summaryrefslogtreecommitdiff
path: root/kernel/bpf/xskmap.c
blob: 9bb96ace9fa126762af4761cb556937cefe880bd (plain)
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
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
// SPDX-License-Identifier: GPL-2.0
/* XSKMAP used for AF_XDP sockets
 * Copyright(c) 2018 Intel Corporation.
 */

#include <linux/bpf.h>
#include <linux/capability.h>
#include <net/xdp_sock.h>
#include <linux/slab.h>
#include <linux/sched.h>

struct xsk_map {
	struct bpf_map map;
	struct xdp_sock **xsk_map;
	struct list_head __percpu *flush_list;
};

static struct bpf_map *xsk_map_alloc(union bpf_attr *attr)
{
	struct xsk_map *m;
	int cpu, err;
	u64 cost;

	if (!capable(CAP_NET_ADMIN))
		return ERR_PTR(-EPERM);

	if (attr->max_entries == 0 || attr->key_size != 4 ||
	    attr->value_size != 4 ||
	    attr->map_flags & ~(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY))
		return ERR_PTR(-EINVAL);

	m = kzalloc(sizeof(*m), GFP_USER);
	if (!m)
		return ERR_PTR(-ENOMEM);

	bpf_map_init_from_attr(&m->map, attr);

	cost = (u64)m->map.max_entries * sizeof(struct xdp_sock *);
	cost += sizeof(struct list_head) * num_possible_cpus();

	/* Notice returns -EPERM on if map size is larger than memlock limit */
	err = bpf_map_charge_init(&m->map.memory, cost);
	if (err)
		goto free_m;

	err = -ENOMEM;

	m->flush_list = alloc_percpu(struct list_head);
	if (!m->flush_list)
		goto free_charge;

	for_each_possible_cpu(cpu)
		INIT_LIST_HEAD(per_cpu_ptr(m->flush_list, cpu));

	m->xsk_map = bpf_map_area_alloc(m->map.max_entries *
					sizeof(struct xdp_sock *),
					m->map.numa_node);
	if (!m->xsk_map)
		goto free_percpu;
	return &m->map;

free_percpu:
	free_percpu(m->flush_list);
free_charge:
	bpf_map_charge_finish(&m->map.memory);
free_m:
	kfree(m);
	return ERR_PTR(err);
}

static void xsk_map_free(struct bpf_map *map)
{
	struct xsk_map *m = container_of(map, struct xsk_map, map);
	int i;

	bpf_clear_redirect_map(map);
	synchronize_net();

	for (i = 0; i < map->max_entries; i++) {
		struct xdp_sock *xs;

		xs = m->xsk_map[i];
		if (!xs)
			continue;

		sock_put((struct sock *)xs);
	}

	free_percpu(m->flush_list);
	bpf_map_area_free(m->xsk_map);
	kfree(m);
}

static int xsk_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
{
	struct xsk_map *m = container_of(map, struct xsk_map, map);
	u32 index = key ? *(u32 *)key : U32_MAX;
	u32 *next = next_key;

	if (index >= m->map.max_entries) {
		*next = 0;
		return 0;
	}

	if (index == m->map.max_entries - 1)
		return -ENOENT;
	*next = index + 1;
	return 0;
}

struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, u32 key)
{
	struct xsk_map *m = container_of(map, struct xsk_map, map);
	struct xdp_sock *xs;

	if (key >= map->max_entries)
		return NULL;

	xs = READ_ONCE(m->xsk_map[key]);
	return xs;
}

int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp,
		       struct xdp_sock *xs)
{
	struct xsk_map *m = container_of(map, struct xsk_map, map);
	struct list_head *flush_list = this_cpu_ptr(m->flush_list);
	int err;

	err = xsk_rcv(xs, xdp);
	if (err)
		return err;

	if (!xs->flush_node.prev)
		list_add(&xs->flush_node, flush_list);

	return 0;
}

void __xsk_map_flush(struct bpf_map *map)
{
	struct xsk_map *m = container_of(map, struct xsk_map, map);
	struct list_head *flush_list = this_cpu_ptr(m->flush_list);
	struct xdp_sock *xs, *tmp;

	list_for_each_entry_safe(xs, tmp, flush_list, flush_node) {
		xsk_flush(xs);
		__list_del_clearprev(&xs->flush_node);
	}
}

static void *xsk_map_lookup_elem(struct bpf_map *map, void *key)
{
	WARN_ON_ONCE(!rcu_read_lock_held());
	return __xsk_map_lookup_elem(map, *(u32 *)key);
}

static void *xsk_map_lookup_elem_sys_only(struct bpf_map *map, void *key)
{
	return ERR_PTR(-EOPNOTSUPP);
}

static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value,
			       u64 map_flags)
{
	struct xsk_map *m = container_of(map, struct xsk_map, map);
	u32 i = *(u32 *)key, fd = *(u32 *)value;
	struct xdp_sock *xs, *old_xs;
	struct socket *sock;
	int err;

	if (unlikely(map_flags > BPF_EXIST))
		return -EINVAL;
	if (unlikely(i >= m->map.max_entries))
		return -E2BIG;
	if (unlikely(map_flags == BPF_NOEXIST))
		return -EEXIST;

	sock = sockfd_lookup(fd, &err);
	if (!sock)
		return err;

	if (sock->sk->sk_family != PF_XDP) {
		sockfd_put(sock);
		return -EOPNOTSUPP;
	}

	xs = (struct xdp_sock *)sock->sk;

	if (!xsk_is_setup_for_bpf_map(xs)) {
		sockfd_put(sock);
		return -EOPNOTSUPP;
	}

	sock_hold(sock->sk);

	old_xs = xchg(&m->xsk_map[i], xs);
	if (old_xs)
		sock_put((struct sock *)old_xs);

	sockfd_put(sock);
	return 0;
}

static int xsk_map_delete_elem(struct bpf_map *map, void *key)
{
	struct xsk_map *m = container_of(map, struct xsk_map, map);
	struct xdp_sock *old_xs;
	int k = *(u32 *)key;

	if (k >= map->max_entries)
		return -EINVAL;

	old_xs = xchg(&m->xsk_map[k], NULL);
	if (old_xs)
		sock_put((struct sock *)old_xs);

	return 0;
}

const struct bpf_map_ops xsk_map_ops = {
	.map_alloc = xsk_map_alloc,
	.map_free = xsk_map_free,
	.map_get_next_key = xsk_map_get_next_key,
	.map_lookup_elem = xsk_map_lookup_elem,
	.map_lookup_elem_sys_only = xsk_map_lookup_elem_sys_only,
	.map_update_elem = xsk_map_update_elem,
	.map_delete_elem = xsk_map_delete_elem,
	.map_check_btf = map_check_no_btf,
};