }; static struct hsr_proto_ops hsr_ops = { .send_sv_frame = send_hsr_supervision_frame, .create_tagged_frame = hsr_create_tagged_frame, .get_untagged_frame = hsr_get_untagged_frame, .drop_frame = hsr_drop_frame, .fill_frame_info = hsr_fill_frame_info, .invalid_dan_ingress_frame = hsr_invalid_dan_ingress_frame, }; static struct hsr_proto_ops prp_ops = { .send_sv_frame = send_prp_supervision_frame, .create_tagged_frame = prp_create_tagged_frame, .get_untagged_frame = prp_get_untagged_frame, .drop_frame = prp_drop_frame, .fill_frame_info = prp_fill_frame_info, .handle_san_frame = prp_handle_san_frame, .update_san_info = prp_update_san_info, }; void hsr_dev_setup(struct net_device *dev) { eth_hw_addr_random(dev); ether_setup(dev); dev->min_mtu = 0; dev->header_ops = &hsr_header_ops; dev->netdev_ops = &hsr_device_ops; SET_NETDEV_DEVTYPE(dev, &hsr_type); dev->priv_flags |= IFF_NO_QUEUE | IFF_DISABLE_NETPOLL; /* Prevent recursive tx locking */ dev->lltx = true; /* Not sure about this. Taken from bridge code. netdevice.h says * it means "Does not change network namespaces". */ dev->netns_local = true; dev->needs_free_netdev = true; dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | NETIF_F_GSO_MASK | NETIF_F_HW_CSUM | NETIF_F_HW_VLAN_CTAG_TX; dev->features = dev->hw_features; /* VLAN on top of HSR needs testing and probably some work on * hsr_header_create() etc. */ dev->features |= NETIF_F_VLAN_CHALLENGED; } /* Return true if dev is a HSR master; return false otherwise. */ bool is_hsr_master(struct net_device *dev) { return (dev->netdev_ops->ndo_start_xmit == hsr_dev_xmit); } EXPORT_SYMBOL(is_hsr_master); /* Default multicast address for HSR Supervision frames */ static const unsigned char def_multicast_addr[ETH_ALEN] __aligned(2) = { 0x01, 0x15, 0x4e, 0x00, 0x01, 0x00 }; int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], struct net_device *interlink, unsigned char multicast_spec, u8 protocol_version, struct netlink_ext_ack *extack) { bool unregister = false; struct hsr_priv *hsr; int res; hsr = netdev_priv(hsr_dev); INIT_LIST_HEAD(&hsr->ports); INIT_LIST_HEAD(&hsr->node_db); INIT_LIST_HEAD(&hsr->proxy_node_db); spin_lock_init(&hsr->list_lock); eth_hw_addr_set(hsr_dev, slave[0]->dev_addr); /* initialize protocol specific functions */ if (protocol_version == PRP_V1) { /* For PRP, lan_id has most significant 3 bits holding * the net_id of PRP_LAN_ID */ hsr->net_id = PRP_LAN_ID << 1; hsr->proto_ops = &prp_ops; } else { hsr->proto_ops = &hsr_ops; } /* Make sure we recognize frames from ourselves in hsr_rcv() */ res = hsr_create_self_node(hsr, hsr_dev->dev_addr, slave[1]->dev_addr); if (res < 0) return res; spin_lock_init(&hsr->seqnr_lock); /* Overflow soon to find bugs easier: */ hsr->sequence_nr = HSR_SEQNR_START; hsr->sup_sequence_nr = HSR_SUP_SEQNR_START; timer_setup(&hsr->announce_timer, hsr_announce, 0); timer_setup(&hsr->prune_timer, hsr_prune_nodes, 0); timer_setup(&hsr->prune_proxy_timer, hsr_prune_proxy_nodes, 0); timer_setup(&hsr->announce_proxy_timer, hsr_proxy_announce, 0); ether_addr_copy(hsr->sup_multicast_addr, def_multicast_addr); hsr->sup_multicast_addr[ETH_ALEN - 1] = multicast_spec; hsr->prot_version = protocol_version; /* Make sure the 1st call to netif_carrier_on() gets through */ netif_carrier_off(hsr_dev); res = hsr_add_port(hsr, hsr_dev, HSR_PT_MASTER, extack); if (res) goto err_add_master; /* HSR forwarding offload supported in lower device? */ if ((slave[0]->features & NETIF_F_HW_HSR_FWD) && (slave[1]->features & NETIF_F_HW_HSR_FWD)) hsr->fwd_offloaded = true; res = register_netdevice(hsr_dev); if (res) goto err_unregister; unregister = true; res = hsr_add_port(hsr, slave[0], HSR_PT_SLAVE_A, extack); if (res) goto err_unregister; res = hsr_add_port(hsr, slave[1], HSR_PT_SLAVE_B, extack); if (res) goto err_unregister; if (interlink) { res = hsr_add_port(hsr, interlink, HSR_PT_INTERLINK, extack); if (res) goto err_unregister; hsr->redbox = true; ether_addr_copy(hsr->macaddress_redbox, interlink->dev_addr); mod_timer(&hsr->prune_proxy_timer, jiffies + msecs_to_jiffies(PRUNE_PROXY_PERIOD)); } hsr_debugfs_init(hsr, hsr_dev); mod_timer(&hsr->prune_timer, jiffies + msecs_to_jiffies(PRUNE_PERIOD)); return 0; err_unregister: hsr_del_ports(hsr); err_add_master: hsr_del_self_node(hsr); if (unregister) unregister_netdevice(hsr_dev); return res; } |
| 1 3 1 2 20 16 3 837 42 42 42 23 25 869 43 837 839 26 10 10 10 10 1 1 41 4 4 2 2 2 4 44 83 83 43 42 42 37 36 42 42 2 41 3 2 42 42 41 3 42 42 1 42 4 42 36 36 3 42 3 41 42 3 3 42 36 42 42 82 88 88 80 88 78 78 78 77 38 3 75 2 6 2 2 2 2 2 2 88 88 88 88 42 42 41 2 2 42 42 1 42 42 42 4 42 42 42 42 5 42 47 36 42 3 40 2 38 44 44 44 2 43 41 4 42 12 42 47 32 32 32 42 41 3 41 2 33 3 3 1 4 4 1 1 1 1 1 1 1 32 5 38 41 6 2 10 1 30 30 30 30 30 48 2 43 35 37 6 1 5 38 2 1 43 43 3 43 43 43 43 5 42 35 45 42 42 42 41 42 35 35 35 2 35 1 3 3 3 8 41 41 41 41 41 41 3 41 8 8 41 41 48 48 48 4 41 41 2 41 40 40 14 48 48 48 6 83 101 7 88 90 76 7 93 48 48 47 93 41 41 39 56 94 96 17 86 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/mmu_notifier.h> #include <linux/rmap.h> #include <linux/swap.h> #include <linux/mm_inline.h> #include <linux/kthread.h> #include <linux/khugepaged.h> #include <linux/freezer.h> #include <linux/mman.h> #include <linux/hashtable.h> #include <linux/userfaultfd_k.h> #include <linux/page_idle.h> #include <linux/page_table_check.h> #include <linux/rcupdate_wait.h> #include <linux/swapops.h> #include <linux/shmem_fs.h> #include <linux/ksm.h> #include <asm/tlb.h> #include <asm/pgalloc.h> #include "internal.h" #include "mm_slot.h" enum scan_result { SCAN_FAIL, SCAN_SUCCEED, SCAN_PMD_NULL, SCAN_PMD_NONE, SCAN_PMD_MAPPED, SCAN_EXCEED_NONE_PTE, SCAN_EXCEED_SWAP_PTE, SCAN_EXCEED_SHARED_PTE, SCAN_PTE_NON_PRESENT, SCAN_PTE_UFFD_WP, SCAN_PTE_MAPPED_HUGEPAGE, SCAN_PAGE_RO, SCAN_LACK_REFERENCED_PAGE, SCAN_PAGE_NULL, SCAN_SCAN_ABORT, SCAN_PAGE_COUNT, SCAN_PAGE_LRU, SCAN_PAGE_LOCK, SCAN_PAGE_ANON, SCAN_PAGE_COMPOUND, SCAN_ANY_PROCESS, SCAN_VMA_NULL, SCAN_VMA_CHECK, SCAN_ADDRESS_RANGE, SCAN_DEL_PAGE_LRU, SCAN_ALLOC_HUGE_PAGE_FAIL, SCAN_CGROUP_CHARGE_FAIL, SCAN_TRUNCATED, SCAN_PAGE_HAS_PRIVATE, SCAN_STORE_FAILED, SCAN_COPY_MC, SCAN_PAGE_FILLED, }; #define CREATE_TRACE_POINTS #include <trace/events/huge_memory.h> static struct task_struct *khugepaged_thread __read_mostly; static DEFINE_MUTEX(khugepaged_mutex); /* default scan 8*512 pte (or vmas) every 30 second */ static unsigned int khugepaged_pages_to_scan __read_mostly; static unsigned int khugepaged_pages_collapsed; static unsigned int khugepaged_full_scans; static unsigned int khugepaged_scan_sleep_millisecs __read_mostly = 10000; /* during fragmentation poll the hugepage allocator once every minute */ static unsigned int khugepaged_alloc_sleep_millisecs __read_mostly = 60000; static unsigned long khugepaged_sleep_expire; static DEFINE_SPINLOCK(khugepaged_mm_lock); static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait); /* * default collapse hugepages if there is at least one pte mapped like * it would have happened if the vma was large enough during page * fault. * * Note that these are only respected if collapse was initiated by khugepaged. */ unsigned int khugepaged_max_ptes_none __read_mostly; static unsigned int khugepaged_max_ptes_swap __read_mostly; static unsigned int khugepaged_max_ptes_shared __read_mostly; #define MM_SLOTS_HASH_BITS 10 static DEFINE_READ_MOSTLY_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS); static struct kmem_cache *mm_slot_cache __ro_after_init; struct collapse_control { bool is_khugepaged; /* Num pages scanned per node */ u32 node_load[MAX_NUMNODES]; /* nodemask for allocation fallback */ nodemask_t alloc_nmask; }; /** * struct khugepaged_mm_slot - khugepaged information per mm that is being scanned * @slot: hash lookup from mm to mm_slot */ struct khugepaged_mm_slot { struct mm_slot slot; }; /** * struct khugepaged_scan - cursor for scanning * @mm_head: the head of the mm list to scan * @mm_slot: the current mm_slot we are scanning * @address: the next address inside that to be scanned * * There is only the one khugepaged_scan instance of this cursor structure. */ struct khugepaged_scan { struct list_head mm_head; struct khugepaged_mm_slot *mm_slot; unsigned long address; }; static struct khugepaged_scan khugepaged_scan = { .mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head), }; #ifdef CONFIG_SYSFS static ssize_t scan_sleep_millisecs_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_scan_sleep_millisecs); } static ssize_t scan_sleep_millisecs_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int msecs; int err; err = kstrtouint(buf, 10, &msecs); if (err) return -EINVAL; khugepaged_scan_sleep_millisecs = msecs; khugepaged_sleep_expire = 0; wake_up_interruptible(&khugepaged_wait); return count; } static struct kobj_attribute scan_sleep_millisecs_attr = __ATTR_RW(scan_sleep_millisecs); static ssize_t alloc_sleep_millisecs_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_alloc_sleep_millisecs); } static ssize_t alloc_sleep_millisecs_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int msecs; int err; err = kstrtouint(buf, 10, &msecs); if (err) return -EINVAL; khugepaged_alloc_sleep_millisecs = msecs; khugepaged_sleep_expire = 0; wake_up_interruptible(&khugepaged_wait); return count; } static struct kobj_attribute alloc_sleep_millisecs_attr = __ATTR_RW(alloc_sleep_millisecs); static ssize_t pages_to_scan_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_pages_to_scan); } static ssize_t pages_to_scan_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int pages; int err; err = kstrtouint(buf, 10, &pages); if (err || !pages) return -EINVAL; khugepaged_pages_to_scan = pages; return count; } static struct kobj_attribute pages_to_scan_attr = __ATTR_RW(pages_to_scan); static ssize_t pages_collapsed_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_pages_collapsed); } static struct kobj_attribute pages_collapsed_attr = __ATTR_RO(pages_collapsed); static ssize_t full_scans_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_full_scans); } static struct kobj_attribute full_scans_attr = __ATTR_RO(full_scans); static ssize_t defrag_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return single_hugepage_flag_show(kobj, attr, buf, TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG); } static ssize_t defrag_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { return single_hugepage_flag_store(kobj, attr, buf, count, TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG); } static struct kobj_attribute khugepaged_defrag_attr = __ATTR_RW(defrag); /* * max_ptes_none controls if khugepaged should collapse hugepages over * any unmapped ptes in turn potentially increasing the memory * footprint of the vmas. When max_ptes_none is 0 khugepaged will not * reduce the available free memory in the system as it * runs. Increasing max_ptes_none will instead potentially reduce the * free memory in the system during the khugepaged scan. */ static ssize_t max_ptes_none_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_none); } static ssize_t max_ptes_none_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long max_ptes_none; err = kstrtoul(buf, 10, &max_ptes_none); if (err || max_ptes_none > HPAGE_PMD_NR - 1) return -EINVAL; khugepaged_max_ptes_none = max_ptes_none; return count; } static struct kobj_attribute khugepaged_max_ptes_none_attr = __ATTR_RW(max_ptes_none); static ssize_t max_ptes_swap_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_swap); } static ssize_t max_ptes_swap_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long max_ptes_swap; err = kstrtoul(buf, 10, &max_ptes_swap); if (err || max_ptes_swap > HPAGE_PMD_NR - 1) return -EINVAL; khugepaged_max_ptes_swap = max_ptes_swap; return count; } static struct kobj_attribute khugepaged_max_ptes_swap_attr = __ATTR_RW(max_ptes_swap); static ssize_t max_ptes_shared_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_shared); } static ssize_t max_ptes_shared_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long max_ptes_shared; err = kstrtoul(buf, 10, &max_ptes_shared); if (err || max_ptes_shared > HPAGE_PMD_NR - 1) return -EINVAL; khugepaged_max_ptes_shared = max_ptes_shared; return count; } static struct kobj_attribute khugepaged_max_ptes_shared_attr = __ATTR_RW(max_ptes_shared); static struct attribute *khugepaged_attr[] = { &khugepaged_defrag_attr.attr, &khugepaged_max_ptes_none_attr.attr, &khugepaged_max_ptes_swap_attr.attr, &khugepaged_max_ptes_shared_attr.attr, &pages_to_scan_attr.attr, &pages_collapsed_attr.attr, &full_scans_attr.attr, &scan_sleep_millisecs_attr.attr, &alloc_sleep_millisecs_attr.attr, NULL, }; struct attribute_group khugepaged_attr_group = { .attrs = khugepaged_attr, .name = "khugepaged", }; #endif /* CONFIG_SYSFS */ int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) { switch (advice) { case MADV_HUGEPAGE: #ifdef CONFIG_S390 /* * qemu blindly sets MADV_HUGEPAGE on all allocations, but s390 * can't handle this properly after s390_enable_sie, so we simply * ignore the madvise to prevent qemu from causing a SIGSEGV. */ if (mm_has_pgste(vma->vm_mm)) return 0; #endif *vm_flags &= ~VM_NOHUGEPAGE; *vm_flags |= VM_HUGEPAGE; /* * If the vma become good for khugepaged to scan, * register it here without waiting a page fault that * may not happen any time soon. */ khugepaged_enter_vma(vma, *vm_flags); break; case MADV_NOHUGEPAGE: *vm_flags &= ~VM_HUGEPAGE; *vm_flags |= VM_NOHUGEPAGE; /* * Setting VM_NOHUGEPAGE will prevent khugepaged from scanning * this vma even if we leave the mm registered in khugepaged if * it got registered before VM_NOHUGEPAGE was set. */ break; } return 0; } int __init khugepaged_init(void) { mm_slot_cache = KMEM_CACHE(khugepaged_mm_slot, 0); if (!mm_slot_cache) return -ENOMEM; khugepaged_pages_to_scan = HPAGE_PMD_NR * 8; khugepaged_max_ptes_none = HPAGE_PMD_NR - 1; khugepaged_max_ptes_swap = HPAGE_PMD_NR / 8; khugepaged_max_ptes_shared = HPAGE_PMD_NR / 2; return 0; } void __init khugepaged_destroy(void) { kmem_cache_destroy(mm_slot_cache); } static inline int hpage_collapse_test_exit(struct mm_struct *mm) { return atomic_read(&mm->mm_users) == 0; } static inline int hpage_collapse_test_exit_or_disable(struct mm_struct *mm) { return hpage_collapse_test_exit(mm) || test_bit(MMF_DISABLE_THP, &mm->flags); } static bool hugepage_pmd_enabled(void) { /* * We cover both the anon and the file-backed case here; file-backed * hugepages, when configured in, are determined by the global control. * Anon pmd-sized hugepages are determined by the pmd-size control. */ if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && hugepage_global_enabled()) return true; if (test_bit(PMD_ORDER, &huge_anon_orders_always)) return true; if (test_bit(PMD_ORDER, &huge_anon_orders_madvise)) return true; if (test_bit(PMD_ORDER, &huge_anon_orders_inherit) && hugepage_global_enabled()) return true; return false; } void __khugepaged_enter(struct mm_struct *mm) { struct khugepaged_mm_slot *mm_slot; struct mm_slot *slot; int wakeup; /* __khugepaged_exit() must not run from under us */ VM_BUG_ON_MM(hpage_collapse_test_exit(mm), mm); if (unlikely(test_and_set_bit(MMF_VM_HUGEPAGE, &mm->flags))) return; mm_slot = mm_slot_alloc(mm_slot_cache); if (!mm_slot) return; slot = &mm_slot->slot; spin_lock(&khugepaged_mm_lock); mm_slot_insert(mm_slots_hash, mm, slot); /* * Insert just behind the scanning cursor, to let the area settle * down a little. */ wakeup = list_empty(&khugepaged_scan.mm_head); list_add_tail(&slot->mm_node, &khugepaged_scan.mm_head); spin_unlock(&khugepaged_mm_lock); mmgrab(mm); if (wakeup) wake_up_interruptible(&khugepaged_wait); } void khugepaged_enter_vma(struct vm_area_struct *vma, unsigned long vm_flags) { if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags) && hugepage_pmd_enabled()) { if (thp_vma_allowable_order(vma, vm_flags, TVA_ENFORCE_SYSFS, PMD_ORDER)) __khugepaged_enter(vma->vm_mm); } } void __khugepaged_exit(struct mm_struct *mm) { struct khugepaged_mm_slot *mm_slot; struct mm_slot *slot; int free = 0; spin_lock(&khugepaged_mm_lock); slot = mm_slot_lookup(mm_slots_hash, mm); mm_slot = mm_slot_entry(slot, struct khugepaged_mm_slot, slot); if (mm_slot && khugepaged_scan.mm_slot != mm_slot) { hash_del(&slot->hash); list_del(&slot->mm_node); free = 1; } spin_unlock(&khugepaged_mm_lock); if (free) { clear_bit(MMF_VM_HUGEPAGE, &mm->flags); mm_slot_free(mm_slot_cache, mm_slot); mmdrop(mm); } else if (mm_slot) { /* * This is required to serialize against * hpage_collapse_test_exit() (which is guaranteed to run * under mmap sem read mode). Stop here (after we return all * pagetables will be destroyed) until khugepaged has finished * working on the pagetables under the mmap_lock. */ mmap_write_lock(mm); mmap_write_unlock(mm); } } static void release_pte_folio(struct folio *folio) { node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), -folio_nr_pages(folio)); folio_unlock(folio); folio_putback_lru(folio); } static void release_pte_pages(pte_t *pte, pte_t *_pte, struct list_head *compound_pagelist) { struct folio *folio, *tmp; while (--_pte >= pte) { pte_t pteval = ptep_get(_pte); unsigned long pfn; if (pte_none(pteval)) continue; pfn = pte_pfn(pteval); if (is_zero_pfn(pfn)) continue; folio = pfn_folio(pfn); if (folio_test_large(folio)) continue; release_pte_folio(folio); } list_for_each_entry_safe(folio, tmp, compound_pagelist, lru) { list_del(&folio->lru); release_pte_folio(folio); } } static bool is_refcount_suitable(struct folio *folio) { int expected_refcount = folio_mapcount(folio); if (!folio_test_anon(folio) || folio_test_swapcache(folio)) expected_refcount += folio_nr_pages(folio); if (folio_test_private(folio)) expected_refcount++; return folio_ref_count(folio) == expected_refcount; } static int __collapse_huge_page_isolate(struct vm_area_struct *vma, unsigned long address, pte_t *pte, struct collapse_control *cc, struct list_head *compound_pagelist) { struct page *page = NULL; struct folio *folio = NULL; pte_t *_pte; int none_or_zero = 0, shared = 0, result = SCAN_FAIL, referenced = 0; bool writable = false; for (_pte = pte; _pte < pte + HPAGE_PMD_NR; _pte++, address += PAGE_SIZE) { pte_t pteval = ptep_get(_pte); if (pte_none(pteval) || (pte_present(pteval) && is_zero_pfn(pte_pfn(pteval)))) { ++none_or_zero; if (!userfaultfd_armed(vma) && (!cc->is_khugepaged || none_or_zero <= khugepaged_max_ptes_none)) { continue; } else { result = SCAN_EXCEED_NONE_PTE; count_vm_event(THP_SCAN_EXCEED_NONE_PTE); goto out; } } if (!pte_present(pteval)) { result = SCAN_PTE_NON_PRESENT; goto out; } if (pte_uffd_wp(pteval)) { result = SCAN_PTE_UFFD_WP; goto out; } page = vm_normal_page(vma, address, pteval); if (unlikely(!page) || unlikely(is_zone_device_page(page))) { result = SCAN_PAGE_NULL; goto out; } folio = page_folio(page); VM_BUG_ON_FOLIO(!folio_test_anon(folio), folio); /* See hpage_collapse_scan_pmd(). */ if (folio_likely_mapped_shared(folio)) { ++shared; if (cc->is_khugepaged && shared > khugepaged_max_ptes_shared) { result = SCAN_EXCEED_SHARED_PTE; count_vm_event(THP_SCAN_EXCEED_SHARED_PTE); goto out; } } if (folio_test_large(folio)) { struct folio *f; /* * Check if we have dealt with the compound page * already */ list_for_each_entry(f, compound_pagelist, lru) { if (folio == f) goto next; } } /* * We can do it before folio_isolate_lru because the * folio can't be freed from under us. NOTE: PG_lock * is needed to serialize against split_huge_page * when invoked from the VM. */ if (!folio_trylock(folio)) { result = SCAN_PAGE_LOCK; goto out; } /* * Check if the page has any GUP (or other external) pins. * * The page table that maps the page has been already unlinked * from the page table tree and this process cannot get * an additional pin on the page. * * New pins can come later if the page is shared across fork, * but not from this process. The other process cannot write to * the page, only trigger CoW. */ if (!is_refcount_suitable(folio)) { folio_unlock(folio); result = SCAN_PAGE_COUNT; goto out; } /* * Isolate the page to avoid collapsing an hugepage * currently in use by the VM. */ if (!folio_isolate_lru(folio)) { folio_unlock(folio); result = SCAN_DEL_PAGE_LRU; goto out; } node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), folio_nr_pages(folio)); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); if (folio_test_large(folio)) list_add_tail(&folio->lru, compound_pagelist); next: /* * If collapse was initiated by khugepaged, check that there is * enough young pte to justify collapsing the page */ if (cc->is_khugepaged && (pte_young(pteval) || folio_test_young(folio) || folio_test_referenced(folio) || mmu_notifier_test_young(vma->vm_mm, address))) referenced++; if (pte_write(pteval)) writable = true; } if (unlikely(!writable)) { result = SCAN_PAGE_RO; } else if (unlikely(cc->is_khugepaged && !referenced)) { result = SCAN_LACK_REFERENCED_PAGE; } else { result = SCAN_SUCCEED; trace_mm_collapse_huge_page_isolate(&folio->page, none_or_zero, referenced, writable, result); return result; } out: release_pte_pages(pte, _pte, compound_pagelist); trace_mm_collapse_huge_page_isolate(&folio->page, none_or_zero, referenced, writable, result); return result; } static void __collapse_huge_page_copy_succeeded(pte_t *pte, struct vm_area_struct *vma, unsigned long address, spinlock_t *ptl, struct list_head *compound_pagelist) { struct folio *src, *tmp; pte_t *_pte; pte_t pteval; for (_pte = pte; _pte < pte + HPAGE_PMD_NR; _pte++, address += PAGE_SIZE) { pteval = ptep_get(_pte); if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { add_mm_counter(vma->vm_mm, MM_ANONPAGES, 1); if (is_zero_pfn(pte_pfn(pteval))) { /* * ptl mostly unnecessary. */ spin_lock(ptl); ptep_clear(vma->vm_mm, address, _pte); spin_unlock(ptl); ksm_might_unmap_zero_page(vma->vm_mm, pteval); } } else { struct page *src_page = pte_page(pteval); src = page_folio(src_page); if (!folio_test_large(src)) release_pte_folio(src); /* * ptl mostly unnecessary, but preempt has to * be disabled to update the per-cpu stats * inside folio_remove_rmap_pte(). */ spin_lock(ptl); ptep_clear(vma->vm_mm, address, _pte); folio_remove_rmap_pte(src, src_page, vma); spin_unlock(ptl); free_page_and_swap_cache(src_page); } } list_for_each_entry_safe(src, tmp, compound_pagelist, lru) { list_del(&src->lru); node_stat_sub_folio(src, NR_ISOLATED_ANON + folio_is_file_lru(src)); folio_unlock(src); free_swap_cache(src); folio_putback_lru(src); } } static void __collapse_huge_page_copy_failed(pte_t *pte, pmd_t *pmd, pmd_t orig_pmd, struct vm_area_struct *vma, struct list_head *compound_pagelist) { spinlock_t *pmd_ptl; /* * Re-establish the PMD to point to the original page table * entry. Restoring PMD needs to be done prior to releasing * pages. Since pages are still isolated and locked here, * acquiring anon_vma_lock_write is unnecessary. */ pmd_ptl = pmd_lock(vma->vm_mm, pmd); pmd_populate(vma->vm_mm, pmd, pmd_pgtable(orig_pmd)); spin_unlock(pmd_ptl); /* * Release both raw and compound pages isolated * in __collapse_huge_page_isolate. */ release_pte_pages(pte, pte + HPAGE_PMD_NR, compound_pagelist); } /* * __collapse_huge_page_copy - attempts to copy memory contents from raw * pages to a hugepage. Cleans up the raw pages if copying succeeds; * otherwise restores the original page table and releases isolated raw pages. * Returns SCAN_SUCCEED if copying succeeds, otherwise returns SCAN_COPY_MC. * * @pte: starting of the PTEs to copy from * @folio: the new hugepage to copy contents to * @pmd: pointer to the new hugepage's PMD * @orig_pmd: the original raw pages' PMD * @vma: the original raw pages' virtual memory area * @address: starting address to copy * @ptl: lock on raw pages' PTEs * @compound_pagelist: list that stores compound pages */ static int __collapse_huge_page_copy(pte_t *pte, struct folio *folio, pmd_t *pmd, pmd_t orig_pmd, struct vm_area_struct *vma, unsigned long address, spinlock_t *ptl, struct list_head *compound_pagelist) { unsigned int i; int result = SCAN_SUCCEED; /* * Copying pages' contents is subject to memory poison at any iteration. */ for (i = 0; i < HPAGE_PMD_NR; i++) { pte_t pteval = ptep_get(pte + i); struct page *page = folio_page(folio, i); unsigned long src_addr = address + i * PAGE_SIZE; struct page *src_page; if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { clear_user_highpage(page, src_addr); continue; } src_page = pte_page(pteval); if (copy_mc_user_highpage(page, src_page, src_addr, vma) > 0) { result = SCAN_COPY_MC; break; } } if (likely(result == SCAN_SUCCEED)) __collapse_huge_page_copy_succeeded(pte, vma, address, ptl, compound_pagelist); else __collapse_huge_page_copy_failed(pte, pmd, orig_pmd, vma, compound_pagelist); return result; } static void khugepaged_alloc_sleep(void) { DEFINE_WAIT(wait); add_wait_queue(&khugepaged_wait, &wait); __set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); schedule_timeout(msecs_to_jiffies(khugepaged_alloc_sleep_millisecs)); remove_wait_queue(&khugepaged_wait, &wait); } struct collapse_control khugepaged_collapse_control = { .is_khugepaged = true, }; static bool hpage_collapse_scan_abort(int nid, struct collapse_control *cc) { int i; /* * If node_reclaim_mode is disabled, then no extra effort is made to * allocate memory locally. */ if (!node_reclaim_enabled()) return false; /* If there is a count for this node already, it must be acceptable */ if (cc->node_load[nid]) return false; for (i = 0; i < MAX_NUMNODES; i++) { if (!cc->node_load[i]) continue; if (node_distance(nid, i) > node_reclaim_distance) return true; } return false; } #define khugepaged_defrag() \ (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)) /* Defrag for khugepaged will enter direct reclaim/compaction if necessary */ static inline gfp_t alloc_hugepage_khugepaged_gfpmask(void) { return khugepaged_defrag() ? GFP_TRANSHUGE : GFP_TRANSHUGE_LIGHT; } #ifdef CONFIG_NUMA static int hpage_collapse_find_target_node(struct collapse_control *cc) { int nid, target_node = 0, max_value = 0; /* find first node with max normal pages hit */ for (nid = 0; nid < MAX_NUMNODES; nid++) if (cc->node_load[nid] > max_value) { max_value = cc->node_load[nid]; target_node = nid; } for_each_online_node(nid) { if (max_value == cc->node_load[nid]) node_set(nid, cc->alloc_nmask); } return target_node; } #else static int hpage_collapse_find_target_node(struct collapse_control *cc) { return 0; } #endif /* * If mmap_lock temporarily dropped, revalidate vma * before taking mmap_lock. * Returns enum scan_result value. */ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address, bool expect_anon, struct vm_area_struct **vmap, struct collapse_control *cc) { struct vm_area_struct *vma; unsigned long tva_flags = cc->is_khugepaged ? TVA_ENFORCE_SYSFS : 0; if (unlikely(hpage_collapse_test_exit_or_disable(mm))) return SCAN_ANY_PROCESS; *vmap = vma = find_vma(mm, address); if (!vma) return SCAN_VMA_NULL; if (!thp_vma_suitable_order(vma, address, PMD_ORDER)) return SCAN_ADDRESS_RANGE; if (!thp_vma_allowable_order(vma, vma->vm_flags, tva_flags, PMD_ORDER)) return SCAN_VMA_CHECK; /* * Anon VMA expected, the address may be unmapped then * remapped to file after khugepaged reaquired the mmap_lock. * * thp_vma_allowable_order may return true for qualified file * vmas. */ if (expect_anon && (!(*vmap)->anon_vma || !vma_is_anonymous(*vmap))) return SCAN_PAGE_ANON; return SCAN_SUCCEED; } static int find_pmd_or_thp_or_none(struct mm_struct *mm, unsigned long address, pmd_t **pmd) { pmd_t pmde; *pmd = mm_find_pmd(mm, address); if (!*pmd) return SCAN_PMD_NULL; pmde = pmdp_get_lockless(*pmd); if (pmd_none(pmde)) return SCAN_PMD_NONE; if (!pmd_present(pmde)) return SCAN_PMD_NULL; if (pmd_trans_huge(pmde)) return SCAN_PMD_MAPPED; if (pmd_devmap(pmde)) return SCAN_PMD_NULL; if (pmd_bad(pmde)) return SCAN_PMD_NULL; return SCAN_SUCCEED; } static int check_pmd_still_valid(struct mm_struct *mm, unsigned long address, pmd_t *pmd) { pmd_t *new_pmd; int result = find_pmd_or_thp_or_none(mm, address, &new_pmd); if (result != SCAN_SUCCEED) return result; if (new_pmd != pmd) return SCAN_FAIL; return SCAN_SUCCEED; } /* * Bring missing pages in from swap, to complete THP collapse. * Only done if hpage_collapse_scan_pmd believes it is worthwhile. * * Called and returns without pte mapped or spinlocks held. * Returns result: if not SCAN_SUCCEED, mmap_lock has been released. */ static int __collapse_huge_page_swapin(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd, int referenced) { int swapped_in = 0; vm_fault_t ret = 0; unsigned long address, end = haddr + (HPAGE_PMD_NR * PAGE_SIZE); int result; pte_t *pte = NULL; spinlock_t *ptl; for (address = haddr; address < end; address += PAGE_SIZE) { struct vm_fault vmf = { .vma = vma, .address = address, .pgoff = linear_page_index(vma, address), .flags = FAULT_FLAG_ALLOW_RETRY, .pmd = pmd, }; if (!pte++) { pte = pte_offset_map_nolock(mm, pmd, address, &ptl); if (!pte) { mmap_read_unlock(mm); result = SCAN_PMD_NULL; goto out; } } vmf.orig_pte = ptep_get_lockless(pte); if (!is_swap_pte(vmf.orig_pte)) continue; vmf.pte = pte; vmf.ptl = ptl; ret = do_swap_page(&vmf); /* Which unmaps pte (after perhaps re-checking the entry) */ pte = NULL; /* * do_swap_page returns VM_FAULT_RETRY with released mmap_lock. * Note we treat VM_FAULT_RETRY as VM_FAULT_ERROR here because * we do not retry here and swap entry will remain in pagetable * resulting in later failure. */ if (ret & VM_FAULT_RETRY) { /* Likely, but not guaranteed, that page lock failed */ result = SCAN_PAGE_LOCK; goto out; } if (ret & VM_FAULT_ERROR) { mmap_read_unlock(mm); result = SCAN_FAIL; goto out; } swapped_in++; } if (pte) pte_unmap(pte); /* Drain LRU cache to remove extra pin on the swapped in pages */ if (swapped_in) lru_add_drain(); result = SCAN_SUCCEED; out: trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, result); return result; } static int alloc_charge_folio(struct folio **foliop, struct mm_struct *mm, struct collapse_control *cc) { gfp_t gfp = (cc->is_khugepaged ? alloc_hugepage_khugepaged_gfpmask() : GFP_TRANSHUGE); int node = hpage_collapse_find_target_node(cc); struct folio *folio; folio = __folio_alloc(gfp, HPAGE_PMD_ORDER, node, &cc->alloc_nmask); if (!folio) { *foliop = NULL; count_vm_event(THP_COLLAPSE_ALLOC_FAILED); return SCAN_ALLOC_HUGE_PAGE_FAIL; } count_vm_event(THP_COLLAPSE_ALLOC); if (unlikely(mem_cgroup_charge(folio, mm, gfp))) { folio_put(folio); *foliop = NULL; return SCAN_CGROUP_CHARGE_FAIL; } count_memcg_folio_events(folio, THP_COLLAPSE_ALLOC, 1); *foliop = folio; return SCAN_SUCCEED; } static int collapse_huge_page(struct mm_struct *mm, unsigned long address, int referenced, int unmapped, struct collapse_control *cc) { LIST_HEAD(compound_pagelist); pmd_t *pmd, _pmd; pte_t *pte; pgtable_t pgtable; struct folio *folio; spinlock_t *pmd_ptl, *pte_ptl; int result = SCAN_FAIL; struct vm_area_struct *vma; struct mmu_notifier_range range; VM_BUG_ON(address & ~HPAGE_PMD_MASK); /* * Before allocating the hugepage, release the mmap_lock read lock. * The allocation can take potentially a long time if it involves * sync compaction, and we do not need to hold the mmap_lock during * that. We will recheck the vma after taking it again in write mode. */ mmap_read_unlock(mm); result = alloc_charge_folio(&folio, mm, cc); if (result != SCAN_SUCCEED) goto out_nolock; mmap_read_lock(mm); result = hugepage_vma_revalidate(mm, address, true, &vma, cc); if (result != SCAN_SUCCEED) { mmap_read_unlock(mm); goto out_nolock; } result = find_pmd_or_thp_or_none(mm, address, &pmd); if (result != SCAN_SUCCEED) { mmap_read_unlock(mm); goto out_nolock; } if (unmapped) { /* * __collapse_huge_page_swapin will return with mmap_lock * released when it fails. So we jump out_nolock directly in * that case. Continuing to collapse causes inconsistency. */ result = __collapse_huge_page_swapin(mm, vma, address, pmd, referenced); if (result != SCAN_SUCCEED) goto out_nolock; } mmap_read_unlock(mm); /* * Prevent all access to pagetables with the exception of * gup_fast later handled by the ptep_clear_flush and the VM * handled by the anon_vma lock + PG_lock. * * UFFDIO_MOVE is prevented to race as well thanks to the * mmap_lock. */ mmap_write_lock(mm); result = hugepage_vma_revalidate(mm, address, true, &vma, cc); if (result != SCAN_SUCCEED) goto out_up_write; /* check if the pmd is still valid */ result = check_pmd_still_valid(mm, address, pmd); if (result != SCAN_SUCCEED) goto out_up_write; vma_start_write(vma); anon_vma_lock_write(vma->anon_vma); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, address, address + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */ /* * This removes any huge TLB entry from the CPU so we won't allow * huge and small TLB entries for the same virtual address to * avoid the risk of CPU bugs in that area. * * Parallel GUP-fast is fine since GUP-fast will back off when * it detects PMD is changed. */ _pmd = pmdp_collapse_flush(vma, address, pmd); spin_unlock(pmd_ptl); mmu_notifier_invalidate_range_end(&range); tlb_remove_table_sync_one(); pte = pte_offset_map_lock(mm, &_pmd, address, &pte_ptl); if (pte) { result = __collapse_huge_page_isolate(vma, address, pte, cc, &compound_pagelist); spin_unlock(pte_ptl); } else { result = SCAN_PMD_NULL; } if (unlikely(result != SCAN_SUCCEED)) { if (pte) pte_unmap(pte); spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); /* * We can only use set_pmd_at when establishing * hugepmds and never for establishing regular pmds that * points to regular pagetables. Use pmd_populate for that */ pmd_populate(mm, pmd, pmd_pgtable(_pmd)); spin_unlock(pmd_ptl); anon_vma_unlock_write(vma->anon_vma); goto out_up_write; } /* * All pages are isolated and locked so anon_vma rmap * can't run anymore. */ anon_vma_unlock_write(vma->anon_vma); result = __collapse_huge_page_copy(pte, folio, pmd, _pmd, vma, address, pte_ptl, &compound_pagelist); pte_unmap(pte); if (unlikely(result != SCAN_SUCCEED)) goto out_up_write; /* * The smp_wmb() inside __folio_mark_uptodate() ensures the * copy_huge_page writes become visible before the set_pmd_at() * write. */ __folio_mark_uptodate(folio); pgtable = pmd_pgtable(_pmd); _pmd = mk_huge_pmd(&folio->page, vma->vm_page_prot); _pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma); spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); folio_add_new_anon_rmap(folio, vma, address, RMAP_EXCLUSIVE); folio_add_lru_vma(folio, vma); pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, address, pmd, _pmd); update_mmu_cache_pmd(vma, address, pmd); deferred_split_folio(folio, false); spin_unlock(pmd_ptl); folio = NULL; result = SCAN_SUCCEED; out_up_write: mmap_write_unlock(mm); out_nolock: if (folio) folio_put(folio); trace_mm_collapse_huge_page(mm, result == SCAN_SUCCEED, result); return result; } static int hpage_collapse_scan_pmd(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, bool *mmap_locked, struct collapse_control *cc) { pmd_t *pmd; pte_t *pte, *_pte; int result = SCAN_FAIL, referenced = 0; int none_or_zero = 0, shared = 0; struct page *page = NULL; struct folio *folio = NULL; unsigned long _address; spinlock_t *ptl; int node = NUMA_NO_NODE, unmapped = 0; bool writable = false; VM_BUG_ON(address & ~HPAGE_PMD_MASK); result = find_pmd_or_thp_or_none(mm, address, &pmd); if (result != SCAN_SUCCEED) goto out; memset(cc->node_load, 0, sizeof(cc->node_load)); nodes_clear(cc->alloc_nmask); pte = pte_offset_map_lock(mm, pmd, address, &ptl); if (!pte) { result = SCAN_PMD_NULL; goto out; } for (_address = address, _pte = pte; _pte < pte + HPAGE_PMD_NR; _pte++, _address += PAGE_SIZE) { pte_t pteval = ptep_get(_pte); if (is_swap_pte(pteval)) { ++unmapped; if (!cc->is_khugepaged || unmapped <= khugepaged_max_ptes_swap) { /* * Always be strict with uffd-wp * enabled swap entries. Please see * comment below for pte_uffd_wp(). */ if (pte_swp_uffd_wp_any(pteval)) { result = SCAN_PTE_UFFD_WP; goto out_unmap; } continue; } else { result = SCAN_EXCEED_SWAP_PTE; count_vm_event(THP_SCAN_EXCEED_SWAP_PTE); goto out_unmap; } } if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { ++none_or_zero; if (!userfaultfd_armed(vma) && (!cc->is_khugepaged || none_or_zero <= khugepaged_max_ptes_none)) { continue; } else { result = SCAN_EXCEED_NONE_PTE; count_vm_event(THP_SCAN_EXCEED_NONE_PTE); goto out_unmap; } } if (pte_uffd_wp(pteval)) { /* * Don't collapse the page if any of the small * PTEs are armed with uffd write protection. * Here we can also mark the new huge pmd as * write protected if any of the small ones is * marked but that could bring unknown * userfault messages that falls outside of * the registered range. So, just be simple. */ result = SCAN_PTE_UFFD_WP; goto out_unmap; } if (pte_write(pteval)) writable = true; page = vm_normal_page(vma, _address, pteval); if (unlikely(!page) || unlikely(is_zone_device_page(page))) { result = SCAN_PAGE_NULL; goto out_unmap; } folio = page_folio(page); if (!folio_test_anon(folio)) { result = SCAN_PAGE_ANON; goto out_unmap; } /* * We treat a single page as shared if any part of the THP * is shared. "False negatives" from * folio_likely_mapped_shared() are not expected to matter * much in practice. */ if (folio_likely_mapped_shared(folio)) { ++shared; if (cc->is_khugepaged && shared > khugepaged_max_ptes_shared) { result = SCAN_EXCEED_SHARED_PTE; count_vm_event(THP_SCAN_EXCEED_SHARED_PTE); goto out_unmap; } } /* * Record which node the original page is from and save this * information to cc->node_load[]. * Khugepaged will allocate hugepage from the node has the max * hit record. */ node = folio_nid(folio); if (hpage_collapse_scan_abort(node, cc)) { result = SCAN_SCAN_ABORT; goto out_unmap; } cc->node_load[node]++; if (!folio_test_lru(folio)) { result = SCAN_PAGE_LRU; goto out_unmap; } if (folio_test_locked(folio)) { result = SCAN_PAGE_LOCK; goto out_unmap; } /* * Check if the page has any GUP (or other external) pins. * * Here the check may be racy: * it may see folio_mapcount() > folio_ref_count(). * But such case is ephemeral we could always retry collapse * later. However it may report false positive if the page * has excessive GUP pins (i.e. 512). Anyway the same check * will be done again later the risk seems low. */ if (!is_refcount_suitable(folio)) { result = SCAN_PAGE_COUNT; goto out_unmap; } /* * If collapse was initiated by khugepaged, check that there is * enough young pte to justify collapsing the page */ if (cc->is_khugepaged && (pte_young(pteval) || folio_test_young(folio) || folio_test_referenced(folio) || mmu_notifier_test_young(vma->vm_mm, address))) referenced++; } if (!writable) { result = SCAN_PAGE_RO; } else if (cc->is_khugepaged && (!referenced || (unmapped && referenced < HPAGE_PMD_NR / 2))) { result = SCAN_LACK_REFERENCED_PAGE; } else { result = SCAN_SUCCEED; } out_unmap: pte_unmap_unlock(pte, ptl); if (result == SCAN_SUCCEED) { result = collapse_huge_page(mm, address, referenced, unmapped, cc); /* collapse_huge_page will return with the mmap_lock released */ *mmap_locked = false; } out: trace_mm_khugepaged_scan_pmd(mm, &folio->page, writable, referenced, none_or_zero, result, unmapped); return result; } static void collect_mm_slot(struct khugepaged_mm_slot *mm_slot) { struct mm_slot *slot = &mm_slot->slot; struct mm_struct *mm = slot->mm; lockdep_assert_held(&khugepaged_mm_lock); if (hpage_collapse_test_exit(mm)) { /* free mm_slot */ hash_del(&slot->hash); list_del(&slot->mm_node); /* * Not strictly needed because the mm exited already. * * clear_bit(MMF_VM_HUGEPAGE, &mm->flags); */ /* khugepaged_mm_lock actually not necessary for the below */ mm_slot_free(mm_slot_cache, mm_slot); mmdrop(mm); } } #ifdef CONFIG_SHMEM /* hpage must be locked, and mmap_lock must be held */ static int set_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp, struct page *hpage) { struct vm_fault vmf = { .vma = vma, .address = addr, .flags = 0, .pmd = pmdp, }; VM_BUG_ON(!PageTransHuge(hpage)); mmap_assert_locked(vma->vm_mm); if (do_set_pmd(&vmf, hpage)) return SCAN_FAIL; get_page(hpage); return SCAN_SUCCEED; } /** * collapse_pte_mapped_thp - Try to collapse a pte-mapped THP for mm at * address haddr. * * @mm: process address space where collapse happens * @addr: THP collapse address * @install_pmd: If a huge PMD should be installed * * This function checks whether all the PTEs in the PMD are pointing to the * right THP. If so, retract the page table so the THP can refault in with * as pmd-mapped. Possibly install a huge PMD mapping the THP. */ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, bool install_pmd) { struct mmu_notifier_range range; bool notified = false; unsigned long haddr = addr & HPAGE_PMD_MASK; struct vm_area_struct *vma = vma_lookup(mm, haddr); struct folio *folio; pte_t *start_pte, *pte; pmd_t *pmd, pgt_pmd; spinlock_t *pml = NULL, *ptl; int nr_ptes = 0, result = SCAN_FAIL; int i; mmap_assert_locked(mm); /* First check VMA found, in case page tables are being torn down */ if (!vma || !vma->vm_file || !range_in_vma(vma, haddr, haddr + HPAGE_PMD_SIZE)) return SCAN_VMA_CHECK; /* Fast check before locking page if already PMD-mapped */ result = find_pmd_or_thp_or_none(mm, haddr, &pmd); if (result == SCAN_PMD_MAPPED) return result; /* * If we are here, we've succeeded in replacing all the native pages * in the page cache with a single hugepage. If a mm were to fault-in * this memory (mapped by a suitably aligned VMA), we'd get the hugepage * and map it by a PMD, regardless of sysfs THP settings. As such, let's * analogously elide sysfs THP settings here. */ if (!thp_vma_allowable_order(vma, vma->vm_flags, 0, PMD_ORDER)) return SCAN_VMA_CHECK; /* Keep pmd pgtable for uffd-wp; see comment in retract_page_tables() */ if (userfaultfd_wp(vma)) return SCAN_PTE_UFFD_WP; folio = filemap_lock_folio(vma->vm_file->f_mapping, linear_page_index(vma, haddr)); if (IS_ERR(folio)) return SCAN_PAGE_NULL; if (folio_order(folio) != HPAGE_PMD_ORDER) { result = SCAN_PAGE_COMPOUND; goto drop_folio; } result = find_pmd_or_thp_or_none(mm, haddr, &pmd); switch (result) { case SCAN_SUCCEED: break; case SCAN_PMD_NONE: /* * All pte entries have been removed and pmd cleared. * Skip all the pte checks and just update the pmd mapping. */ goto maybe_install_pmd; default: goto drop_folio; } result = SCAN_FAIL; start_pte = pte_offset_map_lock(mm, pmd, haddr, &ptl); if (!start_pte) /* mmap_lock + page lock should prevent this */ goto drop_folio; /* step 1: check all mapped PTEs are to the right huge page */ for (i = 0, addr = haddr, pte = start_pte; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE, pte++) { struct page *page; pte_t ptent = ptep_get(pte); /* empty pte, skip */ if (pte_none(ptent)) continue; /* page swapped out, abort */ if (!pte_present(ptent)) { result = SCAN_PTE_NON_PRESENT; goto abort; } page = vm_normal_page(vma, addr, ptent); if (WARN_ON_ONCE(page && is_zone_device_page(page))) page = NULL; /* * Note that uprobe, debugger, or MAP_PRIVATE may change the * page table, but the new page will not be a subpage of hpage. */ if (folio_page(folio, i) != page) goto abort; } pte_unmap_unlock(start_pte, ptl); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, haddr, haddr + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); notified = true; /* * pmd_lock covers a wider range than ptl, and (if split from mm's * page_table_lock) ptl nests inside pml. The less time we hold pml, * the better; but userfaultfd's mfill_atomic_pte() on a private VMA * inserts a valid as-if-COWed PTE without even looking up page cache. * So page lock of folio does not protect from it, so we must not drop * ptl before pgt_pmd is removed, so uffd private needs pml taken now. */ if (userfaultfd_armed(vma) && !(vma->vm_flags & VM_SHARED)) pml = pmd_lock(mm, pmd); start_pte = pte_offset_map_nolock(mm, pmd, haddr, &ptl); if (!start_pte) /* mmap_lock + page lock should prevent this */ goto abort; if (!pml) spin_lock(ptl); else if (ptl != pml) spin_lock_nested(ptl, SINGLE_DEPTH_NESTING); /* step 2: clear page table and adjust rmap */ for (i = 0, addr = haddr, pte = start_pte; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE, pte++) { struct page *page; pte_t ptent = ptep_get(pte); if (pte_none(ptent)) continue; /* * We dropped ptl after the first scan, to do the mmu_notifier: * page lock stops more PTEs of the folio being faulted in, but * does not stop write faults COWing anon copies from existing * PTEs; and does not stop those being swapped out or migrated. */ if (!pte_present(ptent)) { result = SCAN_PTE_NON_PRESENT; goto abort; } page = vm_normal_page(vma, addr, ptent); if (folio_page(folio, i) != page) goto abort; /* * Must clear entry, or a racing truncate may re-remove it. * TLB flush can be left until pmdp_collapse_flush() does it. * PTE dirty? Shmem page is already dirty; file is read-only. */ ptep_clear(mm, addr, pte); folio_remove_rmap_pte(folio, page, vma); nr_ptes++; } pte_unmap(start_pte); if (!pml) spin_unlock(ptl); /* step 3: set proper refcount and mm_counters. */ if (nr_ptes) { folio_ref_sub(folio, nr_ptes); add_mm_counter(mm, mm_counter_file(folio), -nr_ptes); } /* step 4: remove empty page table */ if (!pml) { pml = pmd_lock(mm, pmd); if (ptl != pml) spin_lock_nested(ptl, SINGLE_DEPTH_NESTING); } pgt_pmd = pmdp_collapse_flush(vma, haddr, pmd); pmdp_get_lockless_sync(); if (ptl != pml) spin_unlock(ptl); spin_unlock(pml); mmu_notifier_invalidate_range_end(&range); mm_dec_nr_ptes(mm); page_table_check_pte_clear_range(mm, haddr, pgt_pmd); pte_free_defer(mm, pmd_pgtable(pgt_pmd)); maybe_install_pmd: /* step 5: install pmd entry */ result = install_pmd ? set_huge_pmd(vma, haddr, pmd, &folio->page) : SCAN_SUCCEED; goto drop_folio; abort: if (nr_ptes) { flush_tlb_mm(mm); folio_ref_sub(folio, nr_ptes); add_mm_counter(mm, mm_counter_file(folio), -nr_ptes); } if (start_pte) pte_unmap_unlock(start_pte, ptl); if (pml && pml != ptl) spin_unlock(pml); if (notified) mmu_notifier_invalidate_range_end(&range); drop_folio: folio_unlock(folio); folio_put(folio); return result; } static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff) { struct vm_area_struct *vma; i_mmap_lock_read(mapping); vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { struct mmu_notifier_range range; struct mm_struct *mm; unsigned long addr; pmd_t *pmd, pgt_pmd; spinlock_t *pml; spinlock_t *ptl; bool skipped_uffd = false; /* * Check vma->anon_vma to exclude MAP_PRIVATE mappings that * got written to. These VMAs are likely not worth removing * page tables from, as PMD-mapping is likely to be split later. */ if (READ_ONCE(vma->anon_vma)) continue; addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); if (addr & ~HPAGE_PMD_MASK || vma->vm_end < addr + HPAGE_PMD_SIZE) continue; mm = vma->vm_mm; if (find_pmd_or_thp_or_none(mm, addr, &pmd) != SCAN_SUCCEED) continue; if (hpage_collapse_test_exit(mm)) continue; /* * When a vma is registered with uffd-wp, we cannot recycle * the page table because there may be pte markers installed. * Other vmas can still have the same file mapped hugely, but * skip this one: it will always be mapped in small page size * for uffd-wp registered ranges. */ if (userfaultfd_wp(vma)) continue; /* PTEs were notified when unmapped; but now for the PMD? */ mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, addr, addr + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); pml = pmd_lock(mm, pmd); ptl = pte_lockptr(mm, pmd); if (ptl != pml) spin_lock_nested(ptl, SINGLE_DEPTH_NESTING); /* * Huge page lock is still held, so normally the page table * must remain empty; and we have already skipped anon_vma * and userfaultfd_wp() vmas. But since the mmap_lock is not * held, it is still possible for a racing userfaultfd_ioctl() * to have inserted ptes or markers. Now that we hold ptlock, * repeating the anon_vma check protects from one category, * and repeating the userfaultfd_wp() check from another. */ if (unlikely(vma->anon_vma || userfaultfd_wp(vma))) { skipped_uffd = true; } else { pgt_pmd = pmdp_collapse_flush(vma, addr, pmd); pmdp_get_lockless_sync(); } if (ptl != pml) spin_unlock(ptl); spin_unlock(pml); mmu_notifier_invalidate_range_end(&range); if (!skipped_uffd) { mm_dec_nr_ptes(mm); page_table_check_pte_clear_range(mm, addr, pgt_pmd); pte_free_defer(mm, pmd_pgtable(pgt_pmd)); } } i_mmap_unlock_read(mapping); } /** * collapse_file - collapse filemap/tmpfs/shmem pages into huge one. * * @mm: process address space where collapse happens * @addr: virtual collapse start address * @file: file that collapse on * @start: collapse start address * @cc: collapse context and scratchpad * * Basic scheme is simple, details are more complex: * - allocate and lock a new huge page; * - scan page cache, locking old pages * + swap/gup in pages if necessary; * - copy data to new page * - handle shmem holes * + re-validate that holes weren't filled by someone else * + check for userfaultfd * - finalize updates to the page cache; * - if replacing succeeds: * + unlock huge page; * + free old pages; * - if replacing failed; * + unlock old pages * + unlock and free huge page; */ static int collapse_file(struct mm_struct *mm, unsigned long addr, struct file *file, pgoff_t start, struct collapse_control *cc) { struct address_space *mapping = file->f_mapping; struct page *dst; struct folio *folio, *tmp, *new_folio; pgoff_t index = 0, end = start + HPAGE_PMD_NR; LIST_HEAD(pagelist); XA_STATE_ORDER(xas, &mapping->i_pages, start, HPAGE_PMD_ORDER); int nr_none = 0, result = SCAN_SUCCEED; bool is_shmem = shmem_file(file); VM_BUG_ON(!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !is_shmem); VM_BUG_ON(start & (HPAGE_PMD_NR - 1)); result = alloc_charge_folio(&new_folio, mm, cc); if (result != SCAN_SUCCEED) goto out; __folio_set_locked(new_folio); if (is_shmem) __folio_set_swapbacked(new_folio); new_folio->index = start; new_folio->mapping = mapping; /* * Ensure we have slots for all the pages in the range. This is * almost certainly a no-op because most of the pages must be present */ do { xas_lock_irq(&xas); xas_create_range(&xas); if (!xas_error(&xas)) break; xas_unlock_irq(&xas); if (!xas_nomem(&xas, GFP_KERNEL)) { result = SCAN_FAIL; goto rollback; } } while (1); for (index = start; index < end;) { xas_set(&xas, index); folio = xas_load(&xas); VM_BUG_ON(index != xas.xa_index); if (is_shmem) { if (!folio) { /* * Stop if extent has been truncated or * hole-punched, and is now completely * empty. */ if (index == start) { if (!xas_next_entry(&xas, end - 1)) { result = SCAN_TRUNCATED; goto xa_locked; } } nr_none++; index++; continue; } if (xa_is_value(folio) || !folio_test_uptodate(folio)) { xas_unlock_irq(&xas); /* swap in or instantiate fallocated page */ if (shmem_get_folio(mapping->host, index, 0, &folio, SGP_NOALLOC)) { result = SCAN_FAIL; goto xa_unlocked; } /* drain lru cache to help folio_isolate_lru() */ lru_add_drain(); } else if (folio_trylock(folio)) { folio_get(folio); xas_unlock_irq(&xas); } else { result = SCAN_PAGE_LOCK; goto xa_locked; } } else { /* !is_shmem */ if (!folio || xa_is_value(folio)) { xas_unlock_irq(&xas); page_cache_sync_readahead(mapping, &file->f_ra, file, index, end - index); /* drain lru cache to help folio_isolate_lru() */ lru_add_drain(); folio = filemap_lock_folio(mapping, index); if (IS_ERR(folio)) { result = SCAN_FAIL; goto xa_unlocked; } } else if (folio_test_dirty(folio)) { /* * khugepaged only works on read-only fd, * so this page is dirty because it hasn't * been flushed since first write. There * won't be new dirty pages. * * Trigger async flush here and hope the * writeback is done when khugepaged * revisits this page. * * This is a one-off situation. We are not * forcing writeback in loop. */ xas_unlock_irq(&xas); filemap_flush(mapping); result = SCAN_FAIL; goto xa_unlocked; } else if (folio_test_writeback(folio)) { xas_unlock_irq(&xas); result = SCAN_FAIL; goto xa_unlocked; } else if (folio_trylock(folio)) { folio_get(folio); xas_unlock_irq(&xas); } else { result = SCAN_PAGE_LOCK; goto xa_locked; } } /* * The folio must be locked, so we can drop the i_pages lock * without racing with truncate. */ VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); /* make sure the folio is up to date */ if (unlikely(!folio_test_uptodate(folio))) { result = SCAN_FAIL; goto out_unlock; } /* * If file was truncated then extended, or hole-punched, before * we locked the first folio, then a THP might be there already. * This will be discovered on the first iteration. */ if (folio_order(folio) == HPAGE_PMD_ORDER && folio->index == start) { /* Maybe PMD-mapped */ result = SCAN_PTE_MAPPED_HUGEPAGE; goto out_unlock; } if (folio_mapping(folio) != mapping) { result = SCAN_TRUNCATED; goto out_unlock; } if (!is_shmem && (folio_test_dirty(folio) || folio_test_writeback(folio))) { /* * khugepaged only works on read-only fd, so this * folio is dirty because it hasn't been flushed * since first write. */ result = SCAN_FAIL; goto out_unlock; } if (!folio_isolate_lru(folio)) { result = SCAN_DEL_PAGE_LRU; goto out_unlock; } if (!filemap_release_folio(folio, GFP_KERNEL)) { result = SCAN_PAGE_HAS_PRIVATE; folio_putback_lru(folio); goto out_unlock; } if (folio_mapped(folio)) try_to_unmap(folio, TTU_IGNORE_MLOCK | TTU_BATCH_FLUSH); xas_lock_irq(&xas); VM_BUG_ON_FOLIO(folio != xa_load(xas.xa, index), folio); /* * We control 2 + nr_pages references to the folio: * - we hold a pin on it; * - nr_pages reference from page cache; * - one from lru_isolate_folio; * If those are the only references, then any new usage * of the folio will have to fetch it from the page * cache. That requires locking the folio to handle * truncate, so any new usage will be blocked until we * unlock folio after collapse/during rollback. */ if (folio_ref_count(folio) != 2 + folio_nr_pages(folio)) { result = SCAN_PAGE_COUNT; xas_unlock_irq(&xas); folio_putback_lru(folio); goto out_unlock; } /* * Accumulate the folios that are being collapsed. */ list_add_tail(&folio->lru, &pagelist); index += folio_nr_pages(folio); continue; out_unlock: folio_unlock(folio); folio_put(folio); goto xa_unlocked; } if (!is_shmem) { filemap_nr_thps_inc(mapping); /* * Paired with the fence in do_dentry_open() -> get_write_access() * to ensure i_writecount is up to date and the update to nr_thps * is visible. Ensures the page cache will be truncated if the * file is opened writable. */ smp_mb(); if (inode_is_open_for_write(mapping->host)) { result = SCAN_FAIL; filemap_nr_thps_dec(mapping); } } xa_locked: xas_unlock_irq(&xas); xa_unlocked: /* * If collapse is successful, flush must be done now before copying. * If collapse is unsuccessful, does flush actually need to be done? * Do it anyway, to clear the state. */ try_to_unmap_flush(); if (result == SCAN_SUCCEED && nr_none && !shmem_charge(mapping->host, nr_none)) result = SCAN_FAIL; if (result != SCAN_SUCCEED) { nr_none = 0; goto rollback; } /* * The old folios are locked, so they won't change anymore. */ index = start; dst = folio_page(new_folio, 0); list_for_each_entry(folio, &pagelist, lru) { int i, nr_pages = folio_nr_pages(folio); while (index < folio->index) { clear_highpage(dst); index++; dst++; } for (i = 0; i < nr_pages; i++) { if (copy_mc_highpage(dst, folio_page(folio, i)) > 0) { result = SCAN_COPY_MC; goto rollback; } index++; dst++; } } while (index < end) { clear_highpage(dst); index++; dst++; } if (nr_none) { struct vm_area_struct *vma; int nr_none_check = 0; i_mmap_lock_read(mapping); xas_lock_irq(&xas); xas_set(&xas, start); for (index = start; index < end; index++) { if (!xas_next(&xas)) { xas_store(&xas, XA_RETRY_ENTRY); if (xas_error(&xas)) { result = SCAN_STORE_FAILED; goto immap_locked; } nr_none_check++; } } if (nr_none != nr_none_check) { result = SCAN_PAGE_FILLED; goto immap_locked; } /* * If userspace observed a missing page in a VMA with * a MODE_MISSING userfaultfd, then it might expect a * UFFD_EVENT_PAGEFAULT for that page. If so, we need to * roll back to avoid suppressing such an event. Since * wp/minor userfaultfds don't give userspace any * guarantees that the kernel doesn't fill a missing * page with a zero page, so they don't matter here. * * Any userfaultfds registered after this point will * not be able to observe any missing pages due to the * previously inserted retry entries. */ vma_interval_tree_foreach(vma, &mapping->i_mmap, start, end) { if (userfaultfd_missing(vma)) { result = SCAN_EXCEED_NONE_PTE; goto immap_locked; } } immap_locked: i_mmap_unlock_read(mapping); if (result != SCAN_SUCCEED) { xas_set(&xas, start); for (index = start; index < end; index++) { if (xas_next(&xas) == XA_RETRY_ENTRY) xas_store(&xas, NULL); } xas_unlock_irq(&xas); goto rollback; } } else { xas_lock_irq(&xas); } if (is_shmem) __lruvec_stat_mod_folio(new_folio, NR_SHMEM_THPS, HPAGE_PMD_NR); else __lruvec_stat_mod_folio(new_folio, NR_FILE_THPS, HPAGE_PMD_NR); if (nr_none) { __lruvec_stat_mod_folio(new_folio, NR_FILE_PAGES, nr_none); /* nr_none is always 0 for non-shmem. */ __lruvec_stat_mod_folio(new_folio, NR_SHMEM, nr_none); } /* * Mark new_folio as uptodate before inserting it into the * page cache so that it isn't mistaken for an fallocated but * unwritten page. */ folio_mark_uptodate(new_folio); folio_ref_add(new_folio, HPAGE_PMD_NR - 1); if (is_shmem) folio_mark_dirty(new_folio); folio_add_lru(new_folio); /* Join all the small entries into a single multi-index entry. */ xas_set_order(&xas, start, HPAGE_PMD_ORDER); xas_store(&xas, new_folio); WARN_ON_ONCE(xas_error(&xas)); xas_unlock_irq(&xas); /* * Remove pte page tables, so we can re-fault the page as huge. * If MADV_COLLAPSE, adjust result to call collapse_pte_mapped_thp(). */ retract_page_tables(mapping, start); if (cc && !cc->is_khugepaged) result = SCAN_PTE_MAPPED_HUGEPAGE; folio_unlock(new_folio); /* * The collapse has succeeded, so free the old folios. */ list_for_each_entry_safe(folio, tmp, &pagelist, lru) { list_del(&folio->lru); folio->mapping = NULL; folio_clear_active(folio); folio_clear_unevictable(folio); folio_unlock(folio); folio_put_refs(folio, 2 + folio_nr_pages(folio)); } goto out; rollback: /* Something went wrong: roll back page cache changes */ if (nr_none) { xas_lock_irq(&xas); mapping->nrpages -= nr_none; xas_unlock_irq(&xas); shmem_uncharge(mapping->host, nr_none); } list_for_each_entry_safe(folio, tmp, &pagelist, lru) { list_del(&folio->lru); folio_unlock(folio); folio_putback_lru(folio); folio_put(folio); } /* * Undo the updates of filemap_nr_thps_inc for non-SHMEM * file only. This undo is not needed unless failure is * due to SCAN_COPY_MC. */ if (!is_shmem && result == SCAN_COPY_MC) { filemap_nr_thps_dec(mapping); /* * Paired with the fence in do_dentry_open() -> get_write_access() * to ensure the update to nr_thps is visible. */ smp_mb(); } new_folio->mapping = NULL; folio_unlock(new_folio); folio_put(new_folio); out: VM_BUG_ON(!list_empty(&pagelist)); trace_mm_khugepaged_collapse_file(mm, new_folio, index, addr, is_shmem, file, HPAGE_PMD_NR, result); return result; } static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr, struct file *file, pgoff_t start, struct collapse_control *cc) { struct folio *folio = NULL; struct address_space *mapping = file->f_mapping; XA_STATE(xas, &mapping->i_pages, start); int present, swap; int node = NUMA_NO_NODE; int result = SCAN_SUCCEED; present = 0; swap = 0; memset(cc->node_load, 0, sizeof(cc->node_load)); nodes_clear(cc->alloc_nmask); rcu_read_lock(); xas_for_each(&xas, folio, start + HPAGE_PMD_NR - 1) { if (xas_retry(&xas, folio)) continue; if (xa_is_value(folio)) { swap += 1 << xas_get_order(&xas); if (cc->is_khugepaged && swap > khugepaged_max_ptes_swap) { result = SCAN_EXCEED_SWAP_PTE; count_vm_event(THP_SCAN_EXCEED_SWAP_PTE); break; } continue; } if (folio_order(folio) == HPAGE_PMD_ORDER && folio->index == start) { /* Maybe PMD-mapped */ result = SCAN_PTE_MAPPED_HUGEPAGE; /* * For SCAN_PTE_MAPPED_HUGEPAGE, further processing * by the caller won't touch the page cache, and so * it's safe to skip LRU and refcount checks before * returning. */ break; } node = folio_nid(folio); if (hpage_collapse_scan_abort(node, cc)) { result = SCAN_SCAN_ABORT; break; } cc->node_load[node]++; if (!folio_test_lru(folio)) { result = SCAN_PAGE_LRU; break; } if (!is_refcount_suitable(folio)) { result = SCAN_PAGE_COUNT; break; } /* * We probably should check if the folio is referenced * here, but nobody would transfer pte_young() to * folio_test_referenced() for us. And rmap walk here * is just too costly... */ present += folio_nr_pages(folio); if (need_resched()) { xas_pause(&xas); cond_resched_rcu(); } } rcu_read_unlock(); if (result == SCAN_SUCCEED) { if (cc->is_khugepaged && present < HPAGE_PMD_NR - khugepaged_max_ptes_none) { result = SCAN_EXCEED_NONE_PTE; count_vm_event(THP_SCAN_EXCEED_NONE_PTE); } else { result = collapse_file(mm, addr, file, start, cc); } } trace_mm_khugepaged_scan_file(mm, folio, file, present, swap, result); return result; } #else static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr, struct file *file, pgoff_t start, struct collapse_control *cc) { BUILD_BUG(); } #endif static unsigned int khugepaged_scan_mm_slot(unsigned int pages, int *result, struct collapse_control *cc) __releases(&khugepaged_mm_lock) __acquires(&khugepaged_mm_lock) { struct vma_iterator vmi; struct khugepaged_mm_slot *mm_slot; struct mm_slot *slot; struct mm_struct *mm; struct vm_area_struct *vma; int progress = 0; VM_BUG_ON(!pages); lockdep_assert_held(&khugepaged_mm_lock); *result = SCAN_FAIL; if (khugepaged_scan.mm_slot) { mm_slot = khugepaged_scan.mm_slot; slot = &mm_slot->slot; } else { slot = list_entry(khugepaged_scan.mm_head.next, struct mm_slot, mm_node); mm_slot = mm_slot_entry(slot, struct khugepaged_mm_slot, slot); khugepaged_scan.address = 0; khugepaged_scan.mm_slot = mm_slot; } spin_unlock(&khugepaged_mm_lock); mm = slot->mm; /* * Don't wait for semaphore (to avoid long wait times). Just move to * the next mm on the list. */ vma = NULL; if (unlikely(!mmap_read_trylock(mm))) goto breakouterloop_mmap_lock; progress++; if (unlikely(hpage_collapse_test_exit_or_disable(mm))) goto breakouterloop; vma_iter_init(&vmi, mm, khugepaged_scan.address); for_each_vma(vmi, vma) { unsigned long hstart, hend; cond_resched(); if (unlikely(hpage_collapse_test_exit_or_disable(mm))) { progress++; break; } if (!thp_vma_allowable_order(vma, vma->vm_flags, TVA_ENFORCE_SYSFS, PMD_ORDER)) { skip: progress++; continue; } hstart = round_up(vma->vm_start, HPAGE_PMD_SIZE); hend = round_down(vma->vm_end, HPAGE_PMD_SIZE); if (khugepaged_scan.address > hend) goto skip; if (khugepaged_scan.address < hstart) khugepaged_scan.address = hstart; VM_BUG_ON(khugepaged_scan.address & ~HPAGE_PMD_MASK); while (khugepaged_scan.address < hend) { bool mmap_locked = true; cond_resched(); if (unlikely(hpage_collapse_test_exit_or_disable(mm))) goto breakouterloop; VM_BUG_ON(khugepaged_scan.address < hstart || khugepaged_scan.address + HPAGE_PMD_SIZE > hend); if (IS_ENABLED(CONFIG_SHMEM) && vma->vm_file) { struct file *file = get_file(vma->vm_file); pgoff_t pgoff = linear_page_index(vma, khugepaged_scan.address); mmap_read_unlock(mm); mmap_locked = false; *result = hpage_collapse_scan_file(mm, khugepaged_scan.address, file, pgoff, cc); fput(file); if (*result == SCAN_PTE_MAPPED_HUGEPAGE) { mmap_read_lock(mm); if (hpage_collapse_test_exit_or_disable(mm)) goto breakouterloop; *result = collapse_pte_mapped_thp(mm, khugepaged_scan.address, false); if (*result == SCAN_PMD_MAPPED) *result = SCAN_SUCCEED; mmap_read_unlock(mm); } } else { *result = hpage_collapse_scan_pmd(mm, vma, khugepaged_scan.address, &mmap_locked, cc); } if (*result == SCAN_SUCCEED) ++khugepaged_pages_collapsed; /* move to next address */ khugepaged_scan.address += HPAGE_PMD_SIZE; progress += HPAGE_PMD_NR; if (!mmap_locked) /* * We released mmap_lock so break loop. Note * that we drop mmap_lock before all hugepage * allocations, so if allocation fails, we are * guaranteed to break here and report the * correct result back to caller. */ goto breakouterloop_mmap_lock; if (progress >= pages) goto breakouterloop; } } breakouterloop: mmap_read_unlock(mm); /* exit_mmap will destroy ptes after this */ breakouterloop_mmap_lock: spin_lock(&khugepaged_mm_lock); VM_BUG_ON(khugepaged_scan.mm_slot != mm_slot); /* * Release the current mm_slot if this mm is about to die, or * if we scanned all vmas of this mm. */ if (hpage_collapse_test_exit(mm) || !vma) { /* * Make sure that if mm_users is reaching zero while * khugepaged runs here, khugepaged_exit will find * mm_slot not pointing to the exiting mm. */ if (slot->mm_node.next != &khugepaged_scan.mm_head) { slot = list_entry(slot->mm_node.next, struct mm_slot, mm_node); khugepaged_scan.mm_slot = mm_slot_entry(slot, struct khugepaged_mm_slot, slot); khugepaged_scan.address = 0; } else { khugepaged_scan.mm_slot = NULL; khugepaged_full_scans++; } collect_mm_slot(mm_slot); } return progress; } static int khugepaged_has_work(void) { return !list_empty(&khugepaged_scan.mm_head) && hugepage_pmd_enabled(); } static int khugepaged_wait_event(void) { return !list_empty(&khugepaged_scan.mm_head) || kthread_should_stop(); } static void khugepaged_do_scan(struct collapse_control *cc) { unsigned int progress = 0, pass_through_head = 0; unsigned int pages = READ_ONCE(khugepaged_pages_to_scan); bool wait = true; int result = SCAN_SUCCEED; lru_add_drain_all(); while (true) { cond_resched(); if (unlikely(kthread_should_stop())) break; spin_lock(&khugepaged_mm_lock); if (!khugepaged_scan.mm_slot) pass_through_head++; if (khugepaged_has_work() && pass_through_head < 2) progress += khugepaged_scan_mm_slot(pages - progress, &result, cc); else progress = pages; spin_unlock(&khugepaged_mm_lock); if (progress >= pages) break; if (result == SCAN_ALLOC_HUGE_PAGE_FAIL) { /* * If fail to allocate the first time, try to sleep for * a while. When hit again, cancel the scan. */ if (!wait) break; wait = false; khugepaged_alloc_sleep(); } } } static bool khugepaged_should_wakeup(void) { return kthread_should_stop() || time_after_eq(jiffies, khugepaged_sleep_expire); } static void khugepaged_wait_work(void) { if (khugepaged_has_work()) { const unsigned long scan_sleep_jiffies = msecs_to_jiffies(khugepaged_scan_sleep_millisecs); if (!scan_sleep_jiffies) return; khugepaged_sleep_expire = jiffies + scan_sleep_jiffies; wait_event_freezable_timeout(khugepaged_wait, khugepaged_should_wakeup(), scan_sleep_jiffies); return; } if (hugepage_pmd_enabled()) wait_event_freezable(khugepaged_wait, khugepaged_wait_event()); } static int khugepaged(void *none) { struct khugepaged_mm_slot *mm_slot; set_freezable(); set_user_nice(current, MAX_NICE); while (!kthread_should_stop()) { khugepaged_do_scan(&khugepaged_collapse_control); khugepaged_wait_work(); } spin_lock(&khugepaged_mm_lock); mm_slot = khugepaged_scan.mm_slot; khugepaged_scan.mm_slot = NULL; if (mm_slot) collect_mm_slot(mm_slot); spin_unlock(&khugepaged_mm_lock); return 0; } static void set_recommended_min_free_kbytes(void) { struct zone *zone; int nr_zones = 0; unsigned long recommended_min; if (!hugepage_pmd_enabled()) { calculate_min_free_kbytes(); goto update_wmarks; } for_each_populated_zone(zone) { /* * We don't need to worry about fragmentation of * ZONE_MOVABLE since it only has movable pages. */ if (zone_idx(zone) > gfp_zone(GFP_USER)) continue; nr_zones++; } /* Ensure 2 pageblocks are free to assist fragmentation avoidance */ recommended_min = pageblock_nr_pages * nr_zones * 2; /* * Make sure that on average at least two pageblocks are almost free * of another type, one for a migratetype to fall back to and a * second to avoid subsequent fallbacks of other types There are 3 * MIGRATE_TYPES we care about. */ recommended_min += pageblock_nr_pages * nr_zones * MIGRATE_PCPTYPES * MIGRATE_PCPTYPES; /* don't ever allow to reserve more than 5% of the lowmem */ recommended_min = min(recommended_min, (unsigned long) nr_free_buffer_pages() / 20); recommended_min <<= (PAGE_SHIFT-10); if (recommended_min > min_free_kbytes) { if (user_min_free_kbytes >= 0) pr_info("raising min_free_kbytes from %d to %lu to help transparent hugepage allocations\n", min_free_kbytes, recommended_min); min_free_kbytes = recommended_min; } update_wmarks: setup_per_zone_wmarks(); } int start_stop_khugepaged(void) { int err = 0; mutex_lock(&khugepaged_mutex); if (hugepage_pmd_enabled()) { if (!khugepaged_thread) khugepaged_thread = kthread_run(khugepaged, NULL, "khugepaged"); if (IS_ERR(khugepaged_thread)) { pr_err("khugepaged: kthread_run(khugepaged) failed\n"); err = PTR_ERR(khugepaged_thread); khugepaged_thread = NULL; goto fail; } if (!list_empty(&khugepaged_scan.mm_head)) wake_up_interruptible(&khugepaged_wait); } else if (khugepaged_thread) { kthread_stop(khugepaged_thread); khugepaged_thread = NULL; } set_recommended_min_free_kbytes(); fail: mutex_unlock(&khugepaged_mutex); return err; } void khugepaged_min_free_kbytes_update(void) { mutex_lock(&khugepaged_mutex); if (hugepage_pmd_enabled() && khugepaged_thread) set_recommended_min_free_kbytes(); mutex_unlock(&khugepaged_mutex); } bool current_is_khugepaged(void) { return kthread_func(current) == khugepaged; } static int madvise_collapse_errno(enum scan_result r) { /* * MADV_COLLAPSE breaks from existing madvise(2) conventions to provide * actionable feedback to caller, so they may take an appropriate * fallback measure depending on the nature of the failure. */ switch (r) { case SCAN_ALLOC_HUGE_PAGE_FAIL: return -ENOMEM; case SCAN_CGROUP_CHARGE_FAIL: case SCAN_EXCEED_NONE_PTE: return -EBUSY; /* Resource temporary unavailable - trying again might succeed */ case SCAN_PAGE_COUNT: case SCAN_PAGE_LOCK: case SCAN_PAGE_LRU: case SCAN_DEL_PAGE_LRU: case SCAN_PAGE_FILLED: return -EAGAIN; /* * Other: Trying again likely not to succeed / error intrinsic to * specified memory range. khugepaged likely won't be able to collapse * either. */ default: return -EINVAL; } } int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end) { struct collapse_control *cc; struct mm_struct *mm = vma->vm_mm; unsigned long hstart, hend, addr; int thps = 0, last_fail = SCAN_FAIL; bool mmap_locked = true; BUG_ON(vma->vm_start > start); BUG_ON(vma->vm_end < end); *prev = vma; if (!thp_vma_allowable_order(vma, vma->vm_flags, 0, PMD_ORDER)) return -EINVAL; cc = kmalloc(sizeof(*cc), GFP_KERNEL); if (!cc) return -ENOMEM; cc->is_khugepaged = false; mmgrab(mm); lru_add_drain_all(); hstart = (start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; hend = end & HPAGE_PMD_MASK; for (addr = hstart; addr < hend; addr += HPAGE_PMD_SIZE) { int result = SCAN_FAIL; if (!mmap_locked) { cond_resched(); mmap_read_lock(mm); mmap_locked = true; result = hugepage_vma_revalidate(mm, addr, false, &vma, cc); if (result != SCAN_SUCCEED) { last_fail = result; goto out_nolock; } hend = min(hend, vma->vm_end & HPAGE_PMD_MASK); } mmap_assert_locked(mm); memset(cc->node_load, 0, sizeof(cc->node_load)); nodes_clear(cc->alloc_nmask); if (IS_ENABLED(CONFIG_SHMEM) && vma->vm_file) { struct file *file = get_file(vma->vm_file); pgoff_t pgoff = linear_page_index(vma, addr); mmap_read_unlock(mm); mmap_locked = false; result = hpage_collapse_scan_file(mm, addr, file, pgoff, cc); fput(file); } else { result = hpage_collapse_scan_pmd(mm, vma, addr, &mmap_locked, cc); } if (!mmap_locked) *prev = NULL; /* Tell caller we dropped mmap_lock */ handle_result: switch (result) { case SCAN_SUCCEED: case SCAN_PMD_MAPPED: ++thps; break; case SCAN_PTE_MAPPED_HUGEPAGE: BUG_ON(mmap_locked); BUG_ON(*prev); mmap_read_lock(mm); result = collapse_pte_mapped_thp(mm, addr, true); mmap_read_unlock(mm); goto handle_result; /* Whitelisted set of results where continuing OK */ case SCAN_PMD_NULL: case SCAN_PTE_NON_PRESENT: case SCAN_PTE_UFFD_WP: case SCAN_PAGE_RO: case SCAN_LACK_REFERENCED_PAGE: case SCAN_PAGE_NULL: case SCAN_PAGE_COUNT: case SCAN_PAGE_LOCK: case SCAN_PAGE_COMPOUND: case SCAN_PAGE_LRU: case SCAN_DEL_PAGE_LRU: last_fail = result; break; default: last_fail = result; /* Other error, exit */ goto out_maybelock; } } out_maybelock: /* Caller expects us to hold mmap_lock on return */ if (!mmap_locked) mmap_read_lock(mm); out_nolock: mmap_assert_locked(mm); mmdrop(mm); kfree(cc); return thps == ((hend - hstart) >> HPAGE_PMD_SHIFT) ? 0 : madvise_collapse_errno(last_fail); } |
| 79 79 114 100 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2002-2004, Instant802 Networks, Inc. * Copyright 2008, Jouni Malinen <j@w1.fi> * Copyright (C) 2016-2017 Intel Deutschland GmbH * Copyright (C) 2020-2023 Intel Corporation */ #include <linux/netdevice.h> #include <linux/types.h> #include <linux/skbuff.h> #include <linux/compiler.h> #include <linux/ieee80211.h> #include <linux/gfp.h> #include <linux/unaligned.h> #include <net/mac80211.h> #include <crypto/aes.h> #include <crypto/utils.h> #include "ieee80211_i.h" #include "michael.h" #include "tkip.h" #include "aes_ccm.h" #include "aes_cmac.h" #include "aes_gmac.h" #include "aes_gcm.h" #include "wpa.h" ieee80211_tx_result ieee80211_tx_h_michael_mic_add(struct ieee80211_tx_data *tx) { u8 *data, *key, *mic; size_t data_len; unsigned int hdrlen; struct ieee80211_hdr *hdr; struct sk_buff *skb = tx->skb; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); int tail; hdr = (struct ieee80211_hdr *)skb->data; if (!tx->key || tx->key->conf.cipher != WLAN_CIPHER_SUITE_TKIP || skb->len < 24 || !ieee80211_is_data_present(hdr->frame_control)) return TX_CONTINUE; hdrlen = ieee80211_hdrlen(hdr->frame_control); if (skb->len < hdrlen) return TX_DROP; data = skb->data + hdrlen; data_len = skb->len - hdrlen; if (unlikely(info->flags & IEEE80211_TX_INTFL_TKIP_MIC_FAILURE)) { /* Need to use software crypto for the test */ info->control.hw_key = NULL; } if (info->control.hw_key && (info->flags & IEEE80211_TX_CTL_DONTFRAG || ieee80211_hw_check(&tx->local->hw, SUPPORTS_TX_FRAG)) && !(tx->key->conf.flags & (IEEE80211_KEY_FLAG_GENERATE_MMIC | IEEE80211_KEY_FLAG_PUT_MIC_SPACE))) { /* hwaccel - with no need for SW-generated MMIC or MIC space */ return TX_CONTINUE; } tail = MICHAEL_MIC_LEN; if (!info->control.hw_key) tail += IEEE80211_TKIP_ICV_LEN; if (WARN(skb_tailroom(skb) < tail || skb_headroom(skb) < IEEE80211_TKIP_IV_LEN, "mmic: not enough head/tail (%d/%d,%d/%d)\n", skb_headroom(skb), IEEE80211_TKIP_IV_LEN, skb_tailroom(skb), tail)) return TX_DROP; mic = skb_put(skb, MICHAEL_MIC_LEN); if (tx->key->conf.flags & IEEE80211_KEY_FLAG_PUT_MIC_SPACE) { /* Zeroed MIC can help with debug */ memset(mic, 0, MICHAEL_MIC_LEN); return TX_CONTINUE; } key = &tx->key->conf.key[NL80211_TKIP_DATA_OFFSET_TX_MIC_KEY]; michael_mic(key, hdr, data, data_len, mic); if (unlikely(info->flags & IEEE80211_TX_INTFL_TKIP_MIC_FAILURE)) mic[0]++; return TX_CONTINUE; } ieee80211_rx_result ieee80211_rx_h_michael_mic_verify(struct ieee80211_rx_data *rx) { u8 *data, *key = NULL; size_t data_len; unsigned int hdrlen; u8 mic[MICHAEL_MIC_LEN]; struct sk_buff *skb = rx->skb; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; /* * it makes no sense to check for MIC errors on anything other * than data frames. */ if (!ieee80211_is_data_present(hdr->frame_control)) return RX_CONTINUE; /* * No way to verify the MIC if the hardware stripped it or * the IV with the key index. In this case we have solely rely * on the driver to set RX_FLAG_MMIC_ERROR in the event of a * MIC failure report. */ if (status->flag & (RX_FLAG_MMIC_STRIPPED | RX_FLAG_IV_STRIPPED)) { if (status->flag & RX_FLAG_MMIC_ERROR) goto mic_fail_no_key; if (!(status->flag & RX_FLAG_IV_STRIPPED) && rx->key && rx->key->conf.cipher == WLAN_CIPHER_SUITE_TKIP) goto update_iv; return RX_CONTINUE; } /* * Some hardware seems to generate Michael MIC failure reports; even * though, the frame was not encrypted with TKIP and therefore has no * MIC. Ignore the flag them to avoid triggering countermeasures. */ if (!rx->key || rx->key->conf.cipher != WLAN_CIPHER_SUITE_TKIP || !(status->flag & RX_FLAG_DECRYPTED)) return RX_CONTINUE; if (rx->sdata->vif.type == NL80211_IFTYPE_AP && rx->key->conf.keyidx) { /* * APs with pairwise keys should never receive Michael MIC * errors for non-zero keyidx because these are reserved for * group keys and only the AP is sending real multicast * frames in the BSS. */ return RX_DROP_U_AP_RX_GROUPCAST; } if (status->flag & RX_FLAG_MMIC_ERROR) goto mic_fail; hdrlen = ieee80211_hdrlen(hdr->frame_control); if (skb->len < hdrlen + MICHAEL_MIC_LEN) return RX_DROP_U_SHORT_MMIC; if (skb_linearize(rx->skb)) return RX_DROP_U_OOM; hdr = (void *)skb->data; data = skb->data + hdrlen; data_len = skb->len - hdrlen - MICHAEL_MIC_LEN; key = &rx->key->conf.key[NL80211_TKIP_DATA_OFFSET_RX_MIC_KEY]; michael_mic(key, hdr, data, data_len, mic); if (crypto_memneq(mic, data + data_len, MICHAEL_MIC_LEN)) goto mic_fail; /* remove Michael MIC from payload */ skb_trim(skb, skb->len - MICHAEL_MIC_LEN); update_iv: /* update IV in key information to be able to detect replays */ rx->key->u.tkip.rx[rx->security_idx].iv32 = rx->tkip.iv32; rx->key->u.tkip.rx[rx->security_idx].iv16 = rx->tkip.iv16; return RX_CONTINUE; mic_fail: rx->key->u.tkip.mic_failures++; mic_fail_no_key: /* * In some cases the key can be unset - e.g. a multicast packet, in * a driver that supports HW encryption. Send up the key idx only if * the key is set. */ cfg80211_michael_mic_failure(rx->sdata->dev, hdr->addr2, is_multicast_ether_addr(hdr->addr1) ? NL80211_KEYTYPE_GROUP : NL80211_KEYTYPE_PAIRWISE, rx->key ? rx->key->conf.keyidx : -1, NULL, GFP_ATOMIC); return RX_DROP_U_MMIC_FAIL; } static int tkip_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct ieee80211_key *key = tx->key; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); unsigned int hdrlen; int len, tail; u64 pn; u8 *pos; if (info->control.hw_key && !(info->control.hw_key->flags & IEEE80211_KEY_FLAG_GENERATE_IV) && !(info->control.hw_key->flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE)) { /* hwaccel - with no need for software-generated IV */ return 0; } hdrlen = ieee80211_hdrlen(hdr->frame_control); len = skb->len - hdrlen; if (info->control.hw_key) tail = 0; else tail = IEEE80211_TKIP_ICV_LEN; if (WARN_ON(skb_tailroom(skb) < tail || skb_headroom(skb) < IEEE80211_TKIP_IV_LEN)) return -1; pos = skb_push(skb, IEEE80211_TKIP_IV_LEN); memmove(pos, pos + IEEE80211_TKIP_IV_LEN, hdrlen); pos += hdrlen; /* the HW only needs room for the IV, but not the actual IV */ if (info->control.hw_key && (info->control.hw_key->flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE)) return 0; /* Increase IV for the frame */ pn = atomic64_inc_return(&key->conf.tx_pn); pos = ieee80211_tkip_add_iv(pos, &key->conf, pn); /* hwaccel - with software IV */ if (info->control.hw_key) return 0; /* Add room for ICV */ skb_put(skb, IEEE80211_TKIP_ICV_LEN); return ieee80211_tkip_encrypt_data(&tx->local->wep_tx_ctx, key, skb, pos, len); } ieee80211_tx_result ieee80211_crypto_tkip_encrypt(struct ieee80211_tx_data *tx) { struct sk_buff *skb; ieee80211_tx_set_protected(tx); skb_queue_walk(&tx->skbs, skb) { if (tkip_encrypt_skb(tx, skb) < 0) return TX_DROP; } return TX_CONTINUE; } ieee80211_rx_result ieee80211_crypto_tkip_decrypt(struct ieee80211_rx_data *rx) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) rx->skb->data; int hdrlen, res, hwaccel = 0; struct ieee80211_key *key = rx->key; struct sk_buff *skb = rx->skb; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); hdrlen = ieee80211_hdrlen(hdr->frame_control); if (!ieee80211_is_data(hdr->frame_control)) return RX_CONTINUE; if (!rx->sta || skb->len - hdrlen < 12) return RX_DROP_U_SHORT_TKIP; /* it may be possible to optimize this a bit more */ if (skb_linearize(rx->skb)) return RX_DROP_U_OOM; hdr = (void *)skb->data; /* * Let TKIP code verify IV, but skip decryption. * In the case where hardware checks the IV as well, * we don't even get here, see ieee80211_rx_h_decrypt() */ if (status->flag & RX_FLAG_DECRYPTED) hwaccel = 1; res = ieee80211_tkip_decrypt_data(&rx->local->wep_rx_ctx, key, skb->data + hdrlen, skb->len - hdrlen, rx->sta->sta.addr, hdr->addr1, hwaccel, rx->security_idx, &rx->tkip.iv32, &rx->tkip.iv16); if (res != TKIP_DECRYPT_OK) return RX_DROP_U_TKIP_FAIL; /* Trim ICV */ if (!(status->flag & RX_FLAG_ICV_STRIPPED)) skb_trim(skb, skb->len - IEEE80211_TKIP_ICV_LEN); /* Remove IV */ memmove(skb->data + IEEE80211_TKIP_IV_LEN, skb->data, hdrlen); skb_pull(skb, IEEE80211_TKIP_IV_LEN); return RX_CONTINUE; } /* * Calculate AAD for CCMP/GCMP, returning qos_tid since we * need that in CCMP also for b_0. */ static u8 ccmp_gcmp_aad(struct sk_buff *skb, u8 *aad, bool spp_amsdu) { struct ieee80211_hdr *hdr = (void *)skb->data; __le16 mask_fc; int a4_included, mgmt; u8 qos_tid; u16 len_a = 22; /* * Mask FC: zero subtype b4 b5 b6 (if not mgmt) * Retry, PwrMgt, MoreData, Order (if Qos Data); set Protected */ mgmt = ieee80211_is_mgmt(hdr->frame_control); mask_fc = hdr->frame_control; mask_fc &= ~cpu_to_le16(IEEE80211_FCTL_RETRY | IEEE80211_FCTL_PM | IEEE80211_FCTL_MOREDATA); if (!mgmt) mask_fc &= ~cpu_to_le16(0x0070); mask_fc |= cpu_to_le16(IEEE80211_FCTL_PROTECTED); a4_included = ieee80211_has_a4(hdr->frame_control); if (a4_included) len_a += 6; if (ieee80211_is_data_qos(hdr->frame_control)) { qos_tid = *ieee80211_get_qos_ctl(hdr); if (spp_amsdu) qos_tid &= IEEE80211_QOS_CTL_TID_MASK | IEEE80211_QOS_CTL_A_MSDU_PRESENT; else qos_tid &= IEEE80211_QOS_CTL_TID_MASK; mask_fc &= ~cpu_to_le16(IEEE80211_FCTL_ORDER); len_a += 2; } else { qos_tid = 0; } /* AAD (extra authenticate-only data) / masked 802.11 header * FC | A1 | A2 | A3 | SC | [A4] | [QC] */ put_unaligned_be16(len_a, &aad[0]); put_unaligned(mask_fc, (__le16 *)&aad[2]); memcpy(&aad[4], &hdr->addrs, 3 * ETH_ALEN); /* Mask Seq#, leave Frag# */ aad[22] = *((u8 *) &hdr->seq_ctrl) & 0x0f; aad[23] = 0; if (a4_included) { memcpy(&aad[24], hdr->addr4, ETH_ALEN); aad[30] = qos_tid; aad[31] = 0; } else { memset(&aad[24], 0, ETH_ALEN + IEEE80211_QOS_CTL_LEN); aad[24] = qos_tid; } return qos_tid; } static void ccmp_special_blocks(struct sk_buff *skb, u8 *pn, u8 *b_0, u8 *aad, bool spp_amsdu) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; u8 qos_tid = ccmp_gcmp_aad(skb, aad, spp_amsdu); /* In CCM, the initial vectors (IV) used for CTR mode encryption and CBC * mode authentication are not allowed to collide, yet both are derived * from this vector b_0. We only set L := 1 here to indicate that the * data size can be represented in (L+1) bytes. The CCM layer will take * care of storing the data length in the top (L+1) bytes and setting * and clearing the other bits as is required to derive the two IVs. */ b_0[0] = 0x1; /* Nonce: Nonce Flags | A2 | PN * Nonce Flags: Priority (b0..b3) | Management (b4) | Reserved (b5..b7) */ b_0[1] = qos_tid | (ieee80211_is_mgmt(hdr->frame_control) << 4); memcpy(&b_0[2], hdr->addr2, ETH_ALEN); memcpy(&b_0[8], pn, IEEE80211_CCMP_PN_LEN); } static inline void ccmp_pn2hdr(u8 *hdr, u8 *pn, int key_id) { hdr[0] = pn[5]; hdr[1] = pn[4]; hdr[2] = 0; hdr[3] = 0x20 | (key_id << 6); hdr[4] = pn[3]; hdr[5] = pn[2]; hdr[6] = pn[1]; hdr[7] = pn[0]; } static inline void ccmp_hdr2pn(u8 *pn, u8 *hdr) { pn[0] = hdr[7]; pn[1] = hdr[6]; pn[2] = hdr[5]; pn[3] = hdr[4]; pn[4] = hdr[1]; pn[5] = hdr[0]; } static int ccmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb, unsigned int mic_len) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct ieee80211_key *key = tx->key; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); int hdrlen, len, tail; u8 *pos; u8 pn[6]; u64 pn64; u8 aad[CCM_AAD_LEN]; u8 b_0[AES_BLOCK_SIZE]; if (info->control.hw_key && !(info->control.hw_key->flags & IEEE80211_KEY_FLAG_GENERATE_IV) && !(info->control.hw_key->flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE) && !((info->control.hw_key->flags & IEEE80211_KEY_FLAG_GENERATE_IV_MGMT) && ieee80211_is_mgmt(hdr->frame_control))) { /* * hwaccel has no need for preallocated room for CCMP * header or MIC fields */ return 0; } hdrlen = ieee80211_hdrlen(hdr->frame_control); len = skb->len - hdrlen; if (info->control.hw_key) tail = 0; else tail = mic_len; if (WARN_ON(skb_tailroom(skb) < tail || skb_headroom(skb) < IEEE80211_CCMP_HDR_LEN)) return -1; pos = skb_push(skb, IEEE80211_CCMP_HDR_LEN); memmove(pos, pos + IEEE80211_CCMP_HDR_LEN, hdrlen); /* the HW only needs room for the IV, but not the actual IV */ if (info->control.hw_key && (info->control.hw_key->flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE)) return 0; pos += hdrlen; pn64 = atomic64_inc_return(&key->conf.tx_pn); pn[5] = pn64; pn[4] = pn64 >> 8; pn[3] = pn64 >> 16; pn[2] = pn64 >> 24; pn[1] = pn64 >> 32; pn[0] = pn64 >> 40; ccmp_pn2hdr(pos, pn, key->conf.keyidx); /* hwaccel - with software CCMP header */ if (info->control.hw_key) return 0; pos += IEEE80211_CCMP_HDR_LEN; ccmp_special_blocks(skb, pn, b_0, aad, key->conf.flags & IEEE80211_KEY_FLAG_SPP_AMSDU); return ieee80211_aes_ccm_encrypt(key->u.ccmp.tfm, b_0, aad, pos, len, skb_put(skb, mic_len)); } ieee80211_tx_result ieee80211_crypto_ccmp_encrypt(struct ieee80211_tx_data *tx, unsigned int mic_len) { struct sk_buff *skb; ieee80211_tx_set_protected(tx); skb_queue_walk(&tx->skbs, skb) { if (ccmp_encrypt_skb(tx, skb, mic_len) < 0) return TX_DROP; } return TX_CONTINUE; } ieee80211_rx_result ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx, unsigned int mic_len) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)rx->skb->data; int hdrlen; struct ieee80211_key *key = rx->key; struct sk_buff *skb = rx->skb; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); u8 pn[IEEE80211_CCMP_PN_LEN]; int data_len; int queue; hdrlen = ieee80211_hdrlen(hdr->frame_control); if (!ieee80211_is_data(hdr->frame_control) && !ieee80211_is_robust_mgmt_frame(skb)) return RX_CONTINUE; if (status->flag & RX_FLAG_DECRYPTED) { if (!pskb_may_pull(rx->skb, hdrlen + IEEE80211_CCMP_HDR_LEN)) return RX_DROP_U_SHORT_CCMP; if (status->flag & RX_FLAG_MIC_STRIPPED) mic_len = 0; } else { if (skb_linearize(rx->skb)) return RX_DROP_U_OOM; } /* reload hdr - skb might have been reallocated */ hdr = (void *)rx->skb->data; data_len = skb->len - hdrlen - IEEE80211_CCMP_HDR_LEN - mic_len; if (!rx->sta || data_len < 0) return RX_DROP_U_SHORT_CCMP; if (!(status->flag & RX_FLAG_PN_VALIDATED)) { int res; ccmp_hdr2pn(pn, skb->data + hdrlen); queue = rx->security_idx; res = memcmp(pn, key->u.ccmp.rx_pn[queue], IEEE80211_CCMP_PN_LEN); if (res < 0 || (!res && !(status->flag & RX_FLAG_ALLOW_SAME_PN))) { key->u.ccmp.replays++; return RX_DROP_U_REPLAY; } if (!(status->flag & RX_FLAG_DECRYPTED)) { u8 aad[2 * AES_BLOCK_SIZE]; u8 b_0[AES_BLOCK_SIZE]; /* hardware didn't decrypt/verify MIC */ ccmp_special_blocks(skb, pn, b_0, aad, key->conf.flags & IEEE80211_KEY_FLAG_SPP_AMSDU); if (ieee80211_aes_ccm_decrypt( key->u.ccmp.tfm, b_0, aad, skb->data + hdrlen + IEEE80211_CCMP_HDR_LEN, data_len, skb->data + skb->len - mic_len)) return RX_DROP_U_MIC_FAIL; } memcpy(key->u.ccmp.rx_pn[queue], pn, IEEE80211_CCMP_PN_LEN); if (unlikely(ieee80211_is_frag(hdr))) memcpy(rx->ccm_gcm.pn, pn, IEEE80211_CCMP_PN_LEN); } /* Remove CCMP header and MIC */ if (pskb_trim(skb, skb->len - mic_len)) return RX_DROP_U_SHORT_CCMP_MIC; memmove(skb->data + IEEE80211_CCMP_HDR_LEN, skb->data, hdrlen); skb_pull(skb, IEEE80211_CCMP_HDR_LEN); return RX_CONTINUE; } static void gcmp_special_blocks(struct sk_buff *skb, u8 *pn, u8 *j_0, u8 *aad, bool spp_amsdu) { struct ieee80211_hdr *hdr = (void *)skb->data; memcpy(j_0, hdr->addr2, ETH_ALEN); memcpy(&j_0[ETH_ALEN], pn, IEEE80211_GCMP_PN_LEN); j_0[13] = 0; j_0[14] = 0; j_0[AES_BLOCK_SIZE - 1] = 0x01; ccmp_gcmp_aad(skb, aad, spp_amsdu); } static inline void gcmp_pn2hdr(u8 *hdr, const u8 *pn, int key_id) { hdr[0] = pn[5]; hdr[1] = pn[4]; hdr[2] = 0; hdr[3] = |