summaryrefslogtreecommitdiff
path: root/fs/dax.c
blob: 574763eed8a361444f555c3f2745a9f7eaf3181f (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
/*
 * 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>
#include <linux/dax.h>
#include <linux/fs.h>
#include <linux/genhd.h>
#include <linux/highmem.h>
#include <linux/memcontrol.h>
#include <linux/mm.h>
#include <linux/mutex.h>
#include <linux/pmem.h>
#include <linux/sched.h>
#include <linux/uio.h>
#include <linux/vmstat.h>
#include <linux/pfn_t.h>
#include <linux/sizes.h>

static long dax_map_atomic(struct block_device *bdev, struct blk_dax_ctl *dax)
{
	struct request_queue *q = bdev->bd_queue;
	long rc = -EIO;

	dax->addr = (void __pmem *) ERR_PTR(-EIO);
	if (blk_queue_enter(q, true) != 0)
		return rc;

	rc = bdev_direct_access(bdev, dax);
	if (rc < 0) {
		dax->addr = (void __pmem *) ERR_PTR(rc);
		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);
}

/*
 * dax_clear_blocks() is called from within transaction context from XFS,
 * and hence this means the stack from this point must follow GFP_NOFS
 * semantics for all operations.
 */
int dax_clear_blocks(struct inode *inode, sector_t block, long _size)
{
	struct block_device *bdev = inode->i_sb->s_bdev;
	struct blk_dax_ctl dax = {
		.sector = block << (inode->i_blkbits - 9),
		.size = _size,
	};

	might_sleep();
	do {
		long count, sz;

		count = dax_map_atomic(bdev, &dax);
		if (count < 0)
			return count;
		sz = min_t(long, count, SZ_128K);
		clear_pmem(dax.addr, sz);
		dax.size -= sz;
		dax.sector += sz / 512;
		dax_unmap_atomic(bdev, &dax);
		cond_resched();
	} while (dax.size);

	wmb_pmem();
	return 0;
}
EXPORT_SYMBOL_GPL(dax_clear_blocks);

/* the clear_pmem() calls are ordered by a wmb_pmem() in the caller */
static void dax_new_buf(void __pmem *addr, unsigned size, unsigned first,
		loff_t pos, loff_t end)
{
	loff_t final = end - pos + first; /* The final byte of the buffer */

	if (first > 0)
		clear_pmem(addr, first);
	if (final < size)
		clear_pmem(addr + final, size - final);
}

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;
}


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;
}

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)
{
	loff_t pos = start, max = start, bh_max = start;
	bool hole = false, need_wmb = false;
	struct block_device *bdev = NULL;
	int rw = iov_iter_rw(iter), rc;
	long map_len = 0;
	struct blk_dax_ctl dax = {
		.addr = (void __pmem *) ERR_PTR(-EIO),
	};

	if (rw == READ)
		end = min(end, i_size_read(inode));

	while (pos < end) {
		size_t len;
		if (pos == max) {
			unsigned blkbits = inode->i_blkbits;
			long page = pos >> PAGE_SHIFT;
			sector_t block = page << (PAGE_SHIFT - blkbits);
			unsigned first = pos - (block << blkbits);
			long size;

			if (pos == bh_max) {
				bh->b_size = PAGE_ALIGN(end - pos);
				bh->b_state = 0;
				rc = get_block(inode, block, bh, rw == WRITE);
				if (rc)
					break;
				if (!buffer_size_valid(bh))
					bh->b_size = 1 << blkbits;
				bh_max = pos - first + bh->b_size;
				bdev = bh->b_bdev;
			} else {
				unsigned done = bh->b_size -
						(bh_max - (pos - first));
				bh->b_blocknr += done >> blkbits;
				bh->b_size -= done;
			}

			hole = rw == READ && !buffer_written(bh);
			if (hole) {
				size = bh->b_size - first;
			} else {
				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;
					break;
				}
				if (buffer_unwritten(bh) || buffer_new(bh)) {
					dax_new_buf(dax.addr, map_len, first,
							pos, end);
					need_wmb = true;
				}
				dax.addr += first;
				size = map_len - first;
			}
			max = min(pos + size, end);
		}

		if (iov_iter_rw(iter) == WRITE) {
			len = copy_from_iter_pmem(dax.addr, max - pos, iter);
			need_wmb = true;
		} else if (!hole)
			len = copy_to_iter((void __force *) dax.addr, max - pos,
					iter);
		else
			len = iov_iter_zero(max - pos, iter);

		if (!len) {
			rc = -EFAULT;
			break;
		}

		pos += len;
		if (!IS_ERR(dax.addr))
			dax.addr += len;
	}

	if (need_wmb)
		wmb_pmem();
	dax_unmap_atomic(bdev, &dax);

	return (pos == start) ? rc : pos - start;
}

/**
 * dax_do_io - Perform I/O to a DAX file
 * @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
 * @pos: The file offset where the I/O starts
 * @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.
 */
ssize_t dax_do_io(struct kiocb *iocb, struct inode *inode,
		  struct iov_iter *iter, loff_t pos, get_block_t get_block,
		  dio_iodone_t end_io, int flags)
{
	struct buffer_head bh;
	ssize_t retval = -EINVAL;
	loff_t end = pos + iov_iter_count(iter);

	memset(&bh, 0, sizeof(bh));

	if ((flags & DIO_LOCKING) && iov_iter_rw(iter) == READ) {
		struct address_space *mapping = inode->i_mapping;
		mutex_lock(&inode->i_mutex);
		retval = filemap_write_and_wait_range(mapping, pos, end - 1);
		if (retval) {
			mutex_unlock(&inode->i_mutex);
			goto out;
		}
	}

	/* Protects against truncate */
	if (!(flags & DIO_SKIP_DIO_COUNT))
		inode_dio_begin(inode);

	retval = dax_io(inode, iter, pos, end, get_block, &bh);

	if ((flags & DIO_LOCKING) && iov_iter_rw(iter) == READ)
		mutex_unlock(&inode->i_mutex);

	if ((retval > 0) && end_io)
		end_io(iocb, pos, retval, bh.b_private);

	if (!(flags & DIO_SKIP_DIO_COUNT))
		inode_dio_end(inode);
 out:
	return retval;
}
EXPORT_SYMBOL_GPL(dax_do_io);

/*
 * 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.
 */
static int dax_load_hole(struct address_space *mapping, struct page *page,
							struct vm_fault *vmf)
{
	unsigned long size;
	struct inode *inode = mapping->host;
	if (!page)
		page = find_or_create_page(mapping, vmf->pgoff,
						GFP_KERNEL | __GFP_ZERO);
	if (!page)
		return VM_FAULT_OOM;
	/* Recheck i_size under page lock to avoid truncate race */
	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
	if (vmf->pgoff >= size) {
		unlock_page(page);
		page_cache_release(page);
		return VM_FAULT_SIGBUS;
	}

	vmf->page = page;
	return VM_FAULT_LOCKED;
}

static int copy_user_bh(struct page *to, struct inode *inode,
		struct buffer_head *bh, unsigned long vaddr)
{
	struct blk_dax_ctl dax = {
		.sector = to_sector(bh, inode),
		.size = bh->b_size,
	};
	struct block_device *bdev = bh->b_bdev;
	void *vto;

	if (dax_map_atomic(bdev, &dax) < 0)
		return PTR_ERR(dax.addr);
	vto = kmap_atomic(to);
	copy_user_page(vto, (void __force *)dax.addr, vaddr, to);
	kunmap_atomic(vto);
	dax_unmap_atomic(bdev, &dax);
	return 0;
}

static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
			struct vm_area_struct *vma, struct vm_fault *vmf)
{
	unsigned long vaddr = (unsigned long)vmf->virtual_address;
	struct address_space *mapping = inode->i_mapping;
	struct block_device *bdev = bh->b_bdev;
	struct blk_dax_ctl dax = {
		.sector = to_sector(bh, inode),
		.size = bh->b_size,
	};
	pgoff_t size;
	int error;

	i_mmap_lock_read(mapping);

	/*
	 * Check truncate didn't happen while we were allocating a block.
	 * If it did, this block may or may not be still allocated to the
	 * file.  We can't tell the filesystem to free it because we can't
	 * take i_mutex here.  In the worst case, the file still has blocks
	 * allocated past the end of the file.
	 */
	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
	if (unlikely(vmf->pgoff >= size)) {
		error = -EIO;
		goto out;
	}

	if (dax_map_atomic(bdev, &dax) < 0) {
		error = PTR_ERR(dax.addr);
		goto out;
	}

	if (buffer_unwritten(bh) || buffer_new(bh)) {
		clear_pmem(dax.addr, PAGE_SIZE);
		wmb_pmem();
	}
	dax_unmap_atomic(bdev, &dax);

	error = vm_insert_mixed(vma, vaddr, dax.pfn);

 out:
	i_mmap_unlock_read(mapping);

	return error;
}

/**
 * __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
 * @get_block: The filesystem method used to translate file offsets to blocks
 * @complete_unwritten: The filesystem method used to convert unwritten blocks
 *	to written so the data written to them is exposed. This is required for
 *	required by write faults for filesystems that will return unwritten
 *	extent mappings from @get_block, but it is optional for reads as
 *	dax_insert_mapping() will always zero unwritten blocks. If the fs does
 *	not support unwritten extents, the it should pass NULL.
 *
 * When a page fault occurs, filesystems may call this helper in their
 * fault handler for DAX files. __dax_fault() assumes the caller has done all
 * the necessary locking for the page fault to proceed successfully.
 */
int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
			get_block_t get_block, dax_iodone_t complete_unwritten)
{
	struct file *file = vma->vm_file;
	struct address_space *mapping = file->f_mapping;
	struct inode *inode = mapping->host;
	struct page *page;
	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;

	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);
	bh.b_size = PAGE_SIZE;

 repeat:
	page = find_get_page(mapping, vmf->pgoff);
	if (page) {
		if (!lock_page_or_retry(page, vma->vm_mm, vmf->flags)) {
			page_cache_release(page);
			return VM_FAULT_RETRY;
		}
		if (unlikely(page->mapping != mapping)) {
			unlock_page(page);
			page_cache_release(page);
			goto repeat;
		}
		size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
		if (unlikely(vmf->pgoff >= size)) {
			/*
			 * We have a struct page covering a hole in the file
			 * from a read fault and we've raced with a truncate
			 */
			error = -EIO;
			goto unlock_page;
		}
	}

	error = get_block(inode, block, &bh, 0);
	if (!error && (bh.b_size < PAGE_SIZE))
		error = -EIO;		/* fs corruption? */
	if (error)
		goto unlock_page;

	if (!buffer_mapped(&bh) && !buffer_unwritten(&bh) && !vmf->cow_page) {
		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)
				goto unlock_page;
		} else {
			return dax_load_hole(mapping, page, vmf);
		}
	}

	if (vmf->cow_page) {
		struct page *new_page = vmf->cow_page;
		if (buffer_written(&bh))
			error = copy_user_bh(new_page, inode, &bh, vaddr);
		else
			clear_user_highpage(new_page, vaddr);
		if (error)
			goto unlock_page;
		vmf->page = page;
		if (!page) {
			i_mmap_lock_read(mapping);
			/* Check we didn't race with truncate */
			size = (i_size_read(inode) + PAGE_SIZE - 1) >>
								PAGE_SHIFT;
			if (vmf->pgoff >= size) {
				i_mmap_unlock_read(mapping);
				error = -EIO;
				goto out;
			}
		}
		return VM_FAULT_LOCKED;
	}

	/* Check we didn't race with a read fault installing a new page */
	if (!page && major)
		page = find_lock_page(mapping, vmf->pgoff);

	if (page) {
		unmap_mapping_range(mapping, vmf->pgoff << PAGE_SHIFT,
							PAGE_CACHE_SIZE, 0);
		delete_from_page_cache(page);
		unlock_page(page);
		page_cache_release(page);
	}

	/*
	 * If we successfully insert the new mapping over an unwritten extent,
	 * we need to ensure we convert the unwritten extent. If there is an
	 * error inserting the mapping, the filesystem needs to leave it as
	 * unwritten to prevent exposure of the stale underlying data to
	 * userspace, but we still need to call the completion function so
	 * the private resources on the mapping buffer can be released. We
	 * indicate what the callback should do via the uptodate variable, same
	 * as for normal BH based IO completions.
	 */
	error = dax_insert_mapping(inode, &bh, vma, vmf);
	if (buffer_unwritten(&bh)) {
		if (complete_unwritten)
			complete_unwritten(&bh, !error);
		else
			WARN_ON_ONCE(!(vmf->flags & FAULT_FLAG_WRITE));
	}

 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;

 unlock_page:
	if (page) {
		unlock_page(page);
		page_cache_release(page);
	}
	goto out;
}
EXPORT_SYMBOL(__dax_fault);

/**
 * 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
 * @get_block: The filesystem method used to translate file offsets to blocks
 *
 * When a page fault occurs, filesystems may call this helper in their
 * fault handler for DAX files.
 */
int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
	      get_block_t get_block, dax_iodone_t complete_unwritten)
{
	int result;
	struct super_block *sb = file_inode(vma->vm_file)->i_sb;

	if (vmf->flags & FAULT_FLAG_WRITE) {
		sb_start_pagefault(sb);
		file_update_time(vma->vm_file);
	}
	result = __dax_fault(vma, vmf, get_block, complete_unwritten);
	if (vmf->flags & FAULT_FLAG_WRITE)
		sb_end_pagefault(sb);

	return result;
}
EXPORT_SYMBOL_GPL(dax_fault);

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/*
 * 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)

int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
		pmd_t *pmd, unsigned int flags, get_block_t get_block,
		dax_iodone_t complete_unwritten)
{
	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;
	struct block_device *bdev;
	pgoff_t size, pgoff;
	sector_t block;
	int result = 0;

	/* dax pmd mappings are broken wrt gup and fork */
	if (!IS_ENABLED(CONFIG_FS_DAX_PMD))
		return VM_FAULT_FALLBACK;

	/* Fall back to PTEs if we're going to COW */
	if (write && !(vma->vm_flags & VM_SHARED)) {
		split_huge_pmd(vma, pmd, address);
		return VM_FAULT_FALLBACK;
	}
	/* If the PMD would extend outside the VMA */
	if (pmd_addr < vma->vm_start)
		return VM_FAULT_FALLBACK;
	if ((pmd_addr + PMD_SIZE) > vma->vm_end)
		return VM_FAULT_FALLBACK;

	pgoff = linear_page_index(vma, pmd_addr);
	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 */
	if ((pgoff | PG_PMD_COLOUR) >= size)
		return VM_FAULT_FALLBACK;

	memset(&bh, 0, sizeof(bh));
	block = (sector_t)pgoff << (PAGE_SHIFT - blkbits);

	bh.b_size = PMD_SIZE;
	if (get_block(inode, block, &bh, write) != 0)
		return VM_FAULT_SIGBUS;
	bdev = bh.b_bdev;
	i_mmap_lock_read(mapping);

	/*
	 * 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.
	 */
	if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE)
		goto fallback;

	/*
	 * If we allocated new storage, make sure no process has any
	 * zero pages covering this hole
	 */
	if (buffer_new(&bh)) {
		i_mmap_unlock_read(mapping);
		unmap_mapping_range(mapping, pgoff << PAGE_SHIFT, PMD_SIZE, 0);
		i_mmap_lock_read(mapping);
	}

	/*
	 * If a truncate happened while we were allocating blocks, we may
	 * leave blocks allocated to the file that are beyond EOF.  We can't
	 * take i_mutex here, so just leave them hanging; they'll be freed
	 * when the file is deleted.
	 */
	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
	if (pgoff >= size) {
		result = VM_FAULT_SIGBUS;
		goto out;
	}
	if ((pgoff | PG_PMD_COLOUR) >= size)
		goto fallback;

	if (!write && !buffer_mapped(&bh) && buffer_uptodate(&bh)) {
		spinlock_t *ptl;
		pmd_t entry;
		struct page *zero_page = get_huge_zero_page();

		if (unlikely(!zero_page))
			goto fallback;

		ptl = pmd_lock(vma->vm_mm, pmd);
		if (!pmd_none(*pmd)) {
			spin_unlock(ptl);
			goto fallback;
		}

		entry = mk_pmd(zero_page, vma->vm_page_prot);
		entry = pmd_mkhuge(entry);
		set_pmd_at(vma->vm_mm, pmd_addr, pmd, entry);
		result = VM_FAULT_NOPAGE;
		spin_unlock(ptl);
	} else {
		struct blk_dax_ctl dax = {
			.sector = to_sector(&bh, inode),
			.size = PMD_SIZE,
		};
		long length = dax_map_atomic(bdev, &dax);

		if (length < 0) {
			result = VM_FAULT_SIGBUS;
			goto out;
		}
		if (length < PMD_SIZE
				|| (pfn_t_to_pfn(dax.pfn) & PG_PMD_COLOUR)) {
			dax_unmap_atomic(bdev, &dax);
			goto fallback;
		}

		/*
		 * TODO: teach vmf_insert_pfn_pmd() to support
		 * 'pte_special' for pmds
		 */
		if (pfn_t_has_page(dax.pfn)) {
			dax_unmap_atomic(bdev, &dax);
			goto fallback;
		}

		if (buffer_unwritten(&bh) || buffer_new(&bh)) {
			clear_pmem(dax.addr, PMD_SIZE);
			wmb_pmem();
			count_vm_event(PGMAJFAULT);
			mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
			result |= VM_FAULT_MAJOR;
		}
		dax_unmap_atomic(bdev, &dax);

		result |= vmf_insert_pfn_pmd(vma, address, pmd,
				pfn_t_to_pfn(dax.pfn), write);
	}

 out:
	i_mmap_unlock_read(mapping);

	if (buffer_unwritten(&bh))
		complete_unwritten(&bh, !(result & VM_FAULT_ERROR));

	return result;

 fallback:
	count_vm_event(THP_FAULT_FALLBACK);
	result = VM_FAULT_FALLBACK;
	goto out;
}
EXPORT_SYMBOL_GPL(__dax_pmd_fault);

/**
 * 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,
			pmd_t *pmd, unsigned int flags, get_block_t get_block,
			dax_iodone_t complete_unwritten)
{
	int result;
	struct super_block *sb = file_inode(vma->vm_file)->i_sb;

	if (flags & FAULT_FLAG_WRITE) {
		sb_start_pagefault(sb);
		file_update_time(vma->vm_file);
	}
	result = __dax_pmd_fault(vma, address, pmd, flags, get_block,
				complete_unwritten);
	if (flags & FAULT_FLAG_WRITE)
		sb_end_pagefault(sb);

	return result;
}
EXPORT_SYMBOL_GPL(dax_pmd_fault);
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */

/**
 * dax_pfn_mkwrite - handle first write to DAX page
 * @vma: The virtual memory area where the fault occurred
 * @vmf: The description of the fault
 *
 */
int dax_pfn_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
	struct super_block *sb = file_inode(vma->vm_file)->i_sb;

	sb_start_pagefault(sb);
	file_update_time(vma->vm_file);
	sb_end_pagefault(sb);
	return VM_FAULT_NOPAGE;
}
EXPORT_SYMBOL_GPL(dax_pfn_mkwrite);

/**
 * dax_zero_page_range - zero a range within a page of a DAX file
 * @inode: The file being truncated
 * @from: The file offset that is being truncated to
 * @length: The number of bytes to zero
 * @get_block: The filesystem method used to translate file offsets to blocks
 *
 * 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.
 *
 * We work in terms of PAGE_CACHE_SIZE here for commonality with
 * block_truncate_page(), but we could go down to PAGE_SIZE if the filesystem
 * took care of disposing of the unnecessary blocks.  Even if the filesystem
 * block size is smaller than PAGE_SIZE, we have to zero the rest of the page
 * since the file might be mmapped.
 */
int dax_zero_page_range(struct inode *inode, loff_t from, unsigned length,
							get_block_t get_block)
{
	struct buffer_head bh;
	pgoff_t index = from >> PAGE_CACHE_SHIFT;
	unsigned offset = from & (PAGE_CACHE_SIZE-1);
	int err;

	/* Block boundary? Nothing to do */
	if (!length)
		return 0;
	BUG_ON((offset + length) > PAGE_CACHE_SIZE);

	memset(&bh, 0, sizeof(bh));
	bh.b_size = PAGE_CACHE_SIZE;
	err = get_block(inode, index, &bh, 0);
	if (err < 0)
		return err;
	if (buffer_written(&bh)) {
		struct block_device *bdev = bh.b_bdev;
		struct blk_dax_ctl dax = {
			.sector = to_sector(&bh, inode),
			.size = PAGE_CACHE_SIZE,
		};

		if (dax_map_atomic(bdev, &dax) < 0)
			return PTR_ERR(dax.addr);
		clear_pmem(dax.addr + offset, length);
		wmb_pmem();
		dax_unmap_atomic(bdev, &dax);
	}

	return 0;
}
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.
 *
 * We work in terms of PAGE_CACHE_SIZE here for commonality with
 * block_truncate_page(), but we could go down to PAGE_SIZE if the filesystem
 * took care of disposing of the unnecessary blocks.  Even if the filesystem
 * block size is smaller than PAGE_SIZE, we have to zero the rest of the page
 * since the file might be mmapped.
 */
int dax_truncate_page(struct inode *inode, loff_t from, get_block_t get_block)
{
	unsigned length = PAGE_CACHE_ALIGN(from) - from;
	return dax_zero_page_range(inode, from, length, get_block);
}
EXPORT_SYMBOL_GPL(dax_truncate_page);