Blame view
fs/nfs/blocklayout/blocklayout.c
28.1 KB
155e7524f pnfsblock: add bl... |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 |
/* * linux/fs/nfs/blocklayout/blocklayout.c * * Module for the NFSv4.1 pNFS block layout driver. * * Copyright (c) 2006 The Regents of the University of Michigan. * All rights reserved. * * Andy Adamson <andros@citi.umich.edu> * Fred Isaman <iisaman@umich.edu> * * permission is granted to use, copy, create derivative works and * redistribute this software and such derivative works for any purpose, * so long as the name of the university of michigan is not used in * any advertising or publicity pertaining to the use or distribution * of this software without specific, written prior authorization. if * the above copyright notice or any other identification of the * university of michigan is included in any copy of any portion of * this software, then the disclaimer below must also be included. * * this software is provided as is, without representation from the * university of michigan as to its fitness for any purpose, and without * warranty by the university of michigan of any kind, either express * or implied, including without limitation the implied warranties of * merchantability and fitness for a particular purpose. the regents * of the university of michigan shall not be liable for any damages, * including special, indirect, incidental, or consequential damages, * with respect to any claim arising out or in connection with the use * of the software, even if it has been or is hereafter advised of the * possibility of such damages. */ |
9549ec01b pnfsblock: bl_rea... |
32 |
|
155e7524f pnfsblock: add bl... |
33 34 |
#include <linux/module.h> #include <linux/init.h> |
fe0a9b740 pnfsblock: add de... |
35 36 |
#include <linux/mount.h> #include <linux/namei.h> |
9549ec01b pnfsblock: bl_rea... |
37 |
#include <linux/bio.h> /* struct bio */ |
71cdd40fd pnfsblock: write_... |
38 |
#include <linux/buffer_head.h> /* various write calls */ |
88c9e4219 nfs: add missing ... |
39 |
#include <linux/prefetch.h> |
155e7524f pnfsblock: add bl... |
40 41 42 43 44 45 46 47 |
#include "blocklayout.h" #define NFSDBG_FACILITY NFSDBG_PNFS_LD MODULE_LICENSE("GPL"); MODULE_AUTHOR("Andy Adamson <andros@citi.umich.edu>"); MODULE_DESCRIPTION("The NFSv4.1 pNFS Block layout driver"); |
fe0a9b740 pnfsblock: add de... |
48 49 |
struct dentry *bl_device_pipe; wait_queue_head_t bl_wq; |
9549ec01b pnfsblock: bl_rea... |
50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 |
static void print_page(struct page *page) { dprintk("PRINTPAGE page %p ", page); dprintk(" PagePrivate %d ", PagePrivate(page)); dprintk(" PageUptodate %d ", PageUptodate(page)); dprintk(" PageError %d ", PageError(page)); dprintk(" PageDirty %d ", PageDirty(page)); dprintk(" PageReferenced %d ", PageReferenced(page)); dprintk(" PageLocked %d ", PageLocked(page)); dprintk(" PageWriteback %d ", PageWriteback(page)); dprintk(" PageMappedToDisk %d ", PageMappedToDisk(page)); dprintk(" "); } /* Given the be associated with isect, determine if page data needs to be * initialized. */ static int is_hole(struct pnfs_block_extent *be, sector_t isect) { if (be->be_state == PNFS_BLOCK_NONE_DATA) return 1; else if (be->be_state != PNFS_BLOCK_INVALID_DATA) return 0; else return !bl_is_sector_init(be->be_inval, isect); } |
650e2d39b pnfsblock: bl_wri... |
86 87 88 89 90 |
/* Given the be associated with isect, determine if page data can be * written to disk. */ static int is_writable(struct pnfs_block_extent *be, sector_t isect) { |
71cdd40fd pnfsblock: write_... |
91 92 |
return (be->be_state == PNFS_BLOCK_READWRITE_DATA || be->be_state == PNFS_BLOCK_INVALID_DATA); |
650e2d39b pnfsblock: bl_wri... |
93 |
} |
9549ec01b pnfsblock: bl_rea... |
94 95 96 97 98 |
/* The data we are handed might be spread across several bios. We need * to track when the last one is finished. */ struct parallel_io { struct kref refcnt; |
7c5465d6c pnfsblock: alloc ... |
99 |
void (*pnfs_callback) (void *data, int num_se); |
9549ec01b pnfsblock: bl_rea... |
100 |
void *data; |
7c5465d6c pnfsblock: alloc ... |
101 |
int bse_count; |
9549ec01b pnfsblock: bl_rea... |
102 103 104 105 106 107 108 109 110 111 |
}; static inline struct parallel_io *alloc_parallel(void *data) { struct parallel_io *rv; rv = kmalloc(sizeof(*rv), GFP_NOFS); if (rv) { rv->data = data; kref_init(&rv->refcnt); |
7c5465d6c pnfsblock: alloc ... |
112 |
rv->bse_count = 0; |
9549ec01b pnfsblock: bl_rea... |
113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 |
} return rv; } static inline void get_parallel(struct parallel_io *p) { kref_get(&p->refcnt); } static void destroy_parallel(struct kref *kref) { struct parallel_io *p = container_of(kref, struct parallel_io, refcnt); dprintk("%s enter ", __func__); |
7c5465d6c pnfsblock: alloc ... |
128 |
p->pnfs_callback(p->data, p->bse_count); |
9549ec01b pnfsblock: bl_rea... |
129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 |
kfree(p); } static inline void put_parallel(struct parallel_io *p) { kref_put(&p->refcnt, destroy_parallel); } static struct bio * bl_submit_bio(int rw, struct bio *bio) { if (bio) { get_parallel(bio->bi_private); dprintk("%s submitting %s bio %u@%llu ", __func__, rw == READ ? "read" : "write", bio->bi_size, (unsigned long long)bio->bi_sector); submit_bio(rw, bio); } return NULL; } static struct bio *bl_alloc_init_bio(int npg, sector_t isect, struct pnfs_block_extent *be, void (*end_io)(struct bio *, int err), struct parallel_io *par) { struct bio *bio; |
74a6eeb44 pnfsblock: limit ... |
157 |
npg = min(npg, BIO_MAX_PAGES); |
9549ec01b pnfsblock: bl_rea... |
158 |
bio = bio_alloc(GFP_NOIO, npg); |
74a6eeb44 pnfsblock: limit ... |
159 160 161 162 |
if (!bio && (current->flags & PF_MEMALLOC)) { while (!bio && (npg /= 2)) bio = bio_alloc(GFP_NOIO, npg); } |
9549ec01b pnfsblock: bl_rea... |
163 |
|
74a6eeb44 pnfsblock: limit ... |
164 165 166 167 168 169 |
if (bio) { bio->bi_sector = isect - be->be_f_offset + be->be_v_offset; bio->bi_bdev = be->be_mdev; bio->bi_end_io = end_io; bio->bi_private = par; } |
9549ec01b pnfsblock: bl_rea... |
170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 |
return bio; } static struct bio *bl_add_page_to_bio(struct bio *bio, int npg, int rw, sector_t isect, struct page *page, struct pnfs_block_extent *be, void (*end_io)(struct bio *, int err), struct parallel_io *par) { retry: if (!bio) { bio = bl_alloc_init_bio(npg, isect, be, end_io, par); if (!bio) return ERR_PTR(-ENOMEM); } if (bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) { bio = bl_submit_bio(rw, bio); goto retry; } return bio; } |
9549ec01b pnfsblock: bl_rea... |
191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 |
/* This is basically copied from mpage_end_io_read */ static void bl_end_io_read(struct bio *bio, int err) { struct parallel_io *par = bio->bi_private; const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1; struct nfs_read_data *rdata = (struct nfs_read_data *)par->data; do { struct page *page = bvec->bv_page; if (--bvec >= bio->bi_io_vec) prefetchw(&bvec->bv_page->flags); if (uptodate) SetPageUptodate(page); } while (bvec >= bio->bi_io_vec); if (!uptodate) { if (!rdata->pnfs_error) rdata->pnfs_error = -EIO; |
1b0ae0687 pnfs: make _set_l... |
210 |
pnfs_set_lo_fail(rdata->lseg); |
9549ec01b pnfsblock: bl_rea... |
211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 |
} bio_put(bio); put_parallel(par); } static void bl_read_cleanup(struct work_struct *work) { struct rpc_task *task; struct nfs_read_data *rdata; dprintk("%s enter ", __func__); task = container_of(work, struct rpc_task, u.tk_work); rdata = container_of(task, struct nfs_read_data, task); pnfs_ld_read_done(rdata); } static void |
7c5465d6c pnfsblock: alloc ... |
228 |
bl_end_par_io_read(void *data, int unused) |
9549ec01b pnfsblock: bl_rea... |
229 230 |
{ struct nfs_read_data *rdata = data; |
82b906d65 pnfsblock: set re... |
231 |
rdata->task.tk_status = rdata->pnfs_error; |
9549ec01b pnfsblock: bl_rea... |
232 233 234 |
INIT_WORK(&rdata->task.u.tk_work, bl_read_cleanup); schedule_work(&rdata->task.u.tk_work); } |
155e7524f pnfsblock: add bl... |
235 236 237 |
static enum pnfs_try_status bl_read_pagelist(struct nfs_read_data *rdata) { |
9549ec01b pnfsblock: bl_rea... |
238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 |
int i, hole; struct bio *bio = NULL; struct pnfs_block_extent *be = NULL, *cow_read = NULL; sector_t isect, extent_length = 0; struct parallel_io *par; loff_t f_offset = rdata->args.offset; size_t count = rdata->args.count; struct page **pages = rdata->args.pages; int pg_index = rdata->args.pgbase >> PAGE_CACHE_SHIFT; dprintk("%s enter nr_pages %u offset %lld count %Zd ", __func__, rdata->npages, f_offset, count); par = alloc_parallel(rdata); if (!par) goto use_mds; |
9549ec01b pnfsblock: bl_rea... |
255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 |
par->pnfs_callback = bl_end_par_io_read; /* At this point, we can no longer jump to use_mds */ isect = (sector_t) (f_offset >> SECTOR_SHIFT); /* Code assumes extents are page-aligned */ for (i = pg_index; i < rdata->npages; i++) { if (!extent_length) { /* We've used up the previous extent */ bl_put_extent(be); bl_put_extent(cow_read); bio = bl_submit_bio(READ, bio); /* Get the next one */ be = bl_find_get_extent(BLK_LSEG2EXT(rdata->lseg), isect, &cow_read); if (!be) { rdata->pnfs_error = -EIO; goto out; } extent_length = be->be_length - (isect - be->be_f_offset); if (cow_read) { sector_t cow_length = cow_read->be_length - (isect - cow_read->be_f_offset); extent_length = min(extent_length, cow_length); } } hole = is_hole(be, isect); if (hole && !cow_read) { bio = bl_submit_bio(READ, bio); /* Fill hole w/ zeroes w/o accessing device */ dprintk("%s Zeroing page for hole ", __func__); zero_user_segment(pages[i], 0, PAGE_CACHE_SIZE); print_page(pages[i]); SetPageUptodate(pages[i]); } else { struct pnfs_block_extent *be_read; be_read = (hole && cow_read) ? cow_read : be; bio = bl_add_page_to_bio(bio, rdata->npages - i, READ, isect, pages[i], be_read, bl_end_io_read, par); if (IS_ERR(bio)) { rdata->pnfs_error = PTR_ERR(bio); |
e6d05a757 pnfsblock: fix NU... |
299 |
bio = NULL; |
9549ec01b pnfsblock: bl_rea... |
300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 |
goto out; } } isect += PAGE_CACHE_SECTORS; extent_length -= PAGE_CACHE_SECTORS; } if ((isect << SECTOR_SHIFT) >= rdata->inode->i_size) { rdata->res.eof = 1; rdata->res.count = rdata->inode->i_size - f_offset; } else { rdata->res.count = (isect << SECTOR_SHIFT) - f_offset; } out: bl_put_extent(be); bl_put_extent(cow_read); bl_submit_bio(READ, bio); put_parallel(par); return PNFS_ATTEMPTED; use_mds: dprintk("Giving up and using normal NFS "); |
155e7524f pnfsblock: add bl... |
322 323 |
return PNFS_NOT_ATTEMPTED; } |
31e6306a4 pnfsblock: note w... |
324 325 326 327 328 |
static void mark_extents_written(struct pnfs_block_layout *bl, __u64 offset, __u32 count) { sector_t isect, end; struct pnfs_block_extent *be; |
7c5465d6c pnfsblock: alloc ... |
329 |
struct pnfs_block_short_extent *se; |
31e6306a4 pnfsblock: note w... |
330 331 332 333 334 335 336 337 338 339 340 341 342 |
dprintk("%s(%llu, %u) ", __func__, offset, count); if (count == 0) return; isect = (offset & (long)(PAGE_CACHE_MASK)) >> SECTOR_SHIFT; end = (offset + count + PAGE_CACHE_SIZE - 1) & (long)(PAGE_CACHE_MASK); end >>= SECTOR_SHIFT; while (isect < end) { sector_t len; be = bl_find_get_extent(bl, isect, NULL); BUG_ON(!be); /* FIXME */ len = min(end, be->be_f_offset + be->be_length) - isect; |
7c5465d6c pnfsblock: alloc ... |
343 344 345 346 347 |
if (be->be_state == PNFS_BLOCK_INVALID_DATA) { se = bl_pop_one_short_extent(be->be_inval); BUG_ON(!se); bl_mark_for_commit(be, isect, len, se); } |
31e6306a4 pnfsblock: note w... |
348 349 350 351 |
isect += len; bl_put_extent(be); } } |
71cdd40fd pnfsblock: write_... |
352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 |
static void bl_end_io_write_zero(struct bio *bio, int err) { struct parallel_io *par = bio->bi_private; const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1; struct nfs_write_data *wdata = (struct nfs_write_data *)par->data; do { struct page *page = bvec->bv_page; if (--bvec >= bio->bi_io_vec) prefetchw(&bvec->bv_page->flags); /* This is the zeroing page we added */ end_page_writeback(page); page_cache_release(page); } while (bvec >= bio->bi_io_vec); |
7c5465d6c pnfsblock: alloc ... |
368 369 |
if (unlikely(!uptodate)) { |
71cdd40fd pnfsblock: write_... |
370 371 |
if (!wdata->pnfs_error) wdata->pnfs_error = -EIO; |
1b0ae0687 pnfs: make _set_l... |
372 |
pnfs_set_lo_fail(wdata->lseg); |
71cdd40fd pnfsblock: write_... |
373 374 375 376 |
} bio_put(bio); put_parallel(par); } |
650e2d39b pnfsblock: bl_wri... |
377 378 379 380 381 382 383 384 385 |
static void bl_end_io_write(struct bio *bio, int err) { struct parallel_io *par = bio->bi_private; const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); struct nfs_write_data *wdata = (struct nfs_write_data *)par->data; if (!uptodate) { if (!wdata->pnfs_error) wdata->pnfs_error = -EIO; |
1b0ae0687 pnfs: make _set_l... |
386 |
pnfs_set_lo_fail(wdata->lseg); |
650e2d39b pnfsblock: bl_wri... |
387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 |
} bio_put(bio); put_parallel(par); } /* Function scheduled for call during bl_end_par_io_write, * it marks sectors as written and extends the commitlist. */ static void bl_write_cleanup(struct work_struct *work) { struct rpc_task *task; struct nfs_write_data *wdata; dprintk("%s enter ", __func__); task = container_of(work, struct rpc_task, u.tk_work); wdata = container_of(task, struct nfs_write_data, task); |
7c5465d6c pnfsblock: alloc ... |
403 |
if (likely(!wdata->pnfs_error)) { |
31e6306a4 pnfsblock: note w... |
404 |
/* Marks for LAYOUTCOMMIT */ |
31e6306a4 pnfsblock: note w... |
405 406 407 |
mark_extents_written(BLK_LSEG2EXT(wdata->lseg), wdata->args.offset, wdata->args.count); } |
650e2d39b pnfsblock: bl_wri... |
408 409 410 411 |
pnfs_ld_write_done(wdata); } /* Called when last of bios associated with a bl_write_pagelist call finishes */ |
7c5465d6c pnfsblock: alloc ... |
412 |
static void bl_end_par_io_write(void *data, int num_se) |
650e2d39b pnfsblock: bl_wri... |
413 414 |
{ struct nfs_write_data *wdata = data; |
7c5465d6c pnfsblock: alloc ... |
415 416 417 418 |
if (unlikely(wdata->pnfs_error)) { bl_free_short_extents(&BLK_LSEG2EXT(wdata->lseg)->bl_inval, num_se); } |
82b906d65 pnfsblock: set re... |
419 |
wdata->task.tk_status = wdata->pnfs_error; |
650e2d39b pnfsblock: bl_wri... |
420 421 422 423 |
wdata->verf.committed = NFS_FILE_SYNC; INIT_WORK(&wdata->task.u.tk_work, bl_write_cleanup); schedule_work(&wdata->task.u.tk_work); } |
71cdd40fd pnfsblock: write_... |
424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 |
/* FIXME STUB - mark intersection of layout and page as bad, so is not * used again. */ static void mark_bad_read(void) { return; } /* * map_block: map a requested I/0 block (isect) into an offset in the LVM * block_device */ static void map_block(struct buffer_head *bh, sector_t isect, struct pnfs_block_extent *be) { dprintk("%s enter be=%p ", __func__, be); set_buffer_mapped(bh); bh->b_bdev = be->be_mdev; bh->b_blocknr = (isect - be->be_f_offset + be->be_v_offset) >> (be->be_mdev->bd_inode->i_blkbits - SECTOR_SHIFT); dprintk("%s isect %llu, bh->b_blocknr %ld, using bsize %Zd ", __func__, (unsigned long long)isect, (long)bh->b_blocknr, bh->b_size); return; } /* Given an unmapped page, zero it or read in page for COW, page is locked * by caller. */ static int init_page_for_write(struct page *page, struct pnfs_block_extent *cow_read) { struct buffer_head *bh = NULL; int ret = 0; sector_t isect; dprintk("%s enter, %p ", __func__, page); BUG_ON(PageUptodate(page)); if (!cow_read) { zero_user_segment(page, 0, PAGE_SIZE); SetPageUptodate(page); goto cleanup; } bh = alloc_page_buffers(page, PAGE_CACHE_SIZE, 0); if (!bh) { ret = -ENOMEM; goto cleanup; } isect = (sector_t) page->index << PAGE_CACHE_SECTOR_SHIFT; map_block(bh, isect, cow_read); if (!bh_uptodate_or_lock(bh)) ret = bh_submit_read(bh); if (ret) goto cleanup; SetPageUptodate(page); cleanup: bl_put_extent(cow_read); if (bh) free_buffer_head(bh); if (ret) { /* Need to mark layout with bad read...should now * just use nfs4 for reads and writes. */ mark_bad_read(); } return ret; } |
72c508879 pnfsblock: move f... |
499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 |
/* Find or create a zeroing page marked being writeback. * Return ERR_PTR on error, NULL to indicate skip this page and page itself * to indicate write out. */ static struct page * bl_find_get_zeroing_page(struct inode *inode, pgoff_t index, struct pnfs_block_extent *cow_read) { struct page *page; int locked = 0; page = find_get_page(inode->i_mapping, index); if (page) goto check_page; page = find_or_create_page(inode->i_mapping, index, GFP_NOFS); if (unlikely(!page)) { dprintk("%s oom ", __func__); return ERR_PTR(-ENOMEM); } locked = 1; check_page: /* PageDirty: Other will write this out * PageWriteback: Other is writing this out * PageUptodate: It was read before */ if (PageDirty(page) || PageWriteback(page)) { print_page(page); if (locked) unlock_page(page); page_cache_release(page); return NULL; } if (!locked) { lock_page(page); locked = 1; goto check_page; } if (!PageUptodate(page)) { /* New page, readin or zero it */ init_page_for_write(page, cow_read); } set_page_writeback(page); unlock_page(page); return page; } |
155e7524f pnfsblock: add bl... |
548 |
static enum pnfs_try_status |
650e2d39b pnfsblock: bl_wri... |
549 |
bl_write_pagelist(struct nfs_write_data *wdata, int sync) |
155e7524f pnfsblock: add bl... |
550 |
{ |
71cdd40fd pnfsblock: write_... |
551 |
int i, ret, npg_zero, pg_index, last = 0; |
650e2d39b pnfsblock: bl_wri... |
552 |
struct bio *bio = NULL; |
71cdd40fd pnfsblock: write_... |
553 554 |
struct pnfs_block_extent *be = NULL, *cow_read = NULL; sector_t isect, last_isect = 0, extent_length = 0; |
650e2d39b pnfsblock: bl_wri... |
555 556 557 558 |
struct parallel_io *par; loff_t offset = wdata->args.offset; size_t count = wdata->args.count; struct page **pages = wdata->args.pages; |
71cdd40fd pnfsblock: write_... |
559 560 561 562 563 |
struct page *page; pgoff_t index; u64 temp; int npg_per_block = NFS_SERVER(wdata->inode)->pnfs_blksize >> PAGE_CACHE_SHIFT; |
650e2d39b pnfsblock: bl_wri... |
564 565 566 567 |
dprintk("%s enter, %Zu@%lld ", __func__, count, offset); /* At this point, wdata->pages is a (sequential) list of nfs_pages. |
71cdd40fd pnfsblock: write_... |
568 569 |
* We want to write each, and if there is an error set pnfs_error * to have it redone using nfs. |
650e2d39b pnfsblock: bl_wri... |
570 571 572 |
*/ par = alloc_parallel(wdata); if (!par) |
7c5465d6c pnfsblock: alloc ... |
573 |
goto out_mds; |
650e2d39b pnfsblock: bl_wri... |
574 575 576 577 |
par->pnfs_callback = bl_end_par_io_write; /* At this point, have to be more careful with error handling */ isect = (sector_t) ((offset & (long)PAGE_CACHE_MASK) >> SECTOR_SHIFT); |
71cdd40fd pnfsblock: write_... |
578 579 580 581 |
be = bl_find_get_extent(BLK_LSEG2EXT(wdata->lseg), isect, &cow_read); if (!be || !is_writable(be, isect)) { dprintk("%s no matching extents! ", __func__); |
7c5465d6c pnfsblock: alloc ... |
582 |
goto out_mds; |
71cdd40fd pnfsblock: write_... |
583 584 585 586 |
} /* First page inside INVALID extent */ if (be->be_state == PNFS_BLOCK_INVALID_DATA) { |
7c5465d6c pnfsblock: alloc ... |
587 588 589 590 |
if (likely(!bl_push_one_short_extent(be->be_inval))) par->bse_count++; else goto out_mds; |
71cdd40fd pnfsblock: write_... |
591 592 593 594 595 596 597 598 599 600 |
temp = offset >> PAGE_CACHE_SHIFT; npg_zero = do_div(temp, npg_per_block); isect = (sector_t) (((offset - npg_zero * PAGE_CACHE_SIZE) & (long)PAGE_CACHE_MASK) >> SECTOR_SHIFT); extent_length = be->be_length - (isect - be->be_f_offset); fill_invalid_ext: dprintk("%s need to zero %d pages ", __func__, npg_zero); for (;npg_zero > 0; npg_zero--) { |
754227451 pnfsblock: fix wr... |
601 602 603 604 605 606 |
if (bl_is_sector_init(be->be_inval, isect)) { dprintk("isect %llu already init ", (unsigned long long)isect); goto next_page; } |
71cdd40fd pnfsblock: write_... |
607 608 609 610 611 612 |
/* page ref released in bl_end_io_write_zero */ index = isect >> PAGE_CACHE_SECTOR_SHIFT; dprintk("%s zero %dth page: index %lu isect %llu ", __func__, npg_zero, index, (unsigned long long)isect); |
72c508879 pnfsblock: move f... |
613 614 615 616 |
page = bl_find_get_zeroing_page(wdata->inode, index, cow_read); if (unlikely(IS_ERR(page))) { wdata->pnfs_error = PTR_ERR(page); |
71cdd40fd pnfsblock: write_... |
617 |
goto out; |
72c508879 pnfsblock: move f... |
618 |
} else if (page == NULL) |
71cdd40fd pnfsblock: write_... |
619 |
goto next_page; |
71cdd40fd pnfsblock: write_... |
620 621 |
ret = bl_mark_sectors_init(be->be_inval, isect, |
60c52e3a7 pnfsblock: cleanu... |
622 |
PAGE_CACHE_SECTORS); |
71cdd40fd pnfsblock: write_... |
623 624 625 626 627 628 629 630 631 |
if (unlikely(ret)) { dprintk("%s bl_mark_sectors_init fail %d ", __func__, ret); end_page_writeback(page); page_cache_release(page); wdata->pnfs_error = ret; goto out; } |
7c5465d6c pnfsblock: alloc ... |
632 633 634 635 636 637 638 639 640 641 642 643 |
if (likely(!bl_push_one_short_extent(be->be_inval))) par->bse_count++; else { end_page_writeback(page); page_cache_release(page); wdata->pnfs_error = -ENOMEM; goto out; } /* FIXME: This should be done in bi_end_io */ mark_extents_written(BLK_LSEG2EXT(wdata->lseg), page->index << PAGE_CACHE_SHIFT, PAGE_CACHE_SIZE); |
71cdd40fd pnfsblock: write_... |
644 645 646 647 648 |
bio = bl_add_page_to_bio(bio, npg_zero, WRITE, isect, page, be, bl_end_io_write_zero, par); if (IS_ERR(bio)) { wdata->pnfs_error = PTR_ERR(bio); |
e6d05a757 pnfsblock: fix NU... |
649 |
bio = NULL; |
71cdd40fd pnfsblock: write_... |
650 651 |
goto out; } |
71cdd40fd pnfsblock: write_... |
652 653 654 655 656 657 658 659 660 661 662 663 |
next_page: isect += PAGE_CACHE_SECTORS; extent_length -= PAGE_CACHE_SECTORS; } if (last) goto write_done; } bio = bl_submit_bio(WRITE, bio); /* Middle pages */ pg_index = wdata->args.pgbase >> PAGE_CACHE_SHIFT; for (i = pg_index; i < wdata->npages; i++) { |
650e2d39b pnfsblock: bl_wri... |
664 665 666 667 668 669 670 671 |
if (!extent_length) { /* We've used up the previous extent */ bl_put_extent(be); bio = bl_submit_bio(WRITE, bio); /* Get the next one */ be = bl_find_get_extent(BLK_LSEG2EXT(wdata->lseg), isect, NULL); if (!be || !is_writable(be, isect)) { |
71cdd40fd pnfsblock: write_... |
672 |
wdata->pnfs_error = -EINVAL; |
650e2d39b pnfsblock: bl_wri... |
673 674 |
goto out; } |
7c5465d6c pnfsblock: alloc ... |
675 676 677 678 679 680 681 682 683 |
if (be->be_state == PNFS_BLOCK_INVALID_DATA) { if (likely(!bl_push_one_short_extent( be->be_inval))) par->bse_count++; else { wdata->pnfs_error = -ENOMEM; goto out; } } |
650e2d39b pnfsblock: bl_wri... |
684 |
extent_length = be->be_length - |
71cdd40fd pnfsblock: write_... |
685 |
(isect - be->be_f_offset); |
650e2d39b pnfsblock: bl_wri... |
686 |
} |
71cdd40fd pnfsblock: write_... |
687 688 |
if (be->be_state == PNFS_BLOCK_INVALID_DATA) { ret = bl_mark_sectors_init(be->be_inval, isect, |
60c52e3a7 pnfsblock: cleanu... |
689 |
PAGE_CACHE_SECTORS); |
71cdd40fd pnfsblock: write_... |
690 691 692 693 694 695 |
if (unlikely(ret)) { dprintk("%s bl_mark_sectors_init fail %d ", __func__, ret); wdata->pnfs_error = ret; goto out; |
650e2d39b pnfsblock: bl_wri... |
696 |
} |
71cdd40fd pnfsblock: write_... |
697 698 699 700 701 702 |
} bio = bl_add_page_to_bio(bio, wdata->npages - i, WRITE, isect, pages[i], be, bl_end_io_write, par); if (IS_ERR(bio)) { wdata->pnfs_error = PTR_ERR(bio); |
e6d05a757 pnfsblock: fix NU... |
703 |
bio = NULL; |
71cdd40fd pnfsblock: write_... |
704 |
goto out; |
650e2d39b pnfsblock: bl_wri... |
705 706 |
} isect += PAGE_CACHE_SECTORS; |
71cdd40fd pnfsblock: write_... |
707 |
last_isect = isect; |
650e2d39b pnfsblock: bl_wri... |
708 709 |
extent_length -= PAGE_CACHE_SECTORS; } |
71cdd40fd pnfsblock: write_... |
710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 |
/* Last page inside INVALID extent */ if (be->be_state == PNFS_BLOCK_INVALID_DATA) { bio = bl_submit_bio(WRITE, bio); temp = last_isect >> PAGE_CACHE_SECTOR_SHIFT; npg_zero = npg_per_block - do_div(temp, npg_per_block); if (npg_zero < npg_per_block) { last = 1; goto fill_invalid_ext; } } write_done: wdata->res.count = (last_isect << SECTOR_SHIFT) - (offset); if (count < wdata->res.count) { |
650e2d39b pnfsblock: bl_wri... |
725 |
wdata->res.count = count; |
71cdd40fd pnfsblock: write_... |
726 |
} |
650e2d39b pnfsblock: bl_wri... |
727 728 729 730 731 |
out: bl_put_extent(be); bl_submit_bio(WRITE, bio); put_parallel(par); return PNFS_ATTEMPTED; |
7c5465d6c pnfsblock: alloc ... |
732 733 734 735 |
out_mds: bl_put_extent(be); kfree(par); return PNFS_NOT_ATTEMPTED; |
155e7524f pnfsblock: add bl... |
736 |
} |
9e6929699 pnfsblock: basic ... |
737 |
/* FIXME - range ignored */ |
155e7524f pnfsblock: add bl... |
738 |
static void |
9e6929699 pnfsblock: basic ... |
739 |
release_extents(struct pnfs_block_layout *bl, struct pnfs_layout_range *range) |
155e7524f pnfsblock: add bl... |
740 |
{ |
9e6929699 pnfsblock: basic ... |
741 742 743 744 745 746 747 748 749 750 751 752 753 754 |
int i; struct pnfs_block_extent *be; spin_lock(&bl->bl_ext_lock); for (i = 0; i < EXTENT_LISTS; i++) { while (!list_empty(&bl->bl_extents[i])) { be = list_first_entry(&bl->bl_extents[i], struct pnfs_block_extent, be_node); list_del(&be->be_node); bl_put_extent(be); } } spin_unlock(&bl->bl_ext_lock); |
155e7524f pnfsblock: add bl... |
755 |
} |
155e7524f pnfsblock: add bl... |
756 757 758 |
static void release_inval_marks(struct pnfs_inval_markings *marks) { |
c1c2a4cd3 pnfsblock: add ex... |
759 |
struct pnfs_inval_tracking *pos, *temp; |
7c5465d6c pnfsblock: alloc ... |
760 |
struct pnfs_block_short_extent *se, *stemp; |
c1c2a4cd3 pnfsblock: add ex... |
761 762 763 764 765 |
list_for_each_entry_safe(pos, temp, &marks->im_tree.mtt_stub, it_link) { list_del(&pos->it_link); kfree(pos); } |
7c5465d6c pnfsblock: alloc ... |
766 767 768 769 770 |
list_for_each_entry_safe(se, stemp, &marks->im_extents, bse_node) { list_del(&se->bse_node); kfree(se); } |
155e7524f pnfsblock: add bl... |
771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 |
return; } static void bl_free_layout_hdr(struct pnfs_layout_hdr *lo) { struct pnfs_block_layout *bl = BLK_LO2EXT(lo); dprintk("%s enter ", __func__); release_extents(bl, NULL); release_inval_marks(&bl->bl_inval); kfree(bl); } static struct pnfs_layout_hdr *bl_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags) { struct pnfs_block_layout *bl; dprintk("%s enter ", __func__); bl = kzalloc(sizeof(*bl), gfp_flags); if (!bl) return NULL; spin_lock_init(&bl->bl_ext_lock); INIT_LIST_HEAD(&bl->bl_extents[0]); INIT_LIST_HEAD(&bl->bl_extents[1]); INIT_LIST_HEAD(&bl->bl_commit); INIT_LIST_HEAD(&bl->bl_committing); bl->bl_count = 0; bl->bl_blocksize = NFS_SERVER(inode)->pnfs_blksize >> SECTOR_SHIFT; BL_INIT_INVAL_MARKS(&bl->bl_inval, bl->bl_blocksize); return &bl->bl_layout; } |
a60d2ebd9 pnfsblock: lseg a... |
805 |
static void bl_free_lseg(struct pnfs_layout_segment *lseg) |
155e7524f pnfsblock: add bl... |
806 |
{ |
a60d2ebd9 pnfsblock: lseg a... |
807 808 809 |
dprintk("%s enter ", __func__); kfree(lseg); |
155e7524f pnfsblock: add bl... |
810 |
} |
a60d2ebd9 pnfsblock: lseg a... |
811 812 813 814 815 816 |
/* We pretty much ignore lseg, and store all data layout wide, so we * can correctly merge. */ static struct pnfs_layout_segment *bl_alloc_lseg(struct pnfs_layout_hdr *lo, struct nfs4_layoutget_res *lgr, gfp_t gfp_flags) |
155e7524f pnfsblock: add bl... |
817 |
{ |
a60d2ebd9 pnfsblock: lseg a... |
818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 |
struct pnfs_layout_segment *lseg; int status; dprintk("%s enter ", __func__); lseg = kzalloc(sizeof(*lseg), gfp_flags); if (!lseg) return ERR_PTR(-ENOMEM); status = nfs4_blk_process_layoutget(lo, lgr, gfp_flags); if (status) { /* We don't want to call the full-blown bl_free_lseg, * since on error extents were not touched. */ kfree(lseg); return ERR_PTR(status); } return lseg; |
155e7524f pnfsblock: add bl... |
835 836 837 838 839 840 |
} static void bl_encode_layoutcommit(struct pnfs_layout_hdr *lo, struct xdr_stream *xdr, const struct nfs4_layoutcommit_args *arg) { |
90ace12ac pnfsblock: encode... |
841 842 843 |
dprintk("%s enter ", __func__); encode_pnfs_block_layoutupdate(BLK_LO2EXT(lo), xdr, arg); |
155e7524f pnfsblock: add bl... |
844 845 846 847 848 |
} static void bl_cleanup_layoutcommit(struct nfs4_layoutcommit_data *lcdata) { |
b2be7811d pnfsblock: cleanu... |
849 850 851 852 853 |
struct pnfs_layout_hdr *lo = NFS_I(lcdata->args.inode)->layout; dprintk("%s enter ", __func__); clean_pnfs_block_layoutupdate(BLK_LO2EXT(lo), &lcdata->args, lcdata->res.status); |
155e7524f pnfsblock: add bl... |
854 |
} |
2f9fd1826 pnfsblock: call a... |
855 856 857 |
static void free_blk_mountid(struct block_mount_id *mid) { if (mid) { |
93a3844ee pnfsblock: don't ... |
858 859 860 861 |
struct pnfs_block_dev *dev, *tmp; /* No need to take bm_lock as we are last user freeing bm_devlist */ list_for_each_entry_safe(dev, tmp, &mid->bm_devlist, bm_node) { |
2f9fd1826 pnfsblock: call a... |
862 863 864 |
list_del(&dev->bm_node); bl_free_block_dev(dev); } |
2f9fd1826 pnfsblock: call a... |
865 866 867 868 869 870 871 872 873 874 875 876 |
kfree(mid); } } /* This is mostly copied from the filelayout's get_device_info function. * It seems much of this should be at the generic pnfs level. */ static struct pnfs_block_dev * nfs4_blk_get_deviceinfo(struct nfs_server *server, const struct nfs_fh *fh, struct nfs4_deviceid *d_id) { struct pnfs_device *dev; |
516f2e24f pnfsblock: fix re... |
877 |
struct pnfs_block_dev *rv; |
2f9fd1826 pnfsblock: call a... |
878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 |
u32 max_resp_sz; int max_pages; struct page **pages = NULL; int i, rc; /* * Use the session max response size as the basis for setting * GETDEVICEINFO's maxcount */ max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz; max_pages = max_resp_sz >> PAGE_SHIFT; dprintk("%s max_resp_sz %u max_pages %d ", __func__, max_resp_sz, max_pages); dev = kmalloc(sizeof(*dev), GFP_NOFS); if (!dev) { dprintk("%s kmalloc failed ", __func__); |
516f2e24f pnfsblock: fix re... |
897 |
return ERR_PTR(-ENOMEM); |
2f9fd1826 pnfsblock: call a... |
898 899 900 901 902 |
} pages = kzalloc(max_pages * sizeof(struct page *), GFP_NOFS); if (pages == NULL) { kfree(dev); |
516f2e24f pnfsblock: fix re... |
903 |
return ERR_PTR(-ENOMEM); |
2f9fd1826 pnfsblock: call a... |
904 905 906 |
} for (i = 0; i < max_pages; i++) { pages[i] = alloc_page(GFP_NOFS); |
516f2e24f pnfsblock: fix re... |
907 908 |
if (!pages[i]) { rv = ERR_PTR(-ENOMEM); |
2f9fd1826 pnfsblock: call a... |
909 |
goto out_free; |
516f2e24f pnfsblock: fix re... |
910 |
} |
2f9fd1826 pnfsblock: call a... |
911 912 913 914 915 916 917 918 919 920 921 922 923 924 |
} memcpy(&dev->dev_id, d_id, sizeof(*d_id)); dev->layout_type = LAYOUT_BLOCK_VOLUME; dev->pages = pages; dev->pgbase = 0; dev->pglen = PAGE_SIZE * max_pages; dev->mincount = 0; dprintk("%s: dev_id: %s ", __func__, dev->dev_id.data); rc = nfs4_proc_getdeviceinfo(server, dev); dprintk("%s getdevice info returns %d ", __func__, rc); |
516f2e24f pnfsblock: fix re... |
925 926 |
if (rc) { rv = ERR_PTR(rc); |
2f9fd1826 pnfsblock: call a... |
927 |
goto out_free; |
516f2e24f pnfsblock: fix re... |
928 |
} |
2f9fd1826 pnfsblock: call a... |
929 930 931 932 933 934 935 936 937 |
rv = nfs4_blk_decode_device(server, dev); out_free: for (i = 0; i < max_pages; i++) __free_page(pages[i]); kfree(pages); kfree(dev); return rv; } |
155e7524f pnfsblock: add bl... |
938 939 940 |
static int bl_set_layoutdriver(struct nfs_server *server, const struct nfs_fh *fh) { |
2f9fd1826 pnfsblock: call a... |
941 942 943 944 |
struct block_mount_id *b_mt_id = NULL; struct pnfs_devicelist *dlist = NULL; struct pnfs_block_dev *bdev; LIST_HEAD(block_disklist); |
516f2e24f pnfsblock: fix re... |
945 |
int status, i; |
2f9fd1826 pnfsblock: call a... |
946 |
|
155e7524f pnfsblock: add bl... |
947 948 |
dprintk("%s enter ", __func__); |
2f9fd1826 pnfsblock: call a... |
949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 |
if (server->pnfs_blksize == 0) { dprintk("%s Server did not return blksize ", __func__); return -EINVAL; } b_mt_id = kzalloc(sizeof(struct block_mount_id), GFP_NOFS); if (!b_mt_id) { status = -ENOMEM; goto out_error; } /* Initialize nfs4 block layout mount id */ spin_lock_init(&b_mt_id->bm_lock); INIT_LIST_HEAD(&b_mt_id->bm_devlist); dlist = kmalloc(sizeof(struct pnfs_devicelist), GFP_NOFS); if (!dlist) { status = -ENOMEM; goto out_error; } dlist->eof = 0; while (!dlist->eof) { status = nfs4_proc_getdevicelist(server, fh, dlist); if (status) goto out_error; dprintk("%s GETDEVICELIST numdevs=%i, eof=%i ", __func__, dlist->num_devs, dlist->eof); for (i = 0; i < dlist->num_devs; i++) { bdev = nfs4_blk_get_deviceinfo(server, fh, &dlist->dev_id[i]); |
516f2e24f pnfsblock: fix re... |
980 981 |
if (IS_ERR(bdev)) { status = PTR_ERR(bdev); |
2f9fd1826 pnfsblock: call a... |
982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 |
goto out_error; } spin_lock(&b_mt_id->bm_lock); list_add(&bdev->bm_node, &b_mt_id->bm_devlist); spin_unlock(&b_mt_id->bm_lock); } } dprintk("%s SUCCESS ", __func__); server->pnfs_ld_data = b_mt_id; out_return: kfree(dlist); return status; out_error: free_blk_mountid(b_mt_id); goto out_return; |
155e7524f pnfsblock: add bl... |
1000 1001 1002 1003 1004 |
} static int bl_clear_layoutdriver(struct nfs_server *server) { |
2f9fd1826 pnfsblock: call a... |
1005 |
struct block_mount_id *b_mt_id = server->pnfs_ld_data; |
155e7524f pnfsblock: add bl... |
1006 1007 |
dprintk("%s enter ", __func__); |
2f9fd1826 pnfsblock: call a... |
1008 1009 1010 |
free_blk_mountid(b_mt_id); dprintk("%s RETURNS ", __func__); |
155e7524f pnfsblock: add bl... |
1011 1012 |
return 0; } |
e9643fe80 pnfsblock: use pa... |
1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 |
static const struct nfs_pageio_ops bl_pg_read_ops = { .pg_init = pnfs_generic_pg_init_read, .pg_test = pnfs_generic_pg_test, .pg_doio = pnfs_generic_pg_readpages, }; static const struct nfs_pageio_ops bl_pg_write_ops = { .pg_init = pnfs_generic_pg_init_write, .pg_test = pnfs_generic_pg_test, .pg_doio = pnfs_generic_pg_writepages, }; |
155e7524f pnfsblock: add bl... |
1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 |
static struct pnfs_layoutdriver_type blocklayout_type = { .id = LAYOUT_BLOCK_VOLUME, .name = "LAYOUT_BLOCK_VOLUME", .read_pagelist = bl_read_pagelist, .write_pagelist = bl_write_pagelist, .alloc_layout_hdr = bl_alloc_layout_hdr, .free_layout_hdr = bl_free_layout_hdr, .alloc_lseg = bl_alloc_lseg, .free_lseg = bl_free_lseg, .encode_layoutcommit = bl_encode_layoutcommit, .cleanup_layoutcommit = bl_cleanup_layoutcommit, .set_layoutdriver = bl_set_layoutdriver, .clear_layoutdriver = bl_clear_layoutdriver, |
e9643fe80 pnfsblock: use pa... |
1037 1038 |
.pg_read_ops = &bl_pg_read_ops, .pg_write_ops = &bl_pg_write_ops, |
155e7524f pnfsblock: add bl... |
1039 |
}; |
fe0a9b740 pnfsblock: add de... |
1040 |
static const struct rpc_pipe_ops bl_upcall_ops = { |
c1225158a SUNRPC/NFS: make ... |
1041 |
.upcall = rpc_pipe_generic_upcall, |
fe0a9b740 pnfsblock: add de... |
1042 1043 1044 |
.downcall = bl_pipe_downcall, .destroy_msg = bl_pipe_destroy_msg, }; |
155e7524f pnfsblock: add bl... |
1045 1046 |
static int __init nfs4blocklayout_init(void) { |
fe0a9b740 pnfsblock: add de... |
1047 1048 |
struct vfsmount *mnt; struct path path; |
155e7524f pnfsblock: add bl... |
1049 1050 1051 1052 1053 1054 |
int ret; dprintk("%s: NFSv4 Block Layout Driver Registering... ", __func__); ret = pnfs_register_layoutdriver(&blocklayout_type); |
fe0a9b740 pnfsblock: add de... |
1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 |
if (ret) goto out; init_waitqueue_head(&bl_wq); mnt = rpc_get_mount(); if (IS_ERR(mnt)) { ret = PTR_ERR(mnt); goto out_remove; } ret = vfs_path_lookup(mnt->mnt_root, mnt, NFS_PIPE_DIRNAME, 0, &path); if (ret) |
760383f1e pnfsblock: add mi... |
1070 |
goto out_putrpc; |
fe0a9b740 pnfsblock: add de... |
1071 1072 1073 |
bl_device_pipe = rpc_mkpipe(path.dentry, "blocklayout", NULL, &bl_upcall_ops, 0); |
760383f1e pnfsblock: add mi... |
1074 |
path_put(&path); |
fe0a9b740 pnfsblock: add de... |
1075 1076 |
if (IS_ERR(bl_device_pipe)) { ret = PTR_ERR(bl_device_pipe); |
760383f1e pnfsblock: add mi... |
1077 |
goto out_putrpc; |
fe0a9b740 pnfsblock: add de... |
1078 1079 1080 |
} out: return ret; |
760383f1e pnfsblock: add mi... |
1081 1082 |
out_putrpc: rpc_put_mount(); |
fe0a9b740 pnfsblock: add de... |
1083 1084 |
out_remove: pnfs_unregister_layoutdriver(&blocklayout_type); |
155e7524f pnfsblock: add bl... |
1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 |
return ret; } static void __exit nfs4blocklayout_exit(void) { dprintk("%s: NFSv4 Block Layout Driver Unregistering... ", __func__); pnfs_unregister_layoutdriver(&blocklayout_type); |
fe0a9b740 pnfsblock: add de... |
1095 |
rpc_unlink(bl_device_pipe); |
760383f1e pnfsblock: add mi... |
1096 |
rpc_put_mount(); |
155e7524f pnfsblock: add bl... |
1097 1098 1099 1100 1101 1102 |
} MODULE_ALIAS("nfs-layouttype4-3"); module_init(nfs4blocklayout_init); module_exit(nfs4blocklayout_exit); |