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
|
// SPDX-License-Identifier: GPL-2.0
/* Copyright(c) 2019 Intel Corporation. All rights rsvd. */
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/pci.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
#include <linux/dma-mapping.h>
#include <linux/workqueue.h>
#include <linux/aer.h>
#include <linux/fs.h>
#include <linux/io-64-nonatomic-lo-hi.h>
#include <linux/device.h>
#include <linux/idr.h>
#include <uapi/linux/idxd.h>
#include "registers.h"
#include "idxd.h"
MODULE_VERSION(IDXD_DRIVER_VERSION);
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Intel Corporation");
#define DRV_NAME "idxd"
static struct idr idxd_idrs[IDXD_TYPE_MAX];
static struct mutex idxd_idr_lock;
static struct pci_device_id idxd_pci_tbl[] = {
/* DSA ver 1.0 platforms */
{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_DSA_SPR0) },
{ 0, }
};
MODULE_DEVICE_TABLE(pci, idxd_pci_tbl);
static char *idxd_name[] = {
"dsa",
};
const char *idxd_get_dev_name(struct idxd_device *idxd)
{
return idxd_name[idxd->type];
}
static int idxd_setup_interrupts(struct idxd_device *idxd)
{
struct pci_dev *pdev = idxd->pdev;
struct device *dev = &pdev->dev;
struct msix_entry *msix;
struct idxd_irq_entry *irq_entry;
int i, msixcnt;
int rc = 0;
msixcnt = pci_msix_vec_count(pdev);
if (msixcnt < 0) {
dev_err(dev, "Not MSI-X interrupt capable.\n");
goto err_no_irq;
}
idxd->msix_entries = devm_kzalloc(dev, sizeof(struct msix_entry) *
msixcnt, GFP_KERNEL);
if (!idxd->msix_entries) {
rc = -ENOMEM;
goto err_no_irq;
}
for (i = 0; i < msixcnt; i++)
idxd->msix_entries[i].entry = i;
rc = pci_enable_msix_exact(pdev, idxd->msix_entries, msixcnt);
if (rc) {
dev_err(dev, "Failed enabling %d MSIX entries.\n", msixcnt);
goto err_no_irq;
}
dev_dbg(dev, "Enabled %d msix vectors\n", msixcnt);
/*
* We implement 1 completion list per MSI-X entry except for
* entry 0, which is for errors and others.
*/
idxd->irq_entries = devm_kcalloc(dev, msixcnt,
sizeof(struct idxd_irq_entry),
GFP_KERNEL);
if (!idxd->irq_entries) {
rc = -ENOMEM;
goto err_no_irq;
}
for (i = 0; i < msixcnt; i++) {
idxd->irq_entries[i].id = i;
idxd->irq_entries[i].idxd = idxd;
}
msix = &idxd->msix_entries[0];
irq_entry = &idxd->irq_entries[0];
rc = devm_request_threaded_irq(dev, msix->vector, idxd_irq_handler,
idxd_misc_thread, 0, "idxd-misc",
irq_entry);
if (rc < 0) {
dev_err(dev, "Failed to allocate misc interrupt.\n");
goto err_no_irq;
}
dev_dbg(dev, "Allocated idxd-misc handler on msix vector %d\n",
msix->vector);
/* first MSI-X entry is not for wq interrupts */
idxd->num_wq_irqs = msixcnt - 1;
for (i = 1; i < msixcnt; i++) {
msix = &idxd->msix_entries[i];
irq_entry = &idxd->irq_entries[i];
init_llist_head(&idxd->irq_entries[i].pending_llist);
INIT_LIST_HEAD(&idxd->irq_entries[i].work_list);
rc = devm_request_threaded_irq(dev, msix->vector,
idxd_irq_handler,
idxd_wq_thread, 0,
"idxd-portal", irq_entry);
if (rc < 0) {
dev_err(dev, "Failed to allocate irq %d.\n",
msix->vector);
goto err_no_irq;
}
dev_dbg(dev, "Allocated idxd-msix %d for vector %d\n",
i, msix->vector);
}
idxd_unmask_error_interrupts(idxd);
return 0;
err_no_irq:
/* Disable error interrupt generation */
idxd_mask_error_interrupts(idxd);
pci_disable_msix(pdev);
dev_err(dev, "No usable interrupts\n");
return rc;
}
static void idxd_wqs_free_lock(struct idxd_device *idxd)
{
int i;
for (i = 0; i < idxd->max_wqs; i++) {
struct idxd_wq *wq = &idxd->wqs[i];
percpu_free_rwsem(&wq->submit_lock);
}
}
static int idxd_setup_internals(struct idxd_device *idxd)
{
struct device *dev = &idxd->pdev->dev;
int i;
idxd->groups = devm_kcalloc(dev, idxd->max_groups,
sizeof(struct idxd_group), GFP_KERNEL);
if (!idxd->groups)
return -ENOMEM;
for (i = 0; i < idxd->max_groups; i++) {
idxd->groups[i].idxd = idxd;
idxd->groups[i].id = i;
idxd->groups[i].tc_a = -1;
idxd->groups[i].tc_b = -1;
}
idxd->wqs = devm_kcalloc(dev, idxd->max_wqs, sizeof(struct idxd_wq),
GFP_KERNEL);
if (!idxd->wqs)
return -ENOMEM;
idxd->engines = devm_kcalloc(dev, idxd->max_engines,
sizeof(struct idxd_engine), GFP_KERNEL);
if (!idxd->engines)
return -ENOMEM;
for (i = 0; i < idxd->max_wqs; i++) {
struct idxd_wq *wq = &idxd->wqs[i];
int rc;
wq->id = i;
wq->idxd = idxd;
mutex_init(&wq->wq_lock);
atomic_set(&wq->dq_count, 0);
init_waitqueue_head(&wq->submit_waitq);
rc = percpu_init_rwsem(&wq->submit_lock);
if (rc < 0) {
idxd_wqs_free_lock(idxd);
return rc;
}
}
for (i = 0; i < idxd->max_engines; i++) {
idxd->engines[i].idxd = idxd;
idxd->engines[i].id = i;
}
return 0;
}
static void idxd_read_table_offsets(struct idxd_device *idxd)
{
union offsets_reg offsets;
struct device *dev = &idxd->pdev->dev;
offsets.bits[0] = ioread64(idxd->reg_base + IDXD_TABLE_OFFSET);
offsets.bits[1] = ioread64(idxd->reg_base + IDXD_TABLE_OFFSET
+ sizeof(u64));
idxd->grpcfg_offset = offsets.grpcfg * 0x100;
dev_dbg(dev, "IDXD Group Config Offset: %#x\n", idxd->grpcfg_offset);
idxd->wqcfg_offset = offsets.wqcfg * 0x100;
dev_dbg(dev, "IDXD Work Queue Config Offset: %#x\n",
idxd->wqcfg_offset);
idxd->msix_perm_offset = offsets.msix_perm * 0x100;
dev_dbg(dev, "IDXD MSIX Permission Offset: %#x\n",
idxd->msix_perm_offset);
idxd->perfmon_offset = offsets.perfmon * 0x100;
dev_dbg(dev, "IDXD Perfmon Offset: %#x\n", idxd->perfmon_offset);
}
static void idxd_read_caps(struct idxd_device *idxd)
{
struct device *dev = &idxd->pdev->dev;
int i;
/* reading generic capabilities */
idxd->hw.gen_cap.bits = ioread64(idxd->reg_base + IDXD_GENCAP_OFFSET);
dev_dbg(dev, "gen_cap: %#llx\n", idxd->hw.gen_cap.bits);
idxd->max_xfer_bytes = 1ULL << idxd->hw.gen_cap.max_xfer_shift;
dev_dbg(dev, "max xfer size: %llu bytes\n", idxd->max_xfer_bytes);
idxd->max_batch_size = 1U << idxd->hw.gen_cap.max_batch_shift;
dev_dbg(dev, "max batch size: %u\n", idxd->max_batch_size);
if (idxd->hw.gen_cap.config_en)
set_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags);
/* reading group capabilities */
idxd->hw.group_cap.bits =
ioread64(idxd->reg_base + IDXD_GRPCAP_OFFSET);
dev_dbg(dev, "group_cap: %#llx\n", idxd->hw.group_cap.bits);
idxd->max_groups = idxd->hw.group_cap.num_groups;
dev_dbg(dev, "max groups: %u\n", idxd->max_groups);
idxd->max_tokens = idxd->hw.group_cap.total_tokens;
dev_dbg(dev, "max tokens: %u\n", idxd->max_tokens);
idxd->nr_tokens = idxd->max_tokens;
/* read engine capabilities */
idxd->hw.engine_cap.bits =
ioread64(idxd->reg_base + IDXD_ENGCAP_OFFSET);
dev_dbg(dev, "engine_cap: %#llx\n", idxd->hw.engine_cap.bits);
idxd->max_engines = idxd->hw.engine_cap.num_engines;
dev_dbg(dev, "max engines: %u\n", idxd->max_engines);
/* read workqueue capabilities */
idxd->hw.wq_cap.bits = ioread64(idxd->reg_base + IDXD_WQCAP_OFFSET);
dev_dbg(dev, "wq_cap: %#llx\n", idxd->hw.wq_cap.bits);
idxd->max_wq_size = idxd->hw.wq_cap.total_wq_size;
dev_dbg(dev, "total workqueue size: %u\n", idxd->max_wq_size);
idxd->max_wqs = idxd->hw.wq_cap.num_wqs;
dev_dbg(dev, "max workqueues: %u\n", idxd->max_wqs);
/* reading operation capabilities */
for (i = 0; i < 4; i++) {
idxd->hw.opcap.bits[i] = ioread64(idxd->reg_base +
IDXD_OPCAP_OFFSET + i * sizeof(u64));
dev_dbg(dev, "opcap[%d]: %#llx\n", i, idxd->hw.opcap.bits[i]);
}
}
static struct idxd_device *idxd_alloc(struct pci_dev *pdev,
void __iomem * const *iomap)
{
struct device *dev = &pdev->dev;
struct idxd_device *idxd;
idxd = devm_kzalloc(dev, sizeof(struct idxd_device), GFP_KERNEL);
if (!idxd)
return NULL;
idxd->pdev = pdev;
idxd->reg_base = iomap[IDXD_MMIO_BAR];
spin_lock_init(&idxd->dev_lock);
return idxd;
}
static int idxd_probe(struct idxd_device *idxd)
{
struct pci_dev *pdev = idxd->pdev;
struct device *dev = &pdev->dev;
int rc;
dev_dbg(dev, "%s entered and resetting device\n", __func__);
rc = idxd_device_reset(idxd);
if (rc < 0)
return rc;
dev_dbg(dev, "IDXD reset complete\n");
idxd_read_caps(idxd);
idxd_read_table_offsets(idxd);
rc = idxd_setup_internals(idxd);
if (rc)
goto err_setup;
rc = idxd_setup_interrupts(idxd);
if (rc)
goto err_setup;
dev_dbg(dev, "IDXD interrupt setup complete.\n");
mutex_lock(&idxd_idr_lock);
idxd->id = idr_alloc(&idxd_idrs[idxd->type], idxd, 0, 0, GFP_KERNEL);
mutex_unlock(&idxd_idr_lock);
if (idxd->id < 0) {
rc = -ENOMEM;
goto err_idr_fail;
}
dev_dbg(dev, "IDXD device %d probed successfully\n", idxd->id);
return 0;
err_idr_fail:
idxd_mask_error_interrupts(idxd);
idxd_mask_msix_vectors(idxd);
err_setup:
return rc;
}
static int idxd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
void __iomem * const *iomap;
struct device *dev = &pdev->dev;
struct idxd_device *idxd;
int rc;
unsigned int mask;
rc = pcim_enable_device(pdev);
if (rc)
return rc;
dev_dbg(dev, "Mapping BARs\n");
mask = (1 << IDXD_MMIO_BAR);
rc = pcim_iomap_regions(pdev, mask, DRV_NAME);
if (rc)
return rc;
iomap = pcim_iomap_table(pdev);
if (!iomap)
return -ENOMEM;
dev_dbg(dev, "Set DMA masks\n");
rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
if (rc)
rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
if (rc)
return rc;
rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
if (rc)
rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
if (rc)
return rc;
dev_dbg(dev, "Alloc IDXD context\n");
idxd = idxd_alloc(pdev, iomap);
if (!idxd)
return -ENOMEM;
idxd_set_type(idxd);
dev_dbg(dev, "Set PCI master\n");
pci_set_master(pdev);
pci_set_drvdata(pdev, idxd);
idxd->hw.version = ioread32(idxd->reg_base + IDXD_VER_OFFSET);
rc = idxd_probe(idxd);
if (rc) {
dev_err(dev, "Intel(R) IDXD DMA Engine init failed\n");
return -ENODEV;
}
rc = idxd_setup_sysfs(idxd);
if (rc) {
dev_err(dev, "IDXD sysfs setup failed\n");
return -ENODEV;
}
idxd->state = IDXD_DEV_CONF_READY;
dev_info(&pdev->dev, "Intel(R) Accelerator Device (v%x)\n",
idxd->hw.version);
return 0;
}
static void idxd_shutdown(struct pci_dev *pdev)
{
struct idxd_device *idxd = pci_get_drvdata(pdev);
int rc, i;
struct idxd_irq_entry *irq_entry;
int msixcnt = pci_msix_vec_count(pdev);
unsigned long flags;
spin_lock_irqsave(&idxd->dev_lock, flags);
rc = idxd_device_disable(idxd);
spin_unlock_irqrestore(&idxd->dev_lock, flags);
if (rc)
dev_err(&pdev->dev, "Disabling device failed\n");
dev_dbg(&pdev->dev, "%s called\n", __func__);
idxd_mask_msix_vectors(idxd);
idxd_mask_error_interrupts(idxd);
for (i = 0; i < msixcnt; i++) {
irq_entry = &idxd->irq_entries[i];
synchronize_irq(idxd->msix_entries[i].vector);
if (i == 0)
continue;
}
}
static void idxd_remove(struct pci_dev *pdev)
{
struct idxd_device *idxd = pci_get_drvdata(pdev);
dev_dbg(&pdev->dev, "%s called\n", __func__);
idxd_cleanup_sysfs(idxd);
idxd_shutdown(pdev);
idxd_wqs_free_lock(idxd);
mutex_lock(&idxd_idr_lock);
idr_remove(&idxd_idrs[idxd->type], idxd->id);
mutex_unlock(&idxd_idr_lock);
}
static struct pci_driver idxd_pci_driver = {
.name = DRV_NAME,
.id_table = idxd_pci_tbl,
.probe = idxd_pci_probe,
.remove = idxd_remove,
.shutdown = idxd_shutdown,
};
static int __init idxd_init_module(void)
{
int err, i;
/*
* If the CPU does not support write512, there's no point in
* enumerating the device. We can not utilize it.
*/
if (!boot_cpu_has(X86_FEATURE_MOVDIR64B)) {
pr_warn("idxd driver failed to load without MOVDIR64B.\n");
return -ENODEV;
}
pr_info("%s: Intel(R) Accelerator Devices Driver %s\n",
DRV_NAME, IDXD_DRIVER_VERSION);
mutex_init(&idxd_idr_lock);
for (i = 0; i < IDXD_TYPE_MAX; i++)
idr_init(&idxd_idrs[i]);
err = idxd_register_bus_type();
if (err < 0)
return err;
err = idxd_register_driver();
if (err < 0)
goto err_idxd_driver_register;
err = pci_register_driver(&idxd_pci_driver);
if (err)
goto err_pci_register;
return 0;
err_pci_register:
idxd_unregister_driver();
err_idxd_driver_register:
idxd_unregister_bus_type();
return err;
}
module_init(idxd_init_module);
static void __exit idxd_exit_module(void)
{
pci_unregister_driver(&idxd_pci_driver);
idxd_unregister_bus_type();
}
module_exit(idxd_exit_module);
|