summaryrefslogtreecommitdiff
path: root/drivers/infiniband/hw/cxgb4/mem.c
blob: 9335148c1ad9ce746be5a0cb50062572627a37e3 (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
949
950
951
952
953
954
955
/*
 * 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 <rdma/ib_umem.h>
#include <linux/atomic.h>

#include "iw_cxgb4.h"

int use_dsgl = 0;
module_param(use_dsgl, int, 0644);
MODULE_PARM_DESC(use_dsgl, "Use DSGL for PBL/FastReg (default=0)");

#define T4_ULPTX_MIN_IO 32
#define C4IW_MAX_INLINE_SIZE 96
#define T4_ULPTX_MAX_DMA 1024
#define C4IW_INLINE_THRESHOLD 128

static int inline_threshold = C4IW_INLINE_THRESHOLD;
module_param(inline_threshold, int, 0644);
MODULE_PARM_DESC(inline_threshold, "inline vs dsgl threshold (default=128)");

static int _c4iw_write_mem_dma_aligned(struct c4iw_rdev *rdev, u32 addr,
				       u32 len, dma_addr_t data, int wait)
{
	struct sk_buff *skb;
	struct ulp_mem_io *req;
	struct ulptx_sgl *sgl;
	u8 wr_len;
	int ret = 0;
	struct c4iw_wr_wait wr_wait;

	addr &= 0x7FFFFFF;

	if (wait)
		c4iw_init_wr_wait(&wr_wait);
	wr_len = roundup(sizeof(*req) + sizeof(*sgl), 16);

	skb = alloc_skb(wr_len, GFP_KERNEL | __GFP_NOFAIL);
	if (!skb)
		return -ENOMEM;
	set_wr_txq(skb, CPL_PRIORITY_CONTROL, 0);

	req = (struct ulp_mem_io *)__skb_put(skb, wr_len);
	memset(req, 0, wr_len);
	INIT_ULPTX_WR(req, wr_len, 0, 0);
	req->wr.wr_hi = cpu_to_be32(FW_WR_OP_V(FW_ULPTX_WR) |
			(wait ? FW_WR_COMPL_F : 0));
	req->wr.wr_lo = wait ? (__force __be64)(unsigned long) &wr_wait : 0L;
	req->wr.wr_mid = cpu_to_be32(FW_WR_LEN16_V(DIV_ROUND_UP(wr_len, 16)));
	req->cmd = cpu_to_be32(ULPTX_CMD(ULP_TX_MEM_WRITE));
	req->cmd |= cpu_to_be32(V_T5_ULP_MEMIO_ORDER(1));
	req->dlen = cpu_to_be32(ULP_MEMIO_DATA_LEN(len>>5));
	req->len16 = cpu_to_be32(DIV_ROUND_UP(wr_len-sizeof(req->wr), 16));
	req->lock_addr = cpu_to_be32(ULP_MEMIO_ADDR(addr));

	sgl = (struct ulptx_sgl *)(req + 1);
	sgl->cmd_nsge = cpu_to_be32(ULPTX_CMD(ULP_TX_SC_DSGL) |
				    ULPTX_NSGE(1));
	sgl->len0 = cpu_to_be32(len);
	sgl->addr0 = cpu_to_be64(data);

	ret = c4iw_ofld_send(rdev, skb);
	if (ret)
		return ret;
	if (wait)
		ret = c4iw_wait_for_reply(rdev, &wr_wait, 0, 0, __func__);
	return ret;
}

static int _c4iw_write_mem_inline(struct c4iw_rdev *rdev, u32 addr, u32 len,
				  void *data)
{
	struct sk_buff *skb;
	struct ulp_mem_io *req;
	struct ulptx_idata *sc;
	u8 wr_len, *to_dp, *from_dp;
	int copy_len, num_wqe, i, ret = 0;
	struct c4iw_wr_wait wr_wait;
	__be32 cmd = cpu_to_be32(ULPTX_CMD(ULP_TX_MEM_WRITE));

	if (is_t4(rdev->lldi.adapter_type))
		cmd |= cpu_to_be32(ULP_MEMIO_ORDER(1));
	else
		cmd |= cpu_to_be32(V_T5_ULP_MEMIO_IMM(1));

	addr &= 0x7FFFFFF;
	PDBG("%s addr 0x%x len %u\n", __func__, addr, len);
	num_wqe = DIV_ROUND_UP(len, C4IW_MAX_INLINE_SIZE);
	c4iw_init_wr_wait(&wr_wait);
	for (i = 0; i < num_wqe; i++) {

		copy_len = len > C4IW_MAX_INLINE_SIZE ? C4IW_MAX_INLINE_SIZE :
			   len;
		wr_len = roundup(sizeof *req + sizeof *sc +
				 roundup(copy_len, T4_ULPTX_MIN_IO), 16);

		skb = alloc_skb(wr_len, GFP_KERNEL);
		if (!skb)
			return -ENOMEM;
		set_wr_txq(skb, CPL_PRIORITY_CONTROL, 0);

		req = (struct ulp_mem_io *)__skb_put(skb, wr_len);
		memset(req, 0, wr_len);
		INIT_ULPTX_WR(req, wr_len, 0, 0);

		if (i == (num_wqe-1)) {
			req->wr.wr_hi = cpu_to_be32(FW_WR_OP_V(FW_ULPTX_WR) |
						    FW_WR_COMPL_F);
			req->wr.wr_lo = (__force __be64)(unsigned long) &wr_wait;
		} else
			req->wr.wr_hi = cpu_to_be32(FW_WR_OP_V(FW_ULPTX_WR));
		req->wr.wr_mid = cpu_to_be32(
				       FW_WR_LEN16_V(DIV_ROUND_UP(wr_len, 16)));

		req->cmd = cmd;
		req->dlen = cpu_to_be32(ULP_MEMIO_DATA_LEN(
				DIV_ROUND_UP(copy_len, T4_ULPTX_MIN_IO)));
		req->len16 = cpu_to_be32(DIV_ROUND_UP(wr_len-sizeof(req->wr),
						      16));
		req->lock_addr = cpu_to_be32(ULP_MEMIO_ADDR(addr + i * 3));

		sc = (struct ulptx_idata *)(req + 1);
		sc->cmd_more = cpu_to_be32(ULPTX_CMD(ULP_TX_SC_IMM));
		sc->len = cpu_to_be32(roundup(copy_len, T4_ULPTX_MIN_IO));

		to_dp = (u8 *)(sc + 1);
		from_dp = (u8 *)data + i * C4IW_MAX_INLINE_SIZE;
		if (data)
			memcpy(to_dp, from_dp, copy_len);
		else
			memset(to_dp, 0, copy_len);
		if (copy_len % T4_ULPTX_MIN_IO)
			memset(to_dp + copy_len, 0, T4_ULPTX_MIN_IO -
			       (copy_len % T4_ULPTX_MIN_IO));
		ret = c4iw_ofld_send(rdev, skb);
		if (ret)
			return ret;
		len -= C4IW_MAX_INLINE_SIZE;
	}

	ret = c4iw_wait_for_reply(rdev, &wr_wait, 0, 0, __func__);
	return ret;
}

static int _c4iw_write_mem_dma(struct c4iw_rdev *rdev, u32 addr, u32 len, void *data)
{
	u32 remain = len;
	u32 dmalen;
	int ret = 0;
	dma_addr_t daddr;
	dma_addr_t save;

	daddr = dma_map_single(&rdev->lldi.pdev->dev, data, len, DMA_TO_DEVICE);
	if (dma_mapping_error(&rdev->lldi.pdev->dev, daddr))
		return -1;
	save = daddr;

	while (remain > inline_threshold) {
		if (remain < T4_ULPTX_MAX_DMA) {
			if (remain & ~T4_ULPTX_MIN_IO)
				dmalen = remain & ~(T4_ULPTX_MIN_IO-1);
			else
				dmalen = remain;
		} else
			dmalen = T4_ULPTX_MAX_DMA;
		remain -= dmalen;
		ret = _c4iw_write_mem_dma_aligned(rdev, addr, dmalen, daddr,
						 !remain);
		if (ret)
			goto out;
		addr += dmalen >> 5;
		data += dmalen;
		daddr += dmalen;
	}
	if (remain)
		ret = _c4iw_write_mem_inline(rdev, addr, remain, data);
out:
	dma_unmap_single(&rdev->lldi.pdev->dev, save, len, DMA_TO_DEVICE);
	return ret;
}

/*
 * write len bytes of data into addr (32B aligned address)
 * If data is NULL, clear len byte of memory to zero.
 */
static int write_adapter_mem(struct c4iw_rdev *rdev, u32 addr, u32 len,
			     void *data)
{
	if (is_t5(rdev->lldi.adapter_type) && use_dsgl) {
		if (len > inline_threshold) {
			if (_c4iw_write_mem_dma(rdev, addr, len, data)) {
				printk_ratelimited(KERN_WARNING
						   "%s: dma map"
						   " failure (non fatal)\n",
						   pci_name(rdev->lldi.pdev));
				return _c4iw_write_mem_inline(rdev, addr, len,
							      data);
			} else
				return 0;
		} else
			return _c4iw_write_mem_inline(rdev, addr, len, data);
	} else
		return _c4iw_write_mem_inline(rdev, addr, len, data);
}

/*
 * Build and write a TPT entry.
 * IN: stag key, pdid, perm, bind_enabled, zbva, to, len, page_size,
 *     pbl_size and pbl_addr
 * OUT: stag index
 */
static int write_tpt_entry(struct c4iw_rdev *rdev, u32 reset_tpt_entry,
			   u32 *stag, u8 stag_state, u32 pdid,
			   enum fw_ri_stag_type type, enum fw_ri_mem_perms perm,
			   int bind_enabled, u32 zbva, u64 to,
			   u64 len, u8 page_size, u32 pbl_size, u32 pbl_addr)
{
	int err;
	struct fw_ri_tpte tpt;
	u32 stag_idx;
	static atomic_t key;

	if (c4iw_fatal_error(rdev))
		return -EIO;

	stag_state = stag_state > 0;
	stag_idx = (*stag) >> 8;

	if ((!reset_tpt_entry) && (*stag == T4_STAG_UNSET)) {
		stag_idx = c4iw_get_resource(&rdev->resource.tpt_table);
		if (!stag_idx) {
			mutex_lock(&rdev->stats.lock);
			rdev->stats.stag.fail++;
			mutex_unlock(&rdev->stats.lock);
			return -ENOMEM;
		}
		mutex_lock(&rdev->stats.lock);
		rdev->stats.stag.cur += 32;
		if (rdev->stats.stag.cur > rdev->stats.stag.max)
			rdev->stats.stag.max = rdev->stats.stag.cur;
		mutex_unlock(&rdev->stats.lock);
		*stag = (stag_idx << 8) | (atomic_inc_return(&key) & 0xff);
	}
	PDBG("%s stag_state 0x%0x type 0x%0x pdid 0x%0x, stag_idx 0x%x\n",
	     __func__, stag_state, type, pdid, stag_idx);

	/* write TPT entry */
	if (reset_tpt_entry)
		memset(&tpt, 0, sizeof(tpt));
	else {
		tpt.valid_to_pdid = cpu_to_be32(F_FW_RI_TPTE_VALID |
			V_FW_RI_TPTE_STAGKEY((*stag & M_FW_RI_TPTE_STAGKEY)) |
			V_FW_RI_TPTE_STAGSTATE(stag_state) |
			V_FW_RI_TPTE_STAGTYPE(type) | V_FW_RI_TPTE_PDID(pdid));
		tpt.locread_to_qpid = cpu_to_be32(V_FW_RI_TPTE_PERM(perm) |
			(bind_enabled ? F_FW_RI_TPTE_MWBINDEN : 0) |
			V_FW_RI_TPTE_ADDRTYPE((zbva ? FW_RI_ZERO_BASED_TO :
						      FW_RI_VA_BASED_TO))|
			V_FW_RI_TPTE_PS(page_size));
		tpt.nosnoop_pbladdr = !pbl_size ? 0 : cpu_to_be32(
			V_FW_RI_TPTE_PBLADDR(PBL_OFF(rdev, pbl_addr)>>3));
		tpt.len_lo = cpu_to_be32((u32)(len & 0xffffffffUL));
		tpt.va_hi = cpu_to_be32((u32)(to >> 32));
		tpt.va_lo_fbo = cpu_to_be32((u32)(to & 0xffffffffUL));
		tpt.dca_mwbcnt_pstag = cpu_to_be32(0);
		tpt.len_hi = cpu_to_be32((u32)(len >> 32));
	}
	err = write_adapter_mem(rdev, stag_idx +
				(rdev->lldi.vr->stag.start >> 5),
				sizeof(tpt), &tpt);

	if (reset_tpt_entry) {
		c4iw_put_resource(&rdev->resource.tpt_table, stag_idx);
		mutex_lock(&rdev->stats.lock);
		rdev->stats.stag.cur -= 32;
		mutex_unlock(&rdev->stats.lock);
	}
	return err;
}

static int write_pbl(struct c4iw_rdev *rdev, __be64 *pbl,
		     u32 pbl_addr, u32 pbl_size)
{
	int err;

	PDBG("%s *pdb_addr 0x%x, pbl_base 0x%x, pbl_size %d\n",
	     __func__, pbl_addr, rdev->lldi.vr->pbl.start,
	     pbl_size);

	err = write_adapter_mem(rdev, pbl_addr >> 5, pbl_size << 3, pbl);
	return err;
}

static int dereg_mem(struct c4iw_rdev *rdev, u32 stag, u32 pbl_size,
		     u32 pbl_addr)
{
	return write_tpt_entry(rdev, 1, &stag, 0, 0, 0, 0, 0, 0, 0UL, 0, 0,
			       pbl_size, pbl_addr);
}

static int allocate_window(struct c4iw_rdev *rdev, u32 * stag, u32 pdid)
{
	*stag = T4_STAG_UNSET;
	return write_tpt_entry(rdev, 0, stag, 0, pdid, FW_RI_STAG_MW, 0, 0, 0,
			       0UL, 0, 0, 0, 0);
}

static int deallocate_window(struct c4iw_rdev *rdev, u32 stag)
{
	return write_tpt_entry(rdev, 1, &stag, 0, 0, 0, 0, 0, 0, 0UL, 0, 0, 0,
			       0);
}

static int allocate_stag(struct c4iw_rdev *rdev, u32 *stag, u32 pdid,
			 u32 pbl_size, u32 pbl_addr)
{
	*stag = T4_STAG_UNSET;
	return write_tpt_entry(rdev, 0, stag, 0, pdid, FW_RI_STAG_NSMR, 0, 0, 0,
			       0UL, 0, 0, pbl_size, pbl_addr);
}

static int finish_mem_reg(struct c4iw_mr *mhp, u32 stag)
{
	u32 mmid;

	mhp->attr.state = 1;
	mhp->attr.stag = stag;
	mmid = stag >> 8;
	mhp->ibmr.rkey = mhp->ibmr.lkey = stag;
	PDBG("%s mmid 0x%x mhp %p\n", __func__, mmid, mhp);
	return insert_handle(mhp->rhp, &mhp->rhp->mmidr, mhp, mmid);
}

static int register_mem(struct c4iw_dev *rhp, struct c4iw_pd *php,
		      struct c4iw_mr *mhp, int shift)
{
	u32 stag = T4_STAG_UNSET;
	int ret;

	ret = write_tpt_entry(&rhp->rdev, 0, &stag, 1, mhp->attr.pdid,
			      FW_RI_STAG_NSMR, mhp->attr.perms,
			      mhp->attr.mw_bind_enable, mhp->attr.zbva,
			      mhp->attr.va_fbo, mhp->attr.len, shift - 12,
			      mhp->attr.pbl_size, mhp->attr.pbl_addr);
	if (ret)
		return ret;

	ret = finish_mem_reg(mhp, stag);
	if (ret)
		dereg_mem(&rhp->rdev, mhp->attr.stag, mhp->attr.pbl_size,
		       mhp->attr.pbl_addr);
	return ret;
}

static int reregister_mem(struct c4iw_dev *rhp, struct c4iw_pd *php,
			  struct c4iw_mr *mhp, int shift, int npages)
{
	u32 stag;
	int ret;

	if (npages > mhp->attr.pbl_size)
		return -ENOMEM;

	stag = mhp->attr.stag;
	ret = write_tpt_entry(&rhp->rdev, 0, &stag, 1, mhp->attr.pdid,
			      FW_RI_STAG_NSMR, mhp->attr.perms,
			      mhp->attr.mw_bind_enable, mhp->attr.zbva,
			      mhp->attr.va_fbo, mhp->attr.len, shift - 12,
			      mhp->attr.pbl_size, mhp->attr.pbl_addr);
	if (ret)
		return ret;

	ret = finish_mem_reg(mhp, stag);
	if (ret)
		dereg_mem(&rhp->rdev, mhp->attr.stag, mhp->attr.pbl_size,
		       mhp->attr.pbl_addr);

	return ret;
}

static int alloc_pbl(struct c4iw_mr *mhp, int npages)
{
	mhp->attr.pbl_addr = c4iw_pblpool_alloc(&mhp->rhp->rdev,
						    npages << 3);

	if (!mhp->attr.pbl_addr)
		return -ENOMEM;

	mhp->attr.pbl_size = npages;

	return 0;
}

static int build_phys_page_list(struct ib_phys_buf *buffer_list,
				int num_phys_buf, u64 *iova_start,
				u64 *total_size, int *npages,
				int *shift, __be64 **page_list)
{
	u64 mask;
	int i, j, n;

	mask = 0;
	*total_size = 0;
	for (i = 0; i < num_phys_buf; ++i) {
		if (i != 0 && buffer_list[i].addr & ~PAGE_MASK)
			return -EINVAL;
		if (i != 0 && i != num_phys_buf - 1 &&
		    (buffer_list[i].size & ~PAGE_MASK))
			return -EINVAL;
		*total_size += buffer_list[i].size;
		if (i > 0)
			mask |= buffer_list[i].addr;
		else
			mask |= buffer_list[i].addr & PAGE_MASK;
		if (i != num_phys_buf - 1)
			mask |= buffer_list[i].addr + buffer_list[i].size;
		else
			mask |= (buffer_list[i].addr + buffer_list[i].size +
				PAGE_SIZE - 1) & PAGE_MASK;
	}

	if (*total_size > 0xFFFFFFFFULL)
		return -ENOMEM;

	/* Find largest page shift we can use to cover buffers */
	for (*shift = PAGE_SHIFT; *shift < 27; ++(*shift))
		if ((1ULL << *shift) & mask)
			break;

	buffer_list[0].size += buffer_list[0].addr & ((1ULL << *shift) - 1);
	buffer_list[0].addr &= ~0ull << *shift;

	*npages = 0;
	for (i = 0; i < num_phys_buf; ++i)
		*npages += (buffer_list[i].size +
			(1ULL << *shift) - 1) >> *shift;

	if (!*npages)
		return -EINVAL;

	*page_list = kmalloc(sizeof(u64) * *npages, GFP_KERNEL);
	if (!*page_list)
		return -ENOMEM;

	n = 0;
	for (i = 0; i < num_phys_buf; ++i)
		for (j = 0;
		     j < (buffer_list[i].size + (1ULL << *shift) - 1) >> *shift;
		     ++j)
			(*page_list)[n++] = cpu_to_be64(buffer_list[i].addr +
			    ((u64) j << *shift));

	PDBG("%s va 0x%llx mask 0x%llx shift %d len %lld pbl_size %d\n",
	     __func__, (unsigned long long)*iova_start,
	     (unsigned long long)mask, *shift, (unsigned long long)*total_size,
	     *npages);

	return 0;

}

int c4iw_reregister_phys_mem(struct ib_mr *mr, int mr_rereg_mask,
			     struct ib_pd *pd, struct ib_phys_buf *buffer_list,
			     int num_phys_buf, int acc, u64 *iova_start)
{

	struct c4iw_mr mh, *mhp;
	struct c4iw_pd *php;
	struct c4iw_dev *rhp;
	__be64 *page_list = NULL;
	int shift = 0;
	u64 total_size;
	int npages;
	int ret;

	PDBG("%s ib_mr %p ib_pd %p\n", __func__, mr, pd);

	/* There can be no memory windows */
	if (atomic_read(&mr->usecnt))
		return -EINVAL;

	mhp = to_c4iw_mr(mr);
	rhp = mhp->rhp;
	php = to_c4iw_pd(mr->pd);

	/* make sure we are on the same adapter */
	if (rhp != php->rhp)
		return -EINVAL;

	memcpy(&mh, mhp, sizeof *mhp);

	if (mr_rereg_mask & IB_MR_REREG_PD)
		php = to_c4iw_pd(pd);
	if (mr_rereg_mask & IB_MR_REREG_ACCESS) {
		mh.attr.perms = c4iw_ib_to_tpt_access(acc);
		mh.attr.mw_bind_enable = (acc & IB_ACCESS_MW_BIND) ==
					 IB_ACCESS_MW_BIND;
	}
	if (mr_rereg_mask & IB_MR_REREG_TRANS) {
		ret = build_phys_page_list(buffer_list, num_phys_buf,
						iova_start,
						&total_size, &npages,
						&shift, &page_list);
		if (ret)
			return ret;
	}

	ret = reregister_mem(rhp, php, &mh, shift, npages);
	kfree(page_list);
	if (ret)
		return ret;
	if (mr_rereg_mask & IB_MR_REREG_PD)
		mhp->attr.pdid = php->pdid;
	if (mr_rereg_mask & IB_MR_REREG_ACCESS)
		mhp->attr.perms = c4iw_ib_to_tpt_access(acc);
	if (mr_rereg_mask & IB_MR_REREG_TRANS) {
		mhp->attr.zbva = 0;
		mhp->attr.va_fbo = *iova_start;
		mhp->attr.page_size = shift - 12;
		mhp->attr.len = (u32) total_size;
		mhp->attr.pbl_size = npages;
	}

	return 0;
}

struct ib_mr *c4iw_register_phys_mem(struct ib_pd *pd,
				     struct ib_phys_buf *buffer_list,
				     int num_phys_buf, int acc, u64 *iova_start)
{
	__be64 *page_list;
	int shift;
	u64 total_size;
	int npages;
	struct c4iw_dev *rhp;
	struct c4iw_pd *php;
	struct c4iw_mr *mhp;
	int ret;

	PDBG("%s ib_pd %p\n", __func__, pd);
	php = to_c4iw_pd(pd);
	rhp = php->rhp;

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

	mhp->rhp = rhp;

	/* First check that we have enough alignment */
	if ((*iova_start & ~PAGE_MASK) != (buffer_list[0].addr & ~PAGE_MASK)) {
		ret = -EINVAL;
		goto err;
	}

	if (num_phys_buf > 1 &&
	    ((buffer_list[0].addr + buffer_list[0].size) & ~PAGE_MASK)) {
		ret = -EINVAL;
		goto err;
	}

	ret = build_phys_page_list(buffer_list, num_phys_buf, iova_start,
					&total_size, &npages, &shift,
					&page_list);
	if (ret)
		goto err;

	ret = alloc_pbl(mhp, npages);
	if (ret) {
		kfree(page_list);
		goto err;
	}

	ret = write_pbl(&mhp->rhp->rdev, page_list, mhp->attr.pbl_addr,
			     npages);
	kfree(page_list);
	if (ret)
		goto err_pbl;

	mhp->attr.pdid = php->pdid;
	mhp->attr.zbva = 0;

	mhp->attr.perms = c4iw_ib_to_tpt_access(acc);
	mhp->attr.va_fbo = *iova_start;
	mhp->attr.page_size = shift - 12;

	mhp->attr.len = (u32) total_size;
	mhp->attr.pbl_size = npages;
	ret = register_mem(rhp, php, mhp, shift);
	if (ret)
		goto err_pbl;

	return &mhp->ibmr;

err_pbl:
	c4iw_pblpool_free(&mhp->rhp->rdev, mhp->attr.pbl_addr,
			      mhp->attr.pbl_size << 3);

err:
	kfree(mhp);
	return ERR_PTR(ret);

}

struct ib_mr *c4iw_get_dma_mr(struct ib_pd *pd, int acc)
{
	struct c4iw_dev *rhp;
	struct c4iw_pd *php;
	struct c4iw_mr *mhp;
	int ret;
	u32 stag = T4_STAG_UNSET;

	PDBG("%s ib_pd %p\n", __func__, pd);
	php = to_c4iw_pd(pd);
	rhp = php->rhp;

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

	mhp->rhp = rhp;
	mhp->attr.pdid = php->pdid;
	mhp->attr.perms = c4iw_ib_to_tpt_access(acc);
	mhp->attr.mw_bind_enable = (acc&IB_ACCESS_MW_BIND) == IB_ACCESS_MW_BIND;
	mhp->attr.zbva = 0;
	mhp->attr.va_fbo = 0;
	mhp->attr.page_size = 0;
	mhp->attr.len = ~0UL;
	mhp->attr.pbl_size = 0;

	ret = write_tpt_entry(&rhp->rdev, 0, &stag, 1, php->pdid,
			      FW_RI_STAG_NSMR, mhp->attr.perms,
			      mhp->attr.mw_bind_enable, 0, 0, ~0UL, 0, 0, 0);
	if (ret)
		goto err1;

	ret = finish_mem_reg(mhp, stag);
	if (ret)
		goto err2;
	return &mhp->ibmr;
err2:
	dereg_mem(&rhp->rdev, mhp->attr.stag, mhp->attr.pbl_size,
		  mhp->attr.pbl_addr);
err1:
	kfree(mhp);
	return ERR_PTR(ret);
}

struct ib_mr *c4iw_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
			       u64 virt, int acc, struct ib_udata *udata)
{
	__be64 *pages;
	int shift, n, len;
	int i, k, entry;
	int err = 0;
	struct scatterlist *sg;
	struct c4iw_dev *rhp;
	struct c4iw_pd *php;
	struct c4iw_mr *mhp;

	PDBG("%s ib_pd %p\n", __func__, pd);

	if (length == ~0ULL)
		return ERR_PTR(-EINVAL);

	if ((length + start) < start)
		return ERR_PTR(-EINVAL);

	php = to_c4iw_pd(pd);
	rhp = php->rhp;
	mhp = kzalloc(sizeof(*mhp), GFP_KERNEL);
	if (!mhp)
		return ERR_PTR(-ENOMEM);

	mhp->rhp = rhp;

	mhp->umem = ib_umem_get(pd->uobject->context, start, length, acc, 0);
	if (IS_ERR(mhp->umem)) {
		err = PTR_ERR(mhp->umem);
		kfree(mhp);
		return ERR_PTR(err);
	}

	shift = ffs(mhp->umem->page_size) - 1;

	n = mhp->umem->nmap;
	err = alloc_pbl(mhp, n);
	if (err)
		goto err;

	pages = (__be64 *) __get_free_page(GFP_KERNEL);
	if (!pages) {
		err = -ENOMEM;
		goto err_pbl;
	}

	i = n = 0;

	for_each_sg(mhp->umem->sg_head.sgl, sg, mhp->umem->nmap, entry) {
		len = sg_dma_len(sg) >> shift;
		for (k = 0; k < len; ++k) {
			pages[i++] = cpu_to_be64(sg_dma_address(sg) +
				mhp->umem->page_size * k);
			if (i == PAGE_SIZE / sizeof *pages) {
				err = write_pbl(&mhp->rhp->rdev,
				      pages,
				      mhp->attr.pbl_addr + (n << 3), i);
				if (err)
					goto pbl_done;
				n += i;
				i = 0;
			}
		}
	}

	if (i)
		err = write_pbl(&mhp->rhp->rdev, pages,
				     mhp->attr.pbl_addr + (n << 3), i);

pbl_done:
	free_page((unsigned long) pages);
	if (err)
		goto err_pbl;

	mhp->attr.pdid = php->pdid;
	mhp->attr.zbva = 0;
	mhp->attr.perms = c4iw_ib_to_tpt_access(acc);
	mhp->attr.va_fbo = virt;
	mhp->attr.page_size = shift - 12;
	mhp->attr.len = length;

	err = register_mem(rhp, php, mhp, shift);
	if (err)
		goto err_pbl;

	return &mhp->ibmr;

err_pbl:
	c4iw_pblpool_free(&mhp->rhp->rdev, mhp->attr.pbl_addr,
			      mhp->attr.pbl_size << 3);

err:
	ib_umem_release(mhp->umem);
	kfree(mhp);
	return ERR_PTR(err);
}

struct ib_mw *c4iw_alloc_mw(struct ib_pd *pd, enum ib_mw_type type)
{
	struct c4iw_dev *rhp;
	struct c4iw_pd *php;
	struct c4iw_mw *mhp;
	u32 mmid;
	u32 stag = 0;
	int ret;

	if (type != IB_MW_TYPE_1)
		return ERR_PTR(-EINVAL);

	php = to_c4iw_pd(pd);
	rhp = php->rhp;
	mhp = kzalloc(sizeof(*mhp), GFP_KERNEL);
	if (!mhp)
		return ERR_PTR(-ENOMEM);
	ret = allocate_window(&rhp->rdev, &stag, php->pdid);
	if (ret) {
		kfree(mhp);
		return ERR_PTR(ret);
	}
	mhp->rhp = rhp;
	mhp->attr.pdid = php->pdid;
	mhp->attr.type = FW_RI_STAG_MW;
	mhp->attr.stag = stag;
	mmid = (stag) >> 8;
	mhp->ibmw.rkey = stag;
	if (insert_handle(rhp, &rhp->mmidr, mhp, mmid)) {
		deallocate_window(&rhp->rdev, mhp->attr.stag);
		kfree(mhp);
		return ERR_PTR(-ENOMEM);
	}
	PDBG("%s mmid 0x%x mhp %p stag 0x%x\n", __func__, mmid, mhp, stag);
	return &(mhp->ibmw);
}

int c4iw_dealloc_mw(struct ib_mw *mw)
{
	struct c4iw_dev *rhp;
	struct c4iw_mw *mhp;
	u32 mmid;

	mhp = to_c4iw_mw(mw);
	rhp = mhp->rhp;
	mmid = (mw->rkey) >> 8;
	remove_handle(rhp, &rhp->mmidr, mmid);
	deallocate_window(&rhp->rdev, mhp->attr.stag);
	kfree(mhp);
	PDBG("%s ib_mw %p mmid 0x%x ptr %p\n", __func__, mw, mmid, mhp);
	return 0;
}

struct ib_mr *c4iw_alloc_fast_reg_mr(struct ib_pd *pd, int pbl_depth)
{
	struct c4iw_dev *rhp;
	struct c4iw_pd *php;
	struct c4iw_mr *mhp;
	u32 mmid;
	u32 stag = 0;
	int ret = 0;

	php = to_c4iw_pd(pd);
	rhp = php->rhp;
	mhp = kzalloc(sizeof(*mhp), GFP_KERNEL);
	if (!mhp) {
		ret = -ENOMEM;
		goto err;
	}

	mhp->rhp = rhp;
	ret = alloc_pbl(mhp, pbl_depth);
	if (ret)
		goto err1;
	mhp->attr.pbl_size = pbl_depth;
	ret = allocate_stag(&rhp->rdev, &stag, php->pdid,
				 mhp->attr.pbl_size, mhp->attr.pbl_addr);
	if (ret)
		goto err2;
	mhp->attr.pdid = php->pdid;
	mhp->attr.type = FW_RI_STAG_NSMR;
	mhp->attr.stag = stag;
	mhp->attr.state = 1;
	mmid = (stag) >> 8;
	mhp->ibmr.rkey = mhp->ibmr.lkey = stag;
	if (insert_handle(rhp, &rhp->mmidr, mhp, mmid)) {
		ret = -ENOMEM;
		goto err3;
	}

	PDBG("%s mmid 0x%x mhp %p stag 0x%x\n", __func__, mmid, mhp, stag);
	return &(mhp->ibmr);
err3:
	dereg_mem(&rhp->rdev, stag, mhp->attr.pbl_size,
		       mhp->attr.pbl_addr);
err2:
	c4iw_pblpool_free(&mhp->rhp->rdev, mhp->attr.pbl_addr,
			      mhp->attr.pbl_size << 3);
err1:
	kfree(mhp);
err:
	return ERR_PTR(ret);
}

struct ib_fast_reg_page_list *c4iw_alloc_fastreg_pbl(struct ib_device *device,
						     int page_list_len)
{
	struct c4iw_fr_page_list *c4pl;
	struct c4iw_dev *dev = to_c4iw_dev(device);
	dma_addr_t dma_addr;
	int pll_len = roundup(page_list_len * sizeof(u64), 32);

	c4pl = kmalloc(sizeof(*c4pl), GFP_KERNEL);
	if (!c4pl)
		return ERR_PTR(-ENOMEM);

	c4pl->ibpl.page_list = dma_alloc_coherent(&dev->rdev.lldi.pdev->dev,
						  pll_len, &dma_addr,
						  GFP_KERNEL);
	if (!c4pl->ibpl.page_list) {
		kfree(c4pl);
		return ERR_PTR(-ENOMEM);
	}
	dma_unmap_addr_set(c4pl, mapping, dma_addr);
	c4pl->dma_addr = dma_addr;
	c4pl->dev = dev;
	c4pl->pll_len = pll_len;

	PDBG("%s c4pl %p pll_len %u page_list %p dma_addr %pad\n",
	     __func__, c4pl, c4pl->pll_len, c4pl->ibpl.page_list,
	     &c4pl->dma_addr);

	return &c4pl->ibpl;
}

void c4iw_free_fastreg_pbl(struct ib_fast_reg_page_list *ibpl)
{
	struct c4iw_fr_page_list *c4pl = to_c4iw_fr_page_list(ibpl);

	PDBG("%s c4pl %p pll_len %u page_list %p dma_addr %pad\n",
	     __func__, c4pl, c4pl->pll_len, c4pl->ibpl.page_list,
	     &c4pl->dma_addr);

	dma_free_coherent(&c4pl->dev->rdev.lldi.pdev->dev,
			  c4pl->pll_len,
			  c4pl->ibpl.page_list, dma_unmap_addr(c4pl, mapping));
	kfree(c4pl);
}

int c4iw_dereg_mr(struct ib_mr *ib_mr)
{
	struct c4iw_dev *rhp;
	struct c4iw_mr *mhp;
	u32 mmid;

	PDBG("%s ib_mr %p\n", __func__, ib_mr);
	/* There can be no memory windows */
	if (atomic_read(&ib_mr->usecnt))
		return -EINVAL;

	mhp = to_c4iw_mr(ib_mr);
	rhp = mhp->rhp;
	mmid = mhp->attr.stag >> 8;
	remove_handle(rhp, &rhp->mmidr, mmid);
	dereg_mem(&rhp->rdev, mhp->attr.stag, mhp->attr.pbl_size,
		       mhp->attr.pbl_addr);
	if (mhp->attr.pbl_size)
		c4iw_pblpool_free(&mhp->rhp->rdev, mhp->attr.pbl_addr,
				  mhp->attr.pbl_size << 3);
	if (mhp->kva)
		kfree((void *) (unsigned long) mhp->kva);
	if (mhp->umem)
		ib_umem_release(mhp->umem);
	PDBG("%s mmid 0x%x ptr %p\n", __func__, mmid, mhp);
	kfree(mhp);
	return 0;
}