litmus-rt.git - The LITMUS^RT kernel.

The LITMUS^RT kernel.

Bjoern Brandenburg

about summary refs log tree commit diff stats

diff options

author	Jean Delvare <khali@linux-fr.org>	2007-09-26 17:39:01 -0400
committer	Mark M. Hoffman <mhoffman@lightlink.com>	2007-10-09 22:56:31 -0400
commit	c2803b98557c10464f3a1fc65f56d0c8c01991bd (patch)
tree	90c251f232eab77c8e45bc8d843990196a226b45 /fs/ioctl.c
parent	b965d4b7f614522170af6a7e450be0333792ccd2 (diff)

hwmon: (lm87) Add individual alarm files

Add individual alarm files to the lm87 driver. The new libsensors needs this. Signed-off-by: Jean Delvare <khali@linux-fr.org> Acked-by: Hans de Goede <j.w.r.degoede@hhs.nl> Signed-off-by: Mark M. Hoffman <mhoffman@lightlink.com>

Diffstat (limited to 'fs/ioctl.c')

0 files changed, 0 insertions, 0 deletions

ar <pshelar@nicira.com> 2014-10-19 15:03:40 -0400 committer Pravin B Shelar <pshelar@nicira.com> 2014-11-06 02:52:35 -0500 openvswitch: Avoid NULL mask check while building mask' href='/cgit/cgit.cgi/litmus-rt-budgetable-locks.git/.git/commit/net/openvswitch/flow_netlink.c?h=update_litmus_2019&id=a85311bf1f9f8185682990cafdd4e0572c0ed373'>a85311bf1f9f

19
20

46
47
48

51
52
53

95
96

105
106

128
129

130
131

133
134

136
137

138
139

152
153

155
156

175
176

188
189
190

197
198

201
202

219
220

222
223

238
239

256
257

259
260

287
288
289

295
296
297

310
311

318
319
320

331
332
333

369
370
371

372
373

374
375

408
409

452
453
454

457
458

477
478

481
482

483
484

535
536
537

538
539

541
542
543

544
545

548
549
550

552
553

596
597
598

600
601
602

603
604

605
606
607

608
609

611
612

613
614
615

616
617

633
634

637
638
639

648
649

651
652
653

672
673
674

681
682
683

701
702

711
712
713

714
715

716
717

720
721
722

735
736

741
742

765
766
767

774
775

799
800

803
804

806
807

808
809

816
817

829
830
831

844
845

853
854

860
861

1044
1045
1046

1048
1049

1094
1095

1096
1097
1098

1099
1100

1106
1107
1108

1111
1112
1113

1115
1116

1118
1119

1127
1128
1129

1131
1132

1162
1163

1179
1180
1181

1182
1183
1184

1185
1186

1207
1208
1209

1228
1229

1252
1253

1254
1255

1323
1324

1325
1326
1327

1329
1330
1331

1332
1333
1334

1339
1340

1348
1349

1399
1400

1402
1403

1405
1406

1414
1415
1416

1437
1438
1439

1443
1444

1445
1446

1448
1449

1450
1451

1453
1454
1455

1456
1457
1458

1461
1462
1463

1484
1485
1486

1488
1489

1491
1492

1499
1500

1502
1503
1504

1506
1507

1510
1511

1515
1516
1517

1518
1519

1573
1574

1581
1582
1583

1589
1590

1591
1592

1593
1594
1595

1598
1599

1602
1603
1604

1606
1607
1608

1612
1613

1625
1626
1627

1628
1629

1630
1631
1632

1640
1641
1642

1645
1646

1649
1650

1651
1652

1671
1672

1673
1674
1675

1685
1686

1765
1766

1800
1801

1809
1810

1819
1820

1830
1831

1843
1844

1850
1851

1904
1905

1907
1908
1909

1949
1950
1951

1963
1964

1968
1969
1970

2008
2009
2010

2022
2023
2024

2025
2026

2027
2028
2029

2033
2034
2035

2065
2066

2071
2072

2094
2095

2113
2114

2119
2120
2121

2127
2128

2136
2137

2175
2176
2177

2186
2187

2199
2200

2202
2203
2204

2205
2206
2207

2208
2209
2210

2218
2219
2220

2227
2228

2229
2230

2259
2260

2261
2262

2263
2264
2265

2278
2279

2280
2281
2282

2292
2293

2294
2295
2296

2311
2312

2315
2316

2328
2329
2330

2332
2333

2350
2351
2352

2359
2360
2361

2362
2363

2365
2366

2367
2368
2369

2370
2371

2378
2379

2380
2381
2382

2383
2384

2432
2433

2464
2465
2466

2473
2474

2475
2476
2477

2480
2481

2483
2484

2531
2532

2533
2534

2536
2537
2538

2539
2540

2543
2544
2545

2547
2548

2549
2550
2551

2552
2553
2554

2590
2591

2598
2599

2641
2642
2643

2661
2662

2664
2665
2666

2672
2673

2674
2675

2676
2677

2688
2689
2690

2712
2713

2726
2727

2761
2762

2763
2764

2769
2770
2771

/*
 * Copyright (c) 2007-2017 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 bool actions_may_change_flow(const struct nlattr *actions)
{
	struct nlattr *nla;
	int rem;

	nla_for_each_nested(nla, actions, rem) {
		u16 action = nla_type(nla);

		switch (action) {
		case OVS_ACTION_ATTR_OUTPUT:
		case OVS_ACTION_ATTR_RECIRC:
		case OVS_ACTION_ATTR_TRUNC:
		case OVS_ACTION_ATTR_USERSPACE:
			break;

		case OVS_ACTION_ATTR_CT:
		case OVS_ACTION_ATTR_HASH:
		case OVS_ACTION_ATTR_POP_ETH:
		case OVS_ACTION_ATTR_POP_MPLS:
		case OVS_ACTION_ATTR_POP_VLAN:
		case OVS_ACTION_ATTR_PUSH_ETH:
		case OVS_ACTION_ATTR_PUSH_MPLS:
		case OVS_ACTION_ATTR_PUSH_VLAN:
		case OVS_ACTION_ATTR_SAMPLE:
		case OVS_ACTION_ATTR_SET:
		case OVS_ACTION_ATTR_SET_MASKED:
		default:
			return true;
		}
	}
	return false;
}

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 = 0;
	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_CT_ORIG_TUPLE_IPV4)
			| (1 << OVS_KEY_ATTR_IPV6)
			| (1 << OVS_KEY_ATTR_CT_ORIG_TUPLE_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;
			mask_allowed |= 1 << OVS_KEY_ATTR_CT_ORIG_TUPLE_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;
			mask_allowed |= 1 << OVS_KEY_ATTR_CT_ORIG_TUPLE_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;
					/* Original direction conntrack tuple
					 * uses the same space as the ND fields
					 * in the key, so both are not allowed
					 * at the same time.
					 */
					mask_allowed &= ~(1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6);
					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_64bit(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 != 28);

	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(40)  /* OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6 */
		+ 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) },
	[OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4] = {
		.len = sizeof(struct ovs_key_ct_tuple_ipv4) },
	[OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6] = {
		.len = sizeof(struct ovs_key_ct_tuple_ipv6) },
};

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);
}

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.src,
					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;
		case OVS_TUNNEL_KEY_ATTR_PAD:
			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,
			 OVS_TUNNEL_KEY_ATTR_PAD))
		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 (swkey_tun_opts_len) {
		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_tunnel_info(struct sk_buff *skb,
			    struct ip_tunnel_info *tun_info)
{
	return __ip_tun_to_nlattr(skb, &tun_info->key,
				  ip_tunnel_info_opts(tun_info),
				  tun_info->options_len,
				  ip_tunnel_info_af(tun_info));
}

static int encode_vlan_from_nlattrs(struct sw_flow_match *match,
				    const struct nlattr *a[],
				    bool is_mask, bool inner)
{
	__be16 tci = 0;
	__be16 tpid = 0;

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

	if (a[OVS_KEY_ATTR_ETHERTYPE])
		tpid = nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]);

	if (likely(!inner)) {
		SW_FLOW_KEY_PUT(match, eth.vlan.tpid, tpid, is_mask);
		SW_FLOW_KEY_PUT(match, eth.vlan.tci, tci, is_mask);
	} else {
		SW_FLOW_KEY_PUT(match, eth.cvlan.tpid, tpid, is_mask);
		SW_FLOW_KEY_PUT(match, eth.cvlan.tci, tci, is_mask);
	}
	return 0;
}

static int validate_vlan_from_nlattrs(const struct sw_flow_match *match,
				      u64 key_attrs, bool inner,
				      const struct nlattr **a, bool log)
{
	__be16 tci = 0;

	if (!((key_attrs & (1 << OVS_KEY_ATTR_ETHERNET)) &&
	      (key_attrs & (1 << OVS_KEY_ATTR_ETHERTYPE)) &&
	       eth_type_vlan(nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE])))) {
		/* Not a VLAN. */
		return 0;
	}

	if (!((key_attrs & (1 << OVS_KEY_ATTR_VLAN)) &&
	      (key_attrs & (1 << OVS_KEY_ATTR_ENCAP)))) {
		OVS_NLERR(log, "Invalid %s frame", (inner) ? "C-VLAN" : "VLAN");
		return -EINVAL;
	}

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

	if (!(tci & htons(VLAN_TAG_PRESENT))) {
		if (tci) {
			OVS_NLERR(log, "%s TCI does not have VLAN_TAG_PRESENT bit set.",
				  (inner) ? "C-VLAN" : "VLAN");
			return -EINVAL;
		} else if (nla_len(a[OVS_KEY_ATTR_ENCAP])) {
			/* Corner case for truncated VLAN header. */
			OVS_NLERR(log, "Truncated %s header has non-zero encap attribute.",
				  (inner) ? "C-VLAN" : "VLAN");
			return -EINVAL;
		}
	}

	return 1;
}

static int validate_vlan_mask_from_nlattrs(const struct sw_flow_match *match,
					   u64 key_attrs, bool inner,
					   const struct nlattr **a, bool log)
{
	__be16 tci = 0;
	__be16 tpid = 0;
	bool encap_valid = !!(match->key->eth.vlan.tci &
			      htons(VLAN_TAG_PRESENT));
	bool i_encap_valid = !!(match->key->eth.cvlan.tci &
				htons(VLAN_TAG_PRESENT));

	if (!(key_attrs & (1 << OVS_KEY_ATTR_ENCAP))) {
		/* Not a VLAN. */
		return 0;
	}

	if ((!inner && !encap_valid) || (inner && !i_encap_valid)) {
		OVS_NLERR(log, "Encap mask attribute is set for non-%s frame.",
			  (inner) ? "C-VLAN" : "VLAN");
		return -EINVAL;
	}

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

	if (a[OVS_KEY_ATTR_ETHERTYPE])
		tpid = nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]);

	if (tpid != htons(0xffff)) {
		OVS_NLERR(log, "Must have an exact match on %s TPID (mask=%x).",
			  (inner) ? "C-VLAN" : "VLAN", ntohs(tpid));
		return -EINVAL;
	}
	if (!(tci & htons(VLAN_TAG_PRESENT))) {
		OVS_NLERR(log, "%s TCI mask does not have exact match for VLAN_TAG_PRESENT bit.",
			  (inner) ? "C-VLAN" : "VLAN");
		return -EINVAL;
	}

	return 1;
}

static int __parse_vlan_from_nlattrs(struct sw_flow_match *match,
				     u64 *key_attrs, bool inner,
				     const struct nlattr **a, bool is_mask,
				     bool log)
{
	int err;
	const struct nlattr *encap;

	if (!is_mask)
		err = validate_vlan_from_nlattrs(match, *key_attrs, inner,
						 a, log);
	else
		err = validate_vlan_mask_from_nlattrs(match, *key_attrs, inner,
						      a, log);
	if (err <= 0)
		return err;

	err = encode_vlan_from_nlattrs(match, a, is_mask, inner);
	if (err)
		return err;

	*key_attrs &= ~(1 << OVS_KEY_ATTR_ENCAP);
	*key_attrs &= ~(1 << OVS_KEY_ATTR_VLAN);
	*key_attrs &= ~(1 << OVS_KEY_ATTR_ETHERTYPE);

	encap = a[OVS_KEY_ATTR_ENCAP];

	if (!is_mask)
		err = parse_flow_nlattrs(encap, a, key_attrs, log);
	else
		err = parse_flow_mask_nlattrs(encap, a, key_attrs, log);

	return err;
}

static int parse_vlan_from_nlattrs(struct sw_flow_match *match,
				   u64 *key_attrs, const struct nlattr **a,
				   bool is_mask, bool log)
{
	int err;
	bool encap_valid = false;

	err = __parse_vlan_from_nlattrs(match, key_attrs, false, a,
					is_mask, log);
	if (err)
		return err;

	encap_valid = !!(match->key->eth.vlan.tci & htons(VLAN_TAG_PRESENT));
	if (encap_valid) {
		err = __parse_vlan_from_nlattrs(match, key_attrs, true, a,
						is_mask, log);
		if (err)
			return err;
	}

	return 0;
}

static int parse_eth_type_from_nlattrs(struct sw_flow_match *match,
				       u64 *attrs, const struct nlattr **a,
				       bool is_mask, bool log)
{
	__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);
	return 0;
}

static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match,
				 u64 *attrs, const struct nlattr **a,
				 bool is_mask, bool log)
{
	u8 mac_proto = MAC_PROTO_ETHERNET;

	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 (ct_state & ~CT_SUPPORTED_MASK) {
			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);
	}
	if (*attrs & (1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4)) {
		const struct ovs_key_ct_tuple_ipv4 *ct;

		ct = nla_data(a[OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4]);

		SW_FLOW_KEY_PUT(match, ipv4.ct_orig.src, ct->ipv4_src, is_mask);
		SW_FLOW_KEY_PUT(match, ipv4.ct_orig.dst, ct->ipv4_dst, is_mask);
		SW_FLOW_KEY_PUT(match, ct.orig_tp.src, ct->src_port, is_mask);
		SW_FLOW_KEY_PUT(match, ct.orig_tp.dst, ct->dst_port, is_mask);
		SW_FLOW_KEY_PUT(match, ct_orig_proto, ct->ipv4_proto, is_mask);
		*attrs &= ~(1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4);
	}
	if (*attrs & (1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6)) {
		const struct ovs_key_ct_tuple_ipv6 *ct;

		ct = nla_data(a[OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6]);

		SW_FLOW_KEY_MEMCPY(match, ipv6.ct_orig.src, &ct->ipv6_src,
				   sizeof(match->key->ipv6.ct_orig.src),
				   is_mask);
		SW_FLOW_KEY_MEMCPY(match, ipv6.ct_orig.dst, &ct->ipv6_dst,
				   sizeof(match->key->ipv6.ct_orig.dst),
				   is_mask);
		SW_FLOW_KEY_PUT(match, ct.orig_tp.src, ct->src_port, is_mask);
		SW_FLOW_KEY_PUT(match, ct.orig_tp.dst, ct->dst_port, is_mask);
		SW_FLOW_KEY_PUT(match, ct_orig_proto, ct->ipv6_proto, is_mask);
		*attrs &= ~(1ULL << OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6);
	}

	/* For layer 3 packets the Ethernet type is provided
	 * and treated as metadata but no MAC addresses are provided.
	 */
	if (!(*attrs & (1ULL << OVS_KEY_ATTR_ETHERNET)) &&
	    (*attrs & (1ULL << OVS_KEY_ATTR_ETHERTYPE)))
		mac_proto = MAC_PROTO_NONE;

	/* Always exact match mac_proto */
	SW_FLOW_KEY_PUT(match, mac_proto, is_mask ? 0xff : mac_proto, is_mask);

	if (mac_proto == MAC_PROTO_NONE)
		return parse_eth_type_from_nlattrs(match, attrs, a, is_mask,
						   log);

	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)) {
			/* VLAN attribute is always parsed before getting here since it
			 * may occur multiple times.
			 */
			OVS_NLERR(log, "VLAN attribute unexpected.");
			return -EINVAL;
		}

		if (attrs & (1 << OVS_KEY_ATTR_ETHERTYPE)) {
			err = parse_eth_type_from_nlattrs(match, &attrs, a, is_mask,
							  log);
			if (err)
				return err;
		} else if (!is_mask) {
			SW_FLOW_KEY_PUT(match, eth.type, htons(ETH_P_802_2), is_mask);
		}
	} else if (!match->key->eth.type) {
		OVS_NLERR(log, "Either Ethernet header or EtherType is required.");
		return -EINVAL;
	}

	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)",
				  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));
		}

		if (nla_type(nla) == OVS_KEY_ATTR_CT_STATE)
			*(u32 *)nla_data(nla) &= CT_SUPPORTED_MASK;
	}
}

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];
	struct nlattr *newmask = NULL;
	u64 key_attrs = 0;
	u64 mask_attrs = 0;
	int err;

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

	err = parse_vlan_from_nlattrs(match, &key_attrs, a, false, log);
	if (err)
		return err;

	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.vlan.tci, htons(0xffff), true);
		SW_FLOW_KEY_PUT(match, eth.cvlan.tci, htons(0xffff), true);

		err = parse_vlan_from_nlattrs(match, &mask_attrs, a, true, log);
		if (err)
			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,


context:
space:
mode: