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
|
/*
* Copyright 2014 IBM Corp.
*
* 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.
*/
#include <linux/spinlock.h>
#include <linux/module.h>
#include <linux/export.h>
#include <linux/kernel.h>
#include <linux/bitmap.h>
#include <linux/sched.h>
#include <linux/poll.h>
#include <linux/pid.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <asm/cputable.h>
#include <asm/current.h>
#include <asm/copro.h>
#include "cxl.h"
#define CXL_NUM_MINORS 256 /* Total to reserve */
#define CXL_DEV_MINORS 13 /* 1 control + 4 AFUs * 3 (dedicated/master/shared) */
#define CXL_CARD_MINOR(adapter) (adapter->adapter_num * CXL_DEV_MINORS)
#define CXL_AFU_MINOR_D(afu) (CXL_CARD_MINOR(afu->adapter) + 1 + (3 * afu->slice))
#define CXL_AFU_MINOR_M(afu) (CXL_AFU_MINOR_D(afu) + 1)
#define CXL_AFU_MINOR_S(afu) (CXL_AFU_MINOR_D(afu) + 2)
#define CXL_AFU_MKDEV_D(afu) MKDEV(MAJOR(cxl_dev), CXL_AFU_MINOR_D(afu))
#define CXL_AFU_MKDEV_M(afu) MKDEV(MAJOR(cxl_dev), CXL_AFU_MINOR_M(afu))
#define CXL_AFU_MKDEV_S(afu) MKDEV(MAJOR(cxl_dev), CXL_AFU_MINOR_S(afu))
#define CXL_DEVT_ADAPTER(dev) (MINOR(dev) / CXL_DEV_MINORS)
#define CXL_DEVT_AFU(dev) ((MINOR(dev) % CXL_DEV_MINORS - 1) / 3)
#define CXL_DEVT_IS_CARD(dev) (MINOR(dev) % CXL_DEV_MINORS == 0)
static dev_t cxl_dev;
static struct class *cxl_class;
static int __afu_open(struct inode *inode, struct file *file, bool master)
{
struct cxl *adapter;
struct cxl_afu *afu;
struct cxl_context *ctx;
int adapter_num = CXL_DEVT_ADAPTER(inode->i_rdev);
int slice = CXL_DEVT_AFU(inode->i_rdev);
int rc = -ENODEV;
pr_devel("afu_open afu%i.%i\n", slice, adapter_num);
if (!(adapter = get_cxl_adapter(adapter_num)))
return -ENODEV;
if (slice > adapter->slices)
goto err_put_adapter;
spin_lock(&adapter->afu_list_lock);
if (!(afu = adapter->afu[slice])) {
spin_unlock(&adapter->afu_list_lock);
goto err_put_adapter;
}
get_device(&afu->dev);
spin_unlock(&adapter->afu_list_lock);
if (!afu->current_mode)
goto err_put_afu;
if (!(ctx = cxl_context_alloc())) {
rc = -ENOMEM;
goto err_put_afu;
}
if ((rc = cxl_context_init(ctx, afu, master, inode->i_mapping)))
goto err_put_afu;
pr_devel("afu_open pe: %i\n", ctx->pe);
file->private_data = ctx;
cxl_ctx_get();
/* Our ref on the AFU will now hold the adapter */
put_device(&adapter->dev);
return 0;
err_put_afu:
put_device(&afu->dev);
err_put_adapter:
put_device(&adapter->dev);
return rc;
}
static int afu_open(struct inode *inode, struct file *file)
{
return __afu_open(inode, file, false);
}
static int afu_master_open(struct inode *inode, struct file *file)
{
return __afu_open(inode, file, true);
}
static int afu_release(struct inode *inode, struct file *file)
{
struct cxl_context *ctx = file->private_data;
pr_devel("%s: closing cxl file descriptor. pe: %i\n",
__func__, ctx->pe);
cxl_context_detach(ctx);
mutex_lock(&ctx->mapping_lock);
ctx->mapping = NULL;
mutex_unlock(&ctx->mapping_lock);
put_device(&ctx->afu->dev);
/*
* At this this point all bottom halfs have finished and we should be
* getting no more IRQs from the hardware for this context. Once it's
* removed from the IDR (and RCU synchronised) it's safe to free the
* sstp and context.
*/
cxl_context_free(ctx);
cxl_ctx_put();
return 0;
}
static long afu_ioctl_start_work(struct cxl_context *ctx,
struct cxl_ioctl_start_work __user *uwork)
{
struct cxl_ioctl_start_work work;
u64 amr = 0;
int rc;
pr_devel("%s: pe: %i\n", __func__, ctx->pe);
/* Do this outside the status_mutex to avoid a circular dependency with
* the locking in cxl_mmap_fault() */
if (copy_from_user(&work, uwork,
sizeof(struct cxl_ioctl_start_work))) {
rc = -EFAULT;
goto out;
}
mutex_lock(&ctx->status_mutex);
if (ctx->status != OPENED) {
rc = -EIO;
goto out;
}
/*
* if any of the reserved fields are set or any of the unused
* flags are set it's invalid
*/
if (work.reserved1 || work.reserved2 || work.reserved3 ||
work.reserved4 || work.reserved5 || work.reserved6 ||
(work.flags & ~CXL_START_WORK_ALL)) {
rc = -EINVAL;
goto out;
}
if (!(work.flags & CXL_START_WORK_NUM_IRQS))
work.num_interrupts = ctx->afu->pp_irqs;
else if ((work.num_interrupts < ctx->afu->pp_irqs) ||
(work.num_interrupts > ctx->afu->irqs_max)) {
rc = -EINVAL;
goto out;
}
if ((rc = afu_register_irqs(ctx, work.num_interrupts)))
goto out;
if (work.flags & CXL_START_WORK_AMR)
amr = work.amr & mfspr(SPRN_UAMOR);
/*
* We grab the PID here and not in the file open to allow for the case
* where a process (master, some daemon, etc) has opened the chardev on
* behalf of another process, so the AFU's mm gets bound to the process
* that performs this ioctl and not the process that opened the file.
*/
ctx->pid = get_pid(get_task_pid(current, PIDTYPE_PID));
if ((rc = cxl_attach_process(ctx, false, work.work_element_descriptor,
amr)))
goto out;
ctx->status = STARTED;
rc = 0;
out:
mutex_unlock(&ctx->status_mutex);
return rc;
}
static long afu_ioctl_process_element(struct cxl_context *ctx,
int __user *upe)
{
pr_devel("%s: pe: %i\n", __func__, ctx->pe);
if (copy_to_user(upe, &ctx->pe, sizeof(__u32)))
return -EFAULT;
return 0;
}
static long afu_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
struct cxl_context *ctx = file->private_data;
if (ctx->status == CLOSED)
return -EIO;
pr_devel("afu_ioctl\n");
switch (cmd) {
case CXL_IOCTL_START_WORK:
return afu_ioctl_start_work(ctx, (struct cxl_ioctl_start_work __user *)arg);
case CXL_IOCTL_GET_PROCESS_ELEMENT:
return afu_ioctl_process_element(ctx, (__u32 __user *)arg);
}
return -EINVAL;
}
static long afu_compat_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
return afu_ioctl(file, cmd, arg);
}
static int afu_mmap(struct file *file, struct vm_area_struct *vm)
{
struct cxl_context *ctx = file->private_data;
/* AFU must be started before we can MMIO */
if (ctx->status != STARTED)
return -EIO;
return cxl_context_iomap(ctx, vm);
}
static unsigned int afu_poll(struct file *file, struct poll_table_struct *poll)
{
struct cxl_context *ctx = file->private_data;
int mask = 0;
unsigned long flags;
poll_wait(file, &ctx->wq, poll);
pr_devel("afu_poll wait done pe: %i\n<
|