aboutsummaryrefslogtreecommitdiffstats
path: root/arch/powerpc/platforms/pseries/lpar.c
blob: ea602f7f97ce1df5386f02808438cdb3272dd6d5 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
/*
 * pSeries_lpar.c
 * Copyright (C) 2001 Todd Inglett, IBM Corporation
 *
 * pSeries LPAR support.
 * 
 * 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.
 * 
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 * 
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
 */

/* Enables debugging of low-level hash table routines - careful! */
#undef DEBUG
#define pr_fmt(fmt) "lpar: " fmt

#include <linux/kernel.h>
#include <linux/dma-mapping.h>
#include <linux/console.h>
#include <linux/export.h>
#include <linux/jump_label.h>
#include <linux/delay.h>
#include <linux/stop_machine.h>
#include <asm/processor.h>
#include <asm/mmu.h>
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/machdep.h>
#include <asm/mmu_context.h>
#include <asm/iommu.h>
#include <asm/tlb.h>
#include <asm/prom.h>
#include <asm/cputable.h>
#include <asm/udbg.h>
#include <asm/smp.h>
#include <asm/trace.h>
#include <asm/firmware.h>
#include <asm/plpar_wrappers.h>
#include <asm/kexec.h>
#include <asm/fadump.h>
#include <asm/asm-prototypes.h>

#include "pseries.h"

/* Flag bits for H_BULK_REMOVE */
#define HBR_REQUEST	0x4000000000000000UL
#define HBR_RESPONSE	0x8000000000000000UL
#define HBR_END		0xc000000000000000UL
#define HBR_AVPN	0x0200000000000000UL
#define HBR_ANDCOND	0x0100000000000000UL


/* in hvCall.S */
EXPORT_SYMBOL(plpar_hcall);
EXPORT_SYMBOL(plpar_hcall9);
EXPORT_SYMBOL(plpar_hcall_norets);

void vpa_init(int cpu)
{
	int hwcpu = get_hard_smp_processor_id(cpu);
	unsigned long addr;
	long ret;
	struct paca_struct *pp;
	struct dtl_entry *dtl;

	/*
	 * The spec says it "may be problematic" if CPU x registers the VPA of
	 * CPU y. We should never do that, but wail if we ever do.
	 */
	WARN_ON(cpu != smp_processor_id());

	if (cpu_has_feature(CPU_FTR_ALTIVEC))
		lppaca_of(cpu).vmxregs_in_use = 1;

	if (cpu_has_feature(CPU_FTR_ARCH_207S))
		lppaca_of(cpu).ebb_regs_in_use = 1;

	addr = __pa(&lppaca_of(cpu));
	ret = register_vpa(hwcpu, addr);

	if (ret) {
		pr_err("WARNING: VPA registration for cpu %d (hw %d) of area "
		       "%lx failed with %ld\n", cpu, hwcpu, addr, ret);
		return;
	}

#ifdef CONFIG_PPC_BOOK3S_64
	/*
	 * PAPR says this feature is SLB-Buffer but firmware never
	 * reports that.  All SPLPAR support SLB shadow buffer.
	 */
	if (!radix_enabled() && firmware_has_feature(FW_FEATURE_SPLPAR)) {
		addr = __pa(paca_ptrs[cpu]->slb_shadow_ptr);
		ret = register_slb_shadow(hwcpu, addr);
		if (ret)
			pr_err("WARNING: SLB shadow buffer registration for "
			       "cpu %d (hw %d) of area %lx failed with %ld\n",
			       cpu, hwcpu, addr, ret);
	}
#endif /* CONFIG_PPC_BOOK3S_64 */

	/*
	 * Register dispatch trace log, if one has been allocated.
	 */
	pp = paca_ptrs[cpu];
	dtl = pp->dispatch_log;
	if (dtl) {
		pp->dtl_ridx = 0;
		pp->dtl_curr = dtl;
		lppaca_of(cpu).dtl_idx = 0;

		/* hypervisor reads buffer length from this field */
		dtl->enqueue_to_dispatch_time = cpu_to_be32(DISPATCH_LOG_BYTES);
		ret = register_dtl(hwcpu, __pa(dtl));
		if (ret)
			pr_err("WARNING: DTL registration of cpu %d (hw %d) "
			       "failed with %ld\n", smp_processor_id(),
			       hwcpu, ret);
		lppaca_of(cpu).dtl_enable_mask = 2;
	}
}

#ifdef CONFIG_PPC_BOOK3S_64

static long pSeries_lpar_hpte_insert(unsigned long hpte_group,
				     unsigned long vpn, unsigned long pa,
				     unsigned long rflags, unsigned long vflags,
				     int psize, int apsize, int ssize)
{
	unsigned long lpar_rc;
	unsigned long flags;
	unsigned long slot;
	unsigned long hpte_v, hpte_r;

	if (!(vflags & HPTE_V_BOLTED))
		pr_devel("hpte_insert(group=%lx, vpn=%016lx, "
			 "pa=%016lx, rflags=%lx, vflags=%lx, psize=%d)\n",
			 hpte_group, vpn,  pa, rflags, vflags, psize);

	hpte_v = hpte_encode_v(vpn, psize, apsize, ssize) | vflags | HPTE_V_VALID;
	hpte_r = hpte_encode_r(pa, psize, apsize) | rflags;

	if (!(vflags & HPTE_V_BOLTED))
		pr_devel(" hpte_v=%016lx, hpte_r=%016lx\n", hpte_v, hpte_r);

	/* Now fill in the actual HPTE */
	/* Set CEC cookie to 0         */
	/* Zero page = 0               */
	/* I-cache Invalidate = 0      */
	/* I-cache synchronize = 0     */
	/* Exact = 0                   */
	flags = 0;

	if (firmware_has_feature(FW_FEATURE_XCMO) && !(hpte_r & HPTE_R_N))
		flags |= H_COALESCE_CAND;

	lpar_rc = plpar_pte_enter(flags, hpte_group, hpte_v, hpte_r, &slot);
	if (unlikely(lpar_rc == H_PTEG_FULL)) {
		pr_devel("Hash table group is full\n");
		return -1;
	}

	/*
	 * Since we try and ioremap PHBs we don't own, the pte insert
	 * will fail. However we must catch the failure in hash_page
	 * or we will loop forever, so return -2 in this case.
	 */
	if (unlikely(lpar_rc != H_SUCCESS)) {
		pr_err("Failed hash pte insert with error %ld\n", lpar_rc);
		return -2;
	}
	if (!(vflags & HPTE_V_BOLTED))
		pr_devel(" -> slot: %lu\n", slot & 7);

	/* Because of iSeries, we have to pass down the secondary
	 * bucket bit here as well
	 */
	return (slot & 7) | (!!(vflags & HPTE_V_SECONDARY) << 3);
}

static DEFINE_SPINLOCK(pSeries_lpar_tlbie_lock);

static long pSeries_lpar_hpte_remove(unsigned long hpte_group)
{
	unsigned long slot_offset;
	unsigned long lpar_rc;
	int i;
	unsigned long dummy1, dummy2;

	/* pick a random slot to start at */
	slot_offset = mftb() & 0x7;

	for (i = 0; i < HPTES_PER_GROUP; i++) {

		/* don't remove a bolted entry */
		lpar_rc = plpar_pte_remove(H_ANDCOND, hpte_group + slot_offset,
					   (0x1UL << 4), &dummy1, &dummy2);
		if (lpar_rc == H_SUCCESS)
			return i;

		/*
		 * The test for adjunct partition is performed before the
		 * ANDCOND test.  H_RESOURCE may be returned, so we need to
		 * check for that as well.
		 */
		BUG_ON(lpar_rc != H_NOT_FOUND && lpar_rc != H_RESOURCE);

		slot_offset++;
		slot_offset &= 0x7;
	}

	return -1;
}

static void manual_hpte_clear_all(void)
{
	unsigned long size_bytes = 1UL << ppc64_pft_size;
	unsigned long hpte_count = size_bytes >> 4;
	struct {
		unsigned long pteh;
		unsigned long ptel;
	} ptes[4];
	long lpar_rc;
	unsigned long i, j;

	/* Read in batches of 4,
	 * invalidate only valid entries not in the VRMA
	 * hpte_count will be a multiple of 4
         */
	for (i = 0; i < hpte_count; i += 4) {
		lpar_rc = plpar_pte_read_4_raw(0, i, (void *)ptes);
		if (lpar_rc != H_SUCCESS) {
			pr_info("Failed to read hash page table at %ld err %ld\n",
				i, lpar_rc);
			continue;
		}
		for (j = 0; j < 4; j++){
			if ((ptes[j].pteh & HPTE_V_VRMA_MASK) ==
				HPTE_V_VRMA_MASK)
				continue;
			if (ptes[j].pteh & HPTE_V_VALID)
				plpar_pte_remove_raw(0, i + j, 0,
					&(ptes[j].pteh), &(ptes[j].ptel));
		}
	}
}

static int hcall_hpte_clear_all(void)
{
	int rc;

	do {
		rc = plpar_hcall_norets(H_CLEAR_HPT);
	} while (rc == H_CONTINUE);

	return rc;
}

static void pseries_hpte_clear_all(void)
{
	int rc;

	rc = hcall_hpte_clear_all();
	if (rc != H_SUCCESS)
		manual_hpte_clear_all();

#ifdef __LITTLE_ENDIAN__
	/*
	 * Reset exceptions to big endian.
	 *
	 * FIXME this is a hack for kexec, we need to reset the exception
	 * endian before starting the new kernel and this is a convenient place
	 * to do it.
	 *
	 * This is also called on boot when a fadump happens. In that case we
	 * must not change the exception endian mode.
	 */
	if (firmware_has_feature(FW_FEATURE_SET_MODE) && !is_fadump_active())
		pseries_big_endian_exceptions();
#endif
}

/*
 * NOTE: for updatepp ops we are fortunate that the linux "newpp" bits and
 * the low 3 bits of flags happen to line up.  So no transform is needed.
 * We can probably optimize here and assume the high bits of newpp are
 * already zero.  For now I am paranoid.
 */
static long pSeries_lpar_hpte_updatepp(unsigned long slot,
				       unsigned long newpp,
				       unsigned long vpn,
				       int psize, int apsize,
				       int ssize, unsigned long inv_flags)
{
	unsigned long lpar_rc;
	unsigned long flags;
	unsigned long want_v;

	want_v = hpte_encode_avpn(vpn, psize, ssize);

	flags = (newpp & 7) | H_AVPN;
	if (mmu_has_feature(MMU_FTR_KERNEL_RO))
		/* Move pp0 into bit 8 (IBM 55) */
		flags |= (newpp & HPTE_R_PP0) >> 55;

	pr_devel("    update: avpnv=%016lx, hash=%016lx, f=%lx, psize: %d ...",
		 want_v, slot, flags, psize);

	lpar_rc = plpar_pte_protect(flags, slot, want_v);

	if (lpar_rc == H_NOT_FOUND) {
		pr_devel("not found !\n");
		return -1;
	}

	pr_devel("ok\n");

	BUG_ON(lpar_rc != H_SUCCESS);

	return 0;
}

static long __pSeries_lpar_hpte_find(unsigned long want_v, unsigned long hpte_group)
{
	long lpar_rc;
	unsigned long i, j;
	struct {
		unsigned long pteh;
		unsigned long ptel;
	} ptes[4];

	for (i = 0; i < HPTES_PER_GROUP; i += 4, hpte_group += 4) {

		lpar_rc = plpar_pte_read_4(0, hpte_group, (void *)ptes);
		if (lpar_rc != H_SUCCESS) {
			pr_info("Failed to read hash page table at %ld err %ld\n",
				hpte_group, lpar_rc);
			continue;
		}

		for (j = 0; j < 4; j++) {
			if (HPTE_V_COMPARE(ptes[j].pteh, want_v) &&
			    (ptes[j].pteh & HPTE_V_VALID))
				return i + j;
		}
	}

	return -1;
}

static long pSeries_lpar_hpte_find(unsigned long vpn, int psize, int ssize)
{
	long slot;
	unsigned long hash;
	unsigned long want_v;
	unsigned long hpte_group;

	hash = hpt_hash(vpn, mmu_psize_defs[psize].shift, ssize);
	want_v = hpte_encode_avpn(vpn, psize, ssize);

	/* Bolted entries are always in the primary group */
	hpte_group = (hash & htab_hash_mask) * HPTES_PER_GROUP;
	slot = __pSeries_lpar_hpte_find(want_v, hpte_group);
	if (slot < 0)
		return -1;
	return hpte_group + slot;
}

static void pSeries_lpar_hpte_updateboltedpp(unsigned long newpp,
					     unsigned long ea,
					     int psize, int ssize)
{
	unsigned long vpn;
	unsigned long lpar_rc, slot, vsid, flags;

	vsid = get_kernel_vsid(ea, ssize);
	vpn = hpt_vpn(ea, vsid, ssize);

	slot = pSeries_lpar_hpte_find(vpn, psize, ssize);
	BUG_ON(slot == -1);

	flags = newpp & 7;
	if (mmu_has_feature(MMU_FTR_KERNEL_RO))
		/* Move pp0 into bit 8 (IBM 55) */
		flags |= (newpp & HPTE_R_PP0) >> 55;

	lpar_rc = plpar_pte_protect(flags, slot, 0);

	BUG_ON(lpar_rc != H_SUCCESS);
}

static void pSeries_lpar_hpte_invalidate(unsigned long slot, unsigned long vpn,
					 int psize, int apsize,
					 int ssize, int local)
{
	unsigned long want_v;
	unsigned long lpar_rc;
	unsigned long dummy1, dummy2;

	pr_devel("    inval : slot=%lx, vpn=%016lx, psize: %d, local: %d\n",
		 slot, vpn, psize, local);

	want_v = hpte_encode_avpn(vpn, psize, ssize);
	lpar_rc = plpar_pte_remove(H_AVPN, slot, want_v, &dummy1, &dummy2);
	if (lpar_rc == H_NOT_FOUND)
		return;

	BUG_ON(lpar_rc != H_SUCCESS);
}

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/*
 * Limit iterations holding pSeries_lpar_tlbie_lock to 3. We also need
 * to make sure that we avoid bouncing the hypervisor tlbie lock.
 */
#define PPC64_HUGE_HPTE_BATCH 12

static void __pSeries_lpar_hugepage_invalidate(unsigned long *slot,
					     unsigned long *vpn, int count,
					     int psize, int ssize)
{
	unsigned long param[PLPAR_HCALL9_BUFSIZE];
	int i = 0, pix = 0, rc;
	unsigned long flags = 0;
	int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);

	if (lock_tlbie)
		spin_lock_irqsave(&pSeries_lpar_tlbie_lock, flags);

	for (i = 0; i < count; i++) {

		if (!firmware_has_feature(FW_FEATURE_BULK_REMOVE)) {
			pSeries_lpar_hpte_invalidate(slot[i], vpn[i], psize, 0,
						     ssize, 0);
		} else {
			param[pix] = HBR_REQUEST | HBR_AVPN | slot[i];
			param[pix+1] = hpte_encode_avpn(vpn[i], psize, ssize);
			pix += 2;
			if (pix == 8) {
				rc = plpar_hcall9(H_BULK_REMOVE, param,
						  param[0], param[1], param[2],
						  param[3], param[4], param[5],
						  param[6], param[7]);
				BUG_ON(rc != H_SUCCESS);
				pix = 0;
			}
		}
	}
	if (pix) {
		param[pix] = HBR_END;
		rc = plpar_hcall9(H_BULK_REMOVE, param, param[0], param[1],
				  param[2], param[3], param[4], param[5],
				  param[6], param[7]);
		BUG_ON(rc != H_SUCCESS);
	}

	if (lock_tlbie)
		spin_unlock_irqrestore(&pSeries_lpar_tlbie_lock, flags);
}

static void pSeries_lpar_hugepage_invalidate(unsigned long vsid,
					     unsigned long addr,
					     unsigned char *hpte_slot_array,
					     int psize, int ssize, int local)
{
	int i, index = 0;
	unsigned long s_addr = addr;
	unsigned int max_hpte_count, valid;
	unsigned long vpn_array[PPC64_HUGE_HPTE_BATCH];
	unsigned long slot_array[PPC64_HUGE_HPTE_BATCH];
	unsigned long shift, hidx, vpn = 0, hash, slot;

	shift = mmu_psize_defs[psize].shift;
	max_hpte_count = 1U << (PMD_SHIFT - shift);

	for (i = 0; i < max_hpte_count; i++) {
		valid = hpte_valid(hpte_slot_array, i);
		if (!valid)
			continue;
		hidx =  hpte_hash_index(hpte_slot_array, i);

		/* get the vpn */
		addr = s_addr + (i * (1ul << shift));
		vpn = hpt_vpn(addr, vsid, ssize);
		hash = hpt_hash(vpn, shift, ssize);
		if (hidx & _PTEIDX_SECONDARY)
			hash = ~hash;

		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
		slot += hidx & _PTEIDX_GROUP_IX;

		slot_array[index] = slot;
		vpn_array[index] = vpn;
		if (index == PPC64_HUGE_HPTE_BATCH - 1) {
			/*
			 * Now do a bluk invalidate
			 */
			__pSeries_lpar_hugepage_invalidate(slot_array,
							   vpn_array,
							   PPC64_HUGE_HPTE_BATCH,
							   psize, ssize);
			index = 0;
		} else
			index++;
	}
	if (index)
		__pSeries_lpar_hugepage_invalidate(slot_array, vpn_array,
						   index, psize, ssize);
}
#else
static void pSeries_lpar_hugepage_invalidate(unsigned long vsid,
					     unsigned long addr,
					     unsigned char *hpte_slot_array,
					     int psize, int ssize, int local)
{
	WARN(1, "%s called without THP support\n", __func__);
}
#endif

static int pSeries_lpar_hpte_removebolted(unsigned long ea,
					  int psize, int ssize)
{
	unsigned long vpn;
	unsigned long slot, vsid;

	vsid = get_kernel_vsid(ea, ssize);
	vpn = hpt_vpn(ea, vsid, ssize);

	slot = pSeries_lpar_hpte_find(vpn, psize, ssize);
	if (slot == -1)
		return -ENOENT;

	/*
	 * lpar doesn't use the passed actual page size
	 */
	pSeries_lpar_hpte_invalidate(slot, vpn, psize, 0, ssize, 0);
	return 0;
}

/*
 * Take a spinlock around flushes to avoid bouncing the hypervisor tlbie
 * lock.
 */
static void pSeries_lpar_flush_hash_range(unsigned long number, int local)
{
	unsigned long vpn;
	unsigned long i, pix, rc;
	unsigned long flags = 0;
	struct ppc64_tlb_batch *batch = this_cpu_ptr(&ppc64_tlb_batch);
	int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
	unsigned long param[PLPAR_HCALL9_BUFSIZE];
	unsigned long hash, index, shift, hidx, slot;
	real_pte_t pte;
	int psize, ssize;

	if (lock_tlbie)
		spin_lock_irqsave(&pSeries_lpar_tlbie_lock, flags);

	psize = batch->psize;
	ssize = batch->ssize;
	pix = 0;
	for (i = 0; i < number; i++) {
		vpn = batch->vpn[i];
		pte = batch->pte[i];
		pte_iterate_hashed_subpages(pte, psize, vpn, index, shift) {
			hash = hpt_hash(vpn, shift, ssize);
			hidx = __rpte_to_hidx(pte, index);
			if (hidx & _PTEIDX_SECONDARY)
				hash = ~hash;
			slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
			slot += hidx & _PTEIDX_GROUP_IX;
			if (!firmware_has_feature(FW_FEATURE_BULK_REMOVE)) {
				/*
				 * lpar doesn't use the passed actual page size
				 */
				pSeries_lpar_hpte_invalidate(slot, vpn, psize,
							     0, ssize, local);
			} else {
				param[pix] = HBR_REQUEST | HBR_AVPN | slot;
				param[pix+1] = hpte_encode_avpn(vpn, psize,
								ssize);
				pix += 2;
				if (pix == 8) {
					rc = plpar_hcall9(H_BULK_REMOVE, param,
						param[0], param[1], param[2],
						param[3], param[4], param[5],
						param[6], param[7]);
					BUG_ON(rc != H_SUCCESS);
					pix = 0;
				}
			}
		} pte_iterate_hashed_end();
	}
	if (pix) {
		param[pix] = HBR_END;
		rc = plpar_hcall9(H_BULK_REMOVE, param, param[0], param[1],
				  param[2], param[3], param[4], param[5],
				  param[6], param[7]);
		BUG_ON(rc != H_SUCCESS);
	}

	if (lock_tlbie)
		spin_unlock_irqrestore(&pSeries_lpar_tlbie_lock, flags);
}

static int __init disable_bulk_remove(char *str)
{
	if (strcmp(str, "off") == 0 &&
	    firmware_has_feature(FW_FEATURE_BULK_REMOVE)) {
		pr_info("Disabling BULK_REMOVE firmware feature");
		powerpc_firmware_features &= ~FW_FEATURE_BULK_REMOVE;
	}
	return 1;
}

__setup("bulk_remove=", disable_bulk_remove);

#define HPT_RESIZE_TIMEOUT	10000 /* ms */

struct hpt_resize_state {
	unsigned long shift;
	int commit_rc;
};

static int pseries_lpar_resize_hpt_commit(void *data)
{
	struct hpt_resize_state *state = data;

	state->commit_rc = plpar_resize_hpt_commit(0, state->shift);
	if (state->commit_rc != H_SUCCESS)
		return -EIO;

	/* Hypervisor has transitioned the HTAB, update our globals */
	ppc64_pft_size = state->shift;
	htab_size_bytes = 1UL << ppc64_pft_size;
	htab_hash_mask = (htab_size_bytes >> 7) - 1;

	return 0;
}

/*
 * Must be called in process context. The caller must hold the
 * cpus_lock.
 */
static int pseries_lpar_resize_hpt(unsigned long shift)
{
	struct hpt_resize_state state = {
		.shift = shift,
		.commit_rc = H_FUNCTION,
	};
	unsigned int delay, total_delay = 0;
	int rc;
	ktime_t t0, t1, t2;

	might_sleep();

	if (!firmware_has_feature(FW_FEATURE_HPT_RESIZE))
		return -ENODEV;

	pr_info("Attempting to resize HPT to shift %lu\n", shift);

	t0 = ktime_get();

	rc = plpar_resize_hpt_prepare(0, shift);
	while (H_IS_LONG_BUSY(rc)) {
		delay = get_longbusy_msecs(rc);
		total_delay += delay;
		if (total_delay > HPT_RESIZE_TIMEOUT) {
			/* prepare with shift==0 cancels an in-progress resize */
			rc = plpar_resize_hpt_prepare(0, 0);
			if (rc != H_SUCCESS)
				pr_warn("Unexpected error %d cancelling timed out HPT resize\n",
				       rc);
			return -ETIMEDOUT;
		}
		msleep(delay);
		rc = plpar_resize_hpt_prepare(0, shift);
	};

	switch (rc) {
	case H_SUCCESS:
		/* Continue on */
		break;

	case H_PARAMETER:
		return -EINVAL;
	case H_RESOURCE:
		return -EPERM;
	default:
		pr_warn("Unexpected error %d from H_RESIZE_HPT_PREPARE\n", rc);
		return -EIO;
	}

	t1 = ktime_get();

	rc = stop_machine_cpuslocked(pseries_lpar_resize_hpt_commit,
				     &state, NULL);

	t2 = ktime_get();

	if (rc != 0) {
		switch (state.commit_rc) {
		case H_PTEG_FULL:
			pr_warn("Hash collision while resizing HPT\n");
			return -ENOSPC;

		default:
			pr_warn("Unexpected error %d from H_RESIZE_HPT_COMMIT\n",
				state.commit_rc);
			return -EIO;
		};
	}

	pr_info("HPT resize to shift %lu complete (%lld ms / %lld ms)\n",
		shift, (long long) ktime_ms_delta(t1, t0),
		(long long) ktime_ms_delta(t2, t1));

	return 0;
}

static int pseries_lpar_register_process_table(unsigned long base,
			unsigned long page_size, unsigned long table_size)
{
	long rc;
	unsigned long flags = 0;

	if (table_size)
		flags |= PROC_TABLE_NEW;
	if (radix_enabled())
		flags |= PROC_TABLE_RADIX | PROC_TABLE_GTSE;
	else
		flags |= PROC_TABLE_HPT_SLB;
	for (;;) {
		rc = plpar_hcall_norets(H_REGISTER_PROC_TBL, flags, base,
					page_size, table_size);
		if (!H_IS_LONG_BUSY(rc))
			break;
		mdelay(get_longbusy_msecs(rc));
	}
	if (rc != H_SUCCESS) {
		pr_err("Failed to register process table (rc=%ld)\n", rc);
		BUG();
	}
	return rc;
}

void __init hpte_init_pseries(void)
{
	mmu_hash_ops.hpte_invalidate	 = pSeries_lpar_hpte_invalidate;
	mmu_hash_ops.hpte_updatepp	 = pSeries_lpar_hpte_updatepp;
	mmu_hash_ops.hpte_updateboltedpp = pSeries_lpar_hpte_updateboltedpp;
	mmu_hash_ops.hpte_insert	 = pSeries_lpar_hpte_insert;
	mmu_hash_ops.hpte_remove	 = pSeries_lpar_hpte_remove;
	mmu_hash_ops.hpte_removebolted   = pSeries_lpar_hpte_removebolted;
	mmu_hash_ops.flush_hash_range	 = pSeries_lpar_flush_hash_range;
	mmu_hash_ops.hpte_clear_all      = pseries_hpte_clear_all;
	mmu_hash_ops.hugepage_invalidate = pSeries_lpar_hugepage_invalidate;
	register_process_table		 = pseries_lpar_register_process_table;

	if (firmware_has_feature(FW_FEATURE_HPT_RESIZE))
		mmu_hash_ops.resize_hpt = pseries_lpar_resize_hpt;
}

void radix_init_pseries(void)
{
	pr_info("Using radix MMU under hypervisor\n");
	register_process_table = pseries_lpar_register_process_table;
}

#ifdef CONFIG_PPC_SMLPAR
#define CMO_FREE_HINT_DEFAULT 1
static int cmo_free_hint_flag = CMO_FREE_HINT_DEFAULT;

static int __init cmo_free_hint(char *str)
{
	char *parm;
	parm = strstrip(str);

	if (strcasecmp(parm, "no") == 0 || strcasecmp(parm, "off") == 0) {
		pr_info("%s: CMO free page hinting is not active.\n", __func__);
		cmo_free_hint_flag = 0;
		return 1;
	}

	cmo_free_hint_flag = 1;
	pr_info("%s: CMO free page hinting is active.\n", __func__);

	if (strcasecmp(parm, "yes") == 0 || strcasecmp(parm, "on") == 0)
		return 1;

	return 0;
}

__setup("cmo_free_hint=", cmo_free_hint);

static void pSeries_set_page_state(struct page *page, int order,
				   unsigned long state)
{
	int i, j;
	unsigned long cmo_page_sz, addr;

	cmo_page_sz = cmo_get_page_size();
	addr = __pa((unsigned long)page_address(page));

	for (i = 0; i < (1 << order); i++, addr += PAGE_SIZE) {
		for (j = 0; j < PAGE_SIZE; j += cmo_page_sz)
			plpar_hcall_norets(H_PAGE_INIT, state, addr + j, 0);
	}
}

void arch_free_page(struct page *page, int order)
{
	if (radix_enabled())
		return;
	if (!cmo_free_hint_flag || !firmware_has_feature(FW_FEATURE_CMO))
		return;

	pSeries_set_page_state(page, order, H_PAGE_SET_UNUSED);
}
EXPORT_SYMBOL(arch_free_page);

#endif /* CONFIG_PPC_SMLPAR */
#endif /* CONFIG_PPC_BOOK3S_64 */

#ifdef CONFIG_TRACEPOINTS
#ifdef CONFIG_JUMP_LABEL
struct static_key hcall_tracepoint_key = STATIC_KEY_INIT;

int hcall_tracepoint_regfunc(void)
{
	static_key_slow_inc(&hcall_tracepoint_key);
	return 0;
}

void hcall_tracepoint_unregfunc(void)
{
	static_key_slow_dec(&hcall_tracepoint_key);
}
#else
/*
 * We optimise our hcall path by placing hcall_tracepoint_refcount
 * directly in the TOC so we can check if the hcall tracepoints are
 * enabled via a single load.
 */

/* NB: reg/unreg are called while guarded with the tracepoints_mutex */
extern long hcall_tracepoint_refcount;

int hcall_tracepoint_regfunc(void)
{
	hcall_tracepoint_refcount++;
	return 0;
}

void hcall_tracepoint_unregfunc(void)
{
	hcall_tracepoint_refcount--;
}
#endif

/*
 * Since the tracing code might execute hcalls we need to guard against
 * recursion. One example of this are spinlocks calling H_YIELD on
 * shared processor partitions.
 */
static DEFINE_PER_CPU(unsigned int, hcall_trace_depth);


void __trace_hcall_entry(unsigned long opcode, unsigned long *args)
{
	unsigned long flags;
	unsigned int *depth;

	/*
	 * We cannot call tracepoints inside RCU idle regions which
	 * means we must not trace H_CEDE.
	 */
	if (opcode == H_CEDE)
		return;

	local_irq_save(flags);

	depth = this_cpu_ptr(&hcall_trace_depth);

	if (*depth)
		goto out;

	(*depth)++;
	preempt_disable();
	trace_hcall_entry(opcode, args);
	(*depth)--;

out:
	local_irq_restore(flags);
}

void __trace_hcall_exit(long opcode, long retval, unsigned long *retbuf)
{
	unsigned long flags;
	unsigned int *depth;

	if (opcode == H_CEDE)
		return;

	local_irq_save(flags);

	depth = this_cpu_ptr(&hcall_trace_depth);

	if (*depth)
		goto out;

	(*depth)++;
	trace_hcall_exit(opcode, retval, retbuf);
	preempt_enable();
	(*depth)--;

out:
	local_irq_restore(flags);
}
#endif

/**
 * h_get_mpp
 * H_GET_MPP hcall returns info in 7 parms
 */
int h_get_mpp(struct hvcall_mpp_data *mpp_data)
{
	int rc;
	unsigned long retbuf[PLPAR_HCALL9_BUFSIZE];

	rc = plpar_hcall9(H_GET_MPP, retbuf);

	mpp_data->entitled_mem = retbuf[0];
	mpp_data->mapped_mem = retbuf[1];

	mpp_data->group_num = (retbuf[2] >> 2 * 8) & 0xffff;
	mpp_data->pool_num = retbuf[2] & 0xffff;

	mpp_data->mem_weight = (retbuf[3] >> 7 * 8) & 0xff;
	mpp_data->unallocated_mem_weight = (retbuf[3] >> 6 * 8) & 0xff;
	mpp_data->unallocated_entitlement = retbuf[3] & 0xffffffffffffUL;

	mpp_data->pool_size = retbuf[4];
	mpp_data->loan_request = retbuf[5];
	mpp_data->backing_mem = retbuf[6];

	return rc;
}
EXPORT_SYMBOL(h_get_mpp);

int h_get_mpp_x(struct hvcall_mpp_x_data *mpp_x_data)
{
	int rc;
	unsigned long retbuf[PLPAR_HCALL9_BUFSIZE] = { 0 };

	rc = plpar_hcall9(H_GET_MPP_X, retbuf);

	mpp_x_data->coalesced_bytes = retbuf[0];
	mpp_x_data->pool_coalesced_bytes = retbuf[1];
	mpp_x_data->pool_purr_cycles = retbuf[2];
	mpp_x_data->pool_spurr_cycles = retbuf[3];

	return rc;
}

static unsigned long vsid_unscramble(unsigned long vsid, int ssize)
{
	unsigned long protovsid;
	unsigned long va_bits = VA_BITS;
	unsigned long modinv, vsid_modulus;
	unsigned long max_mod_inv, tmp_modinv;

	if (!mmu_has_feature(MMU_FTR_68_BIT_VA))
		va_bits = 65;

	if (ssize == MMU_SEGSIZE_256M) {
		modinv = VSID_MULINV_256M;
		vsid_modulus = ((1UL << (va_bits - SID_SHIFT)) - 1);
	} else {
		modinv = VSID_MULINV_1T;
		vsid_modulus = ((1UL << (va_bits - SID_SHIFT_1T)) - 1);
	}

	/*
	 * vsid outside our range.
	 */
	if (vsid >= vsid_modulus)
		return 0;

	/*
	 * If modinv is the modular multiplicate inverse of (x % vsid_modulus)
	 * and vsid = (protovsid * x) % vsid_modulus, then we say:
	 *   protovsid = (vsid * modinv) % vsid_modulus
	 */

	/* Check if (vsid * modinv) overflow (63 bits) */
	max_mod_inv = 0x7fffffffffffffffull / vsid;
	if (modinv < max_mod_inv)
		return (vsid * modinv) % vsid_modulus;

	tmp_modinv = modinv/max_mod_inv;
	modinv %= max_mod_inv;

	protovsid = (((vsid * max_mod_inv) % vsid_modulus) * tmp_modinv) % vsid_modulus;
	protovsid = (protovsid + vsid * modinv) % vsid_modulus;

	return protovsid;
}

static int __init reserve_vrma_context_id(void)
{
	unsigned long protovsid;

	/*
	 * Reserve context ids which map to reserved virtual addresses. For now
	 * we only reserve the context id which maps to the VRMA VSID. We ignore
	 * the addresses in "ibm,adjunct-virtual-addresses" because we don't
	 * enable adjunct support via the "ibm,client-architecture-support"
	 * interface.
	 */
	protovsid = vsid_unscramble(VRMA_VSID, MMU_SEGSIZE_1T);
	hash__reserve_context_id(protovsid >> ESID_BITS_1T);
	return 0;
}
machine_device_initcall(pseries, reserve_vrma_context_id);