xref: /kernel/linux/linux-5.10/drivers/net/tap.c (revision 8c2ecf20)
1// SPDX-License-Identifier: GPL-2.0-only
2#include <linux/etherdevice.h>
3#include <linux/if_tap.h>
4#include <linux/if_vlan.h>
5#include <linux/interrupt.h>
6#include <linux/nsproxy.h>
7#include <linux/compat.h>
8#include <linux/if_tun.h>
9#include <linux/module.h>
10#include <linux/skbuff.h>
11#include <linux/cache.h>
12#include <linux/sched/signal.h>
13#include <linux/types.h>
14#include <linux/slab.h>
15#include <linux/wait.h>
16#include <linux/cdev.h>
17#include <linux/idr.h>
18#include <linux/fs.h>
19#include <linux/uio.h>
20
21#include <net/net_namespace.h>
22#include <net/rtnetlink.h>
23#include <net/sock.h>
24#include <linux/virtio_net.h>
25#include <linux/skb_array.h>
26
27#define TAP_IFFEATURES (IFF_VNET_HDR | IFF_MULTI_QUEUE)
28
29#define TAP_VNET_LE 0x80000000
30#define TAP_VNET_BE 0x40000000
31
32#ifdef CONFIG_TUN_VNET_CROSS_LE
33static inline bool tap_legacy_is_little_endian(struct tap_queue *q)
34{
35	return q->flags & TAP_VNET_BE ? false :
36		virtio_legacy_is_little_endian();
37}
38
39static long tap_get_vnet_be(struct tap_queue *q, int __user *sp)
40{
41	int s = !!(q->flags & TAP_VNET_BE);
42
43	if (put_user(s, sp))
44		return -EFAULT;
45
46	return 0;
47}
48
49static long tap_set_vnet_be(struct tap_queue *q, int __user *sp)
50{
51	int s;
52
53	if (get_user(s, sp))
54		return -EFAULT;
55
56	if (s)
57		q->flags |= TAP_VNET_BE;
58	else
59		q->flags &= ~TAP_VNET_BE;
60
61	return 0;
62}
63#else
64static inline bool tap_legacy_is_little_endian(struct tap_queue *q)
65{
66	return virtio_legacy_is_little_endian();
67}
68
69static long tap_get_vnet_be(struct tap_queue *q, int __user *argp)
70{
71	return -EINVAL;
72}
73
74static long tap_set_vnet_be(struct tap_queue *q, int __user *argp)
75{
76	return -EINVAL;
77}
78#endif /* CONFIG_TUN_VNET_CROSS_LE */
79
80static inline bool tap_is_little_endian(struct tap_queue *q)
81{
82	return q->flags & TAP_VNET_LE ||
83		tap_legacy_is_little_endian(q);
84}
85
86static inline u16 tap16_to_cpu(struct tap_queue *q, __virtio16 val)
87{
88	return __virtio16_to_cpu(tap_is_little_endian(q), val);
89}
90
91static inline __virtio16 cpu_to_tap16(struct tap_queue *q, u16 val)
92{
93	return __cpu_to_virtio16(tap_is_little_endian(q), val);
94}
95
96static struct proto tap_proto = {
97	.name = "tap",
98	.owner = THIS_MODULE,
99	.obj_size = sizeof(struct tap_queue),
100};
101
102#define TAP_NUM_DEVS (1U << MINORBITS)
103
104static LIST_HEAD(major_list);
105
106struct major_info {
107	struct rcu_head rcu;
108	dev_t major;
109	struct idr minor_idr;
110	spinlock_t minor_lock;
111	const char *device_name;
112	struct list_head next;
113};
114
115#define GOODCOPY_LEN 128
116
117static const struct proto_ops tap_socket_ops;
118
119#define RX_OFFLOADS (NETIF_F_GRO | NETIF_F_LRO)
120#define TAP_FEATURES (NETIF_F_GSO | NETIF_F_SG | NETIF_F_FRAGLIST)
121
122static struct tap_dev *tap_dev_get_rcu(const struct net_device *dev)
123{
124	return rcu_dereference(dev->rx_handler_data);
125}
126
127/*
128 * RCU usage:
129 * The tap_queue and the macvlan_dev are loosely coupled, the
130 * pointers from one to the other can only be read while rcu_read_lock
131 * or rtnl is held.
132 *
133 * Both the file and the macvlan_dev hold a reference on the tap_queue
134 * through sock_hold(&q->sk). When the macvlan_dev goes away first,
135 * q->vlan becomes inaccessible. When the files gets closed,
136 * tap_get_queue() fails.
137 *
138 * There may still be references to the struct sock inside of the
139 * queue from outbound SKBs, but these never reference back to the
140 * file or the dev. The data structure is freed through __sk_free
141 * when both our references and any pending SKBs are gone.
142 */
143
144static int tap_enable_queue(struct tap_dev *tap, struct file *file,
145			    struct tap_queue *q)
146{
147	int err = -EINVAL;
148
149	ASSERT_RTNL();
150
151	if (q->enabled)
152		goto out;
153
154	err = 0;
155	rcu_assign_pointer(tap->taps[tap->numvtaps], q);
156	q->queue_index = tap->numvtaps;
157	q->enabled = true;
158
159	tap->numvtaps++;
160out:
161	return err;
162}
163
164/* Requires RTNL */
165static int tap_set_queue(struct tap_dev *tap, struct file *file,
166			 struct tap_queue *q)
167{
168	if (tap->numqueues == MAX_TAP_QUEUES)
169		return -EBUSY;
170
171	rcu_assign_pointer(q->tap, tap);
172	rcu_assign_pointer(tap->taps[tap->numvtaps], q);
173	sock_hold(&q->sk);
174
175	q->file = file;
176	q->queue_index = tap->numvtaps;
177	q->enabled = true;
178	file->private_data = q;
179	list_add_tail(&q->next, &tap->queue_list);
180
181	tap->numvtaps++;
182	tap->numqueues++;
183
184	return 0;
185}
186
187static int tap_disable_queue(struct tap_queue *q)
188{
189	struct tap_dev *tap;
190	struct tap_queue *nq;
191
192	ASSERT_RTNL();
193	if (!q->enabled)
194		return -EINVAL;
195
196	tap = rtnl_dereference(q->tap);
197
198	if (tap) {
199		int index = q->queue_index;
200		BUG_ON(index >= tap->numvtaps);
201		nq = rtnl_dereference(tap->taps[tap->numvtaps - 1]);
202		nq->queue_index = index;
203
204		rcu_assign_pointer(tap->taps[index], nq);
205		RCU_INIT_POINTER(tap->taps[tap->numvtaps - 1], NULL);
206		q->enabled = false;
207
208		tap->numvtaps--;
209	}
210
211	return 0;
212}
213
214/*
215 * The file owning the queue got closed, give up both
216 * the reference that the files holds as well as the
217 * one from the macvlan_dev if that still exists.
218 *
219 * Using the spinlock makes sure that we don't get
220 * to the queue again after destroying it.
221 */
222static void tap_put_queue(struct tap_queue *q)
223{
224	struct tap_dev *tap;
225
226	rtnl_lock();
227	tap = rtnl_dereference(q->tap);
228
229	if (tap) {
230		if (q->enabled)
231			BUG_ON(tap_disable_queue(q));
232
233		tap->numqueues--;
234		RCU_INIT_POINTER(q->tap, NULL);
235		sock_put(&q->sk);
236		list_del_init(&q->next);
237	}
238
239	rtnl_unlock();
240
241	synchronize_rcu();
242	sock_put(&q->sk);
243}
244
245/*
246 * Select a queue based on the rxq of the device on which this packet
247 * arrived. If the incoming device is not mq, calculate a flow hash
248 * to select a queue. If all fails, find the first available queue.
249 * Cache vlan->numvtaps since it can become zero during the execution
250 * of this function.
251 */
252static struct tap_queue *tap_get_queue(struct tap_dev *tap,
253				       struct sk_buff *skb)
254{
255	struct tap_queue *queue = NULL;
256	/* Access to taps array is protected by rcu, but access to numvtaps
257	 * isn't. Below we use it to lookup a queue, but treat it as a hint
258	 * and validate that the result isn't NULL - in case we are
259	 * racing against queue removal.
260	 */
261	int numvtaps = READ_ONCE(tap->numvtaps);
262	__u32 rxq;
263
264	if (!numvtaps)
265		goto out;
266
267	if (numvtaps == 1)
268		goto single;
269
270	/* Check if we can use flow to select a queue */
271	rxq = skb_get_hash(skb);
272	if (rxq) {
273		queue = rcu_dereference(tap->taps[rxq % numvtaps]);
274		goto out;
275	}
276
277	if (likely(skb_rx_queue_recorded(skb))) {
278		rxq = skb_get_rx_queue(skb);
279
280		while (unlikely(rxq >= numvtaps))
281			rxq -= numvtaps;
282
283		queue = rcu_dereference(tap->taps[rxq]);
284		goto out;
285	}
286
287single:
288	queue = rcu_dereference(tap->taps[0]);
289out:
290	return queue;
291}
292
293/*
294 * The net_device is going away, give up the reference
295 * that it holds on all queues and safely set the pointer
296 * from the queues to NULL.
297 */
298void tap_del_queues(struct tap_dev *tap)
299{
300	struct tap_queue *q, *tmp;
301
302	ASSERT_RTNL();
303	list_for_each_entry_safe(q, tmp, &tap->queue_list, next) {
304		list_del_init(&q->next);
305		RCU_INIT_POINTER(q->tap, NULL);
306		if (q->enabled)
307			tap->numvtaps--;
308		tap->numqueues--;
309		sock_put(&q->sk);
310	}
311	BUG_ON(tap->numvtaps);
312	BUG_ON(tap->numqueues);
313	/* guarantee that any future tap_set_queue will fail */
314	tap->numvtaps = MAX_TAP_QUEUES;
315}
316EXPORT_SYMBOL_GPL(tap_del_queues);
317
318rx_handler_result_t tap_handle_frame(struct sk_buff **pskb)
319{
320	struct sk_buff *skb = *pskb;
321	struct net_device *dev = skb->dev;
322	struct tap_dev *tap;
323	struct tap_queue *q;
324	netdev_features_t features = TAP_FEATURES;
325
326	tap = tap_dev_get_rcu(dev);
327	if (!tap)
328		return RX_HANDLER_PASS;
329
330	q = tap_get_queue(tap, skb);
331	if (!q)
332		return RX_HANDLER_PASS;
333
334	skb_push(skb, ETH_HLEN);
335
336	/* Apply the forward feature mask so that we perform segmentation
337	 * according to users wishes.  This only works if VNET_HDR is
338	 * enabled.
339	 */
340	if (q->flags & IFF_VNET_HDR)
341		features |= tap->tap_features;
342	if (netif_needs_gso(skb, features)) {
343		struct sk_buff *segs = __skb_gso_segment(skb, features, false);
344		struct sk_buff *next;
345
346		if (IS_ERR(segs))
347			goto drop;
348
349		if (!segs) {
350			if (ptr_ring_produce(&q->ring, skb))
351				goto drop;
352			goto wake_up;
353		}
354
355		consume_skb(skb);
356		skb_list_walk_safe(segs, skb, next) {
357			skb_mark_not_on_list(skb);
358			if (ptr_ring_produce(&q->ring, skb)) {
359				kfree_skb(skb);
360				kfree_skb_list(next);
361				break;
362			}
363		}
364	} else {
365		/* If we receive a partial checksum and the tap side
366		 * doesn't support checksum offload, compute the checksum.
367		 * Note: it doesn't matter which checksum feature to
368		 *	  check, we either support them all or none.
369		 */
370		if (skb->ip_summed == CHECKSUM_PARTIAL &&
371		    !(features & NETIF_F_CSUM_MASK) &&
372		    skb_checksum_help(skb))
373			goto drop;
374		if (ptr_ring_produce(&q->ring, skb))
375			goto drop;
376	}
377
378wake_up:
379	wake_up_interruptible_poll(sk_sleep(&q->sk), EPOLLIN | EPOLLRDNORM | EPOLLRDBAND);
380	return RX_HANDLER_CONSUMED;
381
382drop:
383	/* Count errors/drops only here, thus don't care about args. */
384	if (tap->count_rx_dropped)
385		tap->count_rx_dropped(tap);
386	kfree_skb(skb);
387	return RX_HANDLER_CONSUMED;
388}
389EXPORT_SYMBOL_GPL(tap_handle_frame);
390
391static struct major_info *tap_get_major(int major)
392{
393	struct major_info *tap_major;
394
395	list_for_each_entry_rcu(tap_major, &major_list, next) {
396		if (tap_major->major == major)
397			return tap_major;
398	}
399
400	return NULL;
401}
402
403int tap_get_minor(dev_t major, struct tap_dev *tap)
404{
405	int retval = -ENOMEM;
406	struct major_info *tap_major;
407
408	rcu_read_lock();
409	tap_major = tap_get_major(MAJOR(major));
410	if (!tap_major) {
411		retval = -EINVAL;
412		goto unlock;
413	}
414
415	spin_lock(&tap_major->minor_lock);
416	retval = idr_alloc(&tap_major->minor_idr, tap, 1, TAP_NUM_DEVS, GFP_ATOMIC);
417	if (retval >= 0) {
418		tap->minor = retval;
419	} else if (retval == -ENOSPC) {
420		netdev_err(tap->dev, "Too many tap devices\n");
421		retval = -EINVAL;
422	}
423	spin_unlock(&tap_major->minor_lock);
424
425unlock:
426	rcu_read_unlock();
427	return retval < 0 ? retval : 0;
428}
429EXPORT_SYMBOL_GPL(tap_get_minor);
430
431void tap_free_minor(dev_t major, struct tap_dev *tap)
432{
433	struct major_info *tap_major;
434
435	rcu_read_lock();
436	tap_major = tap_get_major(MAJOR(major));
437	if (!tap_major) {
438		goto unlock;
439	}
440
441	spin_lock(&tap_major->minor_lock);
442	if (tap->minor) {
443		idr_remove(&tap_major->minor_idr, tap->minor);
444		tap->minor = 0;
445	}
446	spin_unlock(&tap_major->minor_lock);
447
448unlock:
449	rcu_read_unlock();
450}
451EXPORT_SYMBOL_GPL(tap_free_minor);
452
453static struct tap_dev *dev_get_by_tap_file(int major, int minor)
454{
455	struct net_device *dev = NULL;
456	struct tap_dev *tap;
457	struct major_info *tap_major;
458
459	rcu_read_lock();
460	tap_major = tap_get_major(major);
461	if (!tap_major) {
462		tap = NULL;
463		goto unlock;
464	}
465
466	spin_lock(&tap_major->minor_lock);
467	tap = idr_find(&tap_major->minor_idr, minor);
468	if (tap) {
469		dev = tap->dev;
470		dev_hold(dev);
471	}
472	spin_unlock(&tap_major->minor_lock);
473
474unlock:
475	rcu_read_unlock();
476	return tap;
477}
478
479static void tap_sock_write_space(struct sock *sk)
480{
481	wait_queue_head_t *wqueue;
482
483	if (!sock_writeable(sk) ||
484	    !test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags))
485		return;
486
487	wqueue = sk_sleep(sk);
488	if (wqueue && waitqueue_active(wqueue))
489		wake_up_interruptible_poll(wqueue, EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND);
490}
491
492static void tap_sock_destruct(struct sock *sk)
493{
494	struct tap_queue *q = container_of(sk, struct tap_queue, sk);
495
496	ptr_ring_cleanup(&q->ring, __skb_array_destroy_skb);
497}
498
499static int tap_open(struct inode *inode, struct file *file)
500{
501	struct net *net = current->nsproxy->net_ns;
502	struct tap_dev *tap;
503	struct tap_queue *q;
504	int err = -ENODEV;
505
506	rtnl_lock();
507	tap = dev_get_by_tap_file(imajor(inode), iminor(inode));
508	if (!tap)
509		goto err;
510
511	err = -ENOMEM;
512	q = (struct tap_queue *)sk_alloc(net, AF_UNSPEC, GFP_KERNEL,
513					     &tap_proto, 0);
514	if (!q)
515		goto err;
516	if (ptr_ring_init(&q->ring, tap->dev->tx_queue_len, GFP_KERNEL)) {
517		sk_free(&q->sk);
518		goto err;
519	}
520
521	init_waitqueue_head(&q->sock.wq.wait);
522	q->sock.type = SOCK_RAW;
523	q->sock.state = SS_CONNECTED;
524	q->sock.file = file;
525	q->sock.ops = &tap_socket_ops;
526	sock_init_data_uid(&q->sock, &q->sk, current_fsuid());
527	q->sk.sk_write_space = tap_sock_write_space;
528	q->sk.sk_destruct = tap_sock_destruct;
529	q->flags = IFF_VNET_HDR | IFF_NO_PI | IFF_TAP;
530	q->vnet_hdr_sz = sizeof(struct virtio_net_hdr);
531
532	/*
533	 * so far only KVM virtio_net uses tap, enable zero copy between
534	 * guest kernel and host kernel when lower device supports zerocopy
535	 *
536	 * The macvlan supports zerocopy iff the lower device supports zero
537	 * copy so we don't have to look at the lower device directly.
538	 */
539	if ((tap->dev->features & NETIF_F_HIGHDMA) && (tap->dev->features & NETIF_F_SG))
540		sock_set_flag(&q->sk, SOCK_ZEROCOPY);
541
542	err = tap_set_queue(tap, file, q);
543	if (err) {
544		/* tap_sock_destruct() will take care of freeing ptr_ring */
545		goto err_put;
546	}
547
548	dev_put(tap->dev);
549
550	rtnl_unlock();
551	return err;
552
553err_put:
554	sock_put(&q->sk);
555err:
556	if (tap)
557		dev_put(tap->dev);
558
559	rtnl_unlock();
560	return err;
561}
562
563static int tap_release(struct inode *inode, struct file *file)
564{
565	struct tap_queue *q = file->private_data;
566	tap_put_queue(q);
567	return 0;
568}
569
570static __poll_t tap_poll(struct file *file, poll_table *wait)
571{
572	struct tap_queue *q = file->private_data;
573	__poll_t mask = EPOLLERR;
574
575	if (!q)
576		goto out;
577
578	mask = 0;
579	poll_wait(file, &q->sock.wq.wait, wait);
580
581	if (!ptr_ring_empty(&q->ring))
582		mask |= EPOLLIN | EPOLLRDNORM;
583
584	if (sock_writeable(&q->sk) ||
585	    (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &q->sock.flags) &&
586	     sock_writeable(&q->sk)))
587		mask |= EPOLLOUT | EPOLLWRNORM;
588
589out:
590	return mask;
591}
592
593static inline struct sk_buff *tap_alloc_skb(struct sock *sk, size_t prepad,
594					    size_t len, size_t linear,
595						int noblock, int *err)
596{
597	struct sk_buff *skb;
598
599	/* Under a page?  Don't bother with paged skb. */
600	if (prepad + len < PAGE_SIZE || !linear)
601		linear = len;
602
603	skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock,
604				   err, 0);
605	if (!skb)
606		return NULL;
607
608	skb_reserve(skb, prepad);
609	skb_put(skb, linear);
610	skb->data_len = len - linear;
611	skb->len += len - linear;
612
613	return skb;
614}
615
616/* Neighbour code has some assumptions on HH_DATA_MOD alignment */
617#define TAP_RESERVE HH_DATA_OFF(ETH_HLEN)
618
619/* Get packet from user space buffer */
620static ssize_t tap_get_user(struct tap_queue *q, void *msg_control,
621			    struct iov_iter *from, int noblock)
622{
623	int good_linear = SKB_MAX_HEAD(TAP_RESERVE);
624	struct sk_buff *skb;
625	struct tap_dev *tap;
626	unsigned long total_len = iov_iter_count(from);
627	unsigned long len = total_len;
628	int err;
629	struct virtio_net_hdr vnet_hdr = { 0 };
630	int vnet_hdr_len = 0;
631	int copylen = 0;
632	int depth;
633	bool zerocopy = false;
634	size_t linear;
635
636	if (q->flags & IFF_VNET_HDR) {
637		vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz);
638
639		err = -EINVAL;
640		if (len < vnet_hdr_len)
641			goto err;
642		len -= vnet_hdr_len;
643
644		err = -EFAULT;
645		if (!copy_from_iter_full(&vnet_hdr, sizeof(vnet_hdr), from))
646			goto err;
647		iov_iter_advance(from, vnet_hdr_len - sizeof(vnet_hdr));
648		if ((vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) &&
649		     tap16_to_cpu(q, vnet_hdr.csum_start) +
650		     tap16_to_cpu(q, vnet_hdr.csum_offset) + 2 >
651			     tap16_to_cpu(q, vnet_hdr.hdr_len))
652			vnet_hdr.hdr_len = cpu_to_tap16(q,
653				 tap16_to_cpu(q, vnet_hdr.csum_start) +
654				 tap16_to_cpu(q, vnet_hdr.csum_offset) + 2);
655		err = -EINVAL;
656		if (tap16_to_cpu(q, vnet_hdr.hdr_len) > len)
657			goto err;
658	}
659
660	err = -EINVAL;
661	if (unlikely(len < ETH_HLEN))
662		goto err;
663
664	if (msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY)) {
665		struct iov_iter i;
666
667		copylen = vnet_hdr.hdr_len ?
668			tap16_to_cpu(q, vnet_hdr.hdr_len) : GOODCOPY_LEN;
669		if (copylen > good_linear)
670			copylen = good_linear;
671		else if (copylen < ETH_HLEN)
672			copylen = ETH_HLEN;
673		linear = copylen;
674		i = *from;
675		iov_iter_advance(&i, copylen);
676		if (iov_iter_npages(&i, INT_MAX) <= MAX_SKB_FRAGS)
677			zerocopy = true;
678	}
679
680	if (!zerocopy) {
681		copylen = len;
682		linear = tap16_to_cpu(q, vnet_hdr.hdr_len);
683		if (linear > good_linear)
684			linear = good_linear;
685		else if (linear < ETH_HLEN)
686			linear = ETH_HLEN;
687	}
688
689	skb = tap_alloc_skb(&q->sk, TAP_RESERVE, copylen,
690			    linear, noblock, &err);
691	if (!skb)
692		goto err;
693
694	if (zerocopy)
695		err = zerocopy_sg_from_iter(skb, from);
696	else
697		err = skb_copy_datagram_from_iter(skb, 0, from, len);
698
699	if (err)
700		goto err_kfree;
701
702	skb_set_network_header(skb, ETH_HLEN);
703	skb_reset_mac_header(skb);
704	skb->protocol = eth_hdr(skb)->h_proto;
705
706	if (vnet_hdr_len) {
707		err = virtio_net_hdr_to_skb(skb, &vnet_hdr,
708					    tap_is_little_endian(q));
709		if (err)
710			goto err_kfree;
711	}
712
713	skb_probe_transport_header(skb);
714
715	/* Move network header to the right position for VLAN tagged packets */
716	if (eth_type_vlan(skb->protocol) &&
717	    vlan_get_protocol_and_depth(skb, skb->protocol, &depth) != 0)
718		skb_set_network_header(skb, depth);
719
720	rcu_read_lock();
721	tap = rcu_dereference(q->tap);
722	/* copy skb_ubuf_info for callback when skb has no error */
723	if (zerocopy) {
724		skb_shinfo(skb)->destructor_arg = msg_control;
725		skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY;
726		skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG;
727	} else if (msg_control) {
728		struct ubuf_info *uarg = msg_control;
729		uarg->callback(uarg, false);
730	}
731
732	if (tap) {
733		skb->dev = tap->dev;
734		dev_queue_xmit(skb);
735	} else {
736		kfree_skb(skb);
737	}
738	rcu_read_unlock();
739
740	return total_len;
741
742err_kfree:
743	kfree_skb(skb);
744
745err:
746	rcu_read_lock();
747	tap = rcu_dereference(q->tap);
748	if (tap && tap->count_tx_dropped)
749		tap->count_tx_dropped(tap);
750	rcu_read_unlock();
751
752	return err;
753}
754
755static ssize_t tap_write_iter(struct kiocb *iocb, struct iov_iter *from)
756{
757	struct file *file = iocb->ki_filp;
758	struct tap_queue *q = file->private_data;
759
760	return tap_get_user(q, NULL, from, file->f_flags & O_NONBLOCK);
761}
762
763/* Put packet to the user space buffer */
764static ssize_t tap_put_user(struct tap_queue *q,
765			    const struct sk_buff *skb,
766			    struct iov_iter *iter)
767{
768	int ret;
769	int vnet_hdr_len = 0;
770	int vlan_offset = 0;
771	int total;
772
773	if (q->flags & IFF_VNET_HDR) {
774		int vlan_hlen = skb_vlan_tag_present(skb) ? VLAN_HLEN : 0;
775		struct virtio_net_hdr vnet_hdr;
776
777		vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz);
778		if (iov_iter_count(iter) < vnet_hdr_len)
779			return -EINVAL;
780
781		if (virtio_net_hdr_from_skb(skb, &vnet_hdr,
782					    tap_is_little_endian(q), true,
783					    vlan_hlen))
784			BUG();
785
786		if (copy_to_iter(&vnet_hdr, sizeof(vnet_hdr), iter) !=
787		    sizeof(vnet_hdr))
788			return -EFAULT;
789
790		iov_iter_advance(iter, vnet_hdr_len - sizeof(vnet_hdr));
791	}
792	total = vnet_hdr_len;
793	total += skb->len;
794
795	if (skb_vlan_tag_present(skb)) {
796		struct {
797			__be16 h_vlan_proto;
798			__be16 h_vlan_TCI;
799		} veth;
800		veth.h_vlan_proto = skb->vlan_proto;
801		veth.h_vlan_TCI = htons(skb_vlan_tag_get(skb));
802
803		vlan_offset = offsetof(struct vlan_ethhdr, h_vlan_proto);
804		total += VLAN_HLEN;
805
806		ret = skb_copy_datagram_iter(skb, 0, iter, vlan_offset);
807		if (ret || !iov_iter_count(iter))
808			goto done;
809
810		ret = copy_to_iter(&veth, sizeof(veth), iter);
811		if (ret != sizeof(veth) || !iov_iter_count(iter))
812			goto done;
813	}
814
815	ret = skb_copy_datagram_iter(skb, vlan_offset, iter,
816				     skb->len - vlan_offset);
817
818done:
819	return ret ? ret : total;
820}
821
822static ssize_t tap_do_read(struct tap_queue *q,
823			   struct iov_iter *to,
824			   int noblock, struct sk_buff *skb)
825{
826	DEFINE_WAIT(wait);
827	ssize_t ret = 0;
828
829	if (!iov_iter_count(to)) {
830		kfree_skb(skb);
831		return 0;
832	}
833
834	if (skb)
835		goto put;
836
837	while (1) {
838		if (!noblock)
839			prepare_to_wait(sk_sleep(&q->sk), &wait,
840					TASK_INTERRUPTIBLE);
841
842		/* Read frames from the queue */
843		skb = ptr_ring_consume(&q->ring);
844		if (skb)
845			break;
846		if (noblock) {
847			ret = -EAGAIN;
848			break;
849		}
850		if (signal_pending(current)) {
851			ret = -ERESTARTSYS;
852			break;
853		}
854		/* Nothing to read, let's sleep */
855		schedule();
856	}
857	if (!noblock)
858		finish_wait(sk_sleep(&q->sk), &wait);
859
860put:
861	if (skb) {
862		ret = tap_put_user(q, skb, to);
863		if (unlikely(ret < 0))
864			kfree_skb(skb);
865		else
866			consume_skb(skb);
867	}
868	return ret;
869}
870
871static ssize_t tap_read_iter(struct kiocb *iocb, struct iov_iter *to)
872{
873	struct file *file = iocb->ki_filp;
874	struct tap_queue *q = file->private_data;
875	ssize_t len = iov_iter_count(to), ret;
876
877	ret = tap_do_read(q, to, file->f_flags & O_NONBLOCK, NULL);
878	ret = min_t(ssize_t, ret, len);
879	if (ret > 0)
880		iocb->ki_pos = ret;
881	return ret;
882}
883
884static struct tap_dev *tap_get_tap_dev(struct tap_queue *q)
885{
886	struct tap_dev *tap;
887
888	ASSERT_RTNL();
889	tap = rtnl_dereference(q->tap);
890	if (tap)
891		dev_hold(tap->dev);
892
893	return tap;
894}
895
896static void tap_put_tap_dev(struct tap_dev *tap)
897{
898	dev_put(tap->dev);
899}
900
901static int tap_ioctl_set_queue(struct file *file, unsigned int flags)
902{
903	struct tap_queue *q = file->private_data;
904	struct tap_dev *tap;
905	int ret;
906
907	tap = tap_get_tap_dev(q);
908	if (!tap)
909		return -EINVAL;
910
911	if (flags & IFF_ATTACH_QUEUE)
912		ret = tap_enable_queue(tap, file, q);
913	else if (flags & IFF_DETACH_QUEUE)
914		ret = tap_disable_queue(q);
915	else
916		ret = -EINVAL;
917
918	tap_put_tap_dev(tap);
919	return ret;
920}
921
922static int set_offload(struct tap_queue *q, unsigned long arg)
923{
924	struct tap_dev *tap;
925	netdev_features_t features;
926	netdev_features_t feature_mask = 0;
927
928	tap = rtnl_dereference(q->tap);
929	if (!tap)
930		return -ENOLINK;
931
932	features = tap->dev->features;
933
934	if (arg & TUN_F_CSUM) {
935		feature_mask = NETIF_F_HW_CSUM;
936
937		if (arg & (TUN_F_TSO4 | TUN_F_TSO6)) {
938			if (arg & TUN_F_TSO_ECN)
939				feature_mask |= NETIF_F_TSO_ECN;
940			if (arg & TUN_F_TSO4)
941				feature_mask |= NETIF_F_TSO;
942			if (arg & TUN_F_TSO6)
943				feature_mask |= NETIF_F_TSO6;
944		}
945	}
946
947	/* tun/tap driver inverts the usage for TSO offloads, where
948	 * setting the TSO bit means that the userspace wants to
949	 * accept TSO frames and turning it off means that user space
950	 * does not support TSO.
951	 * For tap, we have to invert it to mean the same thing.
952	 * When user space turns off TSO, we turn off GSO/LRO so that
953	 * user-space will not receive TSO frames.
954	 */
955	if (feature_mask & (NETIF_F_TSO | NETIF_F_TSO6))
956		features |= RX_OFFLOADS;
957	else
958		features &= ~RX_OFFLOADS;
959
960	/* tap_features are the same as features on tun/tap and
961	 * reflect user expectations.
962	 */
963	tap->tap_features = feature_mask;
964	if (tap->update_features)
965		tap->update_features(tap, features);
966
967	return 0;
968}
969
970/*
971 * provide compatibility with generic tun/tap interface
972 */
973static long tap_ioctl(struct file *file, unsigned int cmd,
974		      unsigned long arg)
975{
976	struct tap_queue *q = file->private_data;
977	struct tap_dev *tap;
978	void __user *argp = (void __user *)arg;
979	struct ifreq __user *ifr = argp;
980	unsigned int __user *up = argp;
981	unsigned short u;
982	int __user *sp = argp;
983	struct sockaddr sa;
984	int s;
985	int ret;
986
987	switch (cmd) {
988	case TUNSETIFF:
989		/* ignore the name, just look at flags */
990		if (get_user(u, &ifr->ifr_flags))
991			return -EFAULT;
992
993		ret = 0;
994		if ((u & ~TAP_IFFEATURES) != (IFF_NO_PI | IFF_TAP))
995			ret = -EINVAL;
996		else
997			q->flags = (q->flags & ~TAP_IFFEATURES) | u;
998
999		return ret;
1000
1001	case TUNGETIFF:
1002		rtnl_lock();
1003		tap = tap_get_tap_dev(q);
1004		if (!tap) {
1005			rtnl_unlock();
1006			return -ENOLINK;
1007		}
1008
1009		ret = 0;
1010		u = q->flags;
1011		if (copy_to_user(&ifr->ifr_name, tap->dev->name, IFNAMSIZ) ||
1012		    put_user(u, &ifr->ifr_flags))
1013			ret = -EFAULT;
1014		tap_put_tap_dev(tap);
1015		rtnl_unlock();
1016		return ret;
1017
1018	case TUNSETQUEUE:
1019		if (get_user(u, &ifr->ifr_flags))
1020			return -EFAULT;
1021		rtnl_lock();
1022		ret = tap_ioctl_set_queue(file, u);
1023		rtnl_unlock();
1024		return ret;
1025
1026	case TUNGETFEATURES:
1027		if (put_user(IFF_TAP | IFF_NO_PI | TAP_IFFEATURES, up))
1028			return -EFAULT;
1029		return 0;
1030
1031	case TUNSETSNDBUF:
1032		if (get_user(s, sp))
1033			return -EFAULT;
1034		if (s <= 0)
1035			return -EINVAL;
1036
1037		q->sk.sk_sndbuf = s;
1038		return 0;
1039
1040	case TUNGETVNETHDRSZ:
1041		s = q->vnet_hdr_sz;
1042		if (put_user(s, sp))
1043			return -EFAULT;
1044		return 0;
1045
1046	case TUNSETVNETHDRSZ:
1047		if (get_user(s, sp))
1048			return -EFAULT;
1049		if (s < (int)sizeof(struct virtio_net_hdr))
1050			return -EINVAL;
1051
1052		q->vnet_hdr_sz = s;
1053		return 0;
1054
1055	case TUNGETVNETLE:
1056		s = !!(q->flags & TAP_VNET_LE);
1057		if (put_user(s, sp))
1058			return -EFAULT;
1059		return 0;
1060
1061	case TUNSETVNETLE:
1062		if (get_user(s, sp))
1063			return -EFAULT;
1064		if (s)
1065			q->flags |= TAP_VNET_LE;
1066		else
1067			q->flags &= ~TAP_VNET_LE;
1068		return 0;
1069
1070	case TUNGETVNETBE:
1071		return tap_get_vnet_be(q, sp);
1072
1073	case TUNSETVNETBE:
1074		return tap_set_vnet_be(q, sp);
1075
1076	case TUNSETOFFLOAD:
1077		/* let the user check for future flags */
1078		if (arg & ~(TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 |
1079			    TUN_F_TSO_ECN | TUN_F_UFO))
1080			return -EINVAL;
1081
1082		rtnl_lock();
1083		ret = set_offload(q, arg);
1084		rtnl_unlock();
1085		return ret;
1086
1087	case SIOCGIFHWADDR:
1088		rtnl_lock();
1089		tap = tap_get_tap_dev(q);
1090		if (!tap) {
1091			rtnl_unlock();
1092			return -ENOLINK;
1093		}
1094		ret = 0;
1095		dev_get_mac_address(&sa, dev_net(tap->dev), tap->dev->name);
1096		if (copy_to_user(&ifr->ifr_name, tap->dev->name, IFNAMSIZ) ||
1097		    copy_to_user(&ifr->ifr_hwaddr, &sa, sizeof(sa)))
1098			ret = -EFAULT;
1099		tap_put_tap_dev(tap);
1100		rtnl_unlock();
1101		return ret;
1102
1103	case SIOCSIFHWADDR:
1104		if (copy_from_user(&sa, &ifr->ifr_hwaddr, sizeof(sa)))
1105			return -EFAULT;
1106		rtnl_lock();
1107		tap = tap_get_tap_dev(q);
1108		if (!tap) {
1109			rtnl_unlock();
1110			return -ENOLINK;
1111		}
1112		ret = dev_set_mac_address_user(tap->dev, &sa, NULL);
1113		tap_put_tap_dev(tap);
1114		rtnl_unlock();
1115		return ret;
1116
1117	default:
1118		return -EINVAL;
1119	}
1120}
1121
1122static const struct file_operations tap_fops = {
1123	.owner		= THIS_MODULE,
1124	.open		= tap_open,
1125	.release	= tap_release,
1126	.read_iter	= tap_read_iter,
1127	.write_iter	= tap_write_iter,
1128	.poll		= tap_poll,
1129	.llseek		= no_llseek,
1130	.unlocked_ioctl	= tap_ioctl,
1131	.compat_ioctl	= compat_ptr_ioctl,
1132};
1133
1134static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp)
1135{
1136	struct tun_xdp_hdr *hdr = xdp->data_hard_start;
1137	struct virtio_net_hdr *gso = &hdr->gso;
1138	int buflen = hdr->buflen;
1139	int vnet_hdr_len = 0;
1140	struct tap_dev *tap;
1141	struct sk_buff *skb;
1142	int err, depth;
1143
1144	if (unlikely(xdp->data_end - xdp->data < ETH_HLEN)) {
1145		err = -EINVAL;
1146		goto err;
1147	}
1148
1149	if (q->flags & IFF_VNET_HDR)
1150		vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz);
1151
1152	skb = build_skb(xdp->data_hard_start, buflen);
1153	if (!skb) {
1154		err = -ENOMEM;
1155		goto err;
1156	}
1157
1158	skb_reserve(skb, xdp->data - xdp->data_hard_start);
1159	skb_put(skb, xdp->data_end - xdp->data);
1160
1161	skb_set_network_header(skb, ETH_HLEN);
1162	skb_reset_mac_header(skb);
1163	skb->protocol = eth_hdr(skb)->h_proto;
1164
1165	if (vnet_hdr_len) {
1166		err = virtio_net_hdr_to_skb(skb, gso, tap_is_little_endian(q));
1167		if (err)
1168			goto err_kfree;
1169	}
1170
1171	/* Move network header to the right position for VLAN tagged packets */
1172	if (eth_type_vlan(skb->protocol) &&
1173	    vlan_get_protocol_and_depth(skb, skb->protocol, &depth) != 0)
1174		skb_set_network_header(skb, depth);
1175
1176	rcu_read_lock();
1177	tap = rcu_dereference(q->tap);
1178	if (tap) {
1179		skb->dev = tap->dev;
1180		skb_probe_transport_header(skb);
1181		dev_queue_xmit(skb);
1182	} else {
1183		kfree_skb(skb);
1184	}
1185	rcu_read_unlock();
1186
1187	return 0;
1188
1189err_kfree:
1190	kfree_skb(skb);
1191err:
1192	rcu_read_lock();
1193	tap = rcu_dereference(q->tap);
1194	if (tap && tap->count_tx_dropped)
1195		tap->count_tx_dropped(tap);
1196	rcu_read_unlock();
1197	return err;
1198}
1199
1200static int tap_sendmsg(struct socket *sock, struct msghdr *m,
1201		       size_t total_len)
1202{
1203	struct tap_queue *q = container_of(sock, struct tap_queue, sock);
1204	struct tun_msg_ctl *ctl = m->msg_control;
1205	struct xdp_buff *xdp;
1206	int i;
1207
1208	if (m->msg_controllen == sizeof(struct tun_msg_ctl) &&
1209	    ctl && ctl->type == TUN_MSG_PTR) {
1210		for (i = 0; i < ctl->num; i++) {
1211			xdp = &((struct xdp_buff *)ctl->ptr)[i];
1212			tap_get_user_xdp(q, xdp);
1213		}
1214		return 0;
1215	}
1216
1217	return tap_get_user(q, ctl ? ctl->ptr : NULL, &m->msg_iter,
1218			    m->msg_flags & MSG_DONTWAIT);
1219}
1220
1221static int tap_recvmsg(struct socket *sock, struct msghdr *m,
1222		       size_t total_len, int flags)
1223{
1224	struct tap_queue *q = container_of(sock, struct tap_queue, sock);
1225	struct sk_buff *skb = m->msg_control;
1226	int ret;
1227	if (flags & ~(MSG_DONTWAIT|MSG_TRUNC)) {
1228		kfree_skb(skb);
1229		return -EINVAL;
1230	}
1231	ret = tap_do_read(q, &m->msg_iter, flags & MSG_DONTWAIT, skb);
1232	if (ret > total_len) {
1233		m->msg_flags |= MSG_TRUNC;
1234		ret = flags & MSG_TRUNC ? ret : total_len;
1235	}
1236	return ret;
1237}
1238
1239static int tap_peek_len(struct socket *sock)
1240{
1241	struct tap_queue *q = container_of(sock, struct tap_queue,
1242					       sock);
1243	return PTR_RING_PEEK_CALL(&q->ring, __skb_array_len_with_tag);
1244}
1245
1246/* Ops structure to mimic raw sockets with tun */
1247static const struct proto_ops tap_socket_ops = {
1248	.sendmsg = tap_sendmsg,
1249	.recvmsg = tap_recvmsg,
1250	.peek_len = tap_peek_len,
1251};
1252
1253/* Get an underlying socket object from tun file.  Returns error unless file is
1254 * attached to a device.  The returned object works like a packet socket, it
1255 * can be used for sock_sendmsg/sock_recvmsg.  The caller is responsible for
1256 * holding a reference to the file for as long as the socket is in use. */
1257struct socket *tap_get_socket(struct file *file)
1258{
1259	struct tap_queue *q;
1260	if (file->f_op != &tap_fops)
1261		return ERR_PTR(-EINVAL);
1262	q = file->private_data;
1263	if (!q)
1264		return ERR_PTR(-EBADFD);
1265	return &q->sock;
1266}
1267EXPORT_SYMBOL_GPL(tap_get_socket);
1268
1269struct ptr_ring *tap_get_ptr_ring(struct file *file)
1270{
1271	struct tap_queue *q;
1272
1273	if (file->f_op != &tap_fops)
1274		return ERR_PTR(-EINVAL);
1275	q = file->private_data;
1276	if (!q)
1277		return ERR_PTR(-EBADFD);
1278	return &q->ring;
1279}
1280EXPORT_SYMBOL_GPL(tap_get_ptr_ring);
1281
1282int tap_queue_resize(struct tap_dev *tap)
1283{
1284	struct net_device *dev = tap->dev;
1285	struct tap_queue *q;
1286	struct ptr_ring **rings;
1287	int n = tap->numqueues;
1288	int ret, i = 0;
1289
1290	rings = kmalloc_array(n, sizeof(*rings), GFP_KERNEL);
1291	if (!rings)
1292		return -ENOMEM;
1293
1294	list_for_each_entry(q, &tap->queue_list, next)
1295		rings[i++] = &q->ring;
1296
1297	ret = ptr_ring_resize_multiple(rings, n,
1298				       dev->tx_queue_len, GFP_KERNEL,
1299				       __skb_array_destroy_skb);
1300
1301	kfree(rings);
1302	return ret;
1303}
1304EXPORT_SYMBOL_GPL(tap_queue_resize);
1305
1306static int tap_list_add(dev_t major, const char *device_name)
1307{
1308	struct major_info *tap_major;
1309
1310	tap_major = kzalloc(sizeof(*tap_major), GFP_ATOMIC);
1311	if (!tap_major)
1312		return -ENOMEM;
1313
1314	tap_major->major = MAJOR(major);
1315
1316	idr_init(&tap_major->minor_idr);
1317	spin_lock_init(&tap_major->minor_lock);
1318
1319	tap_major->device_name = device_name;
1320
1321	list_add_tail_rcu(&tap_major->next, &major_list);
1322	return 0;
1323}
1324
1325int tap_create_cdev(struct cdev *tap_cdev, dev_t *tap_major,
1326		    const char *device_name, struct module *module)
1327{
1328	int err;
1329
1330	err = alloc_chrdev_region(tap_major, 0, TAP_NUM_DEVS, device_name);
1331	if (err)
1332		goto out1;
1333
1334	cdev_init(tap_cdev, &tap_fops);
1335	tap_cdev->owner = module;
1336	err = cdev_add(tap_cdev, *tap_major, TAP_NUM_DEVS);
1337	if (err)
1338		goto out2;
1339
1340	err =  tap_list_add(*tap_major, device_name);
1341	if (err)
1342		goto out3;
1343
1344	return 0;
1345
1346out3:
1347	cdev_del(tap_cdev);
1348out2:
1349	unregister_chrdev_region(*tap_major, TAP_NUM_DEVS);
1350out1:
1351	return err;
1352}
1353EXPORT_SYMBOL_GPL(tap_create_cdev);
1354
1355void tap_destroy_cdev(dev_t major, struct cdev *tap_cdev)
1356{
1357	struct major_info *tap_major, *tmp;
1358
1359	cdev_del(tap_cdev);
1360	unregister_chrdev_region(major, TAP_NUM_DEVS);
1361	list_for_each_entry_safe(tap_major, tmp, &major_list, next) {
1362		if (tap_major->major == MAJOR(major)) {
1363			idr_destroy(&tap_major->minor_idr);
1364			list_del_rcu(&tap_major->next);
1365			kfree_rcu(tap_major, rcu);
1366		}
1367	}
1368}
1369EXPORT_SYMBOL_GPL(tap_destroy_cdev);
1370
1371MODULE_AUTHOR("Arnd Bergmann <arnd@arndb.de>");
1372MODULE_AUTHOR("Sainath Grandhi <sainath.grandhi@intel.com>");
1373MODULE_LICENSE("GPL");
1374