aboutsummaryrefslogblamecommitdiffstats
path: root/include/net/red.h
blob: 2ed4358e3295c2f03595efd9bc9a91c86fa2b496 (plain) (tree)




































































































































































































































































































































                                                                                
#ifndef __NET_SCHED_RED_H
#define __NET_SCHED_RED_H

#include <linux/config.h>
#include <linux/types.h>
#include <net/pkt_sched.h>
#include <net/inet_ecn.h>
#include <net/dsfield.h>

/*	Random Early Detection (RED) algorithm.
	=======================================

	Source: Sally Floyd and Van Jacobson, "Random Early Detection Gateways
	for Congestion Avoidance", 1993, IEEE/ACM Transactions on Networking.

	This file codes a "divisionless" version of RED algorithm
	as written down in Fig.17 of the paper.

	Short description.
	------------------

	When a new packet arrives we calculate the average queue length:

	avg = (1-W)*avg + W*current_queue_len,

	W is the filter time constant (chosen as 2^(-Wlog)), it controls
	the inertia of the algorithm. To allow larger bursts, W should be
	decreased.

	if (avg > th_max) -> packet marked (dropped).
	if (avg < th_min) -> packet passes.
	if (th_min < avg < th_max) we calculate probability:

	Pb = max_P * (avg - th_min)/(th_max-th_min)

	and mark (drop) packet with this probability.
	Pb changes from 0 (at avg==th_min) to max_P (avg==th_max).
	max_P should be small (not 1), usually 0.01..0.02 is good value.

	max_P is chosen as a number, so that max_P/(th_max-th_min)
	is a negative power of two in order arithmetics to contain
	only shifts.


	Parameters, settable by user:
	-----------------------------

	qth_min		- bytes (should be < qth_max/2)
	qth_max		- bytes (should be at least 2*qth_min and less limit)
	Wlog	       	- bits (<32) log(1/W).
	Plog	       	- bits (<32)

	Plog is related to max_P by formula:

	max_P = (qth_max-qth_min)/2^Plog;

	F.e. if qth_max=128K and qth_min=32K, then Plog=22
	corresponds to max_P=0.02

	Scell_log
	Stab

	Lookup table for log((1-W)^(t/t_ave).


	NOTES:

	Upper bound on W.
	-----------------

	If you want to allow bursts of L packets of size S,
	you should choose W:

	L + 1 - th_min/S < (1-(1-W)^L)/W

	th_min/S = 32         th_min/S = 4

	log(W)	L
	-1	33
	-2	35
	-3	39
	-4	46
	-5	57
	-6	75
	-7	101
	-8	135
	-9	190
	etc.
 */

#define RED_STAB_SIZE	256
#define RED_STAB_MASK	(RED_STAB_SIZE - 1)

struct red_stats
{
	u32		prob_drop;	/* Early probability drops */
	u32		prob_mark;	/* Early probability marks */
	u32		forced_drop;	/* Forced drops, qavg > max_thresh */
	u32		forced_mark;	/* Forced marks, qavg > max_thresh */
	u32		pdrop;          /* Drops due to queue limits */
	u32		other;          /* Drops due to drop() calls */
	u32		backlog;
};

struct red_parms
{
	/* Parameters */
	u32		qth_min;	/* Min avg length threshold: A scaled */
	u32		qth_max;	/* Max avg length threshold: A scaled */
	u32		Scell_max;
	u32		Rmask;		/* Cached random mask, see red_rmask */
	u8		Scell_log;
	u8		Wlog;		/* log(W)		*/
	u8		Plog;		/* random number bits	*/
	u8		Stab[RED_STAB_SIZE];

	/* Variables */
	int		qcount;		/* Number of packets since last random
					   number generation */
	u32		qR;		/* Cached random number */

	unsigned long	qavg;		/* Average queue length: A scaled */
	psched_time_t	qidlestart;	/* Start of current idle period */
};

static inline u32 red_rmask(u8 Plog)
{
	return Plog < 32 ? ((1 << Plog) - 1) : ~0UL;
}

static inline void red_set_parms(struct red_parms *p,
				 u32 qth_min, u32 qth_max, u8 Wlog, u8 Plog,
				 u8 Scell_log, u8 *stab)
{
	/* Reset average queue length, the value is strictly bound
	 * to the parameters below, reseting hurts a bit but leaving
	 * it might result in an unreasonable qavg for a while. --TGR
	 */
	p->qavg		= 0;

	p->qcount	= -1;
	p->qth_min	= qth_min << Wlog;
	p->qth_max	= qth_max << Wlog;
	p->Wlog		= Wlog;
	p->Plog		= Plog;
	p->Rmask	= red_rmask(Plog);
	p->Scell_log	= Scell_log;
	p->Scell_max	= (255 << Scell_log);

	memcpy(p->Stab, stab, sizeof(p->Stab));
}

static inline int red_is_idling(struct red_parms *p)
{
	return !PSCHED_IS_PASTPERFECT(p->qidlestart);
}

static inline void red_start_of_idle_period(struct red_parms *p)
{
	PSCHED_GET_TIME(p->qidlestart);
}

static inline void red_end_of_idle_period(struct red_parms *p)
{
	PSCHED_SET_PASTPERFECT(p->qidlestart);
}

static inline void red_restart(struct red_parms *p)
{
	red_end_of_idle_period(p);
	p->qavg = 0;
	p->qcount = -1;
}

static inline unsigned long red_calc_qavg_from_idle_time(struct red_parms *p)
{
	psched_time_t now;
	long us_idle;
	int  shift;

	PSCHED_GET_TIME(now);
	us_idle = PSCHED_TDIFF_SAFE(now, p->qidlestart, p->Scell_max);

	/*
	 * The problem: ideally, average length queue recalcultion should
	 * be done over constant clock intervals. This is too expensive, so
	 * that the calculation is driven by outgoing packets.
	 * When the queue is idle we have to model this clock by hand.
	 *
	 * SF+VJ proposed to "generate":
	 *
	 *	m = idletime / (average_pkt_size / bandwidth)
	 *
	 * dummy packets as a burst after idle time, i.e.
	 *
	 * 	p->qavg *= (1-W)^m
	 *
	 * This is an apparently overcomplicated solution (f.e. we have to
	 * precompute a table to make this calculation in reasonable time)
	 * I believe that a simpler model may be used here,
	 * but it is field for experiments.
	 */

	shift = p->Stab[(us_idle >> p->Scell_log) & RED_STAB_MASK];

	if (shift)
		return p->qavg >> shift;
	else {
		/* Approximate initial part of exponent with linear function:
		 *
		 * 	(1-W)^m ~= 1-mW + ...
		 *
		 * Seems, it is the best solution to
		 * problem of too coarse exponent tabulation.
		 */
		us_idle = (p->qavg * us_idle) >> p->Scell_log;

		if (us_idle < (p->qavg >> 1))
			return p->qavg - us_idle;
		else
			return p->qavg >> 1;
	}
}

static inline unsigned long red_calc_qavg_no_idle_time(struct red_parms *p,
						       unsigned int backlog)
{
	/*
	 * NOTE: p->qavg is fixed point number with point at Wlog.
	 * The formula below is equvalent to floating point
	 * version:
	 *
	 * 	qavg = qavg*(1-W) + backlog*W;
	 *
	 * --ANK (980924)
	 */
	return p->qavg + (backlog - (p->qavg >> p->Wlog));
}

static inline unsigned long red_calc_qavg(struct red_parms *p,
					  unsigned int backlog)
{
	if (!red_is_idling(p))
		return red_calc_qavg_no_idle_time(p, backlog);
	else
		return red_calc_qavg_from_idle_time(p);
}

static inline u32 red_random(struct red_parms *p)
{
	return net_random() & p->Rmask;
}

static inline int red_mark_probability(struct red_parms *p, unsigned long qavg)
{
	/* The formula used below causes questions.

	   OK. qR is random number in the interval 0..Rmask
	   i.e. 0..(2^Plog). If we used floating point
	   arithmetics, it would be: (2^Plog)*rnd_num,
	   where rnd_num is less 1.

	   Taking into account, that qavg have fixed
	   point at Wlog, and Plog is related to max_P by
	   max_P = (qth_max-qth_min)/2^Plog; two lines
	   below have the following floating point equivalent:

	   max_P*(qavg - qth_min)/(qth_max-qth_min) < rnd/qcount

	   Any questions? --ANK (980924)
	 */
	return !(((qavg - p->qth_min) >> p->Wlog) * p->qcount < p->qR);
}

enum {
	RED_BELOW_MIN_THRESH,
	RED_BETWEEN_TRESH,
	RED_ABOVE_MAX_TRESH,
};

static inline int red_cmp_thresh(struct red_parms *p, unsigned long qavg)
{
	if (qavg < p->qth_min)
		return RED_BELOW_MIN_THRESH;
	else if (qavg >= p->qth_max)
		return RED_ABOVE_MAX_TRESH;
	else
		return RED_BETWEEN_TRESH;
}

enum {
	RED_DONT_MARK,
	RED_PROB_MARK,
	RED_HARD_MARK,
};

static inline int red_action(struct red_parms *p, unsigned long qavg)
{
	switch (red_cmp_thresh(p, qavg)) {
		case RED_BELOW_MIN_THRESH:
			p->qcount = -1;
			return RED_DONT_MARK;

		case RED_BETWEEN_TRESH:
			if (++p->qcount) {
				if (red_mark_probability(p, qavg)) {
					p->qcount = 0;
					p->qR = red_random(p);
					return RED_PROB_MARK;
				}
			} else
				p->qR = red_random(p);

			return RED_DONT_MARK;

		case RED_ABOVE_MAX_TRESH:
			p->qcount = -1;
			return RED_HARD_MARK;
	}

	BUG();
	return RED_DONT_MARK;
}

#endif
d='n1092' href='#n1092'>1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 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
#ifndef _LINUX_FS_H
#define _LINUX_FS_H

/*
 * This file has definitions for some important file table
 * structures etc.
 */

#include <linux/limits.h>
#include <linux/ioctl.h>

/*
 * It's silly to have NR_OPEN bigger than NR_FILE, but you can change
 * the file limit at runtime and only root can increase the per-process
 * nr_file rlimit, so it's safe to set up a ridiculously high absolute
 * upper limit on files-per-process.
 *
 * Some programs (notably those using select()) may have to be 
 * recompiled to take full advantage of the new limits..  
 */

/* Fixed constants first: */
#undef NR_OPEN
#define NR_OPEN (1024*1024)	/* Absolute upper limit on fd num */
#define INR_OPEN 1024		/* Initial setting for nfile rlimits */

#define BLOCK_SIZE_BITS 10
#define BLOCK_SIZE (1<<BLOCK_SIZE_BITS)

/* And dynamically-tunable limits and defaults: */
struct files_stat_struct {
	int nr_files;		/* read only */
	int nr_free_files;	/* read only */
	int max_files;		/* tunable */
};
extern struct files_stat_struct files_stat;
extern int get_max_files(void);

struct inodes_stat_t {
	int nr_inodes;
	int nr_unused;
	int dummy[5];
};
extern struct inodes_stat_t inodes_stat;

extern int leases_enable, lease_break_time;

#ifdef CONFIG_DNOTIFY
extern int dir_notify_enable;
#endif

#define NR_FILE  8192	/* this can well be larger on a larger system */

#define MAY_EXEC 1
#define MAY_WRITE 2
#define MAY_READ 4
#define MAY_APPEND 8

#define FMODE_READ 1
#define FMODE_WRITE 2

/* Internal kernel extensions */
#define FMODE_LSEEK	4
#define FMODE_PREAD	8
#define FMODE_PWRITE	FMODE_PREAD	/* These go hand in hand */

/* File is being opened for execution. Primary users of this flag are
   distributed filesystems that can use it to achieve correct ETXTBUSY
   behavior for cross-node execution/opening_for_writing of files */
#define FMODE_EXEC	16

#define RW_MASK		1
#define RWA_MASK	2
#define READ 0
#define WRITE 1
#define READA 2		/* read-ahead  - don't block if no resources */
#define SWRITE 3	/* for ll_rw_block() - wait for buffer lock */
#define SPECIAL 4	/* For non-blockdevice requests in request queue */
#define READ_SYNC	(READ | (1 << BIO_RW_SYNC))
#define WRITE_SYNC	(WRITE | (1 << BIO_RW_SYNC))
#define WRITE_BARRIER	((1 << BIO_RW) | (1 << BIO_RW_BARRIER))

#define SEL_IN		1
#define SEL_OUT		2
#define SEL_EX		4

/* public flags for file_system_type */
#define FS_REQUIRES_DEV 1 
#define FS_BINARY_MOUNTDATA 2
#define FS_REVAL_DOT	16384	/* Check the paths ".", ".." for staleness */
#define FS_ODD_RENAME	32768	/* Temporary stuff; will go away as soon
				  * as nfs_rename() will be cleaned up
				  */
/*
 * These are the fs-independent mount-flags: up to 32 flags are supported
 */
#define MS_RDONLY	 1	/* Mount read-only */
#define MS_NOSUID	 2	/* Ignore suid and sgid bits */
#define MS_NODEV	 4	/* Disallow access to device special files */
#define MS_NOEXEC	 8	/* Disallow program execution */
#define MS_SYNCHRONOUS	16	/* Writes are synced at once */
#define MS_REMOUNT	32	/* Alter flags of a mounted FS */
#define MS_MANDLOCK	64	/* Allow mandatory locks on an FS */
#define MS_DIRSYNC	128	/* Directory modifications are synchronous */
#define MS_NOATIME	1024	/* Do not update access times. */
#define MS_NODIRATIME	2048	/* Do not update directory access times */
#define MS_BIND		4096
#define MS_MOVE		8192
#define MS_REC		16384
#define MS_VERBOSE	32768	/* War is peace. Verbosity is silence.
				   MS_VERBOSE is deprecated. */
#define MS_SILENT	32768
#define MS_POSIXACL	(1<<16)	/* VFS does not apply the umask */
#define MS_UNBINDABLE	(1<<17)	/* change to unbindable */
#define MS_PRIVATE	(1<<18)	/* change to private */
#define MS_SLAVE	(1<<19)	/* change to slave */
#define MS_SHARED	(1<<20)	/* change to shared */
#define MS_ACTIVE	(1<<30)
#define MS_NOUSER	(1<<31)

/*
 * Superblock flags that can be altered by MS_REMOUNT
 */
#define MS_RMT_MASK	(MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK)

/*
 * Old magic mount flag and mask
 */
#define MS_MGC_VAL 0xC0ED0000
#define MS_MGC_MSK 0xffff0000

/* Inode flags - they have nothing to superblock flags now */

#define S_SYNC		1	/* Writes are synced at once */
#define S_NOATIME	2	/* Do not update access times */
#define S_APPEND	4	/* Append-only file */
#define S_IMMUTABLE	8	/* Immutable file */
#define S_DEAD		16	/* removed, but still open directory */
#define S_NOQUOTA	32	/* Inode is not counted to quota */
#define S_DIRSYNC	64	/* Directory modifications are synchronous */
#define S_NOCMTIME	128	/* Do not update file c/mtime */
#define S_SWAPFILE	256	/* Do not truncate: swapon got its bmaps */
#define S_PRIVATE	512	/* Inode is fs-internal */

/*
 * Note that nosuid etc flags are inode-specific: setting some file-system
 * flags just means all the inodes inherit those flags by default. It might be
 * possible to override it selectively if you really wanted to with some
 * ioctl() that is not currently implemented.
 *
 * Exception: MS_RDONLY is always applied to the entire file system.
 *
 * Unfortunately, it is possible to change a filesystems flags with it mounted
 * with files in use.  This means that all of the inodes will not have their
 * i_flags updated.  Hence, i_flags no longer inherit the superblock mount
 * flags, so these have to be checked separately. -- rmk@arm.uk.linux.org
 */
#define __IS_FLG(inode,flg) ((inode)->i_sb->s_flags & (flg))

#define IS_RDONLY(inode) ((inode)->i_sb->s_flags & MS_RDONLY)
#define IS_SYNC(inode)		(__IS_FLG(inode, MS_SYNCHRONOUS) || \
					((inode)->i_flags & S_SYNC))
#define IS_DIRSYNC(inode)	(__IS_FLG(inode, MS_SYNCHRONOUS|MS_DIRSYNC) || \
					((inode)->i_flags & (S_SYNC|S_DIRSYNC)))
#define IS_MANDLOCK(inode)	__IS_FLG(inode, MS_MANDLOCK)

#define IS_NOQUOTA(inode)	((inode)->i_flags & S_NOQUOTA)
#define IS_APPEND(inode)	((inode)->i_flags & S_APPEND)
#define IS_IMMUTABLE(inode)	((inode)->i_flags & S_IMMUTABLE)
#define IS_POSIXACL(inode)	__IS_FLG(inode, MS_POSIXACL)

#define IS_DEADDIR(inode)	((inode)->i_flags & S_DEAD)
#define IS_NOCMTIME(inode)	((inode)->i_flags & S_NOCMTIME)
#define IS_SWAPFILE(inode)	((inode)->i_flags & S_SWAPFILE)
#define IS_PRIVATE(inode)	((inode)->i_flags & S_PRIVATE)

/* the read-only stuff doesn't really belong here, but any other place is
   probably as bad and I don't want to create yet another include file. */

#define BLKROSET   _IO(0x12,93)	/* set device read-only (0 = read-write) */
#define BLKROGET   _IO(0x12,94)	/* get read-only status (0 = read_write) */
#define BLKRRPART  _IO(0x12,95)	/* re-read partition table */
#define BLKGETSIZE _IO(0x12,96)	/* return device size /512 (long *arg) */
#define BLKFLSBUF  _IO(0x12,97)	/* flush buffer cache */
#define BLKRASET   _IO(0x12,98)	/* set read ahead for block device */
#define BLKRAGET   _IO(0x12,99)	/* get current read ahead setting */
#define BLKFRASET  _IO(0x12,100)/* set filesystem (mm/filemap.c) read-ahead */
#define BLKFRAGET  _IO(0x12,101)/* get filesystem (mm/filemap.c) read-ahead */
#define BLKSECTSET _IO(0x12,102)/* set max sectors per request (ll_rw_blk.c) */
#define BLKSECTGET _IO(0x12,103)/* get max sectors per request (ll_rw_blk.c) */
#define BLKSSZGET  _IO(0x12,104)/* get block device sector size */
#if 0
#define BLKPG      _IO(0x12,105)/* See blkpg.h */

/* Some people are morons.  Do not use sizeof! */

#define BLKELVGET  _IOR(0x12,106,size_t)/* elevator get */
#define BLKELVSET  _IOW(0x12,107,size_t)/* elevator set */
/* This was here just to show that the number is taken -
   probably all these _IO(0x12,*) ioctls should be moved to blkpg.h. */
#endif
/* A jump here: 108-111 have been used for various private purposes. */
#define BLKBSZGET  _IOR(0x12,112,size_t)
#define BLKBSZSET  _IOW(0x12,113,size_t)
#define BLKGETSIZE64 _IOR(0x12,114,size_t)	/* return device size in bytes (u64 *arg) */
#define BLKTRACESETUP _IOWR(0x12,115,struct blk_user_trace_setup)
#define BLKTRACESTART _IO(0x12,116)
#define BLKTRACESTOP _IO(0x12,117)
#define BLKTRACETEARDOWN _IO(0x12,118)

#define BMAP_IOCTL 1		/* obsolete - kept for compatibility */
#define FIBMAP	   _IO(0x00,1)	/* bmap access */
#define FIGETBSZ   _IO(0x00,2)	/* get the block size used for bmap */

#define SYNC_FILE_RANGE_WAIT_BEFORE	1
#define SYNC_FILE_RANGE_WRITE		2
#define SYNC_FILE_RANGE_WAIT_AFTER	4

#ifdef __KERNEL__

#include <linux/linkage.h>
#include <linux/wait.h>
#include <linux/types.h>
#include <linux/kdev_t.h>
#include <linux/dcache.h>
#include <linux/stat.h>
#include <linux/cache.h>
#include <linux/kobject.h>
#include <linux/list.h>
#include <linux/radix-tree.h>
#include <linux/prio_tree.h>
#include <linux/init.h>
#include <linux/sched.h>
#include <linux/mutex.h>

#include <asm/atomic.h>
#include <asm/semaphore.h>
#include <asm/byteorder.h>

struct hd_geometry;
struct iovec;
struct nameidata;
struct kiocb;
struct pipe_inode_info;
struct poll_table_struct;
struct kstatfs;
struct vm_area_struct;
struct vfsmount;

extern void __init inode_init(unsigned long);
extern void __init inode_init_early(void);
extern void __init mnt_init(unsigned long);
extern void __init files_init(unsigned long);

struct buffer_head;
typedef int (get_block_t)(struct inode *inode, sector_t iblock,
			struct buffer_head *bh_result, int create);
typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
			ssize_t bytes, void *private);

/*
 * Attribute flags.  These should be or-ed together to figure out what
 * has been changed!
 */
#define ATTR_MODE	1
#define ATTR_UID	2
#define ATTR_GID	4
#define ATTR_SIZE	8
#define ATTR_ATIME	16
#define ATTR_MTIME	32
#define ATTR_CTIME	64
#define ATTR_ATIME_SET	128
#define ATTR_MTIME_SET	256
#define ATTR_FORCE	512	/* Not a change, but a change it */
#define ATTR_ATTR_FLAG	1024
#define ATTR_KILL_SUID	2048
#define ATTR_KILL_SGID	4096
#define ATTR_FILE	8192

/*
 * This is the Inode Attributes structure, used for notify_change().  It
 * uses the above definitions as flags, to know which values have changed.
 * Also, in this manner, a Filesystem can look at only the values it cares
 * about.  Basically, these are the attributes that the VFS layer can
 * request to change from the FS layer.
 *
 * Derek Atkins <warlord@MIT.EDU> 94-10-20
 */
struct iattr {
	unsigned int	ia_valid;
	umode_t		ia_mode;
	uid_t		ia_uid;
	gid_t		ia_gid;
	loff_t		ia_size;
	struct timespec	ia_atime;
	struct timespec	ia_mtime;
	struct timespec	ia_ctime;

	/*
	 * Not an attribute, but an auxilary info for filesystems wanting to
	 * implement an ftruncate() like method.  NOTE: filesystem should
	 * check for (ia_valid & ATTR_FILE), and not for (ia_file != NULL).
	 */
	struct file	*ia_file;
};

/*
 * Includes for diskquotas.
 */
#include <linux/quota.h>

/** 
 * enum positive_aop_returns - aop return codes with specific semantics
 *
 * @AOP_WRITEPAGE_ACTIVATE: Informs the caller that page writeback has
 * 			    completed, that the page is still locked, and
 * 			    should be considered active.  The VM uses this hint
 * 			    to return the page to the active list -- it won't
 * 			    be a candidate for writeback again in the near
 * 			    future.  Other callers must be careful to unlock
 * 			    the page if they get this return.  Returned by
 * 			    writepage(); 
 *
 * @AOP_TRUNCATED_PAGE: The AOP method that was handed a locked page has
 *  			unlocked it and the page might have been truncated.
 *  			The caller should back up to acquiring a new page and
 *  			trying again.  The aop will be taking reasonable
 *  			precautions not to livelock.  If the caller held a page
 *  			reference, it should drop it before retrying.  Returned
 *  			by readpage(), prepare_write(), and commit_write().
 *
 * address_space_operation functions return these large constants to indicate
 * special semantics to the caller.  These are much larger than the bytes in a
 * page to allow for functions that return the number of bytes operated on in a
 * given page.
 */

enum positive_aop_returns {
	AOP_WRITEPAGE_ACTIVATE	= 0x80000,
	AOP_TRUNCATED_PAGE	= 0x80001,
};

/*
 * oh the beauties of C type declarations.
 */
struct page;
struct address_space;
struct writeback_control;

struct address_space_operations {
	int (*writepage)(struct page *page, struct writeback_control *wbc);
	int (*readpage)(struct file *, struct page *);
	void (*sync_page)(struct page *);

	/* Write back some dirty pages from this mapping. */
	int (*writepages)(struct address_space *, struct writeback_control *);

	/* Set a page dirty.  Return true if this dirtied it */
	int (*set_page_dirty)(struct page *page);

	int (*readpages)(struct file *filp, struct address_space *mapping,
			struct list_head *pages, unsigned nr_pages);

	/*
	 * ext3 requires that a successful prepare_write() call be followed
	 * by a commit_write() call - they must be balanced
	 */
	int (*prepare_write)(struct file *, struct page *, unsigned, unsigned);
	int (*commit_write)(struct file *, struct page *, unsigned, unsigned);
	/* Unfortunately this kludge is needed for FIBMAP. Don't use it */
	sector_t (*bmap)(struct address_space *, sector_t);
	void (*invalidatepage) (struct page *, unsigned long);
	int (*releasepage) (struct page *, gfp_t);
	ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
			loff_t offset, unsigned long nr_segs);
	struct page* (*get_xip_page)(struct address_space *, sector_t,
			int);
	/* migrate the contents of a page to the specified target */
	int (*migratepage) (struct address_space *,
			struct page *, struct page *);
};

struct backing_dev_info;
struct address_space {
	struct inode		*host;		/* owner: inode, block_device */
	struct radix_tree_root	page_tree;	/* radix tree of all pages */
	rwlock_t		tree_lock;	/* and rwlock protecting it */
	unsigned int		i_mmap_writable;/* count VM_SHARED mappings */
	struct prio_tree_root	i_mmap;		/* tree of private and shared mappings */
	struct list_head	i_mmap_nonlinear;/*list VM_NONLINEAR mappings */
	spinlock_t		i_mmap_lock;	/* protect tree, count, list */
	unsigned int		truncate_count;	/* Cover race condition with truncate */
	unsigned long		nrpages;	/* number of total pages */
	pgoff_t			writeback_index;/* writeback starts here */
	const struct address_space_operations *a_ops;	/* methods */
	unsigned long		flags;		/* error bits/gfp mask */
	struct backing_dev_info *backing_dev_info; /* device readahead, etc */
	spinlock_t		private_lock;	/* for use by the address_space */
	struct list_head	private_list;	/* ditto */
	struct address_space	*assoc_mapping;	/* ditto */
} __attribute__((aligned(sizeof(long))));
	/*
	 * On most architectures that alignment is already the case; but
	 * must be enforced here for CRIS, to let the least signficant bit
	 * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON.
	 */

struct block_device {
	dev_t			bd_dev;  /* not a kdev_t - it's a search key */
	struct inode *		bd_inode;	/* will die */
	int			bd_openers;
	struct mutex		bd_mutex;	/* open/close mutex */
	struct mutex		bd_mount_mutex;	/* mount mutex */
	struct list_head	bd_inodes;
	void *			bd_holder;
	int			bd_holders;
#ifdef CONFIG_SYSFS
	struct list_head	bd_holder_list;
#endif
	struct block_device *	bd_contains;
	unsigned		bd_block_size;
	struct hd_struct *	bd_part;
	/* number of times partitions within this device have been opened. */
	unsigned		bd_part_count;
	int			bd_invalidated;
	struct gendisk *	bd_disk;
	struct list_head	bd_list;
	struct backing_dev_info *bd_inode_backing_dev_info;
	/*
	 * Private data.  You must have bd_claim'ed the block_device
	 * to use this.  NOTE:  bd_claim allows an owner to claim
	 * the same device multiple times, the owner must take special
	 * care to not mess up bd_private for that case.
	 */
	unsigned long		bd_private;
};

/*
 * Radix-tree tags, for tagging dirty and writeback pages within the pagecache
 * radix trees
 */
#define PAGECACHE_TAG_DIRTY	0
#define PAGECACHE_TAG_WRITEBACK	1

int mapping_tagged(struct address_space *mapping, int tag);

/*
 * Might pages of this file be mapped into userspace?
 */
static inline int mapping_mapped(struct address_space *mapping)
{
	return	!prio_tree_empty(&mapping->i_mmap) ||
		!list_empty(&mapping->i_mmap_nonlinear);
}

/*
 * Might pages of this file have been modified in userspace?
 * Note that i_mmap_writable counts all VM_SHARED vmas: do_mmap_pgoff
 * marks vma as VM_SHARED if it is shared, and the file was opened for
 * writing i.e. vma may be mprotected writable even if now readonly.
 */
static inline int mapping_writably_mapped(struct address_space *mapping)
{
	return mapping->i_mmap_writable != 0;
}

/*
 * Use sequence counter to get consistent i_size on 32-bit processors.
 */
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
#include <linux/seqlock.h>
#define __NEED_I_SIZE_ORDERED
#define i_size_ordered_init(inode) seqcount_init(&inode->i_size_seqcount)
#else
#define i_size_ordered_init(inode) do { } while (0)
#endif

struct inode {
	struct hlist_node	i_hash;
	struct list_head	i_list;
	struct list_head	i_sb_list;
	struct list_head	i_dentry;
	unsigned long		i_ino;
	atomic_t		i_count;
	umode_t			i_mode;
	unsigned int		i_nlink;
	uid_t			i_uid;
	gid_t			i_gid;
	dev_t			i_rdev;
	loff_t			i_size;
	struct timespec		i_atime;
	struct timespec		i_mtime;
	struct timespec		i_ctime;
	unsigned int		i_blkbits;
	unsigned long		i_blksize;
	unsigned long		i_version;
	blkcnt_t		i_blocks;
	unsigned short          i_bytes;
	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
	struct mutex		i_mutex;
	struct rw_semaphore	i_alloc_sem;
	struct inode_operations	*i_op;
	const struct file_operations	*i_fop;	/* former ->i_op->default_file_ops */
	struct super_block	*i_sb;
	struct file_lock	*i_flock;
	struct address_space	*i_mapping;
	struct address_space	i_data;
#ifdef CONFIG_QUOTA
	struct dquot		*i_dquot[MAXQUOTAS];
#endif
	/* These three should probably be a union */
	struct list_head	i_devices;
	struct pipe_inode_info	*i_pipe;
	struct block_device	*i_bdev;
	struct cdev		*i_cdev;
	int			i_cindex;

	__u32			i_generation;

#ifdef CONFIG_DNOTIFY
	unsigned long		i_dnotify_mask; /* Directory notify events */
	struct dnotify_struct	*i_dnotify; /* for directory notifications */
#endif

#ifdef CONFIG_INOTIFY
	struct list_head	inotify_watches; /* watches on this inode */
	struct mutex		inotify_mutex;	/* protects the watches list */
#endif

	unsigned long		i_state;
	unsigned long		dirtied_when;	/* jiffies of first dirtying */

	unsigned int		i_flags;

	atomic_t		i_writecount;
	void			*i_security;
	union {
		void		*generic_ip;
	} u;
#ifdef __NEED_I_SIZE_ORDERED
	seqcount_t		i_size_seqcount;
#endif
};

/*
 * inode->i_mutex nesting subclasses for the lock validator:
 *
 * 0: the object of the current VFS operation
 * 1: parent
 * 2: child/target
 * 3: quota file
 *
 * The locking order between these classes is
 * parent -> child -> normal -> quota
 */
enum inode_i_mutex_lock_class
{
	I_MUTEX_NORMAL,
	I_MUTEX_PARENT,
	I_MUTEX_CHILD,
	I_MUTEX_QUOTA
};

/*
 * NOTE: in a 32bit arch with a preemptable kernel and
 * an UP compile the i_size_read/write must be atomic
 * with respect to the local cpu (unlike with preempt disabled),
 * but they don't need to be atomic with respect to other cpus like in
 * true SMP (so they need either to either locally disable irq around
 * the read or for example on x86 they can be still implemented as a
 * cmpxchg8b without the need of the lock prefix). For SMP compiles
 * and 64bit archs it makes no difference if preempt is enabled or not.
 */
static inline loff_t i_size_read(struct inode *inode)
{
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
	loff_t i_size;
	unsigned int seq;

	do {
		seq = read_seqcount_begin(&inode->i_size_seqcount);
		i_size = inode->i_size;
	} while (read_seqcount_retry(&inode->i_size_seqcount, seq));
	return i_size;
#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
	loff_t i_size;

	preempt_disable();
	i_size = inode->i_size;
	preempt_enable();
	return i_size;
#else
	return inode->i_size;
#endif
}


static inline void i_size_write(struct inode *inode, loff_t i_size)
{
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
	write_seqcount_begin(&inode->i_size_seqcount);
	inode->i_size = i_size;
	write_seqcount_end(&inode->i_size_seqcount);
#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
	preempt_disable();
	inode->i_size = i_size;
	preempt_enable();
#else
	inode->i_size = i_size;
#endif
}

static inline unsigned iminor(struct inode *inode)
{
	return MINOR(inode->i_rdev);
}

static inline unsigned imajor(struct inode *inode)
{
	return MAJOR(inode->i_rdev);
}

extern struct block_device *I_BDEV(struct inode *inode);

struct fown_struct {
	rwlock_t lock;          /* protects pid, uid, euid fields */
	int pid;		/* pid or -pgrp where SIGIO should be sent */
	uid_t uid, euid;	/* uid/euid of process setting the owner */
	void *security;
	int signum;		/* posix.1b rt signal to be delivered on IO */
};

/*
 * Track a single file's readahead state
 */
struct file_ra_state {
	unsigned long start;		/* Current window */
	unsigned long size;
	unsigned long flags;		/* ra flags RA_FLAG_xxx*/
	unsigned long cache_hit;	/* cache hit count*/
	unsigned long prev_page;	/* Cache last read() position */
	unsigned long ahead_start;	/* Ahead window */
	unsigned long ahead_size;
	unsigned long ra_pages;		/* Maximum readahead window */
	unsigned long mmap_hit;		/* Cache hit stat for mmap accesses */
	unsigned long mmap_miss;	/* Cache miss stat for mmap accesses */
};
#define RA_FLAG_MISS 0x01	/* a cache miss occured against this file */
#define RA_FLAG_INCACHE 0x02	/* file is already in cache */

struct file {
	/*
	 * fu_list becomes invalid after file_free is called and queued via
	 * fu_rcuhead for RCU freeing
	 */
	union {
		struct list_head	fu_list;
		struct rcu_head 	fu_rcuhead;
	} f_u;
	struct dentry		*f_dentry;
	struct vfsmount         *f_vfsmnt;
	const struct file_operations	*f_op;
	atomic_t		f_count;
	unsigned int 		f_flags;
	mode_t			f_mode;
	loff_t			f_pos;
	struct fown_struct	f_owner;
	unsigned int		f_uid, f_gid;
	struct file_ra_state	f_ra;

	unsigned long		f_version;
	void			*f_security;

	/* needed for tty driver, and maybe others */
	void			*private_data;

#ifdef CONFIG_EPOLL
	/* Used by fs/eventpoll.c to link all the hooks to this file */
	struct list_head	f_ep_links;
	spinlock_t		f_ep_lock;
#endif /* #ifdef CONFIG_EPOLL */
	struct address_space	*f_mapping;
};
extern spinlock_t files_lock;
#define file_list_lock() spin_lock(&files_lock);
#define file_list_unlock() spin_unlock(&files_lock);

#define get_file(x)	atomic_inc(&(x)->f_count)
#define file_count(x)	atomic_read(&(x)->f_count)

#define	MAX_NON_LFS	((1UL<<31) - 1)

/* Page cache limit. The filesystems should put that into their s_maxbytes 
   limits, otherwise bad things can happen in VM. */ 
#if BITS_PER_LONG==32
#define MAX_LFS_FILESIZE	(((u64)PAGE_CACHE_SIZE << (BITS_PER_LONG-1))-1) 
#elif BITS_PER_LONG==64
#define MAX_LFS_FILESIZE 	0x7fffffffffffffffUL
#endif

#define FL_POSIX	1
#define FL_FLOCK	2
#define FL_ACCESS	8	/* not trying to lock, just looking */
#define FL_LEASE	32	/* lease held on this file */
#define FL_CLOSE	64	/* unlock on close */
#define FL_SLEEP	128	/* A blocking lock */

/*
 * The POSIX file lock owner is determined by
 * the "struct files_struct" in the thread group
 * (or NULL for no owner - BSD locks).
 *
 * Lockd stuffs a "host" pointer into this.
 */
typedef struct files_struct *fl_owner_t;

struct file_lock_operations {
	void (*fl_insert)(struct file_lock *);	/* lock insertion callback */
	void (*fl_remove)(struct file_lock *);	/* lock removal callback */
	void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
	void (*fl_release_private)(struct file_lock *);
};

struct lock_manager_operations {
	int (*fl_compare_owner)(struct file_lock *, struct file_lock *);
	void (*fl_notify)(struct file_lock *);	/* unblock callback */
	void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
	void (*fl_release_private)(struct file_lock *);
	void (*fl_break)(struct file_lock *);
	int (*fl_mylease)(struct file_lock *, struct file_lock *);
	int (*fl_change)(struct file_lock **, int);
};

/* that will die - we need it for nfs_lock_info */
#include <linux/nfs_fs_i.h>

struct file_lock {
	struct file_lock *fl_next;	/* singly linked list for this inode  */
	struct list_head fl_link;	/* doubly linked list of all locks */
	struct list_head fl_block;	/* circular list of blocked processes */
	fl_owner_t fl_owner;
	unsigned int fl_pid;
	wait_queue_head_t fl_wait;
	struct file *fl_file;
	unsigned char fl_flags;
	unsigned char fl_type;
	loff_t fl_start;
	loff_t fl_end;

	struct fasync_struct *	fl_fasync; /* for lease break notifications */
	unsigned long fl_break_time;	/* for nonblocking lease breaks */

	struct file_lock_operations *fl_ops;	/* Callbacks for filesystems */
	struct lock_manager_operations *fl_lmops;	/* Callbacks for lockmanagers */
	union {
		struct nfs_lock_info	nfs_fl;
		struct nfs4_lock_info	nfs4_fl;
	} fl_u;
};

/* The following constant reflects the upper bound of the file/locking space */
#ifndef OFFSET_MAX
#define INT_LIMIT(x)	(~((x)1 << (sizeof(x)*8 - 1)))
#define OFFSET_MAX	INT_LIMIT(loff_t)
#define OFFT_OFFSET_MAX	INT_LIMIT(off_t)
#endif

#include <linux/fcntl.h>

extern int fcntl_getlk(struct file *, struct flock __user *);
extern int fcntl_setlk(unsigned int, struct file *, unsigned int,
			struct flock __user *);

#if BITS_PER_LONG == 32
extern int fcntl_getlk64(struct file *, struct flock64 __user *);
extern int fcntl_setlk64(unsigned int, struct file *, unsigned int,
			struct flock64 __user *);
#endif

extern void send_sigio(struct fown_struct *fown, int fd, int band);
extern int fcntl_setlease(unsigned int fd, struct file *filp, long arg);
extern int fcntl_getlease(struct file *filp);

/* fs/sync.c */
extern int do_sync_file_range(struct file *file, loff_t offset, loff_t endbyte,
			unsigned int flags);

/* fs/locks.c */
extern void locks_init_lock(struct file_lock *);
extern void locks_copy_lock(struct file_lock *, struct file_lock *);
extern void locks_remove_posix(struct file *, fl_owner_t);
extern void locks_remove_flock(struct file *);
extern int posix_test_lock(struct file *, struct file_lock *, struct file_lock *);
extern int posix_lock_file_conf(struct file *, struct file_lock *, struct file_lock *);
extern int posix_lock_file(struct file *, struct file_lock *);
extern int posix_lock_file_wait(struct file *, struct file_lock *);
extern int posix_unblock_lock(struct file *, struct file_lock *);
extern int flock_lock_file_wait(struct file *filp, struct file_lock *fl);
extern int __break_lease(struct inode *inode, unsigned int flags);
extern void lease_get_mtime(struct inode *, struct timespec *time);
extern int setlease(struct file *, long, struct file_lock **);
extern int lease_modify(struct file_lock **, int);
extern int lock_may_read(struct inode *, loff_t start, unsigned long count);
extern int lock_may_write(struct inode *, loff_t start, unsigned long count);

struct fasync_struct {
	int	magic;
	int	fa_fd;
	struct	fasync_struct	*fa_next; /* singly linked list */
	struct	file 		*fa_file;
};

#define FASYNC_MAGIC 0x4601

/* SMP safe fasync helpers: */
extern int fasync_helper(int, struct file *, int, struct fasync_struct **);
/* can be called from interrupts */
extern void kill_fasync(struct fasync_struct **, int, int);
/* only for net: no internal synchronization */
extern void __kill_fasync(struct fasync_struct *, int, int);

extern int f_setown(struct file *filp, unsigned long arg, int force);
extern void f_delown(struct file *filp);
extern int send_sigurg(struct fown_struct *fown);

/*
 *	Umount options
 */

#define MNT_FORCE	0x00000001	/* Attempt to forcibily umount */
#define MNT_DETACH	0x00000002	/* Just detach from the tree */
#define MNT_EXPIRE	0x00000004	/* Mark for expiry */

extern struct list_head super_blocks;
extern spinlock_t sb_lock;

#define sb_entry(list)	list_entry((list), struct super_block, s_list)
#define S_BIAS (1<<30)
struct super_block {
	struct list_head	s_list;		/* Keep this first */
	dev_t			s_dev;		/* search index; _not_ kdev_t */
	unsigned long		s_blocksize;
	unsigned char		s_blocksize_bits;
	unsigned char		s_dirt;
	unsigned long long	s_maxbytes;	/* Max file size */
	struct file_system_type	*s_type;
	struct super_operations	*s_op;
	struct dquot_operations	*dq_op;
 	struct quotactl_ops	*s_qcop;
	struct export_operations *s_export_op;
	unsigned long		s_flags;
	unsigned long		s_magic;
	struct dentry		*s_root;
	struct rw_semaphore	s_umount;
	struct mutex		s_lock;
	int			s_count;
	int			s_syncing;
	int			s_need_sync_fs;
	atomic_t		s_active;
	void                    *s_security;
	struct xattr_handler	**s_xattr;

	struct list_head	s_inodes;	/* all inodes */
	struct list_head	s_dirty;	/* dirty inodes */
	struct list_head	s_io;		/* parked for writeback */
	struct hlist_head	s_anon;		/* anonymous dentries for (nfs) exporting */
	struct list_head	s_files;

	struct block_device	*s_bdev;
	struct list_head	s_instances;
	struct quota_info	s_dquot;	/* Diskquota specific options */

	int			s_frozen;
	wait_queue_head_t	s_wait_unfrozen;

	char s_id[32];				/* Informational name */

	void 			*s_fs_info;	/* Filesystem private info */

	/*
	 * The next field is for VFS *only*. No filesystems have any business
	 * even looking at it. You had been warned.
	 */
	struct mutex s_vfs_rename_mutex;	/* Kludge */

	/* Granularity of c/m/atime in ns.
	   Cannot be worse than a second */
	u32		   s_time_gran;
};

extern struct timespec current_fs_time(struct super_block *sb);

/*
 * Snapshotting support.
 */
enum {
	SB_UNFROZEN = 0,
	SB_FREEZE_WRITE	= 1,
	SB_FREEZE_TRANS = 2,
};

#define vfs_check_frozen(sb, level) \
	wait_event((sb)->s_wait_unfrozen, ((sb)->s_frozen < (level)))

static inline void get_fs_excl(void)
{
	atomic_inc(&current->fs_excl);
}

static inline void put_fs_excl(void)
{
	atomic_dec(&current->fs_excl);
}

static inline int has_fs_excl(void)
{
	return atomic_read(&current->fs_excl);
}


/*
 * Superblock locking.
 */
static inline void lock_super(struct super_block * sb)
{
	get_fs_excl();
	mutex_lock(&sb->s_lock);
}

static inline void unlock_super(struct super_block * sb)
{
	put_fs_excl();
	mutex_unlock(&sb->s_lock);
}

/*
 * VFS helper functions..
 */
extern int vfs_permission(struct nameidata *, int);
extern int vfs_create(struct inode *, struct dentry *, int, struct nameidata *);
extern int vfs_mkdir(struct inode *, struct dentry *, int);
extern int vfs_mknod(struct inode *, struct dentry *, int, dev_t);
extern int vfs_symlink(struct inode *, struct dentry *, const char *, int);
extern int vfs_link(struct dentry *, struct inode *, struct dentry *);
extern int vfs_rmdir(struct inode *, struct dentry *);
extern int vfs_unlink(struct inode *, struct dentry *);
extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *);

/*
 * VFS dentry helper functions.
 */
extern void dentry_unhash(struct dentry *dentry);

/*
 * VFS file helper functions.
 */
extern int file_permission(struct file *, int);

/*
 * File types
 *
 * NOTE! These match bits 12..15 of stat.st_mode
 * (ie "(i_mode >> 12) & 15").
 */
#define DT_UNKNOWN	0
#define DT_FIFO		1
#define DT_CHR		2
#define DT_DIR		4
#define DT_BLK		6
#define DT_REG		8
#define DT_LNK		10
#define DT_SOCK		12
#define DT_WHT		14

#define OSYNC_METADATA	(1<<0)
#define OSYNC_DATA	(1<<1)
#define OSYNC_INODE	(1<<2)
int generic_osync_inode(struct inode *, struct address_space *, int);

/*
 * This is the "filldir" function type, used by readdir() to let
 * the kernel specify what kind of dirent layout it wants to have.
 * This allows the kernel to read directories into kernel space or
 * to have different dirent layouts depending on the binary type.
 */
typedef int (*filldir_t)(void *, const char *, int, loff_t, ino_t, unsigned);

struct block_device_operations {
	int (*open) (struct inode *, struct file *);
	int (*release) (struct inode *, struct file *);
	int (*ioctl) (struct inode *, struct file *, unsigned, unsigned long);
	long (*unlocked_ioctl) (struct file *, unsigned, unsigned long);
	long (*compat_ioctl) (struct file *, unsigned, unsigned long);
	int (*direct_access) (struct block_device *, sector_t, unsigned long *);
	int (*media_changed) (struct gendisk *);
	int (*revalidate_disk) (struct gendisk *);
	int (*getgeo)(struct block_device *, struct hd_geometry *);
	struct module *owner;
};

/*
 * "descriptor" for what we're up to with a read for sendfile().
 * This allows us to use the same read code yet
 * have multiple different users of the data that
 * we read from a file.
 *
 * The simplest case just copies the data to user
 * mode.
 */
typedef struct {
	size_t written;
	size_t count;
	union {
		char __user * buf;
		void *data;
	} arg;
	int error;
} read_descriptor_t;

typedef int (*read_actor_t)(read_descriptor_t *, struct page *, unsigned long, unsigned long);

/* These macros are for out of kernel modules to test that
 * the kernel supports the unlocked_ioctl and compat_ioctl
 * fields in struct file_operations. */
#define HAVE_COMPAT_IOCTL 1
#define HAVE_UNLOCKED_IOCTL 1

/*
 * NOTE:
 * read, write, poll, fsync, readv, writev, unlocked_ioctl and compat_ioctl
 * can be called without the big kernel lock held in all filesystems.
 */
struct file_operations {
	struct module *owner;
	loff_t (*llseek) (struct file *, loff_t, int);
	ssize_t (*read) (struct file *, char __user *, size_t, loff_t *);
	ssize_t (*aio_read) (struct kiocb *, char __user *, size_t, loff_t);
	ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
	ssize_t (*aio_write) (struct kiocb *, const char __user *, size_t, loff_t);
	int (*readdir) (struct file *, void *, filldir_t);
	unsigned int (*poll) (struct file *, struct poll_table_struct *);
	int (*ioctl) (struct inode *, struct file *, unsigned int, unsigned long);
	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
	int (*mmap) (struct file *, struct vm_area_struct *);
	int (*open) (struct inode *, struct file *);
	int (*flush) (struct file *, fl_owner_t id);
	int (*release) (struct inode *, struct file *);
	int (*fsync) (struct file *, struct dentry *, int datasync);
	int (*aio_fsync) (struct kiocb *, int datasync);
	int (*fasync) (int, struct file *, int);
	int (*lock) (struct file *, int, struct file_lock *);
	ssize_t (*readv) (struct file *, const struct iovec *, unsigned long, loff_t *);
	ssize_t (*writev) (struct file *, const struct iovec *, unsigned long, loff_t *);
	ssize_t (*sendfile) (struct file *, loff_t *, size_t, read_actor_t, void *);
	ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int);
	unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
	int (*check_flags)(int);
	int (*dir_notify)(struct file *filp, unsigned long arg);
	int (*flock) (struct file *, int, struct file_lock *);
	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int);
	ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int);
};

struct inode_operations {
	int (*create) (struct inode *,struct dentry *,int, struct nameidata *);
	struct dentry * (*lookup) (struct inode *,struct dentry *, struct nameidata *);
	int (*link) (struct dentry *,struct inode *,struct dentry *);
	int (*unlink) (struct inode *,struct dentry *);
	int (*symlink) (struct inode *,struct dentry *,const char *);
	int (*mkdir) (struct inode *,struct dentry *,int);
	int (*rmdir) (struct inode *,struct dentry *);
	int (*mknod) (struct inode *,struct dentry *,int,dev_t);
	int (*rename) (struct inode *, struct dentry *,
			struct inode *, struct dentry *);
	int (*readlink) (struct dentry *, char __user *,int);
	void * (*follow_link) (struct dentry *, struct nameidata *);
	void (*put_link) (struct dentry *, struct nameidata *, void *);
	void (*truncate) (struct inode *);
	int (*permission) (struct inode *, int, struct nameidata *);
	int (*setattr) (struct dentry *, struct iattr *);
	int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *);
	int (*setxattr) (struct dentry *, const char *,const void *,size_t,int);
	ssize_t (*getxattr) (struct dentry *, const char *, void *, size_t);
	ssize_t (*listxattr) (struct dentry *, char *, size_t);
	int (*removexattr) (struct dentry *, const char *);
	void (*truncate_range)(struct inode *, loff_t, loff_t);
};

struct seq_file;

extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);
extern ssize_t vfs_readv(struct file *, const struct iovec __user *,
		unsigned long, loff_t *);
extern ssize_t vfs_writev(struct file *, const struct iovec __user *,
		unsigned long, loff_t *);

/*
 * NOTE: write_inode, delete_inode, clear_inode, put_inode can be called
 * without the big kernel lock held in all filesystems.
 */
struct super_operations {
   	struct inode *(*alloc_inode)(struct super_block *sb);
	void (*destroy_inode)(struct inode *);

	void (*read_inode) (struct inode *);
  
   	void (*dirty_inode) (struct inode *);
	int (*write_inode) (struct inode *, int);
	void (*put_inode) (struct inode *);
	void (*drop_inode) (struct inode *);
	void (*delete_inode) (struct inode *);
	void (*put_super) (struct super_block *);
	void (*write_super) (struct super_block *);
	int (*sync_fs)(struct super_block *sb, int wait);
	void (*write_super_lockfs) (struct super_block *);
	void (*unlockfs) (struct super_block *);
	int (*statfs) (struct dentry *, struct kstatfs *);
	int (*remount_fs) (struct super_block *, int *, char *);
	void (*clear_inode) (struct inode *);
	void (*umount_begin) (struct vfsmount *, int);

	int (*show_options)(struct seq_file *, struct vfsmount *);
	int (*show_stats)(struct seq_file *, struct vfsmount *);

	ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t);
	ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
};

/* Inode state bits.  Protected by inode_lock. */
#define I_DIRTY_SYNC		1 /* Not dirty enough for O_DATASYNC */
#define I_DIRTY_DATASYNC	2 /* Data-related inode changes pending */
#define I_DIRTY_PAGES		4 /* Data-related inode changes pending */
#define __I_LOCK		3
#define I_LOCK			(1 << __I_LOCK)
#define I_FREEING		16
#define I_CLEAR			32
#define I_NEW			64
#define I_WILL_FREE		128

#define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES)

extern void __mark_inode_dirty(struct inode *, int);
static inline void mark_inode_dirty(struct inode *inode)
{
	__mark_inode_dirty(inode, I_DIRTY);
}

static inline void mark_inode_dirty_sync(struct inode *inode)
{
	__mark_inode_dirty(inode, I_DIRTY_SYNC);
}

static inline void inode_inc_link_count(struct inode *inode)
{
	inode->i_nlink++;
	mark_inode_dirty(inode);
}

static inline void inode_dec_link_count(struct inode *inode)
{
	inode->i_nlink--;
	mark_inode_dirty(inode);
}

extern void touch_atime(struct vfsmount *mnt, struct dentry *dentry);
static inline void file_accessed(struct file *file)
{
	if (!(file->f_flags & O_NOATIME))
		touch_atime(file->f_vfsmnt, file->f_dentry);
}

int sync_inode(struct inode *inode, struct writeback_control *wbc);

/**
 * struct export_operations - for nfsd to communicate with file systems
 * @decode_fh:      decode a file handle fragment and return a &struct dentry
 * @encode_fh:      encode a file handle fragment from a dentry
 * @get_name:       find the name for a given inode in a given directory
 * @get_parent:     find the parent of a given directory
 * @get_dentry:     find a dentry for the inode given a file handle sub-fragment
 * @find_exported_dentry:
 *	set by the exporting module to a standard helper function.
 *
 * Description:
 *    The export_operations structure provides a means for nfsd to communicate
 *    with a particular exported file system  - particularly enabling nfsd and
 *    the filesystem to co-operate when dealing with file handles.
 *
 *    export_operations contains two basic operation for dealing with file
 *    handles, decode_fh() and encode_fh(), and allows for some other
 *    operations to be defined which standard helper routines use to get
 *    specific information from the filesystem.
 *
 *    nfsd encodes information use to determine which filesystem a filehandle
 *    applies to in the initial part of the file handle.  The remainder, termed
 *    a file handle fragment, is controlled completely by the filesystem.  The
 *    standard helper routines assume that this fragment will contain one or
 *    two sub-fragments, one which identifies the file, and one which may be
 *    used to identify the (a) directory containing the file.
 *
 *    In some situations, nfsd needs to get a dentry which is connected into a
 *    specific part of the file tree.  To allow for this, it passes the
 *    function acceptable() together with a @context which can be used to see
 *    if the dentry is acceptable.  As there can be multiple dentrys for a
 *    given file, the filesystem should check each one for acceptability before
 *    looking for the next.  As soon as an acceptable one is found, it should
 *    be returned.
 *
 * decode_fh:
 *    @decode_fh is given a &struct super_block (@sb), a file handle fragment
 *    (@fh, @fh_len) and an acceptability testing function (@acceptable,
 *    @context).  It should return a &struct dentry which refers to the same
 *    file that the file handle fragment refers to,  and which passes the
 *    acceptability test.  If it cannot, it should return a %NULL pointer if
 *    the file was found but no acceptable &dentries were available, or a
 *    %ERR_PTR error code indicating why it couldn't be found (e.g. %ENOENT or
 *    %ENOMEM).
 *
 * encode_fh:
 *    @encode_fh should store in the file handle fragment @fh (using at most
 *    @max_len bytes) information that can be used by @decode_fh to recover the
 *    file refered to by the &struct dentry @de.  If the @connectable flag is
 *    set, the encode_fh() should store sufficient information so that a good
 *    attempt can be made to find not only the file but also it's place in the
 *    filesystem.   This typically means storing a reference to de->d_parent in
 *    the filehandle fragment.  encode_fh() should return the number of bytes
 *    stored or a negative error code such as %-ENOSPC
 *
 * get_name:
 *    @get_name should find a name for the given @child in the given @parent
 *    directory.  The name should be stored in the @name (with the
 *    understanding that it is already pointing to a a %NAME_MAX+1 sized
 *    buffer.   get_name() should return %0 on success, a negative error code
 *    or error.  @get_name will be called without @parent->i_mutex held.
 *
 * get_parent:
 *    @get_parent should find the parent directory for the given @child which
 *    is also a directory.  In the event that it cannot be found, or storage
 *    space cannot be allocated, a %ERR_PTR should be returned.
 *
 * get_dentry:
 *    Given a &super_block (@sb) and a pointer to a file-system specific inode
 *    identifier, possibly an inode number, (@inump) get_dentry() should find
 *    the identified inode and return a dentry for that inode.  Any suitable
 *    dentry can be returned including, if necessary, a new dentry created with
 *    d_alloc_root.  The caller can then find any other extant dentrys by
 *    following the d_alias links.  If a new dentry was created using
 *    d_alloc_root, DCACHE_NFSD_DISCONNECTED should be set, and the dentry
 *    should be d_rehash()ed.
 *
 *    If the inode cannot be found, either a %NULL pointer or an %ERR_PTR code
 *    can be returned.  The @inump will be whatever was passed to
 *    nfsd_find_fh_dentry() in either the @obj or @parent parameters.
 *
 * Locking rules:
 *    get_parent is called with child->d_inode->i_mutex down
 *    get_name is not (which is possibly inconsistent)
 */

struct export_operations {
	struct dentry *(*decode_fh)(struct super_block *sb, __u32 *fh, int fh_len, int fh_type,
			 int (*acceptable)(void *context, struct dentry *de),
			 void *context);
	int (*encode_fh)(struct dentry *de, __u32 *fh, int *max_len,
			 int connectable);

	/* the following are only called from the filesystem itself */
	int (*get_name)(struct dentry *parent, char *name,
			struct dentry *child);
	struct dentry * (*get_parent)(struct dentry *child);
	struct dentry * (*get_dentry)(struct super_block *sb, void *inump);

	/* This is set by the exporting module to a standard helper */
	struct dentry * (*find_exported_dentry)(
		struct super_block *sb, void *obj, void *parent,
		int (*acceptable)(void *context, struct dentry *de),
		void *context);


};

extern struct dentry *
find_exported_dentry(struct super_block *sb, void *obj, void *parent,
		     int (*acceptable)(void *context, struct dentry *de),
		     void *context);

struct file_system_type {
	const char *name;
	int fs_flags;
	int (*get_sb) (struct file_system_type *, int,
		       const char *, void *, struct vfsmount *);
	void (*kill_sb) (struct super_block *);
	struct module *owner;
	struct file_system_type * next;
	struct list_head fs_supers;
};

extern int get_sb_bdev(struct file_system_type *fs_type,
	int flags, const char *dev_name, void *data,
	int (*fill_super)(struct super_block *, void *, int),
	struct vfsmount *mnt);
extern int get_sb_single(struct file_system_type *fs_type,
	int flags, void *data,
	int (*fill_super)(struct super_block *, void *, int),
	struct vfsmount *mnt);
extern int get_sb_nodev(struct file_system_type *fs_type,
	int flags, void *data,
	int (*fill_super)(struct super_block *, void *, int),
	struct vfsmount *mnt);
void generic_shutdown_super(struct super_block *sb);
void kill_block_super(struct super_block *sb);
void kill_anon_super(struct super_block *sb);
void kill_litter_super(struct super_block *sb);
void deactivate_super(struct super_block *sb);
int set_anon_super(struct super_block *s, void *data);
struct super_block *sget(struct file_system_type *type,
			int (*test)(struct super_block *,void *),
			int (*set)(struct super_block *,void *),
			void *data);
extern int get_sb_pseudo(struct file_system_type *, char *,
	struct super_operations *ops, unsigned long,
	struct vfsmount *mnt);
extern int simple_set_mnt(struct vfsmount *mnt, struct super_block *sb);
int __put_super(struct super_block *sb);
int __put_super_and_need_restart(struct super_block *sb);
void unnamed_dev_init(void);

/* Alas, no aliases. Too much hassle with bringing module.h everywhere */
#define fops_get(fops) \
	(((fops) && try_module_get((fops)->owner) ? (fops) : NULL))
#define fops_put(fops) \
	do { if (fops) module_put((fops)->owner); } while(0)

extern int register_filesystem(struct file_system_type *);
extern int unregister_filesystem(struct file_system_type *);
extern struct vfsmount *kern_mount(struct file_system_type *);
extern int may_umount_tree(struct vfsmount *);
extern int may_umount(struct vfsmount *);
extern void umount_tree(struct vfsmount *, int, struct list_head *);
extern void release_mounts(struct list_head *);
extern long do_mount(char *, char *, char *, unsigned long, void *);
extern struct vfsmount *copy_tree(struct vfsmount *, struct dentry *, int);
extern void mnt_set_mountpoint(struct vfsmount *, struct dentry *,
				  struct vfsmount *);

extern int vfs_statfs(struct dentry *, struct kstatfs *);

/* /sys/fs */
extern struct subsystem fs_subsys;

#define FLOCK_VERIFY_READ  1
#define FLOCK_VERIFY_WRITE 2

extern int locks_mandatory_locked(struct inode *);
extern int locks_mandatory_area(int, struct inode *, struct file *, loff_t, size_t);

/*
 * Candidates for mandatory locking have the setgid bit set
 * but no group execute bit -  an otherwise meaningless combination.
 */
#define MANDATORY_LOCK(inode) \
	(IS_MANDLOCK(inode) && ((inode)->i_mode & (S_ISGID | S_IXGRP)) == S_ISGID)

static inline int locks_verify_locked(struct inode *inode)
{
	if (MANDATORY_LOCK(inode))
		return locks_mandatory_locked(inode);
	return 0;
}

extern int rw_verify_area(int, struct file *, loff_t *, size_t);

static inline int locks_verify_truncate(struct inode *inode,
				    struct file *filp,
				    loff_t size)
{
	if (inode->i_flock && MANDATORY_LOCK(inode))
		return locks_mandatory_area(
			FLOCK_VERIFY_WRITE, inode, filp,
			size < inode->i_size ? size : inode->i_size,
			(size < inode->i_size ? inode->i_size - size
			 : size - inode->i_size)
		);
	return 0;
}

static inline int break_lease(struct inode *inode, unsigned int mode)
{
	if (inode->i_flock)
		return __break_lease(inode, mode);
	return 0;
}

/* fs/open.c */

extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs,
		       struct file *filp);
extern long do_sys_open(int fdf, const char __user *filename, int flags,
			int mode);
extern struct file *filp_open(const char *, int, int);
extern struct file * dentry_open(struct dentry *, struct vfsmount *, int);
extern int filp_close(struct file *, fl_owner_t id);
extern char * getname(const char __user *);

/* fs/dcache.c */
extern void __init vfs_caches_init_early(void);
extern void __init vfs_caches_init(unsigned long);

#define __getname()	kmem_cache_alloc(names_cachep, SLAB_KERNEL)
#define __putname(name) kmem_cache_free(names_cachep, (void *)(name))
#ifndef CONFIG_AUDITSYSCALL
#define putname(name)   __putname(name)
#else
extern void putname(const char *name);
#endif

extern int register_blkdev(unsigned int, const char *);
extern int unregister_blkdev(unsigned int, const char *);
extern struct block_device *bdget(dev_t);
extern void bd_set_size(struct block_device *, loff_t size);
extern void bd_forget(struct inode *inode);
extern void bdput(struct block_device *);
extern struct block_device *open_by_devnum(dev_t, unsigned);
extern const struct file_operations def_blk_fops;
extern const struct address_space_operations def_blk_aops;
extern const struct file_operations def_chr_fops;
extern const struct file_operations bad_sock_fops;
extern const struct file_operations def_fifo_fops;
extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long);
extern int blkdev_ioctl(struct inode *, struct file *, unsigned, unsigned long);
extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long);
extern int blkdev_get(struct block_device *, mode_t, unsigned);
extern int blkdev_put(struct block_device *);
extern int bd_claim(struct block_device *, void *);
extern void bd_release(struct block_device *);
#ifdef CONFIG_SYSFS
extern int bd_claim_by_disk(struct block_device *, void *, struct gendisk *);
extern void bd_release_from_disk(struct block_device *, struct gendisk *);
#else
#define bd_claim_by_disk(bdev, holder, disk)	bd_claim(bdev, holder)
#define bd_release_from_disk(bdev, disk)	bd_release(bdev)
#endif

/* fs/char_dev.c */
#define CHRDEV_MAJOR_HASH_SIZE	255
extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *);
extern int register_chrdev_region(dev_t, unsigned, const char *);
extern int register_chrdev(unsigned int, const char *,
			   const struct file_operations *);
extern int unregister_chrdev(unsigned int, const char *);
extern void unregister_chrdev_region(dev_t, unsigned);
extern int chrdev_open(struct inode *, struct file *);
extern void chrdev_show(struct seq_file *,off_t);

/* fs/block_dev.c */
#define BLKDEV_MAJOR_HASH_SIZE	255
#define BDEVNAME_SIZE	32	/* Largest string for a blockdev identifier */
extern const char *__bdevname(dev_t, char *buffer);
extern const char *bdevname(struct block_device *bdev, char *buffer);
extern struct block_device *lookup_bdev(const char *);
extern struct block_device *open_bdev_excl(const char *, int, void *);
extern void close_bdev_excl(struct block_device *);
extern void blkdev_show(struct seq_file *,off_t);

extern void init_special_inode(struct inode *, umode_t, dev_t);

/* Invalid inode operations -- fs/bad_inode.c */
extern void make_bad_inode(struct inode *);
extern int is_bad_inode(struct inode *);

extern const struct file_operations read_fifo_fops;
extern const struct file_operations write_fifo_fops;
extern const struct file_operations rdwr_fifo_fops;

extern int fs_may_remount_ro(struct super_block *);

/*
 * return READ, READA, or WRITE
 */
#define bio_rw(bio)		((bio)->bi_rw & (RW_MASK | RWA_MASK))

/*
 * return data direction, READ or WRITE
 */
#define bio_data_dir(bio)	((bio)->bi_rw & 1)

extern int check_disk_change(struct block_device *);
extern int invalidate_inodes(struct super_block *);
extern int __invalidate_device(struct block_device *);
extern int invalidate_partition(struct gendisk *, int);
unsigned long invalidate_mapping_pages(struct address_space *mapping,
					pgoff_t start, pgoff_t end);
unsigned long invalidate_inode_pages(struct address_space *mapping);
static inline void invalidate_remote_inode(struct inode *inode)
{
	if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
	    S_ISLNK(inode->i_mode))
		invalidate_inode_pages(inode->i_mapping);
}
extern int invalidate_inode_pages2(struct address_space *mapping);
extern int invalidate_inode_pages2_range(struct address_space *mapping,
					 pgoff_t start, pgoff_t end);
extern int write_inode_now(struct inode *, int);
extern int filemap_fdatawrite(struct address_space *);
extern int filemap_flush(struct address_space *);
extern int filemap_fdatawait(struct address_space *);
extern int filemap_write_and_wait(struct address_space *mapping);
extern int filemap_write_and_wait_range(struct address_space *mapping,
				        loff_t lstart, loff_t lend);
extern int wait_on_page_writeback_range(struct address_space *mapping,
				pgoff_t start, pgoff_t end);
extern int __filemap_fdatawrite_range(struct address_space *mapping,
				loff_t start, loff_t end, int sync_mode);

extern long do_fsync(struct file *file, int datasync);
extern void sync_supers(void);
extern void sync_filesystems(int wait);
extern void emergency_sync(void);
extern void emergency_remount(void);
extern int do_remount_sb(struct super_block *sb, int flags,
			 void *data, int force);
extern sector_t bmap(struct inode *, sector_t);
extern int notify_change(struct dentry *, struct iattr *);
extern int permission(struct inode *, int, struct nameidata *);
extern int generic_permission(struct inode *, int,
		int (*check_acl)(struct inode *, int));

extern int get_write_access(struct inode *);
extern int deny_write_access(struct file *);
static inline void put_write_access(struct inode * inode)
{
	atomic_dec(&inode->i_writecount);
}
static inline void allow_write_access(struct file *file)
{
	if (file)
		atomic_inc(&file->f_dentry->d_inode->i_writecount);
}
extern int do_pipe(int *);

extern int open_namei(int dfd, const char *, int, int, struct nameidata *);
extern int may_open(struct nameidata *, int, int);

extern int kernel_read(struct file *, unsigned long, char *, unsigned long);
extern struct file * open_exec(const char *);
 
/* fs/dcache.c -- generic fs support functions */
extern int is_subdir(struct dentry *, struct dentry *);
extern ino_t find_inode_number(struct dentry *, struct qstr *);

#include <linux/err.h>

/* needed for stackable file system support */
extern loff_t default_llseek(struct file *file, loff_t offset, int origin);

extern loff_t vfs_llseek(struct file *file, loff_t offset, int origin);

extern void inode_init_once(struct inode *);
extern void iput(struct inode *);
extern struct inode * igrab(struct inode *);
extern ino_t iunique(struct super_block *, ino_t);
extern int inode_needs_sync(struct inode *inode);
extern void generic_delete_inode(struct inode *inode);
extern void generic_drop_inode(struct inode *inode);

extern struct inode *ilookup5_nowait(struct super_block *sb,
		unsigned long hashval, int (*test)(struct inode *, void *),
		void *data);
extern struct inode *ilookup5(struct super_block *sb, unsigned long hashval,
		int (*test)(struct inode *, void *), void *data);
extern struct inode *ilookup(struct super_block *sb, unsigned long ino);

extern struct inode * iget5_locked(struct super_block *, unsigned long, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *);
extern struct inode * iget_locked(struct super_block *, unsigned long);
extern void unlock_new_inode(struct inode *);

static inline struct inode *iget(struct super_block *sb, unsigned long ino)
{
	struct inode *inode = iget_locked(sb, ino);
	
	if (inode && (inode->i_state & I_NEW)) {
		sb->s_op->read_inode(inode);
		unlock_new_inode(inode);
	}

	return inode;
}

extern void __iget(struct inode * inode);
extern void clear_inode(struct inode *);
extern void destroy_inode(struct inode *);
extern struct inode *new_inode(struct super_block *);
extern int remove_suid(struct dentry *);
extern void remove_dquot_ref(struct super_block *, int, struct list_head *);

extern void __insert_inode_hash(struct inode *, unsigned long hashval);
extern void remove_inode_hash(struct inode *);
static inline void insert_inode_hash(struct inode *inode) {
	__insert_inode_hash(inode, inode->i_ino);
}

extern struct file * get_empty_filp(void);
extern void file_move(struct file *f, struct list_head *list);
extern void file_kill(struct file *f);
struct bio;
extern void submit_bio(int, struct bio *);
extern int bdev_read_only(struct block_device *);
extern int set_blocksize(struct block_device *, int);
extern int sb_set_blocksize(struct super_block *, int);
extern int sb_min_blocksize(struct super_block *, int);

extern int generic_file_mmap(struct file *, struct vm_area_struct *);
extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
extern int file_read_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size);
extern int file_send_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size);
extern ssize_t generic_file_read(struct file *, char __user *, size_t, loff_t *);
int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk);
extern ssize_t generic_file_write(struct file *, const char __user *, size_t, loff_t *);
extern ssize_t generic_file_aio_read(struct kiocb *, char __user *, size_t, loff_t);
extern ssize_t __generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t *);
extern ssize_t generic_file_aio_write(struct kiocb *, const char __user *, size_t, loff_t);
extern ssize_t generic_file_aio_write_nolock(struct kiocb *, const struct iovec *,
		unsigned long, loff_t *);
extern ssize_t generic_file_direct_write(struct kiocb *, const struct iovec *,
		unsigned long *, loff_t, loff_t *, size_t, size_t);
extern ssize_t generic_file_buffered_write(struct kiocb *, const struct iovec *,
		unsigned long, loff_t, loff_t *, size_t, ssize_t);
extern ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos);
extern ssize_t do_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos);
ssize_t generic_file_write_nolock(struct file *file, const struct iovec *iov,
				unsigned long nr_segs, loff_t *ppos);
extern ssize_t generic_file_sendfile(struct file *, loff_t *, size_t, read_actor_t, void *);
extern void do_generic_mapping_read(struct address_space *mapping,
				    struct file_ra_state *, struct file *,
				    loff_t *, read_descriptor_t *, read_actor_t);

/* fs/splice.c */
extern ssize_t generic_file_splice_read(struct file *, loff_t *,
		struct pipe_inode_info *, size_t, unsigned int);
extern ssize_t generic_file_splice_write(struct pipe_inode_info *,
		struct file *, loff_t *, size_t, unsigned int);
extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
		struct file *out, loff_t *, size_t len, unsigned int flags);
extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
		size_t len, unsigned int flags);

extern void
file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping);
extern ssize_t generic_file_readv(struct file *filp, const struct iovec *iov, 
	unsigned long nr_segs, loff_t *ppos);
ssize_t generic_file_writev(struct file *filp, const struct iovec *iov, 
			unsigned long nr_segs, loff_t *ppos);
extern loff_t no_llseek(struct file *file, loff_t offset, int origin);
extern loff_t generic_file_llseek(struct file *file, loff_t offset, int origin);
extern loff_t remote_llseek(struct file *file, loff_t offset, int origin);
extern int generic_file_open(struct inode * inode, struct file * filp);
extern int nonseekable_open(struct inode * inode, struct file * filp);

#ifdef CONFIG_FS_XIP
extern ssize_t xip_file_read(struct file *filp, char __user *buf, size_t len,
			     loff_t *ppos);
extern ssize_t xip_file_sendfile(struct file *in_file, loff_t *ppos,
				 size_t count, read_actor_t actor,
				 void *target);
extern int xip_file_mmap(struct file * file, struct vm_area_struct * vma);
extern ssize_t xip_file_write(struct file *filp, const char __user *buf,
			      size_t len, loff_t *ppos);
extern int xip_truncate_page(struct address_space *mapping, loff_t from);
#else
static inline int xip_truncate_page(struct address_space *mapping, loff_t from)
{
	return 0;
}
#endif

static inline void do_generic_file_read(struct file * filp, loff_t *ppos,
					read_descriptor_t * desc,
					read_actor_t actor)
{
	do_generic_mapping_read(filp->f_mapping,
				&filp->f_ra,
				filp,
				ppos,
				desc,
				actor);
}

ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode,
	struct block_device *bdev, const struct iovec *iov, loff_t offset,
	unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io,
	int lock_type);

enum {
	DIO_LOCKING = 1, /* need locking between buffered and direct access */
	DIO_NO_LOCKING,  /* bdev; no locking at all between buffered/direct */
	DIO_OWN_LOCKING, /* filesystem locks buffered and direct internally */
};

static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb,
	struct inode *inode, struct block_device *bdev, const struct iovec *iov,
	loff_t offset, unsigned long nr_segs, get_block_t get_block,
	dio_iodone_t end_io)
{
	return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset,
				nr_segs, get_block, end_io, DIO_LOCKING);
}

static inline ssize_t blockdev_direct_IO_no_locking(int rw, struct kiocb *iocb,
	struct inode *inode, struct block_device *bdev, const struct iovec *iov,
	loff_t offset, unsigned long nr_segs, get_block_t get_block,
	dio_iodone_t end_io)
{
	return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset,
				nr_segs, get_block, end_io, DIO_NO_LOCKING);
}

static inline ssize_t blockdev_direct_IO_own_locking(int rw, struct kiocb *iocb,
	struct inode *inode, struct block_device *bdev, const struct iovec *iov,
	loff_t offset, unsigned long nr_segs, get_block_t get_block,
	dio_iodone_t end_io)
{
	return __blockdev_direct_IO(rw, iocb, inode, bdev, iov, offset,
				nr_segs, get_block, end_io, DIO_OWN_LOCKING);
}

extern const struct file_operations generic_ro_fops;

#define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m))

extern int vfs_readlink(struct dentry *, char __user *, int, const char *);
extern int vfs_follow_link(struct nameidata *, const char *);
extern int page_readlink(struct dentry *, char __user *, int);
extern void *page_follow_link_light(struct dentry *, struct nameidata *);
extern void page_put_link(struct dentry *, struct nameidata *, void *);
extern int __page_symlink(struct inode *inode, const char *symname, int len,
		gfp_t gfp_mask);
extern int page_symlink(struct inode *inode, const char *symname, int len);
extern struct inode_operations page_symlink_inode_operations;
extern int generic_readlink(struct dentry *, char __user *, int);
extern void generic_fillattr(struct inode *, struct kstat *);
extern int vfs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
void inode_add_bytes(struct inode *inode, loff_t bytes);
void inode_sub_bytes(struct inode *inode, loff_t bytes);
loff_t inode_get_bytes(struct inode *inode);
void inode_set_bytes(struct inode *inode, loff_t bytes);

extern int vfs_readdir(struct file *, filldir_t, void *);

extern int vfs_stat(char __user *, struct kstat *);
extern int vfs_lstat(char __user *, struct kstat *);
extern int vfs_stat_fd(int dfd, char __user *, struct kstat *);
extern int vfs_lstat_fd(int dfd, char __user *, struct kstat *);
extern int vfs_fstat(unsigned int, struct kstat *);

extern int vfs_ioctl(struct file *, unsigned int, unsigned int, unsigned long);

extern struct file_system_type *get_fs_type(const char *name);
extern struct super_block *get_super(struct block_device *);
extern struct super_block *user_get_super(dev_t);
extern void drop_super(struct super_block *sb);

extern int dcache_dir_open(struct inode *, struct file *);
extern int dcache_dir_close(struct inode *, struct file *);
extern loff_t dcache_dir_lseek(struct file *, loff_t, int);
extern int dcache_readdir(struct file *, void *, filldir_t);
extern int simple_getattr(struct vfsmount *, struct dentry *, struct kstat *);
extern int simple_statfs(struct dentry *, struct kstatfs *);
extern int simple_link(struct dentry *, struct inode *, struct dentry *);
extern int simple_unlink(struct inode *, struct dentry *);
extern int simple_rmdir(struct inode *, struct dentry *);
extern int simple_rename(struct inode *, struct dentry *, struct inode *, struct dentry *);
extern int simple_sync_file(struct file *, struct dentry *, int);
extern int simple_empty(struct dentry *);
extern int simple_readpage(struct file *file, struct page *page);
extern int simple_prepare_write(struct file *file, struct page *page,
			unsigned offset, unsigned to);
extern int simple_commit_write(struct file *file, struct page *page,
				unsigned offset, unsigned to);

extern struct dentry *simple_lookup(struct inode *, struct dentry *, struct nameidata *);
extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *);
extern const struct file_operations simple_dir_operations;
extern struct inode_operations simple_dir_inode_operations;
struct tree_descr { char *name; const struct file_operations *ops; int mode; };
struct dentry *d_alloc_name(struct dentry *, const char *);
extern int simple_fill_super(struct super_block *, int, struct tree_descr *);
extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count);
extern void simple_release_fs(struct vfsmount **mount, int *count);

extern ssize_t simple_read_from_buffer(void __user *, size_t, loff_t *, const void *, size_t);

#ifdef CONFIG_MIGRATION
extern int buffer_migrate_page(struct address_space *,
				struct page *, struct page *);
#else
#define buffer_migrate_page NULL
#endif

extern int inode_change_ok(struct inode *, struct iattr *);
extern int __must_check inode_setattr(struct inode *, struct iattr *);

extern void file_update_time(struct file *file);

static inline ino_t parent_ino(struct dentry *dentry)
{
	ino_t res;

	spin_lock(&dentry->d_lock);
	res = dentry->d_parent->d_inode->i_ino;
	spin_unlock(&dentry->d_lock);
	return res;
}

/* kernel/fork.c */
extern int unshare_files(void);

/* Transaction based IO helpers */

/*
 * An argresp is stored in an allocated page and holds the
 * size of the argument or response, along with its content
 */
struct simple_transaction_argresp {
	ssize_t size;
	char data[0];
};

#define SIMPLE_TRANSACTION_LIMIT (PAGE_SIZE - sizeof(struct simple_transaction_argresp))

char *simple_transaction_get(struct file *file, const char __user *buf,
				size_t size);
ssize_t simple_transaction_read(struct file *file, char __user *buf,
				size_t size, loff_t *pos);
int simple_transaction_release(struct inode *inode, struct file *file);

static inline void simple_transaction_set(struct file *file, size_t n)
{
	struct simple_transaction_argresp *ar = file->private_data;

	BUG_ON(n > SIMPLE_TRANSACTION_LIMIT);

	/*
	 * The barrier ensures that ar->size will really remain zero until
	 * ar->data is ready for reading.
	 */
	smp_mb();
	ar->size = n;
}

/*
 * simple attribute files
 *
 * These attributes behave similar to those in sysfs:
 *
 * Writing to an attribute immediately sets a value, an open file can be
 * written to multiple times.
 *
 * Reading from an attribute creates a buffer from the value that might get
 * read with multiple read calls. When the attribute has been read
 * completely, no further read calls are possible until the file is opened
 * again.
 *
 * All attributes contain a text representation of a numeric value
 * that are accessed with the get() and set() functions.
 */
#define DEFINE_SIMPLE_ATTRIBUTE(__fops, __get, __set, __fmt)		\
static int __fops ## _open(struct inode *inode, struct file *file)	\
{									\
	__simple_attr_check_format(__fmt, 0ull);			\
	return simple_attr_open(inode, file, __get, __set, __fmt);	\
}									\
static struct file_operations __fops = {				\
	.owner	 = THIS_MODULE,						\
	.open	 = __fops ## _open,					\
	.release = simple_attr_close,					\
	.read	 = simple_attr_read,					\
	.write	 = simple_attr_write,					\
};

static inline void __attribute__((format(printf, 1, 2)))
__simple_attr_check_format(const char *fmt, ...)
{
	/* don't do anything, just let the compiler check the arguments; */
}

int simple_attr_open(struct inode *inode, struct file *file,
		     u64 (*get)(void *), void (*set)(void *, u64),
		     const char *fmt);
int simple_attr_close(struct inode *inode, struct file *file);
ssize_t simple_attr_read(struct file *file, char __user *buf,
			 size_t len, loff_t *ppos);
ssize_t simple_attr_write(struct file *file, const char __user *buf,
			  size_t len, loff_t *ppos);


#ifdef CONFIG_SECURITY
static inline char *alloc_secdata(void)
{
	return (char *)get_zeroed_page(GFP_KERNEL);
}

static inline void free_secdata(void *secdata)
{
	free_page((unsigned long)secdata);
}
#else
static inline char *alloc_secdata(void)
{
	return (char *)1;
}

static inline void free_secdata(void *secdata)
{ }
#endif	/* CONFIG_SECURITY */

#endif /* __KERNEL__ */
#endif /* _LINUX_FS_H */