summaryrefslogtreecommitdiff
path: root/drivers/infiniband/hw/hns/hns_roce_mr.c
blob: 59f5e2be046b326c7a3f0a8a2355f2ac33df4ab5 (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
/*
 * Copyright (c) 2016 Hisilicon Limited.
 * Copyright (c) 2007, 2008 Mellanox Technologies. All rights reserved.
 *
 * This software is available to you under a choice of one of two
 * licenses.  You may choose to be licensed under the terms of the GNU
 * General Public License (GPL) Version 2, available from the file
 * COPYING in the main directory of this source tree, or the
 * OpenIB.org BSD license below:
 *
 *     Redistribution and use in source and binary forms, with or
 *     without modification, are permitted provided that the following
 *     conditions are met:
 *
 *      - Redistributions of source code must retain the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer.
 *
 *      - Redistributions in binary form must reproduce the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer in the documentation and/or other materials
 *        provided with the distribution.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 */

#include <linux/platform_device.h>
#include <rdma/ib_umem.h>
#include "hns_roce_device.h"
#include "hns_roce_cmd.h"
#include "hns_roce_hem.h"

static u32 hw_index_to_key(unsigned long ind)
{
	return (u32)(ind >> 24) | (ind << 8);
}

static unsigned long key_to_hw_index(u32 key)
{
	return (key << 24) | (key >> 8);
}

static int hns_roce_sw2hw_mpt(struct hns_roce_dev *hr_dev,
			      struct hns_roce_cmd_mailbox *mailbox,
			      unsigned long mpt_index)
{
	return hns_roce_cmd_mbox(hr_dev, mailbox->dma, 0, mpt_index, 0,
				 HNS_ROCE_CMD_SW2HW_MPT,
				 HNS_ROCE_CMD_TIME_CLASS_B);
}

static int hns_roce_hw2sw_mpt(struct hns_roce_dev *hr_dev,
			      struct hns_roce_cmd_mailbox *mailbox,
			      unsigned long mpt_index)
{
	return hns_roce_cmd_mbox(hr_dev, 0, mailbox ? mailbox->dma : 0,
				 mpt_index, !mailbox, HNS_ROCE_CMD_HW2SW_MPT,
				 HNS_ROCE_CMD_TIME_CLASS_B);
}

static int hns_roce_buddy_alloc(struct hns_roce_buddy *buddy, int order,
				unsigned long *seg)
{
	int o;
	u32 m;

	spin_lock(&buddy->lock);

	for (o = order; o <= buddy->max_order; ++o) {
		if (buddy->num_free[o]) {
			m = 1 << (buddy->max_order - o);
			*seg = find_first_bit(buddy->bits[o], m);
			if (*seg < m)
				goto found;
		}
	}
	spin_unlock(&buddy->lock);
	return -1;

 found:
	clear_bit(*seg, buddy->bits[o]);
	--buddy->num_free[o];

	while (o > order) {
		--o;
		*seg <<= 1;
		set_bit(*seg ^ 1, buddy->bits[o]);
		++buddy->num_free[o];
	}

	spin_unlock(&buddy->lock);

	*seg <<= order;
	return 0;
}

static void hns_roce_buddy_free(struct hns_roce_buddy *buddy, unsigned long seg,
				int order)
{
	seg >>= order;

	spin_lock(&buddy->lock);

	while (test_bit(seg ^ 1, buddy->bits[order])) {
		clear_bit(seg ^ 1, buddy->bits[order]);
		--buddy->num_free[order];
		seg >>= 1;
		++order;
	}

	set_bit(seg, buddy->bits[order]);
	++buddy->num_free[order];

	spin_unlock(&buddy->lock);
}

static int hns_roce_buddy_init(struct hns_roce_buddy *buddy, int max_order)
{
	int i, s;

	buddy->max_order = max_order;
	spin_lock_init(&buddy->lock);

	buddy->bits = kzalloc((buddy->max_order + 1) * sizeof(long *),
			       GFP_KERNEL);
	buddy->num_free = kzalloc((buddy->max_order + 1) * sizeof(int *),
				   GFP_KERNEL);
	if (!buddy->bits || !buddy->num_free)
		goto err_out;

	for (i = 0; i <= buddy->max_order; ++i) {
		s = BITS_TO_LONGS(1 << (buddy->max_order - i));
		buddy->bits[i] = kmalloc_array(s, sizeof(long), GFP_KERNEL);
		if (!buddy->bits[i])
			goto err_out_free;

		bitmap_zero(buddy->bits[i], 1 << (buddy->max_order - i));
	}

	set_bit(0, buddy->bits[buddy->max_order]);
	buddy->num_free[buddy->max_order] = 1;

	return 0;

err_out_free:
	for (i = 0; i <= buddy->max_order; ++i)
		kfree(buddy->bits[i]);

err_out:
	kfree(buddy->bits);
	kfree(buddy->num_free);
	return -ENOMEM;
}

static void hns_roce_buddy_cleanup(struct hns_roce_buddy *buddy)
{
	int i;

	for (i = 0; i <= buddy->max_order; ++i)
		kfree(buddy->bits[i]);

	kfree(buddy->bits);
	kfree(buddy->num_free);
}

static int hns_roce_alloc_mtt_range(struct hns_roce_dev *hr_dev, int order,
				    unsigned long *seg)
{
	struct hns_roce_mr_table *mr_table = &hr_dev->mr_table;
	int ret = 0;

	ret = hns_roce_buddy_alloc(&mr_table->mtt_buddy, order, seg);
	if (ret == -1)
		return -1;

	if (hns_roce_table_get_range(hr_dev, &mr_table->mtt_table, *seg,
				     *seg + (1 << order) - 1)) {
		hns_roce_buddy_free(&mr_table->mtt_buddy, *seg, order);
		return -1;
	}

	return 0;
}

int hns_roce_mtt_init(struct hns_roce_dev *hr_dev, int npages, int page_shift,
		      struct hns_roce_mtt *mtt)
{
	int ret = 0;
	int i;

	/* Page num is zero, correspond to DMA memory register */
	if (!npages) {
		mtt->order = -1;
		mtt->page_shift = HNS_ROCE_HEM_PAGE_SHIFT;
		return 0;
	}

	/* Note: if page_shift is zero, FAST memory regsiter */
	mtt->page_shift = page_shift;

	/* Compute MTT entry necessary */
	for (mtt->order = 0, i = HNS_ROCE_MTT_ENTRY_PER_SEG; i < npages;
	     i <<= 1)
		++mtt->order;

	/* Allocate MTT entry */
	ret = hns_roce_alloc_mtt_range(hr_dev, mtt->order, &mtt->first_seg);
	if (ret == -1)
		return -ENOMEM;

	return 0;
}

void hns_roce_mtt_cleanup(struct hns_roce_dev *hr_dev, struct hns_roce_mtt *mtt)
{
	struct hns_roce_mr_table *mr_table = &hr_dev->mr_table;

	if (mtt->order < 0)
		return;

	hns_roce_buddy_free(&mr_table->mtt_buddy, mtt->first_seg, mtt->order);
	hns_roce_table_put_range(hr_dev, &mr_table->mtt_table, mtt->first_seg,
				 mtt->first_seg + (1 << mtt->order) - 1);
}

static int hns_roce_mr_alloc(struct hns_roce_dev *hr_dev, u32 pd, u64 iova,
			     u64 size, u32 access, int npages,
			     struct hns_roce_mr *mr)
{
	unsigned long index = 0;
	int ret = 0;
	struct device *dev = &hr_dev->pdev->dev;

	/* Allocate a key for mr from mr_table */
	ret = hns_roce_bitmap_alloc(&hr_dev->mr_table.mtpt_bitmap, &index);
	if (ret == -1)
		return -ENOMEM;

	mr->iova = iova;			/* MR va starting addr */
	mr->size = size;			/* MR addr range */
	mr->pd = pd;				/* MR num */
	mr->access = access;			/* MR access permit */
	mr->enabled = 0;			/* MR active status */
	mr->key = hw_index_to_key(index);	/* MR key */

	if (size == ~0ull) {
		mr->type = MR_TYPE_DMA;
		mr->pbl_buf = NULL;
		mr->pbl_dma_addr = 0;
	} else {
		mr->type = MR_TYPE_MR;
		mr->pbl_buf = dma_alloc_coherent(dev, npages * 8,
						 &(mr->pbl_dma_addr),
						 GFP_KERNEL);
		if (!mr->pbl_buf)
			return -ENOMEM;
	}

	return 0;
}

static void hns_roce_mr_free(struct hns_roce_dev *hr_dev,
			     struct hns_roce_mr *mr)
{
	struct device *dev = &hr_dev->pdev->dev;
	int npages = 0;
	int ret;

	if (mr->enabled) {
		ret = hns_roce_hw2sw_mpt(hr_dev, NULL, key_to_hw_index(mr->key)
					 & (hr_dev->caps.num_mtpts - 1));
		if (ret)
			dev_warn(dev, "HW2SW_MPT failed (%d)\n", ret);
	}

	if (mr->size != ~0ULL) {
		npages = ib_umem_page_count(mr->umem);
		dma_free_coherent(dev, (unsigned int)(npages * 8), mr->pbl_buf,
				  mr->pbl_dma_addr);
	}

	hns_roce_bitmap_free(&hr_dev->mr_table.mtpt_bitmap,
			     key_to_hw_index(mr->key));
}

static int hns_roce_mr_enable(struct hns_roce_dev *hr_dev,
			      struct hns_roce_mr *mr)
{
	int ret;
	unsigned long mtpt_idx = key_to_hw_index(mr->key);
	struct device *dev = &hr_dev->pdev->dev;
	struct hns_roce_cmd_mailbox *mailbox;
	struct hns_roce_mr_table *mr_table = &hr_dev->mr_table;

	/* Prepare HEM entry memory */
	ret = hns_roce_table_get(hr_dev, &mr_table->mtpt_table, mtpt_idx);
	if (ret)
		return ret;

	/* Allocate mailbox memory */
	mailbox = hns_roce_alloc_cmd_mailbox(hr_dev);
	if (IS_ERR(mailbox)) {
		ret = PTR_ERR(mailbox);
		goto err_table;
	}

	ret = hr_dev->hw->write_mtpt(mailbox->buf, mr, mtpt_idx);
	if (ret) {
		dev_err(dev, "Write mtpt fail!\n");
		goto err_page;
	}

	ret = hns_roce_sw2hw_mpt(hr_dev, mailbox,
				 mtpt_idx & (hr_dev->caps.num_mtpts - 1));
	if (ret) {
		dev_err(dev, "SW2HW_MPT failed (%d)\n", ret);
		goto err_page;
	}

	mr->enabled = 1;
	hns_roce_free_cmd_mailbox(hr_dev, mailbox);

	return 0;

err_page:
	hns_roce_free_cmd_mailbox(hr_dev, mailbox);

err_table:
	hns_roce_table_put(hr_dev, &mr_table->mtpt_table, mtpt_idx);
	return ret;
}

static int hns_roce_write_mtt_chunk(struct hns_roce_dev *hr_dev,
				    struct hns_roce_mtt *mtt, u32 start_index,
				    u32 npages, u64 *page_list)
{
	u32 i = 0;
	__le64 *mtts = NULL;
	dma_addr_t dma_handle;
	u32 s = start_index * sizeof(u64);

	/* All MTTs must fit in the same page */
	if (start_index / (PAGE_SIZE / sizeof(u64)) !=
		(start_index + npages - 1) / (PAGE_SIZE / sizeof(u64)))
		return -EINVAL;

	if (start_index & (HNS_ROCE_MTT_ENTRY_PER_SEG - 1))
		return -EINVAL;

	mtts = hns_roce_table_find(&hr_dev->mr_table.mtt_table,
				mtt->first_seg + s / hr_dev->caps.mtt_entry_sz,
				&dma_handle);
	if (!mtts)
		return -ENOMEM;

	/* Save page addr, low 12 bits : 0 */
	for (i = 0; i < npages; ++i)
		mtts[i] = (cpu_to_le64(page_list[i])) >> PAGE_ADDR_SHIFT;

	return 0;
}

static int hns_roce_write_mtt(struct hns_roce_dev *hr_dev,
			      struct hns_roce_mtt *mtt, u32 start_index,
			      u32 npages, u64 *page_list)
{
	int chunk;
	int ret;

	if (mtt->order < 0)
		return -EINVAL;

	while (npages > 0) {
		chunk = min_t(int, PAGE_SIZE / sizeof(u64), npages);

		ret = hns_roce_write_mtt_chunk(hr_dev, mtt, start_index, chunk,
					       page_list);
		if (ret)
			return ret;

		npages -= chunk;
		start_index += chunk;
		page_list += chunk;
	}

	return 0;
}

int hns_roce_buf_write_mtt(struct hns_roce_dev *hr_dev,
			   struct hns_roce_mtt *mtt, struct hns_roce_buf *buf)
{
	u32 i = 0;
	int ret = 0;
	u64 *page_list = NULL;

	page_list = kmalloc_array(buf->npages, sizeof(*page_list), GFP_KERNEL);
	if (!page_list)
		return -ENOMEM;

	for (i = 0; i < buf->npages; ++i) {
		if (buf->nbufs == 1)
			page_list[i] = buf->direct.map + (i << buf->page_shift);
		else
			page_list[i] = buf->page_list[i].map;

	}
	ret = hns_roce_write_mtt(hr_dev, mtt, 0, buf->npages, page_list);

	kfree(page_list);

	return ret;
}

int hns_roce_init_mr_table(struct hns_roce_dev *hr_dev)
{
	struct hns_roce_mr_table *mr_table = &hr_dev->mr_table;
	int ret = 0;

	ret = hns_roce_bitmap_init(&mr_table->mtpt_bitmap,
				   hr_dev->caps.num_mtpts,
				   hr_dev->caps.num_mtpts - 1,
				   hr_dev->caps.reserved_mrws, 0);
	if (ret)
		return ret;

	ret = hns_roce_buddy_init(&mr_table->mtt_buddy,
				  ilog2(hr_dev->caps.num_mtt_segs));
	if (ret)
		goto err_buddy;

	return 0;

err_buddy:
	hns_roce_bitmap_cleanup(&mr_table->mtpt_bitmap);
	return ret;
}

void hns_roce_cleanup_mr_table(struct hns_roce_dev *hr_dev)
{
	struct hns_roce_mr_table *mr_table = &hr_dev->mr_table;

	hns_roce_buddy_cleanup(&mr_table->mtt_buddy);
	hns_roce_bitmap_cleanup(&mr_table->mtpt_bitmap);
}

struct ib_mr *hns_roce_get_dma_mr(struct ib_pd *pd, int acc)
{
	int ret = 0;
	struct hns_roce_mr *mr = NULL;

	mr = kmalloc(sizeof(*mr), GFP_KERNEL);
	if (mr == NULL)
		return  ERR_PTR(-ENOMEM);

	/* Allocate memory region key */
	ret = hns_roce_mr_alloc(to_hr_dev(pd->device), to_hr_pd(pd)->pdn, 0,
				~0ULL, acc, 0, mr);
	if (ret)
		goto err_free;

	ret = hns_roce_mr_enable(to_hr_dev(pd->device), mr);
	if (ret)
		goto err_mr;

	mr->ibmr.rkey = mr->ibmr.lkey = mr->key;
	mr->umem = NULL;

	return &mr->ibmr;

err_mr:
	hns_roce_mr_free(to_hr_dev(pd->device), mr);

err_free:
	kfree(mr);
	return ERR_PTR(ret);
}

int hns_roce_ib_umem_write_mtt(struct hns_roce_dev *hr_dev,
			       struct hns_roce_mtt *mtt, struct ib_umem *umem)
{
	struct scatterlist *sg;
	int i, k, entry;
	int ret = 0;
	u64 *pages;
	u32 n;
	int len;

	pages = (u64 *) __get_free_page(GFP_KERNEL);
	if (!pages)
		return -ENOMEM;

	i = n = 0;

	for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) {
		len = sg_dma_len(sg) >> mtt->page_shift;
		for (k = 0; k < len; ++k) {
			pages[i++] = sg_dma_address(sg) + umem->page_size * k;
			if (i == PAGE_SIZE / sizeof(u64)) {
				ret = hns_roce_write_mtt(hr_dev, mtt, n, i,
							 pages);
				if (ret)
					goto out;
				n += i;
				i = 0;
			}
		}
	}

	if (i)
		ret = hns_roce_write_mtt(hr_dev, mtt, n, i, pages);

out:
	free_page((unsigned long) pages);
	return ret;
}

static int hns_roce_ib_umem_write_mr(struct hns_roce_mr *mr,
				     struct ib_umem *umem)
{
	int i = 0;
	int entry;
	struct scatterlist *sg;

	for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) {
		mr->pbl_buf[i] = ((u64)sg_dma_address(sg)) >> 12;
		i++;
	}

	/* Memory barrier */
	mb();

	return 0;
}

struct ib_mr *hns_roce_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
				   u64 virt_addr, int access_flags,
				   struct ib_udata *udata)
{
	struct hns_roce_dev *hr_dev = to_hr_dev(pd->device);
	struct device *dev = &hr_dev->pdev->dev;
	struct hns_roce_mr *mr = NULL;
	int ret = 0;
	int n = 0;

	mr = kmalloc(sizeof(*mr), GFP_KERNEL);
	if (!mr)
		return ERR_PTR(-ENOMEM);

	mr->umem = ib_umem_get(pd->uobject->context, start, length,
			       access_flags, 0);
	if (IS_ERR(mr->umem)) {
		ret = PTR_ERR(mr->umem);
		goto err_free;
	}

	n = ib_umem_page_count(mr->umem);
	if (mr->umem->page_size != HNS_ROCE_HEM_PAGE_SIZE) {
		dev_err(dev, "Just support 4K page size but is 0x%x now!\n",
			mr->umem->page_size);
	}

	if (n > HNS_ROCE_MAX_MTPT_PBL_NUM) {
		dev_err(dev, " MR len %lld err. MR is limited to 4G at most!\n",
			length);
		goto err_umem;
	}

	ret = hns_roce_mr_alloc(hr_dev, to_hr_pd(pd)->pdn, virt_addr, length,
				access_flags, n, mr);
	if (ret)
		goto err_umem;

	ret = hns_roce_ib_umem_write_mr(mr, mr->umem);
	if (ret)
		goto err_mr;

	ret = hns_roce_mr_enable(hr_dev, mr);
	if (ret)
		goto err_mr;

	mr->ibmr.rkey = mr->ibmr.lkey = mr->key;

	return &mr->ibmr;

err_mr:
	hns_roce_mr_free(hr_dev, mr);

err_umem:
	ib_umem_release(mr->umem);

err_free:
	kfree(mr);
	return ERR_PTR(ret);
}

int hns_roce_dereg_mr(struct ib_mr *ibmr)
{
	struct hns_roce_mr *mr = to_hr_mr(ibmr);

	hns_roce_mr_free(to_hr_dev(ibmr->device), mr);
	if (mr->umem)
		ib_umem_release(mr->umem);

	kfree(mr);

	return 0;
}