aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/trace/trace_functions.c
blob: c9a0b7df44ff98b38ce20bba58ac2d6d2e963ad4 (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
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
/*
 * ring buffer based function tracer
 *
 * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
 * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com>
 *
 * Based on code from the latency_tracer, that is:
 *
 *  Copyright (C) 2004-2006 Ingo Molnar
 *  Copyright (C) 2004 William Lee Irwin III
 */
#include <linux/ring_buffer.h>
#include <linux/debugfs.h>
#include <linux/uaccess.h>
#include <linux/ftrace.h>
#include <linux/fs.h>

#include "trace.h"

/* function tracing enabled */
static int			ftrace_function_enabled;

static struct trace_array	*func_trace;

static void tracing_start_function_trace(void);
static void tracing_stop_function_trace(void);

static int function_trace_init(struct trace_array *tr)
{
	func_trace = tr;
	tr->cpu = get_cpu();
	put_cpu();

	tracing_start_cmdline_record();
	tracing_start_function_trace();
	return 0;
}

static void function_trace_reset(struct trace_array *tr)
{
	tracing_stop_function_trace();
	tracing_stop_cmdline_record();
}

static void function_trace_start(struct trace_array *tr)
{
	tracing_reset_online_cpus(tr);
}

static void
function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip)
{
	struct trace_array *tr = func_trace;
	struct trace_array_cpu *data;
	unsigned long flags;
	long disabled;
	int cpu, resched;
	int pc;

	if (unlikely(!ftrace_function_enabled))
		return;

	pc = preempt_count();
	resched = ftrace_preempt_disable();
	local_save_flags(flags);
	cpu = raw_smp_processor_id();
	data = tr->data[cpu];
	disabled = atomic_inc_return(&data->disabled);

	if (likely(disabled == 1))
		trace_function(tr, ip, parent_ip, flags, pc);

	atomic_dec(&data->disabled);
	ftrace_preempt_enable(resched);
}

static void
function_trace_call(unsigned long ip, unsigned long parent_ip)
{
	struct trace_array *tr = func_trace;
	struct trace_array_cpu *data;
	unsigned long flags;
	long disabled;
	int cpu;
	int pc;

	if (unlikely(!ftrace_function_enabled))
		return;

	/*
	 * Need to use raw, since this must be called before the
	 * recursive protection is performed.
	 */
	local_irq_save(flags);
	cpu = raw_smp_processor_id();
	data = tr->data[cpu];
	disabled = atomic_inc_return(&data->disabled);

	if (likely(disabled == 1)) {
		pc = preempt_count();
		trace_function(tr, ip, parent_ip, flags, pc);
	}

	atomic_dec(&data->disabled);
	local_irq_restore(flags);
}

static void
function_stack_trace_call(unsigned long ip, unsigned long parent_ip)
{
	struct trace_array *tr = func_trace;
	struct trace_array_cpu *data;
	unsigned long flags;
	long disabled;
	int cpu;
	int pc;

	if (unlikely(!ftrace_function_enabled))
		return;

	/*
	 * Need to use raw, since this must be called before the
	 * recursive protection is performed.
	 */
	local_irq_save(flags);
	cpu = raw_smp_processor_id();
	data = tr->data[cpu];
	disabled = atomic_inc_return(&data->disabled);

	if (likely(disabled == 1)) {
		pc = preempt_count();
		trace_function(tr, ip, parent_ip, flags, pc);
		/*
		 * skip over 5 funcs:
		 *    __ftrace_trace_stack,
		 *    __trace_stack,
		 *    function_stack_trace_call
		 *    ftrace_list_func
		 *    ftrace_call
		 */
		__trace_stack(tr, flags, 5, pc);
	}

	atomic_dec(&data->disabled);
	local_irq_restore(flags);
}


static struct ftrace_ops trace_ops __read_mostly =
{
	.func = function_trace_call,
};

static struct ftrace_ops trace_stack_ops __read_mostly =
{
	.func = function_stack_trace_call,
};

/* Our two options */
enum {
	TRACE_FUNC_OPT_STACK = 0x1,
};

static struct tracer_opt func_opts[] = {
#ifdef CONFIG_STACKTRACE
	{ TRACER_OPT(func_stack_trace, TRACE_FUNC_OPT_STACK) },
#endif
	{ } /* Always set a last empty entry */
};

static struct tracer_flags func_flags = {
	.val = 0, /* By default: all flags disabled */
	.opts = func_opts
};

static void tracing_start_function_trace(void)
{
	ftrace_function_enabled = 0;

	if (trace_flags & TRACE_ITER_PREEMPTONLY)
		trace_ops.func = function_trace_call_preempt_only;
	else
		trace_ops.func = function_trace_call;

	if (func_flags.val & TRACE_FUNC_OPT_STACK)
		register_ftrace_function(&trace_stack_ops);
	else
		register_ftrace_function(&trace_ops);

	ftrace_function_enabled = 1;
}

static void tracing_stop_function_trace(void)
{
	ftrace_function_enabled = 0;
	/* OK if they are not registered */
	unregister_ftrace_function(&trace_stack_ops);
	unregister_ftrace_function(&trace_ops);
}

static int func_set_flag(u32 old_flags, u32 bit, int set)
{
	if (bit == TRACE_FUNC_OPT_STACK) {
		/* do nothing if already set */
		if (!!set == !!(func_flags.val & TRACE_FUNC_OPT_STACK))
			return 0;

		if (set) {
			unregister_ftrace_function(&trace_ops);
			register_ftrace_function(&trace_stack_ops);
		} else {
			unregister_ftrace_function(&trace_stack_ops);
			register_ftrace_function(&trace_ops);
		}

		return 0;
	}

	return -EINVAL;
}

static struct tracer function_trace __read_mostly =
{
	.name		= "function",
	.init		= function_trace_init,
	.reset		= function_trace_reset,
	.start		= function_trace_start,
	.wait_pipe	= poll_wait_pipe,
	.flags		= &func_flags,
	.set_flag	= func_set_flag,
#ifdef CONFIG_FTRACE_SELFTEST
	.selftest	= trace_selftest_startup_function,
#endif
};

#ifdef CONFIG_DYNAMIC_FTRACE
static void
ftrace_traceon(unsigned long ip, unsigned long parent_ip, void **data)
{
	long *count = (long *)data;

	if (tracing_is_on())
		return;

	if (!*count)
		return;

	if (*count != -1)
		(*count)--;

	tracing_on();
}

static void
ftrace_traceoff(unsigned long ip, unsigned long parent_ip, void **data)
{
	long *count = (long *)data;

	if (!tracing_is_on())
		return;

	if (!*count)
		return;

	if (*count != -1)
		(*count)--;

	tracing_off();
}

static int
ftrace_trace_onoff_print(struct seq_file *m, unsigned long ip,
			 struct ftrace_probe_ops *ops, void *data);

static struct ftrace_probe_ops traceon_probe_ops = {
	.func			= ftrace_traceon,
	.print			= ftrace_trace_onoff_print,
};

static struct ftrace_probe_ops traceoff_probe_ops = {
	.func			= ftrace_traceoff,
	.print			= ftrace_trace_onoff_print,
};

static int
ftrace_trace_onoff_print(struct seq_file *m, unsigned long ip,
			 struct ftrace_probe_ops *ops, void *data)
{
	char str[KSYM_SYMBOL_LEN];
	long count = (long)data;

	kallsyms_lookup(ip, NULL, NULL, NULL, str);
	seq_printf(m, "%s:", str);

	if (ops == &traceon_probe_ops)
		seq_printf(m, "traceon");
	else
		seq_printf(m, "traceoff");

	if (count == -1)
		seq_printf(m, ":unlimited\n");
	else
		seq_printf(m, ":count=%ld", count);
	seq_putc(m, '\n');

	return 0;
}

static int
ftrace_trace_onoff_unreg(char *glob, char *cmd, char *param)
{
	struct ftrace_probe_ops *ops;

	/* we register both traceon and traceoff to this callback */
	if (strcmp(cmd, "traceon") == 0)
		ops = &traceon_probe_ops;
	else
		ops = &traceoff_probe_ops;

	unregister_ftrace_function_probe_func(glob, ops);

	return 0;
}

static int
ftrace_trace_onoff_callback(char *glob, char *cmd, char *param, int enable)
{
	struct ftrace_probe_ops *ops;
	void *count = (void *)-1;
	char *number;
	int ret;

	/* hash funcs only work with set_ftrace_filter */
	if (!enable)
		return -EINVAL;

	if (glob[0] == '!')
		return ftrace_trace_onoff_unreg(glob+1, cmd, param);

	/* we register both traceon and traceoff to this callback */
	if (strcmp(cmd, "traceon") == 0)
		ops = &traceon_probe_ops;
	else
		ops = &traceoff_probe_ops;

	if (!param)
		goto out_reg;

	number = strsep(&param, ":");

	if (!strlen(number))
		goto out_reg;

	/*
	 * We use the callback data field (which is a pointer)
	 * as our counter.
	 */
	ret = strict_strtoul(number, 0, (unsigned long *)&count);
	if (ret)
		return ret;

 out_reg:
	ret = register_ftrace_function_probe(glob, ops, count);

	return ret;
}

static struct ftrace_func_command ftrace_traceon_cmd = {
	.name			= "traceon",
	.func			= ftrace_trace_onoff_callback,
};

static struct ftrace_func_command ftrace_traceoff_cmd = {
	.name			= "traceoff",
	.func			= ftrace_trace_onoff_callback,
};

static int __init init_func_cmd_traceon(void)
{
	int ret;

	ret = register_ftrace_command(&ftrace_traceoff_cmd);
	if (ret)
		return ret;

	ret = register_ftrace_command(&ftrace_traceon_cmd);
	if (ret)
		unregister_ftrace_command(&ftrace_traceoff_cmd);
	return ret;
}
#else
static inline int init_func_cmd_traceon(void)
{
	return 0;
}
#endif /* CONFIG_DYNAMIC_FTRACE */

static __init int init_function_trace(void)
{
	init_func_cmd_traceon();
	return register_tracer(&function_trace);
}
device_initcall(init_function_trace);

1399'>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
/*
 * NET4:	Implementation of BSD Unix domain sockets.
 *
 * Authors:	Alan Cox, <alan@lxorguk.ukuu.org.uk>
 *
 *		This program 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.
 *
 * Fixes:
 *		Linus Torvalds	:	Assorted bug cures.
 *		Niibe Yutaka	:	async I/O support.
 *		Carsten Paeth	:	PF_UNIX check, address fixes.
 *		Alan Cox	:	Limit size of allocated blocks.
 *		Alan Cox	:	Fixed the stupid socketpair bug.
 *		Alan Cox	:	BSD compatibility fine tuning.
 *		Alan Cox	:	Fixed a bug in connect when interrupted.
 *		Alan Cox	:	Sorted out a proper draft version of
 *					file descriptor passing hacked up from
 *					Mike Shaver's work.
 *		Marty Leisner	:	Fixes to fd passing
 *		Nick Nevin	:	recvmsg bugfix.
 *		Alan Cox	:	Started proper garbage collector
 *		Heiko EiBfeldt	:	Missing verify_area check
 *		Alan Cox	:	Started POSIXisms
 *		Andreas Schwab	:	Replace inode by dentry for proper
 *					reference counting
 *		Kirk Petersen	:	Made this a module
 *	    Christoph Rohland	:	Elegant non-blocking accept/connect algorithm.
 *					Lots of bug fixes.
 *	     Alexey Kuznetosv	:	Repaired (I hope) bugs introduces
 *					by above two patches.
 *	     Andrea Arcangeli	:	If possible we block in connect(2)
 *					if the max backlog of the listen socket
 *					is been reached. This won't break
 *					old apps and it will avoid huge amount
 *					of socks hashed (this for unix_gc()
 *					performances reasons).
 *					Security fix that limits the max
 *					number of socks to 2*max_files and
 *					the number of skb queueable in the
 *					dgram receiver.
 *		Artur Skawina   :	Hash function optimizations
 *	     Alexey Kuznetsov   :	Full scale SMP. Lot of bugs are introduced 8)
 *	      Malcolm Beattie   :	Set peercred for socketpair
 *	     Michal Ostrowski   :       Module initialization cleanup.
 *	     Arnaldo C. Melo	:	Remove MOD_{INC,DEC}_USE_COUNT,
 *	     				the core infrastructure is doing that
 *	     				for all net proto families now (2.5.69+)
 *
 *
 * Known differences from reference BSD that was tested:
 *
 *	[TO FIX]
 *	ECONNREFUSED is not returned from one end of a connected() socket to the
 *		other the moment one end closes.
 *	fstat() doesn't return st_dev=0, and give the blksize as high water mark
 *		and a fake inode identifier (nor the BSD first socket fstat twice bug).
 *	[NOT TO FIX]
 *	accept() returns a path name even if the connecting socket has closed
 *		in the meantime (BSD loses the path and gives up).
 *	accept() returns 0 length path for an unbound connector. BSD returns 16
 *		and a null first byte in the path (but not for gethost/peername - BSD bug ??)
 *	socketpair(...SOCK_RAW..) doesn't panic the kernel.
 *	BSD af_unix apparently has connect forgetting to block properly.
 *		(need to check this with the POSIX spec in detail)
 *
 * Differences from 2.0.0-11-... (ANK)
 *	Bug fixes and improvements.
 *		- client shutdown killed server socket.
 *		- removed all useless cli/sti pairs.
 *
 *	Semantic changes/extensions.
 *		- generic control message passing.
 *		- SCM_CREDENTIALS control message.
 *		- "Abstract" (not FS based) socket bindings.
 *		  Abstract names are sequences of bytes (not zero terminated)
 *		  started by 0, so that this name space does not intersect
 *		  with BSD names.
 */

#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/stat.h>
#include <linux/dcache.h>
#include <linux/namei.h>
#include <linux/socket.h>
#include <linux/un.h>
#include <linux/fcntl.h>
#include <linux/termios.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/in.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <asm/uaccess.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <net/net_namespace.h>
#include <net/sock.h>
#include <net/tcp_states.h>
#include <net/af_unix.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <net/scm.h>
#include <linux/init.h>
#include <linux/poll.h>
#include <linux/rtnetlink.h>
#include <linux/mount.h>
#include <net/checksum.h>
#include <linux/security.h>

static struct hlist_head unix_socket_table[UNIX_HASH_SIZE + 1];
static DEFINE_SPINLOCK(unix_table_lock);
static atomic_t unix_nr_socks = ATOMIC_INIT(0);

#define unix_sockets_unbound	(&unix_socket_table[UNIX_HASH_SIZE])

#define UNIX_ABSTRACT(sk)	(unix_sk(sk)->addr->hash != UNIX_HASH_SIZE)

#ifdef CONFIG_SECURITY_NETWORK
static void unix_get_secdata(struct scm_cookie *scm, struct sk_buff *skb)
{
	memcpy(UNIXSID(skb), &scm->secid, sizeof(u32));
}

static inline void unix_set_secdata(struct scm_cookie *scm, struct sk_buff *skb)
{
	scm->secid = *UNIXSID(skb);
}
#else
static inline void unix_get_secdata(struct scm_cookie *scm, struct sk_buff *skb)
{ }

static inline void unix_set_secdata(struct scm_cookie *scm, struct sk_buff *skb)
{ }
#endif /* CONFIG_SECURITY_NETWORK */

/*
 *  SMP locking strategy:
 *    hash table is protected with spinlock unix_table_lock
 *    each socket state is protected by separate spin lock.
 */

static inline unsigned unix_hash_fold(__wsum n)
{
	unsigned hash = (__force unsigned)n;
	hash ^= hash>>16;
	hash ^= hash>>8;
	return hash&(UNIX_HASH_SIZE-1);
}

#define unix_peer(sk) (unix_sk(sk)->peer)

static inline int unix_our_peer(struct sock *sk, struct sock *osk)
{
	return unix_peer(osk) == sk;
}

static inline int unix_may_send(struct sock *sk, struct sock *osk)
{
	return unix_peer(osk) == NULL || unix_our_peer(sk, osk);
}

static inline int unix_recvq_full(struct sock const *sk)
{
	return skb_queue_len(&sk->sk_receive_queue) > sk->sk_max_ack_backlog;
}

static struct sock *unix_peer_get(struct sock *s)
{
	struct sock *peer;

	unix_state_lock(s);
	peer = unix_peer(s);
	if (peer)
		sock_hold(peer);
	unix_state_unlock(s);
	return peer;
}

static inline void unix_release_addr(struct unix_address *addr)
{
	if (atomic_dec_and_test(&addr->refcnt))
		kfree(addr);
}

/*
 *	Check unix socket name:
 *		- should be not zero length.
 *	        - if started by not zero, should be NULL terminated (FS object)
 *		- if started by zero, it is abstract name.
 */

static int unix_mkname(struct sockaddr_un *sunaddr, int len, unsigned *hashp)
{
	if (len <= sizeof(short) || len > sizeof(*sunaddr))
		return -EINVAL;
	if (!sunaddr || sunaddr->sun_family != AF_UNIX)
		return -EINVAL;
	if (sunaddr->sun_path[0]) {
		/*
		 * This may look like an off by one error but it is a bit more
		 * subtle. 108 is the longest valid AF_UNIX path for a binding.
		 * sun_path[108] doesnt as such exist.  However in kernel space
		 * we are guaranteed that it is a valid memory location in our
		 * kernel address buffer.
		 */
		((char *)sunaddr)[len] = 0;
		len = strlen(sunaddr->sun_path)+1+sizeof(short);
		return len;
	}

	*hashp = unix_hash_fold(csum_partial(sunaddr, len, 0));
	return len;
}

static void __unix_remove_socket(struct sock *sk)
{
	sk_del_node_init(sk);
}

static void __unix_insert_socket(struct hlist_head *list, struct sock *sk)
{
	WARN_ON(!sk_unhashed(sk));
	sk_add_node(sk, list);
}

static inline void unix_remove_socket(struct sock *sk)
{
	spin_lock(&unix_table_lock);
	__unix_remove_socket(sk);
	spin_unlock(&unix_table_lock);
}

static inline void unix_insert_socket(struct hlist_head *list, struct sock *sk)
{
	spin_lock(&unix_table_lock);
	__unix_insert_socket(list, sk);
	spin_unlock(&unix_table_lock);
}

static struct sock *__unix_find_socket_byname(struct net *net,
					      struct sockaddr_un *sunname,
					      int len, int type, unsigned hash)
{
	struct sock *s;
	struct hlist_node *node;

	sk_for_each(s, node, &unix_socket_table[hash ^ type]) {
		struct unix_sock *u = unix_sk(s);

		if (!net_eq(sock_net(s), net))
			continue;

		if (u->addr->len == len &&
		    !memcmp(u->addr->name, sunname, len))
			goto found;
	}
	s = NULL;
found:
	return s;
}

static inline struct sock *unix_find_socket_byname(struct net *net,
						   struct sockaddr_un *sunname,
						   int len, int type,
						   unsigned hash)
{
	struct sock *s;

	spin_lock(&unix_table_lock);
	s = __unix_find_socket_byname(net, sunname, len, type, hash);
	if (s)
		sock_hold(s);
	spin_unlock(&unix_table_lock);
	return s;
}

static struct sock *unix_find_socket_byinode(struct inode *i)
{
	struct sock *s;
	struct hlist_node *node;

	spin_lock(&unix_table_lock);
	sk_for_each(s, node,
		    &unix_socket_table[i->i_ino & (UNIX_HASH_SIZE - 1)]) {
		struct dentry *dentry = unix_sk(s)->dentry;

		if (dentry && dentry->d_inode == i) {
			sock_hold(s);
			goto found;
		}
	}
	s = NULL;
found:
	spin_unlock(&unix_table_lock);
	return s;
}

static inline int unix_writable(struct sock *sk)
{
	return (atomic_read(&sk->sk_wmem_alloc) << 2) <= sk->sk_sndbuf;
}

static void unix_write_space(struct sock *sk)
{
	struct socket_wq *wq;

	rcu_read_lock();
	if (unix_writable(sk)) {
		wq = rcu_dereference(sk->sk_wq);
		if (wq_has_sleeper(wq))
			wake_up_interruptible_sync(&wq->wait);
		sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
	}
	rcu_read_unlock();
}

/* When dgram socket disconnects (or changes its peer), we clear its receive
 * queue of packets arrived from previous peer. First, it allows to do
 * flow control based only on wmem_alloc; second, sk connected to peer
 * may receive messages only from that peer. */
static void unix_dgram_disconnected(struct sock *sk, struct sock *other)
{
	if (!skb_queue_empty(&sk->sk_receive_queue)) {
		skb_queue_purge(&sk->sk_receive_queue);
		wake_up_interruptible_all(&unix_sk(sk)->peer_wait);

		/* If one link of bidirectional dgram pipe is disconnected,
		 * we signal error. Messages are lost. Do not make this,
		 * when peer was not connected to us.
		 */
		if (!sock_flag(other, SOCK_DEAD) && unix_peer(other) == sk) {
			other->sk_err = ECONNRESET;
			other->sk_error_report(other);
		}
	}
}

static void unix_sock_destructor(struct sock *sk)
{
	struct unix_sock *u = unix_sk(sk);

	skb_queue_purge(&sk->sk_receive_queue);

	WARN_ON(atomic_read(&sk->sk_wmem_alloc));
	WARN_ON(!sk_unhashed(sk));
	WARN_ON(sk->sk_socket);
	if (!sock_flag(sk, SOCK_DEAD)) {
		printk(KERN_INFO "Attempt to release alive unix socket: %p\n", sk);
		return;
	}

	if (u->addr)
		unix_release_addr(u->addr);

	atomic_dec(&unix_nr_socks);
	local_bh_disable();
	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
	local_bh_enable();
#ifdef UNIX_REFCNT_DEBUG
	printk(KERN_DEBUG "UNIX %p is destroyed, %d are still alive.\n", sk,
		atomic_read(&unix_nr_socks));
#endif
}

static int unix_release_sock(struct sock *sk, int embrion)
{
	struct unix_sock *u = unix_sk(sk);
	struct dentry *dentry;
	struct vfsmount *mnt;
	struct sock *skpair;
	struct sk_buff *skb;
	int state;

	unix_remove_socket(sk);

	/* Clear state */
	unix_state_lock(sk);
	sock_orphan(sk);
	sk->sk_shutdown = SHUTDOWN_MASK;
	dentry	     = u->dentry;
	u->dentry    = NULL;
	mnt	     = u->mnt;
	u->mnt	     = NULL;
	state = sk->sk_state;
	sk->sk_state = TCP_CLOSE;
	unix_state_unlock(sk);

	wake_up_interruptible_all(&u->peer_wait);

	skpair = unix_peer(sk);

	if (skpair != NULL) {
		if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) {
			unix_state_lock(skpair);
			/* No more writes */
			skpair->sk_shutdown = SHUTDOWN_MASK;
			if (!skb_queue_empty(&sk->sk_receive_queue) || embrion)
				skpair->sk_err = ECONNRESET;
			unix_state_unlock(skpair);
			skpair->sk_state_change(skpair);
			sk_wake_async(skpair, SOCK_WAKE_WAITD, POLL_HUP);
		}
		sock_put(skpair); /* It may now die */
		unix_peer(sk) = NULL;
	}

	/* Try to flush out this socket. Throw out buffers at least */

	while ((skb = skb_dequeue(&sk->sk_receive_queue)) != NULL) {
		if (state == TCP_LISTEN)
			unix_release_sock(skb->sk, 1);
		/* passed fds are erased in the kfree_skb hook	      */
		kfree_skb(skb);
	}

	if (dentry) {
		dput(dentry);
		mntput(mnt);
	}

	sock_put(sk);

	/* ---- Socket is dead now and most probably destroyed ---- */

	/*
	 * Fixme: BSD difference: In BSD all sockets connected to use get
	 *	  ECONNRESET and we die on the spot. In Linux we behave
	 *	  like files and pipes do and wait for the last
	 *	  dereference.
	 *
	 * Can't we simply set sock->err?
	 *
	 *	  What the above comment does talk about? --ANK(980817)
	 */

	if (unix_tot_inflight)
		unix_gc();		/* Garbage collect fds */

	return 0;
}

static void init_peercred(struct sock *sk)
{
	put_pid(sk->sk_peer_pid);
	if (sk->sk_peer_cred)
		put_cred(sk->sk_peer_cred);
	sk->sk_peer_pid  = get_pid(task_tgid(current));
	sk->sk_peer_cred = get_current_cred();
}

static void copy_peercred(struct sock *sk, struct sock *peersk)
{
	put_pid(sk->sk_peer_pid);
	if (sk->sk_peer_cred)
		put_cred(sk->sk_peer_cred);
	sk->sk_peer_pid  = get_pid(peersk->sk_peer_pid);
	sk->sk_peer_cred = get_cred(peersk->sk_peer_cred);
}

static int unix_listen(struct socket *sock, int backlog)
{
	int err;
	struct sock *sk = sock->sk;
	struct unix_sock *u = unix_sk(sk);
	struct pid *old_pid = NULL;
	const struct cred *old_cred = NULL;

	err = -EOPNOTSUPP;
	if (sock->type != SOCK_STREAM && sock->type != SOCK_SEQPACKET)
		goto out;	/* Only stream/seqpacket sockets accept */
	err = -EINVAL;
	if (!u->addr)
		goto out;	/* No listens on an unbound socket */
	unix_state_lock(sk);
	if (sk->sk_state != TCP_CLOSE && sk->sk_state != TCP_LISTEN)
		goto out_unlock;
	if (backlog > sk->sk_max_ack_backlog)
		wake_up_interruptible_all(&u->peer_wait);
	sk->sk_max_ack_backlog	= backlog;
	sk->sk_state		= TCP_LISTEN;
	/* set credentials so connect can copy them */
	init_peercred(sk);
	err = 0;

out_unlock:
	unix_state_unlock(sk);
	put_pid(old_pid);
	if (old_cred)
		put_cred(old_cred);
out:
	return err;
}

static int unix_release(struct socket *);
static int unix_bind(struct socket *, struct sockaddr *, int);
static int unix_stream_connect(struct socket *, struct sockaddr *,
			       int addr_len, int flags);
static int unix_socketpair(struct socket *, struct socket *);
static int unix_accept(struct socket *, struct socket *, int);
static int unix_getname(struct socket *, struct sockaddr *, int *, int);
static unsigned int unix_poll(struct file *, struct socket *, poll_table *);
static unsigned int unix_dgram_poll(struct file *, struct socket *,
				    poll_table *);
static int unix_ioctl(struct socket *, unsigned int, unsigned long);
static int unix_shutdown(struct socket *, int);
static int unix_stream_sendmsg(struct kiocb *, struct socket *,
			       struct msghdr *, size_t);
static int unix_stream_recvmsg(struct kiocb *, struct socket *,
			       struct msghdr *, size_t, int);
static int unix_dgram_sendmsg(struct kiocb *, struct socket *,
			      struct msghdr *, size_t);
static int unix_dgram_recvmsg(struct kiocb *, struct socket *,
			      struct msghdr *, size_t, int);
static int unix_dgram_connect(struct socket *, struct sockaddr *,
			      int, int);
static int unix_seqpacket_sendmsg(struct kiocb *, struct socket *,
				  struct msghdr *, size_t);

static const struct proto_ops unix_stream_ops = {
	.family =	PF_UNIX,
	.owner =	THIS_MODULE,
	.release =	unix_release,
	.bind =		unix_bind,
	.connect =	unix_stream_connect,
	.socketpair =	unix_socketpair,
	.accept =	unix_accept,
	.getname =	unix_getname,
	.poll =		unix_poll,
	.ioctl =	unix_ioctl,
	.listen =	unix_listen,
	.shutdown =	unix_shutdown,
	.setsockopt =	sock_no_setsockopt,
	.getsockopt =	sock_no_getsockopt,
	.sendmsg =	unix_stream_sendmsg,
	.recvmsg =	unix_stream_recvmsg,
	.mmap =		sock_no_mmap,
	.sendpage =	sock_no_sendpage,
};

static const struct proto_ops unix_dgram_ops = {
	.family =	PF_UNIX,
	.owner =	THIS_MODULE,
	.release =	unix_release,
	.bind =		unix_bind,
	.connect =	unix_dgram_connect,
	.socketpair =	unix_socketpair,
	.accept =	sock_no_accept,
	.getname =	unix_getname,
	.poll =		unix_dgram_poll,
	.ioctl =	unix_ioctl,
	.listen =	sock_no_listen,
	.shutdown =	unix_shutdown,
	.setsockopt =	sock_no_setsockopt,
	.getsockopt =	sock_no_getsockopt,
	.sendmsg =	unix_dgram_sendmsg,
	.recvmsg =	unix_dgram_recvmsg,
	.mmap =		sock_no_mmap,
	.sendpage =	sock_no_sendpage,
};

static const struct proto_ops unix_seqpacket_ops = {
	.family =	PF_UNIX,
	.owner =	THIS_MODULE,
	.release =	unix_release,
	.bind =		unix_bind,
	.connect =	unix_stream_connect,
	.socketpair =	unix_socketpair,
	.accept =	unix_accept,
	.getname =	unix_getname,
	.poll =		unix_dgram_poll,
	.ioctl =	unix_ioctl,
	.listen =	unix_listen,
	.shutdown =	unix_shutdown,
	.setsockopt =	sock_no_setsockopt,
	.getsockopt =	sock_no_getsockopt,
	.sendmsg =	unix_seqpacket_sendmsg,
	.recvmsg =	unix_dgram_recvmsg,
	.mmap =		sock_no_mmap,
	.sendpage =	sock_no_sendpage,
};

static struct proto unix_proto = {
	.name			= "UNIX",
	.owner			= THIS_MODULE,
	.obj_size		= sizeof(struct unix_sock),
};

/*
 * AF_UNIX sockets do not interact with hardware, hence they
 * dont trigger interrupts - so it's safe for them to have
 * bh-unsafe locking for their sk_receive_queue.lock. Split off
 * this special lock-class by reinitializing the spinlock key:
 */
static struct lock_class_key af_unix_sk_receive_queue_lock_key;

static struct sock *unix_create1(struct net *net, struct socket *sock)
{
	struct sock *sk = NULL;
	struct unix_sock *u;

	atomic_inc(&unix_nr_socks);
	if (atomic_read(&unix_nr_socks) > 2 * get_max_files())
		goto out;

	sk = sk_alloc(net, PF_UNIX, GFP_KERNEL, &unix_proto);
	if (!sk)
		goto out;

	sock_init_data(sock, sk);
	lockdep_set_class(&sk->sk_receive_queue.lock,
				&af_unix_sk_receive_queue_lock_key);

	sk->sk_write_space	= unix_write_space;
	sk->sk_max_ack_backlog	= net->unx.sysctl_max_dgram_qlen;
	sk->sk_destruct		= unix_sock_destructor;
	u	  = unix_sk(sk);
	u->dentry = NULL;
	u->mnt	  = NULL;
	spin_lock_init(&u->lock);
	atomic_long_set(&u->inflight, 0);
	INIT_LIST_HEAD(&u->link);
	mutex_init(&u->readlock); /* single task reading lock */
	init_waitqueue_head(&u->peer_wait);
	unix_insert_socket(unix_sockets_unbound, sk);
out:
	if (sk == NULL)
		atomic_dec(&unix_nr_socks);
	else {
		local_bh_disable();
		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
		local_bh_enable();
	}
	return sk;
}

static int unix_create(struct net *net, struct socket *sock, int protocol,
		       int kern)
{
	if (protocol && protocol != PF_UNIX)
		return -EPROTONOSUPPORT;

	sock->state = SS_UNCONNECTED;

	switch (sock->type) {
	case SOCK_STREAM:
		sock->ops = &unix_stream_ops;
		break;
		/*
		 *	Believe it or not BSD has AF_UNIX, SOCK_RAW though
		 *	nothing uses it.
		 */
	case SOCK_RAW:
		sock->type = SOCK_DGRAM;
	case SOCK_DGRAM:
		sock->ops = &unix_dgram_ops;
		break;
	case SOCK_SEQPACKET:
		sock->ops = &unix_seqpacket_ops;
		break;
	default:
		return -ESOCKTNOSUPPORT;
	}

	return unix_create1(net, sock) ? 0 : -ENOMEM;
}

static int unix_release(struct socket *sock)
{
	struct sock *sk = sock->sk;

	if (!sk)
		return 0;

	sock->sk = NULL;

	return unix_release_sock(sk, 0);
}

static int unix_autobind(struct socket *sock)
{
	struct sock *sk = sock->sk;
	struct net *net = sock_net(sk);
	struct unix_sock *u = unix_sk(sk);
	static u32 ordernum = 1;
	struct unix_address *addr;
	int err;
	unsigned int retries = 0;

	mutex_lock(&u->readlock);

	err = 0;
	if (u->addr)
		goto out;

	err = -ENOMEM;
	addr = kzalloc(sizeof(*addr) + sizeof(short) + 16, GFP_KERNEL);
	if (!addr)
		goto out;

	addr->name->sun_family = AF_UNIX;
	atomic_set(&addr->refcnt, 1);

retry:
	addr->len = sprintf(addr->name->sun_path+1, "%05x", ordernum) + 1 + sizeof(short);
	addr->hash = unix_hash_fold(csum_partial(addr->name, addr->len, 0));

	spin_lock(&unix_table_lock);
	ordernum = (ordernum+1)&0xFFFFF;

	if (__unix_find_socket_byname(net, addr->name, addr->len, sock->type,
				      addr->hash)) {
		spin_unlock(&unix_table_lock);
		/*
		 * __unix_find_socket_byname() may take long time if many names
		 * are already in use.
		 */
		cond_resched();
		/* Give up if all names seems to be in use. */
		if (retries++ == 0xFFFFF) {
			err = -ENOSPC;
			kfree(addr);
			goto out;
		}
		goto retry;
	}
	addr->hash ^= sk->sk_type;

	__unix_remove_socket(sk);
	u->addr = addr;
	__unix_insert_socket(&unix_socket_table[addr->hash], sk);
	spin_unlock(&unix_table_lock);
	err = 0;

out:	mutex_unlock(&u->readlock);
	return err;
}

static struct sock *unix_find_other(struct net *net,
				    struct sockaddr_un *sunname, int len,
				    int type, unsigned hash, int *error)
{
	struct sock *u;
	struct path path;
	int err = 0;

	if (sunname->sun_path[0]) {
		struct inode *inode;
		err = kern_path(sunname->sun_path, LOOKUP_FOLLOW, &path);
		if (err)
			goto fail;
		inode = path.dentry->d_inode;
		err = inode_permission(inode, MAY_WRITE);
		if (err)
			goto put_fail;

		err = -ECONNREFUSED;
		if (!S_ISSOCK(inode->i_mode))
			goto put_fail;
		u = unix_find_socket_byinode(inode);
		if (!u)
			goto put_fail;

		if (u->sk_type == type)
			touch_atime(path.mnt, path.dentry);

		path_put(&path);

		err = -EPROTOTYPE;
		if (u->sk_type != type) {
			sock_put(u);
			goto fail;
		}
	} else {
		err = -ECONNREFUSED;
		u = unix_find_socket_byname(net, sunname, len, type, hash);
		if (u) {
			struct dentry *dentry;
			dentry = unix_sk(u)->dentry;
			if (dentry)
				touch_atime(unix_sk(u)->mnt, dentry);
		} else
			goto fail;
	}
	return u;

put_fail:
	path_put(&path);
fail:
	*error = err;
	return NULL;
}


static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
{
	struct sock *sk = sock->sk;
	struct net *net = sock_net(sk);
	struct unix_sock *u = unix_sk(sk);
	struct sockaddr_un *sunaddr = (struct sockaddr_un *)uaddr;
	struct dentry *dentry = NULL;
	struct nameidata nd;
	int err;
	unsigned hash;
	struct unix_address *addr;
	struct hlist_head *list;

	err = -EINVAL;
	if (sunaddr->sun_family != AF_UNIX)
		goto out;

	if (addr_len == sizeof(short)) {
		err = unix_autobind(sock);
		goto out;
	}

	err = unix_mkname(sunaddr, addr_len, &hash);
	if (err < 0)
		goto out;
	addr_len = err;

	mutex_lock(&u->readlock);

	err = -EINVAL;
	if (u->addr)
		goto out_up;

	err = -ENOMEM;
	addr = kmalloc(sizeof(*addr)+addr_len, GFP_KERNEL);
	if (!addr)
		goto out_up;

	memcpy(addr->name, sunaddr, addr_len);
	addr->len = addr_len;
	addr->hash = hash ^ sk->sk_type;
	atomic_set(&addr->refcnt, 1);

	if (sunaddr->sun_path[0]) {
		unsigned int mode;
		err = 0;
		/*
		 * Get the parent directory, calculate the hash for last
		 * component.
		 */
		err = path_lookup(sunaddr->sun_path, LOOKUP_PARENT, &nd);
		if (err)
			goto out_mknod_parent;

		dentry = lookup_create(&nd, 0);
		err = PTR_ERR(dentry);
		if (IS_ERR(dentry))
			goto out_mknod_unlock;

		/*
		 * All right, let's create it.
		 */
		mode = S_IFSOCK |
		       (SOCK_INODE(sock)->i_mode & ~current_umask());
		err = mnt_want_write(nd.path.mnt);
		if (err)
			goto out_mknod_dput;
		err = security_path_mknod(&nd.path, dentry, mode, 0);
		if (err)
			goto out_mknod_drop_write;
		err = vfs_mknod(nd.path.dentry->d_inode, dentry, mode, 0);
out_mknod_drop_write:
		mnt_drop_write(nd.path.mnt);
		if (err)
			goto out_mknod_dput;
		mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
		dput(nd.path.dentry);
		nd.path.dentry = dentry;

		addr->hash = UNIX_HASH_SIZE;
	}

	spin_lock(&unix_table_lock);

	if (!sunaddr->sun_path[0]) {
		err = -EADDRINUSE;
		if (__unix_find_socket_byname(net, sunaddr, addr_len,
					      sk->sk_type, hash)) {
			unix_release_addr(addr);
			goto out_unlock;
		}

		list = &unix_socket_table[addr->hash];
	} else {
		list = &unix_socket_table[dentry->d_inode->i_ino & (UNIX_HASH_SIZE-1)];
		u->dentry = nd.path.dentry;
		u->mnt    = nd.path.mnt;
	}

	err = 0;
	__unix_remove_socket(sk);
	u->addr = addr;
	__unix_insert_socket(list, sk);

out_unlock:
	spin_unlock(&unix_table_lock);
out_up:
	mutex_unlock(&u->readlock);
out:
	return err;

out_mknod_dput:
	dput(dentry);
out_mknod_unlock:
	mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
	path_put(&nd.path);
out_mknod_parent:
	if (err == -EEXIST)
		err = -EADDRINUSE;
	unix_release_addr(addr);
	goto out_up;
}

static void unix_state_double_lock(struct sock *sk1, struct sock *sk2)
{
	if (unlikely(sk1 == sk2) || !sk2) {
		unix_state_lock(sk1);
		return;
	}
	if (sk1 < sk2) {
		unix_state_lock(sk1);
		unix_state_lock_nested(sk2);
	} else {
		unix_state_lock(sk2);
		unix_state_lock_nested(sk1);
	}
}

static void unix_state_double_unlock(struct sock *sk1, struct sock *sk2)
{
	if (unlikely(sk1 == sk2) || !sk2) {
		unix_state_unlock(sk1);
		return;
	}
	unix_state_unlock(sk1);
	unix_state_unlock(sk2);
}

static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr,
			      int alen, int flags)
{
	struct sock *sk = sock->sk;
	struct net *net = sock_net(sk);
	struct sockaddr_un *sunaddr = (struct sockaddr_un *)addr;
	struct sock *other;
	unsigned hash;
	int err;

	if (addr->sa_family != AF_UNSPEC) {
		err = unix_mkname(sunaddr, alen, &hash);
		if (err < 0)
			goto out;
		alen = err;

		if (test_bit(SOCK_PASSCRED, &sock->flags) &&
		    !unix_sk(sk)->addr && (err = unix_autobind(sock)) != 0)
			goto out;

restart:
		other = unix_find_other(net, sunaddr, alen, sock->type, hash, &err);
		if (!other)
			goto out;

		unix_state_double_lock(sk, other);

		/* Apparently VFS overslept socket death. Retry. */
		if (sock_flag(other, SOCK_DEAD)) {
			unix_state_double_unlock(sk, other);
			sock_put(other);
			goto restart;
		}

		err = -EPERM;
		if (!unix_may_send(sk, other))
			goto out_unlock;

		err = security_unix_may_send(sk->sk_socket, other->sk_socket);
		if (err)
			goto out_unlock;

	} else {
		/*
		 *	1003.1g breaking connected state with AF_UNSPEC
		 */
		other = NULL;
		unix_state_double_lock(sk, other);
	}

	/*
	 * If it was connected, reconnect.
	 */
	if (unix_peer(sk)) {
		struct sock *old_peer = unix_peer(sk);
		unix_peer(sk) = other;
		unix_state_double_unlock(sk, other);

		if (other != old_peer)
			unix_dgram_disconnected(sk, old_peer);
		sock_put(old_peer);
	} else {
		unix_peer(sk) = other;
		unix_state_double_unlock(sk, other);
	}
	return 0;

out_unlock:
	unix_state_double_unlock(sk, other);
	sock_put(other);
out:
	return err;
}

static long unix_wait_for_peer(struct sock *other, long timeo)
{
	struct unix_sock *u = unix_sk(other);
	int sched;
	DEFINE_WAIT(wait);

	prepare_to_wait_exclusive(&u->peer_wait, &wait, TASK_INTERRUPTIBLE);

	sched = !sock_flag(other, SOCK_DEAD) &&
		!(other->sk_shutdown & RCV_SHUTDOWN) &&
		unix_recvq_full(other);

	unix_state_unlock(other);

	if (sched)
		timeo = schedule_timeout(timeo);

	finish_wait(&u->peer_wait, &wait);
	return timeo;
}

static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
			       int addr_len, int flags)
{
	struct sockaddr_un *sunaddr = (struct sockaddr_un *)uaddr;
	struct sock *sk = sock->sk;
	struct net *net = sock_net(sk);
	struct unix_sock *u = unix_sk(sk), *newu, *otheru;
	struct sock *newsk = NULL;
	struct sock *other = NULL;
	struct sk_buff *skb = NULL;
	unsigned hash;
	int st;
	int err;
	long timeo;

	err = unix_mkname(sunaddr, addr_len, &hash);
	if (err < 0)
		goto out;
	addr_len = err;

	if (test_bit(SOCK_PASSCRED, &sock->flags) && !u->addr &&
	    (err = unix_autobind(sock)) != 0)
		goto out;

	timeo = sock_sndtimeo(sk, flags & O_NONBLOCK);

	/* First of all allocate resources.
	   If we will make it after state is locked,
	   we will have to recheck all again in any case.
	 */

	err = -ENOMEM;

	/* create new sock for complete connection */
	newsk = unix_create1(sock_net(sk), NULL);
	if (newsk == NULL)
		goto out;

	/* Allocate skb for sending to listening sock */
	skb = sock_wmalloc(newsk, 1, 0, GFP_KERNEL);
	if (skb == NULL)
		goto out;

restart:
	/*  Find listening sock. */
	other = unix_find_other(net, sunaddr, addr_len, sk->sk_type, hash, &err);
	if (!other)
		goto out;

	/* Latch state of peer */
	unix_state_lock(other);

	/* Apparently VFS overslept socket death. Retry. */
	if (sock_flag(other, SOCK_DEAD)) {
		unix_state_unlock(other);
		sock_put(other);
		goto restart;
	}

	err = -ECONNREFUSED;
	if (other->sk_state != TCP_LISTEN)
		goto out_unlock;
	if (other->sk_shutdown & RCV_SHUTDOWN)
		goto out_unlock;

	if (unix_recvq_full(other)) {
		err = -EAGAIN;
		if (!timeo)
			goto out_unlock;

		timeo = unix_wait_for_peer(other, timeo);

		err = sock_intr_errno(timeo);
		if (signal_pending(current))
			goto out;
		sock_put(other);
		goto restart;
	}

	/* Latch our state.

	   It is tricky place. We need to grab write lock and cannot
	   drop lock on peer. It is dangerous because deadlock is
	   possible. Connect to self case and simultaneous
	   attempt to connect are eliminated by checking socket
	   state. other is TCP_LISTEN, if sk is TCP_LISTEN we
	   check this before attempt to grab lock.

	   Well, and we have to recheck the state after socket locked.
	 */
	st = sk->sk_state;

	switch (st) {
	case TCP_CLOSE:
		/* This is ok... continue with connect */
		break;
	case TCP_ESTABLISHED:
		/* Socket is already connected */
		err = -EISCONN;
		goto out_unlock;
	default:
		err = -EINVAL;
		goto out_unlock;
	}

	unix_state_lock_nested(sk);

	if (sk->sk_state != st) {
		unix_state_unlock(sk);
		unix_state_unlock(other);
		sock_put(other);
		goto restart;
	}

	err = security_unix_stream_connect(sock, other->sk_socket, newsk);
	if (err) {
		unix_state_unlock(sk);
		goto out_unlock;
	}

	/* The way is open! Fastly set all the necessary fields... */

	sock_hold(sk);
	unix_peer(newsk)	= sk;
	newsk->sk_state		= TCP_ESTABLISHED;
	newsk->sk_type		= sk->sk_type;
	init_peercred(newsk);
	newu = unix_sk(newsk);
	newsk->sk_wq		= &newu->peer_wq;
	otheru = unix_sk(other);

	/* copy address information from listening to new sock*/
	if (otheru->addr) {
		atomic_inc(&otheru->addr->refcnt);
		newu->addr = otheru->addr;
	}
	if (otheru->dentry) {
		newu->dentry	= dget(otheru->dentry);
		newu->mnt	= mntget(otheru->mnt);
	}

	/* Set credentials */
	copy_peercred(sk, other);

	sock->state	= SS_CONNECTED;
	sk->sk_state	= TCP_ESTABLISHED;
	sock_hold(newsk);

	smp_mb__after_atomic_inc();	/* sock_hold() does an atomic_inc() */
	unix_peer(sk)	= newsk;

	unix_state_unlock(sk);

	/* take ten and and send info to listening sock */
	spin_lock(&other->sk_receive_queue.lock);
	__skb_queue_tail(&other->sk_receive_queue, skb);
	spin_unlock(&other->sk_receive_queue.lock);
	unix_state_unlock(other);
	other->sk_data_ready(other, 0);
	sock_put(other);
	return 0;

out_unlock:
	if (other)
		unix_state_unlock(other);

out:
	kfree_skb(skb);
	if (newsk)
		unix_release_sock(newsk, 0);
	if (other)
		sock_put(other);
	return err;
}

static int unix_socketpair(struct socket *socka, struct socket *sockb)
{
	struct sock *ska = socka->sk, *skb = sockb->sk;

	/* Join our sockets back to back */
	sock_hold(ska);
	sock_hold(skb);
	unix_peer(ska) = skb;
	unix_peer(skb) = ska;
	init_peercred(ska);
	init_peercred(skb);

	if (ska->sk_type != SOCK_DGRAM) {
		ska->sk_state = TCP_ESTABLISHED;
		skb->sk_state = TCP_ESTABLISHED;
		socka->state  = SS_CONNECTED;
		sockb->state  = SS_CONNECTED;
	}
	return 0;
}

static int unix_accept(struct socket *sock, struct socket *newsock, int flags)
{
	struct sock *sk = sock->sk;
	struct sock *tsk;
	struct sk_buff *skb;
	int err;

	err = -EOPNOTSUPP;
	if (sock->type != SOCK_STREAM && sock->type != SOCK_SEQPACKET)
		goto out;

	err = -EINVAL;
	if (sk->sk_state != TCP_LISTEN)
		goto out;

	/* If socket state is TCP_LISTEN it cannot change (for now...),
	 * so that no locks are necessary.
	 */

	skb = skb_recv_datagram(sk, 0, flags&O_NONBLOCK, &err);
	if (!skb) {
		/* This means receive shutdown. */
		if (err == 0)
			err = -EINVAL;
		goto out;
	}

	tsk = skb->sk;
	skb_free_datagram(sk, skb);
	wake_up_interruptible(&unix_sk(sk)->peer_wait);

	/* attach accepted sock to socket */
	unix_state_lock(tsk);
	newsock->state = SS_CONNECTED;
	sock_graft(tsk, newsock);
	unix_state_unlock(tsk);
	return 0;

out:
	return err;
}


static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int *uaddr_len, int peer)
{
	struct sock *sk = sock->sk;
	struct unix_sock *u;
	DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, uaddr);
	int err = 0;

	if (peer) {
		sk = unix_peer_get(sk);

		err = -ENOTCONN;
		if (!sk)
			goto out;
		err = 0;
	} else {
		sock_hold(sk);
	}

	u = unix_sk(sk);
	unix_state_lock(sk);
	if (!u->addr) {
		sunaddr->sun_family = AF_UNIX;
		sunaddr->sun_path[0] = 0;
		*uaddr_len = sizeof(short);
	} else {
		struct unix_address *addr = u->addr;

		*uaddr_len = addr->len;
		memcpy(sunaddr, addr->name, *uaddr_len);
	}
	unix_state_unlock(sk);
	sock_put(sk);
out:
	return err;
}

static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb)
{
	int i;

	scm->fp = UNIXCB(skb).fp;
	UNIXCB(skb).fp = NULL;

	for (i = scm->fp->count-1; i >= 0; i--)
		unix_notinflight(scm->fp->fp[i]);
}

static void unix_destruct_scm(struct sk_buff *skb)
{
	struct scm_cookie scm;
	memset(&scm, 0, sizeof(scm));
	scm.pid  = UNIXCB(skb).pid;
	scm.cred = UNIXCB(skb).cred;
	if (UNIXCB(skb).fp)
		unix_detach_fds(&scm, skb);

	/* Alas, it calls VFS */
	/* So fscking what? fput() had been SMP-safe since the last Summer */
	scm_destroy(&scm);
	sock_wfree(skb);
}

static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
{
	int i;

	/*
	 * Need to duplicate file references for the sake of garbage
	 * collection.  Otherwise a socket in the fps might become a
	 * candidate for GC while the skb is not yet queued.
	 */
	UNIXCB(skb).fp = scm_fp_dup(scm->fp);
	if (!UNIXCB(skb).fp)
		return -ENOMEM;

	for (i = scm->fp->count-1; i >= 0; i--)
		unix_inflight(scm->fp->fp[i]);
	return 0;
}

static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds)
{
	int err = 0;
	UNIXCB(skb).pid  = get_pid(scm->pid);
	UNIXCB(skb).cred = get_cred(scm->cred);
	UNIXCB(skb).fp = NULL;
	if (scm->fp && send_fds)
		err = unix_attach_fds(scm, skb);

	skb->destructor = unix_destruct_scm;
	return err;
}

/*
 *	Send AF_UNIX data.
 */

static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock,
			      struct msghdr *msg, size_t len)
{
	struct sock_iocb *siocb = kiocb_to_siocb(kiocb);
	struct sock *sk = sock->sk;
	struct net *net = sock_net(sk);
	struct unix_sock *u = unix_sk(sk);
	struct sockaddr_un *sunaddr = msg->msg_name;
	struct sock *other = NULL;
	int namelen = 0; /* fake GCC */
	int err;
	unsigned hash;
	struct sk_buff *skb;
	long timeo;
	struct scm_cookie tmp_scm;

	if (NULL == siocb->scm)
		siocb->scm = &tmp_scm;
	wait_for_unix_gc();
	err = scm_send(sock, msg, siocb->scm);
	if (err < 0)
		return err;

	err = -EOPNOTSUPP;
	if (msg->msg_flags&MSG_OOB)
		goto out;

	if (msg->msg_namelen) {
		err = unix_mkname(sunaddr, msg->msg_namelen, &hash);
		if (err < 0)
			goto out;
		namelen = err;
	} else {
		sunaddr = NULL;
		err = -ENOTCONN;
		other = unix_peer_get(sk);
		if (!other)
			goto out;
	}

	if (test_bit(SOCK_PASSCRED, &sock->flags) && !u->addr
	    && (err = unix_autobind(sock)) != 0)
		goto out;

	err = -EMSGSIZE;
	if (len > sk->sk_sndbuf - 32)
		goto out;

	skb = sock_alloc_send_skb(sk, len, msg->msg_flags&MSG_DONTWAIT, &err);
	if (skb == NULL)
		goto out;

	err = unix_scm_to_skb(siocb->scm, skb, true);
	if (err)
		goto out_free;
	unix_get_secdata(siocb->scm, skb);

	skb_reset_transport_header(skb);
	err = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len);
	if (err)
		goto out_free;

	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);

restart:
	if (!other) {
		err = -ECONNRESET;
		if (sunaddr == NULL)
			goto out_free;

		other = unix_find_other(net, sunaddr, namelen, sk->sk_type,
					hash, &err);
		if (other == NULL)
			goto out_free;
	}

	unix_state_lock(other);
	err = -EPERM;
	if (!unix_may_send(sk, other))
		goto out_unlock;

	if (sock_flag(other, SOCK_DEAD)) {
		/*
		 *	Check with 1003.1g - what should
		 *	datagram error
		 */
		unix_state_unlock(other);
		sock_put(other);

		err = 0;
		unix_state_lock(sk);
		if (unix_peer(sk) == other) {
			unix_peer(sk) = NULL;
			unix_state_unlock(sk);

			unix_dgram_disconnected(sk, other);
			sock_put(other);
			err = -ECONNREFUSED;
		} else {
			unix_state_unlock(sk);
		}

		other = NULL;
		if (err)
			goto out_free;
		goto restart;
	}

	err = -EPIPE;
	if (other->sk_shutdown & RCV_SHUTDOWN)
		goto out_unlock;

	if (sk->sk_type != SOCK_SEQPACKET) {
		err = security_unix_may_send(sk->sk_socket, other->sk_socket);
		if (err)
			goto out_unlock;
	}

	if (unix_peer(other) != sk && unix_recvq_full(other)) {
		if (!timeo) {
			err = -EAGAIN;
			goto out_unlock;
		}

		timeo = unix_wait_for_peer(other, timeo);

		err = sock_intr_errno(timeo);
		if (signal_pending(current))
			goto out_free;

		goto restart;
	}

	skb_queue_tail(&other->sk_receive_queue, skb);
	unix_state_unlock(other);
	other->sk_data_ready(other, len);
	sock_put(other);
	scm_destroy(siocb->scm);
	return len;

out_unlock:
	unix_state_unlock(other);
out_free:
	kfree_skb(skb);
out:
	if (other)
		sock_put(other);
	scm_destroy(siocb->scm);
	return err;
}


static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
			       struct msghdr *msg, size_t len)
{
	struct sock_iocb *siocb = kiocb_to_siocb(kiocb);
	struct sock *sk = sock->sk;
	struct sock *other = NULL;
	struct sockaddr_un *sunaddr = msg->msg_name;
	int err, size;
	struct sk_buff *skb;
	int sent = 0;
	struct scm_cookie tmp_scm;
	bool fds_sent = false;

	if (NULL == siocb->scm)
		siocb->scm = &tmp_scm;
	wait_for_unix_gc();
	err = scm_send(sock, msg, siocb->scm);
	if (err < 0)
		return err;

	err = -EOPNOTSUPP;
	if (msg->msg_flags&MSG_OOB)
		goto out_err;

	if (msg->msg_namelen) {
		err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP;
		goto out_err;
	} else {
		sunaddr = NULL;
		err = -ENOTCONN;
		other = unix_peer(sk);
		if (!other)
			goto out_err;
	}

	if (sk->sk_shutdown & SEND_SHUTDOWN)
		goto pipe_err;

	while (sent < len) {
		/*
		 *	Optimisation for the fact that under 0.01% of X
		 *	messages typically need breaking up.
		 */

		size = len-sent;

		/* Keep two messages in the pipe so it schedules better */
		if (size > ((sk->sk_sndbuf >> 1) - 64))
			size = (sk->sk_sndbuf >> 1) - 64;

		if (size > SKB_MAX_ALLOC)
			size = SKB_MAX_ALLOC;

		/*
		 *	Grab a buffer
		 */

		skb = sock_alloc_send_skb(sk, size, msg->msg_flags&MSG_DONTWAIT,
					  &err);

		if (skb == NULL)
			goto out_err;

		/*
		 *	If you pass two values to the sock_alloc_send_skb
		 *	it tries to grab the large buffer with GFP_NOFS
		 *	(which can fail easily), and if it fails grab the
		 *	fallback size buffer which is under a page and will
		 *	succeed. [Alan]
		 */
		size = min_t(int, size, skb_tailroom(skb));


		/* Only send the fds in the first buffer */
		err = unix_scm_to_skb(siocb->scm, skb, !fds_sent);
		if (err) {
			kfree_skb(skb);
			goto out_err;
		}
		fds_sent = true;

		err = memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size);
		if (err) {
			kfree_skb(skb);
			goto out_err;
		}

		unix_state_lock(other);

		if (sock_flag(other, SOCK_DEAD) ||
		    (other->sk_shutdown & RCV_SHUTDOWN))
			goto pipe_err_free;

		skb_queue_tail(&other->sk_receive_queue, skb);
		unix_state_unlock(other);
		other->sk_data_ready(other, size);
		sent += size;
	}

	scm_destroy(siocb->scm);
	siocb->scm = NULL;

	return sent;

pipe_err_free:
	unix_state_unlock(other);
	kfree_skb(skb);
pipe_err:
	if (sent == 0 && !(msg->msg_flags&MSG_NOSIGNAL))
		send_sig(SIGPIPE, current, 0);
	err = -EPIPE;
out_err:
	scm_destroy(siocb->scm);
	siocb->scm = NULL;
	return sent ? : err;
}

static int unix_seqpacket_sendmsg(struct kiocb *kiocb, struct socket *sock,
				  struct msghdr *msg, size_t len)
{
	int err;
	struct sock *sk = sock->sk;

	err = sock_error(sk);
	if (err)
		return err;

	if (sk->sk_state != TCP_ESTABLISHED)
		return -ENOTCONN;

	if (msg->msg_namelen)
		msg->msg_namelen = 0;

	return unix_dgram_sendmsg(kiocb, sock, msg, len);
}

static void unix_copy_addr(struct msghdr *msg, struct sock *sk)
{
	struct unix_sock *u = unix_sk(sk);

	msg->msg_namelen = 0;
	if (u->addr) {
		msg->msg_namelen = u->addr->len;
		memcpy(msg->msg_name, u->addr->name, u->addr->len);
	}
}

static int unix_dgram_recvmsg(struct kiocb *iocb, struct socket *sock,
			      struct msghdr *msg, size_t size,
			      int flags)
{
	struct sock_iocb *siocb = kiocb_to_siocb(iocb);
	struct scm_cookie tmp_scm;
	struct sock *sk = sock->sk;
	struct unix_sock *u = unix_sk(sk);
	int noblock = flags & MSG_DONTWAIT;
	struct sk_buff *skb;
	int err;

	err = -EOPNOTSUPP;
	if (flags&MSG_OOB)
		goto out;

	msg->msg_namelen = 0;

	mutex_lock(&u->readlock);

	skb = skb_recv_datagram(sk, flags, noblock, &err);
	if (!skb) {
		unix_state_lock(sk);
		/* Signal EOF on disconnected non-blocking SEQPACKET socket. */
		if (sk->sk_type == SOCK_SEQPACKET && err == -EAGAIN &&
		    (sk->sk_shutdown & RCV_SHUTDOWN))
			err = 0;
		unix_state_unlock(sk);
		goto out_unlock;
	}

	wake_up_interruptible_sync(&u->peer_wait);

	if (msg->msg_name)
		unix_copy_addr(msg, skb->sk);

	if (size > skb->len)
		size = skb->len;
	else if (size < skb->len)
		msg->msg_flags |= MSG_TRUNC;

	err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, size);
	if (err)
		goto out_free;

	if (!siocb->scm) {
		siocb->scm = &tmp_scm;
		memset(&tmp_scm, 0, sizeof(tmp_scm));
	}
	scm_set_cred(siocb->scm, UNIXCB(skb).pid, UNIXCB(skb).cred);
	unix_set_secdata(siocb->scm, skb);

	if (!(flags & MSG_PEEK)) {
		if (UNIXCB(skb).fp)
			unix_detach_fds(siocb->scm, skb);
	} else {
		/* It is questionable: on PEEK we could:
		   - do not return fds - good, but too simple 8)
		   - return fds, and do not return them on read (old strategy,
		     apparently wrong)
		   - clone fds (I chose it for now, it is the most universal
		     solution)

		   POSIX 1003.1g does not actually define this clearly
		   at all. POSIX 1003.1g doesn't define a lot of things
		   clearly however!

		*/
		if (UNIXCB(skb).fp)
			siocb->scm->fp = scm_fp_dup(UNIXCB(skb).fp);
	}
	err = size;

	scm_recv(sock, msg, siocb->scm, flags);

out_free:
	skb_free_datagram(sk, skb);
out_unlock:
	mutex_unlock(&u->readlock);
out:
	return err;
}

/*
 *	Sleep until data has arrive. But check for races..
 */

static long unix_stream_data_wait(struct sock *sk, long timeo)
{
	DEFINE_WAIT(wait);

	unix_state_lock(sk);

	for (;;) {
		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);

		if (!skb_queue_empty(&sk->sk_receive_queue) ||
		    sk->sk_err ||
		    (sk->sk_shutdown & RCV_SHUTDOWN) ||
		    signal_pending(current) ||
		    !timeo)
			break;

		set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
		unix_state_unlock(sk);
		timeo = schedule_timeout(timeo);
		unix_state_lock(sk);
		clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
	}

	finish_wait(sk_sleep(sk), &wait);
	unix_state_unlock(sk);
	return timeo;
}



static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
			       struct msghdr *msg, size_t size,
			       int flags)
{
	struct sock_iocb *siocb = kiocb_to_siocb(iocb);
	struct scm_cookie tmp_scm;
	struct sock *sk = sock->sk;
	struct unix_sock *u = unix_sk(sk);
	struct sockaddr_un *sunaddr = msg->msg_name;
	int copied = 0;
	int check_creds = 0;
	int target;
	int err = 0;
	long timeo;

	err = -EINVAL;
	if (sk->sk_state != TCP_ESTABLISHED)
		goto out;

	err = -EOPNOTSUPP;
	if (flags&MSG_OOB)
		goto out;

	target = sock_rcvlowat(sk, flags&MSG_WAITALL, size);
	timeo = sock_rcvtimeo(sk, flags&MSG_DONTWAIT);

	msg->msg_namelen = 0;

	/* Lock the socket to prevent queue disordering
	 * while sleeps in memcpy_tomsg
	 */

	if (!siocb->scm) {
		siocb->scm = &tmp_scm;
		memset(&tmp_scm, 0, sizeof(tmp_scm));
	}

	mutex_lock(&u->readlock);

	do {
		int chunk;
		struct sk_buff *skb;

		unix_state_lock(sk);
		skb = skb_dequeue(&sk->sk_receive_queue);
		if (skb == NULL) {
			if (copied >= target)
				goto unlock;

			/*
			 *	POSIX 1003.1g mandates this order.
			 */

			err = sock_error(sk);
			if (err)
				goto unlock;
			if (sk->sk_shutdown & RCV_SHUTDOWN)
				goto unlock;

			unix_state_unlock(sk);
			err = -EAGAIN;
			if (!timeo)
				break;
			mutex_unlock(&u->readlock);

			timeo = unix_stream_data_wait(sk, timeo);

			if (signal_pending(current)) {
				err = sock_intr_errno(timeo);
				goto out;
			}
			mutex_lock(&u->readlock);
			continue;
 unlock:
			unix_state_unlock(sk);
			break;
		}
		unix_state_unlock(sk);

		if (check_creds) {
			/* Never glue messages from different writers */
			if ((UNIXCB(skb).pid  != siocb->scm->pid) ||
			    (UNIXCB(skb).cred != siocb->scm->cred)) {
				skb_queue_head(&sk->sk_receive_queue, skb);
				break;
			}
		} else {
			/* Copy credentials */
			scm_set_cred(siocb->scm, UNIXCB(skb).pid, UNIXCB(skb).cred);
			check_creds = 1;
		}

		/* Copy address just once */
		if (sunaddr) {
			unix_copy_addr(msg, skb->sk);
			sunaddr = NULL;
		}

		chunk = min_t(unsigned int, skb->len, size);
		if (memcpy_toiovec(msg->msg_iov, skb->data, chunk)) {
			skb_queue_head(&sk->sk_receive_queue, skb);
			if (copied == 0)
				copied = -EFAULT;
			break;
		}
		copied += chunk;
		size -= chunk;

		/* Mark read part of skb as used */
		if (!(flags & MSG_PEEK)) {
			skb_pull(skb, chunk);

			if (UNIXCB(skb).fp)
				unix_detach_fds(siocb->scm, skb);

			/* put the skb back if we didn't use it up.. */
			if (skb->len) {
				skb_queue_head(&sk->sk_receive_queue, skb);
				break;
			}

			consume_skb(skb);

			if (siocb->scm->fp)
				break;
		} else {
			/* It is questionable, see note in unix_dgram_recvmsg.
			 */
			if (UNIXCB(skb).fp)
				siocb->scm->fp = scm_fp_dup(UNIXCB(skb).fp);

			/* put message back and return */
			skb_queue_head(&sk->sk_receive_queue, skb);
			break;
		}
	} while (size);

	mutex_unlock(&u->readlock);
	scm_recv(sock, msg, siocb->scm, flags);
out:
	return copied ? : err;
}

static int unix_shutdown(struct socket *sock, int mode)
{
	struct sock *sk = sock->sk;
	struct sock *other;

	mode = (mode+1)&(RCV_SHUTDOWN|SEND_SHUTDOWN);

	if (mode) {
		unix_state_lock(sk);
		sk->sk_shutdown |= mode;
		other = unix_peer(sk);
		if (other)
			sock_hold(other);
		unix_state_unlock(sk);
		sk->sk_state_change(sk);

		if (other &&
			(sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET)) {

			int peer_mode = 0;

			if (mode&RCV_SHUTDOWN)
				peer_mode |= SEND_SHUTDOWN;
			if (mode&SEND_SHUTDOWN)
				peer_mode |= RCV_SHUTDOWN;
			unix_state_lock(other);
			other->sk_shutdown |= peer_mode;
			unix_state_unlock(other);
			other->sk_state_change(other);
			if (peer_mode == SHUTDOWN_MASK)
				sk_wake_async(other, SOCK_WAKE_WAITD, POLL_HUP);
			else if (peer_mode & RCV_SHUTDOWN)
				sk_wake_async(other, SOCK_WAKE_WAITD, POLL_IN);
		}
		if (other)
			sock_put(other);
	}
	return 0;
}

static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
	struct sock *sk = sock->sk;
	long amount = 0;
	int err;

	switch (cmd) {
	case SIOCOUTQ:
		amount = sk_wmem_alloc_get(sk);
		err = put_user(amount, (int __user *)arg);
		break;
	case SIOCINQ:
		{
			struct sk_buff *skb;

			if (sk->sk_state == TCP_LISTEN) {
				err = -EINVAL;
				break;
			}

			spin_lock(&sk->sk_receive_queue.lock);
			if (sk->sk_type == SOCK_STREAM ||
			    sk->sk_type == SOCK_SEQPACKET) {
				skb_queue_walk(&sk->sk_receive_queue, skb)
					amount += skb->len;
			} else {
				skb = skb_peek(&sk->sk_receive_queue);
				if (skb)
					amount = skb->len;
			}
			spin_unlock(&sk->sk_receive_queue.lock);
			err = put_user(amount, (int __user *)arg);
			break;
		}

	default:
		err = -ENOIOCTLCMD;
		break;
	}
	return err;
}

static unsigned int unix_poll(struct file *file, struct socket *sock, poll_table *wait)
{
	struct sock *sk = sock->sk;
	unsigned int mask;

	sock_poll_wait(file, sk_sleep(sk), wait);
	mask = 0;

	/* exceptional events? */
	if (sk->sk_err)
		mask |= POLLERR;
	if (sk->sk_shutdown == SHUTDOWN_MASK)
		mask |= POLLHUP;
	if (sk->sk_shutdown & RCV_SHUTDOWN)
		mask |= POLLRDHUP;

	/* readable? */
	if (!skb_queue_empty(&sk->sk_receive_queue) ||
	    (sk->sk_shutdown & RCV_SHUTDOWN))
		mask |= POLLIN | POLLRDNORM;

	/* Connection-based need to check for termination and startup */
	if ((sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) &&
	    sk->sk_state == TCP_CLOSE)
		mask |= POLLHUP;

	/*
	 * we set writable also when the other side has shut down the
	 * connection. This prevents stuck sockets.
	 */
	if (unix_writable(sk))
		mask |= POLLOUT | POLLWRNORM | POLLWRBAND;

	return mask;
}

static unsigned int unix_dgram_poll(struct file *file, struct socket *sock,
				    poll_table *wait)
{
	struct sock *sk = sock->sk, *other;
	unsigned int mask, writable;

	sock_poll_wait(file, sk_sleep(sk), wait);
	mask = 0;

	/* exceptional events? */
	if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
		mask |= POLLERR;
	if (sk->sk_shutdown & RCV_SHUTDOWN)
		mask |= POLLRDHUP;
	if (sk->sk_shutdown == SHUTDOWN_MASK)
		mask |= POLLHUP;

	/* readable? */
	if (!skb_queue_empty(&sk->sk_receive_queue) ||
	    (sk->sk_shutdown & RCV_SHUTDOWN))
		mask |= POLLIN | POLLRDNORM;

	/* Connection-based need to check for termination and startup */
	if (sk->sk_type == SOCK_SEQPACKET) {
		if (sk->sk_state == TCP_CLOSE)
			mask |= POLLHUP;
		/* connection hasn't started yet? */
		if (sk->sk_state == TCP_SYN_SENT)
			return mask;
	}

	/* writable? */
	writable = unix_writable(sk);
	if (writable) {
		other = unix_peer_get(sk);
		if (other) {
			if (unix_peer(other) != sk) {
				sock_poll_wait(file, &unix_sk(other)->peer_wait,
					  wait);
				if (unix_recvq_full(other))
					writable = 0;
			}

			sock_put(other);
		}
	}

	if (writable)
		mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
	else
		set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);

	return mask;
}

#ifdef CONFIG_PROC_FS
static struct sock *first_unix_socket(int *i)
{
	for (*i = 0; *i <= UNIX_HASH_SIZE; (*i)++) {
		if (!hlist_empty(&unix_socket_table[*i]))
			return __sk_head(&unix_socket_table[*i]);
	}
	return NULL;
}

static struct sock *next_unix_socket(int *i, struct sock *s)
{
	struct sock *next = sk_next(s);
	/* More in this chain? */
	if (next)
		return next;
	/* Look for next non-empty chain. */
	for ((*i)++; *i <= UNIX_HASH_SIZE; (*i)++) {
		if (!hlist_empty(&unix_socket_table[*i]))
			return __sk_head(&unix_socket_table[*i]);
	}
	return NULL;
}

struct unix_iter_state {
	struct seq_net_private p;
	int i;
};

static struct sock *unix_seq_idx(struct seq_file *seq, loff_t pos)
{
	struct unix_iter_state *iter = seq->private;
	loff_t off = 0;
	struct sock *s;

	for (s = first_unix_socket(&iter->i); s; s = next_unix_socket(&iter->i, s)) {
		if (sock_net(s) != seq_file_net(seq))
			continue;
		if (off == pos)
			return s;