summaryrefslogtreecommitdiff
path: root/bin/dd/dd.c
blob: 601da2b113c01132d1b05c03592027de22726241 (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
/*	$OpenBSD: dd.c,v 1.8 1998/04/30 05:55:02 deraadt Exp $	*/
/*	$NetBSD: dd.c,v 1.6 1996/02/20 19:29:06 jtc Exp $	*/

/*-
 * Copyright (c) 1991, 1993, 1994
 *	The Regents of the University of California.  All rights reserved.
 *
 * This code is derived from software contributed to Berkeley by
 * Keith Muller of the University of California, San Diego and Lance
 * Visser of Convex Computer Corporation.
 *
 * 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.
 */

#ifndef lint
static char copyright[] =
"@(#) Copyright (c) 1991, 1993, 1994\n\
	The Regents of the University of California.  All rights reserved.\n";
#endif /* not lint */

#ifndef lint
#if 0
static char sccsid[] = "@(#)dd.c	8.5 (Berkeley) 4/2/94";
#else
static char rcsid[] = "$OpenBSD: dd.c,v 1.8 1998/04/30 05:55:02 deraadt Exp $";
#endif
#endif /* not lint */

#include <sys/param.h>
#include <sys/stat.h>
#include <sys/ioctl.h>
#include <sys/mtio.h>

#include <ctype.h>
#include <err.h>
#include <errno.h>
#include <fcntl.h>
#include <signal.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>

#include "dd.h"
#include "extern.h"

static void dd_close __P((void));
static void dd_in __P((void));
static void getfdtype __P((IO *));
static void setup __P((void));

IO	in, out;		/* input/output state */
STAT	st;			/* statistics */
void	(*cfunc) __P((void));	/* conversion function */
size_t	cpy_cnt;		/* # of blocks to copy */
u_int	ddflags;		/* conversion options */
size_t	cbsz;			/* conversion block size */
size_t	files_cnt = 1;		/* # of files to copy */
const	u_char	*ctab;		/* conversion table */

int
main(argc, argv)
	int argc;
	char *argv[];
{
	jcl(argv);
	setup();

	(void)signal(SIGINFO, summaryx);
	(void)signal(SIGINT, terminate);

	atexit(summary);

	while (files_cnt--)
		dd_in();

	dd_close();
	exit(0);
}

static void
setup()
{
	u_int cnt;

	if (in.name == NULL) {
		in.name = "stdin";
		in.fd = STDIN_FILENO;
	} else {
		in.fd = open(in.name, O_RDONLY, 0);
		if (in.fd < 0)
			err(1, "%s", in.name);
	}

	getfdtype(&in);

	if (files_cnt > 1 && !(in.flags & ISTAPE))
		errx(1, "files is not supported for non-tape devices");

	if (out.name == NULL) {
		/* No way to check for read access here. */
		out.fd = STDOUT_FILENO;
		out.name = "stdout";
	} else {
#define	OFLAGS \
    (O_CREAT | (ddflags & (C_SEEK | C_NOTRUNC) ? 0 : O_TRUNC))
		out.fd = open(out.name, O_RDWR | OFLAGS, DEFFILEMODE);
		/*
		 * May not have read access, so try again with write only.
		 * Without read we may have a problem if output also does
		 * not support seeks.
		 */
		if (out.fd < 0) {
			out.fd = open(out.name, O_WRONLY | OFLAGS, DEFFILEMODE);
			out.flags |= NOREAD;
		}
		if (out.fd < 0)
			err(1, "%s", out.name);
	}

	getfdtype(&out);

	/*
	 * Allocate space for the input and output buffers.  If not doing
	 * record oriented I/O, only need a single buffer.
	 */
	if (!(ddflags & (C_BLOCK|C_UNBLOCK))) {
		if ((in.db = malloc(out.dbsz + in.dbsz - 1)) == NULL)
			err(1, "input buffer");
		out.db = in.db;
	} else if ((in.db =
	    malloc((u_int)(MAX(in.dbsz, cbsz) + cbsz))) == NULL ||
	    (out.db = malloc((u_int)(out.dbsz + cbsz))) == NULL)
		err(1, "output buffer");
	in.dbp = in.db;
	out.dbp = out.db;

	/* Position the input/output streams. */
	if (in.offset)
		pos_in();
	if (out.offset)
		pos_out();

	/*
	 * Truncate the output file; ignore errors because it fails on some
	 * kinds of output files, tapes, for example.
	 */
	if ((ddflags & (C_OF | C_SEEK | C_NOTRUNC)) == (C_OF | C_SEEK))
		(void)ftruncate(out.fd, out.offset * out.dbsz);

	/*
	 * If converting case at the same time as another conversion, build a
	 * table that does both at once.  If just converting case, use the
	 * built-in tables.
	 */
	if (ddflags & (C_LCASE|C_UCASE)) {
#ifdef	NO_CONV
		/* Should not get here, but just in case... */
		errx(1, "case conv and -DNO_CONV");
#else	/* NO_CONV */
		if (ddflags & C_ASCII || ddflags & C_EBCDIC) {
			if (ddflags & C_LCASE) {
				for (cnt = 0; cnt < 0377; ++cnt)
					casetab[cnt] = tolower(ctab[cnt]);
			} else {
				for (cnt = 0; cnt < 0377; ++cnt)
					casetab[cnt] = toupper(ctab[cnt]);
			}
		} else {
			if (ddflags & C_LCASE) {
				for (cnt = 0; cnt < 0377; ++cnt)
					casetab[cnt] = tolower(cnt);
			} else {
				for (cnt = 0; cnt < 0377; ++cnt)
					casetab[cnt] = toupper(cnt);
			}
		}

		ctab = casetab;
#endif	/* NO_CONV */
	}

	(void)time(&st.start);			/* Statistics timestamp. */
}

static void
getfdtype(io)
	IO *io;
{
	struct mtget mt;
	struct stat sb;

	if (fstat(io->fd, &sb))
		err(1, "%s", io->name);
	if (S_ISCHR(sb.st_mode))
		io->flags |= ioctl(io->fd, MTIOCGET, &mt) ? ISCHR : ISTAPE;
	else if (lseek(io->fd, (off_t)0, SEEK_CUR) == -1 && errno == ESPIPE)
		io->flags |= ISPIPE;		/* XXX fixed in 4.4BSD */
}

static void
dd_in()
{
	ssize_t n;

	for (;;) {
		if (cpy_cnt && (st.in_full + st.in_part) >= cpy_cnt)
			return;

		/*
		 * Zero the buffer first if sync; if doing block operations
		 * use spaces.
		 */
		if (ddflags & C_SYNC) {
			if (ddflags & (C_BLOCK|C_UNBLOCK))
				(void)memset(in.dbp, ' ', in.dbsz);
			else
				(void)memset(in.dbp, 0, in.dbsz);
		}

		n = read(in.fd, in.dbp, in.dbsz);
		if (n == 0) {
			in.dbrcnt = 0;
			return;
		}

		/* Read error. */
		if (n < 0) {
			/*
			 * If noerror not specified, die.  POSIX requires that
			 * the warning message be followed by an I/O display.
			 */
			if (!(ddflags & C_NOERROR))
				err(1, "%s", in.name);
			warn("%s", in.name);
			summary();

			/*
			 * If it's not a tape drive or a pipe, seek past the
			 * error.  If your OS doesn't do the right thing for
			 * raw disks this section should be modified to re-read
			 * in sector size chunks.
			 */
			if (!(in.flags & (ISPIPE|ISTAPE)) &&
			    lseek(in.fd, (off_t)in.dbsz, SEEK_CUR))
				warn("%s", in.name);

			/* If sync not specified, omit block and continue. */
			if (!(ddflags & C_SYNC))
				continue;

			/* Read errors count as full blocks. */
			in.dbcnt += in.dbrcnt = in.dbsz;
			++st.in_full;

		/* Handle full input blocks. */
		} else if (n == in.dbsz) {
			in.dbcnt += in.dbrcnt = n;
			++st.in_full;

		/* Handle partial input blocks. */
		} else {
			/* If sync, use the entire block. */
			if (ddflags & C_SYNC)
				in.dbcnt += in.dbrcnt = in.dbsz;
			else
				in.dbcnt += in.dbrcnt = n;
			++st.in_part;
		}

		/*
		 * POSIX states that if bs is set and no other conversions
		 * than noerror, notrunc or sync are specified, the block
		 * is output without buffering as it is read.
		 */
		if (ddflags & C_BS) {
			out.dbcnt = in.dbcnt;
			dd_out(1);
			in.dbcnt = 0;
			continue;
		}

		if (ddflags & C_SWAB) {
			if ((n = in.dbcnt) & 1) {
				++st.swab;
				--n;
			}
			swab(in.dbp, in.dbp, n);
		}

		in.dbp += in.dbrcnt;
		(*cfunc)();
	}
}

/*
 * Cleanup any remaining I/O and flush output.  If necessary, output file
 * is truncated.
 */
static void
dd_close()
{
	if (cfunc == def)
		def_close();
	else if (cfunc == block)
		block_close();
	else if (cfunc == unblock)
		unblock_close();
	if (ddflags & C_OSYNC && out.dbcnt && out.dbcnt < out.dbsz) {
		if (ddflags & (C_BLOCK|C_UNBLOCK))
			memset(out.dbp, ' ', out.dbsz - out.dbcnt);
		else
			memset(out.dbp, 0, out.dbsz - out.dbcnt);
		out.dbcnt = out.dbsz;
	}
	if (out.dbcnt)
		dd_out(1);
}

void
dd_out(force)
	int force;
{
	static int warned;
	size_t cnt, n;
	ssize_t nw;
	u_char *outp;

	/*
	 * Write one or more blocks out.  The common case is writing a full
	 * output block in a single write; increment the full block stats.
	 * Otherwise, we're into partial block writes.  If a partial write,
	 * and it's a character device, just warn.  If a tape device, quit.
	 *
	 * The partial writes represent two cases.  1: Where the input block
	 * was less than expected so the output block was less than expected.
	 * 2: Where the input block was the right size but we were forced to
	 * write the block in multiple chunks.  The original versions of dd(1)
	 * never wrote a block in more than a single write, so the latter case
	 * never happened.
	 *
	 * One special case is if we're forced to do the write -- in that case
	 * we play games with the buffer size, and it's usually a partial write.
	 */
	outp = out.db;
	for (n = force ? out.dbcnt : out.dbsz;; n = out.dbsz) {
		for (cnt = n;; cnt -= nw) {
			nw = write(out.fd, outp, cnt);
			if (nw <= 0) {
				if (nw == 0)
					errx(1, "%s: end of device", out.name);
				if (errno != EINTR)
					err(1, "%s", out.name);
				nw = 0;
			}
			outp += nw;
			st.bytes += nw;
			if (nw == n) {
				if (n != out.dbsz)
					++st.out_part;
				else
					++st.out_full;
				break;
			}
			++st.out_part;
			if (nw == cnt)
				break;
			if (out.flags & ISCHR && !warned) {
				warned = 1;
				warnx("%s: short write on character device",
				    out.name);
			}
			if (out.flags & ISTAPE)
				errx(1, "%s: short write on tape device", out.name);
		}
		if ((out.dbcnt -= n) < out.dbsz)
			break;
	}

	/* Reassemble the output block. */
	if (out.dbcnt)
		(void)memmove(out.db, out.dbp - out.dbcnt, out.dbcnt);
	out.dbp = out.db + out.dbcnt;
}