summaryrefslogtreecommitdiffstats
path: root/drivers/infiniband/hw/cxgb4/device.c
blob: cb4ecd7837005c823ca06841f5d3c2ac19510d6c (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
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
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
/*
 * Copyright (c) 2009-2010 Chelsio, 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/module.h>
#include <linux/moduleparam.h>
#include <linux/debugfs.h>
#include <linux/vmalloc.h>

#include <rdma/ib_verbs.h>

#include "iw_cxgb4.h"

#define DRV_VERSION "0.1"

MODULE_AUTHOR("Steve Wise");
MODULE_DESCRIPTION("Chelsio T4 RDMA Driver");
MODULE_LICENSE("Dual BSD/GPL");
MODULE_VERSION(DRV_VERSION);

struct uld_ctx {
	struct list_head entry;
	struct cxgb4_lld_info lldi;
	struct c4iw_dev *dev;
};

static LIST_HEAD(uld_ctx_list);
static DEFINE_MUTEX(dev_mutex);

static struct dentry *c4iw_debugfs_root;

struct c4iw_debugfs_data {
	struct c4iw_dev *devp;
	char *buf;
	int bufsize;
	int pos;
};

static int count_idrs(int id, void *p, void *data)
{
	int *countp = data;

	*countp = *countp + 1;
	return 0;
}

static ssize_t debugfs_read(struct file *file, char __user *buf, size_t count,
			    loff_t *ppos)
{
	struct c4iw_debugfs_data *d = file->private_data;

	return simple_read_from_buffer(buf, count, ppos, d->buf, d->pos);
}

static int dump_qp(int id, void *p, void *data)
{
	struct c4iw_qp *qp = p;
	struct c4iw_debugfs_data *qpd = data;
	int space;
	int cc;

	if (id != qp->wq.sq.qid)
		return 0;

	space = qpd->bufsize - qpd->pos - 1;
	if (space == 0)
		return 1;

	if (qp->ep)
		cc = snprintf(qpd->buf + qpd->pos, space,
			     "qp sq id %u rq id %u state %u onchip %u "
			     "ep tid %u state %u %pI4:%u->%pI4:%u\n",
			     qp->wq.sq.qid, qp->wq.rq.qid, (int)qp->attr.state,
			     qp->wq.sq.flags & T4_SQ_ONCHIP,
			     qp->ep->hwtid, (int)qp->ep->com.state,
			     &qp->ep->com.local_addr.sin_addr.s_addr,
			     ntohs(qp->ep->com.local_addr.sin_port),
			     &qp->ep->com.remote_addr.sin_addr.s_addr,
			     ntohs(qp->ep->com.remote_addr.sin_port));
	else
		cc = snprintf(qpd->buf + qpd->pos, space,
			     "qp sq id %u rq id %u state %u onchip %u\n",
			      qp->wq.sq.qid, qp->wq.rq.qid,
			      (int)qp->attr.state,
			      qp->wq.sq.flags & T4_SQ_ONCHIP);
	if (cc < space)
		qpd->pos += cc;
	return 0;
}

static int qp_release(struct inode *inode, struct file *file)
{
	struct c4iw_debugfs_data *qpd = file->private_data;
	if (!qpd) {
		printk(KERN_INFO "%s null qpd?\n", __func__);
		return 0;
	}
	vfree(qpd->buf);
	kfree(qpd);
	return 0;
}

static int qp_open(struct inode *inode, struct file *file)
{
	struct c4iw_debugfs_data *qpd;
	int ret = 0;
	int count = 1;

	qpd = kmalloc(sizeof *qpd, GFP_KERNEL);
	if (!qpd) {
		ret = -ENOMEM;
		goto out;
	}
	qpd->devp = inode->i_private;
	qpd->pos = 0;

	spin_lock_irq(&qpd->devp->lock);
	idr_for_each(&qpd->devp->qpidr, count_idrs, &count);
	spin_unlock_irq(&qpd->devp->lock);

	qpd->bufsize = count * 128;
	qpd->buf = vmalloc(qpd->bufsize);
	if (!qpd->buf) {
		ret = -ENOMEM;
		goto err1;
	}

	spin_lock_irq(&qpd->devp->lock);
	idr_for_each(&qpd->devp->qpidr, dump_qp, qpd);
	spin_unlock_irq(&qpd->devp->lock);

	qpd->buf[qpd->pos++] = 0;
	file->private_data = qpd;
	goto out;
err1:
	kfree(qpd);
out:
	return ret;
}

static const struct file_operations qp_debugfs_fops = {
	.owner   = THIS_MODULE,
	.open    = qp_open,
	.release = qp_release,
	.read    = debugfs_read,
	.llseek  = default_llseek,
};

static int dump_stag(int id, void *p, void *data)
{
	struct c4iw_debugfs_data *stagd = data;
	int space;
	int cc;

	space = stagd->bufsize - stagd->pos - 1;
	if (space == 0)
		return 1;

	cc = snprintf(stagd->buf + stagd->pos, space, "0x%x\n", id<<8);
	if (cc < space)
		stagd->pos += cc;
	return 0;
}

static int stag_release(struct inode *inode, struct file *file)
{
	struct c4iw_debugfs_data *stagd = file->private_data;
	if (!stagd) {
		printk(KERN_INFO "%s null stagd?\n", __func__);
		return 0;
	}
	kfree(stagd->buf);
	kfree(stagd);
	return 0;
}

static int stag_open(struct inode *inode, struct file *file)
{
	struct c4iw_debugfs_data *stagd;
	int ret = 0;
	int count = 1;

	stagd = kmalloc(sizeof *stagd, GFP_KERNEL);
	if (!stagd) {
		ret = -ENOMEM;
		goto out;
	}
	stagd->devp = inode->i_private;
	stagd->pos = 0;

	spin_lock_irq(&stagd->devp->lock);
	idr_for_each(&stagd->devp->mmidr, count_idrs, &count);
	spin_unlock_irq(&stagd->devp->lock);

	stagd->bufsize = count * sizeof("0x12345678\n");
	stagd->buf = kmalloc(stagd->bufsize, GFP_KERNEL);
	if (!stagd->buf) {
		ret = -ENOMEM;
		goto err1;
	}

	spin_lock_irq(&stagd->devp->lock);
	idr_for_each(&stagd->devp->mmidr, dump_stag, stagd);
	spin_unlock_irq(&stagd->devp->lock);

	stagd->buf[stagd->pos++] = 0;
	file->private_data = stagd;
	goto out;
err1:
	kfree(stagd);
out:
	return ret;
}

static const struct file_operations stag_debugfs_fops = {
	.owner   = THIS_MODULE,
	.open    = stag_open,
	.release = stag_release,
	.read    = debugfs_read,
	.llseek  = default_llseek,
};

static char *db_state_str[] = {"NORMAL", "FLOW_CONTROL", "RECOVERY"};

static int stats_show(struct seq_file *seq, void *v)
{
	struct c4iw_dev *dev = seq->private;

	seq_printf(seq, "   Object: %10s %10s %10s %10s\n", "Total", "Current",
		   "Max", "Fail");
	seq_printf(seq, "     PDID: %10llu %10llu %10llu %10llu\n",
			dev->rdev.stats.pd.total, dev->rdev.stats.pd.cur,
			dev->rdev.stats.pd.max, dev->rdev.stats.pd.fail);
	seq_printf(seq, "      QID: %10llu %10llu %10llu %10llu\n",
			dev->rdev.stats.qid.total, dev->rdev.stats.qid.cur,
			dev->rdev.stats.qid.max, dev->rdev.stats.qid.fail);
	seq_printf(seq, "   TPTMEM: %10llu %10llu %10llu %10llu\n",
			dev->rdev.stats.stag.total, dev->rdev.stats.stag.cur,
			dev->rdev.stats.stag.max, dev->rdev.stats.stag.fail);
	seq_printf(seq, "   PBLMEM: %10llu %10llu %10llu %10llu\n",
			dev->rdev.stats.pbl.total, dev->rdev.stats.pbl.cur,
			dev->rdev.stats.pbl.max, dev->rdev.stats.pbl.fail);
	seq_printf(seq, "   RQTMEM: %10llu %10llu %10llu %10llu\n",
			dev->rdev.stats.rqt.total, dev->rdev.stats.rqt.cur,
			dev->rdev.stats.rqt.max, dev->rdev.stats.rqt.fail);
	seq_printf(seq, "  OCQPMEM: %10llu %10llu %10llu %10llu\n",
			dev->rdev.stats.ocqp.total, dev->rdev.stats.ocqp.cur,
			dev->rdev.stats.ocqp.max, dev->rdev.stats.ocqp.fail);
	seq_printf(seq, "  DB FULL: %10llu\n", dev->rdev.stats.db_full);
	seq_printf(seq, " DB EMPTY: %10llu\n", dev->rdev.stats.db_empty);
	seq_printf(seq, "  DB DROP: %10llu\n", dev->rdev.stats.db_drop);
	seq_printf(seq, " DB State: %s Transitions %llu\n",
		   db_state_str[dev->db_state],
		   dev->rdev.stats.db_state_transitions);
	return 0;
}

static int stats_open(struct inode *inode, struct file *file)
{
	return single_open(file, stats_show, inode->i_private);
}

static ssize_t stats_clear(struct file *file, const char __user *buf,
		size_t count, loff_t *pos)
{
	struct c4iw_dev *dev = ((struct seq_file *)file->private_data)->private;

	mutex_lock(&dev->rdev.stats.lock);
	dev->rdev.stats.pd.max = 0;
	dev->rdev.stats.pd.fail = 0;
	dev->rdev.stats.qid.max = 0;
	dev->rdev.stats.qid.fail = 0;
	dev->rdev.stats.stag.max = 0;
	dev->rdev.stats.stag.fail = 0;
	dev->rdev.stats.pbl.max = 0;
	dev->rdev.stats.pbl.fail = 0;
	dev->rdev.stats.rqt.max = 0;
	dev->rdev.stats.rqt.fail = 0;
	dev->rdev.stats.ocqp.max = 0;
	dev->rdev.stats.ocqp.fail = 0;
	dev->rdev.stats.db_full = 0;
	dev->rdev.stats.db_empty = 0;
	dev->rdev.stats.db_drop = 0;
	dev->rdev.stats.db_state_transitions = 0;
	mutex_unlock(&dev->rdev.stats.lock);
	return count;
}

static const struct file_operations stats_debugfs_fops = {
	.owner   = THIS_MODULE,
	.open    = stats_open,
	.release = single_release,
	.read    = seq_read,
	.llseek  = seq_lseek,
	.write   = stats_clear,
};

static int setup_debugfs(struct c4iw_dev *devp)
{
	struct dentry *de;

	if (!devp->debugfs_root)
		return -1;

	de = debugfs_create_file("qps", S_IWUSR, devp->debugfs_root,
				 (void *)devp, &qp_debugfs_fops);
	if (de && de->d_inode)
		de->d_inode->i_size = 4096;

	de = debugfs_create_file("stags", S_IWUSR, devp->debugfs_root,
				 (void *)devp, &stag_debugfs_fops);
	if (de && de->d_inode)
		de->d_inode->i_size = 4096;

	de = debugfs_create_file("stats", S_IWUSR, devp->debugfs_root,
			(void *)devp, &stats_debugfs_fops);
	if (de && de->d_inode)
		de->d_inode->i_size = 4096;

	return 0;
}

void c4iw_release_dev_ucontext(struct c4iw_rdev *rdev,
			       struct c4iw_dev_ucontext *uctx)
{
	struct list_head *pos, *nxt;
	struct c4iw_qid_list *entry;

	mutex_lock(&uctx->lock);
	list_for_each_safe(pos, nxt, &uctx->qpids) {
		entry = list_entry(pos, struct c4iw_qid_list, entry);
		list_del_init(&entry->entry);
		if (!(entry->qid & rdev->qpmask)) {
			c4iw_put_resource(&rdev->resource.qid_table,
					  entry->qid);
			mutex_lock(&rdev->stats.lock);
			rdev->stats.qid.cur -= rdev->qpmask + 1;
			mutex_unlock(&rdev->stats.lock);
		}
		kfree(entry);
	}

	list_for_each_safe(pos, nxt, &uctx->qpids) {
		entry = list_entry(pos, struct c4iw_qid_list, entry);
		list_del_init(&entry->entry);
		kfree(entry);
	}
	mutex_unlock(&uctx->lock);
}

void c4iw_init_dev_ucontext(struct c4iw_rdev *rdev,
			    struct c4iw_dev_ucontext *uctx)
{
	INIT_LIST_HEAD(&uctx->qpids);
	INIT_LIST_HEAD(&uctx->cqids);
	mutex_init(&uctx->lock);
}

/* Caller takes care of locking if needed */
static int c4iw_rdev_open(struct c4iw_rdev *rdev)
{
	int err;

	c4iw_init_dev_ucontext(rdev, &rdev->uctx);

	/*
	 * qpshift is the number of bits to shift the qpid left in order
	 * to get the correct address of the doorbell for that qp.
	 */
	rdev->qpshift = PAGE_SHIFT - ilog2(rdev->lldi.udb_density);
	rdev->qpmask = rdev->lldi.udb_density - 1;
	rdev->cqshift = PAGE_SHIFT - ilog2(rdev->lldi.ucq_density);
	rdev->cqmask = rdev->lldi.ucq_density - 1;
	PDBG("%s dev %s stag start 0x%0x size 0x%0x num stags %d "
	     "pbl start 0x%0x size 0x%0x rq start 0x%0x size 0x%0x "
	     "qp qid start %u size %u cq qid start %u size %u\n",
	     __func__, pci_name(rdev->lldi.pdev), rdev->lldi.vr->stag.start,
	     rdev->lldi.vr->stag.size, c4iw_num_stags(rdev),
	     rdev->lldi.vr->pbl.start,
	     rdev->lldi.vr->pbl.size, rdev->lldi.vr->rq.start,
	     rdev->lldi.vr->rq.size,
	     rdev->lldi.vr->qp.start,
	     rdev->lldi.vr->qp.size,
	     rdev->lldi.vr->cq.start,
	     rdev->lldi.vr->cq.size);
	PDBG("udb len 0x%x udb base %p db_reg %p gts_reg %p qpshift %lu "
	     "qpmask 0x%x cqshift %lu cqmask 0x%x\n",
	     (unsigned)pci_resource_len(rdev->lldi.pdev, 2),
	     (void *)pci_resource_start(rdev->lldi.pdev, 2),
	     rdev->lldi.db_reg,
	     rdev->lldi.gts_reg,
	     rdev->qpshift, rdev->qpmask,
	     rdev->cqshift, rdev->cqmask);

	if (c4iw_num_stags(rdev) == 0) {
		err = -EINVAL;
		goto err1;
	}

	rdev->stats.pd.total = T4_MAX_NUM_PD;
	rdev->stats.stag.total = rdev->lldi.vr->stag.size;
	rdev->stats.pbl.total = rdev->lldi.vr->pbl.size;
	rdev->stats.rqt.total = rdev->lldi.vr->rq.size;
	rdev->stats.ocqp.total = rdev->lldi.vr->ocq.size;
	rdev->stats.qid.total = rdev->lldi.vr->qp.size;

	err = c4iw_init_resource(rdev, c4iw_num_stags(rdev), T4_MAX_NUM_PD);
	if (err) {
		printk(KERN_ERR MOD "error %d initializing resources\n", err);
		goto err1;
	}
	err = c4iw_pblpool_create(rdev);
	if (err) {
		printk(KERN_ERR MOD "error %d initializing pbl pool\n", err);
		goto err2;
	}
	err = c4iw_rqtpool_create(rdev);
	if (err) {
		printk(KERN_ERR MOD "error %d initializing rqt pool\n", err);
		goto err3;
	}
	err = c4iw_ocqp_pool_create(rdev);
	if (err) {
		printk(KERN_ERR MOD "error %d initializing ocqp pool\n", err);
		goto err4;
	}
	return 0;
err4:
	c4iw_rqtpool_destroy(rdev);
err3:
	c4iw_pblpool_destroy(rdev);
err2:
	c4iw_destroy_resource(&rdev->resource);
err1:
	return err;
}

static void c4iw_rdev_close(struct c4iw_rdev *rdev)
{
	c4iw_pblpool_destroy(rdev);
	c4iw_rqtpool_destroy(rdev);
	c4iw_destroy_resource(&rdev->resource);
}

static void c4iw_dealloc(struct uld_ctx *ctx)
{
	c4iw_rdev_close(&ctx->dev->rdev);
	idr_destroy(&ctx->dev->cqidr);
	idr_destroy(&ctx->dev->qpidr);
	idr_destroy(&ctx->dev->mmidr);
	iounmap(ctx->dev->rdev.oc_mw_kva);
	ib_dealloc_device(&ctx->dev->ibdev);
	ctx->dev = NULL;
}

static void c4iw_remove(struct uld_ctx *ctx)
{
	PDBG("%s c4iw_dev %p\n", __func__,  ctx->dev);
	c4iw_unregister_device(ctx->dev);
	c4iw_dealloc(ctx);
}

static int rdma_supported(const struct cxgb4_lld_info *infop)
{
	return infop->vr->stag.size > 0 && infop->vr->pbl.size > 0 &&
	       infop->vr->rq.size > 0 && infop->vr->qp.size > 0 &&
	       infop->vr->cq.size > 0 && infop->vr->ocq.size > 0;
}

static struct c4iw_dev *c4iw_alloc(const struct cxgb4_lld_info *infop)
{
	struct c4iw_dev *devp;
	int ret;

	if (!rdma_supported(infop)) {
		printk(KERN_INFO MOD "%s: RDMA not supported on this device.\n",
		       pci_name(infop->pdev));
		return ERR_PTR(-ENOSYS);
	}
	devp = (struct c4iw_dev *)ib_alloc_device(sizeof(*devp));
	if (!devp) {
		printk(KERN_ERR MOD "Cannot allocate ib device\n");
		return ERR_PTR(-ENOMEM);
	}
	devp->rdev.lldi = *infop;

	devp->rdev.oc_mw_pa = pci_resource_start(devp->rdev.lldi.pdev, 2) +
		(pci_resource_len(devp->rdev.lldi.pdev, 2) -
		 roundup_pow_of_two(devp->rdev.lldi.vr->ocq.size));
	devp->rdev.oc_mw_kva = ioremap_wc(devp->rdev.oc_mw_pa,
					       devp->rdev.lldi.vr->ocq.size);

	PDBG(KERN_INFO MOD "ocq memory: "
	       "hw_start 0x%x size %u mw_pa 0x%lx mw_kva %p\n",
	       devp->rdev.lldi.vr->ocq.start, devp->rdev.lldi.vr->ocq.size,
	       devp->rdev.oc_mw_pa, devp->rdev.oc_mw_kva);

	ret = c4iw_rdev_open(&devp->rdev);
	if (ret) {
		printk(KERN_ERR MOD "Unable to open CXIO rdev err %d\n", ret);
		ib_dealloc_device(&devp->ibdev);
		return ERR_PTR(ret);
	}

	idr_init(&devp->cqidr);
	idr_init(&devp->qpidr);
	idr_init(&devp->mmidr);
	spin_lock_init(&devp->lock);
	mutex_init(&devp->rdev.stats.lock);
	mutex_init(&devp->db_mutex);

	if (c4iw_debugfs_root) {
		devp->debugfs_root = debugfs_create_dir(
					pci_name(devp->rdev.lldi.pdev),
					c4iw_debugfs_root);
		setup_debugfs(devp);
	}
	return devp;
}

static void *c4iw_uld_add(const struct cxgb4_lld_info *infop)
{
	struct uld_ctx *ctx;
	static int vers_printed;
	int i;

	if (!vers_printed++)
		printk(KERN_INFO MOD "Chelsio T4 RDMA Driver - version %s\n",
		       DRV_VERSION);

	ctx = kzalloc(sizeof *ctx, GFP_KERNEL);
	if (!ctx) {
		ctx = ERR_PTR(-ENOMEM);
		goto out;
	}
	ctx->lldi = *infop;

	PDBG("%s found device %s nchan %u nrxq %u ntxq %u nports %u\n",
	     __func__, pci_name(ctx->lldi.pdev),
	     ctx->lldi.nchan, ctx->lldi.nrxq,
	     ctx->lldi.ntxq, ctx->lldi.nports);

	mutex_lock(&dev_mutex);
	list_add_tail(&ctx->entry, &uld_ctx_list);
	mutex_unlock(&dev_mutex);

	for (i = 0; i < ctx->lldi.nrxq; i++)
		PDBG("rxqid[%u] %u\n", i, ctx->lldi.rxq_ids[i]);
out:
	return ctx;
}

static int c4iw_uld_rx_handler(void *handle, const __be64 *rsp,
			const struct pkt_gl *gl)
{
	struct uld_ctx *ctx = handle;
	struct c4iw_dev *dev = ctx->dev;
	struct sk_buff *skb;
	const struct cpl_act_establish *rpl;
	unsigned int opcode;

	if (gl == NULL) {
		/* omit RSS and rsp_ctrl at end of descriptor */
		unsigned int len = 64 - sizeof(struct rsp_ctrl) - 8;

		skb = alloc_skb(256, GFP_ATOMIC);
		if (!skb)
			goto nomem;
		__skb_put(skb, len);
		skb_copy_to_linear_data(skb, &rsp[1], len);
	} else if (gl == CXGB4_MSG_AN) {
		const struct rsp_ctrl *rc = (void *)rsp;

		u32 qid = be32_to_cpu(rc->pldbuflen_qid);
		c4iw_ev_handler(dev, qid);
		return 0;
	} else {
		skb = cxgb4_pktgl_to_skb(gl, 128, 128);
		if (unlikely(!skb))
			goto nomem;
	}

	rpl = cplhdr(skb);
	opcode = rpl->ot.opcode;

	if (c4iw_handlers[opcode])
		c4iw_handlers[opcode](dev, skb);
	else
		printk(KERN_INFO "%s no handler opcode 0x%x...\n", __func__,
		       opcode);

	return 0;
nomem:
	return -1;
}

static int c4iw_uld_state_change(void *handle, enum cxgb4_state new_state)
{
	struct uld_ctx *ctx = handle;

	PDBG("%s new_state %u\n", __func__, new_state);
	switch (new_state) {
	case CXGB4_STATE_UP:
		printk(KERN_INFO MOD "%s: Up\n", pci_name(ctx->lldi.pdev));
		if (!ctx->dev) {
			int ret;

			ctx->dev = c4iw_alloc(&ctx->lldi);
			if (IS_ERR(ctx->dev)) {
				printk(KERN_ERR MOD
				       "%s: initialization failed: %ld\n",
				       pci_name(ctx->lldi.pdev),
				       PTR_ERR(ctx->dev));
				ctx->dev = NULL;
				break;
			}
			ret = c4iw_register_device(ctx->dev);
			if (ret) {
				printk(KERN_ERR MOD
				       "%s: RDMA registration failed: %d\n",
				       pci_name(ctx->lldi.pdev), ret);
				c4iw_dealloc(ctx);
			}
		}
		break;
	case CXGB4_STATE_DOWN:
		printk(KERN_INFO MOD "%s: Down\n",
		       pci_name(ctx->lldi.pdev));
		if (ctx->dev)
			c4iw_remove(ctx);
		break;
	case CXGB4_STATE_START_RECOVERY:
		printk(KERN_INFO MOD "%s: Fatal Error\n",
		       pci_name(ctx->lldi.pdev));
		if (ctx->dev) {
			struct ib_event event;

			ctx->dev->rdev.flags |= T4_FATAL_ERROR;
			memset(&event, 0, sizeof event);
			event.event  = IB_EVENT_DEVICE_FATAL;
			event.device = &ctx->dev->ibdev;
			ib_dispatch_event(&event);
			c4iw_remove(ctx);
		}
		break;
	case CXGB4_STATE_DETACH:
		printk(KERN_INFO MOD "%s: Detach\n",
		       pci_name(ctx->lldi.pdev));
		if (ctx->dev)
			c4iw_remove(ctx);
		break;
	}
	return 0;
}

static int disable_qp_db(int id, void *p, void *data)
{
	struct c4iw_qp *qp = p;

	t4_disable_wq_db(&qp->wq);
	return 0;
}

static void stop_queues(struct uld_ctx *ctx)
{
	spin_lock_irq(&ctx->dev->lock);
	if (ctx->dev->db_state == NORMAL) {
		ctx->dev->rdev.stats.db_state_transitions++;
		ctx->dev->db_state = FLOW_CONTROL;
		idr_for_each(&ctx->dev->qpidr, disable_qp_db, NULL);
	}
	spin_unlock_irq(&ctx->dev->lock);
}

static int enable_qp_db(int id, void *p, void *data)
{
	struct c4iw_qp *qp = p;

	t4_enable_wq_db(&qp->wq);
	return 0;
}

static void resume_queues(struct uld_ctx *ctx)
{
	spin_lock_irq(&ctx->dev->lock);
	if (ctx->dev->qpcnt <= db_fc_threshold &&
	    ctx->dev->db_state == FLOW_CONTROL) {
		ctx->dev->db_state = NORMAL;
		ctx->dev->rdev.stats.db_state_transitions++;
		idr_for_each(&ctx->dev->qpidr, enable_qp_db, NULL);
	}
	spin_unlock_irq(&ctx->dev->lock);
}

struct qp_list {
	unsigned idx;
	struct c4iw_qp **qps;
};

static int add_and_ref_qp(int id, void *p, void *data)
{
	struct qp_list *qp_listp = data;
	struct c4iw_qp *qp = p;

	c4iw_qp_add_ref(&qp->ibqp);
	qp_listp->qps[qp_listp->idx++] = qp;
	return 0;
}

static int count_qps(int id, void *p, void *data)
{
	unsigned *countp = data;
	(*countp)++;
	return 0;
}

static void deref_qps(struct qp_list qp_list)
{
	int idx;

	for (idx = 0; idx < qp_list.idx; idx++)
		c4iw_qp_rem_ref(&qp_list.qps[idx]->ibqp);
}

static void recover_lost_dbs(struct uld_ctx *ctx, struct qp_list *qp_list)
{
	int idx;
	int ret;

	for (idx = 0; idx < qp_list->idx; idx++) {
		struct c4iw_qp *qp = qp_list->qps[idx];

		ret = cxgb4_sync_txq_pidx(qp->rhp->rdev.lldi.ports[0],
					  qp->wq.sq.qid,
					  t4_sq_host_wq_pidx(&qp->wq),
					  t4_sq_wq_size(&qp->wq));
		if (ret) {
			printk(KERN_ERR MOD "%s: Fatal error - "
			       "DB overflow recovery failed - "
			       "error syncing SQ qid %u\n",
			       pci_name(ctx->lldi.pdev), qp->wq.sq.qid);
			return;
		}

		ret = cxgb4_sync_txq_pidx(qp->rhp->rdev.lldi.ports[0],
					  qp->wq.rq.qid,
					  t4_rq_host_wq_pidx(&qp->wq),
					  t4_rq_wq_size(&qp->wq));

		if (ret) {
			printk(KERN_ERR MOD "%s: Fatal error - "
			       "DB overflow recovery failed - "
			       "error syncing RQ qid %u\n",
			       pci_name(ctx->lldi.pdev), qp->wq.rq.qid);
			return;
		}

		/* Wait for the dbfifo to drain */
		while (cxgb4_dbfifo_count(qp->rhp->rdev.lldi.ports[0], 1) > 0) {
			set_current_state(TASK_UNINTERRUPTIBLE);
			schedule_timeout(usecs_to_jiffies(10));
		}
	}
}

static void recover_queues(struct uld_ctx *ctx)
{
	int count = 0;
	struct qp_list qp_list;
	int ret;

	/* lock out kernel db ringers */
	mutex_lock(&ctx->dev->db_mutex);

	/* put all queues in to recovery mode */
	spin_lock_irq(&ctx->dev->lock);
	ctx->dev->db_state = RECOVERY;
	ctx->dev->rdev.stats.db_state_transitions++;
	idr_for_each(&ctx->dev->qpidr, disable_qp_db, NULL);
	spin_unlock_irq(&ctx->dev->lock);

	/* slow everybody down */
	set_current_state(TASK_UNINTERRUPTIBLE);
	schedule_timeout(usecs_to_jiffies(1000));

	/* Wait for the dbfifo to completely drain. */
	while (cxgb4_dbfifo_count(ctx->dev->rdev.lldi.ports[0], 1) > 0) {
		set_current_state(TASK_UNINTERRUPTIBLE);
		schedule_timeout(usecs_to_jiffies(10));
	}

	/* flush the SGE contexts */
	ret = cxgb4_flush_eq_cache(ctx->dev->rdev.lldi.ports[0]);
	if (ret) {
		printk(KERN_ERR MOD "%s: Fatal error - DB overflow recovery failed\n",
		       pci_name(ctx->lldi.pdev));
		goto out;
	}

	/* Count active queues so we can build a list of queues to recover */
	spin_lock_irq(&ctx->dev->lock);
	idr_for_each(&ctx->dev->qpidr, count_qps, &count);

	qp_list.qps = kzalloc(count * sizeof *qp_list.qps, GFP_ATOMIC);
	if (!qp_list.qps) {
		printk(KERN_ERR MOD "%s: Fatal error - DB overflow recovery failed\n",
		       pci_name(ctx->lldi.pdev));
		spin_unlock_irq(&ctx->dev->lock);
		goto out;
	}
	qp_list.idx = 0;

	/* add and ref each qp so it doesn't get freed */
	idr_for_each(&ctx->dev->qpidr, add_and_ref_qp, &qp_list);

	spin_unlock_irq(&ctx->dev->lock);

	/* now traverse the list in a safe context to recover the db state*/
	recover_lost_dbs(ctx, &qp_list);

	/* we're almost done!  deref the qps and clean up */
	deref_qps(qp_list);
	kfree(qp_list.qps);

	/* Wait for the dbfifo to completely drain again */
	while (cxgb4_dbfifo_count(ctx->dev->rdev.lldi.ports[0], 1) > 0) {
		set_current_state(TASK_UNINTERRUPTIBLE);
		schedule_timeout(usecs_to_jiffies(10));
	}

	/* resume the queues */
	spin_lock_irq(&ctx->dev->lock);
	if (ctx->dev->qpcnt > db_fc_threshold)
		ctx->dev->db_state = FLOW_CONTROL;
	else {
		ctx->dev->db_state = NORMAL;
		idr_for_each(&ctx->dev->qpidr, enable_qp_db, NULL);
	}
	ctx->dev->rdev.stats.db_state_transitions++;
	spin_unlock_irq(&ctx->dev->lock);

out:
	/* start up kernel db ringers again */
	mutex_unlock(&ctx->dev->db_mutex);
}

static int c4iw_uld_control(void *handle, enum cxgb4_control control, ...)
{
	struct uld_ctx *ctx = handle;

	switch (control) {
	case CXGB4_CONTROL_DB_FULL:
		stop_queues(ctx);
		mutex_lock(&ctx->dev->rdev.stats.lock);
		ctx->dev->rdev.stats.db_full++;
		mutex_unlock(&ctx->dev->rdev.stats.lock);
		break;
	case CXGB4_CONTROL_DB_EMPTY:
		resume_queues(ctx);
		mutex_lock(&ctx->dev->rdev.stats.lock);
		ctx->dev->rdev.stats.db_empty++;
		mutex_unlock(&ctx->dev->rdev.stats.lock);
		break;
	case CXGB4_CONTROL_DB_DROP:
		recover_queues(ctx);
		mutex_lock(&ctx->dev->rdev.stats.lock);
		ctx->dev->rdev.stats.db_drop++;
		mutex_unlock(&ctx->dev->rdev.stats.lock);
		break;
	default:
		printk(KERN_WARNING MOD "%s: unknown control cmd %u\n",
		       pci_name(ctx->lldi.pdev), control);
		break;
	}
	return 0;
}

static struct cxgb4_uld_info c4iw_uld_info = {
	.name = DRV_NAME,
	.add = c4iw_uld_add,
	.rx_handler = c4iw_uld_rx_handler,
	.state_change = c4iw_uld_state_change,
	.control = c4iw_uld_control,
};

static int __init c4iw_init_module(void)
{
	int err;

	err = c4iw_cm_init();
	if (err)
		return err;

	c4iw_debugfs_root = debugfs_create_dir(DRV_NAME, NULL);
	if (!c4iw_debugfs_root)
		printk(KERN_WARNING MOD
		       "could not create debugfs entry, continuing\n");

	cxgb4_register_uld(CXGB4_ULD_RDMA, &c4iw_uld_info);

	return 0;
}

static void __exit c4iw_exit_module(void)
{
	struct uld_ctx *ctx, *tmp;

	mutex_lock(&dev_mutex);
	list_for_each_entry_safe(ctx, tmp, &uld_ctx_list, entry) {
		if (ctx->dev)
			c4iw_remove(ctx);
		kfree(ctx);
	}
	mutex_unlock(&dev_mutex);
	cxgb4_unregister_uld(CXGB4_ULD_RDMA);
	c4iw_cm_term();
	debugfs_remove_recursive(c4iw_debugfs_root);
}

module_init(c4iw_init_module);
module_exit(c4iw_exit_module);