summaryrefslogtreecommitdiff
path: root/net/xdp/xsk.c
blob: 59b57d7086970b53b140bc500c881ab9cf1fb98b (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
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
// 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.
 *
 * 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 <linux/rculist.h>
#include <net/xdp_sock.h>
#include <net/xdp.h>

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

#define TX_BATCH_SIZE 16

bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs)
{
	return READ_ONCE(xs->rx) &&  READ_ONCE(xs->umem) &&
		READ_ONCE(xs->umem->fq);
}

bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt)
{
	return xskq_has_addrs(umem->fq, cnt);
}
EXPORT_SYMBOL(xsk_umem_has_addrs);

u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr)
{
	return xskq_peek_addr(umem->fq, addr);
}
EXPORT_SYMBOL(xsk_umem_peek_addr);

void xsk_umem_discard_addr(struct xdp_umem *umem)
{
	xskq_discard_addr(umem->fq);
}
EXPORT_SYMBOL(xsk_umem_discard_addr);

static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
{
	void *to_buf, *from_buf;
	u32 metalen;
	u64 addr;
	int err;

	if (!xskq_peek_addr(xs->umem->fq, &addr) ||
	    len > xs->umem->chunk_size_nohr - XDP_PACKET_HEADROOM) {
		xs->rx_dropped++;
		return -ENOSPC;
	}

	addr += xs->umem->headroom;

	if (unlikely(xdp_data_meta_unsupported(xdp))) {
		from_buf = xdp->data;
		metalen = 0;
	} else {
		from_buf = xdp->data_meta;
		metalen = xdp->data - xdp->data_meta;
	}

	to_buf = xdp_umem_get_data(xs->umem, addr);
	memcpy(to_buf, from_buf, len + metalen);
	addr += metalen;
	err = xskq_produce_batch_desc(xs->rx, addr, len);
	if (!err) {
		xskq_discard_addr(xs->umem->fq);
		xdp_return_buff(xdp);
		return 0;
	}

	xs->rx_dropped++;
	return err;
}

static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
{
	int err = xskq_produce_batch_desc(xs->rx, (u64)xdp->handle, len);

	if (err)
		xs->rx_dropped++;

	return err;
}

int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
{
	u32 len;

	if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index)
		return -EINVAL;

	len = xdp->data_end - xdp->data;

	return (xdp->rxq->mem.type == MEM_TYPE_ZERO_COPY) ?
		__xsk_rcv_zc(xs, xdp, len) : __xsk_rcv(xs, xdp, len);
}

void xsk_flush(struct xdp_sock *xs)
{
	xskq_produce_flush_desc(xs->rx);
	xs->sk.sk_data_ready(&xs->sk);
}

int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
{
	u32 metalen = xdp->data - xdp->data_meta;
	u32 len = xdp->data_end - xdp->data;
	void *buffer;
	u64 addr;
	int err;

	spin_lock_bh(&xs->rx_lock);

	if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index) {
		err = -EINVAL;
		goto out_unlock;
	}

	if (!xskq_peek_addr(xs->umem->fq, &addr) ||
	    len > xs->umem->chunk_size_nohr - XDP_PACKET_HEADROOM) {
		err = -ENOSPC;
		goto out_drop;
	}

	addr += xs->umem->headroom;

	buffer = xdp_umem_get_data(xs->umem, addr);
	memcpy(buffer, xdp->data_meta, len + metalen);
	addr += metalen;
	err = xskq_produce_batch_desc(xs->rx, addr, len);
	if (err)
		goto out_drop;

	xskq_discard_addr(xs->umem->fq);
	xskq_produce_flush_desc(xs->rx);

	spin_unlock_bh(&xs->rx_lock);

	xs->sk.sk_data_ready(&xs->sk);
	return 0;

out_drop:
	xs->rx_dropped++;
out_unlock:
	spin_unlock_bh(&xs->rx_lock);
	return err;
}

void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries)
{
	xskq_produce_flush_addr_n(umem->cq, nb_entries);
}
EXPORT_SYMBOL(xsk_umem_complete_tx);

void xsk_umem_consume_tx_done(struct xdp_umem *umem)
{
	struct xdp_sock *xs;

	rcu_read_lock();
	list_for_each_entry_rcu(xs, &umem->xsk_list, list) {
		xs->sk.sk_write_space(&xs->sk);
	}
	rcu_read_unlock();
}
EXPORT_SYMBOL(xsk_umem_consume_tx_done);

bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc)
{
	struct xdp_sock *xs;

	rcu_read_lock();
	list_for_each_entry_rcu(xs, &umem->xsk_list, list) {
		if (!xskq_peek_desc(xs->tx, desc))
			continue;

		if (xskq_produce_addr_lazy(umem->cq, desc->addr))
			goto out;

		xskq_discard_desc(xs->tx);
		rcu_read_unlock();
		return true;
	}

out:
	rcu_read_unlock();
	return false;
}
EXPORT_SYMBOL(xsk_umem_consume_tx);

static int xsk_zc_xmit(struct sock *sk)
{
	struct xdp_sock *xs = xdp_sk(sk);
	struct net_device *dev = xs->dev;

	return dev->netdev_ops->ndo_xsk_async_xmit(dev, xs->queue_id);
}

static void xsk_destruct_skb(struct sk_buff *skb)
{
	u64 addr = (u64)(long)skb_shinfo(skb)->destructor_arg;
	struct xdp_sock *xs = xdp_sk(skb->sk);
	unsigned long flags;

	spin_lock_irqsave(&xs->tx_completion_lock, flags);
	WARN_ON_ONCE(xskq_produce_addr(xs->umem->cq, addr));
	spin_unlock_irqrestore(&xs->tx_completion_lock, flags);

	sock_wfree(skb);
}

static int xsk_generic_xmit(struct sock *sk, struct msghdr *m,
			    size_t total_len)
{
	u32 max_batch = TX_BATCH_SIZE;
	struct xdp_sock *xs = xdp_sk(sk);
	bool sent_frame = false;
	struct xdp_desc desc;
	struct sk_buff *skb;
	int err = 0;

	mutex_lock(&xs->mutex);

	if (xs->queue_id >= xs->dev->real_num_tx_queues)
		goto out;

	while (xskq_peek_desc(xs->tx, &desc)) {
		char *buffer;
		u64 addr;
		u32 len;

		if (max_batch-- == 0) {
			err = -EAGAIN;
			goto out;
		}

		len = desc.len;
		skb = sock_alloc_send_skb(sk, len, 1, &err);
		if (unlikely(!skb)) {
			err = -EAGAIN;
			goto out;
		}

		skb_put(skb, len);
		addr = desc.addr;
		buffer = xdp_umem_get_data(xs->umem, addr);
		err = skb_store_bits(skb, 0, buffer, len);
		if (unlikely(err) || xskq_reserve_addr(xs->umem->cq)) {
			kfree_skb(skb);
			goto out;
		}

		skb->dev = xs->dev;
		skb->priority = sk->sk_priority;
		skb->mark = sk->sk_mark;
		skb_shinfo(skb)->destructor_arg = (void *)(long)addr;
		skb->destructor = xsk_destruct_skb;

		err = dev_direct_xmit(skb, xs->queue_id);
		xskq_discard_desc(xs->tx);
		/* Ignore NET_XMIT_CN as packet might have been sent */
		if (err == NET_XMIT_DROP || err == NETDEV_TX_BUSY) {
			/* SKB completed but not sent */
			err = -EBUSY;
			goto out;
		}

		sent_frame = true;
	}

out:
	if (sent_frame)
		sk->sk_write_space(sk);

	mutex_unlock(&xs->mutex);
	return err;
}

static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
{
	bool need_wait = !(m->msg_flags & MSG_DONTWAIT);
	struct sock *sk = sock->sk;
	struct xdp_sock *xs = xdp_sk(sk);

	if (unlikely(!xs->dev))
		return -ENXIO;
	if (unlikely(!(xs->dev->flags & IFF_UP)))
		return -ENETDOWN;
	if (unlikely(!xs->tx))
		return -ENOBUFS;
	if (need_wait)
		return -EOPNOTSUPP;

	return (xs->zc) ? xsk_zc_xmit(sk) : xsk_generic_xmit(sk, m, total_len);
}

static unsigned int xsk_poll(struct file *file, struct socket *sock,
			     struct poll_table_struct *wait)
{
	unsigned int mask = datagram_poll(file, sock, wait);
	struct sock *sk = sock->sk;
	struct xdp_sock *xs = xdp_sk(sk);

	if (xs->rx && !xskq_empty_desc(xs->rx))
		mask |= POLLIN | POLLRDNORM;
	if (xs->tx && !xskq_full_desc(xs->tx))
		mask |= POLLOUT | POLLWRNORM;

	return mask;
}

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;

	/* Make sure queue is ready before it can be seen by others */
	smp_wmb();
	*queue = q;
	return 0;
}

static void xsk_unbind_dev(struct xdp_sock *xs)
{
	struct net_device *dev = xs->dev;

	if (!dev || xs->state != XSK_BOUND)
		return;

	xs->state = XSK_UNBOUND;

	/* Wait for driver to stop using the xdp socket. */
	xdp_del_sk_umem(xs->umem, xs);
	xs->dev = NULL;
	synchronize_net();
	dev_put(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);

	mutex_lock(&net->xdp.lock);
	sk_del_node_init_rcu(sk);
	mutex_unlock(&net->xdp.lock);

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

	xsk_unbind_dev(xs);

	xskq_destroy(xs->rx);
	xskq_destroy(xs->tx);

	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 xdp_sock *xs = xdp_sk(sk);
	struct net_device *dev;
	u32 flags, qid;
	int err = 0;

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

	flags = sxdp->sxdp_flags;
	if (flags & ~(XDP_SHARED_UMEM | XDP_COPY | XDP_ZEROCOPY))
		return -EINVAL;

	rtnl_lock();
	mutex_lock(&xs->mutex);
	if (xs->state != XSK_READY) {
		err = -EBUSY;
		goto out_release;
	}

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

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

	qid = sxdp->sxdp_queue_id;

	if (flags & XDP_SHARED_UMEM) {
		struct xdp_sock *umem_xs;
		struct socket *sock;

		if ((flags & XDP_COPY) || (flags & XDP_ZEROCOPY)) {
			/* Cannot specify flags for shared sockets. */
			err = -EINVAL;
			goto out_unlock;
		}

		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 != qid) {
			err = -EINVAL;
			sockfd_put(sock);
			goto out_unlock;
		}

		xdp_get_umem(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;
	} else {
		/* This xsk has its own umem. */
		xskq_set_umem(xs->umem->fq, xs->umem->size,
			      xs->umem->chunk_mask);
		xskq_set_umem(xs->umem->cq, xs->umem->size,
			      xs->umem->chunk_mask);

		err = xdp_umem_assign_dev(xs->umem, dev, qid, flags);
		if (err)
			goto out_unlock;
	}

	xs->dev = dev;
	xs->zc = xs->umem->zc;
	xs->queue_id = qid;
	xskq_set_umem(xs->rx, xs->umem->size, xs->umem->chunk_mask);
	xskq_set_umem(xs->tx, xs->umem->size, xs->umem->chunk_mask);
	xdp_add_sk_umem(xs->umem, xs);

out_unlock:
	if (err)
		dev_put(dev);
	else
		xs->state = XSK_BOUND;
out_release:
	mutex_unlock(&xs->mutex);
	rtnl_unlock();
	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:
	case XDP_TX_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);
		if (xs->state != XSK_READY) {
			mutex_unlock(&xs->mutex);
			return -EBUSY;
		}
		q = (optname == XDP_TX_RING) ? &xs->tx : &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 (copy_from_user(&mr, optval, sizeof(mr)))
			return -EFAULT;

		mutex_lock(&xs->mutex);
		if (xs->state != XSK_READY || xs->umem) {
			mutex_unlock(&xs->mutex);
			return -EBUSY;
		}

		umem = xdp_umem_create(&mr);
		if (IS_ERR(umem)) {
			mutex_unlock(&xs->mutex);
			return PTR_ERR(umem);
		}

		/* 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:
	case XDP_UMEM_COMPLETION_RING:
	{
		struct xsk_queue **q;
		int entries;

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

		mutex_lock(&xs->mutex);
		if (xs->state != XSK_READY) {
			mutex_unlock(&xs->mutex);
			return -EBUSY;
		}
		if (!xs->umem) {
			mutex_unlock(&xs->mutex);
			return -EINVAL;
		}

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

	return -ENOPROTOOPT;
}

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

	if (level != SOL_XDP)
		return -ENOPROTOOPT;

	if (get_user(len, optlen))
		return -EFAULT;
	if (len < 0)
		return -EINVAL;

	switch (optname) {
	case XDP_STATISTICS:
	{
		struct xdp_statistics stats;

		if (len < sizeof(stats))
			return -EINVAL;

		mutex_lock(&xs->mutex);
		stats.rx_dropped = xs->rx_dropped;
		stats.rx_invalid_descs = xskq_nb_invalid_descs(xs->rx);
		stats.tx_invalid_descs = xskq_nb_invalid_descs(xs->tx);
		mutex_unlock(&xs->mutex);

		if (copy_to_user(optval, &stats, sizeof(stats)))
			return -EFAULT;
		if (put_user(sizeof(stats), optlen))
			return -EFAULT;

		return 0;
	}
	case XDP_MMAP_OFFSETS:
	{
		struct xdp_mmap_offsets off;

		if (len < sizeof(off))
			return -EINVAL;

		off.rx.producer = offsetof(struct xdp_rxtx_ring, ptrs.producer);
		off.rx.consumer = offsetof(struct xdp_rxtx_ring, ptrs.consumer);
		off.rx.desc	= offsetof(struct xdp_rxtx_ring, desc);
		off.tx.producer = offsetof(struct xdp_rxtx_ring, ptrs.producer);
		off.tx.consumer = offsetof(struct xdp_rxtx_ring, ptrs.consumer);
		off.tx.desc	= offsetof(struct xdp_rxtx_ring, desc);

		off.fr.producer = offsetof(struct xdp_umem_ring, ptrs.producer);
		off.fr.consumer = offsetof(struct xdp_umem_ring, ptrs.consumer);
		off.fr.desc	= offsetof(struct xdp_umem_ring, desc);
		off.cr.producer = offsetof(struct xdp_umem_ring, ptrs.producer);
		off.cr.consumer = offsetof(struct xdp_umem_ring, ptrs.consumer);
		off.cr.desc	= offsetof(struct xdp_umem_ring, desc);

		len = sizeof(off);
		if (copy_to_user(optval, &off, len))
			return -EFAULT;
		if (put_user(len, optlen))
			return -EFAULT;

		return 0;
	}
	case XDP_OPTIONS:
	{
		struct xdp_options opts = {};

		if (len < sizeof(opts))
			return -EINVAL;

		mutex_lock(&xs->mutex);
		if (xs->zc)
			opts.flags |= XDP_OPTIONS_ZEROCOPY;
		mutex_unlock(&xs->mutex);

		len = sizeof(opts);
		if (copy_to_user(optval, &opts, len))
			return -EFAULT;
		if (put_user(len, optlen))
			return -EFAULT;

		return 0;
	}
	default:
		break;
	}

	return -EOPNOTSUPP;
}

static int xsk_mmap(struct file *file, struct socket *sock,
		    struct vm_area_struct *vma)
{
	loff_t offset = (loff_t)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;
	struct xdp_umem *umem;
	unsigned long pfn;
	struct page *qpg;

	if (xs->state != XSK_READY)
		return -EBUSY;

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

		/* Matches the smp_wmb() in XDP_UMEM_REG */
		smp_rmb();
		if (offset == XDP_UMEM_PGOFF_FILL_RING)
			q = READ_ONCE(umem->fq);
		else if (offset == XDP_UMEM_PGOFF_COMPLETION_RING)
			q = READ_ONCE(umem->cq);
	}

	if (!q)
		return -EINVAL;

	/* Matches the smp_wmb() in xsk_init_queue */
	smp_rmb();
	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 int xsk_notifier(struct notifier_block *this,
			unsigned long msg, void *ptr)
{
	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
	struct net *net = dev_net(dev);
	struct sock *sk;

	switch (msg) {
	case NETDEV_UNREGISTER:
		mutex_lock(&net->xdp.lock);
		sk_for_each(sk, &net->xdp.list) {
			struct xdp_sock *xs = xdp_sk(sk);

			mutex_lock(&xs->mutex);
			if (xs->dev == dev) {
				sk->sk_err = ENETDOWN;
				if (!sock_flag(sk, SOCK_DEAD))
					sk->sk_error_report(sk);

				xsk_unbind_dev(xs);

				/* Clear device references in umem. */
				xdp_umem_clear_dev(xs->umem);
			}
			mutex_unlock(&xs->mutex);
		}
		mutex_unlock(&net->xdp.lock);
		break;
	}
	return NOTIFY_DONE;
}

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		= xsk_poll,
	.ioctl		= sock_no_ioctl,
	.listen		= sock_no_listen,
	.shutdown	= sock_no_shutdown,
	.setsockopt	= xsk_setsockopt,
	.getsockopt	= xsk_getsockopt,
	.sendmsg	= xsk_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;

	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);

	sock_set_flag(sk, SOCK_RCU_FREE);

	xs = xdp_sk(sk);
	xs->state = XSK_READY;
	mutex_init(&xs->mutex);
	spin_lock_init(&xs->rx_lock);
	spin_lock_init(&xs->tx_completion_lock);

	mutex_lock(&net->xdp.lock);
	sk_add_node_rcu(sk, &net->xdp.list);
	mutex_unlock(&net->xdp.lock);

	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 struct notifier_block xsk_netdev_notifier = {
	.notifier_call	= xsk_notifier,
};

static int __net_init xsk_net_init(struct net *net)
{
	mutex_init(&net->xdp.lock);
	INIT_HLIST_HEAD(&net->xdp.list);
	return 0;
}

static void __net_exit xsk_net_exit(struct net *net)
{
	WARN_ON_ONCE(!hlist_empty(&net->xdp.list));
}

static struct pernet_operations xsk_net_ops = {
	.init = xsk_net_init,
	.exit = xsk_net_exit,
};

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;

	err = register_pernet_subsys(&xsk_net_ops);
	if (err)
		goto out_sk;

	err = register_netdevice_notifier(&xsk_netdev_notifier);
	if (err)
		goto out_pernet;

	return 0;

out_pernet:
	unregister_pernet_subsys(&xsk_net_ops);
out_sk:
	sock_unregister(PF_XDP);
out_proto:
	proto_unregister(&xsk_proto);
out:
	return err;
}

fs_initcall(xsk_init);