summaryrefslogtreecommitdiffstats
path: root/sys/gnu/ext2fs/ext2_readwrite.c
blob: 2772f7b2306e9102a0b8a1cea2873bb24386280f (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
/*
 *  modified for Lites 1.1
 *
 *  Aug 1995, Godmar Back (gback@cs.utah.edu)
 *  University of Utah, Department of Computer Science
 */
/*
 * Copyright (c) 1993
 *	The Regents of the University of California.  All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 3. All advertising materials mentioning features or use of this software
 *    must display the following acknowledgement:
 *	This product includes software developed by the University of
 *	California, Berkeley and its contributors.
 * 4. Neither the name of the University nor the names of its contributors
 *    may be used to endorse or promote products derived from this software
 *    without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 *
 *	@(#)ufs_readwrite.c	8.7 (Berkeley) 1/21/94
 * $FreeBSD$
 */

#define	BLKSIZE(a, b, c)	blksize(a, b, c)
#define	FS			struct ext2_sb_info
#define	I_FS			i_e2fs
#define	READ			ext2_read
#define	READ_S			"ext2_read"
#define	WRITE			ext2_write
#define	WRITE_S			"ext2_write"

/*
 * Vnode op for reading.
 */
/* ARGSUSED */
static int
READ(ap)
	struct vop_read_args /* {
		struct vnode *a_vp;
		struct uio *a_uio;
		int a_ioflag;
		struct ucred *a_cred;
	} */ *ap;
{
	register struct vnode *vp;
	register struct inode *ip;
	register struct uio *uio;
	register FS *fs;
	struct buf *bp;
	daddr_t lbn, nextlbn;
	off_t bytesinfile;
	long size, xfersize, blkoffset;
	int error, orig_resid;
	int seqcount = ap->a_ioflag >> 16;
	u_short mode;

	vp = ap->a_vp;
	ip = VTOI(vp);
	mode = ip->i_mode;
	uio = ap->a_uio;

#ifdef DIAGNOSTIC
	if (uio->uio_rw != UIO_READ)
		panic("%s: mode", READ_S);

	if (vp->v_type == VLNK) {
		if ((int)ip->i_size < vp->v_mount->mnt_maxsymlinklen)
			panic("%s: short symlink", READ_S);
	} else if (vp->v_type != VREG && vp->v_type != VDIR)
		panic("%s: type %d", READ_S, vp->v_type);
#endif
	fs = ip->I_FS;
#if 0
	if ((u_quad_t)uio->uio_offset > fs->fs_maxfilesize)
		return (EFBIG);
#endif

	orig_resid = uio->uio_resid;
	for (error = 0, bp = NULL; uio->uio_resid > 0; bp = NULL) {
		if ((bytesinfile = ip->i_size - uio->uio_offset) <= 0)
			break;
		lbn = lblkno(fs, uio->uio_offset);
		nextlbn = lbn + 1;
		size = BLKSIZE(fs, ip, lbn);
		blkoffset = blkoff(fs, uio->uio_offset);

		xfersize = fs->s_frag_size - blkoffset;
		if (uio->uio_resid < xfersize)
			xfersize = uio->uio_resid;
		if (bytesinfile < xfersize)
			xfersize = bytesinfile;

		if (lblktosize(fs, nextlbn) >= ip->i_size)
			error = bread(vp, lbn, size, NOCRED, &bp);
		else if ((vp->v_mount->mnt_flag & MNT_NOCLUSTERR) == 0)
			error = cluster_read(vp,
			    ip->i_size, lbn, size, NOCRED,
				uio->uio_resid, (ap->a_ioflag >> 16), &bp);
		else if (seqcount > 1) {
			int nextsize = BLKSIZE(fs, ip, nextlbn);
			error = breadn(vp, lbn,
			    size, &nextlbn, &nextsize, 1, NOCRED, &bp);
		} else
			error = bread(vp, lbn, size, NOCRED, &bp);
		if (error) {
			brelse(bp);
			bp = NULL;
			break;
		}

		/*
		 * We should only get non-zero b_resid when an I/O error
		 * has occurred, which should cause us to break above.
		 * However, if the short read did not cause an error,
		 * then we want to ensure that we do not uiomove bad
		 * or uninitialized data.
		 */
		size -= bp->b_resid;
		if (size < xfersize) {
			if (size == 0)
				break;
			xfersize = size;
		}
		error =
		    uiomove((char *)bp->b_data + blkoffset, (int)xfersize, uio);
		if (error)
			break;

		bqrelse(bp);
	}
	if (bp != NULL)
		bqrelse(bp);
	if (orig_resid > 0 && (error == 0 || uio->uio_resid != orig_resid) &&
	    (vp->v_mount->mnt_flag & MNT_NOATIME) == 0)
		ip->i_flag |= IN_ACCESS;
	return (error);
}

/*
 * Vnode op for writing.
 */
static int
WRITE(ap)
	struct vop_write_args /* {
		struct vnode *a_vp;
		struct uio *a_uio;
		int a_ioflag;
		struct ucred *a_cred;
	} */ *ap;
{
	register struct vnode *vp;
	register struct uio *uio;
	register struct inode *ip;
	register FS *fs;
	struct buf *bp;
	struct thread *td;
	daddr_t lbn;
	off_t osize;
	int seqcount;
	int blkoffset, error, flags, ioflag, resid, size, xfersize;

	ioflag = ap->a_ioflag;
	seqcount = ap->a_ioflag >> 16;
	uio = ap->a_uio;
	vp = ap->a_vp;
	ip = VTOI(vp);

#ifdef DIAGNOSTIC
	if (uio->uio_rw != UIO_WRITE)
		panic("%s: mode", WRITE_S);
#endif

	switch (vp->v_type) {
	case VREG:
		if (ioflag & IO_APPEND)
			uio->uio_offset = ip->i_size;
		if ((ip->i_flags & APPEND) && uio->uio_offset != ip->i_size)
			return (EPERM);
		/* FALLTHROUGH */
	case VLNK:
		break;
	case VDIR:
		if ((ioflag & IO_SYNC) == 0)
			panic("%s: nonsync dir write", WRITE_S);
		break;
	default:
		panic("%s: type", WRITE_S);
	}

	fs = ip->I_FS;
#if 0
	if (uio->uio_offset < 0 ||
	    (u_quad_t)uio->uio_offset + uio->uio_resid > fs->fs_maxfilesize)
		return (EFBIG);
#endif
	/*
	 * Maybe this should be above the vnode op call, but so long as
	 * file servers have no limits, I don't think it matters.
	 */
	td = uio->uio_td;
	/* For p_rlimit. */
	mtx_assert(&Giant, MA_OWNED);
	if (vp->v_type == VREG && td &&
	    uio->uio_offset + uio->uio_resid >
	    td->td_proc->p_rlimit[RLIMIT_FSIZE].rlim_cur) {
		PROC_LOCK(td->td_proc);
		psignal(td->td_proc, SIGXFSZ);
		PROC_UNLOCK(td->td_proc);
		return (EFBIG);
	}

	resid = uio->uio_resid;
	osize = ip->i_size;
	flags = ioflag & IO_SYNC ? B_SYNC : 0;

	for (error = 0; uio->uio_resid > 0;) {
		lbn = lblkno(fs, uio->uio_offset);
		blkoffset = blkoff(fs, uio->uio_offset);
		xfersize = fs->s_frag_size - blkoffset;
		if (uio->uio_resid < xfersize)
			xfersize = uio->uio_resid;

		if (uio->uio_offset + xfersize > ip->i_size)
			vnode_pager_setsize(vp, uio->uio_offset + xfersize);

		/*
		 * Avoid a data-consistency race between write() and mmap()
		 * by ensuring that newly allocated blocks are zerod.  The
		 * race can occur even in the case where the write covers
		 * the entire block.
		 */
		flags |= B_CLRBUF;
#if 0
		if (fs->s_frag_size > xfersize)
			flags |= B_CLRBUF;
		else
			flags &= ~B_CLRBUF;
#endif

		error = ext2_balloc(ip,
		    lbn, blkoffset + xfersize, ap->a_cred, &bp, flags);
		if (error)
			break;

		if (uio->uio_offset + xfersize > ip->i_size) {
			ip->i_size = uio->uio_offset + xfersize;
		}

		size = BLKSIZE(fs, ip, lbn) - bp->b_resid;
		if (size < xfersize)
			xfersize = size;

		error =
		    uiomove((char *)bp->b_data + blkoffset, (int)xfersize, uio);
		if ((ioflag & IO_VMIO) &&
		   (LIST_FIRST(&bp->b_dep) == NULL)) /* in ext2fs? */
			bp->b_flags |= B_RELBUF;

		if (ioflag & IO_SYNC) {
			(void)bwrite(bp);
		} else if (xfersize + blkoffset == fs->s_frag_size) {
			if ((vp->v_mount->mnt_flag & MNT_NOCLUSTERW) == 0) {
				bp->b_flags |= B_CLUSTEROK;
				cluster_write(bp, ip->i_size, seqcount);
			} else {
				bawrite(bp);
			}
		} else {
			bp->b_flags |= B_CLUSTEROK;
			bdwrite(bp);
		}
		if (error || xfersize == 0)
			break;
		ip->i_flag |= IN_CHANGE | IN_UPDATE;
	}
	/*
	 * If we successfully wrote any data, and we are not the superuser
	 * we clear the setuid and setgid bits as a precaution against
	 * tampering.
	 */
	if (resid > uio->uio_resid && ap->a_cred && ap->a_cred->cr_uid != 0)
		ip->i_mode &= ~(ISUID | ISGID);
	if (error) {
		if (ioflag & IO_UNIT) {
			(void)UFS_TRUNCATE(vp, osize,
			    ioflag & IO_SYNC, ap->a_cred, uio->uio_td);
			uio->uio_offset -= resid - uio->uio_resid;
			uio->uio_resid = resid;
		}
	} else if (resid > uio->uio_resid && (ioflag & IO_SYNC))
		error = UFS_UPDATE(vp, 1);
	return (error);
}
OpenPOWER on IntegriCloud