aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/infiniband/hw/mlx4/cq.c
blob: a1464574bfdde532d8f6e19c6818fdc68d4f0876 (plain) (blame)
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
/*
 * 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/mlx4/cq.h>
#include <linux/mlx4/qp.h>

#include "mlx4_ib.h"
#include "user.h"

static void mlx4_ib_cq_comp(struct mlx4_cq *cq)
{
	struct ib_cq *ibcq = &to_mibcq(cq)->ibcq;
	ibcq->comp_handler(ibcq, ibcq->cq_context);
}

static void mlx4_ib_cq_event(struct mlx4_cq *cq, enum mlx4_event type)
{
	struct ib_event event;
	struct ib_cq *ibcq;

	if (type != MLX4_EVENT_TYPE_CQ_ERROR) {
		printk(KERN_WARNING "mlx4_ib: Unexpected event type %d "
		       "on CQ %06x\n", type, cq->cqn);
		return;
	}

	ibcq = &to_mibcq(cq)->ibcq;
	if (ibcq->event_handler) {
		event.device     = ibcq->device;
		event.event      = IB_EVENT_CQ_ERR;
		event.element.cq = ibcq;
		ibcq->event_handler(&event, ibcq->cq_context);
	}
}

static void *get_cqe_from_buf(struct mlx4_ib_cq_buf *buf, int n)
{
	return mlx4_buf_offset(&buf->buf, n * sizeof (struct mlx4_cqe));
}

static void *get_cqe(struct mlx4_ib_cq *cq, int n)
{
	return get_cqe_from_buf(&cq->buf, n);
}

static void *get_sw_cqe(struct mlx4_ib_cq *cq, int n)
{
	struct mlx4_cqe *cqe = get_cqe(cq, n & cq->ibcq.cqe);

	return (!!(cqe->owner_sr_opcode & MLX4_CQE_OWNER_MASK) ^
		!!(n & (cq->ibcq.cqe + 1))) ? NULL : cqe;
}

static struct mlx4_cqe *next_cqe_sw(struct mlx4_ib_cq *cq)
{
	return get_sw_cqe(cq, cq->mcq.cons_index);
}

int mlx4_ib_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period)
{
	struct mlx4_ib_cq *mcq = to_mcq(cq);
	struct mlx4_ib_dev *dev = to_mdev(cq->device);

	return mlx4_cq_modify(dev->dev, &mcq->mcq, cq_count, cq_period);
}

static int mlx4_ib_alloc_cq_buf(struct mlx4_ib_dev *dev, struct mlx4_ib_cq_buf *buf, int nent)
{
	int err;

	err = mlx4_buf_alloc(dev->dev, nent * sizeof(struct mlx4_cqe),
			     PAGE_SIZE * 2, &buf->buf);

	if (err)
		goto out;

	err = mlx4_mtt_init(dev->dev, buf->buf.npages, buf->buf.page_shift,
				    &buf->mtt);
	if (err)
		goto err_buf;

	err = mlx4_buf_write_mtt(dev->dev, &buf->mtt, &buf->buf);
	if (err)
		goto err_mtt;

	return 0;

err_mtt:
	mlx4_mtt_cleanup(dev->dev, &buf->mtt);

err_buf:
	mlx4_buf_free(dev->dev, nent * sizeof(struct mlx4_cqe),
			      &buf->buf);

out:
	return err;
}

static void mlx4_ib_free_cq_buf(struct mlx4_ib_dev *dev, struct mlx4_ib_cq_buf *buf, int cqe)
{
	mlx4_buf_free(dev->dev, (cqe + 1) * sizeof(struct mlx4_cqe), &buf->buf);
}

static int mlx4_ib_get_cq_umem(struct mlx4_ib_dev *dev, struct ib_ucontext *context,
			       struct mlx4_ib_cq_buf *buf, struct ib_umem **umem,
			       u64 buf_addr, int cqe)
{
	int err;

	*umem = ib_umem_get(context, buf_addr, cqe * sizeof (struct mlx4_cqe),
			    IB_ACCESS_LOCAL_WRITE, 1);
	if (IS_ERR(*umem))
		return PTR_ERR(*umem);

	err = mlx4_mtt_init(dev->dev, ib_umem_page_count(*umem),
			    ilog2((*umem)->page_size), &buf->mtt);
	if (err)
		goto err_buf;

	err = mlx4_ib_umem_write_mtt(dev, &buf->mtt, *umem);
	if (err)
		goto err_mtt;

	return 0;

err_mtt:
	mlx4_mtt_cleanup(dev->dev, &buf->mtt);

err_buf:
	ib_umem_release(*umem);

	return err;
}

struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, int entries, int vector,
				struct ib_ucontext *context,
				struct ib_udata *udata)
{
	struct mlx4_ib_dev *dev = to_mdev(ibdev);
	struct mlx4_ib_cq *cq;
	struct mlx4_uar *uar;
	int err;

	if (entries < 1 || entries > dev->dev->caps.max_cqes)
		return ERR_PTR(-EINVAL);

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

	entries      = roundup_pow_of_two(entries + 1);
	cq->ibcq.cqe = entries - 1;
	mutex_init(&cq->resize_mutex);
	spin_lock_init(&cq->lock);
	cq->resize_buf = NULL;
	cq->resize_umem = NULL;

	if (context) {
		struct mlx4_ib_create_cq ucmd;

		if (ib_copy_from_udata(&ucmd, udata, sizeof ucmd)) {
			err = -EFAULT;
			goto err_cq;
		}

		err = mlx4_ib_get_cq_umem(dev, context, &cq->buf, &cq->umem,
					  ucmd.buf_addr, entries);
		if (err)
			goto err_cq;

		err = mlx4_ib_db_map_user(to_mucontext(context), ucmd.db_addr,
					  &cq->db);
		if (err)
			goto err_mtt;

		uar = &to_mucontext(context)->uar;
	} else {
		err = mlx4_db_alloc(dev->dev, &cq->db, 1);
		if (err)
			goto err_cq;

		cq->mcq.set_ci_db  = cq->db.db;
		cq->mcq.arm_db     = cq->db.db + 1;
		*cq->mcq.set_ci_db = 0;
		*cq->mcq.arm_db    = 0;

		err = mlx4_ib_alloc_cq_buf(dev, &cq->buf, entries);
		if (err)
			goto err_db;

		uar = &dev->priv_uar;
	}

	err = mlx4_cq_alloc(dev->dev, entries, &cq->buf.mtt, uar,
			    cq->db.dma, &cq->mcq, 0);
	if (err)
		goto err_dbmap;

	cq->mcq.comp  = mlx4_ib_cq_comp;
	cq->mcq.event = mlx4_ib_cq_event;

	if (context)
		if (ib_copy_to_udata(udata, &cq->mcq.cqn, sizeof (__u32))) {
			err = -EFAULT;
			goto err_dbmap;
		}

	return &cq->ibcq;

err_dbmap:
	if (context)
		mlx4_ib_db_unmap_user(to_mucontext(context), &cq->db);

err_mtt:
	mlx4_mtt_cleanup(dev->dev, &cq->buf.mtt);

	if (context)
		ib_umem_release(cq->umem);
	else
		mlx4_ib_free_cq_buf(dev, &cq->buf, cq->ibcq.cqe);

err_db:
	if (!context)
		mlx4_db_free(dev->dev, &cq->db);

err_cq:
	kfree(cq);

	return ERR_PTR(err);
}

static int mlx4_alloc_resize_buf(struct mlx4_ib_dev *dev, struct mlx4_ib_cq *cq,
				  int entries)
{
	int err;

	if (cq->resize_buf)
		return -EBUSY;

	cq->resize_buf = kmalloc(sizeof *cq->resize_buf, GFP_ATOMIC);
	if (!cq->resize_buf)
		return -ENOMEM;

	err = mlx4_ib_alloc_cq_buf(dev, &cq->resize_buf->buf, entries);
	if (err) {
		kfree(cq->resize_buf);
		cq->resize_buf = NULL;
		return err;
	}

	cq->resize_buf->cqe = entries - 1;

	return 0;
}

static int mlx4_alloc_resize_umem(struct mlx4_ib_dev *dev, struct mlx4_ib_cq *cq,
				   int entries, struct ib_udata *udata)
{
	struct mlx4_ib_resize_cq ucmd;
	int err;

	if (cq->resize_umem)
		return -EBUSY;

	if (ib_copy_from_udata(&ucmd, udata, sizeof ucmd))
		return -EFAULT;

	cq->resize_buf = kmalloc(sizeof *cq->resize_buf, GFP_ATOMIC);
	if (!cq->resize_buf)
		return -ENOMEM;

	err = mlx4_ib_get_cq_umem(dev, cq->umem->context, &cq->resize_buf->buf,
				  &cq->resize_umem, ucmd.buf_addr, entries);
	if (err) {
		kfree(cq->resize_buf);
		cq->resize_buf = NULL;
		return err;
	}

	cq->resize_buf->cqe = entries - 1;

	return 0;
}

static int mlx4_ib_get_outstanding_cqes(struct mlx4_ib_cq *cq)
{
	u32 i;

	i = cq->mcq.cons_index;
	while (get_sw_cqe(cq, i & cq->ibcq.cqe))
		++i;

	return i - cq->mcq.cons_index;
}

static void mlx4_ib_cq_resize_copy_cqes(struct mlx4_ib_cq *cq)
{
	struct mlx4_cqe *cqe;
	int i;

	i = cq->mcq.cons_index;
	cqe = get_cqe(cq, i & cq->ibcq.cqe);
	while ((cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) != MLX4_CQE_OPCODE_RESIZE) {
		memcpy(get_cqe_from_buf(&cq->resize_buf->buf,
					(i + 1) & cq->resize_buf->cqe),
			get_cqe(cq, i & cq->ibcq.cqe), sizeof(struct mlx4_cqe));
		cqe = get_cqe(cq, ++i & cq->ibcq.cqe);
	}
	++cq->mcq.cons_index;
}

int mlx4_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata)
{
	struct mlx4_ib_dev *dev = to_mdev(ibcq->device);
	struct mlx4_ib_cq *cq = to_mcq(ibcq);
	int outst_cqe;
	int err;

	mutex_lock(&cq->resize_mutex);

	if (entries < 1 || entries > dev->dev->caps.max_cqes) {
		err = -EINVAL;
		goto out;
	}

	entries = roundup_pow_of_two(entries + 1);
	if (entries == ibcq->cqe + 1) {
		err = 0;
		goto out;
	}

	if (ibcq->uobject) {
		err = mlx4_alloc_resize_umem(dev, cq, entries, udata);
		if (err)
			goto out;
	} else {
		/* Can't be smaller then the number of outstanding CQEs */
		outst_cqe = mlx4_ib_get_outstanding_cqes(cq);
		if (entries < outst_cqe + 1) {
			err = 0;
			goto out;
		}

		err = mlx4_alloc_resize_buf(dev, cq, entries);
		if (err)
			goto out;
	}

	err = mlx4_cq_resize(dev->dev, &cq->mcq, entries, &cq->resize_buf->buf.mtt);
	if (err)
		goto err_buf;

	if (ibcq->uobject) {
		cq->buf      = cq->resize_buf->buf;
		cq->ibcq.cqe = cq->resize_buf->cqe;
		ib_umem_release(cq->umem);
		cq->umem     = cq->resize_umem;

		kfree(cq->resize_buf);
		cq->resize_buf = NULL;
		cq->resize_umem = NULL;
	} else {
		spin_lock_irq(&cq->lock);
		if (cq->resize_buf) {
			mlx4_ib_cq_resize_copy_cqes(cq);
			mlx4_ib_free_cq_buf(dev, &cq->buf, cq->ibcq.cqe);
			cq->buf      = cq->resize_buf->buf;
			cq->ibcq.cqe = cq->resize_buf->cqe;

			kfree(cq->resize_buf);
			cq->resize_buf = NULL;
		}
		spin_unlock_irq(&cq->lock);
	}

	goto out;

err_buf:
	if (!ibcq->uobject)
		mlx4_ib_free_cq_buf(dev, &cq->resize_buf->buf,
				    cq->resize_buf->cqe);

	kfree(cq->resize_buf);
	cq->resize_buf = NULL;

	if (cq->resize_umem) {
		ib_umem_release(cq->resize_umem);
		cq->resize_umem = NULL;
	}

out:
	mutex_unlock(&cq->resize_mutex);
	return err;
}

int mlx4_ib_destroy_cq(struct ib_cq *cq)
{
	struct mlx4_ib_dev *dev = to_mdev(cq->device);
	struct mlx4_ib_cq *mcq = to_mcq(cq);

	mlx4_cq_free(dev->dev, &mcq->mcq);
	mlx4_mtt_cleanup(dev->dev, &mcq->buf.mtt);

	if (cq->uobject) {
		mlx4_ib_db_unmap_user(to_mucontext(cq->uobject->context), &mcq->db);
		ib_umem_release(mcq->umem);
	} else {
		mlx4_ib_free_cq_buf(dev, &mcq->buf, cq->cqe);
		mlx4_db_free(dev->dev, &mcq->db);
	}

	kfree(mcq);

	return 0;
}

static void dump_cqe(void *cqe)
{
	__be32 *buf = cqe;

	printk(KERN_DEBUG "CQE contents %08x %08x %08x %08x %08x %08x %08x %08x\n",
	       be32_to_cpu(buf[0]), be32_to_cpu(buf[1]), be32_to_cpu(buf[2]),
	       be32_to_cpu(buf[3]), be32_to_cpu(buf[4]), be32_to_cpu(buf[5]),
	       be32_to_cpu(buf[6]), be32_to_cpu(buf[7]));
}

static void mlx4_ib_handle_error_cqe(struct mlx4_err_cqe *cqe,
				     struct ib_wc *wc)
{
	if (cqe->syndrome == MLX4_CQE_SYNDROME_LOCAL_QP_OP_ERR) {
		printk(KERN_DEBUG "local QP operation err "
		       "(QPN %06x, WQE index %x, vendor syndrome %02x, "
		       "opcode = %02x)\n",
		       be32_to_cpu(cqe->my_qpn), be16_to_cpu(cqe->wqe_index),
		       cqe->vendor_err_syndrome,
		       cqe->owner_sr_opcode & ~MLX4_CQE_OWNER_MASK);
		dump_cqe(cqe);
	}

	switch (cqe->syndrome) {
	case MLX4_CQE_SYNDROME_LOCAL_LENGTH_ERR:
		wc->status = IB_WC_LOC_LEN_ERR;
		break;
	case MLX4_CQE_SYNDROME_LOCAL_QP_OP_ERR:
		wc->status = IB_WC_LOC_QP_OP_ERR;
		break;
	case MLX4_CQE_SYNDROME_LOCAL_PROT_ERR:
		wc->status = IB_WC_LOC_PROT_ERR;
		break;
	case MLX4_CQE_SYNDROME_WR_FLUSH_ERR:
		wc->status = IB_WC_WR_FLUSH_ERR;
		break;
	case MLX4_CQE_SYNDROME_MW_BIND_ERR:
		wc->status = IB_WC_MW_BIND_ERR;
		break;
	case MLX4_CQE_SYNDROME_BAD_RESP_ERR:
		wc->status = IB_WC_BAD_RESP_ERR;
		break;
	case MLX4_CQE_SYNDROME_LOCAL_ACCESS_ERR:
		wc->status = IB_WC_LOC_ACCESS_ERR;
		break;
	case MLX4_CQE_SYNDROME_REMOTE_INVAL_REQ_ERR:
		wc->status = IB_WC_REM_INV_REQ_ERR;
		break;
	case MLX4_CQE_SYNDROME_REMOTE_ACCESS_ERR:
		wc->status = IB_WC_REM_ACCESS_ERR;
		break;
	case MLX4_CQE_SYNDROME_REMOTE_OP_ERR:
		wc->status = IB_WC_REM_OP_ERR;
		break;
	case MLX4_CQE_SYNDROME_TRANSPORT_RETRY_EXC_ERR:
		wc->status = IB_WC_RETRY_EXC_ERR;
		break;
	case MLX4_CQE_SYNDROME_RNR_RETRY_EXC_ERR:
		wc->status = IB_WC_RNR_RETRY_EXC_ERR;
		break;
	case MLX4_CQE_SYNDROME_REMOTE_ABORTED_ERR:
		wc->status = IB_WC_REM_ABORT_ERR;
		break;
	default:
		wc->status = IB_WC_GENERAL_ERR;
		break;
	}

	wc->vendor_err = cqe->vendor_err_syndrome;
}

static int mlx4_ib_ipoib_csum_ok(__be32 status, __be16 checksum)
{
	return ((status & cpu_to_be32(MLX4_CQE_IPOIB_STATUS_IPV4	|
				      MLX4_CQE_IPOIB_STATUS_IPV4F	|
				      MLX4_CQE_IPOIB_STATUS_IPV4OPT	|
				      MLX4_CQE_IPOIB_STATUS_IPV6	|
				      MLX4_CQE_IPOIB_STATUS_IPOK)) ==
		cpu_to_be32(MLX4_CQE_IPOIB_STATUS_IPV4	|
			    MLX4_CQE_IPOIB_STATUS_IPOK))		&&
		(status & cpu_to_be32(MLX4_CQE_IPOIB_STATUS_UDP	|
				      MLX4_CQE_IPOIB_STATUS_TCP))	&&
		checksum == cpu_to_be16(0xffff);
}

static int mlx4_ib_poll_one(struct mlx4_ib_cq *cq,
			    struct mlx4_ib_qp **cur_qp,
			    struct ib_wc *wc)
{
	struct mlx4_cqe *cqe;
	struct mlx4_qp *mqp;
	struct mlx4_ib_wq *wq;
	struct mlx4_ib_srq *srq;
	int is_send;
	int is_error;
	u32 g_mlpath_rqpn;
	u16 wqe_ctr;

repoll:
	cqe = next_cqe_sw(cq);
	if (!cqe)
		return -EAGAIN;

	++cq->mcq.cons_index;

	/*
	 * Make sure we read CQ entry contents after we've checked the
	 * ownership bit.
	 */
	rmb();

	is_send  = cqe->owner_sr_opcode & MLX4_CQE_IS_SEND_MASK;
	is_error = (cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) ==
		MLX4_CQE_OPCODE_ERROR;

	if (unlikely((cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) == MLX4_OPCODE_NOP &&
		     is_send)) {
		printk(KERN_WARNING "Completion for NOP opcode detected!\n");
		return -EINVAL;
	}

	/* Resize CQ in progress */
	if (unlikely((cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) == MLX4_CQE_OPCODE_RESIZE)) {
		if (cq->resize_buf) {
			struct mlx4_ib_dev *dev = to_mdev(cq->ibcq.device);

			mlx4_ib_free_cq_buf(dev, &cq->buf, cq->ibcq.cqe);
			cq->buf      = cq->resize_buf->buf;
			cq->ibcq.cqe = cq->resize_buf->cqe;

			kfree(cq->resize_buf);
			cq->resize_buf = NULL;
		}

		goto repoll;
	}

	if (!*cur_qp ||
	    (be32_to_cpu(cqe->my_qpn) & 0xffffff) != (*cur_qp)->mqp.qpn) {
		/*
		 * We do not have to take the QP table lock here,
		 * because CQs will be locked while QPs are removed
		 * from the table.
		 */
		mqp = __mlx4_qp_lookup(to_mdev(cq->ibcq.device)->dev,
				       be32_to_cpu(cqe->my_qpn));
		if (unlikely(!mqp)) {
			printk(KERN_WARNING "CQ %06x with entry for unknown QPN %06x\n",
			       cq->mcq.cqn, be32_to_cpu(cqe->my_qpn) & 0xffffff);
			return -EINVAL;
		}

		*cur_qp = to_mibqp(mqp);
	}

	wc->qp = &(*cur_qp)->ibqp;

	if (is_send) {
		wq = &(*cur_qp)->sq;
		if (!(*cur_qp)->sq_signal_bits) {
			wqe_ctr = be16_to_cpu(cqe->wqe_index);
			wq->tail += (u16) (wqe_ctr - (u16) wq->tail);
		}
		wc->wr_id = wq->wrid[wq->tail & (wq->wqe_cnt - 1)];
		++wq->tail;
	} else if ((*cur_qp)->ibqp.srq) {
		srq = to_msrq((*cur_qp)->ibqp.srq);
		wqe_ctr = be16_to_cpu(cqe->wqe_index);
		wc->wr_id = srq->wrid[wqe_ctr];
		mlx4_ib_free_srq_wqe(srq, wqe_ctr);
	} else {
		wq	  = &(*cur_qp)->rq;
		wc->wr_id = wq->wrid[wq->tail & (wq->wqe_cnt - 1)];
		++wq->tail;
	}

	if (unlikely(is_error)) {
		mlx4_ib_handle_error_cqe((struct mlx4_err_cqe *) cqe, wc);
		return 0;
	}

	wc->status = IB_WC_SUCCESS;

	if (is_send) {
		wc->wc_flags = 0;
		switch (cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) {
		case MLX4_OPCODE_RDMA_WRITE_IMM:
			wc->wc_flags |= IB_WC_WITH_IMM;
		case MLX4_OPCODE_RDMA_WRITE:
			wc->opcode    = IB_WC_RDMA_WRITE;
			break;
		case MLX4_OPCODE_SEND_IMM:
			wc->wc_flags |= IB_WC_WITH_IMM;
		case MLX4_OPCODE_SEND:
		case MLX4_OPCODE_SEND_INVAL:
			wc->opcode    = IB_WC_SEND;
			break;
		case MLX4_OPCODE_RDMA_READ:
			wc->opcode    = IB_WC_RDMA_READ;
			wc->byte_len  = be32_to_cpu(cqe->byte_cnt);
			break;
		case MLX4_OPCODE_ATOMIC_CS:
			wc->opcode    = IB_WC_COMP_SWAP;
			wc->byte_len  = 8;
			break;
		case MLX4_OPCODE_ATOMIC_FA:
			wc->opcode    = IB_WC_FETCH_ADD;
			wc->byte_len  = 8;
			break;
		case MLX4_OPCODE_BIND_MW:
			wc->opcode    = IB_WC_BIND_MW;
			break;
		case MLX4_OPCODE_LSO:
			wc->opcode    = IB_WC_LSO;
			break;
		case MLX4_OPCODE_FMR:
			wc->opcode    = IB_WC_FAST_REG_MR;
			break;
		case MLX4_OPCODE_LOCAL_INVAL:
			wc->opcode    = IB_WC_LOCAL_INV;
			break;
		}
	} else {
		wc->byte_len = be32_to_cpu(cqe->byte_cnt);

		switch (cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) {
		case MLX4_RECV_OPCODE_RDMA_WRITE_IMM:
			wc->opcode	= IB_WC_RECV_RDMA_WITH_IMM;
			wc->wc_flags	= IB_WC_WITH_IMM;
			wc->ex.imm_data = cqe->immed_rss_invalid;
			break;
		case MLX4_RECV_OPCODE_SEND_INVAL:
			wc->opcode	= IB_WC_RECV;
			wc->wc_flags	= IB_WC_WITH_INVALIDATE;
			wc->ex.invalidate_rkey = be32_to_cpu(cqe->immed_rss_invalid);
			break;
		case MLX4_RECV_OPCODE_SEND:
			wc->opcode   = IB_WC_RECV;
			wc->wc_flags = 0;
			break;
		case MLX4_RECV_OPCODE_SEND_IMM:
			wc->opcode	= IB_WC_RECV;
			wc->wc_flags	= IB_WC_WITH_IMM;
			wc->ex.imm_data = cqe->immed_rss_invalid;
			break;
		}

		wc->slid	   = be16_to_cpu(cqe->rlid);
		wc->sl		   = cqe->sl >> 4;
		g_mlpath_rqpn	   = be32_to_cpu(cqe->g_mlpath_rqpn);
		wc->src_qp	   = g_mlpath_rqpn & 0xffffff;
		wc->dlid_path_bits = (g_mlpath_rqpn >> 24) & 0x7f;
		wc->wc_flags	  |= g_mlpath_rqpn & 0x80000000 ? IB_WC_GRH : 0;
		wc->pkey_index     = be32_to_cpu(cqe->immed_rss_invalid) & 0x7f;
		wc->csum_ok	   = mlx4_ib_ipoib_csum_ok(cqe->ipoib_status,
							   cqe->checksum);
	}

	return 0;
}

int mlx4_ib_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
{
	struct mlx4_ib_cq *cq = to_mcq(ibcq);
	struct mlx4_ib_qp *cur_qp = NULL;
	unsigned long flags;
	int npolled;
	int err = 0;

	spin_lock_irqsave(&cq->lock, flags);

	for (npolled = 0; npolled < num_entries; ++npolled) {
		err = mlx4_ib_poll_one(cq, &cur_qp, wc + npolled);
		if (err)
			break;
	}

	if (npolled)
		mlx4_cq_set_ci(&cq->mcq);

	spin_unlock_irqrestore(&cq->lock, flags);

	if (err == 0 || err == -EAGAIN)
		return npolled;
	else
		return err;
}

int mlx4_ib_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags)
{
	mlx4_cq_arm(&to_mcq(ibcq)->mcq,
		    (flags & IB_CQ_SOLICITED_MASK) == IB_CQ_SOLICITED ?
		    MLX4_CQ_DB_REQ_NOT_SOL : MLX4_CQ_DB_REQ_NOT,
		    to_mdev(ibcq->device)->uar_map,
		    MLX4_GET_DOORBELL_LOCK(&to_mdev(ibcq->device)->uar_lock));

	return 0;
}

void __mlx4_ib_cq_clean(struct mlx4_ib_cq *cq, u32 qpn, struct mlx4_ib_srq *srq)
{
	u32 prod_index;
	int nfreed = 0;
	struct mlx4_cqe *cqe, *dest;
	u8 owner_bit;

	/*
	 * First we need to find the current producer index, so we
	 * know where to start cleaning from.  It doesn't matter if HW
	 * adds new entries after this loop -- the QP we're worried
	 * about is already in RESET, so the new entries won't come
	 * from our QP and therefore don't need to be checked.
	 */
	for (prod_index = cq->mcq.cons_index; get_sw_cqe(cq, prod_index); ++prod_index)
		if (prod_index == cq->mcq.cons_index + cq->ibcq.cqe)
			break;

	/*
	 * Now sweep backwards through the CQ, removing CQ entries
	 * that match our QP by copying older entries on top of them.
	 */
	while ((int) --prod_index - (int) cq->mcq.cons_index >= 0) {
		cqe = get_cqe(cq, prod_index & cq->ibcq.cqe);
		if ((be32_to_cpu(cqe->my_qpn) & 0xffffff) == qpn) {
			if (srq && !(cqe->owner_sr_opcode & MLX4_CQE_IS_SEND_MASK))
				mlx4_ib_free_srq_wqe(srq, be16_to_cpu(cqe->wqe_index));
			++nfreed;
		} else if (nfreed) {
			dest = get_cqe(cq, (prod_index + nfreed) & cq->ibcq.cqe);
			owner_bit = dest->owner_sr_opcode & MLX4_CQE_OWNER_MASK;
			memcpy(dest, cqe, sizeof *cqe);
			dest->owner_sr_opcode = owner_bit |
				(dest->owner_sr_opcode & ~MLX4_CQE_OWNER_MASK);
		}
	}

	if (nfreed) {
		cq->mcq.cons_index += nfreed;
		/*
		 * Make sure update of buffer contents is done before
		 * updating consumer index.
		 */
		wmb();
		mlx4_cq_set_ci(&cq->mcq);
	}
}

void mlx4_ib_cq_clean(struct mlx4_ib_cq *cq, u32 qpn, struct mlx4_ib_srq *srq)
{
	spin_lock_irq(&cq->lock);
	__mlx4_ib_cq_clean(cq, qpn, srq);
	spin_unlock_irq(&cq->lock);
}