aboutsummaryrefslogtreecommitdiffstats
path: root/net/sctp/chunk.c
blob: 1748ef90950c44c800d06de82bb2999540fe97e4 (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
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
/* SCTP kernel implementation
 * (C) Copyright IBM Corp. 2003, 2004
 *
 * This file is part of the SCTP kernel implementation
 *
 * This file contains the code relating the chunk abstraction.
 *
 * This SCTP implementation is free software;
 * you can redistribute it and/or modify it under the terms of
 * the GNU General Public License as published by
 * the Free Software Foundation; either version 2, or (at your option)
 * any later version.
 *
 * This SCTP implementation is distributed in the hope that it
 * will be useful, but WITHOUT ANY WARRANTY; without even the implied
 *                 ************************
 * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
 * See the GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with GNU CC; see the file COPYING.  If not, write to
 * the Free Software Foundation, 59 Temple Place - Suite 330,
 * Boston, MA 02111-1307, USA.
 *
 * Please send any bug reports or fixes you make to the
 * email address(es):
 *    lksctp developers <lksctp-developers@lists.sourceforge.net>
 *
 * Or submit a bug report through the following website:
 *    http://www.sf.net/projects/lksctp
 *
 * Written or modified by:
 *    Jon Grimm             <jgrimm@us.ibm.com>
 *    Sridhar Samudrala     <sri@us.ibm.com>
 *
 * Any bugs reported given to us we will try to fix... any fixes shared will
 * be incorporated into the next SCTP release.
 */

#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/net.h>
#include <linux/inet.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <net/sctp/sctp.h>
#include <net/sctp/sm.h>

/* This file is mostly in anticipation of future work, but initially
 * populate with fragment tracking for an outbound message.
 */

/* Initialize datamsg from memory. */
static void sctp_datamsg_init(struct sctp_datamsg *msg)
{
	atomic_set(&msg->refcnt, 1);
	msg->send_failed = 0;
	msg->send_error = 0;
	msg->can_abandon = 0;
	msg->expires_at = 0;
	INIT_LIST_HEAD(&msg->chunks);
}

/* Allocate and initialize datamsg. */
SCTP_STATIC struct sctp_datamsg *sctp_datamsg_new(gfp_t gfp)
{
	struct sctp_datamsg *msg;
	msg = kmalloc(sizeof(struct sctp_datamsg), gfp);
	if (msg) {
		sctp_datamsg_init(msg);
		SCTP_DBG_OBJCNT_INC(datamsg);
	}
	return msg;
}

/* Final destructruction of datamsg memory. */
static void sctp_datamsg_destroy(struct sctp_datamsg *msg)
{
	struct list_head *pos, *temp;
	struct sctp_chunk *chunk;
	struct sctp_sock *sp;
	struct sctp_ulpevent *ev;
	struct sctp_association *asoc = NULL;
	int error = 0, notify;

	/* If we failed, we may need to notify. */
	notify = msg->send_failed ? -1 : 0;

	/* Release all references. */
	list_for_each_safe(pos, temp, &msg->chunks) {
		list_del_init(pos);
		chunk = list_entry(pos, struct sctp_chunk, frag_list);
		/* Check whether we _really_ need to notify. */
		if (notify < 0) {
			asoc = chunk->asoc;
			if (msg->send_error)
				error = msg->send_error;
			else
				error = asoc->outqueue.error;

			sp = sctp_sk(asoc->base.sk);
			notify = sctp_ulpevent_type_enabled(SCTP_SEND_FAILED,
							    &sp->subscribe);
		}

		/* Generate a SEND FAILED event only if enabled. */
		if (notify > 0) {
			int sent;
			if (chunk->has_tsn)
				sent = SCTP_DATA_SENT;
			else
				sent = SCTP_DATA_UNSENT;

			ev = sctp_ulpevent_make_send_failed(asoc, chunk, sent,
							    error, GFP_ATOMIC);
			if (ev)
				sctp_ulpq_tail_event(&asoc->ulpq, ev);
		}

		sctp_chunk_put(chunk);
	}

	SCTP_DBG_OBJCNT_DEC(datamsg);
	kfree(msg);
}

/* Hold a reference. */
static void sctp_datamsg_hold(struct sctp_datamsg *msg)
{
	atomic_inc(&msg->refcnt);
}

/* Release a reference. */
void sctp_datamsg_put(struct sctp_datamsg *msg)
{
	if (atomic_dec_and_test(&msg->refcnt))
		sctp_datamsg_destroy(msg);
}

/* Assign a chunk to this datamsg. */
static void sctp_datamsg_assign(struct sctp_datamsg *msg, struct sctp_chunk *chunk)
{
	sctp_datamsg_hold(msg);
	chunk->msg = msg;
}


/* A data chunk can have a maximum payload of (2^16 - 20).  Break
 * down any such message into smaller chunks.  Opportunistically, fragment
 * the chunks down to the current MTU constraints.  We may get refragmented
 * later if the PMTU changes, but it is _much better_ to fragment immediately
 * with a reasonable guess than always doing our fragmentation on the
 * soft-interrupt.
 */
struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc,
					    struct sctp_sndrcvinfo *sinfo,
					    struct msghdr *msgh, int msg_len)
{
	int max, whole, i, offset, over, err;
	int len, first_len;
	struct sctp_chunk *chunk;
	struct sctp_datamsg *msg;
	struct list_head *pos, *temp;
	__u8 frag;

	msg = sctp_datamsg_new(GFP_KERNEL);
	if (!msg)
		return NULL;

	/* Note: Calculate this outside of the loop, so that all fragments
	 * have the same expiration.
	 */
	if (sinfo->sinfo_timetolive) {
		/* sinfo_timetolive is in milliseconds */
		msg->expires_at = jiffies +
				    msecs_to_jiffies(sinfo->sinfo_timetolive);
		msg->can_abandon = 1;
		SCTP_DEBUG_PRINTK("%s: msg:%p expires_at: %ld jiffies:%ld\n",
				  __func__, msg, msg->expires_at, jiffies);
	}

	max = asoc->frag_point;

	/* If the the peer requested that we authenticate DATA chunks
	 * we need to accound for bundling of the AUTH chunks along with
	 * DATA.
	 */
	if (sctp_auth_send_cid(SCTP_CID_DATA, asoc)) {
		struct sctp_hmac *hmac_desc = sctp_auth_asoc_get_hmac(asoc);

		if (hmac_desc)
			max -= WORD_ROUND(sizeof(sctp_auth_chunk_t) +
					    hmac_desc->hmac_len);
	}

	whole = 0;
	first_len = max;

	/* Encourage Cookie-ECHO bundling. */
	if (asoc->state < SCTP_STATE_COOKIE_ECHOED) {
		whole = msg_len / (max - SCTP_ARBITRARY_COOKIE_ECHO_LEN);

		/* Account for the DATA to be bundled with the COOKIE-ECHO. */
		if (whole) {
			first_len = max - SCTP_ARBITRARY_COOKIE_ECHO_LEN;
			msg_len -= first_len;
			whole = 1;
		}
	}

	/* How many full sized?  How many bytes leftover? */
	whole += msg_len / max;
	over = msg_len % max;
	offset = 0;

	if ((whole > 1) || (whole && over))
		SCTP_INC_STATS_USER(SCTP_MIB_FRAGUSRMSGS);

	/* Create chunks for all the full sized DATA chunks. */
	for (i=0, len=first_len; i < whole; i++) {
		frag = SCTP_DATA_MIDDLE_FRAG;

		if (0 == i)
			frag |= SCTP_DATA_FIRST_FRAG;

		if ((i == (whole - 1)) && !over)
			frag |= SCTP_DATA_LAST_FRAG;

		chunk = sctp_make_datafrag_empty(asoc, sinfo, len, frag, 0);

		if (!chunk)
			goto errout;
		err = sctp_user_addto_chunk(chunk, offset, len, msgh->msg_iov);
		if (err < 0)
			goto errout;

		offset += len;

		/* Put the chunk->skb back into the form expected by send.  */
		__skb_pull(chunk->skb, (__u8 *)chunk->chunk_hdr
			   - (__u8 *)chunk->skb->data);

		sctp_datamsg_assign(msg, chunk);
		list_add_tail(&chunk->frag_list, &msg->chunks);

		/* The first chunk, the first chunk was likely short
		 * to allow bundling, so reset to full size.
		 */
		if (0 == i)
			len = max;
	}

	/* .. now the leftover bytes. */
	if (over) {
		if (!whole)
			frag = SCTP_DATA_NOT_FRAG;
		else
			frag = SCTP_DATA_LAST_FRAG;

		chunk = sctp_make_datafrag_empty(asoc, sinfo, over, frag, 0);

		if (!chunk)
			goto errout;

		err = sctp_user_addto_chunk(chunk, offset, over,msgh->msg_iov);

		/* Put the chunk->skb back into the form expected by send.  */
		__skb_pull(chunk->skb, (__u8 *)chunk->chunk_hdr
			   - (__u8 *)chunk->skb->data);
		if (err < 0)
			goto errout;

		sctp_datamsg_assign(msg, chunk);
		list_add_tail(&chunk->frag_list, &msg->chunks);
	}

	return msg;

errout:
	list_for_each_safe(pos, temp, &msg->chunks) {
		list_del_init(pos);
		chunk = list_entry(pos, struct sctp_chunk, frag_list);
		sctp_chunk_free(chunk);
	}
	sctp_datamsg_put(msg);
	return NULL;
}

/* Check whether this message has expired. */
int sctp_chunk_abandoned(struct sctp_chunk *chunk)
{
	struct sctp_datamsg *msg = chunk->msg;

	if (!msg->can_abandon)
		return 0;

	if (time_after(jiffies, msg->expires_at))
		return 1;

	return 0;
}

/* This chunk (and consequently entire message) has failed in its sending. */
void sctp_chunk_fail(struct sctp_chunk *chunk, int error)
{
	chunk->msg->send_failed = 1;
	chunk->msg->send_error = error;
}
> 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435
/*
 * layout.h - All NTFS associated on-disk structures. Part of the Linux-NTFS
 *	      project.
 *
 * Copyright (c) 2001-2005 Anton Altaparmakov
 * Copyright (c) 2002 Richard Russon
 *
 * This program/include file is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as published
 * by the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program/include file is distributed in the hope that it will be
 * useful, but WITHOUT ANY WARRANTY; without even the implied warranty
 * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program (in the main directory of the Linux-NTFS
 * distribution in the file COPYING); if not, write to the Free Software
 * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */

#ifndef _LINUX_NTFS_LAYOUT_H
#define _LINUX_NTFS_LAYOUT_H

#include <linux/types.h>
#include <linux/bitops.h>
#include <linux/list.h>
#include <asm/byteorder.h>

#include "types.h"

/* The NTFS oem_id "NTFS    " */
#define magicNTFS	cpu_to_le64(0x202020205346544eULL)

/*
 * Location of bootsector on partition:
 *	The standard NTFS_BOOT_SECTOR is on sector 0 of the partition.
 *	On NT4 and above there is one backup copy of the boot sector to
 *	be found on the last sector of the partition (not normally accessible
 *	from within Windows as the bootsector contained number of sectors
 *	value is one less than the actual value!).
 *	On versions of NT 3.51 and earlier, the backup copy was located at
 *	number of sectors/2 (integer divide), i.e. in the middle of the volume.
 */

/*
 * BIOS parameter block (bpb) structure.
 */
typedef struct {
	le16 bytes_per_sector;		/* Size of a sector in bytes. */
	u8  sectors_per_cluster;	/* Size of a cluster in sectors. */
	le16 reserved_sectors;		/* zero */
	u8  fats;			/* zero */
	le16 root_entries;		/* zero */
	le16 sectors;			/* zero */
	u8  media_type;			/* 0xf8 = hard disk */
	le16 sectors_per_fat;		/* zero */
	le16 sectors_per_track;		/* irrelevant */
	le16 heads;			/* irrelevant */
	le32 hidden_sectors;		/* zero */
	le32 large_sectors;		/* zero */
} __attribute__ ((__packed__)) BIOS_PARAMETER_BLOCK;

/*
 * NTFS boot sector structure.
 */
typedef struct {
	u8  jump[3];			/* Irrelevant (jump to boot up code).*/
	le64 oem_id;			/* Magic "NTFS    ". */
	BIOS_PARAMETER_BLOCK bpb;	/* See BIOS_PARAMETER_BLOCK. */
	u8  unused[4];			/* zero, NTFS diskedit.exe states that
					   this is actually:
						__u8 physical_drive;	// 0x80
						__u8 current_head;	// zero
						__u8 extended_boot_signature;
									// 0x80
						__u8 unused;		// zero
					 */
/*0x28*/sle64 number_of_sectors;	/* Number of sectors in volume. Gives
					   maximum volume size of 2^63 sectors.
					   Assuming standard sector size of 512
					   bytes, the maximum byte size is
					   approx. 4.7x10^21 bytes. (-; */
	sle64 mft_lcn;			/* Cluster location of mft data. */
	sle64 mftmirr_lcn;		/* Cluster location of copy of mft. */
	s8  clusters_per_mft_record;	/* Mft record size in clusters. */
	u8  reserved0[3];		/* zero */
	s8  clusters_per_index_record;	/* Index block size in clusters. */
	u8  reserved1[3];		/* zero */
	le64 volume_serial_number;	/* Irrelevant (serial number). */
	le32 checksum;			/* Boot sector checksum. */
/*0x54*/u8  bootstrap[426];		/* Irrelevant (boot up code). */
	le16 end_of_sector_marker;	/* End of bootsector magic. Always is
					   0xaa55 in little endian. */
/* sizeof() = 512 (0x200) bytes */
} __attribute__ ((__packed__)) NTFS_BOOT_SECTOR;

/*
 * Magic identifiers present at the beginning of all ntfs record containing
 * records (like mft records for example).
 */
enum {
	/* Found in $MFT/$DATA. */
	magic_FILE = cpu_to_le32(0x454c4946), /* Mft entry. */
	magic_INDX = cpu_to_le32(0x58444e49), /* Index buffer. */
	magic_HOLE = cpu_to_le32(0x454c4f48), /* ? (NTFS 3.0+?) */

	/* Found in $LogFile/$DATA. */
	magic_RSTR = cpu_to_le32(0x52545352), /* Restart page. */
	magic_RCRD = cpu_to_le32(0x44524352), /* Log record page. */

	/* Found in $LogFile/$DATA.  (May be found in $MFT/$DATA, also?) */
	magic_CHKD = cpu_to_le32(0x444b4843), /* Modified by chkdsk. */

	/* Found in all ntfs record containing records. */
	magic_BAAD = cpu_to_le32(0x44414142), /* Failed multi sector
						       transfer was detected. */
	/*
	 * Found in $LogFile/$DATA when a page is full of 0xff bytes and is
	 * thus not initialized.  Page must be initialized before using it.
	 */
	magic_empty = cpu_to_le32(0xffffffff) /* Record is empty. */
};

typedef le32 NTFS_RECORD_TYPE;

/*
 * Generic magic comparison macros. Finally found a use for the ## preprocessor
 * operator! (-8
 */

static inline bool __ntfs_is_magic(le32 x, NTFS_RECORD_TYPE r)
{
	return (x == r);
}
#define ntfs_is_magic(x, m)	__ntfs_is_magic(x, magic_##m)

static inline bool __ntfs_is_magicp(le32 *p, NTFS_RECORD_TYPE r)
{
	return (*p == r);
}
#define ntfs_is_magicp(p, m)	__ntfs_is_magicp(p, magic_##m)

/*
 * Specialised magic comparison macros for the NTFS_RECORD_TYPEs defined above.
 */
#define ntfs_is_file_record(x)		( ntfs_is_magic (x, FILE) )
#define ntfs_is_file_recordp(p)		( ntfs_is_magicp(p, FILE) )
#define ntfs_is_mft_record(x)		( ntfs_is_file_record (x) )
#define ntfs_is_mft_recordp(p)		( ntfs_is_file_recordp(p) )
#define ntfs_is_indx_record(x)		( ntfs_is_magic (x, INDX) )
#define ntfs_is_indx_recordp(p)		( ntfs_is_magicp(p, INDX) )
#define ntfs_is_hole_record(x)		( ntfs_is_magic (x, HOLE) )
#define ntfs_is_hole_recordp(p)		( ntfs_is_magicp(p, HOLE) )

#define ntfs_is_rstr_record(x)		( ntfs_is_magic (x, RSTR) )
#define ntfs_is_rstr_recordp(p)		( ntfs_is_magicp(p, RSTR) )
#define ntfs_is_rcrd_record(x)		( ntfs_is_magic (x, RCRD) )
#define ntfs_is_rcrd_recordp(p)		( ntfs_is_magicp(p, RCRD) )

#define ntfs_is_chkd_record(x)		( ntfs_is_magic (x, CHKD) )
#define ntfs_is_chkd_recordp(p)		( ntfs_is_magicp(p, CHKD) )

#define ntfs_is_baad_record(x)		( ntfs_is_magic (x, BAAD) )
#define ntfs_is_baad_recordp(p)		( ntfs_is_magicp(p, BAAD) )

#define ntfs_is_empty_record(x)		( ntfs_is_magic (x, empty) )
#define ntfs_is_empty_recordp(p)	( ntfs_is_magicp(p, empty) )

/*
 * The Update Sequence Array (usa) is an array of the le16 values which belong
 * to the end of each sector protected by the update sequence record in which
 * this array is contained. Note that the first entry is the Update Sequence
 * Number (usn), a cyclic counter of how many times the protected record has
 * been written to disk. The values 0 and -1 (ie. 0xffff) are not used. All
 * last le16's of each sector have to be equal to the usn (during reading) or
 * are set to it (during writing). If they are not, an incomplete multi sector
 * transfer has occurred when the data was written.
 * The maximum size for the update sequence array is fixed to:
 *	maximum size = usa_ofs + (usa_count * 2) = 510 bytes
 * The 510 bytes comes from the fact that the last le16 in the array has to
 * (obviously) finish before the last le16 of the first 512-byte sector.
 * This formula can be used as a consistency check in that usa_ofs +
 * (usa_count * 2) has to be less than or equal to 510.
 */
typedef struct {
	NTFS_RECORD_TYPE magic;	/* A four-byte magic identifying the record
				   type and/or status. */
	le16 usa_ofs;		/* Offset to the Update Sequence Array (usa)
				   from the start of the ntfs record. */
	le16 usa_count;		/* Number of le16 sized entries in the usa
				   including the Update Sequence Number (usn),
				   thus the number of fixups is the usa_count
				   minus 1. */
} __attribute__ ((__packed__)) NTFS_RECORD;

/*
 * System files mft record numbers. All these files are always marked as used
 * in the bitmap attribute of the mft; presumably in order to avoid accidental
 * allocation for random other mft records. Also, the sequence number for each
 * of the system files is always equal to their mft record number and it is
 * never modified.
 */
typedef enum {
	FILE_MFT       = 0,	/* Master file table (mft). Data attribute
				   contains the entries and bitmap attribute
				   records which ones are in use (bit==1). */
	FILE_MFTMirr   = 1,	/* Mft mirror: copy of first four mft records
				   in data attribute. If cluster size > 4kiB,
				   copy of first N mft records, with
					N = cluster_size / mft_record_size. */
	FILE_LogFile   = 2,	/* Journalling log in data attribute. */
	FILE_Volume    = 3,	/* Volume name attribute and volume information
				   attribute (flags and ntfs version). Windows
				   refers to this file as volume DASD (Direct
				   Access Storage Device). */
	FILE_AttrDef   = 4,	/* Array of attribute definitions in data
				   attribute. */
	FILE_root      = 5,	/* Root directory. */
	FILE_Bitmap    = 6,	/* Allocation bitmap of all clusters (lcns) in
				   data attribute. */
	FILE_Boot      = 7,	/* Boot sector (always at cluster 0) in data
				   attribute. */
	FILE_BadClus   = 8,	/* Contains all bad clusters in the non-resident
				   data attribute. */
	FILE_Secure    = 9,	/* Shared security descriptors in data attribute
				   and two indexes into the descriptors.
				   Appeared in Windows 2000. Before that, this
				   file was named $Quota but was unused. */
	FILE_UpCase    = 10,	/* Uppercase equivalents of all 65536 Unicode
				   characters in data attribute. */
	FILE_Extend    = 11,	/* Directory containing other system files (eg.
				   $ObjId, $Quota, $Reparse and $UsnJrnl). This
				   is new to NTFS3.0. */
	FILE_reserved12 = 12,	/* Reserved for future use (records 12-15). */
	FILE_reserved13 = 13,
	FILE_reserved14 = 14,
	FILE_reserved15 = 15,
	FILE_first_user = 16,	/* First user file, used as test limit for
				   whether to allow opening a file or not. */
} NTFS_SYSTEM_FILES;

/*
 * These are the so far known MFT_RECORD_* flags (16-bit) which contain
 * information about the mft record in which they are present.
 */
enum {
	MFT_RECORD_IN_USE	= cpu_to_le16(0x0001),
	MFT_RECORD_IS_DIRECTORY = cpu_to_le16(0x0002),
} __attribute__ ((__packed__));

typedef le16 MFT_RECORD_FLAGS;

/*
 * mft references (aka file references or file record segment references) are
 * used whenever a structure needs to refer to a record in the mft.
 *
 * A reference consists of a 48-bit index into the mft and a 16-bit sequence
 * number used to detect stale references.
 *
 * For error reporting purposes we treat the 48-bit index as a signed quantity.
 *
 * The sequence number is a circular counter (skipping 0) describing how many
 * times the referenced mft record has been (re)used. This has to match the
 * sequence number of the mft record being referenced, otherwise the reference
 * is considered stale and removed (FIXME: only ntfsck or the driver itself?).
 *
 * If the sequence number is zero it is assumed that no sequence number
 * consistency checking should be performed.
 *
 * FIXME: Since inodes are 32-bit as of now, the driver needs to always check
 * for high_part being 0 and if not either BUG(), cause a panic() or handle
 * the situation in some other way. This shouldn't be a problem as a volume has
 * to become HUGE in order to need more than 32-bits worth of mft records.
 * Assuming the standard mft record size of 1kb only the records (never mind
 * the non-resident attributes, etc.) would require 4Tb of space on their own
 * for the first 32 bits worth of records. This is only if some strange person
 * doesn't decide to foul play and make the mft sparse which would be a really
 * horrible thing to do as it would trash our current driver implementation. )-:
 * Do I hear screams "we want 64-bit inodes!" ?!? (-;
 *
 * FIXME: The mft zone is defined as the first 12% of the volume. This space is
 * reserved so that the mft can grow contiguously and hence doesn't become
 * fragmented. Volume free space includes the empty part of the mft zone and
 * when the volume's free 88% are used up, the mft zone is shrunk by a factor
 * of 2, thus making more space available for more files/data. This process is
 * repeated everytime there is no more free space except for the mft zone until
 * there really is no more free space.
 */

/*
 * Typedef the MFT_REF as a 64-bit value for easier handling.
 * Also define two unpacking macros to get to the reference (MREF) and
 * sequence number (MSEQNO) respectively.
 * The _LE versions are to be applied on little endian MFT_REFs.
 * Note: The _LE versions will return a CPU endian formatted value!
 */
#define MFT_REF_MASK_CPU 0x0000ffffffffffffULL
#define MFT_REF_MASK_LE cpu_to_le64(MFT_REF_MASK_CPU)

typedef u64 MFT_REF;
typedef le64 leMFT_REF;

#define MK_MREF(m, s)	((MFT_REF)(((MFT_REF)(s) << 48) |		\
					((MFT_REF)(m) & MFT_REF_MASK_CPU)))
#define MK_LE_MREF(m, s) cpu_to_le64(MK_MREF(m, s))

#define MREF(x)		((unsigned long)((x) & MFT_REF_MASK_CPU))
#define MSEQNO(x)	((u16)(((x) >> 48) & 0xffff))
#define MREF_LE(x)	((unsigned long)(le64_to_cpu(x) & MFT_REF_MASK_CPU))
#define MSEQNO_LE(x)	((u16)((le64_to_cpu(x) >> 48) & 0xffff))

#define IS_ERR_MREF(x)	(((x) & 0x0000800000000000ULL) ? true : false)
#define ERR_MREF(x)	((u64)((s64)(x)))
#define MREF_ERR(x)	((int)((s64)(x)))

/*
 * The mft record header present at the beginning of every record in the mft.
 * This is followed by a sequence of variable length attribute records which
 * is terminated by an attribute of type AT_END which is a truncated attribute
 * in that it only consists of the attribute type code AT_END and none of the
 * other members of the attribute structure are present.
 */
typedef struct {
/*Ofs*/
/*  0	NTFS_RECORD; -- Unfolded here as gcc doesn't like unnamed structs. */
	NTFS_RECORD_TYPE magic;	/* Usually the magic is "FILE". */
	le16 usa_ofs;		/* See NTFS_RECORD definition above. */
	le16 usa_count;		/* See NTFS_RECORD definition above. */

/*  8*/	le64 lsn;		/* $LogFile sequence number for this record.
				   Changed every time the record is modified. */
/* 16*/	le16 sequence_number;	/* Number of times this mft record has been
				   reused. (See description for MFT_REF
				   above.) NOTE: The increment (skipping zero)
				   is done when the file is deleted. NOTE: If
				   this is zero it is left zero. */
/* 18*/	le16 link_count;	/* Number of hard links, i.e. the number of
				   directory entries referencing this record.
				   NOTE: Only used in mft base records.
				   NOTE: When deleting a directory entry we
				   check the link_count and if it is 1 we
				   delete the file. Otherwise we delete the
				   FILE_NAME_ATTR being referenced by the
				   directory entry from the mft record and
				   decrement the link_count.
				   FIXME: Careful with Win32 + DOS names! */
/* 20*/	le16 attrs_offset;	/* Byte offset to the first attribute in this
				   mft record from the start of the mft record.
				   NOTE: Must be aligned to 8-byte boundary. */
/* 22*/	MFT_RECORD_FLAGS flags;	/* Bit array of MFT_RECORD_FLAGS. When a file
				   is deleted, the MFT_RECORD_IN_USE flag is
				   set to zero. */
/* 24*/	le32 bytes_in_use;	/* Number of bytes used in this mft record.
				   NOTE: Must be aligned to 8-byte boundary. */
/* 28*/	le32 bytes_allocated;	/* Number of bytes allocated for this mft
				   record. This should be equal to the mft
				   record size. */
/* 32*/	leMFT_REF base_mft_record;/* This is zero for base mft records.
				   When it is not zero it is a mft reference
				   pointing to the base mft record to which
				   this record belongs (this is then used to
				   locate the attribute list attribute present
				   in the base record which describes this
				   extension record and hence might need
				   modification when the extension record
				   itself is modified, also locating the
				   attribute list also means finding the other
				   potential extents, belonging to the non-base
				   mft record). */
/* 40*/	le16 next_attr_instance;/* The instance number that will be assigned to
				   the next attribute added to this mft record.
				   NOTE: Incremented each time after it is used.
				   NOTE: Every time the mft record is reused
				   this number is set to zero.  NOTE: The first
				   instance number is always 0. */
/* The below fields are specific to NTFS 3.1+ (Windows XP and above): */
/* 42*/ le16 reserved;		/* Reserved/alignment. */
/* 44*/ le32 mft_record_number;	/* Number of this mft record. */
/* sizeof() = 48 bytes */
/*
 * When (re)using the mft record, we place the update sequence array at this
 * offset, i.e. before we start with the attributes.  This also makes sense,
 * otherwise we could run into problems with the update sequence array
 * containing in itself the last two bytes of a sector which would mean that
 * multi sector transfer protection wouldn't work.  As you can't protect data
 * by overwriting it since you then can't get it back...
 * When reading we obviously use the data from the ntfs record header.
 */
} __attribute__ ((__packed__)) MFT_RECORD;

/* This is the version without the NTFS 3.1+ specific fields. */
typedef struct {
/*Ofs*/
/*  0	NTFS_RECORD; -- Unfolded here as gcc doesn't like unnamed structs. */
	NTFS_RECORD_TYPE magic;	/* Usually the magic is "FILE". */
	le16 usa_ofs;		/* See NTFS_RECORD definition above. */
	le16 usa_count;		/* See NTFS_RECORD definition above. */

/*  8*/	le64 lsn;		/* $LogFile sequence number for this record.
				   Changed every time the record is modified. */
/* 16*/	le16 sequence_number;	/* Number of times this mft record has been
				   reused. (See description for MFT_REF
				   above.) NOTE: The increment (skipping zero)
				   is done when the file is deleted. NOTE: If
				   this is zero it is left zero. */
/* 18*/	le16 link_count;	/* Number of hard links, i.e. the number of
				   directory entries referencing this record.
				   NOTE: Only used in mft base records.
				   NOTE: When deleting a directory entry we
				   check the link_count and if it is 1 we
				   delete the file. Otherwise we delete the
				   FILE_NAME_ATTR being referenced by the
				   directory entry from the mft record and
				   decrement the link_count.
				   FIXME: Careful with Win32 + DOS names! */
/* 20*/	le16 attrs_offset;	/* Byte offset to the first attribute in this
				   mft record from the start of the mft record.
				   NOTE: Must be aligned to 8-byte boundary. */
/* 22*/	MFT_RECORD_FLAGS flags;	/* Bit array of MFT_RECORD_FLAGS. When a file
				   is deleted, the MFT_RECORD_IN_USE flag is
				   set to zero. */
/* 24*/	le32 bytes_in_use;	/* Number of bytes used in this mft record.
				   NOTE: Must be aligned to 8-byte boundary. */
/* 28*/	le32 bytes_allocated;	/* Number of bytes allocated for this mft
				   record. This should be equal to the mft
				   record size. */
/* 32*/	leMFT_REF base_mft_record;/* This is zero for base mft records.
				   When it is not zero it is a mft reference
				   pointing to the base mft record to which
				   this record belongs (this is then used to
				   locate the attribute list attribute present
				   in the base record which describes this
				   extension record and hence might need
				   modification when the extension record
				   itself is modified, also locating the
				   attribute list also means finding the other
				   potential extents, belonging to the non-base
				   mft record). */
/* 40*/	le16 next_attr_instance;/* The instance number that will be assigned to
				   the next attribute added to this mft record.
				   NOTE: Incremented each time after it is used.
				   NOTE: Every time the mft record is reused
				   this number is set to zero.  NOTE: The first
				   instance number is always 0. */
/* sizeof() = 42 bytes */
/*
 * When (re)using the mft record, we place the update sequence array at this
 * offset, i.e. before we start with the attributes.  This also makes sense,
 * otherwise we could run into problems with the update sequence array
 * containing in itself the last two bytes of a sector which would mean that
 * multi sector transfer protection wouldn't work.  As you can't protect data
 * by overwriting it since you then can't get it back...
 * When reading we obviously use the data from the ntfs record header.
 */
} __attribute__ ((__packed__)) MFT_RECORD_OLD;

/*
 * System defined attributes (32-bit).  Each attribute type has a corresponding
 * attribute name (Unicode string of maximum 64 character length) as described
 * by the attribute definitions present in the data attribute of the $AttrDef
 * system file.  On NTFS 3.0 volumes the names are just as the types are named
 * in the below defines exchanging AT_ for the dollar sign ($).  If that is not
 * a revealing choice of symbol I do not know what is... (-;
 */
enum {
	AT_UNUSED			= cpu_to_le32(         0),
	AT_STANDARD_INFORMATION		= cpu_to_le32(      0x10),
	AT_ATTRIBUTE_LIST		= cpu_to_le32(      0x20),
	AT_FILE_NAME			= cpu_to_le32(      0x30),
	AT_OBJECT_ID			= cpu_to_le32(      0x40),
	AT_SECURITY_DESCRIPTOR		= cpu_to_le32(      0x50),
	AT_VOLUME_NAME			= cpu_to_le32(      0x60),
	AT_VOLUME_INFORMATION		= cpu_to_le32(      0x70),
	AT_DATA				= cpu_to_le32(      0x80),
	AT_INDEX_ROOT			= cpu_to_le32(      0x90),
	AT_INDEX_ALLOCATION		= cpu_to_le32(      0xa0),
	AT_BITMAP			= cpu_to_le32(      0xb0),
	AT_REPARSE_POINT		= cpu_to_le32(      0xc0),
	AT_EA_INFORMATION		= cpu_to_le32(      0xd0),
	AT_EA				= cpu_to_le32(      0xe0),
	AT_PROPERTY_SET			= cpu_to_le32(      0xf0),
	AT_LOGGED_UTILITY_STREAM	= cpu_to_le32(     0x100),
	AT_FIRST_USER_DEFINED_ATTRIBUTE	= cpu_to_le32(    0x1000),
	AT_END				= cpu_to_le32(0xffffffff)
};

typedef le32 ATTR_TYPE;

/*
 * The collation rules for sorting views/indexes/etc (32-bit).
 *
 * COLLATION_BINARY - Collate by binary compare where the first byte is most
 *	significant.
 * COLLATION_UNICODE_STRING - Collate Unicode strings by comparing their binary
 *	Unicode values, except that when a character can be uppercased, the
 *	upper case value collates before the lower case one.
 * COLLATION_FILE_NAME - Collate file names as Unicode strings. The collation
 *	is done very much like COLLATION_UNICODE_STRING. In fact I have no idea
 *	what the difference is. Perhaps the difference is that file names
 *	would treat some special characters in an odd way (see
 *	unistr.c::ntfs_collate_names() and unistr.c::legal_ansi_char_array[]
 *	for what I mean but COLLATION_UNICODE_STRING would not give any special
 *	treatment to any characters at all, but this is speculation.
 * COLLATION_NTOFS_ULONG - Sorting is done according to ascending le32 key
 *	values. E.g. used for $SII index in FILE_Secure, which sorts by
 *	security_id (le32).
 * COLLATION_NTOFS_SID - Sorting is done according to ascending SID values.
 *	E.g. used for $O index in FILE_Extend/$Quota.
 * COLLATION_NTOFS_SECURITY_HASH - Sorting is done first by ascending hash
 *	values and second by ascending security_id values. E.g. used for $SDH
 *	index in FILE_Secure.
 * COLLATION_NTOFS_ULONGS - Sorting is done according to a sequence of ascending
 *	le32 key values. E.g. used for $O index in FILE_Extend/$ObjId, which
 *	sorts by object_id (16-byte), by splitting up the object_id in four
 *	le32 values and using them as individual keys. E.g. take the following
 *	two security_ids, stored as follows on disk:
 *		1st: a1 61 65 b7 65 7b d4 11 9e 3d 00 e0 81 10 42 59
 *		2nd: 38 14 37 d2 d2 f3 d4 11 a5 21 c8 6b 79 b1 97 45
 *	To compare them, they are split into four le32 values each, like so:
 *		1st: 0xb76561a1 0x11d47b65 0xe0003d9e 0x59421081
 *		2nd: 0xd2371438 0x11d4f3d2 0x6bc821a5 0x4597b179
 *	Now, it is apparent why the 2nd object_id collates after the 1st: the
 *	first le32 value of the 1st object_id is less than the first le32 of
 *	the 2nd object_id. If the first le32 values of both object_ids were
 *	equal then the second le32 values would be compared, etc.
 */
enum {
	COLLATION_BINARY		= cpu_to_le32(0x00),
	COLLATION_FILE_NAME		= cpu_to_le32(0x01),
	COLLATION_UNICODE_STRING	= cpu_to_le32(0x02),
	COLLATION_NTOFS_ULONG		= cpu_to_le32(0x10),
	COLLATION_NTOFS_SID		= cpu_to_le32(0x11),
	COLLATION_NTOFS_SECURITY_HASH	= cpu_to_le32(0x12),
	COLLATION_NTOFS_ULONGS		= cpu_to_le32(0x13),
};

typedef le32 COLLATION_RULE;

/*
 * The flags (32-bit) describing attribute properties in the attribute
 * definition structure.  FIXME: This information is based on Regis's
 * information and, according to him, it is not certain and probably
 * incomplete.  The INDEXABLE flag is fairly certainly correct as only the file
 * name attribute has this flag set and this is the only attribute indexed in
 * NT4.
 */
enum {
	ATTR_DEF_INDEXABLE	= cpu_to_le32(0x02), /* Attribute can be
					indexed. */
	ATTR_DEF_MULTIPLE	= cpu_to_le32(0x04), /* Attribute type
					can be present multiple times in the
					mft records of an inode. */
	ATTR_DEF_NOT_ZERO	= cpu_to_le32(0x08), /* Attribute value
					must contain at least one non-zero
					byte. */
	ATTR_DEF_INDEXED_UNIQUE	= cpu_to_le32(0x10), /* Attribute must be
					indexed and the attribute value must be
					unique for the attribute type in all of
					the mft records of an inode. */
	ATTR_DEF_NAMED_UNIQUE	= cpu_to_le32(0x20), /* Attribute must be
					named and the name must be unique for
					the attribute type in all of the mft
					records of an inode. */
	ATTR_DEF_RESIDENT	= cpu_to_le32(0x40), /* Attribute must be
					resident. */
	ATTR_DEF_ALWAYS_LOG	= cpu_to_le32(0x80), /* Always log
					modifications to this attribute,
					regardless of whether it is resident or
					non-resident.  Without this, only log
					modifications if the attribute is
					resident. */
};

typedef le32 ATTR_DEF_FLAGS;

/*
 * The data attribute of FILE_AttrDef contains a sequence of attribute
 * definitions for the NTFS volume. With this, it is supposed to be safe for an
 * older NTFS driver to mount a volume containing a newer NTFS version without
 * damaging it (that's the theory. In practice it's: not damaging it too much).
 * Entries are sorted by attribute type. The flags describe whether the
 * attribute can be resident/non-resident and possibly other things, but the
 * actual bits are unknown.
 */
typedef struct {
/*hex ofs*/
/*  0*/	ntfschar name[0x40];		/* Unicode name of the attribute. Zero
					   terminated. */
/* 80*/	ATTR_TYPE type;			/* Type of the attribute. */
/* 84*/	le32 display_rule;		/* Default display rule.
					   FIXME: What does it mean? (AIA) */
/* 88*/ COLLATION_RULE collation_rule;	/* Default collation rule. */
/* 8c*/	ATTR_DEF_FLAGS flags;		/* Flags describing the attribute. */
/* 90*/	sle64 min_size;			/* Optional minimum attribute size. */
/* 98*/	sle64 max_size;			/* Maximum size of attribute. */
/* sizeof() = 0xa0 or 160 bytes */
} __attribute__ ((__packed__)) ATTR_DEF;

/*
 * Attribute flags (16-bit).
 */
enum {
	ATTR_IS_COMPRESSED    = cpu_to_le16(0x0001),
	ATTR_COMPRESSION_MASK = cpu_to_le16(0x00ff), /* Compression method
							      mask.  Also, first
							      illegal value. */
	ATTR_IS_ENCRYPTED     = cpu_to_le16(0x4000),
	ATTR_IS_SPARSE	      = cpu_to_le16(0x8000),
} __attribute__ ((__packed__));

typedef le16 ATTR_FLAGS;

/*
 * Attribute compression.
 *
 * Only the data attribute is ever compressed in the current ntfs driver in
 * Windows. Further, compression is only applied when the data attribute is
 * non-resident. Finally, to use compression, the maximum allowed cluster size
 * on a volume is 4kib.
 *
 * The compression method is based on independently compressing blocks of X
 * clusters, where X is determined from the compression_unit value found in the
 * non-resident attribute record header (more precisely: X = 2^compression_unit
 * clusters). On Windows NT/2k, X always is 16 clusters (compression_unit = 4).
 *
 * There are three different cases of how a compression block of X clusters
 * can be stored:
 *
 *   1) The data in the block is all zero (a sparse block):
 *	  This is stored as a sparse block in the runlist, i.e. the runlist
 *	  entry has length = X and lcn = -1. The mapping pairs array actually
 *	  uses a delta_lcn value length of 0, i.e. delta_lcn is not present at
 *	  all, which is then interpreted by the driver as lcn = -1.
 *	  NOTE: Even uncompressed files can be sparse on NTFS 3.0 volumes, then
 *	  the same principles apply as above, except that the length is not
 *	  restricted to being any particular value.
 *
 *   2) The data in the block is not compressed:
 *	  This happens when compression doesn't reduce the size of the block
 *	  in clusters. I.e. if compression has a small effect so that the
 *	  compressed data still occupies X clusters, then the uncompressed data
 *	  is stored in the block.
 *	  This case is recognised by the fact that the runlist entry has
 *	  length = X and lcn >= 0. The mapping pairs array stores this as
 *	  normal with a run length of X and some specific delta_lcn, i.e.
 *	  delta_lcn has to be present.
 *
 *   3) The data in the block is compressed:
 *	  The common case. This case is recognised by the fact that the run
 *	  list entry has length L < X and lcn >= 0. The mapping pairs array
 *	  stores this as normal with a run length of X and some specific
 *	  delta_lcn, i.e. delta_lcn has to be present. This runlist entry is
 *	  immediately followed by a sparse entry with length = X - L and
 *	  lcn = -1. The latter entry is to make up the vcn counting to the
 *	  full compression block size X.
 *
 * In fact, life is more complicated because adjacent entries of the same type
 * can be coalesced. This means that one has to keep track of the number of
 * clusters handled and work on a basis of X clusters at a time being one
 * block. An example: if length L > X this means that this particular runlist
 * entry contains a block of length X and part of one or more blocks of length
 * L - X. Another example: if length L < X, this does not necessarily mean that
 * the block is compressed as it might be that the lcn changes inside the block
 * and hence the following runlist entry describes the continuation of the
 * potentially compressed block. The block would be compressed if the
 * following runlist entry describes at least X - L sparse clusters, thus
 * making up the compression block length as described in point 3 above. (Of
 * course, there can be several runlist entries with small lengths so that the
 * sparse entry does not follow the first data containing entry with
 * length < X.)
 *
 * NOTE: At the end of the compressed attribute value, there most likely is not
 * just the right amount of data to make up a compression block, thus this data
 * is not even attempted to be compressed. It is just stored as is, unless
 * the number of clusters it occupies is reduced when compressed in which case
 * it is stored as a compressed compression block, complete with sparse
 * clusters at the end.
 */

/*
 * Flags of resident attributes (8-bit).
 */
enum {
	RESIDENT_ATTR_IS_INDEXED = 0x01, /* Attribute is referenced in an index
					    (has implications for deleting and
					    modifying the attribute). */
} __attribute__ ((__packed__));

typedef u8 RESIDENT_ATTR_FLAGS;

/*
 * Attribute record header. Always aligned to 8-byte boundary.
 */
typedef struct {
/*Ofs*/
/*  0*/	ATTR_TYPE type;		/* The (32-bit) type of the attribute. */
/*  4*/	le32 length;		/* Byte size of the resident part of the
				   attribute (aligned to 8-byte boundary).
				   Used to get to the next attribute. */
/*  8*/	u8 non_resident;	/* If 0, attribute is resident.
				   If 1, attribute is non-resident. */
/*  9*/	u8 name_length;		/* Unicode character size of name of attribute.
				   0 if unnamed. */
/* 10*/	le16 name_offset;	/* If name_length != 0, the byte offset to the
				   beginning of the name from the attribute
				   record. Note that the name is stored as a
				   Unicode string. When creating, place offset
				   just at the end of the record header. Then,
				   follow with attribute value or mapping pairs
				   array, resident and non-resident attributes
				   respectively, aligning to an 8-byte
				   boundary. */
/* 12*/	ATTR_FLAGS flags;	/* Flags describing the attribute. */
/* 14*/	le16 instance;		/* The instance of this attribute record. This
				   number is unique within this mft record (see
				   MFT_RECORD/next_attribute_instance notes in
				   in mft.h for more details). */
/* 16*/	union {
		/* Resident attributes. */
		struct {
/* 16 */		le32 value_length;/* Byte size of attribute value. */
/* 20 */		le16 value_offset;/* Byte offset of the attribute
					     value from the start of the
					     attribute record. When creating,
					     align to 8-byte boundary if we
					     have a name present as this might
					     not have a length of a multiple
					     of 8-bytes. */
/* 22 */		RESIDENT_ATTR_FLAGS flags; /* See above. */
/* 23 */		s8 reserved;	  /* Reserved/alignment to 8-byte
					     boundary. */
		} __attribute__ ((__packed__)) resident;
		/* Non-resident attributes. */
		struct {
/* 16*/			leVCN lowest_vcn;/* Lowest valid virtual cluster number
				for this portion of the attribute value or
				0 if this is the only extent (usually the
				case). - Only when an attribute list is used
				does lowest_vcn != 0 ever occur. */
/* 24*/			leVCN highest_vcn;/* Highest valid vcn of this extent of
				the attribute value. - Usually there is only one
				portion, so this usually equals the attribute
				value size in clusters minus 1. Can be -1 for
				zero length files. Can be 0 for "single extent"
				attributes. */
/* 32*/			le16 mapping_pairs_offset; /* Byte offset from the
				beginning of the structure to the mapping pairs
				array which contains the mappings between the
				vcns and the logical cluster numbers (lcns).
				When creating, place this at the end of this
				record header aligned to 8-byte boundary. */
/* 34*/			u8 compression_unit; /* The compression unit expressed
				as the log to the base 2 of the number of
				clusters in a compression unit.  0 means not
				compressed.  (This effectively limits the
				compression unit size to be a power of two
				clusters.)  WinNT4 only uses a value of 4.
				Sparse files have this set to 0 on XPSP2. */
/* 35*/			u8 reserved[5];		/* Align to 8-byte boundary. */
/* The sizes below are only used when lowest_vcn is zero, as otherwise it would
   be difficult to keep them up-to-date.*/
/* 40*/			sle64 allocated_size;	/* Byte size of disk space
				allocated to hold the attribute value. Always
				is a multiple of the cluster size. When a file
				is compressed, this field is a multiple of the
				compression block size (2^compression_unit) and
				it represents the logically allocated space
				rather than the actual on disk usage. For this
				use the compressed_size (see below). */
/* 48*/			sle64 data_size;	/* Byte size of the attribute
				value. Can be larger than allocated_size if
				attribute value is compressed or sparse. */
/* 56*/			sle64 initialized_size;	/* Byte size of initialized
				portion of the attribute value. Usually equals
				data_size. */
/* sizeof(uncompressed attr) = 64*/
/* 64*/			sle64 compressed_size;	/* Byte size of the attribute
				value after compression.  Only present when
				compressed or sparse.  Always is a multiple of
				the cluster size.  Represents the actual amount
				of disk space being used on the disk. */
/* sizeof(compressed attr) = 72*/
		} __attribute__ ((__packed__)) non_resident;
	} __attribute__ ((__packed__)) data;
} __attribute__ ((__packed__)) ATTR_RECORD;

typedef ATTR_RECORD ATTR_REC;

/*
 * File attribute flags (32-bit) appearing in the file_attributes fields of the
 * STANDARD_INFORMATION attribute of MFT_RECORDs and the FILENAME_ATTR
 * attributes of MFT_RECORDs and directory index entries.
 *
 * All of the below flags appear in the directory index entries but only some
 * appear in the STANDARD_INFORMATION attribute whilst only some others appear
 * in the FILENAME_ATTR attribute of MFT_RECORDs.  Unless otherwise stated the
 * flags appear in all of the above.
 */
enum {
	FILE_ATTR_READONLY		= cpu_to_le32(0x00000001),
	FILE_ATTR_HIDDEN		= cpu_to_le32(0x00000002),
	FILE_ATTR_SYSTEM		= cpu_to_le32(0x00000004),
	/* Old DOS volid. Unused in NT.	= cpu_to_le32(0x00000008), */

	FILE_ATTR_DIRECTORY		= cpu_to_le32(0x00000010),
	/* Note, FILE_ATTR_DIRECTORY is not considered valid in NT.  It is
	   reserved for the DOS SUBDIRECTORY flag. */
	FILE_ATTR_ARCHIVE		= cpu_to_le32(0x00000020),
	FILE_ATTR_DEVICE		= cpu_to_le32(0x00000040),
	FILE_ATTR_NORMAL		= cpu_to_le32(0x00000080),

	FILE_ATTR_TEMPORARY		= cpu_to_le32(0x00000100),
	FILE_ATTR_SPARSE_FILE		= cpu_to_le32(0x00000200),
	FILE_ATTR_REPARSE_POINT		= cpu_to_le32(0x00000400),
	FILE_ATTR_COMPRESSED		= cpu_to_le32(0x00000800),

	FILE_ATTR_OFFLINE		= cpu_to_le32(0x00001000),
	FILE_ATTR_NOT_CONTENT_INDEXED	= cpu_to_le32(0x00002000),
	FILE_ATTR_ENCRYPTED		= cpu_to_le32(0x00004000),

	FILE_ATTR_VALID_FLAGS		= cpu_to_le32(0x00007fb7),
	/* Note, FILE_ATTR_VALID_FLAGS masks out the old DOS VolId and the
	   FILE_ATTR_DEVICE and preserves everything else.  This mask is used
	   to obtain all flags that are valid for reading. */
	FILE_ATTR_VALID_SET_FLAGS	= cpu_to_le32(0x000031a7),
	/* Note, FILE_ATTR_VALID_SET_FLAGS masks out the old DOS VolId, the
	   F_A_DEVICE, F_A_DIRECTORY, F_A_SPARSE_FILE, F_A_REPARSE_POINT,
	   F_A_COMPRESSED, and F_A_ENCRYPTED and preserves the rest.  This mask
	   is used to obtain all flags that are valid for setting. */
	/*
	 * The flag FILE_ATTR_DUP_FILENAME_INDEX_PRESENT is present in all
	 * FILENAME_ATTR attributes but not in the STANDARD_INFORMATION
	 * attribute of an mft record.
	 */
	FILE_ATTR_DUP_FILE_NAME_INDEX_PRESENT	= cpu_to_le32(0x10000000),
	/* Note, this is a copy of the corresponding bit from the mft record,
	   telling us whether this is a directory or not, i.e. whether it has
	   an index root attribute or not. */
	FILE_ATTR_DUP_VIEW_INDEX_PRESENT	= cpu_to_le32(0x20000000),
	/* Note, this is a copy of the corresponding bit from the mft record,
	   telling us whether this file has a view index present (eg. object id
	   index, quota index, one of the security indexes or the encrypting
	   filesystem related indexes). */
};

typedef le32 FILE_ATTR_FLAGS;

/*
 * NOTE on times in NTFS: All times are in MS standard time format, i.e. they
 * are the number of 100-nanosecond intervals since 1st January 1601, 00:00:00
 * universal coordinated time (UTC). (In Linux time starts 1st January 1970,
 * 00:00:00 UTC and is stored as the number of 1-second intervals since then.)
 */

/*
 * Attribute: Standard information (0x10).
 *
 * NOTE: Always resident.
 * NOTE: Present in all base file records on a volume.
 * NOTE: There is conflicting information about the meaning of each of the time
 *	 fields but the meaning as defined below has been verified to be
 *	 correct by practical experimentation on Windows NT4 SP6a and is hence
 *	 assumed to be the one and only correct interpretation.
 */
typedef struct {
/*Ofs*/
/*  0*/	sle64 creation_time;		/* Time file was created. Updated when
					   a filename is changed(?). */
/*  8*/	sle64 last_data_change_time;	/* Time the data attribute was last
					   modified. */
/* 16*/	sle64 last_mft_change_time;	/* Time this mft record was last
					   modified. */
/* 24*/	sle64 last_access_time;		/* Approximate time when the file was
					   last accessed (obviously this is not
					   updated on read-only volumes). In
					   Windows this is only updated when
					   accessed if some time delta has
					   passed since the last update. Also,
					   last access time updates can be
					   disabled altogether for speed. */
/* 32*/	FILE_ATTR_FLAGS file_attributes; /* Flags describing the file. */
/* 36*/	union {
	/* NTFS 1.2 */
		struct {
		/* 36*/	u8 reserved12[12];	/* Reserved/alignment to 8-byte
						   boundary. */
		} __attribute__ ((__packed__)) v1;
	/* sizeof() = 48 bytes */
	/* NTFS 3.x */
		struct {
/*
 * If a volume has been upgraded from a previous NTFS version, then these
 * fields are present only if the file has been accessed since the upgrade.
 * Recognize the difference by comparing the length of the resident attribute
 * value. If it is 48, then the following fields are missing. If it is 72 then
 * the fields are present. Maybe just check like this:
 *	if (resident.ValueLength < sizeof(STANDARD_INFORMATION)) {
 *		Assume NTFS 1.2- format.
 *		If (volume version is 3.x)
 *			Upgrade attribute to NTFS 3.x format.
 *		else
 *			Use NTFS 1.2- format for access.
 *	} else
 *		Use NTFS 3.x format for access.
 * Only problem is that it might be legal to set the length of the value to
 * arbitrarily large values thus spoiling this check. - But chkdsk probably
 * views that as a corruption, assuming that it behaves like this for all
 * attributes.
 */
		/* 36*/	le32 maximum_versions;	/* Maximum allowed versions for
				file. Zero if version numbering is disabled. */
		/* 40*/	le32 version_number;	/* This file's version (if any).
				Set to zero if maximum_versions is zero. */
		/* 44*/	le32 class_id;		/* Class id from bidirectional
				class id index (?). */
		/* 48*/	le32 owner_id;		/* Owner_id of the user owning
				the file. Translate via $Q index in FILE_Extend
				/$Quota to the quota control entry for the user
				owning the file. Zero if quotas are disabled. */
		/* 52*/	le32 security_id;	/* Security_id for the file.
				Translate via $SII index and $SDS data stream
				in FILE_Secure to the security descriptor. */
		/* 56*/	le64 quota_charged;	/* Byte size of the charge to
				the quota for all streams of the file. Note: Is
				zero if quotas are disabled. */
		/* 64*/	leUSN usn;		/* Last update sequence number
				of the file.  This is a direct index into the
				transaction log file ($UsnJrnl).  It is zero if
				the usn journal is disabled or this file has
				not been subject to logging yet.  See usnjrnl.h
				for details. */
		} __attribute__ ((__packed__)) v3;
	/* sizeof() = 72 bytes (NTFS 3.x) */
	} __attribute__ ((__packed__)) ver;
} __attribute__ ((__packed__)) STANDARD_INFORMATION;

/*
 * Attribute: Attribute list (0x20).
 *
 * - Can be either resident or non-resident.
 * - Value consists of a sequence of variable length, 8-byte aligned,
 * ATTR_LIST_ENTRY records.
 * - The list is not terminated by anything at all! The only way to know when
 * the end is reached is to keep track of the current offset and compare it to
 * the attribute value size.
 * - The attribute list attribute contains one entry for each attribute of
 * the file in which the list is located, except for the list attribute
 * itself. The list is sorted: first by attribute type, second by attribute
 * name (if present), third by instance number. The extents of one
 * non-resident attribute (if present) immediately follow after the initial
 * extent. They are ordered by lowest_vcn and have their instace set to zero.
 * It is not allowed to have two attributes with all sorting keys equal.
 * - Further restrictions:
 *	- If not resident, the vcn to lcn mapping array has to fit inside the
 *	  base mft record.
 *	- The attribute list attribute value has a maximum size of 256kb. This
 *	  is imposed by the Windows cache manager.
 * - Attribute lists are only used when the attributes of mft record do not
 * fit inside the mft record despite all attributes (that can be made
 * non-resident) having been made non-resident. This can happen e.g. when:
 *	- File has a large number of hard links (lots of file name
 *	  attributes present).
 *	- The mapping pairs array of some non-resident attribute becomes so
 *	  large due to fragmentation that it overflows the mft record.
 *	- The security descriptor is very complex (not applicable to
 *	  NTFS 3.0 volumes).
 *	- There are many named streams.
 */
typedef struct {
/*Ofs*/
/*  0*/	ATTR_TYPE type;		/* Type of referenced attribute. */
/*  4*/	le16 length;		/* Byte size of this entry (8-byte aligned). */
/*  6*/	u8 name_length;		/* Size in Unicode chars of the name of the
				   attribute or 0 if unnamed. */
/*  7*/	u8 name_offset;		/* Byte offset to beginning of attribute name
				   (always set this to where the name would
				   start even if unnamed). */
/*  8*/	leVCN lowest_vcn;	/* Lowest virtual cluster number of this portion
				   of the attribute value. This is usually 0. It
				   is non-zero for the case where one attribute
				   does not fit into one mft record and thus
				   several mft records are allocated to hold
				   this attribute. In the latter case, each mft
				   record holds one extent of the attribute and
				   there is one attribute list entry for each
				   extent. NOTE: This is DEFINITELY a signed
				   value! The windows driver uses cmp, followed
				   by jg when comparing this, thus it treats it
				   as signed. */
/* 16*/	leMFT_REF mft_reference;/* The reference of the mft record holding
				   the ATTR_RECORD for this portion of the
				   attribute value. */
/* 24*/	le16 instance;		/* If lowest_vcn = 0, the instance of the
				   attribute being referenced; otherwise 0. */
/* 26*/	ntfschar name[0];	/* Use when creating only. When reading use
				   name_offset to determine the location of the
				   name. */
/* sizeof() = 26 + (attribute_name_length * 2) bytes */
} __attribute__ ((__packed__)) ATTR_LIST_ENTRY;

/*
 * The maximum allowed length for a file name.
 */
#define MAXIMUM_FILE_NAME_LENGTH	255

/*
 * Possible namespaces for filenames in ntfs (8-bit).
 */
enum {
	FILE_NAME_POSIX		= 0x00,
	/* This is the largest namespace. It is case sensitive and allows all
	   Unicode characters except for: '\0' and '/'.  Beware that in
	   WinNT/2k/2003 by default files which eg have the same name except
	   for their case will not be distinguished by the standard utilities
	   and thus a "del filename" will delete both "filename" and "fileName"
	   without warning.  However if for example Services For Unix (SFU) are
	   installed and the case sensitive option was enabled at installation
	   time, then you can create/access/delete such files.
	   Note that even SFU places restrictions on the filenames beyond the
	   '\0' and '/' and in particular the following set of characters is
	   not allowed: '"', '/', '<', '>', '\'.  All other characters,
	   including the ones no allowed in WIN32 namespace are allowed.
	   Tested with SFU 3.5 (this is now free) running on Windows XP. */
	FILE_NAME_WIN32		= 0x01,
	/* The standard WinNT/2k NTFS long filenames. Case insensitive.  All
	   Unicode chars except: '\0', '"', '*', '/', ':', '<', '>', '?', '\',
	   and '|'.  Further, names cannot end with a '.' or a space. */
	FILE_NAME_DOS		= 0x02,
	/* The standard DOS filenames (8.3 format). Uppercase only.  All 8-bit
	   characters greater space, except: '"', '*', '+', ',', '/', ':', ';',
	   '<', '=', '>', '?', and '\'. */
	FILE_NAME_WIN32_AND_DOS	= 0x03,
	/* 3 means that both the Win32 and the DOS filenames are identical and
	   hence have been saved in this single filename record. */
} __attribute__ ((__packed__));

typedef u8 FILE_NAME_TYPE_FLAGS;

/*
 * Attribute: Filename (0x30).
 *
 * NOTE: Always resident.
 * NOTE: All fields, except the parent_directory, are only updated when the
 *	 filename is changed. Until then, they just become out of sync with
 *	 reality and the more up to date values are present in the standard
 *	 information attribute.
 * NOTE: There is conflicting information about the meaning of each of the time
 *	 fields but the meaning as defined below has been verified to be
 *	 correct by practical experimentation on Windows NT4 SP6a and is hence
 *	 assumed to be the one and only correct interpretation.
 */
typedef struct {
/*hex ofs*/
/*  0*/	leMFT_REF parent_directory;	/* Directory this filename is
					   referenced from. */
/*  8*/	sle64 creation_time;		/* Time file was created. */
/* 10*/	sle64 last_data_change_time;	/* Time the data attribute was last
					   modified. */
/* 18*/	sle64 last_mft_change_time;	/* Time this mft record was last
					   modified. */
/* 20*/	sle64 last_access_time;		/* Time this mft record was last
					   accessed. */
/* 28*/	sle64 allocated_size;		/* Byte size of on-disk allocated space
					   for the unnamed data attribute.  So
					   for normal $DATA, this is the
					   allocated_size from the unnamed
					   $DATA attribute and for compressed
					   and/or sparse $DATA, this is the
					   compressed_size from the unnamed
					   $DATA attribute.  For a directory or
					   other inode without an unnamed $DATA
					   attribute, this is always 0.  NOTE:
					   This is a multiple of the cluster
					   size. */
/* 30*/	sle64 data_size;		/* Byte size of actual data in unnamed
					   data attribute.  For a directory or
					   other inode without an unnamed $DATA
					   attribute, this is always 0. */
/* 38*/	FILE_ATTR_FLAGS file_attributes;	/* Flags describing the file. */
/* 3c*/	union {
	/* 3c*/	struct {
		/* 3c*/	le16 packed_ea_size;	/* Size of the buffer needed to
						   pack the extended attributes
						   (EAs), if such are present.*/
		/* 3e*/	le16 reserved;		/* Reserved for alignment. */
		} __attribute__ ((__packed__)) ea;
	/* 3c*/	struct {
		/* 3c*/	le32 reparse_point_tag;	/* Type of reparse point,
						   present only in reparse
						   points and only if there are
						   no EAs. */
		} __attribute__ ((__packed__)) rp;
	} __attribute__ ((__packed__)) type;
/* 40*/	u8 file_name_length;			/* Length of file name in
						   (Unicode) characters. */
/* 41*/	FILE_NAME_TYPE_FLAGS file_name_type;	/* Namespace of the file name.*/
/* 42*/	ntfschar file_name[0];			/* File name in Unicode. */
} __attribute__ ((__packed__)) FILE_NAME_ATTR;

/*
 * GUID structures store globally unique identifiers (GUID). A GUID is a
 * 128-bit value consisting of one group of eight hexadecimal digits, followed
 * by three groups of four hexadecimal digits each, followed by one group of
 * twelve hexadecimal digits. GUIDs are Microsoft's implementation of the
 * distributed computing environment (DCE) universally unique identifier (UUID).
 * Example of a GUID:
 *	1F010768-5A73-BC91-0010A52216A7
 */
typedef struct {
	le32 data1;	/* The first eight hexadecimal digits of the GUID. */
	le16 data2;	/* The first group of four hexadecimal digits. */
	le16 data3;	/* The second group of four hexadecimal digits. */
	u8 data4[8];	/* The first two bytes are the third group of four
			   hexadecimal digits. The remaining six bytes are the
			   final 12 hexadecimal digits. */
} __attribute__ ((__packed__)) GUID;

/*
 * FILE_Extend/$ObjId contains an index named $O. This index contains all
 * object_ids present on the volume as the index keys and the corresponding
 * mft_record numbers as the index entry data parts. The data part (defined
 * below) also contains three other object_ids:
 *	birth_volume_id - object_id of FILE_Volume on which the file was first
 *			  created. Optional (i.e. can be zero).
 *	birth_object_id - object_id of file when it was first created. Usually
 *			  equals the object_id. Optional (i.e. can be zero).
 *	domain_id	- Reserved (always zero).
 */
typedef struct {
	leMFT_REF mft_reference;/* Mft record containing the object_id in
				   the index entry key. */
	union {
		struct {
			GUID birth_volume_id;
			GUID birth_object_id;
			GUID domain_id;
		} __attribute__ ((__packed__)) origin;
		u8 extended_info[48];
	} __attribute__ ((__packed__)) opt;
} __attribute__ ((__packed__)) OBJ_ID_INDEX_DATA;

/*
 * Attribute: Object id (NTFS 3.0+) (0x40).
 *
 * NOTE: Always resident.
 */
typedef struct {
	GUID object_id;				/* Unique id assigned to the
						   file.*/
	/* The following fields are optional. The attribute value size is 16
	   bytes, i.e. sizeof(GUID), if these are not present at all. Note,
	   the entries can be present but one or more (or all) can be zero
	   meaning that that particular value(s) is(are) not defined. */
	union {
		struct {
			GUID birth_volume_id;	/* Unique id of volume on which
						   the file was first created.*/
			GUID birth_object_id;	/* Unique id of file when it was
						   first created. */
			GUID domain_id;		/* Reserved, zero. */
		} __attribute__ ((__packed__)) origin;
		u8 extended_info[48];
	} __attribute__ ((__packed__)) opt;
} __attribute__ ((__packed__)) OBJECT_ID_ATTR;

/*
 * The pre-defined IDENTIFIER_AUTHORITIES used as SID_IDENTIFIER_AUTHORITY in
 * the SID structure (see below).
 */
//typedef enum {					/* SID string prefix. */
//	SECURITY_NULL_SID_AUTHORITY	= {0, 0, 0, 0, 0, 0},	/* S-1-0 */
//	SECURITY_WORLD_SID_AUTHORITY	= {0, 0, 0, 0, 0, 1},	/* S-1-1 */
//	SECURITY_LOCAL_SID_AUTHORITY	= {0, 0, 0, 0, 0, 2},	/* S-1-2 */
//	SECURITY_CREATOR_SID_AUTHORITY	= {0, 0, 0, 0, 0, 3},	/* S-1-3 */
//	SECURITY_NON_UNIQUE_AUTHORITY	= {0, 0, 0, 0, 0, 4},	/* S-1-4 */
//	SECURITY_NT_SID_AUTHORITY	= {0, 0, 0, 0, 0, 5},	/* S-1-5 */
//} IDENTIFIER_AUTHORITIES;

/*
 * These relative identifiers (RIDs) are used with the above identifier
 * authorities to make up universal well-known SIDs.
 *
 * Note: The relative identifier (RID) refers to the portion of a SID, which
 * identifies a user or group in relation to the authority that issued the SID.
 * For example, the universal well-known SID Creator Owner ID (S-1-3-0) is
 * made up of the identifier authority SECURITY_CREATOR_SID_AUTHORITY (3) and
 * the relative identifier SECURITY_CREATOR_OWNER_RID (0).
 */
typedef enum {					/* Identifier authority. */
	SECURITY_NULL_RID		  = 0,	/* S-1-0 */
	SECURITY_WORLD_RID		  = 0,	/* S-1-1 */
	SECURITY_LOCAL_RID		  = 0,	/* S-1-2 */

	SECURITY_CREATOR_OWNER_RID	  = 0,	/* S-1-3 */
	SECURITY_CREATOR_GROUP_RID	  = 1,	/* S-1-3 */

	SECURITY_CREATOR_OWNER_SERVER_RID = 2,	/* S-1-3 */
	SECURITY_CREATOR_GROUP_SERVER_RID = 3,	/* S-1-3 */

	SECURITY_DIALUP_RID		  = 1,
	SECURITY_NETWORK_RID		  = 2,
	SECURITY_BATCH_RID		  = 3,
	SECURITY_INTERACTIVE_RID	  = 4,
	SECURITY_SERVICE_RID		  = 6,
	SECURITY_ANONYMOUS_LOGON_RID	  = 7,
	SECURITY_PROXY_RID		  = 8,
	SECURITY_ENTERPRISE_CONTROLLERS_RID=9,
	SECURITY_SERVER_LOGON_RID	  = 9,
	SECURITY_PRINCIPAL_SELF_RID	  = 0xa,