summaryrefslogtreecommitdiffstats
path: root/net/sctp/endpointola.c
blob: e47ac0d1a6d64f679bf963113b1989d93e4d4c44 (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
/* SCTP kernel reference Implementation
 * Copyright (c) 1999-2000 Cisco, Inc.
 * Copyright (c) 1999-2001 Motorola, Inc.
 * Copyright (c) 2001-2002 International Business Machines, Corp.
 * Copyright (c) 2001 Intel Corp.
 * Copyright (c) 2001 Nokia, Inc.
 * Copyright (c) 2001 La Monte H.P. Yarroll
 *
 * This file is part of the SCTP kernel reference Implementation
 *
 * This abstraction represents an SCTP endpoint.
 *
 * This file is part of the implementation of the add-IP extension,
 * based on <draft-ietf-tsvwg-addip-sctp-02.txt> June 29, 2001,
 * for 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:
 *    La Monte H.P. Yarroll <piggy@acm.org>
 *    Karl Knutson <karl@athena.chicago.il.us>
 *    Jon Grimm <jgrimm@austin.ibm.com>
 *    Daisy Chang <daisyc@us.ibm.com>
 *    Dajiang Zhang <dajiang.zhang@nokia.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/sched.h>
#include <linux/slab.h>
#include <linux/in.h>
#include <linux/random.h>	/* get_random_bytes() */
#include <linux/crypto.h>
#include <net/sock.h>
#include <net/ipv6.h>
#include <net/sctp/sctp.h>
#include <net/sctp/sm.h>

/* Forward declarations for internal helpers. */
static void sctp_endpoint_bh_rcv(struct sctp_endpoint *ep);

/*
 * Initialize the base fields of the endpoint structure.
 */
static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep,
						struct sock *sk,
						unsigned int __nocast gfp)
{
	struct sctp_sock *sp = sctp_sk(sk);
	memset(ep, 0, sizeof(struct sctp_endpoint));

	/* Initialize the base structure. */
	/* What type of endpoint are we?  */
	ep->base.type = SCTP_EP_TYPE_SOCKET;

	/* Initialize the basic object fields. */
	atomic_set(&ep->base.refcnt, 1);
	ep->base.dead = 0;
	ep->base.malloced = 1;

	/* Create an input queue.  */
	sctp_inq_init(&ep->base.inqueue);

	/* Set its top-half handler */
	sctp_inq_set_th_handler(&ep->base.inqueue,
				(void (*)(void *))sctp_endpoint_bh_rcv, ep);

	/* Initialize the bind addr area */
	sctp_bind_addr_init(&ep->base.bind_addr, 0);
	rwlock_init(&ep->base.addr_lock);

	/* Remember who we are attached to.  */
	ep->base.sk = sk;
	sock_hold(ep->base.sk);

	/* Create the lists of associations.  */
	INIT_LIST_HEAD(&ep->asocs);

	/* Set up the base timeout information.  */
	ep->timeouts[SCTP_EVENT_TIMEOUT_NONE] = 0;
	ep->timeouts[SCTP_EVENT_TIMEOUT_T1_COOKIE] =
		msecs_to_jiffies(sp->rtoinfo.srto_initial);
	ep->timeouts[SCTP_EVENT_TIMEOUT_T1_INIT] =
		msecs_to_jiffies(sp->rtoinfo.srto_initial);
	ep->timeouts[SCTP_EVENT_TIMEOUT_T2_SHUTDOWN] =
		msecs_to_jiffies(sp->rtoinfo.srto_initial);
	ep->timeouts[SCTP_EVENT_TIMEOUT_T3_RTX] = 0;
	ep->timeouts[SCTP_EVENT_TIMEOUT_T4_RTO] = 0;

	/* sctpimpguide-05 Section 2.12.2
	 * If the 'T5-shutdown-guard' timer is used, it SHOULD be set to the
	 * recommended value of 5 times 'RTO.Max'.
	 */
        ep->timeouts[SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD]
		= 5 * msecs_to_jiffies(sp->rtoinfo.srto_max);

	ep->timeouts[SCTP_EVENT_TIMEOUT_HEARTBEAT] = 0;
	ep->timeouts[SCTP_EVENT_TIMEOUT_SACK] = sctp_sack_timeout;
	ep->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE] = sp->autoclose * HZ;

	/* Use SCTP specific send buffer space queues.  */
	ep->sndbuf_policy = sctp_sndbuf_policy;
	sk->sk_write_space = sctp_write_space;
	sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);

	/* Initialize the secret key used with cookie. */
	get_random_bytes(&ep->secret_key[0], SCTP_SECRET_SIZE);
	ep->last_key = ep->current_key = 0;
	ep->key_changed_at = jiffies;

	return ep;
}

/* Create a sctp_endpoint with all that boring stuff initialized.
 * Returns NULL if there isn't enough memory.
 */
struct sctp_endpoint *sctp_endpoint_new(struct sock *sk,
					unsigned int __nocast gfp)
{
	struct sctp_endpoint *ep;

	/* Build a local endpoint. */
	ep = t_new(struct sctp_endpoint, gfp);
	if (!ep)
		goto fail;
	if (!sctp_endpoint_init(ep, sk, gfp))
		goto fail_init;
	ep->base.malloced = 1;
	SCTP_DBG_OBJCNT_INC(ep);
	return ep;

fail_init:
	kfree(ep);
fail:
	return NULL;
}

/* Add an association to an endpoint.  */
void sctp_endpoint_add_asoc(struct sctp_endpoint *ep,
			    struct sctp_association *asoc)
{
	struct sock *sk = ep->base.sk;

	/* Now just add it to our list of asocs */
	list_add_tail(&asoc->asocs, &ep->asocs);

	/* Increment the backlog value for a TCP-style listening socket. */
	if (sctp_style(sk, TCP) && sctp_sstate(sk, LISTENING))
		sk->sk_ack_backlog++;
}

/* Free the endpoint structure.  Delay cleanup until
 * all users have released their reference count on this structure.
 */
void sctp_endpoint_free(struct sctp_endpoint *ep)
{
	ep->base.dead = 1;
	sctp_endpoint_put(ep);
}

/* Final destructor for endpoint.  */
static void sctp_endpoint_destroy(struct sctp_endpoint *ep)
{
	SCTP_ASSERT(ep->base.dead, "Endpoint is not dead", return);

	ep->base.sk->sk_state = SCTP_SS_CLOSED;

	/* Unlink this endpoint, so we can't find it again! */
	sctp_unhash_endpoint(ep);

	/* Free up the HMAC transform. */
	if (sctp_sk(ep->base.sk)->hmac)
		sctp_crypto_free_tfm(sctp_sk(ep->base.sk)->hmac);

	/* Cleanup. */
	sctp_inq_free(&ep->base.inqueue);
	sctp_bind_addr_free(&ep->base.bind_addr);

	/* Remove and free the port */
	if (sctp_sk(ep->base.sk)->bind_hash)
		sctp_put_port(ep->base.sk);

	/* Give up our hold on the sock. */
	if (ep->base.sk)
		sock_put(ep->base.sk);

	/* Finally, free up our memory. */
	if (ep->base.malloced) {
		kfree(ep);
		SCTP_DBG_OBJCNT_DEC(ep);
	}
}

/* Hold a reference to an endpoint. */
void sctp_endpoint_hold(struct sctp_endpoint *ep)
{
	atomic_inc(&ep->base.refcnt);
}

/* Release a reference to an endpoint and clean up if there are
 * no more references.
 */
void sctp_endpoint_put(struct sctp_endpoint *ep)
{
	if (atomic_dec_and_test(&ep->base.refcnt))
		sctp_endpoint_destroy(ep);
}

/* Is this the endpoint we are looking for?  */
struct sctp_endpoint *sctp_endpoint_is_match(struct sctp_endpoint *ep,
					       const union sctp_addr *laddr)
{
	struct sctp_endpoint *retval;

	sctp_read_lock(&ep->base.addr_lock);
	if (ep->base.bind_addr.port == laddr->v4.sin_port) {
		if (sctp_bind_addr_match(&ep->base.bind_addr, laddr,
					 sctp_sk(ep->base.sk))) {
			retval = ep;
			goto out;
		}
	}

	retval = NULL;

out:
	sctp_read_unlock(&ep->base.addr_lock);
	return retval;
}

/* Find the association that goes with this chunk.
 * We do a linear search of the associations for this endpoint.
 * We return the matching transport address too.
 */
static struct sctp_association *__sctp_endpoint_lookup_assoc(
	const struct sctp_endpoint *ep,
	const union sctp_addr *paddr,
	struct sctp_transport **transport)
{
	int rport;
	struct sctp_association *asoc;
	struct list_head *pos;

	rport = paddr->v4.sin_port;

	list_for_each(pos, &ep->asocs) {
		asoc = list_entry(pos, struct sctp_association, asocs);
		if (rport == asoc->peer.port) {
			sctp_read_lock(&asoc->base.addr_lock);
			*transport = sctp_assoc_lookup_paddr(asoc, paddr);
			sctp_read_unlock(&asoc->base.addr_lock);

			if (*transport)
				return asoc;
		}
	}

	*transport = NULL;
	return NULL;
}

/* Lookup association on an endpoint based on a peer address.  BH-safe.  */
struct sctp_association *sctp_endpoint_lookup_assoc(
	const struct sctp_endpoint *ep,
	const union sctp_addr *paddr,
	struct sctp_transport **transport)
{
	struct sctp_association *asoc;

	sctp_local_bh_disable();
	asoc = __sctp_endpoint_lookup_assoc(ep, paddr, transport);
	sctp_local_bh_enable();

	return asoc;
}

/* Look for any peeled off association from the endpoint that matches the
 * given peer address.
 */
int sctp_endpoint_is_peeled_off(struct sctp_endpoint *ep,
				const union sctp_addr *paddr)
{
	struct list_head *pos;
	struct sctp_sockaddr_entry *addr;
	struct sctp_bind_addr *bp;

	sctp_read_lock(&ep->base.addr_lock);
	bp = &ep->base.bind_addr;
	list_for_each(pos, &bp->address_list) {
		addr = list_entry(pos, struct sctp_sockaddr_entry, list);
		if (sctp_has_association(&addr->a, paddr)) {
			sctp_read_unlock(&ep->base.addr_lock);
			return 1;
		}
	}
	sctp_read_unlock(&ep->base.addr_lock);

	return 0;
}

/* Do delayed input processing.  This is scheduled by sctp_rcv().
 * This may be called on BH or task time.
 */
static void sctp_endpoint_bh_rcv(struct sctp_endpoint *ep)
{
	struct sctp_association *asoc;
	struct sock *sk;
	struct sctp_transport *transport;
	struct sctp_chunk *chunk;
	struct sctp_inq *inqueue;
	sctp_subtype_t subtype;
	sctp_state_t state;
	int error = 0;

	if (ep->base.dead)
		return;

	asoc = NULL;
	inqueue = &ep->base.inqueue;
	sk = ep->base.sk;

	while (NULL != (chunk = sctp_inq_pop(inqueue))) {
		subtype = SCTP_ST_CHUNK(chunk->chunk_hdr->type);

		/* We might have grown an association since last we
		 * looked, so try again.
		 *
		 * This happens when we've just processed our
		 * COOKIE-ECHO chunk.
		 */
		if (NULL == chunk->asoc) {
			asoc = sctp_endpoint_lookup_assoc(ep,
							  sctp_source(chunk),
							  &transport);
			chunk->asoc = asoc;
			chunk->transport = transport;
		}

		state = asoc ? asoc->state : SCTP_STATE_CLOSED;

		/* Remember where the last DATA chunk came from so we
		 * know where to send the SACK.
		 */
		if (asoc && sctp_chunk_is_data(chunk))
			asoc->peer.last_data_from = chunk->transport;
		else
			SCTP_INC_STATS(SCTP_MIB_INCTRLCHUNKS);

		if (chunk->transport)
			chunk->transport->last_time_heard = jiffies;

		error = sctp_do_sm(SCTP_EVENT_T_CHUNK, subtype, state,
                                   ep, asoc, chunk, GFP_ATOMIC);

		if (error && chunk)
			chunk->pdiscard = 1;

		/* Check to see if the endpoint is freed in response to
		 * the incoming chunk. If so, get out of the while loop.
		 */
		if (!sctp_sk(sk)->ep)
			break;
	}
}
'n1446' href='#n1446'>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
/*
 * Copyright (c) 2007-2014 Nicira, Inc.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of version 2 of the GNU General Public
 * License as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
 * General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
 * 02110-1301, USA
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include "flow.h"
#include "datapath.h"
#include <linux/uaccess.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/if_ether.h>
#include <linux/if_vlan.h>
#include <net/llc_pdu.h>
#include <linux/kernel.h>
#include <linux/jhash.h>
#include <linux/jiffies.h>
#include <linux/llc.h>
#include <linux/module.h>
#include <linux/in.h>
#include <linux/rcupdate.h>
#include <linux/if_arp.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/sctp.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/icmp.h>
#include <linux/icmpv6.h>
#include <linux/rculist.h>
#include <net/geneve.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/ndisc.h>
#include <net/mpls.h>
#include <net/vxlan.h>

#include "flow_netlink.h"

struct ovs_len_tbl {
	int len;
	const struct ovs_len_tbl *next;
};

#define OVS_ATTR_NESTED -1
#define OVS_ATTR_VARIABLE -2

static void update_range(struct sw_flow_match *match,
			 size_t offset, size_t size, bool is_mask)
{
	struct sw_flow_key_range *range;
	size_t start = rounddown(offset, sizeof(long));
	size_t end = roundup(offset + size, sizeof(long));

	if (!is_mask)
		range = &match->range;
	else
		range = &match->mask->range;

	if (range->start == range->end) {
		range->start = start;
		range->end = end;
		return;
	}

	if (range->start > start)
		range->start = start;

	if (range->end < end)
		range->end = end;
}

#define SW_FLOW_KEY_PUT(match, field, value, is_mask) \
	do { \
		update_range(match, offsetof(struct sw_flow_key, field),    \
			     sizeof((match)->key->field), is_mask);	    \
		if (is_mask)						    \
			(match)->mask->key.field = value;		    \
		else							    \
			(match)->key->field = value;		            \
	} while (0)

#define SW_FLOW_KEY_MEMCPY_OFFSET(match, offset, value_p, len, is_mask)	    \
	do {								    \
		update_range(match, offset, len, is_mask);		    \
		if (is_mask)						    \
			memcpy((u8 *)&(match)->mask->key + offset, value_p, \
			       len);					   \
		else							    \
			memcpy((u8 *)(match)->key + offset, value_p, len);  \
	} while (0)

#define SW_FLOW_KEY_MEMCPY(match, field, value_p, len, is_mask)		      \
	SW_FLOW_KEY_MEMCPY_OFFSET(match, offsetof(struct sw_flow_key, field), \
				  value_p, len, is_mask)

#define SW_FLOW_KEY_MEMSET_FIELD(match, field, value, is_mask)		    \
	do {								    \
		update_range(match, offsetof(struct sw_flow_key, field),    \
			     sizeof((match)->key->field), is_mask);	    \
		if (is_mask)						    \
			memset((u8 *)&(match)->mask->key.field, value,      \
			       sizeof((match)->mask->key.field));	    \
		else							    \
			memset((u8 *)&(match)->key->field, value,           \
			       sizeof((match)->key->field));                \
	} while (0)

static bool match_validate(const struct sw_flow_match *match,
			   u64 key_attrs, u64 mask_attrs, bool log)
{
	u64 key_expected = 1 << OVS_KEY_ATTR_ETHERNET;
	u64 mask_allowed = key_attrs;  /* At most allow all key attributes */

	/* The following mask attributes allowed only if they
	 * pass the validation tests. */
	mask_allowed &= ~((1 << OVS_KEY_ATTR_IPV4)
			| (1 << OVS_KEY_ATTR_IPV6)
			| (1 << OVS_KEY_ATTR_TCP)
			| (1 << OVS_KEY_ATTR_TCP_FLAGS)
			| (1 << OVS_KEY_ATTR_UDP)
			| (1 << OVS_KEY_ATTR_SCTP)
			| (1 << OVS_KEY_ATTR_ICMP)
			| (1 << OVS_KEY_ATTR_ICMPV6)
			| (1 << OVS_KEY_ATTR_ARP)
			| (1 << OVS_KEY_ATTR_ND)
			| (1 << OVS_KEY_ATTR_MPLS));

	/* Always allowed mask fields. */
	mask_allowed |= ((1 << OVS_KEY_ATTR_TUNNEL)
		       | (1 << OVS_KEY_ATTR_IN_PORT)
		       | (1 << OVS_KEY_ATTR_ETHERTYPE));

	/* Check key attributes. */
	if (match->key->eth.type == htons(ETH_P_ARP)
			|| match->key->eth.type == htons(ETH_P_RARP)) {
		key_expected |= 1 << OVS_KEY_ATTR_ARP;
		if (match->mask && (match->mask->key.eth.type == htons(0xffff)))
			mask_allowed |= 1 << OVS_KEY_ATTR_ARP;
	}

	if (eth_p_mpls(match->key->eth.type)) {
		key_expected |= 1 << OVS_KEY_ATTR_MPLS;
		if (match->mask && (match->mask->key.eth.type == htons(0xffff)))
			mask_allowed |= 1 << OVS_KEY_ATTR_MPLS;
	}

	if (match->key->eth.type == htons(ETH_P_IP)) {
		key_expected |= 1 << OVS_KEY_ATTR_IPV4;
		if (match->mask && (match->mask->key.eth.type == htons(0xffff)))
			mask_allowed |= 1 << OVS_KEY_ATTR_IPV4;

		if (match->key->ip.frag != OVS_FRAG_TYPE_LATER) {
			if (match->key->ip.proto == IPPROTO_UDP) {
				key_expected |= 1 << OVS_KEY_ATTR_UDP;
				if (match->mask && (match->mask->key.ip.proto == 0xff))
					mask_allowed |= 1 << OVS_KEY_ATTR_UDP;
			}

			if (match->key->ip.proto == IPPROTO_SCTP) {
				key_expected |= 1 << OVS_KEY_ATTR_SCTP;
				if (match->mask && (match->mask->key.ip.proto == 0xff))
					mask_allowed |= 1 << OVS_KEY_ATTR_SCTP;
			}

			if (match->key->ip.proto == IPPROTO_TCP) {
				key_expected |= 1 << OVS_KEY_ATTR_TCP;
				key_expected |= 1 << OVS_KEY_ATTR_TCP_FLAGS;
				if (match->mask && (match->mask->key.ip.proto == 0xff)) {
					mask_allowed |= 1 << OVS_KEY_ATTR_TCP;
					mask_allowed |= 1 << OVS_KEY_ATTR_TCP_FLAGS;
				}
			}

			if (match->key->ip.proto == IPPROTO_ICMP) {
				key_expected |= 1 << OVS_KEY_ATTR_ICMP;
				if (match->mask && (match->mask->key.ip.proto == 0xff))
					mask_allowed |= 1 << OVS_KEY_ATTR_ICMP;
			}
		}
	}

	if (match->key->eth.type == htons(ETH_P_IPV6)) {
		key_expected |= 1 << OVS_KEY_ATTR_IPV6;
		if (match->mask && (match->mask->key.eth.type == htons(0xffff)))
			mask_allowed |= 1 << OVS_KEY_ATTR_IPV6;

		if (match->key->ip.frag != OVS_FRAG_TYPE_LATER) {
			if (match->key->ip.proto == IPPROTO_UDP) {
				key_expected |= 1 << OVS_KEY_ATTR_UDP;
				if (match->mask && (match->mask->key.ip.proto == 0xff))
					mask_allowed |= 1 << OVS_KEY_ATTR_UDP;
			}

			if (match->key->ip.proto == IPPROTO_SCTP) {
				key_expected |= 1 << OVS_KEY_ATTR_SCTP;
				if (match->mask && (match->mask->key.ip.proto == 0xff))
					mask_allowed |= 1 << OVS_KEY_ATTR_SCTP;
			}

			if (match->key->ip.proto == IPPROTO_TCP) {
				key_expected |= 1 << OVS_KEY_ATTR_TCP;
				key_expected |= 1 << OVS_KEY_ATTR_TCP_FLAGS;
				if (match->mask && (match->mask->key.ip.proto == 0xff)) {
					mask_allowed |= 1 << OVS_KEY_ATTR_TCP;
					mask_allowed |= 1 << OVS_KEY_ATTR_TCP_FLAGS;
				}
			}

			if (match->key->ip.proto == IPPROTO_ICMPV6) {
				key_expected |= 1 << OVS_KEY_ATTR_ICMPV6;
				if (match->mask && (match->mask->key.ip.proto == 0xff))
					mask_allowed |= 1 << OVS_KEY_ATTR_ICMPV6;

				if (match->key->tp.src ==
						htons(NDISC_NEIGHBOUR_SOLICITATION) ||
				    match->key->tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT)) {
					key_expected |= 1 << OVS_KEY_ATTR_ND;
					if (match->mask && (match->mask->key.tp.src == htons(0xff)))
						mask_allowed |= 1 << OVS_KEY_ATTR_ND;
				}
			}
		}
	}

	if ((key_attrs & key_expected) != key_expected) {
		/* Key attributes check failed. */
		OVS_NLERR(log, "Missing key (keys=%llx, expected=%llx)",
			  (unsigned long long)key_attrs,
			  (unsigned long long)key_expected);
		return false;
	}

	if ((mask_attrs & mask_allowed) != mask_attrs) {
		/* Mask attributes check failed. */
		OVS_NLERR(log, "Unexpected mask (mask=%llx, allowed=%llx)",
			  (unsigned long long)mask_attrs,
			  (unsigned long long)mask_allowed);
		return false;
	}

	return true;
}

size_t ovs_tun_key_attr_size(void)
{
	/* Whenever adding new OVS_TUNNEL_KEY_ FIELDS, we should consider
	 * updating this function.
	 */
	return    nla_total_size(8)    /* OVS_TUNNEL_KEY_ATTR_ID */
		+ nla_total_size(16)   /* OVS_TUNNEL_KEY_ATTR_IPV[46]_SRC */
		+ nla_total_size(16)   /* OVS_TUNNEL_KEY_ATTR_IPV[46]_DST */
		+ nla_total_size(1)    /* OVS_TUNNEL_KEY_ATTR_TOS */
		+ nla_total_size(1)    /* OVS_TUNNEL_KEY_ATTR_TTL */
		+ nla_total_size(0)    /* OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT */
		+ nla_total_size(0)    /* OVS_TUNNEL_KEY_ATTR_CSUM */
		+ nla_total_size(0)    /* OVS_TUNNEL_KEY_ATTR_OAM */
		+ nla_total_size(256)  /* OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS */
		/* OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS is mutually exclusive with
		 * OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS and covered by it.
		 */
		+ nla_total_size(2)    /* OVS_TUNNEL_KEY_ATTR_TP_SRC */
		+ nla_total_size(2);   /* OVS_TUNNEL_KEY_ATTR_TP_DST */
}

size_t ovs_key_attr_size(void)
{
	/* Whenever adding new OVS_KEY_ FIELDS, we should consider
	 * updating this function.
	 */
	BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 26);

	return    nla_total_size(4)   /* OVS_KEY_ATTR_PRIORITY */
		+ nla_total_size(0)   /* OVS_KEY_ATTR_TUNNEL */
		  + ovs_tun_key_attr_size()
		+ nla_total_size(4)   /* OVS_KEY_ATTR_IN_PORT */
		+ nla_total_size(4)   /* OVS_KEY_ATTR_SKB_MARK */
		+ nla_total_size(4)   /* OVS_KEY_ATTR_DP_HASH */
		+ nla_total_size(4)   /* OVS_KEY_ATTR_RECIRC_ID */
		+ nla_total_size(4)   /* OVS_KEY_ATTR_CT_STATE */
		+ nla_total_size(2)   /* OVS_KEY_ATTR_CT_ZONE */
		+ nla_total_size(4)   /* OVS_KEY_ATTR_CT_MARK */
		+ nla_total_size(16)  /* OVS_KEY_ATTR_CT_LABELS */
		+ nla_total_size(12)  /* OVS_KEY_ATTR_ETHERNET */
		+ nla_total_size(2)   /* OVS_KEY_ATTR_ETHERTYPE */
		+ nla_total_size(4)   /* OVS_KEY_ATTR_VLAN */
		+ nla_total_size(0)   /* OVS_KEY_ATTR_ENCAP */
		+ nla_total_size(2)   /* OVS_KEY_ATTR_ETHERTYPE */
		+ nla_total_size(40)  /* OVS_KEY_ATTR_IPV6 */
		+ nla_total_size(2)   /* OVS_KEY_ATTR_ICMPV6 */
		+ nla_total_size(28); /* OVS_KEY_ATTR_ND */
}

static const struct ovs_len_tbl ovs_vxlan_ext_key_lens[OVS_VXLAN_EXT_MAX + 1] = {
	[OVS_VXLAN_EXT_GBP]	    = { .len = sizeof(u32) },
};

static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1] = {
	[OVS_TUNNEL_KEY_ATTR_ID]	    = { .len = sizeof(u64) },
	[OVS_TUNNEL_KEY_ATTR_IPV4_SRC]	    = { .len = sizeof(u32) },
	[OVS_TUNNEL_KEY_ATTR_IPV4_DST]	    = { .len = sizeof(u32) },
	[OVS_TUNNEL_KEY_ATTR_TOS]	    = { .len = 1 },
	[OVS_TUNNEL_KEY_ATTR_TTL]	    = { .len = 1 },
	[OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT] = { .len = 0 },
	[OVS_TUNNEL_KEY_ATTR_CSUM]	    = { .len = 0 },
	[OVS_TUNNEL_KEY_ATTR_TP_SRC]	    = { .len = sizeof(u16) },
	[OVS_TUNNEL_KEY_ATTR_TP_DST]	    = { .len = sizeof(u16) },
	[OVS_TUNNEL_KEY_ATTR_OAM]	    = { .len = 0 },
	[OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS]   = { .len = OVS_ATTR_VARIABLE },
	[OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS]    = { .len = OVS_ATTR_NESTED,
						.next = ovs_vxlan_ext_key_lens },
	[OVS_TUNNEL_KEY_ATTR_IPV6_SRC]      = { .len = sizeof(struct in6_addr) },
	[OVS_TUNNEL_KEY_ATTR_IPV6_DST]      = { .len = sizeof(struct in6_addr) },
};

/* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute.  */
static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = {
	[OVS_KEY_ATTR_ENCAP]	 = { .len = OVS_ATTR_NESTED },
	[OVS_KEY_ATTR_PRIORITY]	 = { .len = sizeof(u32) },
	[OVS_KEY_ATTR_IN_PORT]	 = { .len = sizeof(u32) },
	[OVS_KEY_ATTR_SKB_MARK]	 = { .len = sizeof(u32) },
	[OVS_KEY_ATTR_ETHERNET]	 = { .len = sizeof(struct ovs_key_ethernet) },
	[OVS_KEY_ATTR_VLAN]	 = { .len = sizeof(__be16) },
	[OVS_KEY_ATTR_ETHERTYPE] = { .len = sizeof(__be16) },
	[OVS_KEY_ATTR_IPV4]	 = { .len = sizeof(struct ovs_key_ipv4) },
	[OVS_KEY_ATTR_IPV6]	 = { .len = sizeof(struct ovs_key_ipv6) },
	[OVS_KEY_ATTR_TCP]	 = { .len = sizeof(struct ovs_key_tcp) },
	[OVS_KEY_ATTR_TCP_FLAGS] = { .len = sizeof(__be16) },
	[OVS_KEY_ATTR_UDP]	 = { .len = sizeof(struct ovs_key_udp) },
	[OVS_KEY_ATTR_SCTP]	 = { .len = sizeof(struct ovs_key_sctp) },
	[OVS_KEY_ATTR_ICMP]	 = { .len = sizeof(struct ovs_key_icmp) },
	[OVS_KEY_ATTR_ICMPV6]	 = { .len = sizeof(struct ovs_key_icmpv6) },
	[OVS_KEY_ATTR_ARP]	 = { .len = sizeof(struct ovs_key_arp) },
	[OVS_KEY_ATTR_ND]	 = { .len = sizeof(struct ovs_key_nd) },
	[OVS_KEY_ATTR_RECIRC_ID] = { .len = sizeof(u32) },
	[OVS_KEY_ATTR_DP_HASH]	 = { .len = sizeof(u32) },
	[OVS_KEY_ATTR_TUNNEL]	 = { .len = OVS_ATTR_NESTED,
				     .next = ovs_tunnel_key_lens, },
	[OVS_KEY_ATTR_MPLS]	 = { .len = sizeof(struct ovs_key_mpls) },
	[OVS_KEY_ATTR_CT_STATE]	 = { .len = sizeof(u32) },
	[OVS_KEY_ATTR_CT_ZONE]	 = { .len = sizeof(u16) },
	[OVS_KEY_ATTR_CT_MARK]	 = { .len = sizeof(u32) },
	[OVS_KEY_ATTR_CT_LABELS] = { .len = sizeof(struct ovs_key_ct_labels) },
};

static bool check_attr_len(unsigned int attr_len, unsigned int expected_len)
{
	return expected_len == attr_len ||
	       expected_len == OVS_ATTR_NESTED ||
	       expected_len == OVS_ATTR_VARIABLE;
}

static bool is_all_zero(const u8 *fp, size_t size)
{
	int i;

	if (!fp)
		return false;

	for (i = 0; i < size; i++)
		if (fp[i])
			return false;

	return true;
}

static int __parse_flow_nlattrs(const struct nlattr *attr,
				const struct nlattr *a[],
				u64 *attrsp, bool log, bool nz)
{
	const struct nlattr *nla;
	u64 attrs;
	int rem;

	attrs = *attrsp;
	nla_for_each_nested(nla, attr, rem) {
		u16 type = nla_type(nla);
		int expected_len;

		if (type > OVS_KEY_ATTR_MAX) {
			OVS_NLERR(log, "Key type %d is out of range max %d",
				  type, OVS_KEY_ATTR_MAX);
			return -EINVAL;
		}

		if (attrs & (1 << type)) {
			OVS_NLERR(log, "Duplicate key (type %d).", type);
			return -EINVAL;
		}

		expected_len = ovs_key_lens[type].len;
		if (!check_attr_len(nla_len(nla), expected_len)) {
			OVS_NLERR(log, "Key %d has unexpected len %d expected %d",
				  type, nla_len(nla), expected_len);
			return -EINVAL;
		}

		if (!nz || !is_all_zero(nla_data(nla), expected_len)) {
			attrs |= 1 << type;
			a[type] = nla;
		}
	}
	if (rem) {
		OVS_NLERR(log, "Message has %d unknown bytes.", rem);
		return -EINVAL;
	}

	*attrsp = attrs;
	return 0;
}

static int parse_flow_mask_nlattrs(const struct nlattr *attr,
				   const struct nlattr *a[], u64 *attrsp,
				   bool log)
{
	return __parse_flow_nlattrs(attr, a, attrsp, log, true);
}

static int parse_flow_nlattrs(const struct nlattr *attr,
			      const struct nlattr *a[], u64 *attrsp,
			      bool log)
{
	return __parse_flow_nlattrs(attr, a, attrsp, log, false);
}

static int genev_tun_opt_from_nlattr(const struct nlattr *a,
				     struct sw_flow_match *match, bool is_mask,
				     bool log)
{
	unsigned long opt_key_offset;

	if (nla_len(a) > sizeof(match->key->tun_opts)) {
		OVS_NLERR(log, "Geneve option length err (len %d, max %zu).",
			  nla_len(a), sizeof(match->key->tun_opts));
		return -EINVAL;
	}

	if (nla_len(a) % 4 != 0) {
		OVS_NLERR(log, "Geneve opt len %d is not a multiple of 4.",
			  nla_len(a));
		return -EINVAL;
	}

	/* We need to record the length of the options passed
	 * down, otherwise packets with the same format but
	 * additional options will be silently matched.
	 */
	if (!is_mask) {
		SW_FLOW_KEY_PUT(match, tun_opts_len, nla_len(a),
				false);
	} else {
		/* This is somewhat unusual because it looks at
		 * both the key and mask while parsing the
		 * attributes (and by extension assumes the key
		 * is parsed first). Normally, we would verify
		 * that each is the correct length and that the
		 * attributes line up in the validate function.
		 * However, that is difficult because this is
		 * variable length and we won't have the
		 * information later.
		 */
		if (match->key->tun_opts_len != nla_len(a)) {
			OVS_NLERR(log, "Geneve option len %d != mask len %d",
				  match->key->tun_opts_len, nla_len(a));
			return -EINVAL;
		}

		SW_FLOW_KEY_PUT(match, tun_opts_len, 0xff, true);
	}

	opt_key_offset = TUN_METADATA_OFFSET(nla_len(a));
	SW_FLOW_KEY_MEMCPY_OFFSET(match, opt_key_offset, nla_data(a),
				  nla_len(a), is_mask);
	return 0;
}

static int vxlan_tun_opt_from_nlattr(const struct nlattr *attr,
				     struct sw_flow_match *match, bool is_mask,
				     bool log)
{
	struct nlattr *a;
	int rem;
	unsigned long opt_key_offset;
	struct vxlan_metadata opts;

	BUILD_BUG_ON(sizeof(opts) > sizeof(match->key->tun_opts));

	memset(&opts, 0, sizeof(opts));
	nla_for_each_nested(a, attr, rem) {
		int type = nla_type(a);

		if (type > OVS_VXLAN_EXT_MAX) {
			OVS_NLERR(log, "VXLAN extension %d out of range max %d",
				  type, OVS_VXLAN_EXT_MAX);
			return -EINVAL;
		}

		if (!check_attr_len(nla_len(a),
				    ovs_vxlan_ext_key_lens[type].len)) {
			OVS_NLERR(log, "VXLAN extension %d has unexpected len %d expected %d",
				  type, nla_len(a),
				  ovs_vxlan_ext_key_lens[type].len);
			return -EINVAL;
		}

		switch (type) {
		case OVS_VXLAN_EXT_GBP:
			opts.gbp = nla_get_u32(a);
			break;
		default:
			OVS_NLERR(log, "Unknown VXLAN extension attribute %d",
				  type);
			return -EINVAL;
		}
	}
	if (rem) {
		OVS_NLERR(log, "VXLAN extension message has %d unknown bytes.",
			  rem);
		return -EINVAL;
	}

	if (!is_mask)
		SW_FLOW_KEY_PUT(match, tun_opts_len, sizeof(opts), false);
	else
		SW_FLOW_KEY_PUT(match, tun_opts_len, 0xff, true);

	opt_key_offset = TUN_METADATA_OFFSET(sizeof(opts));
	SW_FLOW_KEY_MEMCPY_OFFSET(match, opt_key_offset, &opts, sizeof(opts),
				  is_mask);
	return 0;
}

static int ip_tun_from_nlattr(const struct nlattr *attr,
			      struct sw_flow_match *match, bool is_mask,
			      bool log)
{
	bool ttl = false, ipv4 = false, ipv6 = false;
	__be16 tun_flags = 0;
	int opts_type = 0;
	struct nlattr *a;
	int rem;

	nla_for_each_nested(a, attr, rem) {
		int type = nla_type(a);
		int err;

		if (type > OVS_TUNNEL_KEY_ATTR_MAX) {
			OVS_NLERR(log, "Tunnel attr %d out of range max %d",
				  type, OVS_TUNNEL_KEY_ATTR_MAX);
			return -EINVAL;
		}

		if (!check_attr_len(nla_len(a),
				    ovs_tunnel_key_lens[type].len)) {
			OVS_NLERR(log, "Tunnel attr %d has unexpected len %d expected %d",
				  type, nla_len(a), ovs_tunnel_key_lens[type].len);
			return -EINVAL;
		}

		switch (type) {
		case OVS_TUNNEL_KEY_ATTR_ID:
			SW_FLOW_KEY_PUT(match, tun_key.tun_id,
					nla_get_be64(a), is_mask);
			tun_flags |= TUNNEL_KEY;
			break;
		case OVS_TUNNEL_KEY_ATTR_IPV4_SRC:
			SW_FLOW_KEY_PUT(match, tun_key.u.ipv4.src,
					nla_get_in_addr(a), is_mask);
			ipv4 = true;
			break;
		case OVS_TUNNEL_KEY_ATTR_IPV4_DST:
			SW_FLOW_KEY_PUT(match, tun_key.u.ipv4.dst,
					nla_get_in_addr(a), is_mask);
			ipv4 = true;
			break;
		case OVS_TUNNEL_KEY_ATTR_IPV6_SRC:
			SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.dst,
					nla_get_in6_addr(a), is_mask);
			ipv6 = true;
			break;
		case OVS_TUNNEL_KEY_ATTR_IPV6_DST:
			SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.dst,
					nla_get_in6_addr(a), is_mask);
			ipv6 = true;
			break;
		case OVS_TUNNEL_KEY_ATTR_TOS:
			SW_FLOW_KEY_PUT(match, tun_key.tos,
					nla_get_u8(a), is_mask);
			break;
		case OVS_TUNNEL_KEY_ATTR_TTL:
			SW_FLOW_KEY_PUT(match, tun_key.ttl,
					nla_get_u8(a), is_mask);
			ttl = true;
			break;
		case OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT:
			tun_flags |= TUNNEL_DONT_FRAGMENT;
			break;
		case OVS_TUNNEL_KEY_ATTR_CSUM:
			tun_flags |= TUNNEL_CSUM;
			break;
		case OVS_TUNNEL_KEY_ATTR_TP_SRC:
			SW_FLOW_KEY_PUT(match, tun_key.tp_src,
					nla_get_be16(a), is_mask);
			break;
		case OVS_TUNNEL_KEY_ATTR_TP_DST:
			SW_FLOW_KEY_PUT(match, tun_key.tp_dst,
					nla_get_be16(a), is_mask);
			break;
		case OVS_TUNNEL_KEY_ATTR_OAM:
			tun_flags |= TUNNEL_OAM;
			break;
		case OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS:
			if (opts_type) {
				OVS_NLERR(log, "Multiple metadata blocks provided");
				return -EINVAL;
			}

			err = genev_tun_opt_from_nlattr(a, match, is_mask, log);
			if (err)
				return err;

			tun_flags |= TUNNEL_GENEVE_OPT;
			opts_type = type;
			break;
		case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS:
			if (opts_type) {
				OVS_NLERR(log, "Multiple metadata blocks provided");
				return -EINVAL;
			}

			err = vxlan_tun_opt_from_nlattr(a, match, is_mask, log);
			if (err)
				return err;

			tun_flags |= TUNNEL_VXLAN_OPT;
			opts_type = type;
			break;
		default:
			OVS_NLERR(log, "Unknown IP tunnel attribute %d",
				  type);
			return -EINVAL;
		}
	}

	SW_FLOW_KEY_PUT(match, tun_key.tun_flags, tun_flags, is_mask);
	if (is_mask)
		SW_FLOW_KEY_MEMSET_FIELD(match, tun_proto, 0xff, true);
	else
		SW_FLOW_KEY_PUT(match, tun_proto, ipv6 ? AF_INET6 : AF_INET,
				false);

	if (rem > 0) {
		OVS_NLERR(log, "IP tunnel attribute has %d unknown bytes.",
			  rem);
		return -EINVAL;
	}

	if (ipv4 && ipv6) {
		OVS_NLERR(log, "Mixed IPv4 and IPv6 tunnel attributes");
		return -EINVAL;
	}

	if (!is_mask) {
		if (!ipv4 && !ipv6) {
			OVS_NLERR(log, "IP tunnel dst address not specified");
			return -EINVAL;
		}
		if (ipv4 && !match->key->tun_key.u.ipv4.dst) {
			OVS_NLERR(log, "IPv4 tunnel dst address is zero");
			return -EINVAL;
		}
		if (ipv6 && ipv6_addr_any(&match->key->tun_key.u.ipv6.dst)) {
			OVS_NLERR(log, "IPv6 tunnel dst address is zero");
			return -EINVAL;
		}

		if (!ttl) {
			OVS_NLERR(log, "IP tunnel TTL not specified.");
			return -EINVAL;
		}
	}

	return opts_type;
}

static int vxlan_opt_to_nlattr(struct sk_buff *skb,
			       const void *tun_opts, int swkey_tun_opts_len)
{
	const struct vxlan_metadata *opts = tun_opts;
	struct nlattr *nla;

	nla = nla_nest_start(skb, OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS);
	if (!nla)
		return -EMSGSIZE;

	if (nla_put_u32(skb, OVS_VXLAN_EXT_GBP, opts->gbp) < 0)
		return -EMSGSIZE;

	nla_nest_end(skb, nla);
	return 0;
}

static int __ip_tun_to_nlattr(struct sk_buff *skb,
			      const struct ip_tunnel_key *output,
			      const void *tun_opts, int swkey_tun_opts_len,
			      unsigned short tun_proto)
{
	if (output->tun_flags & TUNNEL_KEY &&
	    nla_put_be64(skb, OVS_TUNNEL_KEY_ATTR_ID, output->tun_id))
		return -EMSGSIZE;
	switch (tun_proto) {
	case AF_INET:
		if (output->u.ipv4.src &&
		    nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC,
				    output->u.ipv4.src))
			return -EMSGSIZE;
		if (output->u.ipv4.dst &&
		    nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST,
				    output->u.ipv4.dst))
			return -EMSGSIZE;
		break;
	case AF_INET6:
		if (!ipv6_addr_any(&output->u.ipv6.src) &&
		    nla_put_in6_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV6_SRC,
				     &output->u.ipv6.src))
			return -EMSGSIZE;
		if (!ipv6_addr_any(&output->u.ipv6.dst) &&
		    nla_put_in6_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV6_DST,
				     &output->u.ipv6.dst))
			return -EMSGSIZE;
		break;
	}
	if (output->tos &&
	    nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TOS, output->tos))
		return -EMSGSIZE;
	if (nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TTL, output->ttl))
		return -EMSGSIZE;
	if ((output->tun_flags & TUNNEL_DONT_FRAGMENT) &&
	    nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT))
		return -EMSGSIZE;
	if ((output->tun_flags & TUNNEL_CSUM) &&
	    nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_CSUM))
		return -EMSGSIZE;
	if (output->tp_src &&
	    nla_put_be16(skb, OVS_TUNNEL_KEY_ATTR_TP_SRC, output->tp_src))
		return -EMSGSIZE;
	if (output->tp_dst &&
	    nla_put_be16(skb, OVS_TUNNEL_KEY_ATTR_TP_DST, output->tp_dst))
		return -EMSGSIZE;
	if ((output->tun_flags & TUNNEL_OAM) &&
	    nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_OAM))
		return -EMSGSIZE;
	if (tun_opts) {
		if (output->tun_flags & TUNNEL_GENEVE_OPT &&
		    nla_put(skb, OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS,
			    swkey_tun_opts_len, tun_opts))
			return -EMSGSIZE;
		else if (output->tun_flags & TUNNEL_VXLAN_OPT &&
			 vxlan_opt_to_nlattr(skb, tun_opts, swkey_tun_opts_len))
			return -EMSGSIZE;
	}

	return 0;
}

static int ip_tun_to_nlattr(struct sk_buff *skb,
			    const struct ip_tunnel_key *output,
			    const void *tun_opts, int swkey_tun_opts_len,
			    unsigned short tun_proto)
{
	struct nlattr *nla;
	int err;

	nla = nla_nest_start(skb, OVS_KEY_ATTR_TUNNEL);
	if (!nla)
		return -EMSGSIZE;

	err = __ip_tun_to_nlattr(skb, output, tun_opts, swkey_tun_opts_len,
				 tun_proto);
	if (err)
		return err;

	nla_nest_end(skb, nla);
	return 0;
}

int ovs_nla_put_egress_tunnel_key(struct sk_buff *skb,
				  const struct ip_tunnel_info *egress_tun_info,
				  const void *egress_tun_opts)
{
	return __ip_tun_to_nlattr(skb, &egress_tun_info->key,
				  egress_tun_opts,
				  egress_tun_info->options_len,
				  ip_tunnel_info_af(egress_tun_info));
}

static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match,
				 u64 *attrs, const struct nlattr **a,
				 bool is_mask, bool log)
{
	if (*attrs & (1 << OVS_KEY_ATTR_DP_HASH)) {
		u32 hash_val = nla_get_u32(a[OVS_KEY_ATTR_DP_HASH]);

		SW_FLOW_KEY_PUT(match, ovs_flow_hash, hash_val, is_mask);
		*attrs &= ~(1 << OVS_KEY_ATTR_DP_HASH);
	}

	if (*attrs & (1 << OVS_KEY_ATTR_RECIRC_ID)) {
		u32 recirc_id = nla_get_u32(a[OVS_KEY_ATTR_RECIRC_ID]);

		SW_FLOW_KEY_PUT(match, recirc_id, recirc_id, is_mask);
		*attrs &= ~(1 << OVS_KEY_ATTR_RECIRC_ID);
	}

	if (*attrs & (1 << OVS_KEY_ATTR_PRIORITY)) {
		SW_FLOW_KEY_PUT(match, phy.priority,
			  nla_get_u32(a[OVS_KEY_ATTR_PRIORITY]), is_mask);
		*attrs &= ~(1 << OVS_KEY_ATTR_PRIORITY);
	}

	if (*attrs & (1 << OVS_KEY_ATTR_IN_PORT)) {
		u32 in_port = nla_get_u32(a[OVS_KEY_ATTR_IN_PORT]);

		if (is_mask) {
			in_port = 0xffffffff; /* Always exact match in_port. */
		} else if (in_port >= DP_MAX_PORTS) {
			OVS_NLERR(log, "Port %d exceeds max allowable %d",
				  in_port, DP_MAX_PORTS);
			return -EINVAL;
		}

		SW_FLOW_KEY_PUT(match, phy.in_port, in_port, is_mask);
		*attrs &= ~(1 << OVS_KEY_ATTR_IN_PORT);
	} else if (!is_mask) {
		SW_FLOW_KEY_PUT(match, phy.in_port, DP_MAX_PORTS, is_mask);
	}

	if (*attrs & (1 << OVS_KEY_ATTR_SKB_MARK)) {
		uint32_t mark = nla_get_u32(a[OVS_KEY_ATTR_SKB_MARK]);

		SW_FLOW_KEY_PUT(match, phy.skb_mark, mark, is_mask);
		*attrs &= ~(1 << OVS_KEY_ATTR_SKB_MARK);
	}
	if (*attrs & (1 << OVS_KEY_ATTR_TUNNEL)) {
		if (ip_tun_from_nlattr(a[OVS_KEY_ATTR_TUNNEL], match,
				       is_mask, log) < 0)
			return -EINVAL;
		*attrs &= ~(1 << OVS_KEY_ATTR_TUNNEL);
	}

	if (*attrs & (1 << OVS_KEY_ATTR_CT_STATE) &&
	    ovs_ct_verify(net, OVS_KEY_ATTR_CT_STATE)) {
		u32 ct_state = nla_get_u32(a[OVS_KEY_ATTR_CT_STATE]);

		if (!is_mask && !ovs_ct_state_supported(ct_state)) {
			OVS_NLERR(log, "ct_state flags %08x unsupported",
				  ct_state);
			return -EINVAL;
		}

		SW_FLOW_KEY_PUT(match, ct.state, ct_state, is_mask);
		*attrs &= ~(1ULL << OVS_KEY_ATTR_CT_STATE);
	}
	if (*attrs & (1 << OVS_KEY_ATTR_CT_ZONE) &&
	    ovs_ct_verify(net, OVS_KEY_ATTR_CT_ZONE)) {
		u16 ct_zone = nla_get_u16(a[OVS_KEY_ATTR_CT_ZONE]);

		SW_FLOW_KEY_PUT(match, ct.zone, ct_zone, is_mask);
		*attrs &= ~(1ULL << OVS_KEY_ATTR_CT_ZONE);
	}
	if (*attrs & (1 << OVS_KEY_ATTR_CT_MARK) &&
	    ovs_ct_verify(net, OVS_KEY_ATTR_CT_MARK)) {
		u32 mark = nla_get_u32(a[OVS_KEY_ATTR_CT_MARK]);

		SW_FLOW_KEY_PUT(match, ct.mark, mark, is_mask);
		*attrs &= ~(1ULL << OVS_KEY_ATTR_CT_MARK);
	}
	if (*attrs & (1 << OVS_KEY_ATTR_CT_LABELS) &&
	    ovs_ct_verify(net, OVS_KEY_ATTR_CT_LABELS)) {
		const struct ovs_key_ct_labels *cl;

		cl = nla_data(a[OVS_KEY_ATTR_CT_LABELS]);
		SW_FLOW_KEY_MEMCPY(match, ct.labels, cl->ct_labels,
				   sizeof(*cl), is_mask);
		*attrs &= ~(1ULL << OVS_KEY_ATTR_CT_LABELS);
	}
	return 0;
}

static int ovs_key_from_nlattrs(struct net *net, struct sw_flow_match *match,
				u64 attrs, const struct nlattr **a,
				bool is_mask, bool log)
{
	int err;

	err = metadata_from_nlattrs(net, match, &attrs, a, is_mask, log);
	if (err)
		return err;

	if (attrs & (1 << OVS_KEY_ATTR_ETHERNET)) {
		const struct ovs_key_ethernet *eth_key;

		eth_key = nla_data(a[OVS_KEY_ATTR_ETHERNET]);
		SW_FLOW_KEY_MEMCPY(match, eth.src,
				eth_key->eth_src, ETH_ALEN, is_mask);
		SW_FLOW_KEY_MEMCPY(match, eth.dst,
				eth_key->eth_dst, ETH_ALEN, is_mask);
		attrs &= ~(1 << OVS_KEY_ATTR_ETHERNET);
	}

	if (attrs & (1 << OVS_KEY_ATTR_VLAN)) {
		__be16 tci;

		tci = nla_get_be16(a[OVS_KEY_ATTR_VLAN]);
		if (!(tci & htons(VLAN_TAG_PRESENT))) {
			if (is_mask)
				OVS_NLERR(log, "VLAN TCI mask does not have exact match for VLAN_TAG_PRESENT bit.");
			else
				OVS_NLERR(log, "VLAN TCI does not have VLAN_TAG_PRESENT bit set.");

			return -EINVAL;
		}

		SW_FLOW_KEY_PUT(match, eth.tci, tci, is_mask);
		attrs &= ~(1 << OVS_KEY_ATTR_VLAN);
	}

	if (attrs & (1 << OVS_KEY_ATTR_ETHERTYPE)) {
		__be16 eth_type;

		eth_type = nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]);
		if (is_mask) {
			/* Always exact match EtherType. */
			eth_type = htons(0xffff);
		} else if (!eth_proto_is_802_3(eth_type)) {
			OVS_NLERR(log, "EtherType %x is less than min %x",
				  ntohs(eth_type), ETH_P_802_3_MIN);
			return -EINVAL;
		}

		SW_FLOW_KEY_PUT(match, eth.type, eth_type, is_mask);
		attrs &= ~(1 << OVS_KEY_ATTR_ETHERTYPE);
	} else if (!is_mask) {
		SW_FLOW_KEY_PUT(match, eth.type, htons(ETH_P_802_2), is_mask);
	}

	if (attrs & (1 << OVS_KEY_ATTR_IPV4)) {
		const struct ovs_key_ipv4 *ipv4_key;

		ipv4_key = nla_data(a[OVS_KEY_ATTR_IPV4]);
		if (!is_mask && ipv4_key->ipv4_frag > OVS_FRAG_TYPE_MAX) {
			OVS_NLERR(log, "IPv4 frag type %d is out of range max %d",
				  ipv4_key->ipv4_frag, OVS_FRAG_TYPE_MAX);
			return -EINVAL;
		}
		SW_FLOW_KEY_PUT(match, ip.proto,
				ipv4_key->ipv4_proto, is_mask);
		SW_FLOW_KEY_PUT(match, ip.tos,
				ipv4_key->ipv4_tos, is_mask);
		SW_FLOW_KEY_PUT(match, ip.ttl,
				ipv4_key->ipv4_ttl, is_mask);
		SW_FLOW_KEY_PUT(match, ip.frag,
				ipv4_key->ipv4_frag, is_mask);
		SW_FLOW_KEY_PUT(match, ipv4.addr.src,
				ipv4_key->ipv4_src, is_mask);
		SW_FLOW_KEY_PUT(match, ipv4.addr.dst,
				ipv4_key->ipv4_dst, is_mask);
		attrs &= ~(1 << OVS_KEY_ATTR_IPV4);
	}

	if (attrs & (1 << OVS_KEY_ATTR_IPV6)) {
		const struct ovs_key_ipv6 *ipv6_key;

		ipv6_key = nla_data(a[OVS_KEY_ATTR_IPV6]);
		if (!is_mask && ipv6_key->ipv6_frag > OVS_FRAG_TYPE_MAX) {
			OVS_NLERR(log, "IPv6 frag type %d is out of range max %d",
				  ipv6_key->ipv6_frag, OVS_FRAG_TYPE_MAX);
			return -EINVAL;
		}

		if (!is_mask && ipv6_key->ipv6_label & htonl(0xFFF00000)) {
			OVS_NLERR(log, "IPv6 flow label %x is out of range (max=%x).\n",
				  ntohl(ipv6_key->ipv6_label), (1 << 20) - 1);
			return -EINVAL;
		}

		SW_FLOW_KEY_PUT(match, ipv6.label,
				ipv6_key->ipv6_label, is_mask);
		SW_FLOW_KEY_PUT(match, ip.proto,
				ipv6_key->ipv6_proto, is_mask);
		SW_FLOW_KEY_PUT(match, ip.tos,
				ipv6_key->ipv6_tclass, is_mask);
		SW_FLOW_KEY_PUT(match, ip.ttl,
				ipv6_key->ipv6_hlimit, is_mask);
		SW_FLOW_KEY_PUT(match, ip.frag,
				ipv6_key->ipv6_frag, is_mask);
		SW_FLOW_KEY_MEMCPY(match, ipv6.addr.src,
				ipv6_key->ipv6_src,
				sizeof(match->key->ipv6.addr.src),
				is_mask);
		SW_FLOW_KEY_MEMCPY(match, ipv6.addr.dst,
				ipv6_key->ipv6_dst,
				sizeof(match->key->ipv6.addr.dst),
				is_mask);

		attrs &= ~(1 << OVS_KEY_ATTR_IPV6);
	}

	if (attrs & (1 << OVS_KEY_ATTR_ARP)) {
		const struct ovs_key_arp *arp_key;

		arp_key = nla_data(a[OVS_KEY_ATTR_ARP]);
		if (!is_mask && (arp_key->arp_op & htons(0xff00))) {
			OVS_NLERR(log, "Unknown ARP opcode (opcode=%d).",
				  arp_key->arp_op);
			return -EINVAL;
		}

		SW_FLOW_KEY_PUT(match, ipv4.addr.src,
				arp_key->arp_sip, is_mask);
		SW_FLOW_KEY_PUT(match, ipv4.addr.dst,
			arp_key->arp_tip, is_mask);
		SW_FLOW_KEY_PUT(match, ip.proto,
				ntohs(arp_key->arp_op), is_mask);
		SW_FLOW_KEY_MEMCPY(match, ipv4.arp.sha,
				arp_key->arp_sha, ETH_ALEN, is_mask);
		SW_FLOW_KEY_MEMCPY(match, ipv4.arp.tha,
				arp_key->arp_tha, ETH_ALEN, is_mask);

		attrs &= ~(1 << OVS_KEY_ATTR_ARP);
	}

	if (attrs & (1 << OVS_KEY_ATTR_MPLS)) {
		const struct ovs_key_mpls *mpls_key;

		mpls_key = nla_data(a[OVS_KEY_ATTR_MPLS]);
		SW_FLOW_KEY_PUT(match, mpls.top_lse,
				mpls_key->mpls_lse, is_mask);

		attrs &= ~(1 << OVS_KEY_ATTR_MPLS);
	 }

	if (attrs & (1 << OVS_KEY_ATTR_TCP)) {
		const struct ovs_key_tcp *tcp_key;

		tcp_key = nla_data(a[OVS_KEY_ATTR_TCP]);
		SW_FLOW_KEY_PUT(match, tp.src, tcp_key->tcp_src, is_mask);
		SW_FLOW_KEY_PUT(match, tp.dst, tcp_key->tcp_dst, is_mask);
		attrs &= ~(1 << OVS_KEY_ATTR_TCP);
	}

	if (attrs & (1 << OVS_KEY_ATTR_TCP_FLAGS)) {
		SW_FLOW_KEY_PUT(match, tp.flags,
				nla_get_be16(a[OVS_KEY_ATTR_TCP_FLAGS]),
				is_mask);
		attrs &= ~(1 << OVS_KEY_ATTR_TCP_FLAGS);
	}

	if (attrs & (1 << OVS_KEY_ATTR_UDP)) {
		const struct ovs_key_udp *udp_key;

		udp_key = nla_data(a[OVS_KEY_ATTR_UDP]);
		SW_FLOW_KEY_PUT(match, tp.src, udp_key->udp_src, is_mask);
		SW_FLOW_KEY_PUT(match, tp.dst, udp_key->udp_dst, is_mask);
		attrs &= ~(1 << OVS_KEY_ATTR_UDP);
	}

	if (attrs & (1 << OVS_KEY_ATTR_SCTP)) {
		const struct ovs_key_sctp *sctp_key;

		sctp_key = nla_data(a[OVS_KEY_ATTR_SCTP]);
		SW_FLOW_KEY_PUT(match, tp.src, sctp_key->sctp_src, is_mask);
		SW_FLOW_KEY_PUT(match, tp.dst, sctp_key->sctp_dst, is_mask);
		attrs &= ~(1 << OVS_KEY_ATTR_SCTP);
	}

	if (attrs & (1 << OVS_KEY_ATTR_ICMP)) {
		const struct ovs_key_icmp *icmp_key;

		icmp_key = nla_data(a[OVS_KEY_ATTR_ICMP]);
		SW_FLOW_KEY_PUT(match, tp.src,
				htons(icmp_key->icmp_type), is_mask);
		SW_FLOW_KEY_PUT(match, tp.dst,
				htons(icmp_key->icmp_code), is_mask);
		attrs &= ~(1 << OVS_KEY_ATTR_ICMP);
	}

	if (attrs & (1 << OVS_KEY_ATTR_ICMPV6)) {
		const struct ovs_key_icmpv6 *icmpv6_key;

		icmpv6_key = nla_data(a[OVS_KEY_ATTR_ICMPV6]);
		SW_FLOW_KEY_PUT(match, tp.src,
				htons(icmpv6_key->icmpv6_type), is_mask);
		SW_FLOW_KEY_PUT(match, tp.dst,
				htons(icmpv6_key->icmpv6_code), is_mask);
		attrs &= ~(1 << OVS_KEY_ATTR_ICMPV6);
	}

	if (attrs & (1 << OVS_KEY_ATTR_ND)) {
		const struct ovs_key_nd *nd_key;

		nd_key = nla_data(a[OVS_KEY_ATTR_ND]);
		SW_FLOW_KEY_MEMCPY(match, ipv6.nd.target,
			nd_key->nd_target,
			sizeof(match->key->ipv6.nd.target),
			is_mask);
		SW_FLOW_KEY_MEMCPY(match, ipv6.nd.sll,
			nd_key->nd_sll, ETH_ALEN, is_mask);
		SW_FLOW_KEY_MEMCPY(match, ipv6.nd.tll,
				nd_key->nd_tll, ETH_ALEN, is_mask);
		attrs &= ~(1 << OVS_KEY_ATTR_ND);
	}

	if (attrs != 0) {
		OVS_NLERR(log, "Unknown key attributes %llx",
			  (unsigned long long)attrs);
		return -EINVAL;
	}

	return 0;
}

static void nlattr_set(struct nlattr *attr, u8 val,
		       const struct ovs_len_tbl *tbl)
{
	struct nlattr *nla;
	int rem;

	/* The nlattr stream should already have been validated */
	nla_for_each_nested(nla, attr, rem) {
		if (tbl[nla_type(nla)].len == OVS_ATTR_NESTED) {
			if (tbl[nla_type(nla)].next)
				tbl = tbl[nla_type(nla)].next;
			nlattr_set(nla, val, tbl);
		} else {
			memset(nla_data(nla), val, nla_len(nla));
		}
	}
}

static void mask_set_nlattr(struct nlattr *attr, u8 val)
{
	nlattr_set(attr, val, ovs_key_lens);
}

/**
 * ovs_nla_get_match - parses Netlink attributes into a flow key and
 * mask. In case the 'mask' is NULL, the flow is treated as exact match
 * flow. Otherwise, it is treated as a wildcarded flow, except the mask
 * does not include any don't care bit.
 * @net: Used to determine per-namespace field support.
 * @match: receives the extracted flow match information.
 * @key: Netlink attribute holding nested %OVS_KEY_ATTR_* Netlink attribute
 * sequence. The fields should of the packet that triggered the creation
 * of this flow.
 * @mask: Optional. Netlink attribute holding nested %OVS_KEY_ATTR_* Netlink
 * attribute specifies the mask field of the wildcarded flow.
 * @log: Boolean to allow kernel error logging.  Normally true, but when
 * probing for feature compatibility this should be passed in as false to
 * suppress unnecessary error logging.
 */
int ovs_nla_get_match(struct net *net, struct sw_flow_match *match,
		      const struct nlattr *nla_key,
		      const struct nlattr *nla_mask,
		      bool log)
{
	const struct nlattr *a[OVS_KEY_ATTR_MAX + 1];
	const struct nlattr *encap;
	struct nlattr *newmask = NULL;
	u64 key_attrs = 0;
	u64 mask_attrs = 0;
	bool encap_valid = false;
	int err;

	err = parse_flow_nlattrs(nla_key, a, &key_attrs, log);
	if (err)
		return err;

	if ((key_attrs & (1 << OVS_KEY_ATTR_ETHERNET)) &&
	    (key_attrs & (1 << OVS_KEY_ATTR_ETHERTYPE)) &&
	    (nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]) == htons(ETH_P_8021Q))) {
		__be16 tci;

		if (!((key_attrs & (1 << OVS_KEY_ATTR_VLAN)) &&
		      (key_attrs & (1 << OVS_KEY_ATTR_ENCAP)))) {
			OVS_NLERR(log, "Invalid Vlan frame.");
			return -EINVAL;
		}

		key_attrs &= ~(1 << OVS_KEY_ATTR_ETHERTYPE);
		tci = nla_get_be16(a[OVS_KEY_ATTR_VLAN]);
		encap = a[OVS_KEY_ATTR_ENCAP];
		key_attrs &= ~(1 << OVS_KEY_ATTR_ENCAP);
		encap_valid = true;

		if (tci & htons(VLAN_TAG_PRESENT)) {
			err = parse_flow_nlattrs(encap, a, &key_attrs, log);
			if (err)
				return err;
		} else if (!tci) {
			/* Corner case for truncated 802.1Q header. */
			if (nla_len(encap)) {
				OVS_NLERR(log, "Truncated 802.1Q header has non-zero encap attribute.");
				return -EINVAL;
			}
		} else {
			OVS_NLERR(log, "Encap attr is set for non-VLAN frame");
			return  -EINVAL;
		}
	}

	err = ovs_key_from_nlattrs(net, match, key_attrs, a, false, log);
	if (err)
		return err;

	if (match->mask) {
		if (!nla_mask) {
			/* Create an exact match mask. We need to set to 0xff
			 * all the 'match->mask' fields that have been touched
			 * in 'match->key'. We cannot simply memset
			 * 'match->mask', because padding bytes and fields not
			 * specified in 'match->key' should be left to 0.
			 * Instead, we use a stream of netlink attributes,
			 * copied from 'key' and set to 0xff.
			 * ovs_key_from_nlattrs() will take care of filling
			 * 'match->mask' appropriately.
			 */
			newmask = kmemdup(nla_key,
					  nla_total_size(nla_len(nla_key)),
					  GFP_KERNEL);
			if (!newmask)
				return -ENOMEM;

			mask_set_nlattr(newmask, 0xff);

			/* The userspace does not send tunnel attributes that
			 * are 0, but we should not wildcard them nonetheless.
			 */
			if (match->key->tun_proto)
				SW_FLOW_KEY_MEMSET_FIELD(match, tun_key,
							 0xff, true);

			nla_mask = newmask;
		}

		err = parse_flow_mask_nlattrs(nla_mask, a, &mask_attrs, log);
		if (err)
			goto free_newmask;

		/* Always match on tci. */
		SW_FLOW_KEY_PUT(match, eth.tci, htons(0xffff), true);

		if (mask_attrs & 1 << OVS_KEY_ATTR_ENCAP) {
			__be16 eth_type = 0;
			__be16 tci = 0;

			if (!encap_valid) {
				OVS_NLERR(log, "Encap mask attribute is set for non-VLAN frame.");
				err = -EINVAL;
				goto free_newmask;
			}

			mask_attrs &= ~(1 << OVS_KEY_ATTR_ENCAP);
			if (a[OVS_KEY_ATTR_ETHERTYPE])
				eth_type = nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]);

			if (eth_type == htons(0xffff)) {
				mask_attrs &= ~(1 << OVS_KEY_ATTR_ETHERTYPE);
				encap = a[OVS_KEY_ATTR_ENCAP];
				err = parse_flow_mask_nlattrs(encap, a,
							      &mask_attrs, log);
				if (err)
					goto free_newmask;
			} else {
				OVS_NLERR(log, "VLAN frames must have an exact match on the TPID (mask=%x).",
					  ntohs(eth_type));
				err = -EINVAL;
				goto free_newmask;
			}

			if (a[OVS_KEY_ATTR_VLAN])
				tci = nla_get_be16(a[OVS_KEY_ATTR_VLAN]);

			if (!(tci & htons(VLAN_TAG_PRESENT))) {
				OVS_NLERR(log, "VLAN tag present bit must have an exact match (tci_mask=%x).",
					  ntohs(tci));
				err = -EINVAL;
				goto free_newmask;
			}
		}

		err = ovs_key_from_nlattrs(net, match, mask_attrs, a, true,
					   log);
		if (err)
			goto free_newmask;
	}

	if (!match_validate(match, key_attrs, mask_attrs, log))
		err = -EINVAL;

free_newmask:
	kfree(newmask);
	return err;
}

static size_t get_ufid_len(const struct nlattr *attr, bool log)
{
	size_t len;

	if (!attr)
		return 0;

	len = nla_len(attr);
	if (len < 1 || len > MAX_UFID_LENGTH) {
		OVS_NLERR(log, "ufid size %u bytes exceeds the range (1, %d)",
			  nla_len(attr), MAX_UFID_LENGTH);
		return 0;
	}

	return len;
}

/* Initializes 'flow->ufid', returning true if 'attr' contains a valid UFID,
 * or false otherwise.
 */
bool ovs_nla_get_ufid(struct sw_flow_id *sfid, const struct nlattr *attr,
		      bool log)
{
	sfid->ufid_len = get_ufid_len(attr, log);
	if (sfid->ufid_len)
		memcpy(sfid->ufid, nla_data(attr), sfid->ufid_len);

	return sfid->ufid_len;
}

int ovs_nla_get_identifier(struct sw_flow_id *sfid, const struct nlattr *ufid,
			   const struct sw_flow_key *key, bool log)
{
	struct sw_flow_key *new_key;

	if (ovs_nla_get_ufid(sfid, ufid, log))
		return 0;

	/* If UFID was not provided, use unmasked key. */
	new_key = kmalloc(sizeof(*new_key), GFP_KERNEL);
	if (!new_key)
		return -ENOMEM;
	memcpy(new_key, key, sizeof(*key));
	sfid->unmasked_key = new_key;

	return 0;
}

u32 ovs_nla_get_ufid_flags(const struct nlattr *attr)
{
	return attr ? nla_get_u32(attr) : 0;
}

/**
 * ovs_nla_get_flow_metadata - parses Netlink attributes into a flow key.
 * @key: Receives extracted in_port, priority, tun_key and skb_mark.
 * @attr: Netlink attribute holding nested %OVS_KEY_ATTR_* Netlink attribute
 * sequence.
 * @log: Boolean to allow kernel error logging.  Normally true, but when
 * probing for feature compatibility this should be passed in as false to
 * suppress unnecessary error logging.
 *
 * This parses a series of Netlink attributes that form a flow key, which must
 * take the same form accepted by flow_from_nlattrs(), but only enough of it to
 * get the metadata, that is, the parts of the flow key that cannot be
 * extracted from the packet itself.
 */

int ovs_nla_get_flow_metadata(struct net *net, const struct nlattr *attr,
			      struct sw_flow_key *key,
			      bool log)
{
	const struct nlattr *a[OVS_KEY_ATTR_MAX + 1];
	struct sw_flow_match match;
	u64 attrs = 0;
	int err;

	err = parse_flow_nlattrs(attr, a, &attrs, log);
	if (err)
		return -EINVAL;

	memset(&match, 0, sizeof(match));
	match.key = key;

	memset(&key->ct, 0, sizeof(key->ct));
	key->phy.in_port = DP_MAX_PORTS;

	return metadata_from_nlattrs(net, &match, &attrs, a, false, log);
}

static int __ovs_nla_put_key(const struct sw_flow_key *swkey,
			     const struct sw_flow_key *output, bool is_mask,
			     struct sk_buff *skb)
{
	struct ovs_key_ethernet *eth_key;
	struct nlattr *nla, *encap;

	if (nla_put_u32(skb, OVS_KEY_ATTR_RECIRC_ID, output->recirc_id))
		goto nla_put_failure;

	if (nla_put_u32(skb, OVS_KEY_ATTR_DP_HASH, output->ovs_flow_hash))
		goto nla_put_failure;

	if (nla_put_u32(skb, OVS_KEY_ATTR_PRIORITY, output->phy.priority))
		goto nla_put_failure;

	if ((swkey->tun_proto || is_mask)) {
		const void *opts = NULL;

		if (output->tun_key.tun_flags & TUNNEL_OPTIONS_PRESENT)
			opts = TUN_METADATA_OPTS(output, swkey->tun_opts_len);

		if (ip_tun_to_nlattr(skb, &output->tun_key, opts,
				     swkey->tun_opts_len, swkey->tun_proto))
			goto nla_put_failure;
	}

	if (swkey->phy.in_port == DP_MAX_PORTS) {
		if (is_mask && (output->phy.in_port == 0xffff))
			if (nla_put_u32(skb, OVS_KEY_ATTR_IN_PORT, 0xffffffff))
				goto nla_put_failure;
	} else {
		u16 upper_u16;
		upper_u16 = !is_mask ? 0 : 0xffff;

		if (nla_put_u32(skb, OVS_KEY_ATTR_IN_PORT,
				(upper_u16 << 16) | output->phy.in_port))
			goto nla_put_failure;
	}

	if (nla_put_u32(skb, OVS_KEY_ATTR_SKB_MARK, output->phy.skb_mark))
		goto nla_put_failure;

	if (ovs_ct_put_key(output, skb))
		goto nla_put_failure;

	nla = nla_reserve(skb, OVS_KEY_ATTR_ETHERNET, sizeof(*eth_key));
	if (!nla)
		goto nla_put_failure;

	eth_key = nla_data(nla);
	ether_addr_copy(eth_key->eth_src, output->eth.src);
	ether_addr_copy(eth_key->eth_dst, output->eth.dst);

	if (swkey->eth.tci || swkey->eth.type == htons(ETH_P_8021Q)) {
		__be16 eth_type;
		eth_type = !is_mask ? htons(ETH_P_8021Q) : htons(0xffff);
		if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE, eth_type) ||
		    nla_put_be16(skb, OVS_KEY_ATTR_VLAN, output->eth.tci))
			goto nla_put_failure;
		encap = nla_nest_start(skb, OVS_KEY_ATTR_ENCAP);
		if (!swkey->eth.tci)
			goto unencap;
	} else
		encap = NULL;

	if (swkey->eth.type == htons(ETH_P_802_2)) {
		/*
		 * Ethertype 802.2 is represented in the netlink with omitted
		 * OVS_KEY_ATTR_ETHERTYPE in the flow key attribute, and
		 * 0xffff in the mask attribute.  Ethertype can also
		 * be wildcarded.
		 */
		if (is_mask && output->eth.type)
			if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE,
						output->eth.type))
				goto nla_put_failure;
		goto unencap;
	}

	if (nla_put_be16(skb, OVS_KEY_ATTR_ETHERTYPE, output->eth.type))
		goto nla_put_failure;

	if (swkey->eth.type == htons(ETH_P_IP)) {
		struct ovs_key_ipv4 *ipv4_key;

		nla = nla_reserve(skb, OVS_KEY_ATTR_IPV4, sizeof(*ipv4_key));
		if (!nla)
			goto nla_put_failure;
		ipv4_key = nla_data(nla);
		ipv4_key->ipv4_src = output->ipv4.addr.src;
		ipv4_key->ipv4_dst = output->ipv4.addr.dst;
		ipv4_key->ipv4_proto = output->ip.proto;
		ipv4_key->ipv4_tos = output->ip.tos;
		ipv4_key->ipv4_ttl = output->ip.ttl;
		ipv4_key->ipv4_frag = output->ip.frag;
	} else if (swkey->eth.type == htons(ETH_P_IPV6)) {
		struct ovs_key_ipv6 *ipv6_key;

		nla = nla_reserve(skb, OVS_KEY_ATTR_IPV6, sizeof(*ipv6_key));
		if (!nla)
			goto nla_put_failure;
		ipv6_key = nla_data(nla);
		memcpy(ipv6_key->ipv6_src, &output->ipv6.addr.src,
				sizeof(ipv6_key->ipv6_src));
		memcpy(ipv6_key->ipv6_dst, &output->ipv6.addr.dst,
				sizeof(ipv6_key->ipv6_dst));
		ipv6_key->ipv6_label = output->ipv6.label;
		ipv6_key->ipv6_proto = output->ip.proto;
		ipv6_key->ipv6_tclass = output->ip.tos;
		ipv6_key->ipv6_hlimit = output->ip.ttl;
		ipv6_key->ipv6_frag = output->ip.frag;
	} else if (swkey->eth.type == htons(ETH_P_ARP) ||
		   swkey->eth.type == htons(ETH_P_RARP)) {
		struct ovs_key_arp *arp_key;

		nla = nla_reserve(skb, OVS_KEY_ATTR_ARP, sizeof(*arp_key));
		if (!nla)
			goto nla_put_failure;
		arp_key = nla_data(nla);
		memset(arp_key, 0, sizeof(struct ovs_key_arp));
		arp_key->arp_sip = output->ipv4.addr.src;
		arp_key->arp_tip = output->ipv4.addr.dst;
		arp_key->arp_op = htons(output->ip.proto);
		ether_addr_copy(arp_key->arp_sha, output->ipv4.arp.sha);
		ether_addr_copy(arp_key->arp_tha, output->ipv4.arp.tha);
	} else if (eth_p_mpls(swkey->eth.type)) {
		struct ovs_key_mpls *mpls_key;

		nla = nla_reserve(skb, OVS_KEY_ATTR_MPLS, sizeof(*mpls_key));
		if (!nla)
			goto nla_put_failure;
		mpls_key = nla_data(nla);
		mpls_key->mpls_lse = output->mpls.top_lse;
	}

	if ((swkey->eth.type == htons(ETH_P_IP) ||
	     swkey->eth.type == htons(ETH_P_IPV6)) &&
	     swkey->ip.frag != OVS_FRAG_TYPE_LATER) {

		if (swkey->ip.proto == IPPROTO_TCP) {
			struct ovs_key_tcp *tcp_key;

			nla = nla_reserve(skb, OVS_KEY_ATTR_TCP, sizeof(*tcp_key));
			if (!nla)
				goto nla_put_failure;
			tcp_key = nla_data(nla);
			tcp_key->tcp_src = output->tp.src;
			tcp_key->tcp_dst = output->tp.dst;
			if (nla_put_be16(skb, OVS_KEY_ATTR_TCP_FLAGS,
					 output->tp.flags))
				goto nla_put_failure;
		} else if (swkey->ip.proto == IPPROTO_UDP) {
			struct ovs_key_udp *udp_key;

			nla = nla_reserve(skb, OVS_KEY_ATTR_UDP, sizeof(*udp_key));
			if (!nla)
				goto nla_put_failure;
			udp_key = nla_data(nla);
			udp_key->udp_src = output->tp.src;
			udp_key->udp_dst = output->tp.dst;
		} else if (swkey->ip.proto == IPPROTO_SCTP) {
			struct ovs_key_sctp *sctp_key;

			nla = nla_reserve(skb, OVS_KEY_ATTR_SCTP, sizeof(*sctp_key));
			if (!nla)
				goto nla_put_failure;
			sctp_key = nla_data(nla);
			sctp_key->sctp_src = output->tp.src;
			sctp_key->sctp_dst = output->tp.dst;
		} else if (swkey->eth.type == htons(ETH_P_IP) &&
			   swkey->ip.proto == IPPROTO_ICMP) {
			struct ovs_key_icmp *icmp_key;

			nla = nla_reserve(skb, OVS_KEY_ATTR_ICMP, sizeof(*icmp_key));
			if (!nla)
				goto nla_put_failure;
			icmp_key = nla_data(nla);
			icmp_key->icmp_type = ntohs(output->tp.src);
			icmp_key->icmp_code = ntohs(output->tp.dst);
		} else if (swkey->eth.type == htons(ETH_P_IPV6) &&
			   swkey->ip.proto == IPPROTO_ICMPV6) {
			struct ovs_key_icmpv6 *icmpv6_key;

			nla = nla_reserve(skb, OVS_KEY_ATTR_ICMPV6,
						sizeof(*icmpv6_key));
			if (!nla)
				goto nla_put_failure;
			icmpv6_key = nla_data(nla);
			icmpv6_key->icmpv6_type = ntohs(output->tp.src);
			icmpv6_key->icmpv6_code = ntohs(output->tp.dst);

			if (icmpv6_key->icmpv6_type == NDISC_NEIGHBOUR_SOLICITATION ||
			    icmpv6_key->icmpv6_type == NDISC_NEIGHBOUR_ADVERTISEMENT) {
				struct ovs_key_nd *nd_key;

				nla = nla_reserve(skb, OVS_KEY_ATTR_ND, sizeof(*nd_key));
				if (!nla)
					goto nla_put_failure;
				nd_key = nla_data(nla);
				memcpy(nd_key->nd_target, &output->ipv6.nd.target,
							sizeof(nd_key->nd_target));
				ether_addr_copy(nd_key->nd_sll, output->ipv6.nd.sll);
				ether_addr_copy(nd_key->nd_tll, output->ipv6.nd.tll);
			}
		}
	}

unencap:
	if (encap)
		nla_nest_end(skb, encap);

	return 0;

nla_put_failure:
	return -EMSGSIZE;
}

int ovs_nla_put_key(const struct sw_flow_key *swkey,
		    const struct sw_flow_key *output, int attr, bool is_mask,
		    struct sk_buff *skb)
{
	int err;
	struct nlattr *nla;

	nla = nla_nest_start(skb, attr);
	if (!nla)
		return -EMSGSIZE;
	err = __ovs_nla_put_key(swkey, output, is_mask, skb);
	if (err)
		return err;
	nla_nest_end(skb, nla);

	return 0;
}

/* Called with ovs_mutex or RCU read lock. */
int ovs_nla_put_identifier(const struct sw_flow *flow, struct sk_buff *skb)
{
	if (ovs_identifier_is_ufid(&flow->id))
		return nla_put(skb, OVS_FLOW_ATTR_UFID, flow->id.ufid_len,
			       flow->id.ufid);

	return ovs_nla_put_key(flow->id.unmasked_key, flow->id.unmasked_key,
			       OVS_FLOW_ATTR_KEY, false, skb);
}

/* Called with ovs_mutex or RCU read lock. */
int ovs_nla_put_masked_key(const struct sw_flow *flow, struct sk_buff *skb)
{
	return ovs_nla_put_key(&flow->key, &flow->key,
				OVS_FLOW_ATTR_KEY, false, skb);
}

/* Called with ovs_mutex or RCU read lock. */
int ovs_nla_put_mask(const struct sw_flow *flow, struct sk_buff *skb)
{
	return ovs_nla_put_key(&flow->key, &flow->mask->key,
				OVS_FLOW_ATTR_MASK, true, skb);
}

#define MAX_ACTIONS_BUFSIZE	(32 * 1024)

static struct sw_flow_actions *nla_alloc_flow_actions(int size, bool log)
{
	struct sw_flow_actions *sfa;

	if (size > MAX_ACTIONS_BUFSIZE) {
		OVS_NLERR(log, "Flow action size %u bytes exceeds max", size);
		return ERR_PTR(-EINVAL);
	}

	sfa = kmalloc(sizeof(*sfa) + size, GFP_KERNEL);
	if (!sfa)
		return ERR_PTR(-ENOMEM);

	sfa->actions_len = 0;
	return sfa;
}

static void ovs_nla_free_set_action(const struct nlattr *a)
{
	const struct nlattr *ovs_key = nla_data(a);
	struct ovs_tunnel_info *ovs_tun;

	switch (nla_type(ovs_key)) {
	case OVS_KEY_ATTR_TUNNEL_INFO:
		ovs_tun = nla_data(ovs_key);
		dst_release((struct dst_entry *)ovs_tun->tun_dst);
		break;
	}
}

void ovs_nla_free_flow_actions(struct sw_flow_actions *sf_acts)
{
	const struct nlattr *a;
	int rem;

	if (!sf_acts)
		return;

	nla_for_each_attr(a, sf_acts->actions, sf_acts->actions_len, rem) {
		switch (nla_type(a)) {
		case OVS_ACTION_ATTR_SET:
			ovs_nla_free_set_action(a);
			break;
		case OVS_ACTION_ATTR_CT:
			ovs_ct_free_action(a);
			break;
		}
	}

	kfree(sf_acts);
}

static void __ovs_nla_free_flow_actions(struct rcu_head *head)
{
	ovs_nla_free_flow_actions(container_of(head, struct sw_flow_actions, rcu));
}

/* Schedules 'sf_acts' to be freed after the next RCU grace period.
 * The caller must hold rcu_read_lock for this to be sensible. */
void ovs_nla_free_flow_actions_rcu(struct sw_flow_actions *sf_acts)
{
	call_rcu(&sf_acts->rcu, __ovs_nla_free_flow_actions);
}

static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa,
				       int attr_len, bool log)
{

	struct sw_flow_actions *acts;
	int new_acts_size;
	int req_size = NLA_ALIGN(attr_len);
	int next_offset = offsetof(struct sw_flow_actions, actions) +
					(*sfa)->actions_len;

	if (req_size <= (ksize(*sfa) - next_offset))
		goto out;

	new_acts_size = ksize(*sfa) * 2;

	if (new_acts_size > MAX_ACTIONS_BUFSIZE) {
		if ((MAX_ACTIONS_BUFSIZE - next_offset) < req_size)
			return ERR_PTR(-EMSGSIZE);
		new_acts_size = MAX_ACTIONS_BUFSIZE;
	}

	acts = nla_alloc_flow_actions(new_acts_size, log);
	if (IS_ERR(acts))
		return (void *)acts;

	memcpy(acts->actions, (*sfa)->actions, (*sfa)->actions_len);
	acts->actions_len = (*sfa)->actions_len;
	acts->orig_len = (*sfa)->orig_len;
	kfree(*sfa);
	*sfa = acts;

out:
	(*sfa)->actions_len += req_size;
	return  (struct nlattr *) ((unsigned char *)(*sfa) + next_offset);
}

static struct nlattr *__add_action(struct sw_flow_actions **sfa,
				   int attrtype, void *data, int len, bool log)
{
	struct nlattr *a;

	a = reserve_sfa_size(sfa, nla_attr_size(len), log);
	if (IS_ERR(a))
		return a;

	a->nla_type = attrtype;
	a->nla_len = nla_attr_size(len);

	if (data)
		memcpy(nla_data(a), data, len);
	memset((unsigned char *) a + a->nla_len, 0, nla_padlen(len));

	return a;
}

int ovs_nla_add_action(struct sw_flow_actions **sfa, int attrtype, void *data,
		       int len, bool log)
{
	struct nlattr *a;

	a = __add_action(sfa, attrtype, data, len, log);

	return PTR_ERR_OR_ZERO(a);
}

static inline int add_nested_action_start(struct sw_flow_actions **sfa,
					  int attrtype, bool log)
{
	int used = (*sfa)->actions_len;
	int err;

	err = ovs_nla_add_action(sfa, attrtype, NULL, 0, log);
	if (err)
		return err;

	return used;
}

static inline void add_nested_action_end(struct sw_flow_actions *sfa,
					 int st_offset)
{
	struct nlattr *a = (struct nlattr *) ((unsigned char *)sfa->actions +
							       st_offset);

	a->nla_len = sfa->actions_len - st_offset;
}

static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
				  const struct sw_flow_key *key,
				  int depth, struct sw_flow_actions **sfa,
				  __be16 eth_type, __be16 vlan_tci, bool log);

static int validate_and_copy_sample(struct net *net, const struct nlattr *attr,
				    const struct sw_flow_key *key, int depth,
				    struct sw_flow_actions **sfa,
				    __be16 eth_type, __be16 vlan_tci, bool log)
{
	const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1];
	const struct nlattr *probability, *actions;
	const struct nlattr *a;
	int rem, start, err, st_acts;

	memset(attrs, 0, sizeof(attrs));
	nla_for_each_nested(a, attr, rem) {
		int type = nla_type(a);
		if (!type || type > OVS_SAMPLE_ATTR_MAX || attrs[type])
			return -EINVAL;
		attrs[type] = a;
	}
	if (rem)
		return -EINVAL;

	probability = attrs[OVS_SAMPLE_ATTR_PROBABILITY];
	if (!probability || nla_len(probability) != sizeof(u32))
		return -EINVAL;

	actions = attrs[OVS_SAMPLE_ATTR_ACTIONS];
	if (!actions || (nla_len(actions) && nla_len(actions) < NLA_HDRLEN))
		return -EINVAL;

	/* validation done, copy sample action. */
	start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SAMPLE, log);
	if (start < 0)
		return start;
	err = ovs_nla_add_action(sfa, OVS_SAMPLE_ATTR_PROBABILITY,
				 nla_data(probability), sizeof(u32), log);
	if (err)
		return err;
	st_acts = add_nested_action_start(sfa, OVS_SAMPLE_ATTR_ACTIONS, log);
	if (st_acts < 0)
		return st_acts;

	err = __ovs_nla_copy_actions(net, actions, key, depth + 1, sfa,
				     eth_type, vlan_tci, log);
	if (err)
		return err;

	add_nested_action_end(*sfa, st_acts);
	add_nested_action_end(*sfa, start);

	return 0;
}

void ovs_match_init(struct sw_flow_match *match,
		    struct sw_flow_key *key,
		    struct sw_flow_mask *mask)
{
	memset(match, 0, sizeof(*match));
	match->key = key;
	match->mask = mask;

	memset(key, 0, sizeof(*key));

	if (mask) {
		memset(&mask->key, 0, sizeof(mask->key));
		mask->range.start = mask->range.end = 0;
	}
}

static int validate_geneve_opts(struct sw_flow_key *key)
{
	struct geneve_opt *option;
	int opts_len = key->tun_opts_len;
	bool crit_opt = false;

	option = (struct geneve_opt *)TUN_METADATA_OPTS(key, key->tun_opts_len);
	while (opts_len > 0) {
		int len;

		if (opts_len < sizeof(*option))
			return -EINVAL;

		len = sizeof(*option) + option->length * 4;
		if (len > opts_len)
			return -EINVAL;

		crit_opt |= !!(option->type & GENEVE_CRIT_OPT_TYPE);

		option = (struct geneve_opt *)((u8 *)option + len);
		opts_len -= len;
	};

	key->tun_key.tun_flags |= crit_opt ? TUNNEL_CRIT_OPT : 0;

	return 0;
}

static int validate_and_copy_set_tun(const struct nlattr *attr,
				     struct sw_flow_actions **sfa, bool log)
{
	struct sw_flow_match match;
	struct sw_flow_key key;
	struct metadata_dst *tun_dst;
	struct ip_tunnel_info *tun_info;
	struct ovs_tunnel_info *ovs_tun;
	struct nlattr *a;
	int err = 0, start, opts_type;

	ovs_match_init(&match, &key, NULL);
	opts_type = ip_tun_from_nlattr(nla_data(attr), &match, false, log);
	if (opts_type < 0)
		return opts_type;

	if (key.tun_opts_len) {
		switch (opts_type) {
		case OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS:
			err = validate_geneve_opts(&key);
			if (err < 0)
				return err;
			break;
		case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS:
			break;
		}
	};

	start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SET, log);
	if (start < 0)
		return start;

	tun_dst = metadata_dst_alloc(key.tun_opts_len, GFP_KERNEL);
	if (!tun_dst)
		return -ENOMEM;

	a = __add_action(sfa, OVS_KEY_ATTR_TUNNEL_INFO, NULL,
			 sizeof(*ovs_tun), log);
	if (IS_ERR(a)) {
		dst_release((struct dst_entry *)tun_dst);
		return PTR_ERR(a);
	}

	ovs_tun = nla_data(a);
	ovs_tun->tun_dst = tun_dst;

	tun_info = &tun_dst->u.tun_info;
	tun_info->mode = IP_TUNNEL_INFO_TX;
	if (key.tun_proto == AF_INET6)
		tun_info->mode |= IP_TUNNEL_INFO_IPV6;
	tun_info->key = key.tun_key;

	/* We need to store the options in the action itself since
	 * everything else will go away after flow setup. We can append
	 * it to tun_info and then point there.
	 */
	ip_tunnel_info_opts_set(tun_info,
				TUN_METADATA_OPTS(&key, key.tun_opts_len),
				key.tun_opts_len);
	add_nested_action_end(*sfa, start);

	return err;
}

/* Return false if there are any non-masked bits set.
 * Mask follows data immediately, before any netlink padding.
 */
static bool validate_masked(u8 *data, int len)
{
	u8 *mask = data + len;

	while (len--)
		if (*data++ & ~*mask++)
			return false;

	return true;
}

static int validate_set(const struct nlattr *a,
			const struct sw_flow_key *flow_key,
			struct sw_flow_actions **sfa,
			bool *skip_copy, __be16 eth_type, bool masked, bool log)
{
	const struct nlattr *ovs_key = nla_data(a);
	int key_type = nla_type(ovs_key);
	size_t key_len;

	/* There can be only one key in a action */
	if (nla_total_size(nla_len(ovs_key)) != nla_len(a))
		return -EINVAL;

	key_len = nla_len(ovs_key);
	if (masked)
		key_len /= 2;

	if (key_type > OVS_KEY_ATTR_MAX ||
	    !check_attr_len(key_len, ovs_key_lens[key_type].len))
		return -EINVAL;

	if (masked && !validate_masked(nla_data(ovs_key), key_len))
		return -EINVAL;

	switch (key_type) {
	const struct ovs_key_ipv4 *ipv4_key;
	const struct ovs_key_ipv6 *ipv6_key;
	int err;

	case OVS_KEY_ATTR_PRIORITY:
	case OVS_KEY_ATTR_SKB_MARK:
	case OVS_KEY_ATTR_CT_MARK:
	case OVS_KEY_ATTR_CT_LABELS:
	case OVS_KEY_ATTR_ETHERNET:
		break;

	case OVS_KEY_ATTR_TUNNEL:
		if (eth_p_mpls(eth_type))
			return -EINVAL;

		if (masked)
			return -EINVAL; /* Masked tunnel set not supported. */

		*skip_copy = true;
		err = validate_and_copy_set_tun(a, sfa, log);
		if (err)
			return err;
		break;

	case OVS_KEY_ATTR_IPV4:
		if (eth_type != htons(ETH_P_IP))
			return -EINVAL;

		ipv4_key = nla_data(ovs_key);

		if (masked) {
			const struct ovs_key_ipv4 *mask = ipv4_key + 1;

			/* Non-writeable fields. */
			if (mask->ipv4_proto || mask->ipv4_frag)
				return -EINVAL;
		} else {
			if (ipv4_key->ipv4_proto != flow_key->ip.proto)
				return -EINVAL;

			if (ipv4_key->ipv4_frag != flow_key->ip.frag)
				return -EINVAL;
		}
		break;

	case OVS_KEY_ATTR_IPV6:
		if (eth_type != htons(ETH_P_IPV6))
			return -EINVAL;

		ipv6_key = nla_data(ovs_key);

		if (masked) {
			const struct ovs_key_ipv6 *mask = ipv6_key + 1;

			/* Non-writeable fields. */
			if (mask->ipv6_proto || mask->ipv6_frag)
				return -EINVAL;

			/* Invalid bits in the flow label mask? */
			if (ntohl(mask->ipv6_label) & 0xFFF00000)
				return -EINVAL;
		} else {
			if (ipv6_key->ipv6_proto != flow_key->ip.proto)
				return -EINVAL;

			if (ipv6_key->ipv6_frag != flow_key->ip.frag)
				return -EINVAL;
		}
		if (ntohl(ipv6_key->ipv6_label) & 0xFFF00000)
			return -EINVAL;

		break;

	case OVS_KEY_ATTR_TCP:
		if ((eth_type != htons(ETH_P_IP) &&
		     eth_type != htons(ETH_P_IPV6)) ||
		    flow_key->ip.proto != IPPROTO_TCP)
			return -EINVAL;

		break;

	case OVS_KEY_ATTR_UDP:
		if ((eth_type != htons(ETH_P_IP) &&
		     eth_type != htons(ETH_P_IPV6)) ||
		    flow_key->ip.proto != IPPROTO_UDP)
			return -EINVAL;

		break;

	case OVS_KEY_ATTR_MPLS:
		if (!eth_p_mpls(eth_type))
			return -EINVAL;
		break;

	case OVS_KEY_ATTR_SCTP:
		if ((eth_type != htons(ETH_P_IP) &&
		     eth_type != htons(ETH_P_IPV6)) ||
		    flow_key->ip.proto != IPPROTO_SCTP)
			return -EINVAL;

		break;

	default:
		return -EINVAL;
	}

	/* Convert non-masked non-tunnel set actions to masked set actions. */
	if (!masked && key_type != OVS_KEY_ATTR_TUNNEL) {
		int start, len = key_len * 2;
		struct nlattr *at;

		*skip_copy = true;

		start = add_nested_action_start(sfa,
						OVS_ACTION_ATTR_SET_TO_MASKED,
						log);
		if (start < 0)
			return start;

		at = __add_action(sfa, key_type, NULL, len, log);
		if (IS_ERR(at))
			return PTR_ERR(at);

		memcpy(nla_data(at), nla_data(ovs_key), key_len); /* Key. */
		memset(nla_data(at) + key_len, 0xff, key_len);    /* Mask. */
		/* Clear non-writeable bits from otherwise writeable fields. */
		if (key_type == OVS_KEY_ATTR_IPV6) {
			struct ovs_key_ipv6 *mask = nla_data(at) + key_len;

			mask->ipv6_label &= htonl(0x000FFFFF);
		}
		add_nested_action_end(*sfa, start);
	}

	return 0;
}

static int validate_userspace(const struct nlattr *attr)
{
	static const struct nla_policy userspace_policy[OVS_USERSPACE_ATTR_MAX + 1] = {
		[OVS_USERSPACE_ATTR_PID] = {.type = NLA_U32 },
		[OVS_USERSPACE_ATTR_USERDATA] = {.type = NLA_UNSPEC },
		[OVS_USERSPACE_ATTR_EGRESS_TUN_PORT] = {.type = NLA_U32 },
	};
	struct nlattr *a[OVS_USERSPACE_ATTR_MAX + 1];
	int error;

	error = nla_parse_nested(a, OVS_USERSPACE_ATTR_MAX,
				 attr, userspace_policy);
	if (error)
		return error;

	if (!a[OVS_USERSPACE_ATTR_PID] ||
	    !nla_get_u32(a[OVS_USERSPACE_ATTR_PID]))
		return -EINVAL;

	return 0;
}

static int copy_action(const struct nlattr *from,
		       struct sw_flow_actions **sfa, bool log)
{
	int totlen = NLA_ALIGN(from->nla_len);
	struct nlattr *to;

	to = reserve_sfa_size(sfa, from->nla_len, log);
	if (IS_ERR(to))
		return PTR_ERR(to);

	memcpy(to, from, totlen);
	return 0;
}

static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
				  const struct sw_flow_key *key,
				  int depth, struct sw_flow_actions **sfa,
				  __be16 eth_type, __be16 vlan_tci, bool log)
{
	const struct nlattr *a;
	int rem, err;

	if (depth >= SAMPLE_ACTION_DEPTH)
		return -EOVERFLOW;

	nla_for_each_nested(a, attr, rem) {
		/* Expected argument lengths, (u32)-1 for variable length. */
		static const u32 action_lens[OVS_ACTION_ATTR_MAX + 1] = {
			[OVS_ACTION_ATTR_OUTPUT] = sizeof(u32),
			[OVS_ACTION_ATTR_RECIRC] = sizeof(u32),
			[OVS_ACTION_ATTR_USERSPACE] = (u32)-1,
			[OVS_ACTION_ATTR_PUSH_MPLS] = sizeof(struct ovs_action_push_mpls),
			[OVS_ACTION_ATTR_POP_MPLS] = sizeof(__be16),
			[OVS_ACTION_ATTR_PUSH_VLAN] = sizeof(struct ovs_action_push_vlan),
			[OVS_ACTION_ATTR_POP_VLAN] = 0,
			[OVS_ACTION_ATTR_SET] = (u32)-1,
			[OVS_ACTION_ATTR_SET_MASKED] = (u32)-1,
			[OVS_ACTION_ATTR_SAMPLE] = (u32)-1,
			[OVS_ACTION_ATTR_HASH] = sizeof(struct ovs_action_hash),
			[OVS_ACTION_ATTR_CT] = (u32)-1,
		};
		const struct ovs_action_push_vlan *vlan;
		int type = nla_type(a);
		bool skip_copy;

		if (type > OVS_ACTION_ATTR_MAX ||
		    (action_lens[type] != nla_len(a) &&
		     action_lens[type] != (u32)-1))
			return -EINVAL;

		skip_copy = false;
		switch (type) {
		case OVS_ACTION_ATTR_UNSPEC:
			return -EINVAL;

		case OVS_ACTION_ATTR_USERSPACE:
			err = validate_userspace(a);
			if (err)
				return err;
			break;

		case OVS_ACTION_ATTR_OUTPUT:
			if (nla_get_u32(a) >= DP_MAX_PORTS)
				return -EINVAL;
			break;

		case OVS_ACTION_ATTR_HASH: {
			const struct ovs_action_hash *act_hash = nla_data(a);

			switch (act_hash->hash_alg) {
			case OVS_HASH_ALG_L4:
				break;
			default:
				return  -EINVAL;
			}

			break;
		}

		case OVS_ACTION_ATTR_POP_VLAN:
			vlan_tci = htons(0);
			break;

		case OVS_ACTION_ATTR_PUSH_VLAN:
			vlan = nla_data(a);
			if (vlan->vlan_tpid != htons(ETH_P_8021Q))
				return -EINVAL;
			if (!(vlan->vlan_tci & htons(VLAN_TAG_PRESENT)))
				return -EINVAL;
			vlan_tci = vlan->vlan_tci;
			break;

		case OVS_ACTION_ATTR_RECIRC:
			break;

		case OVS_ACTION_ATTR_PUSH_MPLS: {
			const struct ovs_action_push_mpls *mpls = nla_data(a);

			if (!eth_p_mpls(mpls->mpls_ethertype))
				return -EINVAL;
			/* Prohibit push MPLS other than to a white list
			 * for packets that have a known tag order.
			 */
			if (vlan_tci & htons(VLAN_TAG_PRESENT) ||
			    (eth_type != htons(ETH_P_IP) &&
			     eth_type != htons(ETH_P_IPV6) &&
			     eth_type != htons(ETH_P_ARP) &&
			     eth_type != htons(ETH_P_RARP) &&
			     !eth_p_mpls(eth_type)))
				return -EINVAL;
			eth_type = mpls->mpls_ethertype;
			break;
		}

		case OVS_ACTION_ATTR_POP_MPLS:
			if (vlan_tci & htons(VLAN_TAG_PRESENT) ||
			    !eth_p_mpls(eth_type))
				return -EINVAL;

			/* Disallow subsequent L2.5+ set and mpls_pop actions
			 * as there is no check here to ensure that the new
			 * eth_type is valid and thus set actions could
			 * write off the end of the packet or otherwise
			 * corrupt it.
			 *
			 * Support for these actions is planned using packet
			 * recirculation.
			 */
			eth_type = htons(0);
			break;

		case OVS_ACTION_ATTR_SET:
			err = validate_set(a, key, sfa,
					   &skip_copy, eth_type, false, log);
			if (err)
				return err;
			break;

		case OVS_ACTION_ATTR_SET_MASKED:
			err = validate_set(a, key, sfa,
					   &skip_copy, eth_type, true, log);
			if (err)
				return err;
			break;

		case OVS_ACTION_ATTR_SAMPLE:
			err = validate_and_copy_sample(net, a, key, depth, sfa,
						       eth_type, vlan_tci, log);
			if (err)
				return err;
			skip_copy = true;
			break;

		case OVS_ACTION_ATTR_CT:
			err = ovs_ct_copy_action(net, a, key, sfa, log);
			if (err)
				return err;
			skip_copy = true;
			break;

		default:
			OVS_NLERR(log, "Unknown Action type %d", type);
			return -EINVAL;
		}
		if (!skip_copy) {
			err = copy_action(a, sfa, log);
			if (err)
				return err;
		}
	}

	if (rem > 0)
		return -EINVAL;

	return 0;
}

/* 'key' must be the masked key. */
int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
			 const struct sw_flow_key *key,
			 struct sw_flow_actions **sfa, bool log)
{
	int err;

	*sfa = nla_alloc_flow_actions(nla_len(attr), log);
	if (IS_ERR(*sfa))
		return PTR_ERR(*sfa);

	(*sfa)->orig_len = nla_len(attr);
	err = __ovs_nla_copy_actions(net, attr, key, 0, sfa, key->eth.type,
				     key->eth.tci, log);
	if (err)
		ovs_nla_free_flow_actions(*sfa);

	return err;
}

static int sample_action_to_attr(const struct nlattr *attr, struct sk_buff *skb)
{
	const struct nlattr *a;
	struct nlattr *start;
	int err = 0, rem;

	start = nla_nest_start(skb, OVS_ACTION_ATTR_SAMPLE);
	if (!start)
		return -EMSGSIZE;

	nla_for_each_nested(a, attr, rem) {
		int type = nla_type(a);
		struct nlattr *st_sample;

		switch (type) {
		case OVS_SAMPLE_ATTR_PROBABILITY:
			if (nla_put(skb, OVS_SAMPLE_ATTR_PROBABILITY,
				    sizeof(u32), nla_data(a)))
				return -EMSGSIZE;
			break;
		case OVS_SAMPLE_ATTR_ACTIONS:
			st_sample = nla_nest_start(skb, OVS_SAMPLE_ATTR_ACTIONS);
			if (!st_sample)
				return -EMSGSIZE;
			err = ovs_nla_put_actions(nla_data(a), nla_len(a), skb);
			if (err)
				return err;
			nla_nest_end(skb, st_sample);
			break;
		}
	}

	nla_nest_end(skb, start);
	return err;
}

static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb)
{
	const struct nlattr *ovs_key = nla_data(a);
	int key_type = nla_type(ovs_key);
	struct nlattr *start;
	int err;

	switch (key_type) {
	case OVS_KEY_ATTR_TUNNEL_INFO: {
		struct ovs_tunnel_info *ovs_tun = nla_data(ovs_key);
		struct ip_tunnel_info *tun_info = &ovs_tun->tun_dst->u.tun_info;

		start = nla_nest_start(skb, OVS_ACTION_ATTR_SET);
		if (!start)
			return -EMSGSIZE;

		err = ip_tun_to_nlattr(skb, &tun_info->key,
				       tun_info->options_len ?
					     ip_tunnel_info_opts(tun_info) : NULL,
				       tun_info->options_len,
				       ip_tunnel_info_af(tun_info));
		if (err)
			return err;
		nla_nest_end(skb, start);
		break;
	}
	default:
		if (nla_put(skb, OVS_ACTION_ATTR_SET, nla_len(a), ovs_key))
			return -EMSGSIZE;
		break;
	}

	return 0;
}

static int masked_set_action_to_set_action_attr(const struct nlattr *a,
						struct sk_buff *skb)
{
	const struct nlattr *ovs_key = nla_data(a);
	struct nlattr *nla;
	size_t key_len = nla_len(ovs_key) / 2;

	/* Revert the conversion we did from a non-masked set action to
	 * masked set action.
	 */
	nla = nla_nest_start(skb, OVS_ACTION_ATTR_SET);
	if (!nla)
		return -EMSGSIZE;

	if (nla_put(skb, nla_type(ovs_key), key_len, nla_data(ovs_key)))
		return -EMSGSIZE;

	nla_nest_end(skb, nla);
	return 0;
}

int ovs_nla_put_actions(const struct nlattr *attr, int len, struct sk_buff *skb)
{
	const struct nlattr *a;
	int rem, err;

	nla_for_each_attr(a, attr, len, rem) {
		int type = nla_type(a);

		switch (type) {
		case OVS_ACTION_ATTR_SET:
			err = set_action_to_attr(a, skb);
			if (err)
				return err;
			break;

		case OVS_ACTION_ATTR_SET_TO_MASKED:
			err = masked_set_action_to_set_action_attr(a, skb);
			if (err)
				return err;
			break;

		case OVS_ACTION_ATTR_SAMPLE:
			err = sample_action_to_attr(a, skb);
			if (err)
				return err;
			break;

		case OVS_ACTION_ATTR_CT:
			err = ovs_ct_action_to_attr(nla_data(a), skb);
			if (err)
				return err;
			break;

		default:
			if (nla_put(skb, type, nla_len(a), nla_data(a)))
				return -EMSGSIZE;
			break;
		}
	}

	return 0;
}