diff mbox series

[net-next,v5,11/25] ovpn: implement basic RX path (UDP)

Message ID 20240627130843.21042-12-antonio@openvpn.net (mailing list archive)
State Changes Requested
Delegated to: Netdev Maintainers
Headers show
Series Introducing OpenVPN Data Channel Offload | expand

Checks

Context Check Description
netdev/series_format fail Series longer than 15 patches
netdev/tree_selection success Clearly marked for net-next, async
netdev/ynl success Generated files up to date; no warnings/errors; GEN HAS DIFF 2 files changed, 2612 insertions(+);
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 842 this patch: 842
netdev/build_tools success No tools touched, skip
netdev/cc_maintainers warning 1 maintainers not CCed: openvpn-devel@lists.sourceforge.net
netdev/build_clang success Errors and warnings before: 849 this patch: 849
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 851 this patch: 851
netdev/checkpatch warning WARNING: added, moved or deleted file(s), does MAINTAINERS need updating?
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0
netdev/contest success net-next-2024-06-28--06-00 (tests: 666)

Commit Message

Antonio Quartulli June 27, 2024, 1:08 p.m. UTC
Packets received over the socket are forwarded to the user device.

Implementation is UDP only. TCP will be added by a later patch.

Note: no decryption/decapsulation exists yet, packets are forwarded as
they arrive without much processing.

Signed-off-by: Antonio Quartulli <antonio@openvpn.net>
---
 drivers/net/ovpn/io.c         |  66 ++++++++++++++++++++-
 drivers/net/ovpn/io.h         |   2 +-
 drivers/net/ovpn/main.c       |   9 ++-
 drivers/net/ovpn/ovpnstruct.h |   3 +
 drivers/net/ovpn/proto.h      |  75 ++++++++++++++++++++++++
 drivers/net/ovpn/skb.h        |   3 -
 drivers/net/ovpn/socket.c     |  24 ++++++++
 drivers/net/ovpn/udp.c        | 104 +++++++++++++++++++++++++++++++++-
 drivers/net/ovpn/udp.h        |   3 +-
 9 files changed, 281 insertions(+), 8 deletions(-)
 create mode 100644 drivers/net/ovpn/proto.h

Comments

Sabrina Dubroca July 8, 2024, 4:11 p.m. UTC | #1
2024-06-27, 15:08:29 +0200, Antonio Quartulli wrote:
> +static void ovpn_netdev_write(struct ovpn_peer *peer, struct sk_buff *skb)
> +{
[...]
> +	/* cause packet to be "received" by the interface */
> +	if (likely(gro_cells_receive(&peer->ovpn->gro_cells,
> +				     skb) == NET_RX_SUCCESS))
> +		/* update RX stats with the size of decrypted packet */
> +		dev_sw_netstats_rx_add(peer->ovpn->dev, skb->len);
> +	else
> +		dev_core_stats_rx_dropped_inc(peer->ovpn->dev);

Not needed AFAICT, gro_cells_receive already does
dev_core_stats_rx_dropped_inc(skb->dev) when it drops the packet.

> +}
> +
> +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:

I really find this "common" return code confusing. The only thing the
two cases have in common is dropping the peer reference.

> +	if (unlikely(skb))
> +		dev_core_stats_rx_dropped_inc(peer->ovpn->dev);
> +	kfree_skb(skb);
> +	ovpn_peer_put(peer);
> +}
Antonio Quartulli July 8, 2024, 10:09 p.m. UTC | #2
Hi,

On 08/07/2024 18:11, Sabrina Dubroca wrote:
> 2024-06-27, 15:08:29 +0200, Antonio Quartulli wrote:
>> +static void ovpn_netdev_write(struct ovpn_peer *peer, struct sk_buff *skb)
>> +{
> [...]
>> +	/* cause packet to be "received" by the interface */
>> +	if (likely(gro_cells_receive(&peer->ovpn->gro_cells,
>> +				     skb) == NET_RX_SUCCESS))
>> +		/* update RX stats with the size of decrypted packet */
>> +		dev_sw_netstats_rx_add(peer->ovpn->dev, skb->len);
>> +	else
>> +		dev_core_stats_rx_dropped_inc(peer->ovpn->dev);
> 
> Not needed AFAICT, gro_cells_receive already does
> dev_core_stats_rx_dropped_inc(skb->dev) when it drops the packet.

You're right! This should be removed.

> 
>> +}
>> +
>> +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:
> 
> I really find this "common" return code confusing. The only thing the
> two cases have in common is dropping the peer reference.

I believe it's just a matter of perspective: I read it as "exit path" 
and if something went wrong I just do some extra actions.

However, I am perfectly fine splitting success/failure paths if the 
common code is little like in this case.

Thanks!

> 
>> +	if (unlikely(skb))
>> +		dev_core_stats_rx_dropped_inc(peer->ovpn->dev);
>> +	kfree_skb(skb);
>> +	ovpn_peer_put(peer);
>> +}
>
diff mbox series

Patch

diff --git a/drivers/net/ovpn/io.c b/drivers/net/ovpn/io.c
index 20997a682098..643637572a40 100644
--- a/drivers/net/ovpn/io.c
+++ b/drivers/net/ovpn/io.c
@@ -9,14 +9,78 @@ 
 
 #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"
 
+/* 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)
+{
+	/* packet integrity was verified on the VPN layer - no need to perform
+	 * any additional check along the stack
+	 */
+	skb->ip_summed = CHECKSUM_UNNECESSARY;
+	skb->csum_level = ~0;
+
+	/* 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_probe_transport_header(skb);
+	skb_reset_inner_headers(skb);
+
+	memset(skb->cb, 0, sizeof(skb->cb));
+
+	/* cause packet to be "received" by the interface */
+	if (likely(gro_cells_receive(&peer->ovpn->gro_cells,
+				     skb) == NET_RX_SUCCESS))
+		/* update RX stats with the size of decrypted packet */
+		dev_sw_netstats_rx_add(peer->ovpn->dev, skb->len);
+	else
+		dev_core_stats_rx_dropped_inc(peer->ovpn->dev);
+}
+
+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);
+	kfree_skb(skb);
+	ovpn_peer_put(peer);
+}
+
+/* pick next packet from RX queue, decrypt 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;
diff --git a/drivers/net/ovpn/io.h b/drivers/net/ovpn/io.h
index 95568671d5ae..9667a0a470e0 100644
--- a/drivers/net/ovpn/io.h
+++ b/drivers/net/ovpn/io.h
@@ -12,6 +12,6 @@ 
 
 netdev_tx_t ovpn_net_xmit(struct sk_buff *skb, struct net_device *dev);
 
-void ovpn_encrypt_work(struct work_struct *work);
+void ovpn_recv(struct ovpn_peer *peer, struct sk_buff *skb);
 
 #endif /* _NET_OVPN_OVPN_H_ */
diff --git a/drivers/net/ovpn/main.c b/drivers/net/ovpn/main.c
index 8a57088491b5..4e6f6fd5ae56 100644
--- a/drivers/net/ovpn/main.c
+++ b/drivers/net/ovpn/main.c
@@ -13,6 +13,7 @@ 
 #include <linux/inetdevice.h>
 //#include <linux/rcupdate.h>
 #include <linux/version.h>
+#include <net/gro_cells.h>
 #include <net/ip.h>
 #include <net/rtnetlink.h>
 #include <uapi/linux/if_arp.h>
@@ -49,11 +50,17 @@  static int ovpn_struct_init(struct net_device *dev, enum ovpn_mode mode)
 
 static void ovpn_struct_free(struct net_device *net)
 {
+	struct ovpn_struct *ovpn = netdev_priv(net);
+
+	gro_cells_destroy(&ovpn->gro_cells);
+	rcu_barrier();
 }
 
 static int ovpn_net_init(struct net_device *dev)
 {
-	return 0;
+	struct ovpn_struct *ovpn = netdev_priv(dev);
+
+	return gro_cells_init(&ovpn->gro_cells, dev);
 }
 
 static int ovpn_net_open(struct net_device *dev)
diff --git a/drivers/net/ovpn/ovpnstruct.h b/drivers/net/ovpn/ovpnstruct.h
index 4d1616628430..af39ee86f168 100644
--- a/drivers/net/ovpn/ovpnstruct.h
+++ b/drivers/net/ovpn/ovpnstruct.h
@@ -10,6 +10,7 @@ 
 #ifndef _NET_OVPN_OVPNSTRUCT_H_
 #define _NET_OVPN_OVPNSTRUCT_H_
 
+#include <net/gro_cells.h>
 #include <uapi/linux/ovpn.h>
 
 /**
@@ -20,6 +21,7 @@ 
  * @lock: protect this object
  * @peer: in P2P mode, this is the only remote peer
  * @dev_list: entry for the module wide device list
+ * @gro_cells: pointer to the Generic Receive Offload cell
  */
 struct ovpn_struct {
 	struct net_device *dev;
@@ -28,6 +30,7 @@  struct ovpn_struct {
 	spinlock_t lock; /* protect writing to the ovpn_struct object */
 	struct ovpn_peer __rcu *peer;
 	struct list_head dev_list;
+	struct gro_cells gro_cells;
 };
 
 #endif /* _NET_OVPN_OVPNSTRUCT_H_ */
diff --git a/drivers/net/ovpn/proto.h b/drivers/net/ovpn/proto.h
new file mode 100644
index 000000000000..69604cf26bbf
--- /dev/null
+++ b/drivers/net/ovpn/proto.h
@@ -0,0 +1,75 @@ 
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2024 OpenVPN, Inc.
+ *
+ *  Author:	Antonio Quartulli <antonio@openvpn.net>
+ *		James Yonan <james@openvpn.net>
+ */
+
+#ifndef _NET_OVPN_OVPNPROTO_H_
+#define _NET_OVPN_OVPNPROTO_H_
+
+#include "main.h"
+
+#include <linux/skbuff.h>
+
+/* Methods for operating on the initial command
+ * byte of the OpenVPN protocol.
+ */
+
+/* packet opcode (high 5 bits) and key-id (low 3 bits) are combined in
+ * one byte
+ */
+#define OVPN_KEY_ID_MASK 0x07
+#define OVPN_OPCODE_SHIFT 3
+#define OVPN_OPCODE_MASK 0x1F
+/* upper bounds on opcode and key ID */
+#define OVPN_KEY_ID_MAX (OVPN_KEY_ID_MASK + 1)
+#define OVPN_OPCODE_MAX (OVPN_OPCODE_MASK + 1)
+/* packet opcodes of interest to us */
+#define OVPN_DATA_V1 6 /* data channel V1 packet */
+#define OVPN_DATA_V2 9 /* data channel V2 packet */
+/* size of initial packet opcode */
+#define OVPN_OP_SIZE_V1 1
+#define OVPN_OP_SIZE_V2	4
+#define OVPN_PEER_ID_MASK 0x00FFFFFF
+#define OVPN_PEER_ID_UNDEF 0x00FFFFFF
+/* first byte of keepalive message */
+#define OVPN_KEEPALIVE_FIRST_BYTE 0x2a
+/* first byte of exit message */
+#define OVPN_EXPLICIT_EXIT_NOTIFY_FIRST_BYTE 0x28
+
+/**
+ * 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)
+{
+	u8 byte = *(skb->data + offset);
+
+	return byte >> OVPN_OPCODE_SHIFT;
+}
+
+/**
+ * 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)
+{
+	return ntohl(*(__be32 *)(skb->data + offset)) & OVPN_PEER_ID_MASK;
+}
+
+#endif /* _NET_OVPN_OVPNPROTO_H_ */
diff --git a/drivers/net/ovpn/skb.h b/drivers/net/ovpn/skb.h
index 7966a10d915f..e070fe6f448c 100644
--- a/drivers/net/ovpn/skb.h
+++ b/drivers/net/ovpn/skb.h
@@ -18,10 +18,7 @@ 
 #include <linux/types.h>
 
 struct ovpn_cb {
-	struct aead_request *req;
 	struct ovpn_peer *peer;
-	struct ovpn_crypto_key_slot *ks;
-	unsigned int payload_offset;
 };
 
 static inline struct ovpn_cb *ovpn_skb_cb(struct sk_buff *skb)
diff --git a/drivers/net/ovpn/socket.c b/drivers/net/ovpn/socket.c
index 090a3232ab0e..964b566de69f 100644
--- a/drivers/net/ovpn/socket.c
+++ b/drivers/net/ovpn/socket.c
@@ -22,6 +22,9 @@  static void ovpn_socket_detach(struct socket *sock)
 	if (!sock)
 		return;
 
+	if (sock->sk->sk_protocol == IPPROTO_UDP)
+		ovpn_udp_socket_detach(sock);
+
 	sockfd_put(sock);
 }
 
@@ -71,6 +74,27 @@  static int ovpn_socket_attach(struct socket *sock, struct ovpn_peer *peer)
 	return ret;
 }
 
+/* Retrieve the corresponding ovpn object from a UDP socket
+ * rcu_read_lock must be held on entry
+ */
+struct ovpn_struct *ovpn_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;
+}
+
 /**
  * ovpn_socket_new - create a new socket and initialize it
  * @sock: the kernel socket to embed
diff --git a/drivers/net/ovpn/udp.c b/drivers/net/ovpn/udp.c
index 4f520a8ce818..37feb64705c0 100644
--- a/drivers/net/ovpn/udp.c
+++ b/drivers/net/ovpn/udp.c
@@ -21,9 +21,94 @@ 
 #include "bind.h"
 #include "io.h"
 #include "peer.h"
+#include "proto.h"
 #include "socket.h"
 #include "udp.h"
 
+/**
+ * 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_peer *peer = NULL;
+	struct ovpn_struct *ovpn;
+	u32 peer_id;
+	u8 opcode;
+
+	ovpn = ovpn_from_udp_sock(sk);
+	if (unlikely(!ovpn)) {
+		net_err_ratelimited("%s: cannot obtain ovpn object from UDP socket\n",
+				    __func__);
+		goto drop;
+	}
+
+	/* 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_OP_SIZE_V2))) {
+		net_dbg_ratelimited("%s: packet too small\n", __func__);
+		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_id(ovpn, peer_id);
+		if (!peer) {
+			net_err_ratelimited("%s: received data from unknown peer (id: %d)\n",
+					    __func__, peer_id);
+			goto drop;
+		}
+	}
+
+	if (!peer) {
+		/* data packet with undef peer-id */
+		peer = ovpn_peer_get_by_transp_addr(ovpn, skb);
+		if (unlikely(!peer)) {
+			net_dbg_ratelimited("%s: received data with undef peer-id from unknown source\n",
+					    __func__);
+			goto drop;
+		}
+	}
+
+	/* pop off outer UDP header */
+	__skb_pull(skb, sizeof(struct udphdr));
+	ovpn_recv(peer, skb);
+	return 0;
+
+drop:
+	if (peer)
+		ovpn_peer_put(peer);
+	dev_core_stats_rx_dropped_inc(ovpn->dev);
+	kfree_skb(skb);
+	return 0;
+}
+
 /**
  * ovpn_udp4_output - send IPv4 packet over udp socket
  * @ovpn: the openvpn instance
@@ -257,8 +342,13 @@  void ovpn_udp_send_skb(struct ovpn_struct *ovpn, struct ovpn_peer *peer,
  */
 int ovpn_udp_socket_attach(struct socket *sock, struct ovpn_struct *ovpn)
 {
+	struct udp_tunnel_sock_cfg cfg = {
+		.sk_user_data = ovpn,
+		.encap_type = UDP_ENCAP_OVPNINUDP,
+		.encap_rcv = ovpn_udp_encap_recv,
+	};
 	struct ovpn_socket *old_data;
-	int ret = 0;
+	int ret;
 
 	/* sanity check */
 	if (sock->sk->sk_protocol != IPPROTO_UDP) {
@@ -272,6 +362,7 @@  int ovpn_udp_socket_attach(struct socket *sock, struct ovpn_struct *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;
 	}
 
@@ -300,3 +391,14 @@  int ovpn_udp_socket_attach(struct socket *sock, struct ovpn_struct *ovpn)
 
 	return ret;
 }
+
+/**
+ * ovpn_udp_socket_detach - clean udp-tunnel status for this socket
+ * @sock: the socket to clean
+ */
+void ovpn_udp_socket_detach(struct socket *sock)
+{
+	struct udp_tunnel_sock_cfg cfg = { };
+
+	setup_udp_tunnel_sock(sock_net(sock->sk), sock, &cfg);
+}
diff --git a/drivers/net/ovpn/udp.h b/drivers/net/ovpn/udp.h
index e60f8cd2b4ac..fecb68464896 100644
--- a/drivers/net/ovpn/udp.h
+++ b/drivers/net/ovpn/udp.h
@@ -18,8 +18,9 @@  struct sk_buff;
 struct socket;
 
 int ovpn_udp_socket_attach(struct socket *sock, struct ovpn_struct *ovpn);
-
+void ovpn_udp_socket_detach(struct socket *sock);
 void ovpn_udp_send_skb(struct ovpn_struct *ovpn, struct ovpn_peer *peer,
 		       struct sk_buff *skb);
+struct ovpn_struct *ovpn_from_udp_sock(struct sock *sk);
 
 #endif /* _NET_OVPN_UDP_H_ */