aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/mtd/nand
diff options
context:
space:
mode:
authorArtem B. Bityuckiy <dedekind@infradead.org>2005-02-11 05:14:15 -0500
committerThomas Gleixner <tglx@mtd.linutronix.de>2005-05-23 06:32:18 -0400
commiteeada24da8bd23fcf6acd2729be054ea99b301bb (patch)
treec5d3cdffbfc11ec2ee82d64aef4177e92dfdffc7 /drivers/mtd/nand
parent41ce921440bd14d9b69b19fbf47d9278582739fe (diff)
[MTD] NAND: Read only OOB bytes during bad block scan
When scanning NAND for bad blocks, don't read the whole page, read only needed OOB bytes instead. Also check the return code of the nand_read_raw() function. Correctly free the this->bbt array in case of failure. Tested with Large page NAND. Fix debugging message. Signed-off-by: Artem B. Bityuckiy <dedekind@infradead.org> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Diffstat (limited to 'drivers/mtd/nand')
-rw-r--r--drivers/mtd/nand/nand_bbt.c52
1 files changed, 38 insertions, 14 deletions
diff --git a/drivers/mtd/nand/nand_bbt.c b/drivers/mtd/nand/nand_bbt.c
index 9a1949751c1f..5ff6eba8bec6 100644
--- a/drivers/mtd/nand/nand_bbt.c
+++ b/drivers/mtd/nand/nand_bbt.c
@@ -6,7 +6,7 @@
6 * 6 *
7 * Copyright (C) 2004 Thomas Gleixner (tglx@linutronix.de) 7 * Copyright (C) 2004 Thomas Gleixner (tglx@linutronix.de)
8 * 8 *
9 * $Id: nand_bbt.c,v 1.28 2004/11/13 10:19:09 gleixner Exp $ 9 * $Id: nand_bbt.c,v 1.30 2005/02/11 10:14:12 dedekind Exp $
10 * 10 *
11 * This program is free software; you can redistribute it and/or modify 11 * This program is free software; you can redistribute it and/or modify
12 * it under the terms of the GNU General Public License version 2 as 12 * it under the terms of the GNU General Public License version 2 as
@@ -252,10 +252,10 @@ static int read_abs_bbts (struct mtd_info *mtd, uint8_t *buf, struct nand_bbt_de
252 * Create a bad block table by scanning the device 252 * Create a bad block table by scanning the device
253 * for the given good/bad block identify pattern 253 * for the given good/bad block identify pattern
254 */ 254 */
255static void create_bbt (struct mtd_info *mtd, uint8_t *buf, struct nand_bbt_descr *bd, int chip) 255static int create_bbt (struct mtd_info *mtd, uint8_t *buf, struct nand_bbt_descr *bd, int chip)
256{ 256{
257 struct nand_chip *this = mtd->priv; 257 struct nand_chip *this = mtd->priv;
258 int i, j, numblocks, len, scanlen; 258 int i, j, numblocks, len, scanlen, pagelen;
259 int startblock; 259 int startblock;
260 loff_t from; 260 loff_t from;
261 size_t readlen, ooblen; 261 size_t readlen, ooblen;
@@ -270,9 +270,18 @@ static void create_bbt (struct mtd_info *mtd, uint8_t *buf, struct nand_bbt_desc
270 else 270 else
271 len = 1; 271 len = 1;
272 } 272 }
273 scanlen = mtd->oobblock + mtd->oobsize; 273
274 readlen = len * mtd->oobblock; 274 if (bd->options == 0) {
275 ooblen = len * mtd->oobsize; 275 /* Memory-based BBT. We may read only needed bytes from the OOB area to
276 * test if block is bad, no need to read the whole page content. */
277 scanlen = ooblen = pagelen = 0;
278 readlen = bd->len;
279 } else {
280 scanlen = mtd->oobblock + mtd->oobsize;
281 readlen = len * mtd->oobblock;
282 ooblen = len * mtd->oobsize;
283 pagelen = mtd->oobblock;
284 }
276 285
277 if (chip == -1) { 286 if (chip == -1) {
278 /* Note that numblocks is 2 * (real numblocks) here, see i+=2 below as it 287 /* Note that numblocks is 2 * (real numblocks) here, see i+=2 below as it
@@ -284,7 +293,7 @@ static void create_bbt (struct mtd_info *mtd, uint8_t *buf, struct nand_bbt_desc
284 if (chip >= this->numchips) { 293 if (chip >= this->numchips) {
285 printk (KERN_WARNING "create_bbt(): chipnr (%d) > available chips (%d)\n", 294 printk (KERN_WARNING "create_bbt(): chipnr (%d) > available chips (%d)\n",
286 chip + 1, this->numchips); 295 chip + 1, this->numchips);
287 return; 296 return -EINVAL;
288 } 297 }
289 numblocks = this->chipsize >> (this->bbt_erase_shift - 1); 298 numblocks = this->chipsize >> (this->bbt_erase_shift - 1);
290 startblock = chip * numblocks; 299 startblock = chip * numblocks;
@@ -293,9 +302,18 @@ static void create_bbt (struct mtd_info *mtd, uint8_t *buf, struct nand_bbt_desc
293 } 302 }
294 303
295 for (i = startblock; i < numblocks;) { 304 for (i = startblock; i < numblocks;) {
296 nand_read_raw (mtd, buf, from, readlen, ooblen); 305 int ret;
306
307 if (bd->options == 0) {
308 size_t retlen;
309 if ((ret = mtd->read_oob(mtd, from + bd->offs, bd->len, &retlen, &buf[bd->offs])))
310 return ret;
311 } else {
312 if ((ret = nand_read_raw (mtd, buf, from, readlen, ooblen)))
313 return ret;
314 }
297 for (j = 0; j < len; j++) { 315 for (j = 0; j < len; j++) {
298 if (check_pattern (&buf[j * scanlen], scanlen, mtd->oobblock, bd)) { 316 if (check_pattern (&buf[j * scanlen], scanlen, pagelen, bd)) {
299 this->bbt[i >> 3] |= 0x03 << (i & 0x6); 317 this->bbt[i >> 3] |= 0x03 << (i & 0x6);
300 printk (KERN_WARNING "Bad eraseblock %d at 0x%08x\n", 318 printk (KERN_WARNING "Bad eraseblock %d at 0x%08x\n",
301 i >> 1, (unsigned int) from); 319 i >> 1, (unsigned int) from);
@@ -305,6 +323,7 @@ static void create_bbt (struct mtd_info *mtd, uint8_t *buf, struct nand_bbt_desc
305 i += 2; 323 i += 2;
306 from += (1 << this->bbt_erase_shift); 324 from += (1 << this->bbt_erase_shift);
307 } 325 }
326 return 0;
308} 327}
309 328
310/** 329/**
@@ -595,8 +614,7 @@ static int nand_memory_bbt (struct mtd_info *mtd, struct nand_bbt_descr *bd)
595 614
596 /* Ensure that we only scan for the pattern and nothing else */ 615 /* Ensure that we only scan for the pattern and nothing else */
597 bd->options = 0; 616 bd->options = 0;
598 create_bbt (mtd, this->data_buf, bd, -1); 617 return create_bbt (mtd, this->data_buf, bd, -1);
599 return 0;
600} 618}
601 619
602/** 620/**
@@ -808,8 +826,14 @@ int nand_scan_bbt (struct mtd_info *mtd, struct nand_bbt_descr *bd)
808 /* If no primary table decriptor is given, scan the device 826 /* If no primary table decriptor is given, scan the device
809 * to build a memory based bad block table 827 * to build a memory based bad block table
810 */ 828 */
811 if (!td) 829 if (!td) {
812 return nand_memory_bbt(mtd, bd); 830 if ((res = nand_memory_bbt(mtd, bd))) {
831 printk (KERN_ERR "nand_bbt: Can't scan flash and build the RAM-based BBT\n");
832 kfree (this->bbt);
833 this->bbt = NULL;
834 }
835 return res;
836 }
813 837
814 /* Allocate a temporary buffer for one eraseblock incl. oob */ 838 /* Allocate a temporary buffer for one eraseblock incl. oob */
815 len = (1 << this->bbt_erase_shift); 839 len = (1 << this->bbt_erase_shift);
@@ -1042,7 +1066,7 @@ int nand_isbad_bbt (struct mtd_info *mtd, loff_t offs, int allowbbt)
1042 res = (this->bbt[block >> 3] >> (block & 0x06)) & 0x03; 1066 res = (this->bbt[block >> 3] >> (block & 0x06)) & 0x03;
1043 1067
1044 DEBUG (MTD_DEBUG_LEVEL2, "nand_isbad_bbt(): bbt info for offs 0x%08x: (block %d) 0x%02x\n", 1068 DEBUG (MTD_DEBUG_LEVEL2, "nand_isbad_bbt(): bbt info for offs 0x%08x: (block %d) 0x%02x\n",
1045 (unsigned int)offs, res, block >> 1); 1069 (unsigned int)offs, block >> 1, res);
1046 1070
1047 switch ((int)res) { 1071 switch ((int)res) {
1048 case 0x00: return 0; 1072 case 0x00: return 0;
href='#n1291'>1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 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
/*
 *	Linux INET6 implementation
 *	FIB front-end.
 *
 *	Authors:
 *	Pedro Roque		<roque@di.fc.ul.pt>
 *
 *	$Id: route.c,v 1.56 2001/10/31 21:55:55 davem Exp $
 *
 *	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.
 */

/*	Changes:
 *
 *	YOSHIFUJI Hideaki @USAGI
 *		reworked default router selection.
 *		- respect outgoing interface
 *		- select from (probably) reachable routers (i.e.
 *		routers in REACHABLE, STALE, DELAY or PROBE states).
 *		- always select the same router if it is (probably)
 *		reachable.  otherwise, round-robin the list.
 *	Ville Nuorvala
 *		Fixed routing subtrees.
 */

#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/times.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/route.h>
#include <linux/netdevice.h>
#include <linux/in6.h>
#include <linux/init.h>
#include <linux/if_arp.h>

#ifdef 	CONFIG_PROC_FS
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#endif

#include <net/net_namespace.h>
#include <net/snmp.h>
#include <net/ipv6.h>
#include <net/ip6_fib.h>
#include <net/ip6_route.h>
#include <net/ndisc.h>
#include <net/addrconf.h>
#include <net/tcp.h>
#include <linux/rtnetlink.h>
#include <net/dst.h>
#include <net/xfrm.h>
#include <net/netevent.h>
#include <net/netlink.h>

#include <asm/uaccess.h>

#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif

/* Set to 3 to get tracing. */
#define RT6_DEBUG 2

#if RT6_DEBUG >= 3
#define RDBG(x) printk x
#define RT6_TRACE(x...) printk(KERN_DEBUG x)
#else
#define RDBG(x)
#define RT6_TRACE(x...) do { ; } while (0)
#endif

#define CLONE_OFFLINK_ROUTE 0

static int ip6_rt_max_size = 4096;
static int ip6_rt_gc_min_interval = HZ / 2;
static int ip6_rt_gc_timeout = 60*HZ;
int ip6_rt_gc_interval = 30*HZ;
static int ip6_rt_gc_elasticity = 9;
static int ip6_rt_mtu_expires = 10*60*HZ;
static int ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40;

static struct rt6_info * ip6_rt_copy(struct rt6_info *ort);
static struct dst_entry	*ip6_dst_check(struct dst_entry *dst, u32 cookie);
static struct dst_entry *ip6_negative_advice(struct dst_entry *);
static void		ip6_dst_destroy(struct dst_entry *);
static void		ip6_dst_ifdown(struct dst_entry *,
				       struct net_device *dev, int how);
static int		 ip6_dst_gc(void);

static int		ip6_pkt_discard(struct sk_buff *skb);
static int		ip6_pkt_discard_out(struct sk_buff *skb);
static void		ip6_link_failure(struct sk_buff *skb);
static void		ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu);

#ifdef CONFIG_IPV6_ROUTE_INFO
static struct rt6_info *rt6_add_route_info(struct in6_addr *prefix, int prefixlen,
					   struct in6_addr *gwaddr, int ifindex,
					   unsigned pref);
static struct rt6_info *rt6_get_route_info(struct in6_addr *prefix, int prefixlen,
					   struct in6_addr *gwaddr, int ifindex);
#endif

static struct dst_ops ip6_dst_ops = {
	.family			=	AF_INET6,
	.protocol		=	__constant_htons(ETH_P_IPV6),
	.gc			=	ip6_dst_gc,
	.gc_thresh		=	1024,
	.check			=	ip6_dst_check,
	.destroy		=	ip6_dst_destroy,
	.ifdown			=	ip6_dst_ifdown,
	.negative_advice	=	ip6_negative_advice,
	.link_failure		=	ip6_link_failure,
	.update_pmtu		=	ip6_rt_update_pmtu,
	.entry_size		=	sizeof(struct rt6_info),
};

static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
{
}

static struct dst_ops ip6_dst_blackhole_ops = {
	.family			=	AF_INET6,
	.protocol		=	__constant_htons(ETH_P_IPV6),
	.destroy		=	ip6_dst_destroy,
	.check			=	ip6_dst_check,
	.update_pmtu		=	ip6_rt_blackhole_update_pmtu,
	.entry_size		=	sizeof(struct rt6_info),
};

struct rt6_info ip6_null_entry = {
	.u = {
		.dst = {
			.__refcnt	= ATOMIC_INIT(1),
			.__use		= 1,
			.obsolete	= -1,
			.error		= -ENETUNREACH,
			.metrics	= { [RTAX_HOPLIMIT - 1] = 255, },
			.input		= ip6_pkt_discard,
			.output		= ip6_pkt_discard_out,
			.ops		= &ip6_dst_ops,
			.path		= (struct dst_entry*)&ip6_null_entry,
		}
	},
	.rt6i_flags	= (RTF_REJECT | RTF_NONEXTHOP),
	.rt6i_metric	= ~(u32) 0,
	.rt6i_ref	= ATOMIC_INIT(1),
};

#ifdef CONFIG_IPV6_MULTIPLE_TABLES

static int ip6_pkt_prohibit(struct sk_buff *skb);
static int ip6_pkt_prohibit_out(struct sk_buff *skb);
static int ip6_pkt_blk_hole(struct sk_buff *skb);

struct rt6_info ip6_prohibit_entry = {
	.u = {
		.dst = {
			.__refcnt	= ATOMIC_INIT(1),
			.__use		= 1,
			.obsolete	= -1,
			.error		= -EACCES,
			.metrics	= { [RTAX_HOPLIMIT - 1] = 255, },
			.input		= ip6_pkt_prohibit,
			.output		= ip6_pkt_prohibit_out,
			.ops		= &ip6_dst_ops,
			.path		= (struct dst_entry*)&ip6_prohibit_entry,
		}
	},
	.rt6i_flags	= (RTF_REJECT | RTF_NONEXTHOP),
	.rt6i_metric	= ~(u32) 0,
	.rt6i_ref	= ATOMIC_INIT(1),
};

struct rt6_info ip6_blk_hole_entry = {
	.u = {
		.dst = {
			.__refcnt	= ATOMIC_INIT(1),
			.__use		= 1,
			.obsolete	= -1,
			.error		= -EINVAL,
			.metrics	= { [RTAX_HOPLIMIT - 1] = 255, },
			.input		= ip6_pkt_blk_hole,
			.output		= ip6_pkt_blk_hole,
			.ops		= &ip6_dst_ops,
			.path		= (struct dst_entry*)&ip6_blk_hole_entry,
		}
	},
	.rt6i_flags	= (RTF_REJECT | RTF_NONEXTHOP),
	.rt6i_metric	= ~(u32) 0,
	.rt6i_ref	= ATOMIC_INIT(1),
};

#endif

/* allocate dst with ip6_dst_ops */
static __inline__ struct rt6_info *ip6_dst_alloc(void)
{
	return (struct rt6_info *)dst_alloc(&ip6_dst_ops);
}

static void ip6_dst_destroy(struct dst_entry *dst)
{
	struct rt6_info *rt = (struct rt6_info *)dst;
	struct inet6_dev *idev = rt->rt6i_idev;

	if (idev != NULL) {
		rt->rt6i_idev = NULL;
		in6_dev_put(idev);
	}
}

static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
			   int how)
{
	struct rt6_info *rt = (struct rt6_info *)dst;
	struct inet6_dev *idev = rt->rt6i_idev;

	if (dev != init_net.loopback_dev && idev != NULL && idev->dev == dev) {
		struct inet6_dev *loopback_idev = in6_dev_get(init_net.loopback_dev);
		if (loopback_idev != NULL) {
			rt->rt6i_idev = loopback_idev;
			in6_dev_put(idev);
		}
	}
}

static __inline__ int rt6_check_expired(const struct rt6_info *rt)
{
	return (rt->rt6i_flags & RTF_EXPIRES &&
		time_after(jiffies, rt->rt6i_expires));
}

static inline int rt6_need_strict(struct in6_addr *daddr)
{
	return (ipv6_addr_type(daddr) &
		(IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL));
}

/*
 *	Route lookup. Any table->tb6_lock is implied.
 */

static __inline__ struct rt6_info *rt6_device_match(struct rt6_info *rt,
						    int oif,
						    int strict)
{
	struct rt6_info *local = NULL;
	struct rt6_info *sprt;

	if (oif) {
		for (sprt = rt; sprt; sprt = sprt->u.dst.rt6_next) {
			struct net_device *dev = sprt->rt6i_dev;
			if (dev->ifindex == oif)
				return sprt;
			if (dev->flags & IFF_LOOPBACK) {
				if (sprt->rt6i_idev == NULL ||
				    sprt->rt6i_idev->dev->ifindex != oif) {
					if (strict && oif)
						continue;
					if (local && (!oif ||
						      local->rt6i_idev->dev->ifindex == oif))
						continue;
				}
				local = sprt;
			}
		}

		if (local)
			return local;

		if (strict)
			return &ip6_null_entry;
	}
	return rt;
}

#ifdef CONFIG_IPV6_ROUTER_PREF
static void rt6_probe(struct rt6_info *rt)
{
	struct neighbour *neigh = rt ? rt->rt6i_nexthop : NULL;
	/*
	 * Okay, this does not seem to be appropriate
	 * for now, however, we need to check if it
	 * is really so; aka Router Reachability Probing.
	 *
	 * Router Reachability Probe MUST be rate-limited
	 * to no more than one per minute.
	 */
	if (!neigh || (neigh->nud_state & NUD_VALID))
		return;
	read_lock_bh(&neigh->lock);
	if (!(neigh->nud_state & NUD_VALID) &&
	    time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) {
		struct in6_addr mcaddr;
		struct in6_addr *target;

		neigh->updated = jiffies;
		read_unlock_bh(&neigh->lock);

		target = (struct in6_addr *)&neigh->primary_key;
		addrconf_addr_solict_mult(target, &mcaddr);
		ndisc_send_ns(rt->rt6i_dev, NULL, target, &mcaddr, NULL);
	} else
		read_unlock_bh(&neigh->lock);
}
#else
static inline void rt6_probe(struct rt6_info *rt)
{
	return;
}
#endif

/*
 * Default Router Selection (RFC 2461 6.3.6)
 */
static inline int rt6_check_dev(struct rt6_info *rt, int oif)
{
	struct net_device *dev = rt->rt6i_dev;
	if (!oif || dev->ifindex == oif)
		return 2;
	if ((dev->flags & IFF_LOOPBACK) &&
	    rt->rt6i_idev && rt->rt6i_idev->dev->ifindex == oif)
		return 1;
	return 0;
}

static inline int rt6_check_neigh(struct rt6_info *rt)
{
	struct neighbour *neigh = rt->rt6i_nexthop;
	int m = 0;
	if (rt->rt6i_flags & RTF_NONEXTHOP ||
	    !(rt->rt6i_flags & RTF_GATEWAY))
		m = 1;
	else if (neigh) {
		read_lock_bh(&neigh->lock);
		if (neigh->nud_state & NUD_VALID)
			m = 2;
		else if (!(neigh->nud_state & NUD_FAILED))
			m = 1;
		read_unlock_bh(&neigh->lock);
	}
	return m;
}

static int rt6_score_route(struct rt6_info *rt, int oif,
			   int strict)
{
	int m, n;

	m = rt6_check_dev(rt, oif);
	if (!m && (strict & RT6_LOOKUP_F_IFACE))
		return -1;
#ifdef CONFIG_IPV6_ROUTER_PREF
	m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(rt->rt6i_flags)) << 2;
#endif
	n = rt6_check_neigh(rt);
	if (!n && (strict & RT6_LOOKUP_F_REACHABLE))
		return -1;
	return m;
}

static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict,
				   int *mpri, struct rt6_info *match)
{
	int m;

	if (rt6_check_expired(rt))
		goto out;

	m = rt6_score_route(rt, oif, strict);
	if (m < 0)
		goto out;

	if (m > *mpri) {
		if (strict & RT6_LOOKUP_F_REACHABLE)
			rt6_probe(match);
		*mpri = m;
		match = rt;
	} else if (strict & RT6_LOOKUP_F_REACHABLE) {
		rt6_probe(rt);
	}

out:
	return match;
}

static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
				     struct rt6_info *rr_head,
				     u32 metric, int oif, int strict)
{
	struct rt6_info *rt, *match;
	int mpri = -1;

	match = NULL;
	for (rt = rr_head; rt && rt->rt6i_metric == metric;
	     rt = rt->u.dst.rt6_next)
		match = find_match(rt, oif, strict, &mpri, match);
	for (rt = fn->leaf; rt && rt != rr_head && rt->rt6i_metric == metric;
	     rt = rt->u.dst.rt6_next)
		match = find_match(rt, oif, strict, &mpri, match);

	return match;
}

static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict)
{
	struct rt6_info *match, *rt0;

	RT6_TRACE("%s(fn->leaf=%p, oif=%d)\n",
		  __FUNCTION__, fn->leaf, oif);

	rt0 = fn->rr_ptr;
	if (!rt0)
		fn->rr_ptr = rt0 = fn->leaf;

	match = find_rr_leaf(fn, rt0, rt0->rt6i_metric, oif, strict);

	if (!match &&
	    (strict & RT6_LOOKUP_F_REACHABLE)) {
		struct rt6_info *next = rt0->u.dst.rt6_next;

		/* no entries matched; do round-robin */
		if (!next || next->rt6i_metric != rt0->rt6i_metric)
			next = fn->leaf;

		if (next != rt0)
			fn->rr_ptr = next;
	}

	RT6_TRACE("%s() => %p\n",
		  __FUNCTION__, match);

	return (match ? match : &ip6_null_entry);
}

#ifdef CONFIG_IPV6_ROUTE_INFO
int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
		  struct in6_addr *gwaddr)
{
	struct route_info *rinfo = (struct route_info *) opt;
	struct in6_addr prefix_buf, *prefix;
	unsigned int pref;
	u32 lifetime;
	struct rt6_info *rt;

	if (len < sizeof(struct route_info)) {
		return -EINVAL;
	}

	/* Sanity check for prefix_len and length */
	if (rinfo->length > 3) {
		return -EINVAL;
	} else if (rinfo->prefix_len > 128) {
		return -EINVAL;
	} else if (rinfo->prefix_len > 64) {
		if (rinfo->length < 2) {
			return -EINVAL;
		}
	} else if (rinfo->prefix_len > 0) {
		if (rinfo->length < 1) {
			return -EINVAL;
		}
	}

	pref = rinfo->route_pref;
	if (pref == ICMPV6_ROUTER_PREF_INVALID)
		pref = ICMPV6_ROUTER_PREF_MEDIUM;

	lifetime = ntohl(rinfo->lifetime);
	if (lifetime == 0xffffffff) {
		/* infinity */
	} else if (lifetime > 0x7fffffff/HZ) {
		/* Avoid arithmetic overflow */
		lifetime = 0x7fffffff/HZ - 1;
	}

	if (rinfo->length == 3)
		prefix = (struct in6_addr *)rinfo->prefix;
	else {
		/* this function is safe */
		ipv6_addr_prefix(&prefix_buf,
				 (struct in6_addr *)rinfo->prefix,
				 rinfo->prefix_len);
		prefix = &prefix_buf;
	}

	rt = rt6_get_route_info(prefix, rinfo->prefix_len, gwaddr, dev->ifindex);

	if (rt && !lifetime) {
		ip6_del_rt(rt);
		rt = NULL;
	}

	if (!rt && lifetime)
		rt = rt6_add_route_info(prefix, rinfo->prefix_len, gwaddr, dev->ifindex,
					pref);
	else if (rt)
		rt->rt6i_flags = RTF_ROUTEINFO |
				 (rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref);

	if (rt) {
		if (lifetime == 0xffffffff) {
			rt->rt6i_flags &= ~RTF_EXPIRES;
		} else {
			rt->rt6i_expires = jiffies + HZ * lifetime;
			rt->rt6i_flags |= RTF_EXPIRES;
		}
		dst_release(&rt->u.dst);
	}
	return 0;
}
#endif

#define BACKTRACK(saddr) \
do { \
	if (rt == &ip6_null_entry) { \
		struct fib6_node *pn; \
		while (1) { \
			if (fn->fn_flags & RTN_TL_ROOT) \
				goto out; \
			pn = fn->parent; \
			if (FIB6_SUBTREE(pn) && FIB6_SUBTREE(pn) != fn) \
				fn = fib6_lookup(FIB6_SUBTREE(pn), NULL, saddr); \
			else \
				fn = pn; \
			if (fn->fn_flags & RTN_RTINFO) \
				goto restart; \
		} \
	} \
} while(0)

static struct rt6_info *ip6_pol_route_lookup(struct fib6_table *table,
					     struct flowi *fl, int flags)
{
	struct fib6_node *fn;
	struct rt6_info *rt;

	read_lock_bh(&table->tb6_lock);
	fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src);
restart:
	rt = fn->leaf;
	rt = rt6_device_match(rt, fl->oif, flags);
	BACKTRACK(&fl->fl6_src);
out:
	dst_hold(&rt->u.dst);
	read_unlock_bh(&table->tb6_lock);

	rt->u.dst.lastuse = jiffies;
	rt->u.dst.__use++;

	return rt;

}

struct rt6_info *rt6_lookup(struct in6_addr *daddr, struct in6_addr *saddr,
			    int oif, int strict)
{
	struct flowi fl = {
		.oif = oif,
		.nl_u = {
			.ip6_u = {
				.daddr = *daddr,
			},
		},
	};
	struct dst_entry *dst;
	int flags = strict ? RT6_LOOKUP_F_IFACE : 0;

	if (saddr) {
		memcpy(&fl.fl6_src, saddr, sizeof(*saddr));
		flags |= RT6_LOOKUP_F_HAS_SADDR;
	}

	dst = fib6_rule_lookup(&fl, flags, ip6_pol_route_lookup);
	if (dst->error == 0)
		return (struct rt6_info *) dst;

	dst_release(dst);

	return NULL;
}

EXPORT_SYMBOL(rt6_lookup);

/* ip6_ins_rt is called with FREE table->tb6_lock.
   It takes new route entry, the addition fails by any reason the
   route is freed. In any case, if caller does not hold it, it may
   be destroyed.
 */

static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info)
{
	int err;
	struct fib6_table *table;

	table = rt->rt6i_table;
	write_lock_bh(&table->tb6_lock);
	err = fib6_add(&table->tb6_root, rt, info);
	write_unlock_bh(&table->tb6_lock);

	return err;
}

int ip6_ins_rt(struct rt6_info *rt)
{
	return __ip6_ins_rt(rt, NULL);
}

static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *daddr,
				      struct in6_addr *saddr)
{
	struct rt6_info *rt;

	/*
	 *	Clone the route.
	 */

	rt = ip6_rt_copy(ort);

	if (rt) {
		if (!(rt->rt6i_flags&RTF_GATEWAY)) {
			if (rt->rt6i_dst.plen != 128 &&
			    ipv6_addr_equal(&rt->rt6i_dst.addr, daddr))
				rt->rt6i_flags |= RTF_ANYCAST;
			ipv6_addr_copy(&rt->rt6i_gateway, daddr);
		}

		ipv6_addr_copy(&rt->rt6i_dst.addr, daddr);
		rt->rt6i_dst.plen = 128;
		rt->rt6i_flags |= RTF_CACHE;
		rt->u.dst.flags |= DST_HOST;

#ifdef CONFIG_IPV6_SUBTREES
		if (rt->rt6i_src.plen && saddr) {
			ipv6_addr_copy(&rt->rt6i_src.addr, saddr);
			rt->rt6i_src.plen = 128;
		}
#endif

		rt->rt6i_nexthop = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway);

	}

	return rt;
}

static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, struct in6_addr *daddr)
{
	struct rt6_info *rt = ip6_rt_copy(ort);
	if (rt) {
		ipv6_addr_copy(&rt->rt6i_dst.addr, daddr);
		rt->rt6i_dst.plen = 128;
		rt->rt6i_flags |= RTF_CACHE;
		rt->u.dst.flags |= DST_HOST;
		rt->rt6i_nexthop = neigh_clone(ort->rt6i_nexthop);
	}
	return rt;
}

static struct rt6_info *ip6_pol_route_input(struct fib6_table *table,
					    struct flowi *fl, int flags)
{
	struct fib6_node *fn;
	struct rt6_info *rt, *nrt;
	int strict = 0;
	int attempts = 3;
	int err;
	int reachable = ipv6_devconf.forwarding ? 0 : RT6_LOOKUP_F_REACHABLE;

	strict |= flags & RT6_LOOKUP_F_IFACE;

relookup:
	read_lock_bh(&table->tb6_lock);

restart_2:
	fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src);

restart:
	rt = rt6_select(fn, fl->iif, strict | reachable);
	BACKTRACK(&fl->fl6_src);
	if (rt == &ip6_null_entry ||
	    rt->rt6i_flags & RTF_CACHE)
		goto out;

	dst_hold(&rt->u.dst);
	read_unlock_bh(&table->tb6_lock);

	if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP))
		nrt = rt6_alloc_cow(rt, &fl->fl6_dst, &fl->fl6_src);
	else {
#if CLONE_OFFLINK_ROUTE
		nrt = rt6_alloc_clone(rt, &fl->fl6_dst);
#else
		goto out2;
#endif
	}

	dst_release(&rt->u.dst);
	rt = nrt ? : &ip6_null_entry;

	dst_hold(&rt->u.dst);
	if (nrt) {
		err = ip6_ins_rt(nrt);
		if (!err)
			goto out2;
	}

	if (--attempts <= 0)
		goto out2;

	/*
	 * Race condition! In the gap, when table->tb6_lock was
	 * released someone could insert this route.  Relookup.
	 */
	dst_release(&rt->u.dst);
	goto relookup;

out:
	if (reachable) {
		reachable = 0;
		goto restart_2;
	}
	dst_hold(&rt->u.dst);
	read_unlock_bh(&table->tb6_lock);
out2:
	rt->u.dst.lastuse = jiffies;
	rt->u.dst.__use++;

	return rt;
}

void ip6_route_input(struct sk_buff *skb)
{
	struct ipv6hdr *iph = ipv6_hdr(skb);
	int flags = RT6_LOOKUP_F_HAS_SADDR;
	struct flowi fl = {
		.iif = skb->dev->ifindex,
		.nl_u = {
			.ip6_u = {
				.daddr = iph->daddr,
				.saddr = iph->saddr,
				.flowlabel = (* (__be32 *) iph)&IPV6_FLOWINFO_MASK,
			},
		},
		.mark = skb->mark,
		.proto = iph->nexthdr,
	};

	if (rt6_need_strict(&iph->daddr))
		flags |= RT6_LOOKUP_F_IFACE;

	skb->dst = fib6_rule_lookup(&fl, flags, ip6_pol_route_input);
}

static struct rt6_info *ip6_pol_route_output(struct fib6_table *table,
					     struct flowi *fl, int flags)
{
	struct fib6_node *fn;
	struct rt6_info *rt, *nrt;
	int strict = 0;
	int attempts = 3;
	int err;
	int reachable = ipv6_devconf.forwarding ? 0 : RT6_LOOKUP_F_REACHABLE;

	strict |= flags & RT6_LOOKUP_F_IFACE;

relookup:
	read_lock_bh(&table->tb6_lock);

restart_2:
	fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src);

restart:
	rt = rt6_select(fn, fl->oif, strict | reachable);
	BACKTRACK(&fl->fl6_src);
	if (rt == &ip6_null_entry ||
	    rt->rt6i_flags & RTF_CACHE)
		goto out;

	dst_hold(&rt->u.dst);
	read_unlock_bh(&table->tb6_lock);

	if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP))
		nrt = rt6_alloc_cow(rt, &fl->fl6_dst, &fl->fl6_src);
	else {
#if CLONE_OFFLINK_ROUTE
		nrt = rt6_alloc_clone(rt, &fl->fl6_dst);
#else
		goto out2;
#endif
	}

	dst_release(&rt->u.dst);
	rt = nrt ? : &ip6_null_entry;

	dst_hold(&rt->u.dst);
	if (nrt) {
		err = ip6_ins_rt(nrt);
		if (!err)
			goto out2;
	}

	if (--attempts <= 0)
		goto out2;

	/*
	 * Race condition! In the gap, when table->tb6_lock was
	 * released someone could insert this route.  Relookup.
	 */
	dst_release(&rt->u.dst);
	goto relookup;

out:
	if (reachable) {
		reachable = 0;
		goto restart_2;
	}
	dst_hold(&rt->u.dst);
	read_unlock_bh(&table->tb6_lock);
out2:
	rt->u.dst.lastuse = jiffies;
	rt->u.dst.__use++;
	return rt;
}

struct dst_entry * ip6_route_output(struct sock *sk, struct flowi *fl)
{
	int flags = 0;

	if (rt6_need_strict(&fl->fl6_dst))
		flags |= RT6_LOOKUP_F_IFACE;

	if (!ipv6_addr_any(&fl->fl6_src))
		flags |= RT6_LOOKUP_F_HAS_SADDR;

	return fib6_rule_lookup(fl, flags, ip6_pol_route_output);
}

EXPORT_SYMBOL(ip6_route_output);

static int ip6_blackhole_output(struct sk_buff *skb)
{
	kfree_skb(skb);
	return 0;
}

int ip6_dst_blackhole(struct sock *sk, struct dst_entry **dstp, struct flowi *fl)
{
	struct rt6_info *ort = (struct rt6_info *) *dstp;
	struct rt6_info *rt = (struct rt6_info *)
		dst_alloc(&ip6_dst_blackhole_ops);
	struct dst_entry *new = NULL;

	if (rt) {
		new = &rt->u.dst;

		atomic_set(&new->__refcnt, 1);
		new->__use = 1;
		new->input = ip6_blackhole_output;
		new->output = ip6_blackhole_output;

		memcpy(new->metrics, ort->u.dst.metrics, RTAX_MAX*sizeof(u32));
		new->dev = ort->u.dst.dev;
		if (new->dev)
			dev_hold(new->dev);
		rt->rt6i_idev = ort->rt6i_idev;
		if (rt->rt6i_idev)
			in6_dev_hold(rt->rt6i_idev);
		rt->rt6i_expires = 0;

		ipv6_addr_copy(&rt->rt6i_gateway, &ort->rt6i_gateway);
		rt->rt6i_flags = ort->rt6i_flags & ~RTF_EXPIRES;
		rt->rt6i_metric = 0;

		memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key));
#ifdef CONFIG_IPV6_SUBTREES
		memcpy(&rt->rt6i_src, &ort->rt6i_src, sizeof(struct rt6key));
#endif

		dst_free(new);
	}

	dst_release(*dstp);
	*dstp = new;
	return (new ? 0 : -ENOMEM);
}
EXPORT_SYMBOL_GPL(ip6_dst_blackhole);

/*
 *	Destination cache support functions
 */

static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
{
	struct rt6_info *rt;

	rt = (struct rt6_info *) dst;

	if (rt && rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie))
		return dst;

	return NULL;
}

static struct dst_entry *ip6_negative_advice(struct dst_entry *dst)
{
	struct rt6_info *rt = (struct rt6_info *) dst;

	if (rt) {
		if (rt->rt6i_flags & RTF_CACHE)
			ip6_del_rt(rt);
		else
			dst_release(dst);
	}
	return NULL;
}

static void ip6_link_failure(struct sk_buff *skb)
{
	struct rt6_info *rt;

	icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0, skb->dev);

	rt = (struct rt6_info *) skb->dst;
	if (rt) {
		if (rt->rt6i_flags&RTF_CACHE) {
			dst_set_expires(&rt->u.dst, 0);
			rt->rt6i_flags |= RTF_EXPIRES;
		} else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT))
			rt->rt6i_node->fn_sernum = -1;
	}
}

static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
{
	struct rt6_info *rt6 = (struct rt6_info*)dst;

	if (mtu < dst_mtu(dst) && rt6->rt6i_dst.plen == 128) {
		rt6->rt6i_flags |= RTF_MODIFIED;
		if (mtu < IPV6_MIN_MTU) {
			mtu = IPV6_MIN_MTU;
			dst->metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG;
		}
		dst->metrics[RTAX_MTU-1] = mtu;
		call_netevent_notifiers(NETEVENT_PMTU_UPDATE, dst);
	}
}

static int ipv6_get_mtu(struct net_device *dev);

static inline unsigned int ipv6_advmss(unsigned int mtu)
{
	mtu -= sizeof(struct ipv6hdr) + sizeof(struct tcphdr);

	if (mtu < ip6_rt_min_advmss)
		mtu = ip6_rt_min_advmss;

	/*
	 * Maximal non-jumbo IPv6 payload is IPV6_MAXPLEN and
	 * corresponding MSS is IPV6_MAXPLEN - tcp_header_size.
	 * IPV6_MAXPLEN is also valid and means: "any MSS,
	 * rely only on pmtu discovery"
	 */
	if (mtu > IPV6_MAXPLEN - sizeof(struct tcphdr))
		mtu = IPV6_MAXPLEN;
	return mtu;
}

static struct dst_entry *ndisc_dst_gc_list;
static DEFINE_SPINLOCK(ndisc_lock);

struct dst_entry *ndisc_dst_alloc(struct net_device *dev,
				  struct neighbour *neigh,
				  struct in6_addr *addr,
				  int (*output)(struct sk_buff *))
{
	struct rt6_info *rt;
	struct inet6_dev *idev = in6_dev_get(dev);

	if (unlikely(idev == NULL))
		return NULL;

	rt = ip6_dst_alloc();
	if (unlikely(rt == NULL)) {
		in6_dev_put(idev);
		goto out;
	}

	dev_hold(dev);
	if (neigh)
		neigh_hold(neigh);
	else
		neigh = ndisc_get_neigh(dev, addr);

	rt->rt6i_dev	  = dev;
	rt->rt6i_idev     = idev;
	rt->rt6i_nexthop  = neigh;
	atomic_set(&rt->u.dst.__refcnt, 1);
	rt->u.dst.metrics[RTAX_HOPLIMIT-1] = 255;
	rt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(rt->rt6i_dev);
	rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dst_mtu(&rt->u.dst));
	rt->u.dst.output  = output;

#if 0	/* there's no chance to use these for ndisc */
	rt->u.dst.flags   = ipv6_addr_type(addr) & IPV6_ADDR_UNICAST
				? DST_HOST
				: 0;
	ipv6_addr_copy(&rt->rt6i_dst.addr, addr);
	rt->rt6i_dst.plen = 128;
#endif

	spin_lock_bh(&ndisc_lock);
	rt->u.dst.next = ndisc_dst_gc_list;
	ndisc_dst_gc_list = &rt->u.dst;
	spin_unlock_bh(&ndisc_lock);

	fib6_force_start_gc();

out:
	return &rt->u.dst;
}

int ndisc_dst_gc(int *more)
{
	struct dst_entry *dst, *next, **pprev;
	int freed;

	next = NULL;
	freed = 0;

	spin_lock_bh(&ndisc_lock);
	pprev = &ndisc_dst_gc_list;

	while ((dst = *pprev) != NULL) {
		if (!atomic_read(&dst->__refcnt)) {
			*pprev = dst->next;
			dst_free(dst);
			freed++;
		} else {
			pprev = &dst->next;
			(*more)++;
		}
	}

	spin_unlock_bh(&ndisc_lock);

	return freed;
}

static int ip6_dst_gc(void)
{
	static unsigned expire = 30*HZ;
	static unsigned long last_gc;
	unsigned long now = jiffies;

	if (time_after(last_gc + ip6_rt_gc_min_interval, now) &&
	    atomic_read(&ip6_dst_ops.entries) <= ip6_rt_max_size)
		goto out;

	expire++;
	fib6_run_gc(expire);
	last_gc = now;
	if (atomic_read(&ip6_dst_ops.entries) < ip6_dst_ops.gc_thresh)
		expire = ip6_rt_gc_timeout>>1;

out:
	expire -= expire>>ip6_rt_gc_elasticity;
	return (atomic_read(&ip6_dst_ops.entries) > ip6_rt_max_size);
}

/* Clean host part of a prefix. Not necessary in radix tree,
   but results in cleaner routing tables.

   Remove it only when all the things will work!
 */

static int ipv6_get_mtu(struct net_device *dev)
{
	int mtu = IPV6_MIN_MTU;
	struct inet6_dev *idev;

	idev = in6_dev_get(dev);
	if (idev) {
		mtu = idev->cnf.mtu6;
		in6_dev_put(idev);
	}
	return mtu;
}

int ipv6_get_hoplimit(struct net_device *dev)
{
	int hoplimit = ipv6_devconf.hop_limit;
	struct inet6_dev *idev;

	idev = in6_dev_get(dev);
	if (idev) {
		hoplimit = idev->cnf.hop_limit;
		in6_dev_put(idev);
	}
	return hoplimit;
}

/*
 *
 */

int ip6_route_add(struct fib6_config *cfg)
{
	int err;
	struct rt6_info *rt = NULL;
	struct net_device *dev = NULL;
	struct inet6_dev *idev = NULL;
	struct fib6_table *table;
	int addr_type;

	if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128)
		return -EINVAL;
#ifndef CONFIG_IPV6_SUBTREES
	if (cfg->fc_src_len)
		return -EINVAL;
#endif
	if (cfg->fc_ifindex) {
		err = -ENODEV;
		dev = dev_get_by_index(&init_net, cfg->fc_ifindex);
		if (!dev)
			goto out;
		idev = in6_dev_get(dev);
		if (!idev)
			goto out;
	}

	if (cfg->fc_metric == 0)
		cfg->fc_metric = IP6_RT_PRIO_USER;

	table = fib6_new_table(cfg->fc_table);
	if (table == NULL) {
		err = -ENOBUFS;
		goto out;
	}

	rt = ip6_dst_alloc();

	if (rt == NULL) {
		err = -ENOMEM;
		goto out;
	}

	rt->u.dst.obsolete = -1;
	rt->rt6i_expires = jiffies + clock_t_to_jiffies(cfg->fc_expires);

	if (cfg->fc_protocol == RTPROT_UNSPEC)
		cfg->fc_protocol = RTPROT_BOOT;
	rt->rt6i_protocol = cfg->fc_protocol;

	addr_type = ipv6_addr_type(&cfg->fc_dst);

	if (addr_type & IPV6_ADDR_MULTICAST)
		rt->u.dst.input = ip6_mc_input;
	else
		rt->u.dst.input = ip6_forward;

	rt->u.dst.output = ip6_output;

	ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len);
	rt->rt6i_dst.plen = cfg->fc_dst_len;
	if (rt->rt6i_dst.plen == 128)
	       rt->u.dst.flags = DST_HOST;

#ifdef CONFIG_IPV6_SUBTREES
	ipv6_addr_prefix(&rt->rt6i_src.addr, &cfg->fc_src, cfg->fc_src_len);
	rt->rt6i_src.plen = cfg->fc_src_len;
#endif

	rt->rt6i_metric = cfg->fc_metric;

	/* We cannot add true routes via loopback here,
	   they would result in kernel looping; promote them to reject routes
	 */
	if ((cfg->fc_flags & RTF_REJECT) ||
	    (dev && (dev->flags&IFF_LOOPBACK) && !(addr_type&IPV6_ADDR_LOOPBACK))) {
		/* hold loopback dev/idev if we haven't done so. */
		if (dev != init_net.loopback_dev) {
			if (dev) {
				dev_put(dev);
				in6_dev_put(idev);
			}
			dev = init_net.loopback_dev;
			dev_hold(dev);
			idev = in6_dev_get(dev);
			if (!idev) {
				err = -ENODEV;
				goto out;
			}
		}
		rt->u.dst.output = ip6_pkt_discard_out;
		rt->u.dst.input = ip6_pkt_discard;
		rt->u.dst.error = -ENETUNREACH;
		rt->rt6i_flags = RTF_REJECT|RTF_NONEXTHOP;
		goto install_route;
	}

	if (cfg->fc_flags & RTF_GATEWAY) {
		struct in6_addr *gw_addr;
		int gwa_type;

		gw_addr = &cfg->fc_gateway;
		ipv6_addr_copy(&rt->rt6i_gateway, gw_addr);
		gwa_type = ipv6_addr_type(gw_addr);

		if (gwa_type != (IPV6_ADDR_LINKLOCAL|IPV6_ADDR_UNICAST)) {
			struct rt6_info *grt;

			/* IPv6 strictly inhibits using not link-local
			   addresses as nexthop address.
			   Otherwise, router will not able to send redirects.
			   It is very good, but in some (rare!) circumstances
			   (SIT, PtP, NBMA NOARP links) it is handy to allow
			   some exceptions. --ANK
			 */
			err = -EINVAL;
			if (!(gwa_type&IPV6_ADDR_UNICAST))
				goto out;

			grt = rt6_lookup(gw_addr, NULL, cfg->fc_ifindex, 1);

			err = -EHOSTUNREACH;
			if (grt == NULL)
				goto out;
			if (dev) {
				if (dev != grt->rt6i_dev) {
					dst_release(&grt->u.dst);
					goto out;
				}
			} else {
				dev = grt->rt6i_dev;
				idev = grt->rt6i_idev;
				dev_hold(dev);
				in6_dev_hold(grt->rt6i_idev);
			}
			if (!(grt->rt6i_flags&RTF_GATEWAY))
				err = 0;
			dst_release(&grt->u.dst);

			if (err)
				goto out;
		}
		err = -EINVAL;
		if (dev == NULL || (dev->flags&IFF_LOOPBACK))
			goto out;
	}

	err = -ENODEV;
	if (dev == NULL)
		goto out;

	if (cfg->fc_flags & (RTF_GATEWAY | RTF_NONEXTHOP)) {
		rt->rt6i_nexthop = __neigh_lookup_errno(&nd_tbl, &rt->rt6i_gateway, dev);
		if (IS_ERR(rt->rt6i_nexthop)) {
			err = PTR_ERR(rt->rt6i_nexthop);
			rt->rt6i_nexthop = NULL;
			goto out;
		}
	}

	rt->rt6i_flags = cfg->fc_flags;

install_route:
	if (cfg->fc_mx) {
		struct nlattr *nla;
		int remaining;

		nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
			int type = nla_type(nla);

			if (type) {
				if (type > RTAX_MAX) {
					err = -EINVAL;
					goto out;
				}

				rt->u.dst.metrics[type - 1] = nla_get_u32(nla);
			}
		}
	}

	if (rt->u.dst.metrics[RTAX_HOPLIMIT-1] == 0)
		rt->u.dst.metrics[RTAX_HOPLIMIT-1] = -1;
	if (!rt->u.dst.metrics[RTAX_MTU-1])
		rt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(dev);
	if (!rt->u.dst.metrics[RTAX_ADVMSS-1])
		rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dst_mtu(&rt->u.dst));
	rt->u.dst.dev = dev;
	rt->rt6i_idev = idev;
	rt->rt6i_table = table;
	return __ip6_ins_rt(rt, &cfg->fc_nlinfo);

out:
	if (dev)
		dev_put(dev);
	if (idev)
		in6_dev_put(idev);
	if (rt)
		dst_free(&rt->u.dst);
	return err;
}

static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info)
{
	int err;
	struct fib6_table *table;

	if (rt == &ip6_null_entry)
		return -ENOENT;

	table = rt->rt6i_table;
	write_lock_bh(&table->tb6_lock);

	err = fib6_del(rt, info);
	dst_release(&rt->u.dst);

	write_unlock_bh(&table->tb6_lock);

	return err;
}

int ip6_del_rt(struct rt6_info *rt)
{
	return __ip6_del_rt(rt, NULL);
}

static int ip6_route_del(struct fib6_config *cfg)
{
	struct fib6_table *table;
	struct fib6_node *fn;
	struct rt6_info *rt;
	int err = -ESRCH;

	table = fib6_get_table(cfg->fc_table);
	if (table == NULL)
		return err;

	read_lock_bh(&table->tb6_lock);

	fn = fib6_locate(&table->tb6_root,
			 &cfg->fc_dst, cfg->fc_dst_len,
			 &cfg->fc_src, cfg->fc_src_len);

	if (fn) {
		for (rt = fn->leaf; rt; rt = rt->u.dst.rt6_next) {
			if (cfg->fc_ifindex &&
			    (rt->rt6i_dev == NULL ||
			     rt->rt6i_dev->ifindex != cfg->fc_ifindex))
				continue;
			if (cfg->fc_flags & RTF_GATEWAY &&
			    !ipv6_addr_equal(&cfg->fc_gateway, &rt->rt6i_gateway))
				continue;
			if (cfg->fc_metric && cfg->fc_metric != rt->rt6i_metric)
				continue;
			dst_hold(&rt->u.dst);
			read_unlock_bh(&table->tb6_lock);

			return __ip6_del_rt(rt, &cfg->fc_nlinfo);
		}
	}
	read_unlock_bh(&table->tb6_lock);

	return err;
}

/*
 *	Handle redirects
 */
struct ip6rd_flowi {
	struct flowi fl;
	struct in6_addr gateway;
};

static struct rt6_info *__ip6_route_redirect(struct fib6_table *table,
					     struct flowi *fl,
					     int flags)
{
	struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl;
	struct rt6_info *rt;
	struct fib6_node *fn;

	/*
	 * Get the "current" route for this destination and
	 * check if the redirect has come from approriate router.
	 *
	 * RFC 2461 specifies that redirects should only be
	 * accepted if they come from the nexthop to the target.
	 * Due to the way the routes are chosen, this notion
	 * is a bit fuzzy and one might need to check all possible
	 * routes.
	 */

	read_lock_bh(&table->tb6_lock);
	fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src);
restart:
	for (rt = fn->leaf; rt; rt = rt->u.dst.rt6_next) {
		/*
		 * Current route is on-link; redirect is always invalid.
		 *
		 * Seems, previous statement is not true. It could
		 * be node, which looks for us as on-link (f.e. proxy ndisc)
		 * But then router serving it might decide, that we should
		 * know truth 8)8) --ANK (980726).
		 */
		if (rt6_check_expired(rt))
			continue;
		if (!(rt->rt6i_flags & RTF_GATEWAY))
			continue;
		if (fl->oif != rt->rt6i_dev->ifindex)
			continue;
		if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway))
			continue;
		break;
	}

	if (!rt)
		rt = &ip6_null_entry;
	BACKTRACK(&fl->fl6_src);
out:
	dst_hold(&rt->u.dst);

	read_unlock_bh(&table->tb6_lock);

	return rt;
};

static struct rt6_info *ip6_route_redirect(struct in6_addr *dest,
					   struct in6_addr *src,
					   struct in6_addr *gateway,
					   struct net_device *dev)
{
	int flags = RT6_LOOKUP_F_HAS_SADDR;
	struct ip6rd_flowi rdfl = {
		.fl = {
			.oif = dev->ifindex,
			.nl_u = {
				.ip6_u = {
					.daddr = *dest,
					.saddr = *src,
				},
			},
		},
		.gateway = *gateway,
	};

	if (rt6_need_strict(dest))
		flags |= RT6_LOOKUP_F_IFACE;

	return (struct rt6_info *)fib6_rule_lookup((struct flowi *)&rdfl, flags, __ip6_route_redirect);
}

void rt6_redirect(struct in6_addr *dest, struct in6_addr *src,
		  struct in6_addr *saddr,
		  struct neighbour *neigh, u8 *lladdr, int on_link)
{
	struct rt6_info *rt, *nrt = NULL;
	struct netevent_redirect netevent;

	rt = ip6_route_redirect(dest, src, saddr, neigh->dev);

	if (rt == &ip6_null_entry) {
		if (net_ratelimit())
			printk(KERN_DEBUG "rt6_redirect: source isn't a valid nexthop "
			       "for redirect target\n");
		goto out;
	}

	/*
	 *	We have finally decided to accept it.
	 */

	neigh_update(neigh, lladdr, NUD_STALE,
		     NEIGH_UPDATE_F_WEAK_OVERRIDE|
		     NEIGH_UPDATE_F_OVERRIDE|
		     (on_link ? 0 : (NEIGH_UPDATE_F_OVERRIDE_ISROUTER|
				     NEIGH_UPDATE_F_ISROUTER))
		     );

	/*
	 * Redirect received -> path was valid.
	 * Look, redirects are sent only in response to data packets,
	 * so that this nexthop apparently is reachable. --ANK
	 */
	dst_confirm(&rt->u.dst);

	/* Duplicate redirect: silently ignore. */
	if (neigh == rt->u.dst.neighbour)
		goto out;

	nrt = ip6_rt_copy(rt);
	if (nrt == NULL)
		goto out;

	nrt->rt6i_flags = RTF_GATEWAY|RTF_UP|RTF_DYNAMIC|RTF_CACHE;
	if (on_link)
		nrt->rt6i_flags &= ~RTF_GATEWAY;

	ipv6_addr_copy(&nrt->rt6i_dst.addr, dest);
	nrt->rt6i_dst.plen = 128;
	nrt->u.dst.flags |= DST_HOST;

	ipv6_addr_copy(&nrt->rt6i_gateway, (struct in6_addr*)neigh->primary_key);
	nrt->rt6i_nexthop = neigh_clone(neigh);
	/* Reset pmtu, it may be better */
	nrt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(neigh->dev);
	nrt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dst_mtu(&nrt->u.dst));

	if (ip6_ins_rt(nrt))
		goto out;

	netevent.old = &rt->u.dst;
	netevent.new = &nrt->u.dst;
	call_netevent_notifiers(NETEVENT_REDIRECT, &netevent);

	if (rt->rt6i_flags&RTF_CACHE) {
		ip6_del_rt(rt);
		return;
	}

out:
	dst_release(&rt->u.dst);
	return;
}

/*
 *	Handle ICMP "packet too big" messages
 *	i.e. Path MTU discovery
 */

void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr,
			struct net_device *dev, u32 pmtu)
{
	struct rt6_info *rt, *nrt;
	int allfrag = 0;

	rt = rt6_lookup(daddr, saddr, dev->ifindex, 0);
	if (rt == NULL)
		return;

	if (pmtu >= dst_mtu(&rt->u.dst))
		goto out;

	if (pmtu < IPV6_MIN_MTU) {
		/*
		 * According to RFC2460, PMTU is set to the IPv6 Minimum Link
		 * MTU (1280) and a fragment header should always be included
		 * after a node receiving Too Big message reporting PMTU is
		 * less than the IPv6 Minimum Link MTU.
		 */
		pmtu = IPV6_MIN_MTU;
		allfrag = 1;
	}

	/* New mtu received -> path was valid.
	   They are sent only in response to data packets,
	   so that this nexthop apparently is reachable. --ANK
	 */
	dst_confirm(&rt->u.dst);

	/* Host route. If it is static, it would be better
	   not to override it, but add new one, so that
	   when cache entry will expire old pmtu
	   would return automatically.
	 */
	if (rt->rt6i_flags & RTF_CACHE) {
		rt->u.dst.metrics[RTAX_MTU-1] = pmtu;
		if (allfrag)
			rt->u.dst.metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG;
		dst_set_expires(&rt->u.dst, ip6_rt_mtu_expires);
		rt->rt6i_flags |= RTF_MODIFIED|RTF_EXPIRES;
		goto out;
	}

	/* Network route.
	   Two cases are possible:
	   1. It is connected route. Action: COW
	   2. It is gatewayed route or NONEXTHOP route. Action: clone it.
	 */
	if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP))
		nrt = rt6_alloc_cow(rt, daddr, saddr);
	else
		nrt = rt6_alloc_clone(rt, daddr);

	if (nrt) {
		nrt->u.dst.metrics[RTAX_MTU-1] = pmtu;
		if (allfrag)
			nrt->u.dst.metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG;

		/* According to RFC 1981, detecting PMTU increase shouldn't be
		 * happened within 5 mins, the recommended timer is 10 mins.
		 * Here this route expiration time is set to ip6_rt_mtu_expires
		 * which is 10 mins. After 10 mins the decreased pmtu is expired
		 * and detecting PMTU increase will be automatically happened.
		 */
		dst_set_expires(&nrt->u.dst, ip6_rt_mtu_expires);
		nrt->rt6i_flags |= RTF_DYNAMIC|RTF_EXPIRES;

		ip6_ins_rt(nrt);
	}
out:
	dst_release(&rt->u.dst);
}

/*
 *	Misc support functions
 */

static struct rt6_info * ip6_rt_copy(struct rt6_info *ort)
{
	struct rt6_info *rt = ip6_dst_alloc();

	if (rt) {
		rt->u.dst.input = ort->u.dst.input;
		rt->u.dst.output = ort->u.dst.output;

		memcpy(rt->u.dst.metrics, ort->u.dst.metrics, RTAX_MAX*sizeof(u32));
		rt->u.dst.error = ort->u.dst.error;
		rt->u.dst.dev = ort->u.dst.dev;
		if (rt->u.dst.dev)
			dev_hold(rt->u.dst.dev);
		rt->rt6i_idev = ort->rt6i_idev;
		if (rt->rt6i_idev)
			in6_dev_hold(rt->rt6i_idev);
		rt->u.dst.lastuse = jiffies;
		rt->rt6i_expires = 0;

		ipv6_addr_copy(&rt->rt6i_gateway, &ort->rt6i_gateway);
		rt->rt6i_flags = ort->rt6i_flags & ~RTF_EXPIRES;
		rt->rt6i_metric = 0;

		memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key));
#ifdef CONFIG_IPV6_SUBTREES
		memcpy(&rt->rt6i_src, &ort->rt6i_src, sizeof(struct rt6key));
#endif
		rt->rt6i_table = ort->rt6i_table;
	}
	return rt;
}

#ifdef CONFIG_IPV6_ROUTE_INFO
static struct rt6_info *rt6_get_route_info(struct in6_addr *prefix, int prefixlen,
					   struct in6_addr *gwaddr, int ifindex)
{
	struct fib6_node *fn;
	struct rt6_info *rt = NULL;
	struct fib6_table *table;

	table = fib6_get_table(RT6_TABLE_INFO);
	if (table == NULL)
		return NULL;

	write_lock_bh(&table->tb6_lock);
	fn = fib6_locate(&table->tb6_root, prefix ,prefixlen, NULL, 0);
	if (!fn)
		goto out;

	for (rt = fn->leaf; rt; rt = rt->u.dst.rt6_next) {
		if (rt->rt6i_dev->ifindex != ifindex)
			continue;
		if ((rt->rt6i_flags & (RTF_ROUTEINFO|RTF_GATEWAY)) != (RTF_ROUTEINFO|RTF_GATEWAY))
			continue;
		if (!ipv6_addr_equal(&rt->rt6i_gateway, gwaddr))
			continue;
		dst_hold(&rt->u.dst);
		break;
	}
out:
	write_unlock_bh(&table->tb6_lock);
	return rt;
}

static struct rt6_info *rt6_add_route_info(struct in6_addr *prefix, int prefixlen,
					   struct in6_addr *gwaddr, int ifindex,
					   unsigned pref)
{
	struct fib6_config cfg = {
		.fc_table	= RT6_TABLE_INFO,
		.fc_metric	= 1024,
		.fc_ifindex	= ifindex,
		.fc_dst_len	= prefixlen,
		.fc_flags	= RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO |
				  RTF_UP | RTF_PREF(pref),
	};

	ipv6_addr_copy(&cfg.fc_dst, prefix);
	ipv6_addr_copy(&cfg.fc_gateway, gwaddr);

	/* We should treat it as a default route if prefix length is 0. */
	if (!prefixlen)
		cfg.fc_flags |= RTF_DEFAULT;

	ip6_route_add(&cfg);

	return rt6_get_route_info(prefix, prefixlen, gwaddr, ifindex);
}
#endif

struct rt6_info *rt6_get_dflt_router(struct in6_addr *addr, struct net_device *dev)
{
	struct rt6_info *rt;
	struct fib6_table *table;

	table = fib6_get_table(RT6_TABLE_DFLT);
	if (table == NULL)
		return NULL;

	write_lock_bh(&table->tb6_lock);
	for (rt = table->tb6_root.leaf; rt; rt=rt->u.dst.rt6_next) {
		if (dev == rt->rt6i_dev &&
		    ((rt->rt6i_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) &&
		    ipv6_addr_equal(&rt->rt6i_gateway, addr))
			break;
	}
	if (rt)
		dst_hold(&rt->u.dst);
	write_unlock_bh(&table->tb6_lock);
	return rt;
}

struct rt6_info *rt6_add_dflt_router(struct in6_addr *gwaddr,
				     struct net_device *dev,
				     unsigned int pref)
{
	struct fib6_config cfg = {
		.fc_table	= RT6_TABLE_DFLT,
		.fc_metric	= 1024,
		.fc_ifindex	= dev->ifindex,
		.fc_flags	= RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT |
				  RTF_UP | RTF_EXPIRES | RTF_PREF(pref),
	};

	ipv6_addr_copy(&cfg.fc_gateway, gwaddr);

	ip6_route_add(&cfg);

	return rt6_get_dflt_router(gwaddr, dev);
}

void rt6_purge_dflt_routers(void)
{
	struct rt6_info *rt;
	struct fib6_table *table;

	/* NOTE: Keep consistent with rt6_get_dflt_router */
	table = fib6_get_table(RT6_TABLE_DFLT);
	if (table == NULL)
		return;

restart:
	read_lock_bh(&table->tb6_lock);
	for (rt = table->tb6_root.leaf; rt; rt = rt->u.dst.rt6_next) {
		if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) {
			dst_hold(&rt->u.dst);
			read_unlock_bh(&table->tb6_lock);
			ip6_del_rt(rt);
			goto restart;
		}
	}
	read_unlock_bh(&table->tb6_lock);
}

static void rtmsg_to_fib6_config(struct in6_rtmsg *rtmsg,
				 struct fib6_config *cfg)
{
	memset(cfg, 0, sizeof(*cfg));

	cfg->fc_table = RT6_TABLE_MAIN;
	cfg->fc_ifindex = rtmsg->rtmsg_ifindex;
	cfg->fc_metric = rtmsg->rtmsg_metric;
	cfg->fc_expires = rtmsg->rtmsg_info;
	cfg->fc_dst_len = rtmsg->rtmsg_dst_len;
	cfg->fc_src_len = rtmsg->rtmsg_src_len;
	cfg->fc_flags = rtmsg->rtmsg_flags;

	ipv6_addr_copy(&cfg->fc_dst, &rtmsg->rtmsg_dst);
	ipv6_addr_copy(&cfg->fc_src, &rtmsg->rtmsg_src);
	ipv6_addr_copy(&cfg->fc_gateway, &rtmsg->rtmsg_gateway);
}

int ipv6_route_ioctl(unsigned int cmd, void __user *arg)
{
	struct fib6_config cfg;
	struct in6_rtmsg rtmsg;
	int err;

	switch(cmd) {
	case SIOCADDRT:		/* Add a route */
	case SIOCDELRT:		/* Delete a route */
		if (!capable(CAP_NET_ADMIN))
			return -EPERM;
		err = copy_from_user(&rtmsg, arg,
				     sizeof(struct in6_rtmsg));
		if (err)
			return -EFAULT;

		rtmsg_to_fib6_config(&rtmsg, &cfg);

		rtnl_lock();
		switch (cmd) {
		case SIOCADDRT:
			err = ip6_route_add(&cfg);
			break;
		case SIOCDELRT:
			err = ip6_route_del(&cfg);
			break;
		default:
			err = -EINVAL;
		}
		rtnl_unlock();

		return err;
	}

	return -EINVAL;
}

/*
 *	Drop the packet on the floor
 */

static inline int ip6_pkt_drop(struct sk_buff *skb, int code,
			       int ipstats_mib_noroutes)
{
	int type;
	switch (ipstats_mib_noroutes) {
	case IPSTATS_MIB_INNOROUTES:
		type = ipv6_addr_type(&ipv6_hdr(skb)->daddr);
		if (type == IPV6_ADDR_ANY || type == IPV6_ADDR_RESERVED) {
			IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_INADDRERRORS);
			break;
		}
		/* FALLTHROUGH */
	case IPSTATS_MIB_OUTNOROUTES:
		IP6_INC_STATS(ip6_dst_idev(skb->dst), ipstats_mib_noroutes);
		break;
	}
	icmpv6_send(skb, ICMPV6_DEST_UNREACH, code, 0, skb->dev);
	kfree_skb(skb);
	return 0;
}

static int ip6_pkt_discard(struct sk_buff *skb)
{
	return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_INNOROUTES);
}

static int ip6_pkt_discard_out(struct sk_buff *skb)
{
	skb->dev = skb->dst->dev;
	return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_OUTNOROUTES);
}

#ifdef CONFIG_IPV6_MULTIPLE_TABLES

static int ip6_pkt_prohibit(struct sk_buff *skb)
{
	return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_INNOROUTES);
}

static int ip6_pkt_prohibit_out(struct sk_buff *skb)
{
	skb->dev = skb->dst->dev;
	return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_OUTNOROUTES);
}

static int ip6_pkt_blk_hole(struct sk_buff *skb)
{
	kfree_skb(skb);
	return 0;
}

#endif

/*
 *	Allocate a dst for local (unicast / anycast) address.
 */

struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
				    const struct in6_addr *addr,
				    int anycast)
{
	struct rt6_info *rt = ip6_dst_alloc();

	if (rt == NULL)
		return ERR_PTR(-ENOMEM);

	dev_hold(init_net.loopback_dev);
	in6_dev_hold(idev);

	rt->u.dst.flags = DST_HOST;
	rt->u.dst.input = ip6_input;
	rt->u.dst.output = ip6_output;
	rt->rt6i_dev = init_net.loopback_dev;
	rt->rt6i_idev = idev;
	rt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(rt->rt6i_dev);
	rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dst_mtu(&rt->u.dst));
	rt->u.dst.metrics[RTAX_HOPLIMIT-1] = -1;
	rt->u.dst.obsolete = -1;

	rt->rt6i_flags = RTF_UP | RTF_NONEXTHOP;
	if (anycast)
		rt->rt6i_flags |= RTF_ANYCAST;
	else
		rt->rt6i_flags |= RTF_LOCAL;
	rt->rt6i_nexthop = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway);
	if (rt->rt6i_nexthop == NULL) {
		dst_free(&rt->u.dst);
		return ERR_PTR(-ENOMEM);
	}

	ipv6_addr_copy(&rt->rt6i_dst.addr, addr);
	rt->rt6i_dst.plen = 128;
	rt->rt6i_table = fib6_get_table(RT6_TABLE_LOCAL);

	atomic_set(&rt->u.dst.__refcnt, 1);

	return rt;
}

static int fib6_ifdown(struct rt6_info *rt, void *arg)
{
	if (((void*)rt->rt6i_dev == arg || arg == NULL) &&
	    rt != &ip6_null_entry) {
		RT6_TRACE("deleted by ifdown %p\n", rt);
		return -1;
	}
	return 0;
}

void rt6_ifdown(struct net_device *dev)
{
	fib6_clean_all(fib6_ifdown, 0, dev);
}

struct rt6_mtu_change_arg
{
	struct net_device *dev;
	unsigned mtu;
};

static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg)
{
	struct rt6_mtu_change_arg *arg = (struct rt6_mtu_change_arg *) p_arg;
	struct inet6_dev *idev;

	/* In IPv6 pmtu discovery is not optional,
	   so that RTAX_MTU lock cannot disable it.
	   We still use this lock to block changes
	   caused by addrconf/ndisc.
	*/

	idev = __in6_dev_get(arg->dev);
	if (idev == NULL)
		return 0;

	/* For administrative MTU increase, there is no way to discover
	   IPv6 PMTU increase, so PMTU increase should be updated here.
	   Since RFC 1981 doesn't include administrative MTU increase
	   update PMTU increase is a MUST. (i.e. jumbo frame)
	 */
	/*
	   If new MTU is less than route PMTU, this new MTU will be the
	   lowest MTU in the path, update the route PMTU to reflect PMTU
	   decreases; if new MTU is greater than route PMTU, and the
	   old MTU is the lowest MTU in the path, update the route PMTU
	   to reflect the increase. In this case if the other nodes' MTU
	   also have the lowest MTU, TOO BIG MESSAGE will be lead to
	   PMTU discouvery.
	 */
	if (rt->rt6i_dev == arg->dev &&
	    !dst_metric_locked(&rt->u.dst, RTAX_MTU) &&
	    (dst_mtu(&rt->u.dst) > arg->mtu ||
	     (dst_mtu(&rt->u.dst) < arg->mtu &&
	      dst_mtu(&rt->u.dst) == idev->cnf.mtu6))) {
		rt->u.dst.metrics[RTAX_MTU-1] = arg->mtu;
		rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(arg->mtu);
	}
	return 0;
}

void rt6_mtu_change(struct net_device *dev, unsigned mtu)
{
	struct rt6_mtu_change_arg arg = {
		.dev = dev,
		.mtu = mtu,
	};

	fib6_clean_all(rt6_mtu_change_route, 0, &arg);
}

static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
	[RTA_GATEWAY]           = { .len = sizeof(struct in6_addr) },
	[RTA_OIF]               = { .type = NLA_U32 },
	[RTA_IIF]		= { .type = NLA_U32 },
	[RTA_PRIORITY]          = { .type = NLA_U32 },
	[RTA_METRICS]           = { .type = NLA_NESTED },
};

static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
			      struct fib6_config *cfg)
{
	struct rtmsg *rtm;
	struct nlattr *tb[RTA_MAX+1];
	int err;

	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy);
	if (err < 0)
		goto errout;

	err = -EINVAL;
	rtm = nlmsg_data(nlh);
	memset(cfg, 0, sizeof(*cfg));

	cfg->fc_table = rtm->rtm_table;
	cfg->fc_dst_len = rtm->rtm_dst_len;
	cfg->fc_src_len = rtm->rtm_src_len;
	cfg->fc_flags = RTF_UP;
	cfg->fc_protocol = rtm->rtm_protocol;

	if (rtm->rtm_type == RTN_UNREACHABLE)
		cfg->fc_flags |= RTF_REJECT;

	cfg->fc_nlinfo.pid = NETLINK_CB(skb).pid;
	cfg->fc_nlinfo.nlh = nlh;

	if (tb[RTA_GATEWAY]) {
		nla_memcpy(&cfg->fc_gateway, tb[RTA_GATEWAY], 16);
		cfg->fc_flags |= RTF_GATEWAY;
	}

	if (tb[RTA_DST]) {
		int plen = (rtm->rtm_dst_len + 7) >> 3;

		if (nla_len(tb[RTA_DST]) < plen)
			goto errout;

		nla_memcpy(&cfg->fc_dst, tb[RTA_DST], plen);
	}

	if (tb[RTA_SRC]) {
		int plen = (rtm->rtm_src_len + 7) >> 3;

		if (nla_len(tb[RTA_SRC]) < plen)
			goto errout;

		nla_memcpy(&cfg->fc_src, tb[RTA_SRC], plen);
	}

	if (tb[RTA_OIF])
		cfg->fc_ifindex = nla_get_u32(tb[RTA_OIF]);

	if (tb[RTA_PRIORITY])
		cfg->fc_metric = nla_get_u32(tb[RTA_PRIORITY]);

	if (tb[RTA_METRICS]) {
		cfg->fc_mx = nla_data(tb[RTA_METRICS]);
		cfg->fc_mx_len = nla_len(tb[RTA_METRICS]);
	}

	if (tb[RTA_TABLE])
		cfg->fc_table = nla_get_u32(tb[RTA_TABLE]);

	err = 0;
errout:
	return err;
}

static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
{
	struct fib6_config cfg;
	int err;

	err = rtm_to_fib6_config(skb, nlh, &cfg);
	if (err < 0)
		return err;

	return ip6_route_del(&cfg);
}

static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
{
	struct fib6_config cfg;
	int err;

	err = rtm_to_fib6_config(skb, nlh, &cfg);
	if (err < 0)
		return err;

	return ip6_route_add(&cfg);
}

static inline size_t rt6_nlmsg_size(void)
{
	return NLMSG_ALIGN(sizeof(struct rtmsg))
	       + nla_total_size(16) /* RTA_SRC */
	       + nla_total_size(16) /* RTA_DST */
	       + nla_total_size(16) /* RTA_GATEWAY */
	       + nla_total_size(16) /* RTA_PREFSRC */
	       + nla_total_size(4) /* RTA_TABLE */
	       + nla_total_size(4) /* RTA_IIF */
	       + nla_total_size(4) /* RTA_OIF */
	       + nla_total_size(4) /* RTA_PRIORITY */
	       + RTAX_MAX * nla_total_size(4) /* RTA_METRICS */
	       + nla_total_size(sizeof(struct rta_cacheinfo));
}

static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt,
			 struct in6_addr *dst, struct in6_addr *src,
			 int iif, int type, u32 pid, u32 seq,
			 int prefix, unsigned int flags)
{
	struct rtmsg *rtm;
	struct nlmsghdr *nlh;
	long expires;
	u32 table;

	if (prefix) {	/* user wants prefix routes only */
		if (!(rt->rt6i_flags & RTF_PREFIX_RT)) {
			/* success since this is not a prefix route */
			return 1;
		}
	}

	nlh = nlmsg_put(skb, pid, seq, type, sizeof(*rtm), flags);
	if (nlh == NULL)
		return -EMSGSIZE;

	rtm = nlmsg_data(nlh);
	rtm->rtm_family = AF_INET6;
	rtm->rtm_dst_len = rt->rt6i_dst.plen;
	rtm->rtm_src_len = rt->rt6i_src.plen;
	rtm->rtm_tos = 0;
	if (rt->rt6i_table)
		table = rt->rt6i_table->tb6_id;
	else
		table = RT6_TABLE_UNSPEC;
	rtm->rtm_table = table;
	NLA_PUT_U32(skb, RTA_TABLE, table);
	if (rt->rt6i_flags&RTF_REJECT)
		rtm->rtm_type = RTN_UNREACHABLE;
	else if (rt->rt6i_dev && (rt->rt6i_dev->flags&IFF_LOOPBACK))
		rtm->rtm_type = RTN_LOCAL;
	else
		rtm->rtm_type = RTN_UNICAST;
	rtm->rtm_flags = 0;
	rtm->rtm_scope = RT_SCOPE_UNIVERSE;
	rtm->rtm_protocol = rt->rt6i_protocol;
	if (rt->rt6i_flags&RTF_DYNAMIC)
		rtm->rtm_protocol = RTPROT_REDIRECT;
	else if (rt->rt6i_flags & RTF_ADDRCONF)
		rtm->rtm_protocol = RTPROT_KERNEL;
	else if (rt->rt6i_flags&RTF_DEFAULT)
		rtm->rtm_protocol = RTPROT_RA;

	if (rt->rt6i_flags&RTF_CACHE)
		rtm->rtm_flags |= RTM_F_CLONED;

	if (dst) {
		NLA_PUT(skb, RTA_DST, 16, dst);
		rtm->rtm_dst_len = 128;
	} else if (rtm->rtm_dst_len)
		NLA_PUT(skb, RTA_DST, 16, &rt->rt6i_dst.addr);
#ifdef CONFIG_IPV6_SUBTREES
	if (src) {
		NLA_PUT(skb, RTA_SRC, 16, src);
		rtm->rtm_src_len = 128;
	} else if (rtm->rtm_src_len)
		NLA_PUT(skb, RTA_SRC, 16, &rt->rt6i_src.addr);
#endif
	if (iif)
		NLA_PUT_U32(skb, RTA_IIF, iif);
	else if (dst) {
		struct in6_addr saddr_buf;
		if (ipv6_get_saddr(&rt->u.dst, dst, &saddr_buf) == 0)
			NLA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf);
	}

	if (rtnetlink_put_metrics(skb, rt->u.dst.metrics) < 0)
		goto nla_put_failure;

	if (rt->u.dst.neighbour)
		NLA_PUT(skb, RTA_GATEWAY, 16, &rt->u.dst.neighbour->primary_key);

	if (rt->u.dst.dev)
		NLA_PUT_U32(skb, RTA_OIF, rt->rt6i_dev->ifindex);

	NLA_PUT_U32(skb, RTA_PRIORITY, rt->rt6i_metric);

	expires = rt->rt6i_expires ? rt->rt6i_expires - jiffies : 0;
	if (rtnl_put_cacheinfo(skb, &rt->u.dst, 0, 0, 0,
			       expires, rt->u.dst.error) < 0)
		goto nla_put_failure;

	return nlmsg_end(skb, nlh);

nla_put_failure:
	nlmsg_cancel(skb, nlh);
	return -EMSGSIZE;
}

int rt6_dump_route(struct rt6_info *rt, void *p_arg)
{
	struct rt6_rtnl_dump_arg *arg = (struct rt6_rtnl_dump_arg *) p_arg;
	int prefix;

	if (nlmsg_len(arg->cb->nlh) >= sizeof(struct rtmsg)) {
		struct rtmsg *rtm = nlmsg_data(arg->cb->nlh);
		prefix = (rtm->rtm_flags & RTM_F_PREFIX) != 0;
	} else
		prefix = 0;

	return rt6_fill_node(arg->skb, rt, NULL, NULL, 0, RTM_NEWROUTE,
		     NETLINK_CB(arg->cb->skb).pid, arg->cb->nlh->nlmsg_seq,
		     prefix, NLM_F_MULTI);
}

static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg)
{
	struct nlattr *tb[RTA_MAX+1];
	struct rt6_info *rt;
	struct sk_buff *skb;
	struct rtmsg *rtm;
	struct flowi fl;
	int err, iif = 0;

	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy);
	if (err < 0)
		goto errout;

	err = -EINVAL;
	memset(&fl, 0, sizeof(fl));

	if (tb[RTA_SRC]) {
		if (nla_len(tb[RTA_SRC]) < sizeof(struct in6_addr))
			goto errout;

		ipv6_addr_copy(&fl.fl6_src, nla_data(tb[RTA_SRC]));
	}

	if (tb[RTA_DST]) {
		if (nla_len(tb[RTA_DST]) < sizeof(struct in6_addr))
			goto errout;

		ipv6_addr_copy(&fl.fl6_dst, nla_data(tb[RTA_DST]));
	}

	if (tb[RTA_IIF])
		iif = nla_get_u32(tb[RTA_IIF]);

	if (tb[RTA_OIF])
		fl.oif = nla_get_u32(tb[RTA_OIF]);

	if (iif) {
		struct net_device *dev;
		dev = __dev_get_by_index(&init_net, iif);
		if (!dev) {
			err = -ENODEV;
			goto errout;
		}
	}

	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
	if (skb == NULL) {
		err = -ENOBUFS;
		goto errout;
	}

	/* Reserve room for dummy headers, this skb can pass
	   through good chunk of routing engine.
	 */
	skb_reset_mac_header(skb);
	skb_reserve(skb, MAX_HEADER + sizeof(struct ipv6hdr));

	rt = (struct rt6_info*) ip6_route_output(NULL, &fl);
	skb->dst = &rt->u.dst;

	err = rt6_fill_node(skb, rt, &fl.fl6_dst, &fl.fl6_src, iif,
			    RTM_NEWROUTE, NETLINK_CB(in_skb).pid,
			    nlh->nlmsg_seq, 0, 0);
	if (err < 0) {
		kfree_skb(skb);
		goto errout;
	}

	err = rtnl_unicast(skb, NETLINK_CB(in_skb).pid);
errout:
	return err;
}

void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info)
{
	struct sk_buff *skb;
	u32 pid = 0, seq = 0;
	struct nlmsghdr *nlh = NULL;
	int err = -ENOBUFS;

	if (info) {
		pid = info->pid;
		nlh = info->nlh;
		if (nlh)
			seq = nlh->nlmsg_seq;
	}

	skb = nlmsg_new(rt6_nlmsg_size(), gfp_any());
	if (skb == NULL)
		goto errout;

	err = rt6_fill_node(skb, rt, NULL, NULL, 0, event, pid, seq, 0, 0);
	if (err < 0) {
		/* -EMSGSIZE implies BUG in rt6_nlmsg_size() */
		WARN_ON(err == -EMSGSIZE);
		kfree_skb(skb);
		goto errout;
	}
	err = rtnl_notify(skb, pid, RTNLGRP_IPV6_ROUTE, nlh, gfp_any());
errout:
	if (err < 0)
		rtnl_set_sk_err(RTNLGRP_IPV6_ROUTE, err);
}

/*
 *	/proc
 */

#ifdef CONFIG_PROC_FS

#define RT6_INFO_LEN (32 + 4 + 32 + 4 + 32 + 40 + 5 + 1)

struct rt6_proc_arg
{
	char *buffer;
	int offset;
	int length;
	int skip;
	int len;
};

static int rt6_info_route(struct rt6_info *rt, void *p_arg)
{
	struct rt6_proc_arg *arg = (struct rt6_proc_arg *) p_arg;

	if (arg->skip < arg->offset / RT6_INFO_LEN) {
		arg->skip++;
		return 0;
	}

	if (arg->len >= arg->length)
		return 0;

	arg->len += sprintf(arg->buffer + arg->len,
			    NIP6_SEQFMT " %02x ",
			    NIP6(rt->rt6i_dst.addr),
			    rt->rt6i_dst.plen);

#ifdef CONFIG_IPV6_SUBTREES
	arg->len += sprintf(arg->buffer + arg->len,
			    NIP6_SEQFMT " %02x ",
			    NIP6(rt->rt6i_src.addr),
			    rt->rt6i_src.plen);
#else
	arg->len += sprintf(arg->buffer + arg->len,
			    "00000000000000000000000000000000 00 ");
#endif

	if (rt->rt6i_nexthop) {
		arg->len += sprintf(arg->buffer + arg->len,
				    NIP6_SEQFMT,
				    NIP6(*((struct in6_addr *)rt->rt6i_nexthop->primary_key)));
	} else {
		arg->len += sprintf(arg->buffer + arg->len,
				    "00000000000000000000000000000000");
	}
	arg->len += sprintf(arg->buffer + arg->len,
			    " %08x %08x %08x %08x %8s\n",
			    rt->rt6i_metric, atomic_read(&rt->u.dst.__refcnt),
			    rt->u.dst.__use, rt->rt6i_flags,
			    rt->rt6i_dev ? rt->rt6i_dev->name : "");
	return 0;
}