Free Electrons

Electrons Libres - Embedded Linux Experts

  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
/*
 *	SUCS NET3:
 *
 *	Generic datagram handling routines. These are generic for all
 *	protocols. Possibly a generic IP version on top of these would
 *	make sense. Not tonight however 8-).
 *	This is used because UDP, RAW, PACKET, DDP, IPX, AX.25 and
 *	NetROM layer all have identical poll code and mostly
 *	identical recvmsg() code. So we share it here. The poll was
 *	shared before but buried in udp.c so I moved it.
 *
 *	Authors:	Alan Cox <alan@redhat.com>. (datagram_poll() from old
 *						     udp.c code)
 *
 *	Fixes:
 *		Alan Cox	:	NULL return from skb_peek_copy()
 *					understood
 *		Alan Cox	:	Rewrote skb_read_datagram to avoid the
 *					skb_peek_copy stuff.
 *		Alan Cox	:	Added support for SOCK_SEQPACKET.
 *					IPX can no longer use the SO_TYPE hack
 *					but AX.25 now works right, and SPX is
 *					feasible.
 *		Alan Cox	:	Fixed write poll of non IP protocol
 *					crash.
 *		Florian  La Roche:	Changed for my new skbuff handling.
 *		Darryl Miles	:	Fixed non-blocking SOCK_SEQPACKET.
 *		Linus Torvalds	:	BSD semantic fixes.
 *		Alan Cox	:	Datagram iovec handling
 *		Darryl Miles	:	Fixed non-blocking SOCK_STREAM.
 *		Alan Cox	:	POSIXisms
 *		Pete Wyckoff    :       Unconnected accept() fix.
 *
 */

#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <asm/uaccess.h>
#include <asm/system.h>
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/rtnetlink.h>
#include <linux/poll.h>
#include <linux/highmem.h>

#include <net/protocol.h>
#include <linux/skbuff.h>

#include <net/checksum.h>
#include <net/sock.h>
#include <net/tcp_states.h>

/*
 *	Is a socket 'connection oriented' ?
 */
static inline int connection_based(struct sock *sk)
{
	return sk->sk_type == SOCK_SEQPACKET || sk->sk_type == SOCK_STREAM;
}

/*
 * Wait for a packet..
 */
static int wait_for_packet(struct sock *sk, int *err, long *timeo_p)
{
	int error;
	DEFINE_WAIT(wait);

	prepare_to_wait_exclusive(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);

	/* Socket errors? */
	error = sock_error(sk);
	if (error)
		goto out_err;

	if (!skb_queue_empty(&sk->sk_receive_queue))
		goto out;

	/* Socket shut down? */
	if (sk->sk_shutdown & RCV_SHUTDOWN)
		goto out_noerr;

	/* Sequenced packets can come disconnected.
	 * If so we report the problem
	 */
	error = -ENOTCONN;
	if (connection_based(sk) &&
	    !(sk->sk_state == TCP_ESTABLISHED || sk->sk_state == TCP_LISTEN))
		goto out_err;

	/* handle signals */
	if (signal_pending(current))
		goto interrupted;

	error = 0;
	*timeo_p = schedule_timeout(*timeo_p);
out:
	finish_wait(sk->sk_sleep, &wait);
	return error;
interrupted:
	error = sock_intr_errno(*timeo_p);
out_err:
	*err = error;
	goto out;
out_noerr:
	*err = 0;
	error = 1;
	goto out;
}

/**
 *	skb_recv_datagram - Receive a datagram skbuff
 *	@sk: socket
 *	@flags: MSG_ flags
 *	@noblock: blocking operation?
 *	@err: error code returned
 *
 *	Get a datagram skbuff, understands the peeking, nonblocking wakeups
 *	and possible races. This replaces identical code in packet, raw and
 *	udp, as well as the IPX AX.25 and Appletalk. It also finally fixes
 *	the long standing peek and read race for datagram sockets. If you
 *	alter this routine remember it must be re-entrant.
 *
 *	This function will lock the socket if a skb is returned, so the caller
 *	needs to unlock the socket in that case (usually by calling
 *	skb_free_datagram)
 *
 *	* It does not lock socket since today. This function is
 *	* free of race conditions. This measure should/can improve
 *	* significantly datagram socket latencies at high loads,
 *	* when data copying to user space takes lots of time.
 *	* (BTW I've just killed the last cli() in IP/IPv6/core/netlink/packet
 *	*  8) Great win.)
 *	*			                    --ANK (980729)
 *
 *	The order of the tests when we find no data waiting are specified
 *	quite explicitly by POSIX 1003.1g, don't change them without having
 *	the standard around please.
 */
struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags,
				  int noblock, int *err)
{
	struct sk_buff *skb;
	long timeo;
	/*
	 * Caller is allowed not to check sk->sk_err before skb_recv_datagram()
	 */
	int error = sock_error(sk);

	if (error)
		goto no_packet;

	timeo = sock_rcvtimeo(sk, noblock);

	do {
		/* Again only user level code calls this function, so nothing
		 * interrupt level will suddenly eat the receive_queue.
		 *
		 * Look at current nfs client by the way...
		 * However, this function was corrent in any case. 8)
		 */
		if (flags & MSG_PEEK) {
			unsigned long cpu_flags;

			spin_lock_irqsave(&sk->sk_receive_queue.lock,
					  cpu_flags);
			skb = skb_peek(&sk->sk_receive_queue);
			if (skb)
				atomic_inc(&skb->users);
			spin_unlock_irqrestore(&sk->sk_receive_queue.lock,
					       cpu_flags);
		} else
			skb = skb_dequeue(&sk->sk_receive_queue);

		if (skb)
			return skb;

		/* User doesn't want to wait */
		error = -EAGAIN;
		if (!timeo)
			goto no_packet;

	} while (!wait_for_packet(sk, err, &timeo));

	return NULL;

no_packet:
	*err = error;
	return NULL;
}

void skb_free_datagram(struct sock *sk, struct sk_buff *skb)
{
	kfree_skb(skb);
}

/**
 *	skb_copy_datagram_iovec - Copy a datagram to an iovec.
 *	@skb: buffer to copy
 *	@offset: offset in the buffer to start copying from
 *	@to: io vector to copy to
 *	@len: amount of data to copy from buffer to iovec
 *
 *	Note: the iovec is modified during the copy.
 */
int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset,
			    struct iovec *to, int len)
{
	int i, err, fraglen, end = 0;
	struct sk_buff *next = skb_shinfo(skb)->frag_list;

	if (!len)
		return 0;

next_skb:
	fraglen = skb_headlen(skb);
	i = -1;

	while (1) {
		int start = end;

		if ((end += fraglen) > offset) {
			int copy = end - offset, o = offset - start;

			if (copy > len)
				copy = len;
			if (i == -1)
				err = memcpy_toiovec(to, skb->data + o, copy);
			else {
				skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
				struct page *page = frag->page;
				void *p = kmap(page) + frag->page_offset + o;
				err = memcpy_toiovec(to, p, copy);
				kunmap(page);
			}
			if (err)
				goto fault;
			if (!(len -= copy))
				return 0;
			offset += copy;
		}
		if (++i >= skb_shinfo(skb)->nr_frags)
			break;
		fraglen = skb_shinfo(skb)->frags[i].size;
	}
	if (next) {
		skb = next;
		BUG_ON(skb_shinfo(skb)->frag_list);
		next = skb->next;
		goto next_skb;
	}
fault:
	return -EFAULT;
}

static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset,
				      u8 __user *to, int len,
				      unsigned int *csump)
{
	int start = skb_headlen(skb);
	int pos = 0;
	int i, copy = start - offset;

	/* Copy header. */
	if (copy > 0) {
		int err = 0;
		if (copy > len)
			copy = len;
		*csump = csum_and_copy_to_user(skb->data + offset, to, copy,
					       *csump, &err);
		if (err)
			goto fault;
		if ((len -= copy) == 0)
			return 0;
		offset += copy;
		to += copy;
		pos = copy;
	}

	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
		int end;

		BUG_TRAP(start <= offset + len);

		end = start + skb_shinfo(skb)->frags[i].size;
		if ((copy = end - offset) > 0) {
			unsigned int csum2;
			int err = 0;
			u8  *vaddr;
			skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
			struct page *page = frag->page;

			if (copy > len)
				copy = len;
			vaddr = kmap(page);
			csum2 = csum_and_copy_to_user(vaddr +
							frag->page_offset +
							offset - start,
						      to, copy, 0, &err);
			kunmap(page);
			if (err)
				goto fault;
			*csump = csum_block_add(*csump, csum2, pos);
			if (!(len -= copy))
				return 0;
			offset += copy;
			to += copy;
			pos += copy;
		}
		start = end;
	}

	if (skb_shinfo(skb)->frag_list) {
		struct sk_buff *list = skb_shinfo(skb)->frag_list;

		for (; list; list=list->next) {
			int end;

			BUG_TRAP(start <= offset + len);

			end = start + list->len;
			if ((copy = end - offset) > 0) {
				unsigned int csum2 = 0;
				if (copy > len)
					copy = len;
				if (skb_copy_and_csum_datagram(list,
							       offset - start,
							       to, copy,
							       &csum2))
					goto fault;
				*csump = csum_block_add(*csump, csum2, pos);
				if ((len -= copy) == 0)
					return 0;
				offset += copy;
				to += copy;
				pos += copy;
			}
			start = end;
		}
	}
	if (!len)
		return 0;

fault:
	return -EFAULT;
}

/**
 *	skb_copy_and_csum_datagram_iovec - Copy and checkum skb to user iovec.
 *	@skb: skbuff
 *	@hlen: hardware length
 *	@iov: io vector
 * 
 *	Caller _must_ check that skb will fit to this iovec.
 *
 *	Returns: 0       - success.
 *		 -EINVAL - checksum failure.
 *		 -EFAULT - fault during copy. Beware, in this case iovec
 *			   can be modified!
 */
int skb_copy_and_csum_datagram_iovec(const struct sk_buff *skb,
				     int hlen, struct iovec *iov)
{
	unsigned int csum;
	int chunk = skb->len - hlen;

	/* Skip filled elements.
	 * Pretty silly, look at memcpy_toiovec, though 8)
	 */
	while (!iov->iov_len)
		iov++;

	if (iov->iov_len < chunk) {
		if ((unsigned short)csum_fold(skb_checksum(skb, 0, chunk + hlen,
							   skb->csum)))
			goto csum_error;
		if (skb_copy_datagram_iovec(skb, hlen, iov, chunk))
			goto fault;
	} else {
		csum = csum_partial(skb->data, hlen, skb->csum);
		if (skb_copy_and_csum_datagram(skb, hlen, iov->iov_base,
					       chunk, &csum))
			goto fault;
		if ((unsigned short)csum_fold(csum))
			goto csum_error;
		iov->iov_len -= chunk;
		iov->iov_base += chunk;
	}
	return 0;
csum_error:
	return -EINVAL;
fault:
	return -EFAULT;
}

/**
 * 	datagram_poll - generic datagram poll
 *	@file: file struct
 *	@sock: socket
 *	@wait: poll table
 *
 *	Datagram poll: Again totally generic. This also handles
 *	sequenced packet sockets providing the socket receive queue
 *	is only ever holding data ready to receive.
 *
 *	Note: when you _don't_ use this routine for this protocol,
 *	and you use a different write policy from sock_writeable()
 *	then please supply your own write_space callback.
 */
unsigned int datagram_poll(struct file *file, struct socket *sock,
			   poll_table *wait)
{
	struct sock *sk = sock->sk;
	unsigned int mask;

	poll_wait(file, sk->sk_sleep, wait);
	mask = 0;

	/* exceptional events? */
	if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
		mask |= POLLERR;
	if (sk->sk_shutdown == SHUTDOWN_MASK)
		mask |= POLLHUP;

	/* readable? */
	if (!skb_queue_empty(&sk->sk_receive_queue) ||
	    (sk->sk_shutdown & RCV_SHUTDOWN))
		mask |= POLLIN | POLLRDNORM;

	/* Connection-based need to check for termination and startup */
	if (connection_based(sk)) {
		if (sk->sk_state == TCP_CLOSE)
			mask |= POLLHUP;
		/* connection hasn't started yet? */
		if (sk->sk_state == TCP_SYN_SENT)
			return mask;
	}

	/* writable? */
	if (sock_writeable(sk))
		mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
	else
		set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);

	return mask;
}

EXPORT_SYMBOL(datagram_poll);
EXPORT_SYMBOL(skb_copy_and_csum_datagram_iovec);
EXPORT_SYMBOL(skb_copy_datagram_iovec);
EXPORT_SYMBOL(skb_free_datagram);
EXPORT_SYMBOL(skb_recv_datagram);