aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/infiniband/hw/hfi1/qsfp.c
blob: 52cce1c8b76a9051b23e03aafbf1f3ed7616d886 (plain)
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
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
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
744
745
746
747
748
749
750
751
752
753
754
755
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
// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
/*
 * Copyright(c) 2015, 2016 Intel Corporation.
 */

#include <linux/delay.h>
#include <linux/pci.h>
#include <linux/vmalloc.h>

#include "hfi.h"

/* for the given bus number, return the CSR for reading an i2c line */
static inline u32 i2c_in_csr(u32 bus_num)
{
	return bus_num ? ASIC_QSFP2_IN : ASIC_QSFP1_IN;
}

/* for the given bus number, return the CSR for writing an i2c line */
static inline u32 i2c_oe_csr(u32 bus_num)
{
	return bus_num ? ASIC_QSFP2_OE : ASIC_QSFP1_OE;
}

static void hfi1_setsda(void *data, int state)
{
	struct hfi1_i2c_bus *bus = (struct hfi1_i2c_bus *)data;
	struct hfi1_devdata *dd = bus->controlling_dd;
	u64 reg;
	u32 target_oe;

	target_oe = i2c_oe_csr(bus->num);
	reg = read_csr(dd, target_oe);
	/*
	 * The OE bit value is inverted and connected to the pin.  When
	 * OE is 0 the pin is left to be pulled up, when the OE is 1
	 * the pin is driven low.  This matches the "open drain" or "open
	 * collector" convention.
	 */
	if (state)
		reg &= ~QSFP_HFI0_I2CDAT;
	else
		reg |= QSFP_HFI0_I2CDAT;
	write_csr(dd, target_oe, reg);
	/* do a read to force the write into the chip */
	(void)read_csr(dd, target_oe);
}

static void hfi1_setscl(void *data, int state)
{
	struct hfi1_i2c_bus *bus = (struct hfi1_i2c_bus *)data;
	struct hfi1_devdata *dd = bus->controlling_dd;
	u64 reg;
	u32 target_oe;

	target_oe = i2c_oe_csr(bus->num);
	reg = read_csr(dd, target_oe);
	/*
	 * The OE bit value is inverted and connected to the pin.  When
	 * OE is 0 the pin is left to be pulled up, when the OE is 1
	 * the pin is driven low.  This matches the "open drain" or "open
	 * collector" convention.
	 */
	if (state)
		reg &= ~QSFP_HFI0_I2CCLK;
	else
		reg |= QSFP_HFI0_I2CCLK;
	write_csr(dd, target_oe, reg);
	/* do a read to force the write into the chip */
	(void)read_csr(dd, target_oe);
}

static int hfi1_getsda(void *data)
{
	struct hfi1_i2c_bus *bus = (struct hfi1_i2c_bus *)data;
	u64 reg;
	u32 target_in;

	hfi1_setsda(data, 1);	/* clear OE so we do not pull line down */
	udelay(2);		/* 1us pull up + 250ns hold */

	target_in = i2c_in_csr(bus->num);
	reg = read_csr(bus->controlling_dd, target_in);
	return !!(reg & QSFP_HFI0_I2CDAT);
}

static int hfi1_getscl(void *data)
{
	struct hfi1_i2c_bus *bus = (struct hfi1_i2c_bus *)data;
	u64 reg;
	u32 target_in;

	hfi1_setscl(data, 1);	/* clear OE so we do not pull line down */
	udelay(2);		/* 1us pull up + 250ns hold */

	target_in = i2c_in_csr(bus->num);
	reg = read_csr(bus->controlling_dd, target_in);
	return !!(reg & QSFP_HFI0_I2CCLK);
}

/*
 * Allocate and initialize the given i2c bus number.
 * Returns NULL on failure.
 */
static struct hfi1_i2c_bus *init_i2c_bus(struct hfi1_devdata *dd,
					 struct hfi1_asic_data *ad, int num)
{
	struct hfi1_i2c_bus *bus;
	int ret;

	bus = kzalloc(sizeof(*bus), GFP_KERNEL);
	if (!bus)
		return NULL;

	bus->controlling_dd = dd;
	bus->num = num;	/* our bus number */

	bus->algo.setsda = hfi1_setsda;
	bus->algo.setscl = hfi1_setscl;
	bus->algo.getsda = hfi1_getsda;
	bus->algo.getscl = hfi1_getscl;
	bus->algo.udelay = 5;
	bus->algo.timeout = usecs_to_jiffies(100000);
	bus->algo.data = bus;

	bus->adapter.owner = THIS_MODULE;
	bus->adapter.algo_data = &bus->algo;
	bus->adapter.dev.parent = &dd->pcidev->dev;
	snprintf(bus->adapter.name, sizeof(bus->adapter.name),
		 "hfi1_i2c%d", num);

	ret = i2c_bit_add_bus(&bus->adapter);
	if (ret) {
		dd_dev_info(dd, "%s: unable to add i2c bus %d, err %d\n",
			    __func__, num, ret);
		kfree(bus);
		return NULL;
	}

	return bus;
}

/*
 * Initialize i2c buses.
 * Return 0 on success, -errno on error.
 */
int set_up_i2c(struct hfi1_devdata *dd, struct hfi1_asic_data *ad)
{
	ad->i2c_bus0 = init_i2c_bus(dd, ad, 0);
	ad->i2c_bus1 = init_i2c_bus(dd, ad, 1);
	if (!ad->i2c_bus0 || !ad->i2c_bus1)
		return -ENOMEM;
	return 0;
};

static void clean_i2c_bus(struct hfi1_i2c_bus *bus)
{
	if (bus) {
		i2c_del_adapter(&bus->adapter);
		kfree(bus);
	}
}

void clean_up_i2c(struct hfi1_devdata *dd, struct hfi1_asic_data *ad)
{
	if (!ad)
		return;
	clean_i2c_bus(ad->i2c_bus0);
	ad->i2c_bus0 = NULL;
	clean_i2c_bus(ad->i2c_bus1);
	ad->i2c_bus1 = NULL;
}

static int i2c_bus_write(struct hfi1_devdata *dd, struct hfi1_i2c_bus *i2c,
			 u8 slave_addr, int offset, int offset_size,
			 u8 *data, u16 len)
{
	int ret;
	int num_msgs;
	u8 offset_bytes[2];
	struct i2c_msg msgs[2];

	switch (offset_size) {
	case 0:
		num_msgs = 1;
		msgs[0].addr = slave_addr;
		msgs[0].flags = 0;
		msgs[0].len = len;
		msgs[0].buf = data;
		break;
	case 2:
		offset_bytes[1] = (offset >> 8) & 0xff;
		fallthrough;
	case 1:
		num_msgs = 2;
		offset_bytes[0] = offset & 0xff;

		msgs[0].addr = slave_addr;
		msgs[0].flags = 0;
		msgs[0].len = offset_size;
		msgs[0].buf = offset_bytes;

		msgs[1].addr = slave_addr;
		msgs[1].flags = I2C_M_NOSTART;
		msgs[1].len = len;
		msgs[1].buf = data;
		break;
	default:
		return -EINVAL;
	}

	i2c->controlling_dd = dd;
	ret = i2c_transfer(&i2c->adapter, msgs, num_msgs);
	if (ret != num_msgs) {
		dd_dev_err(dd, "%s: bus %d, i2c slave 0x%x, offset 0x%x, len 0x%x; write failed, ret %d\n",
			   __func__, i2c->num, slave_addr, offset, len, ret);
		return ret < 0 ? ret : -EIO;
	}
	return 0;
}

static int i2c_bus_read(struct hfi1_devdata *dd, struct hfi1_i2c_bus *bus,
			u8 slave_addr, int offset, int offset_size,
			u8 *data, u16 len)
{
	int ret;
	int num_msgs;
	u8 offset_bytes[2];
	struct i2c_msg msgs[2];

	switch (offset_size) {
	case 0:
		num_msgs = 1;
		msgs[0].addr = slave_addr;
		msgs[0].flags = I2C_M_RD;
		msgs[0].len = len;
		msgs[0].buf = data;
		break;
	case 2:
		offset_bytes[1] = (offset >> 8) & 0xff;
		fallthrough;
	case 1:
		num_msgs = 2;
		offset_bytes[0] = offset & 0xff;

		msgs[0].addr = slave_addr;
		msgs[0].flags = 0;
		msgs[0].len = offset_size;
		msgs[0].buf = offset_bytes;

		msgs[1].addr = slave_addr;
		msgs[1].flags = I2C_M_RD;
		msgs[1].len = len;
		msgs[1].buf = data;
		break;
	default:
		return -EINVAL;
	}

	bus->controlling_dd = dd;
	ret = i2c_transfer(&bus->adapter, msgs, num_msgs);
	if (ret != num_msgs) {
		dd_dev_err(dd, "%s: bus %d, i2c slave 0x%x, offset 0x%x, len 0x%x; read failed, ret %d\n",
			   __func__, bus->num, slave_addr, offset, len, ret);
		return ret < 0 ? ret : -EIO;
	}
	return 0;
}

/*
 * Raw i2c write.  No set-up or lock checking.
 *
 * Return 0 on success, -errno on error.
 */
static int __i2c_write(struct hfi1_pportdata *ppd, u32 target, int i2c_addr,
		       int offset, void *bp, int len)
{
	struct hfi1_devdata *dd = ppd->dd;
	struct hfi1_i2c_bus *bus;
	u8 slave_addr;
	int offset_size;

	bus = target ? dd->asic_data->i2c_bus1 : dd->asic_data->i2c_bus0;
	slave_addr = (i2c_addr & 0xff) >> 1; /* convert to 7-bit addr */
	offset_size = (i2c_addr >> 8) & 0x3;
	return i2c_bus_write(dd, bus, slave_addr, offset, offset_size, bp, len);
}

/*
 * Caller must hold the i2c chain resource.
 *
 * Return number of bytes written, or -errno.
 */
int i2c_write(struct hfi1_pportdata *ppd, u32 target, int i2c_addr, int offset,
	      void *bp, int len)
{
	int ret;

	if (!check_chip_resource(ppd->dd, i2c_target(target), __func__))
		return -EACCES;

	ret = __i2c_write(ppd, target, i2c_addr, offset, bp, len);
	if (ret)
		return ret;

	return len;
}

/*
 * Raw i2c read.  No set-up or lock checking.
 *
 * Return 0 on success, -errno on error.
 */
static int __i2c_read(struct hfi1_pportdata *ppd, u32 target, int i2c_addr,
		      int offset, void *bp, int len)
{
	struct hfi1_devdata *dd = ppd->dd;
	struct hfi1_i2c_bus *bus;
	u8 slave_addr;
	int offset_size;

	bus = target ? dd->asic_data->i2c_bus1 : dd->asic_data->i2c_bus0;
	slave_addr = (i2c_addr & 0xff) >> 1; /* convert to 7-bit addr */
	offset_size = (i2c_addr >> 8) & 0x3;
	return i2c_bus_read(dd, bus, slave_addr, offset, offset_size, bp, len);
}

/*
 * Caller must hold the i2c chain resource.
 *
 * Return number of bytes read, or -errno.
 */
int i2c_read(struct hfi1_pportdata *ppd, u32 target, int i2c_addr, int offset,
	     void *bp, int len)
{
	int ret;

	if (!check_chip_resource(ppd->dd, i2c_target(target), __func__))
		return -EACCES;

	ret = __i2c_read(ppd, target, i2c_addr, offset, bp, len);
	if (ret)
		return ret;

	return len;
}

/*
 * Write page n, offset m of QSFP memory as defined by SFF 8636
 * by writing @addr = ((256 * n) + m)
 *
 * Caller must hold the i2c chain resource.
 *
 * Return number of bytes written or -errno.
 */
int qsfp_write(struct hfi1_pportdata *ppd, u32 target, int addr, void *bp,
	       int len)
{
	int count = 0;
	int offset;
	int nwrite;
	int ret = 0;
	u8 page;

	if (!check_chip_resource(ppd->dd, i2c_target(target), __func__))
		return -EACCES;

	while (count < len) {
		/*
		 * Set the qsfp page based on a zero-based address
		 * and a page size of QSFP_PAGESIZE bytes.
		 */
		page = (u8)(addr / QSFP_PAGESIZE);

		ret = __i2c_write(ppd, target, QSFP_DEV | QSFP_OFFSET_SIZE,
				  QSFP_PAGE_SELECT_BYTE_OFFS, &page, 1);
		/* QSFPs require a 5-10msec delay after write operations */
		mdelay(5);
		if (ret) {
			hfi1_dev_porterr(ppd->dd, ppd->port,
					 "QSFP chain %d can't write QSFP_PAGE_SELECT_BYTE: %d\n",
					 target, ret);
			break;
		}

		offset = addr % QSFP_PAGESIZE;
		nwrite = len - count;
		/* truncate write to boundary if crossing boundary */
		if (((addr % QSFP_RW_BOUNDARY) + nwrite) > QSFP_RW_BOUNDARY)
			nwrite = QSFP_RW_BOUNDARY - (addr % QSFP_RW_BOUNDARY);

		ret = __i2c_write(ppd, target, QSFP_DEV | QSFP_OFFSET_SIZE,
				  offset, bp + count, nwrite);
		/* QSFPs require a 5-10msec delay after write operations */
		mdelay(5);
		if (ret)	/* stop on error */
			break;

		count += nwrite;
		addr += nwrite;
	}

	if (ret < 0)
		return ret;
	return count;
}

/*
 * Perform a stand-alone single QSFP write.  Acquire the resource, do the
 * write, then release the resource.
 */
int one_qsfp_write(struct hfi1_pportdata *ppd, u32 target, int addr, void *bp,
		   int len)
{
	struct hfi1_devdata *dd = ppd->dd;
	u32 resource = qsfp_resource(dd);
	int ret;

	ret = acquire_chip_resource(dd, resource, QSFP_WAIT);
	if (ret)
		return ret;
	ret = qsfp_write(ppd, target, addr, bp, len);
	release_chip_resource(dd, resource);

	return ret;
}

/*
 * Access page n, offset m of QSFP memory as defined by SFF 8636
 * by reading @addr = ((256 * n) + m)
 *
 * Caller must hold the i2c chain resource.
 *
 * Return the number of bytes read or -errno.
 */
int qsfp_read(struct hfi1_pportdata *ppd, u32 target, int addr, void *bp,
	      int len)
{
	int count = 0;
	int offset;
	int nread;
	int ret = 0;
	u8 page;

	if (!check_chip_resource(ppd->dd, i2c_target(target), __func__))
		return -EACCES;

	while (count < len) {
		/*
		 * Set the qsfp page based on a zero-based address
		 * and a page size of QSFP_PAGESIZE bytes.
		 */
		page = (u8)(addr / QSFP_PAGESIZE);
		ret = __i2c_write(ppd, target, QSFP_DEV | QSFP_OFFSET_SIZE,
				  QSFP_PAGE_SELECT_BYTE_OFFS, &page, 1);
		/* QSFPs require a 5-10msec delay after write operations */
		mdelay(5);
		if (ret) {
			hfi1_dev_porterr(ppd->dd, ppd->port,
					 "QSFP chain %d can't write QSFP_PAGE_SELECT_BYTE: %d\n",
					 target, ret);
			break;
		}

		offset = addr % QSFP_PAGESIZE;
		nread = len - count;
		/* truncate read to boundary if crossing boundary */
		if (((addr % QSFP_RW_BOUNDARY) + nread) > QSFP_RW_BOUNDARY)
			nread = QSFP_RW_BOUNDARY - (addr % QSFP_RW_BOUNDARY);

		ret = __i2c_read(ppd, target, QSFP_DEV | QSFP_OFFSET_SIZE,
				 offset, bp + count, nread);
		if (ret)	/* stop on error */
			break;

		count += nread;
		addr += nread;
	}

	if (ret < 0)
		return ret;
	return count;
}

/*
 * Perform a stand-alone single QSFP read.  Acquire the resource, do the
 * read, then release the resource.
 */
int one_qsfp_read(struct hfi1_pportdata *ppd, u32 target, int addr, void *bp,
		  int len)
{
	struct hfi1_devdata *dd = ppd->dd;
	u32 resource = qsfp_resource(dd);
	int ret;

	ret = acquire_chip_resource(dd, resource, QSFP_WAIT);
	if (ret)
		return ret;
	ret = qsfp_read(ppd, target, addr, bp, len);
	release_chip_resource(dd, resource);

	return ret;
}

/*
 * This function caches the QSFP memory range in 128 byte chunks.
 * As an example, the next byte after address 255 is byte 128 from
 * upper page 01H (if existing) rather than byte 0 from lower page 00H.
 * Access page n, offset m of QSFP memory as defined by SFF 8636
 * in the cache by reading byte ((128 * n) + m)
 * The calls to qsfp_{read,write} in this function correctly handle the
 * address map difference between this mapping and the mapping implemented
 * by those functions
 *
 * The caller must be holding the QSFP i2c chain resource.
 */
int refresh_qsfp_cache(struct hfi1_pportdata *ppd, struct qsfp_data *cp)
{
	u32 target = ppd->dd->hfi1_id;
	int ret;
	unsigned long flags;
	u8 *cache = &cp->cache[0];

	/* ensure sane contents on invalid reads, for cable swaps */
	memset(cache, 0, (QSFP_MAX_NUM_PAGES * 128));
	spin_lock_irqsave(&ppd->qsfp_info.qsfp_lock, flags);
	ppd->qsfp_info.cache_valid = 0;
	spin_unlock_irqrestore(&ppd->qsfp_info.qsfp_lock, flags);

	if (!qsfp_mod_present(ppd)) {
		ret = -ENODEV;
		goto bail;
	}

	ret = qsfp_read(ppd, target, 0, cache, QSFP_PAGESIZE);
	if (ret != QSFP_PAGESIZE) {
		dd_dev_info(ppd->dd,
			    "%s: Page 0 read failed, expected %d, got %d\n",
			    __func__, QSFP_PAGESIZE, ret);
		goto bail;
	}

	/* Is paging enabled? */
	if (!(cache[2] & 4)) {
		/* Paging enabled, page 03 required */
		if ((cache[195] & 0xC0) == 0xC0) {
			/* all */
			ret = qsfp_read(ppd, target, 384, cache + 256, 128);
			if (ret <= 0 || ret != 128) {
				dd_dev_info(ppd->dd, "%s failed\n", __func__);
				goto bail;
			}
			ret = qsfp_read(ppd, target, 640, cache + 384, 128);
			if (ret <= 0 || ret != 128) {
				dd_dev_info(ppd->dd, "%s failed\n", __func__);
				goto bail;
			}
			ret = qsfp_read(ppd, target, 896, cache + 512, 128);
			if (ret <= 0 || ret != 128) {
				dd_dev_info(ppd->dd, "%s failed\n", __func__);
				goto bail;
			}
		} else if ((cache[195] & 0x80) == 0x80) {
			/* only page 2 and 3 */
			ret = qsfp_read(ppd, target, 640, cache + 384, 128);
			if (ret <= 0 || ret != 128) {
				dd_dev_info(ppd->dd, "%s failed\n", __func__);
				goto bail;
			}
			ret = qsfp_read(ppd, target, 896, cache + 512, 128);
			if (ret <= 0 || ret != 128) {
				dd_dev_info(ppd->dd, "%s failed\n", __func__);
				goto bail;
			}
		} else if ((cache[195] & 0x40) == 0x40) {
			/* only page 1 and 3 */
			ret = qsfp_read(ppd, target, 384, cache + 256, 128);
			if (ret <= 0 || ret != 128) {
				dd_dev_info(ppd->dd, "%s failed\n", __func__);
				goto bail;
			}
			ret = qsfp_read(ppd, target, 896, cache + 512, 128);
			if (ret <= 0 || ret != 128) {
				dd_dev_info(ppd->dd, "%s failed\n", __func__);
				goto bail;
			}
		} else {
			/* only page 3 */
			ret = qsfp_read(ppd, target, 896, cache + 512, 128);
			if (ret <= 0 || ret != 128) {
				dd_dev_info(ppd->dd, "%s failed\n", __func__);
				goto bail;
			}
		}
	}

	spin_lock_irqsave(&ppd->qsfp_info.qsfp_lock, flags);
	ppd->qsfp_info.cache_valid = 1;
	ppd->qsfp_info.cache_refresh_required = 0;
	spin_unlock_irqrestore(&ppd->qsfp_info.qsfp_lock, flags);

	return 0;

bail:
	memset(cache, 0, (QSFP_MAX_NUM_PAGES * 128));
	return ret;
}

const char * const hfi1_qsfp_devtech[16] = {
	"850nm VCSEL", "1310nm VCSEL", "1550nm VCSEL", "1310nm FP",
	"1310nm DFB", "1550nm DFB", "1310nm EML", "1550nm EML",
	"Cu Misc", "1490nm DFB", "Cu NoEq", "Cu Eq",
	"Undef", "Cu Active BothEq", "Cu FarEq", "Cu NearEq"
};

#define QSFP_DUMP_CHUNK 16 /* Holds longest string */
#define QSFP_DEFAULT_HDR_CNT 224

#define QSFP_PWR(pbyte) (((pbyte) >> 6) & 3)
#define QSFP_HIGH_PWR(pbyte) ((pbyte) & 3)
/* For use with QSFP_HIGH_PWR macro */
#define QSFP_HIGH_PWR_UNUSED	0 /* Bits [1:0] = 00 implies low power module */

/*
 * Takes power class byte [Page 00 Byte 129] in SFF 8636
 * Returns power class as integer (1 through 7, per SFF 8636 rev 2.4)
 */
int get_qsfp_power_class(u8 power_byte)
{
	if (QSFP_HIGH_PWR(power_byte) == QSFP_HIGH_PWR_UNUSED)
		/* power classes count from 1, their bit encodings from 0 */
		return (QSFP_PWR(power_byte) + 1);
	/*
	 * 00 in the high power classes stands for unused, bringing
	 * balance to the off-by-1 offset above, we add 4 here to
	 * account for the difference between the low and high power
	 * groups
	 */
	return (QSFP_HIGH_PWR(power_byte) + 4);
}

int qsfp_mod_present(struct hfi1_pportdata *ppd)
{
	struct hfi1_devdata *dd = ppd->dd;
	u64 reg;

	reg = read_csr(dd, dd->hfi1_id ? ASIC_QSFP2_IN : ASIC_QSFP1_IN);
	return !(reg & QSFP_HFI0_MODPRST_N);
}

/*
 * This function maps QSFP memory addresses in 128 byte chunks in the following
 * fashion per the CableInfo SMA query definition in the IBA 1.3 spec/OPA Gen 1
 * spec
 * For addr 000-127, lower page 00h
 * For addr 128-255, upper page 00h
 * For addr 256-383, upper page 01h
 * For addr 384-511, upper page 02h
 * For addr 512-639, upper page 03h
 *
 * For addresses beyond this range, it returns the invalid range of data buffer
 * set to 0.
 * For upper pages that are optional, if they are not valid, returns the
 * particular range of bytes in the data buffer set to 0.
 */
int get_cable_info(struct hfi1_devdata *dd, u32 port_num, u32 addr, u32 len,
		   u8 *data)
{
	struct hfi1_pportdata *ppd;
	u32 excess_len = len;
	int ret = 0, offset = 0;

	if (port_num > dd->num_pports || port_num < 1) {
		dd_dev_info(dd, "%s: Invalid port number %d\n",
			    __func__, port_num);
		ret = -EINVAL;
		goto set_zeroes;
	}

	ppd = dd->pport + (port_num - 1);
	if (!qsfp_mod_present(ppd)) {
		ret = -ENODEV;
		goto set_zeroes;
	}

	if (!ppd->qsfp_info.cache_valid) {
		ret = -EINVAL;
		goto set_zeroes;
	}

	if (addr >= (QSFP_MAX_NUM_PAGES * 128)) {
		ret = -ERANGE;
		goto set_zeroes;
	}

	if ((addr + len) > (QSFP_MAX_NUM_PAGES * 128)) {
		excess_len = (addr + len) - (QSFP_MAX_NUM_PAGES * 128);
		memcpy(data, &ppd->qsfp_info.cache[addr], (len - excess_len));
		data += (len - excess_len);
		goto set_zeroes;
	}

	memcpy(data, &ppd->qsfp_info.cache[addr], len);

	if (addr <= QSFP_MONITOR_VAL_END &&
	    (addr + len) >= QSFP_MONITOR_VAL_START) {
		/* Overlap with the dynamic channel monitor range */
		if (addr < QSFP_MONITOR_VAL_START) {
			if (addr + len <= QSFP_MONITOR_VAL_END)
				len = addr + len - QSFP_MONITOR_VAL_START;
			else
				len = QSFP_MONITOR_RANGE;
			offset = QSFP_MONITOR_VAL_START - addr;
			addr = QSFP_MONITOR_VAL_START;
		} else if (addr == QSFP_MONITOR_VAL_START) {
			offset = 0;
			if (addr + len > QSFP_MONITOR_VAL_END)
				len = QSFP_MONITOR_RANGE;
		} else {
			offset = 0;
			if (addr + len > QSFP_MONITOR_VAL_END)
				len = QSFP_MONITOR_VAL_END - addr + 1;
		}
		/* Refresh the values of the dynamic monitors from the cable */
		ret = one_qsfp_read(ppd, dd->hfi1_id, addr, data + offset, len);
		if (ret != len) {
			ret = -EAGAIN;
			goto set_zeroes;
		}
	}

	return 0;

set_zeroes:
	memset(data, 0, excess_len);
	return ret;
}

static const char *pwr_codes[8] = {"N/AW",
				  "1.5W",
				  "2.0W",
				  "2.5W",
				  "3.5W",
				  "4.0W",
				  "4.5W",
				  "5.0W"
				 };

int qsfp_dump(struct hfi1_pportdata *ppd, char *buf, int len)
{
	u8 *cache = &ppd->qsfp_info.cache[0];
	u8 bin_buff[QSFP_DUMP_CHUNK];
	char lenstr[6];
	int sofar;
	int bidx = 0;
	u8 *atten = &cache[QSFP_ATTEN_OFFS];
	u8 *vendor_oui = &cache[QSFP_VOUI_OFFS];
	u8 power_byte = 0;

	sofar = 0;
	lenstr[0] = ' ';
	lenstr[1] = '\0';

	if (ppd->qsfp_info.cache_valid) {
		if (QSFP_IS_CU(cache[QSFP_MOD_TECH_OFFS]))
			snprintf(lenstr, sizeof(lenstr), "%dM ",
				 cache[QSFP_MOD_LEN_OFFS]);

		power_byte = cache[QSFP_MOD_PWR_OFFS];
		sofar += scnprintf(buf + sofar, len - sofar, "PWR:%.3sW\n",
				pwr_codes[get_qsfp_power_class(power_byte)]);

		sofar += scnprintf(buf + sofar, len - sofar, "TECH:%s%s\n",
				lenstr,
			hfi1_qsfp_devtech[(cache[QSFP_MOD_TECH_OFFS]) >> 4]);

		sofar += scnprintf(buf + sofar, len - sofar, "Vendor:%.*s\n",
				   QSFP_VEND_LEN, &cache[QSFP_VEND_OFFS]);

		sofar += scnprintf(buf + sofar, len - sofar, "OUI:%06X\n",
				   QSFP_OUI(vendor_oui));

		sofar += scnprintf(buf + sofar, len - sofar, "Part#:%.*s\n",
				   QSFP_PN_LEN, &cache[QSFP_PN_OFFS]);

		sofar += scnprintf(buf + sofar, len - sofar, "Rev:%.*s\n",
				   QSFP_REV_LEN, &cache[QSFP_REV_OFFS]);

		if (QSFP_IS_CU(cache[QSFP_MOD_TECH_OFFS]))
			sofar += scnprintf(buf + sofar, len - sofar,
				"Atten:%d, %d\n",
				QSFP_ATTEN_SDR(atten),
				QSFP_ATTEN_DDR(atten));

		sofar += scnprintf(buf + sofar, len - sofar, "Serial:%.*s\n",
				   QSFP_SN_LEN, &cache[QSFP_SN_OFFS]);

		sofar += scnprintf(buf + sofar, len - sofar, "Date:%.*s\n",
				   QSFP_DATE_LEN, &cache[QSFP_DATE_OFFS]);

		sofar += scnprintf(buf + sofar, len - sofar, "Lot:%.*s\n",
				   QSFP_LOT_LEN, &cache[QSFP_LOT_OFFS]);

		while (bidx < QSFP_DEFAULT_HDR_CNT) {
			int iidx;

			memcpy(bin_buff, &cache[bidx], QSFP_DUMP_CHUNK);
			for (iidx = 0; iidx < QSFP_DUMP_CHUNK; ++iidx) {
				sofar += scnprintf(buf + sofar, len - sofar,
					" %02X", bin_buff[iidx]);
			}
			sofar += scnprintf(buf + sofar, len - sofar, "\n");
			bidx += QSFP_DUMP_CHUNK;
		}
	}
	return sofar;
}
_domain(adev, domain); if (bo->pin_count) { uint32_t mem_type = bo->tbo.mem.mem_type; if (!(domain & amdgpu_mem_type_to_domain(mem_type))) return -EINVAL; bo->pin_count++; if (max_offset != 0) { u64 domain_start = bo->tbo.bdev->man[mem_type].gpu_offset; WARN_ON_ONCE(max_offset < (amdgpu_bo_gpu_offset(bo) - domain_start)); } return 0; } bo->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS; /* force to pin into visible video ram */ if (!(bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS)) bo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; amdgpu_bo_placement_from_domain(bo, domain); for (i = 0; i < bo->placement.num_placement; i++) { unsigned fpfn, lpfn; fpfn = min_offset >> PAGE_SHIFT; lpfn = max_offset >> PAGE_SHIFT; if (fpfn > bo->placements[i].fpfn) bo->placements[i].fpfn = fpfn; if (!bo->placements[i].lpfn || (lpfn && lpfn < bo->placements[i].lpfn)) bo->placements[i].lpfn = lpfn; bo->placements[i].flags |= TTM_PL_FLAG_NO_EVICT; } r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx); if (unlikely(r)) { dev_err(adev->dev, "%p pin failed\n", bo); goto error; } bo->pin_count = 1; domain = amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type); if (domain == AMDGPU_GEM_DOMAIN_VRAM) { atomic64_add(amdgpu_bo_size(bo), &adev->vram_pin_size); atomic64_add(amdgpu_vram_mgr_bo_visible_size(bo), &adev->visible_pin_size); } else if (domain == AMDGPU_GEM_DOMAIN_GTT) { atomic64_add(amdgpu_bo_size(bo), &adev->gart_pin_size); } error: return r; } /** * amdgpu_bo_pin - pin an &amdgpu_bo buffer object * @bo: &amdgpu_bo buffer object to be pinned * @domain: domain to be pinned to * * A simple wrapper to amdgpu_bo_pin_restricted(). * Provides a simpler API for buffers that do not have any strict restrictions * on where a buffer must be located. * * Returns: * 0 for success or a negative error code on failure. */ int amdgpu_bo_pin(struct amdgpu_bo *bo, u32 domain) { return amdgpu_bo_pin_restricted(bo, domain, 0, 0); } /** * amdgpu_bo_unpin - unpin an &amdgpu_bo buffer object * @bo: &amdgpu_bo buffer object to be unpinned * * Decreases the pin_count, and clears the flags if pin_count reaches 0. * Changes placement and pin size accordingly. * * Returns: * 0 for success or a negative error code on failure. */ int amdgpu_bo_unpin(struct amdgpu_bo *bo) { struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); struct ttm_operation_ctx ctx = { false, false }; int r, i; if (WARN_ON_ONCE(!bo->pin_count)) { dev_warn(adev->dev, "%p unpin not necessary\n", bo); return 0; } bo->pin_count--; if (bo->pin_count) return 0; amdgpu_bo_subtract_pin_size(bo); for (i = 0; i < bo->placement.num_placement; i++) { bo->placements[i].lpfn = 0; bo->placements[i].flags &= ~TTM_PL_FLAG_NO_EVICT; } r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx); if (unlikely(r)) dev_err(adev->dev, "%p validate failed for unpin\n", bo); return r; } /** * amdgpu_bo_evict_vram - evict VRAM buffers * @adev: amdgpu device object * * Evicts all VRAM buffers on the lru list of the memory type. * Mainly used for evicting vram at suspend time. * * Returns: * 0 for success or a negative error code on failure. */ int amdgpu_bo_evict_vram(struct amdgpu_device *adev) { /* late 2.6.33 fix IGP hibernate - we need pm ops to do this correct */ #ifndef CONFIG_HIBERNATION if (adev->flags & AMD_IS_APU) { /* Useless to evict on IGP chips */ return 0; } #endif return ttm_bo_evict_mm(&adev->mman.bdev, TTM_PL_VRAM); } static const char *amdgpu_vram_names[] = { "UNKNOWN", "GDDR1", "DDR2", "GDDR3", "GDDR4", "GDDR5", "HBM", "DDR3", "DDR4", "GDDR6", }; /** * amdgpu_bo_init - initialize memory manager * @adev: amdgpu device object * * Calls amdgpu_ttm_init() to initialize amdgpu memory manager. * * Returns: * 0 for success or a negative error code on failure. */ int amdgpu_bo_init(struct amdgpu_device *adev) { /* reserve PAT memory space to WC for VRAM */ arch_io_reserve_memtype_wc(adev->gmc.aper_base, adev->gmc.aper_size); /* Add an MTRR for the VRAM */ adev->gmc.vram_mtrr = arch_phys_wc_add(adev->gmc.aper_base, adev->gmc.aper_size); DRM_INFO("Detected VRAM RAM=%lluM, BAR=%lluM\n", adev->gmc.mc_vram_size >> 20, (unsigned long long)adev->gmc.aper_size >> 20); DRM_INFO("RAM width %dbits %s\n", adev->gmc.vram_width, amdgpu_vram_names[adev->gmc.vram_type]); return amdgpu_ttm_init(adev); } /** * amdgpu_bo_late_init - late init * @adev: amdgpu device object * * Calls amdgpu_ttm_late_init() to free resources used earlier during * initialization. * * Returns: * 0 for success or a negative error code on failure. */ int amdgpu_bo_late_init(struct amdgpu_device *adev) { amdgpu_ttm_late_init(adev); return 0; } /** * amdgpu_bo_fini - tear down memory manager * @adev: amdgpu device object * * Reverses amdgpu_bo_init() to tear down memory manager. */ void amdgpu_bo_fini(struct amdgpu_device *adev) { amdgpu_ttm_fini(adev); arch_phys_wc_del(adev->gmc.vram_mtrr); arch_io_free_memtype_wc(adev->gmc.aper_base, adev->gmc.aper_size); } /** * amdgpu_bo_fbdev_mmap - mmap fbdev memory * @bo: &amdgpu_bo buffer object * @vma: vma as input from the fbdev mmap method * * Calls ttm_fbdev_mmap() to mmap fbdev memory if it is backed by a bo. * * Returns: * 0 for success or a negative error code on failure. */ int amdgpu_bo_fbdev_mmap(struct amdgpu_bo *bo, struct vm_area_struct *vma) { return ttm_fbdev_mmap(vma, &bo->tbo); } /** * amdgpu_bo_set_tiling_flags - set tiling flags * @bo: &amdgpu_bo buffer object * @tiling_flags: new flags * * Sets buffer object's tiling flags with the new one. Used by GEM ioctl or * kernel driver to set the tiling flags on a buffer. * * Returns: * 0 for success or a negative error code on failure. */ int amdgpu_bo_set_tiling_flags(struct amdgpu_bo *bo, u64 tiling_flags) { struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); if (adev->family <= AMDGPU_FAMILY_CZ && AMDGPU_TILING_GET(tiling_flags, TILE_SPLIT) > 6) return -EINVAL; bo->tiling_flags = tiling_flags; return 0; } /** * amdgpu_bo_get_tiling_flags - get tiling flags * @bo: &amdgpu_bo buffer object * @tiling_flags: returned flags * * Gets buffer object's tiling flags. Used by GEM ioctl or kernel driver to * set the tiling flags on a buffer. */ void amdgpu_bo_get_tiling_flags(struct amdgpu_bo *bo, u64 *tiling_flags) { dma_resv_assert_held(bo->tbo.base.resv); if (tiling_flags) *tiling_flags = bo->tiling_flags; } /** * amdgpu_bo_set_metadata - set metadata * @bo: &amdgpu_bo buffer object * @metadata: new metadata * @metadata_size: size of the new metadata * @flags: flags of the new metadata * * Sets buffer object's metadata, its size and flags. * Used via GEM ioctl. * * Returns: * 0 for success or a negative error code on failure. */ int amdgpu_bo_set_metadata (struct amdgpu_bo *bo, void *metadata, uint32_t metadata_size, uint64_t flags) { void *buffer; if (!metadata_size) { if (bo->metadata_size) { kfree(bo->metadata); bo->metadata = NULL; bo->metadata_size = 0; } return 0; } if (metadata == NULL) return -EINVAL; buffer = kmemdup(metadata, metadata_size, GFP_KERNEL); if (buffer == NULL) return -ENOMEM; kfree(bo->metadata); bo->metadata_flags = flags; bo->metadata = buffer; bo->metadata_size = metadata_size; return 0; } /** * amdgpu_bo_get_metadata - get metadata * @bo: &amdgpu_bo buffer object * @buffer: returned metadata * @buffer_size: size of the buffer * @metadata_size: size of the returned metadata * @flags: flags of the returned metadata * * Gets buffer object's metadata, its size and flags. buffer_size shall not be * less than metadata_size. * Used via GEM ioctl. * * Returns: * 0 for success or a negative error code on failure. */ int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer, size_t buffer_size, uint32_t *metadata_size, uint64_t *flags) { if (!buffer && !metadata_size) return -EINVAL; if (buffer) { if (buffer_size < bo->metadata_size) return -EINVAL; if (bo->metadata_size) memcpy(buffer, bo->metadata, bo->metadata_size); } if (metadata_size) *metadata_size = bo->metadata_size; if (flags) *flags = bo->metadata_flags; return 0; } /** * amdgpu_bo_move_notify - notification about a memory move * @bo: pointer to a buffer object * @evict: if this move is evicting the buffer from the graphics address space * @new_mem: new information of the bufer object * * Marks the corresponding &amdgpu_bo buffer object as invalid, also performs * bookkeeping. * TTM driver callback which is called when ttm moves a buffer. */ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo, bool evict, struct ttm_mem_reg *new_mem) { struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev); struct amdgpu_bo *abo; struct ttm_mem_reg *old_mem = &bo->mem; if (!amdgpu_bo_is_amdgpu_bo(bo)) return; abo = ttm_to_amdgpu_bo(bo); amdgpu_vm_bo_invalidate(adev, abo, evict); amdgpu_bo_kunmap(abo); /* remember the eviction */ if (evict) atomic64_inc(&adev->num_evictions); /* update statistics */ if (!new_mem) return; /* move_notify is called before move happens */ trace_amdgpu_bo_move(abo, new_mem->mem_type, old_mem->mem_type); } /** * amdgpu_bo_move_notify - notification about a BO being released * @bo: pointer to a buffer object * * Wipes VRAM buffers whose contents should not be leaked before the * memory is released. */ void amdgpu_bo_release_notify(struct ttm_buffer_object *bo) { struct dma_fence *fence = NULL; struct amdgpu_bo *abo; int r; if (!amdgpu_bo_is_amdgpu_bo(bo)) return; abo = ttm_to_amdgpu_bo(bo); if (abo->kfd_bo) amdgpu_amdkfd_unreserve_memory_limit(abo); if (bo->mem.mem_type != TTM_PL_VRAM || !bo->mem.mm_node || !(abo->flags & AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE)) return; dma_resv_lock(bo->base.resv, NULL); r = amdgpu_fill_buffer(abo, AMDGPU_POISON, bo->base.resv, &fence); if (!WARN_ON(r)) { amdgpu_bo_fence(abo, fence, false); dma_fence_put(fence); } dma_resv_unlock(bo->base.resv); } /** * amdgpu_bo_fault_reserve_notify - notification about a memory fault * @bo: pointer to a buffer object * * Notifies the driver we are taking a fault on this BO and have reserved it, * also performs bookkeeping. * TTM driver callback for dealing with vm faults. * * Returns: * 0 for success or a negative error code on failure. */ int amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo) { struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev); struct ttm_operation_ctx ctx = { false, false }; struct amdgpu_bo *abo; unsigned long offset, size; int r; if (!amdgpu_bo_is_amdgpu_bo(bo)) return 0; abo = ttm_to_amdgpu_bo(bo); /* Remember that this BO was accessed by the CPU */ abo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED; if (bo->mem.mem_type != TTM_PL_VRAM) return 0; size = bo->mem.num_pages << PAGE_SHIFT; offset = bo->mem.start << PAGE_SHIFT; if ((offset + size) <= adev->gmc.visible_vram_size) return 0; /* Can't move a pinned BO to visible VRAM */ if (abo->pin_count > 0) return -EINVAL; /* hurrah the memory is not visible ! */ atomic64_inc(&adev->num_vram_cpu_page_faults); amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT); /* Avoid costly evictions; only set GTT as a busy placement */ abo->placement.num_busy_placement = 1; abo->placement.busy_placement = &abo->placements[1]; r = ttm_bo_validate(bo, &abo->placement, &ctx); if (unlikely(r != 0)) return r; offset = bo->mem.start << PAGE_SHIFT; /* this should never happen */ if (bo->mem.mem_type == TTM_PL_VRAM && (offset + size) > adev->gmc.visible_vram_size) return -EINVAL; return 0; } /** * amdgpu_bo_fence - add fence to buffer object * * @bo: buffer object in question * @fence: fence to add * @shared: true if fence should be added shared * */ void amdgpu_bo_fence(struct amdgpu_bo *bo, struct dma_fence *fence, bool shared) { struct dma_resv *resv = bo->tbo.base.resv; if (shared) dma_resv_add_shared_fence(resv, fence); else dma_resv_add_excl_fence(resv, fence); } /** * amdgpu_sync_wait_resv - Wait for BO reservation fences * * @bo: buffer object * @owner: fence owner * @intr: Whether the wait is interruptible * * Returns: * 0 on success, errno otherwise. */ int amdgpu_bo_sync_wait(struct amdgpu_bo *bo, void *owner, bool intr) { struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); struct amdgpu_sync sync; int r; amdgpu_sync_create(&sync); amdgpu_sync_resv(adev, &sync, bo->tbo.base.resv, owner, false); r = amdgpu_sync_wait(&sync, intr); amdgpu_sync_free(&sync); return r; } /** * amdgpu_bo_gpu_offset - return GPU offset of bo * @bo: amdgpu object for which we query the offset * * Note: object should either be pinned or reserved when calling this * function, it might be useful to add check for this for debugging. * * Returns: * current GPU offset of the object. */ u64 amdgpu_bo_gpu_offset(struct amdgpu_bo *bo) { WARN_ON_ONCE(bo->tbo.mem.mem_type == TTM_PL_SYSTEM); WARN_ON_ONCE(!dma_resv_is_locked(bo->tbo.base.resv) && !bo->pin_count && bo->tbo.type != ttm_bo_type_kernel); WARN_ON_ONCE(bo->tbo.mem.start == AMDGPU_BO_INVALID_OFFSET); WARN_ON_ONCE(bo->tbo.mem.mem_type == TTM_PL_VRAM && !(bo->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)); return amdgpu_gmc_sign_extend(bo->tbo.offset); } /** * amdgpu_bo_get_preferred_pin_domain - get preferred domain for scanout * @adev: amdgpu device object * @domain: allowed :ref:`memory domains <amdgpu_memory_domains>` * * Returns: * Which of the allowed domains is preferred for pinning the BO for scanout. */ uint32_t amdgpu_bo_get_preferred_pin_domain(struct amdgpu_device *adev, uint32_t domain) { if (domain == (AMDGPU_GEM_DOMAIN_VRAM | AMDGPU_GEM_DOMAIN_GTT)) { domain = AMDGPU_GEM_DOMAIN_VRAM; if (adev->gmc.real_vram_size <= AMDGPU_SG_THRESHOLD) domain = AMDGPU_GEM_DOMAIN_GTT; } return domain; }