Newer
Older
/*
* NET3 Protocol independent device support routines.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
* Derived from the non IP parts of dev.c 1.0.19
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
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Mark Evans, <evansmp@uhura.aston.ac.uk>
*
* Additional Authors:
* Florian la Roche <rzsfl@rz.uni-sb.de>
* Alan Cox <gw4pts@gw4pts.ampr.org>
* David Hinds <dahinds@users.sourceforge.net>
* Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
* Adam Sulmicki <adam@cfar.umd.edu>
* Pekka Riikonen <priikone@poesidon.pspt.fi>
*
* Changes:
* D.J. Barrow : Fixed bug where dev->refcnt gets set
* to 2 if register_netdev gets called
* before net_dev_init & also removed a
* few lines of code in the process.
* Alan Cox : device private ioctl copies fields back.
* Alan Cox : Transmit queue code does relevant
* stunts to keep the queue safe.
* Alan Cox : Fixed double lock.
* Alan Cox : Fixed promisc NULL pointer trap
* ???????? : Support the full private ioctl range
* Alan Cox : Moved ioctl permission check into
* drivers
* Tim Kordas : SIOCADDMULTI/SIOCDELMULTI
* Alan Cox : 100 backlog just doesn't cut it when
* you start doing multicast video 8)
* Alan Cox : Rewrote net_bh and list manager.
* Alan Cox : Fix ETH_P_ALL echoback lengths.
* Alan Cox : Took out transmit every packet pass
* Saved a few bytes in the ioctl handler
* Alan Cox : Network driver sets packet type before
* calling netif_rx. Saves a function
* call a packet.
* Alan Cox : Hashed net_bh()
* Richard Kooijman: Timestamp fixes.
* Alan Cox : Wrong field in SIOCGIFDSTADDR
* Alan Cox : Device lock protection.
* Alan Cox : Fixed nasty side effect of device close
* changes.
* Rudi Cilibrasi : Pass the right thing to
* set_mac_address()
* Dave Miller : 32bit quantity for the device lock to
* make it work out on a Sparc.
* Bjorn Ekwall : Added KERNELD hack.
* Alan Cox : Cleaned up the backlog initialise.
* Craig Metz : SIOCGIFCONF fix if space for under
* 1 device.
* Thomas Bogendoerfer : Return ENODEV for dev_open, if there
* is no device open function.
* Andi Kleen : Fix error reporting for SIOCGIFCONF
* Michael Chastain : Fix signed/unsigned for SIOCGIFCONF
* Cyrus Durgin : Cleaned for KMOD
* Adam Sulmicki : Bug Fix : Network Device Unload
* A network device unload needs to purge
* the backlog queue.
* Paul Rusty Russell : SIOCSIFNAME
* Pekka Riikonen : Netdev boot-time settings code
* Andrew Morton : Make unregister_netdevice wait
* indefinitely on dev->refcnt
* J Hadi Salim : - Backlog queue sampling
* - netif_rx() feedback
*/
#include <asm/uaccess.h>
#include <asm/system.h>
#include <linux/bitops.h>
#include <linux/config.h>
#include <linux/cpu.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/errno.h>
#include <linux/interrupt.h>
#include <linux/if_ether.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/notifier.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <linux/rtnetlink.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/stat.h>
#include <linux/if_bridge.h>
#include <linux/divert.h>
#include <net/dst.h>
#include <net/pkt_sched.h>
#include <net/checksum.h>
#include <linux/highmem.h>
#include <linux/init.h>
#include <linux/kmod.h>
#include <linux/module.h>
#include <linux/kallsyms.h>
#include <linux/netpoll.h>
#include <linux/rcupdate.h>
#include <linux/delay.h>
#ifdef CONFIG_NET_RADIO
#include <linux/wireless.h> /* Note : will define WIRELESS_EXT */
#include <net/iw_handler.h>
#endif /* CONFIG_NET_RADIO */
#include <asm/current.h>
/*
* The list of packet types we will receive (as opposed to discard)
* and the routines to invoke.
*
* Why 16. Because with 16 the only overlap we get on a hash of the
* low nibble of the protocol value is RARP/SNAP/X.25.
*
* NOTE: That is no longer true with the addition of VLAN tags. Not
* sure which should go first, but I bet it won't make much
* difference if we are running VLANs. The good news is that
* this protocol won't be in the list unless compiled in, so
* the average user (w/out VLANs) will not be adversly affected.
* --BLG
*
* 0800 IP
* 8100 802.1Q VLAN
* 0001 802.3
* 0002 AX.25
* 0004 802.2
* 8035 RARP
* 0005 SNAP
* 0805 X.25
* 0806 ARP
* 8137 IPX
* 0009 Localtalk
* 86DD IPv6
*/
static DEFINE_SPINLOCK(ptype_lock);
static struct list_head ptype_base[16]; /* 16 way hashed list */
static struct list_head ptype_all; /* Taps */
/*
* The @dev_base list is protected by @dev_base_lock and the rtln
* semaphore.
*
* Pure readers hold dev_base_lock for reading.
*
* Writers must hold the rtnl semaphore while they loop through the
* dev_base list, and hold dev_base_lock for writing when they do the
* actual updates. This allows pure readers to access the list even
* while a writer is preparing to update it.
*
* To put it another way, dev_base_lock is held for writing only to
* protect against pure readers; the rtnl semaphore provides the
* protection against other writers.
*
* See, for example usages, register_netdevice() and
* unregister_netdevice(), which must be called with the rtnl
* semaphore held.
*/
struct net_device *dev_base;
static struct net_device **dev_tail = &dev_base;
DEFINE_RWLOCK(dev_base_lock);
EXPORT_SYMBOL(dev_base);
EXPORT_SYMBOL(dev_base_lock);
#define NETDEV_HASHBITS 8
static struct hlist_head dev_name_head[1<<NETDEV_HASHBITS];
static struct hlist_head dev_index_head[1<<NETDEV_HASHBITS];
static inline struct hlist_head *dev_name_hash(const char *name)
{
unsigned hash = full_name_hash(name, strnlen(name, IFNAMSIZ));
return &dev_name_head[hash & ((1<<NETDEV_HASHBITS)-1)];
}
static inline struct hlist_head *dev_index_hash(int ifindex)
{
return &dev_index_head[ifindex & ((1<<NETDEV_HASHBITS)-1)];
}
/*
* Our notifier list
*/
static struct notifier_block *netdev_chain;
/*
* Device drivers call our routines to queue packets here. We empty the
* queue in the local softnet handler.
*/
DEFINE_PER_CPU(struct softnet_data, softnet_data) = { NULL };
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
#ifdef CONFIG_SYSFS
extern int netdev_sysfs_init(void);
extern int netdev_register_sysfs(struct net_device *);
extern void netdev_unregister_sysfs(struct net_device *);
#else
#define netdev_sysfs_init() (0)
#define netdev_register_sysfs(dev) (0)
#define netdev_unregister_sysfs(dev) do { } while(0)
#endif
/*******************************************************************************
Protocol management and registration routines
*******************************************************************************/
/*
* For efficiency
*/
int netdev_nit;
/*
* Add a protocol ID to the list. Now that the input handler is
* smarter we can dispense with all the messy stuff that used to be
* here.
*
* BEWARE!!! Protocol handlers, mangling input packets,
* MUST BE last in hash buckets and checking protocol handlers
* MUST start from promiscuous ptype_all chain in net_bh.
* It is true now, do not change it.
* Explanation follows: if protocol handler, mangling packet, will
* be the first on list, it is not able to sense, that packet
* is cloned and should be copied-on-write, so that it will
* change it and subsequent readers will get broken packet.
* --ANK (980803)
*/
/**
* dev_add_pack - add packet handler
* @pt: packet type declaration
*
* Add a protocol handler to the networking stack. The passed &packet_type
* is linked into kernel lists and may not be freed until it has been
* removed from the kernel lists.
*
* This call does not sleep therefore it can not
* guarantee all CPU's that are in middle of receiving packets
* will see the new packet type (until the next received packet).
*/
void dev_add_pack(struct packet_type *pt)
{
int hash;
spin_lock_bh(&ptype_lock);
if (pt->type == htons(ETH_P_ALL)) {
netdev_nit++;
list_add_rcu(&pt->list, &ptype_all);
} else {
hash = ntohs(pt->type) & 15;
list_add_rcu(&pt->list, &ptype_base[hash]);
}
spin_unlock_bh(&ptype_lock);
}
/**
* __dev_remove_pack - remove packet handler
* @pt: packet type declaration
*
* Remove a protocol handler that was previously added to the kernel
* protocol handlers by dev_add_pack(). The passed &packet_type is removed
* from the kernel lists and can be freed or reused once this function
* returns.
*
* The packet type might still be in use by receivers
* and must not be freed until after all the CPU's have gone
* through a quiescent state.
*/
void __dev_remove_pack(struct packet_type *pt)
{
struct list_head *head;
struct packet_type *pt1;
spin_lock_bh(&ptype_lock);
if (pt->type == htons(ETH_P_ALL)) {
netdev_nit--;
head = &ptype_all;
} else
head = &ptype_base[ntohs(pt->type) & 15];
list_for_each_entry(pt1, head, list) {
if (pt == pt1) {
list_del_rcu(&pt->list);
goto out;
}
}
printk(KERN_WARNING "dev_remove_pack: %p not found.\n", pt);
out:
spin_unlock_bh(&ptype_lock);
}
/**
* dev_remove_pack - remove packet handler
* @pt: packet type declaration
*
* Remove a protocol handler that was previously added to the kernel
* protocol handlers by dev_add_pack(). The passed &packet_type is removed
* from the kernel lists and can be freed or reused once this function
* returns.
*
* This call sleeps to guarantee that no CPU is looking at the packet
* type after return.
*/
void dev_remove_pack(struct packet_type *pt)
{
__dev_remove_pack(pt);
synchronize_net();
}
/******************************************************************************
Device Boot-time Settings Routines
*******************************************************************************/
/* Boot time configuration table */
static struct netdev_boot_setup dev_boot_setup[NETDEV_BOOT_SETUP_MAX];
/**
* netdev_boot_setup_add - add new setup entry
* @name: name of the device
* @map: configured settings for the device
*
* Adds new setup entry to the dev_boot_setup list. The function
* returns 0 on error and 1 on success. This is a generic routine to
* all netdevices.
*/
static int netdev_boot_setup_add(char *name, struct ifmap *map)
{
struct netdev_boot_setup *s;
int i;
s = dev_boot_setup;
for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) {
if (s[i].name[0] == '\0' || s[i].name[0] == ' ') {
memset(s[i].name, 0, sizeof(s[i].name));
strcpy(s[i].name, name);
memcpy(&s[i].map, map, sizeof(s[i].map));
break;
}
}
return i >= NETDEV_BOOT_SETUP_MAX ? 0 : 1;
}
/**
* netdev_boot_setup_check - check boot time settings
* @dev: the netdevice
*
* Check boot time settings for the device.
* The found settings are set for the device to be used
* later in the device probing.
* Returns 0 if no settings found, 1 if they are.
*/
int netdev_boot_setup_check(struct net_device *dev)
{
struct netdev_boot_setup *s = dev_boot_setup;
int i;
for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) {
if (s[i].name[0] != '\0' && s[i].name[0] != ' ' &&
!strncmp(dev->name, s[i].name, strlen(s[i].name))) {
dev->irq = s[i].map.irq;
dev->base_addr = s[i].map.base_addr;
dev->mem_start = s[i].map.mem_start;
dev->mem_end = s[i].map.mem_end;
return 1;
}
}
return 0;
}
/**
* netdev_boot_base - get address from boot time settings
* @prefix: prefix for network device
* @unit: id for network device
*
* Check boot time settings for the base address of device.
* The found settings are set for the device to be used
* later in the device probing.
* Returns 0 if no settings found.
*/
unsigned long netdev_boot_base(const char *prefix, int unit)
{
const struct netdev_boot_setup *s = dev_boot_setup;
char name[IFNAMSIZ];
int i;
sprintf(name, "%s%d", prefix, unit);
/*
* If device already registered then return base of 1
* to indicate not to probe for this interface
*/
if (__dev_get_by_name(name))
return 1;
for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++)
if (!strcmp(name, s[i].name))
return s[i].map.base_addr;
return 0;
}
/*
* Saves at boot time configured settings for any netdevice.
*/
int __init netdev_boot_setup(char *str)
{
int ints[5];
struct ifmap map;
str = get_options(str, ARRAY_SIZE(ints), ints);
if (!str || !*str)
return 0;
/* Save settings */
memset(&map, 0, sizeof(map));
if (ints[0] > 0)
map.irq = ints[1];
if (ints[0] > 1)
map.base_addr = ints[2];
if (ints[0] > 2)
map.mem_start = ints[3];
if (ints[0] > 3)
map.mem_end = ints[4];
/* Add new entry to the list */
return netdev_boot_setup_add(str, &map);
}
__setup("netdev=", netdev_boot_setup);
/*******************************************************************************
Device Interface Subroutines
*******************************************************************************/
/**
* __dev_get_by_name - find a device by its name
* @name: name to find
*
* Find an interface by name. Must be called under RTNL semaphore
* or @dev_base_lock. If the name is found a pointer to the device
* is returned. If the name is not found then %NULL is returned. The
* reference counters are not incremented so the caller must be
* careful with locks.
*/
struct net_device *__dev_get_by_name(const char *name)
{
struct hlist_node *p;
hlist_for_each(p, dev_name_hash(name)) {
struct net_device *dev
= hlist_entry(p, struct net_device, name_hlist);
if (!strncmp(dev->name, name, IFNAMSIZ))
return dev;
}
return NULL;
}
/**
* dev_get_by_name - find a device by its name
* @name: name to find
*
* Find an interface by name. This can be called from any
* context and does its own locking. The returned handle has
* the usage count incremented and the caller must use dev_put() to
* release it when it is no longer needed. %NULL is returned if no
* matching device is found.
*/
struct net_device *dev_get_by_name(const char *name)
{
struct net_device *dev;
read_lock(&dev_base_lock);
dev = __dev_get_by_name(name);
if (dev)
dev_hold(dev);
read_unlock(&dev_base_lock);
return dev;
}
/**
* __dev_get_by_index - find a device by its ifindex
* @ifindex: index of device
*
* Search for an interface by index. Returns %NULL if the device
* is not found or a pointer to the device. The device has not
* had its reference counter increased so the caller must be careful
* about locking. The caller must hold either the RTNL semaphore
* or @dev_base_lock.
*/
struct net_device *__dev_get_by_index(int ifindex)
{
struct hlist_node *p;
hlist_for_each(p, dev_index_hash(ifindex)) {
struct net_device *dev
= hlist_entry(p, struct net_device, index_hlist);
if (dev->ifindex == ifindex)
return dev;
}
return NULL;
}
/**
* dev_get_by_index - find a device by its ifindex
* @ifindex: index of device
*
* Search for an interface by index. Returns NULL if the device
* is not found or a pointer to the device. The device returned has
* had a reference added and the pointer is safe until the user calls
* dev_put to indicate they have finished with it.
*/
struct net_device *dev_get_by_index(int ifindex)
{
struct net_device *dev;
read_lock(&dev_base_lock);
dev = __dev_get_by_index(ifindex);
if (dev)
dev_hold(dev);
read_unlock(&dev_base_lock);
return dev;
}
/**
* dev_getbyhwaddr - find a device by its hardware address
* @type: media type of device
* @ha: hardware address
*
* Search for an interface by MAC address. Returns NULL if the device
* is not found or a pointer to the device. The caller must hold the
* rtnl semaphore. The returned device has not had its ref count increased
* and the caller must therefore be careful about locking
*
* BUGS:
* If the API was consistent this would be __dev_get_by_hwaddr
*/
struct net_device *dev_getbyhwaddr(unsigned short type, char *ha)
{
struct net_device *dev;
ASSERT_RTNL();
for (dev = dev_base; dev; dev = dev->next)
if (dev->type == type &&
!memcmp(dev->dev_addr, ha, dev->addr_len))
break;
return dev;
}
EXPORT_SYMBOL(dev_getbyhwaddr);
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
struct net_device *dev_getfirstbyhwtype(unsigned short type)
{
struct net_device *dev;
rtnl_lock();
for (dev = dev_base; dev; dev = dev->next) {
if (dev->type == type) {
dev_hold(dev);
break;
}
}
rtnl_unlock();
return dev;
}
EXPORT_SYMBOL(dev_getfirstbyhwtype);
/**
* dev_get_by_flags - find any device with given flags
* @if_flags: IFF_* values
* @mask: bitmask of bits in if_flags to check
*
* Search for any interface with the given flags. Returns NULL if a device
* is not found or a pointer to the device. The device returned has
* had a reference added and the pointer is safe until the user calls
* dev_put to indicate they have finished with it.
*/
struct net_device * dev_get_by_flags(unsigned short if_flags, unsigned short mask)
{
struct net_device *dev;
read_lock(&dev_base_lock);
for (dev = dev_base; dev != NULL; dev = dev->next) {
if (((dev->flags ^ if_flags) & mask) == 0) {
dev_hold(dev);
break;
}
}
read_unlock(&dev_base_lock);
return dev;
}
/**
* dev_valid_name - check if name is okay for network device
* @name: name string
*
* Network device names need to be valid file names to
* to allow sysfs to work
*/
int dev_valid_name(const char *name)
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
{
return !(*name == '\0'
|| !strcmp(name, ".")
|| !strcmp(name, "..")
|| strchr(name, '/'));
}
/**
* dev_alloc_name - allocate a name for a device
* @dev: device
* @name: name format string
*
* Passed a format string - eg "lt%d" it will try and find a suitable
* id. Not efficient for many devices, not called a lot. The caller
* must hold the dev_base or rtnl lock while allocating the name and
* adding the device in order to avoid duplicates. Returns the number
* of the unit assigned or a negative errno code.
*/
int dev_alloc_name(struct net_device *dev, const char *name)
{
int i = 0;
char buf[IFNAMSIZ];
const char *p;
const int max_netdevices = 8*PAGE_SIZE;
long *inuse;
struct net_device *d;
p = strnchr(name, IFNAMSIZ-1, '%');
if (p) {
/*
* Verify the string as this thing may have come from
* the user. There must be either one "%d" and no other "%"
* characters.
*/
if (p[1] != 'd' || strchr(p + 2, '%'))
return -EINVAL;
/* Use one page as a bit array of possible slots */
inuse = (long *) get_zeroed_page(GFP_ATOMIC);
if (!inuse)
return -ENOMEM;
for (d = dev_base; d; d = d->next) {
if (!sscanf(d->name, name, &i))
continue;
if (i < 0 || i >= max_netdevices)
continue;
/* avoid cases where sscanf is not exact inverse of printf */
snprintf(buf, sizeof(buf), name, i);
if (!strncmp(buf, d->name, IFNAMSIZ))
set_bit(i, inuse);
}
i = find_first_zero_bit(inuse, max_netdevices);
free_page((unsigned long) inuse);
}
snprintf(buf, sizeof(buf), name, i);
if (!__dev_get_by_name(buf)) {
strlcpy(dev->name, buf, IFNAMSIZ);
return i;
}
/* It is possible to run out of possible slots
* when the name is long and there isn't enough space left
* for the digits, or if all bits are used.
*/
return -ENFILE;
}
/**
* dev_change_name - change name of a device
* @dev: device
* @newname: name (or format string) must be at least IFNAMSIZ
*
* Change name of a device, can pass format strings "eth%d".
* for wildcarding.
*/
int dev_change_name(struct net_device *dev, char *newname)
{
int err = 0;
ASSERT_RTNL();
if (dev->flags & IFF_UP)
return -EBUSY;
if (!dev_valid_name(newname))
return -EINVAL;
if (strchr(newname, '%')) {
err = dev_alloc_name(dev, newname);
if (err < 0)
return err;
strcpy(newname, dev->name);
}
else if (__dev_get_by_name(newname))
return -EEXIST;
else
strlcpy(dev->name, newname, IFNAMSIZ);
err = class_device_rename(&dev->class_dev, dev->name);
if (!err) {
hlist_del(&dev->name_hlist);
hlist_add_head(&dev->name_hlist, dev_name_hash(dev->name));
notifier_call_chain(&netdev_chain, NETDEV_CHANGENAME, dev);
}
return err;
}
/**
* netdev_features_change - device changes fatures
* @dev: device to cause notification
*
* Called to indicate a device has changed features.
*/
void netdev_features_change(struct net_device *dev)
{
notifier_call_chain(&netdev_chain, NETDEV_FEAT_CHANGE, dev);
}
EXPORT_SYMBOL(netdev_features_change);
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
/**
* netdev_state_change - device changes state
* @dev: device to cause notification
*
* Called to indicate a device has changed state. This function calls
* the notifier chains for netdev_chain and sends a NEWLINK message
* to the routing socket.
*/
void netdev_state_change(struct net_device *dev)
{
if (dev->flags & IFF_UP) {
notifier_call_chain(&netdev_chain, NETDEV_CHANGE, dev);
rtmsg_ifinfo(RTM_NEWLINK, dev, 0);
}
}
/**
* dev_load - load a network module
* @name: name of interface
*
* If a network interface is not present and the process has suitable
* privileges this function loads the module. If module loading is not
* available in this kernel then it becomes a nop.
*/
void dev_load(const char *name)
{
struct net_device *dev;
read_lock(&dev_base_lock);
dev = __dev_get_by_name(name);
read_unlock(&dev_base_lock);
if (!dev && capable(CAP_SYS_MODULE))
request_module("%s", name);
}
static int default_rebuild_header(struct sk_buff *skb)
{
printk(KERN_DEBUG "%s: default_rebuild_header called -- BUG!\n",
skb->dev ? skb->dev->name : "NULL!!!");
kfree_skb(skb);
return 1;
}
/**
* dev_open - prepare an interface for use.
* @dev: device to open
*
* Takes a device from down to up state. The device's private open
* function is invoked and then the multicast lists are loaded. Finally
* the device is moved into the up state and a %NETDEV_UP message is
* sent to the netdev notifier chain.
*
* Calling this function on an active interface is a nop. On a failure
* a negative errno code is returned.
*/
int dev_open(struct net_device *dev)
{
int ret = 0;
/*
* Is it already up?
*/
if (dev->flags & IFF_UP)
return 0;
/*
* Is it even present?
*/
if (!netif_device_present(dev))
return -ENODEV;
/*
* Call device private open method
*/
set_bit(__LINK_STATE_START, &dev->state);
if (dev->open) {
ret = dev->open(dev);
if (ret)
clear_bit(__LINK_STATE_START, &dev->state);
}
/*
* If it went open OK then:
*/
if (!ret) {
/*
* Set the flags.
*/
dev->flags |= IFF_UP;
/*
* Initialize multicasting status
*/
dev_mc_upload(dev);
/*
* Wakeup transmit queue engine
*/
dev_activate(dev);
/*
* ... and announce new interface.
*/
notifier_call_chain(&netdev_chain, NETDEV_UP, dev);
}
return ret;
}
/**
* dev_close - shutdown an interface.
* @dev: device to shutdown
*
* This function moves an active device into down state. A
* %NETDEV_GOING_DOWN is sent to the netdev notifier chain. The device
* is then deactivated and finally a %NETDEV_DOWN is sent to the notifier
* chain.
*/
int dev_close(struct net_device *dev)
{
if (!(dev->flags & IFF_UP))
return 0;
/*
* Tell people we are going down, so that they can
* prepare to death, when device is still operating.
*/
notifier_call_chain(&netdev_chain, NETDEV_GOING_DOWN, dev);
dev_deactivate(dev);
clear_bit(__LINK_STATE_START, &dev->state);
/* Synchronize to scheduled poll. We cannot touch poll list,
* it can be even on different cpu. So just clear netif_running(),
* and wait when poll really will happen. Actually, the best place
* for this is inside dev->stop() after device stopped its irq
* engine, but this requires more changes in devices. */
smp_mb__after_clear_bit(); /* Commit netif_running(). */
while (test_bit(__LINK_STATE_RX_SCHED, &dev->state)) {
/* No hurry. */
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
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
}
/*
* Call the device specific close. This cannot fail.
* Only if device is UP
*
* We allow it to be called even after a DETACH hot-plug
* event.
*/
if (dev->stop)
dev->stop(dev);
/*
* Device is now down.
*/
dev->flags &= ~IFF_UP;
/*
* Tell people we are down
*/
notifier_call_chain(&netdev_chain, NETDEV_DOWN, dev);
return 0;
}
/*
* Device change register/unregister. These are not inline or static
* as we export them to the world.
*/
/**
* register_netdevice_notifier - register a network notifier block
* @nb: notifier
*
* Register a notifier to be called when network device events occur.
* The notifier passed is linked into the kernel structures and must
* not be reused until it has been unregistered. A negative errno code
* is returned on a failure.
*
* When registered all registration and up events are replayed
* to the new notifier to allow device to have a race free
* view of the network device list.
*/
int register_netdevice_notifier(struct notifier_block *nb)
{
struct net_device *dev;
int err;
rtnl_lock();
err = notifier_chain_register(&netdev_chain, nb);
if (!err) {
for (dev = dev_base; dev; dev = dev->next) {
nb->notifier_call(nb, NETDEV_REGISTER, dev);
if (dev->flags & IFF_UP)
nb->notifier_call(nb, NETDEV_UP, dev);
}
}
rtnl_unlock();
return err;
}
/**
* unregister_netdevice_notifier - unregister a network notifier block
* @nb: notifier
*
* Unregister a notifier previously registered by
* register_netdevice_notifier(). The notifier is unlinked into the
* kernel structures and may then be reused. A negative errno code
* is returned on a failure.
*/
int unregister_netdevice_notifier(struct notifier_block *nb)
{
return notifier_chain_unregister(&netdev_chain, nb);
}
/**
* call_netdevice_notifiers - call all network notifier blocks
* @val: value passed unmodified to notifier function
* @v: pointer passed unmodified to notifier function
*
* Call all network notifier blocks. Parameters and return value
* are as for notifier_call_chain().
*/
int call_netdevice_notifiers(unsigned long val, void *v)
{
return notifier_call_chain(&netdev_chain, val, v);
}
/* When > 0 there are consumers of rx skb time stamps */
static atomic_t netstamp_needed = ATOMIC_INIT(0);
void net_enable_timestamp(void)
{
atomic_inc(&netstamp_needed);
}
void net_disable_timestamp(void)
{
atomic_dec(&netstamp_needed);
}
void __net_timestamp(struct sk_buff *skb)
{
struct timeval tv;
do_gettimeofday(&tv);
skb_set_timestamp(skb, &tv);
}
EXPORT_SYMBOL(__net_timestamp);
static inline void net_timestamp(struct sk_buff *skb)
__net_timestamp(skb);
skb->tstamp.off_sec = 0;
skb->tstamp.off_usec = 0;
}
}
/*
* Support routine. Sends outgoing frames to any network
* taps currently in use.
*/
void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
{
struct packet_type *ptype;
net_timestamp(skb);
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
rcu_read_lock();
list_for_each_entry_rcu(ptype, &ptype_all, list) {
/* Never send packets back to the socket
* they originated from - MvS (miquels@drinkel.ow.org)
*/
if ((ptype->dev == dev || !ptype->dev) &&
(ptype->af_packet_priv == NULL ||
(struct sock *)ptype->af_packet_priv != skb->sk)) {
struct sk_buff *skb2= skb_clone(skb, GFP_ATOMIC);
if (!skb2)
break;
/* skb->nh should be correctly
set by sender, so that the second statement is
just protection against buggy protocols.
*/
skb2->mac.raw = skb2->data;
if (skb2->nh.raw < skb2->data ||
skb2->nh.raw > skb2->tail) {
if (net_ratelimit())
printk(KERN_CRIT "protocol %04x is "
"buggy, dev %s\n",
skb2->protocol, dev->name);
skb2->nh.raw = skb2->data;
}
skb2->h.raw = skb2->nh.raw;
skb2->pkt_type = PACKET_OUTGOING;
ptype->func(skb2, skb->dev, ptype, skb->dev);
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
}
}
rcu_read_unlock();
}
/*
* Invalidate hardware checksum when packet is to be mangled, and
* complete checksum manually on outgoing path.
*/
int skb_checksum_help(struct sk_buff *skb, int inward)
{
unsigned int csum;
int ret = 0, offset = skb->h.raw - skb->data;
if (inward) {
skb->ip_summed = CHECKSUM_NONE;
goto out;
}
if (skb_cloned(skb)) {
ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
if (ret)
goto out;
}
BUG_ON(offset > (int)skb->len);
csum = skb_checksum(skb, offset, skb->len-offset, 0);
offset = skb->tail - skb->h.raw;
BUG_ON(offset <= 0);
BUG_ON(skb->csum + 2 > offset);
*(u16*)(skb->h.raw + skb->csum) = csum_fold(csum);
skb->ip_summed = CHECKSUM_NONE;
out:
return ret;
}
/* Take action when hardware reception checksum errors are detected. */
#ifdef CONFIG_BUG
void netdev_rx_csum_fault(struct net_device *dev)
{
if (net_ratelimit()) {
printk(KERN_ERR "%s: hw csum failure.\n",
dev ? dev->name : "<unknown>");
dump_stack();
}
}
EXPORT_SYMBOL(netdev_rx_csum_fault);
#endif
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
#ifdef CONFIG_HIGHMEM
/* Actually, we should eliminate this check as soon as we know, that:
* 1. IOMMU is present and allows to map all the memory.
* 2. No high memory really exists on this machine.
*/
static inline int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
{
int i;
if (dev->features & NETIF_F_HIGHDMA)
return 0;
for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
if (PageHighMem(skb_shinfo(skb)->frags[i].page))
return 1;
return 0;
}
#else
#define illegal_highdma(dev, skb) (0)
#endif
/* Keep head the same: replace data */
int __skb_linearize(struct sk_buff *skb, gfp_t gfp_mask)
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
{
unsigned int size;
u8 *data;
long offset;
struct skb_shared_info *ninfo;
int headerlen = skb->data - skb->head;
int expand = (skb->tail + skb->data_len) - skb->end;
if (skb_shared(skb))
BUG();
if (expand <= 0)
expand = 0;
size = skb->end - skb->head + expand;
size = SKB_DATA_ALIGN(size);
data = kmalloc(size + sizeof(struct skb_shared_info), gfp_mask);
if (!data)
return -ENOMEM;
/* Copy entire thing */
if (skb_copy_bits(skb, -headerlen, data, headerlen + skb->len))
BUG();
/* Set up shinfo */
ninfo = (struct skb_shared_info*)(data + size);
atomic_set(&ninfo->dataref, 1);
ninfo->tso_size = skb_shinfo(skb)->tso_size;
ninfo->tso_segs = skb_shinfo(skb)->tso_segs;
ninfo->nr_frags = 0;
ninfo->frag_list = NULL;
/* Offset between the two in bytes */
offset = data - skb->head;
/* Free old data. */
skb_release_data(skb);
skb->head = data;
skb->end = data + size;
/* Set up new pointers */
skb->h.raw += offset;
skb->nh.raw += offset;
skb->mac.raw += offset;
skb->tail += offset;
skb->data += offset;
/* We are no longer a clone, even if we were. */
skb->cloned = 0;
skb->tail += skb->data_len;
skb->data_len = 0;
return 0;
}
#define HARD_TX_LOCK(dev, cpu) { \
if ((dev->features & NETIF_F_LLTX) == 0) { \
spin_lock(&dev->xmit_lock); \
dev->xmit_lock_owner = cpu; \
} \
}
#define HARD_TX_UNLOCK(dev) { \
if ((dev->features & NETIF_F_LLTX) == 0) { \
dev->xmit_lock_owner = -1; \
spin_unlock(&dev->xmit_lock); \
} \
}
/**
* dev_queue_xmit - transmit a buffer
* @skb: buffer to transmit
*
* Queue a buffer for transmission to a network device. The caller must
* have set the device and priority and built the buffer before calling
* this function. The function can be called from an interrupt.
*
* A negative errno code is returned on a failure. A success does not
* guarantee the frame will be transmitted as it may be dropped due
* to congestion or traffic shaping.
*
* -----------------------------------------------------------------------------------
* I notice this method can also return errors from the queue disciplines,
* including NET_XMIT_DROP, which is a positive value. So, errors can also
* be positive.
*
* Regardless of the return value, the skb is consumed, so it is currently
* difficult to retry a send to this method. (You can bump the ref count
* before sending to hold a reference for retry if you are careful.)
*
* When calling this method, interrupts MUST be enabled. This is because
* the BH enable code must have IRQs enabled so that it will not deadlock.
* --BLG
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
*/
int dev_queue_xmit(struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
struct Qdisc *q;
int rc = -ENOMEM;
if (skb_shinfo(skb)->frag_list &&
!(dev->features & NETIF_F_FRAGLIST) &&
__skb_linearize(skb, GFP_ATOMIC))
goto out_kfree_skb;
/* Fragmented skb is linearized if device does not support SG,
* or if at least one of fragments is in highmem and device
* does not support DMA from it.
*/
if (skb_shinfo(skb)->nr_frags &&
(!(dev->features & NETIF_F_SG) || illegal_highdma(dev, skb)) &&
__skb_linearize(skb, GFP_ATOMIC))
goto out_kfree_skb;
/* If packet is not checksummed and device does not support
* checksumming for this protocol, complete checksumming here.
*/
if (skb->ip_summed == CHECKSUM_HW &&
(!(dev->features & (NETIF_F_HW_CSUM | NETIF_F_NO_CSUM)) &&
(!(dev->features & NETIF_F_IP_CSUM) ||
skb->protocol != htons(ETH_P_IP))))
if (skb_checksum_help(skb, 0))
goto out_kfree_skb;
spin_lock_prefetch(&dev->queue_lock);
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
/* Disable soft irqs for various locks below. Also
* stops preemption for RCU.
*/
local_bh_disable();
/* Updates of qdisc are serialized by queue_lock.
* The struct Qdisc which is pointed to by qdisc is now a
* rcu structure - it may be accessed without acquiring
* a lock (but the structure may be stale.) The freeing of the
* qdisc will be deferred until it's known that there are no
* more references to it.
*
* If the qdisc has an enqueue function, we still need to
* hold the queue_lock before calling it, since queue_lock
* also serializes access to the device queue.
*/
q = rcu_dereference(dev->qdisc);
#ifdef CONFIG_NET_CLS_ACT
skb->tc_verd = SET_TC_AT(skb->tc_verd,AT_EGRESS);
#endif
if (q->enqueue) {
/* Grab device queue */
spin_lock(&dev->queue_lock);
rc = q->enqueue(skb, q);
qdisc_run(dev);
spin_unlock(&dev->queue_lock);
rc = rc == NET_XMIT_BYPASS ? NET_XMIT_SUCCESS : rc;
goto out;
}
/* The device has no queue. Common case for software devices:
loopback, all the sorts of tunnels...
Really, it is unlikely that xmit_lock protection is necessary here.
(f.e. loopback and IP tunnels are clean ignoring statistics
counters.)
However, it is possible, that they rely on protection
made by us here.
Check this and shot the lock. It is not prone from deadlocks.
Either shot noqueue qdisc, it is even simpler 8)
*/
if (dev->flags & IFF_UP) {
int cpu = smp_processor_id(); /* ok because BHs are off */
if (dev->xmit_lock_owner != cpu) {
HARD_TX_LOCK(dev, cpu);
if (!netif_queue_stopped(dev)) {
if (netdev_nit)
dev_queue_xmit_nit(skb, dev);
rc = 0;
if (!dev->hard_start_xmit(skb, dev)) {
HARD_TX_UNLOCK(dev);
goto out;
}
}
HARD_TX_UNLOCK(dev);
if (net_ratelimit())
printk(KERN_CRIT "Virtual device %s asks to "
"queue packet!\n", dev->name);
} else {
/* Recursion is detected! It is possible,
* unfortunately */
if (net_ratelimit())
printk(KERN_CRIT "Dead loop on virtual device "
"%s, fix it urgently!\n", dev->name);
}
}
rc = -ENETDOWN;
local_bh_enable();
out_kfree_skb:
kfree_skb(skb);
return rc;
out:
local_bh_enable();
return rc;
}
/*=======================================================================
Receiver routines
=======================================================================*/
int netdev_max_backlog = 1000;
int netdev_budget = 300;
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
int weight_p = 64; /* old backlog weight */
DEFINE_PER_CPU(struct netif_rx_stats, netdev_rx_stat) = { 0, };
/**
* netif_rx - post buffer to the network code
* @skb: buffer to post
*
* This function receives a packet from a device driver and queues it for
* the upper (protocol) levels to process. It always succeeds. The buffer
* may be dropped during processing for congestion control or by the
* protocol layers.
*
* return values:
* NET_RX_SUCCESS (no congestion)
* NET_RX_CN_LOW (low congestion)
* NET_RX_CN_MOD (moderate congestion)
* NET_RX_CN_HIGH (high congestion)
* NET_RX_DROP (packet was dropped)
*
*/
int netif_rx(struct sk_buff *skb)
{
struct softnet_data *queue;
unsigned long flags;
/* if netpoll wants it, pretend we never saw it */
if (netpoll_rx(skb))
return NET_RX_DROP;
if (!skb->tstamp.off_sec)
net_timestamp(skb);
/*
* The code is rearranged so that the path is the most
* short when CPU is congested, but is still operating.
*/
local_irq_save(flags);
queue = &__get_cpu_var(softnet_data);
__get_cpu_var(netdev_rx_stat).total++;
if (queue->input_pkt_queue.qlen <= netdev_max_backlog) {
if (queue->input_pkt_queue.qlen) {
enqueue:
dev_hold(skb->dev);
__skb_queue_tail(&queue->input_pkt_queue, skb);
local_irq_restore(flags);
return NET_RX_SUCCESS;
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
}
netif_rx_schedule(&queue->backlog_dev);
goto enqueue;
}
__get_cpu_var(netdev_rx_stat).dropped++;
local_irq_restore(flags);
kfree_skb(skb);
return NET_RX_DROP;
}
int netif_rx_ni(struct sk_buff *skb)
{
int err;
preempt_disable();
err = netif_rx(skb);
if (local_softirq_pending())
do_softirq();
preempt_enable();
return err;
}
EXPORT_SYMBOL(netif_rx_ni);
static inline struct net_device *skb_bond(struct sk_buff *skb)
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
}
static void net_tx_action(struct softirq_action *h)
{
struct softnet_data *sd = &__get_cpu_var(softnet_data);
if (sd->completion_queue) {
struct sk_buff *clist;
local_irq_disable();
clist = sd->completion_queue;
sd->completion_queue = NULL;
local_irq_enable();
while (clist) {
struct sk_buff *skb = clist;
clist = clist->next;
BUG_TRAP(!atomic_read(&skb->users));
__kfree_skb(skb);
}
}
if (sd->output_queue) {
struct net_device *head;
local_irq_disable();
head = sd->output_queue;
sd->output_queue = NULL;
local_irq_enable();
while (head) {
struct net_device *dev = head;
head = head->next_sched;
smp_mb__before_clear_bit();
clear_bit(__LINK_STATE_SCHED, &dev->state);
if (spin_trylock(&dev->queue_lock)) {
qdisc_run(dev);
spin_unlock(&dev->queue_lock);
} else {
netif_schedule(dev);
}
}
}
}
static __inline__ int deliver_skb(struct sk_buff *skb,
struct packet_type *pt_prev,
struct net_device *orig_dev)
return pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
}
#if defined(CONFIG_BRIDGE) || defined (CONFIG_BRIDGE_MODULE)
int (*br_handle_frame_hook)(struct net_bridge_port *p, struct sk_buff **pskb);
struct net_bridge;
struct net_bridge_fdb_entry *(*br_fdb_get_hook)(struct net_bridge *br,
unsigned char *addr);
void (*br_fdb_put_hook)(struct net_bridge_fdb_entry *ent);
static __inline__ int handle_bridge(struct sk_buff **pskb,
struct packet_type **pt_prev, int *ret,
struct net_device *orig_dev)
{
struct net_bridge_port *port;
if ((*pskb)->pkt_type == PACKET_LOOPBACK ||
(port = rcu_dereference((*pskb)->dev->br_port)) == NULL)
return 0;
if (*pt_prev) {
*ret = deliver_skb(*pskb, *pt_prev, orig_dev);
*pt_prev = NULL;
}
return br_handle_frame_hook(port, pskb);
}
#else
#define handle_bridge(skb, pt_prev, ret, orig_dev) (0)
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
#endif
#ifdef CONFIG_NET_CLS_ACT
/* TODO: Maybe we should just force sch_ingress to be compiled in
* when CONFIG_NET_CLS_ACT is? otherwise some useless instructions
* a compare and 2 stores extra right now if we dont have it on
* but have CONFIG_NET_CLS_ACT
* NOTE: This doesnt stop any functionality; if you dont have
* the ingress scheduler, you just cant add policies on ingress.
*
*/
static int ing_filter(struct sk_buff *skb)
{
struct Qdisc *q;
struct net_device *dev = skb->dev;
int result = TC_ACT_OK;
if (dev->qdisc_ingress) {
__u32 ttl = (__u32) G_TC_RTTL(skb->tc_verd);
if (MAX_RED_LOOP < ttl++) {
printk("Redir loop detected Dropping packet (%s->%s)\n",
skb->input_dev->name, skb->dev->name);
return TC_ACT_SHOT;
}
skb->tc_verd = SET_TC_RTTL(skb->tc_verd,ttl);
skb->tc_verd = SET_TC_AT(skb->tc_verd,AT_INGRESS);
spin_lock(&dev->ingress_lock);
if ((q = dev->qdisc_ingress) != NULL)
result = q->enqueue(skb, q);
spin_unlock(&dev->ingress_lock);
}
return result;
}
#endif
int netif_receive_skb(struct sk_buff *skb)
{
struct packet_type *ptype, *pt_prev;
int ret = NET_RX_DROP;
unsigned short type;
/* if we've gotten here through NAPI, check netpoll */
if (skb->dev->poll && netpoll_rx(skb))
return NET_RX_DROP;
if (!skb->tstamp.off_sec)
net_timestamp(skb);
if (!skb->input_dev)
skb->input_dev = skb->dev;
__get_cpu_var(netdev_rx_stat).total++;
skb->h.raw = skb->nh.raw = skb->data;
skb->mac_len = skb->nh.raw - skb->mac.raw;
pt_prev = NULL;
rcu_read_lock();
#ifdef CONFIG_NET_CLS_ACT
if (skb->tc_verd & TC_NCLS) {
skb->tc_verd = CLR_TC_NCLS(skb->tc_verd);
goto ncls;
}
#endif
list_for_each_entry_rcu(ptype, &ptype_all, list) {
if (!ptype->dev || ptype->dev == skb->dev) {
if (pt_prev)
pt_prev = ptype;
}
}
#ifdef CONFIG_NET_CLS_ACT
if (pt_prev) {
pt_prev = NULL; /* noone else should process this after*/
} else {
skb->tc_verd = SET_TC_OK2MUNGE(skb->tc_verd);
}
ret = ing_filter(skb);
if (ret == TC_ACT_SHOT || (ret == TC_ACT_STOLEN)) {
kfree_skb(skb);
goto out;
}
skb->tc_verd = 0;
ncls:
#endif
handle_diverter(skb);
if (handle_bridge(&skb, &pt_prev, &ret, orig_dev))
goto out;
type = skb->protocol;
list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type)&15], list) {
if (ptype->type == type &&
(!ptype->dev || ptype->dev == skb->dev)) {
if (pt_prev)
pt_prev = ptype;
}
}
if (pt_prev) {
ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
} else {
kfree_skb(skb);
/* Jamal, now you will not able to escape explaining
* me how you were going to use this. :-)
*/
ret = NET_RX_DROP;
}
out:
rcu_read_unlock();
return ret;
}
static int process_backlog(struct net_device *backlog_dev, int *budget)
{
int work = 0;
int quota = min(backlog_dev->quota, *budget);
struct softnet_data *queue = &__get_cpu_var(softnet_data);
unsigned long start_time = jiffies;
backlog_dev->weight = weight_p;
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
for (;;) {
struct sk_buff *skb;
struct net_device *dev;
local_irq_disable();
skb = __skb_dequeue(&queue->input_pkt_queue);
if (!skb)
goto job_done;
local_irq_enable();
dev = skb->dev;
netif_receive_skb(skb);
dev_put(dev);
work++;
if (work >= quota || jiffies - start_time > 1)
break;
}
backlog_dev->quota -= work;
*budget -= work;
return -1;
job_done:
backlog_dev->quota -= work;
*budget -= work;
list_del(&backlog_dev->poll_list);
smp_mb__before_clear_bit();
netif_poll_enable(backlog_dev);
local_irq_enable();
return 0;
}
static void net_rx_action(struct softirq_action *h)
{
struct softnet_data *queue = &__get_cpu_var(softnet_data);
unsigned long start_time = jiffies;
int budget = netdev_budget;
local_irq_disable();
while (!list_empty(&queue->poll_list)) {
struct net_device *dev;
if (budget <= 0 || jiffies - start_time > 1)
goto softnet_break;
local_irq_enable();
dev = list_entry(queue->poll_list.next,
struct net_device, poll_list);
if (dev->quota <= 0 || dev->poll(dev, &budget)) {
local_irq_disable();
list_del(&dev->poll_list);
list_add_tail(&dev->poll_list, &queue->poll_list);
if (dev->quota < 0)
dev->quota += dev->weight;
else
dev->quota = dev->weight;
} else {
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
dev_put(dev);
local_irq_disable();
}
}
out:
local_irq_enable();
return;
softnet_break:
__get_cpu_var(netdev_rx_stat).time_squeeze++;
__raise_softirq_irqoff(NET_RX_SOFTIRQ);
goto out;
}
static gifconf_func_t * gifconf_list [NPROTO];
/**
* register_gifconf - register a SIOCGIF handler
* @family: Address family
* @gifconf: Function handler
*
* Register protocol dependent address dumping routines. The handler
* that is passed must not be freed or reused until it has been replaced
* by another handler.
*/
int register_gifconf(unsigned int family, gifconf_func_t * gifconf)
{
if (family >= NPROTO)
return -EINVAL;
gifconf_list[family] = gifconf;
return 0;
}
/*
* Map an interface index to its name (SIOCGIFNAME)
*/
/*
* We need this ioctl for efficient implementation of the
* if_indextoname() function required by the IPv6 API. Without
* it, we would have to search all the interfaces to find a
* match. --pb
*/
static int dev_ifname(struct ifreq __user *arg)
{
struct net_device *dev;
struct ifreq ifr;
/*
* Fetch the caller's info block.
*/
if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
return -EFAULT;
read_lock(&dev_base_lock);
dev = __dev_get_by_index(ifr.ifr_ifindex);
if (!dev) {
read_unlock(&dev_base_lock);
return -ENODEV;
}
strcpy(ifr.ifr_name, dev->name);
read_unlock(&dev_base_lock);
if (copy_to_user(arg, &ifr, sizeof(struct ifreq)))
return -EFAULT;
return 0;
}
/*
* Perform a SIOCGIFCONF call. This structure will change
* size eventually, and there is nothing I can do about it.
* Thus we will need a 'compatibility mode'.
*/
static int dev_ifconf(char __user *arg)
{
struct ifconf ifc;
struct net_device *dev;
char __user *pos;
int len;
int total;
int i;
/*
* Fetch the caller's info block.
*/
if (copy_from_user(&ifc, arg, sizeof(struct ifconf)))
return -EFAULT;
pos = ifc.ifc_buf;
len = ifc.ifc_len;
/*
* Loop over the interfaces, and write an info block for each.
*/
total = 0;
for (dev = dev_base; dev; dev = dev->next) {
for (i = 0; i < NPROTO; i++) {
if (gifconf_list[i]) {
int done;
if (!pos)
done = gifconf_list[i](dev, NULL, 0);
else
done = gifconf_list[i](dev, pos + total,
len - total);
if (done < 0)
return -EFAULT;
total += done;
}
}
}
/*
* All done. Write the updated control block back to the caller.
*/
ifc.ifc_len = total;
/*
* Both BSD and Solaris return 0 here, so we do too.
*/
return copy_to_user(arg, &ifc, sizeof(struct ifconf)) ? -EFAULT : 0;
}
#ifdef CONFIG_PROC_FS
/*
* This is invoked by the /proc filesystem handler to display a device
* in detail.
*/
static __inline__ struct net_device *dev_get_idx(loff_t pos)
{
struct net_device *dev;
loff_t i;
for (i = 0, dev = dev_base; dev && i < pos; ++i, dev = dev->next);
return i == pos ? dev : NULL;
}
void *dev_seq_start(struct seq_file *seq, loff_t *pos)
{
read_lock(&dev_base_lock);
return *pos ? dev_get_idx(*pos - 1) : SEQ_START_TOKEN;
}
void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
++*pos;
return v == SEQ_START_TOKEN ? dev_base : ((struct net_device *)v)->next;
}
void dev_seq_stop(struct seq_file *seq, void *v)
{
read_unlock(&dev_base_lock);
}
static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev)
{
if (dev->get_stats) {
struct net_device_stats *stats = dev->get_stats(dev);
seq_printf(seq, "%6s:%8lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu "
"%8lu %7lu %4lu %4lu %4lu %5lu %7lu %10lu\n",
dev->name, stats->rx_bytes, stats->rx_packets,
stats->rx_errors,
stats->rx_dropped + stats->rx_missed_errors,
stats->rx_fifo_errors,
stats->rx_length_errors + stats->rx_over_errors +
stats->rx_crc_errors + stats->rx_frame_errors,
stats->rx_compressed, stats->multicast,
stats->tx_bytes, stats->tx_packets,
stats->tx_errors, stats->tx_dropped,
stats->tx_fifo_errors, stats->collisions,
stats->tx_carrier_errors +
stats->tx_aborted_errors +
stats->tx_window_errors +
stats->tx_heartbeat_errors,
stats->tx_compressed);
} else
seq_printf(seq, "%6s: No statistics available.\n", dev->name);
}
/*
* Called from the PROCfs module. This now uses the new arbitrary sized
* /proc/net interface to create /proc/net/dev
*/
static int dev_seq_show(struct seq_file *seq, void *v)
{
if (v == SEQ_START_TOKEN)
seq_puts(seq, "Inter-| Receive "
" | Transmit\n"
" face |bytes packets errs drop fifo frame "
"compressed multicast|bytes packets errs "
"drop fifo colls carrier compressed\n");
else
dev_seq_printf_stats(seq, v);
return 0;
}
static struct netif_rx_stats *softnet_get_online(loff_t *pos)
{
struct netif_rx_stats *rc = NULL;
while (*pos < NR_CPUS)
if (cpu_online(*pos)) {
rc = &per_cpu(netdev_rx_stat, *pos);
break;
} else
++*pos;
return rc;
}
static void *softnet_seq_start(struct seq_file *seq, loff_t *pos)
{
return softnet_get_online(pos);
}
static void *softnet_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
++*pos;
return softnet_get_online(pos);
}
static void softnet_seq_stop(struct seq_file *seq, void *v)
{
}
static int softnet_seq_show(struct seq_file *seq, void *v)
{
struct netif_rx_stats *s = v;
seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x\n",
s->total, s->dropped, s->time_squeeze, 0,
0, 0, 0, 0, /* was fastroute */
s->cpu_collision );
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
return 0;
}
static struct seq_operations dev_seq_ops = {
.start = dev_seq_start,
.next = dev_seq_next,
.stop = dev_seq_stop,
.show = dev_seq_show,
};
static int dev_seq_open(struct inode *inode, struct file *file)
{
return seq_open(file, &dev_seq_ops);
}
static struct file_operations dev_seq_fops = {
.owner = THIS_MODULE,
.open = dev_seq_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
};
static struct seq_operations softnet_seq_ops = {
.start = softnet_seq_start,
.next = softnet_seq_next,
.stop = softnet_seq_stop,
.show = softnet_seq_show,
};
static int softnet_seq_open(struct inode *inode, struct file *file)
{
return seq_open(file, &softnet_seq_ops);
}
static struct file_operations softnet_seq_fops = {
.owner = THIS_MODULE,
.open = softnet_seq_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
};
#ifdef WIRELESS_EXT
extern int wireless_proc_init(void);
#else
#define wireless_proc_init() 0
#endif
static int __init dev_proc_init(void)
{
int rc = -ENOMEM;
if (!proc_net_fops_create("dev", S_IRUGO, &dev_seq_fops))
goto out;
if (!proc_net_fops_create("softnet_stat", S_IRUGO, &softnet_seq_fops))
goto out_dev;
if (wireless_proc_init())
goto out_softnet;
rc = 0;
out:
return rc;
out_softnet:
proc_net_remove("softnet_stat");
out_dev:
proc_net_remove("dev");
goto out;
}
#else
#define dev_proc_init() 0
#endif /* CONFIG_PROC_FS */
/**
* netdev_set_master - set up master/slave pair
* @slave: slave device
* @master: new master device
*
* Changes the master device of the slave. Pass %NULL to break the
* bonding. The caller must hold the RTNL semaphore. On a failure
* a negative errno code is returned. On success the reference counts
* are adjusted, %RTM_NEWLINK is sent to the routing socket and the
* function returns zero.
*/
int netdev_set_master(struct net_device *slave, struct net_device *master)
{
struct net_device *old = slave->master;
ASSERT_RTNL();
if (master) {
if (old)
return -EBUSY;
dev_hold(master);
}
slave->master = master;
synchronize_net();
if (old)
dev_put(old);
if (master)
slave->flags |= IFF_SLAVE;
else
slave->flags &= ~IFF_SLAVE;
rtmsg_ifinfo(RTM_NEWLINK, slave, IFF_SLAVE);
return 0;
}
/**
* dev_set_promiscuity - update promiscuity count on a device
* @dev: device
* @inc: modifier
*
* Add or remove promsicuity from a device. While the count in the device
* remains above zero the interface remains promiscuous. Once it hits zero
* the device reverts back to normal filtering operation. A negative inc
* value is used to drop promiscuity on the device.
*/
void dev_set_promiscuity(struct net_device *dev, int inc)
{
unsigned short old_flags = dev->flags;
if ((dev->promiscuity += inc) == 0)
dev->flags &= ~IFF_PROMISC;
else
dev->flags |= IFF_PROMISC;
if (dev->flags != old_flags) {
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
dev_mc_upload(dev);
printk(KERN_INFO "device %s %s promiscuous mode\n",
dev->name, (dev->flags & IFF_PROMISC) ? "entered" :
"left");
}
}
/**
* dev_set_allmulti - update allmulti count on a device
* @dev: device
* @inc: modifier
*
* Add or remove reception of all multicast frames to a device. While the
* count in the device remains above zero the interface remains listening
* to all interfaces. Once it hits zero the device reverts back to normal
* filtering operation. A negative @inc value is used to drop the counter
* when releasing a resource needing all multicasts.
*/
void dev_set_allmulti(struct net_device *dev, int inc)
{
unsigned short old_flags = dev->flags;
dev->flags |= IFF_ALLMULTI;
if ((dev->allmulti += inc) == 0)
dev->flags &= ~IFF_ALLMULTI;
if (dev->flags ^ old_flags)
dev_mc_upload(dev);
}
unsigned dev_get_flags(const struct net_device *dev)
{
unsigned flags;
flags = (dev->flags & ~(IFF_PROMISC |
IFF_ALLMULTI |
IFF_RUNNING)) |
(dev->gflags & (IFF_PROMISC |
IFF_ALLMULTI));
if (netif_running(dev) && netif_carrier_ok(dev))
flags |= IFF_RUNNING;
return flags;
}
int dev_change_flags(struct net_device *dev, unsigned flags)
{
int ret;
int old_flags = dev->flags;
/*
* Set the flags on our device.
*/
dev->flags = (flags & (IFF_DEBUG | IFF_NOTRAILERS | IFF_NOARP |
IFF_DYNAMIC | IFF_MULTICAST | IFF_PORTSEL |
IFF_AUTOMEDIA)) |
(dev->flags & (IFF_UP | IFF_VOLATILE | IFF_PROMISC |
IFF_ALLMULTI));
/*
* Load in the correct multicast list now the flags have changed.
*/
dev_mc_upload(dev);
/*
* Have we downed the interface. We handle IFF_UP ourselves
* according to user attempts to set it, rather than blindly
* setting it.
*/
ret = 0;
if ((old_flags ^ flags) & IFF_UP) { /* Bit is different ? */
ret = ((old_flags & IFF_UP) ? dev_close : dev_open)(dev);
if (!ret)
dev_mc_upload(dev);
}
if (dev->flags & IFF_UP &&
((old_flags ^ dev->flags) &~ (IFF_UP | IFF_PROMISC | IFF_ALLMULTI |
Loading
Loading full blame...