cregit-Linux how code gets into the kernel

Release 4.11 net/ipv4/fou.c

Directory: net/ipv4
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/socket.h>
#include <linux/skbuff.h>
#include <linux/ip.h>
#include <linux/udp.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <net/genetlink.h>
#include <net/gue.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <net/udp.h>
#include <net/udp_tunnel.h>
#include <net/xfrm.h>
#include <uapi/linux/fou.h>
#include <uapi/linux/genetlink.h>


struct fou {
	
struct socket *sock;
	
u8 protocol;
	
u8 flags;
	
__be16 port;
	
u8 family;
	
u16 type;
	
struct list_head list;
	
struct rcu_head rcu;
};


#define FOU_F_REMCSUM_NOPARTIAL BIT(0)


struct fou_cfg {
	
u16 type;
	
u8 protocol;
	
u8 flags;
	
struct udp_port_cfg udp_config;
};


static unsigned int fou_net_id;


struct fou_net {
	
struct list_head fou_list;
	
struct mutex fou_lock;
};




static inline struct fou *fou_from_sock(struct sock *sk)
{
	return sk->sk_user_data;
}


Contributors
PersonTokensPropCommitsCommitProp
Tom Herbert19100.00%1100.00%


Total19100.00%1100.00%






static int fou_recv_pull(struct sk_buff *skb, struct fou *fou, size_t len)
{
	/* Remove 'len' bytes from the packet (UDP header and
         * FOU header if present).
         */
	if (fou->family == AF_INET)
		ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(skb)->tot_len) - len);
	else
		ipv6_hdr(skb)->payload_len =
		    htons(ntohs(ipv6_hdr(skb)->payload_len) - len);

	__skb_pull(skb, len);
	skb_postpull_rcsum(skb, udp_hdr(skb), len);
	skb_reset_transport_header(skb);
	return iptunnel_pull_offloads(skb);
}


Contributors
PersonTokensPropCommitsCommitProp
Tom Herbert9693.20%375.00%


Jesse Gross76.80%125.00%


Total103100.00%4100.00%






static int fou_udp_recv(struct sock *sk, struct sk_buff *skb)
{
	struct fou *fou = fou_from_sock(sk);

	if (!fou)
		return 1;

	if (fou_recv_pull(skb, fou, sizeof(struct udphdr)))
		goto drop;

	return -fou->protocol;

drop:
	kfree_skb(skb);
	return 0;
}


Contributors
PersonTokensPropCommitsCommitProp
Tom Herbert5276.47%375.00%


Jesse Gross1623.53%125.00%


Total68100.00%4100.00%






static struct guehdr *gue_remcsum(struct sk_buff *skb, struct guehdr *guehdr,
				  void *data, size_t hdrlen, u8 ipproto,
				  bool nopartial)
{
	__be16 *pd = data;
	size_t start = ntohs(pd[0]);
	size_t offset = ntohs(pd[1]);
	size_t plen = sizeof(struct udphdr) + hdrlen +
	    max_t(size_t, offset + sizeof(u16), start);

	if (skb->remcsum_offload)
		return guehdr;

	if (!pskb_may_pull(skb, plen))
		return NULL;
	guehdr = (struct guehdr *)&udp_hdr(skb)[1];

	skb_remcsum_process(skb, (void *)guehdr + hdrlen,
			    start, offset, nopartial);

	return guehdr;
}


Contributors
PersonTokensPropCommitsCommitProp
Tom Herbert144100.00%6100.00%


Total144100.00%6100.00%






static int gue_control_message(struct sk_buff *skb, struct guehdr *guehdr)
{
	/* No support yet */
	kfree_skb(skb);
	return 0;
}


Contributors
PersonTokensPropCommitsCommitProp
Tom Herbert25100.00%2100.00%


Total25100.00%2100.00%






static int gue_udp_recv(struct sock *sk, struct sk_buff *skb)
{
	struct fou *fou = fou_from_sock(sk);
	size_t len, optlen, hdrlen;
	struct guehdr *guehdr;
	void *data;
	u16 doffset = 0;

	if (!fou)
		return 1;

	len = sizeof(struct udphdr) + sizeof(struct guehdr);
	if (!pskb_may_pull(skb, len))
		goto drop;

	guehdr = (struct guehdr *)&udp_hdr(skb)[1];

	switch (guehdr->version) {
	case 0: /* Full GUE header present */
		break;

	case 1: {
		/* Direct encasulation of IPv4 or IPv6 */

		int prot;

		switch (((struct iphdr *)guehdr)->version) {
		case 4:
			prot = IPPROTO_IPIP;
			break;
		case 6:
			prot = IPPROTO_IPV6;
			break;
		default:
			goto drop;
		}

		if (fou_recv_pull(skb, fou, sizeof(struct udphdr)))
			goto drop;

		return -prot;
	}

	default: /* Undefined version */
		goto drop;
	}

	optlen = guehdr->hlen << 2;
	len += optlen;

	if (!pskb_may_pull(skb, len))
		goto drop;

	/* guehdr may change after pull */
	guehdr = (struct guehdr *)&udp_hdr(skb)[1];

	hdrlen = sizeof(struct guehdr) + optlen;

	if (guehdr->version != 0 || validate_gue_flags(guehdr, optlen))
		goto drop;

	hdrlen = sizeof(struct guehdr) + optlen;

	if (fou->family == AF_INET)
		ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(skb)->tot_len) - len);
	else
		ipv6_hdr(skb)->payload_len =
		    htons(ntohs(ipv6_hdr(skb)->payload_len) - len);

	/* Pull csum through the guehdr now . This can be used if
         * there is a remote checksum offload.
         */
	skb_postpull_rcsum(skb, udp_hdr(skb), len);

	data = &guehdr[1];

	if (guehdr->flags & GUE_FLAG_PRIV) {
		__be32 flags = *(__be32 *)(data + doffset);

		doffset += GUE_LEN_PRIV;

		if (flags & GUE_PFLAG_REMCSUM) {
			guehdr = gue_remcsum(skb, guehdr, data + doffset,
					     hdrlen, guehdr->proto_ctype,
					     !!(fou->flags &
						FOU_F_REMCSUM_NOPARTIAL));
			if (!guehdr)
				goto drop;

			data = &guehdr[1];

			doffset += GUE_PLEN_REMCSUM;
		}
	}

	if (unlikely(guehdr->control))
		return gue_control_message(skb, guehdr);

	__skb_pull(skb, sizeof(struct udphdr) + hdrlen);
	skb_reset_transport_header(skb);

	if (iptunnel_pull_offloads(skb))
		goto drop;

	return -guehdr->proto_ctype;

drop:
	kfree_skb(skb);
	return 0;
}


Contributors
PersonTokensPropCommitsCommitProp
Tom Herbert46095.44%777.78%


Li RongQing122.49%111.11%


Jesse Gross102.07%111.11%


Total482100.00%9100.00%






static struct sk_buff **fou_gro_receive(struct sock *sk,
					struct sk_buff **head,
					struct sk_buff *skb)
{
	const struct net_offload *ops;
	struct sk_buff **pp = NULL;
	u8 proto = fou_from_sock(sk)->protocol;
	const struct net_offload **offloads;

	/* We can clear the encap_mark for FOU as we are essentially doing
         * one of two possible things.  We are either adding an L4 tunnel
         * header to the outer L3 tunnel header, or we are are simply
         * treating the GRE tunnel header as though it is a UDP protocol
         * specific header such as VXLAN or GENEVE.
         */
	NAPI_GRO_CB(skb)->encap_mark = 0;

	/* Flag this frame as already having an outer encap header */
	NAPI_GRO_CB(skb)->is_fou = 1;

	rcu_read_lock();
	offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
	ops = rcu_dereference(offloads[proto]);
	if (!ops || !ops->callbacks.gro_receive)
		goto out_unlock;

	pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);

out_unlock:
	rcu_read_unlock();

	return pp;
}


Contributors
PersonTokensPropCommitsCommitProp
Tom Herbert11783.57%457.14%


Alexander Duyck2014.29%228.57%


Sabrina Dubroca32.14%114.29%


Total140100.00%7100.00%






static int fou_gro_complete(struct sock *sk, struct sk_buff *skb,
			    int nhoff)
{
	const struct net_offload *ops;
	u8 proto = fou_from_sock(sk)->protocol;
	int err = -ENOSYS;
	const struct net_offload **offloads;

	rcu_read_lock();
	offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
	ops = rcu_dereference(offloads[proto]);
	if (WARN_ON(!ops || !ops->callbacks.gro_complete))
		goto out_unlock;

	err = ops->callbacks.gro_complete(skb, nhoff);

	skb_set_inner_mac_header(skb, nhoff);

out_unlock:
	rcu_read_unlock();

	return err;
}


Contributors
PersonTokensPropCommitsCommitProp
Tom Herbert11394.17%266.67%


Jarno Rajahalme75.83%133.33%


Total120100.00%3100.00%






static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off,
				      struct guehdr *guehdr, void *data,
				      size_t hdrlen, struct gro_remcsum *grc,
				      bool nopartial)
{
	__be16 *pd = data;
	size_t start = ntohs(pd[0]);
	size_t offset = ntohs(pd[1]);

	if (skb->remcsum_offload)
		return guehdr;

	if (!NAPI_GRO_CB(skb)->csum_valid)
		return NULL;

	guehdr = skb_gro_remcsum_process(skb, (void *)guehdr, off, hdrlen,
					 start, offset, grc, nopartial);

	skb->remcsum_offload = 1;

	return guehdr;
}


Contributors
PersonTokensPropCommitsCommitProp
Tom Herbert121100.00%8100.00%


Total121100.00%8100.00%






static struct sk_buff **gue_gro_receive(struct sock *sk,
					struct sk_buff **head,
					struct sk_buff *skb)
{
	const struct net_offload **offloads;
	const struct net_offload *ops;
	struct sk_buff **pp = NULL;
	struct sk_buff *p;
	struct guehdr *guehdr;
	size_t len, optlen, hdrlen, off;
	void *data;
	u16 doffset = 0;
	int flush = 1;
	struct fou *fou = fou_from_sock(sk);
	struct gro_remcsum grc;
	u8 proto;

	skb_gro_remcsum_init(&grc);

	off = skb_gro_offset(skb);
	len = off + sizeof(*guehdr);

	guehdr = skb_gro_header_fast(skb, off);
	if (skb_gro_header_hard(skb, len)) {
		guehdr = skb_gro_header_slow(skb, len, off);
		if (unlikely(!guehdr))
			goto out;
	}

	switch (guehdr->version) {
	case 0:
		break;
	case 1:
		switch (((struct iphdr *)guehdr)->version) {
		case 4:
			proto = IPPROTO_IPIP;
			break;
		case 6:
			proto = IPPROTO_IPV6;
			break;
		default:
			goto out;
		}
		goto next_proto;
	default:
		goto out;
	}

	optlen = guehdr->hlen << 2;
	len += optlen;

	if (skb_gro_header_hard(skb, len)) {
		guehdr = skb_gro_header_slow(skb, len, off);
		if (unlikely(!guehdr))
			goto out;
	}

	if (unlikely(guehdr->control) || guehdr->version != 0 ||
	    validate_gue_flags(guehdr, optlen))
		goto out;

	hdrlen = sizeof(*guehdr) + optlen;

	/* Adjust NAPI_GRO_CB(skb)->csum to account for guehdr,
         * this is needed if there is a remote checkcsum offload.
         */
	skb_gro_postpull_rcsum(skb, guehdr, hdrlen);

	data = &guehdr[1];

	if (guehdr->flags & GUE_FLAG_PRIV) {
		__be32 flags = *(__be32 *)(data + doffset);

		doffset += GUE_LEN_PRIV;

		if (flags & GUE_PFLAG_REMCSUM) {
			guehdr = gue_gro_remcsum(skb, off, guehdr,
						 data + doffset, hdrlen, &grc,
						 !!(fou->flags &
						    FOU_F_REMCSUM_NOPARTIAL));

			if (!guehdr)
				goto out;

			data = &guehdr[1];

			doffset += GUE_PLEN_REMCSUM;
		}
	}

	skb_gro_pull(skb, hdrlen);

	for (p = *head; p; p = p->next) {
		const struct guehdr *guehdr2;

		if (!NAPI_GRO_CB(p)->same_flow)
			continue;

		guehdr2 = (struct guehdr *)(p->data + off);

		/* Compare base GUE header to be equal (covers
                 * hlen, version, proto_ctype, and flags.
                 */
		if (guehdr->word != guehdr2->word) {
			NAPI_GRO_CB(p)->same_flow = 0;
			continue;
		}

		/* Compare optional fields are the same. */
		if (guehdr->hlen && memcmp(&guehdr[1], &guehdr2[1],
					   guehdr->hlen << 2)) {
			NAPI_GRO_CB(p)->same_flow = 0;
			continue;
		}
	}

	proto = guehdr->proto_ctype;

next_proto:

	/* We can clear the encap_mark for GUE as we are essentially doing
         * one of two possible things.  We are either adding an L4 tunnel
         * header to the outer L3 tunnel header, or we are are simply
         * treating the GRE tunnel header as though it is a UDP protocol
         * specific header such as VXLAN or GENEVE.
         */
	NAPI_GRO_CB(skb)->encap_mark = 0;

	/* Flag this frame as already having an outer encap header */
	NAPI_GRO_CB(skb)->is_fou = 1;

	rcu_read_lock();
	offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
	ops = rcu_dereference(offloads[proto]);
	if (WARN_ON_ONCE(!ops || !ops->callbacks.gro_receive))
		goto out_unlock;

	pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
	flush = 0;

out_unlock:
	rcu_read_unlock();
out:
	NAPI_GRO_CB(skb)->flush |= flush;
	skb_gro_remcsum_cleanup(skb, &grc);

	return pp;
}


Contributors
PersonTokensPropCommitsCommitProp
Tom Herbert61295.77%969.23%


Alexander Duyck243.76%323.08%


Sabrina Dubroca30.47%17.69%


Total639100.00%13100.00%






static int gue_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff)
{
	const struct net_offload **offloads;
	struct guehdr *guehdr = (struct guehdr *)(skb->data + nhoff);
	const struct net_offload *ops;
	unsigned int guehlen = 0;
	u8 proto;
	int err = -ENOENT;

	switch (guehdr->version) {
	case 0:
		proto = guehdr->proto_ctype;
		guehlen = sizeof(*guehdr) + (guehdr->hlen << 2);
		break;
	case 1:
		switch (((struct iphdr *)guehdr)->version) {
		case 4:
			proto = IPPROTO_IPIP;
			break;
		case 6:
			proto = IPPROTO_IPV6;
			break;
		default:
			return err;
		}
		break;
	default:
		return err;
	}

	rcu_read_lock();
	offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
	ops = rcu_dereference(offloads[proto]);
	if (WARN_ON(!ops || !ops->callbacks.gro_complete))
		goto out_unlock;

	err = ops->callbacks.gro_complete(skb, nhoff + guehlen);

	skb_set_inner_mac_header(skb, nhoff + guehlen);

out_unlock:
	rcu_read_unlock();
	return err;
}


Contributors
PersonTokensPropCommitsCommitProp
Tom Herbert21196.79%480.00%


Jarno Rajahalme73.21%120.00%


Total218100.00%5100.00%






static int fou_add_to_port_list(struct net *net, struct fou *fou)
{
	struct fou_net *fn = net_generic(net, fou_net_id);
	struct fou *fout;

	mutex_lock(&fn->fou_lock);
	list_for_each_entry(fout, &fn->fou_list, list) {
		if (fou->port == fout->port &&
		    fou->family == fout->family) {
			mutex_unlock(&fn->fou_lock);
			return -EALREADY;
		}
	}

	list_add(&fou->list, &fn->fou_list);
	mutex_unlock(&fn->fou_lock);

	return 0;
}


Contributors
PersonTokensPropCommitsCommitProp
Tom Herbert7872.90%266.67%


Américo Wang2927.10%133.33%


Total107100.00%3100.00%






static void fou_release(struct fou *fou)
{
	struct socket *sock = fou->sock;

	list_del(&fou->list);
	udp_tunnel_sock_release(sock);

	kfree_rcu(fou, rcu);
}


Contributors
PersonTokensPropCommitsCommitProp
Tom Herbert3690.00%133.33%


Hannes Frederic Sowa37.50%133.33%


Américo Wang12.50%133.33%


Total40100.00%3100.00%






static int fou_create(struct net *net, struct fou_cfg *cfg,
		      struct socket **sockp)
{
	struct socket *sock = NULL;
	struct fou *fou = NULL;
	struct sock *sk;
	struct udp_tunnel_sock_cfg tunnel_cfg;
	int err;

	/* Open UDP socket */
	err = udp_sock_create(net, &cfg->udp_config, &sock);
	if (err < 0)
		goto error;

	/* Allocate FOU port structure */
	fou = kzalloc(sizeof(*fou), GFP_KERNEL);
	if (!fou) {
		err = -ENOMEM;
		goto error;
	}

	sk = sock->sk;

	fou->port = cfg->udp_config.local_udp_port;
	fou->family = cfg->udp_config.family;
	fou->flags = cfg->flags;
	fou->type = cfg->type;
	fou->sock = sock;

	memset(&tunnel_cfg, 0, sizeof(tunnel_cfg));
	tunnel_cfg.encap_type = 1;
	tunnel_cfg.sk_user_data = fou;
	tunnel_cfg.encap_destroy = NULL;

	/* Initial for fou type */
	switch (cfg->type) {
	case FOU_ENCAP_DIRECT:
		tunnel_cfg.encap_rcv = fou_udp_recv;
		tunnel_cfg.gro_receive = fou_gro_receive;
		tunnel_cfg.gro_complete = fou_gro_complete;
		fou->protocol = cfg->protocol;
		break;
	case FOU_ENCAP_GUE:
		tunnel_cfg.encap_rcv = gue_udp_recv;
		tunnel_cfg.gro_receive = gue_gro_receive;
		tunnel_cfg.gro_complete = gue_gro_complete;
		break;
	default:
		err = -EINVAL;
		goto error;
	}

	setup_udp_tunnel_sock(net, sock, &tunnel_cfg);

	sk->sk_allocation = GFP_ATOMIC;

	err = fou_add_to_port_list(net, fou);
	if (err)
		goto error;

	if (sockp)
		*sockp = sock;

	return 0;

error:
	kfree(fou);
	if (sock)
		udp_tunnel_sock_release(sock);

	return err;
}


Contributors
PersonTokensPropCommitsCommitProp
Tom Herbert30496.82%583.33%


Américo Wang103.18%116.67%


Total314100.00%6100.00%






static int fou_destroy(struct net *net, struct fou_cfg *cfg)
{
	struct fou_net *fn = net_generic(net, fou_net_id);
	__be16 port = cfg->udp_config.local_udp_port;
	u8 family = cfg->udp_config.family;
	int err = -EINVAL;
	struct fou *fou;

	mutex_lock(&fn->fou_lock);
	list_for_each_entry(fou, &fn->fou_list, list) {
		if (fou->port == port && fou->family == family) {
			fou_release(fou);
			err = 0;
			break;
		}
	}
	mutex_unlock(&fn->fou_lock);

	return err;
}


Contributors
PersonTokensPropCommitsCommitProp
Tom Herbert9080.36%250.00%


Américo Wang2219.64%250.00%


Total112100.00%4100.00%




static struct genl_family fou_nl_family;


static const struct nla_policy fou_nl_policy[FOU_ATTR_MAX + 1] = {
	[FOU_ATTR_PORT] = { .type = NLA_U16, },
	[FOU_ATTR_AF] = { .type = NLA_U8, },
	[FOU_ATTR_IPPROTO] = { .type = NLA_U8, },
	[FOU_ATTR_TYPE] = { .type = NLA_U8, },
	[FOU_ATTR_REMCSUM_NOPARTIAL] = { .type = NLA_FLAG, },
};




static int parse_nl_config(struct genl_info *info,
			   struct fou_cfg *cfg)
{
	memset(cfg, 0, sizeof(*cfg));

	cfg->udp_config.family = AF_INET;

	if (info->attrs[FOU_ATTR_AF]) {
		u8 family = nla_get_u8(info->attrs[FOU_ATTR_AF]);

		switch (family) {
		case AF_INET:
			break;
		case AF_INET6:
			cfg->udp_config.ipv6_v6only = 1;
			break;
		default:
			return -EAFNOSUPPORT;
		}

		cfg->udp_config.family = family;
	}

	if (info->attrs[FOU_ATTR_PORT]) {
		__be16 port = nla_get_be16(info->attrs[FOU_ATTR_PORT]);

		cfg->udp_config.local_udp_port = port;
	}

	if (info->attrs[FOU_ATTR_IPPROTO])
		cfg->protocol = nla_get_u8(info->attrs[FOU_ATTR_IPPROTO]);

	if (info->attrs[FOU_ATTR_TYPE])
		cfg->type = nla_get_u8(info->attrs[FOU_ATTR_TYPE]);

	if (info->attrs[FOU_ATTR_REMCSUM_NOPARTIAL])
		cfg->flags |= FOU_F_REMCSUM_NOPARTIAL;

	return 0;
}


Contributors
PersonTokensPropCommitsCommitProp
Tom Herbert19098.96%480.00%


Américo Wang21.04%120.00%


Total192100.00%5100.00%






static int fou_nl_cmd_add_port(struct sk_buff *skb, struct genl_info *info)
{
	struct net *net = genl_info_net(info);
	struct fou_cfg cfg;
	int err;

	err = parse_nl_config(info, &cfg);
	if (err)
		return err;

	return fou_create(net, &cfg, NULL)