1// SPDX-License-Identifier: GPL-2.0-only 2/* 3 * linux/fs/nfs/write.c 4 * 5 * Write file data over NFS. 6 * 7 * Copyright (C) 1996, 1997, Olaf Kirch <okir@monad.swb.de> 8 */ 9 10#include <linux/types.h> 11#include <linux/slab.h> 12#include <linux/mm.h> 13#include <linux/pagemap.h> 14#include <linux/file.h> 15#include <linux/writeback.h> 16#include <linux/swap.h> 17#include <linux/migrate.h> 18 19#include <linux/sunrpc/clnt.h> 20#include <linux/nfs_fs.h> 21#include <linux/nfs_mount.h> 22#include <linux/nfs_page.h> 23#include <linux/backing-dev.h> 24#include <linux/export.h> 25#include <linux/freezer.h> 26#include <linux/wait.h> 27#include <linux/iversion.h> 28#include <linux/filelock.h> 29 30#include <linux/uaccess.h> 31#include <linux/sched/mm.h> 32 33#include "delegation.h" 34#include "internal.h" 35#include "iostat.h" 36#include "nfs4_fs.h" 37#include "fscache.h" 38#include "pnfs.h" 39 40#include "nfstrace.h" 41 42#define NFSDBG_FACILITY NFSDBG_PAGECACHE 43 44#define MIN_POOL_WRITE (32) 45#define MIN_POOL_COMMIT (4) 46 47struct nfs_io_completion { 48 void (*complete)(void *data); 49 void *data; 50 struct kref refcount; 51}; 52 53/* 54 * Local function declarations 55 */ 56static void nfs_redirty_request(struct nfs_page *req); 57static const struct rpc_call_ops nfs_commit_ops; 58static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops; 59static const struct nfs_commit_completion_ops nfs_commit_completion_ops; 60static const struct nfs_rw_ops nfs_rw_write_ops; 61static void nfs_inode_remove_request(struct nfs_page *req); 62static void nfs_clear_request_commit(struct nfs_commit_info *cinfo, 63 struct nfs_page *req); 64static void nfs_init_cinfo_from_inode(struct nfs_commit_info *cinfo, 65 struct inode *inode); 66static struct nfs_page * 67nfs_page_search_commits_for_head_request_locked(struct nfs_inode *nfsi, 68 struct folio *folio); 69 70static struct kmem_cache *nfs_wdata_cachep; 71static mempool_t *nfs_wdata_mempool; 72static struct kmem_cache *nfs_cdata_cachep; 73static mempool_t *nfs_commit_mempool; 74 75struct nfs_commit_data *nfs_commitdata_alloc(void) 76{ 77 struct nfs_commit_data *p; 78 79 p = kmem_cache_zalloc(nfs_cdata_cachep, nfs_io_gfp_mask()); 80 if (!p) { 81 p = mempool_alloc(nfs_commit_mempool, GFP_NOWAIT); 82 if (!p) 83 return NULL; 84 memset(p, 0, sizeof(*p)); 85 } 86 INIT_LIST_HEAD(&p->pages); 87 return p; 88} 89EXPORT_SYMBOL_GPL(nfs_commitdata_alloc); 90 91void nfs_commit_free(struct nfs_commit_data *p) 92{ 93 mempool_free(p, nfs_commit_mempool); 94} 95EXPORT_SYMBOL_GPL(nfs_commit_free); 96 97static struct nfs_pgio_header *nfs_writehdr_alloc(void) 98{ 99 struct nfs_pgio_header *p; 100 101 p = kmem_cache_zalloc(nfs_wdata_cachep, nfs_io_gfp_mask()); 102 if (!p) { 103 p = mempool_alloc(nfs_wdata_mempool, GFP_NOWAIT); 104 if (!p) 105 return NULL; 106 memset(p, 0, sizeof(*p)); 107 } 108 p->rw_mode = FMODE_WRITE; 109 return p; 110} 111 112static void nfs_writehdr_free(struct nfs_pgio_header *hdr) 113{ 114 mempool_free(hdr, nfs_wdata_mempool); 115} 116 117static struct nfs_io_completion *nfs_io_completion_alloc(gfp_t gfp_flags) 118{ 119 return kmalloc(sizeof(struct nfs_io_completion), gfp_flags); 120} 121 122static void nfs_io_completion_init(struct nfs_io_completion *ioc, 123 void (*complete)(void *), void *data) 124{ 125 ioc->complete = complete; 126 ioc->data = data; 127 kref_init(&ioc->refcount); 128} 129 130static void nfs_io_completion_release(struct kref *kref) 131{ 132 struct nfs_io_completion *ioc = container_of(kref, 133 struct nfs_io_completion, refcount); 134 ioc->complete(ioc->data); 135 kfree(ioc); 136} 137 138static void nfs_io_completion_get(struct nfs_io_completion *ioc) 139{ 140 if (ioc != NULL) 141 kref_get(&ioc->refcount); 142} 143 144static void nfs_io_completion_put(struct nfs_io_completion *ioc) 145{ 146 if (ioc != NULL) 147 kref_put(&ioc->refcount, nfs_io_completion_release); 148} 149 150static void 151nfs_page_set_inode_ref(struct nfs_page *req, struct inode *inode) 152{ 153 if (!test_and_set_bit(PG_INODE_REF, &req->wb_flags)) { 154 kref_get(&req->wb_kref); 155 atomic_long_inc(&NFS_I(inode)->nrequests); 156 } 157} 158 159static int 160nfs_cancel_remove_inode(struct nfs_page *req, struct inode *inode) 161{ 162 int ret; 163 164 if (!test_bit(PG_REMOVE, &req->wb_flags)) 165 return 0; 166 ret = nfs_page_group_lock(req); 167 if (ret) 168 return ret; 169 if (test_and_clear_bit(PG_REMOVE, &req->wb_flags)) 170 nfs_page_set_inode_ref(req, inode); 171 nfs_page_group_unlock(req); 172 return 0; 173} 174 175static struct nfs_page *nfs_folio_private_request(struct folio *folio) 176{ 177 return folio_get_private(folio); 178} 179 180/** 181 * nfs_folio_find_private_request - find head request associated with a folio 182 * @folio: pointer to folio 183 * 184 * must be called while holding the inode lock. 185 * 186 * returns matching head request with reference held, or NULL if not found. 187 */ 188static struct nfs_page *nfs_folio_find_private_request(struct folio *folio) 189{ 190 struct address_space *mapping = folio_file_mapping(folio); 191 struct nfs_page *req; 192 193 if (!folio_test_private(folio)) 194 return NULL; 195 spin_lock(&mapping->private_lock); 196 req = nfs_folio_private_request(folio); 197 if (req) { 198 WARN_ON_ONCE(req->wb_head != req); 199 kref_get(&req->wb_kref); 200 } 201 spin_unlock(&mapping->private_lock); 202 return req; 203} 204 205static struct nfs_page *nfs_folio_find_swap_request(struct folio *folio) 206{ 207 struct inode *inode = folio_file_mapping(folio)->host; 208 struct nfs_inode *nfsi = NFS_I(inode); 209 struct nfs_page *req = NULL; 210 if (!folio_test_swapcache(folio)) 211 return NULL; 212 mutex_lock(&nfsi->commit_mutex); 213 if (folio_test_swapcache(folio)) { 214 req = nfs_page_search_commits_for_head_request_locked(nfsi, 215 folio); 216 if (req) { 217 WARN_ON_ONCE(req->wb_head != req); 218 kref_get(&req->wb_kref); 219 } 220 } 221 mutex_unlock(&nfsi->commit_mutex); 222 return req; 223} 224 225/** 226 * nfs_folio_find_head_request - find head request associated with a folio 227 * @folio: pointer to folio 228 * 229 * returns matching head request with reference held, or NULL if not found. 230 */ 231static struct nfs_page *nfs_folio_find_head_request(struct folio *folio) 232{ 233 struct nfs_page *req; 234 235 req = nfs_folio_find_private_request(folio); 236 if (!req) 237 req = nfs_folio_find_swap_request(folio); 238 return req; 239} 240 241static struct nfs_page *nfs_folio_find_and_lock_request(struct folio *folio) 242{ 243 struct inode *inode = folio_file_mapping(folio)->host; 244 struct nfs_page *req, *head; 245 int ret; 246 247 for (;;) { 248 req = nfs_folio_find_head_request(folio); 249 if (!req) 250 return req; 251 head = nfs_page_group_lock_head(req); 252 if (head != req) 253 nfs_release_request(req); 254 if (IS_ERR(head)) 255 return head; 256 ret = nfs_cancel_remove_inode(head, inode); 257 if (ret < 0) { 258 nfs_unlock_and_release_request(head); 259 return ERR_PTR(ret); 260 } 261 /* Ensure that nobody removed the request before we locked it */ 262 if (head == nfs_folio_private_request(folio)) 263 break; 264 if (folio_test_swapcache(folio)) 265 break; 266 nfs_unlock_and_release_request(head); 267 } 268 return head; 269} 270 271/* Adjust the file length if we're writing beyond the end */ 272static void nfs_grow_file(struct folio *folio, unsigned int offset, 273 unsigned int count) 274{ 275 struct inode *inode = folio_file_mapping(folio)->host; 276 loff_t end, i_size; 277 pgoff_t end_index; 278 279 spin_lock(&inode->i_lock); 280 i_size = i_size_read(inode); 281 end_index = ((i_size - 1) >> folio_shift(folio)) << folio_order(folio); 282 if (i_size > 0 && folio_index(folio) < end_index) 283 goto out; 284 end = folio_file_pos(folio) + (loff_t)offset + (loff_t)count; 285 if (i_size >= end) 286 goto out; 287 trace_nfs_size_grow(inode, end); 288 i_size_write(inode, end); 289 NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_SIZE; 290 nfs_inc_stats(inode, NFSIOS_EXTENDWRITE); 291out: 292 spin_unlock(&inode->i_lock); 293 nfs_fscache_invalidate(inode, 0); 294} 295 296/* A writeback failed: mark the page as bad, and invalidate the page cache */ 297static void nfs_set_pageerror(struct address_space *mapping) 298{ 299 struct inode *inode = mapping->host; 300 301 nfs_zap_mapping(mapping->host, mapping); 302 /* Force file size revalidation */ 303 spin_lock(&inode->i_lock); 304 nfs_set_cache_invalid(inode, NFS_INO_REVAL_FORCED | 305 NFS_INO_INVALID_CHANGE | 306 NFS_INO_INVALID_SIZE); 307 spin_unlock(&inode->i_lock); 308} 309 310static void nfs_mapping_set_error(struct folio *folio, int error) 311{ 312 struct address_space *mapping = folio_file_mapping(folio); 313 314 folio_set_error(folio); 315 filemap_set_wb_err(mapping, error); 316 if (mapping->host) 317 errseq_set(&mapping->host->i_sb->s_wb_err, 318 error == -ENOSPC ? -ENOSPC : -EIO); 319 nfs_set_pageerror(mapping); 320} 321 322/* 323 * nfs_page_group_search_locked 324 * @head - head request of page group 325 * @page_offset - offset into page 326 * 327 * Search page group with head @head to find a request that contains the 328 * page offset @page_offset. 329 * 330 * Returns a pointer to the first matching nfs request, or NULL if no 331 * match is found. 332 * 333 * Must be called with the page group lock held 334 */ 335static struct nfs_page * 336nfs_page_group_search_locked(struct nfs_page *head, unsigned int page_offset) 337{ 338 struct nfs_page *req; 339 340 req = head; 341 do { 342 if (page_offset >= req->wb_pgbase && 343 page_offset < (req->wb_pgbase + req->wb_bytes)) 344 return req; 345 346 req = req->wb_this_page; 347 } while (req != head); 348 349 return NULL; 350} 351 352/* 353 * nfs_page_group_covers_page 354 * @head - head request of page group 355 * 356 * Return true if the page group with head @head covers the whole page, 357 * returns false otherwise 358 */ 359static bool nfs_page_group_covers_page(struct nfs_page *req) 360{ 361 unsigned int len = nfs_folio_length(nfs_page_to_folio(req)); 362 struct nfs_page *tmp; 363 unsigned int pos = 0; 364 365 nfs_page_group_lock(req); 366 367 for (;;) { 368 tmp = nfs_page_group_search_locked(req->wb_head, pos); 369 if (!tmp) 370 break; 371 pos = tmp->wb_pgbase + tmp->wb_bytes; 372 } 373 374 nfs_page_group_unlock(req); 375 return pos >= len; 376} 377 378/* We can set the PG_uptodate flag if we see that a write request 379 * covers the full page. 380 */ 381static void nfs_mark_uptodate(struct nfs_page *req) 382{ 383 struct folio *folio = nfs_page_to_folio(req); 384 385 if (folio_test_uptodate(folio)) 386 return; 387 if (!nfs_page_group_covers_page(req)) 388 return; 389 folio_mark_uptodate(folio); 390} 391 392static int wb_priority(struct writeback_control *wbc) 393{ 394 int ret = 0; 395 396 if (wbc->sync_mode == WB_SYNC_ALL) 397 ret = FLUSH_COND_STABLE; 398 return ret; 399} 400 401/* 402 * NFS congestion control 403 */ 404 405int nfs_congestion_kb; 406 407#define NFS_CONGESTION_ON_THRESH (nfs_congestion_kb >> (PAGE_SHIFT-10)) 408#define NFS_CONGESTION_OFF_THRESH \ 409 (NFS_CONGESTION_ON_THRESH - (NFS_CONGESTION_ON_THRESH >> 2)) 410 411static void nfs_folio_set_writeback(struct folio *folio) 412{ 413 struct nfs_server *nfss = NFS_SERVER(folio_file_mapping(folio)->host); 414 415 folio_start_writeback(folio); 416 if (atomic_long_inc_return(&nfss->writeback) > NFS_CONGESTION_ON_THRESH) 417 nfss->write_congested = 1; 418} 419 420static void nfs_folio_end_writeback(struct folio *folio) 421{ 422 struct nfs_server *nfss = NFS_SERVER(folio_file_mapping(folio)->host); 423 424 folio_end_writeback(folio); 425 if (atomic_long_dec_return(&nfss->writeback) < 426 NFS_CONGESTION_OFF_THRESH) 427 nfss->write_congested = 0; 428} 429 430static void nfs_page_end_writeback(struct nfs_page *req) 431{ 432 if (nfs_page_group_sync_on_bit(req, PG_WB_END)) { 433 nfs_unlock_request(req); 434 nfs_folio_end_writeback(nfs_page_to_folio(req)); 435 } else 436 nfs_unlock_request(req); 437} 438 439/* 440 * nfs_destroy_unlinked_subrequests - destroy recently unlinked subrequests 441 * 442 * @destroy_list - request list (using wb_this_page) terminated by @old_head 443 * @old_head - the old head of the list 444 * 445 * All subrequests must be locked and removed from all lists, so at this point 446 * they are only "active" in this function, and possibly in nfs_wait_on_request 447 * with a reference held by some other context. 448 */ 449static void 450nfs_destroy_unlinked_subrequests(struct nfs_page *destroy_list, 451 struct nfs_page *old_head, 452 struct inode *inode) 453{ 454 while (destroy_list) { 455 struct nfs_page *subreq = destroy_list; 456 457 destroy_list = (subreq->wb_this_page == old_head) ? 458 NULL : subreq->wb_this_page; 459 460 /* Note: lock subreq in order to change subreq->wb_head */ 461 nfs_page_set_headlock(subreq); 462 WARN_ON_ONCE(old_head != subreq->wb_head); 463 464 /* make sure old group is not used */ 465 subreq->wb_this_page = subreq; 466 subreq->wb_head = subreq; 467 468 clear_bit(PG_REMOVE, &subreq->wb_flags); 469 470 /* Note: races with nfs_page_group_destroy() */ 471 if (!kref_read(&subreq->wb_kref)) { 472 /* Check if we raced with nfs_page_group_destroy() */ 473 if (test_and_clear_bit(PG_TEARDOWN, &subreq->wb_flags)) { 474 nfs_page_clear_headlock(subreq); 475 nfs_free_request(subreq); 476 } else 477 nfs_page_clear_headlock(subreq); 478 continue; 479 } 480 nfs_page_clear_headlock(subreq); 481 482 nfs_release_request(old_head); 483 484 if (test_and_clear_bit(PG_INODE_REF, &subreq->wb_flags)) { 485 nfs_release_request(subreq); 486 atomic_long_dec(&NFS_I(inode)->nrequests); 487 } 488 489 /* subreq is now totally disconnected from page group or any 490 * write / commit lists. last chance to wake any waiters */ 491 nfs_unlock_and_release_request(subreq); 492 } 493} 494 495/* 496 * nfs_join_page_group - destroy subrequests of the head req 497 * @head: the page used to lookup the "page group" of nfs_page structures 498 * @inode: Inode to which the request belongs. 499 * 500 * This function joins all sub requests to the head request by first 501 * locking all requests in the group, cancelling any pending operations 502 * and finally updating the head request to cover the whole range covered by 503 * the (former) group. All subrequests are removed from any write or commit 504 * lists, unlinked from the group and destroyed. 505 */ 506void nfs_join_page_group(struct nfs_page *head, struct nfs_commit_info *cinfo, 507 struct inode *inode) 508{ 509 struct nfs_page *subreq; 510 struct nfs_page *destroy_list = NULL; 511 unsigned int pgbase, off, bytes; 512 513 pgbase = head->wb_pgbase; 514 bytes = head->wb_bytes; 515 off = head->wb_offset; 516 for (subreq = head->wb_this_page; subreq != head; 517 subreq = subreq->wb_this_page) { 518 /* Subrequests should always form a contiguous range */ 519 if (pgbase > subreq->wb_pgbase) { 520 off -= pgbase - subreq->wb_pgbase; 521 bytes += pgbase - subreq->wb_pgbase; 522 pgbase = subreq->wb_pgbase; 523 } 524 bytes = max(subreq->wb_pgbase + subreq->wb_bytes 525 - pgbase, bytes); 526 } 527 528 /* Set the head request's range to cover the former page group */ 529 head->wb_pgbase = pgbase; 530 head->wb_bytes = bytes; 531 head->wb_offset = off; 532 533 /* Now that all requests are locked, make sure they aren't on any list. 534 * Commit list removal accounting is done after locks are dropped */ 535 subreq = head; 536 do { 537 nfs_clear_request_commit(cinfo, subreq); 538 subreq = subreq->wb_this_page; 539 } while (subreq != head); 540 541 /* unlink subrequests from head, destroy them later */ 542 if (head->wb_this_page != head) { 543 /* destroy list will be terminated by head */ 544 destroy_list = head->wb_this_page; 545 head->wb_this_page = head; 546 } 547 548 nfs_destroy_unlinked_subrequests(destroy_list, head, inode); 549} 550 551/* 552 * nfs_lock_and_join_requests - join all subreqs to the head req 553 * @folio: the folio used to lookup the "page group" of nfs_page structures 554 * 555 * This function joins all sub requests to the head request by first 556 * locking all requests in the group, cancelling any pending operations 557 * and finally updating the head request to cover the whole range covered by 558 * the (former) group. All subrequests are removed from any write or commit 559 * lists, unlinked from the group and destroyed. 560 * 561 * Returns a locked, referenced pointer to the head request - which after 562 * this call is guaranteed to be the only request associated with the page. 563 * Returns NULL if no requests are found for @folio, or a ERR_PTR if an 564 * error was encountered. 565 */ 566static struct nfs_page *nfs_lock_and_join_requests(struct folio *folio) 567{ 568 struct inode *inode = folio_file_mapping(folio)->host; 569 struct nfs_page *head; 570 struct nfs_commit_info cinfo; 571 int ret; 572 573 nfs_init_cinfo_from_inode(&cinfo, inode); 574 /* 575 * A reference is taken only on the head request which acts as a 576 * reference to the whole page group - the group will not be destroyed 577 * until the head reference is released. 578 */ 579 head = nfs_folio_find_and_lock_request(folio); 580 if (IS_ERR_OR_NULL(head)) 581 return head; 582 583 /* lock each request in the page group */ 584 ret = nfs_page_group_lock_subrequests(head); 585 if (ret < 0) { 586 nfs_unlock_and_release_request(head); 587 return ERR_PTR(ret); 588 } 589 590 nfs_join_page_group(head, &cinfo, inode); 591 592 return head; 593} 594 595static void nfs_write_error(struct nfs_page *req, int error) 596{ 597 trace_nfs_write_error(nfs_page_to_inode(req), req, error); 598 nfs_mapping_set_error(nfs_page_to_folio(req), error); 599 nfs_inode_remove_request(req); 600 nfs_page_end_writeback(req); 601 nfs_release_request(req); 602} 603 604/* 605 * Find an associated nfs write request, and prepare to flush it out 606 * May return an error if the user signalled nfs_wait_on_request(). 607 */ 608static int nfs_page_async_flush(struct folio *folio, 609 struct writeback_control *wbc, 610 struct nfs_pageio_descriptor *pgio) 611{ 612 struct nfs_page *req; 613 int ret = 0; 614 615 req = nfs_lock_and_join_requests(folio); 616 if (!req) 617 goto out; 618 ret = PTR_ERR(req); 619 if (IS_ERR(req)) 620 goto out; 621 622 nfs_folio_set_writeback(folio); 623 WARN_ON_ONCE(test_bit(PG_CLEAN, &req->wb_flags)); 624 625 /* If there is a fatal error that covers this write, just exit */ 626 ret = pgio->pg_error; 627 if (nfs_error_is_fatal_on_server(ret)) 628 goto out_launder; 629 630 ret = 0; 631 if (!nfs_pageio_add_request(pgio, req)) { 632 ret = pgio->pg_error; 633 /* 634 * Remove the problematic req upon fatal errors on the server 635 */ 636 if (nfs_error_is_fatal_on_server(ret)) 637 goto out_launder; 638 if (wbc->sync_mode == WB_SYNC_NONE) 639 ret = AOP_WRITEPAGE_ACTIVATE; 640 folio_redirty_for_writepage(wbc, folio); 641 nfs_redirty_request(req); 642 pgio->pg_error = 0; 643 } else 644 nfs_add_stats(folio_file_mapping(folio)->host, 645 NFSIOS_WRITEPAGES, 1); 646out: 647 return ret; 648out_launder: 649 nfs_write_error(req, ret); 650 return 0; 651} 652 653static int nfs_do_writepage(struct folio *folio, struct writeback_control *wbc, 654 struct nfs_pageio_descriptor *pgio) 655{ 656 nfs_pageio_cond_complete(pgio, folio_index(folio)); 657 return nfs_page_async_flush(folio, wbc, pgio); 658} 659 660/* 661 * Write an mmapped page to the server. 662 */ 663static int nfs_writepage_locked(struct folio *folio, 664 struct writeback_control *wbc) 665{ 666 struct nfs_pageio_descriptor pgio; 667 struct inode *inode = folio_file_mapping(folio)->host; 668 int err; 669 670 if (wbc->sync_mode == WB_SYNC_NONE && 671 NFS_SERVER(inode)->write_congested) { 672 folio_redirty_for_writepage(wbc, folio); 673 return AOP_WRITEPAGE_ACTIVATE; 674 } 675 676 nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE); 677 nfs_pageio_init_write(&pgio, inode, 0, false, 678 &nfs_async_write_completion_ops); 679 err = nfs_do_writepage(folio, wbc, &pgio); 680 pgio.pg_error = 0; 681 nfs_pageio_complete(&pgio); 682 return err; 683} 684 685int nfs_writepage(struct page *page, struct writeback_control *wbc) 686{ 687 struct folio *folio = page_folio(page); 688 int ret; 689 690 ret = nfs_writepage_locked(folio, wbc); 691 if (ret != AOP_WRITEPAGE_ACTIVATE) 692 unlock_page(page); 693 return ret; 694} 695 696static int nfs_writepages_callback(struct folio *folio, 697 struct writeback_control *wbc, void *data) 698{ 699 int ret; 700 701 ret = nfs_do_writepage(folio, wbc, data); 702 if (ret != AOP_WRITEPAGE_ACTIVATE) 703 folio_unlock(folio); 704 return ret; 705} 706 707static void nfs_io_completion_commit(void *inode) 708{ 709 nfs_commit_inode(inode, 0); 710} 711 712int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc) 713{ 714 struct inode *inode = mapping->host; 715 struct nfs_pageio_descriptor pgio; 716 struct nfs_io_completion *ioc = NULL; 717 unsigned int mntflags = NFS_SERVER(inode)->flags; 718 int priority = 0; 719 int err; 720 721 if (wbc->sync_mode == WB_SYNC_NONE && 722 NFS_SERVER(inode)->write_congested) 723 return 0; 724 725 nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES); 726 727 if (!(mntflags & NFS_MOUNT_WRITE_EAGER) || wbc->for_kupdate || 728 wbc->for_background || wbc->for_sync || wbc->for_reclaim) { 729 ioc = nfs_io_completion_alloc(GFP_KERNEL); 730 if (ioc) 731 nfs_io_completion_init(ioc, nfs_io_completion_commit, 732 inode); 733 priority = wb_priority(wbc); 734 } 735 736 do { 737 nfs_pageio_init_write(&pgio, inode, priority, false, 738 &nfs_async_write_completion_ops); 739 pgio.pg_io_completion = ioc; 740 err = write_cache_pages(mapping, wbc, nfs_writepages_callback, 741 &pgio); 742 pgio.pg_error = 0; 743 nfs_pageio_complete(&pgio); 744 } while (err < 0 && !nfs_error_is_fatal(err)); 745 nfs_io_completion_put(ioc); 746 747 if (err < 0) 748 goto out_err; 749 return 0; 750out_err: 751 return err; 752} 753 754/* 755 * Insert a write request into an inode 756 */ 757static void nfs_inode_add_request(struct nfs_page *req) 758{ 759 struct folio *folio = nfs_page_to_folio(req); 760 struct address_space *mapping = folio_file_mapping(folio); 761 struct nfs_inode *nfsi = NFS_I(mapping->host); 762 763 WARN_ON_ONCE(req->wb_this_page != req); 764 765 /* Lock the request! */ 766 nfs_lock_request(req); 767 768 /* 769 * Swap-space should not get truncated. Hence no need to plug the race 770 * with invalidate/truncate. 771 */ 772 spin_lock(&mapping->private_lock); 773 if (likely(!folio_test_swapcache(folio))) { 774 set_bit(PG_MAPPED, &req->wb_flags); 775 folio_set_private(folio); 776 folio->private = req; 777 } 778 spin_unlock(&mapping->private_lock); 779 atomic_long_inc(&nfsi->nrequests); 780 /* this a head request for a page group - mark it as having an 781 * extra reference so sub groups can follow suit. 782 * This flag also informs pgio layer when to bump nrequests when 783 * adding subrequests. */ 784 WARN_ON(test_and_set_bit(PG_INODE_REF, &req->wb_flags)); 785 kref_get(&req->wb_kref); 786} 787 788/* 789 * Remove a write request from an inode 790 */ 791static void nfs_inode_remove_request(struct nfs_page *req) 792{ 793 struct nfs_inode *nfsi = NFS_I(nfs_page_to_inode(req)); 794 795 if (nfs_page_group_sync_on_bit(req, PG_REMOVE)) { 796 struct folio *folio = nfs_page_to_folio(req->wb_head); 797 struct address_space *mapping = folio_file_mapping(folio); 798 799 spin_lock(&mapping->private_lock); 800 if (likely(folio && !folio_test_swapcache(folio))) { 801 folio->private = NULL; 802 folio_clear_private(folio); 803 clear_bit(PG_MAPPED, &req->wb_head->wb_flags); 804 } 805 spin_unlock(&mapping->private_lock); 806 } 807 808 if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags)) { 809 atomic_long_dec(&nfsi->nrequests); 810 nfs_release_request(req); 811 } 812} 813 814static void nfs_mark_request_dirty(struct nfs_page *req) 815{ 816 struct folio *folio = nfs_page_to_folio(req); 817 if (folio) 818 filemap_dirty_folio(folio_mapping(folio), folio); 819} 820 821/* 822 * nfs_page_search_commits_for_head_request_locked 823 * 824 * Search through commit lists on @inode for the head request for @folio. 825 * Must be called while holding the inode (which is cinfo) lock. 826 * 827 * Returns the head request if found, or NULL if not found. 828 */ 829static struct nfs_page * 830nfs_page_search_commits_for_head_request_locked(struct nfs_inode *nfsi, 831 struct folio *folio) 832{ 833 struct nfs_page *freq, *t; 834 struct nfs_commit_info cinfo; 835 struct inode *inode = &nfsi->vfs_inode; 836 837 nfs_init_cinfo_from_inode(&cinfo, inode); 838 839 /* search through pnfs commit lists */ 840 freq = pnfs_search_commit_reqs(inode, &cinfo, folio); 841 if (freq) 842 return freq->wb_head; 843 844 /* Linearly search the commit list for the correct request */ 845 list_for_each_entry_safe(freq, t, &cinfo.mds->list, wb_list) { 846 if (nfs_page_to_folio(freq) == folio) 847 return freq->wb_head; 848 } 849 850 return NULL; 851} 852 853/** 854 * nfs_request_add_commit_list_locked - add request to a commit list 855 * @req: pointer to a struct nfs_page 856 * @dst: commit list head 857 * @cinfo: holds list lock and accounting info 858 * 859 * This sets the PG_CLEAN bit, updates the cinfo count of 860 * number of outstanding requests requiring a commit as well as 861 * the MM page stats. 862 * 863 * The caller must hold NFS_I(cinfo->inode)->commit_mutex, and the 864 * nfs_page lock. 865 */ 866void 867nfs_request_add_commit_list_locked(struct nfs_page *req, struct list_head *dst, 868 struct nfs_commit_info *cinfo) 869{ 870 set_bit(PG_CLEAN, &req->wb_flags); 871 nfs_list_add_request(req, dst); 872 atomic_long_inc(&cinfo->mds->ncommit); 873} 874EXPORT_SYMBOL_GPL(nfs_request_add_commit_list_locked); 875 876/** 877 * nfs_request_add_commit_list - add request to a commit list 878 * @req: pointer to a struct nfs_page 879 * @cinfo: holds list lock and accounting info 880 * 881 * This sets the PG_CLEAN bit, updates the cinfo count of 882 * number of outstanding requests requiring a commit as well as 883 * the MM page stats. 884 * 885 * The caller must _not_ hold the cinfo->lock, but must be 886 * holding the nfs_page lock. 887 */ 888void 889nfs_request_add_commit_list(struct nfs_page *req, struct nfs_commit_info *cinfo) 890{ 891 mutex_lock(&NFS_I(cinfo->inode)->commit_mutex); 892 nfs_request_add_commit_list_locked(req, &cinfo->mds->list, cinfo); 893 mutex_unlock(&NFS_I(cinfo->inode)->commit_mutex); 894 nfs_folio_mark_unstable(nfs_page_to_folio(req), cinfo); 895} 896EXPORT_SYMBOL_GPL(nfs_request_add_commit_list); 897 898/** 899 * nfs_request_remove_commit_list - Remove request from a commit list 900 * @req: pointer to a nfs_page 901 * @cinfo: holds list lock and accounting info 902 * 903 * This clears the PG_CLEAN bit, and updates the cinfo's count of 904 * number of outstanding requests requiring a commit 905 * It does not update the MM page stats. 906 * 907 * The caller _must_ hold the cinfo->lock and the nfs_page lock. 908 */ 909void 910nfs_request_remove_commit_list(struct nfs_page *req, 911 struct nfs_commit_info *cinfo) 912{ 913 if (!test_and_clear_bit(PG_CLEAN, &(req)->wb_flags)) 914 return; 915 nfs_list_remove_request(req); 916 atomic_long_dec(&cinfo->mds->ncommit); 917} 918EXPORT_SYMBOL_GPL(nfs_request_remove_commit_list); 919 920static void nfs_init_cinfo_from_inode(struct nfs_commit_info *cinfo, 921 struct inode *inode) 922{ 923 cinfo->inode = inode; 924 cinfo->mds = &NFS_I(inode)->commit_info; 925 cinfo->ds = pnfs_get_ds_info(inode); 926 cinfo->dreq = NULL; 927 cinfo->completion_ops = &nfs_commit_completion_ops; 928} 929 930void nfs_init_cinfo(struct nfs_commit_info *cinfo, 931 struct inode *inode, 932 struct nfs_direct_req *dreq) 933{ 934 if (dreq) 935 nfs_init_cinfo_from_dreq(cinfo, dreq); 936 else 937 nfs_init_cinfo_from_inode(cinfo, inode); 938} 939EXPORT_SYMBOL_GPL(nfs_init_cinfo); 940 941/* 942 * Add a request to the inode's commit list. 943 */ 944void 945nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg, 946 struct nfs_commit_info *cinfo, u32 ds_commit_idx) 947{ 948 if (pnfs_mark_request_commit(req, lseg, cinfo, ds_commit_idx)) 949 return; 950 nfs_request_add_commit_list(req, cinfo); 951} 952 953static void nfs_folio_clear_commit(struct folio *folio) 954{ 955 if (folio) { 956 long nr = folio_nr_pages(folio); 957 958 node_stat_mod_folio(folio, NR_WRITEBACK, -nr); 959 wb_stat_mod(&inode_to_bdi(folio_file_mapping(folio)->host)->wb, 960 WB_WRITEBACK, -nr); 961 } 962} 963 964/* Called holding the request lock on @req */ 965static void nfs_clear_request_commit(struct nfs_commit_info *cinfo, 966 struct nfs_page *req) 967{ 968 if (test_bit(PG_CLEAN, &req->wb_flags)) { 969 struct nfs_open_context *ctx = nfs_req_openctx(req); 970 struct inode *inode = d_inode(ctx->dentry); 971 972 mutex_lock(&NFS_I(inode)->commit_mutex); 973 if (!pnfs_clear_request_commit(req, cinfo)) { 974 nfs_request_remove_commit_list(req, cinfo); 975 } 976 mutex_unlock(&NFS_I(inode)->commit_mutex); 977 nfs_folio_clear_commit(nfs_page_to_folio(req)); 978 } 979} 980 981int nfs_write_need_commit(struct nfs_pgio_header *hdr) 982{ 983 if (hdr->verf.committed == NFS_DATA_SYNC) 984 return hdr->lseg == NULL; 985 return hdr->verf.committed != NFS_FILE_SYNC; 986} 987 988static void nfs_async_write_init(struct nfs_pgio_header *hdr) 989{ 990 nfs_io_completion_get(hdr->io_completion); 991} 992 993static void nfs_write_completion(struct nfs_pgio_header *hdr) 994{ 995 struct nfs_commit_info cinfo; 996 unsigned long bytes = 0; 997 998 if (test_bit(NFS_IOHDR_REDO, &hdr->flags)) 999 goto out; 1000 nfs_init_cinfo_from_inode(&cinfo, hdr->inode); 1001 while (!list_empty(&hdr->pages)) { 1002 struct nfs_page *req = nfs_list_entry(hdr->pages.next); 1003 1004 bytes += req->wb_bytes; 1005 nfs_list_remove_request(req); 1006 if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && 1007 (hdr->good_bytes < bytes)) { 1008 trace_nfs_comp_error(hdr->inode, req, hdr->error); 1009 nfs_mapping_set_error(nfs_page_to_folio(req), 1010 hdr->error); 1011 goto remove_req; 1012 } 1013 if (nfs_write_need_commit(hdr)) { 1014 /* Reset wb_nio, since the write was successful. */ 1015 req->wb_nio = 0; 1016 memcpy(&req->wb_verf, &hdr->verf.verifier, sizeof(req->wb_verf)); 1017 nfs_mark_request_commit(req, hdr->lseg, &cinfo, 1018 hdr->pgio_mirror_idx); 1019 goto next; 1020 } 1021remove_req: 1022 nfs_inode_remove_request(req); 1023next: 1024 nfs_page_end_writeback(req); 1025 nfs_release_request(req); 1026 } 1027out: 1028 nfs_io_completion_put(hdr->io_completion); 1029 hdr->release(hdr); 1030} 1031 1032unsigned long 1033nfs_reqs_to_commit(struct nfs_commit_info *cinfo) 1034{ 1035 return atomic_long_read(&cinfo->mds->ncommit); 1036} 1037 1038/* NFS_I(cinfo->inode)->commit_mutex held by caller */ 1039int 1040nfs_scan_commit_list(struct list_head *src, struct list_head *dst, 1041 struct nfs_commit_info *cinfo, int max) 1042{ 1043 struct nfs_page *req, *tmp; 1044 int ret = 0; 1045 1046 list_for_each_entry_safe(req, tmp, src, wb_list) { 1047 kref_get(&req->wb_kref); 1048 if (!nfs_lock_request(req)) { 1049 nfs_release_request(req); 1050 continue; 1051 } 1052 nfs_request_remove_commit_list(req, cinfo); 1053 clear_bit(PG_COMMIT_TO_DS, &req->wb_flags); 1054 nfs_list_add_request(req, dst); 1055 ret++; 1056 if ((ret == max) && !cinfo->dreq) 1057 break; 1058 cond_resched(); 1059 } 1060 return ret; 1061} 1062EXPORT_SYMBOL_GPL(nfs_scan_commit_list); 1063 1064/* 1065 * nfs_scan_commit - Scan an inode for commit requests 1066 * @inode: NFS inode to scan 1067 * @dst: mds destination list 1068 * @cinfo: mds and ds lists of reqs ready to commit 1069 * 1070 * Moves requests from the inode's 'commit' request list. 1071 * The requests are *not* checked to ensure that they form a contiguous set. 1072 */ 1073int 1074nfs_scan_commit(struct inode *inode, struct list_head *dst, 1075 struct nfs_commit_info *cinfo) 1076{ 1077 int ret = 0; 1078 1079 if (!atomic_long_read(&cinfo->mds->ncommit)) 1080 return 0; 1081 mutex_lock(&NFS_I(cinfo->inode)->commit_mutex); 1082 if (atomic_long_read(&cinfo->mds->ncommit) > 0) { 1083 const int max = INT_MAX; 1084 1085 ret = nfs_scan_commit_list(&cinfo->mds->list, dst, 1086 cinfo, max); 1087 ret += pnfs_scan_commit_lists(inode, cinfo, max - ret); 1088 } 1089 mutex_unlock(&NFS_I(cinfo->inode)->commit_mutex); 1090 return ret; 1091} 1092 1093/* 1094 * Search for an existing write request, and attempt to update 1095 * it to reflect a new dirty region on a given page. 1096 * 1097 * If the attempt fails, then the existing request is flushed out 1098 * to disk. 1099 */ 1100static struct nfs_page *nfs_try_to_update_request(struct folio *folio, 1101 unsigned int offset, 1102 unsigned int bytes) 1103{ 1104 struct nfs_page *req; 1105 unsigned int rqend; 1106 unsigned int end; 1107 int error; 1108 1109 end = offset + bytes; 1110 1111 req = nfs_lock_and_join_requests(folio); 1112 if (IS_ERR_OR_NULL(req)) 1113 return req; 1114 1115 rqend = req->wb_offset + req->wb_bytes; 1116 /* 1117 * Tell the caller to flush out the request if 1118 * the offsets are non-contiguous. 1119 * Note: nfs_flush_incompatible() will already 1120 * have flushed out requests having wrong owners. 1121 */ 1122 if (offset > rqend || end < req->wb_offset) 1123 goto out_flushme; 1124 1125 /* Okay, the request matches. Update the region */ 1126 if (offset < req->wb_offset) { 1127 req->wb_offset = offset; 1128 req->wb_pgbase = offset; 1129 } 1130 if (end > rqend) 1131 req->wb_bytes = end - req->wb_offset; 1132 else 1133 req->wb_bytes = rqend - req->wb_offset; 1134 req->wb_nio = 0; 1135 return req; 1136out_flushme: 1137 /* 1138 * Note: we mark the request dirty here because 1139 * nfs_lock_and_join_requests() cannot preserve 1140 * commit flags, so we have to replay the write. 1141 */ 1142 nfs_mark_request_dirty(req); 1143 nfs_unlock_and_release_request(req); 1144 error = nfs_wb_folio(folio_file_mapping(folio)->host, folio); 1145 return (error < 0) ? ERR_PTR(error) : NULL; 1146} 1147 1148/* 1149 * Try to update an existing write request, or create one if there is none. 1150 * 1151 * Note: Should always be called with the Page Lock held to prevent races 1152 * if we have to add a new request. Also assumes that the caller has 1153 * already called nfs_flush_incompatible() if necessary. 1154 */ 1155static struct nfs_page *nfs_setup_write_request(struct nfs_open_context *ctx, 1156 struct folio *folio, 1157 unsigned int offset, 1158 unsigned int bytes) 1159{ 1160 struct nfs_page *req; 1161 1162 req = nfs_try_to_update_request(folio, offset, bytes); 1163 if (req != NULL) 1164 goto out; 1165 req = nfs_page_create_from_folio(ctx, folio, offset, bytes); 1166 if (IS_ERR(req)) 1167 goto out; 1168 nfs_inode_add_request(req); 1169out: 1170 return req; 1171} 1172 1173static int nfs_writepage_setup(struct nfs_open_context *ctx, 1174 struct folio *folio, unsigned int offset, 1175 unsigned int count) 1176{ 1177 struct nfs_page *req; 1178 1179 req = nfs_setup_write_request(ctx, folio, offset, count); 1180 if (IS_ERR(req)) 1181 return PTR_ERR(req); 1182 /* Update file length */ 1183 nfs_grow_file(folio, offset, count); 1184 nfs_mark_uptodate(req); 1185 nfs_mark_request_dirty(req); 1186 nfs_unlock_and_release_request(req); 1187 return 0; 1188} 1189 1190int nfs_flush_incompatible(struct file *file, struct folio *folio) 1191{ 1192 struct nfs_open_context *ctx = nfs_file_open_context(file); 1193 struct nfs_lock_context *l_ctx; 1194 struct file_lock_context *flctx = locks_inode_context(file_inode(file)); 1195 struct nfs_page *req; 1196 int do_flush, status; 1197 /* 1198 * Look for a request corresponding to this page. If there 1199 * is one, and it belongs to another file, we flush it out 1200 * before we try to copy anything into the page. Do this 1201 * due to the lack of an ACCESS-type call in NFSv2. 1202 * Also do the same if we find a request from an existing 1203 * dropped page. 1204 */ 1205 do { 1206 req = nfs_folio_find_head_request(folio); 1207 if (req == NULL) 1208 return 0; 1209 l_ctx = req->wb_lock_context; 1210 do_flush = nfs_page_to_folio(req) != folio || 1211 !nfs_match_open_context(nfs_req_openctx(req), ctx); 1212 if (l_ctx && flctx && 1213 !(list_empty_careful(&flctx->flc_posix) && 1214 list_empty_careful(&flctx->flc_flock))) { 1215 do_flush |= l_ctx->lockowner != current->files; 1216 } 1217 nfs_release_request(req); 1218 if (!do_flush) 1219 return 0; 1220 status = nfs_wb_folio(folio_file_mapping(folio)->host, folio); 1221 } while (status == 0); 1222 return status; 1223} 1224 1225/* 1226 * Avoid buffered writes when a open context credential's key would 1227 * expire soon. 1228 * 1229 * Returns -EACCES if the key will expire within RPC_KEY_EXPIRE_FAIL. 1230 * 1231 * Return 0 and set a credential flag which triggers the inode to flush 1232 * and performs NFS_FILE_SYNC writes if the key will expired within 1233 * RPC_KEY_EXPIRE_TIMEO. 1234 */ 1235int 1236nfs_key_timeout_notify(struct file *filp, struct inode *inode) 1237{ 1238 struct nfs_open_context *ctx = nfs_file_open_context(filp); 1239 1240 if (nfs_ctx_key_to_expire(ctx, inode) && 1241 !rcu_access_pointer(ctx->ll_cred)) 1242 /* Already expired! */ 1243 return -EACCES; 1244 return 0; 1245} 1246 1247/* 1248 * Test if the open context credential key is marked to expire soon. 1249 */ 1250bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx, struct inode *inode) 1251{ 1252 struct rpc_auth *auth = NFS_SERVER(inode)->client->cl_auth; 1253 struct rpc_cred *cred, *new, *old = NULL; 1254 struct auth_cred acred = { 1255 .cred = ctx->cred, 1256 }; 1257 bool ret = false; 1258 1259 rcu_read_lock(); 1260 cred = rcu_dereference(ctx->ll_cred); 1261 if (cred && !(cred->cr_ops->crkey_timeout && 1262 cred->cr_ops->crkey_timeout(cred))) 1263 goto out; 1264 rcu_read_unlock(); 1265 1266 new = auth->au_ops->lookup_cred(auth, &acred, 0); 1267 if (new == cred) { 1268 put_rpccred(new); 1269 return true; 1270 } 1271 if (IS_ERR_OR_NULL(new)) { 1272 new = NULL; 1273 ret = true; 1274 } else if (new->cr_ops->crkey_timeout && 1275 new->cr_ops->crkey_timeout(new)) 1276 ret = true; 1277 1278 rcu_read_lock(); 1279 old = rcu_dereference_protected(xchg(&ctx->ll_cred, 1280 RCU_INITIALIZER(new)), 1); 1281out: 1282 rcu_read_unlock(); 1283 put_rpccred(old); 1284 return ret; 1285} 1286 1287/* 1288 * If the page cache is marked as unsafe or invalid, then we can't rely on 1289 * the PageUptodate() flag. In this case, we will need to turn off 1290 * write optimisations that depend on the page contents being correct. 1291 */ 1292static bool nfs_folio_write_uptodate(struct folio *folio, unsigned int pagelen) 1293{ 1294 struct inode *inode = folio_file_mapping(folio)->host; 1295 struct nfs_inode *nfsi = NFS_I(inode); 1296 1297 if (nfs_have_delegated_attributes(inode)) 1298 goto out; 1299 if (nfsi->cache_validity & 1300 (NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_SIZE)) 1301 return false; 1302 smp_rmb(); 1303 if (test_bit(NFS_INO_INVALIDATING, &nfsi->flags) && pagelen != 0) 1304 return false; 1305out: 1306 if (nfsi->cache_validity & NFS_INO_INVALID_DATA && pagelen != 0) 1307 return false; 1308 return folio_test_uptodate(folio) != 0; 1309} 1310 1311static bool 1312is_whole_file_wrlock(struct file_lock *fl) 1313{ 1314 return fl->fl_start == 0 && fl->fl_end == OFFSET_MAX && 1315 fl->fl_type == F_WRLCK; 1316} 1317 1318/* If we know the page is up to date, and we're not using byte range locks (or 1319 * if we have the whole file locked for writing), it may be more efficient to 1320 * extend the write to cover the entire page in order to avoid fragmentation 1321 * inefficiencies. 1322 * 1323 * If the file is opened for synchronous writes then we can just skip the rest 1324 * of the checks. 1325 */ 1326static int nfs_can_extend_write(struct file *file, struct folio *folio, 1327 unsigned int pagelen) 1328{ 1329 struct inode *inode = file_inode(file); 1330 struct file_lock_context *flctx = locks_inode_context(inode); 1331 struct file_lock *fl; 1332 int ret; 1333 1334 if (file->f_flags & O_DSYNC) 1335 return 0; 1336 if (!nfs_folio_write_uptodate(folio, pagelen)) 1337 return 0; 1338 if (NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE)) 1339 return 1; 1340 if (!flctx || (list_empty_careful(&flctx->flc_flock) && 1341 list_empty_careful(&flctx->flc_posix))) 1342 return 1; 1343 1344 /* Check to see if there are whole file write locks */ 1345 ret = 0; 1346 spin_lock(&flctx->flc_lock); 1347 if (!list_empty(&flctx->flc_posix)) { 1348 fl = list_first_entry(&flctx->flc_posix, struct file_lock, 1349 fl_list); 1350 if (is_whole_file_wrlock(fl)) 1351 ret = 1; 1352 } else if (!list_empty(&flctx->flc_flock)) { 1353 fl = list_first_entry(&flctx->flc_flock, struct file_lock, 1354 fl_list); 1355 if (fl->fl_type == F_WRLCK) 1356 ret = 1; 1357 } 1358 spin_unlock(&flctx->flc_lock); 1359 return ret; 1360} 1361 1362/* 1363 * Update and possibly write a cached page of an NFS file. 1364 * 1365 * XXX: Keep an eye on generic_file_read to make sure it doesn't do bad 1366 * things with a page scheduled for an RPC call (e.g. invalidate it). 1367 */ 1368int nfs_update_folio(struct file *file, struct folio *folio, 1369 unsigned int offset, unsigned int count) 1370{ 1371 struct nfs_open_context *ctx = nfs_file_open_context(file); 1372 struct address_space *mapping = folio_file_mapping(folio); 1373 struct inode *inode = mapping->host; 1374 unsigned int pagelen = nfs_folio_length(folio); 1375 int status = 0; 1376 1377 nfs_inc_stats(inode, NFSIOS_VFSUPDATEPAGE); 1378 1379 dprintk("NFS: nfs_update_folio(%pD2 %d@%lld)\n", file, count, 1380 (long long)(folio_file_pos(folio) + offset)); 1381 1382 if (!count) 1383 goto out; 1384 1385 if (nfs_can_extend_write(file, folio, pagelen)) { 1386 count = max(count + offset, pagelen); 1387 offset = 0; 1388 } 1389 1390 status = nfs_writepage_setup(ctx, folio, offset, count); 1391 if (status < 0) 1392 nfs_set_pageerror(mapping); 1393out: 1394 dprintk("NFS: nfs_update_folio returns %d (isize %lld)\n", 1395 status, (long long)i_size_read(inode)); 1396 return status; 1397} 1398 1399static int flush_task_priority(int how) 1400{ 1401 switch (how & (FLUSH_HIGHPRI|FLUSH_LOWPRI)) { 1402 case FLUSH_HIGHPRI: 1403 return RPC_PRIORITY_HIGH; 1404 case FLUSH_LOWPRI: 1405 return RPC_PRIORITY_LOW; 1406 } 1407 return RPC_PRIORITY_NORMAL; 1408} 1409 1410static void nfs_initiate_write(struct nfs_pgio_header *hdr, 1411 struct rpc_message *msg, 1412 const struct nfs_rpc_ops *rpc_ops, 1413 struct rpc_task_setup *task_setup_data, int how) 1414{ 1415 int priority = flush_task_priority(how); 1416 1417 if (IS_SWAPFILE(hdr->inode)) 1418 task_setup_data->flags |= RPC_TASK_SWAPPER; 1419 task_setup_data->priority = priority; 1420 rpc_ops->write_setup(hdr, msg, &task_setup_data->rpc_client); 1421 trace_nfs_initiate_write(hdr); 1422} 1423 1424/* If a nfs_flush_* function fails, it should remove reqs from @head and 1425 * call this on each, which will prepare them to be retried on next 1426 * writeback using standard nfs. 1427 */ 1428static void nfs_redirty_request(struct nfs_page *req) 1429{ 1430 struct nfs_inode *nfsi = NFS_I(nfs_page_to_inode(req)); 1431 1432 /* Bump the transmission count */ 1433 req->wb_nio++; 1434 nfs_mark_request_dirty(req); 1435 atomic_long_inc(&nfsi->redirtied_pages); 1436 nfs_page_end_writeback(req); 1437 nfs_release_request(req); 1438} 1439 1440static void nfs_async_write_error(struct list_head *head, int error) 1441{ 1442 struct nfs_page *req; 1443 1444 while (!list_empty(head)) { 1445 req = nfs_list_entry(head->next); 1446 nfs_list_remove_request(req); 1447 if (nfs_error_is_fatal_on_server(error)) 1448 nfs_write_error(req, error); 1449 else 1450 nfs_redirty_request(req); 1451 } 1452} 1453 1454static void nfs_async_write_reschedule_io(struct nfs_pgio_header *hdr) 1455{ 1456 nfs_async_write_error(&hdr->pages, 0); 1457} 1458 1459static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops = { 1460 .init_hdr = nfs_async_write_init, 1461 .error_cleanup = nfs_async_write_error, 1462 .completion = nfs_write_completion, 1463 .reschedule_io = nfs_async_write_reschedule_io, 1464}; 1465 1466void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, 1467 struct inode *inode, int ioflags, bool force_mds, 1468 const struct nfs_pgio_completion_ops *compl_ops) 1469{ 1470 struct nfs_server *server = NFS_SERVER(inode); 1471 const struct nfs_pageio_ops *pg_ops = &nfs_pgio_rw_ops; 1472 1473#ifdef CONFIG_NFS_V4_1 1474 if (server->pnfs_curr_ld && !force_mds) 1475 pg_ops = server->pnfs_curr_ld->pg_write_ops; 1476#endif 1477 nfs_pageio_init(pgio, inode, pg_ops, compl_ops, &nfs_rw_write_ops, 1478 server->wsize, ioflags); 1479} 1480EXPORT_SYMBOL_GPL(nfs_pageio_init_write); 1481 1482void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio) 1483{ 1484 struct nfs_pgio_mirror *mirror; 1485 1486 if (pgio->pg_ops && pgio->pg_ops->pg_cleanup) 1487 pgio->pg_ops->pg_cleanup(pgio); 1488 1489 pgio->pg_ops = &nfs_pgio_rw_ops; 1490 1491 nfs_pageio_stop_mirroring(pgio); 1492 1493 mirror = &pgio->pg_mirrors[0]; 1494 mirror->pg_bsize = NFS_SERVER(pgio->pg_inode)->wsize; 1495} 1496EXPORT_SYMBOL_GPL(nfs_pageio_reset_write_mds); 1497 1498 1499void nfs_commit_prepare(struct rpc_task *task, void *calldata) 1500{ 1501 struct nfs_commit_data *data = calldata; 1502 1503 NFS_PROTO(data->inode)->commit_rpc_prepare(task, data); 1504} 1505 1506static void nfs_writeback_check_extend(struct nfs_pgio_header *hdr, 1507 struct nfs_fattr *fattr) 1508{ 1509 struct nfs_pgio_args *argp = &hdr->args; 1510 struct nfs_pgio_res *resp = &hdr->res; 1511 u64 size = argp->offset + resp->count; 1512 1513 if (!(fattr->valid & NFS_ATTR_FATTR_SIZE)) 1514 fattr->size = size; 1515 if (nfs_size_to_loff_t(fattr->size) < i_size_read(hdr->inode)) { 1516 fattr->valid &= ~NFS_ATTR_FATTR_SIZE; 1517 return; 1518 } 1519 if (size != fattr->size) 1520 return; 1521 /* Set attribute barrier */ 1522 nfs_fattr_set_barrier(fattr); 1523 /* ...and update size */ 1524 fattr->valid |= NFS_ATTR_FATTR_SIZE; 1525} 1526 1527void nfs_writeback_update_inode(struct nfs_pgio_header *hdr) 1528{ 1529 struct nfs_fattr *fattr = &hdr->fattr; 1530 struct inode *inode = hdr->inode; 1531 1532 spin_lock(&inode->i_lock); 1533 nfs_writeback_check_extend(hdr, fattr); 1534 nfs_post_op_update_inode_force_wcc_locked(inode, fattr); 1535 spin_unlock(&inode->i_lock); 1536} 1537EXPORT_SYMBOL_GPL(nfs_writeback_update_inode); 1538 1539/* 1540 * This function is called when the WRITE call is complete. 1541 */ 1542static int nfs_writeback_done(struct rpc_task *task, 1543 struct nfs_pgio_header *hdr, 1544 struct inode *inode) 1545{ 1546 int status; 1547 1548 /* 1549 * ->write_done will attempt to use post-op attributes to detect 1550 * conflicting writes by other clients. A strict interpretation 1551 * of close-to-open would allow us to continue caching even if 1552 * another writer had changed the file, but some applications 1553 * depend on tighter cache coherency when writing. 1554 */ 1555 status = NFS_PROTO(inode)->write_done(task, hdr); 1556 if (status != 0) 1557 return status; 1558 1559 nfs_add_stats(inode, NFSIOS_SERVERWRITTENBYTES, hdr->res.count); 1560 trace_nfs_writeback_done(task, hdr); 1561 1562 if (task->tk_status >= 0) { 1563 enum nfs3_stable_how committed = hdr->res.verf->committed; 1564 1565 if (committed == NFS_UNSTABLE) { 1566 /* 1567 * We have some uncommitted data on the server at 1568 * this point, so ensure that we keep track of that 1569 * fact irrespective of what later writes do. 1570 */ 1571 set_bit(NFS_IOHDR_UNSTABLE_WRITES, &hdr->flags); 1572 } 1573 1574 if (committed < hdr->args.stable) { 1575 /* We tried a write call, but the server did not 1576 * commit data to stable storage even though we 1577 * requested it. 1578 * Note: There is a known bug in Tru64 < 5.0 in which 1579 * the server reports NFS_DATA_SYNC, but performs 1580 * NFS_FILE_SYNC. We therefore implement this checking 1581 * as a dprintk() in order to avoid filling syslog. 1582 */ 1583 static unsigned long complain; 1584 1585 /* Note this will print the MDS for a DS write */ 1586 if (time_before(complain, jiffies)) { 1587 dprintk("NFS: faulty NFS server %s:" 1588 " (committed = %d) != (stable = %d)\n", 1589 NFS_SERVER(inode)->nfs_client->cl_hostname, 1590 committed, hdr->args.stable); 1591 complain = jiffies + 300 * HZ; 1592 } 1593 } 1594 } 1595 1596 /* Deal with the suid/sgid bit corner case */ 1597 if (nfs_should_remove_suid(inode)) { 1598 spin_lock(&inode->i_lock); 1599 nfs_set_cache_invalid(inode, NFS_INO_INVALID_MODE); 1600 spin_unlock(&inode->i_lock); 1601 } 1602 return 0; 1603} 1604 1605/* 1606 * This function is called when the WRITE call is complete. 1607 */ 1608static void nfs_writeback_result(struct rpc_task *task, 1609 struct nfs_pgio_header *hdr) 1610{ 1611 struct nfs_pgio_args *argp = &hdr->args; 1612 struct nfs_pgio_res *resp = &hdr->res; 1613 1614 if (resp->count < argp->count) { 1615 static unsigned long complain; 1616 1617 /* This a short write! */ 1618 nfs_inc_stats(hdr->inode, NFSIOS_SHORTWRITE); 1619 1620 /* Has the server at least made some progress? */ 1621 if (resp->count == 0) { 1622 if (time_before(complain, jiffies)) { 1623 printk(KERN_WARNING 1624 "NFS: Server wrote zero bytes, expected %u.\n", 1625 argp->count); 1626 complain = jiffies + 300 * HZ; 1627 } 1628 nfs_set_pgio_error(hdr, -EIO, argp->offset); 1629 task->tk_status = -EIO; 1630 return; 1631 } 1632 1633 /* For non rpc-based layout drivers, retry-through-MDS */ 1634 if (!task->tk_ops) { 1635 hdr->pnfs_error = -EAGAIN; 1636 return; 1637 } 1638 1639 /* Was this an NFSv2 write or an NFSv3 stable write? */ 1640 if (resp->verf->committed != NFS_UNSTABLE) { 1641 /* Resend from where the server left off */ 1642 hdr->mds_offset += resp->count; 1643 argp->offset += resp->count; 1644 argp->pgbase += resp->count; 1645 argp->count -= resp->count; 1646 } else { 1647 /* Resend as a stable write in order to avoid 1648 * headaches in the case of a server crash. 1649 */ 1650 argp->stable = NFS_FILE_SYNC; 1651 } 1652 resp->count = 0; 1653 resp->verf->committed = 0; 1654 rpc_restart_call_prepare(task); 1655 } 1656} 1657 1658static int wait_on_commit(struct nfs_mds_commit_info *cinfo) 1659{ 1660 return wait_var_event_killable(&cinfo->rpcs_out, 1661 !atomic_read(&cinfo->rpcs_out)); 1662} 1663 1664void nfs_commit_begin(struct nfs_mds_commit_info *cinfo) 1665{ 1666 atomic_inc(&cinfo->rpcs_out); 1667} 1668 1669bool nfs_commit_end(struct nfs_mds_commit_info *cinfo) 1670{ 1671 if (atomic_dec_and_test(&cinfo->rpcs_out)) { 1672 wake_up_var(&cinfo->rpcs_out); 1673 return true; 1674 } 1675 return false; 1676} 1677 1678void nfs_commitdata_release(struct nfs_commit_data *data) 1679{ 1680 put_nfs_open_context(data->context); 1681 nfs_commit_free(data); 1682} 1683EXPORT_SYMBOL_GPL(nfs_commitdata_release); 1684 1685int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data, 1686 const struct nfs_rpc_ops *nfs_ops, 1687 const struct rpc_call_ops *call_ops, 1688 int how, int flags) 1689{ 1690 struct rpc_task *task; 1691 int priority = flush_task_priority(how); 1692 struct rpc_message msg = { 1693 .rpc_argp = &data->args, 1694 .rpc_resp = &data->res, 1695 .rpc_cred = data->cred, 1696 }; 1697 struct rpc_task_setup task_setup_data = { 1698 .task = &data->task, 1699 .rpc_client = clnt, 1700 .rpc_message = &msg, 1701 .callback_ops = call_ops, 1702 .callback_data = data, 1703 .workqueue = nfsiod_workqueue, 1704 .flags = RPC_TASK_ASYNC | flags, 1705 .priority = priority, 1706 }; 1707 1708 if (nfs_server_capable(data->inode, NFS_CAP_MOVEABLE)) 1709 task_setup_data.flags |= RPC_TASK_MOVEABLE; 1710 1711 /* Set up the initial task struct. */ 1712 nfs_ops->commit_setup(data, &msg, &task_setup_data.rpc_client); 1713 trace_nfs_initiate_commit(data); 1714 1715 dprintk("NFS: initiated commit call\n"); 1716 1717 task = rpc_run_task(&task_setup_data); 1718 if (IS_ERR(task)) 1719 return PTR_ERR(task); 1720 if (how & FLUSH_SYNC) 1721 rpc_wait_for_completion_task(task); 1722 rpc_put_task(task); 1723 return 0; 1724} 1725EXPORT_SYMBOL_GPL(nfs_initiate_commit); 1726 1727static loff_t nfs_get_lwb(struct list_head *head) 1728{ 1729 loff_t lwb = 0; 1730 struct nfs_page *req; 1731 1732 list_for_each_entry(req, head, wb_list) 1733 if (lwb < (req_offset(req) + req->wb_bytes)) 1734 lwb = req_offset(req) + req->wb_bytes; 1735 1736 return lwb; 1737} 1738 1739/* 1740 * Set up the argument/result storage required for the RPC call. 1741 */ 1742void nfs_init_commit(struct nfs_commit_data *data, 1743 struct list_head *head, 1744 struct pnfs_layout_segment *lseg, 1745 struct nfs_commit_info *cinfo) 1746{ 1747 struct nfs_page *first; 1748 struct nfs_open_context *ctx; 1749 struct inode *inode; 1750 1751 /* Set up the RPC argument and reply structs 1752 * NB: take care not to mess about with data->commit et al. */ 1753 1754 if (head) 1755 list_splice_init(head, &data->pages); 1756 1757 first = nfs_list_entry(data->pages.next); 1758 ctx = nfs_req_openctx(first); 1759 inode = d_inode(ctx->dentry); 1760 1761 data->inode = inode; 1762 data->cred = ctx->cred; 1763 data->lseg = lseg; /* reference transferred */ 1764 /* only set lwb for pnfs commit */ 1765 if (lseg) 1766 data->lwb = nfs_get_lwb(&data->pages); 1767 data->mds_ops = &nfs_commit_ops; 1768 data->completion_ops = cinfo->completion_ops; 1769 data->dreq = cinfo->dreq; 1770 1771 data->args.fh = NFS_FH(data->inode); 1772 /* Note: we always request a commit of the entire inode */ 1773 data->args.offset = 0; 1774 data->args.count = 0; 1775 data->context = get_nfs_open_context(ctx); 1776 data->res.fattr = &data->fattr; 1777 data->res.verf = &data->verf; 1778 nfs_fattr_init(&data->fattr); 1779 nfs_commit_begin(cinfo->mds); 1780} 1781EXPORT_SYMBOL_GPL(nfs_init_commit); 1782 1783void nfs_retry_commit(struct list_head *page_list, 1784 struct pnfs_layout_segment *lseg, 1785 struct nfs_commit_info *cinfo, 1786 u32 ds_commit_idx) 1787{ 1788 struct nfs_page *req; 1789 1790 while (!list_empty(page_list)) { 1791 req = nfs_list_entry(page_list->next); 1792 nfs_list_remove_request(req); 1793 nfs_mark_request_commit(req, lseg, cinfo, ds_commit_idx); 1794 nfs_folio_clear_commit(nfs_page_to_folio(req)); 1795 nfs_unlock_and_release_request(req); 1796 } 1797} 1798EXPORT_SYMBOL_GPL(nfs_retry_commit); 1799 1800static void nfs_commit_resched_write(struct nfs_commit_info *cinfo, 1801 struct nfs_page *req) 1802{ 1803 struct folio *folio = nfs_page_to_folio(req); 1804 1805 filemap_dirty_folio(folio_mapping(folio), folio); 1806} 1807 1808/* 1809 * Commit dirty pages 1810 */ 1811static int 1812nfs_commit_list(struct inode *inode, struct list_head *head, int how, 1813 struct nfs_commit_info *cinfo) 1814{ 1815 struct nfs_commit_data *data; 1816 unsigned short task_flags = 0; 1817 1818 /* another commit raced with us */ 1819 if (list_empty(head)) 1820 return 0; 1821 1822 data = nfs_commitdata_alloc(); 1823 if (!data) { 1824 nfs_retry_commit(head, NULL, cinfo, -1); 1825 return -ENOMEM; 1826 } 1827 1828 /* Set up the argument struct */ 1829 nfs_init_commit(data, head, NULL, cinfo); 1830 if (NFS_SERVER(inode)->nfs_client->cl_minorversion) 1831 task_flags = RPC_TASK_MOVEABLE; 1832 return nfs_initiate_commit(NFS_CLIENT(inode), data, NFS_PROTO(inode), 1833 data->mds_ops, how, 1834 RPC_TASK_CRED_NOREF | task_flags); 1835} 1836 1837/* 1838 * COMMIT call returned 1839 */ 1840static void nfs_commit_done(struct rpc_task *task, void *calldata) 1841{ 1842 struct nfs_commit_data *data = calldata; 1843 1844 /* Call the NFS version-specific code */ 1845 NFS_PROTO(data->inode)->commit_done(task, data); 1846 trace_nfs_commit_done(task, data); 1847} 1848 1849static void nfs_commit_release_pages(struct nfs_commit_data *data) 1850{ 1851 const struct nfs_writeverf *verf = data->res.verf; 1852 struct nfs_page *req; 1853 int status = data->task.tk_status; 1854 struct nfs_commit_info cinfo; 1855 struct nfs_server *nfss; 1856 struct folio *folio; 1857 1858 while (!list_empty(&data->pages)) { 1859 req = nfs_list_entry(data->pages.next); 1860 nfs_list_remove_request(req); 1861 folio = nfs_page_to_folio(req); 1862 nfs_folio_clear_commit(folio); 1863 1864 dprintk("NFS: commit (%s/%llu %d@%lld)", 1865 nfs_req_openctx(req)->dentry->d_sb->s_id, 1866 (unsigned long long)NFS_FILEID(d_inode(nfs_req_openctx(req)->dentry)), 1867 req->wb_bytes, 1868 (long long)req_offset(req)); 1869 if (status < 0) { 1870 if (folio) { 1871 trace_nfs_commit_error(data->inode, req, 1872 status); 1873 nfs_mapping_set_error(folio, status); 1874 nfs_inode_remove_request(req); 1875 } 1876 dprintk_cont(", error = %d\n", status); 1877 goto next; 1878 } 1879 1880 /* Okay, COMMIT succeeded, apparently. Check the verifier 1881 * returned by the server against all stored verfs. */ 1882 if (nfs_write_match_verf(verf, req)) { 1883 /* We have a match */ 1884 if (folio) 1885 nfs_inode_remove_request(req); 1886 dprintk_cont(" OK\n"); 1887 goto next; 1888 } 1889 /* We have a mismatch. Write the page again */ 1890 dprintk_cont(" mismatch\n"); 1891 nfs_mark_request_dirty(req); 1892 atomic_long_inc(&NFS_I(data->inode)->redirtied_pages); 1893 next: 1894 nfs_unlock_and_release_request(req); 1895 /* Latency breaker */ 1896 cond_resched(); 1897 } 1898 nfss = NFS_SERVER(data->inode); 1899 if (atomic_long_read(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH) 1900 nfss->write_congested = 0; 1901 1902 nfs_init_cinfo(&cinfo, data->inode, data->dreq); 1903 nfs_commit_end(cinfo.mds); 1904} 1905 1906static void nfs_commit_release(void *calldata) 1907{ 1908 struct nfs_commit_data *data = calldata; 1909 1910 data->completion_ops->completion(data); 1911 nfs_commitdata_release(calldata); 1912} 1913 1914static const struct rpc_call_ops nfs_commit_ops = { 1915 .rpc_call_prepare = nfs_commit_prepare, 1916 .rpc_call_done = nfs_commit_done, 1917 .rpc_release = nfs_commit_release, 1918}; 1919 1920static const struct nfs_commit_completion_ops nfs_commit_completion_ops = { 1921 .completion = nfs_commit_release_pages, 1922 .resched_write = nfs_commit_resched_write, 1923}; 1924 1925int nfs_generic_commit_list(struct inode *inode, struct list_head *head, 1926 int how, struct nfs_commit_info *cinfo) 1927{ 1928 int status; 1929 1930 status = pnfs_commit_list(inode, head, how, cinfo); 1931 if (status == PNFS_NOT_ATTEMPTED) 1932 status = nfs_commit_list(inode, head, how, cinfo); 1933 return status; 1934} 1935 1936static int __nfs_commit_inode(struct inode *inode, int how, 1937 struct writeback_control *wbc) 1938{ 1939 LIST_HEAD(head); 1940 struct nfs_commit_info cinfo; 1941 int may_wait = how & FLUSH_SYNC; 1942 int ret, nscan; 1943 1944 how &= ~FLUSH_SYNC; 1945 nfs_init_cinfo_from_inode(&cinfo, inode); 1946 nfs_commit_begin(cinfo.mds); 1947 for (;;) { 1948 ret = nscan = nfs_scan_commit(inode, &head, &cinfo); 1949 if (ret <= 0) 1950 break; 1951 ret = nfs_generic_commit_list(inode, &head, how, &cinfo); 1952 if (ret < 0) 1953 break; 1954 ret = 0; 1955 if (wbc && wbc->sync_mode == WB_SYNC_NONE) { 1956 if (nscan < wbc->nr_to_write) 1957 wbc->nr_to_write -= nscan; 1958 else 1959 wbc->nr_to_write = 0; 1960 } 1961 if (nscan < INT_MAX) 1962 break; 1963 cond_resched(); 1964 } 1965 nfs_commit_end(cinfo.mds); 1966 if (ret || !may_wait) 1967 return ret; 1968 return wait_on_commit(cinfo.mds); 1969} 1970 1971int nfs_commit_inode(struct inode *inode, int how) 1972{ 1973 return __nfs_commit_inode(inode, how, NULL); 1974} 1975EXPORT_SYMBOL_GPL(nfs_commit_inode); 1976 1977int nfs_write_inode(struct inode *inode, struct writeback_control *wbc) 1978{ 1979 struct nfs_inode *nfsi = NFS_I(inode); 1980 int flags = FLUSH_SYNC; 1981 int ret = 0; 1982 1983 if (wbc->sync_mode == WB_SYNC_NONE) { 1984 /* no commits means nothing needs to be done */ 1985 if (!atomic_long_read(&nfsi->commit_info.ncommit)) 1986 goto check_requests_outstanding; 1987 1988 /* Don't commit yet if this is a non-blocking flush and there 1989 * are a lot of outstanding writes for this mapping. 1990 */ 1991 if (mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK)) 1992 goto out_mark_dirty; 1993 1994 /* don't wait for the COMMIT response */ 1995 flags = 0; 1996 } 1997 1998 ret = __nfs_commit_inode(inode, flags, wbc); 1999 if (!ret) { 2000 if (flags & FLUSH_SYNC) 2001 return 0; 2002 } else if (atomic_long_read(&nfsi->commit_info.ncommit)) 2003 goto out_mark_dirty; 2004 2005check_requests_outstanding: 2006 if (!atomic_read(&nfsi->commit_info.rpcs_out)) 2007 return ret; 2008out_mark_dirty: 2009 __mark_inode_dirty(inode, I_DIRTY_DATASYNC); 2010 return ret; 2011} 2012EXPORT_SYMBOL_GPL(nfs_write_inode); 2013 2014/* 2015 * Wrapper for filemap_write_and_wait_range() 2016 * 2017 * Needed for pNFS in order to ensure data becomes visible to the 2018 * client. 2019 */ 2020int nfs_filemap_write_and_wait_range(struct address_space *mapping, 2021 loff_t lstart, loff_t lend) 2022{ 2023 int ret; 2024 2025 ret = filemap_write_and_wait_range(mapping, lstart, lend); 2026 if (ret == 0) 2027 ret = pnfs_sync_inode(mapping->host, true); 2028 return ret; 2029} 2030EXPORT_SYMBOL_GPL(nfs_filemap_write_and_wait_range); 2031 2032/* 2033 * flush the inode to disk. 2034 */ 2035int nfs_wb_all(struct inode *inode) 2036{ 2037 int ret; 2038 2039 trace_nfs_writeback_inode_enter(inode); 2040 2041 ret = filemap_write_and_wait(inode->i_mapping); 2042 if (ret) 2043 goto out; 2044 ret = nfs_commit_inode(inode, FLUSH_SYNC); 2045 if (ret < 0) 2046 goto out; 2047 pnfs_sync_inode(inode, true); 2048 ret = 0; 2049 2050out: 2051 trace_nfs_writeback_inode_exit(inode, ret); 2052 return ret; 2053} 2054EXPORT_SYMBOL_GPL(nfs_wb_all); 2055 2056int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio) 2057{ 2058 struct nfs_page *req; 2059 int ret = 0; 2060 2061 folio_wait_writeback(folio); 2062 2063 /* blocking call to cancel all requests and join to a single (head) 2064 * request */ 2065 req = nfs_lock_and_join_requests(folio); 2066 2067 if (IS_ERR(req)) { 2068 ret = PTR_ERR(req); 2069 } else if (req) { 2070 /* all requests from this folio have been cancelled by 2071 * nfs_lock_and_join_requests, so just remove the head 2072 * request from the inode / page_private pointer and 2073 * release it */ 2074 nfs_inode_remove_request(req); 2075 nfs_unlock_and_release_request(req); 2076 } 2077 2078 return ret; 2079} 2080 2081/** 2082 * nfs_wb_folio - Write back all requests on one page 2083 * @inode: pointer to page 2084 * @folio: pointer to folio 2085 * 2086 * Assumes that the folio has been locked by the caller, and will 2087 * not unlock it. 2088 */ 2089int nfs_wb_folio(struct inode *inode, struct folio *folio) 2090{ 2091 loff_t range_start = folio_file_pos(folio); 2092 loff_t range_end = range_start + (loff_t)folio_size(folio) - 1; 2093 struct writeback_control wbc = { 2094 .sync_mode = WB_SYNC_ALL, 2095 .nr_to_write = 0, 2096 .range_start = range_start, 2097 .range_end = range_end, 2098 }; 2099 int ret; 2100 2101 trace_nfs_writeback_folio(inode, folio); 2102 2103 for (;;) { 2104 folio_wait_writeback(folio); 2105 if (folio_clear_dirty_for_io(folio)) { 2106 ret = nfs_writepage_locked(folio, &wbc); 2107 if (ret < 0) 2108 goto out_error; 2109 continue; 2110 } 2111 ret = 0; 2112 if (!folio_test_private(folio)) 2113 break; 2114 ret = nfs_commit_inode(inode, FLUSH_SYNC); 2115 if (ret < 0) 2116 goto out_error; 2117 } 2118out_error: 2119 trace_nfs_writeback_folio_done(inode, folio, ret); 2120 return ret; 2121} 2122 2123#ifdef CONFIG_MIGRATION 2124int nfs_migrate_folio(struct address_space *mapping, struct folio *dst, 2125 struct folio *src, enum migrate_mode mode) 2126{ 2127 /* 2128 * If the private flag is set, the folio is currently associated with 2129 * an in-progress read or write request. Don't try to migrate it. 2130 * 2131 * FIXME: we could do this in principle, but we'll need a way to ensure 2132 * that we can safely release the inode reference while holding 2133 * the folio lock. 2134 */ 2135 if (folio_test_private(src)) 2136 return -EBUSY; 2137 2138 if (folio_test_fscache(src)) { 2139 if (mode == MIGRATE_ASYNC) 2140 return -EBUSY; 2141 folio_wait_fscache(src); 2142 } 2143 2144 return migrate_folio(mapping, dst, src, mode); 2145} 2146#endif 2147 2148int __init nfs_init_writepagecache(void) 2149{ 2150 nfs_wdata_cachep = kmem_cache_create("nfs_write_data", 2151 sizeof(struct nfs_pgio_header), 2152 0, SLAB_HWCACHE_ALIGN, 2153 NULL); 2154 if (nfs_wdata_cachep == NULL) 2155 return -ENOMEM; 2156 2157 nfs_wdata_mempool = mempool_create_slab_pool(MIN_POOL_WRITE, 2158 nfs_wdata_cachep); 2159 if (nfs_wdata_mempool == NULL) 2160 goto out_destroy_write_cache; 2161 2162 nfs_cdata_cachep = kmem_cache_create("nfs_commit_data", 2163 sizeof(struct nfs_commit_data), 2164 0, SLAB_HWCACHE_ALIGN, 2165 NULL); 2166 if (nfs_cdata_cachep == NULL) 2167 goto out_destroy_write_mempool; 2168 2169 nfs_commit_mempool = mempool_create_slab_pool(MIN_POOL_COMMIT, 2170 nfs_cdata_cachep); 2171 if (nfs_commit_mempool == NULL) 2172 goto out_destroy_commit_cache; 2173 2174 /* 2175 * NFS congestion size, scale with available memory. 2176 * 2177 * 64MB: 8192k 2178 * 128MB: 11585k 2179 * 256MB: 16384k 2180 * 512MB: 23170k 2181 * 1GB: 32768k 2182 * 2GB: 46340k 2183 * 4GB: 65536k 2184 * 8GB: 92681k 2185 * 16GB: 131072k 2186 * 2187 * This allows larger machines to have larger/more transfers. 2188 * Limit the default to 256M 2189 */ 2190 nfs_congestion_kb = (16*int_sqrt(totalram_pages())) << (PAGE_SHIFT-10); 2191 if (nfs_congestion_kb > 256*1024) 2192 nfs_congestion_kb = 256*1024; 2193 2194 return 0; 2195 2196out_destroy_commit_cache: 2197 kmem_cache_destroy(nfs_cdata_cachep); 2198out_destroy_write_mempool: 2199 mempool_destroy(nfs_wdata_mempool); 2200out_destroy_write_cache: 2201 kmem_cache_destroy(nfs_wdata_cachep); 2202 return -ENOMEM; 2203} 2204 2205void nfs_destroy_writepagecache(void) 2206{ 2207 mempool_destroy(nfs_commit_mempool); 2208 kmem_cache_destroy(nfs_cdata_cachep); 2209 mempool_destroy(nfs_wdata_mempool); 2210 kmem_cache_destroy(nfs_wdata_cachep); 2211} 2212 2213static const struct nfs_rw_ops nfs_rw_write_ops = { 2214 .rw_alloc_header = nfs_writehdr_alloc, 2215 .rw_free_header = nfs_writehdr_free, 2216 .rw_done = nfs_writeback_done, 2217 .rw_result = nfs_writeback_result, 2218 .rw_initiate = nfs_initiate_write, 2219}; 2220