1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
|
/*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file "COPYING" in the main directory of this archive
* for more details.
*
* Copyright (C) 1999-2009 Silicon Graphics, Inc. All rights reserved.
*/
/*
* Cross Partition Network Interface (XPNET) support
*
* XPNET provides a virtual network layered on top of the Cross
* Partition communication layer.
*
* XPNET provides direct point-to-point and broadcast-like support
* for an ethernet-like device. The ethernet broadcast medium is
* replaced with a point-to-point message structure which passes
* pointers to a DMA-capable block that a remote partition should
* retrieve and pass to the upper level networking layer.
*
*/
#include <linux/module.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include "xp.h"
/*
* The message payload transferred by XPC.
*
* buf_pa is the physical address where the DMA should pull from.
*
* NOTE: for performance reasons, buf_pa should _ALWAYS_ begin on a
* cacheline boundary. To accomplish this, we record the number of
* bytes from the beginning of the first cacheline to the first useful
* byte of the skb (leadin_ignore) and the number of bytes from the
* last useful byte of the skb to the end of the last cacheline
* (tailout_ignore).
*
* size is the number of bytes to transfer which includes the skb->len
* (useful bytes of the senders skb) plus the leadin and tailout
*/
struct xpnet_message {
u16 version; /* Version for this message */
u16 embedded_bytes; /* #of bytes embedded in XPC message */
u32 magic; /* Special number indicating this is xpnet */
unsigned long buf_pa; /* phys address of buffer to retrieve */
u32 size; /* #of bytes in buffer */
u8 leadin_ignore; /* #of bytes to ignore at the beginning */
u8 tailout_ignore; /* #of bytes to ignore at the end */
unsigned char data; /* body of small packets */
};
/*
* Determine the size of our message, the cacheline aligned size,
* and then the number of message will request from XPC.
*
* XPC expects each message to exist in an individual cacheline.
*/
#define XPNET_MSG_SIZE XPC_MSG_PAYLOAD_MAX_SIZE
#define XPNET_MSG_DATA_MAX \
(XPNET_MSG_SIZE - offsetof(struct xpnet_message, data))
#define XPNET_MSG_NENTRIES (PAGE_SIZE / XPC_MSG_MAX_SIZE)
#define XPNET_MAX_KTHREADS (XPNET_MSG_NENTRIES + 1)
#define XPNET_MAX_IDLE_KTHREADS (XPNET_MSG_NENTRIES + 1)
/*
* Version number of XPNET implementation. XPNET can always talk to versions
* with same major #, and never talk to versions with a different version.
*/
#define _XPNET_VERSION(_major, _minor) (((_major) << 4) | (_minor))
#define XPNET_VERSION_MAJOR(_v) ((_v) >> 4)
#define XPNET_VERSION_MINOR(_v) ((_v) & 0xf)
#define XPNET_VERSION _XPNET_VERSION(1, 0) /* version 1.0 */
#define XPNET_VERSION_EMBED _XPNET_VERSION(1, 1) /* version 1.1 */
#define XPNET_MAGIC 0x88786984 /* "XNET" */
#define XPNET_VALID_MSG(_m) \
((XPNET_VERSION_MAJOR(_m->version) == XPNET_VERSION_MAJOR(XPNET_VERSION)) \
&& (msg->magic == XPNET_MAGIC))
#define XPNET_DEVICE_NAME "xp0"
/*
* When messages are queued with xpc_send_notify, a kmalloc'd buffer
* of the following type is passed as a notification cookie. When the
* notification function is called, we use the cookie to decide
* whether all outstanding message sends have completed. The skb can
* then be released.
*/
struct xpnet_pending_msg {
struct sk_buff *skb;
atomic_t use_count;
};
struct net_device *xpnet_device;
/*
* When we are notified of other partitions activating, we add them to
* our bitmask of partitions to which we broadcast.
*/
static unsigned long *xpnet_broadcast_partitions;
/* protect above */
static DEFINE_SPINLOCK(xpnet_broadcast_lock);
/*
* Since the Block Transfer Engine (BTE) is being used for the transfer
* and it relies upon cache-line size transfers, we need to reserve at
* least one cache-line for head and tail alignment. The BTE is
* limited to 8MB transfers.
*
* Testing has shown that changing MTU to greater than 64KB has no effect
* on TCP as the two sides negotiate a Max Segment Size that is limited
* to 64K. Other protocols May use packets greater than this, but for
* now, the default is 64KB.
*/
#define XPNET_MAX_MTU (0x800000UL - L1_CACHE_BYTES)
/* 32KB has been determined to be the ideal */
#define XPNET_DEF_MTU (0x8000UL)
/*
* The partid is encapsulated in the MAC address beginning in the following
* octet and it consists of two octets.
*/
#define XPNET_PARTID_OCTET 2
/* Define the XPNET debug device structures to be used with dev_dbg() et al */
struct device_driver xpnet_dbg_name = {
.name = "xpnet"
};
struct device xpnet_dbg_subname = {
.init_name = "", /* set to "" */
.driver = &xpnet_dbg_name
};
struct device *xpnet = &xpnet_dbg_subname;
/*
* Packet was recevied by XPC and forwarded to us.
*/
static void
xpnet_receive(short partid, int channel, struct xpnet_message *msg)
{
struct sk_buff *skb;
void *dst;
enum xp_retval ret;
if (!XPNET_VALID_MSG(msg)) {
/*
* Packet with a different XPC version. Ignore.
*/
xpc_received(partid, channel, (void *)msg);
xpnet_device->stats.rx_errors++;
return;
}
dev_dbg(xpnet, "received 0x%lx, %d, %d, %d\n", msg->buf_pa, msg->size,
msg->leadin_ignore, msg->tailout_ignore);
/* reserve an extra cache line */
skb = dev_alloc_skb(msg->size + L1_CACHE_BYTES);
if (!skb) {
dev_err(xpnet, "failed on dev_alloc_skb(%d)\n",
msg->size + L1_CACHE_BYTES);
xpc_received(partid, channel, (void *)msg);
xpnet_device->stats.rx_errors++;
return;
}
/*
* The allocated skb has some reserved space.
* In order to use xp_remote_memcpy(), we need to get the
* skb->data pointer moved forward.
*/
skb_reserve(skb, (L1_CACHE_BYTES - ((u64)skb->data &
(L1_CACHE_BYTES - 1)) +
msg->leadin_ignore));
/*
* Update the tail pointer to indicate data actually
* transferred.
*/
skb_put(skb, (msg->size - msg->leadin_ignore - msg->tailout_ignore));
/*
* Move the data over from the other side.
*/
if ((XPNET_VERSION_MINOR(msg->version) == 1) &&
(msg->embedded_bytes != 0)) {
dev_dbg(xpnet, "copying embedded message. memcpy(0x%p, 0x%p, "
"%lu)\n", skb->data, &msg->data,
(size_t)msg->embedded_bytes);
skb_copy_to_linear_data(skb, &msg->data,
(size_t)msg->embedded_bytes);
} else {
dst = (void *)((u64)skb->data & ~(L1_CACHE_BYTES - 1));
dev_dbg(xpnet, "transferring buffer to the skb->data area;\n\t"
"xp_remote_memcpy(0x%p, 0x%p, %hu)\n", dst,
(void *)msg->buf_pa, msg->size);
ret = xp_remote_memcpy(xp_pa(dst), msg->buf_pa, msg->size);
if (ret != xpSuccess) {
/*
* !!! Need better way of cleaning skb. Currently skb
* !!! appears in_use and we can't just call
* !!! dev_kfree_skb.
*/
dev_err(xpnet, "xp_remote_memcpy(0x%p, 0x%p, 0x%hx) "
"returned error=0x%x\n", dst,
(void *)msg->buf_pa, msg->size, ret);
xpc_received(partid, channel, (void *)msg);
xpnet_device->stats.rx_errors++;
return;
}
}
dev_dbg(xpnet, "<skb->head=0x%p skb->data=0x%p skb->tail=0x%p "
"skb->end=0x%p skb->len=%d\n", (void *)skb->head,
(void *)skb->data, skb_tail_pointer(skb), skb_end_pointer(skb),
skb->len);
skb->protocol = eth_type_trans(skb, xpnet_device);
skb->ip_summed = CHECKSUM_UNNECESSARY;
dev_dbg(xpnet, "passing skb to network layer\n"
KERN_DEBUG "\tskb->head=0x%p skb->data=0x%p skb->tail=0x%p "
"skb->end=0x%p skb->len=%d\n",
(void *)skb->head, (void *)skb->data, skb_tail_pointer(skb),
skb_end_pointer(skb), skb->len);
xpnet_device->last_rx = jiffies;
xpnet_device->stats.rx_packets++;
xpnet_device->stats.rx_bytes += skb->len + ETH_HLEN;
netif_rx_ni(skb);
xpc_received(partid, channel, (void *)msg);
}
/*
* This is the handler which XPC calls during any sort of change in
* state or message reception on a connection.
*/
static void
xpnet_connection_activity(enum xp_retval reason, short partid, int channel,
void *data, void *key)
{
DBUG_ON(partid < 0 || partid >= xp_max_npartitions);
DBUG_ON(channel != XPC_NET_CHANNEL);
switch (reason) {
case xpMsgReceived: /* message received */
DBUG_ON(data == NULL);
xpnet_receive(partid, channel, (struct xpnet_message *)data);
break;
case xpConnected: /* connection completed to a partition */
spin_lock_bh(&xpnet_broadcast_lock);
__set_bit(partid, xpnet_broadcast_partitions);
spin_unlock_bh(&xpnet_broadcast_lock);
netif_carrier_on(xpnet_device);
dev_dbg(xpnet, "%s connected to partition %d\n",
xpnet_device->name, partid);
break;
default:
spin_lock_bh(&xpnet_broadcast_lock);
__clear_bit(partid, xpnet_broadcast_partitions);
spin_unlock_bh(&xpnet_broadcast_lock);
if (bitmap_empty((unsigned long *)xpnet_broadcast_partitions
|