aboutsummaryrefslogtreecommitdiffstats
path: root/net/sctp/proc.c
blob: b3493bdbcacbc884cabedc055c3cd82f5097850e (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
/* SCTP kernel reference Implementation
 * Copyright (c) 2003 International Business Machines, Corp.
 *
 * This file is part of the SCTP kernel reference Implementation
 *
 * The SCTP reference implementation is free software;
 * you can redistribute it and/or modify it under the terms of
 * the GNU General Public License as published by
 * the Free Software Foundation; either version 2, or (at your option)
 * any later version.
 *
 * The SCTP reference implementation is distributed in the hope that it
 * will be useful, but WITHOUT ANY WARRANTY; without even the implied
 *                 ************************
 * warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
 * See the GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with GNU CC; see the file COPYING.  If not, write to
 * the Free Software Foundation, 59 Temple Place - Suite 330,
 * Boston, MA 02111-1307, USA.
 *
 * Please send any bug reports or fixes you make to the
 * email address(es):
 *    lksctp developers <lksctp-developers@lists.sourceforge.net>
 *
 * Or submit a bug report through the following website:
 *    http://www.sf.net/projects/lksctp
 *
 * Written or modified by:
 *    Sridhar Samudrala <sri@us.ibm.com>
 *
 * Any bugs reported given to us we will try to fix... any fixes shared will
 * be incorporated into the next SCTP release.
 */

#include <linux/types.h>
#include <linux/seq_file.h>
#include <linux/init.h>
#include <net/sctp/sctp.h>

static struct snmp_mib sctp_snmp_list[] = {
	SNMP_MIB_ITEM("SctpCurrEstab", SCTP_MIB_CURRESTAB),
	SNMP_MIB_ITEM("SctpActiveEstabs", SCTP_MIB_ACTIVEESTABS),
	SNMP_MIB_ITEM("SctpPassiveEstabs", SCTP_MIB_PASSIVEESTABS),
	SNMP_MIB_ITEM("SctpAborteds", SCTP_MIB_ABORTEDS),
	SNMP_MIB_ITEM("SctpShutdowns", SCTP_MIB_SHUTDOWNS),
	SNMP_MIB_ITEM("SctpOutOfBlues", SCTP_MIB_OUTOFBLUES),
	SNMP_MIB_ITEM("SctpChecksumErrors", SCTP_MIB_CHECKSUMERRORS),
	SNMP_MIB_ITEM("SctpOutCtrlChunks", SCTP_MIB_OUTCTRLCHUNKS),
	SNMP_MIB_ITEM("SctpOutOrderChunks", SCTP_MIB_OUTORDERCHUNKS),
	SNMP_MIB_ITEM("SctpOutUnorderChunks", SCTP_MIB_OUTUNORDERCHUNKS),
	SNMP_MIB_ITEM("SctpInCtrlChunks", SCTP_MIB_INCTRLCHUNKS),
	SNMP_MIB_ITEM("SctpInOrderChunks", SCTP_MIB_INORDERCHUNKS),
	SNMP_MIB_ITEM("SctpInUnorderChunks", SCTP_MIB_INUNORDERCHUNKS),
	SNMP_MIB_ITEM("SctpFragUsrMsgs", SCTP_MIB_FRAGUSRMSGS),
	SNMP_MIB_ITEM("SctpReasmUsrMsgs", SCTP_MIB_REASMUSRMSGS),
	SNMP_MIB_ITEM("SctpOutSCTPPacks", SCTP_MIB_OUTSCTPPACKS),
	SNMP_MIB_ITEM("SctpInSCTPPacks", SCTP_MIB_INSCTPPACKS),
	SNMP_MIB_ITEM("SctpT1InitExpireds", SCTP_MIB_T1_INIT_EXPIREDS),
	SNMP_MIB_ITEM("SctpT1CookieExpireds", SCTP_MIB_T1_COOKIE_EXPIREDS),
	SNMP_MIB_ITEM("SctpT2ShutdownExpireds", SCTP_MIB_T2_SHUTDOWN_EXPIREDS),
	SNMP_MIB_ITEM("SctpT3RtxExpireds", SCTP_MIB_T3_RTX_EXPIREDS),
	SNMP_MIB_ITEM("SctpT4RtoExpireds", SCTP_MIB_T4_RTO_EXPIREDS),
	SNMP_MIB_ITEM("SctpT5ShutdownGuardExpireds", SCTP_MIB_T5_SHUTDOWN_GUARD_EXPIREDS),
	SNMP_MIB_ITEM("SctpDelaySackExpireds", SCTP_MIB_DELAY_SACK_EXPIREDS),
	SNMP_MIB_ITEM("SctpAutocloseExpireds", SCTP_MIB_AUTOCLOSE_EXPIREDS),
	SNMP_MIB_ITEM("SctpT3Retransmits", SCTP_MIB_T3_RETRANSMITS),
	SNMP_MIB_ITEM("SctpPmtudRetransmits", SCTP_MIB_PMTUD_RETRANSMITS),
	SNMP_MIB_ITEM("SctpFastRetransmits", SCTP_MIB_FAST_RETRANSMITS),
	SNMP_MIB_ITEM("SctpInPktSoftirq", SCTP_MIB_IN_PKT_SOFTIRQ),
	SNMP_MIB_ITEM("SctpInPktBacklog", SCTP_MIB_IN_PKT_BACKLOG),
	SNMP_MIB_ITEM("SctpInPktDiscards", SCTP_MIB_IN_PKT_DISCARDS),
	SNMP_MIB_ITEM("SctpInDataChunkDiscards", SCTP_MIB_IN_DATA_CHUNK_DISCARDS),
	SNMP_MIB_SENTINEL
};

/* Return the current value of a particular entry in the mib by adding its
 * per cpu counters.
 */ 
static unsigned long
fold_field(void *mib[], int nr)
{
	unsigned long res = 0;
	int i;

	for_each_possible_cpu(i) {
		res +=
		    *((unsigned long *) (((void *) per_cpu_ptr(mib[0], i)) +
					 sizeof (unsigned long) * nr));
		res +=
		    *((unsigned long *) (((void *) per_cpu_ptr(mib[1], i)) +
					 sizeof (unsigned long) * nr));
	}
	return res;
}

/* Display sctp snmp mib statistics(/proc/net/sctp/snmp). */
static int sctp_snmp_seq_show(struct seq_file *seq, void *v)
{
	int i;

	for (i = 0; sctp_snmp_list[i].name != NULL; i++)
		seq_printf(seq, "%-32s\t%ld\n", sctp_snmp_list[i].name,
			   fold_field((void **)sctp_statistics, 
				      sctp_snmp_list[i].entry));

	return 0;
}

/* Initialize the seq file operations for 'snmp' object. */
static int sctp_snmp_seq_open(struct inode *inode, struct file *file)
{
	return single_open(file, sctp_snmp_seq_show, NULL);
}

static struct file_operations sctp_snmp_seq_fops = {
	.owner	 = THIS_MODULE,
	.open	 = sctp_snmp_seq_open,
	.read	 = seq_read,
	.llseek	 = seq_lseek,
	.release = single_release,
};

/* Set up the proc fs entry for 'snmp' object. */
int __init sctp_snmp_proc_init(void)
{
	struct proc_dir_entry *p;

	p = create_proc_entry("snmp", S_IRUGO, proc_net_sctp);
	if (!p)
		return -ENOMEM;

	p->proc_fops = &sctp_snmp_seq_fops;

	return 0;
}

/* Cleanup the proc fs entry for 'snmp' object. */
void sctp_snmp_proc_exit(void)
{
	remove_proc_entry("snmp", proc_net_sctp);
}

/* Dump local addresses of an association/endpoint. */
static void sctp_seq_dump_local_addrs(struct seq_file *seq, struct sctp_ep_common *epb)
{
	struct list_head *pos;
	struct sctp_association *asoc;
	struct sctp_sockaddr_entry *laddr;
	struct sctp_transport *peer;
	union sctp_addr *addr, *primary = NULL;
	struct sctp_af *af;

	if (epb->type == SCTP_EP_TYPE_ASSOCIATION) {
	    asoc = sctp_assoc(epb);
	    peer = asoc->peer.primary_path;
	    primary = &peer->saddr;
	}

	list_for_each(pos, &epb->bind_addr.address_list) {
		laddr = list_entry(pos, struct sctp_sockaddr_entry, list);
		addr = &laddr->a;
		af = sctp_get_af_specific(addr->sa.sa_family);
		if (primary && af->cmp_addr(addr, primary)) {
			seq_printf(seq, "*");
		}
		af->seq_dump_addr(seq, addr);
	}
}

/* Dump remote addresses of an association. */
static void sctp_seq_dump_remote_addrs(struct seq_file *seq, struct sctp_association *assoc)
{
	struct list_head *pos;
	struct sctp_transport *transport;
	union sctp_addr *addr, *primary;
	struct sctp_af *af;

	primary = &assoc->peer.primary_addr;
	list_for_each(pos, &assoc->peer.transport_addr_list) {
		transport = list_entry(pos, struct sctp_transport, transports);
		addr = &transport->ipaddr;
		af = sctp_get_af_specific(addr->sa.sa_family);
		if (af->cmp_addr(addr, primary)) {
			seq_printf(seq, "*");
		}
		af->seq_dump_addr(seq, addr);
	}
}

static void * sctp_eps_seq_start(struct seq_file *seq, loff_t *pos)
{
	if (*pos >= sctp_ep_hashsize)
		return NULL;

	if (*pos < 0)
		*pos = 0;

	if (*pos == 0)
		seq_printf(seq, " ENDPT     SOCK   STY SST HBKT LPORT   UID INODE LADDRS\n");

	return (void *)pos;
}

static void sctp_eps_seq_stop(struct seq_file *seq, void *v)
{
	return;
}


static void * sctp_eps_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	if (++*pos >= sctp_ep_hashsize)
		return NULL;

	return pos;
}


/* Display sctp endpoints (/proc/net/sctp/eps). */
static int sctp_eps_seq_show(struct seq_file *seq, void *v)
{
	struct sctp_hashbucket *head;
	struct sctp_ep_common *epb;
	struct sctp_endpoint *ep;
	struct sock *sk;
	int    hash = *(loff_t *)v;

	if (hash >= sctp_ep_hashsize)
		return -ENOMEM;

	head = &sctp_ep_hashtable[hash];
	sctp_local_bh_disable();
	read_lock(&head->lock);
	for (epb = head->chain; epb; epb = epb->next) {
		ep = sctp_ep(epb);
		sk = epb->sk;
		seq_printf(seq, "%8p %8p %-3d %-3d %-4d %-5d %5d %5lu ", ep, sk,
			   sctp_sk(sk)->type, sk->sk_state, hash,
			   epb->bind_addr.port,
			   sock_i_uid(sk), sock_i_ino(sk));

		sctp_seq_dump_local_addrs(seq, epb);
		seq_printf(seq, "\n");
	}
	read_unlock(&head->lock);
	sctp_local_bh_enable();

	return 0;
}

static struct seq_operations sctp_eps_ops = {
	.start = sctp_eps_seq_start,
	.next  = sctp_eps_seq_next,
	.stop  = sctp_eps_seq_stop,
	.show  = sctp_eps_seq_show,
};


/* Initialize the seq file operations for 'eps' object. */
static int sctp_eps_seq_open(struct inode *inode, struct file *file)
{
	return seq_open(file, &sctp_eps_ops);
}

static struct file_operations sctp_eps_seq_fops = {
	.open	 = sctp_eps_seq_open,
	.read	 = seq_read,
	.llseek	 = seq_lseek,
	.release = seq_release,
};

/* Set up the proc fs entry for 'eps' object. */
int __init sctp_eps_proc_init(void)
{
	struct proc_dir_entry *p;

	p = create_proc_entry("eps", S_IRUGO, proc_net_sctp);
	if (!p)
		return -ENOMEM;

	p->proc_fops = &sctp_eps_seq_fops;

	return 0;
}

/* Cleanup the proc fs entry for 'eps' object. */
void sctp_eps_proc_exit(void)
{
	remove_proc_entry("eps", proc_net_sctp);
}


static void * sctp_assocs_seq_start(struct seq_file *seq, loff_t *pos)
{
	if (*pos >= sctp_assoc_hashsize)
		return NULL;

	if (*pos < 0)
		*pos = 0;

	if (*pos == 0)
		seq_printf(seq, " ASSOC     SOCK   STY SST ST HBKT ASSOC-ID TX_QUEUE RX_QUEUE UID INODE LPORT "
				"RPORT LADDRS <-> RADDRS\n");

	return (void *)pos;
}

static void sctp_assocs_seq_stop(struct seq_file *seq, void *v)
{
	return;
}


static void * sctp_assocs_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	if (++*pos >= sctp_assoc_hashsize)
		return NULL;

	return pos;
}

/* Display sctp associations (/proc/net/sctp/assocs). */
static int sctp_assocs_seq_show(struct seq_file *seq, void *v)
{
	struct sctp_hashbucket *head;
	struct sctp_ep_common *epb;
	struct sctp_association *assoc;
	struct sock *sk;
	int    hash = *(loff_t *)v;

	if (hash >= sctp_assoc_hashsize)
		return -ENOMEM;

	head = &sctp_assoc_hashtable[hash];
	sctp_local_bh_disable();
	read_lock(&head->lock);
	for (epb = head->chain; epb; epb = epb->next) {
		assoc = sctp_assoc(epb);
		sk = epb->sk;
		seq_printf(seq,
			   "%8p %8p %-3d %-3d %-2d %-4d %4d %8d %8d %7d %5lu %-5d %5d ",
			   assoc, sk, sctp_sk(sk)->type, sk->sk_state,
			   assoc->state, hash, assoc->assoc_id,
			   assoc->sndbuf_used,
			   atomic_read(&assoc->rmem_alloc),
			   sock_i_uid(sk), sock_i_ino(sk),
			   epb->bind_addr.port,
			   assoc->peer.port);

		seq_printf(seq, " ");
		sctp_seq_dump_local_addrs(seq, epb);
		seq_printf(seq, "<-> ");
		sctp_seq_dump_remote_addrs(seq, assoc);
		seq_printf(seq, "\n");
	}
	read_unlock(&head->lock);
	sctp_local_bh_enable();

	return 0;
}

static struct seq_operations sctp_assoc_ops = {
	.start = sctp_assocs_seq_start,
	.next  = sctp_assocs_seq_next,
	.stop  = sctp_assocs_seq_stop,
	.show  = sctp_assocs_seq_show,
};

/* Initialize the seq file operations for 'assocs' object. */
static int sctp_assocs_seq_open(struct inode *inode, struct file *file)
{
	return seq_open(file, &sctp_assoc_ops);
}

static struct file_operations sctp_assocs_seq_fops = {
	.open	 = sctp_assocs_seq_open,
	.read	 = seq_read,
	.llseek	 = seq_lseek,
	.release = seq_release,
};

/* Set up the proc fs entry for 'assocs' object. */
int __init sctp_assocs_proc_init(void)
{
	struct proc_dir_entry *p;

	p = create_proc_entry("assocs", S_IRUGO, proc_net_sctp);
	if (!p)
		return -ENOMEM;

	p->proc_fops = &sctp_assocs_seq_fops;

	return 0;
}

/* Cleanup the proc fs entry for 'assocs' object. */
void sctp_assocs_proc_exit(void)
{
	remove_proc_entry("assocs", proc_net_sctp);
}
1638'>1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839
/*
 * Copyright (c) 2000-2005 Silicon Graphics, Inc.
 * All Rights Reserved.
 *
 * 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.
 *
 * This program is distributed in the hope that it would be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write the Free Software Foundation,
 * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_types.h"
#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_inum.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_dir2.h"
#include "xfs_dmapi.h"
#include "xfs_mount.h"
#include "xfs_error.h"
#include "xfs_log_priv.h"
#include "xfs_buf_item.h"
#include "xfs_bmap_btree.h"
#include "xfs_alloc_btree.h"
#include "xfs_ialloc_btree.h"
#include "xfs_log_recover.h"
#include "xfs_trans_priv.h"
#include "xfs_dir2_sf.h"
#include "xfs_attr_sf.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_rw.h"
#include "xfs_trace.h"

kmem_zone_t	*xfs_log_ticket_zone;

/* Local miscellaneous function prototypes */
STATIC int	 xlog_commit_record(struct log *log, struct xlog_ticket *ticket,
				    xlog_in_core_t **, xfs_lsn_t *);
STATIC xlog_t *  xlog_alloc_log(xfs_mount_t	*mp,
				xfs_buftarg_t	*log_target,
				xfs_daddr_t	blk_offset,
				int		num_bblks);
STATIC int	 xlog_space_left(xlog_t *log, int cycle, int bytes);
STATIC int	 xlog_sync(xlog_t *log, xlog_in_core_t *iclog);
STATIC void	 xlog_dealloc_log(xlog_t *log);

/* local state machine functions */
STATIC void xlog_state_done_syncing(xlog_in_core_t *iclog, int);
STATIC void xlog_state_do_callback(xlog_t *log,int aborted, xlog_in_core_t *iclog);
STATIC int  xlog_state_get_iclog_space(xlog_t		*log,
				       int		len,
				       xlog_in_core_t	**iclog,
				       xlog_ticket_t	*ticket,
				       int		*continued_write,
				       int		*logoffsetp);
STATIC int  xlog_state_release_iclog(xlog_t		*log,
				     xlog_in_core_t	*iclog);
STATIC void xlog_state_switch_iclogs(xlog_t		*log,
				     xlog_in_core_t *iclog,
				     int		eventual_size);
STATIC void xlog_state_want_sync(xlog_t	*log, xlog_in_core_t *iclog);

/* local functions to manipulate grant head */
STATIC int  xlog_grant_log_space(xlog_t		*log,
				 xlog_ticket_t	*xtic);
STATIC void xlog_grant_push_ail(xfs_mount_t	*mp,
				int		need_bytes);
STATIC void xlog_regrant_reserve_log_space(xlog_t	 *log,
					   xlog_ticket_t *ticket);
STATIC int xlog_regrant_write_log_space(xlog_t		*log,
					 xlog_ticket_t  *ticket);
STATIC void xlog_ungrant_log_space(xlog_t	 *log,
				   xlog_ticket_t *ticket);

#if defined(DEBUG)
STATIC void	xlog_verify_dest_ptr(xlog_t *log, char *ptr);
STATIC void	xlog_verify_grant_head(xlog_t *log, int equals);
STATIC void	xlog_verify_iclog(xlog_t *log, xlog_in_core_t *iclog,
				  int count, boolean_t syncing);
STATIC void	xlog_verify_tail_lsn(xlog_t *log, xlog_in_core_t *iclog,
				     xfs_lsn_t tail_lsn);
#else
#define xlog_verify_dest_ptr(a,b)
#define xlog_verify_grant_head(a,b)
#define xlog_verify_iclog(a,b,c,d)
#define xlog_verify_tail_lsn(a,b,c)
#endif

STATIC int	xlog_iclogs_empty(xlog_t *log);


static void
xlog_ins_ticketq(struct xlog_ticket **qp, struct xlog_ticket *tic)
{
	if (*qp) {
		tic->t_next	    = (*qp);
		tic->t_prev	    = (*qp)->t_prev;
		(*qp)->t_prev->t_next = tic;
		(*qp)->t_prev	    = tic;
	} else {
		tic->t_prev = tic->t_next = tic;
		*qp = tic;
	}

	tic->t_flags |= XLOG_TIC_IN_Q;
}

static void
xlog_del_ticketq(struct xlog_ticket **qp, struct xlog_ticket *tic)
{
	if (tic == tic->t_next) {
		*qp = NULL;
	} else {
		*qp = tic->t_next;
		tic->t_next->t_prev = tic->t_prev;
		tic->t_prev->t_next = tic->t_next;
	}

	tic->t_next = tic->t_prev = NULL;
	tic->t_flags &= ~XLOG_TIC_IN_Q;
}

static void
xlog_grant_sub_space(struct log *log, int bytes)
{
	log->l_grant_write_bytes -= bytes;
	if (log->l_grant_write_bytes < 0) {
		log->l_grant_write_bytes += log->l_logsize;
		log->l_grant_write_cycle--;
	}

	log->l_grant_reserve_bytes -= bytes;
	if ((log)->l_grant_reserve_bytes < 0) {
		log->l_grant_reserve_bytes += log->l_logsize;
		log->l_grant_reserve_cycle--;
	}

}

static void
xlog_grant_add_space_write(struct log *log, int bytes)
{
	int tmp = log->l_logsize - log->l_grant_write_bytes;
	if (tmp > bytes)
		log->l_grant_write_bytes += bytes;
	else {
		log->l_grant_write_cycle++;
		log->l_grant_write_bytes = bytes - tmp;
	}
}

static void
xlog_grant_add_space_reserve(struct log *log, int bytes)
{
	int tmp = log->l_logsize - log->l_grant_reserve_bytes;
	if (tmp > bytes)
		log->l_grant_reserve_bytes += bytes;
	else {
		log->l_grant_reserve_cycle++;
		log->l_grant_reserve_bytes = bytes - tmp;
	}
}

static inline void
xlog_grant_add_space(struct log *log, int bytes)
{
	xlog_grant_add_space_write(log, bytes);
	xlog_grant_add_space_reserve(log, bytes);
}

static void
xlog_tic_reset_res(xlog_ticket_t *tic)
{
	tic->t_res_num = 0;
	tic->t_res_arr_sum = 0;
	tic->t_res_num_ophdrs = 0;
}

static void
xlog_tic_add_region(xlog_ticket_t *tic, uint len, uint type)
{
	if (tic->t_res_num == XLOG_TIC_LEN_MAX) {
		/* add to overflow and start again */
		tic->t_res_o_flow += tic->t_res_arr_sum;
		tic->t_res_num = 0;
		tic->t_res_arr_sum = 0;
	}

	tic->t_res_arr[tic->t_res_num].r_len = len;
	tic->t_res_arr[tic->t_res_num].r_type = type;
	tic->t_res_arr_sum += len;
	tic->t_res_num++;
}

/*
 * NOTES:
 *
 *	1. currblock field gets updated at startup and after in-core logs
 *		marked as with WANT_SYNC.
 */

/*
 * This routine is called when a user of a log manager ticket is done with
 * the reservation.  If the ticket was ever used, then a commit record for
 * the associated transaction is written out as a log operation header with
 * no data.  The flag XLOG_TIC_INITED is set when the first write occurs with
 * a given ticket.  If the ticket was one with a permanent reservation, then
 * a few operations are done differently.  Permanent reservation tickets by
 * default don't release the reservation.  They just commit the current
 * transaction with the belief that the reservation is still needed.  A flag
 * must be passed in before permanent reservations are actually released.
 * When these type of tickets are not released, they need to be set into
 * the inited state again.  By doing this, a start record will be written
 * out when the next write occurs.
 */
xfs_lsn_t
xfs_log_done(
	struct xfs_mount	*mp,
	struct xlog_ticket	*ticket,
	struct xlog_in_core	**iclog,
	uint			flags)
{
	struct log		*log = mp->m_log;
	xfs_lsn_t		lsn = 0;

	if (XLOG_FORCED_SHUTDOWN(log) ||
	    /*
	     * If nothing was ever written, don't write out commit record.
	     * If we get an error, just continue and give back the log ticket.
	     */
	    (((ticket->t_flags & XLOG_TIC_INITED) == 0) &&
	     (xlog_commit_record(log, ticket, iclog, &lsn)))) {
		lsn = (xfs_lsn_t) -1;
		if (ticket->t_flags & XLOG_TIC_PERM_RESERV) {
			flags |= XFS_LOG_REL_PERM_RESERV;
		}
	}


	if ((ticket->t_flags & XLOG_TIC_PERM_RESERV) == 0 ||
	    (flags & XFS_LOG_REL_PERM_RESERV)) {
		trace_xfs_log_done_nonperm(log, ticket);

		/*
		 * Release ticket if not permanent reservation or a specific
		 * request has been made to release a permanent reservation.
		 */
		xlog_ungrant_log_space(log, ticket);
		xfs_log_ticket_put(ticket);
	} else {
		trace_xfs_log_done_perm(log, ticket);

		xlog_regrant_reserve_log_space(log, ticket);
		/* If this ticket was a permanent reservation and we aren't
		 * trying to release it, reset the inited flags; so next time
		 * we write, a start record will be written out.
		 */
		ticket->t_flags |= XLOG_TIC_INITED;
	}

	return lsn;
}

/*
 * Attaches a new iclog I/O completion callback routine during
 * transaction commit.  If the log is in error state, a non-zero
 * return code is handed back and the caller is responsible for
 * executing the callback at an appropriate time.
 */
int
xfs_log_notify(
	struct xfs_mount	*mp,
	struct xlog_in_core	*iclog,
	xfs_log_callback_t	*cb)
{
	int	abortflg;

	spin_lock(&iclog->ic_callback_lock);
	abortflg = (iclog->ic_state & XLOG_STATE_IOERROR);
	if (!abortflg) {
		ASSERT_ALWAYS((iclog->ic_state == XLOG_STATE_ACTIVE) ||
			      (iclog->ic_state == XLOG_STATE_WANT_SYNC));
		cb->cb_next = NULL;
		*(iclog->ic_callback_tail) = cb;
		iclog->ic_callback_tail = &(cb->cb_next);
	}
	spin_unlock(&iclog->ic_callback_lock);
	return abortflg;
}

int
xfs_log_release_iclog(
	struct xfs_mount	*mp,
	struct xlog_in_core	*iclog)
{
	if (xlog_state_release_iclog(mp->m_log, iclog)) {
		xfs_force_shutdown(mp, SHUTDOWN_LOG_IO_ERROR);
		return EIO;
	}

	return 0;
}

/*
 *  1. Reserve an amount of on-disk log space and return a ticket corresponding
 *	to the reservation.
 *  2. Potentially, push buffers at tail of log to disk.
 *
 * Each reservation is going to reserve extra space for a log record header.
 * When writes happen to the on-disk log, we don't subtract the length of the
 * log record header from any reservation.  By wasting space in each
 * reservation, we prevent over allocation problems.
 */
int
xfs_log_reserve(
	struct xfs_mount	*mp,
	int		 	unit_bytes,
	int		 	cnt,
	struct xlog_ticket	**ticket,
	__uint8_t	 	client,
	uint		 	flags,
	uint		 	t_type)
{
	struct log		*log = mp->m_log;
	struct xlog_ticket	*internal_ticket;
	int			retval = 0;

	ASSERT(client == XFS_TRANSACTION || client == XFS_LOG);
	ASSERT((flags & XFS_LOG_NOSLEEP) == 0);

	if (XLOG_FORCED_SHUTDOWN(log))
		return XFS_ERROR(EIO);

	XFS_STATS_INC(xs_try_logspace);


	if (*ticket != NULL) {
		ASSERT(flags & XFS_LOG_PERM_RESERV);
		internal_ticket = *ticket;

		/*
		 * this is a new transaction on the ticket, so we need to
		 * change the transaction ID so that the next transaction has a
		 * different TID in the log. Just add one to the existing tid
		 * so that we can see chains of rolling transactions in the log
		 * easily.
		 */
		internal_ticket->t_tid++;

		trace_xfs_log_reserve(log, internal_ticket);

		xlog_grant_push_ail(mp, internal_ticket->t_unit_res);
		retval = xlog_regrant_write_log_space(log, internal_ticket);
	} else {
		/* may sleep if need to allocate more tickets */
		internal_ticket = xlog_ticket_alloc(log, unit_bytes, cnt,
						  client, flags,
						  KM_SLEEP|KM_MAYFAIL);
		if (!internal_ticket)
			return XFS_ERROR(ENOMEM);
		internal_ticket->t_trans_type = t_type;
		*ticket = internal_ticket;

		trace_xfs_log_reserve(log, internal_ticket);

		xlog_grant_push_ail(mp,
				    (internal_ticket->t_unit_res *
				     internal_ticket->t_cnt));
		retval = xlog_grant_log_space(log, internal_ticket);
	}

	return retval;
}	/* xfs_log_reserve */


/*
 * Mount a log filesystem
 *
 * mp		- ubiquitous xfs mount point structure
 * log_target	- buftarg of on-disk log device
 * blk_offset	- Start block # where block size is 512 bytes (BBSIZE)
 * num_bblocks	- Number of BBSIZE blocks in on-disk log
 *
 * Return error or zero.
 */
int
xfs_log_mount(
	xfs_mount_t	*mp,
	xfs_buftarg_t	*log_target,
	xfs_daddr_t	blk_offset,
	int		num_bblks)
{
	int		error;

	if (!(mp->m_flags & XFS_MOUNT_NORECOVERY))
		cmn_err(CE_NOTE, "XFS mounting filesystem %s", mp->m_fsname);
	else {
		cmn_err(CE_NOTE,
			"!Mounting filesystem \"%s\" in no-recovery mode.  Filesystem will be inconsistent.",
			mp->m_fsname);
		ASSERT(mp->m_flags & XFS_MOUNT_RDONLY);
	}

	mp->m_log = xlog_alloc_log(mp, log_target, blk_offset, num_bblks);
	if (IS_ERR(mp->m_log)) {
		error = -PTR_ERR(mp->m_log);
		goto out;
	}

	/*
	 * Initialize the AIL now we have a log.
	 */
	error = xfs_trans_ail_init(mp);
	if (error) {
		cmn_err(CE_WARN, "XFS: AIL initialisation failed: error %d", error);
		goto out_free_log;
	}
	mp->m_log->l_ailp = mp->m_ail;

	/*
	 * skip log recovery on a norecovery mount.  pretend it all
	 * just worked.
	 */
	if (!(mp->m_flags & XFS_MOUNT_NORECOVERY)) {
		int	readonly = (mp->m_flags & XFS_MOUNT_RDONLY);

		if (readonly)
			mp->m_flags &= ~XFS_MOUNT_RDONLY;

		error = xlog_recover(mp->m_log);

		if (readonly)
			mp->m_flags |= XFS_MOUNT_RDONLY;
		if (error) {
			cmn_err(CE_WARN, "XFS: log mount/recovery failed: error %d", error);
			goto out_destroy_ail;
		}
	}

	/* Normal transactions can now occur */
	mp->m_log->l_flags &= ~XLOG_ACTIVE_RECOVERY;

	/*
	 * Now the log has been fully initialised and we know were our
	 * space grant counters are, we can initialise the permanent ticket
	 * needed for delayed logging to work.
	 */
	xlog_cil_init_post_recovery(mp->m_log);

	return 0;

out_destroy_ail:
	xfs_trans_ail_destroy(mp);
out_free_log:
	xlog_dealloc_log(mp->m_log);
out:
	return error;
}

/*
 * Finish the recovery of the file system.  This is separate from
 * the xfs_log_mount() call, because it depends on the code in
 * xfs_mountfs() to read in the root and real-time bitmap inodes
 * between calling xfs_log_mount() and here.
 *
 * mp		- ubiquitous xfs mount point structure
 */
int
xfs_log_mount_finish(xfs_mount_t *mp)
{
	int	error;

	if (!(mp->m_flags & XFS_MOUNT_NORECOVERY))
		error = xlog_recover_finish(mp->m_log);
	else {
		error = 0;
		ASSERT(mp->m_flags & XFS_MOUNT_RDONLY);
	}

	return error;
}

/*
 * Final log writes as part of unmount.
 *
 * Mark the filesystem clean as unmount happens.  Note that during relocation
 * this routine needs to be executed as part of source-bag while the
 * deallocation must not be done until source-end.
 */

/*
 * Unmount record used to have a string "Unmount filesystem--" in the
 * data section where the "Un" was really a magic number (XLOG_UNMOUNT_TYPE).
 * We just write the magic number now since that particular field isn't
 * currently architecture converted and "nUmount" is a bit foo.
 * As far as I know, there weren't any dependencies on the old behaviour.
 */

int
xfs_log_unmount_write(xfs_mount_t *mp)
{
	xlog_t		 *log = mp->m_log;
	xlog_in_core_t	 *iclog;
#ifdef DEBUG
	xlog_in_core_t	 *first_iclog;
#endif
	xlog_ticket_t	*tic = NULL;
	xfs_lsn_t	 lsn;
	int		 error;

	/*
	 * Don't write out unmount record on read-only mounts.
	 * Or, if we are doing a forced umount (typically because of IO errors).
	 */
	if (mp->m_flags & XFS_MOUNT_RDONLY)
		return 0;

	error = _xfs_log_force(mp, XFS_LOG_SYNC, NULL);
	ASSERT(error || !(XLOG_FORCED_SHUTDOWN(log)));

#ifdef DEBUG
	first_iclog = iclog = log->l_iclog;
	do {
		if (!(iclog->ic_state & XLOG_STATE_IOERROR)) {
			ASSERT(iclog->ic_state & XLOG_STATE_ACTIVE);
			ASSERT(iclog->ic_offset == 0);
		}
		iclog = iclog->ic_next;
	} while (iclog != first_iclog);
#endif
	if (! (XLOG_FORCED_SHUTDOWN(log))) {
		error = xfs_log_reserve(mp, 600, 1, &tic,
					XFS_LOG, 0, XLOG_UNMOUNT_REC_TYPE);
		if (!error) {
			/* the data section must be 32 bit size aligned */
			struct {
			    __uint16_t magic;
			    __uint16_t pad1;
			    __uint32_t pad2; /* may as well make it 64 bits */
			} magic = {
				.magic = XLOG_UNMOUNT_TYPE,
			};
			struct xfs_log_iovec reg = {
				.i_addr = (void *)&magic,
				.i_len = sizeof(magic),
				.i_type = XLOG_REG_TYPE_UNMOUNT,
			};
			struct xfs_log_vec vec = {
				.lv_niovecs = 1,
				.lv_iovecp = &reg,
			};

			/* remove inited flag */
			tic->t_flags = 0;
			error = xlog_write(log, &vec, tic, &lsn,
					   NULL, XLOG_UNMOUNT_TRANS);
			/*
			 * At this point, we're umounting anyway,
			 * so there's no point in transitioning log state
			 * to IOERROR. Just continue...
			 */
		}

		if (error) {
			xfs_fs_cmn_err(CE_ALERT, mp,
				"xfs_log_unmount: unmount record failed");
		}


		spin_lock(&log->l_icloglock);
		iclog = log->l_iclog;
		atomic_inc(&iclog->ic_refcnt);
		xlog_state_want_sync(log, iclog);
		spin_unlock(&log->l_icloglock);
		error = xlog_state_release_iclog(log, iclog);

		spin_lock(&log->l_icloglock);
		if (!(iclog->ic_state == XLOG_STATE_ACTIVE ||
		      iclog->ic_state == XLOG_STATE_DIRTY)) {
			if (!XLOG_FORCED_SHUTDOWN(log)) {
				sv_wait(&iclog->ic_force_wait, PMEM,
					&log->l_icloglock, s);
			} else {
				spin_unlock(&log->l_icloglock);
			}
		} else {
			spin_unlock(&log->l_icloglock);
		}
		if (tic) {
			trace_xfs_log_umount_write(log, tic);
			xlog_ungrant_log_space(log, tic);
			xfs_log_ticket_put(tic);
		}
	} else {
		/*
		 * We're already in forced_shutdown mode, couldn't
		 * even attempt to write out the unmount transaction.
		 *
		 * Go through the motions of sync'ing and releasing
		 * the iclog, even though no I/O will actually happen,
		 * we need to wait for other log I/Os that may already
		 * be in progress.  Do this as a separate section of
		 * code so we'll know if we ever get stuck here that
		 * we're in this odd situation of trying to unmount
		 * a file system that went into forced_shutdown as
		 * the result of an unmount..
		 */
		spin_lock(&log->l_icloglock);
		iclog = log->l_iclog;
		atomic_inc(&iclog->ic_refcnt);

		xlog_state_want_sync(log, iclog);
		spin_unlock(&log->l_icloglock);
		error =  xlog_state_release_iclog(log, iclog);

		spin_lock(&log->l_icloglock);

		if ( ! (   iclog->ic_state == XLOG_STATE_ACTIVE
			|| iclog->ic_state == XLOG_STATE_DIRTY
			|| iclog->ic_state == XLOG_STATE_IOERROR) ) {

				sv_wait(&iclog->ic_force_wait, PMEM,
					&log->l_icloglock, s);
		} else {
			spin_unlock(&log->l_icloglock);
		}
	}

	return error;
}	/* xfs_log_unmount_write */

/*
 * Deallocate log structures for unmount/relocation.
 *
 * We need to stop the aild from running before we destroy
 * and deallocate the log as the aild references the log.
 */
void
xfs_log_unmount(xfs_mount_t *mp)
{
	xfs_trans_ail_destroy(mp);
	xlog_dealloc_log(mp->m_log);
}

void
xfs_log_item_init(
	struct xfs_mount	*mp,
	struct xfs_log_item	*item,
	int			type,
	struct xfs_item_ops	*ops)
{
	item->li_mountp = mp;
	item->li_ailp = mp->m_ail;
	item->li_type = type;
	item->li_ops = ops;
	item->li_lv = NULL;

	INIT_LIST_HEAD(&item->li_ail);
	INIT_LIST_HEAD(&item->li_cil);
}

/*
 * Write region vectors to log.  The write happens using the space reservation
 * of the ticket (tic).  It is not a requirement that all writes for a given
 * transaction occur with one call to xfs_log_write(). However, it is important
 * to note that the transaction reservation code makes an assumption about the
 * number of log headers a transaction requires that may be violated if you
 * don't pass all the transaction vectors in one call....
 */
int
xfs_log_write(
	struct xfs_mount	*mp,
	struct xfs_log_iovec	reg[],
	int			nentries,
	struct xlog_ticket	*tic,
	xfs_lsn_t		*start_lsn)
{
	struct log		*log = mp->m_log;
	int			error;
	struct xfs_log_vec	vec = {
		.lv_niovecs = nentries,
		.lv_iovecp = reg,
	};

	if (XLOG_FORCED_SHUTDOWN(log))
		return XFS_ERROR(EIO);

	error = xlog_write(log, &vec, tic, start_lsn, NULL, 0);
	if (error)
		xfs_force_shutdown(mp, SHUTDOWN_LOG_IO_ERROR);
	return error;
}

void
xfs_log_move_tail(xfs_mount_t	*mp,
		  xfs_lsn_t	tail_lsn)
{
	xlog_ticket_t	*tic;
	xlog_t		*log = mp->m_log;
	int		need_bytes, free_bytes, cycle, bytes;

	if (XLOG_FORCED_SHUTDOWN(log))
		return;

	if (tail_lsn == 0) {
		/* needed since sync_lsn is 64 bits */
		spin_lock(&log->l_icloglock);
		tail_lsn = log->l_last_sync_lsn;
		spin_unlock(&log->l_icloglock);
	}

	spin_lock(&log->l_grant_lock);

	/* Also an invalid lsn.  1 implies that we aren't passing in a valid
	 * tail_lsn.
	 */
	if (tail_lsn != 1) {
		log->l_tail_lsn = tail_lsn;
	}

	if ((tic = log->l_write_headq)) {
#ifdef DEBUG
		if (log->l_flags & XLOG_ACTIVE_RECOVERY)
			panic("Recovery problem");
#endif
		cycle = log->l_grant_write_cycle;
		bytes = log->l_grant_write_bytes;
		free_bytes = xlog_space_left(log, cycle, bytes);
		do {
			ASSERT(tic->t_flags & XLOG_TIC_PERM_RESERV);

			if (free_bytes < tic->t_unit_res && tail_lsn != 1)
				break;
			tail_lsn = 0;
			free_bytes -= tic->t_unit_res;
			sv_signal(&tic->t_wait);
			tic = tic->t_next;
		} while (tic != log->l_write_headq);
	}
	if ((tic = log->l_reserve_headq)) {
#ifdef DEBUG
		if (log->l_flags & XLOG_ACTIVE_RECOVERY)
			panic("Recovery problem");
#endif
		cycle = log->l_grant_reserve_cycle;
		bytes = log->l_grant_reserve_bytes;
		free_bytes = xlog_space_left(log, cycle, bytes);
		do {
			if (tic->t_flags & XLOG_TIC_PERM_RESERV)
				need_bytes = tic->t_unit_res*tic->t_cnt;
			else
				need_bytes = tic->t_unit_res;
			if (free_bytes < need_bytes && tail_lsn != 1)
				break;
			tail_lsn = 0;
			free_bytes -= need_bytes;
			sv_signal(&tic->t_wait);
			tic = tic->t_next;
		} while (tic != log->l_reserve_headq);
	}
	spin_unlock(&log->l_grant_lock);
}	/* xfs_log_move_tail */

/*
 * Determine if we have a transaction that has gone to disk
 * that needs to be covered. To begin the transition to the idle state
 * firstly the log needs to be idle (no AIL and nothing in the iclogs).
 * If we are then in a state where covering is needed, the caller is informed
 * that dummy transactions are required to move the log into the idle state.
 *
 * Because this is called as part of the sync process, we should also indicate
 * that dummy transactions should be issued in anything but the covered or
 * idle states. This ensures that the log tail is accurately reflected in
 * the log at the end of the sync, hence if a crash occurrs avoids replay
 * of transactions where the metadata is already on disk.
 */
int
xfs_log_need_covered(xfs_mount_t *mp)
{
	int		needed = 0;
	xlog_t		*log = mp->m_log;

	if (!xfs_fs_writable(mp))
		return 0;

	spin_lock(&log->l_icloglock);
	switch (log->l_covered_state) {
	case XLOG_STATE_COVER_DONE:
	case XLOG_STATE_COVER_DONE2:
	case XLOG_STATE_COVER_IDLE:
		break;
	case XLOG_STATE_COVER_NEED:
	case XLOG_STATE_COVER_NEED2:
		if (!xfs_trans_ail_tail(log->l_ailp) &&
		    xlog_iclogs_empty(log)) {
			if (log->l_covered_state == XLOG_STATE_COVER_NEED)
				log->l_covered_state = XLOG_STATE_COVER_DONE;
			else
				log->l_covered_state = XLOG_STATE_COVER_DONE2;
		}
		/* FALLTHRU */
	default:
		needed = 1;
		break;
	}
	spin_unlock(&log->l_icloglock);
	return needed;
}

/******************************************************************************
 *
 *	local routines
 *
 ******************************************************************************
 */

/* xfs_trans_tail_ail returns 0 when there is nothing in the list.
 * The log manager must keep track of the last LR which was committed
 * to disk.  The lsn of this LR will become the new tail_lsn whenever
 * xfs_trans_tail_ail returns 0.  If we don't do this, we run into
 * the situation where stuff could be written into the log but nothing
 * was ever in the AIL when asked.  Eventually, we panic since the
 * tail hits the head.
 *
 * We may be holding the log iclog lock upon entering this routine.
 */
xfs_lsn_t
xlog_assign_tail_lsn(xfs_mount_t *mp)
{
	xfs_lsn_t tail_lsn;
	xlog_t	  *log = mp->m_log;

	tail_lsn = xfs_trans_ail_tail(mp->m_ail);
	spin_lock(&log->l_grant_lock);
	if (tail_lsn != 0) {
		log->l_tail_lsn = tail_lsn;
	} else {
		tail_lsn = log->l_tail_lsn = log->l_last_sync_lsn;
	}
	spin_unlock(&log->l_grant_lock);

	return tail_lsn;
}	/* xlog_assign_tail_lsn */


/*
 * Return the space in the log between the tail and the head.  The head
 * is passed in the cycle/bytes formal parms.  In the special case where
 * the reserve head has wrapped passed the tail, this calculation is no
 * longer valid.  In this case, just return 0 which means there is no space
 * in the log.  This works for all places where this function is called
 * with the reserve head.  Of course, if the write head were to ever
 * wrap the tail, we should blow up.  Rather than catch this case here,
 * we depend on other ASSERTions in other parts of the code.   XXXmiken
 *
 * This code also handles the case where the reservation head is behind
 * the tail.  The details of this case are described below, but the end
 * result is that we return the size of the log as the amount of space left.
 */
STATIC int
xlog_space_left(xlog_t *log, int cycle, int bytes)
{
	int free_bytes;
	int tail_bytes;
	int tail_cycle;

	tail_bytes = BBTOB(BLOCK_LSN(log->l_tail_lsn));
	tail_cycle = CYCLE_LSN(log->l_tail_lsn);
	if ((tail_cycle == cycle) && (bytes >= tail_bytes)) {
		free_bytes = log->l_logsize - (bytes - tail_bytes);
	} else if ((tail_cycle + 1) < cycle) {
		return 0;
	} else if (tail_cycle < cycle) {
		ASSERT(tail_cycle == (cycle - 1));
		free_bytes = tail_bytes - bytes;
	} else {
		/*
		 * The reservation head is behind the tail.
		 * In this case we just want to return the size of the
		 * log as the amount of space left.
		 */
		xfs_fs_cmn_err(CE_ALERT, log->l_mp,
			"xlog_space_left: head behind tail\n"
			"  tail_cycle = %d, tail_bytes = %d\n"
			"  GH   cycle = %d, GH   bytes = %d",
			tail_cycle, tail_bytes, cycle, bytes);
		ASSERT(0);
		free_bytes = log->l_logsize;
	}
	return free_bytes;
}	/* xlog_space_left */


/*
 * Log function which is called when an io completes.
 *
 * The log manager needs its own routine, in order to control what
 * happens with the buffer after the write completes.
 */
void
xlog_iodone(xfs_buf_t *bp)
{
	xlog_in_core_t	*iclog;
	xlog_t		*l;
	int		aborted;

	iclog = XFS_BUF_FSPRIVATE(bp, xlog_in_core_t *);
	ASSERT(XFS_BUF_FSPRIVATE2(bp, unsigned long) == (unsigned long) 2);
	XFS_BUF_SET_FSPRIVATE2(bp, (unsigned long)1);
	aborted = 0;
	l = iclog->ic_log;

	/*
	 * If the _XFS_BARRIER_FAILED flag was set by a lower
	 * layer, it means the underlying device no longer supports
	 * barrier I/O. Warn loudly and turn off barriers.
	 */
	if (bp->b_flags & _XFS_BARRIER_FAILED) {
		bp->b_flags &= ~_XFS_BARRIER_FAILED;
		l->l_mp->m_flags &= ~XFS_MOUNT_BARRIER;
		xfs_fs_cmn_err(CE_WARN, l->l_mp,
				"xlog_iodone: Barriers are no longer supported"
				" by device. Disabling barriers\n");
	}

	/*
	 * Race to shutdown the filesystem if we see an error.
	 */
	if (XFS_TEST_ERROR((XFS_BUF_GETERROR(bp)), l->l_mp,
			XFS_ERRTAG_IODONE_IOERR, XFS_RANDOM_IODONE_IOERR)) {
		xfs_ioerror_alert("xlog_iodone", l->l_mp, bp, XFS_BUF_ADDR(bp));
		XFS_BUF_STALE(bp);
		xfs_force_shutdown(l->l_mp, SHUTDOWN_LOG_IO_ERROR);
		/*
		 * This flag will be propagated to the trans-committed
		 * callback routines to let them know that the log-commit
		 * didn't succeed.
		 */
		aborted = XFS_LI_ABORTED;
	} else if (iclog->ic_state & XLOG_STATE_IOERROR) {
		aborted = XFS_LI_ABORTED;
	}

	/* log I/O is always issued ASYNC */
	ASSERT(XFS_BUF_ISASYNC(bp));
	xlog_state_done_syncing(iclog, aborted);
	/*
	 * do not reference the buffer (bp) here as we could race
	 * with it being freed after writing the unmount record to the
	 * log.
	 */

}	/* xlog_iodone */

/*
 * Return size of each in-core log record buffer.
 *
 * All machines get 8 x 32kB buffers by default, unless tuned otherwise.
 *
 * If the filesystem blocksize is too large, we may need to choose a
 * larger size since the directory code currently logs entire blocks.
 */

STATIC void
xlog_get_iclog_buffer_size(xfs_mount_t	*mp,
			   xlog_t	*log)
{
	int size;
	int xhdrs;

	if (mp->m_logbufs <= 0)
		log->l_iclog_bufs = XLOG_MAX_ICLOGS;
	else
		log->l_iclog_bufs = mp->m_logbufs;

	/*
	 * Buffer size passed in from mount system call.
	 */
	if (mp->m_logbsize > 0) {
		size = log->l_iclog_size = mp->m_logbsize;
		log->l_iclog_size_log = 0;
		while (size != 1) {
			log->l_iclog_size_log++;
			size >>= 1;
		}

		if (xfs_sb_version_haslogv2(&mp->m_sb)) {
			/* # headers = size / 32k
			 * one header holds cycles from 32k of data
			 */

			xhdrs = mp->m_logbsize / XLOG_HEADER_CYCLE_SIZE;
			if (mp->m_logbsize % XLOG_HEADER_CYCLE_SIZE)
				xhdrs++;
			log->l_iclog_hsize = xhdrs << BBSHIFT;
			log->l_iclog_heads = xhdrs;
		} else {
			ASSERT(mp->m_logbsize <= XLOG_BIG_RECORD_BSIZE);
			log->l_iclog_hsize = BBSIZE;
			log->l_iclog_heads = 1;
		}
		goto done;
	}

	/* All machines use 32kB buffers by default. */
	log->l_iclog_size = XLOG_BIG_RECORD_BSIZE;
	log->l_iclog_size_log = XLOG_BIG_RECORD_BSHIFT;

	/* the default log size is 16k or 32k which is one header sector */
	log->l_iclog_hsize = BBSIZE;
	log->l_iclog_heads = 1;

done:
	/* are we being asked to make the sizes selected above visible? */
	if (mp->m_logbufs == 0)
		mp->m_logbufs = log->l_iclog_bufs;
	if (mp->m_logbsize == 0)
		mp->m_logbsize = log->l_iclog_size;
}	/* xlog_get_iclog_buffer_size */


/*
 * This routine initializes some of the log structure for a given mount point.
 * Its primary purpose is to fill in enough, so recovery can occur.  However,
 * some other stuff may be filled in too.
 */
STATIC xlog_t *
xlog_alloc_log(xfs_mount_t	*mp,
	       xfs_buftarg_t	*log_target,
	       xfs_daddr_t	blk_offset,
	       int		num_bblks)
{
	xlog_t			*log;
	xlog_rec_header_t	*head;
	xlog_in_core_t		**iclogp;
	xlog_in_core_t		*iclog, *prev_iclog=NULL;
	xfs_buf_t		*bp;
	int			i;
	int			iclogsize;
	int			error = ENOMEM;
	uint			log2_size = 0;

	log = kmem_zalloc(sizeof(xlog_t), KM_MAYFAIL);
	if (!log) {
		xlog_warn("XFS: Log allocation failed: No memory!");
		goto out;
	}

	log->l_mp	   = mp;
	log->l_targ	   = log_target;
	log->l_logsize     = BBTOB(num_bblks);
	log->l_logBBstart  = blk_offset;
	log->l_logBBsize   = num_bblks;
	log->l_covered_state = XLOG_STATE_COVER_IDLE;
	log->l_flags	   |= XLOG_ACTIVE_RECOVERY;

	log->l_prev_block  = -1;
	log->l_tail_lsn	   = xlog_assign_lsn(1, 0);
	/* log->l_tail_lsn = 0x100000000LL; cycle = 1; current block = 0 */
	log->l_last_sync_lsn = log->l_tail_lsn;
	log->l_curr_cycle  = 1;	    /* 0 is bad since this is initial value */
	log->l_grant_reserve_cycle = 1;
	log->l_grant_write_cycle = 1;

	error = EFSCORRUPTED;
	if (xfs_sb_version_hassector(&mp->m_sb)) {
	        log2_size = mp->m_sb.sb_logsectlog;
		if (log2_size < BBSHIFT) {
			xlog_warn("XFS: Log sector size too small "
				"(0x%x < 0x%x)", log2_size, BBSHIFT);
			goto out_free_log;
		}

	        log2_size -= BBSHIFT;
		if (log2_size > mp->m_sectbb_log) {
			xlog_warn("XFS: Log sector size too large "
				"(0x%x > 0x%x)", log2_size, mp->m_sectbb_log);
			goto out_free_log;
		}

		/* for larger sector sizes, must have v2 or external log */
		if (log2_size && log->l_logBBstart > 0 &&
			    !xfs_sb_version_haslogv2(&mp->m_sb)) {

			xlog_warn("XFS: log sector size (0x%x) invalid "
				  "for configuration.", log2_size);
			goto out_free_log;
		}
	}
	log->l_sectBBsize = 1 << log2_size;

	xlog_get_iclog_buffer_size(mp, log);

	error = ENOMEM;
	bp = xfs_buf_get_empty(log->l_iclog_size, mp->m_logdev_targp);
	if (!bp)
		goto out_free_log;
	XFS_BUF_SET_IODONE_FUNC(bp, xlog_iodone);
	XFS_BUF_SET_FSPRIVATE2(bp, (unsigned long)1);
	ASSERT(XFS_BUF_ISBUSY(bp));
	ASSERT(XFS_BUF_VALUSEMA(bp) <= 0);
	log->l_xbuf = bp;

	spin_lock_init(&log->l_icloglock);
	spin_lock_init(&log->l_grant_lock);
	sv_init(&log->l_flush_wait, 0, "flush_wait");

	/* log record size must be multiple of BBSIZE; see xlog_rec_header_t */
	ASSERT((XFS_BUF_SIZE(bp) & BBMASK) == 0);

	iclogp = &log->l_iclog;
	/*
	 * The amount of memory to allocate for the iclog structure is
	 * rather funky due to the way the structure is defined.  It is
	 * done this way so that we can use different sizes for machines
	 * with different amounts of memory.  See the definition of
	 * xlog_in_core_t in xfs_log_priv.h for details.
	 */
	iclogsize = log->l_iclog_size;
	ASSERT(log->l_iclog_size >= 4096);
	for (i=0; i < log->l_iclog_bufs; i++) {
		*iclogp = kmem_zalloc(sizeof(xlog_in_core_t), KM_MAYFAIL);
		if (!*iclogp)
			goto out_free_iclog;

		iclog = *iclogp;
		iclog->ic_prev = prev_iclog;
		prev_iclog = iclog;

		bp = xfs_buf_get_noaddr(log->l_iclog_size, mp->m_logdev_targp);
		if (!bp)
			goto out_free_iclog;
		if (!XFS_BUF_CPSEMA(bp))
			ASSERT(0);
		XFS_BUF_SET_IODONE_FUNC(bp, xlog_iodone);
		XFS_BUF_SET_FSPRIVATE2(bp, (unsigned long)1);
		iclog->ic_bp = bp;
		iclog->ic_data = bp->b_addr;
#ifdef DEBUG
		log->l_iclog_bak[i] = (xfs_caddr_t)&(iclog->ic_header);
#endif
		head = &iclog->ic_header;
		memset(head, 0, sizeof(xlog_rec_header_t));
		head->h_magicno = cpu_to_be32(XLOG_HEADER_MAGIC_NUM);
		head->h_version = cpu_to_be32(
			xfs_sb_version_haslogv2(&log->l_mp->m_sb) ? 2 : 1);
		head->h_size = cpu_to_be32(log->l_iclog_size);
		/* new fields */
		head->h_fmt = cpu_to_be32(XLOG_FMT);
		memcpy(&head->h_fs_uuid, &mp->m_sb.sb_uuid, sizeof(uuid_t));

		iclog->ic_size = XFS_BUF_SIZE(bp) - log->l_iclog_hsize;
		iclog->ic_state = XLOG_STATE_ACTIVE;
		iclog->ic_log = log;
		atomic_set(&iclog->ic_refcnt, 0);
		spin_lock_init(&iclog->ic_callback_lock);
		iclog->ic_callback_tail = &(iclog->ic_callback);
		iclog->ic_datap = (char *)iclog->ic_data + log->l_iclog_hsize;

		ASSERT(XFS_BUF_ISBUSY(iclog->ic_bp));
		ASSERT(XFS_BUF_VALUSEMA(iclog->ic_bp) <= 0);
		sv_init(&iclog->ic_force_wait, SV_DEFAULT, "iclog-force");
		sv_init(&iclog->ic_write_wait, SV_DEFAULT, "iclog-write");

		iclogp = &iclog->ic_next;
	}
	*iclogp = log->l_iclog;			/* complete ring */
	log->l_iclog->ic_prev = prev_iclog;	/* re-write 1st prev ptr */

	error = xlog_cil_init(log);
	if (error)
		goto out_free_iclog;
	return log;

out_free_iclog:
	for (iclog = log->l_iclog; iclog; iclog = prev_iclog) {
		prev_iclog = iclog->ic_next;
		if (iclog->ic_bp) {
			sv_destroy(&iclog->ic_force_wait);
			sv_destroy(&iclog->ic_write_wait);
			xfs_buf_free(iclog->ic_bp);
		}
		kmem_free(iclog);
	}
	spinlock_destroy(&log->l_icloglock);
	spinlock_destroy(&log->l_grant_lock);
	xfs_buf_free(log->l_xbuf);
out_free_log:
	kmem_free(log);
out:
	return ERR_PTR(-error);
}	/* xlog_alloc_log */


/*
 * Write out the commit record of a transaction associated with the given
 * ticket.  Return the lsn of the commit record.
 */
STATIC int
xlog_commit_record(
	struct log		*log,
	struct xlog_ticket	*ticket,
	struct xlog_in_core	**iclog,
	xfs_lsn_t		*commitlsnp)
{
	struct xfs_mount *mp = log->l_mp;
	int	error;
	struct xfs_log_iovec reg = {
		.i_addr = NULL,
		.i_len = 0,
		.i_type = XLOG_REG_TYPE_COMMIT,
	};
	struct xfs_log_vec vec = {
		.lv_niovecs = 1,
		.lv_iovecp = &reg,
	};

	ASSERT_ALWAYS(iclog);
	error = xlog_write(log, &vec, ticket, commitlsnp, iclog,
					XLOG_COMMIT_TRANS);
	if (error)
		xfs_force_shutdown(mp, SHUTDOWN_LOG_IO_ERROR);
	return error;
}

/*
 * Push on the buffer cache code if we ever use more than 75% of the on-disk
 * log space.  This code pushes on the lsn which would supposedly free up
 * the 25% which we want to leave free.  We may need to adopt a policy which
 * pushes on an lsn which is further along in the log once we reach the high
 * water mark.  In this manner, we would be creating a low water mark.
 */
STATIC void
xlog_grant_push_ail(xfs_mount_t	*mp,
		    int		need_bytes)
{
    xlog_t	*log = mp->m_log;	/* pointer to the log */
    xfs_lsn_t	tail_lsn;		/* lsn of the log tail */
    xfs_lsn_t	threshold_lsn = 0;	/* lsn we'd like to be at */
    int		free_blocks;		/* free blocks left to write to */
    int		free_bytes;		/* free bytes left to write to */
    int		threshold_block;	/* block in lsn we'd like to be at */
    int		threshold_cycle;	/* lsn cycle we'd like to be at */
    int		free_threshold;

    ASSERT(BTOBB(need_bytes) < log->l_logBBsize);

    spin_lock(&log->l_grant_lock);
    free_bytes = xlog_space_left(log,
				 log->l_grant_reserve_cycle,
				 log->l_grant_reserve_bytes);
    tail_lsn = log->l_tail_lsn;
    free_blocks = BTOBBT(free_bytes);

    /*
     * Set the threshold for the minimum number of free blocks in the
     * log to the maximum of what the caller needs, one quarter of the
     * log, and 256 blocks.
     */
    free_threshold = BTOBB(need_bytes);
    free_threshold = MAX(free_threshold, (log->l_logBBsize >> 2));
    free_threshold = MAX(free_threshold, 256);
    if (free_blocks < free_threshold) {
	threshold_block = BLOCK_LSN(tail_lsn) + free_threshold;
	threshold_cycle = CYCLE_LSN(tail_lsn);
	if (threshold_block >= log->l_logBBsize) {
	    threshold_block -= log->l_logBBsize;
	    threshold_cycle += 1;
	}
	threshold_lsn = xlog_assign_lsn(threshold_cycle, threshold_block);

	/* Don't pass in an lsn greater than the lsn of the last
	 * log record known to be on disk.
	 */
	if (XFS_LSN_CMP(threshold_lsn, log->l_last_sync_lsn) > 0)
	    threshold_lsn = log->l_last_sync_lsn;
    }
    spin_unlock(&log->l_grant_lock);

    /*
     * Get the transaction layer to kick the dirty buffers out to
     * disk asynchronously. No point in trying to do this if
     * the filesystem is shutting down.
     */
    if (threshold_lsn &&
	!XLOG_FORCED_SHUTDOWN(log))
	    xfs_trans_ail_push(log->l_ailp, threshold_lsn);
}	/* xlog_grant_push_ail */

/*
 * The bdstrat callback function for log bufs. This gives us a central
 * place to trap bufs in case we get hit by a log I/O error and need to
 * shutdown. Actually, in practice, even when we didn't get a log error,
 * we transition the iclogs to IOERROR state *after* flushing all existing
 * iclogs to disk. This is because we don't want anymore new transactions to be
 * started or completed afterwards.
 */
STATIC int
xlog_bdstrat(
	struct xfs_buf		*bp)
{
	struct xlog_in_core	*iclog;

	iclog = XFS_BUF_FSPRIVATE(bp, xlog_in_core_t *);
	if (iclog->ic_state & XLOG_STATE_IOERROR) {
		XFS_BUF_ERROR(bp, EIO);
		XFS_BUF_STALE(bp);
		xfs_biodone(bp);
		/*
		 * It would seem logical to return EIO here, but we rely on
		 * the log state machine to propagate I/O errors instead of
		 * doing it here.
		 */
		return 0;
	}

	bp->b_flags |= _XBF_RUN_QUEUES;
	xfs_buf_iorequest(bp);
	return 0;
}

/*
 * Flush out the in-core log (iclog) to the on-disk log in an asynchronous 
 * fashion.  Previously, we should have moved the current iclog
 * ptr in the log to point to the next available iclog.  This allows further
 * write to continue while this code syncs out an iclog ready to go.
 * Before an in-core log can be written out, the data section must be scanned
 * to save away the 1st word of each BBSIZE block into the header.  We replace
 * it with the current cycle count.  Each BBSIZE block is tagged with the
 * cycle count because there in an implicit assumption that drives will
 * guarantee that entire 512 byte blocks get written at once.  In other words,
 * we can't have part of a 512 byte block written and part not written.  By
 * tagging each block, we will know which blocks are valid when recovering
 * after an unclean shutdown.
 *
 * This routine is single threaded on the iclog.  No other thread can be in
 * this routine with the same iclog.  Changing contents of iclog can there-
 * fore be done without grabbing the state machine lock.  Updating the global
 * log will require grabbing the lock though.
 *
 * The entire log manager uses a logical block numbering scheme.  Only
 * log_sync (and then only bwrite()) know about the fact that the log may
 * not start with block zero on a given device.  The log block start offset
 * is added immediately before calling bwrite().
 */

STATIC int
xlog_sync(xlog_t		*log,
	  xlog_in_core_t	*iclog)
{
	xfs_caddr_t	dptr;		/* pointer to byte sized element */
	xfs_buf_t	*bp;
	int		i;
	uint		count;		/* byte count of bwrite */
	uint		count_init;	/* initial count before roundup */
	int		roundoff;       /* roundoff to BB or stripe */
	int		split = 0;	/* split write into two regions */
	int		error;
	int		v2 = xfs_sb_version_haslogv2(&log->l_mp->m_sb);

	XFS_STATS_INC(xs_log_writes);
	ASSERT(atomic_read(&iclog->ic_refcnt) == 0);

	/* Add for LR header */
	count_init = log->l_iclog_hsize + iclog->ic_offset;

	/* Round out the log write size */
	if (v2 && log->l_mp->m_sb.sb_logsunit > 1) {
		/* we have a v2 stripe unit to use */
		count = XLOG_LSUNITTOB(log, XLOG_BTOLSUNIT(log, count_init));
	} else {
		count = BBTOB(BTOBB(count_init));
	}
	roundoff = count - count_init;
	ASSERT(roundoff >= 0);
	ASSERT((v2 && log->l_mp->m_sb.sb_logsunit > 1 && 
                roundoff < log->l_mp->m_sb.sb_logsunit)
		|| 
		(log->l_mp->m_sb.sb_logsunit <= 1 && 
		 roundoff < BBTOB(1)));

	/* move grant heads by roundoff in sync */
	spin_lock(&log->l_grant_lock);
	xlog_grant_add_space(log, roundoff);
	spin_unlock(&log->l_grant_lock);

	/* put cycle number in every block */
	xlog_pack_data(log, iclog, roundoff); 

	/* real byte length */
	if (v2) {
		iclog->ic_header.h_len =
			cpu_to_be32(iclog->ic_offset + roundoff);
	} else {
		iclog->ic_header.h_len =
			cpu_to_be32(iclog->ic_offset);
	}

	bp = iclog->ic_bp;
	ASSERT(XFS_BUF_FSPRIVATE2(bp, unsigned long) == (unsigned long)1);
	XFS_BUF_SET_FSPRIVATE2(bp, (unsigned long)2);
	XFS_BUF_SET_ADDR(bp, BLOCK_LSN(be64_to_cpu(iclog->ic_header.h_lsn)));

	XFS_STATS_ADD(xs_log_blocks, BTOBB(count));

	/* Do we need to split this write into 2 parts? */
	if (XFS_BUF_ADDR(bp) + BTOBB(count) > log->l_logBBsize) {
		split = count - (BBTOB(log->l_logBBsize - XFS_BUF_ADDR(bp)));
		count = BBTOB(log->l_logBBsize - XFS_BUF_ADDR(bp));
		iclog->ic_bwritecnt = 2;	/* split into 2 writes */
	} else {
		iclog->ic_bwritecnt = 1;
	}
	XFS_BUF_SET_COUNT(bp, count);
	XFS_BUF_SET_FSPRIVATE(bp, iclog);	/* save for later */
	XFS_BUF_ZEROFLAGS(bp);
	XFS_BUF_BUSY(bp);
	XFS_BUF_ASYNC(bp);
	bp->b_flags |= XBF_LOG_BUFFER;
	/*
	 * Do an ordered write for the log block.
	 * Its unnecessary to flush the first split block in the log wrap case.
	 */
	if (!split && (log->l_mp->m_flags & XFS_MOUNT_BARRIER))
		XFS_BUF_ORDERED(bp);

	ASSERT(XFS_BUF_ADDR(bp) <= log->l_logBBsize-1);
	ASSERT(XFS_BUF_ADDR(bp) + BTOBB(count) <= log->l_logBBsize);

	xlog_verify_iclog(log, iclog, count, B_TRUE);

	/* account for log which doesn't start at block #0 */
	XFS_BUF_SET_ADDR(bp, XFS_BUF_ADDR(bp) + log->l_logBBstart);
	/*
	 * Don't call xfs_bwrite here. We do log-syncs even when the filesystem
	 * is shutting down.
	 */
	XFS_BUF_WRITE(bp);

	if ((error = xlog_bdstrat(bp))) {
		xfs_ioerror_alert("xlog_sync", log->l_mp, bp,
				  XFS_BUF_ADDR(bp));
		return error;
	}
	if (split) {
		bp = iclog->ic_log->l_xbuf;
		ASSERT(XFS_BUF_FSPRIVATE2(bp, unsigned long) ==
							(unsigned long)1);
		XFS_BUF_SET_FSPRIVATE2(bp, (unsigned long)2);
		XFS_BUF_SET_ADDR(bp, 0);	     /* logical 0 */
		XFS_BUF_SET_PTR(bp, (xfs_caddr_t)((__psint_t)&(iclog->ic_header)+
					    (__psint_t)count), split);
		XFS_BUF_SET_FSPRIVATE(bp, iclog);
		XFS_BUF_ZEROFLAGS(bp);
		XFS_BUF_BUSY(bp);
		XFS_BUF_ASYNC(bp);
		bp->b_flags |= XBF_LOG_BUFFER;
		if (log->l_mp->m_flags & XFS_MOUNT_BARRIER)
			XFS_BUF_ORDERED(bp);
		dptr = XFS_BUF_PTR(bp);
		/*
		 * Bump the cycle numbers at the start of each block
		 * since this part of the buffer is at the start of
		 * a new cycle.  Watch out for the header magic number
		 * case, though.
		 */
		for (i = 0; i < split; i += BBSIZE) {
			be32_add_cpu((__be32 *)dptr, 1);
			if (be32_to_cpu(*(__be32 *)dptr) == XLOG_HEADER_MAGIC_NUM)
				be32_add_cpu((__be32 *)dptr, 1);
			dptr += BBSIZE;
		}

		ASSERT(XFS_BUF_ADDR(bp) <= log->l_logBBsize-1);
		ASSERT(XFS_BUF_ADDR(bp) + BTOBB(count) <= log->l_logBBsize);

		/* account for internal log which doesn't start at block #0 */
		XFS_BUF_SET_ADDR(bp, XFS_BUF_ADDR(bp) + log->l_logBBstart);
		XFS_BUF_WRITE(bp);
		if ((error = xlog_bdstrat(bp))) {
			xfs_ioerror_alert("xlog_sync (split)", log->l_mp,
					  bp, XFS_BUF_ADDR(bp));
			return error;
		}
	}
	return 0;
}	/* xlog_sync */


/*
 * Deallocate a log structure
 */
STATIC void
xlog_dealloc_log(xlog_t *log)
{
	xlog_in_core_t	*iclog, *next_iclog;
	int		i;

	xlog_cil_destroy(log);

	iclog = log->l_iclog;
	for (i=0; i<log->l_iclog_bufs; i++) {
		sv_destroy(&iclog->ic_force_wait);
		sv_destroy(&iclog->ic_write_wait);
		xfs_buf_free(iclog->ic_bp);
		next_iclog = iclog->ic_next;
		kmem_free(iclog);
		iclog = next_iclog;
	}
	spinlock_destroy(&log->l_icloglock);
	spinlock_destroy(&log->l_grant_lock);

	xfs_buf_free(log->l_xbuf);
	log->l_mp->m_log = NULL;
	kmem_free(log);
}	/* xlog_dealloc_log */

/*
 * Update counters atomically now that memcpy is done.
 */
/* ARGSUSED */
static inline void
xlog_state_finish_copy(xlog_t		*log,
		       xlog_in_core_t	*iclog,
		       int		record_cnt,
		       int		copy_bytes)
{
	spin_lock(&log->l_icloglock);

	be32_add_cpu(&iclog->ic_header.h_num_logops, record_cnt);
	iclog->ic_offset += copy_bytes;

	spin_unlock(&log->l_icloglock);
}	/* xlog_state_finish_copy */




/*
 * print out info relating to regions written which consume
 * the reservation
 */
void
xlog_print_tic_res(
	struct xfs_mount	*mp,
	struct xlog_ticket	*ticket)
{
	uint i;
	uint ophdr_spc = ticket->t_res_num_ophdrs * (uint)sizeof(xlog_op_header_t);

	/* match with XLOG_REG_TYPE_* in xfs_log.h */
	static char *res_type_str[XLOG_REG_TYPE_MAX] = {
	    "bformat",
	    "bchunk",
	    "efi_format",
	    "efd_format",
	    "iformat",
	    "icore",
	    "iext",
	    "ibroot",
	    "ilocal",
	    "iattr_ext",
	    "iattr_broot",
	    "iattr_local",
	    "qformat",
	    "dquot",
	    "quotaoff",
	    "LR header",
	    "unmount",
	    "commit",
	    "trans header"
	};
	static char *trans_type_str[XFS_TRANS_TYPE_MAX] = {
	    "SETATTR_NOT_SIZE",
	    "SETATTR_SIZE",
	    "INACTIVE",
	    "CREATE",
	    "CREATE_TRUNC",
	    "TRUNCATE_FILE",
	    "REMOVE",
	    "LINK",
	    "RENAME",
	    "MKDIR",
	    "RMDIR",
	    "SYMLINK",
	    "SET_DMATTRS",
	    "GROWFS",
	    "STRAT_WRITE",
	    "DIOSTRAT",
	    "WRITE_SYNC",
	    "WRITEID",
	    "ADDAFORK",
	    "ATTRINVAL",
	    "ATRUNCATE",
	    "ATTR_SET",
	    "ATTR_RM",
	    "ATTR_FLAG",
	    "CLEAR_AGI_BUCKET",
	    "QM_SBCHANGE",
	    "DUMMY1",
	    "DUMMY2",
	    "QM_QUOTAOFF",
	    "QM_DQALLOC",
	    "QM_SETQLIM",
	    "QM_DQCLUSTER",
	    "QM_QINOCREATE",
	    "QM_QUOTAOFF_END",
	    "SB_UNIT",
	    "FSYNC_TS",
	    "GROWFSRT_ALLOC",
	    "GROWFSRT_ZERO",
	    "GROWFSRT_FREE",
	    "SWAPEXT"
	};

	xfs_fs_cmn_err(CE_WARN, mp,
			"xfs_log_write: reservation summary:\n"
			"  trans type  = %s (%u)\n"
			"  unit res    = %d bytes\n"
			"  current res = %d bytes\n"
			"  total reg   = %u bytes (o/flow = %u bytes)\n"
			"  ophdrs      = %u (ophdr space = %u bytes)\n"
			"  ophdr + reg = %u bytes\n"
			"  num regions = %u\n",
			((ticket->t_trans_type <= 0 ||
			  ticket->t_trans_type > XFS_TRANS_TYPE_MAX) ?
			  "bad-trans-type" : trans_type_str[ticket->t_trans_type-1]),
			ticket->t_trans_type,
			ticket->t_unit_res,
			ticket->t_curr_res,
			ticket->t_res_arr_sum, ticket->t_res_o_flow,
			ticket->t_res_num_ophdrs, ophdr_spc,
			ticket->t_res_arr_sum + 
			ticket->t_res_o_flow + ophdr_spc,
			ticket->t_res_num);

	for (i = 0; i < ticket->t_res_num; i++) {
		uint r_type = ticket->t_res_arr[i].r_type; 
		cmn_err(CE_WARN,
			    "region[%u]: %s - %u bytes\n",
			    i, 
			    ((r_type <= 0 || r_type > XLOG_REG_TYPE_MAX) ?
			    "bad-rtype" : res_type_str[r_type-1]),
			    ticket->t_res_arr[i].r_len);
	}

	xfs_cmn_err(XFS_PTAG_LOGRES, CE_ALERT, mp,
		"xfs_log_write: reservation ran out. Need to up reservation");
	xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
}

/*
 * Calculate the potential space needed by the log vector.  Each region gets
 * its own xlog_op_header_t and may need to be double word aligned.
 */
static int
xlog_write_calc_vec_length(
	struct xlog_ticket	*ticket,
	struct xfs_log_vec	*log_vector)
{
	struct xfs_log_vec	*lv;
	int			headers = 0;
	int			len = 0;
	int			i;

	/* acct for start rec of xact */
	if (ticket->t_flags & XLOG_TIC_INITED)
		headers++;

	for (lv = log_vector; lv; lv = lv->lv_next) {
		headers += lv->lv_niovecs;

		for (i = 0; i < lv->lv_niovecs; i++) {
			struct xfs_log_iovec	*vecp = &lv->lv_iovecp[i];

			len += vecp->i_len;
			xlog_tic_add_region(ticket, vecp->i_len, vecp->i_type);
		}
	}

	ticket->t_res_num_ophdrs += headers;
	len += headers * sizeof(struct xlog_op_header);

	return len;
}

/*
 * If first write for transaction, insert start record  We can't be trying to
 * commit if we are inited.  We can't have any "partial_copy" if we are inited.
 */
static int
xlog_write_start_rec(
	struct xlog_op_header	*ophdr,
	struct xlog_ticket	*ticket)
{
	if (!(ticket->t_flags & XLOG_TIC_INITED))
		return 0;

	ophdr->oh_tid	= cpu_to_be32(ticket->t_tid);
	ophdr->oh_clientid = ticket->t_clientid;
	ophdr->oh_len = 0;
	ophdr->oh_flags = XLOG_START_TRANS;
	ophdr->oh_res2 = 0;

	ticket->t_flags &= ~XLOG_TIC_INITED;

	return sizeof(struct xlog_op_header);
}

static xlog_op_header_t *
xlog_write_setup_ophdr(
	struct log		*log,
	struct xlog_op_header	*ophdr,
	struct xlog_ticket	*ticket,
	uint			flags)
{
	ophdr->oh_tid = cpu_to_be32(ticket->t_tid);
	ophdr->oh_clientid = ticket->t_clientid;
	ophdr->oh_res2 = 0;

	/* are we copying a commit or unmount record? */
	ophdr->oh_flags = flags;

	/*
	 * We've seen logs corrupted with bad transaction client ids.  This
	 * makes sure that XFS doesn't generate them on.  Turn this into an EIO
	 * and shut down the filesystem.
	 */
	switch (ophdr->oh_clientid)  {
	case XFS_TRANSACTION:
	case XFS_VOLUME:
	case XFS_LOG:
		break;
	default:
		xfs_fs_cmn_err(CE_WARN, log->l_mp,
			"Bad XFS transaction clientid 0x%x in ticket 0x%p",
			ophdr->oh_clientid, ticket);
		return NULL;
	}

	return ophdr;
}

/*
 * Set up the parameters of the region copy into the log. This has
 * to handle region write split across multiple log buffers - this
 * state is kept external to this function so that this code can
 * can be written in an obvious, self documenting manner.
 */
static int
xlog_write_setup_copy(
	struct xlog_ticket	*ticket,
	struct xlog_op_header	*ophdr,
	int			space_available,
	int			space_required,
	int			*copy_off,
	int			*copy_len,
	int			*last_was_partial_copy,
	int			*bytes_consumed)
{
	int			still_to_copy;

	still_to_copy = space_required - *bytes_consumed;
	*copy_off = *bytes_consumed;

	if (still_to_copy <= space_available) {
		/* write of region completes here */
		*copy_len = still_to_copy;
		ophdr->oh_len = cpu_to_be32(*copy_len);
		if (*last_was_partial_copy)
			ophdr->oh_flags |= (XLOG_END_TRANS|XLOG_WAS_CONT_TRANS);
		*last_was_partial_copy = 0;
		*bytes_consumed = 0;
		return 0;
	}

	/* partial write of region, needs extra log op header reservation */
	*copy_len = space_available;
	ophdr->oh_len = cpu_to_be32(*copy_len);
	ophdr->oh_flags |= XLOG_CONTINUE_TRANS;
	if (*last_was_partial_copy)
		ophdr->oh_flags |= XLOG_WAS_CONT_TRANS;
	*bytes_consumed += *copy_len;
	(*last_was_partial_copy)++;

	/* account for new log op header */
	ticket->t_curr_res -= sizeof(struct xlog_op_header);
	ticket->t_res_num_ophdrs++;

	return sizeof(struct xlog_op_header);
}

static int
xlog_write_copy_finish(
	struct log		*log,
	struct xlog_in_core	*iclog,
	uint			flags,
	int			*record_cnt,
	int			*data_cnt,
	int			*partial_copy,
	int			*partial_copy_len,
	int			log_offset,
	struct xlog_in_core	**commit_iclog)
{
	if (*partial_copy) {
		/*
		 * This iclog has already been marked WANT_SYNC by
		 * xlog_state_get_iclog_space.
		 */
		xlog_state_finish_copy(log, iclog, *record_cnt, *data_cnt);
		*record_cnt = 0;
		*data_cnt = 0;
		return xlog_state_release_iclog(log, iclog);
	}

	*partial_copy = 0;
	*partial_copy_len = 0;

	if (iclog->ic_size - log_offset <= sizeof(xlog_op_header_t)) {
		/* no more space in this iclog - push it. */
		xlog_state_finish_copy(log, iclog, *record_cnt, *data_cnt);
		*record_cnt = 0;
		*data_cnt = 0;

		spin_lock(&log->l_icloglock);
		xlog_state_want_sync(log, iclog);
		spin_unlock(&log->l_icloglock);

		if (!commit_iclog)
			return xlog_state_release_iclog(log, iclog);
		ASSERT(flags & XLOG_COMMIT_TRANS);
		*commit_iclog = iclog;
	}

	return 0;
}

/*
 * Write some region out to in-core log
 *
 * This will be called when writing externally provided regions or when
 * writing out a commit record for a given transaction.
 *
 * General algorithm:
 *	1. Find total length of this write.  This may include adding to the
 *		lengths passed in.
 *	2. Check whether we violate the tickets reservation.
 *	3. While writing to this iclog
 *	    A. Reserve as much space in this iclog as can get
 *	    B. If this is first write, save away start lsn
 *	    C. While writing this region:
 *		1. If first write of transaction, write start record
 *		2. Write log operation header (header per region)
 *		3. Find out if we can fit entire region into this iclog
 *		4. Potentially, verify destination memcpy ptr
 *		5. Memcpy (partial) region
 *		6. If partial copy, release iclog; otherwise, continue
 *			copying more regions into current iclog
 *	4. Mark want sync bit (in simulation mode)
 *	5. Release iclog for potential flush to on-disk log.
 *
 * ERRORS:
 * 1.	Panic if reservation is overrun.  This should never happen since
 *	reservation amounts are generated internal to the filesystem.
 * NOTES:
 * 1. Tickets are single threaded data structures.
 * 2. The XLOG_END_TRANS & XLOG_CONTINUE_TRANS flags are passed down to the
 *	syncing routine.  When a single log_write region needs to span
 *	multiple in-core logs, the XLOG_CONTINUE_TRANS bit should be set
 *	on all log operation writes which don't contain the end of the
 *	region.  The XLOG_END_TRANS bit is used for the in-core log
 *	operation which contains the end of the continued log_write region.
 * 3. When xlog_state_get_iclog_space() grabs the rest of the current iclog,
 *	we don't really know exactly how much space will be used.  As a result,
 *	we don't update ic_offset until the end when we know exactly how many
 *	bytes have been written out.
 */
int
xlog_write(
	struct log		*log,
	struct xfs_log_vec	*log_vector,
	struct xlog_ticket	*ticket,
	xfs_lsn_t		*start_lsn,
	struct xlog_in_core	**commit_iclog,
	uint			flags)
{
	struct xlog_in_core	*iclog = NULL;
	struct xfs_log_iovec	*vecp;
	struct xfs_log_vec	*lv;
	int			len;
	int			index;
	int			partial_copy = 0;
	int			partial_copy_len = 0;
	int			contwr = 0;
	int			record_cnt = 0;
	int			data_cnt = 0;
	int			error;

	*start_lsn = 0;

	len = xlog_write_calc_vec_length(ticket, log_vector);
	if (log->l_cilp) {
		/*
		 * Region headers and bytes are already accounted for.
		 * We only need to take into account start records and
		 * split regions in this function.
		 */
		if (ticket->t_flags & XLOG_TIC_INITED)
			ticket->t_curr_res -= sizeof(xlog_op_header_t);

		/*
		 * Commit record headers need to be accounted for. These
		 * come in as separate writes so are easy to detect.
		 */
		if (flags & (XLOG_COMMIT_TRANS | XLOG_UNMOUNT_TRANS))
			ticket->t_curr_res -= sizeof(xlog_op_header_t);
	} else
		ticket->t_curr_res -= len;

	if (ticket->t_curr_res < 0)
		xlog_print_tic_res(log->l_mp, ticket);

	index = 0;
	lv = log_vector;
	vecp = lv->lv_iovecp;
	while (lv && index < lv->lv_niovecs) {
		void		*ptr;
		int		log_offset;

		error = xlog_state_get_iclog_space(log, len, &iclog, ticket,
						   &contwr, &log_offset);
		if (error)
			return error;

		ASSERT(log_offset <= iclog->ic_size - 1);
		ptr = iclog->ic_datap + log_offset;

		/* start_lsn is the first lsn written to. That's all we need. */
		if (!*start_lsn)
			*start_lsn = be64_to_cpu(iclog->ic_header.h_lsn);

		/*
		 * This loop writes out as many regions as can fit in the amount
		 * of space which was allocated by xlog_state_get_iclog_space().
		 */
		while (lv && index < lv->lv_niovecs) {
			struct xfs_log_iovec	*reg = &vecp[index];
			struct xlog_op_header	*ophdr;
			int			start_rec_copy;
			int			copy_len;
			int			copy_off;

			ASSERT(reg->i_len % sizeof(__int32_t) == 0);
			ASSERT((unsigned long)ptr % sizeof(__int32_t) == 0);

			start_rec_copy = xlog_write_start_rec(ptr, ticket);
			if (start_rec_copy) {
				record_cnt++;
				xlog_write_adv_cnt(&ptr, &len, &log_offset,
						   start_rec_copy);
			}

			ophdr = xlog_write_setup_ophdr(log, ptr, ticket, flags);
			if (!ophdr)
				return XFS_ERROR(EIO);

			xlog_write_adv_cnt(&ptr, &len, &log_offset,
					   sizeof(struct xlog_op_header));

			len += xlog_write_setup_copy(ticket, ophdr,
						     iclog->ic_size-log_offset,
						     reg->i_len,
						     &copy_off, &copy_len,
						     &partial_copy,
						     &partial_copy_len);
			xlog_verify_dest_ptr(log, ptr);

			/* copy region */
			ASSERT(copy_len >= 0);
			memcpy(ptr, reg->i_addr + copy_off, copy_len);
			xlog_write_adv_cnt(&ptr, &len, &log_offset, copy_len);

			copy_len += start_rec_copy + sizeof(xlog_op_header_t);
			record_cnt++;
			data_cnt += contwr ? copy_len : 0;

			error = xlog_write_copy_finish(log, iclog, flags,
						       &record_cnt, &data_cnt,
						       &partial_copy,
						       &partial_copy_len,
						       log_offset,
						       commit_iclog);
			if (error)
				return error;

			/*
			 * if we had a partial copy, we need to get more iclog
			 * space but we don't want to increment the region
			 * index because there is still more is this region to
			 * write.
			 *
			 * If we completed writing this region, and we flushed
			 * the iclog (indicated by resetting of the record
			 * count), then we also need to get more log space. If
			 * this was the last record, though, we are done and
			 * can just return.
			 */
			if (partial_copy)
				break;

			if (++index == lv->lv_niovecs) {
				lv = lv->lv_next;
				index = 0;
				if (lv)
					vecp = lv->lv_iovecp;
			}
			if (record_cnt == 0) {
				if (!lv)
					return 0;
				break;
			}
		}
	}

	ASSERT(len == 0);

	xlog_state_finish_copy(log, iclog, record_cnt, data_cnt);
	if (!commit_iclog)
		return xlog_state_release_iclog(log, iclog);

	ASSERT(flags & XLOG_COMMIT_TRANS);
	*commit_iclog = iclog;
	return 0;
}


/*****************************************************************************
 *
 *		State Machine functions
 *
 *****************************************************************************
 */

/* Clean iclogs starting from the head.  This ordering must be
 * maintained, so an iclog doesn't become ACTIVE beyond one that
 * is SYNCING.  This is also required to maintain the notion that we use
 * a ordered wait queue to hold off would be writers to the log when every
 * iclog is trying to sync to disk.
 *
 * State Change: DIRTY -> ACTIVE
 */
STATIC void
xlog_state_clean_log(xlog_t *log)
{
	xlog_in_core_t	*iclog;
	int changed = 0;

	iclog = log->l_iclog;
	do {
		if (iclog->ic_state == XLOG_STATE_DIRTY) {
			iclog->ic_state	= XLOG_STATE_ACTIVE;
			iclog->ic_offset       = 0;
			ASSERT(iclog->ic_callback == NULL);
			/*
			 * If the number of ops in this iclog indicate it just
			 * contains the dummy transaction, we can
			 * change state into IDLE (the second time around).
			 * Otherwise we should change the state into
			 * NEED a dummy.
			 * We don't need to cover the dummy.
			 */
			if (!changed &&
			   (be32_to_cpu(iclog->ic_header.h_num_logops) ==
			   		XLOG_COVER_OPS)) {
				changed = 1;
			} else {
				/*
				 * We have two dirty iclogs so start over
				 * This could also be num of ops indicates
				 * this is not the dummy going out.
				 */
				changed = 2;
			}
			iclog->ic_header.h_num_logops = 0;
			memset(iclog->ic_header.h_cycle_data, 0,
			      sizeof(iclog->ic_header.h_cycle_data));
			iclog->ic_header.h_lsn = 0;
		} else if (iclog->ic_state == XLOG_STATE_ACTIVE)
			/* do nothing */;
		else
			break;	/* stop cleaning */
		iclog = iclog->ic_next;
	} while (iclog != log->l_iclog);

	/* log is locked when we are called */
	/*
	 * Change state for the dummy log recording.
	 * We usually go to NEED. But we go to NEED2 if the changed indicates
	 * we are done writing the dummy record.
	 * If we are done with the second dummy recored (DONE2), then
	 * we go to IDLE.
	 */
	if (changed) {
		switch (log->l_covered_state) {
		case XLOG_STATE_COVER_IDLE:
		case XLOG_STATE_COVER_NEED:
		case XLOG_STATE_COVER_NEED2:
			log->l_covered_state = XLOG_STATE_COVER_NEED;
			break;

		case XLOG_STATE_COVER_DONE:
			if (changed == 1)
				log->l_covered_state = XLOG_STATE_COVER_NEED2;
			else
				log->l_covered_state = XLOG_STATE_COVER_NEED;
			break;

		case XLOG_STATE_COVER_DONE2:
			if (changed == 1)
				log->l_covered_state = XLOG_STATE_COVER_IDLE;
			else
				log->l_covered_state = XLOG_STATE_COVER_NEED;
			break;

		default:
			ASSERT(0);
		}
	}
}	/* xlog_state_clean_log */

STATIC xfs_lsn_t
xlog_get_lowest_lsn(
	xlog_t		*log)
{
	xlog_in_core_t  *lsn_log;
	xfs_lsn_t	lowest_lsn, lsn;

	lsn_log = log->l_iclog;
	lowest_lsn = 0;
	do {
	    if (!(lsn_log->ic_state & (XLOG_STATE_ACTIVE|XLOG_STATE_DIRTY))) {
		lsn = be64_to_cpu(lsn_log->ic_header.h_lsn);
		if ((lsn && !lowest_lsn) ||
		    (XFS_LSN_CMP(lsn, lowest_lsn) < 0)) {
			lowest_lsn = lsn;
		}
	    }
	    lsn_log = lsn_log->ic_next;
	} while (lsn_log != log->l_iclog);
	return lowest_lsn;
}


STATIC void
xlog_state_do_callback(
	xlog_t		*log,
	int		aborted,
	xlog_in_core_t	*ciclog)
{
	xlog_in_core_t	   *iclog;
	xlog_in_core_t	   *first_iclog;	/* used to know when we've
						 * processed all iclogs once */
	xfs_log_callback_t *cb, *cb_next;
	int		   flushcnt = 0;
	xfs_lsn_t	   lowest_lsn;
	int		   ioerrors;	/* counter: iclogs with errors */
	int		   loopdidcallbacks; /* flag: inner loop did callbacks*/
	int		   funcdidcallbacks; /* flag: function did callbacks */
	int		   repeats;	/* for issuing console warnings if
					 * looping too many times */
	int		   wake = 0;

	spin_lock(&log->l_icloglock);
	first_iclog = iclog = log->l_iclog;
	ioerrors = 0;
	funcdidcallbacks = 0;
	repeats = 0;

	do {
		/*
		 * Scan all iclogs starting with the one pointed to by the
		 * log.  Reset this starting point each time the log is
		 * unlocked (during callbacks).
		 *
		 * Keep looping through iclogs until one full pass is made
		 * without running any callbacks.
		 */
		first_iclog = log->l_iclog;
		iclog = log->l_iclog;
		loopdidcallbacks = 0;
		repeats++;

		do {

			/* skip all iclogs in the ACTIVE & DIRTY states */
			if (iclog->ic_state &
			    (XLOG_STATE_ACTIVE|XLOG_STATE_DIRTY)) {
				iclog = iclog->ic_next;
				continue;
			}

			/*
			 * Between marking a filesystem SHUTDOWN and stopping
			 * the log, we do flush all iclogs to disk (if there
			 * wasn't a log I/O error). So, we do want things to
			 * go smoothly in case of just a SHUTDOWN  w/o a
			 * LOG_IO_ERROR.
			 */
			if (!(iclog->ic_state & XLOG_STATE_IOERROR)) {
				/*
				 * Can only perform callbacks in order.  Since
				 * this iclog is not in the DONE_SYNC/
				 * DO_CALLBACK state, we skip the rest and
				 * just try to clean up.  If we set our iclog
				 * to DO_CALLBACK, we will not process it when
				 * we retry since a previous iclog is in the
				 * CALLBACK and the state cannot change since
				 * we are holding the l_icloglock.
				 */
				if (!(iclog->ic_state &
					(XLOG_STATE_DONE_SYNC |
						 XLOG_STATE_DO_CALLBACK))) {
					if (ciclog && (ciclog->ic_state ==
							XLOG_STATE_DONE_SYNC)) {
						ciclog->ic_state = XLOG_STATE_DO_CALLBACK;
					}
					break;
				}
				/*
				 * We now have an iclog that is in either the
				 * DO_CALLBACK or DONE_SYNC states. The other
				 * states (WANT_SYNC, SYNCING, or CALLBACK were
				 * caught by the above if and are going to
				 * clean (i.e. we aren't doing their callbacks)
				 * see the above if.
				 */

				/*
				 * We will do one more check here to see if we
				 * have chased our tail around.
				 */

				lowest_lsn = xlog_get_lowest_lsn(log);
				if (lowest_lsn &&
				    XFS_LSN_CMP(lowest_lsn,
				    		be64_to_cpu(iclog->ic_header.h_lsn)) < 0) {
					iclog = iclog->ic_next;
					continue; /* Leave this iclog for
						   * another thread */
				}

				iclog->ic_state = XLOG_STATE_CALLBACK;

				spin_unlock(&log->l_icloglock);

				/* l_last_sync_lsn field protected by
				 * l_grant_lock. Don't worry about iclog's lsn.
				 * No one else can be here except us.
				 */
				spin_lock(&log->l_grant_lock);
				ASSERT(XFS_LSN_CMP(log->l_last_sync_lsn,
				       be64_to_cpu(iclog->ic_header.h_lsn)) <= 0);
				log->l_last_sync_lsn =
					be64_to_cpu(iclog->ic_header.h_lsn);
				spin_unlock(&log->l_grant_lock);

			} else {
				spin_unlock(&log->l_icloglock);
				ioerrors++;
			}

			/*
			 * Keep processing entries in the callback list until
			 * we come around and it is empty.  We need to
			 * atomically see that the list is empty and change the
			 * state to DIRTY so that we don't miss any more
			 * callbacks being added.
			 */
			spin_lock(&iclog->ic_callback_lock);
			cb = iclog->ic_callback;
			while (cb) {
				iclog->ic_callback_tail = &(iclog->ic_callback);
				iclog->ic_callback = NULL;
				spin_unlock(&iclog->ic_callback_lock);

				/* perform callbacks in the order given */
				for (; cb; cb = cb_next) {
					cb_next = cb->cb_next;
					cb->cb_func(cb->cb_arg, aborted);
				}
				spin_lock(&iclog->ic_callback_lock);
				cb = iclog->ic_callback;
			}

			loopdidcallbacks++;
			funcdidcallbacks++;