[PATCH net-next v18 08/25] ovpn: implement basic RX path (UDP)

@@ -9,15 +9,77 @@
 
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
+#include <net/gro_cells.h>
 #include <net/gso.h>
 
-#include "io.h"
 #include "ovpnstruct.h"
 #include "peer.h"
+#include "io.h"
+#include "netlink.h"
+#include "proto.h"
 #include "udp.h"
 #include "skb.h"
 #include "socket.h"
 
+/* Called after decrypt to write the IP packet to the device.
+ * This method is expected to manage/free the skb.
+ */
+static void ovpn_netdev_write(struct ovpn_peer *peer, struct sk_buff *skb)
+{
+	unsigned int pkt_len;
+	int ret;
+
+	/* we can't guarantee the packet wasn't corrupted before entering the
+	 * VPN, therefore we give other layers a chance to check that
+	 */
+	skb->ip_summed = CHECKSUM_NONE;
+
+	/* skb hash for transport packet no longer valid after decapsulation */
+	skb_clear_hash(skb);
+
+	/* post-decrypt scrub -- prepare to inject encapsulated packet onto the
+	 * interface, based on __skb_tunnel_rx() in dst.h
+	 */
+	skb->dev = peer->ovpn->dev;
+	skb_set_queue_mapping(skb, 0);
+	skb_scrub_packet(skb, true);
+
+	skb_reset_network_header(skb);
+	skb_reset_transport_header(skb);
+	skb_reset_inner_headers(skb);
+
+	/* cause packet to be "received" by the interface */
+	pkt_len = skb->len;
+	ret = gro_cells_receive(&peer->ovpn->gro_cells, skb);
+	if (likely(ret == NET_RX_SUCCESS))
+		/* update RX stats with the size of decrypted packet */
+		dev_sw_netstats_rx_add(peer->ovpn->dev, pkt_len);
+}
+
+static void ovpn_decrypt_post(struct sk_buff *skb, int ret)
+{
+	struct ovpn_peer *peer = ovpn_skb_cb(skb)->peer;
+
+	if (unlikely(ret < 0))
+		goto drop;
+
+	ovpn_netdev_write(peer, skb);
+	/* skb is passed to upper layer - don't free it */
+	skb = NULL;
+drop:
+	if (unlikely(skb))
+		dev_core_stats_rx_dropped_inc(peer->ovpn->dev);
+	ovpn_peer_put(peer);
+	kfree_skb(skb);
+}
+
+/* RX path entry point: decrypt packet and forward it to the device */
+void ovpn_recv(struct ovpn_peer *peer, struct sk_buff *skb)
+{
+	ovpn_skb_cb(skb)->peer = peer;
+	ovpn_decrypt_post(skb, 0);
+}
+
 static void ovpn_encrypt_post(struct sk_buff *skb, int ret)
 {
 	struct ovpn_peer *peer = ovpn_skb_cb(skb)->peer;

@@ -21,4 +21,6 @@
 
 netdev_tx_t ovpn_net_xmit(struct sk_buff *skb, struct net_device *dev);
 
+void ovpn_recv(struct ovpn_peer *peer, struct sk_buff *skb);
+
 #endif /* _NET_OVPN_OVPN_H_ */

@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/inetdevice.h>
+#include <net/gro_cells.h>
 #include <net/ip.h>
 #include <net/rtnetlink.h>
 #include <uapi/linux/if_arp.h>

@@ -24,7 +25,16 @@
 
 static int ovpn_net_init(struct net_device *dev)
 {
-	return 0;
+	struct ovpn_priv *ovpn = netdev_priv(dev);
+
+	return gro_cells_init(&ovpn->gro_cells, dev);
+}
+
+static void ovpn_net_uninit(struct net_device *dev)
+{
+	struct ovpn_priv *ovpn = netdev_priv(dev);
+
+	gro_cells_destroy(&ovpn->gro_cells);
 }
 
 static int ovpn_net_open(struct net_device *dev)

@@ -50,6 +60,7 @@ static int ovpn_net_stop(struct net_device *dev)
 
 static const struct net_device_ops ovpn_netdev_ops = {
 	.ndo_init		= ovpn_net_init,
+	.ndo_uninit		= ovpn_net_uninit,
 	.ndo_open		= ovpn_net_open,
 	.ndo_stop		= ovpn_net_stop,
 	.ndo_start_xmit		= ovpn_net_xmit,

@@ -10,6 +10,7 @@
 #ifndef _NET_OVPN_OVPNSTRUCT_H_
 #define _NET_OVPN_OVPNSTRUCT_H_
 
+#include <net/gro_cells.h>
 #include <uapi/linux/if_link.h>
 #include <uapi/linux/ovpn.h>
 

@@ -20,6 +21,7 @@
  * @mode: device operation mode (i.e. p2p, mp, ..)
  * @lock: protect this object
  * @peer: in P2P mode, this is the only remote peer
+ * @gro_cells: pointer to the Generic Receive Offload cell
  */
 struct ovpn_priv {
 	struct net_device *dev;

@@ -27,6 +29,7 @@ struct ovpn_priv {
 	enum ovpn_mode mode;
 	spinlock_t lock; /* protect writing to the ovpn_priv object */
 	struct ovpn_peer __rcu *peer;
+	struct gro_cells gro_cells;
 };
 
 #endif /* _NET_OVPN_OVPNSTRUCT_H_ */

@@ -10,6 +10,11 @@
 #ifndef _NET_OVPN_PROTO_H_
 #define _NET_OVPN_PROTO_H_
 
+#include "main.h"
+
+#include <linux/bitfield.h>
+#include <linux/skbuff.h>
+
 /* When the OpenVPN protocol is ran in AEAD mode, use
  * the OpenVPN packet ID as the AEAD nonce:
  *

@@ -34,5 +39,48 @@
 #define OVPN_NONCE_WIRE_SIZE (OVPN_NONCE_SIZE - OVPN_NONCE_TAIL_SIZE)
 
 #define OVPN_OPCODE_SIZE		4 /* DATA_V2 opcode size */
+#define OVPN_OPCODE_KEYID_MASK		0x07000000
+#define OVPN_OPCODE_PKTTYPE_MASK	0xF8000000
+#define OVPN_OPCODE_PEERID_MASK		0x00FFFFFF
+
+/* packet opcodes of interest to us */
+#define OVPN_DATA_V1			6 /* data channel v1 packet */
+#define OVPN_DATA_V2			9 /* data channel v2 packet */
+
+#define OVPN_PEER_ID_UNDEF		0x00FFFFFF
+
+/**
+ * ovpn_opcode_from_skb - extract OP code from skb at specified offset
+ * @skb: the packet to extract the OP code from
+ * @offset: the offset in the data buffer where the OP code is located
+ *
+ * Note: this function assumes that the skb head was pulled enough
+ * to access the first byte.
+ *
+ * Return: the OP code
+ */
+static inline u8 ovpn_opcode_from_skb(const struct sk_buff *skb, u16 offset)
+{
+	u32 opcode = be32_to_cpu(*(__be32 *)(skb->data + offset));
+
+	return FIELD_GET(OVPN_OPCODE_PKTTYPE_MASK, opcode);
+}
+
+/**
+ * ovpn_peer_id_from_skb - extract peer ID from skb at specified offset
+ * @skb: the packet to extract the OP code from
+ * @offset: the offset in the data buffer where the OP code is located
+ *
+ * Note: this function assumes that the skb head was pulled enough
+ * to access the first 4 bytes.
+ *
+ * Return: the peer ID
+ */
+static inline u32 ovpn_peer_id_from_skb(const struct sk_buff *skb, u16 offset)
+{
+	u32 opcode = be32_to_cpu(*(__be32 *)(skb->data + offset));
+
+	return FIELD_GET(OVPN_OPCODE_PEERID_MASK, opcode);
+}
 
-#endif /* _NET_OVPN_PROTO_H_ */
+#endif /* _NET_OVPN_OVPNPROTO_H_ */

@@ -178,6 +178,15 @@ struct ovpn_socket *ovpn_socket_new(struct socket *sock, struct ovpn_peer *peer)
 	ovpn_sock->sock = sock;
 	kref_init(&ovpn_sock->refcount);
 
+	if (sock->sk->sk_protocol == IPPROTO_UDP) {
+		/* in UDP we only link the ovpn instance since the socket is
+		 * shared among multiple peers
+		 */
+		ovpn_sock->ovpn = peer->ovpn;
+		netdev_hold(peer->ovpn->dev, &ovpn_sock->dev_tracker,
+			    GFP_KERNEL);
+	}
+
 	rcu_assign_sk_user_data(sock->sk, ovpn_sock);
 sock_release:
 	release_sock(sock->sk);

@@ -20,12 +20,19 @@ struct ovpn_peer;
 /**
  * struct ovpn_socket - a kernel socket referenced in the ovpn code
  * @ovpn: ovpn instance owning this socket (UDP only)
+ * @dev_tracker: reference tracker for associated dev (UDP only)
  * @sock: the low level sock object
  * @refcount: amount of contexts currently referencing this object
  * @rcu: member used to schedule RCU destructor callback
  */
 struct ovpn_socket {
-	struct ovpn_priv *ovpn;
+	union {
+		struct {
+			struct ovpn_priv *ovpn;
+			netdevice_tracker dev_tracker;
+		};
+	};
+
 	struct socket *sock;
 	struct kref refcount;
 	struct rcu_head rcu;

@@ -23,9 +23,111 @@
 #include "bind.h"
 #include "io.h"
 #include "peer.h"
+#include "proto.h"
 #include "socket.h"
 #include "udp.h"
 
+/* Retrieve the corresponding ovpn object from a UDP socket
+ * rcu_read_lock must be held on entry
+ */
+static struct ovpn_socket *ovpn_socket_from_udp_sock(struct sock *sk)
+{
+	struct ovpn_socket *ovpn_sock;
+
+	if (unlikely(READ_ONCE(udp_sk(sk)->encap_type) != UDP_ENCAP_OVPNINUDP))
+		return NULL;
+
+	ovpn_sock = rcu_dereference_sk_user_data(sk);
+	if (unlikely(!ovpn_sock))
+		return NULL;
+
+	/* make sure that sk matches our stored transport socket */
+	if (unlikely(!ovpn_sock->sock || sk != ovpn_sock->sock->sk))
+		return NULL;
+
+	return ovpn_sock;
+}
+
+/**
+ * ovpn_udp_encap_recv - Start processing a received UDP packet.
+ * @sk: socket over which the packet was received
+ * @skb: the received packet
+ *
+ * If the first byte of the payload is DATA_V2, the packet is further processed,
+ * otherwise it is forwarded to the UDP stack for delivery to user space.
+ *
+ * Return:
+ *  0 if skb was consumed or dropped
+ * >0 if skb should be passed up to userspace as UDP (packet not consumed)
+ * <0 if skb should be resubmitted as proto -N (packet not consumed)
+ */
+static int ovpn_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
+{
+	struct ovpn_socket *ovpn_sock;
+	struct ovpn_priv *ovpn;
+	struct ovpn_peer *peer;
+	u32 peer_id;
+	u8 opcode;
+
+	ovpn_sock = ovpn_socket_from_udp_sock(sk);
+	if (unlikely(!ovpn_sock)) {
+		net_err_ratelimited("ovpn: %s invoked on non ovpn socket\n",
+				    __func__);
+		goto drop_noovpn;
+	}
+
+	ovpn = ovpn_sock->ovpn;
+	if (unlikely(!ovpn)) {
+		net_err_ratelimited("ovpn: cannot obtain ovpn object from UDP socket\n");
+		goto drop_noovpn;
+	}
+
+	/* Make sure the first 4 bytes of the skb data buffer after the UDP
+	 * header are accessible.
+	 * They are required to fetch the OP code, the key ID and the peer ID.
+	 */
+	if (unlikely(!pskb_may_pull(skb, sizeof(struct udphdr) +
+				    OVPN_OPCODE_SIZE))) {
+		net_dbg_ratelimited("%s: packet too small from UDP socket\n",
+				    netdev_name(ovpn->dev));
+		goto drop;
+	}
+
+	opcode = ovpn_opcode_from_skb(skb, sizeof(struct udphdr));
+	if (unlikely(opcode != OVPN_DATA_V2)) {
+		/* DATA_V1 is not supported */
+		if (opcode == OVPN_DATA_V1)
+			goto drop;
+
+		/* unknown or control packet: let it bubble up to userspace */
+		return 1;
+	}
+
+	peer_id = ovpn_peer_id_from_skb(skb, sizeof(struct udphdr));
+	/* some OpenVPN server implementations send data packets with the
+	 * peer-id set to UNDEF. In this case we skip the peer lookup by peer-id
+	 * and we try with the transport address
+	 */
+	if (peer_id == OVPN_PEER_ID_UNDEF)
+		peer = ovpn_peer_get_by_transp_addr(ovpn, skb);
+	else
+		peer = ovpn_peer_get_by_id(ovpn, peer_id);
+
+	if (unlikely(!peer))
+		goto drop;
+
+	/* pop off outer UDP header */
+	__skb_pull(skb, sizeof(struct udphdr));
+	ovpn_recv(peer, skb);
+	return 0;
+
+drop:
+	dev_core_stats_rx_dropped_inc(ovpn->dev);
+drop_noovpn:
+	kfree_skb(skb);
+	return 0;
+}
+
 /**
  * ovpn_udp4_output - send IPv4 packet over udp socket
  * @peer: the destination peer

@@ -262,8 +364,12 @@ void ovpn_udp_send_skb(struct ovpn_peer *peer, struct sk_buff *skb)
  */
 int ovpn_udp_socket_attach(struct socket *sock, struct ovpn_priv *ovpn)
 {
+	struct udp_tunnel_sock_cfg cfg = {
+		.encap_type = UDP_ENCAP_OVPNINUDP,
+		.encap_rcv = ovpn_udp_encap_recv,
+	};
 	struct ovpn_socket *old_data;
-	int ret = 0;
+	int ret;
 
 	/* make sure no pre-existing encapsulation handler exists */
 	rcu_read_lock();

@@ -271,6 +377,7 @@ int ovpn_udp_socket_attach(struct socket *sock, struct ovpn_priv *ovpn)
 	if (!old_data) {
 		/* socket is currently unused - we can take it */
 		rcu_read_unlock();
+		setup_udp_tunnel_sock(sock_net(sock->sk), sock, &cfg);
 		return 0;
 	}
 

@@ -304,4 +411,11 @@ int ovpn_udp_socket_attach(struct socket *sock, struct ovpn_priv *ovpn)
  */
 void ovpn_udp_socket_detach(struct ovpn_socket *ovpn_sock)
 {
+	struct udp_tunnel_sock_cfg cfg = { };
+
+	if (ovpn_sock->ovpn)
+		/* drop reference to netdev held in sk_user_data */
+		netdev_put(ovpn_sock->ovpn->dev, &ovpn_sock->dev_tracker);
+	setup_udp_tunnel_sock(sock_net(ovpn_sock->sock->sk), ovpn_sock->sock,
+			      &cfg);
 }

@@ -17,7 +17,6 @@ struct socket;
 
 int ovpn_udp_socket_attach(struct socket *sock, struct ovpn_priv *ovpn);
 void ovpn_udp_socket_detach(struct ovpn_socket *ovpn_sock);
-
 void ovpn_udp_send_skb(struct ovpn_peer *peer, struct sk_buff *skb);
 
 #endif /* _NET_OVPN_UDP_H_ */