summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/sysdev/xive/spapr.c
blob: 7d5128676e830082ba1a21436aa8b99dc2dd12b9 (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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Copyright 2016,2017 IBM Corporation.
 */

#define pr_fmt(fmt) "xive: " fmt

#include <linux/types.h>
#include <linux/irq.h>
#include <linux/smp.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/of.h>
#include <linux/of_address.h>
#include <linux/of_fdt.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/cpumask.h>
#include <linux/mm.h>
#include <linux/delay.h>
#include <linux/libfdt.h>

#include <asm/machdep.h>
#include <asm/prom.h>
#include <asm/io.h>
#include <asm/smp.h>
#include <asm/irq.h>
#include <asm/errno.h>
#include <asm/xive.h>
#include <asm/xive-regs.h>
#include <asm/hvcall.h>
#include <asm/svm.h>
#include <asm/ultravisor.h>

#include "xive-internal.h"

static u32 xive_queue_shift;

struct xive_irq_bitmap {
	unsigned long		*bitmap;
	unsigned int		base;
	unsigned int		count;
	spinlock_t		lock;
	struct list_head	list;
};

static LIST_HEAD(xive_irq_bitmaps);

static int __init xive_irq_bitmap_add(int base, int count)
{
	struct xive_irq_bitmap *xibm;

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

	spin_lock_init(&xibm->lock);
	xibm->base = base;
	xibm->count = count;
	xibm->bitmap = kzalloc(xibm->count, GFP_KERNEL);
	if (!xibm->bitmap) {
		kfree(xibm);
		return -ENOMEM;
	}
	list_add(&xibm->list, &xive_irq_bitmaps);

	pr_info("Using IRQ range [%x-%x]", xibm->base,
		xibm->base + xibm->count - 1);
	return 0;
}

static void xive_irq_bitmap_remove_all(void)
{
	struct xive_irq_bitmap *xibm, *tmp;

	list_for_each_entry_safe(xibm, tmp, &xive_irq_bitmaps, list) {
		list_del(&xibm->list);
		kfree(xibm->bitmap);
		kfree(xibm);
	}
}

static int __xive_irq_bitmap_alloc(struct xive_irq_bitmap *xibm)
{
	int irq;

	irq = find_first_zero_bit(xibm->bitmap, xibm->count);
	if (irq != xibm->count) {
		set_bit(irq, xibm->bitmap);
		irq += xibm->base;
	} else {
		irq = -ENOMEM;
	}

	return irq;
}

static int xive_irq_bitmap_alloc(void)
{
	struct xive_irq_bitmap *xibm;
	unsigned long flags;
	int irq = -ENOENT;

	list_for_each_entry(xibm, &xive_irq_bitmaps, list) {
		spin_lock_irqsave(&xibm->lock, flags);
		irq = __xive_irq_bitmap_alloc(xibm);
		spin_unlock_irqrestore(&xibm->lock, flags);
		if (irq >= 0)
			break;
	}
	return irq;
}

static void xive_irq_bitmap_free(int irq)
{
	unsigned long flags;
	struct xive_irq_bitmap *xibm;

	list_for_each_entry(xibm, &xive_irq_bitmaps, list) {
		if ((irq >= xibm->base) && (irq < xibm->base + xibm->count)) {
			spin_lock_irqsave(&xibm->lock, flags);
			clear_bit(irq - xibm->base, xibm->bitmap);
			spin_unlock_irqrestore(&xibm->lock, flags);
			break;
		}
	}
}


/* Based on the similar routines in RTAS */
static unsigned int plpar_busy_delay_time(long rc)
{
	unsigned int ms = 0;

	if (H_IS_LONG_BUSY(rc)) {
		ms = get_longbusy_msecs(rc);
	} else if (rc == H_BUSY) {
		ms = 10; /* seems appropriate for XIVE hcalls */
	}

	return ms;
}

static unsigned int plpar_busy_delay(int rc)
{
	unsigned int ms;

	ms = plpar_busy_delay_time(rc);
	if (ms)
		mdelay(ms);

	return ms;
}

/*
 * Note: this call has a partition wide scope and can take a while to
 * complete. If it returns H_LONG_BUSY_* it should be retried
 * periodically.
 */
static long plpar_int_reset(unsigned long flags)
{
	long rc;

	do {
		rc = plpar_hcall_norets(H_INT_RESET, flags);
	} while (plpar_busy_delay(rc));

	if (rc)
		pr_err("H_INT_RESET failed %ld\n", rc);

	return rc;
}

static long plpar_int_get_source_info(unsigned long flags,
				      unsigned long lisn,
				      unsigned long *src_flags,
				      unsigned long *eoi_page,
				      unsigned long *trig_page,
				      unsigned long *esb_shift)
{
	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
	long rc;

	do {
		rc = plpar_hcall(H_INT_GET_SOURCE_INFO, retbuf, flags, lisn);
	} while (plpar_busy_delay(rc));

	if (rc) {
		pr_err("H_INT_GET_SOURCE_INFO lisn=0x%lx failed %ld\n", lisn, rc);
		return rc;
	}

	*src_flags = retbuf[0];
	*eoi_page  = retbuf[1];
	*trig_page = retbuf[2];
	*esb_shift = retbuf[3];

	pr_debug("H_INT_GET_SOURCE_INFO lisn=0x%lx flags=0x%lx eoi=0x%lx trig=0x%lx shift=0x%lx\n",
		 lisn, retbuf[0], retbuf[1], retbuf[2], retbuf[3]);

	return 0;
}

#define XIVE_SRC_SET_EISN (1ull << (63 - 62))
#define XIVE_SRC_MASK     (1ull << (63 - 63)) /* unused */

static long plpar_int_set_source_config(unsigned long flags,
					unsigned long lisn,
					unsigned long target,
					unsigned long prio,
					unsigned long sw_irq)
{
	long rc;


	pr_debug("H_INT_SET_SOURCE_CONFIG flags=0x%lx lisn=0x%lx target=%ld prio=%ld sw_irq=%ld\n",
		 flags, lisn, target, prio, sw_irq);


	do {
		rc = plpar_hcall_norets(H_INT_SET_SOURCE_CONFIG, flags, lisn,
					target, prio, sw_irq);
	} while (plpar_busy_delay(rc));

	if (rc) {
		pr_err("H_INT_SET_SOURCE_CONFIG lisn=0x%lx target=%ld prio=%ld failed %ld\n",
		       lisn, target, prio, rc);
		return rc;
	}

	return 0;
}

static long plpar_int_get_source_config(unsigned long flags,
					unsigned long lisn,
					unsigned long *target,
					unsigned long *prio,
					unsigned long *sw_irq)
{
	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
	long rc;

	pr_debug("H_INT_GET_SOURCE_CONFIG flags=0x%lx lisn=0x%lx\n", flags, lisn);

	do {
		rc = plpar_hcall(H_INT_GET_SOURCE_CONFIG, retbuf, flags, lisn,
				 target, prio, sw_irq);
	} while (plpar_busy_delay(rc));

	if (rc) {
		pr_err("H_INT_GET_SOURCE_CONFIG lisn=0x%lx failed %ld\n",
		       lisn, rc);
		return rc;
	}

	*target = retbuf[0];
	*prio   = retbuf[1];
	*sw_irq = retbuf[2];

	pr_debug("H_INT_GET_SOURCE_CONFIG target=%ld prio=%ld sw_irq=%ld\n",
		 retbuf[0], retbuf[1], retbuf[2]);

	return 0;
}

static long plpar_int_get_queue_info(unsigned long flags,
				     unsigned long target,
				     unsigned long priority,
				     unsigned long *esn_page,
				     unsigned long *esn_size)
{
	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
	long rc;

	do {
		rc = plpar_hcall(H_INT_GET_QUEUE_INFO, retbuf, flags, target,
				 priority);
	} while (plpar_busy_delay(rc));

	if (rc) {
		pr_err("H_INT_GET_QUEUE_INFO cpu=%ld prio=%ld failed %ld\n",
		       target, priority, rc);
		return rc;
	}

	*esn_page = retbuf[0];
	*esn_size = retbuf[1];

	pr_debug("H_INT_GET_QUEUE_INFO cpu=%ld prio=%ld page=0x%lx size=0x%lx\n",
		 target, priority, retbuf[0], retbuf[1]);

	return 0;
}

#define XIVE_EQ_ALWAYS_NOTIFY (1ull << (63 - 63))

static long plpar_int_set_queue_config(unsigned long flags,
				       unsigned long target,
				       unsigned long priority,
				       unsigned long qpage,
				       unsigned long qsize)
{
	long rc;

	pr_debug("H_INT_SET_QUEUE_CONFIG flags=0x%lx target=%ld priority=0x%lx qpage=0x%lx qsize=0x%lx\n",
		 flags,  target, priority, qpage, qsize);

	do {
		rc = plpar_hcall_norets(H_INT_SET_QUEUE_CONFIG, flags, target,
					priority, qpage, qsize);
	} while (plpar_busy_delay(rc));

	if (rc) {
		pr_err("H_INT_SET_QUEUE_CONFIG cpu=%ld prio=%ld qpage=0x%lx returned %ld\n",
		       target, priority, qpage, rc);
		return  rc;
	}

	return 0;
}

static long plpar_int_sync(unsigned long flags, unsigned long lisn)
{
	long rc;

	do {
		rc = plpar_hcall_norets(H_INT_SYNC, flags, lisn);
	} while (plpar_busy_delay(rc));

	if (rc) {
		pr_err("H_INT_SYNC lisn=0x%lx returned %ld\n", lisn, rc);
		return  rc;
	}

	return 0;
}

#define XIVE_ESB_FLAG_STORE (1ull << (63 - 63))

static long plpar_int_esb(unsigned long flags,
			  unsigned long lisn,
			  unsigned long offset,
			  unsigned long in_data,
			  unsigned long *out_data)
{
	unsigned long retbuf[PLPAR_HCALL_BUFSIZE];
	long rc;

	pr_debug("H_INT_ESB flags=0x%lx lisn=0x%lx offset=0x%lx in=0x%lx\n",
		 flags,  lisn, offset, in_data);

	do {
		rc = plpar_hcall(H_INT_ESB, retbuf, flags, lisn, offset,
				 in_data);
	} while (plpar_busy_delay(rc));

	if (rc) {
		pr_err("H_INT_ESB lisn=0x%lx offset=0x%lx returned %ld\n",
		       lisn, offset, rc);
		return  rc;
	}

	*out_data = retbuf[0];

	return 0;
}

static u64 xive_spapr_esb_rw(u32 lisn, u32 offset, u64 data, bool write)
{
	unsigned long read_data;
	long rc;

	rc = plpar_int_esb(write ? XIVE_ESB_FLAG_STORE : 0,
			   lisn, offset, data, &read_data);
	if (rc)
		return -1;

	return write ? 0 : read_data;
}

#define XIVE_SRC_H_INT_ESB     (1ull << (63 - 60))
#define XIVE_SRC_LSI           (1ull << (63 - 61))
#define XIVE_SRC_TRIGGER       (1ull << (63 - 62))
#define XIVE_SRC_STORE_EOI     (1ull << (63 - 63))

static int xive_spapr_populate_irq_data(u32 hw_irq, struct xive_irq_data *data)
{
	long rc;
	unsigned long flags;
	unsigned long eoi_page;
	unsigned long trig_page;
	unsigned long esb_shift;

	memset(data, 0, sizeof(*data));

	rc = plpar_int_get_source_info(0, hw_irq, &flags, &eoi_page, &trig_page,
				       &esb_shift);
	if (rc)
		return  -EINVAL;

	if (flags & XIVE_SRC_H_INT_ESB)
		data->flags  |= XIVE_IRQ_FLAG_H_INT_ESB;
	if (flags & XIVE_SRC_STORE_EOI)
		data->flags  |= XIVE_IRQ_FLAG_STORE_EOI;
	if (flags & XIVE_SRC_LSI)
		data->flags  |= XIVE_IRQ_FLAG_LSI;
	data->eoi_page  = eoi_page;
	data->esb_shift = esb_shift;
	data->trig_page = trig_page;

	data->hw_irq = hw_irq;

	/*
	 * No chip-id for the sPAPR backend. This has an impact how we
	 * pick a target. See xive_pick_irq_target().
	 */
	data->src_chip = XIVE_INVALID_CHIP_ID;

	/*
	 * When the H_INT_ESB flag is set, the H_INT_ESB hcall should
	 * be used for interrupt management. Skip the remapping of the
	 * ESB pages which are not available.
	 */
	if (data->flags & XIVE_IRQ_FLAG_H_INT_ESB)
		return 0;

	data->eoi_mmio = ioremap(data->eoi_page, 1u << data->esb_shift);
	if (!data->eoi_mmio) {
		pr_err("Failed to map EOI page for irq 0x%x\n", hw_irq);
		return -ENOMEM;
	}

	/* Full function page supports trigger */
	if (flags & XIVE_SRC_TRIGGER) {
		data->trig_mmio = data->eoi_mmio;
		return 0;
	}

	data->trig_mmio = ioremap(data->trig_page, 1u << data->esb_shift);
	if (!data->trig_mmio) {
		pr_err("Failed to map trigger page for irq 0x%x\n", hw_irq);
		return -ENOMEM;
	}
	return 0;
}

static int xive_spapr_configure_irq(u32 hw_irq, u32 target, u8 prio, u32 sw_irq)
{
	long rc;

	rc = plpar_int_set_source_config(XIVE_SRC_SET_EISN, hw_irq, target,
					 prio, sw_irq);

	return rc == 0 ? 0 : -ENXIO;
}

static int xive_spapr_get_irq_config(u32 hw_irq, u32 *target, u8 *prio,
				     u32 *sw_irq)
{
	long rc;
	unsigned long h_target;
	unsigned long h_prio;
	unsigned long h_sw_irq;

	rc = plpar_int_get_source_config(0, hw_irq, &h_target, &h_prio,
					 &h_sw_irq);

	*target = h_target;
	*prio = h_prio;
	*sw_irq = h_sw_irq;

	return rc == 0 ? 0 : -ENXIO;
}

/* This can be called multiple time to change a queue configuration */
static int xive_spapr_configure_queue(u32 target, struct xive_q *q, u8 prio,
				   __be32 *qpage, u32 order)
{
	s64 rc = 0;
	unsigned long esn_page;
	unsigned long esn_size;
	u64 flags, qpage_phys;

	/* If there's an actual queue page, clean it */
	if (order) {
		if (WARN_ON(!qpage))
			return -EINVAL;
		qpage_phys = __pa(qpage);
	} else {
		qpage_phys = 0;
	}

	/* Initialize the rest of the fields */
	q->msk = order ? ((1u << (order - 2)) - 1) : 0;
	q->idx = 0;
	q->toggle = 0;

	rc = plpar_int_get_queue_info(0, target, prio, &esn_page, &esn_size);
	if (rc) {
		pr_err("Error %lld getting queue info CPU %d prio %d\n", rc,
		       target, prio);
		rc = -EIO;
		goto fail;
	}

	/* TODO: add support for the notification page */
	q->eoi_phys = esn_page;

	/* Default is to always notify */
	flags = XIVE_EQ_ALWAYS_NOTIFY;

	/* Configure and enable the queue in HW */
	rc = plpar_int_set_queue_config(flags, target, prio, qpage_phys, order);
	if (rc) {
		pr_err("Error %lld setting queue for CPU %d prio %d\n", rc,
		       target, prio);
		rc = -EIO;
	} else {
		q->qpage = qpage;
		if (is_secure_guest())
			uv_share_page(PHYS_PFN(qpage_phys),
					1 << xive_alloc_order(order));
	}
fail:
	return rc;
}

static int xive_spapr_setup_queue(unsigned int cpu, struct xive_cpu *xc,
				  u8 prio)
{
	struct xive_q *q = &xc->queue[prio];
	__be32 *qpage;

	qpage = xive_queue_page_alloc(cpu, xive_queue_shift);
	if (IS_ERR(qpage))
		return PTR_ERR(qpage);

	return xive_spapr_configure_queue(get_hard_smp_processor_id(cpu),
					  q, prio, qpage, xive_queue_shift);
}

static void xive_spapr_cleanup_queue(unsigned int cpu, struct xive_cpu *xc,
				  u8 prio)
{
	struct xive_q *q = &xc->queue[prio];
	unsigned int alloc_order;
	long rc;
	int hw_cpu = get_hard_smp_processor_id(cpu);

	rc = plpar_int_set_queue_config(0, hw_cpu, prio, 0, 0);
	if (rc)
		pr_err("Error %ld setting queue for CPU %d prio %d\n", rc,
		       hw_cpu, prio);

	alloc_order = xive_alloc_order(xive_queue_shift);
	if (is_secure_guest())
		uv_unshare_page(PHYS_PFN(__pa(q->qpage)), 1 << alloc_order);
	free_pages((unsigned long)q->qpage, alloc_order);
	q->qpage = NULL;
}

static bool xive_spapr_match(struct device_node *node)
{
	/* Ignore cascaded controllers for the moment */
	return true;
}

#ifdef CONFIG_SMP
static int xive_spapr_get_ipi(unsigned int cpu, struct xive_cpu *xc)
{
	int irq = xive_irq_bitmap_alloc();

	if (irq < 0) {
		pr_err("Failed to allocate IPI on CPU %d\n", cpu);
		return -ENXIO;
	}

	xc->hw_ipi = irq;
	return 0;
}

static void xive_spapr_put_ipi(unsigned int cpu, struct xive_cpu *xc)
{
	if (xc->hw_ipi == XIVE_BAD_IRQ)
		return;

	xive_irq_bitmap_free(xc->hw_ipi);
	xc->hw_ipi = XIVE_BAD_IRQ;
}
#endif /* CONFIG_SMP */

static void xive_spapr_shutdown(void)
{
	plpar_int_reset(0);
}

/*
 * Perform an "ack" cycle on the current thread. Grab the pending
 * active priorities and update the CPPR to the most favored one.
 */
static void xive_spapr_update_pending(struct xive_cpu *xc)
{
	u8 nsr, cppr;
	u16 ack;

	/*
	 * Perform the "Acknowledge O/S to Register" cycle.
	 *
	 * Let's speedup the access to the TIMA using the raw I/O
	 * accessor as we don't need the synchronisation routine of
	 * the higher level ones
	 */
	ack = be16_to_cpu(__raw_readw(xive_tima + TM_SPC_ACK_OS_REG));

	/* Synchronize subsequent queue accesses */
	mb();

	/*
	 * Grab the CPPR and the "NSR" field which indicates the source
	 * of the interrupt (if any)
	 */
	cppr = ack & 0xff;
	nsr = ack >> 8;

	if (nsr & TM_QW1_NSR_EO) {
		if (cppr == 0xff)
			return;
		/* Mark the priority pending */
		xc->pending_prio |= 1 << cppr;

		/*
		 * A new interrupt should never have a CPPR less favored
		 * than our current one.
		 */
		if (cppr >= xc->cppr)
			pr_err("CPU %d odd ack CPPR, got %d at %d\n",
			       smp_processor_id(), cppr, xc->cppr);

		/* Update our idea of what the CPPR is */
		xc->cppr = cppr;
	}
}

static void xive_spapr_setup_cpu(unsigned int cpu, struct xive_cpu *xc)
{
	/* Only some debug on the TIMA settings */
	pr_debug("(HW value: %08x %08x %08x)\n",
		 in_be32(xive_tima + TM_QW1_OS + TM_WORD0),
		 in_be32(xive_tima + TM_QW1_OS + TM_WORD1),
		 in_be32(xive_tima + TM_QW1_OS + TM_WORD2));
}

static void xive_spapr_teardown_cpu(unsigned int cpu, struct xive_cpu *xc)
{
	/* Nothing to do */;
}

static void xive_spapr_sync_source(u32 hw_irq)
{
	/* Specs are unclear on what this is doing */
	plpar_int_sync(0, hw_irq);
}

static int xive_spapr_debug_show(struct seq_file *m, void *private)
{
	struct xive_irq_bitmap *xibm;
	char *buf = kmalloc(PAGE_SIZE, GFP_KERNEL);

	if (!buf)
		return -ENOMEM;

	list_for_each_entry(xibm, &xive_irq_bitmaps, list) {
		memset(buf, 0, PAGE_SIZE);
		bitmap_print_to_pagebuf(true, buf, xibm->bitmap, xibm->count);
		seq_printf(m, "bitmap #%d: %s", xibm->count, buf);
	}
	kfree(buf);

	return 0;
}

static const struct xive_ops xive_spapr_ops = {
	.populate_irq_data	= xive_spapr_populate_irq_data,
	.configure_irq		= xive_spapr_configure_irq,
	.get_irq_config		= xive_spapr_get_irq_config,
	.setup_queue		= xive_spapr_setup_queue,
	.cleanup_queue		= xive_spapr_cleanup_queue,
	.match			= xive_spapr_match,
	.shutdown		= xive_spapr_shutdown,
	.update_pending		= xive_spapr_update_pending,
	.setup_cpu		= xive_spapr_setup_cpu,
	.teardown_cpu		= xive_spapr_teardown_cpu,
	.sync_source		= xive_spapr_sync_source,
	.esb_rw			= xive_spapr_esb_rw,
#ifdef CONFIG_SMP
	.get_ipi		= xive_spapr_get_ipi,
	.put_ipi		= xive_spapr_put_ipi,
	.debug_show		= xive_spapr_debug_show,
#endif /* CONFIG_SMP */
	.name			= "spapr",
};

/*
 * get max priority from "/ibm,plat-res-int-priorities"
 */
static bool __init xive_get_max_prio(u8 *max_prio)
{
	struct device_node *rootdn;
	const __be32 *reg;
	u32 len;
	int prio, found;

	rootdn = of_find_node_by_path("/");
	if (!rootdn) {
		pr_err("not root node found !\n");
		return false;
	}

	reg = of_get_property(rootdn, "ibm,plat-res-int-priorities", &len);
	if (!reg) {
		pr_err("Failed to read 'ibm,plat-res-int-priorities' property\n");
		return false;
	}

	if (len % (2 * sizeof(u32)) != 0) {
		pr_err("invalid 'ibm,plat-res-int-priorities' property\n");
		return false;
	}

	/* HW supports priorities in the range [0-7] and 0xFF is a
	 * wildcard priority used to mask. We scan the ranges reserved
	 * by the hypervisor to find the lowest priority we can use.
	 */
	found = 0xFF;
	for (prio = 0; prio < 8; prio++) {
		int reserved = 0;
		int i;

		for (i = 0; i < len / (2 * sizeof(u32)); i++) {
			int base  = be32_to_cpu(reg[2 * i]);
			int range = be32_to_cpu(reg[2 * i + 1]);

			if (prio >= base && prio < base + range)
				reserved++;
		}

		if (!reserved)
			found = prio;
	}

	if (found == 0xFF) {
		pr_err("no valid priority found in 'ibm,plat-res-int-priorities'\n");
		return false;
	}

	*max_prio = found;
	return true;
}

static const u8 *__init get_vec5_feature(unsigned int index)
{
	unsigned long root, chosen;
	int size;
	const u8 *vec5;

	root = of_get_flat_dt_root();
	chosen = of_get_flat_dt_subnode_by_name(root, "chosen");
	if (chosen == -FDT_ERR_NOTFOUND)
		return NULL;

	vec5 = of_get_flat_dt_prop(chosen, "ibm,architecture-vec-5", &size);
	if (!vec5)
		return NULL;

	if (size <= index)
		return NULL;

	return vec5 + index;
}

static bool __init xive_spapr_disabled(void)
{
	const u8 *vec5_xive;

	vec5_xive = get_vec5_feature(OV5_INDX(OV5_XIVE_SUPPORT));
	if (vec5_xive) {
		u8 val;

		val = *vec5_xive & OV5_FEAT(OV5_XIVE_SUPPORT);
		switch (val) {
		case OV5_FEAT(OV5_XIVE_EITHER):
		case OV5_FEAT(OV5_XIVE_LEGACY):
			break;
		case OV5_FEAT(OV5_XIVE_EXPLOIT):
			/* Hypervisor only supports XIVE */
			if (xive_cmdline_disabled)
				pr_warn("WARNING: Ignoring cmdline option xive=off\n");
			return false;
		default:
			pr_warn("%s: Unknown xive support option: 0x%x\n",
				__func__, val);
			break;
		}
	}

	return xive_cmdline_disabled;
}

bool __init xive_spapr_init(void)
{
	struct device_node *np;
	struct resource r;
	void __iomem *tima;
	struct property *prop;
	u8 max_prio;
	u32 val;
	u32 len;
	const __be32 *reg;
	int i, err;

	if (xive_spapr_disabled())
		return false;

	pr_devel("%s()\n", __func__);
	np = of_find_compatible_node(NULL, NULL, "ibm,power-ivpe");
	if (!np) {
		pr_devel("not found !\n");
		return false;
	}
	pr_devel("Found %s\n", np->full_name);

	/* Resource 1 is the OS ring TIMA */
	if (of_address_to_resource(np, 1, &r)) {
		pr_err("Failed to get thread mgmnt area resource\n");
		goto err_put;
	}
	tima = ioremap(r.start, resource_size(&r));
	if (!tima) {
		pr_err("Failed to map thread mgmnt area\n");
		goto err_put;
	}

	if (!xive_get_max_prio(&max_prio))
		goto err_unmap;

	/* Feed the IRQ number allocator with the ranges given in the DT */
	reg = of_get_property(np, "ibm,xive-lisn-ranges", &len);
	if (!reg) {
		pr_err("Failed to read 'ibm,xive-lisn-ranges' property\n");
		goto err_unmap;
	}

	if (len % (2 * sizeof(u32)) != 0) {
		pr_err("invalid 'ibm,xive-lisn-ranges' property\n");
		goto err_unmap;
	}

	for (i = 0; i < len / (2 * sizeof(u32)); i++, reg += 2) {
		err = xive_irq_bitmap_add(be32_to_cpu(reg[0]),
					  be32_to_cpu(reg[1]));
		if (err < 0)
			goto err_mem_free;
	}

	/* Iterate the EQ sizes and pick one */
	of_property_for_each_u32(np, "ibm,xive-eq-sizes", prop, reg, val) {
		xive_queue_shift = val;
		if (val == PAGE_SHIFT)
			break;
	}

	/* Initialize XIVE core with our backend */
	if (!xive_core_init(np, &xive_spapr_ops, tima, TM_QW1_OS, max_prio))
		goto err_mem_free;

	of_node_put(np);
	pr_info("Using %dkB queues\n", 1 << (xive_queue_shift - 10));
	return true;

err_mem_free:
	xive_irq_bitmap_remove_all();
err_unmap:
	iounmap(tima);
err_put:
	of_node_put(np);
	return false;
}

machine_arch_initcall(pseries, xive_core_debug_init);