summaryrefslogtreecommitdiffstats
path: root/net/xdp/xsk.c
blob: bf2c97b87992963b6ab025f4447e64d95789b01f (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
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
// SPDX-License-Identifier: GPL-2.0
/* XDP sockets
 *
 * AF_XDP sockets allows a channel between XDP programs and userspace
 * applications.
 * Copyright(c) 2018 Intel Corporation.
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms and conditions of the GNU General Public License,
 * version 2, as published by the Free Software Foundation.
 *
 * This program is distributed in the hope it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 * more details.
 *
 * Author(s): Björn Töpel <bjorn.topel@intel.com>
 *	      Magnus Karlsson <magnus.karlsson@intel.com>
 */

#define pr_fmt(fmt) "AF_XDP: %s: " fmt, __func__

#include <linux/if_xdp.h>
#include <linux/init.h>
#include <linux/sched/mm.h>
#include <linux/sched/signal.h>
#include <linux/sched/task.h>
#include <linux/socket.h>
#include <linux/file.h>
#include <linux/uaccess.h>
#include <linux/net.h>
#include <linux/netdevice.h>
#include <net/xdp_sock.h>
#include <net/xdp.h>

#include "xsk_queue.h"
#include "xdp_umem.h"

static struct xdp_sock *xdp_sk(struct sock *sk)
{
	return (struct xdp_sock *)sk;
}

static int xsk_init_queue(u32 entries, struct xsk_queue **queue,
			  bool umem_queue)
{
	struct xsk_queue *q;

	if (entries == 0 || *queue || !is_power_of_2(entries))
		return -EINVAL;

	q = xskq_create(entries, umem_queue);
	if (!q)
		return -ENOMEM;

	*queue = q;
	return 0;
}

static void __xsk_release(struct xdp_sock *xs)
{
	/* Wait for driver to stop using the xdp socket. */
	synchronize_net();

	dev_put(xs->dev);
}

static int xsk_release(struct socket *sock)
{
	struct sock *sk = sock->sk;
	struct xdp_sock *xs = xdp_sk(sk);
	struct net *net;

	if (!sk)
		return 0;

	net = sock_net(sk);

	local_bh_disable();
	sock_prot_inuse_add(net, sk->sk_prot, -1);
	local_bh_enable();

	if (xs->dev) {
		__xsk_release(xs);
		xs->dev = NULL;
	}

	sock_orphan(sk);
	sock->sk = NULL;

	sk_refcnt_debug_release(sk);
	sock_put(sk);

	return 0;
}

static struct socket *xsk_lookup_xsk_from_fd(int fd)
{
	struct socket *sock;
	int err;

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

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

	return sock;
}

static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
{
	struct sockaddr_xdp *sxdp = (struct sockaddr_xdp *)addr;
	struct sock *sk = sock->sk;
	struct net_device *dev, *dev_curr;
	struct xdp_sock *xs = xdp_sk(sk);
	struct xdp_umem *old_umem = NULL;
	int err = 0;

	if (addr_len < sizeof(struct sockaddr_xdp))
		return -EINVAL;
	if (sxdp->sxdp_family != AF_XDP)
		return -EINVAL;

	mutex_lock(&xs->mutex);
	dev_curr = xs->dev;
	dev = dev_get_by_index(sock_net(sk), sxdp->sxdp_ifindex);
	if (!dev) {
		err = -ENODEV;
		goto out_release;
	}

	if (!xs->rx) {
		err = -EINVAL;
		goto out_unlock;
	}

	if (sxdp->sxdp_queue_id >= dev->num_rx_queues) {
		err = -EINVAL;
		goto out_unlock;
	}

	if (sxdp->sxdp_flags & XDP_SHARED_UMEM) {
		struct xdp_sock *umem_xs;
		struct socket *sock;

		if (xs->umem) {
			/* We have already our own. */
			err = -EINVAL;
			goto out_unlock;
		}

		sock = xsk_lookup_xsk_from_fd(sxdp->sxdp_shared_umem_fd);
		if (IS_ERR(sock)) {
			err = PTR_ERR(sock);
			goto out_unlock;
		}

		umem_xs = xdp_sk(sock->sk);
		if (!umem_xs->umem) {
			/* No umem to inherit. */
			err = -EBADF;
			sockfd_put(sock);
			goto out_unlock;
		} else if (umem_xs->dev != dev ||
			   umem_xs->queue_id != sxdp->sxdp_queue_id) {
			err = -EINVAL;
			sockfd_put(sock);
			goto out_unlock;
		}

		xdp_get_umem(umem_xs->umem);
		old_umem = xs->umem;
		xs->umem = umem_xs->umem;
		sockfd_put(sock);
	} else if (!xs->umem || !xdp_umem_validate_queues(xs->umem)) {
		err = -EINVAL;
		goto out_unlock;
	}

	/* Rebind? */
	if (dev_curr && (dev_curr != dev ||
			 xs->queue_id != sxdp->sxdp_queue_id)) {
		__xsk_release(xs);
		if (old_umem)
			xdp_put_umem(old_umem);
	}

	xs->dev = dev;
	xs->queue_id = sxdp->sxdp_queue_id;

	xskq_set_umem(xs->rx, &xs->umem->props);

out_unlock:
	if (err)
		dev_put(dev);
out_release:
	mutex_unlock(&xs->mutex);
	return err;
}

static int xsk_setsockopt(struct socket *sock, int level, int optname,
			  char __user *optval, unsigned int optlen)
{
	struct sock *sk = sock->sk;
	struct xdp_sock *xs = xdp_sk(sk);
	int err;

	if (level != SOL_XDP)
		return -ENOPROTOOPT;

	switch (optname) {
	case XDP_RX_RING:
	{
		struct xsk_queue **q;
		int entries;

		if (optlen < sizeof(entries))
			return -EINVAL;
		if (copy_from_user(&entries, optval, sizeof(entries)))
			return -EFAULT;

		mutex_lock(&xs->mutex);
		q = &xs->rx;
		err = xsk_init_queue(entries, q, false);
		mutex_unlock(&xs->mutex);
		return err;
	}
	case XDP_UMEM_REG:
	{
		struct xdp_umem_reg mr;
		struct xdp_umem *umem;

		if (xs->umem)
			return -EBUSY;

		if (copy_from_user(&mr, optval, sizeof(mr)))
			return -EFAULT;

		mutex_lock(&xs->mutex);
		err = xdp_umem_create(&umem);

		err = xdp_umem_reg(umem, &mr);
		if (err) {
			kfree(umem);
			mutex_unlock(&xs->mutex);
			return err;
		}

		/* Make sure umem is ready before it can be seen by others */
		smp_wmb();

		xs->umem = umem;
		mutex_unlock(&xs->mutex);
		return 0;
	}
	case XDP_UMEM_FILL_RING:
	{
		struct xsk_queue **q;
		int entries;

		if (!xs->umem)
			return -EINVAL;

		if (copy_from_user(&entries, optval, sizeof(entries)))
			return -EFAULT;

		mutex_lock(&xs->mutex);
		q = &xs->umem->fq;
		err = xsk_init_queue(entries, q, true);
		mutex_unlock(&xs->mutex);
		return err;
	}
	default:
		break;
	}

	return -ENOPROTOOPT;
}

static int xsk_mmap(struct file *file, struct socket *sock,
		    struct vm_area_struct *vma)
{
	unsigned long offset = vma->vm_pgoff << PAGE_SHIFT;
	unsigned long size = vma->vm_end - vma->vm_start;
	struct xdp_sock *xs = xdp_sk(sock->sk);
	struct xsk_queue *q = NULL;
	unsigned long pfn;
	struct page *qpg;

	if (offset == XDP_PGOFF_RX_RING) {
		q = xs->rx;
	} else {
		if (!xs->umem)
			return -EINVAL;

		if (offset == XDP_UMEM_PGOFF_FILL_RING)
			q = xs->umem->fq;
		else
			return -EINVAL;
	}

	if (!q)
		return -EINVAL;

	qpg = virt_to_head_page(q->ring);
	if (size > (PAGE_SIZE << compound_order(qpg)))
		return -EINVAL;

	pfn = virt_to_phys(q->ring) >> PAGE_SHIFT;
	return remap_pfn_range(vma, vma->vm_start, pfn,
			       size, vma->vm_page_prot);
}

static struct proto xsk_proto = {
	.name =		"XDP",
	.owner =	THIS_MODULE,
	.obj_size =	sizeof(struct xdp_sock),
};

static const struct proto_ops xsk_proto_ops = {
	.family =	PF_XDP,
	.owner =	THIS_MODULE,
	.release =	xsk_release,
	.bind =		xsk_bind,
	.connect =	sock_no_connect,
	.socketpair =	sock_no_socketpair,
	.accept =	sock_no_accept,
	.getname =	sock_no_getname,
	.poll =		sock_no_poll,
	.ioctl =	sock_no_ioctl,
	.listen =	sock_no_listen,
	.shutdown =	sock_no_shutdown,
	.setsockopt =	xsk_setsockopt,
	.getsockopt =	sock_no_getsockopt,
	.sendmsg =	sock_no_sendmsg,
	.recvmsg =	sock_no_recvmsg,
	.mmap =		xsk_mmap,
	.sendpage =	sock_no_sendpage,
};

static void xsk_destruct(struct sock *sk)
{
	struct xdp_sock *xs = xdp_sk(sk);

	if (!sock_flag(sk, SOCK_DEAD))
		return;

	xskq_destroy(xs->rx);
	xdp_put_umem(xs->umem);

	sk_refcnt_debug_dec(sk);
}

static int xsk_create(struct net *net, struct socket *sock, int protocol,
		      int kern)
{
	struct sock *sk;
	struct xdp_sock *xs;

	if (!ns_capable(net->user_ns, CAP_NET_RAW))
		return -EPERM;
	if (sock->type != SOCK_RAW)
		return -ESOCKTNOSUPPORT;

	if (protocol)
		return -EPROTONOSUPPORT;

	sock->state = SS_UNCONNECTED;

	sk = sk_alloc(net, PF_XDP, GFP_KERNEL, &xsk_proto, kern);
	if (!sk)
		return -ENOBUFS;

	sock->ops = &xsk_proto_ops;

	sock_init_data(sock, sk);

	sk->sk_family = PF_XDP;

	sk->sk_destruct = xsk_destruct;
	sk_refcnt_debug_inc(sk);

	xs = xdp_sk(sk);
	mutex_init(&xs->mutex);

	local_bh_disable();
	sock_prot_inuse_add(net, &xsk_proto, 1);
	local_bh_enable();

	return 0;
}

static const struct net_proto_family xsk_family_ops = {
	.family = PF_XDP,
	.create = xsk_create,
	.owner	= THIS_MODULE,
};

static int __init xsk_init(void)
{
	int err;

	err = proto_register(&xsk_proto, 0 /* no slab */);
	if (err)
		goto out;

	err = sock_register(&xsk_family_ops);
	if (err)
		goto out_proto;

	return 0;

out_proto:
	proto_unregister(&xsk_proto);
out:
	return err;
}

fs_initcall(xsk_init);