summaryrefslogtreecommitdiffstats
path: root/drivers/net/ethernet/mellanox/mlx4/qp.c
blob: 40e82edac99d37d8788a0678161a9d8b05b4c53f (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
/*
 * Copyright (c) 2004 Topspin Communications.  All rights reserved.
 * Copyright (c) 2005, 2006, 2007 Cisco Systems, Inc. All rights reserved.
 * Copyright (c) 2005, 2006, 2007, 2008 Mellanox Technologies. All rights reserved.
 * Copyright (c) 2004 Voltaire, 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 <linux/gfp.h>
#include <linux/export.h>

#include <linux/mlx4/cmd.h>
#include <linux/mlx4/qp.h>

#include "mlx4.h"
#include "icm.h"

/* QP to support BF should have bits 6,7 cleared */
#define MLX4_BF_QP_SKIP_MASK	0xc0
#define MLX4_MAX_BF_QP_RANGE	0x40

void mlx4_qp_event(struct mlx4_dev *dev, u32 qpn, int event_type)
{
	struct mlx4_qp_table *qp_table = &mlx4_priv(dev)->qp_table;
	struct mlx4_qp *qp;

	spin_lock(&qp_table->lock);

	qp = __mlx4_qp_lookup(dev, qpn);
	if (qp)
		atomic_inc(&qp->refcount);

	spin_unlock(&qp_table->lock);

	if (!qp) {
		mlx4_dbg(dev, "Async event for none existent QP %08x\n", qpn);
		return;
	}

	qp->event(qp, event_type);

	if (atomic_dec_and_test(&qp->refcount))
		complete(&qp->free);
}

/* used for INIT/CLOSE port logic */
static int is_master_qp0(struct mlx4_dev *dev, struct mlx4_qp *qp, int *real_qp0, int *proxy_qp0)
{
	/* this procedure is called after we already know we are on the master */
	/* qp0 is either the proxy qp0, or the real qp0 */
	u32 pf_proxy_offset = dev->phys_caps.base_proxy_sqpn + 8 * mlx4_master_func_num(dev);
	*proxy_qp0 = qp->qpn >= pf_proxy_offset && qp->qpn <= pf_proxy_offset + 1;

	*real_qp0 = qp->qpn >= dev->phys_caps.base_sqpn &&
		qp->qpn <= dev->phys_caps.base_sqpn + 1;

	return *real_qp0 || *proxy_qp0;
}

static int __mlx4_qp_modify(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
		     enum mlx4_qp_state cur_state, enum mlx4_qp_state new_state,
		     struct mlx4_qp_context *context,
		     enum mlx4_qp_optpar optpar,
		     int sqd_event, struct mlx4_qp *qp, int native)
{
	static const u16 op[MLX4_QP_NUM_STATE][MLX4_QP_NUM_STATE] = {
		[MLX4_QP_STATE_RST] = {
			[MLX4_QP_STATE_RST]	= MLX4_CMD_2RST_QP,
			[MLX4_QP_STATE_ERR]	= MLX4_CMD_2ERR_QP,
			[MLX4_QP_STATE_INIT]	= MLX4_CMD_RST2INIT_QP,
		},
		[MLX4_QP_STATE_INIT]  = {
			[MLX4_QP_STATE_RST]	= MLX4_CMD_2RST_QP,
			[MLX4_QP_STATE_ERR]	= MLX4_CMD_2ERR_QP,
			[MLX4_QP_STATE_INIT]	= MLX4_CMD_INIT2INIT_QP,
			[MLX4_QP_STATE_RTR]	= MLX4_CMD_INIT2RTR_QP,
		},
		[MLX4_QP_STATE_RTR]   = {
			[MLX4_QP_STATE_RST]	= MLX4_CMD_2RST_QP,
			[MLX4_QP_STATE_ERR]	= MLX4_CMD_2ERR_QP,
			[MLX4_QP_STATE_RTS]	= MLX4_CMD_RTR2RTS_QP,
		},
		[MLX4_QP_STATE_RTS]   = {
			[MLX4_QP_STATE_RST]	= MLX4_CMD_2RST_QP,
			[MLX4_QP_STATE_ERR]	= MLX4_CMD_2ERR_QP,
			[MLX4_QP_STATE_RTS]	= MLX4_CMD_RTS2RTS_QP,
			[MLX4_QP_STATE_SQD]	= MLX4_CMD_RTS2SQD_QP,
		},
		[MLX4_QP_STATE_SQD] = {
			[MLX4_QP_STATE_RST]	= MLX4_CMD_2RST_QP,
			[MLX4_QP_STATE_ERR]	= MLX4_CMD_2ERR_QP,
			[MLX4_QP_STATE_RTS]	= MLX4_CMD_SQD2RTS_QP,
			[MLX4_QP_STATE_SQD]	= MLX4_CMD_SQD2SQD_QP,
		},
		[MLX4_QP_STATE_SQER] = {
			[MLX4_QP_STATE_RST]	= MLX4_CMD_2RST_QP,
			[MLX4_QP_STATE_ERR]	= MLX4_CMD_2ERR_QP,
			[MLX4_QP_STATE_RTS]	= MLX4_CMD_SQERR2RTS_QP,
		},
		[MLX4_QP_STATE_ERR] = {
			[MLX4_QP_STATE_RST]	= MLX4_CMD_2RST_QP,
			[MLX4_QP_STATE_ERR]	= MLX4_CMD_2ERR_QP,
		}
	};

	struct mlx4_priv *priv = mlx4_priv(dev);
	struct mlx4_cmd_mailbox *mailbox;
	int ret = 0;
	int real_qp0 = 0;
	int proxy_qp0 = 0;
	u8 port;

	if (cur_state >= MLX4_QP_NUM_STATE || new_state >= MLX4_QP_NUM_STATE ||
	    !op[cur_state][new_state])
		return -EINVAL;

	if (op[cur_state][new_state] == MLX4_CMD_2RST_QP) {
		ret = mlx4_cmd(dev, 0, qp->qpn, 2,
			MLX4_CMD_2RST_QP, MLX4_CMD_TIME_CLASS_A, native);
		if (mlx4_is_master(dev) && cur_state != MLX4_QP_STATE_ERR &&
		    cur_state != MLX4_QP_STATE_RST &&
		    is_master_qp0(dev, qp, &real_qp0, &proxy_qp0)) {
			port = (qp->qpn & 1) + 1;
			if (proxy_qp0)
				priv->mfunc.master.qp0_state[port].proxy_qp0_active = 0;
			else
				priv->mfunc.master.qp0_state[port].qp0_active = 0;
		}
		return ret;
	}

	mailbox = mlx4_alloc_cmd_mailbox(dev);
	if (IS_ERR(mailbox))
		return PTR_ERR(mailbox);

	if (cur_state == MLX4_QP_STATE_RST && new_state == MLX4_QP_STATE_INIT) {
		u64 mtt_addr = mlx4_mtt_addr(dev, mtt);
		context->mtt_base_addr_h = mtt_addr >> 32;
		context->mtt_base_addr_l = cpu_to_be32(mtt_addr & 0xffffffff);
		context->log_page_size   = mtt->page_shift - MLX4_ICM_PAGE_SHIFT;
	}

	*(__be32 *) mailbox->buf = cpu_to_be32(optpar);
	memcpy(mailbox->buf + 8, context, sizeof *context);

	((struct mlx4_qp_context *) (mailbox->buf + 8))->local_qpn =
		cpu_to_be32(qp->qpn);

	ret = mlx4_cmd(dev, mailbox->dma,
		       qp->qpn | (!!sqd_event << 31),
		       new_state == MLX4_QP_STATE_RST ? 2 : 0,
		       op[cur_state][new_state], MLX4_CMD_TIME_CLASS_C, native);

	if (mlx4_is_master(dev) && is_master_qp0(dev, qp, &real_qp0, &proxy_qp0)) {
		port = (qp->qpn & 1) + 1;
		if (cur_state != MLX4_QP_STATE_ERR &&
		    cur_state != MLX4_QP_STATE_RST &&
		    new_state == MLX4_QP_STATE_ERR) {
			if (proxy_qp0)
				priv->mfunc.master.qp0_state[port].proxy_qp0_active = 0;
			else
				priv->mfunc.master.qp0_state[port].qp0_active = 0;
		} else if (new_state == MLX4_QP_STATE_RTR) {
			if (proxy_qp0)
				priv->mfunc.master.qp0_state[port].proxy_qp0_active = 1;
			else
				priv->mfunc.master.qp0_state[port].qp0_active = 1;
		}
	}

	mlx4_free_cmd_mailbox(dev, mailbox);
	return ret;
}

int mlx4_qp_modify(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
		   enum mlx4_qp_state cur_state, enum mlx4_qp_state new_state,
		   struct mlx4_qp_context *context,
		   enum mlx4_qp_optpar optpar,
		   int sqd_event, struct mlx4_qp *qp)
{
	return __mlx4_qp_modify(dev, mtt, cur_state, new_state, context,
				optpar, sqd_event, qp, 0);
}
EXPORT_SYMBOL_GPL(mlx4_qp_modify);

int __mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align,
			    int *base, u8 flags)
{
	int bf_qp = !!(flags & (u8)MLX4_RESERVE_ETH_BF_QP);

	struct mlx4_priv *priv = mlx4_priv(dev);
	struct mlx4_qp_table *qp_table = &priv->qp_table;

	if (cnt > MLX4_MAX_BF_QP_RANGE && bf_qp)
		return -ENOMEM;

	*base = mlx4_bitmap_alloc_range(&qp_table->bitmap, cnt, align,
					bf_qp ? MLX4_BF_QP_SKIP_MASK : 0);
	if (*base == -1)
		return -ENOMEM;

	return 0;
}

int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align,
			  int *base, u8 flags)
{
	u64 in_param = 0;
	u64 out_param;
	int err;

	/* Turn off all unsupported QP allocation flags */
	flags &= dev->caps.alloc_res_qp_mask;

	if (mlx4_is_mfunc(dev)) {
		set_param_l(&in_param, (((u32)flags) << 24) | (u32)cnt);
		set_param_h(&in_param, align);
		err = mlx4_cmd_imm(dev, in_param, &out_param,
				   RES_QP, RES_OP_RESERVE,
				   MLX4_CMD_ALLOC_RES,
				   MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
		if (err)
			return err;

		*base = get_param_l(&out_param);
		return 0;
	}
	return __mlx4_qp_reserve_range(dev, cnt, align, base, flags);
}
EXPORT_SYMBOL_GPL(mlx4_qp_reserve_range);

void __mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	struct mlx4_qp_table *qp_table = &priv->qp_table;

	if (mlx4_is_qp_reserved(dev, (u32) base_qpn))
		return;
	mlx4_bitmap_free_range(&qp_table->bitmap, base_qpn, cnt, MLX4_USE_RR);
}

void mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt)
{
	u64 in_param = 0;
	int err;

	if (mlx4_is_mfunc(dev)) {
		set_param_l(&in_param, base_qpn);
		set_param_h(&in_param, cnt);
		err = mlx4_cmd(dev, in_param, RES_QP, RES_OP_RESERVE,
			       MLX4_CMD_FREE_RES,
			       MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
		if (err) {
			mlx4_warn(dev, "Failed to release qp range base:%d cnt:%d\n",
				  base_qpn, cnt);
		}
	} else
		 __mlx4_qp_release_range(dev, base_qpn, cnt);
}
EXPORT_SYMBOL_GPL(mlx4_qp_release_range);

int __mlx4_qp_alloc_icm(struct mlx4_dev *dev, int qpn, gfp_t gfp)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	struct mlx4_qp_table *qp_table = &priv->qp_table;
	int err;

	err = mlx4_table_get(dev, &qp_table->qp_table, qpn, gfp);
	if (err)
		goto err_out;

	err = mlx4_table_get(dev, &qp_table->auxc_table, qpn, gfp);
	if (err)
		goto err_put_qp;

	err = mlx4_table_get(dev, &qp_table->altc_table, qpn, gfp);
	if (err)
		goto err_put_auxc;

	err = mlx4_table_get(dev, &qp_table->rdmarc_table, qpn, gfp);
	if (err)
		goto err_put_altc;

	err = mlx4_table_get(dev, &qp_table->cmpt_table, qpn, gfp);
	if (err)
		goto err_put_rdmarc;

	return 0;

err_put_rdmarc:
	mlx4_table_put(dev, &qp_table->rdmarc_table, qpn);

err_put_altc:
	mlx4_table_put(dev, &qp_table->altc_table, qpn);

err_put_auxc:
	mlx4_table_put(dev, &qp_table->auxc_table, qpn);

err_put_qp:
	mlx4_table_put(dev, &qp_table->qp_table, qpn);

err_out:
	return err;
}

static int mlx4_qp_alloc_icm(struct mlx4_dev *dev, int qpn, gfp_t gfp)
{
	u64 param = 0;

	if (mlx4_is_mfunc(dev)) {
		set_param_l(&param, qpn);
		return mlx4_cmd_imm(dev, param, &param, RES_QP, RES_OP_MAP_ICM,
				    MLX4_CMD_ALLOC_RES, MLX4_CMD_TIME_CLASS_A,
				    MLX4_CMD_WRAPPED);
	}
	return __mlx4_qp_alloc_icm(dev, qpn, gfp);
}

void __mlx4_qp_free_icm(struct mlx4_dev *dev, int qpn)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	struct mlx4_qp_table *qp_table = &priv->qp_table;

	mlx4_table_put(dev, &qp_table->cmpt_table, qpn);
	mlx4_table_put(dev, &qp_table->rdmarc_table, qpn);
	mlx4_table_put(dev, &qp_table->altc_table, qpn);
	mlx4_table_put(dev, &qp_table->auxc_table, qpn);
	mlx4_table_put(dev, &qp_table->qp_table, qpn);
}

static void mlx4_qp_free_icm(struct mlx4_dev *dev, int qpn)
{
	u64 in_param = 0;

	if (mlx4_is_mfunc(dev)) {
		set_param_l(&in_param, qpn);
		if (mlx4_cmd(dev, in_param, RES_QP, RES_OP_MAP_ICM,
			     MLX4_CMD_FREE_RES, MLX4_CMD_TIME_CLASS_A,
			     MLX4_CMD_WRAPPED))
			mlx4_warn(dev, "Failed to free icm of qp:%d\n", qpn);
	} else
		__mlx4_qp_free_icm(dev, qpn);
}

int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp, gfp_t gfp)
{
	struct mlx4_priv *priv = mlx4_priv(dev);
	struct mlx4_qp_table *qp_table = &priv->qp_table;
	int err;

	if (!qpn)
		return -EINVAL;

	qp->qpn = qpn;

	err = mlx4_qp_alloc_icm(dev, qpn, gfp);
	if (err)
		return err;

	spin_lock_irq(&qp_table->lock);
	err = radix_tree_insert(&dev->qp_table_tree, qp->qpn &
				(dev->caps.num_qps - 1), qp);
	spin_unlock_irq(&qp_table->lock);
	if (err)
		goto err_icm;

	atomic_set(&qp->refcount, 1);
	init_completion(&qp->free);

	return 0;

err_icm:
	mlx4_qp_free_icm(dev, qpn);
	return err;
}

EXPORT_SYMBOL_GPL(mlx4_qp_alloc);

#define MLX4_UPDATE_QP_SUPPORTED_ATTRS MLX4_UPDATE_QP_SMAC
int mlx4_update_qp(struct mlx4_dev *dev, u32 qpn,
		   enum mlx4_update_qp_attr attr,
		   struct mlx4_update_qp_params *params)
{
	struct mlx4_cmd_mailbox *mailbox;
	struct mlx4_update_qp_context *cmd;
	u64 pri_addr_path_mask = 0;
	u64 qp_mask = 0;
	int err = 0;

	mailbox = mlx4_alloc_cmd_mailbox(dev);
	if (IS_ERR(mailbox))
		return PTR_ERR(mailbox);

	cmd = (struct mlx4_update_qp_context *)mailbox->buf;

	if (!attr || (attr & ~MLX4_UPDATE_QP_SUPPORTED_ATTRS))
		return -EINVAL;

	if (attr & MLX4_UPDATE_QP_SMAC) {
		pri_addr_path_mask |= 1ULL << MLX4_UPD_QP_PATH_MASK_MAC_INDEX;
		cmd->qp_context.pri_path.grh_mylmc = params->smac_index;
	}

	if (attr & MLX4_UPDATE_QP_VSD) {
		qp_mask |= 1ULL << MLX4_UPD_QP_MASK_VSD;
		if (params->flags & MLX4_UPDATE_QP_PARAMS_FLAGS_VSD_ENABLE)
			cmd->qp_context.param3 |= cpu_to_be32(MLX4_STRIP_VLAN);
	}

	cmd->primary_addr_path_mask = cpu_to_be64(pri_addr_path_mask);
	cmd->qp_mask = cpu_to_be64(qp_mask);

	err = mlx4_cmd(dev, mailbox->dma, qpn & 0xffffff, 0,
		       MLX4_CMD_UPDATE_QP, MLX4_CMD_TIME_CLASS_A,
		       MLX4_CMD_NATIVE);

	mlx4_free_cmd_mailbox(dev, mailbox);
	return err;
}
EXPORT_SYMBOL_GPL(mlx4_update_qp);

void mlx4_qp_remove(struct mlx4_dev *dev, struct mlx4_qp *qp)
{
	struct mlx4_qp_table *qp_table = &mlx4_priv(dev)->qp_table;
	unsigned long flags;

	spin_lock_irqsave(&qp_table->lock, flags);
	radix_tree_delete(&dev->qp_table_tree, qp->qpn & (dev->caps.num_qps - 1));
	spin_unlock_irqrestore(&qp_table->lock, flags);
}
EXPORT_SYMBOL_GPL(mlx4_qp_remove);

void mlx4_qp_free(struct mlx4_dev *dev, struct mlx4_qp *qp)
{
	if (atomic_dec_and_test(&qp->refcount))
		complete(&qp->free);
	wait_for_completion(&qp->free);

	mlx4_qp_free_icm(dev, qp->qpn);
}
EXPORT_SYMBOL_GPL(mlx4_qp_free);

static int mlx4_CONF_SPECIAL_QP(struct mlx4_dev *dev, u32 base_qpn)
{
	return mlx4_cmd(dev, 0, base_qpn, 0, MLX4_CMD_CONF_SPECIAL_QP,
			MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
}

int mlx4_init_qp_table(struct mlx4_dev *dev)
{
	struct mlx4_qp_table *qp_table = &mlx4_priv(dev)->qp_table;
	int err;
	int reserved_from_top = 0;
	int k;

	spin_lock_init(&qp_table->lock);
	INIT_RADIX_TREE(&dev->qp_table_tree, GFP_ATOMIC);
	if (mlx4_is_slave(dev))
		return 0;

	/*
	 * We reserve 2 extra QPs per port for the special QPs.  The
	 * block of special QPs must be aligned to a multiple of 8, so
	 * round up.
	 *
	 * We also reserve the MSB of the 24-bit QP number to indicate
	 * that a QP is an XRC QP.
	 */
	dev->phys_caps.base_sqpn =
		ALIGN(dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW], 8);

	{
		int sort[MLX4_NUM_QP_REGION];
		int i, j, tmp;
		int last_base = dev->caps.num_qps;

		for (i = 1; i < MLX4_NUM_QP_REGION; ++i)
			sort[i] = i;

		for (i = MLX4_NUM_QP_REGION; i > 0; --i) {
			for (j = 2; j < i; ++j) {
				if (dev->caps.reserved_qps_cnt[sort[j]] >
				    dev->caps.reserved_qps_cnt[sort[j - 1]]) {
					tmp             = sort[j];
					sort[j]         = sort[j - 1];
					sort[j - 1]     = tmp;
				}
			}
		}

		for (i = 1; i < MLX4_NUM_QP_REGION; ++i) {
			last_base -= dev->caps.reserved_qps_cnt[sort[i]];
			dev->caps.reserved_qps_base[sort[i]] = last_base;
			reserved_from_top +=
				dev->caps.reserved_qps_cnt[sort[i]];
		}

	}

       /* Reserve 8 real SQPs in both native and SRIOV modes.
	* In addition, in SRIOV mode, reserve 8 proxy SQPs per function
	* (for all PFs and VFs), and 8 corresponding tunnel QPs.
	* Each proxy SQP works opposite its own tunnel QP.
	*
	* The QPs are arranged as follows:
	* a. 8 real SQPs
	* b. All the proxy SQPs (8 per function)
	* c. All the tunnel QPs (8 per function)
	*/

	err = mlx4_bitmap_init(&qp_table->bitmap, dev->caps.num_qps,
			       (1 << 23) - 1, mlx4_num_reserved_sqps(dev),
			       reserved_from_top);
	if (err)
		return err;

	if (mlx4_is_mfunc(dev)) {
		/* for PPF use */
		dev->phys_caps.base_proxy_sqpn = dev->phys_caps.base_sqpn + 8;
		dev->phys_caps.base_tunnel_sqpn = dev->phys_caps.base_sqpn + 8 + 8 * MLX4_MFUNC_MAX;

		/* In mfunc, calculate proxy and tunnel qp offsets for the PF here,
		 * since the PF does not call mlx4_slave_caps */
		dev->caps.qp0_tunnel = kcalloc(dev->caps.num_ports, sizeof (u32), GFP_KERNEL);
		dev->caps.qp0_proxy = kcalloc(dev->caps.num_ports, sizeof (u32), GFP_KERNEL);
		dev->caps.qp1_tunnel = kcalloc(dev->caps.num_ports, sizeof (u32), GFP_KERNEL);
		dev->caps.qp1_proxy = kcalloc(dev->caps.num_ports, sizeof (u32), GFP_KERNEL);

		if (!dev->caps.qp0_tunnel || !dev->caps.qp0_proxy ||
		    !dev->caps.qp1_tunnel || !dev->caps.qp1_proxy) {
			err = -ENOMEM;
			goto err_mem;
		}

		for (k = 0; k < dev->caps.num_ports; k++) {
			dev->caps.qp0_proxy[k] = dev->phys_caps.base_proxy_sqpn +
				8 * mlx4_master_func_num(dev) + k;
			dev->caps.qp0_tunnel[k] = dev->caps.qp0_proxy[k] + 8 * MLX4_MFUNC_MAX;
			dev->caps.qp1_proxy[k] = dev->phys_caps.base_proxy_sqpn +
				8 * mlx4_master_func_num(dev) + MLX4_MAX_PORTS + k;
			dev->caps.qp1_tunnel[k] = dev->caps.qp1_proxy[k] + 8 * MLX4_MFUNC_MAX;
		}
	}


	err = mlx4_CONF_SPECIAL_QP(dev, dev->phys_caps.base_sqpn);
	if (err)
		goto err_mem;
	return 0;

err_mem:
	kfree(dev->caps.qp0_tunnel);
	kfree(dev->caps.qp0_proxy);
	kfree(dev->caps.qp1_tunnel);
	kfree(dev->caps.qp1_proxy);
	dev->caps.qp0_tunnel = dev->caps.qp0_proxy =
		dev->caps.qp1_tunnel = dev->caps.qp1_proxy = NULL;
	return err;
}

void mlx4_cleanup_qp_table(struct mlx4_dev *dev)
{
	if (mlx4_is_slave(dev))
		return;

	mlx4_CONF_SPECIAL_QP(dev, 0);
	mlx4_bitmap_cleanup(&mlx4_priv(dev)->qp_table.bitmap);
}

int mlx4_qp_query(struct mlx4_dev *dev, struct mlx4_qp *qp,
		  struct mlx4_qp_context *context)
{
	struct mlx4_cmd_mailbox *mailbox;
	int err;

	mailbox = mlx4_alloc_cmd_mailbox(dev);
	if (IS_ERR(mailbox))
		return PTR_ERR(mailbox);

	err = mlx4_cmd_box(dev, 0, mailbox->dma, qp->qpn, 0,
			   MLX4_CMD_QUERY_QP, MLX4_CMD_TIME_CLASS_A,
			   MLX4_CMD_WRAPPED);
	if (!err)
		memcpy(context, mailbox->buf + 8, sizeof *context);

	mlx4_free_cmd_mailbox(dev, mailbox);
	return err;
}
EXPORT_SYMBOL_GPL(mlx4_qp_query);

int mlx4_qp_to_ready(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
		     struct mlx4_qp_context *context,
		     struct mlx4_qp *qp, enum mlx4_qp_state *qp_state)
{
	int err;
	int i;
	enum mlx4_qp_state states[] = {
		MLX4_QP_STATE_RST,
		MLX4_QP_STATE_INIT,
		MLX4_QP_STATE_RTR,
		MLX4_QP_STATE_RTS
	};

	for (i = 0; i < ARRAY_SIZE(states) - 1; i++) {
		context->flags &= cpu_to_be32(~(0xf << 28));
		context->flags |= cpu_to_be32(states[i + 1] << 28);
		err = mlx4_qp_modify(dev, mtt, states[i], states[i + 1],
				     context, 0, 0, qp);
		if (err) {
			mlx4_err(dev, "Failed to bring QP to state: %d with error: %d\n",
				 states[i + 1], err);
			return err;
		}

		*qp_state = states[i + 1];
	}

	return 0;
}
EXPORT_SYMBOL_GPL(mlx4_qp_to_ready);