summaryrefslogtreecommitdiff
path: root/fs/dax.c
blob: 553e55b93495d64e88ba49808c0ca10c0ac206f8 (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
/*
 * 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/fs.h>
#include <linux/genhd.h>
#include <linux/highmem.h>
#include <linux/memcontrol.h>
#include <linux/mm.h>
#include <linux/mutex.h>
#include <linux/sched.h>
#include <linux/uio.h>
#include <linux/vmstat.h>

int dax_clear_blocks(struct inode *inode, sector_t block, long size)
{
	struct block_device *bdev = inode->i_sb->s_bdev;
	sector_t sector = block << (inode->i_blkbits - 9);

	might_sleep();
	do {
		void *addr;
		unsigned long pfn;
		long count;

		count = bdev_direct_access(bdev, sector, &addr, &pfn, size);
		if (count < 0)
			return count;
		BUG_ON(size < count);
		while (count > 0) {
			unsigned pgsz = PAGE_SIZE - offset_in_page(addr);
			if (pgsz > count)
				pgsz = count;
			if (pgsz < PAGE_SIZE)
				memset(addr, 0, pgsz);
			else
				clear_page(addr);
			addr += pgsz;
			size -= pgsz;
			count -= pgsz;
			BUG_ON(pgsz & 511);
			sector += pgsz / 512;
			cond_resched();
		}
	} while (size);

	return 0;
}
EXPORT_SYMBOL_GPL(dax_clear_blocks);

static long dax_get_addr(struct buffer_head *bh, void **addr, unsigned blkbits)
{
	unsigned long pfn;
	sector_t sector = bh->b_blocknr << (blkbits - 9);
	return bdev_direct_access(bh->b_bdev, sector, addr, &pfn, bh->b_size);
}

static void dax_new_buf(void *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)
		memset(addr, 0, first);
	if (final < size)
		memset(addr + final, 0, 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 ssize_t dax_io(int rw, struct inode *inode, struct iov_iter *iter,
			loff_t start, loff_t end, get_block_t get_block,
			struct buffer_head *bh)
{
	ssize_t retval = 0;
	loff_t pos = start;
	loff_t max = start;
	loff_t bh_max = start;
	void *addr;
	bool hole = false;

	if (rw != WRITE)
		end = min(end, i_size_read(inode));

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

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

			hole = (rw != WRITE) && !buffer_written(bh);
			if (hole) {
				addr = NULL;
				size = bh->b_size - first;
			} else {
				retval = dax_get_addr(bh, &addr, blkbits);
				if (retval < 0)
					break;
				if (buffer_unwritten(bh) || buffer_new(bh))
					dax_new_buf(addr, retval, first, pos,
									end);
				addr += first;
				size = retval - first;
			}
			max = min(pos + size, end);
		}

		if (rw == WRITE)
			len = copy_from_iter(addr, max - pos, iter);
		else if (!hole)
			len = copy_to_iter(addr, max - pos, iter);
		else
			len = iov_iter_zero(max - pos, iter);

		if (!len)
			break;

		pos += len;
		addr += len;
	}

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

/**
 * dax_do_io - Perform I/O to a DAX file
 * @rw: READ to read or WRITE to write
 * @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(int rw, 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) && (rw == 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 */
	atomic_inc(&inode->i_dio_count);

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

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

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

	inode_dio_done(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 buffer_head *bh,
			unsigned blkbits, unsigned long vaddr)
{
	void *vfrom, *vto;
	if (dax_get_addr(bh, &vfrom, blkbits) < 0)
		return -EIO;
	vto = kmap_atomic(to);
	copy_user_page(vto, vfrom, vaddr, to);
	kunmap_atomic(vto);
	return 0;
}

static int dax_insert_mapping(struct inode *inode, struct buffer_head *bh,
			struct vm_area_struct *vma, struct vm_fault *vmf)
{
	struct address_space *mapping = inode->i_mapping;
	sector_t sector = bh->b_blocknr << (inode->i_blkbits - 9);
	unsigned long vaddr = (unsigned long)vmf->virtual_address;
	void *addr;
	unsigned long pfn;
	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;
	}

	error = bdev_direct_access(bh->b_bdev, sector, &addr, &pfn, bh->b_size);
	if (error < 0)
		goto out;
	if (error < PAGE_SIZE) {
		error = -EIO;
		goto out;
	}

	if (buffer_unwritten(bh) || buffer_new(bh))
		clear_page(addr);

	error = vm_insert_mixed(vma, vaddr, pfn);

 out:
	i_mmap_unlock_read(mapping);

	if (bh->b_end_io)
		bh->b_end_io(bh, 1);

	return error;
}

static int do_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
			get_block_t get_block)
{
	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, &bh, blkbits, 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);
	}

	error = dax_insert_mapping(inode, &bh, vma, vmf);

 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;
}

/**
 * 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)
{
	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 = do_dax_fault(vma, vmf, get_block);
	if (vmf->flags & FAULT_FLAG_WRITE)
		sb_end_pagefault(sb);

	return result;
}
EXPORT_SYMBOL_GPL(dax_fault);