aboutsummaryrefslogtreecommitdiff
path: root/arch/sparc64/kernel/pci_sun4v.c
blob: 4b27b0e10ce78baa287691d04c695dfcce293751 (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
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
/* pci_sun4v.c: SUN4V specific PCI controller support.
 *
 * Copyright (C) 2006, 2007, 2008 David S. Miller (davem@davemloft.net)
 */

#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/pci.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/interrupt.h>
#include <linux/percpu.h>
#include <linux/irq.h>
#include <linux/msi.h>
#include <linux/log2.h>
#include <linux/of_device.h>

#include <asm/iommu.h>
#include <asm/irq.h>
#include <asm/hypervisor.h>
#include <asm/prom.h>

#include "pci_impl.h"
#include "iommu_common.h"

#include "pci_sun4v.h"

#define DRIVER_NAME	"pci_sun4v"
#define PFX		DRIVER_NAME ": "

static unsigned long vpci_major = 1;
static unsigned long vpci_minor = 1;

#define PGLIST_NENTS	(PAGE_SIZE / sizeof(u64))

struct iommu_batch {
	struct device	*dev;		/* Device mapping is for.	*/
	unsigned long	prot;		/* IOMMU page protections	*/
	unsigned long	entry;		/* Index into IOTSB.		*/
	u64		*pglist;	/* List of physical pages	*/
	unsigned long	npages;		/* Number of pages in list.	*/
};

static DEFINE_PER_CPU(struct iommu_batch, iommu_batch);
static int iommu_batch_initialized;

/* Interrupts must be disabled.  */
static inline void iommu_batch_start(struct device *dev, unsigned long prot, unsigned long entry)
{
	struct iommu_batch *p = &__get_cpu_var(iommu_batch);

	p->dev		= dev;
	p->prot		= prot;
	p->entry	= entry;
	p->npages	= 0;
}

/* Interrupts must be disabled.  */
static long iommu_batch_flush(struct iommu_batch *p)
{
	struct pci_pbm_info *pbm = p->dev->archdata.host_controller;
	unsigned long devhandle = pbm->devhandle;
	unsigned long prot = p->prot;
	unsigned long entry = p->entry;
	u64 *pglist = p->pglist;
	unsigned long npages = p->npages;

	while (npages != 0) {
		long num;

		num = pci_sun4v_iommu_map(devhandle, HV_PCI_TSBID(0, entry),
					  npages, prot, __pa(pglist));
		if (unlikely(num < 0)) {
			if (printk_ratelimit())
				printk("iommu_batch_flush: IOMMU map of "
				       "[%08lx:%08lx:%lx:%lx:%lx] failed with "
				       "status %ld\n",
				       devhandle, HV_PCI_TSBID(0, entry),
				       npages, prot, __pa(pglist), num);
			return -1;
		}

		entry += num;
		npages -= num;
		pglist += num;
	}

	p->entry = entry;
	p->npages = 0;

	return 0;
}

static inline void iommu_batch_new_entry(unsigned long entry)
{
	struct iommu_batch *p = &__get_cpu_var(iommu_batch);

	if (p->entry + p->npages == entry)
		return;
	if (p->entry != ~0UL)
		iommu_batch_flush(p);
	p->entry = entry;
}

/* Interrupts must be disabled.  */
static inline long iommu_batch_add(u64 phys_page)
{
	struct iommu_batch *p = &__get_cpu_var(iommu_batch);

	BUG_ON(p->npages >= PGLIST_NENTS);

	p->pglist[p->npages++] = phys_page;
	if (p->npages == PGLIST_NENTS)
		return iommu_batch_flush(p);

	return 0;
}

/* Interrupts must be disabled.  */
static inline long iommu_batch_end(void)
{
	struct iommu_batch *p = &__get_cpu_var(iommu_batch);

	BUG_ON(p->npages >= PGLIST_NENTS);

	return iommu_batch_flush(p);
}

static void *dma_4v_alloc_coherent(struct device *dev, size_t size,
				   dma_addr_t *dma_addrp, gfp_t gfp)
{
	unsigned long flags, order, first_page, npages, n;
	struct iommu *iommu;
	struct page *page;
	void *ret;
	long entry;
	int nid;

	size = IO_PAGE_ALIGN(size);
	order = get_order(size);
	if (unlikely(order >= MAX_ORDER))
		return NULL;

	npages = size >> IO_PAGE_SHIFT;

	nid = dev->archdata.numa_node;
	page = alloc_pages_node(nid, gfp, order);
	if (unlikely(!page))
		return NULL;

	first_page = (unsigned long) page_address(page);
	memset((char *)first_page, 0, PAGE_SIZE << order);

	iommu = dev->archdata.iommu;

	spin_lock_irqsave(&iommu->lock, flags);
	entry = iommu_range_alloc(dev, iommu, npages, NULL);
	spin_unlock_irqrestore(&iommu->lock, flags);

	if (unlikely(entry == DMA_ERROR_CODE))
		goto range_alloc_fail;

	*dma_addrp = (iommu->page_table_map_base +
		      (entry << IO_PAGE_SHIFT));
	ret = (void *) first_page;
	first_page = __pa(first_page);

	local_irq_save(flags);

	iommu_batch_start(dev,
			  (HV_PCI_MAP_ATTR_READ |
			   HV_PCI_MAP_ATTR_WRITE),
			  entry);

	for (n = 0; n < npages; n++) {
		long err = iommu_batch_add(first_page + (n * PAGE_SIZE));
		if (unlikely(err < 0L))
			goto iommu_map_fail;
	}

	if (unlikely(iommu_batch_end() < 0L))
		goto iommu_map_fail;

	local_irq_restore(flags);

	return ret;

iommu_map_fail:
	/* Interrupts are disabled.  */
	spin_lock(&iommu->lock);
	iommu_range_free(iommu, *dma_addrp, npages);
	spin_unlock_irqrestore(&iommu->lock, flags);

range_alloc_fail:
	free_pages(first_page, order);
	return NULL;
}

static void dma_4v_free_coherent(struct device *dev, size_t size, void *cpu,
				 dma_addr_t dvma)
{
	struct pci_pbm_info *pbm;
	struct iommu *iommu;
	unsigned long flags, order, npages, entry;
	u32 devhandle;

	npages = IO_PAGE_ALIGN(size) >> IO_PAGE_SHIFT;
	iommu = dev->archdata.iommu;
	pbm = dev->archdata.host_controller;
	devhandle = pbm->devhandle;
	entry = ((dvma - iommu->page_table_map_base) >> IO_PAGE_SHIFT);

	spin_lock_irqsave(&iommu->lock, flags);

	iommu_range_free(iommu, dvma, npages);

	do {
		unsigned long num;

		num = pci_sun4v_iommu_demap(devhandle, HV_PCI_TSBID(0, entry),
					    npages);
		entry += num;
		npages -= num;
	} while (npages != 0);

	spin_unlock_irqrestore(&iommu->lock, flags);

	order = get_order(size);
	if (order < 10)
		free_pages((unsigned long)cpu, order);
}

static dma_addr_t dma_4v_map_single(struct device *dev, void *ptr, size_t sz,
				    enum dma_data_direction direction)
{
	struct iommu *iommu;
	unsigned long flags, npages, oaddr;
	unsigned long i, base_paddr;
	u32 bus_addr, ret;
	unsigned long prot;
	long entry;

	iommu = dev->archdata.iommu;

	if (unlikely(direction == DMA_NONE))
		goto bad;

	oaddr = (unsigned long)ptr;
	npages = IO_PAGE_ALIGN(oaddr + sz) - (oaddr & IO_PAGE_MASK);
	npages >>= IO_PAGE_SHIFT;

	spin_lock_irqsave(&iommu->lock, flags);
	entry = iommu_range_alloc(dev, iommu, npages, NULL);
	spin_unlock_irqrestore(&iommu->lock, flags);

	if (unlikely(entry == DMA_ERROR_CODE))
		goto bad;

	bus_addr = (iommu->page_table_map_base +
		    (entry << IO_PAGE_SHIFT));
	ret = bus_addr | (oaddr & ~IO_PAGE_MASK);
	base_paddr = __pa(oaddr & IO_PAGE_MASK);
	prot = HV_PCI_MAP_ATTR_READ;
	if (direction != DMA_TO_DEVICE)
		prot |= HV_PCI_MAP_ATTR_WRITE;

	local_irq_save(flags);

	iommu_batch_start(dev, prot, entry);

	for (i = 0; i < npages; i++, base_paddr += IO_PAGE_SIZE) {
		long err = iommu_batch_add(base_paddr);
		if (unlikely(err < 0L))
			goto iommu_map_fail;
	}
	if (unlikely(iommu_batch_end() < 0L))
		goto iommu_map_fail;

	local_irq_restore(flags);

	return ret;

bad:
	if (printk_ratelimit())
		WARN_ON(1);
	return DMA_ERROR_CODE;

iommu_map_fail:
	/* Interrupts are disabled.  */
	spin_lock(&iommu->lock);
	iommu_range_free(iommu, bus_addr, npages);
	spin_unlock_irqrestore(&iommu->lock, flags);

	return DMA_ERROR_CODE;
}

static void dma_4v_unmap_single(struct device *dev, dma_addr_t bus_addr,
				size_t sz, enum dma_data_direction direction)
{
	struct pci_pbm_info *pbm;
	struct iommu *iommu;
	unsigned long flags, npages;
	long entry;
	u32 devhandle;

	if (unlikely(direction == DMA_NONE)) {
		if (printk_ratelimit())
			WARN_ON(1);
		return;
	}

	iommu = dev->archdata.iommu;
	pbm = dev->archdata.host_controller;
	devhandle = pbm->devhandle;

	npages = IO_PAGE_ALIGN(bus_addr + sz) - (bus_addr & IO_PAGE_MASK);
	npages >>= IO_PAGE_SHIFT;
	bus_addr &= IO_PAGE_MASK;

	spin_lock_irqsave(&iommu->lock, flags);

	iommu_range_free(iommu, bus_addr, npages);

	entry = (bus_addr - iommu->page_table_map_base) >> IO_PAGE_SHIFT;
	do {
		unsigned long num;

		num = pci_sun4v_iommu_demap(devhandle, HV_PCI_TSBID(0, entry),
					    npages);
		entry += num;
		npages -= num;
	} while (npages != 0);

	spin_unlock_irqrestore(&iommu->lock, flags);
}

static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
			 int nelems, enum dma_data_direction direction)
{
	struct scatterlist *s, *outs, *segstart;
	unsigned long flags, handle, prot;
	dma_addr_t dma_next = 0, dma_addr;
	unsigned int max_seg_size;
	unsigned long seg_boundary_size;
	int outcount, incount, i;
	struct iommu *iommu;
	unsigned long base_shift;
	long err;

	BUG_ON(direction == DMA_NONE);

	iommu = dev->archdata.iommu;
	if (nelems == 0 || !iommu)
		return 0;
	
	prot = HV_PCI_MAP_ATTR_READ;
	if (direction != DMA_TO_DEVICE)
		prot |= HV_PCI_MAP_ATTR_WRITE;

	outs = s = segstart = &sglist[0];
	outcount = 1;
	incount = nelems;
	handle = 0;

	/* Init first segment length for backout at failure */
	outs->dma_length = 0;

	spin_lock_irqsave(&iommu->lock, flags);

	iommu_batch_start(dev, prot, ~0UL);

	max_seg_size = dma_get_max_seg_size(dev);
	seg_boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
				  IO_PAGE_SIZE) >> IO_PAGE_SHIFT;
	base_shift = iommu->page_table_map_base >> IO_PAGE_SHIFT;
	for_each_sg(sglist, s, nelems, i) {
		unsigned long paddr, npages, entry, out_entry = 0, slen;

		slen = s->length;
		/* Sanity check */
		if (slen == 0) {
			dma_next = 0;
			continue;
		}
		/* Allocate iommu entries for that segment */
		paddr = (unsigned long) SG_ENT_PHYS_ADDRESS(s);
		npages = iommu_num_pages(paddr, slen, IO_PAGE_SIZE);
		entry = iommu_range_alloc(dev, iommu, npages, &handle);

		/* Handle failure */
		if (unlikely(entry == DMA_ERROR_CODE)) {
			if (printk_ratelimit())
				printk(KERN_INFO "iommu_alloc failed, iommu %p paddr %lx"
				       " npages %lx\n", iommu, paddr, npages);
			goto iommu_map_failed;
		}

		iommu_batch_new_entry(entry);

		/* Convert entry to a dma_addr_t */
		dma_addr = iommu->page_table_map_base +
			(entry << IO_PAGE_SHIFT);
		dma_addr |= (s->offset & ~IO_PAGE_MASK);

		/* Insert into HW table */
		paddr &= IO_PAGE_MASK;
		while (npages--) {
			err = iommu_batch_add(paddr);
			if (unlikely(err < 0L))
				goto iommu_map_failed;
			paddr += IO_PAGE_SIZE;
		}

		/* If we are in an open segment, try merging */
		if (segstart != s) {
			/* We cannot merge if:
			 * - allocated dma_addr isn't contiguous to previous allocation
			 */
			if ((dma_addr != dma_next) ||
			    (outs->dma_length + s->length > max_seg_size) ||
			    (is_span_boundary(out_entry, base_shift,
					      seg_boundary_size, outs, s))) {
				/* Can't merge: create a new segment */
				segstart = s;
				outcount++;
				outs = sg_next(outs);
			} else {
				outs->dma_length += s->length;
			}
		}

		if (segstart == s) {
			/* This is a new segment, fill entries */
			outs->dma_address = dma_addr;
			outs->dma_length = slen;
			out_entry = entry;
		}

		/* Calculate next page pointer for contiguous check */
		dma_next = dma_addr + slen;
	}

	err = iommu_batch_end();

	if (unlikely(err < 0L))
		goto iommu_map_failed;

	spin_unlock_irqrestore(&iommu->lock, flags);

	if (outcount < incount) {
		outs = sg_next(outs);
		outs->dma_address = DMA_ERROR_CODE;
		outs->dma_length = 0;
	}

	return outcount;

iommu_map_failed:
	for_each_sg(sglist, s, nelems, i) {
		if (s->dma_length != 0) {
			unsigned long vaddr, npages;

			vaddr = s->dma_address & IO_PAGE_MASK;
			npages = iommu_num_pages(s->dma_address, s->dma_length,
						 IO_PAGE_SIZE);
			iommu_range_free(iommu, vaddr, npages);
			/* XXX demap? XXX */
			s->dma_address = DMA_ERROR_CODE;
			s->dma_length = 0;
		}
		if (s == outs)
			break;
	}
	spin_unlock_irqrestore(&iommu->lock, flags);

	return 0;
}

static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist,
			    int nelems, enum dma_data_direction direction)
{
	struct pci_pbm_info *pbm;
	struct scatterlist *sg;
	struct iommu *iommu;
	unsigned long flags;
	u32 devhandle;

	BUG_ON(direction == DMA_NONE);

	iommu = dev->archdata.iommu;
	pbm = dev->archdata.host_controller;
	devhandle = pbm->devhandle;
	
	spin_lock_irqsave(&iommu->lock, flags);

	sg = sglist;
	while (nelems--) {
		dma_addr_t dma_handle = sg->dma_address;
		unsigned int len = sg->dma_length;
		unsigned long npages, entry;

		if (!len)
			break;
		npages = iommu_num_pages(dma_handle, len, IO_PAGE_SIZE);
		iommu_range_free(iommu, dma_handle, npages);

		entry = ((dma_handle - iommu->page_table_map_base) >> IO_PAGE_SHIFT);
		while (npages) {
			unsigned long num;

			num = pci_sun4v_iommu_demap(devhandle, HV_PCI_TSBID(0, entry),
						    npages);
			entry += num;
			npages -= num;
		}

		sg = sg_next(sg);
	}

	spin_unlock_irqrestore(&iommu->lock, flags);
}

static void dma_4v_sync_single_for_cpu(struct device *dev,
				       dma_addr_t bus_addr, size_t sz,
				       enum dma_data_direction direction)
{
	/* Nothing to do... */
}

static void dma_4v_sync_sg_for_cpu(struct device *dev,
				   struct scatterlist *sglist, int nelems,
				   enum dma_data_direction direction)
{
	/* Nothing to do... */
}

static const struct dma_ops sun4v_dma_ops = {
	.alloc_coherent			= dma_4v_alloc_coherent,
	.free_coherent			= dma_4v_free_coherent,
	.map_single			= dma_4v_map_single,
	.unmap_single			= dma_4v_unmap_single,
	.map_sg				= dma_4v_map_sg,
	.unmap_sg			= dma_4v_unmap_sg,
	.sync_single_for_cpu		= dma_4v_sync_single_for_cpu,
	.sync_sg_for_cpu		= dma_4v_sync_sg_for_cpu,
};

static void __init pci_sun4v_scan_bus(struct pci_pbm_info *pbm,
				      struct device *parent)
{
	struct property *prop;
	struct device_node *dp;

	dp = pbm->op->node;
	prop = of_find_property(dp, "66mhz-capable", NULL);
	pbm->is_66mhz_capable = (prop != NULL);
	pbm->pci_bus = pci_scan_one_pbm(pbm, parent);

	/* XXX register error interrupt handlers XXX */
}

static unsigned long __init probe_existing_entries(struct pci_pbm_info *pbm,
						   struct iommu *iommu)
{
	struct iommu_arena *arena = &iommu->arena;
	unsigned long i, cnt = 0;
	u32 devhandle;

	devhandle = pbm->devhandle;
	for (i = 0; i < arena->limit; i++) {
		unsigned long ret, io_attrs, ra;

		ret = pci_sun4v_iommu_getmap(devhandle,
					     HV_PCI_TSBID(0, i),
					     &io_attrs, &ra);
		if (ret == HV_EOK) {
			if (page_in_phys_avail(ra)) {
				pci_sun4v_iommu_demap(devhandle,
						      HV_PCI_TSBID(0, i), 1);
			} else {
				cnt++;
				__set_bit(i, arena->map);
			}
		}
	}

	return cnt;
}

static int __init pci_sun4v_iommu_init(struct pci_pbm_info *pbm)
{
	static const u32 vdma_default[] = { 0x80000000, 0x80000000 };
	struct iommu *iommu = pbm->iommu;
	unsigned long num_tsb_entries, sz, tsbsize;
	u32 dma_mask, dma_offset;
	const u32 *vdma;

	vdma = of_get_property(pbm->op->node, "virtual-dma", NULL);
	if (!vdma)
		vdma = vdma_default;

	if ((vdma[0] | vdma[1]) & ~IO_PAGE_MASK) {
		printk(KERN_ERR PFX "Strange virtual-dma[%08x:%08x].\n",
		       vdma[0], vdma[1]);
		return -EINVAL;
	};

	dma_mask = (roundup_pow_of_two(vdma[1]) - 1UL);
	num_tsb_entries = vdma[1] / IO_PAGE_SIZE;
	tsbsize = num_tsb_entries * sizeof(iopte_t);

	dma_offset = vdma[0];

	/* Setup initial software IOMMU state. */
	spin_lock_init(&iommu->lock);
	iommu->ctx_lowest_free = 1;
	iommu->page_table_map_base = dma_offset;
	iommu->dma_addr_mask = dma_mask;

	/* Allocate and initialize the free area map.  */
	sz = (num_tsb_entries + 7) / 8;
	sz = (sz + 7UL) & ~7UL;
	iommu->arena.map = kzalloc(sz, GFP_KERNEL);
	if (!iommu->arena.map) {
		printk(KERN_ERR PFX "Error, kmalloc(arena.map) failed.\n");
		return -ENOMEM;
	}
	iommu->arena.limit = num_tsb_entries;

	sz = probe_existing_entries(pbm, iommu);
	if (sz)
		printk("%s: Imported %lu TSB entries from OBP\n",
		       pbm->name, sz);

	return 0;
}

#ifdef CONFIG_PCI_MSI
struct pci_sun4v_msiq_entry {
	u64		version_type;
#define MSIQ_VERSION_MASK		0xffffffff00000000UL
#define MSIQ_VERSION_SHIFT		32
#define MSIQ_TYPE_MASK			0x00000000000000ffUL
#define MSIQ_TYPE_SHIFT			0
#define MSIQ_TYPE_NONE			0x00
#define MSIQ_TYPE_MSG			0x01
#define MSIQ_TYPE_MSI32			0x02
#define MSIQ_TYPE_MSI64			0x03
#define MSIQ_TYPE_INTX			0x08
#define MSIQ_TYPE_NONE2			0xff

	u64		intx_sysino;
	u64		reserved1;
	u64		stick;
	u64		req_id;  /* bus/device/func */
#define MSIQ_REQID_BUS_MASK		0xff00UL
#define MSIQ_REQID_BUS_SHIFT		8
#define MSIQ_REQID_DEVICE_MASK		0x00f8UL
#define MSIQ_REQID_DEVICE_SHIFT		3
#define MSIQ_REQID_FUNC_MASK		0x0007UL
#define MSIQ_REQID_FUNC_SHIFT		0

	u64		msi_address;

	/* The format of this value is message type dependent.
	 * For MSI bits 15:0 are the data from the MSI packet.
	 * For MSI-X bits 31:0 are the data from the MSI packet.
	 * For MSG, the message code and message routing code where:
	 * 	bits 39:32 is the bus/device/fn of the msg target-id
	 *	bits 18:16 is the message routing code
	 *	bits 7:0 is the message code
	 * For INTx the low order 2-bits are:
	 *	00 - INTA
	 *	01 - INTB
	 *	10 - INTC
	 *	11 - INTD
	 */
	u64		msi_data;

	u64		reserved2;
};

static int pci_sun4v_get_head(struct pci_pbm_info *pbm, unsigned long msiqid,
			      unsigned long *head)
{
	unsigned long err, limit;

	err = pci_sun4v_msiq_gethead(pbm->devhandle, msiqid, head);
	if (unlikely(err))
		return -ENXIO;

	limit = pbm->msiq_ent_count * sizeof(struct pci_sun4v_msiq_entry);
	if (unlikely(*head >= limit))
		return -EFBIG;

	return 0;
}

static int pci_sun4v_dequeue_msi(struct pci_pbm_info *pbm,
				 unsigned long msiqid, unsigned long *head,
				 unsigned long *msi)
{
	struct pci_sun4v_msiq_entry *ep;
	unsigned long err, type;

	/* Note: void pointer arithmetic, 'head' is a byte offset  */
	ep = (pbm->msi_queues + ((msiqid - pbm->msiq_first) *
				 (pbm->msiq_ent_count *
				  sizeof(struct pci_sun4v_msiq_entry))) +
	      *head);

	if ((ep->version_type & MSIQ_TYPE_MASK) == 0)
		return 0;

	type = (ep->version_type & MSIQ_TYPE_MASK) >> MSIQ_TYPE_SHIFT;
	if (unlikely(type != MSIQ_TYPE_MSI32 &&
		     type != MSIQ_TYPE_MSI64))
		return -EINVAL;

	*msi = ep->msi_data;

	err = pci_sun4v_msi_setstate(pbm->devhandle,
				     ep->msi_data /* msi_num */,
				     HV_MSISTATE_IDLE);
	if (unlikely(err))
		return -ENXIO;

	/* Clear the entry.  */
	ep->version_type &= ~MSIQ_TYPE_MASK;

	(*head) += sizeof(struct pci_sun4v_msiq_entry);
	if (*head >=
	    (pbm->msiq_ent_count * sizeof(struct pci_sun4v_msiq_entry)))
		*head = 0;

	return 1;
}

static int pci_sun4v_set_head(struct pci_pbm_info *pbm, unsigned long msiqid,
			      unsigned long head)
{
	unsigned long err;

	err = pci_sun4v_msiq_sethead(pbm->devhandle, msiqid, head);
	if (unlikely(err))
		return -EINVAL;

	return 0;
}

static int pci_sun4v_msi_setup(struct pci_pbm_info *pbm, unsigned long msiqid,
			       unsigned long msi, int is_msi64)
{
	if (pci_sun4v_msi_setmsiq(pbm->devhandle, msi, msiqid,
				  (is_msi64 ?
				   HV_MSITYPE_MSI64 : HV_MSITYPE_MSI32)))
		return -ENXIO;
	if (pci_sun4v_msi_setstate(pbm->devhandle, msi, HV_MSISTATE_IDLE))
		return -ENXIO;
	if (pci_sun4v_msi_setvalid(pbm->devhandle, msi, HV_MSIVALID_VALID))
		return -ENXIO;
	return 0;
}

static int pci_sun4v_msi_teardown(struct pci_pbm_info *pbm, unsigned long msi)
{
	unsigned long err, msiqid;

	err = pci_sun4v_msi_getmsiq(pbm->devhandle, msi, &msiqid);
	if (err)
		return -ENXIO;

	pci_sun4v_msi_setvalid(pbm->devhandle, msi, HV_MSIVALID_INVALID);

	return 0;
}

static int pci_sun4v_msiq_alloc(struct pci_pbm_info *pbm)
{
	unsigned long q_size, alloc_size, pages, order;
	int i;

	q_size = pbm->msiq_ent_count * sizeof(struct pci_sun4v_msiq_entry);
	alloc_size = (pbm->msiq_num * q_size);
	order = get_order(alloc_size);
	pages = __get_free_pages(GFP_KERNEL | __GFP_COMP, order);
	if (pages == 0UL) {
		printk(KERN_ERR "MSI: Cannot allocate MSI queues (o=%lu).\n",
		       order);
		return -ENOMEM;
	}
	memset((char *)pages, 0, PAGE_SIZE << order);
	pbm->msi_queues = (void *) pages;

	for (i = 0; i < pbm->msiq_num; i++) {
		unsigned long err, base = __pa(pages + (i * q_size));
		unsigned long ret1, ret2;

		err = pci_sun4v_msiq_conf(pbm->devhandle,
					  pbm->msiq_first + i,
					  base, pbm->msiq_ent_count);
		if (err) {
			printk(KERN_ERR "MSI: msiq register fails (err=%lu)\n",
			       err);
			goto h_error;
		}

		err = pci_sun4v_msiq_info(pbm->devhandle,
					  pbm->msiq_first + i,
					  &ret1, &ret2);
		if (err) {
			printk(KERN_ERR "MSI: Cannot read msiq (err=%lu)\n",
			       err);
			goto h_error;
		}
		if (ret1 != base || ret2 != pbm->msiq_ent_count) {
			printk(KERN_ERR "MSI: Bogus qconf "
			       "expected[%lx:%x] got[%lx:%lx]\n",
			       base, pbm->msiq_ent_count,
			       ret1, ret2);
			goto h_error;
		}
	}

	return 0;

h_error:
	free_pages(pages, order);
	return -EINVAL;
}

static void pci_sun4v_msiq_free(struct pci_pbm_info *pbm)
{
	unsigned long q_size, alloc_size, pages, order;
	int i;

	for (i = 0; i < pbm->msiq_num; i++) {
		unsigned long msiqid = pbm->msiq_first + i;

		(void) pci_sun4v_msiq_conf(pbm->devhandle, msiqid, 0UL, 0);
	}

	q_size = pbm->msiq_ent_count * sizeof(struct pci_sun4v_msiq_entry);
	alloc_size = (pbm->msiq_num * q_size);
	order = get_order(alloc_size);

	pages = (unsigned long) pbm->msi_queues;

	free_pages(pages, order);

	pbm->msi_queues = NULL;
}

static int pci_sun4v_msiq_build_irq(struct pci_pbm_info *pbm,
				    unsigned long msiqid,
				    unsigned long devino)
{
	unsigned int virt_irq = sun4v_build_irq(pbm->devhandle, devino);

	if (!virt_irq)
		return -ENOMEM;

	if (pci_sun4v_msiq_setstate(pbm->devhandle, msiqid, HV_MSIQSTATE_IDLE))
		return -EINVAL;
	if (pci_sun4v_msiq_setvalid(pbm->devhandle, msiqid, HV_MSIQ_VALID))
		return -EINVAL;

	return virt_irq;
}

static const struct sparc64_msiq_ops pci_sun4v_msiq_ops = {
	.get_head	=	pci_sun4v_get_head,
	.dequeue_msi	=	pci_sun4v_dequeue_msi,
	.set_head	=	pci_sun4v_set_head,
	.msi_setup	=	pci_sun4v_msi_setup,
	.msi_teardown	=	pci_sun4v_msi_teardown,
	.msiq_alloc	=	pci_sun4v_msiq_alloc,
	.msiq_free	=	pci_sun4v_msiq_free,
	.msiq_build_irq	=	pci_sun4v_msiq_build_irq,
};

static void pci_sun4v_msi_init(struct pci_pbm_info *pbm)
{
	sparc64_pbm_msi_init(pbm, &pci_sun4v_msiq_ops);
}
#else /* CONFIG_PCI_MSI */
static void pci_sun4v_msi_init(struct pci_pbm_info *pbm)
{
}
#endif /* !(CONFIG_PCI_MSI) */

static int __init pci_sun4v_pbm_init(struct pci_pbm_info *pbm,
				     struct of_device *op, u32 devhandle)
{
	struct device_node *dp = op->node;
	int err;

	pbm->numa_node = of_node_to_nid(dp);

	pbm->pci_ops = &sun4v_pci_ops;
	pbm->config_space_reg_bits = 12;

	pbm->index = pci_num_pbms++;

	pbm->op = op;

	pbm->devhandle = devhandle;

	pbm->name = dp->full_name;

	printk("%s: SUN4V PCI Bus Module\n", pbm->name);
	printk("%s: On NUMA node %d\n", pbm->name, pbm->numa_node);

	pci_determine_mem_io_space(pbm);

	pci_get_pbm_props(pbm);

	err = pci_sun4v_iommu_init(pbm);
	if (err)
		return err;

	pci_sun4v_msi_init(pbm);

	pci_sun4v_scan_bus(pbm, &op->dev);

	pbm->next = pci_pbm_root;
	pci_pbm_root = pbm;

	return 0;
}

static int __init pci_sun4v_probe(struct of_device *op,
				     const struct of_device_id *match)
{
	const struct linux_prom64_registers *regs;
	static int hvapi_negotiated = 0;
	struct pci_pbm_info *pbm;
	struct device_node *dp;
	struct iommu *iommu;
	u32 devhandle;
	int i, err;

	dp = op->node;

	if (!hvapi_negotiated++) {
		err = sun4v_hvapi_register(HV_GRP_PCI,
					   vpci_major,
					   &vpci_minor);

		if (err) {
			printk(KERN_ERR PFX "Could not register hvapi, "
			       "err=%d\n", err);
			return err;
		}
		printk(KERN_INFO PFX "Registered hvapi major[%lu] minor[%lu]\n",
		       vpci_major, vpci_minor);

		dma_ops = &sun4v_dma_ops;
	}

	regs = of_get_property(dp, "reg", NULL);
	err = -ENODEV;
	if (!regs) {
		printk(KERN_ERR PFX "Could not find config registers\n");
		goto out_err;
	}
	devhandle = (regs->phys_addr >> 32UL) & 0x0fffffff;

	err = -ENOMEM;
	if (!iommu_batch_initialized) {
		for_each_possible_cpu(i) {
			unsigned long page = get_zeroed_page(GFP_KERNEL);

			if (!page)
				goto out_err;

			per_cpu(iommu_batch, i).pglist = (u64 *) page;
		}
		iommu_batch_initialized = 1;
	}

	pbm = kzalloc(sizeof(*pbm), GFP_KERNEL);
	if (!pbm) {
		printk(KERN_ERR PFX "Could not allocate pci_pbm_info\n");
		goto out_err;
	}

	iommu = kzalloc(sizeof(struct iommu), GFP_KERNEL);
	if (!iommu) {
		printk(KERN_ERR PFX "Could not allocate pbm iommu\n");
		goto out_free_controller;
	}

	pbm->iommu = iommu;

	err = pci_sun4v_pbm_init(pbm, op, devhandle);
	if (err)
		goto out_free_iommu;

	dev_set_drvdata(&op->dev, pbm);

	return 0;

out_free_iommu:
	kfree(pbm->iommu);

out_free_controller:
	kfree(pbm);

out_err:
	return err;
}

static struct of_device_id __initdata pci_sun4v_match[] = {
	{
		.name = "pci",
		.compatible = "SUNW,sun4v-pci",
	},
	{},
};

static struct of_platform_driver pci_sun4v_driver = {
	.name		= DRIVER_NAME,
	.match_table	= pci_sun4v_match,
	.probe		= pci_sun4v_probe,
};

static int __init pci_sun4v_init(void)
{
	return of_register_driver(&pci_sun4v_driver, &of_bus_type);
}

subsys_initcall(pci_sun4v_init);