aboutsummaryrefslogtreecommitdiffstats
path: root/arch/powerpc/platforms/pseries/xics.c
blob: d6901334d66ea3705cb9a3be46b5dcac37710f70 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
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
/*
 * arch/powerpc/platforms/pseries/xics.c
 *
 * Copyright 2000 IBM Corporation.
 *
 *  This program is free software; you can redistribute it and/or
 *  modify it under the terms of the GNU General Public License
 *  as published by the Free Software Foundation; either version
 *  2 of the License, or (at your option) any later version.
 */

#include <linux/types.h>
#include <linux/threads.h>
#include <linux/kernel.h>
#include <linux/irq.h>
#include <linux/smp.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/radix-tree.h>
#include <linux/cpu.h>
#include <linux/msi.h>
#include <linux/of.h>
#include <linux/percpu.h>

#include <asm/firmware.h>
#include <asm/io.h>
#include <asm/pgtable.h>
#include <asm/smp.h>
#include <asm/rtas.h>
#include <asm/hvcall.h>
#include <asm/machdep.h>

#include "xics.h"
#include "plpar_wrappers.h"

static struct irq_host *xics_host;

#define XICS_IPI		2
#define XICS_IRQ_SPURIOUS	0

/* Want a priority other than 0.  Various HW issues require this. */
#define	DEFAULT_PRIORITY	5

/*
 * Mark IPIs as higher priority so we can take them inside interrupts that
 * arent marked IRQF_DISABLED
 */
#define IPI_PRIORITY		4

/* The least favored priority */
#define LOWEST_PRIORITY		0xFF

/* The number of priorities defined above */
#define MAX_NUM_PRIORITIES	3

static unsigned int default_server = 0xFF;
static unsigned int default_distrib_server = 0;
static unsigned int interrupt_server_size = 8;

/* RTAS service tokens */
static int ibm_get_xive;
static int ibm_set_xive;
static int ibm_int_on;
static int ibm_int_off;

struct xics_cppr {
	unsigned char stack[MAX_NUM_PRIORITIES];
	int index;
};

static DEFINE_PER_CPU(struct xics_cppr, xics_cppr);

/* Direct hardware low level accessors */

/* The part of the interrupt presentation layer that we care about */
struct xics_ipl {
	union {
		u32 word;
		u8 bytes[4];
	} xirr_poll;
	union {
		u32 word;
		u8 bytes[4];
	} xirr;
	u32 dummy;
	union {
		u32 word;
		u8 bytes[4];
	} qirr;
};

static struct xics_ipl __iomem *xics_per_cpu[NR_CPUS];

static inline unsigned int direct_xirr_info_get(void)
{
	int cpu = smp_processor_id();

	return in_be32(&xics_per_cpu[cpu]->xirr.word);
}

static inline void direct_xirr_info_set(unsigned int value)
{
	int cpu = smp_processor_id();

	out_be32(&xics_per_cpu[cpu]->xirr.word, value);
}

static inline void direct_cppr_info(u8 value)
{
	int cpu = smp_processor_id();

	out_8(&xics_per_cpu[cpu]->xirr.bytes[0], value);
}

static inline void direct_qirr_info(int n_cpu, u8 value)
{
	out_8(&xics_per_cpu[n_cpu]->qirr.bytes[0], value);
}


/* LPAR low level accessors */

static inline unsigned int lpar_xirr_info_get(unsigned char cppr)
{
	unsigned long lpar_rc;
	unsigned long return_value;

	lpar_rc = plpar_xirr(&return_value, cppr);
	if (lpar_rc != H_SUCCESS)
		panic(" bad return code xirr - rc = %lx\n", lpar_rc);
	return (unsigned int)return_value;
}

static inline void lpar_xirr_info_set(unsigned int value)
{
	unsigned long lpar_rc;

	lpar_rc = plpar_eoi(value);
	if (lpar_rc != H_SUCCESS)
		panic("bad return code EOI - rc = %ld, value=%x\n", lpar_rc,
		      value);
}

static inline void lpar_cppr_info(u8 value)
{
	unsigned long lpar_rc;

	lpar_rc = plpar_cppr(value);
	if (lpar_rc != H_SUCCESS)
		panic("bad return code cppr - rc = %lx\n", lpar_rc);
}

static inline void lpar_qirr_info(int n_cpu , u8 value)
{
	unsigned long lpar_rc;

	lpar_rc = plpar_ipi(get_hard_smp_processor_id(n_cpu), value);
	if (lpar_rc != H_SUCCESS)
		panic("bad return code qirr - rc = %lx\n", lpar_rc);
}


/* Interface to generic irq subsystem */

#ifdef CONFIG_SMP
/*
 * For the moment we only implement delivery to all cpus or one cpu.
 *
 * If the requested affinity is cpu_all_mask, we set global affinity.
 * If not we set it to the first cpu in the mask, even if multiple cpus
 * are set. This is so things like irqbalance (which set core and package
 * wide affinities) do the right thing.
 */
static int get_irq_server(unsigned int virq, const struct cpumask *cpumask,
			  unsigned int strict_check)
{

	if (!distribute_irqs)
		return default_server;

	if (!cpumask_subset(cpu_possible_mask, cpumask)) {
		int server = cpumask_first_and(cpu_online_mask, cpumask);

		if (server < nr_cpu_ids)
			return get_hard_smp_processor_id(server);

		if (strict_check)
			return -1;
	}

	/*
	 * Workaround issue with some versions of JS20 firmware that
	 * deliver interrupts to cpus which haven't been started. This
	 * happens when using the maxcpus= boot option.
	 */
	if (cpumask_equal(cpu_online_mask, cpu_present_mask))
		return default_distrib_server;

	return default_server;
}
#else
#define get_irq_server(virq, cpumask, strict_check) (default_server)
#endif

static void xics_unmask_irq(struct irq_data *d)
{
	unsigned int hwirq;
	int call_status;
	int server;

	pr_devel("xics: unmask virq %d\n", d->irq);

	hwirq = (unsigned int)irq_map[d->irq].hwirq;
	pr_devel(" -> map to hwirq 0x%x\n", hwirq);
	if (hwirq == XICS_IPI || hwirq == XICS_IRQ_SPURIOUS)
		return;

	server = get_irq_server(d->irq, d->affinity, 0);

	call_status = rtas_call(ibm_set_xive, 3, 1, NULL, hwirq, server,
				DEFAULT_PRIORITY);
	if (call_status != 0) {
		printk(KERN_ERR
			"%s: ibm_set_xive irq %u server %x returned %d\n",
			__func__, hwirq, server, call_status);
		return;
	}

	/* Now unmask the interrupt (often a no-op) */
	call_status = rtas_call(ibm_int_on, 1, 1, NULL, hwirq);
	if (call_status != 0) {
		printk(KERN_ERR "%s: ibm_int_on irq=%u returned %d\n",
			__func__, hwirq, call_status);
		return;
	}
}

static unsigned int xics_startup(struct irq_data *d)
{
	/*
	 * The generic MSI code returns with the interrupt disabled on the
	 * card, using the MSI mask bits. Firmware doesn't appear to unmask
	 * at that level, so we do it here by hand.
	 */
	if (d->msi_desc)
		unmask_msi_irq(d);

	/* unmask it */
	xics_unmask_irq(d);
	return 0;
}

static void xics_mask_real_irq(unsigned int hwirq)
{
	int call_status;

	if (hwirq == XICS_IPI)
		return;

	call_status = rtas_call(ibm_int_off, 1, 1, NULL, hwirq);
	if (call_status != 0) {
		printk(KERN_ERR "%s: ibm_int_off irq=%u returned %d\n",
			__func__, hwirq, call_status);
		return;
	}

	/* Have to set XIVE to 0xff to be able to remove a slot */
	call_status = rtas_call(ibm_set_xive, 3, 1, NULL, hwirq,
				default_server, 0xff);
	if (call_status != 0) {
		printk(KERN_ERR "%s: ibm_set_xive(0xff) irq=%u returned %d\n",
			__func__, hwirq, call_status);
		return;
	}
}

static void xics_mask_irq(struct irq_data *d)
{
	unsigned int hwirq;

	pr_devel("xics: mask virq %d\n", d->irq);

	hwirq = (unsigned int)irq_map[d->irq].hwirq;
	if (hwirq == XICS_IPI || hwirq == XICS_IRQ_SPURIOUS)
		return;
	xics_mask_real_irq(hwirq);
}

static void xics_mask_unknown_vec(unsigned int vec)
{
	printk(KERN_ERR "Interrupt %u (real) is invalid, disabling it.\n", vec);
	xics_mask_real_irq(vec);
}

static inline unsigned int xics_xirr_vector(unsigned int xirr)
{
	/*
	 * The top byte is the old cppr, to be restored on EOI.
	 * The remaining 24 bits are the vector.
	 */
	return xirr & 0x00ffffff;
}

static void push_cppr(unsigned int vec)
{
	struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr);

	if (WARN_ON(os_cppr->index >= MAX_NUM_PRIORITIES - 1))
		return;

	if (vec == XICS_IPI)
		os_cppr->stack[++os_cppr->index] = IPI_PRIORITY;
	else
		os_cppr->stack[++os_cppr->index] = DEFAULT_PRIORITY;
}

static unsigned int xics_get_irq_direct(void)
{
	unsigned int xirr = direct_xirr_info_get();
	unsigned int vec = xics_xirr_vector(xirr);
	unsigned int irq;

	if (vec == XICS_IRQ_SPURIOUS)
		return NO_IRQ;

	irq = irq_radix_revmap_lookup(xics_host, vec);
	if (likely(irq != NO_IRQ)) {
		push_cppr(vec);
		return irq;
	}

	/* We don't have a linux mapping, so have rtas mask it. */
	xics_mask_unknown_vec(vec);

	/* We might learn about it later, so EOI it */
	direct_xirr_info_set(xirr);
	return NO_IRQ;
}

static unsigned int xics_get_irq_lpar(void)
{
	struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr);
	unsigned int xirr = lpar_xirr_info_get(os_cppr->stack[os_cppr->index]);
	unsigned int vec = xics_xirr_vector(xirr);
	unsigned int irq;

	if (vec == XICS_IRQ_SPURIOUS)
		return NO_IRQ;

	irq = irq_radix_revmap_lookup(xics_host, vec);
	if (likely(irq != NO_IRQ)) {
		push_cppr(vec);
		return irq;
	}

	/* We don't have a linux mapping, so have RTAS mask it. */
	xics_mask_unknown_vec(vec);

	/* We might learn about it later, so EOI it */
	lpar_xirr_info_set(xirr);
	return NO_IRQ;
}

static unsigned char pop_cppr(void)
{
	struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr);

	if (WARN_ON(os_cppr->index < 1))
		return LOWEST_PRIORITY;

	return os_cppr->stack[--os_cppr->index];
}

static void xics_eoi_direct(struct irq_data *d)
{
	unsigned int hwirq = (unsigned int)irq_map[d->irq].hwirq;

	iosync();
	direct_xirr_info_set((pop_cppr() << 24) | hwirq);
}

static void xics_eoi_lpar(struct irq_data *d)
{
	unsigned int hwirq = (unsigned int)irq_map[d->irq].hwirq;

	iosync();
	lpar_xirr_info_set((pop_cppr() << 24) | hwirq);
}

static int
xics_set_affinity(struct irq_data *d, const struct cpumask *cpumask, bool force)
{
	unsigned int hwirq;
	int status;
	int xics_status[2];
	int irq_server;

	hwirq = (unsigned int)irq_map[d->irq].hwirq;
	if (hwirq == XICS_IPI || hwirq == XICS_IRQ_SPURIOUS)
		return -1;

	status = rtas_call(ibm_get_xive, 1, 3, xics_status, hwirq);

	if (status) {
		printk(KERN_ERR "%s: ibm,get-xive irq=%u returns %d\n",
			__func__, hwirq, status);
		return -1;
	}

	irq_server = get_irq_server(d->irq, cpumask, 1);
	if (irq_server == -1) {
		char cpulist[128];
		cpumask_scnprintf(cpulist, sizeof(cpulist), cpumask);
		printk(KERN_WARNING
			"%s: No online cpus in the mask %s for irq %d\n",
			__func__, cpulist, d->irq);
		return -1;
	}

	status = rtas_call(ibm_set_xive, 3, 1, NULL,
				hwirq, irq_server, xics_status[1]);

	if (status) {
		printk(KERN_ERR "%s: ibm,set-xive irq=%u returns %d\n",
			__func__, hwirq, status);
		return -1;
	}

	return 0;
}

static struct irq_chip xics_pic_direct = {
	.name = "XICS",
	.irq_startup = xics_startup,
	.irq_mask = xics_mask_irq,
	.irq_unmask = xics_unmask_irq,
	.irq_eoi = xics_eoi_direct,
	.irq_set_affinity = xics_set_affinity
};

static struct irq_chip xics_pic_lpar = {
	.name = "XICS",
	.irq_startup = xics_startup,
	.irq_mask = xics_mask_irq,
	.irq_unmask = xics_unmask_irq,
	.irq_eoi = xics_eoi_lpar,
	.irq_set_affinity = xics_set_affinity
};


/* Interface to arch irq controller subsystem layer */

/* Points to the irq_chip we're actually using */
static struct irq_chip *xics_irq_chip;

static int xics_host_match(struct irq_host *h, struct device_node *node)
{
	/* IBM machines have interrupt parents of various funky types for things
	 * like vdevices, events, etc... The trick we use here is to match
	 * everything here except the legacy 8259 which is compatible "chrp,iic"
	 */
	return !of_device_is_compatible(node, "chrp,iic");
}

static int xics_host_map(struct irq_host *h, unsigned int virq,
			 irq_hw_number_t hw)
{
	pr_devel("xics: map virq %d, hwirq 0x%lx\n", virq, hw);

	/* Insert the interrupt mapping into the radix tree for fast lookup */
	irq_radix_revmap_insert(xics_host, virq, hw);

	irq_set_status_flags(virq, IRQ_LEVEL);
	irq_set_chip_and_handler(virq, xics_irq_chip, handle_fasteoi_irq);
	return 0;
}

static int xics_host_xlate(struct irq_host *h, struct device_node *ct,
			   const u32 *intspec, unsigned int intsize,
			   irq_hw_number_t *out_hwirq, unsigned int *out_flags)

{
	/* Current xics implementation translates everything
	 * to level. It is not technically right for MSIs but this
	 * is irrelevant at this point. We might get smarter in the future
	 */
	*out_hwirq = intspec[0];
	*out_flags = IRQ_TYPE_LEVEL_LOW;

	return 0;
}

static struct irq_host_ops xics_host_ops = {
	.match = xics_host_match,
	.map = xics_host_map,
	.xlate = xics_host_xlate,
};

static void __init xics_init_host(void)
{
	if (firmware_has_feature(FW_FEATURE_LPAR))
		xics_irq_chip = &xics_pic_lpar;
	else
		xics_irq_chip = &xics_pic_direct;

	xics_host = irq_alloc_host(NULL, IRQ_HOST_MAP_TREE, 0, &xics_host_ops,
				   XICS_IRQ_SPURIOUS);
	BUG_ON(xics_host == NULL);
	irq_set_default_host(xics_host);
}


/* Inter-processor interrupt support */

#ifdef CONFIG_SMP
/*
 * XICS only has a single IPI, so encode the messages per CPU
 */
static DEFINE_PER_CPU_SHARED_ALIGNED(unsigned long, xics_ipi_message);

static inline void smp_xics_do_message(int cpu, int msg)
{
	unsigned long *tgt = &per_cpu(xics_ipi_message, cpu);

	set_bit(msg, tgt);
	mb();
	if (firmware_has_feature(FW_FEATURE_LPAR))
		lpar_qirr_info(cpu, IPI_PRIORITY);
	else
		direct_qirr_info(cpu, IPI_PRIORITY);
}

void smp_xics_message_pass(int target, int msg)
{
	unsigned int i;

	if (target < NR_CPUS) {
		smp_xics_do_message(target, msg);
	} else {
		for_each_online_cpu(i) {
			if (target == MSG_ALL_BUT_SELF
			    && i == smp_processor_id())
				continue;
			smp_xics_do_message(i, msg);
		}
	}
}

static irqreturn_t xics_ipi_dispatch(int cpu)
{
	unsigned long *tgt = &per_cpu(xics_ipi_message, cpu);

	mb();	/* order mmio clearing qirr */
	while (*tgt) {
		if (test_and_clear_bit(PPC_MSG_CALL_FUNCTION, tgt)) {
			smp_message_recv(PPC_MSG_CALL_FUNCTION);
		}
		if (test_and_clear_bit(PPC_MSG_RESCHEDULE, tgt)) {
			smp_message_recv(PPC_MSG_RESCHEDULE);
		}
		if (test_and_clear_bit(PPC_MSG_CALL_FUNC_SINGLE, tgt)) {
			smp_message_recv(PPC_MSG_CALL_FUNC_SINGLE);
		}
#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC)
		if (test_and_clear_bit(PPC_MSG_DEBUGGER_BREAK, tgt)) {
			smp_message_recv(PPC_MSG_DEBUGGER_BREAK);
		}
#endif
	}
	return IRQ_HANDLED;
}

static irqreturn_t xics_ipi_action_direct(int irq, void *dev_id)
{
	int cpu = smp_processor_id();

	direct_qirr_info(cpu, 0xff);

	return xics_ipi_dispatch(cpu);
}

static irqreturn_t xics_ipi_action_lpar(int irq, void *dev_id)
{
	int cpu = smp_processor_id();

	lpar_qirr_info(cpu, 0xff);

	return xics_ipi_dispatch(cpu);
}

static void xics_request_ipi(void)
{
	unsigned int ipi;
	int rc;

	ipi = irq_create_mapping(xics_host, XICS_IPI);
	BUG_ON(ipi == NO_IRQ);

	/*
	 * IPIs are marked IRQF_DISABLED as they must run with irqs
	 * disabled
	 */
	irq_set_handler(ipi, handle_percpu_irq);
	if (firmware_has_feature(FW_FEATURE_LPAR))
		rc = request_irq(ipi, xics_ipi_action_lpar,
				IRQF_DISABLED|IRQF_PERCPU, "IPI", NULL);
	else
		rc = request_irq(ipi, xics_ipi_action_direct,
				IRQF_DISABLED|IRQF_PERCPU, "IPI", NULL);
	BUG_ON(rc);
}

int __init smp_xics_probe(void)
{
	xics_request_ipi();

	return cpumask_weight(cpu_possible_mask);
}

#endif /* CONFIG_SMP */


/* Initialization */

static void xics_update_irq_servers(void)
{
	int i, j;
	struct device_node *np;
	u32 ilen;
	const u32 *ireg;
	u32 hcpuid;

	/* Find the server numbers for the boot cpu. */
	np = of_get_cpu_node(boot_cpuid, NULL);
	BUG_ON(!np);

	ireg = of_get_property(np, "ibm,ppc-interrupt-gserver#s", &ilen);
	if (!ireg) {
		of_node_put(np);
		return;
	}

	i = ilen / sizeof(int);
	hcpuid = get_hard_smp_processor_id(boot_cpuid);

	/* Global interrupt distribution server is specified in the last
	 * entry of "ibm,ppc-interrupt-gserver#s" property. Get the last
	 * entry fom this property for current boot cpu id and use it as
	 * default distribution server
	 */
	for (j = 0; j < i; j += 2) {
		if (ireg[j] == hcpuid) {
			default_server = hcpuid;
			default_distrib_server = ireg[j+1];
		}
	}

	of_node_put(np);
}

static void __init xics_map_one_cpu(int hw_id, unsigned long addr,
				     unsigned long size)
{
	int i;

	/* This may look gross but it's good enough for now, we don't quite
	 * have a hard -> linux processor id matching.
	 */
	for_each_possible_cpu(i) {
		if (!cpu_present(i))
			continue;
		if (hw_id == get_hard_smp_processor_id(i)) {
			xics_per_cpu[i] = ioremap(addr, size);
			return;
		}
	}
}

static void __init xics_init_one_node(struct device_node *np,
				      unsigned int *indx)
{
	unsigned int ilen;
	const u32 *ireg;

	/* This code does the theorically broken assumption that the interrupt
	 * server numbers are the same as the hard CPU numbers.
	 * This happens to be the case so far but we are playing with fire...
	 * should be fixed one of these days. -BenH.
	 */
	ireg = of_get_property(np, "ibm,interrupt-server-ranges", NULL);

	/* Do that ever happen ? we'll know soon enough... but even good'old
	 * f80 does have that property ..
	 */
	WARN_ON(ireg == NULL);
	if (ireg) {
		/*
		 * set node starting index for this node
		 */
		*indx = *ireg;
	}
	ireg = of_get_property(np, "reg", &ilen);
	if (!ireg)
		panic("xics_init_IRQ: can't find interrupt reg property");

	while (ilen >= (4 * sizeof(u32))) {
		unsigned long addr, size;

		/* XXX Use proper OF parsing code here !!! */
		addr = (unsigned long)*ireg++ << 32;
		ilen -= sizeof(u32);
		addr |= *ireg++;
		ilen -= sizeof(u32);
		size = (unsigned long)*ireg++ << 32;
		ilen -= sizeof(u32);
		size |= *ireg++;
		ilen -= sizeof(u32);
		xics_map_one_cpu(*indx, addr, size);
		(*indx)++;
	}
}

void __init xics_init_IRQ(void)
{
	struct device_node *np;
	u32 indx = 0;
	int found = 0;
	const u32 *isize;

	ppc64_boot_msg(0x20, "XICS Init");

	ibm_get_xive = rtas_token("ibm,get-xive");
	ibm_set_xive = rtas_token("ibm,set-xive");
	ibm_int_on  = rtas_token("ibm,int-on");
	ibm_int_off = rtas_token("ibm,int-off");

	for_each_node_by_type(np, "PowerPC-External-Interrupt-Presentation") {
		found = 1;
		if (firmware_has_feature(FW_FEATURE_LPAR)) {
			of_node_put(np);
			break;
			}
		xics_init_one_node(np, &indx);
	}
	if (found == 0)
		return;

	/* get the bit size of server numbers */
	found = 0;

	for_each_compatible_node(np, NULL, "ibm,ppc-xics") {
		isize = of_get_property(np, "ibm,interrupt-server#-size", NULL);

		if (!isize)
			continue;

		if (!found) {
			interrupt_server_size = *isize;
			found = 1;
		} else if (*isize != interrupt_server_size) {
			printk(KERN_WARNING "XICS: "
			       "mismatched ibm,interrupt-server#-size\n");
			interrupt_server_size = max(*isize,
						    interrupt_server_size);
		}
	}

	xics_update_irq_servers();
	xics_init_host();

	if (firmware_has_feature(FW_FEATURE_LPAR))
		ppc_md.get_irq = xics_get_irq_lpar;
	else
		ppc_md.get_irq = xics_get_irq_direct;

	xics_setup_cpu();

	ppc64_boot_msg(0x21, "XICS Done");
}

/* Cpu startup, shutdown, and hotplug */

static void xics_set_cpu_priority(unsigned char cppr)
{
	struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr);

	/*
	 * we only really want to set the priority when there's
	 * just one cppr value on the stack
	 */
	WARN_ON(os_cppr->index != 0);

	os_cppr->stack[0] = cppr;

	if (firmware_has_feature(FW_FEATURE_LPAR))
		lpar_cppr_info(cppr);
	else
		direct_cppr_info(cppr);
	iosync();
}

/* Have the calling processor join or leave the specified global queue */
static void xics_set_cpu_giq(unsigned int gserver, unsigned int join)
{
	int index;
	int status;

	if (!rtas_indicator_present(GLOBAL_INTERRUPT_QUEUE, NULL))
		return;

	index = (1UL << interrupt_server_size) - 1 - gserver;

	status = rtas_set_indicator_fast(GLOBAL_INTERRUPT_QUEUE, index, join);

	WARN(status < 0, "set-indicator(%d, %d, %u) returned %d\n",
	     GLOBAL_INTERRUPT_QUEUE, index, join, status);
}

void xics_setup_cpu(void)
{
	xics_set_cpu_priority(LOWEST_PRIORITY);

	xics_set_cpu_giq(default_distrib_server, 1);
}

void xics_teardown_cpu(void)
{
	struct xics_cppr *os_cppr = &__get_cpu_var(xics_cppr);
	int cpu = smp_processor_id();

	/*
	 * we have to reset the cppr index to 0 because we're
	 * not going to return from the IPI
	 */
	os_cppr->index = 0;
	xics_set_cpu_priority(0);

	/* Clear any pending IPI request */
	if (firmware_has_feature(FW_FEATURE_LPAR))
		lpar_qirr_info(cpu, 0xff);
	else
		direct_qirr_info(cpu, 0xff);
}

void xics_kexec_teardown_cpu(int secondary)
{
	xics_teardown_cpu();

	/*
	 * we take the ipi irq but and never return so we
	 * need to EOI the IPI, but want to leave our priority 0
	 *
	 * should we check all the other interrupts too?
	 * should we be flagging idle loop instead?
	 * or creating some task to be scheduled?
	 */

	if (firmware_has_feature(FW_FEATURE_LPAR))
		lpar_xirr_info_set((0x00 << 24) | XICS_IPI);
	else
		direct_xirr_info_set((0x00 << 24) | XICS_IPI);

	/*
	 * Some machines need to have at least one cpu in the GIQ,
	 * so leave the master cpu in the group.
	 */
	if (secondary)
		xics_set_cpu_giq(default_distrib_server, 0);
}

#ifdef CONFIG_HOTPLUG_CPU

/* Interrupts are disabled. */
void xics_migrate_irqs_away(void)
{
	int cpu = smp_processor_id(), hw_cpu = hard_smp_processor_id();
	int virq;

	/* If we used to be the default server, move to the new "boot_cpuid" */
	if (hw_cpu == default_server)
		xics_update_irq_servers();

	/* Reject any interrupt that was queued to us... */
	xics_set_cpu_priority(0);

	/* Remove ourselves from the global interrupt queue */
	xics_set_cpu_giq(default_distrib_server, 0);

	/* Allow IPIs again... */
	xics_set_cpu_priority(DEFAULT_PRIORITY);

	for_each_irq(virq) {
		struct irq_desc *desc;
		struct irq_chip *chip;
		unsigned int hwirq;
		int xics_status[2];
		int status;
		unsigned long flags;

		/* We can't set affinity on ISA interrupts */
		if (virq < NUM_ISA_INTERRUPTS)
			continue;
		if (irq_map[virq].host != xics_host)
			continue;
		hwirq = (unsigned int)irq_map[virq].hwirq;
		/* We need to get IPIs still. */
		if (hwirq == XICS_IPI || hwirq == XICS_IRQ_SPURIOUS)
			continue;

		desc = irq_to_desc(virq);

		/* We only need to migrate enabled IRQS */
		if (desc == NULL || desc->action == NULL)
			continue;

		chip = irq_desc_get_chip(desc);
		if (chip == NULL || chip->irq_set_affinity == NULL)
			continue;

		raw_spin_lock_irqsave(&desc->lock, flags);

		status = rtas_call(ibm_get_xive, 1, 3, xics_status, hwirq);
		if (status) {
			printk(KERN_ERR "%s: ibm,get-xive irq=%u returns %d\n",
					__func__, hwirq, status);
			goto unlock;
		}

		/*
		 * We only support delivery to all cpus or to one cpu.
		 * The irq has to be migrated only in the single cpu
		 * case.
		 */
		if (xics_status[0] != hw_cpu)
			goto unlock;

		/* This is expected during cpu offline. */
		if (cpu_online(cpu))
			printk(KERN_WARNING "IRQ %u affinity broken off cpu %u\n",
			       virq, cpu);

		/* Reset affinity to all cpus */
		cpumask_setall(desc->irq_data.affinity);
		chip->irq_set_affinity(&desc->irq_data, cpu_all_mask, true);
unlock:
		raw_spin_unlock_irqrestore(&desc->lock, flags);
	}
}
#endif