summaryrefslogtreecommitdiffstats
path: root/drivers/infiniband/hw/mlx4/mr.c
blob: 4d1e1c632603a7b81e6685cd5ad6020f98a02a47 (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
/*
 * Copyright (c) 2007 Cisco Systems, Inc. All rights reserved.
 * 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/slab.h>

#include "mlx4_ib.h"

static u32 convert_access(int acc)
{
	return (acc & IB_ACCESS_REMOTE_ATOMIC ? MLX4_PERM_ATOMIC       : 0) |
	       (acc & IB_ACCESS_REMOTE_WRITE  ? MLX4_PERM_REMOTE_WRITE : 0) |
	       (acc & IB_ACCESS_REMOTE_READ   ? MLX4_PERM_REMOTE_READ  : 0) |
	       (acc & IB_ACCESS_LOCAL_WRITE   ? MLX4_PERM_LOCAL_WRITE  : 0) |
	       (acc & IB_ACCESS_MW_BIND	      ? MLX4_PERM_BIND_MW      : 0) |
	       MLX4_PERM_LOCAL_READ;
}

static enum mlx4_mw_type to_mlx4_type(enum ib_mw_type type)
{
	switch (type) {
	case IB_MW_TYPE_1:	return MLX4_MW_TYPE_1;
	case IB_MW_TYPE_2:	return MLX4_MW_TYPE_2;
	default:		return -1;
	}
}

struct ib_mr *mlx4_ib_get_dma_mr(struct ib_pd *pd, int acc)
{
	struct mlx4_ib_mr *mr;
	int err;

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

	err = mlx4_mr_alloc(to_mdev(pd->device)->dev, to_mpd(pd)->pdn, 0,
			    ~0ull, convert_access(acc), 0, 0, &mr->mmr);
	if (err)
		goto err_free;

	err = mlx4_mr_enable(to_mdev(pd->device)->dev, &mr->mmr);
	if (err)
		goto err_mr;

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

	return &mr->ibmr;

err_mr:
	(void) mlx4_mr_free(to_mdev(pd->device)->dev, &mr->mmr);

err_free:
	kfree(mr);

	return ERR_PTR(err);
}

int mlx4_ib_umem_write_mtt(struct mlx4_ib_dev *dev, struct mlx4_mtt *mtt,
			   struct ib_umem *umem)
{
	u64 *pages;
	int i, k, entry;
	int n;
	int len;
	int err = 0;
	struct scatterlist *sg;

	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;
			/*
			 * Be friendly to mlx4_write_mtt() and
			 * pass it chunks of appropriate size.
			 */
			if (i == PAGE_SIZE / sizeof (u64)) {
				err = mlx4_write_mtt(dev->dev, mtt, n,
						     i, pages);
				if (err)
					goto out;
				n += i;
				i = 0;
			}
		}
	}

	if (i)
		err = mlx4_write_mtt(dev->dev, mtt, n, i, pages);

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

struct ib_mr *mlx4_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
				  u64 virt_addr, int access_flags,
				  struct ib_udata *udata)
{
	struct mlx4_ib_dev *dev = to_mdev(pd->device);
	struct mlx4_ib_mr *mr;
	int shift;
	int err;
	int n;

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

	/* Force registering the memory as writable. */
	/* Used for memory re-registeration. HCA protects the access */
	mr->umem = ib_umem_get(pd->uobject->context, start, length,
			       access_flags | IB_ACCESS_LOCAL_WRITE, 0);
	if (IS_ERR(mr->umem)) {
		err = PTR_ERR(mr->umem);
		goto err_free;
	}

	n = ib_umem_page_count(mr->umem);
	shift = ilog2(mr->umem->page_size);

	err = mlx4_mr_alloc(dev->dev, to_mpd(pd)->pdn, virt_addr, length,
			    convert_access(access_flags), n, shift, &mr->mmr);
	if (err)
		goto err_umem;

	err = mlx4_ib_umem_write_mtt(dev, &mr->mmr.mtt, mr->umem);
	if (err)
		goto err_mr;

	err = mlx4_mr_enable(dev->dev, &mr->mmr);
	if (err)
		goto err_mr;

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

	return &mr->ibmr;

err_mr:
	(void) mlx4_mr_free(to_mdev(pd->device)->dev, &mr->mmr);

err_umem:
	ib_umem_release(mr->umem);

err_free:
	kfree(mr);

	return ERR_PTR(err);
}

int mlx4_ib_rereg_user_mr(struct ib_mr *mr, int flags,
			  u64 start, u64 length, u64 virt_addr,
			  int mr_access_flags, struct ib_pd *pd,
			  struct ib_udata *udata)
{
	struct mlx4_ib_dev *dev = to_mdev(mr->device);
	struct mlx4_ib_mr *mmr = to_mmr(mr);
	struct mlx4_mpt_entry *mpt_entry;
	struct mlx4_mpt_entry **pmpt_entry = &mpt_entry;
	int err;

	/* Since we synchronize this call and mlx4_ib_dereg_mr via uverbs,
	 * we assume that the calls can't run concurrently. Otherwise, a
	 * race exists.
	 */
	err =  mlx4_mr_hw_get_mpt(dev->dev, &mmr->mmr, &pmpt_entry);

	if (err)
		return err;

	if (flags & IB_MR_REREG_PD) {
		err = mlx4_mr_hw_change_pd(dev->dev, *pmpt_entry,
					   to_mpd(pd)->pdn);

		if (err)
			goto release_mpt_entry;
	}

	if (flags & IB_MR_REREG_ACCESS) {
		err = mlx4_mr_hw_change_access(dev->dev, *pmpt_entry,
					       convert_access(mr_access_flags));

		if (err)
			goto release_mpt_entry;
	}

	if (flags & IB_MR_REREG_TRANS) {
		int shift;
		int n;

		mlx4_mr_rereg_mem_cleanup(dev->dev, &mmr->mmr);
		ib_umem_release(mmr->umem);
		mmr->umem = ib_umem_get(mr->uobject->context, start, length,
					mr_access_flags |
					IB_ACCESS_LOCAL_WRITE,
					0);
		if (IS_ERR(mmr->umem)) {
			err = PTR_ERR(mmr->umem);
			/* Prevent mlx4_ib_dereg_mr from free'ing invalid pointer */
			mmr->umem = NULL;
			goto release_mpt_entry;
		}
		n = ib_umem_page_count(mmr->umem);
		shift = ilog2(mmr->umem->page_size);

		err = mlx4_mr_rereg_mem_write(dev->dev, &mmr->mmr,
					      virt_addr, length, n, shift,
					      *pmpt_entry);
		if (err) {
			ib_umem_release(mmr->umem);
			goto release_mpt_entry;
		}
		mmr->mmr.iova       = virt_addr;
		mmr->mmr.size       = length;

		err = mlx4_ib_umem_write_mtt(dev, &mmr->mmr.mtt, mmr->umem);
		if (err) {
			mlx4_mr_rereg_mem_cleanup(dev->dev, &mmr->mmr);
			ib_umem_release(mmr->umem);
			goto release_mpt_entry;
		}
	}

	/* If we couldn't transfer the MR to the HCA, just remember to
	 * return a failure. But dereg_mr will free the resources.
	 */
	err = mlx4_mr_hw_write_mpt(dev->dev, &mmr->mmr, pmpt_entry);
	if (!err && flags & IB_MR_REREG_ACCESS)
		mmr->mmr.access = mr_access_flags;

release_mpt_entry:
	mlx4_mr_hw_put_mpt(dev->dev, pmpt_entry);

	return err;
}

static int
mlx4_alloc_priv_pages(struct ib_device *device,
		      struct mlx4_ib_mr *mr,
		      int max_pages)
{
	int size = max_pages * sizeof(u64);
	int add_size;
	int ret;

	add_size = max_t(int, MLX4_MR_PAGES_ALIGN - ARCH_KMALLOC_MINALIGN, 0);

	mr->pages_alloc = kzalloc(size + add_size, GFP_KERNEL);
	if (!mr->pages_alloc)
		return -ENOMEM;

	mr->pages = PTR_ALIGN(mr->pages_alloc, MLX4_MR_PAGES_ALIGN);

	mr->page_map = dma_map_single(device->dma_device, mr->pages,
				      size, DMA_TO_DEVICE);

	if (dma_mapping_error(device->dma_device, mr->page_map)) {
		ret = -ENOMEM;
		goto err;
	}

	return 0;
err:
	kfree(mr->pages_alloc);

	return ret;
}

static void
mlx4_free_priv_pages(struct mlx4_ib_mr *mr)
{
	if (mr->pages) {
		struct ib_device *device = mr->ibmr.device;
		int size = mr->max_pages * sizeof(u64);

		dma_unmap_single(device->dma_device, mr->page_map,
				 size, DMA_TO_DEVICE);
		kfree(mr->pages_alloc);
		mr->pages = NULL;
	}
}

int mlx4_ib_dereg_mr(struct ib_mr *ibmr)
{
	struct mlx4_ib_mr *mr = to_mmr(ibmr);
	int ret;

	mlx4_free_priv_pages(mr);

	ret = mlx4_mr_free(to_mdev(ibmr->device)->dev, &mr->mmr);
	if (ret)
		return ret;
	if (mr->umem)
		ib_umem_release(mr->umem);
	kfree(mr);

	return 0;
}

struct ib_mw *mlx4_ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type)
{
	struct mlx4_ib_dev *dev = to_mdev(pd->device);
	struct mlx4_ib_mw *mw;
	int err;

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

	err = mlx4_mw_alloc(dev->dev, to_mpd(pd)->pdn,
			    to_mlx4_type(type), &mw->mmw);
	if (err)
		goto err_free;

	err = mlx4_mw_enable(dev->dev, &mw->mmw);
	if (err)
		goto err_mw;

	mw->ibmw.rkey = mw->mmw.key;

	return &mw->ibmw;

err_mw:
	mlx4_mw_free(dev->dev, &mw->mmw);

err_free:
	kfree(mw);

	return ERR_PTR(err);
}

int mlx4_ib_bind_mw(struct ib_qp *qp, struct ib_mw *mw,
		    struct ib_mw_bind *mw_bind)
{
	struct ib_bind_mw_wr  wr;
	struct ib_send_wr *bad_wr;
	int ret;

	memset(&wr, 0, sizeof(wr));
	wr.wr.opcode		= IB_WR_BIND_MW;
	wr.wr.wr_id		= mw_bind->wr_id;
	wr.wr.send_flags	= mw_bind->send_flags;
	wr.mw			= mw;
	wr.bind_info		= mw_bind->bind_info;
	wr.rkey			= ib_inc_rkey(mw->rkey);

	ret = mlx4_ib_post_send(qp, &wr.wr, &bad_wr);
	if (!ret)
		mw->rkey = wr.rkey;

	return ret;
}

int mlx4_ib_dealloc_mw(struct ib_mw *ibmw)
{
	struct mlx4_ib_mw *mw = to_mmw(ibmw);

	mlx4_mw_free(to_mdev(ibmw->device)->dev, &mw->mmw);
	kfree(mw);

	return 0;
}

struct ib_mr *mlx4_ib_alloc_mr(struct ib_pd *pd,
			       enum ib_mr_type mr_type,
			       u32 max_num_sg)
{
	struct mlx4_ib_dev *dev = to_mdev(pd->device);
	struct mlx4_ib_mr *mr;
	int err;

	if (mr_type != IB_MR_TYPE_MEM_REG ||
	    max_num_sg > MLX4_MAX_FAST_REG_PAGES)
		return ERR_PTR(-EINVAL);

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

	err = mlx4_mr_alloc(dev->dev, to_mpd(pd)->pdn, 0, 0, 0,
			    max_num_sg, 0, &mr->mmr);
	if (err)
		goto err_free;

	err = mlx4_alloc_priv_pages(pd->device, mr, max_num_sg);
	if (err)
		goto err_free_mr;

	mr->max_pages = max_num_sg;

	err = mlx4_mr_enable(dev->dev, &mr->mmr);
	if (err)
		goto err_free_pl;

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

	return &mr->ibmr;

err_free_pl:
	mlx4_free_priv_pages(mr);
err_free_mr:
	(void) mlx4_mr_free(dev->dev, &mr->mmr);
err_free:
	kfree(mr);
	return ERR_PTR(err);
}

struct ib_fmr *mlx4_ib_fmr_alloc(struct ib_pd *pd, int acc,
				 struct ib_fmr_attr *fmr_attr)
{
	struct mlx4_ib_dev *dev = to_mdev(pd->device);
	struct mlx4_ib_fmr *fmr;
	int err = -ENOMEM;

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

	err = mlx4_fmr_alloc(dev->dev, to_mpd(pd)->pdn, convert_access(acc),
			     fmr_attr->max_pages, fmr_attr->max_maps,
			     fmr_attr->page_shift, &fmr->mfmr);
	if (err)
		goto err_free;

	err = mlx4_fmr_enable(to_mdev(pd->device)->dev, &fmr->mfmr);
	if (err)
		goto err_mr;

	fmr->ibfmr.rkey = fmr->ibfmr.lkey = fmr->mfmr.mr.key;

	return &fmr->ibfmr;

err_mr:
	(void) mlx4_mr_free(to_mdev(pd->device)->dev, &fmr->mfmr.mr);

err_free:
	kfree(fmr);

	return ERR_PTR(err);
}

int mlx4_ib_map_phys_fmr(struct ib_fmr *ibfmr, u64 *page_list,
		      int npages, u64 iova)
{
	struct mlx4_ib_fmr *ifmr = to_mfmr(ibfmr);
	struct mlx4_ib_dev *dev = to_mdev(ifmr->ibfmr.device);

	return mlx4_map_phys_fmr(dev->dev, &ifmr->mfmr, page_list, npages, iova,
				 &ifmr->ibfmr.lkey, &ifmr->ibfmr.rkey);
}

int mlx4_ib_unmap_fmr(struct list_head *fmr_list)
{
	struct ib_fmr *ibfmr;
	int err;
	struct mlx4_dev *mdev = NULL;

	list_for_each_entry(ibfmr, fmr_list, list) {
		if (mdev && to_mdev(ibfmr->device)->dev != mdev)
			return -EINVAL;
		mdev = to_mdev(ibfmr->device)->dev;
	}

	if (!mdev)
		return 0;

	list_for_each_entry(ibfmr, fmr_list, list) {
		struct mlx4_ib_fmr *ifmr = to_mfmr(ibfmr);

		mlx4_fmr_unmap(mdev, &ifmr->mfmr, &ifmr->ibfmr.lkey, &ifmr->ibfmr.rkey);
	}

	/*
	 * Make sure all MPT status updates are visible before issuing
	 * SYNC_TPT firmware command.
	 */
	wmb();

	err = mlx4_SYNC_TPT(mdev);
	if (err)
		pr_warn("SYNC_TPT error %d when "
		       "unmapping FMRs\n", err);

	return 0;
}

int mlx4_ib_fmr_dealloc(struct ib_fmr *ibfmr)
{
	struct mlx4_ib_fmr *ifmr = to_mfmr(ibfmr);
	struct mlx4_ib_dev *dev = to_mdev(ibfmr->device);
	int err;

	err = mlx4_fmr_free(dev->dev, &ifmr->mfmr);

	if (!err)
		kfree(ifmr);

	return err;
}

static int mlx4_set_page(struct ib_mr *ibmr, u64 addr)
{
	struct mlx4_ib_mr *mr = to_mmr(ibmr);

	if (unlikely(mr->npages == mr->max_pages))
		return -ENOMEM;

	mr->pages[mr->npages++] = cpu_to_be64(addr | MLX4_MTT_FLAG_PRESENT);

	return 0;
}

int mlx4_ib_map_mr_sg(struct ib_mr *ibmr,
		      struct scatterlist *sg,
		      int sg_nents)
{
	struct mlx4_ib_mr *mr = to_mmr(ibmr);
	int rc;

	mr->npages = 0;

	ib_dma_sync_single_for_cpu(ibmr->device, mr->page_map,
				   sizeof(u64) * mr->max_pages,
				   DMA_TO_DEVICE);

	rc = ib_sg_to_pages(ibmr, sg, sg_nents, mlx4_set_page);

	ib_dma_sync_single_for_device(ibmr->device, mr->page_map,
				      sizeof(u64) * mr->max_pages,
				      DMA_TO_DEVICE);

	return rc;
}