summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/kernel/prom.c
blob: 8f32f14ba50839b4250a692c2e4cc562509792b6 (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
/*
 * Procedures for creating, accessing and interpreting the device tree.
 *
 * Paul Mackerras	August 1996.
 * Copyright (C) 1996-2005 Paul Mackerras.
 * 
 *  Adapted for 64bit PowerPC by Dave Engebretsen and Peter Bergner.
 *    {engebret|bergner}@us.ibm.com 
 *
 *      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.
 */

#undef DEBUG

#include <stdarg.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/threads.h>
#include <linux/spinlock.h>
#include <linux/types.h>
#include <linux/pci.h>
#include <linux/stringify.h>
#include <linux/delay.h>
#include <linux/initrd.h>
#include <linux/bitops.h>
#include <linux/export.h>
#include <linux/kexec.h>
#include <linux/irq.h>
#include <linux/memblock.h>
#include <linux/of.h>
#include <linux/of_fdt.h>
#include <linux/libfdt.h>
#include <linux/cpu.h>

#include <asm/prom.h>
#include <asm/rtas.h>
#include <asm/page.h>
#include <asm/processor.h>
#include <asm/irq.h>
#include <asm/io.h>
#include <asm/kdump.h>
#include <asm/smp.h>
#include <asm/mmu.h>
#include <asm/paca.h>
#include <asm/pgtable.h>
#include <asm/powernv.h>
#include <asm/iommu.h>
#include <asm/btext.h>
#include <asm/sections.h>
#include <asm/machdep.h>
#include <asm/pci-bridge.h>
#include <asm/kexec.h>
#include <asm/opal.h>
#include <asm/fadump.h>
#include <asm/epapr_hcalls.h>
#include <asm/firmware.h>
#include <asm/dt_cpu_ftrs.h>
#include <asm/drmem.h>

#include <mm/mmu_decl.h>

#ifdef DEBUG
#define DBG(fmt...) printk(KERN_ERR fmt)
#else
#define DBG(fmt...)
#endif

#ifdef CONFIG_PPC64
int __initdata iommu_is_off;
int __initdata iommu_force_on;
unsigned long tce_alloc_start, tce_alloc_end;
u64 ppc64_rma_size;
#endif
static phys_addr_t first_memblock_size;
static int __initdata boot_cpu_count;

static int __init early_parse_mem(char *p)
{
	if (!p)
		return 1;

	memory_limit = PAGE_ALIGN(memparse(p, &p));
	DBG("memory limit = 0x%llx\n", memory_limit);

	return 0;
}
early_param("mem", early_parse_mem);

/*
 * overlaps_initrd - check for overlap with page aligned extension of
 * initrd.
 */
static inline int overlaps_initrd(unsigned long start, unsigned long size)
{
#ifdef CONFIG_BLK_DEV_INITRD
	if (!initrd_start)
		return 0;

	return	(start + size) > _ALIGN_DOWN(initrd_start, PAGE_SIZE) &&
			start <= _ALIGN_UP(initrd_end, PAGE_SIZE);
#else
	return 0;
#endif
}

/**
 * move_device_tree - move tree to an unused area, if needed.
 *
 * The device tree may be allocated beyond our memory limit, or inside the
 * crash kernel region for kdump, or within the page aligned range of initrd.
 * If so, move it out of the way.
 */
static void __init move_device_tree(void)
{
	unsigned long start, size;
	void *p;

	DBG("-> move_device_tree\n");

	start = __pa(initial_boot_params);
	size = fdt_totalsize(initial_boot_params);

	if ((memory_limit && (start + size) > PHYSICAL_START + memory_limit) ||
			overlaps_crashkernel(start, size) ||
			overlaps_initrd(start, size)) {
		p = __va(memblock_alloc(size, PAGE_SIZE));
		memcpy(p, initial_boot_params, size);
		initial_boot_params = p;
		DBG("Moved device tree to 0x%p\n", p);
	}

	DBG("<- move_device_tree\n");
}

/*
 * ibm,pa-features is a per-cpu property that contains a string of
 * attribute descriptors, each of which has a 2 byte header plus up
 * to 254 bytes worth of processor attribute bits.  First header
 * byte specifies the number of bytes following the header.
 * Second header byte is an "attribute-specifier" type, of which
 * zero is the only currently-defined value.
 * Implementation:  Pass in the byte and bit offset for the feature
 * that we are interested in.  The function will return -1 if the
 * pa-features property is missing, or a 1/0 to indicate if the feature
 * is supported/not supported.  Note that the bit numbers are
 * big-endian to match the definition in PAPR.
 */
static struct ibm_pa_feature {
	unsigned long	cpu_features;	/* CPU_FTR_xxx bit */
	unsigned long	mmu_features;	/* MMU_FTR_xxx bit */
	unsigned int	cpu_user_ftrs;	/* PPC_FEATURE_xxx bit */
	unsigned int	cpu_user_ftrs2;	/* PPC_FEATURE2_xxx bit */
	unsigned char	pabyte;		/* byte number in ibm,pa-features */
	unsigned char	pabit;		/* bit number (big-endian) */
	unsigned char	invert;		/* if 1, pa bit set => clear feature */
} ibm_pa_features[] __initdata = {
	{ .pabyte = 0,  .pabit = 0, .cpu_user_ftrs = PPC_FEATURE_HAS_MMU },
	{ .pabyte = 0,  .pabit = 1, .cpu_user_ftrs = PPC_FEATURE_HAS_FPU },
	{ .pabyte = 0,  .pabit = 3, .cpu_features  = CPU_FTR_CTRL },
	{ .pabyte = 0,  .pabit = 6, .cpu_features  = CPU_FTR_NOEXECUTE },
	{ .pabyte = 1,  .pabit = 2, .mmu_features  = MMU_FTR_CI_LARGE_PAGE },
#ifdef CONFIG_PPC_RADIX_MMU
	{ .pabyte = 40, .pabit = 0, .mmu_features  = MMU_FTR_TYPE_RADIX },
#endif
	{ .pabyte = 1,  .pabit = 1, .invert = 1, .cpu_features = CPU_FTR_NODSISRALIGN },
	{ .pabyte = 5,  .pabit = 0, .cpu_features  = CPU_FTR_REAL_LE,
				    .cpu_user_ftrs = PPC_FEATURE_TRUE_LE },
	/*
	 * If the kernel doesn't support TM (ie CONFIG_PPC_TRANSACTIONAL_MEM=n),
	 * we don't want to turn on TM here, so we use the *_COMP versions
	 * which are 0 if the kernel doesn't support TM.
	 */
	{ .pabyte = 22, .pabit = 0, .cpu_features = CPU_FTR_TM_COMP,
	  .cpu_user_ftrs2 = PPC_FEATURE2_HTM_COMP | PPC_FEATURE2_HTM_NOSC_COMP },
};

static void __init scan_features(unsigned long node, const unsigned char *ftrs,
				 unsigned long tablelen,
				 struct ibm_pa_feature *fp,
				 unsigned long ft_size)
{
	unsigned long i, len, bit;

	/* find descriptor with type == 0 */
	for (;;) {
		if (tablelen < 3)
			return;
		len = 2 + ftrs[0];
		if (tablelen < len)
			return;		/* descriptor 0 not found */
		if (ftrs[1] == 0)
			break;
		tablelen -= len;
		ftrs += len;
	}

	/* loop over bits we know about */
	for (i = 0; i < ft_size; ++i, ++fp) {
		if (fp->pabyte >= ftrs[0])
			continue;
		bit = (ftrs[2 + fp->pabyte] >> (7 - fp->pabit)) & 1;
		if (bit ^ fp->invert) {
			cur_cpu_spec->cpu_features |= fp->cpu_features;
			cur_cpu_spec->cpu_user_features |= fp->cpu_user_ftrs;
			cur_cpu_spec->cpu_user_features2 |= fp->cpu_user_ftrs2;
			cur_cpu_spec->mmu_features |= fp->mmu_features;
		} else {
			cur_cpu_spec->cpu_features &= ~fp->cpu_features;
			cur_cpu_spec->cpu_user_features &= ~fp->cpu_user_ftrs;
			cur_cpu_spec->cpu_user_features2 &= ~fp->cpu_user_ftrs2;
			cur_cpu_spec->mmu_features &= ~fp->mmu_features;
		}
	}
}

static void __init check_cpu_pa_features(unsigned long node)
{
	const unsigned char *pa_ftrs;
	int tablelen;

	pa_ftrs = of_get_flat_dt_prop(node, "ibm,pa-features", &tablelen);
	if (pa_ftrs == NULL)
		return;

	scan_features(node, pa_ftrs, tablelen,
		      ibm_pa_features, ARRAY_SIZE(ibm_pa_features));
}

#ifdef CONFIG_PPC_BOOK3S_64
static void __init init_mmu_slb_size(unsigned long node)
{
	const __be32 *slb_size_ptr;

	slb_size_ptr = of_get_flat_dt_prop(node, "slb-size", NULL) ? :
			of_get_flat_dt_prop(node, "ibm,slb-size", NULL);

	if (slb_size_ptr)
		mmu_slb_size = be32_to_cpup(slb_size_ptr);
}
#else
#define init_mmu_slb_size(node) do { } while(0)
#endif

static struct feature_property {
	const char *name;
	u32 min_value;
	unsigned long cpu_feature;
	unsigned long cpu_user_ftr;
} feature_properties[] __initdata = {
#ifdef CONFIG_ALTIVEC
	{"altivec", 0, CPU_FTR_ALTIVEC, PPC_FEATURE_HAS_ALTIVEC},
	{"ibm,vmx", 1, CPU_FTR_ALTIVEC, PPC_FEATURE_HAS_ALTIVEC},
#endif /* CONFIG_ALTIVEC */
#ifdef CONFIG_VSX
	/* Yes, this _really_ is ibm,vmx == 2 to enable VSX */
	{"ibm,vmx", 2, CPU_FTR_VSX, PPC_FEATURE_HAS_VSX},
#endif /* CONFIG_VSX */
#ifdef CONFIG_PPC64
	{"ibm,dfp", 1, 0, PPC_FEATURE_HAS_DFP},
	{"ibm,purr", 1, CPU_FTR_PURR, 0},
	{"ibm,spurr", 1, CPU_FTR_SPURR, 0},
#endif /* CONFIG_PPC64 */
};

#if defined(CONFIG_44x) && defined(CONFIG_PPC_FPU)
static inline void identical_pvr_fixup(unsigned long node)
{
	unsigned int pvr;
	const char *model = of_get_flat_dt_prop(node, "model", NULL);

	/*
	 * Since 440GR(x)/440EP(x) processors have the same pvr,
	 * we check the node path and set bit 28 in the cur_cpu_spec
	 * pvr for EP(x) processor version. This bit is always 0 in
	 * the "real" pvr. Then we call identify_cpu again with
	 * the new logical pvr to enable FPU support.
	 */
	if (model && strstr(model, "440EP")) {
		pvr = cur_cpu_spec->pvr_value | 0x8;
		identify_cpu(0, pvr);
		DBG("Using logical pvr %x for %s\n", pvr, model);
	}
}
#else
#define identical_pvr_fixup(node) do { } while(0)
#endif

static void __init check_cpu_feature_properties(unsigned long node)
{
	int i;
	struct feature_property *fp = feature_properties;
	const __be32 *prop;

	for (i = 0; i < (int)ARRAY_SIZE(feature_properties); ++i, ++fp) {
		prop = of_get_flat_dt_prop(node, fp->name, NULL);
		if (prop && be32_to_cpup(prop) >= fp->min_value) {
			cur_cpu_spec->cpu_features |= fp->cpu_feature;
			cur_cpu_spec->cpu_user_features |= fp->cpu_user_ftr;
		}
	}
}

static int __init early_init_dt_scan_cpus(unsigned long node,
					  const char *uname, int depth,
					  void *data)
{
	const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
	const __be32 *prop;
	const __be32 *intserv;
	int i, nthreads;
	int len;
	int found = -1;
	int found_thread = 0;

	/* We are scanning "cpu" nodes only */
	if (type == NULL || strcmp(type, "cpu") != 0)
		return 0;

	/* Get physical cpuid */
	intserv = of_get_flat_dt_prop(node, "ibm,ppc-interrupt-server#s", &len);
	if (!intserv)
		intserv = of_get_flat_dt_prop(node, "reg", &len);

	nthreads = len / sizeof(int);

	/*
	 * Now see if any of these threads match our boot cpu.
	 * NOTE: This must match the parsing done in smp_setup_cpu_maps.
	 */
	for (i = 0; i < nthreads; i++) {
		if (be32_to_cpu(intserv[i]) ==
			fdt_boot_cpuid_phys(initial_boot_params)) {
			found = boot_cpu_count;
			found_thread = i;
		}
#ifdef CONFIG_SMP
		/* logical cpu id is always 0 on UP kernels */
		boot_cpu_count++;
#endif
	}

	/* Not the boot CPU */
	if (found < 0)
		return 0;

	DBG("boot cpu: logical %d physical %d\n", found,
	    be32_to_cpu(intserv[found_thread]));
	boot_cpuid = found;

	/*
	 * PAPR defines "logical" PVR values for cpus that
	 * meet various levels of the architecture:
	 * 0x0f000001	Architecture version 2.04
	 * 0x0f000002	Architecture version 2.05
	 * If the cpu-version property in the cpu node contains
	 * such a value, we call identify_cpu again with the
	 * logical PVR value in order to use the cpu feature
	 * bits appropriate for the architecture level.
	 *
	 * A POWER6 partition in "POWER6 architected" mode
	 * uses the 0x0f000002 PVR value; in POWER5+ mode
	 * it uses 0x0f000001.
	 *
	 * If we're using device tree CPU feature discovery then we don't
	 * support the cpu-version property, and it's the responsibility of the
	 * firmware/hypervisor to provide the correct feature set for the
	 * architecture level via the ibm,powerpc-cpu-features binding.
	 */
	if (!dt_cpu_ftrs_in_use()) {
		prop = of_get_flat_dt_prop(node, "cpu-version", NULL);
		if (prop && (be32_to_cpup(prop) & 0xff000000) == 0x0f000000)
			identify_cpu(0, be32_to_cpup(prop));

		check_cpu_feature_properties(node);
		check_cpu_pa_features(node);
	}

	identical_pvr_fixup(node);
	init_mmu_slb_size(node);

#ifdef CONFIG_PPC64
	if (nthreads == 1)
		cur_cpu_spec->cpu_features &= ~CPU_FTR_SMT;
	else if (!dt_cpu_ftrs_in_use())
		cur_cpu_spec->cpu_features |= CPU_FTR_SMT;
	allocate_paca(boot_cpuid);
#endif
	set_hard_smp_processor_id(found, be32_to_cpu(intserv[found_thread]));

	return 0;
}

static int __init early_init_dt_scan_chosen_ppc(unsigned long node,
						const char *uname,
						int depth, void *data)
{
	const unsigned long *lprop; /* All these set by kernel, so no need to convert endian */

	/* Use common scan routine to determine if this is the chosen node */
	if (early_init_dt_scan_chosen(node, uname, depth, data) == 0)
		return 0;

#ifdef CONFIG_PPC64
	/* check if iommu is forced on or off */
	if (of_get_flat_dt_prop(node, "linux,iommu-off", NULL) != NULL)
		iommu_is_off = 1;
	if (of_get_flat_dt_prop(node, "linux,iommu-force-on", NULL) != NULL)
		iommu_force_on = 1;
#endif

	/* mem=x on the command line is the preferred mechanism */
	lprop = of_get_flat_dt_prop(node, "linux,memory-limit", NULL);
	if (lprop)
		memory_limit = *lprop;

#ifdef CONFIG_PPC64
	lprop = of_get_flat_dt_prop(node, "linux,tce-alloc-start", NULL);
	if (lprop)
		tce_alloc_start = *lprop;
	lprop = of_get_flat_dt_prop(node, "linux,tce-alloc-end", NULL);
	if (lprop)
		tce_alloc_end = *lprop;
#endif

#ifdef CONFIG_KEXEC_CORE
	lprop = of_get_flat_dt_prop(node, "linux,crashkernel-base", NULL);
	if (lprop)
		crashk_res.start = *lprop;

	lprop = of_get_flat_dt_prop(node, "linux,crashkernel-size", NULL);
	if (lprop)
		crashk_res.end = crashk_res.start + *lprop - 1;
#endif

	/* break now */
	return 1;
}

/*
 * Compare the range against max mem limit and update
 * size if it cross the limit.
 */

#ifdef CONFIG_SPARSEMEM
static bool validate_mem_limit(u64 base, u64 *size)
{
	u64 max_mem = 1UL << (MAX_PHYSMEM_BITS);

	if (base >= max_mem)
		return false;
	if ((base + *size) > max_mem)
		*size = max_mem - base;
	return true;
}
#else
static bool validate_mem_limit(u64 base, u64 *size)
{
	return true;
}
#endif

#ifdef CONFIG_PPC_PSERIES
/*
 * Interpret the ibm dynamic reconfiguration memory LMBs.
 * This contains a list of memory blocks along with NUMA affinity
 * information.
 */
static void __init early_init_drmem_lmb(struct drmem_lmb *lmb,
					const __be32 **usm)
{
	u64 base, size;
	int is_kexec_kdump = 0, rngs;

	base = lmb->base_addr;
	size = drmem_lmb_size();
	rngs = 1;

	/*
	 * Skip this block if the reserved bit is set in flags
	 * or if the block is not assigned to this partition.
	 */
	if ((lmb->flags & DRCONF_MEM_RESERVED) ||
	    !(lmb->flags & DRCONF_MEM_ASSIGNED))
		return;

	if (*usm)
		is_kexec_kdump = 1;

	if (is_kexec_kdump) {
		/*
		 * For each memblock in ibm,dynamic-memory, a
		 * corresponding entry in linux,drconf-usable-memory
		 * property contains a counter 'p' followed by 'p'
		 * (base, size) duple. Now read the counter from
		 * linux,drconf-usable-memory property
		 */
		rngs = dt_mem_next_cell(dt_root_size_cells, usm);
		if (!rngs) /* there are no (base, size) duple */
			return;
	}

	do {
		if (is_kexec_kdump) {
			base = dt_mem_next_cell(dt_root_addr_cells, usm);
			size = dt_mem_next_cell(dt_root_size_cells, usm);
		}

		if (iommu_is_off) {
			if (base >= 0x80000000ul)
				continue;
			if ((base + size) > 0x80000000ul)
				size = 0x80000000ul - base;
		}

		DBG("Adding: %llx -> %llx\n", base, size);
		if (validate_mem_limit(base, &size))
			memblock_add(base, size);
	} while (--rngs);
}
#endif /* CONFIG_PPC_PSERIES */

static int __init early_init_dt_scan_memory_ppc(unsigned long node,
						const char *uname,
						int depth, void *data)
{
#ifdef CONFIG_PPC_PSERIES
	if (depth == 1 &&
	    strcmp(uname, "ibm,dynamic-reconfiguration-memory") == 0) {
		walk_drmem_lmbs_early(node, early_init_drmem_lmb);
		return 0;
	}
#endif
	
	return early_init_dt_scan_memory(node, uname, depth, data);
}

/*
 * For a relocatable kernel, we need to get the memstart_addr first,
 * then use it to calculate the virtual kernel start address. This has
 * to happen at a very early stage (before machine_init). In this case,
 * we just want to get the memstart_address and would not like to mess the
 * memblock at this stage. So introduce a variable to skip the memblock_add()
 * for this reason.
 */
#ifdef CONFIG_RELOCATABLE
static int add_mem_to_memblock = 1;
#else
#define add_mem_to_memblock 1
#endif

void __init early_init_dt_add_memory_arch(u64 base, u64 size)
{
#ifdef CONFIG_PPC64
	if (iommu_is_off) {
		if (base >= 0x80000000ul)
			return;
		if ((base + size) > 0x80000000ul)
			size = 0x80000000ul - base;
	}
#endif
	/* Keep track of the beginning of memory -and- the size of
	 * the very first block in the device-tree as it represents
	 * the RMA on ppc64 server
	 */
	if (base < memstart_addr) {
		memstart_addr = base;
		first_memblock_size = size;
	}

	/* Add the chunk to the MEMBLOCK list */
	if (add_mem_to_memblock) {
		if (validate_mem_limit(base, &size))
			memblock_add(base, size);
	}
}

static void __init early_reserve_mem_dt(void)
{
	unsigned long i, dt_root;
	int len;
	const __be32 *prop;

	early_init_fdt_reserve_self();
	early_init_fdt_scan_reserved_mem();

	dt_root = of_get_flat_dt_root();

	prop = of_get_flat_dt_prop(dt_root, "reserved-ranges", &len);

	if (!prop)
		return;

	DBG("Found new-style reserved-ranges\n");

	/* Each reserved range is an (address,size) pair, 2 cells each,
	 * totalling 4 cells per range. */
	for (i = 0; i < len / (sizeof(*prop) * 4); i++) {
		u64 base, size;

		base = of_read_number(prop + (i * 4) + 0, 2);
		size = of_read_number(prop + (i * 4) + 2, 2);

		if (size) {
			DBG("reserving: %llx -> %llx\n", base, size);
			memblock_reserve(base, size);
		}
	}
}

static void __init early_reserve_mem(void)
{
	__be64 *reserve_map;

	reserve_map = (__be64 *)(((unsigned long)initial_boot_params) +
			fdt_off_mem_rsvmap(initial_boot_params));

	/* Look for the new "reserved-regions" property in the DT */
	early_reserve_mem_dt();

#ifdef CONFIG_BLK_DEV_INITRD
	/* Then reserve the initrd, if any */
	if (initrd_start && (initrd_end > initrd_start)) {
		memblock_reserve(_ALIGN_DOWN(__pa(initrd_start), PAGE_SIZE),
			_ALIGN_UP(initrd_end, PAGE_SIZE) -
			_ALIGN_DOWN(initrd_start, PAGE_SIZE));
	}
#endif /* CONFIG_BLK_DEV_INITRD */

#ifdef CONFIG_PPC32
	/* 
	 * Handle the case where we might be booting from an old kexec
	 * image that setup the mem_rsvmap as pairs of 32-bit values
	 */
	if (be64_to_cpup(reserve_map) > 0xffffffffull) {
		u32 base_32, size_32;
		__be32 *reserve_map_32 = (__be32 *)reserve_map;

		DBG("Found old 32-bit reserve map\n");

		while (1) {
			base_32 = be32_to_cpup(reserve_map_32++);
			size_32 = be32_to_cpup(reserve_map_32++);
			if (size_32 == 0)
				break;
			DBG("reserving: %x -> %x\n", base_32, size_32);
			memblock_reserve(base_32, size_32);
		}
		return;
	}
#endif
}

#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
static bool tm_disabled __initdata;

static int __init parse_ppc_tm(char *str)
{
	bool res;

	if (kstrtobool(str, &res))
		return -EINVAL;

	tm_disabled = !res;

	return 0;
}
early_param("ppc_tm", parse_ppc_tm);

static void __init tm_init(void)
{
	if (tm_disabled) {
		pr_info("Disabling hardware transactional memory (HTM)\n");
		cur_cpu_spec->cpu_user_features2 &=
			~(PPC_FEATURE2_HTM_NOSC | PPC_FEATURE2_HTM);
		cur_cpu_spec->cpu_features &= ~CPU_FTR_TM;
		return;
	}

	pnv_tm_init();
}
#else
static void tm_init(void) { }
#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */

void __init early_init_devtree(void *params)
{
	phys_addr_t limit;

	DBG(" -> early_init_devtree(%p)\n", params);

	/* Too early to BUG_ON(), do it by hand */
	if (!early_init_dt_verify(params))
		panic("BUG: Failed verifying flat device tree, bad version?");

#ifdef CONFIG_PPC_RTAS
	/* Some machines might need RTAS info for debugging, grab it now. */
	of_scan_flat_dt(early_init_dt_scan_rtas, NULL);
#endif

#ifdef CONFIG_PPC_POWERNV
	/* Some machines might need OPAL info for debugging, grab it now. */
	of_scan_flat_dt(early_init_dt_scan_opal, NULL);
#endif

#ifdef CONFIG_FA_DUMP
	/* scan tree to see if dump is active during last boot */
	of_scan_flat_dt(early_init_dt_scan_fw_dump, NULL);
#endif

	/* Retrieve various informations from the /chosen node of the
	 * device-tree, including the platform type, initrd location and
	 * size, TCE reserve, and more ...
	 */
	of_scan_flat_dt(early_init_dt_scan_chosen_ppc, boot_command_line);

	/* Scan memory nodes and rebuild MEMBLOCKs */
	of_scan_flat_dt(early_init_dt_scan_root, NULL);
	of_scan_flat_dt(early_init_dt_scan_memory_ppc, NULL);

	parse_early_param();

	/* make sure we've parsed cmdline for mem= before this */
	if (memory_limit)
		first_memblock_size = min_t(u64, first_memblock_size, memory_limit);
	setup_initial_memory_limit(memstart_addr, first_memblock_size);
	/* Reserve MEMBLOCK regions used by kernel, initrd, dt, etc... */
	memblock_reserve(PHYSICAL_START, __pa(klimit) - PHYSICAL_START);
	/* If relocatable, reserve first 32k for interrupt vectors etc. */
	if (PHYSICAL_START > MEMORY_START)
		memblock_reserve(MEMORY_START, 0x8000);
	reserve_kdump_trampoline();
#ifdef CONFIG_FA_DUMP
	/*
	 * If we fail to reserve memory for firmware-assisted dump then
	 * fallback to kexec based kdump.
	 */
	if (fadump_reserve_mem() == 0)
#endif
		reserve_crashkernel();
	early_reserve_mem();

	/* Ensure that total memory size is page-aligned. */
	limit = ALIGN(memory_limit ?: memblock_phys_mem_size(), PAGE_SIZE);
	memblock_enforce_memory_limit(limit);

	memblock_allow_resize();
	memblock_dump_all();

	DBG("Phys. mem: %llx\n", memblock_phys_mem_size());

	/* We may need to relocate the flat tree, do it now.
	 * FIXME .. and the initrd too? */
	move_device_tree();

	allocate_paca_ptrs();

	DBG("Scanning CPUs ...\n");

	dt_cpu_ftrs_scan();

	/* Retrieve CPU related informations from the flat tree
	 * (altivec support, boot CPU ID, ...)
	 */
	of_scan_flat_dt(early_init_dt_scan_cpus, NULL);
	if (boot_cpuid < 0) {
		printk("Failed to identify boot CPU !\n");
		BUG();
	}

#if defined(CONFIG_SMP) && defined(CONFIG_PPC64)
	/* We'll later wait for secondaries to check in; there are
	 * NCPUS-1 non-boot CPUs  :-)
	 */
	spinning_secondaries = boot_cpu_count - 1;
#endif

	mmu_early_init_devtree();

#ifdef CONFIG_PPC_POWERNV
	/* Scan and build the list of machine check recoverable ranges */
	of_scan_flat_dt(early_init_dt_scan_recoverable_ranges, NULL);
#endif
	epapr_paravirt_early_init();

	/* Now try to figure out if we are running on LPAR and so on */
	pseries_probe_fw_features();

#ifdef CONFIG_PPC_PS3
	/* Identify PS3 firmware */
	if (of_flat_dt_is_compatible(of_get_flat_dt_root(), "sony,ps3"))
		powerpc_firmware_features |= FW_FEATURE_PS3_POSSIBLE;
#endif

	tm_init();

	DBG(" <- early_init_devtree()\n");
}

#ifdef CONFIG_RELOCATABLE
/*
 * This function run before early_init_devtree, so we have to init
 * initial_boot_params.
 */
void __init early_get_first_memblock_info(void *params, phys_addr_t *size)
{
	/* Setup flat device-tree pointer */
	initial_boot_params = params;

	/*
	 * Scan the memory nodes and set add_mem_to_memblock to 0 to avoid
	 * mess the memblock.
	 */
	add_mem_to_memblock = 0;
	of_scan_flat_dt(early_init_dt_scan_root, NULL);
	of_scan_flat_dt(early_init_dt_scan_memory_ppc, NULL);
	add_mem_to_memblock = 1;

	if (size)
		*size = first_memblock_size;
}
#endif

/*******
 *
 * New implementation of the OF "find" APIs, return a refcounted
 * object, call of_node_put() when done.  The device tree and list
 * are protected by a rw_lock.
 *
 * Note that property management will need some locking as well,
 * this isn't dealt with yet.
 *
 *******/

/**
 * of_get_ibm_chip_id - Returns the IBM "chip-id" of a device
 * @np: device node of the device
 *
 * This looks for a property "ibm,chip-id" in the node or any
 * of its parents and returns its content, or -1 if it cannot
 * be found.
 */
int of_get_ibm_chip_id(struct device_node *np)
{
	of_node_get(np);
	while (np) {
		u32 chip_id;

		/*
		 * Skiboot may produce memory nodes that contain more than one
		 * cell in chip-id, we only read the first one here.
		 */
		if (!of_property_read_u32(np, "ibm,chip-id", &chip_id)) {
			of_node_put(np);
			return chip_id;
		}

		np = of_get_next_parent(np);
	}
	return -1;
}
EXPORT_SYMBOL(of_get_ibm_chip_id);

/**
 * cpu_to_chip_id - Return the cpus chip-id
 * @cpu: The logical cpu number.
 *
 * Return the value of the ibm,chip-id property corresponding to the given
 * logical cpu number. If the chip-id can not be found, returns -1.
 */
int cpu_to_chip_id(int cpu)
{
	struct device_node *np;

	np = of_get_cpu_node(cpu, NULL);
	if (!np)
		return -1;

	of_node_put(np);
	return of_get_ibm_chip_id(np);
}
EXPORT_SYMBOL(cpu_to_chip_id);

bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
{
#ifdef CONFIG_SMP
	/*
	 * Early firmware scanning must use this rather than
	 * get_hard_smp_processor_id because we don't have pacas allocated
	 * until memory topology is discovered.
	 */
	if (cpu_to_phys_id != NULL)
		return (int)phys_id == cpu_to_phys_id[cpu];
#endif

	return (int)phys_id == get_hard_smp_processor_id(cpu);
}