Blame view
fs/dax.c
40.6 KB
d475c6346
|
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 |
/* * fs/dax.c - Direct Access filesystem code * Copyright (c) 2013-2014 Intel Corporation * Author: Matthew Wilcox <matthew.r.wilcox@intel.com> * Author: Ross Zwisler <ross.zwisler@linux.intel.com> * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, * version 2, as published by the Free Software Foundation. * * This program is distributed in the hope it will be useful, but WITHOUT * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for * more details. */ #include <linux/atomic.h> #include <linux/blkdev.h> #include <linux/buffer_head.h> |
d77e92e27
|
20 |
#include <linux/dax.h> |
d475c6346
|
21 22 |
#include <linux/fs.h> #include <linux/genhd.h> |
f7ca90b16
|
23 24 25 |
#include <linux/highmem.h> #include <linux/memcontrol.h> #include <linux/mm.h> |
d475c6346
|
26 |
#include <linux/mutex.h> |
9973c98ec
|
27 |
#include <linux/pagevec.h> |
2765cfbb3
|
28 |
#include <linux/pmem.h> |
289c6aeda
|
29 |
#include <linux/sched.h> |
d475c6346
|
30 |
#include <linux/uio.h> |
f7ca90b16
|
31 |
#include <linux/vmstat.h> |
34c0fd540
|
32 |
#include <linux/pfn_t.h> |
0e749e542
|
33 |
#include <linux/sizes.h> |
a254e5681
|
34 35 |
#include <linux/iomap.h> #include "internal.h" |
d475c6346
|
36 |
|
e804315dd
|
37 38 39 40 41 42 43 44 45 |
/* * We use lowest available bit in exceptional entry for locking, other two * bits to determine entry type. In total 3 special bits. */ #define RADIX_DAX_SHIFT (RADIX_TREE_EXCEPTIONAL_SHIFT + 3) #define RADIX_DAX_PTE (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1)) #define RADIX_DAX_PMD (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2)) #define RADIX_DAX_TYPE_MASK (RADIX_DAX_PTE | RADIX_DAX_PMD) #define RADIX_DAX_TYPE(entry) ((unsigned long)entry & RADIX_DAX_TYPE_MASK) |
78a9be0a0
|
46 47 |
#define RADIX_DAX_SECTOR(entry) (((unsigned long)entry >> RADIX_DAX_SHIFT)) #define RADIX_DAX_ENTRY(sector, pmd) ((void *)((unsigned long)sector << \ |
e804315dd
|
48 49 |
RADIX_DAX_SHIFT | (pmd ? RADIX_DAX_PMD : RADIX_DAX_PTE) | \ RADIX_TREE_EXCEPTIONAL_ENTRY)) |
e4b274915
|
50 |
|
ac401cc78
|
51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 |
/* We choose 4096 entries - same as per-zone page wait tables */ #define DAX_WAIT_TABLE_BITS 12 #define DAX_WAIT_TABLE_ENTRIES (1 << DAX_WAIT_TABLE_BITS) wait_queue_head_t wait_table[DAX_WAIT_TABLE_ENTRIES]; static int __init init_dax_wait_table(void) { int i; for (i = 0; i < DAX_WAIT_TABLE_ENTRIES; i++) init_waitqueue_head(wait_table + i); return 0; } fs_initcall(init_dax_wait_table); static wait_queue_head_t *dax_entry_waitqueue(struct address_space *mapping, pgoff_t index) { unsigned long hash = hash_long((unsigned long)mapping ^ index, DAX_WAIT_TABLE_BITS); return wait_table + hash; } |
78a9be0a0
|
74 |
|
b2e0d1625
|
75 76 77 78 |
static long dax_map_atomic(struct block_device *bdev, struct blk_dax_ctl *dax) { struct request_queue *q = bdev->bd_queue; long rc = -EIO; |
7a9eb2066
|
79 |
dax->addr = ERR_PTR(-EIO); |
b2e0d1625
|
80 81 82 83 84 |
if (blk_queue_enter(q, true) != 0) return rc; rc = bdev_direct_access(bdev, dax); if (rc < 0) { |
7a9eb2066
|
85 |
dax->addr = ERR_PTR(rc); |
b2e0d1625
|
86 87 88 89 90 91 92 93 94 95 96 97 98 |
blk_queue_exit(q); return rc; } return rc; } static void dax_unmap_atomic(struct block_device *bdev, const struct blk_dax_ctl *dax) { if (IS_ERR(dax->addr)) return; blk_queue_exit(bdev->bd_queue); } |
d1a5f2b4d
|
99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 |
struct page *read_dax_sector(struct block_device *bdev, sector_t n) { struct page *page = alloc_pages(GFP_KERNEL, 0); struct blk_dax_ctl dax = { .size = PAGE_SIZE, .sector = n & ~((((int) PAGE_SIZE) / 512) - 1), }; long rc; if (!page) return ERR_PTR(-ENOMEM); rc = dax_map_atomic(bdev, &dax); if (rc < 0) return ERR_PTR(rc); memcpy_from_pmem(page_address(page), dax.addr, PAGE_SIZE); dax_unmap_atomic(bdev, &dax); return page; } |
d475c6346
|
118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 |
static bool buffer_written(struct buffer_head *bh) { return buffer_mapped(bh) && !buffer_unwritten(bh); } /* * When ext4 encounters a hole, it returns without modifying the buffer_head * which means that we can't trust b_size. To cope with this, we set b_state * to 0 before calling get_block and, if any bit is set, we know we can trust * b_size. Unfortunate, really, since ext4 knows precisely how long a hole is * and would save us time calling get_block repeatedly. */ static bool buffer_size_valid(struct buffer_head *bh) { return bh->b_state != 0; } |
b2e0d1625
|
134 135 136 137 138 139 140 141 |
static sector_t to_sector(const struct buffer_head *bh, const struct inode *inode) { sector_t sector = bh->b_blocknr << (inode->i_blkbits - 9); return sector; } |
a95cd6311
|
142 143 144 |
static ssize_t dax_io(struct inode *inode, struct iov_iter *iter, loff_t start, loff_t end, get_block_t get_block, struct buffer_head *bh) |
d475c6346
|
145 |
{ |
b2e0d1625
|
146 |
loff_t pos = start, max = start, bh_max = start; |
14df6a4e7
|
147 |
bool hole = false; |
b2e0d1625
|
148 149 150 151 |
struct block_device *bdev = NULL; int rw = iov_iter_rw(iter), rc; long map_len = 0; struct blk_dax_ctl dax = { |
7a9eb2066
|
152 |
.addr = ERR_PTR(-EIO), |
b2e0d1625
|
153 |
}; |
069c77bc9
|
154 155 156 |
unsigned blkbits = inode->i_blkbits; sector_t file_blks = (i_size_read(inode) + (1 << blkbits) - 1) >> blkbits; |
b2e0d1625
|
157 158 |
if (rw == READ) |
d475c6346
|
159 160 161 |
end = min(end, i_size_read(inode)); while (pos < end) { |
2765cfbb3
|
162 |
size_t len; |
d475c6346
|
163 |
if (pos == max) { |
e94f5a228
|
164 165 |
long page = pos >> PAGE_SHIFT; sector_t block = page << (PAGE_SHIFT - blkbits); |
d475c6346
|
166 167 168 169 170 171 |
unsigned first = pos - (block << blkbits); long size; if (pos == bh_max) { bh->b_size = PAGE_ALIGN(end - pos); bh->b_state = 0; |
b2e0d1625
|
172 173 |
rc = get_block(inode, block, bh, rw == WRITE); if (rc) |
d475c6346
|
174 175 176 177 |
break; if (!buffer_size_valid(bh)) bh->b_size = 1 << blkbits; bh_max = pos - first + bh->b_size; |
b2e0d1625
|
178 |
bdev = bh->b_bdev; |
069c77bc9
|
179 180 181 182 183 184 185 |
/* * We allow uninitialized buffers for writes * beyond EOF as those cannot race with faults */ WARN_ON_ONCE( (buffer_new(bh) && block < file_blks) || (rw == WRITE && buffer_unwritten(bh))); |
d475c6346
|
186 187 188 189 190 191 |
} else { unsigned done = bh->b_size - (bh_max - (pos - first)); bh->b_blocknr += done >> blkbits; bh->b_size -= done; } |
b2e0d1625
|
192 |
hole = rw == READ && !buffer_written(bh); |
d475c6346
|
193 |
if (hole) { |
d475c6346
|
194 195 |
size = bh->b_size - first; } else { |
b2e0d1625
|
196 197 198 199 200 201 |
dax_unmap_atomic(bdev, &dax); dax.sector = to_sector(bh, inode); dax.size = bh->b_size; map_len = dax_map_atomic(bdev, &dax); if (map_len < 0) { rc = map_len; |
d475c6346
|
202 |
break; |
b2e0d1625
|
203 |
} |
b2e0d1625
|
204 205 |
dax.addr += first; size = map_len - first; |
d475c6346
|
206 |
} |
023954351
|
207 208 209 210 211 212 |
/* * pos + size is one past the last offset for IO, * so pos + size can overflow loff_t at extreme offsets. * Cast to u64 to catch this and get the true minimum. */ max = min_t(u64, pos + size, end); |
d475c6346
|
213 |
} |
2765cfbb3
|
214 |
if (iov_iter_rw(iter) == WRITE) { |
b2e0d1625
|
215 |
len = copy_from_iter_pmem(dax.addr, max - pos, iter); |
2765cfbb3
|
216 |
} else if (!hole) |
b2e0d1625
|
217 |
len = copy_to_iter((void __force *) dax.addr, max - pos, |
e2e05394e
|
218 |
iter); |
d475c6346
|
219 220 |
else len = iov_iter_zero(max - pos, iter); |
cadfbb6ec
|
221 |
if (!len) { |
b2e0d1625
|
222 |
rc = -EFAULT; |
d475c6346
|
223 |
break; |
cadfbb6ec
|
224 |
} |
d475c6346
|
225 226 |
pos += len; |
b2e0d1625
|
227 228 |
if (!IS_ERR(dax.addr)) dax.addr += len; |
d475c6346
|
229 |
} |
b2e0d1625
|
230 |
dax_unmap_atomic(bdev, &dax); |
2765cfbb3
|
231 |
|
b2e0d1625
|
232 |
return (pos == start) ? rc : pos - start; |
d475c6346
|
233 234 235 236 |
} /** * dax_do_io - Perform I/O to a DAX file |
d475c6346
|
237 238 239 |
* @iocb: The control block for this I/O * @inode: The file which the I/O is directed at * @iter: The addresses to do I/O from or to |
d475c6346
|
240 241 242 243 244 245 246 247 248 249 250 |
* @get_block: The filesystem method used to translate file offsets to blocks * @end_io: A filesystem callback for I/O completion * @flags: See below * * This function uses the same locking scheme as do_blockdev_direct_IO: * If @flags has DIO_LOCKING set, we assume that the i_mutex is held by the * caller for writes. For reads, we take and release the i_mutex ourselves. * If DIO_LOCKING is not set, the filesystem takes care of its own locking. * As with do_blockdev_direct_IO(), we increment i_dio_count while the I/O * is in progress. */ |
a95cd6311
|
251 |
ssize_t dax_do_io(struct kiocb *iocb, struct inode *inode, |
c8b8e32d7
|
252 |
struct iov_iter *iter, get_block_t get_block, |
a95cd6311
|
253 |
dio_iodone_t end_io, int flags) |
d475c6346
|
254 255 256 |
{ struct buffer_head bh; ssize_t retval = -EINVAL; |
c8b8e32d7
|
257 |
loff_t pos = iocb->ki_pos; |
d475c6346
|
258 259 260 |
loff_t end = pos + iov_iter_count(iter); memset(&bh, 0, sizeof(bh)); |
eab95db69
|
261 |
bh.b_bdev = inode->i_sb->s_bdev; |
d475c6346
|
262 |
|
c3d98e39d
|
263 |
if ((flags & DIO_LOCKING) && iov_iter_rw(iter) == READ) |
5955102c9
|
264 |
inode_lock(inode); |
d475c6346
|
265 266 |
/* Protects against truncate */ |
bbab37ddc
|
267 268 |
if (!(flags & DIO_SKIP_DIO_COUNT)) inode_dio_begin(inode); |
d475c6346
|
269 |
|
a95cd6311
|
270 |
retval = dax_io(inode, iter, pos, end, get_block, &bh); |
d475c6346
|
271 |
|
a95cd6311
|
272 |
if ((flags & DIO_LOCKING) && iov_iter_rw(iter) == READ) |
5955102c9
|
273 |
inode_unlock(inode); |
d475c6346
|
274 |
|
187372a3b
|
275 276 277 278 279 280 281 |
if (end_io) { int err; err = end_io(iocb, pos, retval, bh.b_private); if (err) retval = err; } |
d475c6346
|
282 |
|
bbab37ddc
|
283 284 |
if (!(flags & DIO_SKIP_DIO_COUNT)) inode_dio_end(inode); |
d475c6346
|
285 286 287 |
return retval; } EXPORT_SYMBOL_GPL(dax_do_io); |
f7ca90b16
|
288 289 |
/* |
ac401cc78
|
290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 |
* DAX radix tree locking */ struct exceptional_entry_key { struct address_space *mapping; unsigned long index; }; struct wait_exceptional_entry_queue { wait_queue_t wait; struct exceptional_entry_key key; }; static int wake_exceptional_entry_func(wait_queue_t *wait, unsigned int mode, int sync, void *keyp) { struct exceptional_entry_key *key = keyp; struct wait_exceptional_entry_queue *ewait = container_of(wait, struct wait_exceptional_entry_queue, wait); if (key->mapping != ewait->key.mapping || key->index != ewait->key.index) return 0; return autoremove_wake_function(wait, mode, sync, NULL); } /* * Check whether the given slot is locked. The function must be called with * mapping->tree_lock held */ static inline int slot_locked(struct address_space *mapping, void **slot) { unsigned long entry = (unsigned long) radix_tree_deref_slot_protected(slot, &mapping->tree_lock); return entry & RADIX_DAX_ENTRY_LOCK; } /* * Mark the given slot is locked. The function must be called with * mapping->tree_lock held */ static inline void *lock_slot(struct address_space *mapping, void **slot) { unsigned long entry = (unsigned long) radix_tree_deref_slot_protected(slot, &mapping->tree_lock); entry |= RADIX_DAX_ENTRY_LOCK; radix_tree_replace_slot(slot, (void *)entry); return (void *)entry; } /* * Mark the given slot is unlocked. The function must be called with * mapping->tree_lock held */ static inline void *unlock_slot(struct address_space *mapping, void **slot) { unsigned long entry = (unsigned long) radix_tree_deref_slot_protected(slot, &mapping->tree_lock); entry &= ~(unsigned long)RADIX_DAX_ENTRY_LOCK; radix_tree_replace_slot(slot, (void *)entry); return (void *)entry; } /* * Lookup entry in radix tree, wait for it to become unlocked if it is * exceptional entry and return it. The caller must call * put_unlocked_mapping_entry() when he decided not to lock the entry or * put_locked_mapping_entry() when he locked the entry and now wants to * unlock it. * * The function must be called with mapping->tree_lock held. */ static void *get_unlocked_mapping_entry(struct address_space *mapping, pgoff_t index, void ***slotp) { void *ret, **slot; struct wait_exceptional_entry_queue ewait; wait_queue_head_t *wq = dax_entry_waitqueue(mapping, index); init_wait(&ewait.wait); ewait.wait.func = wake_exceptional_entry_func; ewait.key.mapping = mapping; ewait.key.index = index; for (;;) { ret = __radix_tree_lookup(&mapping->page_tree, index, NULL, &slot); if (!ret || !radix_tree_exceptional_entry(ret) || !slot_locked(mapping, slot)) { if (slotp) *slotp = slot; return ret; } prepare_to_wait_exclusive(wq, &ewait.wait, TASK_UNINTERRUPTIBLE); spin_unlock_irq(&mapping->tree_lock); schedule(); finish_wait(wq, &ewait.wait); spin_lock_irq(&mapping->tree_lock); } } /* * Find radix tree entry at given index. If it points to a page, return with * the page locked. If it points to the exceptional entry, return with the * radix tree entry locked. If the radix tree doesn't contain given index, * create empty exceptional entry for the index and return with it locked. * * Note: Unlike filemap_fault() we don't honor FAULT_FLAG_RETRY flags. For * persistent memory the benefit is doubtful. We can add that later if we can * show it helps. */ static void *grab_mapping_entry(struct address_space *mapping, pgoff_t index) { void *ret, **slot; restart: spin_lock_irq(&mapping->tree_lock); ret = get_unlocked_mapping_entry(mapping, index, &slot); /* No entry for given index? Make sure radix tree is big enough. */ if (!ret) { int err; spin_unlock_irq(&mapping->tree_lock); err = radix_tree_preload( mapping_gfp_mask(mapping) & ~__GFP_HIGHMEM); if (err) return ERR_PTR(err); ret = (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY | RADIX_DAX_ENTRY_LOCK); spin_lock_irq(&mapping->tree_lock); err = radix_tree_insert(&mapping->page_tree, index, ret); radix_tree_preload_end(); if (err) { spin_unlock_irq(&mapping->tree_lock); /* Someone already created the entry? */ if (err == -EEXIST) goto restart; return ERR_PTR(err); } /* Good, we have inserted empty locked entry into the tree. */ mapping->nrexceptional++; spin_unlock_irq(&mapping->tree_lock); return ret; } /* Normal page in radix tree? */ if (!radix_tree_exceptional_entry(ret)) { struct page *page = ret; get_page(page); spin_unlock_irq(&mapping->tree_lock); lock_page(page); /* Page got truncated? Retry... */ if (unlikely(page->mapping != mapping)) { unlock_page(page); put_page(page); goto restart; } return page; } ret = lock_slot(mapping, slot); spin_unlock_irq(&mapping->tree_lock); return ret; } void dax_wake_mapping_entry_waiter(struct address_space *mapping, pgoff_t index, bool wake_all) { wait_queue_head_t *wq = dax_entry_waitqueue(mapping, index); /* * Checking for locked entry and prepare_to_wait_exclusive() happens * under mapping->tree_lock, ditto for entry handling in our callers. * So at this point all tasks that could have seen our entry locked * must be in the waitqueue and the following check will see them. */ if (waitqueue_active(wq)) { struct exceptional_entry_key key; key.mapping = mapping; key.index = index; __wake_up(wq, TASK_NORMAL, wake_all ? 0 : 1, &key); } } |
bc2466e42
|
475 |
void dax_unlock_mapping_entry(struct address_space *mapping, pgoff_t index) |
ac401cc78
|
476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 |
{ void *ret, **slot; spin_lock_irq(&mapping->tree_lock); ret = __radix_tree_lookup(&mapping->page_tree, index, NULL, &slot); if (WARN_ON_ONCE(!ret || !radix_tree_exceptional_entry(ret) || !slot_locked(mapping, slot))) { spin_unlock_irq(&mapping->tree_lock); return; } unlock_slot(mapping, slot); spin_unlock_irq(&mapping->tree_lock); dax_wake_mapping_entry_waiter(mapping, index, false); } static void put_locked_mapping_entry(struct address_space *mapping, pgoff_t index, void *entry) { if (!radix_tree_exceptional_entry(entry)) { unlock_page(entry); put_page(entry); } else { |
bc2466e42
|
498 |
dax_unlock_mapping_entry(mapping, index); |
ac401cc78
|
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 |
} } /* * Called when we are done with radix tree entry we looked up via * get_unlocked_mapping_entry() and which we didn't lock in the end. */ static void put_unlocked_mapping_entry(struct address_space *mapping, pgoff_t index, void *entry) { if (!radix_tree_exceptional_entry(entry)) return; /* We have to wake up next waiter for the radix tree entry lock */ dax_wake_mapping_entry_waiter(mapping, index, false); } /* * Delete exceptional DAX entry at @index from @mapping. Wait for radix tree * entry to get unlocked before deleting it. */ int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index) { void *entry; spin_lock_irq(&mapping->tree_lock); entry = get_unlocked_mapping_entry(mapping, index, NULL); /* * This gets called from truncate / punch_hole path. As such, the caller * must hold locks protecting against concurrent modifications of the * radix tree (usually fs-private i_mmap_sem for writing). Since the * caller has seen exceptional entry for this index, we better find it * at that index as well... */ if (WARN_ON_ONCE(!entry || !radix_tree_exceptional_entry(entry))) { spin_unlock_irq(&mapping->tree_lock); return 0; } radix_tree_delete(&mapping->page_tree, index); mapping->nrexceptional--; spin_unlock_irq(&mapping->tree_lock); dax_wake_mapping_entry_waiter(mapping, index, true); return 1; } /* |
f7ca90b16
|
546 547 548 549 550 551 552 |
* The user has performed a load from a hole in the file. Allocating * a new page in the file would cause excessive storage usage for * workloads with sparse files. We allocate a page cache page instead. * We'll kick it out of the page cache if it's ever written to, * otherwise it will simply fall out of the page cache under memory * pressure without ever having been dirtied. */ |
ac401cc78
|
553 554 |
static int dax_load_hole(struct address_space *mapping, void *entry, struct vm_fault *vmf) |
f7ca90b16
|
555 |
{ |
ac401cc78
|
556 |
struct page *page; |
f7ca90b16
|
557 |
|
ac401cc78
|
558 559 560 561 562 |
/* Hole page already exists? Return it... */ if (!radix_tree_exceptional_entry(entry)) { vmf->page = entry; return VM_FAULT_LOCKED; } |
f7ca90b16
|
563 |
|
ac401cc78
|
564 565 566 567 568 569 570 |
/* This will replace locked radix tree entry with a hole page */ page = find_or_create_page(mapping, vmf->pgoff, vmf->gfp_mask | __GFP_ZERO); if (!page) { put_locked_mapping_entry(mapping, vmf->pgoff, entry); return VM_FAULT_OOM; } |
f7ca90b16
|
571 572 573 |
vmf->page = page; return VM_FAULT_LOCKED; } |
b0d5e82fc
|
574 575 |
static int copy_user_dax(struct block_device *bdev, sector_t sector, size_t size, struct page *to, unsigned long vaddr) |
f7ca90b16
|
576 |
{ |
b2e0d1625
|
577 |
struct blk_dax_ctl dax = { |
b0d5e82fc
|
578 579 |
.sector = sector, .size = size, |
b2e0d1625
|
580 |
}; |
e2e05394e
|
581 |
void *vto; |
b2e0d1625
|
582 583 |
if (dax_map_atomic(bdev, &dax) < 0) return PTR_ERR(dax.addr); |
f7ca90b16
|
584 |
vto = kmap_atomic(to); |
b2e0d1625
|
585 |
copy_user_page(vto, (void __force *)dax.addr, vaddr, to); |
f7ca90b16
|
586 |
kunmap_atomic(vto); |
b2e0d1625
|
587 |
dax_unmap_atomic(bdev, &dax); |
f7ca90b16
|
588 589 |
return 0; } |
09cbfeaf1
|
590 |
#define DAX_PMD_INDEX(page_index) (page_index & (PMD_MASK >> PAGE_SHIFT)) |
9973c98ec
|
591 |
|
ac401cc78
|
592 593 594 |
static void *dax_insert_mapping_entry(struct address_space *mapping, struct vm_fault *vmf, void *entry, sector_t sector) |
9973c98ec
|
595 596 |
{ struct radix_tree_root *page_tree = &mapping->page_tree; |
ac401cc78
|
597 598 599 600 |
int error = 0; bool hole_fill = false; void *new_entry; pgoff_t index = vmf->pgoff; |
9973c98ec
|
601 |
|
ac401cc78
|
602 |
if (vmf->flags & FAULT_FLAG_WRITE) |
d2b2a28e6
|
603 |
__mark_inode_dirty(mapping->host, I_DIRTY_PAGES); |
9973c98ec
|
604 |
|
ac401cc78
|
605 606 607 608 609 610 611 612 613 614 615 616 |
/* Replacing hole page with block mapping? */ if (!radix_tree_exceptional_entry(entry)) { hole_fill = true; /* * Unmap the page now before we remove it from page cache below. * The page is locked so it cannot be faulted in again. */ unmap_mapping_range(mapping, vmf->pgoff << PAGE_SHIFT, PAGE_SIZE, 0); error = radix_tree_preload(vmf->gfp_mask & ~__GFP_HIGHMEM); if (error) return ERR_PTR(error); |
9973c98ec
|
617 |
} |
ac401cc78
|
618 619 620 621 622 623 624 625 626 627 |
spin_lock_irq(&mapping->tree_lock); new_entry = (void *)((unsigned long)RADIX_DAX_ENTRY(sector, false) | RADIX_DAX_ENTRY_LOCK); if (hole_fill) { __delete_from_page_cache(entry, NULL); /* Drop pagecache reference */ put_page(entry); error = radix_tree_insert(page_tree, index, new_entry); if (error) { new_entry = ERR_PTR(error); |
9973c98ec
|
628 629 |
goto unlock; } |
ac401cc78
|
630 631 632 633 |
mapping->nrexceptional++; } else { void **slot; void *ret; |
9973c98ec
|
634 |
|
ac401cc78
|
635 636 637 |
ret = __radix_tree_lookup(page_tree, index, NULL, &slot); WARN_ON_ONCE(ret != entry); radix_tree_replace_slot(slot, new_entry); |
9973c98ec
|
638 |
} |
ac401cc78
|
639 |
if (vmf->flags & FAULT_FLAG_WRITE) |
9973c98ec
|
640 641 642 |
radix_tree_tag_set(page_tree, index, PAGECACHE_TAG_DIRTY); unlock: spin_unlock_irq(&mapping->tree_lock); |
ac401cc78
|
643 644 645 646 647 648 649 650 651 652 653 654 |
if (hole_fill) { radix_tree_preload_end(); /* * We don't need hole page anymore, it has been replaced with * locked radix tree entry now. */ if (mapping->a_ops->freepage) mapping->a_ops->freepage(entry); unlock_page(entry); put_page(entry); } return new_entry; |
9973c98ec
|
655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 |
} static int dax_writeback_one(struct block_device *bdev, struct address_space *mapping, pgoff_t index, void *entry) { struct radix_tree_root *page_tree = &mapping->page_tree; int type = RADIX_DAX_TYPE(entry); struct radix_tree_node *node; struct blk_dax_ctl dax; void **slot; int ret = 0; spin_lock_irq(&mapping->tree_lock); /* * Regular page slots are stabilized by the page lock even * without the tree itself locked. These unlocked entries * need verification under the tree lock. */ if (!__radix_tree_lookup(page_tree, index, &node, &slot)) goto unlock; if (*slot != entry) goto unlock; /* another fsync thread may have already written back this entry */ if (!radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE)) goto unlock; if (WARN_ON_ONCE(type != RADIX_DAX_PTE && type != RADIX_DAX_PMD)) { ret = -EIO; goto unlock; } dax.sector = RADIX_DAX_SECTOR(entry); dax.size = (type == RADIX_DAX_PMD ? PMD_SIZE : PAGE_SIZE); spin_unlock_irq(&mapping->tree_lock); /* * We cannot hold tree_lock while calling dax_map_atomic() because it * eventually calls cond_resched(). */ ret = dax_map_atomic(bdev, &dax); if (ret < 0) return ret; if (WARN_ON_ONCE(ret < dax.size)) { ret = -EIO; goto unmap; } wb_cache_pmem(dax.addr, dax.size); spin_lock_irq(&mapping->tree_lock); radix_tree_tag_clear(page_tree, index, PAGECACHE_TAG_TOWRITE); spin_unlock_irq(&mapping->tree_lock); unmap: dax_unmap_atomic(bdev, &dax); return ret; unlock: spin_unlock_irq(&mapping->tree_lock); return ret; } /* * Flush the mapping to the persistent domain within the byte range of [start, * end]. This is required by data integrity operations to ensure file data is * on persistent storage prior to completion of the operation. */ |
7f6d5b529
|
723 724 |
int dax_writeback_mapping_range(struct address_space *mapping, struct block_device *bdev, struct writeback_control *wbc) |
9973c98ec
|
725 726 |
{ struct inode *inode = mapping->host; |
9973c98ec
|
727 728 729 730 731 732 733 734 735 |
pgoff_t start_index, end_index, pmd_index; pgoff_t indices[PAGEVEC_SIZE]; struct pagevec pvec; bool done = false; int i, ret = 0; void *entry; if (WARN_ON_ONCE(inode->i_blkbits != PAGE_SHIFT)) return -EIO; |
7f6d5b529
|
736 737 |
if (!mapping->nrexceptional || wbc->sync_mode != WB_SYNC_ALL) return 0; |
09cbfeaf1
|
738 739 |
start_index = wbc->range_start >> PAGE_SHIFT; end_index = wbc->range_end >> PAGE_SHIFT; |
9973c98ec
|
740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 |
pmd_index = DAX_PMD_INDEX(start_index); rcu_read_lock(); entry = radix_tree_lookup(&mapping->page_tree, pmd_index); rcu_read_unlock(); /* see if the start of our range is covered by a PMD entry */ if (entry && RADIX_DAX_TYPE(entry) == RADIX_DAX_PMD) start_index = pmd_index; tag_pages_for_writeback(mapping, start_index, end_index); pagevec_init(&pvec, 0); while (!done) { pvec.nr = find_get_entries_tag(mapping, start_index, PAGECACHE_TAG_TOWRITE, PAGEVEC_SIZE, pvec.pages, indices); if (pvec.nr == 0) break; for (i = 0; i < pvec.nr; i++) { if (indices[i] > end_index) { done = true; break; } ret = dax_writeback_one(bdev, mapping, indices[i], pvec.pages[i]); if (ret < 0) return ret; } } |
9973c98ec
|
773 774 775 |
return 0; } EXPORT_SYMBOL_GPL(dax_writeback_mapping_range); |
ac401cc78
|
776 |
static int dax_insert_mapping(struct address_space *mapping, |
1aaba0958
|
777 778 |
struct block_device *bdev, sector_t sector, size_t size, void **entryp, struct vm_area_struct *vma, struct vm_fault *vmf) |
f7ca90b16
|
779 |
{ |
f7ca90b16
|
780 |
unsigned long vaddr = (unsigned long)vmf->virtual_address; |
b2e0d1625
|
781 |
struct blk_dax_ctl dax = { |
1aaba0958
|
782 783 |
.sector = sector, .size = size, |
b2e0d1625
|
784 |
}; |
ac401cc78
|
785 786 |
void *ret; void *entry = *entryp; |
f7ca90b16
|
787 |
|
4d9a2c874
|
788 789 |
if (dax_map_atomic(bdev, &dax) < 0) return PTR_ERR(dax.addr); |
b2e0d1625
|
790 |
dax_unmap_atomic(bdev, &dax); |
f7ca90b16
|
791 |
|
ac401cc78
|
792 |
ret = dax_insert_mapping_entry(mapping, vmf, entry, dax.sector); |
4d9a2c874
|
793 794 |
if (IS_ERR(ret)) return PTR_ERR(ret); |
ac401cc78
|
795 |
*entryp = ret; |
9973c98ec
|
796 |
|
4d9a2c874
|
797 |
return vm_insert_mixed(vma, vaddr, dax.pfn); |
f7ca90b16
|
798 |
} |
ce5c5d554
|
799 |
/** |
6b524995a
|
800 |
* dax_fault - handle a page fault on a DAX file |
ce5c5d554
|
801 802 803 804 805 |
* @vma: The virtual memory area where the fault occurred * @vmf: The description of the fault * @get_block: The filesystem method used to translate file offsets to blocks * * When a page fault occurs, filesystems may call this helper in their |
6b524995a
|
806 |
* fault handler for DAX files. dax_fault() assumes the caller has done all |
ce5c5d554
|
807 808 |
* the necessary locking for the page fault to proceed successfully. */ |
6b524995a
|
809 |
int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, |
02fbd1397
|
810 |
get_block_t get_block) |
f7ca90b16
|
811 812 813 814 |
{ struct file *file = vma->vm_file; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; |
ac401cc78
|
815 |
void *entry; |
f7ca90b16
|
816 817 818 819 820 821 822 |
struct buffer_head bh; unsigned long vaddr = (unsigned long)vmf->virtual_address; unsigned blkbits = inode->i_blkbits; sector_t block; pgoff_t size; int error; int major = 0; |
ac401cc78
|
823 824 825 826 827 |
/* * Check whether offset isn't beyond end of file now. Caller is supposed * to hold locks serializing us with truncate / punch hole so this is * a reliable test. */ |
f7ca90b16
|
828 829 830 831 832 833 |
size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT; if (vmf->pgoff >= size) return VM_FAULT_SIGBUS; memset(&bh, 0, sizeof(bh)); block = (sector_t)vmf->pgoff << (PAGE_SHIFT - blkbits); |
eab95db69
|
834 |
bh.b_bdev = inode->i_sb->s_bdev; |
f7ca90b16
|
835 |
bh.b_size = PAGE_SIZE; |
ac401cc78
|
836 837 838 839 |
entry = grab_mapping_entry(mapping, vmf->pgoff); if (IS_ERR(entry)) { error = PTR_ERR(entry); goto out; |
f7ca90b16
|
840 841 842 843 844 845 |
} error = get_block(inode, block, &bh, 0); if (!error && (bh.b_size < PAGE_SIZE)) error = -EIO; /* fs corruption? */ if (error) |
ac401cc78
|
846 |
goto unlock_entry; |
f7ca90b16
|
847 848 849 850 |
if (vmf->cow_page) { struct page *new_page = vmf->cow_page; if (buffer_written(&bh)) |
b0d5e82fc
|
851 852 |
error = copy_user_dax(bh.b_bdev, to_sector(&bh, inode), bh.b_size, new_page, vaddr); |
f7ca90b16
|
853 854 855 |
else clear_user_highpage(new_page, vaddr); if (error) |
ac401cc78
|
856 857 858 |
goto unlock_entry; if (!radix_tree_exceptional_entry(entry)) { vmf->page = entry; |
bc2466e42
|
859 |
return VM_FAULT_LOCKED; |
ac401cc78
|
860 |
} |
bc2466e42
|
861 862 |
vmf->entry = entry; return VM_FAULT_DAX_LOCKED; |
f7ca90b16
|
863 |
} |
f7ca90b16
|
864 |
|
ac401cc78
|
865 |
if (!buffer_mapped(&bh)) { |
f7ca90b16
|
866 867 868 869 870 871 872 873 |
if (vmf->flags & FAULT_FLAG_WRITE) { error = get_block(inode, block, &bh, 1); count_vm_event(PGMAJFAULT); mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT); major = VM_FAULT_MAJOR; if (!error && (bh.b_size < PAGE_SIZE)) error = -EIO; if (error) |
ac401cc78
|
874 |
goto unlock_entry; |
f7ca90b16
|
875 |
} else { |
ac401cc78
|
876 |
return dax_load_hole(mapping, entry, vmf); |
f7ca90b16
|
877 878 |
} } |
02fbd1397
|
879 |
/* Filesystem should not return unwritten buffers to us! */ |
2b10945c5
|
880 |
WARN_ON_ONCE(buffer_unwritten(&bh) || buffer_new(&bh)); |
1aaba0958
|
881 882 |
error = dax_insert_mapping(mapping, bh.b_bdev, to_sector(&bh, inode), bh.b_size, &entry, vma, vmf); |
ac401cc78
|
883 884 |
unlock_entry: put_locked_mapping_entry(mapping, vmf->pgoff, entry); |
f7ca90b16
|
885 886 887 888 889 890 891 |
out: if (error == -ENOMEM) return VM_FAULT_OOM | major; /* -EBUSY is fine, somebody else faulted on the same PTE */ if ((error < 0) && (error != -EBUSY)) return VM_FAULT_SIGBUS | major; return VM_FAULT_NOPAGE | major; |
f7ca90b16
|
892 |
} |
f7ca90b16
|
893 |
EXPORT_SYMBOL_GPL(dax_fault); |
4c0ccfef2
|
894 |
|
348e967ab
|
895 |
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) |
844f35db1
|
896 897 898 899 900 |
/* * The 'colour' (ie low bits) within a PMD of a page offset. This comes up * more often than one might expect in the below function. */ #define PG_PMD_COLOUR ((PMD_SIZE >> PAGE_SHIFT) - 1) |
cbb38e41a
|
901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 |
static void __dax_dbg(struct buffer_head *bh, unsigned long address, const char *reason, const char *fn) { if (bh) { char bname[BDEVNAME_SIZE]; bdevname(bh->b_bdev, bname); pr_debug("%s: %s addr: %lx dev %s state %lx start %lld " "length %zd fallback: %s ", fn, current->comm, address, bname, bh->b_state, (u64)bh->b_blocknr, bh->b_size, reason); } else { pr_debug("%s: %s addr: %lx fallback: %s ", fn, current->comm, address, reason); } } #define dax_pmd_dbg(bh, address, reason) __dax_dbg(bh, address, reason, "dax_pmd") |
6b524995a
|
920 921 922 923 924 925 926 927 928 929 |
/** * dax_pmd_fault - handle a PMD fault on a DAX file * @vma: The virtual memory area where the fault occurred * @vmf: The description of the fault * @get_block: The filesystem method used to translate file offsets to blocks * * When a page fault occurs, filesystems may call this helper in their * pmd_fault handler for DAX files. */ int dax_pmd_fault(struct vm_area_struct *vma, unsigned long address, |
02fbd1397
|
930 |
pmd_t *pmd, unsigned int flags, get_block_t get_block) |
844f35db1
|
931 932 933 934 935 936 937 938 |
{ struct file *file = vma->vm_file; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; struct buffer_head bh; unsigned blkbits = inode->i_blkbits; unsigned long pmd_addr = address & PMD_MASK; bool write = flags & FAULT_FLAG_WRITE; |
b2e0d1625
|
939 |
struct block_device *bdev; |
844f35db1
|
940 |
pgoff_t size, pgoff; |
b2e0d1625
|
941 |
sector_t block; |
ac401cc78
|
942 |
int result = 0; |
9973c98ec
|
943 |
bool alloc = false; |
844f35db1
|
944 |
|
c046c321c
|
945 |
/* dax pmd mappings require pfn_t_devmap() */ |
ee82c9ed4
|
946 947 |
if (!IS_ENABLED(CONFIG_FS_DAX_PMD)) return VM_FAULT_FALLBACK; |
844f35db1
|
948 |
/* Fall back to PTEs if we're going to COW */ |
59bf4fb9d
|
949 950 |
if (write && !(vma->vm_flags & VM_SHARED)) { split_huge_pmd(vma, pmd, address); |
cbb38e41a
|
951 |
dax_pmd_dbg(NULL, address, "cow write"); |
844f35db1
|
952 |
return VM_FAULT_FALLBACK; |
59bf4fb9d
|
953 |
} |
844f35db1
|
954 |
/* If the PMD would extend outside the VMA */ |
cbb38e41a
|
955 956 |
if (pmd_addr < vma->vm_start) { dax_pmd_dbg(NULL, address, "vma start unaligned"); |
844f35db1
|
957 |
return VM_FAULT_FALLBACK; |
cbb38e41a
|
958 959 960 |
} if ((pmd_addr + PMD_SIZE) > vma->vm_end) { dax_pmd_dbg(NULL, address, "vma end unaligned"); |
844f35db1
|
961 |
return VM_FAULT_FALLBACK; |
cbb38e41a
|
962 |
} |
844f35db1
|
963 |
|
3fdd1b479
|
964 |
pgoff = linear_page_index(vma, pmd_addr); |
844f35db1
|
965 966 967 968 |
size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT; if (pgoff >= size) return VM_FAULT_SIGBUS; /* If the PMD would cover blocks out of the file */ |
cbb38e41a
|
969 970 971 |
if ((pgoff | PG_PMD_COLOUR) >= size) { dax_pmd_dbg(NULL, address, "offset + huge page size > file size"); |
844f35db1
|
972 |
return VM_FAULT_FALLBACK; |
cbb38e41a
|
973 |
} |
844f35db1
|
974 975 |
memset(&bh, 0, sizeof(bh)); |
d4bbe7068
|
976 |
bh.b_bdev = inode->i_sb->s_bdev; |
844f35db1
|
977 978 979 |
block = (sector_t)pgoff << (PAGE_SHIFT - blkbits); bh.b_size = PMD_SIZE; |
9973c98ec
|
980 981 |
if (get_block(inode, block, &bh, 0) != 0) |
844f35db1
|
982 |
return VM_FAULT_SIGBUS; |
9973c98ec
|
983 984 985 986 987 |
if (!buffer_mapped(&bh) && write) { if (get_block(inode, block, &bh, 1) != 0) return VM_FAULT_SIGBUS; alloc = true; |
2b10945c5
|
988 |
WARN_ON_ONCE(buffer_unwritten(&bh) || buffer_new(&bh)); |
9973c98ec
|
989 |
} |
b2e0d1625
|
990 |
bdev = bh.b_bdev; |
844f35db1
|
991 992 993 994 995 996 |
/* * If the filesystem isn't willing to tell us the length of a hole, * just fall back to PTEs. Calling get_block 512 times in a loop * would be silly. */ |
cbb38e41a
|
997 998 |
if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE) { dax_pmd_dbg(&bh, address, "allocated block too small"); |
9973c98ec
|
999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 |
return VM_FAULT_FALLBACK; } /* * If we allocated new storage, make sure no process has any * zero pages covering this hole */ if (alloc) { loff_t lstart = pgoff << PAGE_SHIFT; loff_t lend = lstart + PMD_SIZE - 1; /* inclusive */ truncate_pagecache_range(inode, lstart, lend); |
cbb38e41a
|
1011 |
} |
844f35db1
|
1012 |
|
b9953536c
|
1013 |
if (!write && !buffer_mapped(&bh)) { |
844f35db1
|
1014 |
spinlock_t *ptl; |
d295e3415
|
1015 |
pmd_t entry; |
6fcb52a56
|
1016 |
struct page *zero_page = mm_get_huge_zero_page(vma->vm_mm); |
d295e3415
|
1017 |
|
cbb38e41a
|
1018 1019 |
if (unlikely(!zero_page)) { dax_pmd_dbg(&bh, address, "no zero page"); |
844f35db1
|
1020 |
goto fallback; |
cbb38e41a
|
1021 |
} |
844f35db1
|
1022 |
|
d295e3415
|
1023 1024 1025 |
ptl = pmd_lock(vma->vm_mm, pmd); if (!pmd_none(*pmd)) { spin_unlock(ptl); |
cbb38e41a
|
1026 |
dax_pmd_dbg(&bh, address, "pmd already present"); |
d295e3415
|
1027 1028 |
goto fallback; } |
cbb38e41a
|
1029 1030 1031 1032 1033 |
dev_dbg(part_to_dev(bdev->bd_part), "%s: %s addr: %lx pfn: <zero> sect: %llx ", __func__, current->comm, address, (unsigned long long) to_sector(&bh, inode)); |
d295e3415
|
1034 1035 1036 |
entry = mk_pmd(zero_page, vma->vm_page_prot); entry = pmd_mkhuge(entry); set_pmd_at(vma->vm_mm, pmd_addr, pmd, entry); |
844f35db1
|
1037 |
result = VM_FAULT_NOPAGE; |
d295e3415
|
1038 |
spin_unlock(ptl); |
844f35db1
|
1039 |
} else { |
b2e0d1625
|
1040 1041 1042 1043 1044 |
struct blk_dax_ctl dax = { .sector = to_sector(&bh, inode), .size = PMD_SIZE, }; long length = dax_map_atomic(bdev, &dax); |
844f35db1
|
1045 |
if (length < 0) { |
8b3db9798
|
1046 1047 |
dax_pmd_dbg(&bh, address, "dax-error fallback"); goto fallback; |
844f35db1
|
1048 |
} |
cbb38e41a
|
1049 1050 1051 1052 1053 1054 1055 |
if (length < PMD_SIZE) { dax_pmd_dbg(&bh, address, "dax-length too small"); dax_unmap_atomic(bdev, &dax); goto fallback; } if (pfn_t_to_pfn(dax.pfn) & PG_PMD_COLOUR) { dax_pmd_dbg(&bh, address, "pfn unaligned"); |
b2e0d1625
|
1056 |
dax_unmap_atomic(bdev, &dax); |
844f35db1
|
1057 |
goto fallback; |
b2e0d1625
|
1058 |
} |
844f35db1
|
1059 |
|
c046c321c
|
1060 |
if (!pfn_t_devmap(dax.pfn)) { |
b2e0d1625
|
1061 |
dax_unmap_atomic(bdev, &dax); |
cbb38e41a
|
1062 |
dax_pmd_dbg(&bh, address, "pfn not in memmap"); |
152d7bd80
|
1063 |
goto fallback; |
b2e0d1625
|
1064 |
} |
b2e0d1625
|
1065 |
dax_unmap_atomic(bdev, &dax); |
0f90cc660
|
1066 |
|
9973c98ec
|
1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 |
/* * For PTE faults we insert a radix tree entry for reads, and * leave it clean. Then on the first write we dirty the radix * tree entry via the dax_pfn_mkwrite() path. This sequence * allows the dax_pfn_mkwrite() call to be simpler and avoid a * call into get_block() to translate the pgoff to a sector in * order to be able to create a new radix tree entry. * * The PMD path doesn't have an equivalent to * dax_pfn_mkwrite(), though, so for a read followed by a |
6b524995a
|
1077 |
* write we traverse all the way through dax_pmd_fault() |
9973c98ec
|
1078 1079 1080 1081 1082 |
* twice. This means we can just skip inserting a radix tree * entry completely on the initial read and just wait until * the write to insert a dirty entry. */ if (write) { |
ac401cc78
|
1083 1084 1085 1086 |
/* * We should insert radix-tree entry and dirty it here. * For now this is broken... */ |
9973c98ec
|
1087 |
} |
cbb38e41a
|
1088 1089 1090 1091 1092 1093 |
dev_dbg(part_to_dev(bdev->bd_part), "%s: %s addr: %lx pfn: %lx sect: %llx ", __func__, current->comm, address, pfn_t_to_pfn(dax.pfn), (unsigned long long) dax.sector); |
34c0fd540
|
1094 |
result |= vmf_insert_pfn_pmd(vma, address, pmd, |
f25748e3c
|
1095 |
dax.pfn, write); |
844f35db1
|
1096 1097 1098 |
} out: |
844f35db1
|
1099 1100 1101 1102 1103 1104 1105 |
return result; fallback: count_vm_event(THP_FAULT_FALLBACK); result = VM_FAULT_FALLBACK; goto out; } |
844f35db1
|
1106 |
EXPORT_SYMBOL_GPL(dax_pmd_fault); |
dd8a2b6c2
|
1107 |
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ |
844f35db1
|
1108 |
|
4c0ccfef2
|
1109 |
/** |
0e3b210ce
|
1110 1111 1112 |
* dax_pfn_mkwrite - handle first write to DAX page * @vma: The virtual memory area where the fault occurred * @vmf: The description of the fault |
0e3b210ce
|
1113 1114 1115 |
*/ int dax_pfn_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) { |
9973c98ec
|
1116 |
struct file *file = vma->vm_file; |
ac401cc78
|
1117 1118 1119 |
struct address_space *mapping = file->f_mapping; void *entry; pgoff_t index = vmf->pgoff; |
30f471fd8
|
1120 |
|
ac401cc78
|
1121 1122 1123 1124 1125 1126 1127 1128 |
spin_lock_irq(&mapping->tree_lock); entry = get_unlocked_mapping_entry(mapping, index, NULL); if (!entry || !radix_tree_exceptional_entry(entry)) goto out; radix_tree_tag_set(&mapping->page_tree, index, PAGECACHE_TAG_DIRTY); put_unlocked_mapping_entry(mapping, index, entry); out: spin_unlock_irq(&mapping->tree_lock); |
0e3b210ce
|
1129 1130 1131 |
return VM_FAULT_NOPAGE; } EXPORT_SYMBOL_GPL(dax_pfn_mkwrite); |
4b0228fa1
|
1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 |
static bool dax_range_is_aligned(struct block_device *bdev, unsigned int offset, unsigned int length) { unsigned short sector_size = bdev_logical_block_size(bdev); if (!IS_ALIGNED(offset, sector_size)) return false; if (!IS_ALIGNED(length, sector_size)) return false; return true; } |
679c8bd3b
|
1144 1145 1146 1147 1148 1149 1150 |
int __dax_zero_page_range(struct block_device *bdev, sector_t sector, unsigned int offset, unsigned int length) { struct blk_dax_ctl dax = { .sector = sector, .size = PAGE_SIZE, }; |
4b0228fa1
|
1151 1152 1153 1154 1155 1156 1157 1158 1159 |
if (dax_range_is_aligned(bdev, offset, length)) { sector_t start_sector = dax.sector + (offset >> 9); return blkdev_issue_zeroout(bdev, start_sector, length >> 9, GFP_NOFS, true); } else { if (dax_map_atomic(bdev, &dax) < 0) return PTR_ERR(dax.addr); clear_pmem(dax.addr + offset, length); |
4b0228fa1
|
1160 1161 |
dax_unmap_atomic(bdev, &dax); } |
679c8bd3b
|
1162 1163 1164 |
return 0; } EXPORT_SYMBOL_GPL(__dax_zero_page_range); |
0e3b210ce
|
1165 |
/** |
25726bc15
|
1166 |
* dax_zero_page_range - zero a range within a page of a DAX file |
4c0ccfef2
|
1167 1168 |
* @inode: The file being truncated * @from: The file offset that is being truncated to |
25726bc15
|
1169 |
* @length: The number of bytes to zero |
4c0ccfef2
|
1170 1171 |
* @get_block: The filesystem method used to translate file offsets to blocks * |
25726bc15
|
1172 1173 1174 1175 |
* This function can be called by a filesystem when it is zeroing part of a * page in a DAX file. This is intended for hole-punch operations. If * you are truncating a file, the helper function dax_truncate_page() may be * more convenient. |
4c0ccfef2
|
1176 |
*/ |
25726bc15
|
1177 1178 |
int dax_zero_page_range(struct inode *inode, loff_t from, unsigned length, get_block_t get_block) |
4c0ccfef2
|
1179 1180 |
{ struct buffer_head bh; |
09cbfeaf1
|
1181 1182 |
pgoff_t index = from >> PAGE_SHIFT; unsigned offset = from & (PAGE_SIZE-1); |
4c0ccfef2
|
1183 1184 1185 1186 1187 |
int err; /* Block boundary? Nothing to do */ if (!length) return 0; |
09cbfeaf1
|
1188 |
BUG_ON((offset + length) > PAGE_SIZE); |
4c0ccfef2
|
1189 1190 |
memset(&bh, 0, sizeof(bh)); |
eab95db69
|
1191 |
bh.b_bdev = inode->i_sb->s_bdev; |
09cbfeaf1
|
1192 |
bh.b_size = PAGE_SIZE; |
4c0ccfef2
|
1193 |
err = get_block(inode, index, &bh, 0); |
679c8bd3b
|
1194 |
if (err < 0 || !buffer_written(&bh)) |
4c0ccfef2
|
1195 |
return err; |
4c0ccfef2
|
1196 |
|
679c8bd3b
|
1197 1198 |
return __dax_zero_page_range(bh.b_bdev, to_sector(&bh, inode), offset, length); |
4c0ccfef2
|
1199 |
} |
25726bc15
|
1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 |
EXPORT_SYMBOL_GPL(dax_zero_page_range); /** * dax_truncate_page - handle a partial page being truncated in a DAX file * @inode: The file being truncated * @from: The file offset that is being truncated to * @get_block: The filesystem method used to translate file offsets to blocks * * Similar to block_truncate_page(), this function can be called by a * filesystem when it is truncating a DAX file to handle the partial page. |
25726bc15
|
1210 1211 1212 |
*/ int dax_truncate_page(struct inode *inode, loff_t from, get_block_t get_block) { |
09cbfeaf1
|
1213 |
unsigned length = PAGE_ALIGN(from) - from; |
25726bc15
|
1214 1215 |
return dax_zero_page_range(inode, from, length, get_block); } |
4c0ccfef2
|
1216 |
EXPORT_SYMBOL_GPL(dax_truncate_page); |
a254e5681
|
1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 |
#ifdef CONFIG_FS_IOMAP static loff_t iomap_dax_actor(struct inode *inode, loff_t pos, loff_t length, void *data, struct iomap *iomap) { struct iov_iter *iter = data; loff_t end = pos + length, done = 0; ssize_t ret = 0; if (iov_iter_rw(iter) == READ) { end = min(end, i_size_read(inode)); if (pos >= end) return 0; if (iomap->type == IOMAP_HOLE || iomap->type == IOMAP_UNWRITTEN) return iov_iter_zero(min(length, end - pos), iter); } if (WARN_ON_ONCE(iomap->type != IOMAP_MAPPED)) return -EIO; while (pos < end) { unsigned offset = pos & (PAGE_SIZE - 1); struct blk_dax_ctl dax = { 0 }; ssize_t map_len; dax.sector = iomap->blkno + (((pos & PAGE_MASK) - iomap->offset) >> 9); dax.size = (length + offset + PAGE_SIZE - 1) & PAGE_MASK; map_len = dax_map_atomic(iomap->bdev, &dax); if (map_len < 0) { ret = map_len; break; } dax.addr += offset; map_len -= offset; if (map_len > end - pos) map_len = end - pos; if (iov_iter_rw(iter) == WRITE) map_len = copy_from_iter_pmem(dax.addr, map_len, iter); else map_len = copy_to_iter(dax.addr, map_len, iter); dax_unmap_atomic(iomap->bdev, &dax); if (map_len <= 0) { ret = map_len ? map_len : -EFAULT; break; } pos += map_len; length -= map_len; done += map_len; } return done ? done : ret; } /** * iomap_dax_rw - Perform I/O to a DAX file * @iocb: The control block for this I/O * @iter: The addresses to do I/O from or to * @ops: iomap ops passed from the file system * * This function performs read and write operations to directly mapped * persistent memory. The callers needs to take care of read/write exclusion * and evicting any page cache pages in the region under I/O. */ ssize_t iomap_dax_rw(struct kiocb *iocb, struct iov_iter *iter, struct iomap_ops *ops) { struct address_space *mapping = iocb->ki_filp->f_mapping; struct inode *inode = mapping->host; loff_t pos = iocb->ki_pos, ret = 0, done = 0; unsigned flags = 0; if (iov_iter_rw(iter) == WRITE) flags |= IOMAP_WRITE; /* * Yes, even DAX files can have page cache attached to them: A zeroed * page is inserted into the pagecache when we have to serve a write * fault on a hole. It should never be dirtied and can simply be * dropped from the pagecache once we get real data for the page. * * XXX: This is racy against mmap, and there's nothing we can do about * it. We'll eventually need to shift this down even further so that * we can check if we allocated blocks over a hole first. */ if (mapping->nrpages) { ret = invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, (pos + iov_iter_count(iter) - 1) >> PAGE_SHIFT); WARN_ON_ONCE(ret); } while (iov_iter_count(iter)) { ret = iomap_apply(inode, pos, iov_iter_count(iter), flags, ops, iter, iomap_dax_actor); if (ret <= 0) break; pos += ret; done += ret; } iocb->ki_pos += done; return done ? done : ret; } EXPORT_SYMBOL_GPL(iomap_dax_rw); |
a7d73fe6c
|
1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 |
/** * iomap_dax_fault - handle a page fault on a DAX file * @vma: The virtual memory area where the fault occurred * @vmf: The description of the fault * @ops: iomap ops passed from the file system * * When a page fault occurs, filesystems may call this helper in their fault * or mkwrite handler for DAX files. Assumes the caller has done all the * necessary locking for the page fault to proceed successfully. */ int iomap_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf, struct iomap_ops *ops) { struct address_space *mapping = vma->vm_file->f_mapping; struct inode *inode = mapping->host; unsigned long vaddr = (unsigned long)vmf->virtual_address; loff_t pos = (loff_t)vmf->pgoff << PAGE_SHIFT; sector_t sector; struct iomap iomap = { 0 }; unsigned flags = 0; int error, major = 0; void *entry; /* * Check whether offset isn't beyond end of file now. Caller is supposed * to hold locks serializing us with truncate / punch hole so this is * a reliable test. */ if (pos >= i_size_read(inode)) return VM_FAULT_SIGBUS; entry = grab_mapping_entry(mapping, vmf->pgoff); if (IS_ERR(entry)) { error = PTR_ERR(entry); goto out; } if ((vmf->flags & FAULT_FLAG_WRITE) && !vmf->cow_page) flags |= IOMAP_WRITE; /* * Note that we don't bother to use iomap_apply here: DAX required * the file system block size to be equal the page size, which means * that we never have to deal with more than a single extent here. */ error = ops->iomap_begin(inode, pos, PAGE_SIZE, flags, &iomap); if (error) goto unlock_entry; if (WARN_ON_ONCE(iomap.offset + iomap.length < pos + PAGE_SIZE)) { error = -EIO; /* fs corruption? */ goto unlock_entry; } sector = iomap.blkno + (((pos & PAGE_MASK) - iomap.offset) >> 9); if (vmf->cow_page) { switch (iomap.type) { case IOMAP_HOLE: case IOMAP_UNWRITTEN: clear_user_highpage(vmf->cow_page, vaddr); break; case IOMAP_MAPPED: error = copy_user_dax(iomap.bdev, sector, PAGE_SIZE, vmf->cow_page, vaddr); break; default: WARN_ON_ONCE(1); error = -EIO; break; } if (error) goto unlock_entry; if (!radix_tree_exceptional_entry(entry)) { vmf->page = entry; return VM_FAULT_LOCKED; } vmf->entry = entry; return VM_FAULT_DAX_LOCKED; } switch (iomap.type) { case IOMAP_MAPPED: if (iomap.flags & IOMAP_F_NEW) { count_vm_event(PGMAJFAULT); mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT); major = VM_FAULT_MAJOR; } error = dax_insert_mapping(mapping, iomap.bdev, sector, PAGE_SIZE, &entry, vma, vmf); break; case IOMAP_UNWRITTEN: case IOMAP_HOLE: if (!(vmf->flags & FAULT_FLAG_WRITE)) return dax_load_hole(mapping, entry, vmf); /*FALLTHRU*/ default: WARN_ON_ONCE(1); error = -EIO; break; } unlock_entry: put_locked_mapping_entry(mapping, vmf->pgoff, entry); out: if (error == -ENOMEM) return VM_FAULT_OOM | major; /* -EBUSY is fine, somebody else faulted on the same PTE */ if (error < 0 && error != -EBUSY) return VM_FAULT_SIGBUS | major; return VM_FAULT_NOPAGE | major; } EXPORT_SYMBOL_GPL(iomap_dax_fault); |
a254e5681
|
1442 |
#endif /* CONFIG_FS_IOMAP */ |