1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
|
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
*/
#ifndef _WG_QUEUEING_H
#define _WG_QUEUEING_H
#include "peer.h"
#include <linux/types.h>
#include <linux/skbuff.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <net/ip_tunnels.h>
struct wg_device;
struct wg_peer;
struct multicore_worker;
struct crypt_queue;
struct prev_queue;
struct sk_buff;
/* queueing.c APIs: */
int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function,
unsigned int len);
void wg_packet_queue_free(struct crypt_queue *queue);
struct multicore_worker __percpu *
wg_packet_percpu_multicore_worker_alloc(work_func_t function, void *ptr);
/* receive.c APIs: */
void wg_packet_receive(struct wg_device *wg, struct sk_buff *skb);
void wg_packet_handshake_receive_worker(struct work_struct *work);
/* NAPI poll function: */
int wg_packet_rx_poll(struct napi_struct *napi, int budget);
/* Workqueue worker: */
void wg_packet_decrypt_worker(struct work_struct *work);
/* send.c APIs: */
void wg_packet_send_queued_handshake_initiation(struct wg_peer *peer,
bool is_retry);
void wg_packet_send_handshake_response(struct wg_peer *peer);
void wg_packet_send_handshake_cookie(struct wg_device *wg,
struct sk_buff *initiating_skb,
__le32 sender_index);
void wg_packet_send_keepalive(struct wg_peer *peer);
void wg_packet_purge_staged_packets(struct wg_peer *peer);
void wg_packet_send_staged_packets(struct wg_peer *peer);
/* Workqueue workers: */
void wg_packet_handshake_send_worker(struct work_struct *work);
void wg_packet_tx_worker(struct work_struct *work);
void wg_packet_encrypt_worker(struct work_struct *work);
enum packet_state {
PACKET_STATE_UNCRYPTED,
PACKET_STATE_CRYPTED,
PACKET_STATE_DEAD
};
struct packet_cb {
u64 nonce;
struct noise_keypair *keypair;
atomic_t state;
u32 mtu;
u8 ds;
};
#define PACKET_CB(skb) ((struct packet_cb *)((skb)->cb))
#define PACKET_PEER(skb) (PACKET_CB(skb)->keypair->entry.peer)
static inline bool wg_check_packet_protocol(struct sk_buff *skb)
{
__be16 real_protocol = ip_tunnel_parse_protocol(skb);
return real_protocol && skb->protocol == real_protocol;
}
static inline void wg_reset_packet(struct sk_buff *skb, bool encapsulating)
{
u8 l4_hash = skb->l4_hash;
u8 sw_hash = skb->sw_hash;
u32 hash = skb->hash;
skb_scrub_packet(skb, true);
memset(&skb->headers, 0, sizeof(skb->headers));
if (encapsulating) {
skb->l4_hash = l4_hash;
skb->sw_hash = sw_hash;
skb->hash = hash;
}
skb->queue_mapping = 0;
skb->nohdr = 0;
skb->peeked = 0;
skb->mac_len = 0;
skb->dev = NULL;
#ifdef CONFIG_NET_SCHED
skb->tc_index = 0;
#endif
skb_reset_redirect(skb);
skb->hdr_len = skb_headroom(skb);
skb_reset_mac_header(skb);
skb_reset_network_header(skb);
skb_reset_transport_header(skb);
skb_probe_transport_header(skb);
skb_reset_inner_headers(skb);
}
static inline int wg_cpumask_choose_online(int *stored_cpu, unsigned int id)
{
unsigned int cpu = *stored_cpu, cpu_index, i;
if (unlikely(cpu == nr_cpumask_bits ||
!cpumask_test_cpu(cpu, cpu_online_mask))) {
cpu_index = id % cpumask_weight(cpu_online_mask);
cpu = cpumask_first(cpu_online_mask);
for (i = 0; i < cpu_index; ++i)
cpu = cpumask_next(cpu, cpu_online_mask);
*stored_cpu = cpu;
}
return cpu;
}
/* This function is racy, in the sense that next is unlocked, so it could return
* the same CPU twice. A race-free version of this would be to instead store an
* atomic sequence number, do an increment-and-return, and then iterate through
* every possible CPU until we get to that index -- choose_cpu. However that's
* a bit slower, and it doesn't seem like this potential race actually
* introduces any performance loss, so we live with it.
*/
static inline int wg_cpumask_next_online(int *next)
{
int cpu = *next;
while (unlikely(!cpumask_test_cpu(cpu, cpu_online_mask)))
cpu = cpumask_next(cpu, cpu_online_mask) % nr_cpumask_bits;
*next = cpumask_next(cpu, cpu_online_mask) % nr_cpumask_bits;
return cpu;
}
void wg_prev_queue_init(struct prev_queue *queue);
/* Multi producer */
bool wg_prev_queue_enqueue(struct prev_queue *queue, struct sk_buff *skb);
/* Single consumer */
struct sk_buff *wg_prev_queue_dequeue(struct prev_queue *queue);
/* Single consumer */
static inline struct sk_buff *wg_prev_queue_peek(struct prev_queue *queue)
{
if (queue->peeked)
return queue->peeked;
queue->peeked = wg_prev_queue_dequeue(queue);
return queue->peeked;
}
/* Single consumer */
static inline void wg_prev_queue_drop_peeked(struct prev_queue *queue)
{
queue->peeked = NULL;
}
static inline int wg_queue_enqueue_per_device_and_peer(
struct crypt_queue *device_queue, struct prev_queue *peer_queue,
struct sk_buff *skb, struct workqueue_struct *wq, int *next_cpu)
{
int cpu;
atomic_set_release(&PACKET_CB(skb)->state, PACKET_STATE_UNCRYPTED);
/* We first queue this up for the peer ingestion, but the consumer
* will wait for the state to change to CRYPTED or DEAD before.
*/
if (unlikely(!wg_prev_queue_enqueue(peer_queue, skb)))
return -ENOSPC;
/* Then we queue it up in the device queue, which consumes the
* packet as soon as it can.
*/
cpu = wg_cpumask_next_online(next_cpu);
if (unlikely(ptr_ring_produce_bh(&device_queue->ring, skb)))
return -EPIPE;
queue_work_on(cpu, wq, &per_cpu_ptr(device_queue->worker, cpu)->work);
return 0;
}
static inline void wg_queue_enqueue_per_peer_tx(struct sk_buff *skb, enum packet_state state)
{
/* We take a reference, because as soon as we call atomic_set, the
* peer can be freed from below us.
*/
struct wg_peer *peer = wg_peer_get(PACKET_PEER(skb));
atomic_set_release(&PACKET_CB(skb)->state, state);
queue_work_on(wg_cpumask_choose_online(&peer->serial_work_cpu, peer->internal_id),
peer->device->packet_crypt_wq, &peer->transmit_packet_work);
wg_peer_put(peer);
}
static inline void wg_queue_enqueue_per_peer_rx(struct sk_buff *skb, enum packet_state state)
{
/* We take a reference, because as soon as we call atomic_set, the
* peer can be freed from below us.
*/
struct wg_peer *peer = wg_peer_get(PACKET_PEER(skb));
atomic_set_release(&PACKET_CB(skb)->state, state);
napi_schedule(&peer->napi);
wg_peer_put(peer);
}
#ifdef DEBUG
bool wg_packet_counter_selftest(void);
#endif
#endif /* _WG_QUEUEING_H */
|
