| David Howells | 9ae326a | 2009-04-03 16:42:41 +0100 | [diff] [blame] | 1 | /* Storage object read/write | 
|  | 2 | * | 
|  | 3 | * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. | 
|  | 4 | * Written by David Howells (dhowells@redhat.com) | 
|  | 5 | * | 
|  | 6 | * This program is free software; you can redistribute it and/or | 
|  | 7 | * modify it under the terms of the GNU General Public Licence | 
|  | 8 | * as published by the Free Software Foundation; either version | 
|  | 9 | * 2 of the Licence, or (at your option) any later version. | 
|  | 10 | */ | 
|  | 11 |  | 
|  | 12 | #include <linux/mount.h> | 
|  | 13 | #include <linux/file.h> | 
|  | 14 | #include "internal.h" | 
|  | 15 |  | 
|  | 16 | /* | 
|  | 17 | * detect wake up events generated by the unlocking of pages in which we're | 
|  | 18 | * interested | 
|  | 19 | * - we use this to detect read completion of backing pages | 
|  | 20 | * - the caller holds the waitqueue lock | 
|  | 21 | */ | 
|  | 22 | static int cachefiles_read_waiter(wait_queue_t *wait, unsigned mode, | 
|  | 23 | int sync, void *_key) | 
|  | 24 | { | 
|  | 25 | struct cachefiles_one_read *monitor = | 
|  | 26 | container_of(wait, struct cachefiles_one_read, monitor); | 
|  | 27 | struct cachefiles_object *object; | 
|  | 28 | struct wait_bit_key *key = _key; | 
|  | 29 | struct page *page = wait->private; | 
|  | 30 |  | 
|  | 31 | ASSERT(key); | 
|  | 32 |  | 
|  | 33 | _enter("{%lu},%u,%d,{%p,%u}", | 
|  | 34 | monitor->netfs_page->index, mode, sync, | 
|  | 35 | key->flags, key->bit_nr); | 
|  | 36 |  | 
|  | 37 | if (key->flags != &page->flags || | 
|  | 38 | key->bit_nr != PG_locked) | 
|  | 39 | return 0; | 
|  | 40 |  | 
|  | 41 | _debug("--- monitor %p %lx ---", page, page->flags); | 
|  | 42 |  | 
|  | 43 | if (!PageUptodate(page) && !PageError(page)) | 
|  | 44 | dump_stack(); | 
|  | 45 |  | 
|  | 46 | /* remove from the waitqueue */ | 
|  | 47 | list_del(&wait->task_list); | 
|  | 48 |  | 
|  | 49 | /* move onto the action list and queue for FS-Cache thread pool */ | 
|  | 50 | ASSERT(monitor->op); | 
|  | 51 |  | 
|  | 52 | object = container_of(monitor->op->op.object, | 
|  | 53 | struct cachefiles_object, fscache); | 
|  | 54 |  | 
|  | 55 | spin_lock(&object->work_lock); | 
|  | 56 | list_add_tail(&monitor->op_link, &monitor->op->to_do); | 
|  | 57 | spin_unlock(&object->work_lock); | 
|  | 58 |  | 
|  | 59 | fscache_enqueue_retrieval(monitor->op); | 
|  | 60 | return 0; | 
|  | 61 | } | 
|  | 62 |  | 
|  | 63 | /* | 
|  | 64 | * copy data from backing pages to netfs pages to complete a read operation | 
|  | 65 | * - driven by FS-Cache's thread pool | 
|  | 66 | */ | 
|  | 67 | static void cachefiles_read_copier(struct fscache_operation *_op) | 
|  | 68 | { | 
|  | 69 | struct cachefiles_one_read *monitor; | 
|  | 70 | struct cachefiles_object *object; | 
|  | 71 | struct fscache_retrieval *op; | 
|  | 72 | struct pagevec pagevec; | 
|  | 73 | int error, max; | 
|  | 74 |  | 
|  | 75 | op = container_of(_op, struct fscache_retrieval, op); | 
|  | 76 | object = container_of(op->op.object, | 
|  | 77 | struct cachefiles_object, fscache); | 
|  | 78 |  | 
|  | 79 | _enter("{ino=%lu}", object->backer->d_inode->i_ino); | 
|  | 80 |  | 
|  | 81 | pagevec_init(&pagevec, 0); | 
|  | 82 |  | 
|  | 83 | max = 8; | 
|  | 84 | spin_lock_irq(&object->work_lock); | 
|  | 85 |  | 
|  | 86 | while (!list_empty(&op->to_do)) { | 
|  | 87 | monitor = list_entry(op->to_do.next, | 
|  | 88 | struct cachefiles_one_read, op_link); | 
|  | 89 | list_del(&monitor->op_link); | 
|  | 90 |  | 
|  | 91 | spin_unlock_irq(&object->work_lock); | 
|  | 92 |  | 
|  | 93 | _debug("- copy {%lu}", monitor->back_page->index); | 
|  | 94 |  | 
|  | 95 | error = -EIO; | 
|  | 96 | if (PageUptodate(monitor->back_page)) { | 
|  | 97 | copy_highpage(monitor->netfs_page, monitor->back_page); | 
|  | 98 |  | 
|  | 99 | pagevec_add(&pagevec, monitor->netfs_page); | 
|  | 100 | fscache_mark_pages_cached(monitor->op, &pagevec); | 
|  | 101 | error = 0; | 
|  | 102 | } | 
|  | 103 |  | 
|  | 104 | if (error) | 
|  | 105 | cachefiles_io_error_obj( | 
|  | 106 | object, | 
|  | 107 | "Readpage failed on backing file %lx", | 
|  | 108 | (unsigned long) monitor->back_page->flags); | 
|  | 109 |  | 
|  | 110 | page_cache_release(monitor->back_page); | 
|  | 111 |  | 
|  | 112 | fscache_end_io(op, monitor->netfs_page, error); | 
|  | 113 | page_cache_release(monitor->netfs_page); | 
|  | 114 | fscache_put_retrieval(op); | 
|  | 115 | kfree(monitor); | 
|  | 116 |  | 
|  | 117 | /* let the thread pool have some air occasionally */ | 
|  | 118 | max--; | 
|  | 119 | if (max < 0 || need_resched()) { | 
|  | 120 | if (!list_empty(&op->to_do)) | 
|  | 121 | fscache_enqueue_retrieval(op); | 
|  | 122 | _leave(" [maxed out]"); | 
|  | 123 | return; | 
|  | 124 | } | 
|  | 125 |  | 
|  | 126 | spin_lock_irq(&object->work_lock); | 
|  | 127 | } | 
|  | 128 |  | 
|  | 129 | spin_unlock_irq(&object->work_lock); | 
|  | 130 | _leave(""); | 
|  | 131 | } | 
|  | 132 |  | 
|  | 133 | /* | 
|  | 134 | * read the corresponding page to the given set from the backing file | 
|  | 135 | * - an uncertain page is simply discarded, to be tried again another time | 
|  | 136 | */ | 
|  | 137 | static int cachefiles_read_backing_file_one(struct cachefiles_object *object, | 
|  | 138 | struct fscache_retrieval *op, | 
|  | 139 | struct page *netpage, | 
|  | 140 | struct pagevec *pagevec) | 
|  | 141 | { | 
|  | 142 | struct cachefiles_one_read *monitor; | 
|  | 143 | struct address_space *bmapping; | 
|  | 144 | struct page *newpage, *backpage; | 
|  | 145 | int ret; | 
|  | 146 |  | 
|  | 147 | _enter(""); | 
|  | 148 |  | 
|  | 149 | pagevec_reinit(pagevec); | 
|  | 150 |  | 
|  | 151 | _debug("read back %p{%lu,%d}", | 
|  | 152 | netpage, netpage->index, page_count(netpage)); | 
|  | 153 |  | 
|  | 154 | monitor = kzalloc(sizeof(*monitor), GFP_KERNEL); | 
|  | 155 | if (!monitor) | 
|  | 156 | goto nomem; | 
|  | 157 |  | 
|  | 158 | monitor->netfs_page = netpage; | 
|  | 159 | monitor->op = fscache_get_retrieval(op); | 
|  | 160 |  | 
|  | 161 | init_waitqueue_func_entry(&monitor->monitor, cachefiles_read_waiter); | 
|  | 162 |  | 
|  | 163 | /* attempt to get hold of the backing page */ | 
|  | 164 | bmapping = object->backer->d_inode->i_mapping; | 
|  | 165 | newpage = NULL; | 
|  | 166 |  | 
|  | 167 | for (;;) { | 
|  | 168 | backpage = find_get_page(bmapping, netpage->index); | 
|  | 169 | if (backpage) | 
|  | 170 | goto backing_page_already_present; | 
|  | 171 |  | 
|  | 172 | if (!newpage) { | 
|  | 173 | newpage = page_cache_alloc_cold(bmapping); | 
|  | 174 | if (!newpage) | 
|  | 175 | goto nomem_monitor; | 
|  | 176 | } | 
|  | 177 |  | 
|  | 178 | ret = add_to_page_cache(newpage, bmapping, | 
|  | 179 | netpage->index, GFP_KERNEL); | 
|  | 180 | if (ret == 0) | 
|  | 181 | goto installed_new_backing_page; | 
|  | 182 | if (ret != -EEXIST) | 
|  | 183 | goto nomem_page; | 
|  | 184 | } | 
|  | 185 |  | 
|  | 186 | /* we've installed a new backing page, so now we need to add it | 
|  | 187 | * to the LRU list and start it reading */ | 
|  | 188 | installed_new_backing_page: | 
|  | 189 | _debug("- new %p", newpage); | 
|  | 190 |  | 
|  | 191 | backpage = newpage; | 
|  | 192 | newpage = NULL; | 
|  | 193 |  | 
|  | 194 | page_cache_get(backpage); | 
|  | 195 | pagevec_add(pagevec, backpage); | 
|  | 196 | __pagevec_lru_add_file(pagevec); | 
|  | 197 |  | 
|  | 198 | read_backing_page: | 
|  | 199 | ret = bmapping->a_ops->readpage(NULL, backpage); | 
|  | 200 | if (ret < 0) | 
|  | 201 | goto read_error; | 
|  | 202 |  | 
|  | 203 | /* set the monitor to transfer the data across */ | 
|  | 204 | monitor_backing_page: | 
|  | 205 | _debug("- monitor add"); | 
|  | 206 |  | 
|  | 207 | /* install the monitor */ | 
|  | 208 | page_cache_get(monitor->netfs_page); | 
|  | 209 | page_cache_get(backpage); | 
|  | 210 | monitor->back_page = backpage; | 
|  | 211 | monitor->monitor.private = backpage; | 
|  | 212 | add_page_wait_queue(backpage, &monitor->monitor); | 
|  | 213 | monitor = NULL; | 
|  | 214 |  | 
|  | 215 | /* but the page may have been read before the monitor was installed, so | 
|  | 216 | * the monitor may miss the event - so we have to ensure that we do get | 
|  | 217 | * one in such a case */ | 
|  | 218 | if (trylock_page(backpage)) { | 
|  | 219 | _debug("jumpstart %p {%lx}", backpage, backpage->flags); | 
|  | 220 | unlock_page(backpage); | 
|  | 221 | } | 
|  | 222 | goto success; | 
|  | 223 |  | 
|  | 224 | /* if the backing page is already present, it can be in one of | 
|  | 225 | * three states: read in progress, read failed or read okay */ | 
|  | 226 | backing_page_already_present: | 
|  | 227 | _debug("- present"); | 
|  | 228 |  | 
|  | 229 | if (newpage) { | 
|  | 230 | page_cache_release(newpage); | 
|  | 231 | newpage = NULL; | 
|  | 232 | } | 
|  | 233 |  | 
|  | 234 | if (PageError(backpage)) | 
|  | 235 | goto io_error; | 
|  | 236 |  | 
|  | 237 | if (PageUptodate(backpage)) | 
|  | 238 | goto backing_page_already_uptodate; | 
|  | 239 |  | 
|  | 240 | if (!trylock_page(backpage)) | 
|  | 241 | goto monitor_backing_page; | 
|  | 242 | _debug("read %p {%lx}", backpage, backpage->flags); | 
|  | 243 | goto read_backing_page; | 
|  | 244 |  | 
|  | 245 | /* the backing page is already up to date, attach the netfs | 
|  | 246 | * page to the pagecache and LRU and copy the data across */ | 
|  | 247 | backing_page_already_uptodate: | 
|  | 248 | _debug("- uptodate"); | 
|  | 249 |  | 
|  | 250 | pagevec_add(pagevec, netpage); | 
|  | 251 | fscache_mark_pages_cached(op, pagevec); | 
|  | 252 |  | 
|  | 253 | copy_highpage(netpage, backpage); | 
|  | 254 | fscache_end_io(op, netpage, 0); | 
|  | 255 |  | 
|  | 256 | success: | 
|  | 257 | _debug("success"); | 
|  | 258 | ret = 0; | 
|  | 259 |  | 
|  | 260 | out: | 
|  | 261 | if (backpage) | 
|  | 262 | page_cache_release(backpage); | 
|  | 263 | if (monitor) { | 
|  | 264 | fscache_put_retrieval(monitor->op); | 
|  | 265 | kfree(monitor); | 
|  | 266 | } | 
|  | 267 | _leave(" = %d", ret); | 
|  | 268 | return ret; | 
|  | 269 |  | 
|  | 270 | read_error: | 
|  | 271 | _debug("read error %d", ret); | 
|  | 272 | if (ret == -ENOMEM) | 
|  | 273 | goto out; | 
|  | 274 | io_error: | 
|  | 275 | cachefiles_io_error_obj(object, "Page read error on backing file"); | 
|  | 276 | ret = -ENOBUFS; | 
|  | 277 | goto out; | 
|  | 278 |  | 
|  | 279 | nomem_page: | 
|  | 280 | page_cache_release(newpage); | 
|  | 281 | nomem_monitor: | 
|  | 282 | fscache_put_retrieval(monitor->op); | 
|  | 283 | kfree(monitor); | 
|  | 284 | nomem: | 
|  | 285 | _leave(" = -ENOMEM"); | 
|  | 286 | return -ENOMEM; | 
|  | 287 | } | 
|  | 288 |  | 
|  | 289 | /* | 
|  | 290 | * read a page from the cache or allocate a block in which to store it | 
|  | 291 | * - cache withdrawal is prevented by the caller | 
|  | 292 | * - returns -EINTR if interrupted | 
|  | 293 | * - returns -ENOMEM if ran out of memory | 
|  | 294 | * - returns -ENOBUFS if no buffers can be made available | 
|  | 295 | * - returns -ENOBUFS if page is beyond EOF | 
|  | 296 | * - if the page is backed by a block in the cache: | 
|  | 297 | *   - a read will be started which will call the callback on completion | 
|  | 298 | *   - 0 will be returned | 
|  | 299 | * - else if the page is unbacked: | 
|  | 300 | *   - the metadata will be retained | 
|  | 301 | *   - -ENODATA will be returned | 
|  | 302 | */ | 
|  | 303 | int cachefiles_read_or_alloc_page(struct fscache_retrieval *op, | 
|  | 304 | struct page *page, | 
|  | 305 | gfp_t gfp) | 
|  | 306 | { | 
|  | 307 | struct cachefiles_object *object; | 
|  | 308 | struct cachefiles_cache *cache; | 
|  | 309 | struct pagevec pagevec; | 
|  | 310 | struct inode *inode; | 
|  | 311 | sector_t block0, block; | 
|  | 312 | unsigned shift; | 
|  | 313 | int ret; | 
|  | 314 |  | 
|  | 315 | object = container_of(op->op.object, | 
|  | 316 | struct cachefiles_object, fscache); | 
|  | 317 | cache = container_of(object->fscache.cache, | 
|  | 318 | struct cachefiles_cache, cache); | 
|  | 319 |  | 
|  | 320 | _enter("{%p},{%lx},,,", object, page->index); | 
|  | 321 |  | 
|  | 322 | if (!object->backer) | 
|  | 323 | return -ENOBUFS; | 
|  | 324 |  | 
|  | 325 | inode = object->backer->d_inode; | 
|  | 326 | ASSERT(S_ISREG(inode->i_mode)); | 
|  | 327 | ASSERT(inode->i_mapping->a_ops->bmap); | 
|  | 328 | ASSERT(inode->i_mapping->a_ops->readpages); | 
|  | 329 |  | 
|  | 330 | /* calculate the shift required to use bmap */ | 
|  | 331 | if (inode->i_sb->s_blocksize > PAGE_SIZE) | 
|  | 332 | return -ENOBUFS; | 
|  | 333 |  | 
|  | 334 | shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits; | 
|  | 335 |  | 
|  | 336 | op->op.flags = FSCACHE_OP_FAST; | 
|  | 337 | op->op.processor = cachefiles_read_copier; | 
|  | 338 |  | 
|  | 339 | pagevec_init(&pagevec, 0); | 
|  | 340 |  | 
|  | 341 | /* we assume the absence or presence of the first block is a good | 
|  | 342 | * enough indication for the page as a whole | 
|  | 343 | * - TODO: don't use bmap() for this as it is _not_ actually good | 
|  | 344 | *   enough for this as it doesn't indicate errors, but it's all we've | 
|  | 345 | *   got for the moment | 
|  | 346 | */ | 
|  | 347 | block0 = page->index; | 
|  | 348 | block0 <<= shift; | 
|  | 349 |  | 
|  | 350 | block = inode->i_mapping->a_ops->bmap(inode->i_mapping, block0); | 
|  | 351 | _debug("%llx -> %llx", | 
|  | 352 | (unsigned long long) block0, | 
|  | 353 | (unsigned long long) block); | 
|  | 354 |  | 
|  | 355 | if (block) { | 
|  | 356 | /* submit the apparently valid page to the backing fs to be | 
|  | 357 | * read from disk */ | 
|  | 358 | ret = cachefiles_read_backing_file_one(object, op, page, | 
|  | 359 | &pagevec); | 
|  | 360 | } else if (cachefiles_has_space(cache, 0, 1) == 0) { | 
|  | 361 | /* there's space in the cache we can use */ | 
|  | 362 | pagevec_add(&pagevec, page); | 
|  | 363 | fscache_mark_pages_cached(op, &pagevec); | 
|  | 364 | ret = -ENODATA; | 
|  | 365 | } else { | 
|  | 366 | ret = -ENOBUFS; | 
|  | 367 | } | 
|  | 368 |  | 
|  | 369 | _leave(" = %d", ret); | 
|  | 370 | return ret; | 
|  | 371 | } | 
|  | 372 |  | 
|  | 373 | /* | 
|  | 374 | * read the corresponding pages to the given set from the backing file | 
|  | 375 | * - any uncertain pages are simply discarded, to be tried again another time | 
|  | 376 | */ | 
|  | 377 | static int cachefiles_read_backing_file(struct cachefiles_object *object, | 
|  | 378 | struct fscache_retrieval *op, | 
|  | 379 | struct list_head *list, | 
|  | 380 | struct pagevec *mark_pvec) | 
|  | 381 | { | 
|  | 382 | struct cachefiles_one_read *monitor = NULL; | 
|  | 383 | struct address_space *bmapping = object->backer->d_inode->i_mapping; | 
|  | 384 | struct pagevec lru_pvec; | 
|  | 385 | struct page *newpage = NULL, *netpage, *_n, *backpage = NULL; | 
|  | 386 | int ret = 0; | 
|  | 387 |  | 
|  | 388 | _enter(""); | 
|  | 389 |  | 
|  | 390 | pagevec_init(&lru_pvec, 0); | 
|  | 391 |  | 
|  | 392 | list_for_each_entry_safe(netpage, _n, list, lru) { | 
|  | 393 | list_del(&netpage->lru); | 
|  | 394 |  | 
|  | 395 | _debug("read back %p{%lu,%d}", | 
|  | 396 | netpage, netpage->index, page_count(netpage)); | 
|  | 397 |  | 
|  | 398 | if (!monitor) { | 
|  | 399 | monitor = kzalloc(sizeof(*monitor), GFP_KERNEL); | 
|  | 400 | if (!monitor) | 
|  | 401 | goto nomem; | 
|  | 402 |  | 
|  | 403 | monitor->op = fscache_get_retrieval(op); | 
|  | 404 | init_waitqueue_func_entry(&monitor->monitor, | 
|  | 405 | cachefiles_read_waiter); | 
|  | 406 | } | 
|  | 407 |  | 
|  | 408 | for (;;) { | 
|  | 409 | backpage = find_get_page(bmapping, netpage->index); | 
|  | 410 | if (backpage) | 
|  | 411 | goto backing_page_already_present; | 
|  | 412 |  | 
|  | 413 | if (!newpage) { | 
|  | 414 | newpage = page_cache_alloc_cold(bmapping); | 
|  | 415 | if (!newpage) | 
|  | 416 | goto nomem; | 
|  | 417 | } | 
|  | 418 |  | 
|  | 419 | ret = add_to_page_cache(newpage, bmapping, | 
|  | 420 | netpage->index, GFP_KERNEL); | 
|  | 421 | if (ret == 0) | 
|  | 422 | goto installed_new_backing_page; | 
|  | 423 | if (ret != -EEXIST) | 
|  | 424 | goto nomem; | 
|  | 425 | } | 
|  | 426 |  | 
|  | 427 | /* we've installed a new backing page, so now we need to add it | 
|  | 428 | * to the LRU list and start it reading */ | 
|  | 429 | installed_new_backing_page: | 
|  | 430 | _debug("- new %p", newpage); | 
|  | 431 |  | 
|  | 432 | backpage = newpage; | 
|  | 433 | newpage = NULL; | 
|  | 434 |  | 
|  | 435 | page_cache_get(backpage); | 
|  | 436 | if (!pagevec_add(&lru_pvec, backpage)) | 
|  | 437 | __pagevec_lru_add_file(&lru_pvec); | 
|  | 438 |  | 
|  | 439 | reread_backing_page: | 
|  | 440 | ret = bmapping->a_ops->readpage(NULL, backpage); | 
|  | 441 | if (ret < 0) | 
|  | 442 | goto read_error; | 
|  | 443 |  | 
|  | 444 | /* add the netfs page to the pagecache and LRU, and set the | 
|  | 445 | * monitor to transfer the data across */ | 
|  | 446 | monitor_backing_page: | 
|  | 447 | _debug("- monitor add"); | 
|  | 448 |  | 
|  | 449 | ret = add_to_page_cache(netpage, op->mapping, netpage->index, | 
|  | 450 | GFP_KERNEL); | 
|  | 451 | if (ret < 0) { | 
|  | 452 | if (ret == -EEXIST) { | 
|  | 453 | page_cache_release(netpage); | 
|  | 454 | continue; | 
|  | 455 | } | 
|  | 456 | goto nomem; | 
|  | 457 | } | 
|  | 458 |  | 
|  | 459 | page_cache_get(netpage); | 
|  | 460 | if (!pagevec_add(&lru_pvec, netpage)) | 
|  | 461 | __pagevec_lru_add_file(&lru_pvec); | 
|  | 462 |  | 
|  | 463 | /* install a monitor */ | 
|  | 464 | page_cache_get(netpage); | 
|  | 465 | monitor->netfs_page = netpage; | 
|  | 466 |  | 
|  | 467 | page_cache_get(backpage); | 
|  | 468 | monitor->back_page = backpage; | 
|  | 469 | monitor->monitor.private = backpage; | 
|  | 470 | add_page_wait_queue(backpage, &monitor->monitor); | 
|  | 471 | monitor = NULL; | 
|  | 472 |  | 
|  | 473 | /* but the page may have been read before the monitor was | 
|  | 474 | * installed, so the monitor may miss the event - so we have to | 
|  | 475 | * ensure that we do get one in such a case */ | 
|  | 476 | if (trylock_page(backpage)) { | 
|  | 477 | _debug("2unlock %p {%lx}", backpage, backpage->flags); | 
|  | 478 | unlock_page(backpage); | 
|  | 479 | } | 
|  | 480 |  | 
|  | 481 | page_cache_release(backpage); | 
|  | 482 | backpage = NULL; | 
|  | 483 |  | 
|  | 484 | page_cache_release(netpage); | 
|  | 485 | netpage = NULL; | 
|  | 486 | continue; | 
|  | 487 |  | 
|  | 488 | /* if the backing page is already present, it can be in one of | 
|  | 489 | * three states: read in progress, read failed or read okay */ | 
|  | 490 | backing_page_already_present: | 
|  | 491 | _debug("- present %p", backpage); | 
|  | 492 |  | 
|  | 493 | if (PageError(backpage)) | 
|  | 494 | goto io_error; | 
|  | 495 |  | 
|  | 496 | if (PageUptodate(backpage)) | 
|  | 497 | goto backing_page_already_uptodate; | 
|  | 498 |  | 
|  | 499 | _debug("- not ready %p{%lx}", backpage, backpage->flags); | 
|  | 500 |  | 
|  | 501 | if (!trylock_page(backpage)) | 
|  | 502 | goto monitor_backing_page; | 
|  | 503 |  | 
|  | 504 | if (PageError(backpage)) { | 
|  | 505 | _debug("error %lx", backpage->flags); | 
|  | 506 | unlock_page(backpage); | 
|  | 507 | goto io_error; | 
|  | 508 | } | 
|  | 509 |  | 
|  | 510 | if (PageUptodate(backpage)) | 
|  | 511 | goto backing_page_already_uptodate_unlock; | 
|  | 512 |  | 
|  | 513 | /* we've locked a page that's neither up to date nor erroneous, | 
|  | 514 | * so we need to attempt to read it again */ | 
|  | 515 | goto reread_backing_page; | 
|  | 516 |  | 
|  | 517 | /* the backing page is already up to date, attach the netfs | 
|  | 518 | * page to the pagecache and LRU and copy the data across */ | 
|  | 519 | backing_page_already_uptodate_unlock: | 
|  | 520 | _debug("uptodate %lx", backpage->flags); | 
|  | 521 | unlock_page(backpage); | 
|  | 522 | backing_page_already_uptodate: | 
|  | 523 | _debug("- uptodate"); | 
|  | 524 |  | 
|  | 525 | ret = add_to_page_cache(netpage, op->mapping, netpage->index, | 
|  | 526 | GFP_KERNEL); | 
|  | 527 | if (ret < 0) { | 
|  | 528 | if (ret == -EEXIST) { | 
|  | 529 | page_cache_release(netpage); | 
|  | 530 | continue; | 
|  | 531 | } | 
|  | 532 | goto nomem; | 
|  | 533 | } | 
|  | 534 |  | 
|  | 535 | copy_highpage(netpage, backpage); | 
|  | 536 |  | 
|  | 537 | page_cache_release(backpage); | 
|  | 538 | backpage = NULL; | 
|  | 539 |  | 
|  | 540 | if (!pagevec_add(mark_pvec, netpage)) | 
|  | 541 | fscache_mark_pages_cached(op, mark_pvec); | 
|  | 542 |  | 
|  | 543 | page_cache_get(netpage); | 
|  | 544 | if (!pagevec_add(&lru_pvec, netpage)) | 
|  | 545 | __pagevec_lru_add_file(&lru_pvec); | 
|  | 546 |  | 
|  | 547 | fscache_end_io(op, netpage, 0); | 
|  | 548 | page_cache_release(netpage); | 
|  | 549 | netpage = NULL; | 
|  | 550 | continue; | 
|  | 551 | } | 
|  | 552 |  | 
|  | 553 | netpage = NULL; | 
|  | 554 |  | 
|  | 555 | _debug("out"); | 
|  | 556 |  | 
|  | 557 | out: | 
|  | 558 | /* tidy up */ | 
|  | 559 | pagevec_lru_add_file(&lru_pvec); | 
|  | 560 |  | 
|  | 561 | if (newpage) | 
|  | 562 | page_cache_release(newpage); | 
|  | 563 | if (netpage) | 
|  | 564 | page_cache_release(netpage); | 
|  | 565 | if (backpage) | 
|  | 566 | page_cache_release(backpage); | 
|  | 567 | if (monitor) { | 
|  | 568 | fscache_put_retrieval(op); | 
|  | 569 | kfree(monitor); | 
|  | 570 | } | 
|  | 571 |  | 
|  | 572 | list_for_each_entry_safe(netpage, _n, list, lru) { | 
|  | 573 | list_del(&netpage->lru); | 
|  | 574 | page_cache_release(netpage); | 
|  | 575 | } | 
|  | 576 |  | 
|  | 577 | _leave(" = %d", ret); | 
|  | 578 | return ret; | 
|  | 579 |  | 
|  | 580 | nomem: | 
|  | 581 | _debug("nomem"); | 
|  | 582 | ret = -ENOMEM; | 
|  | 583 | goto out; | 
|  | 584 |  | 
|  | 585 | read_error: | 
|  | 586 | _debug("read error %d", ret); | 
|  | 587 | if (ret == -ENOMEM) | 
|  | 588 | goto out; | 
|  | 589 | io_error: | 
|  | 590 | cachefiles_io_error_obj(object, "Page read error on backing file"); | 
|  | 591 | ret = -ENOBUFS; | 
|  | 592 | goto out; | 
|  | 593 | } | 
|  | 594 |  | 
|  | 595 | /* | 
|  | 596 | * read a list of pages from the cache or allocate blocks in which to store | 
|  | 597 | * them | 
|  | 598 | */ | 
|  | 599 | int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op, | 
|  | 600 | struct list_head *pages, | 
|  | 601 | unsigned *nr_pages, | 
|  | 602 | gfp_t gfp) | 
|  | 603 | { | 
|  | 604 | struct cachefiles_object *object; | 
|  | 605 | struct cachefiles_cache *cache; | 
|  | 606 | struct list_head backpages; | 
|  | 607 | struct pagevec pagevec; | 
|  | 608 | struct inode *inode; | 
|  | 609 | struct page *page, *_n; | 
|  | 610 | unsigned shift, nrbackpages; | 
|  | 611 | int ret, ret2, space; | 
|  | 612 |  | 
|  | 613 | object = container_of(op->op.object, | 
|  | 614 | struct cachefiles_object, fscache); | 
|  | 615 | cache = container_of(object->fscache.cache, | 
|  | 616 | struct cachefiles_cache, cache); | 
|  | 617 |  | 
|  | 618 | _enter("{OBJ%x,%d},,%d,,", | 
|  | 619 | object->fscache.debug_id, atomic_read(&op->op.usage), | 
|  | 620 | *nr_pages); | 
|  | 621 |  | 
|  | 622 | if (!object->backer) | 
|  | 623 | return -ENOBUFS; | 
|  | 624 |  | 
|  | 625 | space = 1; | 
|  | 626 | if (cachefiles_has_space(cache, 0, *nr_pages) < 0) | 
|  | 627 | space = 0; | 
|  | 628 |  | 
|  | 629 | inode = object->backer->d_inode; | 
|  | 630 | ASSERT(S_ISREG(inode->i_mode)); | 
|  | 631 | ASSERT(inode->i_mapping->a_ops->bmap); | 
|  | 632 | ASSERT(inode->i_mapping->a_ops->readpages); | 
|  | 633 |  | 
|  | 634 | /* calculate the shift required to use bmap */ | 
|  | 635 | if (inode->i_sb->s_blocksize > PAGE_SIZE) | 
|  | 636 | return -ENOBUFS; | 
|  | 637 |  | 
|  | 638 | shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits; | 
|  | 639 |  | 
|  | 640 | pagevec_init(&pagevec, 0); | 
|  | 641 |  | 
|  | 642 | op->op.flags = FSCACHE_OP_FAST; | 
|  | 643 | op->op.processor = cachefiles_read_copier; | 
|  | 644 |  | 
|  | 645 | INIT_LIST_HEAD(&backpages); | 
|  | 646 | nrbackpages = 0; | 
|  | 647 |  | 
|  | 648 | ret = space ? -ENODATA : -ENOBUFS; | 
|  | 649 | list_for_each_entry_safe(page, _n, pages, lru) { | 
|  | 650 | sector_t block0, block; | 
|  | 651 |  | 
|  | 652 | /* we assume the absence or presence of the first block is a | 
|  | 653 | * good enough indication for the page as a whole | 
|  | 654 | * - TODO: don't use bmap() for this as it is _not_ actually | 
|  | 655 | *   good enough for this as it doesn't indicate errors, but | 
|  | 656 | *   it's all we've got for the moment | 
|  | 657 | */ | 
|  | 658 | block0 = page->index; | 
|  | 659 | block0 <<= shift; | 
|  | 660 |  | 
|  | 661 | block = inode->i_mapping->a_ops->bmap(inode->i_mapping, | 
|  | 662 | block0); | 
|  | 663 | _debug("%llx -> %llx", | 
|  | 664 | (unsigned long long) block0, | 
|  | 665 | (unsigned long long) block); | 
|  | 666 |  | 
|  | 667 | if (block) { | 
|  | 668 | /* we have data - add it to the list to give to the | 
|  | 669 | * backing fs */ | 
|  | 670 | list_move(&page->lru, &backpages); | 
|  | 671 | (*nr_pages)--; | 
|  | 672 | nrbackpages++; | 
|  | 673 | } else if (space && pagevec_add(&pagevec, page) == 0) { | 
|  | 674 | fscache_mark_pages_cached(op, &pagevec); | 
|  | 675 | ret = -ENODATA; | 
|  | 676 | } | 
|  | 677 | } | 
|  | 678 |  | 
|  | 679 | if (pagevec_count(&pagevec) > 0) | 
|  | 680 | fscache_mark_pages_cached(op, &pagevec); | 
|  | 681 |  | 
|  | 682 | if (list_empty(pages)) | 
|  | 683 | ret = 0; | 
|  | 684 |  | 
|  | 685 | /* submit the apparently valid pages to the backing fs to be read from | 
|  | 686 | * disk */ | 
|  | 687 | if (nrbackpages > 0) { | 
|  | 688 | ret2 = cachefiles_read_backing_file(object, op, &backpages, | 
|  | 689 | &pagevec); | 
|  | 690 | if (ret2 == -ENOMEM || ret2 == -EINTR) | 
|  | 691 | ret = ret2; | 
|  | 692 | } | 
|  | 693 |  | 
|  | 694 | if (pagevec_count(&pagevec) > 0) | 
|  | 695 | fscache_mark_pages_cached(op, &pagevec); | 
|  | 696 |  | 
|  | 697 | _leave(" = %d [nr=%u%s]", | 
|  | 698 | ret, *nr_pages, list_empty(pages) ? " empty" : ""); | 
|  | 699 | return ret; | 
|  | 700 | } | 
|  | 701 |  | 
|  | 702 | /* | 
|  | 703 | * allocate a block in the cache in which to store a page | 
|  | 704 | * - cache withdrawal is prevented by the caller | 
|  | 705 | * - returns -EINTR if interrupted | 
|  | 706 | * - returns -ENOMEM if ran out of memory | 
|  | 707 | * - returns -ENOBUFS if no buffers can be made available | 
|  | 708 | * - returns -ENOBUFS if page is beyond EOF | 
|  | 709 | * - otherwise: | 
|  | 710 | *   - the metadata will be retained | 
|  | 711 | *   - 0 will be returned | 
|  | 712 | */ | 
|  | 713 | int cachefiles_allocate_page(struct fscache_retrieval *op, | 
|  | 714 | struct page *page, | 
|  | 715 | gfp_t gfp) | 
|  | 716 | { | 
|  | 717 | struct cachefiles_object *object; | 
|  | 718 | struct cachefiles_cache *cache; | 
|  | 719 | struct pagevec pagevec; | 
|  | 720 | int ret; | 
|  | 721 |  | 
|  | 722 | object = container_of(op->op.object, | 
|  | 723 | struct cachefiles_object, fscache); | 
|  | 724 | cache = container_of(object->fscache.cache, | 
|  | 725 | struct cachefiles_cache, cache); | 
|  | 726 |  | 
|  | 727 | _enter("%p,{%lx},", object, page->index); | 
|  | 728 |  | 
|  | 729 | ret = cachefiles_has_space(cache, 0, 1); | 
|  | 730 | if (ret == 0) { | 
|  | 731 | pagevec_init(&pagevec, 0); | 
|  | 732 | pagevec_add(&pagevec, page); | 
|  | 733 | fscache_mark_pages_cached(op, &pagevec); | 
|  | 734 | } else { | 
|  | 735 | ret = -ENOBUFS; | 
|  | 736 | } | 
|  | 737 |  | 
|  | 738 | _leave(" = %d", ret); | 
|  | 739 | return ret; | 
|  | 740 | } | 
|  | 741 |  | 
|  | 742 | /* | 
|  | 743 | * allocate blocks in the cache in which to store a set of pages | 
|  | 744 | * - cache withdrawal is prevented by the caller | 
|  | 745 | * - returns -EINTR if interrupted | 
|  | 746 | * - returns -ENOMEM if ran out of memory | 
|  | 747 | * - returns -ENOBUFS if some buffers couldn't be made available | 
|  | 748 | * - returns -ENOBUFS if some pages are beyond EOF | 
|  | 749 | * - otherwise: | 
|  | 750 | *   - -ENODATA will be returned | 
|  | 751 | * - metadata will be retained for any page marked | 
|  | 752 | */ | 
|  | 753 | int cachefiles_allocate_pages(struct fscache_retrieval *op, | 
|  | 754 | struct list_head *pages, | 
|  | 755 | unsigned *nr_pages, | 
|  | 756 | gfp_t gfp) | 
|  | 757 | { | 
|  | 758 | struct cachefiles_object *object; | 
|  | 759 | struct cachefiles_cache *cache; | 
|  | 760 | struct pagevec pagevec; | 
|  | 761 | struct page *page; | 
|  | 762 | int ret; | 
|  | 763 |  | 
|  | 764 | object = container_of(op->op.object, | 
|  | 765 | struct cachefiles_object, fscache); | 
|  | 766 | cache = container_of(object->fscache.cache, | 
|  | 767 | struct cachefiles_cache, cache); | 
|  | 768 |  | 
|  | 769 | _enter("%p,,,%d,", object, *nr_pages); | 
|  | 770 |  | 
|  | 771 | ret = cachefiles_has_space(cache, 0, *nr_pages); | 
|  | 772 | if (ret == 0) { | 
|  | 773 | pagevec_init(&pagevec, 0); | 
|  | 774 |  | 
|  | 775 | list_for_each_entry(page, pages, lru) { | 
|  | 776 | if (pagevec_add(&pagevec, page) == 0) | 
|  | 777 | fscache_mark_pages_cached(op, &pagevec); | 
|  | 778 | } | 
|  | 779 |  | 
|  | 780 | if (pagevec_count(&pagevec) > 0) | 
|  | 781 | fscache_mark_pages_cached(op, &pagevec); | 
|  | 782 | ret = -ENODATA; | 
|  | 783 | } else { | 
|  | 784 | ret = -ENOBUFS; | 
|  | 785 | } | 
|  | 786 |  | 
|  | 787 | _leave(" = %d", ret); | 
|  | 788 | return ret; | 
|  | 789 | } | 
|  | 790 |  | 
|  | 791 | /* | 
|  | 792 | * request a page be stored in the cache | 
|  | 793 | * - cache withdrawal is prevented by the caller | 
|  | 794 | * - this request may be ignored if there's no cache block available, in which | 
|  | 795 | *   case -ENOBUFS will be returned | 
|  | 796 | * - if the op is in progress, 0 will be returned | 
|  | 797 | */ | 
|  | 798 | int cachefiles_write_page(struct fscache_storage *op, struct page *page) | 
|  | 799 | { | 
|  | 800 | struct cachefiles_object *object; | 
|  | 801 | struct cachefiles_cache *cache; | 
|  | 802 | mm_segment_t old_fs; | 
|  | 803 | struct file *file; | 
|  | 804 | loff_t pos; | 
|  | 805 | void *data; | 
|  | 806 | int ret; | 
|  | 807 |  | 
|  | 808 | ASSERT(op != NULL); | 
|  | 809 | ASSERT(page != NULL); | 
|  | 810 |  | 
|  | 811 | object = container_of(op->op.object, | 
|  | 812 | struct cachefiles_object, fscache); | 
|  | 813 |  | 
|  | 814 | _enter("%p,%p{%lx},,,", object, page, page->index); | 
|  | 815 |  | 
|  | 816 | if (!object->backer) { | 
|  | 817 | _leave(" = -ENOBUFS"); | 
|  | 818 | return -ENOBUFS; | 
|  | 819 | } | 
|  | 820 |  | 
|  | 821 | ASSERT(S_ISREG(object->backer->d_inode->i_mode)); | 
|  | 822 |  | 
|  | 823 | cache = container_of(object->fscache.cache, | 
|  | 824 | struct cachefiles_cache, cache); | 
|  | 825 |  | 
|  | 826 | /* write the page to the backing filesystem and let it store it in its | 
|  | 827 | * own time */ | 
|  | 828 | dget(object->backer); | 
|  | 829 | mntget(cache->mnt); | 
|  | 830 | file = dentry_open(object->backer, cache->mnt, O_RDWR, | 
|  | 831 | cache->cache_cred); | 
|  | 832 | if (IS_ERR(file)) { | 
|  | 833 | ret = PTR_ERR(file); | 
|  | 834 | } else { | 
|  | 835 | ret = -EIO; | 
|  | 836 | if (file->f_op->write) { | 
|  | 837 | pos = (loff_t) page->index << PAGE_SHIFT; | 
|  | 838 | data = kmap(page); | 
|  | 839 | old_fs = get_fs(); | 
|  | 840 | set_fs(KERNEL_DS); | 
|  | 841 | ret = file->f_op->write( | 
|  | 842 | file, (const void __user *) data, PAGE_SIZE, | 
|  | 843 | &pos); | 
|  | 844 | set_fs(old_fs); | 
|  | 845 | kunmap(page); | 
|  | 846 | if (ret != PAGE_SIZE) | 
|  | 847 | ret = -EIO; | 
|  | 848 | } | 
|  | 849 | fput(file); | 
|  | 850 | } | 
|  | 851 |  | 
|  | 852 | if (ret < 0) { | 
|  | 853 | if (ret == -EIO) | 
|  | 854 | cachefiles_io_error_obj( | 
|  | 855 | object, "Write page to backing file failed"); | 
|  | 856 | ret = -ENOBUFS; | 
|  | 857 | } | 
|  | 858 |  | 
|  | 859 | _leave(" = %d", ret); | 
|  | 860 | return ret; | 
|  | 861 | } | 
|  | 862 |  | 
|  | 863 | /* | 
|  | 864 | * detach a backing block from a page | 
|  | 865 | * - cache withdrawal is prevented by the caller | 
|  | 866 | */ | 
|  | 867 | void cachefiles_uncache_page(struct fscache_object *_object, struct page *page) | 
|  | 868 | { | 
|  | 869 | struct cachefiles_object *object; | 
|  | 870 | struct cachefiles_cache *cache; | 
|  | 871 |  | 
|  | 872 | object = container_of(_object, struct cachefiles_object, fscache); | 
|  | 873 | cache = container_of(object->fscache.cache, | 
|  | 874 | struct cachefiles_cache, cache); | 
|  | 875 |  | 
|  | 876 | _enter("%p,{%lu}", object, page->index); | 
|  | 877 |  | 
|  | 878 | spin_unlock(&object->fscache.cookie->lock); | 
|  | 879 | } |