aboutsummaryrefslogtreecommitdiffstats
path: root/mm/page_io.c
blob: f57da454569d1fb025a4a5f7eec7c6c6f5b78450 (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
/*
 *  linux/mm/page_io.c
 *
 *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 *
 *  Swap reorganised 29.12.95, 
 *  Asynchronous swapping added 30.12.95. Stephen Tweedie
 *  Removed race in async swapping. 14.4.1996. Bruno Haible
 *  Add swap of shared pages through the page cache. 20.2.1998. Stephen Tweedie
 *  Always use brw_page, life becomes simpler. 12 May 1998 Eric Biederman
 */

#include <linux/mm.h>
#include <linux/kernel_stat.h>
#include <linux/gfp.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/bio.h>
#include <linux/swapops.h>
#include <linux/writeback.h>
#include <linux/aio.h>
#include <linux/blkdev.h>
#include <asm/pgtable.h>

static struct bio *get_swap_bio(gfp_t gfp_flags,
				struct page *page, bio_end_io_t end_io)
{
	struct bio *bio;

	bio = bio_alloc(gfp_flags, 1);
	if (bio) {
		bio->bi_sector = map_swap_page(page, &bio->bi_bdev);
		bio->bi_sector <<= PAGE_SHIFT - 9;
		bio->bi_io_vec[0].bv_page = page;
		bio->bi_io_vec[0].bv_len = PAGE_SIZE;
		bio->bi_io_vec[0].bv_offset = 0;
		bio->bi_vcnt = 1;
		bio->bi_idx = 0;
		bio->bi_size = PAGE_SIZE;
		bio->bi_end_io = end_io;
	}
	return bio;
}

static void end_swap_bio_write(struct bio *bio, int err)
{
	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
	struct page *page = bio->bi_io_vec[0].bv_page;

	if (!uptodate) {
		SetPageError(page);
		/*
		 * We failed to write the page out to swap-space.
		 * Re-dirty the page in order to avoid it being reclaimed.
		 * Also print a dire warning that things will go BAD (tm)
		 * very quickly.
		 *
		 * Also clear PG_reclaim to avoid rotate_reclaimable_page()
		 */
		set_page_dirty(page);
		printk(KERN_ALERT "Write-error on swap-device (%u:%u:%Lu)\n",
				imajor(bio->bi_bdev->bd_inode),
				iminor(bio->bi_bdev->bd_inode),
				(unsigned long long)bio->bi_sector);
		ClearPageReclaim(page);
	}
	end_page_writeback(page);
	bio_put(bio);
}

void end_swap_bio_read(struct bio *bio, int err)
{
	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
	struct page *page = bio->bi_io_vec[0].bv_page;

	if (!uptodate) {
		SetPageError(page);
		ClearPageUptodate(page);
		printk(KERN_ALERT "Read-error on swap-device (%u:%u:%Lu)\n",
				imajor(bio->bi_bdev->bd_inode),
				iminor(bio->bi_bdev->bd_inode),
				(unsigned long long)bio->bi_sector);
		goto out;
	}

	SetPageUptodate(page);

	/*
	 * There is no guarantee that the page is in swap cache - the software
	 * suspend code (at least) uses end_swap_bio_read() against a non-
	 * swapcache page.  So we must check PG_swapcache before proceeding with
	 * this optimization.
	 */
	if (likely(PageSwapCache(page))) {
		/*
		 * The swap subsystem performs lazy swap slot freeing,
		 * expecting that the page will be swapped out again.
		 * So we can avoid an unnecessary write if the page
		 * isn't redirtied.
		 * This is good for real swap storage because we can
		 * reduce unnecessary I/O and enhance wear-leveling
		 * if an SSD is used as the as swap device.
		 * But if in-memory swap device (eg zram) is used,
		 * this causes a duplicated copy between uncompressed
		 * data in VM-owned memory and compressed data in
		 * zram-owned memory.  So let's free zram-owned memory
		 * and make the VM-owned decompressed page *dirty*,
		 * so the page should be swapped out somewhere again if
		 * we again wish to reclaim it.
		 */
		struct gendisk *disk = bio->bi_bdev->bd_disk;
		if (disk->fops->swap_slot_free_notify) {
			swp_entry_t entry;
			unsigned long offset;

			entry.val = page_private(page);
			offset = swp_offset(entry);

			SetPageDirty(page);
			disk->fops->swap_slot_free_notify(bio->bi_bdev,
					offset);
		}
	}

out:
	unlock_page(page);
	bio_put(bio);
}

/*
 * We may have stale swap cache pages in memory: notice
 * them here and get rid of the unnecessary final write.
 */
int swap_writepage(struct page *page, struct writeback_control *wbc)
{
	struct bio *bio;
	int ret = 0, rw = WRITE;

	if (try_to_free_swap(page)) {
		unlock_page(page);
		goto out;
	}
	bio = get_swap_bio(GFP_NOIO, page, end_swap_bio_write);
	if (bio == NULL) {
		set_page_dirty(page);
		unlock_page(page);
		ret = -ENOMEM;
		goto out;
	}
	if (wbc->sync_mode == WB_SYNC_ALL)
		rw |= REQ_SYNC;
	count_vm_event(PSWPOUT);
	set_page_writeback(page);
	unlock_page(page);
	submit_bio(rw, bio);
out:
	return ret;
}

int swap_readpage(struct page *page)
{
	struct bio *bio;
	int ret = 0;

	VM_BUG_ON(!PageLocked(page));
	VM_BUG_ON(PageUptodate(page));
	bio = get_swap_bio(GFP_KERNEL, page, end_swap_bio_read);
	if (bio == NULL) {
		unlock_page(page);
		ret = -ENOMEM;
		goto out;
	}
	count_vm_event(PSWPIN);
	submit_bio(READ, bio);
out:
	return ret;
}