summaryrefslogtreecommitdiff
path: root/drivers/infiniband/hw/qib/qib_mr.c
blob: 294f5c706be972b4b6563e37a32064fade665be2 (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
/*
 * Copyright (c) 2006, 2007, 2008, 2009 QLogic Corporation. All rights reserved.
 * Copyright (c) 2005, 2006 PathScale, Inc. 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 <rdma/ib_umem.h>
#include <rdma/ib_smi.h>

#include "qib.h"

/* Fast memory region */
struct qib_fmr {
	struct ib_fmr ibfmr;
	struct qib_mregion mr;        /* must be last */
};

static inline struct qib_fmr *to_ifmr(struct ib_fmr *ibfmr)
{
	return container_of(ibfmr, struct qib_fmr, ibfmr);
}

static int init_qib_mregion(struct qib_mregion *mr, struct ib_pd *pd,
	int count)
{
	int m, i = 0;
	int rval = 0;

	m = (count + QIB_SEGSZ - 1) / QIB_SEGSZ;
	for (; i < m; i++) {
		mr->map[i] = kzalloc(sizeof(*mr->map[0]), GFP_KERNEL);
		if (!mr->map[i])
			goto bail;
	}
	mr->mapsz = m;
	init_completion(&mr->comp);
	/* count returning the ptr to user */
	atomic_set(&mr->refcount, 1);
	mr->pd = pd;
	mr->max_segs = count;
out:
	return rval;
bail:
	while (i)
		kfree(mr->map[--i]);
	rval = -ENOMEM;
	goto out;
}

static void deinit_qib_mregion(struct qib_mregion *mr)
{
	int i = mr->mapsz;

	mr->mapsz = 0;
	while (i)
		kfree(mr->map[--i]);
}


/**
 * qib_get_dma_mr - get a DMA memory region
 * @pd: protection domain for this memory region
 * @acc: access flags
 *
 * Returns the memory region on success, otherwise returns an errno.
 * Note that all DMA addresses should be created via the
 * struct ib_dma_mapping_ops functions (see qib_dma.c).
 */
struct ib_mr *qib_get_dma_mr(struct ib_pd *pd, int acc)
{
	struct qib_mr *mr = NULL;
	struct ib_mr *ret;
	int rval;

	if (to_ipd(pd)->user) {
		ret = ERR_PTR(-EPERM);
		goto bail;
	}

	mr = kzalloc(sizeof(*mr), GFP_KERNEL);
	if (!mr) {
		ret = ERR_PTR(-ENOMEM);
		goto bail;
	}

	rval = init_qib_mregion(&mr->mr, pd, 0);
	if (rval) {
		ret = ERR_PTR(rval);
		goto bail;
	}


	rval = qib_alloc_lkey(&mr->mr, 1);
	if (rval) {
		ret = ERR_PTR(rval);
		goto bail_mregion;
	}

	mr->mr.access_flags = acc;
	ret = &mr->ibmr;
done:
	return ret;

bail_mregion:
	deinit_qib_mregion(&mr->mr);
bail:
	kfree(mr);
	goto done;
}

static struct qib_mr *alloc_mr(int count, struct ib_pd *pd)
{
	struct qib_mr *mr;
	int rval = -ENOMEM;
	int m;

	/* Allocate struct plus pointers to first level page tables. */
	m = (count + QIB_SEGSZ - 1) / QIB_SEGSZ;
	mr = kzalloc(sizeof(*mr) + m * sizeof(mr->mr.map[0]), GFP_KERNEL);
	if (!mr)
		goto bail;

	rval = init_qib_mregion(&mr->mr, pd, count);
	if (rval)
		goto bail;
	/*
	 * ib_reg_phys_mr() will initialize mr->ibmr except for
	 * lkey and rkey.
	 */
	rval = qib_alloc_lkey(&mr->mr, 0);
	if (rval)
		goto bail_mregion;
	mr->ibmr.lkey = mr->mr.lkey;
	mr->ibmr.rkey = mr->mr.lkey;
done:
	return mr;

bail_mregion:
	deinit_qib_mregion(&mr->mr);
bail:
	kfree(mr);
	mr = ERR_PTR(rval);
	goto done;
}

/**
 * qib_reg_phys_mr - register a physical memory region
 * @pd: protection domain for this memory region
 * @buffer_list: pointer to the list of physical buffers to register
 * @num_phys_buf: the number of physical buffers to register
 * @iova_start: the starting address passed over IB which maps to this MR
 *
 * Returns the memory region on success, otherwise returns an errno.
 */
struct ib_mr *qib_reg_phys_mr(struct ib_pd *pd,
			      struct ib_phys_buf *buffer_list,
			      int num_phys_buf, int acc, u64 *iova_start)
{
	struct qib_mr *mr;
	int n, m, i;
	struct ib_mr *ret;

	mr = alloc_mr(num_phys_buf, pd);
	if (IS_ERR(mr)) {
		ret = (struct ib_mr *)mr;
		goto bail;
	}

	mr->mr.user_base = *iova_start;
	mr->mr.iova = *iova_start;
	mr->mr.access_flags = acc;

	m = 0;
	n = 0;
	for (i = 0; i < num_phys_buf; i++) {
		mr->mr.map[m]->segs[n].vaddr = (void *) buffer_list[i].addr;
		mr->mr.map[m]->segs[n].length = buffer_list[i].size;
		mr->mr.length += buffer_list[i].size;
		n++;
		if (n == QIB_SEGSZ) {
			m++;
			n = 0;
		}
	}

	ret = &mr->ibmr;

bail:
	return ret;
}

/**
 * qib_reg_user_mr - register a userspace memory region
 * @pd: protection domain for this memory region
 * @start: starting userspace address
 * @length: length of region to register
 * @mr_access_flags: access flags for this memory region
 * @udata: unused by the QLogic_IB driver
 *
 * Returns the memory region on success, otherwise returns an errno.
 */
struct ib_mr *qib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
			      u64 virt_addr, int mr_access_flags,
			      struct ib_udata *udata)
{
	struct qib_mr *mr;
	struct ib_umem *umem;
	struct scatterlist *sg;
	int n, m, entry;
	struct ib_mr *ret;

	if (length == 0) {
		ret = ERR_PTR(-EINVAL);
		goto bail;
	}

	umem = ib_umem_get(pd->uobject->context, start, length,
			   mr_access_flags, 0);
	if (IS_ERR(umem))
		return (void *) umem;

	n = umem->nmap;

	mr = alloc_mr(n, pd);
	if (IS_ERR(mr)) {
		ret = (struct ib_mr *)mr;
		ib_umem_release(umem);
		goto bail;
	}

	mr->mr.user_base = start;
	mr->mr.iova = virt_addr;
	mr->mr.length = length;
	mr->mr.offset = ib_umem_offset(umem);
	mr->mr.access_flags = mr_access_flags;
	mr->umem = umem;

	if (is_power_of_2(umem->page_size))
		mr->mr.page_shift = ilog2(umem->page_size);
	m = 0;
	n = 0;
	for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) {
			void *vaddr;

			vaddr = page_address(sg_page(sg));
			if (!vaddr) {
				ret = ERR_PTR(-EINVAL);
				goto bail;
			}
			mr->mr.map[m]->segs[n].vaddr = vaddr;
			mr->mr.map[m]->segs[n].length = umem->page_size;
			n++;
			if (n == QIB_SEGSZ) {
				m++;
				n = 0;
			}
	}
	ret = &mr->ibmr;

bail:
	return ret;
}

/**
 * qib_dereg_mr - unregister and free a memory region
 * @ibmr: the memory region to free
 *
 * Returns 0 on success.
 *
 * Note that this is called to free MRs created by qib_get_dma_mr()
 * or qib_reg_user_mr().
 */
int qib_dereg_mr(struct ib_mr *ibmr)
{
	struct qib_mr *mr = to_imr(ibmr);
	int ret = 0;
	unsigned long timeout;

	kfree(mr->pages);
	qib_free_lkey(&mr->mr);

	qib_put_mr(&mr->mr); /* will set completion if last */
	timeout = wait_for_completion_timeout(&mr->mr.comp,
		5 * HZ);
	if (!timeout) {
		qib_get_mr(&mr->mr);
		ret = -EBUSY;
		goto out;
	}
	deinit_qib_mregion(&mr->mr);
	if (mr->umem)
		ib_umem_release(mr->umem);
	kfree(mr);
out:
	return ret;
}

/*
 * Allocate a memory region usable with the
 * IB_WR_REG_MR send work request.
 *
 * Return the memory region on success, otherwise return an errno.
 */
struct ib_mr *qib_alloc_mr(struct ib_pd *pd,
			   enum ib_mr_type mr_type,
			   u32 max_num_sg)
{
	struct qib_mr *mr;

	if (mr_type != IB_MR_TYPE_MEM_REG)
		return ERR_PTR(-EINVAL);

	mr = alloc_mr(max_num_sg, pd);
	if (IS_ERR(mr))
		return (struct ib_mr *)mr;

	mr->pages = kcalloc(max_num_sg, sizeof(u64), GFP_KERNEL);
	if (!mr->pages)
		goto err;

	return &mr->ibmr;

err:
	qib_dereg_mr(&mr->ibmr);
	return ERR_PTR(-ENOMEM);
}

static int qib_set_page(struct ib_mr *ibmr, u64 addr)
{
	struct qib_mr *mr = to_imr(ibmr);

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

	mr->pages[mr->npages++] = addr;

	return 0;
}

int qib_map_mr_sg(struct ib_mr *ibmr,
		  struct scatterlist *sg,
		  int sg_nents)
{
	struct qib_mr *mr = to_imr(ibmr);

	mr->npages = 0;

	return ib_sg_to_pages(ibmr, sg, sg_nents, qib_set_page);
}

/**
 * qib_alloc_fmr - allocate a fast memory region
 * @pd: the protection domain for this memory region
 * @mr_access_flags: access flags for this memory region
 * @fmr_attr: fast memory region attributes
 *
 * Returns the memory region on success, otherwise returns an errno.
 */
struct ib_fmr *qib_alloc_fmr(struct ib_pd *pd, int mr_access_flags,
			     struct ib_fmr_attr *fmr_attr)
{
	struct qib_fmr *fmr;
	int m;
	struct ib_fmr *ret;
	int rval = -ENOMEM;

	/* Allocate struct plus pointers to first level page tables. */
	m = (fmr_attr->max_pages + QIB_SEGSZ - 1) / QIB_SEGSZ;
	fmr = kzalloc(sizeof(*fmr) + m * sizeof(fmr->mr.map[0]), GFP_KERNEL);
	if (!fmr)
		goto bail;

	rval = init_qib_mregion(&fmr->mr, pd, fmr_attr->max_pages);
	if (rval)
		goto bail;

	/*
	 * ib_alloc_fmr() will initialize fmr->ibfmr except for lkey &
	 * rkey.
	 */
	rval = qib_alloc_lkey(&fmr->mr, 0);
	if (rval)
		goto bail_mregion;
	fmr->ibfmr.rkey = fmr->mr.lkey;
	fmr->ibfmr.lkey = fmr->mr.lkey;
	/*
	 * Resources are allocated but no valid mapping (RKEY can't be
	 * used).
	 */
	fmr->mr.access_flags = mr_access_flags;
	fmr->mr.max_segs = fmr_attr->max_pages;
	fmr->mr.page_shift = fmr_attr->page_shift;

	ret = &fmr->ibfmr;
done:
	return ret;

bail_mregion:
	deinit_qib_mregion(&fmr->mr);
bail:
	kfree(fmr);
	ret = ERR_PTR(rval);
	goto done;
}

/**
 * qib_map_phys_fmr - set up a fast memory region
 * @ibmfr: the fast memory region to set up
 * @page_list: the list of pages to associate with the fast memory region
 * @list_len: the number of pages to associate with the fast memory region
 * @iova: the virtual address of the start of the fast memory region
 *
 * This may be called from interrupt context.
 */

int qib_map_phys_fmr(struct ib_fmr *ibfmr, u64 *page_list,
		     int list_len, u64 iova)
{
	struct qib_fmr *fmr = to_ifmr(ibfmr);
	struct qib_lkey_table *rkt;
	unsigned long flags;
	int m, n, i;
	u32 ps;
	int ret;

	i = atomic_read(&fmr->mr.refcount);
	if (i > 2)
		return -EBUSY;

	if (list_len > fmr->mr.max_segs) {
		ret = -EINVAL;
		goto bail;
	}
	rkt = &to_idev(ibfmr->device)->lk_table;
	spin_lock_irqsave(&rkt->lock, flags);
	fmr->mr.user_base = iova;
	fmr->mr.iova = iova;
	ps = 1 << fmr->mr.page_shift;
	fmr->mr.length = list_len * ps;
	m = 0;
	n = 0;
	for (i = 0; i < list_len; i++) {
		fmr->mr.map[m]->segs[n].vaddr = (void *) page_list[i];
		fmr->mr.map[m]->segs[n].length = ps;
		if (++n == QIB_SEGSZ) {
			m++;
			n = 0;
		}
	}
	spin_unlock_irqrestore(&rkt->lock, flags);
	ret = 0;

bail:
	return ret;
}

/**
 * qib_unmap_fmr - unmap fast memory regions
 * @fmr_list: the list of fast memory regions to unmap
 *
 * Returns 0 on success.
 */
int qib_unmap_fmr(struct list_head *fmr_list)
{
	struct qib_fmr *fmr;
	struct qib_lkey_table *rkt;
	unsigned long flags;

	list_for_each_entry(fmr, fmr_list, ibfmr.list) {
		rkt = &to_idev(fmr->ibfmr.device)->lk_table;
		spin_lock_irqsave(&rkt->lock, flags);
		fmr->mr.user_base = 0;
		fmr->mr.iova = 0;
		fmr->mr.length = 0;
		spin_unlock_irqrestore(&rkt->lock, flags);
	}
	return 0;
}

/**
 * qib_dealloc_fmr - deallocate a fast memory region
 * @ibfmr: the fast memory region to deallocate
 *
 * Returns 0 on success.
 */
int qib_dealloc_fmr(struct ib_fmr *ibfmr)
{
	struct qib_fmr *fmr = to_ifmr(ibfmr);
	int ret = 0;
	unsigned long timeout;

	qib_free_lkey(&fmr->mr);
	qib_put_mr(&fmr->mr); /* will set completion if last */
	timeout = wait_for_completion_timeout(&fmr->mr.comp,
		5 * HZ);
	if (!timeout) {
		qib_get_mr(&fmr->mr);
		ret = -EBUSY;
		goto out;
	}
	deinit_qib_mregion(&fmr->mr);
	kfree(fmr);
out:
	return ret;
}

void mr_rcu_callback(struct rcu_head *list)
{
	struct qib_mregion *mr = container_of(list, struct qib_mregion, list);

	complete(&mr->comp);
}