summaryrefslogtreecommitdiffstats
path: root/fs/block_dev.c
blob: 8331e9514d3cf6e34913cab5cb33b8c7221e29a7 (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
/*
 *  linux/fs/block_dev.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 */

#include <linux/mm.h>
#include <linux/locks.h>
#include <linux/fcntl.h>

#include <asm/uaccess.h>

extern int *blk_size[];
extern int *blksize_size[];

#define MAX_BUF_PER_PAGE (PAGE_SIZE / 512)
#define NBUF 64

ssize_t block_write(struct file * filp, const char * buf,
		    size_t count, loff_t *ppos)
{
	struct inode * inode = filp->f_dentry->d_inode;
	ssize_t blocksize, blocksize_bits, i, buffercount, write_error;
	ssize_t block, blocks;
	loff_t offset;
	ssize_t chars;
	ssize_t written = 0;
	struct buffer_head * bhlist[NBUF];
	size_t size;
	kdev_t dev;
	struct buffer_head * bh, *bufferlist[NBUF];
	register char * p;

	write_error = buffercount = 0;
	dev = inode->i_rdev;
	if ( is_read_only( inode->i_rdev ))
		return -EPERM;
	blocksize = BLOCK_SIZE;
	if (blksize_size[MAJOR(dev)] && blksize_size[MAJOR(dev)][MINOR(dev)])
		blocksize = blksize_size[MAJOR(dev)][MINOR(dev)];

	i = blocksize;
	blocksize_bits = 0;
	while(i != 1) {
		blocksize_bits++;
		i >>= 1;
	}

	block = *ppos >> blocksize_bits;
	offset = *ppos & (blocksize-1);

	if (blk_size[MAJOR(dev)])
		size = ((loff_t) blk_size[MAJOR(dev)][MINOR(dev)] << BLOCK_SIZE_BITS) >> blocksize_bits;
	else
		size = INT_MAX;
	while (count>0) {
		if (block >= size)
			return written ? written : -ENOSPC;
		chars = blocksize - offset;
		if (chars > count)
			chars=count;

#if 0
		/* get the buffer head */
		{
			struct buffer_head * (*fn)(kdev_t, int, int) = getblk;
			if (chars != blocksize)
				fn = bread;
			bh = fn(dev, block, blocksize);
		}
#else
		bh = getblk(dev, block, blocksize);

		if (chars != blocksize && !buffer_uptodate(bh)) {
		  if(!filp->f_reada ||
		     !read_ahead[MAJOR(dev)]) {
		    /* We do this to force the read of a single buffer */
		    brelse(bh);
		    bh = bread(dev,block,blocksize);
		  } else {
		    /* Read-ahead before write */
		    blocks = read_ahead[MAJOR(dev)] / (blocksize >> 9) / 2;
		    if (block + blocks > size) blocks = size - block;
		    if (blocks > NBUF) blocks=NBUF;
		    bhlist[0] = bh;
		    for(i=1; i<blocks; i++){
		      bhlist[i] = getblk (dev, block+i, blocksize);
		      if(!bhlist[i]){
			while(i >= 0) brelse(bhlist[i--]);
			return written ? written : -EIO;
		      };
		    };
		    ll_rw_block(READ, blocks, bhlist);
		    for(i=1; i<blocks; i++) brelse(bhlist[i]);
		    wait_on_buffer(bh);
		      
		  };
		};
#endif
		block++;
		if (!bh)
			return written ? written : -EIO;
		p = offset + bh->b_data;
		offset = 0;
		*ppos += chars;
		written += chars;
		count -= chars;
		copy_from_user(p,buf,chars);
		p += chars;
		buf += chars;
		mark_buffer_uptodate(bh, 1);
		mark_buffer_dirty(bh, 0);
		if (filp->f_flags & O_SYNC)
			bufferlist[buffercount++] = bh;
		else
			brelse(bh);
		if (buffercount == NBUF){
			ll_rw_block(WRITE, buffercount, bufferlist);
			for(i=0; i<buffercount; i++){
				wait_on_buffer(bufferlist[i]);
				if (!buffer_uptodate(bufferlist[i]))
					write_error=1;
				brelse(bufferlist[i]);
			}
			buffercount=0;
		}
		balance_dirty(dev);
		if (write_error)
			break;
	}
	if ( buffercount ){
		ll_rw_block(WRITE, buffercount, bufferlist);
		for(i=0; i<buffercount; i++){
			wait_on_buffer(bufferlist[i]);
			if (!buffer_uptodate(bufferlist[i]))
				write_error=1;
			brelse(bufferlist[i]);
		}
	}		
	filp->f_reada = 1;
	if(write_error)
		return -EIO;
	return written;
}

ssize_t block_read(struct file * filp, char * buf, size_t count, loff_t *ppos)
{
	struct inode * inode = filp->f_dentry->d_inode;
	size_t block;
	loff_t offset;
	ssize_t blocksize;
	ssize_t blocksize_bits, i;
	size_t blocks, rblocks, left;
	int bhrequest, uptodate;
	struct buffer_head ** bhb, ** bhe;
	struct buffer_head * buflist[NBUF];
	struct buffer_head * bhreq[NBUF];
	unsigned int chars;
	loff_t size;
	kdev_t dev;
	ssize_t read;

	dev = inode->i_rdev;
	blocksize = BLOCK_SIZE;
	if (blksize_size[MAJOR(dev)] && blksize_size[MAJOR(dev)][MINOR(dev)])
		blocksize = blksize_size[MAJOR(dev)][MINOR(dev)];
	i = blocksize;
	blocksize_bits = 0;
	while (i != 1) {
		blocksize_bits++;
		i >>= 1;
	}

	offset = *ppos;
	if (blk_size[MAJOR(dev)])
		size = (loff_t) blk_size[MAJOR(dev)][MINOR(dev)] << BLOCK_SIZE_BITS;
	else
		size = INT_MAX;

	if (offset > size)
		left = 0;
	/* size - offset might not fit into left, so check explicitly. */
	else if (size - offset > INT_MAX)
		left = INT_MAX;
	else
		left = size - offset;
	if (left > count)
		left = count;
	if (left <= 0)
		return 0;
	read = 0;
	block = offset >> blocksize_bits;
	offset &= blocksize-1;
	size >>= blocksize_bits;
	rblocks = blocks = (left + offset + blocksize - 1) >> blocksize_bits;
	bhb = bhe = buflist;
	if (filp->f_reada) {
	        if (blocks < read_ahead[MAJOR(dev)] / (blocksize >> 9))
			blocks = read_ahead[MAJOR(dev)] / (blocksize >> 9);
		if (rblocks > blocks)
			blocks = rblocks;
		
	}
	if (block + blocks > size) {
		blocks = size - block;
		if (blocks == 0)
			return 0;
	}

	/* We do this in a two stage process.  We first try to request
	   as many blocks as we can, then we wait for the first one to
	   complete, and then we try to wrap up as many as are actually
	   done.  This routine is rather generic, in that it can be used
	   in a filesystem by substituting the appropriate function in
	   for getblk.

	   This routine is optimized to make maximum use of the various
	   buffers and caches. */

	do {
		bhrequest = 0;
		uptodate = 1;
		while (blocks) {
			--blocks;
			*bhb = getblk(dev, block++, blocksize);
			if (*bhb && !buffer_uptodate(*bhb)) {
				uptodate = 0;
				bhreq[bhrequest++] = *bhb;
			}

			if (++bhb == &buflist[NBUF])
				bhb = buflist;

			/* If the block we have on hand is uptodate, go ahead
			   and complete processing. */
			if (uptodate)
				break;
			if (bhb == bhe)
				break;
		}

		/* Now request them all */
		if (bhrequest) {
			ll_rw_block(READ, bhrequest, bhreq);
		}

		do { /* Finish off all I/O that has actually completed */
			if (*bhe) {
				wait_on_buffer(*bhe);
				if (!buffer_uptodate(*bhe)) {	/* read error? */
				        brelse(*bhe);
					if (++bhe == &buflist[NBUF])
					  bhe = buflist;
					left = 0;
					break;
				}
			}			
			if (left < blocksize - offset)
				chars = left;
			else
				chars = blocksize - offset;
			*ppos += chars;
			left -= chars;
			read += chars;
			if (*bhe) {
				copy_to_user(buf,offset+(*bhe)->b_data,chars);
				brelse(*bhe);
				buf += chars;
			} else {
				while (chars-- > 0)
					put_user(0,buf++);
			}
			offset = 0;
			if (++bhe == &buflist[NBUF])
				bhe = buflist;
		} while (left > 0 && bhe != bhb && (!*bhe || !buffer_locked(*bhe)));
		if (bhe == bhb && !blocks)
			break;
	} while (left > 0);

/* Release the read-ahead blocks */
	while (bhe != bhb) {
		brelse(*bhe);
		if (++bhe == &buflist[NBUF])
			bhe = buflist;
	};
	if (!read)
		return -EIO;
	filp->f_reada = 1;
	return read;
}

/*
 *	Filp may be NULL when we are called by an msync of a vma
 *	since the vma has no handle.
 */
 
int block_fsync(struct file *filp, struct dentry *dentry)
{
	return fsync_dev(dentry->d_inode->i_rdev);
}