diff options
Diffstat (limited to 'drivers/net/ovpn')
30 files changed, 6700 insertions, 0 deletions
diff --git a/drivers/net/ovpn/Makefile b/drivers/net/ovpn/Makefile new file mode 100644 index 000000000000..229be66167e1 --- /dev/null +++ b/drivers/net/ovpn/Makefile @@ -0,0 +1,22 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# ovpn -- OpenVPN data channel offload in kernel space +# +# Copyright (C) 2020-2025 OpenVPN, Inc. +# +# Author: Antonio Quartulli <antonio@openvpn.net> + +obj-$(CONFIG_OVPN) := ovpn.o +ovpn-y += bind.o +ovpn-y += crypto.o +ovpn-y += crypto_aead.o +ovpn-y += main.o +ovpn-y += io.o +ovpn-y += netlink.o +ovpn-y += netlink-gen.o +ovpn-y += peer.o +ovpn-y += pktid.o +ovpn-y += socket.o +ovpn-y += stats.o +ovpn-y += tcp.o +ovpn-y += udp.o diff --git a/drivers/net/ovpn/bind.c b/drivers/net/ovpn/bind.c new file mode 100644 index 000000000000..24d2788a277e --- /dev/null +++ b/drivers/net/ovpn/bind.c @@ -0,0 +1,55 @@ +// SPDX-License-Identifier: GPL-2.0 +/* OpenVPN data channel offload + * + * Copyright (C) 2012-2025 OpenVPN, Inc. + * + * Author: James Yonan <james@openvpn.net> + * Antonio Quartulli <antonio@openvpn.net> + */ + +#include <linux/netdevice.h> +#include <linux/socket.h> + +#include "ovpnpriv.h" +#include "bind.h" +#include "peer.h" + +/** + * ovpn_bind_from_sockaddr - retrieve binding matching sockaddr + * @ss: the sockaddr to match + * + * Return: the bind matching the passed sockaddr if found, NULL otherwise + */ +struct ovpn_bind *ovpn_bind_from_sockaddr(const struct sockaddr_storage *ss) +{ + struct ovpn_bind *bind; + size_t sa_len; + + if (ss->ss_family == AF_INET) + sa_len = sizeof(struct sockaddr_in); + else if (ss->ss_family == AF_INET6) + sa_len = sizeof(struct sockaddr_in6); + else + return ERR_PTR(-EAFNOSUPPORT); + + bind = kzalloc(sizeof(*bind), GFP_ATOMIC); + if (unlikely(!bind)) + return ERR_PTR(-ENOMEM); + + memcpy(&bind->remote, ss, sa_len); + + return bind; +} + +/** + * ovpn_bind_reset - assign new binding to peer + * @peer: the peer whose binding has to be replaced + * @new: the new bind to assign + */ +void ovpn_bind_reset(struct ovpn_peer *peer, struct ovpn_bind *new) +{ + lockdep_assert_held(&peer->lock); + + kfree_rcu(rcu_replace_pointer(peer->bind, new, + lockdep_is_held(&peer->lock)), rcu); +} diff --git a/drivers/net/ovpn/bind.h b/drivers/net/ovpn/bind.h new file mode 100644 index 000000000000..4e0b8398bfd9 --- /dev/null +++ b/drivers/net/ovpn/bind.h @@ -0,0 +1,101 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* OpenVPN data channel offload + * + * Copyright (C) 2012-2025 OpenVPN, Inc. + * + * Author: James Yonan <james@openvpn.net> + * Antonio Quartulli <antonio@openvpn.net> + */ + +#ifndef _NET_OVPN_OVPNBIND_H_ +#define _NET_OVPN_OVPNBIND_H_ + +#include <net/ip.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <linux/rcupdate.h> +#include <linux/skbuff.h> +#include <linux/spinlock.h> + +struct ovpn_peer; + +/** + * union ovpn_sockaddr - basic transport layer address + * @in4: IPv4 address + * @in6: IPv6 address + */ +union ovpn_sockaddr { + struct sockaddr_in in4; + struct sockaddr_in6 in6; +}; + +/** + * struct ovpn_bind - remote peer binding + * @remote: the remote peer sockaddress + * @local: local endpoint used to talk to the peer + * @local.ipv4: local IPv4 used to talk to the peer + * @local.ipv6: local IPv6 used to talk to the peer + * @rcu: used to schedule RCU cleanup job + */ +struct ovpn_bind { + union ovpn_sockaddr remote; /* remote sockaddr */ + + union { + struct in_addr ipv4; + struct in6_addr ipv6; + } local; + + struct rcu_head rcu; +}; + +/** + * ovpn_bind_skb_src_match - match packet source with binding + * @bind: the binding to match + * @skb: the packet to match + * + * Return: true if the packet source matches the remote peer sockaddr + * in the binding + */ +static inline bool ovpn_bind_skb_src_match(const struct ovpn_bind *bind, + const struct sk_buff *skb) +{ + const union ovpn_sockaddr *remote; + + if (unlikely(!bind)) + return false; + + remote = &bind->remote; + + switch (skb->protocol) { + case htons(ETH_P_IP): + if (unlikely(remote->in4.sin_family != AF_INET)) + return false; + + if (unlikely(remote->in4.sin_addr.s_addr != ip_hdr(skb)->saddr)) + return false; + + if (unlikely(remote->in4.sin_port != udp_hdr(skb)->source)) + return false; + break; + case htons(ETH_P_IPV6): + if (unlikely(remote->in6.sin6_family != AF_INET6)) + return false; + + if (unlikely(!ipv6_addr_equal(&remote->in6.sin6_addr, + &ipv6_hdr(skb)->saddr))) + return false; + + if (unlikely(remote->in6.sin6_port != udp_hdr(skb)->source)) + return false; + break; + default: + return false; + } + + return true; +} + +struct ovpn_bind *ovpn_bind_from_sockaddr(const struct sockaddr_storage *sa); +void ovpn_bind_reset(struct ovpn_peer *peer, struct ovpn_bind *bind); + +#endif /* _NET_OVPN_OVPNBIND_H_ */ diff --git a/drivers/net/ovpn/crypto.c b/drivers/net/ovpn/crypto.c new file mode 100644 index 000000000000..90580e32052f --- /dev/null +++ b/drivers/net/ovpn/crypto.c @@ -0,0 +1,210 @@ +// SPDX-License-Identifier: GPL-2.0 +/* OpenVPN data channel offload + * + * Copyright (C) 2020-2025 OpenVPN, Inc. + * + * Author: James Yonan <james@openvpn.net> + * Antonio Quartulli <antonio@openvpn.net> + */ + +#include <linux/types.h> +#include <linux/net.h> +#include <linux/netdevice.h> +#include <uapi/linux/ovpn.h> + +#include "ovpnpriv.h" +#include "main.h" +#include "pktid.h" +#include "crypto_aead.h" +#include "crypto.h" + +static void ovpn_ks_destroy_rcu(struct rcu_head *head) +{ + struct ovpn_crypto_key_slot *ks; + + ks = container_of(head, struct ovpn_crypto_key_slot, rcu); + ovpn_aead_crypto_key_slot_destroy(ks); +} + +void ovpn_crypto_key_slot_release(struct kref *kref) +{ + struct ovpn_crypto_key_slot *ks; + + ks = container_of(kref, struct ovpn_crypto_key_slot, refcount); + call_rcu(&ks->rcu, ovpn_ks_destroy_rcu); +} + +/* can only be invoked when all peer references have been dropped (i.e. RCU + * release routine) + */ +void ovpn_crypto_state_release(struct ovpn_crypto_state *cs) +{ + struct ovpn_crypto_key_slot *ks; + + ks = rcu_access_pointer(cs->slots[0]); + if (ks) { + RCU_INIT_POINTER(cs->slots[0], NULL); + ovpn_crypto_key_slot_put(ks); + } + + ks = rcu_access_pointer(cs->slots[1]); + if (ks) { + RCU_INIT_POINTER(cs->slots[1], NULL); + ovpn_crypto_key_slot_put(ks); + } +} + +/* removes the key matching the specified id from the crypto context */ +bool ovpn_crypto_kill_key(struct ovpn_crypto_state *cs, u8 key_id) +{ + struct ovpn_crypto_key_slot *ks = NULL; + + spin_lock_bh(&cs->lock); + if (rcu_access_pointer(cs->slots[0])->key_id == key_id) { + ks = rcu_replace_pointer(cs->slots[0], NULL, + lockdep_is_held(&cs->lock)); + } else if (rcu_access_pointer(cs->slots[1])->key_id == key_id) { + ks = rcu_replace_pointer(cs->slots[1], NULL, + lockdep_is_held(&cs->lock)); + } + spin_unlock_bh(&cs->lock); + + if (ks) + ovpn_crypto_key_slot_put(ks); + + /* let the caller know if a key was actually killed */ + return ks; +} + +/* Reset the ovpn_crypto_state object in a way that is atomic + * to RCU readers. + */ +int ovpn_crypto_state_reset(struct ovpn_crypto_state *cs, + const struct ovpn_peer_key_reset *pkr) +{ + struct ovpn_crypto_key_slot *old = NULL, *new; + u8 idx; + + if (pkr->slot != OVPN_KEY_SLOT_PRIMARY && + pkr->slot != OVPN_KEY_SLOT_SECONDARY) + return -EINVAL; + + new = ovpn_aead_crypto_key_slot_new(&pkr->key); + if (IS_ERR(new)) + return PTR_ERR(new); + + spin_lock_bh(&cs->lock); + idx = cs->primary_idx; + switch (pkr->slot) { + case OVPN_KEY_SLOT_PRIMARY: + old = rcu_replace_pointer(cs->slots[idx], new, + lockdep_is_held(&cs->lock)); + break; + case OVPN_KEY_SLOT_SECONDARY: + old = rcu_replace_pointer(cs->slots[!idx], new, + lockdep_is_held(&cs->lock)); + break; + } + spin_unlock_bh(&cs->lock); + + if (old) + ovpn_crypto_key_slot_put(old); + + return 0; +} + +void ovpn_crypto_key_slot_delete(struct ovpn_crypto_state *cs, + enum ovpn_key_slot slot) +{ + struct ovpn_crypto_key_slot *ks = NULL; + u8 idx; + + if (slot != OVPN_KEY_SLOT_PRIMARY && + slot != OVPN_KEY_SLOT_SECONDARY) { + pr_warn("Invalid slot to release: %u\n", slot); + return; + } + + spin_lock_bh(&cs->lock); + idx = cs->primary_idx; + switch (slot) { + case OVPN_KEY_SLOT_PRIMARY: + ks = rcu_replace_pointer(cs->slots[idx], NULL, + lockdep_is_held(&cs->lock)); + break; + case OVPN_KEY_SLOT_SECONDARY: + ks = rcu_replace_pointer(cs->slots[!idx], NULL, + lockdep_is_held(&cs->lock)); + break; + } + spin_unlock_bh(&cs->lock); + + if (!ks) { + pr_debug("Key slot already released: %u\n", slot); + return; + } + + pr_debug("deleting key slot %u, key_id=%u\n", slot, ks->key_id); + ovpn_crypto_key_slot_put(ks); +} + +void ovpn_crypto_key_slots_swap(struct ovpn_crypto_state *cs) +{ + const struct ovpn_crypto_key_slot *old_primary, *old_secondary; + u8 idx; + + spin_lock_bh(&cs->lock); + idx = cs->primary_idx; + old_primary = rcu_dereference_protected(cs->slots[idx], + lockdep_is_held(&cs->lock)); + old_secondary = rcu_dereference_protected(cs->slots[!idx], + lockdep_is_held(&cs->lock)); + /* perform real swap by switching the index of the primary key */ + WRITE_ONCE(cs->primary_idx, !cs->primary_idx); + + pr_debug("key swapped: (old primary) %d <-> (new primary) %d\n", + old_primary ? old_primary->key_id : -1, + old_secondary ? old_secondary->key_id : -1); + + spin_unlock_bh(&cs->lock); +} + +/** + * ovpn_crypto_config_get - populate keyconf object with non-sensible key data + * @cs: the crypto state to extract the key data from + * @slot: the specific slot to inspect + * @keyconf: the output object to populate + * + * Return: 0 on success or a negative error code otherwise + */ +int ovpn_crypto_config_get(struct ovpn_crypto_state *cs, + enum ovpn_key_slot slot, + struct ovpn_key_config *keyconf) +{ + struct ovpn_crypto_key_slot *ks; + int idx; + + switch (slot) { + case OVPN_KEY_SLOT_PRIMARY: + idx = cs->primary_idx; + break; + case OVPN_KEY_SLOT_SECONDARY: + idx = !cs->primary_idx; + break; + default: + return -EINVAL; + } + + rcu_read_lock(); + ks = rcu_dereference(cs->slots[idx]); + if (!ks) { + rcu_read_unlock(); + return -ENOENT; + } + + keyconf->cipher_alg = ovpn_aead_crypto_alg(ks); + keyconf->key_id = ks->key_id; + rcu_read_unlock(); + + return 0; +} diff --git a/drivers/net/ovpn/crypto.h b/drivers/net/ovpn/crypto.h new file mode 100644 index 000000000000..0e284fec3a75 --- /dev/null +++ b/drivers/net/ovpn/crypto.h @@ -0,0 +1,145 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* OpenVPN data channel offload + * + * Copyright (C) 2020-2025 OpenVPN, Inc. + * + * Author: James Yonan <james@openvpn.net> + * Antonio Quartulli <antonio@openvpn.net> + */ + +#ifndef _NET_OVPN_OVPNCRYPTO_H_ +#define _NET_OVPN_OVPNCRYPTO_H_ + +#include "pktid.h" +#include "proto.h" + +/* info needed for both encrypt and decrypt directions */ +struct ovpn_key_direction { + const u8 *cipher_key; + size_t cipher_key_size; + const u8 *nonce_tail; /* only needed for GCM modes */ + size_t nonce_tail_size; /* only needed for GCM modes */ +}; + +/* all info for a particular symmetric key (primary or secondary) */ +struct ovpn_key_config { + enum ovpn_cipher_alg cipher_alg; + u8 key_id; + struct ovpn_key_direction encrypt; + struct ovpn_key_direction decrypt; +}; + +/* used to pass settings from netlink to the crypto engine */ +struct ovpn_peer_key_reset { + enum ovpn_key_slot slot; + struct ovpn_key_config key; +}; + +struct ovpn_crypto_key_slot { + u8 key_id; + + struct crypto_aead *encrypt; + struct crypto_aead *decrypt; + u8 nonce_tail_xmit[OVPN_NONCE_TAIL_SIZE]; + u8 nonce_tail_recv[OVPN_NONCE_TAIL_SIZE]; + + struct ovpn_pktid_recv pid_recv ____cacheline_aligned_in_smp; + struct ovpn_pktid_xmit pid_xmit ____cacheline_aligned_in_smp; + struct kref refcount; + struct rcu_head rcu; +}; + +struct ovpn_crypto_state { + struct ovpn_crypto_key_slot __rcu *slots[2]; + u8 primary_idx; + + /* protects primary and secondary slots */ + spinlock_t lock; +}; + +static inline bool ovpn_crypto_key_slot_hold(struct ovpn_crypto_key_slot *ks) +{ + return kref_get_unless_zero(&ks->refcount); +} + +static inline void ovpn_crypto_state_init(struct ovpn_crypto_state *cs) +{ + RCU_INIT_POINTER(cs->slots[0], NULL); + RCU_INIT_POINTER(cs->slots[1], NULL); + cs->primary_idx = 0; + spin_lock_init(&cs->lock); +} + +static inline struct ovpn_crypto_key_slot * +ovpn_crypto_key_id_to_slot(const struct ovpn_crypto_state *cs, u8 key_id) +{ + struct ovpn_crypto_key_slot *ks; + u8 idx; + + if (unlikely(!cs)) + return NULL; + + rcu_read_lock(); + idx = READ_ONCE(cs->primary_idx); + ks = rcu_dereference(cs->slots[idx]); + if (ks && ks->key_id == key_id) { + if (unlikely(!ovpn_crypto_key_slot_hold(ks))) + ks = NULL; + goto out; + } + + ks = rcu_dereference(cs->slots[!idx]); + if (ks && ks->key_id == key_id) { + if (unlikely(!ovpn_crypto_key_slot_hold(ks))) + ks = NULL; + goto out; + } + + /* when both key slots are occupied but no matching key ID is found, ks + * has to be reset to NULL to avoid carrying a stale pointer + */ + ks = NULL; +out: + rcu_read_unlock(); + + return ks; +} + +static inline struct ovpn_crypto_key_slot * +ovpn_crypto_key_slot_primary(const struct ovpn_crypto_state *cs) +{ + struct ovpn_crypto_key_slot *ks; + + rcu_read_lock(); + ks = rcu_dereference(cs->slots[cs->primary_idx]); + if (unlikely(ks && !ovpn_crypto_key_slot_hold(ks))) + ks = NULL; + rcu_read_unlock(); + + return ks; +} + +void ovpn_crypto_key_slot_release(struct kref *kref); + +static inline void ovpn_crypto_key_slot_put(struct ovpn_crypto_key_slot *ks) +{ + kref_put(&ks->refcount, ovpn_crypto_key_slot_release); +} + +int ovpn_crypto_state_reset(struct ovpn_crypto_state *cs, + const struct ovpn_peer_key_reset *pkr); + +void ovpn_crypto_key_slot_delete(struct ovpn_crypto_state *cs, + enum ovpn_key_slot slot); + +void ovpn_crypto_state_release(struct ovpn_crypto_state *cs); + +void ovpn_crypto_key_slots_swap(struct ovpn_crypto_state *cs); + +int ovpn_crypto_config_get(struct ovpn_crypto_state *cs, + enum ovpn_key_slot slot, + struct ovpn_key_config *keyconf); + +bool ovpn_crypto_kill_key(struct ovpn_crypto_state *cs, u8 key_id); + +#endif /* _NET_OVPN_OVPNCRYPTO_H_ */ diff --git a/drivers/net/ovpn/crypto_aead.c b/drivers/net/ovpn/crypto_aead.c new file mode 100644 index 000000000000..2cca759feffa --- /dev/null +++ b/drivers/net/ovpn/crypto_aead.c @@ -0,0 +1,389 @@ +// SPDX-License-Identifier: GPL-2.0 +/* OpenVPN data channel offload + * + * Copyright (C) 2020-2025 OpenVPN, Inc. + * + * Author: James Yonan <james@openvpn.net> + * Antonio Quartulli <antonio@openvpn.net> + */ + +#include <crypto/aead.h> +#include <linux/skbuff.h> +#include <net/ip.h> +#include <net/ipv6.h> +#include <net/udp.h> + +#include "ovpnpriv.h" +#include "main.h" +#include "io.h" +#include "pktid.h" +#include "crypto_aead.h" +#include "crypto.h" +#include "peer.h" +#include "proto.h" +#include "skb.h" + +#define OVPN_AUTH_TAG_SIZE 16 +#define OVPN_AAD_SIZE (OVPN_OPCODE_SIZE + OVPN_NONCE_WIRE_SIZE) + +#define ALG_NAME_AES "gcm(aes)" +#define ALG_NAME_CHACHAPOLY "rfc7539(chacha20,poly1305)" + +static int ovpn_aead_encap_overhead(const struct ovpn_crypto_key_slot *ks) +{ + return OVPN_OPCODE_SIZE + /* OP header size */ + sizeof(u32) + /* Packet ID */ + crypto_aead_authsize(ks->encrypt); /* Auth Tag */ +} + +int ovpn_aead_encrypt(struct ovpn_peer *peer, struct ovpn_crypto_key_slot *ks, + struct sk_buff *skb) +{ + const unsigned int tag_size = crypto_aead_authsize(ks->encrypt); + struct aead_request *req; + struct sk_buff *trailer; + struct scatterlist *sg; + int nfrags, ret; + u32 pktid, op; + u8 *iv; + + ovpn_skb_cb(skb)->peer = peer; + ovpn_skb_cb(skb)->ks = ks; + + /* Sample AEAD header format: + * 48000001 00000005 7e7046bd 444a7e28 cc6387b1 64a4d6c1 380275a... + * [ OP32 ] [seq # ] [ auth tag ] [ payload ... ] + * [4-byte + * IV head] + */ + + /* check that there's enough headroom in the skb for packet + * encapsulation + */ + if (unlikely(skb_cow_head(skb, OVPN_HEAD_ROOM))) + return -ENOBUFS; + + /* get number of skb frags and ensure that packet data is writable */ + nfrags = skb_cow_data(skb, 0, &trailer); + if (unlikely(nfrags < 0)) + return nfrags; + + if (unlikely(nfrags + 2 > (MAX_SKB_FRAGS + 2))) + return -ENOSPC; + + /* sg may be required by async crypto */ + ovpn_skb_cb(skb)->sg = kmalloc(sizeof(*ovpn_skb_cb(skb)->sg) * + (nfrags + 2), GFP_ATOMIC); + if (unlikely(!ovpn_skb_cb(skb)->sg)) + return -ENOMEM; + + sg = ovpn_skb_cb(skb)->sg; + + /* sg table: + * 0: op, wire nonce (AD, len=OVPN_OP_SIZE_V2+OVPN_NONCE_WIRE_SIZE), + * 1, 2, 3, ..., n: payload, + * n+1: auth_tag (len=tag_size) + */ + sg_init_table(sg, nfrags + 2); + + /* build scatterlist to encrypt packet payload */ + ret = skb_to_sgvec_nomark(skb, sg + 1, 0, skb->len); + if (unlikely(ret < 0)) { + netdev_err(peer->ovpn->dev, + "encrypt: cannot map skb to sg: %d\n", ret); + return ret; + } + + /* append auth_tag onto scatterlist */ + __skb_push(skb, tag_size); + sg_set_buf(sg + ret + 1, skb->data, tag_size); + + /* obtain packet ID, which is used both as a first + * 4 bytes of nonce and last 4 bytes of associated data. + */ + ret = ovpn_pktid_xmit_next(&ks->pid_xmit, &pktid); + if (unlikely(ret < 0)) + return ret; + + /* iv may be required by async crypto */ + ovpn_skb_cb(skb)->iv = kmalloc(OVPN_NONCE_SIZE, GFP_ATOMIC); + if (unlikely(!ovpn_skb_cb(skb)->iv)) + return -ENOMEM; + + iv = ovpn_skb_cb(skb)->iv; + + /* concat 4 bytes packet id and 8 bytes nonce tail into 12 bytes + * nonce + */ + ovpn_pktid_aead_write(pktid, ks->nonce_tail_xmit, iv); + + /* make space for packet id and push it to the front */ + __skb_push(skb, OVPN_NONCE_WIRE_SIZE); + memcpy(skb->data, iv, OVPN_NONCE_WIRE_SIZE); + + /* add packet op as head of additional data */ + op = ovpn_opcode_compose(OVPN_DATA_V2, ks->key_id, peer->id); + __skb_push(skb, OVPN_OPCODE_SIZE); + BUILD_BUG_ON(sizeof(op) != OVPN_OPCODE_SIZE); + *((__force __be32 *)skb->data) = htonl(op); + + /* AEAD Additional data */ + sg_set_buf(sg, skb->data, OVPN_AAD_SIZE); + + req = aead_request_alloc(ks->encrypt, GFP_ATOMIC); + if (unlikely(!req)) + return -ENOMEM; + + ovpn_skb_cb(skb)->req = req; + + /* setup async crypto operation */ + aead_request_set_tfm(req, ks->encrypt); + aead_request_set_callback(req, 0, ovpn_encrypt_post, skb); + aead_request_set_crypt(req, sg, sg, + skb->len - ovpn_aead_encap_overhead(ks), iv); + aead_request_set_ad(req, OVPN_AAD_SIZE); + + /* encrypt it */ + return crypto_aead_encrypt(req); +} + +int ovpn_aead_decrypt(struct ovpn_peer *peer, struct ovpn_crypto_key_slot *ks, + struct sk_buff *skb) +{ + const unsigned int tag_size = crypto_aead_authsize(ks->decrypt); + int ret, payload_len, nfrags; + unsigned int payload_offset; + struct aead_request *req; + struct sk_buff *trailer; + struct scatterlist *sg; + u8 *iv; + + payload_offset = OVPN_AAD_SIZE + tag_size; + payload_len = skb->len - payload_offset; + + ovpn_skb_cb(skb)->payload_offset = payload_offset; + ovpn_skb_cb(skb)->peer = peer; + ovpn_skb_cb(skb)->ks = ks; + + /* sanity check on packet size, payload size must be >= 0 */ + if (unlikely(payload_len < 0)) + return -EINVAL; + + /* Prepare the skb data buffer to be accessed up until the auth tag. + * This is required because this area is directly mapped into the sg + * list. + */ + if (unlikely(!pskb_may_pull(skb, payload_offset))) + return -ENODATA; + + /* get number of skb frags and ensure that packet data is writable */ + nfrags = skb_cow_data(skb, 0, &trailer); + if (unlikely(nfrags < 0)) + return nfrags; + + if (unlikely(nfrags + 2 > (MAX_SKB_FRAGS + 2))) + return -ENOSPC; + + /* sg may be required by async crypto */ + ovpn_skb_cb(skb)->sg = kmalloc(sizeof(*ovpn_skb_cb(skb)->sg) * + (nfrags + 2), GFP_ATOMIC); + if (unlikely(!ovpn_skb_cb(skb)->sg)) + return -ENOMEM; + + sg = ovpn_skb_cb(skb)->sg; + + /* sg table: + * 0: op, wire nonce (AD, len=OVPN_OPCODE_SIZE+OVPN_NONCE_WIRE_SIZE), + * 1, 2, 3, ..., n: payload, + * n+1: auth_tag (len=tag_size) + */ + sg_init_table(sg, nfrags + 2); + + /* packet op is head of additional data */ + sg_set_buf(sg, skb->data, OVPN_AAD_SIZE); + + /* build scatterlist to decrypt packet payload */ + ret = skb_to_sgvec_nomark(skb, sg + 1, payload_offset, payload_len); + if (unlikely(ret < 0)) { + netdev_err(peer->ovpn->dev, + "decrypt: cannot map skb to sg: %d\n", ret); + return ret; + } + + /* append auth_tag onto scatterlist */ + sg_set_buf(sg + ret + 1, skb->data + OVPN_AAD_SIZE, tag_size); + + /* iv may be required by async crypto */ + ovpn_skb_cb(skb)->iv = kmalloc(OVPN_NONCE_SIZE, GFP_ATOMIC); + if (unlikely(!ovpn_skb_cb(skb)->iv)) + return -ENOMEM; + + iv = ovpn_skb_cb(skb)->iv; + + /* copy nonce into IV buffer */ + memcpy(iv, skb->data + OVPN_OPCODE_SIZE, OVPN_NONCE_WIRE_SIZE); + memcpy(iv + OVPN_NONCE_WIRE_SIZE, ks->nonce_tail_recv, + OVPN_NONCE_TAIL_SIZE); + + req = aead_request_alloc(ks->decrypt, GFP_ATOMIC); + if (unlikely(!req)) + return -ENOMEM; + + ovpn_skb_cb(skb)->req = req; + + /* setup async crypto operation */ + aead_request_set_tfm(req, ks->decrypt); + aead_request_set_callback(req, 0, ovpn_decrypt_post, skb); + aead_request_set_crypt(req, sg, sg, payload_len + tag_size, iv); + + aead_request_set_ad(req, OVPN_AAD_SIZE); + + /* decrypt it */ + return crypto_aead_decrypt(req); +} + +/* Initialize a struct crypto_aead object */ +static struct crypto_aead *ovpn_aead_init(const char *title, + const char *alg_name, + const unsigned char *key, + unsigned int keylen) +{ + struct crypto_aead *aead; + int ret; + + aead = crypto_alloc_aead(alg_name, 0, 0); + if (IS_ERR(aead)) { + ret = PTR_ERR(aead); + pr_err("%s crypto_alloc_aead failed, err=%d\n", title, ret); + aead = NULL; + goto error; + } + + ret = crypto_aead_setkey(aead, key, keylen); + if (ret) { + pr_err("%s crypto_aead_setkey size=%u failed, err=%d\n", title, + keylen, ret); + goto error; + } + + ret = crypto_aead_setauthsize(aead, OVPN_AUTH_TAG_SIZE); + if (ret) { + pr_err("%s crypto_aead_setauthsize failed, err=%d\n", title, + ret); + goto error; + } + + /* basic AEAD assumption */ + if (crypto_aead_ivsize(aead) != OVPN_NONCE_SIZE) { + pr_err("%s IV size must be %d\n", title, OVPN_NONCE_SIZE); + ret = -EINVAL; + goto error; + } + + pr_debug("********* Cipher %s (%s)\n", alg_name, title); + pr_debug("*** IV size=%u\n", crypto_aead_ivsize(aead)); + pr_debug("*** req size=%u\n", crypto_aead_reqsize(aead)); + pr_debug("*** block size=%u\n", crypto_aead_blocksize(aead)); + pr_debug("*** auth size=%u\n", crypto_aead_authsize(aead)); + pr_debug("*** alignmask=0x%x\n", crypto_aead_alignmask(aead)); + + return aead; + +error: + crypto_free_aead(aead); + return ERR_PTR(ret); +} + +void ovpn_aead_crypto_key_slot_destroy(struct ovpn_crypto_key_slot *ks) +{ + if (!ks) + return; + + crypto_free_aead(ks->encrypt); + crypto_free_aead(ks->decrypt); + kfree(ks); +} + +struct ovpn_crypto_key_slot * +ovpn_aead_crypto_key_slot_new(const struct ovpn_key_config *kc) +{ + struct ovpn_crypto_key_slot *ks = NULL; + const char *alg_name; + int ret; + + /* validate crypto alg */ + switch (kc->cipher_alg) { + case OVPN_CIPHER_ALG_AES_GCM: + alg_name = ALG_NAME_AES; + break; + case OVPN_CIPHER_ALG_CHACHA20_POLY1305: + alg_name = ALG_NAME_CHACHAPOLY; + break; + default: + return ERR_PTR(-EOPNOTSUPP); + } + + if (kc->encrypt.nonce_tail_size != OVPN_NONCE_TAIL_SIZE || + kc->decrypt.nonce_tail_size != OVPN_NONCE_TAIL_SIZE) + return ERR_PTR(-EINVAL); + + /* build the key slot */ + ks = kmalloc(sizeof(*ks), GFP_KERNEL); + if (!ks) + return ERR_PTR(-ENOMEM); + + ks->encrypt = NULL; + ks->decrypt = NULL; + kref_init(&ks->refcount); + ks->key_id = kc->key_id; + + ks->encrypt = ovpn_aead_init("encrypt", alg_name, + kc->encrypt.cipher_key, + kc->encrypt.cipher_key_size); + if (IS_ERR(ks->encrypt)) { + ret = PTR_ERR(ks->encrypt); + ks->encrypt = NULL; + goto destroy_ks; + } + + ks->decrypt = ovpn_aead_init("decrypt", alg_name, + kc->decrypt.cipher_key, + kc->decrypt.cipher_key_size); + if (IS_ERR(ks->decrypt)) { + ret = PTR_ERR(ks->decrypt); + ks->decrypt = NULL; + goto destroy_ks; + } + + memcpy(ks->nonce_tail_xmit, kc->encrypt.nonce_tail, + OVPN_NONCE_TAIL_SIZE); + memcpy(ks->nonce_tail_recv, kc->decrypt.nonce_tail, + OVPN_NONCE_TAIL_SIZE); + + /* init packet ID generation/validation */ + ovpn_pktid_xmit_init(&ks->pid_xmit); + ovpn_pktid_recv_init(&ks->pid_recv); + + return ks; + +destroy_ks: + ovpn_aead_crypto_key_slot_destroy(ks); + return ERR_PTR(ret); +} + +enum ovpn_cipher_alg ovpn_aead_crypto_alg(struct ovpn_crypto_key_slot *ks) +{ + const char *alg_name; + + if (!ks->encrypt) + return OVPN_CIPHER_ALG_NONE; + + alg_name = crypto_tfm_alg_name(crypto_aead_tfm(ks->encrypt)); + + if (!strcmp(alg_name, ALG_NAME_AES)) + return OVPN_CIPHER_ALG_AES_GCM; + else if (!strcmp(alg_name, ALG_NAME_CHACHAPOLY)) + return OVPN_CIPHER_ALG_CHACHA20_POLY1305; + else + return OVPN_CIPHER_ALG_NONE; +} diff --git a/drivers/net/ovpn/crypto_aead.h b/drivers/net/ovpn/crypto_aead.h new file mode 100644 index 000000000000..65a2ff307898 --- /dev/null +++ b/drivers/net/ovpn/crypto_aead.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* OpenVPN data channel offload + * + * Copyright (C) 2020-2025 OpenVPN, Inc. + * + * Author: James Yonan <james@openvpn.net> + * Antonio Quartulli <antonio@openvpn.net> + */ + +#ifndef _NET_OVPN_OVPNAEAD_H_ +#define _NET_OVPN_OVPNAEAD_H_ + +#include "crypto.h" + +#include <asm/types.h> +#include <linux/skbuff.h> + +int ovpn_aead_encrypt(struct ovpn_peer *peer, struct ovpn_crypto_key_slot *ks, + struct sk_buff *skb); +int ovpn_aead_decrypt(struct ovpn_peer *peer, struct ovpn_crypto_key_slot *ks, + struct sk_buff *skb); + +struct ovpn_crypto_key_slot * +ovpn_aead_crypto_key_slot_new(const struct ovpn_key_config *kc); +void ovpn_aead_crypto_key_slot_destroy(struct ovpn_crypto_key_slot *ks); + +enum ovpn_cipher_alg ovpn_aead_crypto_alg(struct ovpn_crypto_key_slot *ks); + +#endif /* _NET_OVPN_OVPNAEAD_H_ */ diff --git a/drivers/net/ovpn/io.c b/drivers/net/ovpn/io.c new file mode 100644 index 000000000000..10d8afecec55 --- /dev/null +++ b/drivers/net/ovpn/io.c @@ -0,0 +1,458 @@ +// SPDX-License-Identifier: GPL-2.0 +/* OpenVPN data channel offload + * + * Copyright (C) 2019-2025 OpenVPN, Inc. + * + * Author: James Yonan <james@openvpn.net> + * Antonio Quartulli <antonio@openvpn.net> + */ + +#include <crypto/aead.h> +#include <linux/netdevice.h> +#include <linux/skbuff.h> +#include <net/gro_cells.h> +#include <net/gso.h> +#include <net/ip.h> + +#include "ovpnpriv.h" +#include "peer.h" +#include "io.h" +#include "bind.h" +#include "crypto.h" +#include "crypto_aead.h" +#include "netlink.h" +#include "proto.h" +#include "tcp.h" +#include "udp.h" +#include "skb.h" +#include "socket.h" + +const unsigned char ovpn_keepalive_message[OVPN_KEEPALIVE_SIZE] = { + 0x2a, 0x18, 0x7b, 0xf3, 0x64, 0x1e, 0xb4, 0xcb, + 0x07, 0xed, 0x2d, 0x0a, 0x98, 0x1f, 0xc7, 0x48 +}; + +/** + * ovpn_is_keepalive - check if skb contains a keepalive message + * @skb: packet to check + * + * Assumes that the first byte of skb->data is defined. + * + * Return: true if skb contains a keepalive or false otherwise + */ +static bool ovpn_is_keepalive(struct sk_buff *skb) +{ + if (*skb->data != ovpn_keepalive_message[0]) + return false; + + if (skb->len != OVPN_KEEPALIVE_SIZE) + return false; + + if (!pskb_may_pull(skb, OVPN_KEEPALIVE_SIZE)) + return false; + + return !memcmp(skb->data, ovpn_keepalive_message, OVPN_KEEPALIVE_SIZE); +} + +/* 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); + + /* network header reset in ovpn_decrypt_post() */ + 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 */ + ovpn_peer_stats_increment_rx(&peer->vpn_stats, pkt_len); + dev_dstats_rx_add(peer->ovpn->dev, pkt_len); + } +} + +void ovpn_decrypt_post(void *data, int ret) +{ + struct ovpn_crypto_key_slot *ks; + unsigned int payload_offset = 0; + struct sk_buff *skb = data; + struct ovpn_socket *sock; + struct ovpn_peer *peer; + __be16 proto; + __be32 *pid; + + /* crypto is happening asynchronously. this function will be called + * again later by the crypto callback with a proper return code + */ + if (unlikely(ret == -EINPROGRESS)) + return; + + payload_offset = ovpn_skb_cb(skb)->payload_offset; + ks = ovpn_skb_cb(skb)->ks; + peer = ovpn_skb_cb(skb)->peer; + + /* crypto is done, cleanup skb CB and its members */ + kfree(ovpn_skb_cb(skb)->iv); + kfree(ovpn_skb_cb(skb)->sg); + aead_request_free(ovpn_skb_cb(skb)->req); + + if (unlikely(ret < 0)) + goto drop; + + /* PID sits after the op */ + pid = (__force __be32 *)(skb->data + OVPN_OPCODE_SIZE); + ret = ovpn_pktid_recv(&ks->pid_recv, ntohl(*pid), 0); + if (unlikely(ret < 0)) { + net_err_ratelimited("%s: PKT ID RX error for peer %u: %d\n", + netdev_name(peer->ovpn->dev), peer->id, + ret); + goto drop; + } + + /* keep track of last received authenticated packet for keepalive */ + WRITE_ONCE(peer->last_recv, ktime_get_real_seconds()); + + rcu_read_lock(); + sock = rcu_dereference(peer->sock); + if (sock && sock->sock->sk->sk_protocol == IPPROTO_UDP) + /* check if this peer changed local or remote endpoint */ + ovpn_peer_endpoints_update(peer, skb); + rcu_read_unlock(); + + /* point to encapsulated IP packet */ + __skb_pull(skb, payload_offset); + + /* check if this is a valid datapacket that has to be delivered to the + * ovpn interface + */ + skb_reset_network_header(skb); + proto = ovpn_ip_check_protocol(skb); + if (unlikely(!proto)) { + /* check if null packet */ + if (unlikely(!pskb_may_pull(skb, 1))) { + net_info_ratelimited("%s: NULL packet received from peer %u\n", + netdev_name(peer->ovpn->dev), + peer->id); + goto drop; + } + + if (ovpn_is_keepalive(skb)) { + net_dbg_ratelimited("%s: ping received from peer %u\n", + netdev_name(peer->ovpn->dev), + peer->id); + /* we drop the packet, but this is not a failure */ + consume_skb(skb); + goto drop_nocount; + } + + net_info_ratelimited("%s: unsupported protocol received from peer %u\n", + netdev_name(peer->ovpn->dev), peer->id); + goto drop; + } + skb->protocol = proto; + + /* perform Reverse Path Filtering (RPF) */ + if (unlikely(!ovpn_peer_check_by_src(peer->ovpn, skb, peer))) { + if (skb->protocol == htons(ETH_P_IPV6)) + net_dbg_ratelimited("%s: RPF dropped packet from peer %u, src: %pI6c\n", + netdev_name(peer->ovpn->dev), + peer->id, &ipv6_hdr(skb)->saddr); + else + net_dbg_ratelimited("%s: RPF dropped packet from peer %u, src: %pI4\n", + netdev_name(peer->ovpn->dev), + peer->id, &ip_hdr(skb)->saddr); + goto drop; + } + + ovpn_netdev_write(peer, skb); + /* skb is passed to upper layer - don't free it */ + skb = NULL; +drop: + if (unlikely(skb)) + dev_dstats_rx_dropped(peer->ovpn->dev); + kfree_skb(skb); +drop_nocount: + if (likely(peer)) + ovpn_peer_put(peer); + if (likely(ks)) + ovpn_crypto_key_slot_put(ks); +} + +/* RX path entry point: decrypt packet and forward it to the device */ +void ovpn_recv(struct ovpn_peer *peer, struct sk_buff *skb) +{ + struct ovpn_crypto_key_slot *ks; + u8 key_id; + + ovpn_peer_stats_increment_rx(&peer->link_stats, skb->len); + + /* get the key slot matching the key ID in the received packet */ + key_id = ovpn_key_id_from_skb(skb); + ks = ovpn_crypto_key_id_to_slot(&peer->crypto, key_id); + if (unlikely(!ks)) { + net_info_ratelimited("%s: no available key for peer %u, key-id: %u\n", + netdev_name(peer->ovpn->dev), peer->id, + key_id); + dev_dstats_rx_dropped(peer->ovpn->dev); + kfree_skb(skb); + ovpn_peer_put(peer); + return; + } + + memset(ovpn_skb_cb(skb), 0, sizeof(struct ovpn_cb)); + ovpn_decrypt_post(skb, ovpn_aead_decrypt(peer, ks, skb)); +} + +void ovpn_encrypt_post(void *data, int ret) +{ + struct ovpn_crypto_key_slot *ks; + struct sk_buff *skb = data; + struct ovpn_socket *sock; + struct ovpn_peer *peer; + unsigned int orig_len; + + /* encryption is happening asynchronously. This function will be + * called later by the crypto callback with a proper return value + */ + if (unlikely(ret == -EINPROGRESS)) + return; + + ks = ovpn_skb_cb(skb)->ks; + peer = ovpn_skb_cb(skb)->peer; + + /* crypto is done, cleanup skb CB and its members */ + kfree(ovpn_skb_cb(skb)->iv); + kfree(ovpn_skb_cb(skb)->sg); + aead_request_free(ovpn_skb_cb(skb)->req); + + if (unlikely(ret == -ERANGE)) { + /* we ran out of IVs and we must kill the key as it can't be + * use anymore + */ + netdev_warn(peer->ovpn->dev, + "killing key %u for peer %u\n", ks->key_id, + peer->id); + if (ovpn_crypto_kill_key(&peer->crypto, ks->key_id)) + /* let userspace know so that a new key must be negotiated */ + ovpn_nl_key_swap_notify(peer, ks->key_id); + + goto err; + } + + if (unlikely(ret < 0)) + goto err; + + skb_mark_not_on_list(skb); + orig_len = skb->len; + + rcu_read_lock(); + sock = rcu_dereference(peer->sock); + if (unlikely(!sock)) + goto err_unlock; + + switch (sock->sock->sk->sk_protocol) { + case IPPROTO_UDP: + ovpn_udp_send_skb(peer, sock->sock, skb); + break; + case IPPROTO_TCP: + ovpn_tcp_send_skb(peer, sock->sock, skb); + break; + default: + /* no transport configured yet */ + goto err_unlock; + } + + ovpn_peer_stats_increment_tx(&peer->link_stats, orig_len); + /* keep track of last sent packet for keepalive */ + WRITE_ONCE(peer->last_sent, ktime_get_real_seconds()); + /* skb passed down the stack - don't free it */ + skb = NULL; +err_unlock: + rcu_read_unlock(); +err: + if (unlikely(skb)) + dev_dstats_tx_dropped(peer->ovpn->dev); + if (likely(peer)) + ovpn_peer_put(peer); + if (likely(ks)) + ovpn_crypto_key_slot_put(ks); + kfree_skb(skb); +} + +static bool ovpn_encrypt_one(struct ovpn_peer *peer, struct sk_buff *skb) +{ + struct ovpn_crypto_key_slot *ks; + + /* get primary key to be used for encrypting data */ + ks = ovpn_crypto_key_slot_primary(&peer->crypto); + if (unlikely(!ks)) + return false; + + /* take a reference to the peer because the crypto code may run async. + * ovpn_encrypt_post() will release it upon completion + */ + if (unlikely(!ovpn_peer_hold(peer))) { + DEBUG_NET_WARN_ON_ONCE(1); + ovpn_crypto_key_slot_put(ks); + return false; + } + + memset(ovpn_skb_cb(skb), 0, sizeof(struct ovpn_cb)); + ovpn_encrypt_post(skb, ovpn_aead_encrypt(peer, ks, skb)); + return true; +} + +/* send skb to connected peer, if any */ +static void ovpn_send(struct ovpn_priv *ovpn, struct sk_buff *skb, + struct ovpn_peer *peer) +{ + struct sk_buff *curr, *next; + + /* this might be a GSO-segmented skb list: process each skb + * independently + */ + skb_list_walk_safe(skb, curr, next) { + if (unlikely(!ovpn_encrypt_one(peer, curr))) { + dev_dstats_tx_dropped(ovpn->dev); + kfree_skb(curr); + } + } + + ovpn_peer_put(peer); +} + +/* Send user data to the network + */ +netdev_tx_t ovpn_net_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct ovpn_priv *ovpn = netdev_priv(dev); + struct sk_buff *segments, *curr, *next; + struct sk_buff_head skb_list; + struct ovpn_peer *peer; + __be16 proto; + int ret; + + /* reset netfilter state */ + nf_reset_ct(skb); + + /* verify IP header size in network packet */ + proto = ovpn_ip_check_protocol(skb); + if (unlikely(!proto || skb->protocol != proto)) + goto drop; + + if (skb_is_gso(skb)) { + segments = skb_gso_segment(skb, 0); + if (IS_ERR(segments)) { + ret = PTR_ERR(segments); + net_err_ratelimited("%s: cannot segment payload packet: %d\n", + netdev_name(dev), ret); + goto drop; + } + + consume_skb(skb); + skb = segments; + } + + /* from this moment on, "skb" might be a list */ + + __skb_queue_head_init(&skb_list); + skb_list_walk_safe(skb, curr, next) { + skb_mark_not_on_list(curr); + + curr = skb_share_check(curr, GFP_ATOMIC); + if (unlikely(!curr)) { + net_err_ratelimited("%s: skb_share_check failed for payload packet\n", + netdev_name(dev)); + dev_dstats_tx_dropped(ovpn->dev); + continue; + } + + __skb_queue_tail(&skb_list, curr); + } + skb_list.prev->next = NULL; + + /* retrieve peer serving the destination IP of this packet */ + peer = ovpn_peer_get_by_dst(ovpn, skb); + if (unlikely(!peer)) { + switch (skb->protocol) { + case htons(ETH_P_IP): + net_dbg_ratelimited("%s: no peer to send data to dst=%pI4\n", + netdev_name(ovpn->dev), + &ip_hdr(skb)->daddr); + break; + case htons(ETH_P_IPV6): + net_dbg_ratelimited("%s: no peer to send data to dst=%pI6c\n", + netdev_name(ovpn->dev), + &ipv6_hdr(skb)->daddr); + break; + } + goto drop; + } + /* dst was needed for peer selection - it can now be dropped */ + skb_dst_drop(skb); + + ovpn_peer_stats_increment_tx(&peer->vpn_stats, skb->len); + ovpn_send(ovpn, skb_list.next, peer); + + return NETDEV_TX_OK; + +drop: + dev_dstats_tx_dropped(ovpn->dev); + skb_tx_error(skb); + kfree_skb_list(skb); + return NETDEV_TX_OK; +} + +/** + * ovpn_xmit_special - encrypt and transmit an out-of-band message to peer + * @peer: peer to send the message to + * @data: message content + * @len: message length + * + * Assumes that caller holds a reference to peer, which will be + * passed to ovpn_send() + */ +void ovpn_xmit_special(struct ovpn_peer *peer, const void *data, + const unsigned int len) +{ + struct ovpn_priv *ovpn; + struct sk_buff *skb; + + ovpn = peer->ovpn; + if (unlikely(!ovpn)) { + ovpn_peer_put(peer); + return; + } + + skb = alloc_skb(256 + len, GFP_ATOMIC); + if (unlikely(!skb)) { + ovpn_peer_put(peer); + return; + } + + skb_reserve(skb, 128); + skb->priority = TC_PRIO_BESTEFFORT; + __skb_put_data(skb, data, len); + + ovpn_send(ovpn, skb, peer); +} diff --git a/drivers/net/ovpn/io.h b/drivers/net/ovpn/io.h new file mode 100644 index 000000000000..db9e10f9077c --- /dev/null +++ b/drivers/net/ovpn/io.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* OpenVPN data channel offload + * + * Copyright (C) 2019-2025 OpenVPN, Inc. + * + * Author: James Yonan <james@openvpn.net> + * Antonio Quartulli <antonio@openvpn.net> + */ + +#ifndef _NET_OVPN_OVPN_H_ +#define _NET_OVPN_OVPN_H_ + +/* DATA_V2 header size with AEAD encryption */ +#define OVPN_HEAD_ROOM (OVPN_OPCODE_SIZE + OVPN_NONCE_WIRE_SIZE + \ + 16 /* AEAD TAG length */ + \ + max(sizeof(struct udphdr), sizeof(struct tcphdr)) +\ + max(sizeof(struct ipv6hdr), sizeof(struct iphdr))) + +/* max padding required by encryption */ +#define OVPN_MAX_PADDING 16 + +#define OVPN_KEEPALIVE_SIZE 16 +extern const unsigned char ovpn_keepalive_message[OVPN_KEEPALIVE_SIZE]; + +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); +void ovpn_xmit_special(struct ovpn_peer *peer, const void *data, + const unsigned int len); + +void ovpn_encrypt_post(void *data, int ret); +void ovpn_decrypt_post(void *data, int ret); + +#endif /* _NET_OVPN_OVPN_H_ */ diff --git a/drivers/net/ovpn/main.c b/drivers/net/ovpn/main.c new file mode 100644 index 000000000000..1bb1afe766a4 --- /dev/null +++ b/drivers/net/ovpn/main.c @@ -0,0 +1,279 @@ +// SPDX-License-Identifier: GPL-2.0 +/* OpenVPN data channel offload + * + * Copyright (C) 2020-2025 OpenVPN, Inc. + * + * Author: Antonio Quartulli <antonio@openvpn.net> + * James Yonan <james@openvpn.net> + */ + +#include <linux/ethtool.h> +#include <linux/genetlink.h> +#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> + +#include "ovpnpriv.h" +#include "main.h" +#include "netlink.h" +#include "io.h" +#include "peer.h" +#include "proto.h" +#include "tcp.h" +#include "udp.h" + +static void ovpn_priv_free(struct net_device *net) +{ + struct ovpn_priv *ovpn = netdev_priv(net); + + kfree(ovpn->peers); +} + +static int ovpn_mp_alloc(struct ovpn_priv *ovpn) +{ + struct in_device *dev_v4; + int i; + + if (ovpn->mode != OVPN_MODE_MP) + return 0; + + dev_v4 = __in_dev_get_rtnl(ovpn->dev); + if (dev_v4) { + /* disable redirects as Linux gets confused by ovpn + * handling same-LAN routing. + * This happens because a multipeer interface is used as + * relay point between hosts in the same subnet, while + * in a classic LAN this would not be needed because the + * two hosts would be able to talk directly. + */ + IN_DEV_CONF_SET(dev_v4, SEND_REDIRECTS, false); + IPV4_DEVCONF_ALL(dev_net(ovpn->dev), SEND_REDIRECTS) = false; + } + + /* the peer container is fairly large, therefore we allocate it only in + * MP mode + */ + ovpn->peers = kzalloc(sizeof(*ovpn->peers), GFP_KERNEL); + if (!ovpn->peers) + return -ENOMEM; + + for (i = 0; i < ARRAY_SIZE(ovpn->peers->by_id); i++) { + INIT_HLIST_HEAD(&ovpn->peers->by_id[i]); + INIT_HLIST_NULLS_HEAD(&ovpn->peers->by_vpn_addr4[i], i); + INIT_HLIST_NULLS_HEAD(&ovpn->peers->by_vpn_addr6[i], i); + INIT_HLIST_NULLS_HEAD(&ovpn->peers->by_transp_addr[i], i); + } + + return 0; +} + +static int ovpn_net_init(struct net_device *dev) +{ + struct ovpn_priv *ovpn = netdev_priv(dev); + int err = gro_cells_init(&ovpn->gro_cells, dev); + + if (err < 0) + return err; + + err = ovpn_mp_alloc(ovpn); + if (err < 0) { + gro_cells_destroy(&ovpn->gro_cells); + return err; + } + + return 0; +} + +static void ovpn_net_uninit(struct net_device *dev) +{ + struct ovpn_priv *ovpn = netdev_priv(dev); + + gro_cells_destroy(&ovpn->gro_cells); +} + +static const struct net_device_ops ovpn_netdev_ops = { + .ndo_init = ovpn_net_init, + .ndo_uninit = ovpn_net_uninit, + .ndo_start_xmit = ovpn_net_xmit, +}; + +static const struct device_type ovpn_type = { + .name = OVPN_FAMILY_NAME, +}; + +static const struct nla_policy ovpn_policy[IFLA_OVPN_MAX + 1] = { + [IFLA_OVPN_MODE] = NLA_POLICY_RANGE(NLA_U8, OVPN_MODE_P2P, + OVPN_MODE_MP), +}; + +/** + * ovpn_dev_is_valid - check if the netdevice is of type 'ovpn' + * @dev: the interface to check + * + * Return: whether the netdevice is of type 'ovpn' + */ +bool ovpn_dev_is_valid(const struct net_device *dev) +{ + return dev->netdev_ops == &ovpn_netdev_ops; +} + +static void ovpn_get_drvinfo(struct net_device *dev, + struct ethtool_drvinfo *info) +{ + strscpy(info->driver, "ovpn", sizeof(info->driver)); + strscpy(info->bus_info, "ovpn", sizeof(info->bus_info)); +} + +static const struct ethtool_ops ovpn_ethtool_ops = { + .get_drvinfo = ovpn_get_drvinfo, + .get_link = ethtool_op_get_link, + .get_ts_info = ethtool_op_get_ts_info, +}; + +static void ovpn_setup(struct net_device *dev) +{ + netdev_features_t feat = NETIF_F_SG | NETIF_F_GSO | + NETIF_F_GSO_SOFTWARE | NETIF_F_HIGHDMA; + + dev->needs_free_netdev = true; + + dev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS; + + dev->ethtool_ops = &ovpn_ethtool_ops; + dev->netdev_ops = &ovpn_netdev_ops; + + dev->priv_destructor = ovpn_priv_free; + + dev->hard_header_len = 0; + dev->addr_len = 0; + dev->mtu = ETH_DATA_LEN - OVPN_HEAD_ROOM; + dev->min_mtu = IPV4_MIN_MTU; + dev->max_mtu = IP_MAX_MTU - OVPN_HEAD_ROOM; + + dev->type = ARPHRD_NONE; + dev->flags = IFF_POINTOPOINT | IFF_NOARP; + dev->priv_flags |= IFF_NO_QUEUE; + /* when routing packets to a LAN behind a client, we rely on the + * route entry that originally brought the packet into ovpn, so + * don't release it + */ + netif_keep_dst(dev); + + dev->lltx = true; + dev->features |= feat; + dev->hw_features |= feat; + dev->hw_enc_features |= feat; + + dev->needed_headroom = ALIGN(OVPN_HEAD_ROOM, 4); + dev->needed_tailroom = OVPN_MAX_PADDING; + + SET_NETDEV_DEVTYPE(dev, &ovpn_type); +} + +static int ovpn_newlink(struct net_device *dev, + struct rtnl_newlink_params *params, + struct netlink_ext_ack *extack) +{ + struct ovpn_priv *ovpn = netdev_priv(dev); + struct nlattr **data = params->data; + enum ovpn_mode mode = OVPN_MODE_P2P; + + if (data && data[IFLA_OVPN_MODE]) { + mode = nla_get_u8(data[IFLA_OVPN_MODE]); + netdev_dbg(dev, "setting device mode: %u\n", mode); + } + + ovpn->dev = dev; + ovpn->mode = mode; + spin_lock_init(&ovpn->lock); + INIT_DELAYED_WORK(&ovpn->keepalive_work, ovpn_peer_keepalive_work); + + /* Set carrier explicitly after registration, this way state is + * clearly defined. + * + * In case of MP interfaces we keep the carrier always on. + * + * Carrier for P2P interfaces is initially off and it is then + * switched on and off when the remote peer is added or deleted. + */ + if (ovpn->mode == OVPN_MODE_MP) + netif_carrier_on(dev); + else + netif_carrier_off(dev); + + return register_netdevice(dev); +} + +static void ovpn_dellink(struct net_device *dev, struct list_head *head) +{ + struct ovpn_priv *ovpn = netdev_priv(dev); + + cancel_delayed_work_sync(&ovpn->keepalive_work); + ovpn_peers_free(ovpn, NULL, OVPN_DEL_PEER_REASON_TEARDOWN); + unregister_netdevice_queue(dev, head); +} + +static int ovpn_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct ovpn_priv *ovpn = netdev_priv(dev); + + if (nla_put_u8(skb, IFLA_OVPN_MODE, ovpn->mode)) + return -EMSGSIZE; + + return 0; +} + +static struct rtnl_link_ops ovpn_link_ops = { + .kind = "ovpn", + .netns_refund = false, + .priv_size = sizeof(struct ovpn_priv), + .setup = ovpn_setup, + .policy = ovpn_policy, + .maxtype = IFLA_OVPN_MAX, + .newlink = ovpn_newlink, + .dellink = ovpn_dellink, + .fill_info = ovpn_fill_info, +}; + +static int __init ovpn_init(void) +{ + int err = rtnl_link_register(&ovpn_link_ops); + + if (err) { + pr_err("ovpn: can't register rtnl link ops: %d\n", err); + return err; + } + + err = ovpn_nl_register(); + if (err) { + pr_err("ovpn: can't register netlink family: %d\n", err); + goto unreg_rtnl; + } + + ovpn_tcp_init(); + + return 0; + +unreg_rtnl: + rtnl_link_unregister(&ovpn_link_ops); + return err; +} + +static __exit void ovpn_cleanup(void) +{ + ovpn_nl_unregister(); + rtnl_link_unregister(&ovpn_link_ops); + + rcu_barrier(); +} + +module_init(ovpn_init); +module_exit(ovpn_cleanup); + +MODULE_DESCRIPTION("OpenVPN data channel offload (ovpn)"); +MODULE_AUTHOR("Antonio Quartulli <antonio@openvpn.net>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ovpn/main.h b/drivers/net/ovpn/main.h new file mode 100644 index 000000000000..017cd0100765 --- /dev/null +++ b/drivers/net/ovpn/main.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* OpenVPN data channel offload + * + * Copyright (C) 2020-2025 OpenVPN, Inc. + * + * Author: Antonio Quartulli <antonio@openvpn.net> + */ + +#ifndef _NET_OVPN_MAIN_H_ +#define _NET_OVPN_MAIN_H_ + +bool ovpn_dev_is_valid(const struct net_device *dev); + +#endif /* _NET_OVPN_MAIN_H_ */ diff --git a/drivers/net/ovpn/netlink-gen.c b/drivers/net/ovpn/netlink-gen.c new file mode 100644 index 000000000000..58e1a4342378 --- /dev/null +++ b/drivers/net/ovpn/netlink-gen.c @@ -0,0 +1,213 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/ovpn.yaml */ +/* YNL-GEN kernel source */ + +#include <net/netlink.h> +#include <net/genetlink.h> + +#include "netlink-gen.h" + +#include <uapi/linux/ovpn.h> + +/* Integer value ranges */ +static const struct netlink_range_validation ovpn_a_peer_id_range = { + .max = 16777215ULL, +}; + +static const struct netlink_range_validation ovpn_a_keyconf_peer_id_range = { + .max = 16777215ULL, +}; + +/* Common nested types */ +const struct nla_policy ovpn_keyconf_nl_policy[OVPN_A_KEYCONF_DECRYPT_DIR + 1] = { + [OVPN_A_KEYCONF_PEER_ID] = NLA_POLICY_FULL_RANGE(NLA_U32, &ovpn_a_keyconf_peer_id_range), + [OVPN_A_KEYCONF_SLOT] = NLA_POLICY_MAX(NLA_U32, 1), + [OVPN_A_KEYCONF_KEY_ID] = NLA_POLICY_MAX(NLA_U32, 7), + [OVPN_A_KEYCONF_CIPHER_ALG] = NLA_POLICY_MAX(NLA_U32, 2), + [OVPN_A_KEYCONF_ENCRYPT_DIR] = NLA_POLICY_NESTED(ovpn_keydir_nl_policy), + [OVPN_A_KEYCONF_DECRYPT_DIR] = NLA_POLICY_NESTED(ovpn_keydir_nl_policy), +}; + +const struct nla_policy ovpn_keydir_nl_policy[OVPN_A_KEYDIR_NONCE_TAIL + 1] = { + [OVPN_A_KEYDIR_CIPHER_KEY] = NLA_POLICY_MAX_LEN(256), + [OVPN_A_KEYDIR_NONCE_TAIL] = NLA_POLICY_EXACT_LEN(OVPN_NONCE_TAIL_SIZE), +}; + +const struct nla_policy ovpn_peer_nl_policy[OVPN_A_PEER_LINK_TX_PACKETS + 1] = { + [OVPN_A_PEER_ID] = NLA_POLICY_FULL_RANGE(NLA_U32, &ovpn_a_peer_id_range), + [OVPN_A_PEER_REMOTE_IPV4] = { .type = NLA_BE32, }, + [OVPN_A_PEER_REMOTE_IPV6] = NLA_POLICY_EXACT_LEN(16), + [OVPN_A_PEER_REMOTE_IPV6_SCOPE_ID] = { .type = NLA_U32, }, + [OVPN_A_PEER_REMOTE_PORT] = NLA_POLICY_MIN(NLA_BE16, 1), + [OVPN_A_PEER_SOCKET] = { .type = NLA_U32, }, + [OVPN_A_PEER_SOCKET_NETNSID] = { .type = NLA_S32, }, + [OVPN_A_PEER_VPN_IPV4] = { .type = NLA_BE32, }, + [OVPN_A_PEER_VPN_IPV6] = NLA_POLICY_EXACT_LEN(16), + [OVPN_A_PEER_LOCAL_IPV4] = { .type = NLA_BE32, }, + [OVPN_A_PEER_LOCAL_IPV6] = NLA_POLICY_EXACT_LEN(16), + [OVPN_A_PEER_LOCAL_PORT] = NLA_POLICY_MIN(NLA_BE16, 1), + [OVPN_A_PEER_KEEPALIVE_INTERVAL] = { .type = NLA_U32, }, + [OVPN_A_PEER_KEEPALIVE_TIMEOUT] = { .type = NLA_U32, }, + [OVPN_A_PEER_DEL_REASON] = NLA_POLICY_MAX(NLA_U32, 4), + [OVPN_A_PEER_VPN_RX_BYTES] = { .type = NLA_UINT, }, + [OVPN_A_PEER_VPN_TX_BYTES] = { .type = NLA_UINT, }, + [OVPN_A_PEER_VPN_RX_PACKETS] = { .type = NLA_UINT, }, + [OVPN_A_PEER_VPN_TX_PACKETS] = { .type = NLA_UINT, }, + [OVPN_A_PEER_LINK_RX_BYTES] = { .type = NLA_UINT, }, + [OVPN_A_PEER_LINK_TX_BYTES] = { .type = NLA_UINT, }, + [OVPN_A_PEER_LINK_RX_PACKETS] = { .type = NLA_UINT, }, + [OVPN_A_PEER_LINK_TX_PACKETS] = { .type = NLA_UINT, }, +}; + +/* OVPN_CMD_PEER_NEW - do */ +static const struct nla_policy ovpn_peer_new_nl_policy[OVPN_A_PEER + 1] = { + [OVPN_A_IFINDEX] = { .type = NLA_U32, }, + [OVPN_A_PEER] = NLA_POLICY_NESTED(ovpn_peer_nl_policy), +}; + +/* OVPN_CMD_PEER_SET - do */ +static const struct nla_policy ovpn_peer_set_nl_policy[OVPN_A_PEER + 1] = { + [OVPN_A_IFINDEX] = { .type = NLA_U32, }, + [OVPN_A_PEER] = NLA_POLICY_NESTED(ovpn_peer_nl_policy), +}; + +/* OVPN_CMD_PEER_GET - do */ +static const struct nla_policy ovpn_peer_get_do_nl_policy[OVPN_A_PEER + 1] = { + [OVPN_A_IFINDEX] = { .type = NLA_U32, }, + [OVPN_A_PEER] = NLA_POLICY_NESTED(ovpn_peer_nl_policy), +}; + +/* OVPN_CMD_PEER_GET - dump */ +static const struct nla_policy ovpn_peer_get_dump_nl_policy[OVPN_A_IFINDEX + 1] = { + [OVPN_A_IFINDEX] = { .type = NLA_U32, }, +}; + +/* OVPN_CMD_PEER_DEL - do */ +static const struct nla_policy ovpn_peer_del_nl_policy[OVPN_A_PEER + 1] = { + [OVPN_A_IFINDEX] = { .type = NLA_U32, }, + [OVPN_A_PEER] = NLA_POLICY_NESTED(ovpn_peer_nl_policy), +}; + +/* OVPN_CMD_KEY_NEW - do */ +static const struct nla_policy ovpn_key_new_nl_policy[OVPN_A_KEYCONF + 1] = { + [OVPN_A_IFINDEX] = { .type = NLA_U32, }, + [OVPN_A_KEYCONF] = NLA_POLICY_NESTED(ovpn_keyconf_nl_policy), +}; + +/* OVPN_CMD_KEY_GET - do */ +static const struct nla_policy ovpn_key_get_nl_policy[OVPN_A_KEYCONF + 1] = { + [OVPN_A_IFINDEX] = { .type = NLA_U32, }, + [OVPN_A_KEYCONF] = NLA_POLICY_NESTED(ovpn_keyconf_nl_policy), +}; + +/* OVPN_CMD_KEY_SWAP - do */ +static const struct nla_policy ovpn_key_swap_nl_policy[OVPN_A_KEYCONF + 1] = { + [OVPN_A_IFINDEX] = { .type = NLA_U32, }, + [OVPN_A_KEYCONF] = NLA_POLICY_NESTED(ovpn_keyconf_nl_policy), +}; + +/* OVPN_CMD_KEY_DEL - do */ +static const struct nla_policy ovpn_key_del_nl_policy[OVPN_A_KEYCONF + 1] = { + [OVPN_A_IFINDEX] = { .type = NLA_U32, }, + [OVPN_A_KEYCONF] = NLA_POLICY_NESTED(ovpn_keyconf_nl_policy), +}; + +/* Ops table for ovpn */ +static const struct genl_split_ops ovpn_nl_ops[] = { + { + .cmd = OVPN_CMD_PEER_NEW, + .pre_doit = ovpn_nl_pre_doit, + .doit = ovpn_nl_peer_new_doit, + .post_doit = ovpn_nl_post_doit, + .policy = ovpn_peer_new_nl_policy, + .maxattr = OVPN_A_PEER, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = OVPN_CMD_PEER_SET, + .pre_doit = ovpn_nl_pre_doit, + .doit = ovpn_nl_peer_set_doit, + .post_doit = ovpn_nl_post_doit, + .policy = ovpn_peer_set_nl_policy, + .maxattr = OVPN_A_PEER, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = OVPN_CMD_PEER_GET, + .pre_doit = ovpn_nl_pre_doit, + .doit = ovpn_nl_peer_get_doit, + .post_doit = ovpn_nl_post_doit, + .policy = ovpn_peer_get_do_nl_policy, + .maxattr = OVPN_A_PEER, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = OVPN_CMD_PEER_GET, + .dumpit = ovpn_nl_peer_get_dumpit, + .policy = ovpn_peer_get_dump_nl_policy, + .maxattr = OVPN_A_IFINDEX, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP, + }, + { + .cmd = OVPN_CMD_PEER_DEL, + .pre_doit = ovpn_nl_pre_doit, + .doit = ovpn_nl_peer_del_doit, + .post_doit = ovpn_nl_post_doit, + .policy = ovpn_peer_del_nl_policy, + .maxattr = OVPN_A_PEER, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = OVPN_CMD_KEY_NEW, + .pre_doit = ovpn_nl_pre_doit, + .doit = ovpn_nl_key_new_doit, + .post_doit = ovpn_nl_post_doit, + .policy = ovpn_key_new_nl_policy, + .maxattr = OVPN_A_KEYCONF, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = OVPN_CMD_KEY_GET, + .pre_doit = ovpn_nl_pre_doit, + .doit = ovpn_nl_key_get_doit, + .post_doit = ovpn_nl_post_doit, + .policy = ovpn_key_get_nl_policy, + .maxattr = OVPN_A_KEYCONF, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = OVPN_CMD_KEY_SWAP, + .pre_doit = ovpn_nl_pre_doit, + .doit = ovpn_nl_key_swap_doit, + .post_doit = ovpn_nl_post_doit, + .policy = ovpn_key_swap_nl_policy, + .maxattr = OVPN_A_KEYCONF, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = OVPN_CMD_KEY_DEL, + .pre_doit = ovpn_nl_pre_doit, + .doit = ovpn_nl_key_del_doit, + .post_doit = ovpn_nl_post_doit, + .policy = ovpn_key_del_nl_policy, + .maxattr = OVPN_A_KEYCONF, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, +}; + +static const struct genl_multicast_group ovpn_nl_mcgrps[] = { + [OVPN_NLGRP_PEERS] = { "peers", }, +}; + +struct genl_family ovpn_nl_family __ro_after_init = { + .name = OVPN_FAMILY_NAME, + .version = OVPN_FAMILY_VERSION, + .netnsok = true, + .parallel_ops = true, + .module = THIS_MODULE, + .split_ops = ovpn_nl_ops, + .n_split_ops = ARRAY_SIZE(ovpn_nl_ops), + .mcgrps = ovpn_nl_mcgrps, + .n_mcgrps = ARRAY_SIZE(ovpn_nl_mcgrps), +}; diff --git a/drivers/net/ovpn/netlink-gen.h b/drivers/net/ovpn/netlink-gen.h new file mode 100644 index 000000000000..66a4e4a0a055 --- /dev/null +++ b/drivers/net/ovpn/netlink-gen.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/ovpn.yaml */ +/* YNL-GEN kernel header */ + +#ifndef _LINUX_OVPN_GEN_H +#define _LINUX_OVPN_GEN_H + +#include <net/netlink.h> +#include <net/genetlink.h> + +#include <uapi/linux/ovpn.h> + +/* Common nested types */ +extern const struct nla_policy ovpn_keyconf_nl_policy[OVPN_A_KEYCONF_DECRYPT_DIR + 1]; +extern const struct nla_policy ovpn_keydir_nl_policy[OVPN_A_KEYDIR_NONCE_TAIL + 1]; +extern const struct nla_policy ovpn_peer_nl_policy[OVPN_A_PEER_LINK_TX_PACKETS + 1]; + +int ovpn_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb, + struct genl_info *info); +void +ovpn_nl_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb, + struct genl_info *info); + +int ovpn_nl_peer_new_doit(struct sk_buff *skb, struct genl_info *info); +int ovpn_nl_peer_set_doit(struct sk_buff *skb, struct genl_info *info); +int ovpn_nl_peer_get_doit(struct sk_buff *skb, struct genl_info *info); +int ovpn_nl_peer_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int ovpn_nl_peer_del_doit(struct sk_buff *skb, struct genl_info *info); +int ovpn_nl_key_new_doit(struct sk_buff *skb, struct genl_info *info); +int ovpn_nl_key_get_doit(struct sk_buff *skb, struct genl_info *info); +int ovpn_nl_key_swap_doit(struct sk_buff *skb, struct genl_info *info); +int ovpn_nl_key_del_doit(struct sk_buff *skb, struct genl_info *info); + +enum { + OVPN_NLGRP_PEERS, +}; + +extern struct genl_family ovpn_nl_family; + +#endif /* _LINUX_OVPN_GEN_H */ diff --git a/drivers/net/ovpn/netlink.c b/drivers/net/ovpn/netlink.c new file mode 100644 index 000000000000..bea03913bfb1 --- /dev/null +++ b/drivers/net/ovpn/netlink.c @@ -0,0 +1,1258 @@ +// SPDX-License-Identifier: GPL-2.0 +/* OpenVPN data channel offload + * + * Copyright (C) 2020-2025 OpenVPN, Inc. + * + * Author: Antonio Quartulli <antonio@openvpn.net> + */ + +#include <linux/netdevice.h> +#include <linux/types.h> +#include <net/genetlink.h> + +#include <uapi/linux/ovpn.h> + +#include "ovpnpriv.h" +#include "main.h" +#include "netlink.h" +#include "netlink-gen.h" +#include "bind.h" +#include "crypto.h" +#include "peer.h" +#include "socket.h" + +MODULE_ALIAS_GENL_FAMILY(OVPN_FAMILY_NAME); + +/** + * ovpn_get_dev_from_attrs - retrieve the ovpn private data from the netdevice + * a netlink message is targeting + * @net: network namespace where to look for the interface + * @info: generic netlink info from the user request + * @tracker: tracker object to be used for the netdev reference acquisition + * + * Return: the ovpn private data, if found, or an error otherwise + */ +static struct ovpn_priv * +ovpn_get_dev_from_attrs(struct net *net, const struct genl_info *info, + netdevice_tracker *tracker) +{ + struct ovpn_priv *ovpn; + struct net_device *dev; + int ifindex; + + if (GENL_REQ_ATTR_CHECK(info, OVPN_A_IFINDEX)) + return ERR_PTR(-EINVAL); + + ifindex = nla_get_u32(info->attrs[OVPN_A_IFINDEX]); + + rcu_read_lock(); + dev = dev_get_by_index_rcu(net, ifindex); + if (!dev) { + rcu_read_unlock(); + NL_SET_ERR_MSG_MOD(info->extack, + "ifindex does not match any interface"); + return ERR_PTR(-ENODEV); + } + + if (!ovpn_dev_is_valid(dev)) { + rcu_read_unlock(); + NL_SET_ERR_MSG_MOD(info->extack, + "specified interface is not ovpn"); + NL_SET_BAD_ATTR(info->extack, info->attrs[OVPN_A_IFINDEX]); + return ERR_PTR(-EINVAL); + } + + ovpn = netdev_priv(dev); + netdev_hold(dev, tracker, GFP_ATOMIC); + rcu_read_unlock(); + + return ovpn; +} + +int ovpn_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb, + struct genl_info *info) +{ + netdevice_tracker *tracker = (netdevice_tracker *)&info->user_ptr[1]; + struct ovpn_priv *ovpn = ovpn_get_dev_from_attrs(genl_info_net(info), + info, tracker); + + if (IS_ERR(ovpn)) + return PTR_ERR(ovpn); + + info->user_ptr[0] = ovpn; + + return 0; +} + +void ovpn_nl_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb, + struct genl_info *info) +{ + netdevice_tracker *tracker = (netdevice_tracker *)&info->user_ptr[1]; + struct ovpn_priv *ovpn = info->user_ptr[0]; + + if (ovpn) + netdev_put(ovpn->dev, tracker); +} + +static bool ovpn_nl_attr_sockaddr_remote(struct nlattr **attrs, + struct sockaddr_storage *ss) +{ + struct sockaddr_in6 *sin6; + struct sockaddr_in *sin; + struct in6_addr *in6; + __be16 port = 0; + __be32 *in; + + ss->ss_family = AF_UNSPEC; + + if (attrs[OVPN_A_PEER_REMOTE_PORT]) + port = nla_get_be16(attrs[OVPN_A_PEER_REMOTE_PORT]); + + if (attrs[OVPN_A_PEER_REMOTE_IPV4]) { + ss->ss_family = AF_INET; + in = nla_data(attrs[OVPN_A_PEER_REMOTE_IPV4]); + } else if (attrs[OVPN_A_PEER_REMOTE_IPV6]) { + ss->ss_family = AF_INET6; + in6 = nla_data(attrs[OVPN_A_PEER_REMOTE_IPV6]); + } else { + return false; + } + + switch (ss->ss_family) { + case AF_INET6: + /* If this is a regular IPv6 just break and move on, + * otherwise switch to AF_INET and extract the IPv4 accordingly + */ + if (!ipv6_addr_v4mapped(in6)) { + sin6 = (struct sockaddr_in6 *)ss; + sin6->sin6_port = port; + memcpy(&sin6->sin6_addr, in6, sizeof(*in6)); + break; + } + + /* v4-mapped-v6 address */ + ss->ss_family = AF_INET; + in = &in6->s6_addr32[3]; + fallthrough; + case AF_INET: + sin = (struct sockaddr_in *)ss; + sin->sin_port = port; + sin->sin_addr.s_addr = *in; + break; + } + + return true; +} + +static u8 *ovpn_nl_attr_local_ip(struct nlattr **attrs) +{ + u8 *addr6; + + if (!attrs[OVPN_A_PEER_LOCAL_IPV4] && !attrs[OVPN_A_PEER_LOCAL_IPV6]) + return NULL; + + if (attrs[OVPN_A_PEER_LOCAL_IPV4]) + return nla_data(attrs[OVPN_A_PEER_LOCAL_IPV4]); + + addr6 = nla_data(attrs[OVPN_A_PEER_LOCAL_IPV6]); + /* this is an IPv4-mapped IPv6 address, therefore extract the actual + * v4 address from the last 4 bytes + */ + if (ipv6_addr_v4mapped((struct in6_addr *)addr6)) + return addr6 + 12; + + return addr6; +} + +static sa_family_t ovpn_nl_family_get(struct nlattr *addr4, + struct nlattr *addr6) +{ + if (addr4) + return AF_INET; + + if (addr6) { + if (ipv6_addr_v4mapped((struct in6_addr *)nla_data(addr6))) + return AF_INET; + return AF_INET6; + } + + return AF_UNSPEC; +} + +static int ovpn_nl_peer_precheck(struct ovpn_priv *ovpn, + struct genl_info *info, + struct nlattr **attrs) +{ + sa_family_t local_fam, remote_fam; + + if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_PEER], attrs, + OVPN_A_PEER_ID)) + return -EINVAL; + + if (attrs[OVPN_A_PEER_REMOTE_IPV4] && attrs[OVPN_A_PEER_REMOTE_IPV6]) { + NL_SET_ERR_MSG_MOD(info->extack, + "cannot specify both remote IPv4 or IPv6 address"); + return -EINVAL; + } + + if (!attrs[OVPN_A_PEER_REMOTE_IPV4] && + !attrs[OVPN_A_PEER_REMOTE_IPV6] && attrs[OVPN_A_PEER_REMOTE_PORT]) { + NL_SET_ERR_MSG_MOD(info->extack, + "cannot specify remote port without IP address"); + return -EINVAL; + } + + if ((attrs[OVPN_A_PEER_REMOTE_IPV4] || + attrs[OVPN_A_PEER_REMOTE_IPV6]) && + !attrs[OVPN_A_PEER_REMOTE_PORT]) { + NL_SET_ERR_MSG_MOD(info->extack, + "cannot specify remote IP address without port"); + return -EINVAL; + } + + if (!attrs[OVPN_A_PEER_REMOTE_IPV4] && + attrs[OVPN_A_PEER_LOCAL_IPV4]) { + NL_SET_ERR_MSG_MOD(info->extack, + "cannot specify local IPv4 address without remote"); + return -EINVAL; + } + + if (!attrs[OVPN_A_PEER_REMOTE_IPV6] && + attrs[OVPN_A_PEER_LOCAL_IPV6]) { + NL_SET_ERR_MSG_MOD(info->extack, + "cannot specify local IPV6 address without remote"); + return -EINVAL; + } + + /* check that local and remote address families are the same even + * after parsing v4mapped IPv6 addresses. + * (if addresses are not provided, family will be AF_UNSPEC and + * the check is skipped) + */ + local_fam = ovpn_nl_family_get(attrs[OVPN_A_PEER_LOCAL_IPV4], + attrs[OVPN_A_PEER_LOCAL_IPV6]); + remote_fam = ovpn_nl_family_get(attrs[OVPN_A_PEER_REMOTE_IPV4], + attrs[OVPN_A_PEER_REMOTE_IPV6]); + if (local_fam != AF_UNSPEC && remote_fam != AF_UNSPEC && + local_fam != remote_fam) { + NL_SET_ERR_MSG_MOD(info->extack, + "mismatching local and remote address families"); + return -EINVAL; + } + + if (remote_fam != AF_INET6 && attrs[OVPN_A_PEER_REMOTE_IPV6_SCOPE_ID]) { + NL_SET_ERR_MSG_MOD(info->extack, + "cannot specify scope id without remote IPv6 address"); + return -EINVAL; + } + + /* VPN IPs are needed only in MP mode for selecting the right peer */ + if (ovpn->mode == OVPN_MODE_P2P && (attrs[OVPN_A_PEER_VPN_IPV4] || + attrs[OVPN_A_PEER_VPN_IPV6])) { + NL_SET_ERR_MSG_FMT_MOD(info->extack, + "unexpected VPN IP in P2P mode"); + return -EINVAL; + } + + if ((attrs[OVPN_A_PEER_KEEPALIVE_INTERVAL] && + !attrs[OVPN_A_PEER_KEEPALIVE_TIMEOUT]) || + (!attrs[OVPN_A_PEER_KEEPALIVE_INTERVAL] && + attrs[OVPN_A_PEER_KEEPALIVE_TIMEOUT])) { + NL_SET_ERR_MSG_FMT_MOD(info->extack, + "keepalive interval and timeout are required together"); + return -EINVAL; + } + + return 0; +} + +/** + * ovpn_nl_peer_modify - modify the peer attributes according to the incoming msg + * @peer: the peer to modify + * @info: generic netlink info from the user request + * @attrs: the attributes from the user request + * + * Return: a negative error code in case of failure, 0 on success or 1 on + * success and the VPN IPs have been modified (requires rehashing in MP + * mode) + */ +static int ovpn_nl_peer_modify(struct ovpn_peer *peer, struct genl_info *info, + struct nlattr **attrs) +{ + struct sockaddr_storage ss = {}; + void *local_ip = NULL; + u32 interv, timeout; + bool rehash = false; + int ret; + + spin_lock_bh(&peer->lock); + + if (ovpn_nl_attr_sockaddr_remote(attrs, &ss)) { + /* we carry the local IP in a generic container. + * ovpn_peer_reset_sockaddr() will properly interpret it + * based on ss.ss_family + */ + local_ip = ovpn_nl_attr_local_ip(attrs); + + /* set peer sockaddr */ + ret = ovpn_peer_reset_sockaddr(peer, &ss, local_ip); + if (ret < 0) { + NL_SET_ERR_MSG_FMT_MOD(info->extack, + "cannot set peer sockaddr: %d", + ret); + goto err_unlock; + } + dst_cache_reset(&peer->dst_cache); + } + + if (attrs[OVPN_A_PEER_VPN_IPV4]) { + rehash = true; + peer->vpn_addrs.ipv4.s_addr = + nla_get_in_addr(attrs[OVPN_A_PEER_VPN_IPV4]); + } + + if (attrs[OVPN_A_PEER_VPN_IPV6]) { + rehash = true; + peer->vpn_addrs.ipv6 = + nla_get_in6_addr(attrs[OVPN_A_PEER_VPN_IPV6]); + } + + /* when setting the keepalive, both parameters have to be configured */ + if (attrs[OVPN_A_PEER_KEEPALIVE_INTERVAL] && + attrs[OVPN_A_PEER_KEEPALIVE_TIMEOUT]) { + interv = nla_get_u32(attrs[OVPN_A_PEER_KEEPALIVE_INTERVAL]); + timeout = nla_get_u32(attrs[OVPN_A_PEER_KEEPALIVE_TIMEOUT]); + ovpn_peer_keepalive_set(peer, interv, timeout); + } + + netdev_dbg(peer->ovpn->dev, + "modify peer id=%u endpoint=%pIScp VPN-IPv4=%pI4 VPN-IPv6=%pI6c\n", + peer->id, &ss, + &peer->vpn_addrs.ipv4.s_addr, &peer->vpn_addrs.ipv6); + + spin_unlock_bh(&peer->lock); + + return rehash ? 1 : 0; +err_unlock: + spin_unlock_bh(&peer->lock); + return ret; +} + +int ovpn_nl_peer_new_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *attrs[OVPN_A_PEER_MAX + 1]; + struct ovpn_priv *ovpn = info->user_ptr[0]; + struct ovpn_socket *ovpn_sock; + struct socket *sock = NULL; + struct ovpn_peer *peer; + u32 sockfd, peer_id; + int ret; + + if (GENL_REQ_ATTR_CHECK(info, OVPN_A_PEER)) + return -EINVAL; + + ret = nla_parse_nested(attrs, OVPN_A_PEER_MAX, info->attrs[OVPN_A_PEER], + ovpn_peer_nl_policy, info->extack); + if (ret) + return ret; + + ret = ovpn_nl_peer_precheck(ovpn, info, attrs); + if (ret < 0) + return ret; + + if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_PEER], attrs, + OVPN_A_PEER_SOCKET)) + return -EINVAL; + + /* in MP mode VPN IPs are required for selecting the right peer */ + if (ovpn->mode == OVPN_MODE_MP && !attrs[OVPN_A_PEER_VPN_IPV4] && + !attrs[OVPN_A_PEER_VPN_IPV6]) { + NL_SET_ERR_MSG_FMT_MOD(info->extack, + "VPN IP must be provided in MP mode"); + return -EINVAL; + } + + peer_id = nla_get_u32(attrs[OVPN_A_PEER_ID]); + peer = ovpn_peer_new(ovpn, peer_id); + if (IS_ERR(peer)) { + NL_SET_ERR_MSG_FMT_MOD(info->extack, + "cannot create new peer object for peer %u: %ld", + peer_id, PTR_ERR(peer)); + return PTR_ERR(peer); + } + + /* lookup the fd in the kernel table and extract the socket object */ + sockfd = nla_get_u32(attrs[OVPN_A_PEER_SOCKET]); + /* sockfd_lookup() increases sock's refcounter */ + sock = sockfd_lookup(sockfd, &ret); + if (!sock) { + NL_SET_ERR_MSG_FMT_MOD(info->extack, + "cannot lookup peer socket (fd=%u): %d", + sockfd, ret); + ret = -ENOTSOCK; + goto peer_release; + } + + /* Only when using UDP as transport protocol the remote endpoint + * can be configured so that ovpn knows where to send packets to. + */ + if (sock->sk->sk_protocol == IPPROTO_UDP && + !attrs[OVPN_A_PEER_REMOTE_IPV4] && + !attrs[OVPN_A_PEER_REMOTE_IPV6]) { + NL_SET_ERR_MSG_FMT_MOD(info->extack, + "missing remote IP address for UDP socket"); + sockfd_put(sock); + ret = -EINVAL; + goto peer_release; + } + + /* In case of TCP, the socket is connected to the peer and ovpn + * will just send bytes over it, without the need to specify a + * destination. + */ + if (sock->sk->sk_protocol == IPPROTO_TCP && + (attrs[OVPN_A_PEER_REMOTE_IPV4] || + attrs[OVPN_A_PEER_REMOTE_IPV6])) { + NL_SET_ERR_MSG_FMT_MOD(info->extack, + "unexpected remote IP address with TCP socket"); + sockfd_put(sock); + ret = -EINVAL; + goto peer_release; + } + + ovpn_sock = ovpn_socket_new(sock, peer); + /* at this point we unconditionally drop the reference to the socket: + * - in case of error, the socket has to be dropped + * - if case of success, the socket is configured and let + * userspace own the reference, so that the latter can + * trigger the final close() + */ + sockfd_put(sock); + if (IS_ERR(ovpn_sock)) { + NL_SET_ERR_MSG_FMT_MOD(info->extack, + "cannot encapsulate socket: %ld", + PTR_ERR(ovpn_sock)); + ret = -ENOTSOCK; + goto peer_release; + } + + rcu_assign_pointer(peer->sock, ovpn_sock); + + ret = ovpn_nl_peer_modify(peer, info, attrs); + if (ret < 0) + goto sock_release; + + ret = ovpn_peer_add(ovpn, peer); + if (ret < 0) { + NL_SET_ERR_MSG_FMT_MOD(info->extack, + "cannot add new peer (id=%u) to hashtable: %d", + peer->id, ret); + goto sock_release; + } + + return 0; + +sock_release: + ovpn_socket_release(peer); +peer_release: + /* release right away because peer was not yet hashed, thus it is not + * used in any context + */ + ovpn_peer_release(peer); + + return ret; +} + +int ovpn_nl_peer_set_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *attrs[OVPN_A_PEER_MAX + 1]; + struct ovpn_priv *ovpn = info->user_ptr[0]; + struct ovpn_socket *sock; + struct ovpn_peer *peer; + u32 peer_id; + int ret; + + if (GENL_REQ_ATTR_CHECK(info, OVPN_A_PEER)) + return -EINVAL; + + ret = nla_parse_nested(attrs, OVPN_A_PEER_MAX, info->attrs[OVPN_A_PEER], + ovpn_peer_nl_policy, info->extack); + if (ret) + return ret; + + ret = ovpn_nl_peer_precheck(ovpn, info, attrs); + if (ret < 0) + return ret; + + if (attrs[OVPN_A_PEER_SOCKET]) { + NL_SET_ERR_MSG_FMT_MOD(info->extack, + "socket cannot be modified"); + return -EINVAL; + } + + peer_id = nla_get_u32(attrs[OVPN_A_PEER_ID]); + peer = ovpn_peer_get_by_id(ovpn, peer_id); + if (!peer) { + NL_SET_ERR_MSG_FMT_MOD(info->extack, + "cannot find peer with id %u", peer_id); + return -ENOENT; + } + + /* when using a TCP socket the remote IP is not expected */ + rcu_read_lock(); + sock = rcu_dereference(peer->sock); + if (sock && sock->sock->sk->sk_protocol == IPPROTO_TCP && + (attrs[OVPN_A_PEER_REMOTE_IPV4] || + attrs[OVPN_A_PEER_REMOTE_IPV6])) { + rcu_read_unlock(); + NL_SET_ERR_MSG_FMT_MOD(info->extack, + "unexpected remote IP address with TCP socket"); + ovpn_peer_put(peer); + return -EINVAL; + } + rcu_read_unlock(); + + spin_lock_bh(&ovpn->lock); + ret = ovpn_nl_peer_modify(peer, info, attrs); + if (ret < 0) { + spin_unlock_bh(&ovpn->lock); + ovpn_peer_put(peer); + return ret; + } + + /* ret == 1 means that VPN IPv4/6 has been modified and rehashing + * is required + */ + if (ret > 0) + ovpn_peer_hash_vpn_ip(peer); + spin_unlock_bh(&ovpn->lock); + ovpn_peer_put(peer); + + return 0; +} + +static int ovpn_nl_send_peer(struct sk_buff *skb, const struct genl_info *info, + const struct ovpn_peer *peer, u32 portid, u32 seq, + int flags) +{ + const struct ovpn_bind *bind; + struct ovpn_socket *sock; + int ret = -EMSGSIZE; + struct nlattr *attr; + __be16 local_port; + void *hdr; + int id; + + hdr = genlmsg_put(skb, portid, seq, &ovpn_nl_family, flags, + OVPN_CMD_PEER_GET); + if (!hdr) + return -ENOBUFS; + + attr = nla_nest_start(skb, OVPN_A_PEER); + if (!attr) + goto err; + + rcu_read_lock(); + sock = rcu_dereference(peer->sock); + if (!sock) { + ret = -EINVAL; + goto err_unlock; + } + + if (!net_eq(genl_info_net(info), sock_net(sock->sock->sk))) { + id = peernet2id_alloc(genl_info_net(info), + sock_net(sock->sock->sk), + GFP_ATOMIC); + if (nla_put_s32(skb, OVPN_A_PEER_SOCKET_NETNSID, id)) + goto err_unlock; + } + local_port = inet_sk(sock->sock->sk)->inet_sport; + rcu_read_unlock(); + + if (nla_put_u32(skb, OVPN_A_PEER_ID, peer->id)) + goto err; + + if (peer->vpn_addrs.ipv4.s_addr != htonl(INADDR_ANY)) + if (nla_put_in_addr(skb, OVPN_A_PEER_VPN_IPV4, + peer->vpn_addrs.ipv4.s_addr)) + goto err; + + if (!ipv6_addr_equal(&peer->vpn_addrs.ipv6, &in6addr_any)) + if (nla_put_in6_addr(skb, OVPN_A_PEER_VPN_IPV6, + &peer->vpn_addrs.ipv6)) + goto err; + + if (nla_put_u32(skb, OVPN_A_PEER_KEEPALIVE_INTERVAL, + peer->keepalive_interval) || + nla_put_u32(skb, OVPN_A_PEER_KEEPALIVE_TIMEOUT, + peer->keepalive_timeout)) + goto err; + + rcu_read_lock(); + bind = rcu_dereference(peer->bind); + if (bind) { + if (bind->remote.in4.sin_family == AF_INET) { + if (nla_put_in_addr(skb, OVPN_A_PEER_REMOTE_IPV4, + bind->remote.in4.sin_addr.s_addr) || + nla_put_net16(skb, OVPN_A_PEER_REMOTE_PORT, + bind->remote.in4.sin_port) || + nla_put_in_addr(skb, OVPN_A_PEER_LOCAL_IPV4, + bind->local.ipv4.s_addr)) + goto err_unlock; + } else if (bind->remote.in4.sin_family == AF_INET6) { + if (nla_put_in6_addr(skb, OVPN_A_PEER_REMOTE_IPV6, + &bind->remote.in6.sin6_addr) || + nla_put_u32(skb, OVPN_A_PEER_REMOTE_IPV6_SCOPE_ID, + bind->remote.in6.sin6_scope_id) || + nla_put_net16(skb, OVPN_A_PEER_REMOTE_PORT, + bind->remote.in6.sin6_port) || + nla_put_in6_addr(skb, OVPN_A_PEER_LOCAL_IPV6, + &bind->local.ipv6)) + goto err_unlock; + } + } + rcu_read_unlock(); + + if (nla_put_net16(skb, OVPN_A_PEER_LOCAL_PORT, local_port) || + /* VPN RX stats */ + nla_put_uint(skb, OVPN_A_PEER_VPN_RX_BYTES, + atomic64_read(&peer->vpn_stats.rx.bytes)) || + nla_put_uint(skb, OVPN_A_PEER_VPN_RX_PACKETS, + atomic64_read(&peer->vpn_stats.rx.packets)) || + /* VPN TX stats */ + nla_put_uint(skb, OVPN_A_PEER_VPN_TX_BYTES, + atomic64_read(&peer->vpn_stats.tx.bytes)) || + nla_put_uint(skb, OVPN_A_PEER_VPN_TX_PACKETS, + atomic64_read(&peer->vpn_stats.tx.packets)) || + /* link RX stats */ + nla_put_uint(skb, OVPN_A_PEER_LINK_RX_BYTES, + atomic64_read(&peer->link_stats.rx.bytes)) || + nla_put_uint(skb, OVPN_A_PEER_LINK_RX_PACKETS, + atomic64_read(&peer->link_stats.rx.packets)) || + /* link TX stats */ + nla_put_uint(skb, OVPN_A_PEER_LINK_TX_BYTES, + atomic64_read(&peer->link_stats.tx.bytes)) || + nla_put_uint(skb, OVPN_A_PEER_LINK_TX_PACKETS, + atomic64_read(&peer->link_stats.tx.packets))) + goto err; + + nla_nest_end(skb, attr); + genlmsg_end(skb, hdr); + + return 0; +err_unlock: + rcu_read_unlock(); +err: + genlmsg_cancel(skb, hdr); + return ret; +} + +int ovpn_nl_peer_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *attrs[OVPN_A_PEER_MAX + 1]; + struct ovpn_priv *ovpn = info->user_ptr[0]; + struct ovpn_peer *peer; + struct sk_buff *msg; + u32 peer_id; + int ret; + + if (GENL_REQ_ATTR_CHECK(info, OVPN_A_PEER)) + return -EINVAL; + + ret = nla_parse_nested(attrs, OVPN_A_PEER_MAX, info->attrs[OVPN_A_PEER], + ovpn_peer_nl_policy, info->extack); + if (ret) + return ret; + + if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_PEER], attrs, + OVPN_A_PEER_ID)) + return -EINVAL; + + peer_id = nla_get_u32(attrs[OVPN_A_PEER_ID]); + peer = ovpn_peer_get_by_id(ovpn, peer_id); + if (!peer) { + NL_SET_ERR_MSG_FMT_MOD(info->extack, + "cannot find peer with id %u", peer_id); + return -ENOENT; + } + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) { + ret = -ENOMEM; + goto err; + } + + ret = ovpn_nl_send_peer(msg, info, peer, info->snd_portid, + info->snd_seq, 0); + if (ret < 0) { + nlmsg_free(msg); + goto err; + } + + ret = genlmsg_reply(msg, info); +err: + ovpn_peer_put(peer); + return ret; +} + +int ovpn_nl_peer_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) +{ + const struct genl_info *info = genl_info_dump(cb); + int bkt, last_idx = cb->args[1], dumped = 0; + netdevice_tracker tracker; + struct ovpn_priv *ovpn; + struct ovpn_peer *peer; + + ovpn = ovpn_get_dev_from_attrs(sock_net(cb->skb->sk), info, &tracker); + if (IS_ERR(ovpn)) + return PTR_ERR(ovpn); + + if (ovpn->mode == OVPN_MODE_P2P) { + /* if we already dumped a peer it means we are done */ + if (last_idx) + goto out; + + rcu_read_lock(); + peer = rcu_dereference(ovpn->peer); + if (peer) { + if (ovpn_nl_send_peer(skb, info, peer, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI) == 0) + dumped++; + } + rcu_read_unlock(); + } else { + rcu_read_lock(); + hash_for_each_rcu(ovpn->peers->by_id, bkt, peer, + hash_entry_id) { + /* skip already dumped peers that were dumped by + * previous invocations + */ + if (last_idx > 0) { + last_idx--; + continue; + } + + if (ovpn_nl_send_peer(skb, info, peer, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI) < 0) + break; + + /* count peers being dumped during this invocation */ + dumped++; + } + rcu_read_unlock(); + } + +out: + netdev_put(ovpn->dev, &tracker); + + /* sum up peers dumped in this message, so that at the next invocation + * we can continue from where we left + */ + cb->args[1] += dumped; + return skb->len; +} + +int ovpn_nl_peer_del_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *attrs[OVPN_A_PEER_MAX + 1]; + struct ovpn_priv *ovpn = info->user_ptr[0]; + struct ovpn_peer *peer; + u32 peer_id; + int ret; + + if (GENL_REQ_ATTR_CHECK(info, OVPN_A_PEER)) + return -EINVAL; + + ret = nla_parse_nested(attrs, OVPN_A_PEER_MAX, info->attrs[OVPN_A_PEER], + ovpn_peer_nl_policy, info->extack); + if (ret) + return ret; + + if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_PEER], attrs, + OVPN_A_PEER_ID)) + return -EINVAL; + + peer_id = nla_get_u32(attrs[OVPN_A_PEER_ID]); + peer = ovpn_peer_get_by_id(ovpn, peer_id); + if (!peer) { + NL_SET_ERR_MSG_FMT_MOD(info->extack, + "cannot find peer with id %u", peer_id); + return -ENOENT; + } + + netdev_dbg(ovpn->dev, "del peer %u\n", peer->id); + ret = ovpn_peer_del(peer, OVPN_DEL_PEER_REASON_USERSPACE); + ovpn_peer_put(peer); + + return ret; +} + +static int ovpn_nl_get_key_dir(struct genl_info *info, struct nlattr *key, + enum ovpn_cipher_alg cipher, + struct ovpn_key_direction *dir) +{ + struct nlattr *attrs[OVPN_A_KEYDIR_MAX + 1]; + int ret; + + ret = nla_parse_nested(attrs, OVPN_A_KEYDIR_MAX, key, + ovpn_keydir_nl_policy, info->extack); + if (ret) + return ret; + + switch (cipher) { + case OVPN_CIPHER_ALG_AES_GCM: + case OVPN_CIPHER_ALG_CHACHA20_POLY1305: + if (NL_REQ_ATTR_CHECK(info->extack, key, attrs, + OVPN_A_KEYDIR_CIPHER_KEY) || + NL_REQ_ATTR_CHECK(info->extack, key, attrs, + OVPN_A_KEYDIR_NONCE_TAIL)) + return -EINVAL; + + dir->cipher_key = nla_data(attrs[OVPN_A_KEYDIR_CIPHER_KEY]); + dir->cipher_key_size = nla_len(attrs[OVPN_A_KEYDIR_CIPHER_KEY]); + + /* These algorithms require a 96bit nonce, + * Construct it by combining 4-bytes packet id and + * 8-bytes nonce-tail from userspace + */ + dir->nonce_tail = nla_data(attrs[OVPN_A_KEYDIR_NONCE_TAIL]); + dir->nonce_tail_size = nla_len(attrs[OVPN_A_KEYDIR_NONCE_TAIL]); + break; + default: + NL_SET_ERR_MSG_MOD(info->extack, "unsupported cipher"); + return -EINVAL; + } + + return 0; +} + +/** + * ovpn_nl_key_new_doit - configure a new key for the specified peer + * @skb: incoming netlink message + * @info: genetlink metadata + * + * This function allows the user to install a new key in the peer crypto + * state. + * Each peer has two 'slots', namely 'primary' and 'secondary', where + * keys can be installed. The key in the 'primary' slot is used for + * encryption, while both keys can be used for decryption by matching the + * key ID carried in the incoming packet. + * + * The user is responsible for rotating keys when necessary. The user + * may fetch peer traffic statistics via netlink in order to better + * identify the right time to rotate keys. + * The renegotiation follows these steps: + * 1. a new key is computed by the user and is installed in the 'secondary' + * slot + * 2. at user discretion (usually after a predetermined time) 'primary' and + * 'secondary' contents are swapped and the new key starts being used for + * encryption, while the old key is kept around for decryption of late + * packets. + * + * Return: 0 on success or a negative error code otherwise. + */ +int ovpn_nl_key_new_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *attrs[OVPN_A_KEYCONF_MAX + 1]; + struct ovpn_priv *ovpn = info->user_ptr[0]; + struct ovpn_peer_key_reset pkr; + struct ovpn_peer *peer; + u32 peer_id; + int ret; + + if (GENL_REQ_ATTR_CHECK(info, OVPN_A_KEYCONF)) + return -EINVAL; + + ret = nla_parse_nested(attrs, OVPN_A_KEYCONF_MAX, + info->attrs[OVPN_A_KEYCONF], + ovpn_keyconf_nl_policy, info->extack); + if (ret) + return ret; + + if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs, + OVPN_A_KEYCONF_PEER_ID)) + return -EINVAL; + + if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs, + OVPN_A_KEYCONF_SLOT) || + NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs, + OVPN_A_KEYCONF_KEY_ID) || + NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs, + OVPN_A_KEYCONF_CIPHER_ALG) || + NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs, + OVPN_A_KEYCONF_ENCRYPT_DIR) || + NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs, + OVPN_A_KEYCONF_DECRYPT_DIR)) + return -EINVAL; + + pkr.slot = nla_get_u32(attrs[OVPN_A_KEYCONF_SLOT]); + pkr.key.key_id = nla_get_u32(attrs[OVPN_A_KEYCONF_KEY_ID]); + pkr.key.cipher_alg = nla_get_u32(attrs[OVPN_A_KEYCONF_CIPHER_ALG]); + + ret = ovpn_nl_get_key_dir(info, attrs[OVPN_A_KEYCONF_ENCRYPT_DIR], + pkr.key.cipher_alg, &pkr.key.encrypt); + if (ret < 0) + return ret; + + ret = ovpn_nl_get_key_dir(info, attrs[OVPN_A_KEYCONF_DECRYPT_DIR], + pkr.key.cipher_alg, &pkr.key.decrypt); + if (ret < 0) + return ret; + + peer_id = nla_get_u32(attrs[OVPN_A_KEYCONF_PEER_ID]); + peer = ovpn_peer_get_by_id(ovpn, peer_id); + if (!peer) { + NL_SET_ERR_MSG_FMT_MOD(info->extack, + "no peer with id %u to set key for", + peer_id); + return -ENOENT; + } + + ret = ovpn_crypto_state_reset(&peer->crypto, &pkr); + if (ret < 0) { + NL_SET_ERR_MSG_FMT_MOD(info->extack, + "cannot install new key for peer %u", + peer_id); + goto out; + } + + netdev_dbg(ovpn->dev, "new key installed (id=%u) for peer %u\n", + pkr.key.key_id, peer_id); +out: + ovpn_peer_put(peer); + return ret; +} + +static int ovpn_nl_send_key(struct sk_buff *skb, const struct genl_info *info, + u32 peer_id, enum ovpn_key_slot slot, + const struct ovpn_key_config *keyconf) +{ + struct nlattr *attr; + void *hdr; + + hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq, &ovpn_nl_family, + 0, OVPN_CMD_KEY_GET); + if (!hdr) + return -ENOBUFS; + + attr = nla_nest_start(skb, OVPN_A_KEYCONF); + if (!attr) + goto err; + + if (nla_put_u32(skb, OVPN_A_KEYCONF_PEER_ID, peer_id)) + goto err; + + if (nla_put_u32(skb, OVPN_A_KEYCONF_SLOT, slot) || + nla_put_u32(skb, OVPN_A_KEYCONF_KEY_ID, keyconf->key_id) || + nla_put_u32(skb, OVPN_A_KEYCONF_CIPHER_ALG, keyconf->cipher_alg)) + goto err; + + nla_nest_end(skb, attr); + genlmsg_end(skb, hdr); + + return 0; +err: + genlmsg_cancel(skb, hdr); + return -EMSGSIZE; +} + +int ovpn_nl_key_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *attrs[OVPN_A_KEYCONF_MAX + 1]; + struct ovpn_priv *ovpn = info->user_ptr[0]; + struct ovpn_key_config keyconf = { 0 }; + enum ovpn_key_slot slot; + struct ovpn_peer *peer; + struct sk_buff *msg; + u32 peer_id; + int ret; + + if (GENL_REQ_ATTR_CHECK(info, OVPN_A_KEYCONF)) + return -EINVAL; + + ret = nla_parse_nested(attrs, OVPN_A_KEYCONF_MAX, + info->attrs[OVPN_A_KEYCONF], + ovpn_keyconf_nl_policy, info->extack); + if (ret) + return ret; + + if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs, + OVPN_A_KEYCONF_PEER_ID)) + return -EINVAL; + + if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs, + OVPN_A_KEYCONF_SLOT)) + return -EINVAL; + + peer_id = nla_get_u32(attrs[OVPN_A_KEYCONF_PEER_ID]); + peer = ovpn_peer_get_by_id(ovpn, peer_id); + if (!peer) { + NL_SET_ERR_MSG_FMT_MOD(info->extack, + "cannot find peer with id %u", peer_id); + return -ENOENT; + } + + slot = nla_get_u32(attrs[OVPN_A_KEYCONF_SLOT]); + + ret = ovpn_crypto_config_get(&peer->crypto, slot, &keyconf); + if (ret < 0) { + NL_SET_ERR_MSG_FMT_MOD(info->extack, + "cannot extract key from slot %u for peer %u", + slot, peer_id); + goto err; + } + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) { + ret = -ENOMEM; + goto err; + } + + ret = ovpn_nl_send_key(msg, info, peer->id, slot, &keyconf); + if (ret < 0) { + nlmsg_free(msg); + goto err; + } + + ret = genlmsg_reply(msg, info); +err: + ovpn_peer_put(peer); + return ret; +} + +int ovpn_nl_key_swap_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct ovpn_priv *ovpn = info->user_ptr[0]; + struct nlattr *attrs[OVPN_A_PEER_MAX + 1]; + struct ovpn_peer *peer; + u32 peer_id; + int ret; + + if (GENL_REQ_ATTR_CHECK(info, OVPN_A_KEYCONF)) + return -EINVAL; + + ret = nla_parse_nested(attrs, OVPN_A_KEYCONF_MAX, + info->attrs[OVPN_A_KEYCONF], + ovpn_keyconf_nl_policy, info->extack); + if (ret) + return ret; + + if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs, + OVPN_A_KEYCONF_PEER_ID)) + return -EINVAL; + + peer_id = nla_get_u32(attrs[OVPN_A_KEYCONF_PEER_ID]); + peer = ovpn_peer_get_by_id(ovpn, peer_id); + if (!peer) { + NL_SET_ERR_MSG_FMT_MOD(info->extack, + "no peer with id %u to swap keys for", + peer_id); + return -ENOENT; + } + + ovpn_crypto_key_slots_swap(&peer->crypto); + ovpn_peer_put(peer); + + return 0; +} + +int ovpn_nl_key_del_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *attrs[OVPN_A_KEYCONF_MAX + 1]; + struct ovpn_priv *ovpn = info->user_ptr[0]; + enum ovpn_key_slot slot; + struct ovpn_peer *peer; + u32 peer_id; + int ret; + + if (GENL_REQ_ATTR_CHECK(info, OVPN_A_KEYCONF)) + return -EINVAL; + + ret = nla_parse_nested(attrs, OVPN_A_KEYCONF_MAX, + info->attrs[OVPN_A_KEYCONF], + ovpn_keyconf_nl_policy, info->extack); + if (ret) + return ret; + + if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs, + OVPN_A_KEYCONF_PEER_ID)) + return -EINVAL; + + if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs, + OVPN_A_KEYCONF_SLOT)) + return -EINVAL; + + peer_id = nla_get_u32(attrs[OVPN_A_KEYCONF_PEER_ID]); + slot = nla_get_u32(attrs[OVPN_A_KEYCONF_SLOT]); + + peer = ovpn_peer_get_by_id(ovpn, peer_id); + if (!peer) { + NL_SET_ERR_MSG_FMT_MOD(info->extack, + "no peer with id %u to delete key for", + peer_id); + return -ENOENT; + } + + ovpn_crypto_key_slot_delete(&peer->crypto, slot); + ovpn_peer_put(peer); + + return 0; +} + +/** + * ovpn_nl_peer_del_notify - notify userspace about peer being deleted + * @peer: the peer being deleted + * + * Return: 0 on success or a negative error code otherwise + */ +int ovpn_nl_peer_del_notify(struct ovpn_peer *peer) +{ + struct ovpn_socket *sock; + struct sk_buff *msg; + struct nlattr *attr; + int ret = -EMSGSIZE; + void *hdr; + + netdev_info(peer->ovpn->dev, "deleting peer with id %u, reason %d\n", + peer->id, peer->delete_reason); + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); + if (!msg) + return -ENOMEM; + + hdr = genlmsg_put(msg, 0, 0, &ovpn_nl_family, 0, OVPN_CMD_PEER_DEL_NTF); + if (!hdr) { + ret = -ENOBUFS; + goto err_free_msg; + } + + if (nla_put_u32(msg, OVPN_A_IFINDEX, peer->ovpn->dev->ifindex)) + goto err_cancel_msg; + + attr = nla_nest_start(msg, OVPN_A_PEER); + if (!attr) + goto err_cancel_msg; + + if (nla_put_u32(msg, OVPN_A_PEER_DEL_REASON, peer->delete_reason)) + goto err_cancel_msg; + + if (nla_put_u32(msg, OVPN_A_PEER_ID, peer->id)) + goto err_cancel_msg; + + nla_nest_end(msg, attr); + + genlmsg_end(msg, hdr); + + rcu_read_lock(); + sock = rcu_dereference(peer->sock); + if (!sock) { + ret = -EINVAL; + goto err_unlock; + } + genlmsg_multicast_netns(&ovpn_nl_family, sock_net(sock->sock->sk), + msg, 0, OVPN_NLGRP_PEERS, GFP_ATOMIC); + rcu_read_unlock(); + + return 0; + +err_unlock: + rcu_read_unlock(); +err_cancel_msg: + genlmsg_cancel(msg, hdr); +err_free_msg: + nlmsg_free(msg); + return ret; +} + +/** + * ovpn_nl_key_swap_notify - notify userspace peer's key must be renewed + * @peer: the peer whose key needs to be renewed + * @key_id: the ID of the key that needs to be renewed + * + * Return: 0 on success or a negative error code otherwise + */ +int ovpn_nl_key_swap_notify(struct ovpn_peer *peer, u8 key_id) +{ + struct ovpn_socket *sock; + struct nlattr *k_attr; + struct sk_buff *msg; + int ret = -EMSGSIZE; + void *hdr; + + netdev_info(peer->ovpn->dev, "peer with id %u must rekey - primary key unusable.\n", + peer->id); + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); + if (!msg) + return -ENOMEM; + + hdr = genlmsg_put(msg, 0, 0, &ovpn_nl_family, 0, OVPN_CMD_KEY_SWAP_NTF); + if (!hdr) { + ret = -ENOBUFS; + goto err_free_msg; + } + + if (nla_put_u32(msg, OVPN_A_IFINDEX, peer->ovpn->dev->ifindex)) + goto err_cancel_msg; + + k_attr = nla_nest_start(msg, OVPN_A_KEYCONF); + if (!k_attr) + goto err_cancel_msg; + + if (nla_put_u32(msg, OVPN_A_KEYCONF_PEER_ID, peer->id)) + goto err_cancel_msg; + + if (nla_put_u16(msg, OVPN_A_KEYCONF_KEY_ID, key_id)) + goto err_cancel_msg; + + nla_nest_end(msg, k_attr); + genlmsg_end(msg, hdr); + + rcu_read_lock(); + sock = rcu_dereference(peer->sock); + if (!sock) { + ret = -EINVAL; + goto err_unlock; + } + genlmsg_multicast_netns(&ovpn_nl_family, sock_net(sock->sock->sk), + msg, 0, OVPN_NLGRP_PEERS, GFP_ATOMIC); + rcu_read_unlock(); + + return 0; +err_unlock: + rcu_read_unlock(); +err_cancel_msg: + genlmsg_cancel(msg, hdr); +err_free_msg: + nlmsg_free(msg); + return ret; +} + +/** + * ovpn_nl_register - perform any needed registration in the NL subsustem + * + * Return: 0 on success, a negative error code otherwise + */ +int __init ovpn_nl_register(void) +{ + int ret = genl_register_family(&ovpn_nl_family); + + if (ret) { + pr_err("ovpn: genl_register_family failed: %d\n", ret); + return ret; + } + + return 0; +} + +/** + * ovpn_nl_unregister - undo any module wide netlink registration + */ +void ovpn_nl_unregister(void) +{ + genl_unregister_family(&ovpn_nl_family); +} diff --git a/drivers/net/ovpn/netlink.h b/drivers/net/ovpn/netlink.h new file mode 100644 index 000000000000..8615dfc3c472 --- /dev/null +++ b/drivers/net/ovpn/netlink.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* OpenVPN data channel offload + * + * Copyright (C) 2020-2025 OpenVPN, Inc. + * + * Author: Antonio Quartulli <antonio@openvpn.net> + */ + +#ifndef _NET_OVPN_NETLINK_H_ +#define _NET_OVPN_NETLINK_H_ + +int ovpn_nl_register(void); +void ovpn_nl_unregister(void); + +int ovpn_nl_peer_del_notify(struct ovpn_peer *peer); +int ovpn_nl_key_swap_notify(struct ovpn_peer *peer, u8 key_id); + +#endif /* _NET_OVPN_NETLINK_H_ */ diff --git a/drivers/net/ovpn/ovpnpriv.h b/drivers/net/ovpn/ovpnpriv.h new file mode 100644 index 000000000000..5898f6adada7 --- /dev/null +++ b/drivers/net/ovpn/ovpnpriv.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* OpenVPN data channel offload + * + * Copyright (C) 2019-2025 OpenVPN, Inc. + * + * Author: James Yonan <james@openvpn.net> + * Antonio Quartulli <antonio@openvpn.net> + */ + +#ifndef _NET_OVPN_OVPNSTRUCT_H_ +#define _NET_OVPN_OVPNSTRUCT_H_ + +#include <linux/workqueue.h> +#include <net/gro_cells.h> +#include <uapi/linux/if_link.h> +#include <uapi/linux/ovpn.h> + +/** + * struct ovpn_peer_collection - container of peers for MultiPeer mode + * @by_id: table of peers index by ID + * @by_vpn_addr4: table of peers indexed by VPN IPv4 address (items can be + * rehashed on the fly due to peer IP change) + * @by_vpn_addr6: table of peers indexed by VPN IPv6 address (items can be + * rehashed on the fly due to peer IP change) + * @by_transp_addr: table of peers indexed by transport address (items can be + * rehashed on the fly due to peer IP change) + */ +struct ovpn_peer_collection { + DECLARE_HASHTABLE(by_id, 12); + struct hlist_nulls_head by_vpn_addr4[1 << 12]; + struct hlist_nulls_head by_vpn_addr6[1 << 12]; + struct hlist_nulls_head by_transp_addr[1 << 12]; +}; + +/** + * struct ovpn_priv - per ovpn interface state + * @dev: the actual netdev representing the tunnel + * @mode: device operation mode (i.e. p2p, mp, ..) + * @lock: protect this object + * @peers: data structures holding multi-peer references + * @peer: in P2P mode, this is the only remote peer + * @gro_cells: pointer to the Generic Receive Offload cell + * @keepalive_work: struct used to schedule keepalive periodic job + */ +struct ovpn_priv { + struct net_device *dev; + enum ovpn_mode mode; + spinlock_t lock; /* protect writing to the ovpn_priv object */ + struct ovpn_peer_collection *peers; + struct ovpn_peer __rcu *peer; + struct gro_cells gro_cells; + struct delayed_work keepalive_work; +}; + +#endif /* _NET_OVPN_OVPNSTRUCT_H_ */ diff --git a/drivers/net/ovpn/peer.c b/drivers/net/ovpn/peer.c new file mode 100644 index 000000000000..a1fd27b9c038 --- /dev/null +++ b/drivers/net/ovpn/peer.c @@ -0,0 +1,1364 @@ +// SPDX-License-Identifier: GPL-2.0 +/* OpenVPN data channel offload + * + * Copyright (C) 2020-2025 OpenVPN, Inc. + * + * Author: James Yonan <james@openvpn.net> + * Antonio Quartulli <antonio@openvpn.net> + */ + +#include <linux/skbuff.h> +#include <linux/list.h> +#include <linux/hashtable.h> +#include <net/ip6_route.h> + +#include "ovpnpriv.h" +#include "bind.h" +#include "pktid.h" +#include "crypto.h" +#include "io.h" +#include "main.h" +#include "netlink.h" +#include "peer.h" +#include "socket.h" + +static void unlock_ovpn(struct ovpn_priv *ovpn, + struct llist_head *release_list) + __releases(&ovpn->lock) +{ + struct ovpn_peer *peer; + + spin_unlock_bh(&ovpn->lock); + + llist_for_each_entry(peer, release_list->first, release_entry) { + ovpn_socket_release(peer); + ovpn_peer_put(peer); + } +} + +/** + * ovpn_peer_keepalive_set - configure keepalive values for peer + * @peer: the peer to configure + * @interval: outgoing keepalive interval + * @timeout: incoming keepalive timeout + */ +void ovpn_peer_keepalive_set(struct ovpn_peer *peer, u32 interval, u32 timeout) +{ + time64_t now = ktime_get_real_seconds(); + + netdev_dbg(peer->ovpn->dev, + "scheduling keepalive for peer %u: interval=%u timeout=%u\n", + peer->id, interval, timeout); + + peer->keepalive_interval = interval; + WRITE_ONCE(peer->last_sent, now); + peer->keepalive_xmit_exp = now + interval; + + peer->keepalive_timeout = timeout; + WRITE_ONCE(peer->last_recv, now); + peer->keepalive_recv_exp = now + timeout; + + /* now that interval and timeout have been changed, kick + * off the worker so that the next delay can be recomputed + */ + mod_delayed_work(system_wq, &peer->ovpn->keepalive_work, 0); +} + +/** + * ovpn_peer_keepalive_send - periodic worker sending keepalive packets + * @work: pointer to the work member of the related peer object + * + * NOTE: the reference to peer is not dropped because it gets inherited + * by ovpn_xmit_special() + */ +static void ovpn_peer_keepalive_send(struct work_struct *work) +{ + struct ovpn_peer *peer = container_of(work, struct ovpn_peer, + keepalive_work); + + local_bh_disable(); + ovpn_xmit_special(peer, ovpn_keepalive_message, + sizeof(ovpn_keepalive_message)); + local_bh_enable(); +} + +/** + * ovpn_peer_new - allocate and initialize a new peer object + * @ovpn: the openvpn instance inside which the peer should be created + * @id: the ID assigned to this peer + * + * Return: a pointer to the new peer on success or an error code otherwise + */ +struct ovpn_peer *ovpn_peer_new(struct ovpn_priv *ovpn, u32 id) +{ + struct ovpn_peer *peer; + int ret; + + /* alloc and init peer object */ + peer = kzalloc(sizeof(*peer), GFP_KERNEL); + if (!peer) + return ERR_PTR(-ENOMEM); + + peer->id = id; + peer->ovpn = ovpn; + + peer->vpn_addrs.ipv4.s_addr = htonl(INADDR_ANY); + peer->vpn_addrs.ipv6 = in6addr_any; + + RCU_INIT_POINTER(peer->bind, NULL); + ovpn_crypto_state_init(&peer->crypto); + spin_lock_init(&peer->lock); + kref_init(&peer->refcount); + ovpn_peer_stats_init(&peer->vpn_stats); + ovpn_peer_stats_init(&peer->link_stats); + INIT_WORK(&peer->keepalive_work, ovpn_peer_keepalive_send); + + ret = dst_cache_init(&peer->dst_cache, GFP_KERNEL); + if (ret < 0) { + netdev_err(ovpn->dev, + "cannot initialize dst cache for peer %u\n", + peer->id); + kfree(peer); + return ERR_PTR(ret); + } + + netdev_hold(ovpn->dev, &peer->dev_tracker, GFP_KERNEL); + + return peer; +} + +/** + * ovpn_peer_reset_sockaddr - recreate binding for peer + * @peer: peer to recreate the binding for + * @ss: sockaddr to use as remote endpoint for the binding + * @local_ip: local IP for the binding + * + * Return: 0 on success or a negative error code otherwise + */ +int ovpn_peer_reset_sockaddr(struct ovpn_peer *peer, + const struct sockaddr_storage *ss, + const void *local_ip) +{ + struct ovpn_bind *bind; + size_t ip_len; + + lockdep_assert_held(&peer->lock); + + /* create new ovpn_bind object */ + bind = ovpn_bind_from_sockaddr(ss); + if (IS_ERR(bind)) + return PTR_ERR(bind); + + if (local_ip) { + if (ss->ss_family == AF_INET) { + ip_len = sizeof(struct in_addr); + } else if (ss->ss_family == AF_INET6) { + ip_len = sizeof(struct in6_addr); + } else { + net_dbg_ratelimited("%s: invalid family %u for remote endpoint for peer %u\n", + netdev_name(peer->ovpn->dev), + ss->ss_family, peer->id); + kfree(bind); + return -EINVAL; + } + + memcpy(&bind->local, local_ip, ip_len); + } + + /* set binding */ + ovpn_bind_reset(peer, bind); + + return 0; +} + +/* variable name __tbl2 needs to be different from __tbl1 + * in the macro below to avoid confusing clang + */ +#define ovpn_get_hash_slot(_tbl, _key, _key_len) ({ \ + typeof(_tbl) *__tbl2 = &(_tbl); \ + jhash(_key, _key_len, 0) % HASH_SIZE(*__tbl2); \ +}) + +#define ovpn_get_hash_head(_tbl, _key, _key_len) ({ \ + typeof(_tbl) *__tbl1 = &(_tbl); \ + &(*__tbl1)[ovpn_get_hash_slot(*__tbl1, _key, _key_len)];\ +}) + +/** + * ovpn_peer_endpoints_update - update remote or local endpoint for peer + * @peer: peer to update the remote endpoint for + * @skb: incoming packet to retrieve the source/destination address from + */ +void ovpn_peer_endpoints_update(struct ovpn_peer *peer, struct sk_buff *skb) +{ + struct hlist_nulls_head *nhead; + struct sockaddr_storage ss; + struct sockaddr_in6 *sa6; + bool reset_cache = false; + struct sockaddr_in *sa; + struct ovpn_bind *bind; + const void *local_ip; + size_t salen = 0; + + spin_lock_bh(&peer->lock); + bind = rcu_dereference_protected(peer->bind, + lockdep_is_held(&peer->lock)); + if (unlikely(!bind)) + goto unlock; + + switch (skb->protocol) { + case htons(ETH_P_IP): + /* float check */ + if (unlikely(!ovpn_bind_skb_src_match(bind, skb))) { + /* unconditionally save local endpoint in case + * of float, as it may have changed as well + */ + local_ip = &ip_hdr(skb)->daddr; + sa = (struct sockaddr_in *)&ss; + sa->sin_family = AF_INET; + sa->sin_addr.s_addr = ip_hdr(skb)->saddr; + sa->sin_port = udp_hdr(skb)->source; + salen = sizeof(*sa); + reset_cache = true; + break; + } + + /* if no float happened, let's double check if the local endpoint + * has changed + */ + if (unlikely(bind->local.ipv4.s_addr != ip_hdr(skb)->daddr)) { + net_dbg_ratelimited("%s: learning local IPv4 for peer %d (%pI4 -> %pI4)\n", + netdev_name(peer->ovpn->dev), + peer->id, &bind->local.ipv4.s_addr, + &ip_hdr(skb)->daddr); + bind->local.ipv4.s_addr = ip_hdr(skb)->daddr; + reset_cache = true; + } + break; + case htons(ETH_P_IPV6): + /* float check */ + if (unlikely(!ovpn_bind_skb_src_match(bind, skb))) { + /* unconditionally save local endpoint in case + * of float, as it may have changed as well + */ + local_ip = &ipv6_hdr(skb)->daddr; + sa6 = (struct sockaddr_in6 *)&ss; + sa6->sin6_family = AF_INET6; + sa6->sin6_addr = ipv6_hdr(skb)->saddr; + sa6->sin6_port = udp_hdr(skb)->source; + sa6->sin6_scope_id = ipv6_iface_scope_id(&ipv6_hdr(skb)->saddr, + skb->skb_iif); + salen = sizeof(*sa6); + reset_cache = true; + break; + } + + /* if no float happened, let's double check if the local endpoint + * has changed + */ + if (unlikely(!ipv6_addr_equal(&bind->local.ipv6, + &ipv6_hdr(skb)->daddr))) { + net_dbg_ratelimited("%s: learning local IPv6 for peer %d (%pI6c -> %pI6c)\n", + netdev_name(peer->ovpn->dev), + peer->id, &bind->local.ipv6, + &ipv6_hdr(skb)->daddr); + bind->local.ipv6 = ipv6_hdr(skb)->daddr; + reset_cache = true; + } + break; + default: + goto unlock; + } + + if (unlikely(reset_cache)) + dst_cache_reset(&peer->dst_cache); + + /* if the peer did not float, we can bail out now */ + if (likely(!salen)) + goto unlock; + + if (unlikely(ovpn_peer_reset_sockaddr(peer, + (struct sockaddr_storage *)&ss, + local_ip) < 0)) + goto unlock; + + net_dbg_ratelimited("%s: peer %d floated to %pIScp", + netdev_name(peer->ovpn->dev), peer->id, &ss); + + spin_unlock_bh(&peer->lock); + + /* rehashing is required only in MP mode as P2P has one peer + * only and thus there is no hashtable + */ + if (peer->ovpn->mode == OVPN_MODE_MP) { + spin_lock_bh(&peer->ovpn->lock); + spin_lock_bh(&peer->lock); + bind = rcu_dereference_protected(peer->bind, + lockdep_is_held(&peer->lock)); + if (unlikely(!bind)) { + spin_unlock_bh(&peer->lock); + spin_unlock_bh(&peer->ovpn->lock); + return; + } + + /* This function may be invoked concurrently, therefore another + * float may have happened in parallel: perform rehashing + * using the peer->bind->remote directly as key + */ + + switch (bind->remote.in4.sin_family) { + case AF_INET: + salen = sizeof(*sa); + break; + case AF_INET6: + salen = sizeof(*sa6); + break; + } + + /* remove old hashing */ + hlist_nulls_del_init_rcu(&peer->hash_entry_transp_addr); + /* re-add with new transport address */ + nhead = ovpn_get_hash_head(peer->ovpn->peers->by_transp_addr, + &bind->remote, salen); + hlist_nulls_add_head_rcu(&peer->hash_entry_transp_addr, nhead); + spin_unlock_bh(&peer->lock); + spin_unlock_bh(&peer->ovpn->lock); + } + return; +unlock: + spin_unlock_bh(&peer->lock); +} + +/** + * ovpn_peer_release_rcu - RCU callback performing last peer release steps + * @head: RCU member of the ovpn_peer + */ +static void ovpn_peer_release_rcu(struct rcu_head *head) +{ + struct ovpn_peer *peer = container_of(head, struct ovpn_peer, rcu); + + /* this call will immediately free the dst_cache, therefore we + * perform it in the RCU callback, when all contexts are done + */ + dst_cache_destroy(&peer->dst_cache); + kfree(peer); +} + +/** + * ovpn_peer_release - release peer private members + * @peer: the peer to release + */ +void ovpn_peer_release(struct ovpn_peer *peer) +{ + ovpn_crypto_state_release(&peer->crypto); + spin_lock_bh(&peer->lock); + ovpn_bind_reset(peer, NULL); + spin_unlock_bh(&peer->lock); + call_rcu(&peer->rcu, ovpn_peer_release_rcu); + netdev_put(peer->ovpn->dev, &peer->dev_tracker); +} + +/** + * ovpn_peer_release_kref - callback for kref_put + * @kref: the kref object belonging to the peer + */ +void ovpn_peer_release_kref(struct kref *kref) +{ + struct ovpn_peer *peer = container_of(kref, struct ovpn_peer, refcount); + + ovpn_peer_release(peer); +} + +/** + * ovpn_peer_skb_to_sockaddr - fill sockaddr with skb source address + * @skb: the packet to extract data from + * @ss: the sockaddr to fill + * + * Return: sockaddr length on success or -1 otherwise + */ +static int ovpn_peer_skb_to_sockaddr(struct sk_buff *skb, + struct sockaddr_storage *ss) +{ + struct sockaddr_in6 *sa6; + struct sockaddr_in *sa4; + + switch (skb->protocol) { + case htons(ETH_P_IP): + sa4 = (struct sockaddr_in *)ss; + sa4->sin_family = AF_INET; + sa4->sin_addr.s_addr = ip_hdr(skb)->saddr; + sa4->sin_port = udp_hdr(skb)->source; + return sizeof(*sa4); + case htons(ETH_P_IPV6): + sa6 = (struct sockaddr_in6 *)ss; + sa6->sin6_family = AF_INET6; + sa6->sin6_addr = ipv6_hdr(skb)->saddr; + sa6->sin6_port = udp_hdr(skb)->source; + return sizeof(*sa6); + } + + return -1; +} + +/** + * ovpn_nexthop_from_skb4 - retrieve IPv4 nexthop for outgoing skb + * @skb: the outgoing packet + * + * Return: the IPv4 of the nexthop + */ +static __be32 ovpn_nexthop_from_skb4(struct sk_buff *skb) +{ + const struct rtable *rt = skb_rtable(skb); + + if (rt && rt->rt_uses_gateway) + return rt->rt_gw4; + + return ip_hdr(skb)->daddr; +} + +/** + * ovpn_nexthop_from_skb6 - retrieve IPv6 nexthop for outgoing skb + * @skb: the outgoing packet + * + * Return: the IPv6 of the nexthop + */ +static struct in6_addr ovpn_nexthop_from_skb6(struct sk_buff *skb) +{ + const struct rt6_info *rt = skb_rt6_info(skb); + + if (!rt || !(rt->rt6i_flags & RTF_GATEWAY)) + return ipv6_hdr(skb)->daddr; + + return rt->rt6i_gateway; +} + +/** + * ovpn_peer_get_by_vpn_addr4 - retrieve peer by its VPN IPv4 address + * @ovpn: the openvpn instance to search + * @addr: VPN IPv4 to use as search key + * + * Refcounter is not increased for the returned peer. + * + * Return: the peer if found or NULL otherwise + */ +static struct ovpn_peer *ovpn_peer_get_by_vpn_addr4(struct ovpn_priv *ovpn, + __be32 addr) +{ + struct hlist_nulls_head *nhead; + struct hlist_nulls_node *ntmp; + struct ovpn_peer *tmp; + unsigned int slot; + +begin: + slot = ovpn_get_hash_slot(ovpn->peers->by_vpn_addr4, &addr, + sizeof(addr)); + nhead = &ovpn->peers->by_vpn_addr4[slot]; + + hlist_nulls_for_each_entry_rcu(tmp, ntmp, nhead, hash_entry_addr4) + if (addr == tmp->vpn_addrs.ipv4.s_addr) + return tmp; + + /* item may have moved during lookup - check nulls and restart + * if that's the case + */ + if (get_nulls_value(ntmp) != slot) + goto begin; + + return NULL; +} + +/** + * ovpn_peer_get_by_vpn_addr6 - retrieve peer by its VPN IPv6 address + * @ovpn: the openvpn instance to search + * @addr: VPN IPv6 to use as search key + * + * Refcounter is not increased for the returned peer. + * + * Return: the peer if found or NULL otherwise + */ +static struct ovpn_peer *ovpn_peer_get_by_vpn_addr6(struct ovpn_priv *ovpn, + struct in6_addr *addr) +{ + struct hlist_nulls_head *nhead; + struct hlist_nulls_node *ntmp; + struct ovpn_peer *tmp; + unsigned int slot; + +begin: + slot = ovpn_get_hash_slot(ovpn->peers->by_vpn_addr6, addr, + sizeof(*addr)); + nhead = &ovpn->peers->by_vpn_addr6[slot]; + + hlist_nulls_for_each_entry_rcu(tmp, ntmp, nhead, hash_entry_addr6) + if (ipv6_addr_equal(addr, &tmp->vpn_addrs.ipv6)) + return tmp; + + /* item may have moved during lookup - check nulls and restart + * if that's the case + */ + if (get_nulls_value(ntmp) != slot) + goto begin; + + return NULL; +} + +/** + * ovpn_peer_transp_match - check if sockaddr and peer binding match + * @peer: the peer to get the binding from + * @ss: the sockaddr to match + * + * Return: true if sockaddr and binding match or false otherwise + */ +static bool ovpn_peer_transp_match(const struct ovpn_peer *peer, + const struct sockaddr_storage *ss) +{ + struct ovpn_bind *bind = rcu_dereference(peer->bind); + struct sockaddr_in6 *sa6; + struct sockaddr_in *sa4; + + if (unlikely(!bind)) + return false; + + if (ss->ss_family != bind->remote.in4.sin_family) + return false; + + switch (ss->ss_family) { + case AF_INET: + sa4 = (struct sockaddr_in *)ss; + if (sa4->sin_addr.s_addr != bind->remote.in4.sin_addr.s_addr) + return false; + if (sa4->sin_port != bind->remote.in4.sin_port) + return false; + break; + case AF_INET6: + sa6 = (struct sockaddr_in6 *)ss; + if (!ipv6_addr_equal(&sa6->sin6_addr, + &bind->remote.in6.sin6_addr)) + return false; + if (sa6->sin6_port != bind->remote.in6.sin6_port) + return false; + break; + default: + return false; + } + + return true; +} + +/** + * ovpn_peer_get_by_transp_addr_p2p - get peer by transport address in a P2P + * instance + * @ovpn: the openvpn instance to search + * @ss: the transport socket address + * + * Return: the peer if found or NULL otherwise + */ +static struct ovpn_peer * +ovpn_peer_get_by_transp_addr_p2p(struct ovpn_priv *ovpn, + struct sockaddr_storage *ss) +{ + struct ovpn_peer *tmp, *peer = NULL; + + rcu_read_lock(); + tmp = rcu_dereference(ovpn->peer); + if (likely(tmp && ovpn_peer_transp_match(tmp, ss) && + ovpn_peer_hold(tmp))) + peer = tmp; + rcu_read_unlock(); + + return peer; +} + +/** + * ovpn_peer_get_by_transp_addr - retrieve peer by transport address + * @ovpn: the openvpn instance to search + * @skb: the skb to retrieve the source transport address from + * + * Return: a pointer to the peer if found or NULL otherwise + */ +struct ovpn_peer *ovpn_peer_get_by_transp_addr(struct ovpn_priv *ovpn, + struct sk_buff *skb) +{ + struct ovpn_peer *tmp, *peer = NULL; + struct sockaddr_storage ss = { 0 }; + struct hlist_nulls_head *nhead; + struct hlist_nulls_node *ntmp; + unsigned int slot; + ssize_t sa_len; + + sa_len = ovpn_peer_skb_to_sockaddr(skb, &ss); + if (unlikely(sa_len < 0)) + return NULL; + + if (ovpn->mode == OVPN_MODE_P2P) + return ovpn_peer_get_by_transp_addr_p2p(ovpn, &ss); + + rcu_read_lock(); +begin: + slot = ovpn_get_hash_slot(ovpn->peers->by_transp_addr, &ss, sa_len); + nhead = &ovpn->peers->by_transp_addr[slot]; + + hlist_nulls_for_each_entry_rcu(tmp, ntmp, nhead, + hash_entry_transp_addr) { + if (!ovpn_peer_transp_match(tmp, &ss)) + continue; + + if (!ovpn_peer_hold(tmp)) + continue; + + peer = tmp; + break; + } + + /* item may have moved during lookup - check nulls and restart + * if that's the case + */ + if (!peer && get_nulls_value(ntmp) != slot) + goto begin; + rcu_read_unlock(); + + return peer; +} + +/** + * ovpn_peer_get_by_id_p2p - get peer by ID in a P2P instance + * @ovpn: the openvpn instance to search + * @peer_id: the ID of the peer to find + * + * Return: the peer if found or NULL otherwise + */ +static struct ovpn_peer *ovpn_peer_get_by_id_p2p(struct ovpn_priv *ovpn, + u32 peer_id) +{ + struct ovpn_peer *tmp, *peer = NULL; + + rcu_read_lock(); + tmp = rcu_dereference(ovpn->peer); + if (likely(tmp && tmp->id == peer_id && ovpn_peer_hold(tmp))) + peer = tmp; + rcu_read_unlock(); + + return peer; +} + +/** + * ovpn_peer_get_by_id - retrieve peer by ID + * @ovpn: the openvpn instance to search + * @peer_id: the unique peer identifier to match + * + * Return: a pointer to the peer if found or NULL otherwise + */ +struct ovpn_peer *ovpn_peer_get_by_id(struct ovpn_priv *ovpn, u32 peer_id) +{ + struct ovpn_peer *tmp, *peer = NULL; + struct hlist_head *head; + + if (ovpn->mode == OVPN_MODE_P2P) + return ovpn_peer_get_by_id_p2p(ovpn, peer_id); + + head = ovpn_get_hash_head(ovpn->peers->by_id, &peer_id, + sizeof(peer_id)); + + rcu_read_lock(); + hlist_for_each_entry_rcu(tmp, head, hash_entry_id) { + if (tmp->id != peer_id) + continue; + + if (!ovpn_peer_hold(tmp)) + continue; + + peer = tmp; + break; + } + rcu_read_unlock(); + + return peer; +} + +static void ovpn_peer_remove(struct ovpn_peer *peer, + enum ovpn_del_peer_reason reason, + struct llist_head *release_list) +{ + lockdep_assert_held(&peer->ovpn->lock); + + switch (peer->ovpn->mode) { + case OVPN_MODE_MP: + /* prevent double remove */ + if (hlist_unhashed(&peer->hash_entry_id)) + return; + + hlist_del_init_rcu(&peer->hash_entry_id); + hlist_nulls_del_init_rcu(&peer->hash_entry_addr4); + hlist_nulls_del_init_rcu(&peer->hash_entry_addr6); + hlist_nulls_del_init_rcu(&peer->hash_entry_transp_addr); + break; + case OVPN_MODE_P2P: + /* prevent double remove */ + if (peer != rcu_access_pointer(peer->ovpn->peer)) + return; + + RCU_INIT_POINTER(peer->ovpn->peer, NULL); + /* in P2P mode the carrier is switched off when the peer is + * deleted so that third party protocols can react accordingly + */ + netif_carrier_off(peer->ovpn->dev); + break; + } + + peer->delete_reason = reason; + ovpn_nl_peer_del_notify(peer); + + /* append to provided list for later socket release and ref drop */ + llist_add(&peer->release_entry, release_list); +} + +/** + * ovpn_peer_get_by_dst - Lookup peer to send skb to + * @ovpn: the private data representing the current VPN session + * @skb: the skb to extract the destination address from + * + * This function takes a tunnel packet and looks up the peer to send it to + * after encapsulation. The skb is expected to be the in-tunnel packet, without + * any OpenVPN related header. + * + * Assume that the IP header is accessible in the skb data. + * + * Return: the peer if found or NULL otherwise. + */ +struct ovpn_peer *ovpn_peer_get_by_dst(struct ovpn_priv *ovpn, + struct sk_buff *skb) +{ + struct ovpn_peer *peer = NULL; + struct in6_addr addr6; + __be32 addr4; + + /* in P2P mode, no matter the destination, packets are always sent to + * the single peer listening on the other side + */ + if (ovpn->mode == OVPN_MODE_P2P) { + rcu_read_lock(); + peer = rcu_dereference(ovpn->peer); + if (unlikely(peer && !ovpn_peer_hold(peer))) + peer = NULL; + rcu_read_unlock(); + return peer; + } + + rcu_read_lock(); + switch (skb->protocol) { + case htons(ETH_P_IP): + addr4 = ovpn_nexthop_from_skb4(skb); + peer = ovpn_peer_get_by_vpn_addr4(ovpn, addr4); + break; + case htons(ETH_P_IPV6): + addr6 = ovpn_nexthop_from_skb6(skb); + peer = ovpn_peer_get_by_vpn_addr6(ovpn, &addr6); + break; + } + + if (unlikely(peer && !ovpn_peer_hold(peer))) + peer = NULL; + rcu_read_unlock(); + + return peer; +} + +/** + * ovpn_nexthop_from_rt4 - look up the IPv4 nexthop for the given destination + * @ovpn: the private data representing the current VPN session + * @dest: the destination to be looked up + * + * Looks up in the IPv4 system routing table the IP of the nexthop to be used + * to reach the destination passed as argument. If no nexthop can be found, the + * destination itself is returned as it probably has to be used as nexthop. + * + * Return: the IP of the next hop if found or dest itself otherwise + */ +static __be32 ovpn_nexthop_from_rt4(struct ovpn_priv *ovpn, __be32 dest) +{ + struct rtable *rt; + struct flowi4 fl = { + .daddr = dest + }; + + rt = ip_route_output_flow(dev_net(ovpn->dev), &fl, NULL); + if (IS_ERR(rt)) { + net_dbg_ratelimited("%s: no route to host %pI4\n", + netdev_name(ovpn->dev), &dest); + /* if we end up here this packet is probably going to be + * thrown away later + */ + return dest; + } + + if (!rt->rt_uses_gateway) + goto out; + + dest = rt->rt_gw4; +out: + ip_rt_put(rt); + return dest; +} + +/** + * ovpn_nexthop_from_rt6 - look up the IPv6 nexthop for the given destination + * @ovpn: the private data representing the current VPN session + * @dest: the destination to be looked up + * + * Looks up in the IPv6 system routing table the IP of the nexthop to be used + * to reach the destination passed as argument. If no nexthop can be found, the + * destination itself is returned as it probably has to be used as nexthop. + * + * Return: the IP of the next hop if found or dest itself otherwise + */ +static struct in6_addr ovpn_nexthop_from_rt6(struct ovpn_priv *ovpn, + struct in6_addr dest) +{ +#if IS_ENABLED(CONFIG_IPV6) + struct dst_entry *entry; + struct rt6_info *rt; + struct flowi6 fl = { + .daddr = dest, + }; + + entry = ipv6_stub->ipv6_dst_lookup_flow(dev_net(ovpn->dev), NULL, &fl, + NULL); + if (IS_ERR(entry)) { + net_dbg_ratelimited("%s: no route to host %pI6c\n", + netdev_name(ovpn->dev), &dest); + /* if we end up here this packet is probably going to be + * thrown away later + */ + return dest; + } + + rt = dst_rt6_info(entry); + + if (!(rt->rt6i_flags & RTF_GATEWAY)) + goto out; + + dest = rt->rt6i_gateway; +out: + dst_release((struct dst_entry *)rt); +#endif + return dest; +} + +/** + * ovpn_peer_check_by_src - check that skb source is routed via peer + * @ovpn: the openvpn instance to search + * @skb: the packet to extract source address from + * @peer: the peer to check against the source address + * + * Return: true if the peer is matching or false otherwise + */ +bool ovpn_peer_check_by_src(struct ovpn_priv *ovpn, struct sk_buff *skb, + struct ovpn_peer *peer) +{ + bool match = false; + struct in6_addr addr6; + __be32 addr4; + + if (ovpn->mode == OVPN_MODE_P2P) { + /* in P2P mode, no matter the destination, packets are always + * sent to the single peer listening on the other side + */ + return peer == rcu_access_pointer(ovpn->peer); + } + + /* This function performs a reverse path check, therefore we now + * lookup the nexthop we would use if we wanted to route a packet + * to the source IP. If the nexthop matches the sender we know the + * latter is valid and we allow the packet to come in + */ + + switch (skb->protocol) { + case htons(ETH_P_IP): + addr4 = ovpn_nexthop_from_rt4(ovpn, ip_hdr(skb)->saddr); + rcu_read_lock(); + match = (peer == ovpn_peer_get_by_vpn_addr4(ovpn, addr4)); + rcu_read_unlock(); + break; + case htons(ETH_P_IPV6): + addr6 = ovpn_nexthop_from_rt6(ovpn, ipv6_hdr(skb)->saddr); + rcu_read_lock(); + match = (peer == ovpn_peer_get_by_vpn_addr6(ovpn, &addr6)); + rcu_read_unlock(); + break; + } + + return match; +} + +void ovpn_peer_hash_vpn_ip(struct ovpn_peer *peer) +{ + struct hlist_nulls_head *nhead; + + lockdep_assert_held(&peer->ovpn->lock); + + /* rehashing makes sense only in multipeer mode */ + if (peer->ovpn->mode != OVPN_MODE_MP) + return; + + if (peer->vpn_addrs.ipv4.s_addr != htonl(INADDR_ANY)) { + /* remove potential old hashing */ + hlist_nulls_del_init_rcu(&peer->hash_entry_addr4); + + nhead = ovpn_get_hash_head(peer->ovpn->peers->by_vpn_addr4, + &peer->vpn_addrs.ipv4, + sizeof(peer->vpn_addrs.ipv4)); + hlist_nulls_add_head_rcu(&peer->hash_entry_addr4, nhead); + } + + if (!ipv6_addr_any(&peer->vpn_addrs.ipv6)) { + /* remove potential old hashing */ + hlist_nulls_del_init_rcu(&peer->hash_entry_addr6); + + nhead = ovpn_get_hash_head(peer->ovpn->peers->by_vpn_addr6, + &peer->vpn_addrs.ipv6, + sizeof(peer->vpn_addrs.ipv6)); + hlist_nulls_add_head_rcu(&peer->hash_entry_addr6, nhead); + } +} + +/** + * ovpn_peer_add_mp - add peer to related tables in a MP instance + * @ovpn: the instance to add the peer to + * @peer: the peer to add + * + * Return: 0 on success or a negative error code otherwise + */ +static int ovpn_peer_add_mp(struct ovpn_priv *ovpn, struct ovpn_peer *peer) +{ + struct sockaddr_storage sa = { 0 }; + struct hlist_nulls_head *nhead; + struct sockaddr_in6 *sa6; + struct sockaddr_in *sa4; + struct ovpn_bind *bind; + struct ovpn_peer *tmp; + size_t salen; + int ret = 0; + + spin_lock_bh(&ovpn->lock); + /* do not add duplicates */ + tmp = ovpn_peer_get_by_id(ovpn, peer->id); + if (tmp) { + ovpn_peer_put(tmp); + ret = -EEXIST; + goto out; + } + + bind = rcu_dereference_protected(peer->bind, true); + /* peers connected via TCP have bind == NULL */ + if (bind) { + switch (bind->remote.in4.sin_family) { + case AF_INET: + sa4 = (struct sockaddr_in *)&sa; + + sa4->sin_family = AF_INET; + sa4->sin_addr.s_addr = bind->remote.in4.sin_addr.s_addr; + sa4->sin_port = bind->remote.in4.sin_port; + salen = sizeof(*sa4); + break; + case AF_INET6: + sa6 = (struct sockaddr_in6 *)&sa; + + sa6->sin6_family = AF_INET6; + sa6->sin6_addr = bind->remote.in6.sin6_addr; + sa6->sin6_port = bind->remote.in6.sin6_port; + salen = sizeof(*sa6); + break; + default: + ret = -EPROTONOSUPPORT; + goto out; + } + + nhead = ovpn_get_hash_head(ovpn->peers->by_transp_addr, &sa, + salen); + hlist_nulls_add_head_rcu(&peer->hash_entry_transp_addr, nhead); + } + + hlist_add_head_rcu(&peer->hash_entry_id, + ovpn_get_hash_head(ovpn->peers->by_id, &peer->id, + sizeof(peer->id))); + + ovpn_peer_hash_vpn_ip(peer); +out: + spin_unlock_bh(&ovpn->lock); + return ret; +} + +/** + * ovpn_peer_add_p2p - add peer to related tables in a P2P instance + * @ovpn: the instance to add the peer to + * @peer: the peer to add + * + * Return: 0 on success or a negative error code otherwise + */ +static int ovpn_peer_add_p2p(struct ovpn_priv *ovpn, struct ovpn_peer *peer) +{ + LLIST_HEAD(release_list); + struct ovpn_peer *tmp; + + spin_lock_bh(&ovpn->lock); + /* in p2p mode it is possible to have a single peer only, therefore the + * old one is released and substituted by the new one + */ + tmp = rcu_dereference_protected(ovpn->peer, + lockdep_is_held(&ovpn->lock)); + if (tmp) + ovpn_peer_remove(tmp, OVPN_DEL_PEER_REASON_TEARDOWN, + &release_list); + + rcu_assign_pointer(ovpn->peer, peer); + /* in P2P mode the carrier is switched on when the peer is added */ + netif_carrier_on(ovpn->dev); + unlock_ovpn(ovpn, &release_list); + + return 0; +} + +/** + * ovpn_peer_add - add peer to the related tables + * @ovpn: the openvpn instance the peer belongs to + * @peer: the peer object to add + * + * Assume refcounter was increased by caller + * + * Return: 0 on success or a negative error code otherwise + */ +int ovpn_peer_add(struct ovpn_priv *ovpn, struct ovpn_peer *peer) +{ + switch (ovpn->mode) { + case OVPN_MODE_MP: + return ovpn_peer_add_mp(ovpn, peer); + case OVPN_MODE_P2P: + return ovpn_peer_add_p2p(ovpn, peer); + } + + return -EOPNOTSUPP; +} + +/** + * ovpn_peer_del_mp - delete peer from related tables in a MP instance + * @peer: the peer to delete + * @reason: reason why the peer was deleted (sent to userspace) + * @release_list: list where delete peer should be appended + * + * Return: 0 on success or a negative error code otherwise + */ +static int ovpn_peer_del_mp(struct ovpn_peer *peer, + enum ovpn_del_peer_reason reason, + struct llist_head *release_list) +{ + struct ovpn_peer *tmp; + int ret = -ENOENT; + + lockdep_assert_held(&peer->ovpn->lock); + + tmp = ovpn_peer_get_by_id(peer->ovpn, peer->id); + if (tmp == peer) { + ovpn_peer_remove(peer, reason, release_list); + ret = 0; + } + + if (tmp) + ovpn_peer_put(tmp); + + return ret; +} + +/** + * ovpn_peer_del_p2p - delete peer from related tables in a P2P instance + * @peer: the peer to delete + * @reason: reason why the peer was deleted (sent to userspace) + * @release_list: list where delete peer should be appended + * + * Return: 0 on success or a negative error code otherwise + */ +static int ovpn_peer_del_p2p(struct ovpn_peer *peer, + enum ovpn_del_peer_reason reason, + struct llist_head *release_list) +{ + struct ovpn_peer *tmp; + + lockdep_assert_held(&peer->ovpn->lock); + + tmp = rcu_dereference_protected(peer->ovpn->peer, + lockdep_is_held(&peer->ovpn->lock)); + if (tmp != peer) + return -ENOENT; + + ovpn_peer_remove(peer, reason, release_list); + + return 0; +} + +/** + * ovpn_peer_del - delete peer from related tables + * @peer: the peer object to delete + * @reason: reason for deleting peer (will be sent to userspace) + * + * Return: 0 on success or a negative error code otherwise + */ +int ovpn_peer_del(struct ovpn_peer *peer, enum ovpn_del_peer_reason reason) +{ + LLIST_HEAD(release_list); + int ret = -EOPNOTSUPP; + + spin_lock_bh(&peer->ovpn->lock); + switch (peer->ovpn->mode) { + case OVPN_MODE_MP: + ret = ovpn_peer_del_mp(peer, reason, &release_list); + break; + case OVPN_MODE_P2P: + ret = ovpn_peer_del_p2p(peer, reason, &release_list); + break; + default: + break; + } + unlock_ovpn(peer->ovpn, &release_list); + + return ret; +} + +/** + * ovpn_peer_release_p2p - release peer upon P2P device teardown + * @ovpn: the instance being torn down + * @sk: if not NULL, release peer only if it's using this specific socket + * @reason: the reason for releasing the peer + */ +static void ovpn_peer_release_p2p(struct ovpn_priv *ovpn, struct sock *sk, + enum ovpn_del_peer_reason reason) +{ + struct ovpn_socket *ovpn_sock; + LLIST_HEAD(release_list); + struct ovpn_peer *peer; + + spin_lock_bh(&ovpn->lock); + peer = rcu_dereference_protected(ovpn->peer, + lockdep_is_held(&ovpn->lock)); + if (!peer) { + spin_unlock_bh(&ovpn->lock); + return; + } + + if (sk) { + ovpn_sock = rcu_access_pointer(peer->sock); + if (!ovpn_sock || ovpn_sock->sock->sk != sk) { + spin_unlock_bh(&ovpn->lock); + ovpn_peer_put(peer); + return; + } + } + + ovpn_peer_remove(peer, reason, &release_list); + unlock_ovpn(ovpn, &release_list); +} + +static void ovpn_peers_release_mp(struct ovpn_priv *ovpn, struct sock *sk, + enum ovpn_del_peer_reason reason) +{ + struct ovpn_socket *ovpn_sock; + LLIST_HEAD(release_list); + struct ovpn_peer *peer; + struct hlist_node *tmp; + int bkt; + + spin_lock_bh(&ovpn->lock); + hash_for_each_safe(ovpn->peers->by_id, bkt, tmp, peer, hash_entry_id) { + bool remove = true; + + /* if a socket was passed as argument, skip all peers except + * those using it + */ + if (sk) { + rcu_read_lock(); + ovpn_sock = rcu_dereference(peer->sock); + remove = ovpn_sock && ovpn_sock->sock->sk == sk; + rcu_read_unlock(); + } + + if (remove) + ovpn_peer_remove(peer, reason, &release_list); + } + unlock_ovpn(ovpn, &release_list); +} + +/** + * ovpn_peers_free - free all peers in the instance + * @ovpn: the instance whose peers should be released + * @sk: if not NULL, only peers using this socket are removed and the socket + * is released immediately + * @reason: the reason for releasing all peers + */ +void ovpn_peers_free(struct ovpn_priv *ovpn, struct sock *sk, + enum ovpn_del_peer_reason reason) +{ + switch (ovpn->mode) { + case OVPN_MODE_P2P: + ovpn_peer_release_p2p(ovpn, sk, reason); + break; + case OVPN_MODE_MP: + ovpn_peers_release_mp(ovpn, sk, reason); + break; + } +} + +static time64_t ovpn_peer_keepalive_work_single(struct ovpn_peer *peer, + time64_t now, + struct llist_head *release_list) +{ + time64_t last_recv, last_sent, next_run1, next_run2; + unsigned long timeout, interval; + bool expired; + + spin_lock_bh(&peer->lock); + /* we expect both timers to be configured at the same time, + * therefore bail out if either is not set + */ + if (!peer->keepalive_timeout || !peer->keepalive_interval) { + spin_unlock_bh(&peer->lock); + return 0; + } + + /* check for peer timeout */ + expired = false; + timeout = peer->keepalive_timeout; + last_recv = READ_ONCE(peer->last_recv); + if (now < last_recv + timeout) { + peer->keepalive_recv_exp = last_recv + timeout; + next_run1 = peer->keepalive_recv_exp; + } else if (peer->keepalive_recv_exp > now) { + next_run1 = peer->keepalive_recv_exp; + } else { + expired = true; + } + + if (expired) { + /* peer is dead -> kill it and move on */ + spin_unlock_bh(&peer->lock); + netdev_dbg(peer->ovpn->dev, "peer %u expired\n", + peer->id); + ovpn_peer_remove(peer, OVPN_DEL_PEER_REASON_EXPIRED, + release_list); + return 0; + } + + /* check for peer keepalive */ + expired = false; + interval = peer->keepalive_interval; + last_sent = READ_ONCE(peer->last_sent); + if (now < last_sent + interval) { + peer->keepalive_xmit_exp = last_sent + interval; + next_run2 = peer->keepalive_xmit_exp; + } else if (peer->keepalive_xmit_exp > now) { + next_run2 = peer->keepalive_xmit_exp; + } else { + expired = true; + next_run2 = now + interval; + } + spin_unlock_bh(&peer->lock); + + if (expired) { + /* a keepalive packet is required */ + netdev_dbg(peer->ovpn->dev, + "sending keepalive to peer %u\n", + peer->id); + if (schedule_work(&peer->keepalive_work)) + ovpn_peer_hold(peer); + } + + if (next_run1 < next_run2) + return next_run1; + + return next_run2; +} + +static time64_t ovpn_peer_keepalive_work_mp(struct ovpn_priv *ovpn, + time64_t now, + struct llist_head *release_list) +{ + time64_t tmp_next_run, next_run = 0; + struct hlist_node *tmp; + struct ovpn_peer *peer; + int bkt; + + lockdep_assert_held(&ovpn->lock); + + hash_for_each_safe(ovpn->peers->by_id, bkt, tmp, peer, hash_entry_id) { + tmp_next_run = ovpn_peer_keepalive_work_single(peer, now, + release_list); + if (!tmp_next_run) + continue; + + /* the next worker run will be scheduled based on the shortest + * required interval across all peers + */ + if (!next_run || tmp_next_run < next_run) + next_run = tmp_next_run; + } + + return next_run; +} + +static time64_t ovpn_peer_keepalive_work_p2p(struct ovpn_priv *ovpn, + time64_t now, + struct llist_head *release_list) +{ + struct ovpn_peer *peer; + time64_t next_run = 0; + + lockdep_assert_held(&ovpn->lock); + + peer = rcu_dereference_protected(ovpn->peer, + lockdep_is_held(&ovpn->lock)); + if (peer) + next_run = ovpn_peer_keepalive_work_single(peer, now, + release_list); + + return next_run; +} + +/** + * ovpn_peer_keepalive_work - run keepalive logic on each known peer + * @work: pointer to the work member of the related ovpn object + * + * Each peer has two timers (if configured): + * 1. peer timeout: when no data is received for a certain interval, + * the peer is considered dead and it gets killed. + * 2. peer keepalive: when no data is sent to a certain peer for a + * certain interval, a special 'keepalive' packet is explicitly sent. + * + * This function iterates across the whole peer collection while + * checking the timers described above. + */ +void ovpn_peer_keepalive_work(struct work_struct *work) +{ + struct ovpn_priv *ovpn = container_of(work, struct ovpn_priv, + keepalive_work.work); + time64_t next_run = 0, now = ktime_get_real_seconds(); + LLIST_HEAD(release_list); + + spin_lock_bh(&ovpn->lock); + switch (ovpn->mode) { + case OVPN_MODE_MP: + next_run = ovpn_peer_keepalive_work_mp(ovpn, now, + &release_list); + break; + case OVPN_MODE_P2P: + next_run = ovpn_peer_keepalive_work_p2p(ovpn, now, + &release_list); + break; + } + + /* prevent rearming if the interface is being destroyed */ + if (next_run > 0) { + netdev_dbg(ovpn->dev, + "scheduling keepalive work: now=%llu next_run=%llu delta=%llu\n", + next_run, now, next_run - now); + schedule_delayed_work(&ovpn->keepalive_work, + (next_run - now) * HZ); + } + unlock_ovpn(ovpn, &release_list); +} diff --git a/drivers/net/ovpn/peer.h b/drivers/net/ovpn/peer.h new file mode 100644 index 000000000000..a1423f2b09e0 --- /dev/null +++ b/drivers/net/ovpn/peer.h @@ -0,0 +1,163 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* OpenVPN data channel offload + * + * Copyright (C) 2020-2025 OpenVPN, Inc. + * + * Author: James Yonan <james@openvpn.net> + * Antonio Quartulli <antonio@openvpn.net> + */ + +#ifndef _NET_OVPN_OVPNPEER_H_ +#define _NET_OVPN_OVPNPEER_H_ + +#include <net/dst_cache.h> +#include <net/strparser.h> + +#include "crypto.h" +#include "socket.h" +#include "stats.h" + +/** + * struct ovpn_peer - the main remote peer object + * @ovpn: main openvpn instance this peer belongs to + * @dev_tracker: reference tracker for associated dev + * @id: unique identifier + * @vpn_addrs: IP addresses assigned over the tunnel + * @vpn_addrs.ipv4: IPv4 assigned to peer on the tunnel + * @vpn_addrs.ipv6: IPv6 assigned to peer on the tunnel + * @hash_entry_id: entry in the peer ID hashtable + * @hash_entry_addr4: entry in the peer IPv4 hashtable + * @hash_entry_addr6: entry in the peer IPv6 hashtable + * @hash_entry_transp_addr: entry in the peer transport address hashtable + * @sock: the socket being used to talk to this peer + * @tcp: keeps track of TCP specific state + * @tcp.strp: stream parser context (TCP only) + * @tcp.user_queue: received packets that have to go to userspace (TCP only) + * @tcp.out_queue: packets on hold while socket is taken by user (TCP only) + * @tcp.tx_in_progress: true if TX is already ongoing (TCP only) + * @tcp.out_msg.skb: packet scheduled for sending (TCP only) + * @tcp.out_msg.offset: offset where next send should start (TCP only) + * @tcp.out_msg.len: remaining data to send within packet (TCP only) + * @tcp.sk_cb.sk_data_ready: pointer to original cb (TCP only) + * @tcp.sk_cb.sk_write_space: pointer to original cb (TCP only) + * @tcp.sk_cb.prot: pointer to original prot object (TCP only) + * @tcp.sk_cb.ops: pointer to the original prot_ops object (TCP only) + * @crypto: the crypto configuration (ciphers, keys, etc..) + * @dst_cache: cache for dst_entry used to send to peer + * @bind: remote peer binding + * @keepalive_interval: seconds after which a new keepalive should be sent + * @keepalive_xmit_exp: future timestamp when next keepalive should be sent + * @last_sent: timestamp of the last successfully sent packet + * @keepalive_timeout: seconds after which an inactive peer is considered dead + * @keepalive_recv_exp: future timestamp when the peer should expire + * @last_recv: timestamp of the last authenticated received packet + * @vpn_stats: per-peer in-VPN TX/RX stats + * @link_stats: per-peer link/transport TX/RX stats + * @delete_reason: why peer was deleted (i.e. timeout, transport error, ..) + * @lock: protects binding to peer (bind) and keepalive* fields + * @refcount: reference counter + * @rcu: used to free peer in an RCU safe way + * @release_entry: entry for the socket release list + * @keepalive_work: used to schedule keepalive sending + */ +struct ovpn_peer { + struct ovpn_priv *ovpn; + netdevice_tracker dev_tracker; + u32 id; + struct { + struct in_addr ipv4; + struct in6_addr ipv6; + } vpn_addrs; + struct hlist_node hash_entry_id; + struct hlist_nulls_node hash_entry_addr4; + struct hlist_nulls_node hash_entry_addr6; + struct hlist_nulls_node hash_entry_transp_addr; + struct ovpn_socket __rcu *sock; + + struct { + struct strparser strp; + struct sk_buff_head user_queue; + struct sk_buff_head out_queue; + bool tx_in_progress; + + struct { + struct sk_buff *skb; + int offset; + int len; + } out_msg; + + struct { + void (*sk_data_ready)(struct sock *sk); + void (*sk_write_space)(struct sock *sk); + struct proto *prot; + const struct proto_ops *ops; + } sk_cb; + + struct work_struct defer_del_work; + } tcp; + struct ovpn_crypto_state crypto; + struct dst_cache dst_cache; + struct ovpn_bind __rcu *bind; + unsigned long keepalive_interval; + unsigned long keepalive_xmit_exp; + time64_t last_sent; + unsigned long keepalive_timeout; + unsigned long keepalive_recv_exp; + time64_t last_recv; + struct ovpn_peer_stats vpn_stats; + struct ovpn_peer_stats link_stats; + enum ovpn_del_peer_reason delete_reason; + spinlock_t lock; /* protects bind and keepalive* */ + struct kref refcount; + struct rcu_head rcu; + struct llist_node release_entry; + struct work_struct keepalive_work; +}; + +/** + * ovpn_peer_hold - increase reference counter + * @peer: the peer whose counter should be increased + * + * Return: true if the counter was increased or false if it was zero already + */ +static inline bool ovpn_peer_hold(struct ovpn_peer *peer) +{ + return kref_get_unless_zero(&peer->refcount); +} + +void ovpn_peer_release(struct ovpn_peer *peer); +void ovpn_peer_release_kref(struct kref *kref); + +/** + * ovpn_peer_put - decrease reference counter + * @peer: the peer whose counter should be decreased + */ +static inline void ovpn_peer_put(struct ovpn_peer *peer) +{ + kref_put(&peer->refcount, ovpn_peer_release_kref); +} + +struct ovpn_peer *ovpn_peer_new(struct ovpn_priv *ovpn, u32 id); +int ovpn_peer_add(struct ovpn_priv *ovpn, struct ovpn_peer *peer); +int ovpn_peer_del(struct ovpn_peer *peer, enum ovpn_del_peer_reason reason); +void ovpn_peers_free(struct ovpn_priv *ovpn, struct sock *sock, + enum ovpn_del_peer_reason reason); + +struct ovpn_peer *ovpn_peer_get_by_transp_addr(struct ovpn_priv *ovpn, + struct sk_buff *skb); +struct ovpn_peer *ovpn_peer_get_by_id(struct ovpn_priv *ovpn, u32 peer_id); +struct ovpn_peer *ovpn_peer_get_by_dst(struct ovpn_priv *ovpn, + struct sk_buff *skb); +void ovpn_peer_hash_vpn_ip(struct ovpn_peer *peer); +bool ovpn_peer_check_by_src(struct ovpn_priv *ovpn, struct sk_buff *skb, + struct ovpn_peer *peer); + +void ovpn_peer_keepalive_set(struct ovpn_peer *peer, u32 interval, u32 timeout); +void ovpn_peer_keepalive_work(struct work_struct *work); + +void ovpn_peer_endpoints_update(struct ovpn_peer *peer, struct sk_buff *skb); +int ovpn_peer_reset_sockaddr(struct ovpn_peer *peer, + const struct sockaddr_storage *ss, + const void *local_ip); + +#endif /* _NET_OVPN_OVPNPEER_H_ */ diff --git a/drivers/net/ovpn/pktid.c b/drivers/net/ovpn/pktid.c new file mode 100644 index 000000000000..2f29049897e3 --- /dev/null +++ b/drivers/net/ovpn/pktid.c @@ -0,0 +1,129 @@ +// SPDX-License-Identifier: GPL-2.0 +/* OpenVPN data channel offload + * + * Copyright (C) 2020-2025 OpenVPN, Inc. + * + * Author: Antonio Quartulli <antonio@openvpn.net> + * James Yonan <james@openvpn.net> + */ + +#include <linux/atomic.h> +#include <linux/jiffies.h> +#include <linux/net.h> +#include <linux/netdevice.h> +#include <linux/types.h> + +#include "ovpnpriv.h" +#include "main.h" +#include "pktid.h" + +void ovpn_pktid_xmit_init(struct ovpn_pktid_xmit *pid) +{ + atomic_set(&pid->seq_num, 1); +} + +void ovpn_pktid_recv_init(struct ovpn_pktid_recv *pr) +{ + memset(pr, 0, sizeof(*pr)); + spin_lock_init(&pr->lock); +} + +/* Packet replay detection. + * Allows ID backtrack of up to REPLAY_WINDOW_SIZE - 1. + */ +int ovpn_pktid_recv(struct ovpn_pktid_recv *pr, u32 pkt_id, u32 pkt_time) +{ + const unsigned long now = jiffies; + int ret; + + /* ID must not be zero */ + if (unlikely(pkt_id == 0)) + return -EINVAL; + + spin_lock_bh(&pr->lock); + + /* expire backtracks at or below pr->id after PKTID_RECV_EXPIRE time */ + if (unlikely(time_after_eq(now, pr->expire))) + pr->id_floor = pr->id; + + /* time changed? */ + if (unlikely(pkt_time != pr->time)) { + if (pkt_time > pr->time) { + /* time moved forward, accept */ + pr->base = 0; + pr->extent = 0; + pr->id = 0; + pr->time = pkt_time; + pr->id_floor = 0; + } else { + /* time moved backward, reject */ + ret = -ETIME; + goto out; + } + } + + if (likely(pkt_id == pr->id + 1)) { + /* well-formed ID sequence (incremented by 1) */ + pr->base = REPLAY_INDEX(pr->base, -1); + pr->history[pr->base / 8] |= (1 << (pr->base % 8)); + if (pr->extent < REPLAY_WINDOW_SIZE) + ++pr->extent; + pr->id = pkt_id; + } else if (pkt_id > pr->id) { + /* ID jumped forward by more than one */ + const unsigned int delta = pkt_id - pr->id; + + if (delta < REPLAY_WINDOW_SIZE) { + unsigned int i; + + pr->base = REPLAY_INDEX(pr->base, -delta); + pr->history[pr->base / 8] |= (1 << (pr->base % 8)); + pr->extent += delta; + if (pr->extent > REPLAY_WINDOW_SIZE) + pr->extent = REPLAY_WINDOW_SIZE; + for (i = 1; i < delta; ++i) { + unsigned int newb = REPLAY_INDEX(pr->base, i); + + pr->history[newb / 8] &= ~BIT(newb % 8); + } + } else { + pr->base = 0; + pr->extent = REPLAY_WINDOW_SIZE; + memset(pr->history, 0, sizeof(pr->history)); + pr->history[0] = 1; + } + pr->id = pkt_id; + } else { + /* ID backtrack */ + const unsigned int delta = pr->id - pkt_id; + + if (delta > pr->max_backtrack) + pr->max_backtrack = delta; + if (delta < pr->extent) { + if (pkt_id > pr->id_floor) { + const unsigned int ri = REPLAY_INDEX(pr->base, + delta); + u8 *p = &pr->history[ri / 8]; + const u8 mask = (1 << (ri % 8)); + + if (*p & mask) { + ret = -EINVAL; + goto out; + } + *p |= mask; + } else { + ret = -EINVAL; + goto out; + } + } else { + ret = -EINVAL; + goto out; + } + } + + pr->expire = now + PKTID_RECV_EXPIRE; + ret = 0; +out: + spin_unlock_bh(&pr->lock); + return ret; +} diff --git a/drivers/net/ovpn/pktid.h b/drivers/net/ovpn/pktid.h new file mode 100644 index 000000000000..0262d026d15e --- /dev/null +++ b/drivers/net/ovpn/pktid.h @@ -0,0 +1,86 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* OpenVPN data channel offload + * + * Copyright (C) 2020-2025 OpenVPN, Inc. + * + * Author: Antonio Quartulli <antonio@openvpn.net> + * James Yonan <james@openvpn.net> + */ + +#ifndef _NET_OVPN_OVPNPKTID_H_ +#define _NET_OVPN_OVPNPKTID_H_ + +#include "proto.h" + +/* If no packets received for this length of time, set a backtrack floor + * at highest received packet ID thus far. + */ +#define PKTID_RECV_EXPIRE (30 * HZ) + +/* Packet-ID state for transmitter */ +struct ovpn_pktid_xmit { + atomic_t seq_num; +}; + +/* replay window sizing in bytes = 2^REPLAY_WINDOW_ORDER */ +#define REPLAY_WINDOW_ORDER 8 + +#define REPLAY_WINDOW_BYTES BIT(REPLAY_WINDOW_ORDER) +#define REPLAY_WINDOW_SIZE (REPLAY_WINDOW_BYTES * 8) +#define REPLAY_INDEX(base, i) (((base) + (i)) & (REPLAY_WINDOW_SIZE - 1)) + +/* Packet-ID state for receiver. + * Other than lock member, can be zeroed to initialize. + */ +struct ovpn_pktid_recv { + /* "sliding window" bitmask of recent packet IDs received */ + u8 history[REPLAY_WINDOW_BYTES]; + /* bit position of deque base in history */ + unsigned int base; + /* extent (in bits) of deque in history */ + unsigned int extent; + /* expiration of history in jiffies */ + unsigned long expire; + /* highest sequence number received */ + u32 id; + /* highest time stamp received */ + u32 time; + /* we will only accept backtrack IDs > id_floor */ + u32 id_floor; + unsigned int max_backtrack; + /* protects entire pktd ID state */ + spinlock_t lock; +}; + +/* Get the next packet ID for xmit */ +static inline int ovpn_pktid_xmit_next(struct ovpn_pktid_xmit *pid, u32 *pktid) +{ + const u32 seq_num = atomic_fetch_add_unless(&pid->seq_num, 1, 0); + /* when the 32bit space is over, we return an error because the packet + * ID is used to create the cipher IV and we do not want to reuse the + * same value more than once + */ + if (unlikely(!seq_num)) + return -ERANGE; + + *pktid = seq_num; + + return 0; +} + +/* Write 12-byte AEAD IV to dest */ +static inline void ovpn_pktid_aead_write(const u32 pktid, + const u8 nt[], + unsigned char *dest) +{ + *(__force __be32 *)(dest) = htonl(pktid); + BUILD_BUG_ON(4 + OVPN_NONCE_TAIL_SIZE != OVPN_NONCE_SIZE); + memcpy(dest + 4, nt, OVPN_NONCE_TAIL_SIZE); +} + +void ovpn_pktid_xmit_init(struct ovpn_pktid_xmit *pid); +void ovpn_pktid_recv_init(struct ovpn_pktid_recv *pr); + +int ovpn_pktid_recv(struct ovpn_pktid_recv *pr, u32 pkt_id, u32 pkt_time); + +#endif /* _NET_OVPN_OVPNPKTID_H_ */ diff --git a/drivers/net/ovpn/proto.h b/drivers/net/ovpn/proto.h new file mode 100644 index 000000000000..b7d285b4d9c1 --- /dev/null +++ b/drivers/net/ovpn/proto.h @@ -0,0 +1,118 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* OpenVPN data channel offload + * + * Copyright (C) 2020-2025 OpenVPN, Inc. + * + * Author: Antonio Quartulli <antonio@openvpn.net> + * James Yonan <james@openvpn.net> + */ + +#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: + * + * 00000005 521c3b01 4308c041 + * [seq # ] [ nonce_tail ] + * [ 12-byte full IV ] -> OVPN_NONCE_SIZE + * [4-bytes -> OVPN_NONCE_WIRE_SIZE + * on wire] + */ + +/* nonce size (96bits) as required by AEAD ciphers */ +#define OVPN_NONCE_SIZE 12 +/* last 8 bytes of AEAD nonce: provided by userspace and usually derived + * from key material generated during TLS handshake + */ +#define OVPN_NONCE_TAIL_SIZE 8 + +/* OpenVPN nonce size reduced by 8-byte nonce tail -- this is the + * size of the AEAD Associated Data (AD) sent over the wire + * and is normally the head of the IV + */ +#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 4 bytes. + * + * 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); +} + +/** + * ovpn_key_id_from_skb - extract key ID from the skb head + * @skb: the packet to extract the key ID code from + * + * Note: this function assumes that the skb head was pulled enough + * to access the first 4 bytes. + * + * Return: the key ID + */ +static inline u8 ovpn_key_id_from_skb(const struct sk_buff *skb) +{ + u32 opcode = be32_to_cpu(*(__be32 *)skb->data); + + return FIELD_GET(OVPN_OPCODE_KEYID_MASK, opcode); +} + +/** + * ovpn_opcode_compose - combine OP code, key ID and peer ID to wire format + * @opcode: the OP code + * @key_id: the key ID + * @peer_id: the peer ID + * + * Return: a 4 bytes integer obtained combining all input values following the + * OpenVPN wire format. This integer can then be written to the packet header. + */ +static inline u32 ovpn_opcode_compose(u8 opcode, u8 key_id, u32 peer_id) +{ + return FIELD_PREP(OVPN_OPCODE_PKTTYPE_MASK, opcode) | + FIELD_PREP(OVPN_OPCODE_KEYID_MASK, key_id) | + FIELD_PREP(OVPN_OPCODE_PEERID_MASK, peer_id); +} + +#endif /* _NET_OVPN_OVPNPROTO_H_ */ diff --git a/drivers/net/ovpn/skb.h b/drivers/net/ovpn/skb.h new file mode 100644 index 000000000000..64430880f1da --- /dev/null +++ b/drivers/net/ovpn/skb.h @@ -0,0 +1,61 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* OpenVPN data channel offload + * + * Copyright (C) 2020-2025 OpenVPN, Inc. + * + * Author: Antonio Quartulli <antonio@openvpn.net> + * James Yonan <james@openvpn.net> + */ + +#ifndef _NET_OVPN_SKB_H_ +#define _NET_OVPN_SKB_H_ + +#include <linux/in.h> +#include <linux/in6.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/skbuff.h> +#include <linux/socket.h> +#include <linux/types.h> + +struct ovpn_cb { + struct ovpn_peer *peer; + struct ovpn_crypto_key_slot *ks; + struct aead_request *req; + struct scatterlist *sg; + u8 *iv; + unsigned int payload_offset; + bool nosignal; +}; + +static inline struct ovpn_cb *ovpn_skb_cb(struct sk_buff *skb) +{ + BUILD_BUG_ON(sizeof(struct ovpn_cb) > sizeof(skb->cb)); + return (struct ovpn_cb *)skb->cb; +} + +/* Return IP protocol version from skb header. + * Return 0 if protocol is not IPv4/IPv6 or cannot be read. + */ +static inline __be16 ovpn_ip_check_protocol(struct sk_buff *skb) +{ + __be16 proto = 0; + + /* skb could be non-linear, + * make sure IP header is in non-fragmented part + */ + if (!pskb_network_may_pull(skb, sizeof(struct iphdr))) + return 0; + + if (ip_hdr(skb)->version == 4) { + proto = htons(ETH_P_IP); + } else if (ip_hdr(skb)->version == 6) { + if (!pskb_network_may_pull(skb, sizeof(struct ipv6hdr))) + return 0; + proto = htons(ETH_P_IPV6); + } + + return proto; +} + +#endif /* _NET_OVPN_SKB_H_ */ diff --git a/drivers/net/ovpn/socket.c b/drivers/net/ovpn/socket.c new file mode 100644 index 000000000000..a83cbab72591 --- /dev/null +++ b/drivers/net/ovpn/socket.c @@ -0,0 +1,233 @@ +// SPDX-License-Identifier: GPL-2.0 +/* OpenVPN data channel offload + * + * Copyright (C) 2020-2025 OpenVPN, Inc. + * + * Author: James Yonan <james@openvpn.net> + * Antonio Quartulli <antonio@openvpn.net> + */ + +#include <linux/net.h> +#include <linux/netdevice.h> +#include <linux/udp.h> + +#include "ovpnpriv.h" +#include "main.h" +#include "io.h" +#include "peer.h" +#include "socket.h" +#include "tcp.h" +#include "udp.h" + +static void ovpn_socket_release_kref(struct kref *kref) +{ + struct ovpn_socket *sock = container_of(kref, struct ovpn_socket, + refcount); + + if (sock->sock->sk->sk_protocol == IPPROTO_UDP) + ovpn_udp_socket_detach(sock); + else if (sock->sock->sk->sk_protocol == IPPROTO_TCP) + ovpn_tcp_socket_detach(sock); +} + +/** + * ovpn_socket_put - decrease reference counter + * @peer: peer whose socket reference counter should be decreased + * @sock: the RCU protected peer socket + * + * This function is only used internally. Users willing to release + * references to the ovpn_socket should use ovpn_socket_release() + * + * Return: true if the socket was released, false otherwise + */ +static bool ovpn_socket_put(struct ovpn_peer *peer, struct ovpn_socket *sock) +{ + return kref_put(&sock->refcount, ovpn_socket_release_kref); +} + +/** + * ovpn_socket_release - release resources owned by socket user + * @peer: peer whose socket should be released + * + * This function should be invoked when the peer is being removed + * and wants to drop its link to the socket. + * + * In case of UDP, the detach routine will drop a reference to the + * ovpn netdev, pointed by the ovpn_socket. + * + * In case of TCP, releasing the socket will cause dropping + * the refcounter for the peer it is linked to, thus allowing the peer + * disappear as well. + * + * This function is expected to be invoked exactly once per peer + * + * NOTE: this function may sleep + */ +void ovpn_socket_release(struct ovpn_peer *peer) +{ + struct ovpn_socket *sock; + bool released; + + might_sleep(); + + sock = rcu_replace_pointer(peer->sock, NULL, true); + /* release may be invoked after socket was detached */ + if (!sock) + return; + + /* sanity check: we should not end up here if the socket + * was already closed + */ + if (!sock->sock->sk) { + DEBUG_NET_WARN_ON_ONCE(1); + return; + } + + /* Drop the reference while holding the sock lock to avoid + * concurrent ovpn_socket_new call to mess up with a partially + * detached socket. + * + * Holding the lock ensures that a socket with refcnt 0 is fully + * detached before it can be picked by a concurrent reader. + */ + lock_sock(sock->sock->sk); + released = ovpn_socket_put(peer, sock); + release_sock(sock->sock->sk); + + /* align all readers with sk_user_data being NULL */ + synchronize_rcu(); + + /* following cleanup should happen with lock released */ + if (released) { + if (sock->sock->sk->sk_protocol == IPPROTO_UDP) { + netdev_put(sock->ovpn->dev, &sock->dev_tracker); + } else if (sock->sock->sk->sk_protocol == IPPROTO_TCP) { + /* wait for TCP jobs to terminate */ + ovpn_tcp_socket_wait_finish(sock); + ovpn_peer_put(sock->peer); + } + /* we can call plain kfree() because we already waited one RCU + * period due to synchronize_rcu() + */ + kfree(sock); + } +} + +static bool ovpn_socket_hold(struct ovpn_socket *sock) +{ + return kref_get_unless_zero(&sock->refcount); +} + +static int ovpn_socket_attach(struct ovpn_socket *sock, struct ovpn_peer *peer) +{ + if (sock->sock->sk->sk_protocol == IPPROTO_UDP) + return ovpn_udp_socket_attach(sock, peer->ovpn); + else if (sock->sock->sk->sk_protocol == IPPROTO_TCP) + return ovpn_tcp_socket_attach(sock, peer); + + return -EOPNOTSUPP; +} + +/** + * ovpn_socket_new - create a new socket and initialize it + * @sock: the kernel socket to embed + * @peer: the peer reachable via this socket + * + * Return: an openvpn socket on success or a negative error code otherwise + */ +struct ovpn_socket *ovpn_socket_new(struct socket *sock, struct ovpn_peer *peer) +{ + struct ovpn_socket *ovpn_sock; + int ret; + + lock_sock(sock->sk); + + /* a TCP socket can only be owned by a single peer, therefore there + * can't be any other user + */ + if (sock->sk->sk_protocol == IPPROTO_TCP && sock->sk->sk_user_data) { + ovpn_sock = ERR_PTR(-EBUSY); + goto sock_release; + } + + /* a UDP socket can be shared across multiple peers, but we must make + * sure it is not owned by something else + */ + if (sock->sk->sk_protocol == IPPROTO_UDP) { + u8 type = READ_ONCE(udp_sk(sock->sk)->encap_type); + + /* socket owned by other encapsulation module */ + if (type && type != UDP_ENCAP_OVPNINUDP) { + ovpn_sock = ERR_PTR(-EBUSY); + goto sock_release; + } + + rcu_read_lock(); + ovpn_sock = rcu_dereference_sk_user_data(sock->sk); + if (ovpn_sock) { + /* socket owned by another ovpn instance, we can't use it */ + if (ovpn_sock->ovpn != peer->ovpn) { + ovpn_sock = ERR_PTR(-EBUSY); + rcu_read_unlock(); + goto sock_release; + } + + /* this socket is already owned by this instance, + * therefore we can increase the refcounter and + * use it as expected + */ + if (WARN_ON(!ovpn_socket_hold(ovpn_sock))) { + /* this should never happen because setting + * the refcnt to 0 and detaching the socket + * is expected to be atomic + */ + ovpn_sock = ERR_PTR(-EAGAIN); + rcu_read_unlock(); + goto sock_release; + } + + rcu_read_unlock(); + goto sock_release; + } + rcu_read_unlock(); + } + + /* socket is not owned: attach to this ovpn instance */ + + ovpn_sock = kzalloc(sizeof(*ovpn_sock), GFP_KERNEL); + if (!ovpn_sock) { + ovpn_sock = ERR_PTR(-ENOMEM); + goto sock_release; + } + + ovpn_sock->sock = sock; + kref_init(&ovpn_sock->refcount); + + ret = ovpn_socket_attach(ovpn_sock, peer); + if (ret < 0) { + kfree(ovpn_sock); + ovpn_sock = ERR_PTR(ret); + goto sock_release; + } + + /* TCP sockets are per-peer, therefore they are linked to their unique + * peer + */ + if (sock->sk->sk_protocol == IPPROTO_TCP) { + INIT_WORK(&ovpn_sock->tcp_tx_work, ovpn_tcp_tx_work); + ovpn_sock->peer = peer; + ovpn_peer_hold(peer); + } else 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); + return ovpn_sock; +} diff --git a/drivers/net/ovpn/socket.h b/drivers/net/ovpn/socket.h new file mode 100644 index 000000000000..00d856b1a5d8 --- /dev/null +++ b/drivers/net/ovpn/socket.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* OpenVPN data channel offload + * + * Copyright (C) 2020-2025 OpenVPN, Inc. + * + * Author: James Yonan <james@openvpn.net> + * Antonio Quartulli <antonio@openvpn.net> + */ + +#ifndef _NET_OVPN_SOCK_H_ +#define _NET_OVPN_SOCK_H_ + +#include <linux/net.h> +#include <linux/kref.h> +#include <net/sock.h> + +struct ovpn_priv; +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) + * @peer: unique peer transmitting over this socket (TCP only) + * @sock: the low level sock object + * @refcount: amount of contexts currently referencing this object + * @work: member used to schedule release routine (it may block) + * @tcp_tx_work: work for deferring outgoing packet processing (TCP only) + */ +struct ovpn_socket { + union { + struct { + struct ovpn_priv *ovpn; + netdevice_tracker dev_tracker; + }; + struct ovpn_peer *peer; + }; + + struct socket *sock; + struct kref refcount; + struct work_struct work; + struct work_struct tcp_tx_work; +}; + +struct ovpn_socket *ovpn_socket_new(struct socket *sock, + struct ovpn_peer *peer); +void ovpn_socket_release(struct ovpn_peer *peer); + +#endif /* _NET_OVPN_SOCK_H_ */ diff --git a/drivers/net/ovpn/stats.c b/drivers/net/ovpn/stats.c new file mode 100644 index 000000000000..d637143473bb --- /dev/null +++ b/drivers/net/ovpn/stats.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 +/* OpenVPN data channel offload + * + * Copyright (C) 2020-2025 OpenVPN, Inc. + * + * Author: James Yonan <james@openvpn.net> + * Antonio Quartulli <antonio@openvpn.net> + */ + +#include <linux/atomic.h> + +#include "stats.h" + +void ovpn_peer_stats_init(struct ovpn_peer_stats *ps) +{ + atomic64_set(&ps->rx.bytes, 0); + atomic64_set(&ps->rx.packets, 0); + + atomic64_set(&ps->tx.bytes, 0); + atomic64_set(&ps->tx.packets, 0); +} diff --git a/drivers/net/ovpn/stats.h b/drivers/net/ovpn/stats.h new file mode 100644 index 000000000000..53433d8b6c33 --- /dev/null +++ b/drivers/net/ovpn/stats.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* OpenVPN data channel offload + * + * Copyright (C) 2020-2025 OpenVPN, Inc. + * + * Author: James Yonan <james@openvpn.net> + * Antonio Quartulli <antonio@openvpn.net> + * Lev Stipakov <lev@openvpn.net> + */ + +#ifndef _NET_OVPN_OVPNSTATS_H_ +#define _NET_OVPN_OVPNSTATS_H_ + +/* one stat */ +struct ovpn_peer_stat { + atomic64_t bytes; + atomic64_t packets; +}; + +/* rx and tx stats combined */ +struct ovpn_peer_stats { + struct ovpn_peer_stat rx; + struct ovpn_peer_stat tx; +}; + +void ovpn_peer_stats_init(struct ovpn_peer_stats *ps); + +static inline void ovpn_peer_stats_increment(struct ovpn_peer_stat *stat, + const unsigned int n) +{ + atomic64_add(n, &stat->bytes); + atomic64_inc(&stat->packets); +} + +static inline void ovpn_peer_stats_increment_rx(struct ovpn_peer_stats *stats, + const unsigned int n) +{ + ovpn_peer_stats_increment(&stats->rx, n); +} + +static inline void ovpn_peer_stats_increment_tx(struct ovpn_peer_stats *stats, + const unsigned int n) +{ + ovpn_peer_stats_increment(&stats->tx, n); +} + +#endif /* _NET_OVPN_OVPNSTATS_H_ */ diff --git a/drivers/net/ovpn/tcp.c b/drivers/net/ovpn/tcp.c new file mode 100644 index 000000000000..7c42d84987ad --- /dev/null +++ b/drivers/net/ovpn/tcp.c @@ -0,0 +1,598 @@ +// SPDX-License-Identifier: GPL-2.0 +/* OpenVPN data channel offload + * + * Copyright (C) 2019-2025 OpenVPN, Inc. + * + * Author: Antonio Quartulli <antonio@openvpn.net> + */ + +#include <linux/skbuff.h> +#include <net/hotdata.h> +#include <net/inet_common.h> +#include <net/ipv6.h> +#include <net/tcp.h> +#include <net/transp_v6.h> +#include <net/route.h> +#include <trace/events/sock.h> + +#include "ovpnpriv.h" +#include "main.h" +#include "io.h" +#include "peer.h" +#include "proto.h" +#include "skb.h" +#include "tcp.h" + +#define OVPN_TCP_DEPTH_NESTING 2 +#if OVPN_TCP_DEPTH_NESTING == SINGLE_DEPTH_NESTING +#error "OVPN TCP requires its own lockdep subclass" +#endif + +static struct proto ovpn_tcp_prot __ro_after_init; +static struct proto_ops ovpn_tcp_ops __ro_after_init; +static struct proto ovpn_tcp6_prot __ro_after_init; +static struct proto_ops ovpn_tcp6_ops __ro_after_init; + +static int ovpn_tcp_parse(struct strparser *strp, struct sk_buff *skb) +{ + struct strp_msg *rxm = strp_msg(skb); + __be16 blen; + u16 len; + int err; + + /* when packets are written to the TCP stream, they are prepended with + * two bytes indicating the actual packet size. + * Parse accordingly and return the actual size (including the size + * header) + */ + + if (skb->len < rxm->offset + 2) + return 0; + + err = skb_copy_bits(skb, rxm->offset, &blen, sizeof(blen)); + if (err < 0) + return err; + + len = be16_to_cpu(blen); + if (len < 2) + return -EINVAL; + + return len + 2; +} + +/* queue skb for sending to userspace via recvmsg on the socket */ +static void ovpn_tcp_to_userspace(struct ovpn_peer *peer, struct sock *sk, + struct sk_buff *skb) +{ + skb_set_owner_r(skb, sk); + memset(skb->cb, 0, sizeof(skb->cb)); + skb_queue_tail(&peer->tcp.user_queue, skb); + peer->tcp.sk_cb.sk_data_ready(sk); +} + +static void ovpn_tcp_rcv(struct strparser *strp, struct sk_buff *skb) +{ + struct ovpn_peer *peer = container_of(strp, struct ovpn_peer, tcp.strp); + struct strp_msg *msg = strp_msg(skb); + size_t pkt_len = msg->full_len - 2; + size_t off = msg->offset + 2; + u8 opcode; + + /* ensure skb->data points to the beginning of the openvpn packet */ + if (!pskb_pull(skb, off)) { + net_warn_ratelimited("%s: packet too small for peer %u\n", + netdev_name(peer->ovpn->dev), peer->id); + goto err; + } + + /* strparser does not trim the skb for us, therefore we do it now */ + if (pskb_trim(skb, pkt_len) != 0) { + net_warn_ratelimited("%s: trimming skb failed for peer %u\n", + netdev_name(peer->ovpn->dev), peer->id); + goto err; + } + + /* we need the first 4 bytes of data to be accessible + * to extract the opcode and the key ID later on + */ + if (!pskb_may_pull(skb, OVPN_OPCODE_SIZE)) { + net_warn_ratelimited("%s: packet too small to fetch opcode for peer %u\n", + netdev_name(peer->ovpn->dev), peer->id); + goto err; + } + + /* DATA_V2 packets are handled in kernel, the rest goes to user space */ + opcode = ovpn_opcode_from_skb(skb, 0); + if (unlikely(opcode != OVPN_DATA_V2)) { + if (opcode == OVPN_DATA_V1) { + net_warn_ratelimited("%s: DATA_V1 detected on the TCP stream\n", + netdev_name(peer->ovpn->dev)); + goto err; + } + + /* The packet size header must be there when sending the packet + * to userspace, therefore we put it back + */ + skb_push(skb, 2); + ovpn_tcp_to_userspace(peer, strp->sk, skb); + return; + } + + /* hold reference to peer as required by ovpn_recv(). + * + * NOTE: in this context we should already be holding a reference to + * this peer, therefore ovpn_peer_hold() is not expected to fail + */ + if (WARN_ON(!ovpn_peer_hold(peer))) + goto err; + + ovpn_recv(peer, skb); + return; +err: + dev_dstats_rx_dropped(peer->ovpn->dev); + kfree_skb(skb); + ovpn_peer_del(peer, OVPN_DEL_PEER_REASON_TRANSPORT_ERROR); +} + +static int ovpn_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, + int flags, int *addr_len) +{ + int err = 0, off, copied = 0, ret; + struct ovpn_socket *sock; + struct ovpn_peer *peer; + struct sk_buff *skb; + + rcu_read_lock(); + sock = rcu_dereference_sk_user_data(sk); + if (unlikely(!sock || !sock->peer || !ovpn_peer_hold(sock->peer))) { + rcu_read_unlock(); + return -EBADF; + } + peer = sock->peer; + rcu_read_unlock(); + + skb = __skb_recv_datagram(sk, &peer->tcp.user_queue, flags, &off, &err); + if (!skb) { + if (err == -EAGAIN && sk->sk_shutdown & RCV_SHUTDOWN) { + ret = 0; + goto out; + } + ret = err; + goto out; + } + + copied = len; + if (copied > skb->len) + copied = skb->len; + else if (copied < skb->len) + msg->msg_flags |= MSG_TRUNC; + + err = skb_copy_datagram_msg(skb, 0, msg, copied); + if (unlikely(err)) { + kfree_skb(skb); + ret = err; + goto out; + } + + if (flags & MSG_TRUNC) + copied = skb->len; + kfree_skb(skb); + ret = copied; +out: + ovpn_peer_put(peer); + return ret; +} + +void ovpn_tcp_socket_detach(struct ovpn_socket *ovpn_sock) +{ + struct ovpn_peer *peer = ovpn_sock->peer; + struct socket *sock = ovpn_sock->sock; + + strp_stop(&peer->tcp.strp); + skb_queue_purge(&peer->tcp.user_queue); + + /* restore CBs that were saved in ovpn_sock_set_tcp_cb() */ + sock->sk->sk_data_ready = peer->tcp.sk_cb.sk_data_ready; + sock->sk->sk_write_space = peer->tcp.sk_cb.sk_write_space; + sock->sk->sk_prot = peer->tcp.sk_cb.prot; + sock->sk->sk_socket->ops = peer->tcp.sk_cb.ops; + + rcu_assign_sk_user_data(sock->sk, NULL); +} + +void ovpn_tcp_socket_wait_finish(struct ovpn_socket *sock) +{ + struct ovpn_peer *peer = sock->peer; + + /* NOTE: we don't wait for peer->tcp.defer_del_work to finish: + * either the worker is not running or this function + * was invoked by that worker. + */ + + cancel_work_sync(&sock->tcp_tx_work); + strp_done(&peer->tcp.strp); + + skb_queue_purge(&peer->tcp.out_queue); + kfree_skb(peer->tcp.out_msg.skb); + peer->tcp.out_msg.skb = NULL; +} + +static void ovpn_tcp_send_sock(struct ovpn_peer *peer, struct sock *sk) +{ + struct sk_buff *skb = peer->tcp.out_msg.skb; + int ret, flags; + + if (!skb) + return; + + if (peer->tcp.tx_in_progress) + return; + + peer->tcp.tx_in_progress = true; + + do { + flags = ovpn_skb_cb(skb)->nosignal ? MSG_NOSIGNAL : 0; + ret = skb_send_sock_locked_with_flags(sk, skb, + peer->tcp.out_msg.offset, + peer->tcp.out_msg.len, + flags); + if (unlikely(ret < 0)) { + if (ret == -EAGAIN) + goto out; + + net_warn_ratelimited("%s: TCP error to peer %u: %d\n", + netdev_name(peer->ovpn->dev), + peer->id, ret); + + /* in case of TCP error we can't recover the VPN + * stream therefore we abort the connection + */ + ovpn_peer_hold(peer); + schedule_work(&peer->tcp.defer_del_work); + + /* we bail out immediately and keep tx_in_progress set + * to true. This way we prevent more TX attempts + * which would lead to more invocations of + * schedule_work() + */ + return; + } + + peer->tcp.out_msg.len -= ret; + peer->tcp.out_msg.offset += ret; + } while (peer->tcp.out_msg.len > 0); + + if (!peer->tcp.out_msg.len) { + preempt_disable(); + dev_dstats_tx_add(peer->ovpn->dev, skb->len); + preempt_enable(); + } + + kfree_skb(peer->tcp.out_msg.skb); + peer->tcp.out_msg.skb = NULL; + peer->tcp.out_msg.len = 0; + peer->tcp.out_msg.offset = 0; + +out: + peer->tcp.tx_in_progress = false; +} + +void ovpn_tcp_tx_work(struct work_struct *work) +{ + struct ovpn_socket *sock; + + sock = container_of(work, struct ovpn_socket, tcp_tx_work); + + lock_sock(sock->sock->sk); + if (sock->peer) + ovpn_tcp_send_sock(sock->peer, sock->sock->sk); + release_sock(sock->sock->sk); +} + +static void ovpn_tcp_send_sock_skb(struct ovpn_peer *peer, struct sock *sk, + struct sk_buff *skb) +{ + if (peer->tcp.out_msg.skb) + ovpn_tcp_send_sock(peer, sk); + + if (peer->tcp.out_msg.skb) { + dev_dstats_tx_dropped(peer->ovpn->dev); + kfree_skb(skb); + return; + } + + peer->tcp.out_msg.skb = skb; + peer->tcp.out_msg.len = skb->len; + peer->tcp.out_msg.offset = 0; + ovpn_tcp_send_sock(peer, sk); +} + +void ovpn_tcp_send_skb(struct ovpn_peer *peer, struct socket *sock, + struct sk_buff *skb) +{ + u16 len = skb->len; + + *(__be16 *)__skb_push(skb, sizeof(u16)) = htons(len); + + spin_lock_nested(&sock->sk->sk_lock.slock, OVPN_TCP_DEPTH_NESTING); + if (sock_owned_by_user(sock->sk)) { + if (skb_queue_len(&peer->tcp.out_queue) >= + READ_ONCE(net_hotdata.max_backlog)) { + dev_dstats_tx_dropped(peer->ovpn->dev); + kfree_skb(skb); + goto unlock; + } + __skb_queue_tail(&peer->tcp.out_queue, skb); + } else { + ovpn_tcp_send_sock_skb(peer, sock->sk, skb); + } +unlock: + spin_unlock(&sock->sk->sk_lock.slock); +} + +static void ovpn_tcp_release(struct sock *sk) +{ + struct sk_buff_head queue; + struct ovpn_socket *sock; + struct ovpn_peer *peer; + struct sk_buff *skb; + + rcu_read_lock(); + sock = rcu_dereference_sk_user_data(sk); + if (!sock) { + rcu_read_unlock(); + return; + } + + peer = sock->peer; + + /* during initialization this function is called before + * assigning sock->peer + */ + if (unlikely(!peer || !ovpn_peer_hold(peer))) { + rcu_read_unlock(); + return; + } + rcu_read_unlock(); + + __skb_queue_head_init(&queue); + skb_queue_splice_init(&peer->tcp.out_queue, &queue); + + while ((skb = __skb_dequeue(&queue))) + ovpn_tcp_send_sock_skb(peer, sk, skb); + + peer->tcp.sk_cb.prot->release_cb(sk); + ovpn_peer_put(peer); +} + +static int ovpn_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) +{ + struct ovpn_socket *sock; + int ret, linear = PAGE_SIZE; + struct ovpn_peer *peer; + struct sk_buff *skb; + + lock_sock(sk); + rcu_read_lock(); + sock = rcu_dereference_sk_user_data(sk); + if (unlikely(!sock || !sock->peer || !ovpn_peer_hold(sock->peer))) { + rcu_read_unlock(); + release_sock(sk); + return -EIO; + } + rcu_read_unlock(); + peer = sock->peer; + + if (msg->msg_flags & ~(MSG_DONTWAIT | MSG_NOSIGNAL)) { + ret = -EOPNOTSUPP; + goto peer_free; + } + + if (peer->tcp.out_msg.skb) { + ret = -EAGAIN; + goto peer_free; + } + + if (size < linear) + linear = size; + + skb = sock_alloc_send_pskb(sk, linear, size - linear, + msg->msg_flags & MSG_DONTWAIT, &ret, 0); + if (!skb) { + net_err_ratelimited("%s: skb alloc failed: %d\n", + netdev_name(peer->ovpn->dev), ret); + goto peer_free; + } + + skb_put(skb, linear); + skb->len = size; + skb->data_len = size - linear; + + ret = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size); + if (ret) { + kfree_skb(skb); + net_err_ratelimited("%s: skb copy from iter failed: %d\n", + netdev_name(peer->ovpn->dev), ret); + goto peer_free; + } + + ovpn_skb_cb(skb)->nosignal = msg->msg_flags & MSG_NOSIGNAL; + ovpn_tcp_send_sock_skb(peer, sk, skb); + ret = size; +peer_free: + release_sock(sk); + ovpn_peer_put(peer); + return ret; +} + +static int ovpn_tcp_disconnect(struct sock *sk, int flags) +{ + return -EBUSY; +} + +static void ovpn_tcp_data_ready(struct sock *sk) +{ + struct ovpn_socket *sock; + + trace_sk_data_ready(sk); + + rcu_read_lock(); + sock = rcu_dereference_sk_user_data(sk); + if (likely(sock && sock->peer)) + strp_data_ready(&sock->peer->tcp.strp); + rcu_read_unlock(); +} + +static void ovpn_tcp_write_space(struct sock *sk) +{ + struct ovpn_socket *sock; + + rcu_read_lock(); + sock = rcu_dereference_sk_user_data(sk); + if (likely(sock && sock->peer)) { + schedule_work(&sock->tcp_tx_work); + sock->peer->tcp.sk_cb.sk_write_space(sk); + } + rcu_read_unlock(); +} + +static void ovpn_tcp_build_protos(struct proto *new_prot, + struct proto_ops *new_ops, + const struct proto *orig_prot, + const struct proto_ops *orig_ops); + +static void ovpn_tcp_peer_del_work(struct work_struct *work) +{ + struct ovpn_peer *peer = container_of(work, struct ovpn_peer, + tcp.defer_del_work); + + ovpn_peer_del(peer, OVPN_DEL_PEER_REASON_TRANSPORT_ERROR); + ovpn_peer_put(peer); +} + +/* Set TCP encapsulation callbacks */ +int ovpn_tcp_socket_attach(struct ovpn_socket *ovpn_sock, + struct ovpn_peer *peer) +{ + struct socket *sock = ovpn_sock->sock; + struct strp_callbacks cb = { + .rcv_msg = ovpn_tcp_rcv, + .parse_msg = ovpn_tcp_parse, + }; + int ret; + + /* make sure no pre-existing encapsulation handler exists */ + if (sock->sk->sk_user_data) + return -EBUSY; + + /* only a fully connected socket is expected. Connection should be + * handled in userspace + */ + if (sock->sk->sk_state != TCP_ESTABLISHED) { + net_err_ratelimited("%s: provided TCP socket is not in ESTABLISHED state: %d\n", + netdev_name(peer->ovpn->dev), + sock->sk->sk_state); + return -EINVAL; + } + + ret = strp_init(&peer->tcp.strp, sock->sk, &cb); + if (ret < 0) { + DEBUG_NET_WARN_ON_ONCE(1); + return ret; + } + + INIT_WORK(&peer->tcp.defer_del_work, ovpn_tcp_peer_del_work); + + __sk_dst_reset(sock->sk); + skb_queue_head_init(&peer->tcp.user_queue); + skb_queue_head_init(&peer->tcp.out_queue); + + /* save current CBs so that they can be restored upon socket release */ + peer->tcp.sk_cb.sk_data_ready = sock->sk->sk_data_ready; + peer->tcp.sk_cb.sk_write_space = sock->sk->sk_write_space; + peer->tcp.sk_cb.prot = sock->sk->sk_prot; + peer->tcp.sk_cb.ops = sock->sk->sk_socket->ops; + + /* assign our static CBs and prot/ops */ + sock->sk->sk_data_ready = ovpn_tcp_data_ready; + sock->sk->sk_write_space = ovpn_tcp_write_space; + + if (sock->sk->sk_family == AF_INET) { + sock->sk->sk_prot = &ovpn_tcp_prot; + sock->sk->sk_socket->ops = &ovpn_tcp_ops; + } else { + sock->sk->sk_prot = &ovpn_tcp6_prot; + sock->sk->sk_socket->ops = &ovpn_tcp6_ops; + } + + /* avoid using task_frag */ + sock->sk->sk_allocation = GFP_ATOMIC; + sock->sk->sk_use_task_frag = false; + + /* enqueue the RX worker */ + strp_check_rcv(&peer->tcp.strp); + + return 0; +} + +static void ovpn_tcp_close(struct sock *sk, long timeout) +{ + struct ovpn_socket *sock; + struct ovpn_peer *peer; + + rcu_read_lock(); + sock = rcu_dereference_sk_user_data(sk); + if (!sock || !sock->peer || !ovpn_peer_hold(sock->peer)) { + rcu_read_unlock(); + return; + } + peer = sock->peer; + rcu_read_unlock(); + + ovpn_peer_del(sock->peer, OVPN_DEL_PEER_REASON_TRANSPORT_DISCONNECT); + peer->tcp.sk_cb.prot->close(sk, timeout); + ovpn_peer_put(peer); +} + +static __poll_t ovpn_tcp_poll(struct file *file, struct socket *sock, + poll_table *wait) +{ + __poll_t mask = datagram_poll(file, sock, wait); + struct ovpn_socket *ovpn_sock; + + rcu_read_lock(); + ovpn_sock = rcu_dereference_sk_user_data(sock->sk); + if (ovpn_sock && ovpn_sock->peer && + !skb_queue_empty(&ovpn_sock->peer->tcp.user_queue)) + mask |= EPOLLIN | EPOLLRDNORM; + rcu_read_unlock(); + + return mask; +} + +static void ovpn_tcp_build_protos(struct proto *new_prot, + struct proto_ops *new_ops, + const struct proto *orig_prot, + const struct proto_ops *orig_ops) +{ + memcpy(new_prot, orig_prot, sizeof(*new_prot)); + memcpy(new_ops, orig_ops, sizeof(*new_ops)); + new_prot->recvmsg = ovpn_tcp_recvmsg; + new_prot->sendmsg = ovpn_tcp_sendmsg; + new_prot->disconnect = ovpn_tcp_disconnect; + new_prot->close = ovpn_tcp_close; + new_prot->release_cb = ovpn_tcp_release; + new_ops->poll = ovpn_tcp_poll; +} + +/* Initialize TCP static objects */ +void __init ovpn_tcp_init(void) +{ + ovpn_tcp_build_protos(&ovpn_tcp_prot, &ovpn_tcp_ops, &tcp_prot, + &inet_stream_ops); + +#if IS_ENABLED(CONFIG_IPV6) + ovpn_tcp_build_protos(&ovpn_tcp6_prot, &ovpn_tcp6_ops, &tcpv6_prot, + &inet6_stream_ops); +#endif +} diff --git a/drivers/net/ovpn/tcp.h b/drivers/net/ovpn/tcp.h new file mode 100644 index 000000000000..10aefa834cf3 --- /dev/null +++ b/drivers/net/ovpn/tcp.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* OpenVPN data channel offload + * + * Copyright (C) 2019-2025 OpenVPN, Inc. + * + * Author: Antonio Quartulli <antonio@openvpn.net> + */ + +#ifndef _NET_OVPN_TCP_H_ +#define _NET_OVPN_TCP_H_ + +#include <linux/net.h> +#include <linux/skbuff.h> +#include <linux/types.h> + +#include "peer.h" +#include "skb.h" +#include "socket.h" + +void __init ovpn_tcp_init(void); + +int ovpn_tcp_socket_attach(struct ovpn_socket *ovpn_sock, + struct ovpn_peer *peer); +void ovpn_tcp_socket_detach(struct ovpn_socket *ovpn_sock); +void ovpn_tcp_socket_wait_finish(struct ovpn_socket *sock); + +/* Prepare skb and enqueue it for sending to peer. + * + * Preparation consist in prepending the skb payload with its size. + * Required by the OpenVPN protocol in order to extract packets from + * the TCP stream on the receiver side. + */ +void ovpn_tcp_send_skb(struct ovpn_peer *peer, struct socket *sock, struct sk_buff *skb); +void ovpn_tcp_tx_work(struct work_struct *work); + +#endif /* _NET_OVPN_TCP_H_ */ diff --git a/drivers/net/ovpn/udp.c b/drivers/net/ovpn/udp.c new file mode 100644 index 000000000000..aef8c0406ec9 --- /dev/null +++ b/drivers/net/ovpn/udp.c @@ -0,0 +1,449 @@ +// SPDX-License-Identifier: GPL-2.0 +/* OpenVPN data channel offload + * + * Copyright (C) 2019-2025 OpenVPN, Inc. + * + * Author: Antonio Quartulli <antonio@openvpn.net> + */ + +#include <linux/netdevice.h> +#include <linux/inetdevice.h> +#include <linux/skbuff.h> +#include <linux/socket.h> +#include <linux/udp.h> +#include <net/addrconf.h> +#include <net/dst_cache.h> +#include <net/route.h> +#include <net/ipv6_stubs.h> +#include <net/transp_v6.h> +#include <net/udp.h> +#include <net/udp_tunnel.h> + +#include "ovpnpriv.h" +#include "main.h" +#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 accepted for further processing, + * - DATA_V1 the packet is dropped as not supported, + * - anything else the packet 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_dstats_rx_dropped(ovpn->dev); +drop_noovpn: + kfree_skb(skb); + return 0; +} + +/** + * ovpn_udp4_output - send IPv4 packet over udp socket + * @peer: the destination peer + * @bind: the binding related to the destination peer + * @cache: dst cache + * @sk: the socket to send the packet over + * @skb: the packet to send + * + * Return: 0 on success or a negative error code otherwise + */ +static int ovpn_udp4_output(struct ovpn_peer *peer, struct ovpn_bind *bind, + struct dst_cache *cache, struct sock *sk, + struct sk_buff *skb) +{ + struct rtable *rt; + struct flowi4 fl = { + .saddr = bind->local.ipv4.s_addr, + .daddr = bind->remote.in4.sin_addr.s_addr, + .fl4_sport = inet_sk(sk)->inet_sport, + .fl4_dport = bind->remote.in4.sin_port, + .flowi4_proto = sk->sk_protocol, + .flowi4_mark = sk->sk_mark, + }; + int ret; + + local_bh_disable(); + rt = dst_cache_get_ip4(cache, &fl.saddr); + if (rt) + goto transmit; + + if (unlikely(!inet_confirm_addr(sock_net(sk), NULL, 0, fl.saddr, + RT_SCOPE_HOST))) { + /* we may end up here when the cached address is not usable + * anymore. In this case we reset address/cache and perform a + * new look up + */ + fl.saddr = 0; + spin_lock_bh(&peer->lock); + bind->local.ipv4.s_addr = 0; + spin_unlock_bh(&peer->lock); + dst_cache_reset(cache); + } + + rt = ip_route_output_flow(sock_net(sk), &fl, sk); + if (IS_ERR(rt) && PTR_ERR(rt) == -EINVAL) { + fl.saddr = 0; + spin_lock_bh(&peer->lock); + bind->local.ipv4.s_addr = 0; + spin_unlock_bh(&peer->lock); + dst_cache_reset(cache); + + rt = ip_route_output_flow(sock_net(sk), &fl, sk); + } + + if (IS_ERR(rt)) { + ret = PTR_ERR(rt); + net_dbg_ratelimited("%s: no route to host %pISpc: %d\n", + netdev_name(peer->ovpn->dev), + &bind->remote.in4, + ret); + goto err; + } + dst_cache_set_ip4(cache, &rt->dst, fl.saddr); + +transmit: + udp_tunnel_xmit_skb(rt, sk, skb, fl.saddr, fl.daddr, 0, + ip4_dst_hoplimit(&rt->dst), 0, fl.fl4_sport, + fl.fl4_dport, false, sk->sk_no_check_tx); + ret = 0; +err: + local_bh_enable(); + return ret; +} + +#if IS_ENABLED(CONFIG_IPV6) +/** + * ovpn_udp6_output - send IPv6 packet over udp socket + * @peer: the destination peer + * @bind: the binding related to the destination peer + * @cache: dst cache + * @sk: the socket to send the packet over + * @skb: the packet to send + * + * Return: 0 on success or a negative error code otherwise + */ +static int ovpn_udp6_output(struct ovpn_peer *peer, struct ovpn_bind *bind, + struct dst_cache *cache, struct sock *sk, + struct sk_buff *skb) +{ + struct dst_entry *dst; + int ret; + + struct flowi6 fl = { + .saddr = bind->local.ipv6, + .daddr = bind->remote.in6.sin6_addr, + .fl6_sport = inet_sk(sk)->inet_sport, + .fl6_dport = bind->remote.in6.sin6_port, + .flowi6_proto = sk->sk_protocol, + .flowi6_mark = sk->sk_mark, + .flowi6_oif = bind->remote.in6.sin6_scope_id, + }; + + local_bh_disable(); + dst = dst_cache_get_ip6(cache, &fl.saddr); + if (dst) + goto transmit; + + if (unlikely(!ipv6_chk_addr(sock_net(sk), &fl.saddr, NULL, 0))) { + /* we may end up here when the cached address is not usable + * anymore. In this case we reset address/cache and perform a + * new look up + */ + fl.saddr = in6addr_any; + spin_lock_bh(&peer->lock); + bind->local.ipv6 = in6addr_any; + spin_unlock_bh(&peer->lock); + dst_cache_reset(cache); + } + + dst = ipv6_stub->ipv6_dst_lookup_flow(sock_net(sk), sk, &fl, NULL); + if (IS_ERR(dst)) { + ret = PTR_ERR(dst); + net_dbg_ratelimited("%s: no route to host %pISpc: %d\n", + netdev_name(peer->ovpn->dev), + &bind->remote.in6, ret); + goto err; + } + dst_cache_set_ip6(cache, dst, &fl.saddr); + +transmit: + /* user IPv6 packets may be larger than the transport interface + * MTU (after encapsulation), however, since they are locally + * generated we should ensure they get fragmented. + * Setting the ignore_df flag to 1 will instruct ip6_fragment() to + * fragment packets if needed. + * + * NOTE: this is not needed for IPv4 because we pass df=0 to + * udp_tunnel_xmit_skb() + */ + skb->ignore_df = 1; + udp_tunnel6_xmit_skb(dst, sk, skb, skb->dev, &fl.saddr, &fl.daddr, 0, + ip6_dst_hoplimit(dst), 0, fl.fl6_sport, + fl.fl6_dport, udp_get_no_check6_tx(sk)); + ret = 0; +err: + local_bh_enable(); + return ret; +} +#endif + +/** + * ovpn_udp_output - transmit skb using udp-tunnel + * @peer: the destination peer + * @cache: dst cache + * @sk: the socket to send the packet over + * @skb: the packet to send + * + * rcu_read_lock should be held on entry. + * On return, the skb is consumed. + * + * Return: 0 on success or a negative error code otherwise + */ +static int ovpn_udp_output(struct ovpn_peer *peer, struct dst_cache *cache, + struct sock *sk, struct sk_buff *skb) +{ + struct ovpn_bind *bind; + int ret; + + /* set sk to null if skb is already orphaned */ + if (!skb->destructor) + skb->sk = NULL; + + rcu_read_lock(); + bind = rcu_dereference(peer->bind); + if (unlikely(!bind)) { + net_warn_ratelimited("%s: no bind for remote peer %u\n", + netdev_name(peer->ovpn->dev), peer->id); + ret = -ENODEV; + goto out; + } + + switch (bind->remote.in4.sin_family) { + case AF_INET: + ret = ovpn_udp4_output(peer, bind, cache, sk, skb); + break; +#if IS_ENABLED(CONFIG_IPV6) + case AF_INET6: + ret = ovpn_udp6_output(peer, bind, cache, sk, skb); + break; +#endif + default: + ret = -EAFNOSUPPORT; + break; + } + +out: + rcu_read_unlock(); + return ret; +} + +/** + * ovpn_udp_send_skb - prepare skb and send it over via UDP + * @peer: the destination peer + * @sock: the RCU protected peer socket + * @skb: the packet to send + */ +void ovpn_udp_send_skb(struct ovpn_peer *peer, struct socket *sock, + struct sk_buff *skb) +{ + int ret = -1; + + skb->dev = peer->ovpn->dev; + /* no checksum performed at this layer */ + skb->ip_summed = CHECKSUM_NONE; + + /* get socket info */ + if (unlikely(!sock)) { + net_warn_ratelimited("%s: no sock for remote peer %u\n", + netdev_name(peer->ovpn->dev), peer->id); + goto out; + } + + /* crypto layer -> transport (UDP) */ + ret = ovpn_udp_output(peer, &peer->dst_cache, sock->sk, skb); +out: + if (unlikely(ret < 0)) { + kfree_skb(skb); + return; + } +} + +static void ovpn_udp_encap_destroy(struct sock *sk) +{ + struct ovpn_socket *sock; + struct ovpn_priv *ovpn; + + rcu_read_lock(); + sock = rcu_dereference_sk_user_data(sk); + if (!sock || !sock->ovpn) { + rcu_read_unlock(); + return; + } + ovpn = sock->ovpn; + rcu_read_unlock(); + + ovpn_peers_free(ovpn, sk, OVPN_DEL_PEER_REASON_TRANSPORT_DISCONNECT); +} + +/** + * ovpn_udp_socket_attach - set udp-tunnel CBs on socket and link it to ovpn + * @ovpn_sock: socket to configure + * @ovpn: the openvp instance to link + * + * After invoking this function, the sock will be controlled by ovpn so that + * any incoming packet may be processed by ovpn first. + * + * Return: 0 on success or a negative error code otherwise + */ +int ovpn_udp_socket_attach(struct ovpn_socket *ovpn_sock, + struct ovpn_priv *ovpn) +{ + struct udp_tunnel_sock_cfg cfg = { + .encap_type = UDP_ENCAP_OVPNINUDP, + .encap_rcv = ovpn_udp_encap_recv, + .encap_destroy = ovpn_udp_encap_destroy, + }; + struct socket *sock = ovpn_sock->sock; + struct ovpn_socket *old_data; + int ret; + + /* make sure no pre-existing encapsulation handler exists */ + rcu_read_lock(); + old_data = rcu_dereference_sk_user_data(sock->sk); + 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; + } + + /* socket is in use. We need to understand if it's owned by this ovpn + * instance or by something else. + * In the former case, we can increase the refcounter and happily + * use it, because the same UDP socket is expected to be shared among + * different peers. + * + * Unlikely TCP, a single UDP socket can be used to talk to many remote + * hosts and therefore openvpn instantiates one only for all its peers + */ + if ((READ_ONCE(udp_sk(sock->sk)->encap_type) == UDP_ENCAP_OVPNINUDP) && + old_data->ovpn == ovpn) { + netdev_dbg(ovpn->dev, + "provided socket already owned by this interface\n"); + ret = -EALREADY; + } else { + netdev_dbg(ovpn->dev, + "provided socket already taken by other user\n"); + ret = -EBUSY; + } + rcu_read_unlock(); + + return ret; +} + +/** + * ovpn_udp_socket_detach - clean udp-tunnel status for this socket + * @ovpn_sock: the socket to clean + */ +void ovpn_udp_socket_detach(struct ovpn_socket *ovpn_sock) +{ + struct udp_tunnel_sock_cfg cfg = { }; + + setup_udp_tunnel_sock(sock_net(ovpn_sock->sock->sk), ovpn_sock->sock, + &cfg); +} diff --git a/drivers/net/ovpn/udp.h b/drivers/net/ovpn/udp.h new file mode 100644 index 000000000000..9994eb6e0428 --- /dev/null +++ b/drivers/net/ovpn/udp.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* OpenVPN data channel offload + * + * Copyright (C) 2019-2025 OpenVPN, Inc. + * + * Author: Antonio Quartulli <antonio@openvpn.net> + */ + +#ifndef _NET_OVPN_UDP_H_ +#define _NET_OVPN_UDP_H_ + +#include <net/sock.h> + +struct ovpn_peer; +struct ovpn_priv; +struct socket; + +int ovpn_udp_socket_attach(struct ovpn_socket *ovpn_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 socket *sock, + struct sk_buff *skb); + +#endif /* _NET_OVPN_UDP_H_ */ |