summaryrefslogtreecommitdiff
path: root/arch/powerpc/kernel/setup_64.c
blob: 0e8fc1cd1c558e1acd17ae1e14efd795e66c9318 (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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * 
 * Common boot and setup code.
 *
 * Copyright (C) 2001 PPC64 Team, IBM Corp
 */

#include <linux/export.h>
#include <linux/string.h>
#include <linux/sched.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/reboot.h>
#include <linux/delay.h>
#include <linux/initrd.h>
#include <linux/seq_file.h>
#include <linux/ioport.h>
#include <linux/console.h>
#include <linux/utsname.h>
#include <linux/tty.h>
#include <linux/root_dev.h>
#include <linux/notifier.h>
#include <linux/cpu.h>
#include <linux/unistd.h>
#include <linux/serial.h>
#include <linux/serial_8250.h>
#include <linux/memblock.h>
#include <linux/pci.h>
#include <linux/lockdep.h>
#include <linux/memory.h>
#include <linux/nmi.h>
#include <linux/pgtable.h>
#include <linux/of.h>
#include <linux/of_fdt.h>

#include <asm/kvm_guest.h>
#include <asm/io.h>
#include <asm/kdump.h>
#include <asm/processor.h>
#include <asm/smp.h>
#include <asm/elf.h>
#include <asm/machdep.h>
#include <asm/paca.h>
#include <asm/time.h>
#include <asm/cputable.h>
#include <asm/dt_cpu_ftrs.h>
#include <asm/sections.h>
#include <asm/btext.h>
#include <asm/nvram.h>
#include <asm/setup.h>
#include <asm/rtas.h>
#include <asm/iommu.h>
#include <asm/serial.h>
#include <asm/cache.h>
#include <asm/page.h>
#include <asm/mmu.h>
#include <asm/firmware.h>
#include <asm/xmon.h>
#include <asm/udbg.h>
#include <asm/kexec.h>
#include <asm/code-patching.h>
#include <asm/livepatch.h>
#include <asm/opal.h>
#include <asm/cputhreads.h>
#include <asm/hw_irq.h>
#include <asm/feature-fixups.h>
#include <asm/kup.h>
#include <asm/early_ioremap.h>
#include <asm/pgalloc.h>

#include "setup.h"

int spinning_secondaries;
u64 ppc64_pft_size;

struct ppc64_caches ppc64_caches = {
	.l1d = {
		.block_size = 0x40,
		.log_block_size = 6,
	},
	.l1i = {
		.block_size = 0x40,
		.log_block_size = 6
	},
};
EXPORT_SYMBOL_GPL(ppc64_caches);

#if defined(CONFIG_PPC_BOOK3E) && defined(CONFIG_SMP)
void __init setup_tlb_core_data(void)
{
	int cpu;

	BUILD_BUG_ON(offsetof(struct tlb_core_data, lock) != 0);

	for_each_possible_cpu(cpu) {
		int first = cpu_first_thread_sibling(cpu);

		/*
		 * If we boot via kdump on a non-primary thread,
		 * make sure we point at the thread that actually
		 * set up this TLB.
		 */
		if (cpu_first_thread_sibling(boot_cpuid) == first)
			first = boot_cpuid;

		paca_ptrs[cpu]->tcd_ptr = &paca_ptrs[first]->tcd;

		/*
		 * If we have threads, we need either tlbsrx.
		 * or e6500 tablewalk mode, or else TLB handlers
		 * will be racy and could produce duplicate entries.
		 * Should we panic instead?
		 */
		WARN_ONCE(smt_enabled_at_boot >= 2 &&
			  !mmu_has_feature(MMU_FTR_USE_TLBRSRV) &&
			  book3e_htw_mode != PPC_HTW_E6500,
			  "%s: unsupported MMU configuration\n", __func__);
	}
}
#endif

#ifdef CONFIG_SMP

static char *smt_enabled_cmdline;

/* Look for ibm,smt-enabled OF option */
void __init check_smt_enabled(void)
{
	struct device_node *dn;
	const char *smt_option;

	/* Default to enabling all threads */
	smt_enabled_at_boot = threads_per_core;

	/* Allow the command line to overrule the OF option */
	if (smt_enabled_cmdline) {
		if (!strcmp(smt_enabled_cmdline, "on"))
			smt_enabled_at_boot = threads_per_core;
		else if (!strcmp(smt_enabled_cmdline, "off"))
			smt_enabled_at_boot = 0;
		else {
			int smt;
			int rc;

			rc = kstrtoint(smt_enabled_cmdline, 10, &smt);
			if (!rc)
				smt_enabled_at_boot =
					min(threads_per_core, smt);
		}
	} else {
		dn = of_find_node_by_path("/options");
		if (dn) {
			smt_option = of_get_property(dn, "ibm,smt-enabled",
						     NULL);

			if (smt_option) {
				if (!strcmp(smt_option, "on"))
					smt_enabled_at_boot = threads_per_core;
				else if (!strcmp(smt_option, "off"))
					smt_enabled_at_boot = 0;
			}

			of_node_put(dn);
		}
	}
}

/* Look for smt-enabled= cmdline option */
static int __init early_smt_enabled(char *p)
{
	smt_enabled_cmdline = p;
	return 0;
}
early_param("smt-enabled", early_smt_enabled);

#endif /* CONFIG_SMP */

/** Fix up paca fields required for the boot cpu */
static void __init fixup_boot_paca(void)
{
	/* The boot cpu is started */
	get_paca()->cpu_start = 1;
	/* Allow percpu accesses to work until we setup percpu data */
	get_paca()->data_offset = 0;
	/* Mark interrupts disabled in PACA */
	irq_soft_mask_set(IRQS_DISABLED);
}

static void __init configure_exceptions(void)
{
	/*
	 * Setup the trampolines from the lowmem exception vectors
	 * to the kdump kernel when not using a relocatable kernel.
	 */
	setup_kdump_trampoline();

	/* Under a PAPR hypervisor, we need hypercalls */
	if (firmware_has_feature(FW_FEATURE_SET_MODE)) {
		/*
		 * - PR KVM does not support AIL mode interrupts in the host
		 *   while a PR guest is running.
		 *
		 * - SCV system call interrupt vectors are only implemented for
		 *   AIL mode interrupts.
		 *
		 * - On pseries, AIL mode can only be enabled and disabled
		 *   system-wide so when a PR VM is created on a pseries host,
		 *   all CPUs of the host are set to AIL=0 mode.
		 *
		 * - Therefore host CPUs must not execute scv while a PR VM
		 *   exists.
		 *
		 * - SCV support can not be disabled dynamically because the
		 *   feature is advertised to host userspace. Disabling the
		 *   facility and emulating it would be possible but is not
		 *   implemented.
		 *
		 * - So SCV support is blanket disabled if PR KVM could possibly
		 *   run. That is, PR support compiled in, booting on pseries
		 *   with hash MMU.
		 */
		if (IS_ENABLED(CONFIG_KVM_BOOK3S_PR_POSSIBLE) && !radix_enabled()) {
			init_task.thread.fscr &= ~FSCR_SCV;
			cur_cpu_spec->cpu_user_features2 &= ~PPC_FEATURE2_SCV;
		}

		/* Enable AIL if possible */
		if (!pseries_enable_reloc_on_exc()) {
			init_task.thread.fscr &= ~FSCR_SCV;
			cur_cpu_spec->cpu_user_features2 &= ~PPC_FEATURE2_SCV;
		}

		/*
		 * Tell the hypervisor that we want our exceptions to
		 * be taken in little endian mode.
		 *
		 * We don't call this for big endian as our calling convention
		 * makes us always enter in BE, and the call may fail under
		 * some circumstances with kdump.
		 */
#ifdef __LITTLE_ENDIAN__
		pseries_little_endian_exceptions();
#endif
	} else {
		/* Set endian mode using OPAL */
		if (firmware_has_feature(FW_FEATURE_OPAL))
			opal_configure_cores();

		/* AIL on native is done in cpu_ready_for_interrupts() */
	}
}

static void cpu_ready_for_interrupts(void)
{
	/*
	 * Enable AIL if supported, and we are in hypervisor mode. This
	 * is called once for every processor.
	 *
	 * If we are not in hypervisor mode the job is done once for
	 * the whole partition in configure_exceptions().
	 */
	if (cpu_has_feature(CPU_FTR_HVMODE)) {
		unsigned long lpcr = mfspr(SPRN_LPCR);
		unsigned long new_lpcr = lpcr;

		if (cpu_has_feature(CPU_FTR_ARCH_31)) {
			/* P10 DD1 does not have HAIL */
			if (pvr_version_is(PVR_POWER10) &&
					(mfspr(SPRN_PVR) & 0xf00) == 0x100)
				new_lpcr |= LPCR_AIL_3;
			else
				new_lpcr |= LPCR_HAIL;
		} else if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
			new_lpcr |= LPCR_AIL_3;
		}

		if (new_lpcr != lpcr)
			mtspr(SPRN_LPCR, new_lpcr);
	}

	/*
	 * Set HFSCR:TM based on CPU features:
	 * In the special case of TM no suspend (P9N DD2.1), Linux is
	 * told TM is off via the dt-ftrs but told to (partially) use
	 * it via OPAL_REINIT_CPUS_TM_SUSPEND_DISABLED. So HFSCR[TM]
	 * will be off from dt-ftrs but we need to turn it on for the
	 * no suspend case.
	 */
	if (cpu_has_feature(CPU_FTR_HVMODE)) {
		if (cpu_has_feature(CPU_FTR_TM_COMP))
			mtspr(SPRN_HFSCR, mfspr(SPRN_HFSCR) | HFSCR_TM);
		else
			mtspr(SPRN_HFSCR, mfspr(SPRN_HFSCR) & ~HFSCR_TM);
	}

	/* Set IR and DR in PACA MSR */
	get_paca()->kernel_msr = MSR_KERNEL;
}

unsigned long spr_default_dscr = 0;

static void __init record_spr_defaults(void)
{
	if (early_cpu_has_feature(CPU_FTR_DSCR))
		spr_default_dscr = mfspr(SPRN_DSCR);
}

/*
 * Early initialization entry point. This is called by head.S
 * with MMU translation disabled. We rely on the "feature" of
 * the CPU that ignores the top 2 bits of the address in real
 * mode so we can access kernel globals normally provided we
 * only toy with things in the RMO region. From here, we do
 * some early parsing of the device-tree to setup out MEMBLOCK
 * data structures, and allocate & initialize the hash table
 * and segment tables so we can start running with translation
 * enabled.
 *
 * It is this function which will call the probe() callback of
 * the various platform types and copy the matching one to the
 * global ppc_md structure. Your platform can eventually do
 * some very early initializations from the probe() routine, but
 * this is not recommended, be very careful as, for example, the
 * device-tree is not accessible via normal means at this point.
 */

void __init early_setup(unsigned long dt_ptr)
{
	static __initdata struct paca_struct boot_paca;

	/* -------- printk is _NOT_ safe to use here ! ------- */

	/*
	 * Assume we're on cpu 0 for now.
	 *
	 * We need to load a PACA very early for a few reasons.
	 *
	 * The stack protector canary is stored in the paca, so as soon as we
	 * call any stack protected code we need r13 pointing somewhere valid.
	 *
	 * If we are using kcov it will call in_task() in its instrumentation,
	 * which relies on the current task from the PACA.
	 *
	 * dt_cpu_ftrs_init() calls into generic OF/fdt code, as well as
	 * printk(), which can trigger both stack protector and kcov.
	 *
	 * percpu variables and spin locks also use the paca.
	 *
	 * So set up a temporary paca. It will be replaced below once we know
	 * what CPU we are on.
	 */
	initialise_paca(&boot_paca, 0);
	setup_paca(&boot_paca);
	fixup_boot_paca();

	/* -------- printk is now safe to use ------- */

	/* Try new device tree based feature discovery ... */
	if (!dt_cpu_ftrs_init(__va(dt_ptr)))
		/* Otherwise use the old style CPU table */
		identify_cpu(0, mfspr(SPRN_PVR));

	/* Enable early debugging if any specified (see udbg.h) */
	udbg_early_init();

	udbg_printf(" -> %s(), dt_ptr: 0x%lx\n", __func__, dt_ptr);

	/*
	 * Do early initialization using the flattened device
	 * tree, such as retrieving the physical memory map or
	 * calculating/retrieving the hash table size.
	 */
	early_init_devtree(__va(dt_ptr));

	/* Now we know the logical id of our boot cpu, setup the paca. */
	if (boot_cpuid != 0) {
		/* Poison paca_ptrs[0] again if it's not the boot cpu */
		memset(&paca_ptrs[0], 0x88, sizeof(paca_ptrs[0]));
	}
	setup_paca(paca_ptrs[boot_cpuid]);
	fixup_boot_paca();

	/*
	 * Configure exception handlers. This include setting up trampolines
	 * if needed, setting exception endian mode, etc...
	 */
	configure_exceptions();

	/*
	 * Configure Kernel Userspace Protection. This needs to happen before
	 * feature fixups for platforms that implement this using features.
	 */
	setup_kup();

	/* Apply all the dynamic patching */
	apply_feature_fixups();
	setup_feature_keys();

	/* Initialize the hash table or TLB handling */
	early_init_mmu();

	early_ioremap_setup();

	/*
	 * After firmware and early platform setup code has set things up,
	 * we note the SPR values for configurable control/performance
	 * registers, and use those as initial defaults.
	 */
	record_spr_defaults();

	/*
	 * At this point, we can let interrupts switch to virtual mode
	 * (the MMU has been setup), so adjust the MSR in the PACA to
	 * have IR and DR set and enable AIL if it exists
	 */
	cpu_ready_for_interrupts();

	/*
	 * We enable ftrace here, but since we only support DYNAMIC_FTRACE, it
	 * will only actually get enabled on the boot cpu much later once
	 * ftrace itself has been initialized.
	 */
	this_cpu_enable_ftrace();

	udbg_printf(" <- %s()\n", __func__);

#ifdef CONFIG_PPC_EARLY_DEBUG_BOOTX
	/*
	 * This needs to be done *last* (after the above udbg_printf() even)
	 *
	 * Right after we return from this function, we turn on the MMU
	 * which means the real-mode access trick that btext does will
	 * no longer work, it needs to switch to using a real MMU
	 * mapping. This call will ensure that it does
	 */
	btext_map();
#endif /* CONFIG_PPC_EARLY_DEBUG_BOOTX */
}

#ifdef CONFIG_SMP
void early_setup_secondary(void)
{
	/* Mark interrupts disabled in PACA */
	irq_soft_mask_set(IRQS_DISABLED);

	/* Initialize the hash table or TLB handling */
	early_init_mmu_secondary();

	/* Perform any KUP setup that is per-cpu */
	setup_kup();

	/*
	 * At this point, we can let interrupts switch to virtual mode
	 * (the MMU has been setup), so adjust the MSR in the PACA to
	 * have IR and DR set.
	 */
	cpu_ready_for_interrupts();
}

#endif /* CONFIG_SMP */

void panic_smp_self_stop(void)
{
	hard_irq_disable();
	spin_begin();
	while (1)
		spin_cpu_relax();
}

#if defined(CONFIG_SMP) || defined(CONFIG_KEXEC_CORE)
static bool use_spinloop(void)
{
	if (IS_ENABLED(CONFIG_PPC_BOOK3S)) {
		/*
		 * See comments in head_64.S -- not all platforms insert
		 * secondaries at __secondary_hold and wait at the spin
		 * loop.
		 */
		if (firmware_has_feature(FW_FEATURE_OPAL))
			return false;
		return true;
	}

	/*
	 * When book3e boots from kexec, the ePAPR spin table does
	 * not get used.
	 */
	return of_property_read_bool(of_chosen, "linux,booted-from-kexec");
}

void smp_release_cpus(void)
{
	unsigned long *ptr;
	int i;

	if (!use_spinloop())
		return;

	/* All secondary cpus are spinning on a common spinloop, release them
	 * all now so they can start to spin on their individual paca
	 * spinloops. For non SMP kernels, the secondary cpus never get out
	 * of the common spinloop.
	 */

	ptr  = (unsigned long *)((unsigned long)&__secondary_hold_spinloop
			- PHYSICAL_START);
	*ptr = ppc_function_entry(generic_secondary_smp_init);

	/* And wait a bit for them to catch up */
	for (i = 0; i < 100000; i++) {
		mb();
		HMT_low();
		if (spinning_secondaries == 0)
			break;
		udelay(1);
	}
	pr_debug("spinning_secondaries = %d\n", spinning_secondaries);
}
#endif /* CONFIG_SMP || CONFIG_KEXEC_CORE */

/*
 * Initialize some remaining members of the ppc64_caches and systemcfg
 * structures
 * (at least until we get rid of them completely). This is mostly some
 * cache informations about the CPU that will be used by cache flush
 * routines and/or provided to userland
 */

static void __init init_cache_info(struct ppc_cache_info *info, u32 size, u32 lsize,
			    u32 bsize, u32 sets)
{
	info->size = size;
	info->sets = sets;
	info->line_size = lsize;
	info->block_size = bsize;
	info->log_block_size = __ilog2(bsize);
	if (bsize)
		info->blocks_per_page = PAGE_SIZE / bsize;
	else
		info->blocks_per_page = 0;

	if (sets == 0)
		info->assoc = 0xffff;
	else
		info->assoc = size / (sets * lsize);
}

static bool __init parse_cache_info(struct device_node *np,
				    bool icache,
				    struct ppc_cache_info *info)
{
	static const char *ipropnames[] __initdata = {
		"i-cache-size",
		"i-cache-sets",
		"i-cache-block-size",
		"i-cache-line-size",
	};
	static const char *dpropnames[] __initdata = {
		"d-cache-size",
		"d-cache-sets",
		"d-cache-block-size",
		"d-cache-line-size",
	};
	const char **propnames = icache ? ipropnames : dpropnames;
	const __be32 *sizep, *lsizep, *bsizep, *setsp;
	u32 size, lsize, bsize, sets;
	bool success = true;

	size = 0;
	sets = -1u;
	lsize = bsize = cur_cpu_spec->dcache_bsize;
	sizep = of_get_property(np, propnames[0], NULL);
	if (sizep != NULL)
		size = be32_to_cpu(*sizep);
	setsp = of_get_property(np, propnames[1], NULL);
	if (setsp != NULL)
		sets = be32_to_cpu(*setsp);
	bsizep = of_get_property(np, propnames[2], NULL);
	lsizep = of_get_property(np, propnames[3], NULL);
	if (bsizep == NULL)
		bsizep = lsizep;
	if (lsizep == NULL)
		lsizep = bsizep;
	if (lsizep != NULL)
		lsize = be32_to_cpu(*lsizep);
	if (bsizep != NULL)
		bsize = be32_to_cpu(*bsizep);
	if (sizep == NULL || bsizep == NULL || lsizep == NULL)
		success = false;

	/*
	 * OF is weird .. it represents fully associative caches
	 * as "1 way" which doesn't make much sense and doesn't
	 * leave room for direct mapped. We'll assume that 0
	 * in OF means direct mapped for that reason.
	 */
	if (sets == 1)
		sets = 0;
	else if (sets == 0)
		sets = 1;

	init_cache_info(info, size, lsize, bsize, sets);

	return success;
}

void __init initialize_cache_info(void)
{
	struct device_node *cpu = NULL, *l2, *l3 = NULL;
	u32 pvr;

	/*
	 * All shipping POWER8 machines have a firmware bug that
	 * puts incorrect information in the device-tree. This will
	 * be (hopefully) fixed for future chips but for now hard
	 * code the values if we are running on one of these
	 */
	pvr = PVR_VER(mfspr(SPRN_PVR));
	if (pvr == PVR_POWER8 || pvr == PVR_POWER8E ||
	    pvr == PVR_POWER8NVL) {
						/* size    lsize   blk  sets */
		init_cache_info(&ppc64_caches.l1i, 0x8000,   128,  128, 32);
		init_cache_info(&ppc64_caches.l1d, 0x10000,  128,  128, 64);
		init_cache_info(&ppc64_caches.l2,  0x80000,  128,  0,   512);
		init_cache_info(&ppc64_caches.l3,  0x800000, 128,  0,   8192);
	} else
		cpu = of_find_node_by_type(NULL, "cpu");

	/*
	 * We're assuming *all* of the CPUs have the same
	 * d-cache and i-cache sizes... -Peter
	 */
	if (cpu) {
		if (!parse_cache_info(cpu, false, &ppc64_caches.l1d))
			pr_warn("Argh, can't find dcache properties !\n");

		if (!parse_cache_info(cpu, true, &ppc64_caches.l1i))
			pr_warn("Argh, can't find icache properties !\n");

		/*
		 * Try to find the L2 and L3 if any. Assume they are
		 * unified and use the D-side properties.
		 */
		l2 = of_find_next_cache_node(cpu);
		of_node_put(cpu);
		if (l2) {
			parse_cache_info(l2, false, &ppc64_caches.l2);
			l3 = of_find_next_cache_node(l2);
			of_node_put(l2);
		}
		if (l3) {
			parse_cache_info(l3, false, &ppc64_caches.l3);
			of_node_put(l3);
		}
	}

	/* For use by binfmt_elf */
	dcache_bsize = ppc64_caches.l1d.block_size;
	icache_bsize = ppc64_caches.l1i.block_size;

	cur_cpu_spec->dcache_bsize = dcache_bsize;
	cur_cpu_spec->icache_bsize = icache_bsize;
}

/*
 * This returns the limit below which memory accesses to the linear
 * mapping are guarnateed not to cause an architectural exception (e.g.,
 * TLB or SLB miss fault).
 *
 * This is used to allocate PACAs and various interrupt stacks that
 * that are accessed early in interrupt handlers that must not cause
 * re-entrant interrupts.
 */
__init u64 ppc64_bolted_size(void)
{
#ifdef CONFIG_PPC_BOOK3E
	/* Freescale BookE bolts the entire linear mapping */
	/* XXX: BookE ppc64_rma_limit setup seems to disagree? */
	if (early_mmu_has_feature(MMU_FTR_TYPE_FSL_E))
		return linear_map_top;
	/* Other BookE, we assume the first GB is bolted */
	return 1ul << 30;
#else
	/* BookS radix, does not take faults on linear mapping */
	if (early_radix_enabled())
		return ULONG_MAX;

	/* BookS hash, the first segment is bolted */
	if (early_mmu_has_feature(MMU_FTR_1T_SEGMENT))
		return 1UL << SID_SHIFT_1T;
	return 1UL << SID_SHIFT;
#endif
}

static void *__init alloc_stack(unsigned long limit, int cpu)
{
	void *ptr;

	BUILD_BUG_ON(STACK_INT_FRAME_SIZE % 16);

	ptr = memblock_alloc_try_nid(THREAD_SIZE, THREAD_ALIGN,
				     MEMBLOCK_LOW_LIMIT, limit,
				     early_cpu_to_node(cpu));
	if (!ptr)
		panic("cannot allocate stacks");

	return ptr;
}

void __init irqstack_early_init(void)
{
	u64 limit = ppc64_bolted_size();
	unsigned int i;

	/*
	 * Interrupt stacks must be in the first segment since we
	 * cannot afford to take SLB misses on them. They are not
	 * accessed in realmode.
	 */
	for_each_possible_cpu(i) {
		softirq_ctx[i] = alloc_stack(limit, i);
		hardirq_ctx[i] = alloc_stack(limit, i);
	}
}

#ifdef CONFIG_PPC_BOOK3E
void __init exc_lvl_early_init(void)
{
	unsigned int i;

	for_each_possible_cpu(i) {
		void *sp;

		sp = alloc_stack(ULONG_MAX, i);
		critirq_ctx[i] = sp;
		paca_ptrs[i]->crit_kstack = sp + THREAD_SIZE;

		sp = alloc_stack(ULONG_MAX, i);
		dbgirq_ctx[i] = sp;
		paca_ptrs[i]->dbg_kstack = sp + THREAD_SIZE;

		sp = alloc_stack(ULONG_MAX, i);
		mcheckirq_ctx[i] = sp;
		paca_ptrs[i]->mc_kstack = sp + THREAD_SIZE;
	}

	if (cpu_has_feature(CPU_FTR_DEBUG_LVL_EXC))
		patch_exception(0x040, exc_debug_debug_book3e);
}
#endif

/*
 * Stack space used when we detect a bad kernel stack pointer, and
 * early in SMP boots before relocation is enabled. Exclusive emergency
 * stack for machine checks.
 */
void __init emergency_stack_init(void)
{
	u64 limit, mce_limit;
	unsigned int i;

	/*
	 * Emergency stacks must be under 256MB, we cannot afford to take
	 * SLB misses on them. The ABI also requires them to be 128-byte
	 * aligned.
	 *
	 * Since we use these as temporary stacks during secondary CPU
	 * bringup, machine check, system reset, and HMI, we need to get
	 * at them in real mode. This means they must also be within the RMO
	 * region.
	 *
	 * The IRQ stacks allocated elsewhere in this file are zeroed and
	 * initialized in kernel/irq.c. These are initialized here in order
	 * to have emergency stacks available as early as possible.
	 */
	limit = mce_limit = min(ppc64_bolted_size(), ppc64_rma_size);

	/*
	 * Machine check on pseries calls rtas, but can't use the static
	 * rtas_args due to a machine check hitting while the lock is held.
	 * rtas args have to be under 4GB, so the machine check stack is
	 * limited to 4GB so args can be put on stack.
	 */
	if (firmware_has_feature(FW_FEATURE_LPAR) && mce_limit > SZ_4G)
		mce_limit = SZ_4G;

	for_each_possible_cpu(i) {
		paca_ptrs[i]->emergency_sp = alloc_stack(limit, i) + THREAD_SIZE;

#ifdef CONFIG_PPC_BOOK3S_64
		/* emergency stack for NMI exception handling. */
		paca_ptrs[i]->nmi_emergency_sp = alloc_stack(limit, i) + THREAD_SIZE;

		/* emergency stack for machine check exception handling. */
		paca_ptrs[i]->mc_emergency_sp = alloc_stack(mce_limit, i) + THREAD_SIZE;
#endif
	}
}

#ifdef CONFIG_SMP
static int pcpu_cpu_distance(unsigned int from, unsigned int to)
{
	if (early_cpu_to_node(from) == early_cpu_to_node(to))
		return LOCAL_DISTANCE;
	else
		return REMOTE_DISTANCE;
}

static __init int pcpu_cpu_to_node(int cpu)
{
	return early_cpu_to_node(cpu);
}

unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
EXPORT_SYMBOL(__per_cpu_offset);

void __init setup_per_cpu_areas(void)
{
	const size_t dyn_size = PERCPU_MODULE_RESERVE + PERCPU_DYNAMIC_RESERVE;
	size_t atom_size;
	unsigned long delta;
	unsigned int cpu;
	int rc = -EINVAL;

	/*
	 * BookE and BookS radix are historical values and should be revisited.
	 */
	if (IS_ENABLED(CONFIG_PPC_BOOK3E)) {
		atom_size = SZ_1M;
	} else if (radix_enabled()) {
		atom_size = PAGE_SIZE;
	} else if (IS_ENABLED(CONFIG_PPC_64S_HASH_MMU)) {
		/*
		 * Linear mapping is one of 4K, 1M and 16M.  For 4K, no need
		 * to group units.  For larger mappings, use 1M atom which
		 * should be large enough to contain a number of units.
		 */
		if (mmu_linear_psize == MMU_PAGE_4K)
			atom_size = PAGE_SIZE;
		else
			atom_size = SZ_1M;
	}

	if (pcpu_chosen_fc != PCPU_FC_PAGE) {
		rc = pcpu_embed_first_chunk(0, dyn_size, atom_size, pcpu_cpu_distance,
					    pcpu_cpu_to_node);
		if (rc)
			pr_warn("PERCPU: %s allocator failed (%d), "
				"falling back to page size\n",
				pcpu_fc_names[pcpu_chosen_fc], rc);
	}

	if (rc < 0)
		rc = pcpu_page_first_chunk(0, pcpu_cpu_to_node);
	if (rc < 0)
		panic("cannot initialize percpu area (err=%d)", rc);

	delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
	for_each_possible_cpu(cpu) {
                __per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu];
		paca_ptrs[cpu]->data_offset = __per_cpu_offset[cpu];
	}
}
#endif

#ifdef CONFIG_MEMORY_HOTPLUG
unsigned long memory_block_size_bytes(void)
{
	if (ppc_md.memory_block_size)
		return ppc_md.memory_block_size();

	return MIN_MEMORY_BLOCK_SIZE;
}
#endif

#if defined(CONFIG_PPC_INDIRECT_PIO) || defined(CONFIG_PPC_INDIRECT_MMIO)
struct ppc_pci_io ppc_pci_io;
EXPORT_SYMBOL(ppc_pci_io);
#endif

#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF
u64 hw_nmi_get_sample_period(int watchdog_thresh)
{
	return ppc_proc_freq * watchdog_thresh;
}
#endif

/*
 * The perf based hardlockup detector breaks PMU event based branches, so
 * disable it by default. Book3S has a soft-nmi hardlockup detector based
 * on the decrementer interrupt, so it does not suffer from this problem.
 *
 * It is likely to get false positives in KVM guests, so disable it there
 * by default too. PowerVM will not stop or arbitrarily oversubscribe
 * CPUs, but give a minimum regular allotment even with SPLPAR, so enable
 * the detector for non-KVM guests, assume PowerVM.
 */
static int __init disable_hardlockup_detector(void)
{
#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF
	hardlockup_detector_disable();
#else
	if (firmware_has_feature(FW_FEATURE_LPAR)) {
		if (is_kvm_guest())
			hardlockup_detector_disable();
	}
#endif

	return 0;
}
early_initcall(disable_hardlockup_detector);