aboutsummaryrefslogtreecommitdiffstats
path: root/fs/logfs/file.c
blob: abe1cafbd4c263f4191217a591d3d5f4f258a841 (plain) (blame)
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
/*
 * fs/logfs/file.c	- prepare_write, commit_write and friends
 *
 * As should be obvious for Linux kernel code, license is GPLv2
 *
 * Copyright (c) 2005-2008 Joern Engel <joern@logfs.org>
 */
#include "logfs.h"
#include <linux/sched.h>
#include <linux/writeback.h>

static int logfs_write_begin(struct file *file, struct address_space *mapping,
		loff_t pos, unsigned len, unsigned flags,
		struct page **pagep, void **fsdata)
{
	struct inode *inode = mapping->host;
	struct page *page;
	pgoff_t index = pos >> PAGE_CACHE_SHIFT;

	page = grab_cache_page_write_begin(mapping, index, flags);
	if (!page)
		return -ENOMEM;
	*pagep = page;

	if ((len == PAGE_CACHE_SIZE) || PageUptodate(page))
		return 0;
	if ((pos & PAGE_CACHE_MASK) >= i_size_read(inode)) {
		unsigned start = pos & (PAGE_CACHE_SIZE - 1);
		unsigned end = start + len;

		/* Reading beyond i_size is simple: memset to zero */
		zero_user_segments(page, 0, start, end, PAGE_CACHE_SIZE);
		return 0;
	}
	return logfs_readpage_nolock(page);
}

static int logfs_write_end(struct file *file, struct address_space *mapping,
		loff_t pos, unsigned len, unsigned copied, struct page *page,
		void *fsdata)
{
	struct inode *inode = mapping->host;
	pgoff_t index = page->index;
	unsigned start = pos & (PAGE_CACHE_SIZE - 1);
	unsigned end = start + copied;
	int ret = 0;

	BUG_ON(PAGE_CACHE_SIZE != inode->i_sb->s_blocksize);
	BUG_ON(page->index > I3_BLOCKS);

	if (copied < len) {
		/*
		 * Short write of a non-initialized paged.  Just tell userspace
		 * to retry the entire page.
		 */
		if (!PageUptodate(page)) {
			copied = 0;
			goto out;
		}
	}
	if (copied == 0)
		goto out; /* FIXME: do we need to update inode? */

	if (i_size_read(inode) < (index << PAGE_CACHE_SHIFT) + end) {
		i_size_write(inode, (index << PAGE_CACHE_SHIFT) + end);
		mark_inode_dirty_sync(inode);
	}

	SetPageUptodate(page);
	if (!PageDirty(page)) {
		if (!get_page_reserve(inode, page))
			__set_page_dirty_nobuffers(page);
		else
			ret = logfs_write_buf(inode, page, WF_LOCK);
	}
out:
	unlock_page(page);
	page_cache_release(page);
	return ret ? ret : copied;
}

int logfs_readpage(struct file *file, struct page *page)
{
	int ret;

	ret = logfs_readpage_nolock(page);
	unlock_page(page);
	return ret;
}

/* Clear the page's dirty flag in the radix tree. */
/* TODO: mucking with PageWriteback is silly.  Add a generic function to clear
 * the dirty bit from the radix tree for filesystems that don't have to wait
 * for page writeback to finish (i.e. any compressing filesystem).
 */
static void clear_radix_tree_dirty(struct page *page)
{
	BUG_ON(PagePrivate(page) || page->private);
	set_page_writeback(page);
	end_page_writeback(page);
}

static int __logfs_writepage(struct page *page)
{
	struct inode *inode = page->mapping->host;
	int err;

	err = logfs_write_buf(inode, page, WF_LOCK);
	if (err)
		set_page_dirty(page);
	else
		clear_radix_tree_dirty(page);
	unlock_page(page);
	return err;
}

static int logfs_writepage(struct page *page, struct writeback_control *wbc)
{
	struct inode *inode = page->mapping->host;
	loff_t i_size = i_size_read(inode);
	pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
	unsigned offset;
	u64 bix;
	level_t level;

	log_file("logfs_writepage(%lx, %lx, %p)\n", inode->i_ino, page->index,
			page);

	logfs_unpack_index(page->index, &bix, &level);

	/* Indirect blocks are never truncated */
	if (level != 0)
		return __logfs_writepage(page);

	/*
	 * TODO: everything below is a near-verbatim copy of nobh_writepage().
	 * The relevant bits should be factored out after logfs is merged.
	 */

	/* Is the page fully inside i_size? */
	if (bix < end_index)
		return __logfs_writepage(page);

	 /* Is the page fully outside i_size? (truncate in progress) */
	offset = i_size & (PAGE_CACHE_SIZE-1);
	if (bix > end_index || offset == 0) {
		unlock_page(page);
		return 0; /* don't care */
	}

	/*
	 * The page straddles i_size.  It must be zeroed out on each and every
	 * writepage invokation because it may be mmapped.  "A file is mapped
	 * in multiples of the page size.  For a file that is not a multiple of
	 * the  page size, the remaining memory is zeroed when mapped, and
	 * writes to that region are not written out to the file."
	 */
	zero_user_segment(page, offset, PAGE_CACHE_SIZE);
	return __logfs_writepage(page);
}

static void logfs_invalidatepage(struct page *page, unsigned long offset)
{
	struct logfs_block *block = logfs_block(page);

	if (block->reserved_bytes) {
		struct super_block *sb = page->mapping->host->i_sb;
		struct logfs_super *super = logfs_super(sb);

		super->s_dirty_pages -= block->reserved_bytes;
		block->ops->free_block(sb, block);
		BUG_ON(bitmap_weight(block->alias_map, LOGFS_BLOCK_FACTOR));
	} else
		move_page_to_btree(page);
	BUG_ON(PagePrivate(page) || page->private);
}

static int logfs_releasepage(struct page *page, gfp_t only_xfs_uses_this)
{
	return 0; /* None of these are easy to release */
}


int logfs_ioctl(struct inode *inode, struct file *file, unsigned int cmd,
		unsigned long arg)
{
	struct logfs_inode *li = logfs_inode(inode);
	unsigned int oldflags, flags;
	int err;

	switch (cmd) {
	case FS_IOC_GETFLAGS:
		flags = li->li_flags & LOGFS_FL_USER_VISIBLE;
		return put_user(flags, (int __user *)arg);
	case FS_IOC_SETFLAGS:
		if (IS_RDONLY(inode))
			return -EROFS;

		if (!is_owner_or_cap(inode))
			return -EACCES;

		err = get_user(flags, (int __user *)arg);
		if (err)
			return err;

		mutex_lock(&inode->i_mutex);
		oldflags = li->li_flags;
		flags &= LOGFS_FL_USER_MODIFIABLE;
		flags |= oldflags & ~LOGFS_FL_USER_MODIFIABLE;
		li->li_flags = flags;
		mutex_unlock(&inode->i_mutex);

		inode->i_ctime = CURRENT_TIME;
		mark_inode_dirty_sync(inode);
		return 0;

	default:
		return -ENOTTY;
	}
}

int logfs_fsync(struct file *file, int datasync)
{
	struct super_block *sb = file->f_mapping->host->i_sb;

	logfs_write_anchor(sb);
	return 0;
}

static int logfs_setattr(struct dentry *dentry, struct iattr *attr)
{
	struct inode *inode = dentry->d_inode;
	int err = 0;

	if (attr->ia_valid & ATTR_SIZE)
		err = logfs_truncate(inode, attr->ia_size);
	attr->ia_valid &= ~ATTR_SIZE;

	if (!err)
		err = inode_change_ok(inode, attr);
	if (!err)
		err = inode_setattr(inode, attr);
	return err;
}

const struct inode_operations logfs_reg_iops = {
	.setattr	= logfs_setattr,
};

const struct file_operations logfs_reg_fops = {
	.aio_read	= generic_file_aio_read,
	.aio_write	= generic_file_aio_write,
	.fsync		= logfs_fsync,
	.ioctl		= logfs_ioctl,
	.llseek		= generic_file_llseek,
	.mmap		= generic_file_readonly_mmap,
	.open		= generic_file_open,
	.read		= do_sync_read,
	.write		= do_sync_write,
};

const struct address_space_operations logfs_reg_aops = {
	.invalidatepage	= logfs_invalidatepage,
	.readpage	= logfs_readpage,
	.releasepage	= logfs_releasepage,
	.set_page_dirty	= __set_page_dirty_nobuffers,
	.writepage	= logfs_writepage,
	.writepages	= generic_writepages,
	.write_begin	= logfs_write_begin,
	.write_end	= logfs_write_end,
};