flow_dissector.c

#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/export.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/if_vlan.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <linux/igmp.h>
#include <linux/icmp.h>
#include <linux/sctp.h>
#include <linux/dccp.h>
#include <linux/if_tunnel.h>
#include <linux/if_pppox.h>
#include <linux/ppp_defs.h>
#include <linux/stddef.h>
#include <linux/if_ether.h>
#include <net/flow_dissector.h>
#include <scsi/fc/fc_fcoe.h>

static bool skb_flow_dissector_uses_key(struct flow_dissector *flow_dissector,
					enum flow_dissector_key_id key_id)
{
	return flow_dissector->used_keys & (1 << key_id);
}

static void skb_flow_dissector_set_key(struct flow_dissector *flow_dissector,
				       enum flow_dissector_key_id key_id)
{
	flow_dissector->used_keys |= (1 << key_id);
}

static void *skb_flow_dissector_target(struct flow_dissector *flow_dissector,
				       enum flow_dissector_key_id key_id,
				       void *target_container)
{
	return ((char *) target_container) + flow_dissector->offset[key_id];
}

void skb_flow_dissector_init(struct flow_dissector *flow_dissector,
			     const struct flow_dissector_key *key,
			     unsigned int key_count)
{
	unsigned int i;

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

	for (i = 0; i < key_count; i++, key++) {
		/* User should make sure that every key target offset is withing
		 * boundaries of unsigned short.
		 */
		BUG_ON(key->offset > USHRT_MAX);
		BUG_ON(skb_flow_dissector_uses_key(flow_dissector,
						   key->key_id));

		skb_flow_dissector_set_key(flow_dissector, key->key_id);
		flow_dissector->offset[key->key_id] = key->offset;
	}

	/* Ensure that the dissector always includes control and basic key.
	 * That way we are able to avoid handling lack of these in fast path.
	 */
	BUG_ON(!skb_flow_dissector_uses_key(flow_dissector,
					    FLOW_DISSECTOR_KEY_CONTROL));
	BUG_ON(!skb_flow_dissector_uses_key(flow_dissector,
					    FLOW_DISSECTOR_KEY_BASIC));
}
EXPORT_SYMBOL(skb_flow_dissector_init);

/**
 * __skb_flow_get_ports - extract the upper layer ports and return them
 * @skb: sk_buff to extract the ports from
 * @thoff: transport header offset
 * @ip_proto: protocol for which to get port offset
 * @data: raw buffer pointer to the packet, if NULL use skb->data
 * @hlen: packet header length, if @data is NULL use skb_headlen(skb)
 *
 * The function will try to retrieve the ports at offset thoff + poff where poff
 * is the protocol port offset returned from proto_ports_offset
 */
__be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
			    void *data, int hlen)
{
	int poff = proto_ports_offset(ip_proto);

	if (!data) {
		data = skb->data;
		hlen = skb_headlen(skb);
	}

	if (poff >= 0) {
		__be32 *ports, _ports;

		ports = __skb_header_pointer(skb, thoff + poff,
					     sizeof(_ports), data, hlen, &_ports);
		if (ports)
			return *ports;
	}

	return 0;
}
EXPORT_SYMBOL(__skb_flow_get_ports);

/**
 * __skb_flow_dissect - extract the flow_keys struct and return it
 * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified
 * @flow_dissector: list of keys to dissect
 * @target_container: target structure to put dissected values into
 * @data: raw buffer pointer to the packet, if NULL use skb->data
 * @proto: protocol for which to get the flow, if @data is NULL use skb->protocol
 * @nhoff: network header offset, if @data is NULL use skb_network_offset(skb)
 * @hlen: packet header length, if @data is NULL use skb_headlen(skb)
 *
 * The function will try to retrieve individual keys into target specified
 * by flow_dissector from either the skbuff or a raw buffer specified by the
 * rest parameters.
 *
 * Caller must take care of zeroing target container memory.
 */
bool __skb_flow_dissect(const struct sk_buff *skb,
			struct flow_dissector *flow_dissector,
			void *target_container,
			void *data, __be16 proto, int nhoff, int hlen)
{
	struct flow_dissector_key_control *key_control;
	struct flow_dissector_key_basic *key_basic;
	struct flow_dissector_key_addrs *key_addrs;
	struct flow_dissector_key_ports *key_ports;
	u8 ip_proto;

	if (!data) {
		data = skb->data;
		proto = skb->protocol;
		nhoff = skb_network_offset(skb);
		hlen = skb_headlen(skb);
	}

	/* It is ensured by skb_flow_dissector_init() that control key will
	 * be always present.
	 */
	key_control = skb_flow_dissector_target(flow_dissector,
						FLOW_DISSECTOR_KEY_CONTROL,
						target_container);

	/* It is ensured by skb_flow_dissector_init() that basic key will
	 * be always present.
	 */
	key_basic = skb_flow_dissector_target(flow_dissector,
					      FLOW_DISSECTOR_KEY_BASIC,
					      target_container);

	if (skb_flow_dissector_uses_key(flow_dissector,
					FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
		struct ethhdr *eth = eth_hdr(skb);
		struct flow_dissector_key_eth_addrs *key_eth_addrs;

		key_eth_addrs = skb_flow_dissector_target(flow_dissector,
							  FLOW_DISSECTOR_KEY_ETH_ADDRS,
							  target_container);
		memcpy(key_eth_addrs, &eth->h_dest, sizeof(*key_eth_addrs));
	}

again:
	switch (proto) {
	case htons(ETH_P_IP): {
		const struct iphdr *iph;
		struct iphdr _iph;
ip:
		iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph);
		if (!iph || iph->ihl < 5)
			return false;
		nhoff += iph->ihl * 4;

		ip_proto = iph->protocol;
		if (ip_is_fragment(iph))
			ip_proto = 0;

		if (!skb_flow_dissector_uses_key(flow_dissector,
						 FLOW_DISSECTOR_KEY_IPV4_ADDRS))
			break;
		key_addrs = skb_flow_dissector_target(flow_dissector,
						      FLOW_DISSECTOR_KEY_IPV4_ADDRS,
						      target_container);
		memcpy(key_addrs, &iph->saddr, sizeof(*key_addrs));
		break;
	}
	case htons(ETH_P_IPV6): {
		const struct ipv6hdr *iph;
		struct ipv6hdr _iph;
		__be32 flow_label;

ipv6:
		iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph);
		if (!iph)
			return false;

		ip_proto = iph->nexthdr;
		nhoff += sizeof(struct ipv6hdr);

		if (skb_flow_dissector_uses_key(flow_dissector,
						FLOW_DISSECTOR_KEY_IPV6_HASH_ADDRS)) {
			key_addrs = skb_flow_dissector_target(flow_dissector,
							      FLOW_DISSECTOR_KEY_IPV6_HASH_ADDRS,
							      target_container);

			key_addrs->src = (__force __be32)ipv6_addr_hash(&iph->saddr);
			key_addrs->dst = (__force __be32)ipv6_addr_hash(&iph->daddr);
			goto flow_label;
		}
		if (skb_flow_dissector_uses_key(flow_dissector,
						FLOW_DISSECTOR_KEY_IPV6_ADDRS)) {
			struct flow_dissector_key_ipv6_addrs *key_ipv6_addrs;

			key_ipv6_addrs = skb_flow_dissector_target(flow_dissector,
								   FLOW_DISSECTOR_KEY_IPV6_ADDRS,
								   target_container);

			memcpy(key_ipv6_addrs, &iph->saddr, sizeof(*key_ipv6_addrs));
			goto flow_label;
		}
		break;
flow_label:
		flow_label = ip6_flowlabel(iph);
		if (flow_label) {
			/* Awesome, IPv6 packet has a flow label so we can
			 * use that to represent the ports without any
			 * further dissection.
			 */

			key_basic->n_proto = proto;
			key_basic->ip_proto = ip_proto;
			key_control->thoff = (u16)nhoff;

			if (skb_flow_dissector_uses_key(flow_dissector,
							FLOW_DISSECTOR_KEY_PORTS)) {
				key_ports = skb_flow_dissector_target(flow_dissector,
								      FLOW_DISSECTOR_KEY_PORTS,
								      target_container);
				key_ports->ports = flow_label;
			}

			return true;
		}

		break;
	}
	case htons(ETH_P_8021AD):
	case htons(ETH_P_8021Q): {
		const struct vlan_hdr *vlan;
		struct vlan_hdr _vlan;

		vlan = __skb_header_pointer(skb, nhoff, sizeof(_vlan), data, hlen, &_vlan);
		if (!vlan)
			return false;

		proto = vlan->h_vlan_encapsulated_proto;
		nhoff += sizeof(*vlan);
		goto again;
	}
	case htons(ETH_P_PPP_SES): {
		struct {
			struct pppoe_hdr hdr;
			__be16 proto;
		} *hdr, _hdr;
		hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr);
		if (!hdr)
			return false;
		proto = hdr->proto;
		nhoff += PPPOE_SES_HLEN;
		switch (proto) {
		case htons(PPP_IP):
			goto ip;
		case htons(PPP_IPV6):
			goto ipv6;
		default:
			return false;
		}
	}
	case htons(ETH_P_TIPC): {
		struct {
			__be32 pre[3];
			__be32 srcnode;
		} *hdr, _hdr;
		hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr);
		if (!hdr)
			return false;
		key_basic->n_proto = proto;
		key_control->thoff = (u16)nhoff;

		if (skb_flow_dissector_uses_key(flow_dissector,
						FLOW_DISSECTOR_KEY_IPV6_HASH_ADDRS)) {
			key_addrs = skb_flow_dissector_target(flow_dissector,
							      FLOW_DISSECTOR_KEY_IPV6_HASH_ADDRS,
							      target_container);
			key_addrs->src = hdr->srcnode;
			key_addrs->dst = 0;
		}
		return true;
	}
	case htons(ETH_P_FCOE):
		key_control->thoff = (u16)(nhoff + FCOE_HEADER_LEN);
		/* fall through */
	default:
		return false;
	}

	switch (ip_proto) {
	case IPPROTO_GRE: {
		struct gre_hdr {
			__be16 flags;
			__be16 proto;
		} *hdr, _hdr;

		hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr);
		if (!hdr)
			return false;
		/*
		 * Only look inside GRE if version zero and no
		 * routing
		 */
		if (hdr->flags & (GRE_VERSION | GRE_ROUTING))
			break;

		proto = hdr->proto;
		nhoff += 4;
		if (hdr->flags & GRE_CSUM)
			nhoff += 4;
		if (hdr->flags & GRE_KEY)
			nhoff += 4;
		if (hdr->flags & GRE_SEQ)
			nhoff += 4;
		if (proto == htons(ETH_P_TEB)) {
			const struct ethhdr *eth;
			struct ethhdr _eth;

			eth = __skb_header_pointer(skb, nhoff,
						   sizeof(_eth),
						   data, hlen, &_eth);
			if (!eth)
				return false;
			proto = eth->h_proto;
			nhoff += sizeof(*eth);
		}
		goto again;
	}
	case IPPROTO_IPIP:
		proto = htons(ETH_P_IP);
		goto ip;
	case IPPROTO_IPV6:
		proto = htons(ETH_P_IPV6);
		goto ipv6;
	default:
		break;
	}

	key_basic->n_proto = proto;
	key_basic->ip_proto = ip_proto;
	key_control->thoff = (u16)nhoff;

	if (skb_flow_dissector_uses_key(flow_dissector,
					FLOW_DISSECTOR_KEY_PORTS)) {
		key_ports = skb_flow_dissector_target(flow_dissector,
						      FLOW_DISSECTOR_KEY_PORTS,
						      target_container);
		key_ports->ports = __skb_flow_get_ports(skb, nhoff, ip_proto,
							data, hlen);
	}

	return true;
}
EXPORT_SYMBOL(__skb_flow_dissect);

static u32 hashrnd __read_mostly;
static __always_inline void __flow_hash_secret_init(void)
{
	net_get_random_once(&hashrnd, sizeof(hashrnd));
}

static __always_inline u32 __flow_hash_words(u32 *words, u32 length, u32 keyval)
{
	return jhash2(words, length, keyval);
}

static inline void *flow_keys_hash_start(struct flow_keys *flow)
{
	BUILD_BUG_ON(FLOW_KEYS_HASH_OFFSET % sizeof(u32));
	return (void *)flow + FLOW_KEYS_HASH_OFFSET;
}

static inline size_t flow_keys_hash_length(struct flow_keys *flow)
{
	BUILD_BUG_ON((sizeof(*flow) - FLOW_KEYS_HASH_OFFSET) % sizeof(u32));
	return (sizeof(*flow) - FLOW_KEYS_HASH_OFFSET) / sizeof(u32);
}

static inline u32 __flow_hash_from_keys(struct flow_keys *keys, u32 keyval)
{
	u32 hash;

	/* get a consistent hash (same value on both flow directions) */
	if (((__force u32)keys->addrs.dst < (__force u32)keys->addrs.src) ||
	    (((__force u32)keys->addrs.dst == (__force u32)keys->addrs.src) &&
	     ((__force u16)keys->ports.dst < (__force u16)keys->ports.src))) {
		swap(keys->addrs.dst, keys->addrs.src);
		swap(keys->ports.src, keys->ports.dst);
	}

	hash = __flow_hash_words((u32 *)flow_keys_hash_start(keys),
				 flow_keys_hash_length(keys), keyval);
	if (!hash)
		hash = 1;

	return hash;
}

u32 flow_hash_from_keys(struct flow_keys *keys)
{
	__flow_hash_secret_init();
	return __flow_hash_from_keys(keys, hashrnd);
}
EXPORT_SYMBOL(flow_hash_from_keys);

static inline u32 ___skb_get_hash(const struct sk_buff *skb,
				  struct flow_keys *keys, u32 keyval)
{
	if (!skb_flow_dissect_flow_keys(skb, keys))
		return 0;

	return __flow_hash_from_keys(keys, keyval);
}

struct _flow_keys_digest_data {
	__be16	n_proto;
	u8	ip_proto;
	u8	padding;
	__be32	ports;
	__be32	src;
	__be32	dst;
};

void make_flow_keys_digest(struct flow_keys_digest *digest,
			   const struct flow_keys *flow)
{
	struct _flow_keys_digest_data *data =
	    (struct _flow_keys_digest_data *)digest;

	BUILD_BUG_ON(sizeof(*data) > sizeof(*digest));

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

	data->n_proto = flow->basic.n_proto;
	data->ip_proto = flow->basic.ip_proto;
	data->ports = flow->ports.ports;
	data->src = flow->addrs.src;
	data->dst = flow->addrs.dst;
}
EXPORT_SYMBOL(make_flow_keys_digest);

/**
 * __skb_get_hash: calculate a flow hash
 * @skb: sk_buff to calculate flow hash from
 *
 * This function calculates a flow hash based on src/dst addresses
 * and src/dst port numbers.  Sets hash in skb to non-zero hash value
 * on success, zero indicates no valid hash.  Also, sets l4_hash in skb
 * if hash is a canonical 4-tuple hash over transport ports.
 */
void __skb_get_hash(struct sk_buff *skb)
{
	struct flow_keys keys;
	u32 hash;

	__flow_hash_secret_init();

	hash = ___skb_get_hash(skb, &keys, hashrnd);
	if (!hash)
		return;
	if (keys.ports.ports)
		skb->l4_hash = 1;
	skb->sw_hash = 1;
	skb->hash = hash;
}
EXPORT_SYMBOL(__skb_get_hash);

__u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb)
{
	struct flow_keys keys;

	return ___skb_get_hash(skb, &keys, perturb);
}
EXPORT_SYMBOL(skb_get_hash_perturb);

u32 __skb_get_poff(const struct sk_buff *skb, void *data,
		   const struct flow_keys *keys, int hlen)
{
	u32 poff = keys->control.thoff;

	switch (keys->basic.ip_proto) {
	case IPPROTO_TCP: {
		/* access doff as u8 to avoid unaligned access */
		const u8 *doff;
		u8 _doff;

		doff = __skb_header_pointer(skb, poff + 12, sizeof(_doff),
					    data, hlen, &_doff);
		if (!doff)
			return poff;

		poff += max_t(u32, sizeof(struct tcphdr), (*doff & 0xF0) >> 2);
		break;
	}
	case IPPROTO_UDP:
	case IPPROTO_UDPLITE:
		poff += sizeof(struct udphdr);
		break;
	/* For the rest, we do not really care about header
	 * extensions at this point for now.
	 */
	case IPPROTO_ICMP:
		poff += sizeof(struct icmphdr);
		break;
	case IPPROTO_ICMPV6:
		poff += sizeof(struct icmp6hdr);
		break;
	case IPPROTO_IGMP:
		poff += sizeof(struct igmphdr);
		break;
	case IPPROTO_DCCP:
		poff += sizeof(struct dccp_hdr);
		break;
	case IPPROTO_SCTP:
		poff += sizeof(struct sctphdr);
		break;
	}

	return poff;
}

/**
 * skb_get_poff - get the offset to the payload
 * @skb: sk_buff to get the payload offset from
 *
 * The function will get the offset to the payload as far as it could
 * be dissected.  The main user is currently BPF, so that we can dynamically
 * truncate packets without needing to push actual payload to the user
 * space and can analyze headers only, instead.
 */
u32 skb_get_poff(const struct sk_buff *skb)
{
	struct flow_keys keys;

	if (!skb_flow_dissect_flow_keys(skb, &keys))
		return 0;

	return __skb_get_poff(skb, skb->data, &keys, skb_headlen(skb));
}

static const struct flow_dissector_key flow_keys_dissector_keys[] = {
	{
		.key_id = FLOW_DISSECTOR_KEY_CONTROL,
		.offset = offsetof(struct flow_keys, control),
	},
	{
		.key_id = FLOW_DISSECTOR_KEY_BASIC,
		.offset = offsetof(struct flow_keys, basic),
	},
	{
		.key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS,
		.offset = offsetof(struct flow_keys, addrs),
	},
	{
		.key_id = FLOW_DISSECTOR_KEY_IPV6_HASH_ADDRS,
		.offset = offsetof(struct flow_keys, addrs),
	},
	{
		.key_id = FLOW_DISSECTOR_KEY_PORTS,
		.offset = offsetof(struct flow_keys, ports),
	},
};

static const struct flow_dissector_key flow_keys_buf_dissector_keys[] = {
	{
		.key_id = FLOW_DISSECTOR_KEY_CONTROL,
		.offset = offsetof(struct flow_keys, control),
	},
	{
		.key_id = FLOW_DISSECTOR_KEY_BASIC,
		.offset = offsetof(struct flow_keys, basic),
	},
};

struct flow_dissector flow_keys_dissector __read_mostly;
EXPORT_SYMBOL(flow_keys_dissector);

struct flow_dissector flow_keys_buf_dissector __read_mostly;

static int __init init_default_flow_dissectors(void)
{
	skb_flow_dissector_init(&flow_keys_dissector,
				flow_keys_dissector_keys,
				ARRAY_SIZE(flow_keys_dissector_keys));
	skb_flow_dissector_init(&flow_keys_buf_dissector,
				flow_keys_buf_dissector_keys,
				ARRAY_SIZE(flow_keys_buf_dissector_keys));
	return 0;
}

late_initcall_sync(init_default_flow_dissectors);