summaryrefslogtreecommitdiff
path: root/arch/powerpc/mm/slice.c
blob: 205fe557ca109dda9a16e3fd9a8fe0f75909bc25 (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
/*
 * address space "slices" (meta-segments) support
 *
 * Copyright (C) 2007 Benjamin Herrenschmidt, IBM Corporation.
 *
 * Based on hugetlb implementation
 *
 * Copyright (C) 2003 David Gibson, 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.
 *
 * 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
 */

#undef DEBUG

#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/err.h>
#include <linux/spinlock.h>
#include <linux/export.h>
#include <linux/hugetlb.h>
#include <asm/mman.h>
#include <asm/mmu.h>
#include <asm/copro.h>
#include <asm/hugetlb.h>
#include <asm/mmu_context.h>

static DEFINE_SPINLOCK(slice_convert_lock);

#ifdef DEBUG
int _slice_debug = 1;

static void slice_print_mask(const char *label, const struct slice_mask *mask)
{
	if (!_slice_debug)
		return;
	pr_devel("%s low_slice: %*pbl\n", label,
			(int)SLICE_NUM_LOW, &mask->low_slices);
	pr_devel("%s high_slice: %*pbl\n", label,
			(int)SLICE_NUM_HIGH, mask->high_slices);
}

#define slice_dbg(fmt...) do { if (_slice_debug) pr_devel(fmt); } while (0)

#else

static void slice_print_mask(const char *label, const struct slice_mask *mask) {}
#define slice_dbg(fmt...)

#endif

static void slice_range_to_mask(unsigned long start, unsigned long len,
				struct slice_mask *ret)
{
	unsigned long end = start + len - 1;

	ret->low_slices = 0;
	if (SLICE_NUM_HIGH)
		bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);

	if (start < SLICE_LOW_TOP) {
		unsigned long mend = min(end,
					 (unsigned long)(SLICE_LOW_TOP - 1));

		ret->low_slices = (1u << (GET_LOW_SLICE_INDEX(mend) + 1))
			- (1u << GET_LOW_SLICE_INDEX(start));
	}

	if ((start + len) > SLICE_LOW_TOP) {
		unsigned long start_index = GET_HIGH_SLICE_INDEX(start);
		unsigned long align_end = ALIGN(end, (1UL << SLICE_HIGH_SHIFT));
		unsigned long count = GET_HIGH_SLICE_INDEX(align_end) - start_index;

		bitmap_set(ret->high_slices, start_index, count);
	}
}

static int slice_area_is_free(struct mm_struct *mm, unsigned long addr,
			      unsigned long len)
{
	struct vm_area_struct *vma;

	if ((mm->context.slb_addr_limit - len) < addr)
		return 0;
	vma = find_vma(mm, addr);
	return (!vma || (addr + len) <= vm_start_gap(vma));
}

static int slice_low_has_vma(struct mm_struct *mm, unsigned long slice)
{
	return !slice_area_is_free(mm, slice << SLICE_LOW_SHIFT,
				   1ul << SLICE_LOW_SHIFT);
}

static int slice_high_has_vma(struct mm_struct *mm, unsigned long slice)
{
	unsigned long start = slice << SLICE_HIGH_SHIFT;
	unsigned long end = start + (1ul << SLICE_HIGH_SHIFT);

#ifdef CONFIG_PPC64
	/* Hack, so that each addresses is controlled by exactly one
	 * of the high or low area bitmaps, the first high area starts
	 * at 4GB, not 0 */
	if (start == 0)
		start = SLICE_LOW_TOP;
#endif

	return !slice_area_is_free(mm, start, end - start);
}

static void slice_mask_for_free(struct mm_struct *mm, struct slice_mask *ret,
				unsigned long high_limit)
{
	unsigned long i;

	ret->low_slices = 0;
	if (SLICE_NUM_HIGH)
		bitmap_zero(ret->high_slices, SLICE_NUM_HIGH);

	for (i = 0; i < SLICE_NUM_LOW; i++)
		if (!slice_low_has_vma(mm, i))
			ret->low_slices |= 1u << i;

	if (high_limit <= SLICE_LOW_TOP)
		return;

	for (i = 0; i < GET_HIGH_SLICE_INDEX(high_limit); i++)
		if (!slice_high_has_vma(mm, i))
			__set_bit(i, ret->high_slices);
}

#ifdef CONFIG_PPC_BOOK3S_64
static struct slice_mask *slice_mask_for_size(struct mm_struct *mm, int psize)
{
#ifdef CONFIG_PPC_64K_PAGES
	if (psize == MMU_PAGE_64K)
		return &mm->context.mask_64k;
#endif
	if (psize == MMU_PAGE_4K)
		return &mm->context.mask_4k;
#ifdef CONFIG_HUGETLB_PAGE
	if (psize == MMU_PAGE_16M)
		return &mm->context.mask_16m;
	if (psize == MMU_PAGE_16G)
		return &mm->context.mask_16g;
#endif
	BUG();
}
#elif defined(CONFIG_PPC_8xx)
static struct slice_mask *slice_mask_for_size(struct mm_struct *mm, int psize)
{
	if (psize == mmu_virtual_psize)
		return &mm->context.mask_base_psize;
#ifdef CONFIG_HUGETLB_PAGE
	if (psize == MMU_PAGE_512K)
		return &mm->context.mask_512k;
	if (psize == MMU_PAGE_8M)
		return &mm->context.mask_8m;
#endif
	BUG();
}
#else
#error "Must define the slice masks for page sizes supported by the platform"
#endif

static bool slice_check_range_fits(struct mm_struct *mm,
			   const struct slice_mask *available,
			   unsigned long start, unsigned long len)
{
	unsigned long end = start + len - 1;
	u64 low_slices = 0;

	if (start < SLICE_LOW_TOP) {
		unsigned long mend = min(end,
					 (unsigned long)(SLICE_LOW_TOP - 1));

		low_slices = (1u << (GET_LOW_SLICE_INDEX(mend) + 1))
				- (1u << GET_LOW_SLICE_INDEX(start));
	}
	if ((low_slices & available->low_slices) != low_slices)
		return false;

	if (SLICE_NUM_HIGH && ((start + len) > SLICE_LOW_TOP)) {
		unsigned long start_index = GET_HIGH_SLICE_INDEX(start);
		unsigned long align_end = ALIGN(end, (1UL << SLICE_HIGH_SHIFT));
		unsigned long count = GET_HIGH_SLICE_INDEX(align_end) - start_index;
		unsigned long i;

		for (i = start_index; i < start_index + count; i++) {
			if (!test_bit(i, available->high_slices))
				return false;
		}
	}

	return true;
}

static void slice_flush_segments(void *parm)
{
#ifdef CONFIG_PPC64
	struct mm_struct *mm = parm;
	unsigned long flags;

	if (mm != current->active_mm)
		return;

	copy_mm_to_paca(current->active_mm);

	local_irq_save(flags);
	slb_flush_and_rebolt();
	local_irq_restore(flags);
#endif
}

static void slice_convert(struct mm_struct *mm,
				const struct slice_mask *mask, int psize)
{
	int index, mask_index;
	/* Write the new slice psize bits */
	unsigned char *hpsizes, *lpsizes;
	struct slice_mask *psize_mask, *old_mask;
	unsigned long i, flags;
	int old_psize;

	slice_dbg("slice_convert(mm=%p, psize=%d)\n", mm, psize);
	slice_print_mask(" mask", mask);

	psize_mask = slice_mask_for_size(mm, psize);

	/* We need to use a spinlock here to protect against
	 * concurrent 64k -> 4k demotion ...
	 */
	spin_lock_irqsave(&slice_convert_lock, flags);

	lpsizes = mm->context.low_slices_psize;
	for (i = 0; i < SLICE_NUM_LOW; i++) {
		if (!(mask->low_slices & (1u << i)))
			continue;

		mask_index = i & 0x1;
		index = i >> 1;

		/* Update the slice_mask */
		old_psize = (lpsizes[index] >> (mask_index * 4)) & 0xf;
		old_mask = slice_mask_for_size(mm, old_psize);
		old_mask->low_slices &= ~(1u << i);
		psize_mask->low_slices |= 1u << i;

		/* Update the sizes array */
		lpsizes[index] = (lpsizes[index] & ~(0xf << (mask_index * 4))) |
				(((unsigned long)psize) << (mask_index * 4));
	}

	hpsizes = mm->context.high_slices_psize;
	for (i = 0; i < GET_HIGH_SLICE_INDEX(mm->context.slb_addr_limit); i++) {
		if (!test_bit(i, mask->high_slices))
			continue;

		mask_index = i & 0x1;
		index = i >> 1;

		/* Update the slice_mask */
		old_psize = (hpsizes[index] >> (mask_index * 4)) & 0xf;
		old_mask = slice_mask_for_size(mm, old_psize);
		__clear_bit(i, old_mask->high_slices);
		__set_bit(i, psize_mask->high_slices);

		/* Update the sizes array */
		hpsizes[index] = (hpsizes[index] & ~(0xf << (mask_index * 4))) |
				(((unsigned long)psize) << (mask_index * 4));
	}

	slice_dbg(" lsps=%lx, hsps=%lx\n",
		  (unsigned long)mm->context.low_slices_psize,
		  (unsigned long)mm->context.high_slices_psize);

	spin_unlock_irqrestore(&slice_convert_lock, flags);

	copro_flush_all_slbs(mm);
}

/*
 * Compute which slice addr is part of;
 * set *boundary_addr to the start or end boundary of that slice
 * (depending on 'end' parameter);
 * return boolean indicating if the slice is marked as available in the
 * 'available' slice_mark.
 */
static bool slice_scan_available(unsigned long addr,
				 const struct slice_mask *available,
				 int end, unsigned long *boundary_addr)
{
	unsigned long slice;
	if (addr < SLICE_LOW_TOP) {
		slice = GET_LOW_SLICE_INDEX(addr);
		*boundary_addr = (slice + end) << SLICE_LOW_SHIFT;
		return !!(available->low_slices & (1u << slice));
	} else {
		slice = GET_HIGH_SLICE_INDEX(addr);
		*boundary_addr = (slice + end) ?
			((slice + end) << SLICE_HIGH_SHIFT) : SLICE_LOW_TOP;
		return !!test_bit(slice, available->high_slices);
	}
}

static unsigned long slice_find_area_bottomup(struct mm_struct *mm,
					      unsigned long len,
					      const struct slice_mask *available,
					      int psize, unsigned long high_limit)
{
	int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT);
	unsigned long addr, found, next_end;
	struct vm_unmapped_area_info info;

	info.flags = 0;
	info.length = len;
	info.align_mask = PAGE_MASK & ((1ul << pshift) - 1);
	info.align_offset = 0;

	addr = TASK_UNMAPPED_BASE;
	/*
	 * Check till the allow max value for this mmap request
	 */
	while (addr < high_limit) {
		info.low_limit = addr;
		if (!slice_scan_available(addr, available, 1, &addr))
			continue;

 next_slice:
		/*
		 * At this point [info.low_limit; addr) covers
		 * available slices only and ends at a slice boundary.
		 * Check if we need to reduce the range, or if we can
		 * extend it to cover the next available slice.
		 */
		if (addr >= high_limit)
			addr = high_limit;
		else if (slice_scan_available(addr, available, 1, &next_end)) {
			addr = next_end;
			goto next_slice;
		}
		info.high_limit = addr;

		found = vm_unmapped_area(&info);
		if (!(found & ~PAGE_MASK))
			return found;
	}

	return -ENOMEM;
}

static unsigned long slice_find_area_topdown(struct mm_struct *mm,
					     unsigned long len,
					     const struct slice_mask *available,
					     int psize, unsigned long high_limit)
{
	int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT);
	unsigned long addr, found, prev;
	struct vm_unmapped_area_info info;

	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
	info.length = len;
	info.align_mask = PAGE_MASK & ((1ul << pshift) - 1);
	info.align_offset = 0;

	addr = mm->mmap_base;
	/*
	 * If we are trying to allocate above DEFAULT_MAP_WINDOW
	 * Add the different to the mmap_base.
	 * Only for that request for which high_limit is above
	 * DEFAULT_MAP_WINDOW we should apply this.
	 */
	if (high_limit > DEFAULT_MAP_WINDOW)
		addr += mm->context.slb_addr_limit - DEFAULT_MAP_WINDOW;

	while (addr > PAGE_SIZE) {
		info.high_limit = addr;
		if (!slice_scan_available(addr - 1, available, 0, &addr))
			continue;

 prev_slice:
		/*
		 * At this point [addr; info.high_limit) covers
		 * available slices only and starts at a slice boundary.
		 * Check if we need to reduce the range, or if we can
		 * extend it to cover the previous available slice.
		 */
		if (addr < PAGE_SIZE)
			addr = PAGE_SIZE;
		else if (slice_scan_available(addr - 1, available, 0, &prev)) {
			addr = prev;
			goto prev_slice;
		}
		info.low_limit = addr;

		found = vm_unmapped_area(&info);
		if (!(found & ~PAGE_MASK))
			return found;
	}

	/*
	 * A failed mmap() very likely causes application failure,
	 * so fall back to the bottom-up function here. This scenario
	 * can happen with large stack limits and large mmap()
	 * allocations.
	 */
	return slice_find_area_bottomup(mm, len, available, psize, high_limit);
}


static unsigned long slice_find_area(struct mm_struct *mm, unsigned long len,
				     const struct slice_mask *mask, int psize,
				     int topdown, unsigned long high_limit)
{
	if (topdown)
		return slice_find_area_topdown(mm, len, mask, psize, high_limit);
	else
		return slice_find_area_bottomup(mm, len, mask, psize, high_limit);
}

static inline void slice_copy_mask(struct slice_mask *dst,
					const struct slice_mask *src)
{
	dst->low_slices = src->low_slices;
	if (!SLICE_NUM_HIGH)
		return;
	bitmap_copy(dst->high_slices, src->high_slices, SLICE_NUM_HIGH);
}

static inline void slice_or_mask(struct slice_mask *dst,
					const struct slice_mask *src1,
					const struct slice_mask *src2)
{
	dst->low_slices = src1->low_slices | src2->low_slices;
	if (!SLICE_NUM_HIGH)
		return;
	bitmap_or(dst->high_slices, src1->high_slices, src2->high_slices, SLICE_NUM_HIGH);
}

static inline void slice_andnot_mask(struct slice_mask *dst,
					const struct slice_mask *src1,
					const struct slice_mask *src2)
{
	dst->low_slices = src1->low_slices & ~src2->low_slices;
	if (!SLICE_NUM_HIGH)
		return;
	bitmap_andnot(dst->high_slices, src1->high_slices, src2->high_slices, SLICE_NUM_HIGH);
}

#ifdef CONFIG_PPC_64K_PAGES
#define MMU_PAGE_BASE	MMU_PAGE_64K
#else
#define MMU_PAGE_BASE	MMU_PAGE_4K
#endif

unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
				      unsigned long flags, unsigned int psize,
				      int topdown)
{
	struct slice_mask good_mask;
	struct slice_mask potential_mask;
	const struct slice_mask *maskp;
	const struct slice_mask *compat_maskp = NULL;
	int fixed = (flags & MAP_FIXED);
	int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT);
	unsigned long page_size = 1UL << pshift;
	struct mm_struct *mm = current->mm;
	unsigned long newaddr;
	unsigned long high_limit;

	high_limit = DEFAULT_MAP_WINDOW;
	if (addr >= high_limit || (fixed && (addr + len > high_limit)))
		high_limit = TASK_SIZE;

	if (len > high_limit)
		return -ENOMEM;
	if (len & (page_size - 1))
		return -EINVAL;
	if (fixed) {
		if (addr & (page_size - 1))
			return -EINVAL;
		if (addr > high_limit - len)
			return -ENOMEM;
	}

	if (high_limit > mm->context.slb_addr_limit) {
		/*
		 * Increasing the slb_addr_limit does not require
		 * slice mask cache to be recalculated because it should
		 * be already initialised beyond the old address limit.
		 */
		mm->context.slb_addr_limit = high_limit;

		on_each_cpu(slice_flush_segments, mm, 1);
	}

	/* Sanity checks */
	BUG_ON(mm->task_size == 0);
	BUG_ON(mm->context.slb_addr_limit == 0);
	VM_BUG_ON(radix_enabled());

	slice_dbg("slice_get_unmapped_area(mm=%p, psize=%d...\n", mm, psize);
	slice_dbg(" addr=%lx, len=%lx, flags=%lx, topdown=%d\n",
		  addr, len, flags, topdown);

	/* If hint, make sure it matches our alignment restrictions */
	if (!fixed && addr) {
		addr = _ALIGN_UP(addr, page_size);
		slice_dbg(" aligned addr=%lx\n", addr);
		/* Ignore hint if it's too large or overlaps a VMA */
		if (addr > high_limit - len ||
		    !slice_area_is_free(mm, addr, len))
			addr = 0;
	}

	/* First make up a "good" mask of slices that have the right size
	 * already
	 */
	maskp = slice_mask_for_size(mm, psize);

	/*
	 * Here "good" means slices that are already the right page size,
	 * "compat" means slices that have a compatible page size (i.e.
	 * 4k in a 64k pagesize kernel), and "free" means slices without
	 * any VMAs.
	 *
	 * If MAP_FIXED:
	 *	check if fits in good | compat => OK
	 *	check if fits in good | compat | free => convert free
	 *	else bad
	 * If have hint:
	 *	check if hint fits in good => OK
	 *	check if hint fits in good | free => convert free
	 * Otherwise:
	 *	search in good, found => OK
	 *	search in good | free, found => convert free
	 *	search in good | compat | free, found => convert free.
	 */

	/*
	 * If we support combo pages, we can allow 64k pages in 4k slices
	 * The mask copies could be avoided in most cases here if we had
	 * a pointer to good mask for the next code to use.
	 */
	if (IS_ENABLED(CONFIG_PPC_64K_PAGES) && psize == MMU_PAGE_64K) {
		compat_maskp = slice_mask_for_size(mm, MMU_PAGE_4K);
		if (fixed)
			slice_or_mask(&good_mask, maskp, compat_maskp);
		else
			slice_copy_mask(&good_mask, maskp);
	} else {
		slice_copy_mask(&good_mask, maskp);
	}

	slice_print_mask(" good_mask", &good_mask);
	if (compat_maskp)
		slice_print_mask(" compat_mask", compat_maskp);

	/* First check hint if it's valid or if we have MAP_FIXED */
	if (addr != 0 || fixed) {
		/* Check if we fit in the good mask. If we do, we just return,
		 * nothing else to do
		 */
		if (slice_check_range_fits(mm, &good_mask, addr, len)) {
			slice_dbg(" fits good !\n");
			newaddr = addr;
			goto return_addr;
		}
	} else {
		/* Now let's see if we can find something in the existing
		 * slices for that size
		 */
		newaddr = slice_find_area(mm, len, &good_mask,
					  psize, topdown, high_limit);
		if (newaddr != -ENOMEM) {
			/* Found within the good mask, we don't have to setup,
			 * we thus return directly
			 */
			slice_dbg(" found area at 0x%lx\n", newaddr);
			goto return_addr;
		}
	}
	/*
	 * We don't fit in the good mask, check what other slices are
	 * empty and thus can be converted
	 */
	slice_mask_for_free(mm, &potential_mask, high_limit);
	slice_or_mask(&potential_mask, &potential_mask, &good_mask);
	slice_print_mask(" potential", &potential_mask);

	if (addr != 0 || fixed) {
		if (slice_check_range_fits(mm, &potential_mask, addr, len)) {
			slice_dbg(" fits potential !\n");
			newaddr = addr;
			goto convert;
		}
	}

	/* If we have MAP_FIXED and failed the above steps, then error out */
	if (fixed)
		return -EBUSY;

	slice_dbg(" search...\n");

	/* If we had a hint that didn't work out, see if we can fit
	 * anywhere in the good area.
	 */
	if (addr) {
		newaddr = slice_find_area(mm, len, &good_mask,
					  psize, topdown, high_limit);
		if (newaddr != -ENOMEM) {
			slice_dbg(" found area at 0x%lx\n", newaddr);
			goto return_addr;
		}
	}

	/* Now let's see if we can find something in the existing slices
	 * for that size plus free slices
	 */
	newaddr = slice_find_area(mm, len, &potential_mask,
				  psize, topdown, high_limit);

#ifdef CONFIG_PPC_64K_PAGES
	if (newaddr == -ENOMEM && psize == MMU_PAGE_64K) {
		/* retry the search with 4k-page slices included */
		slice_or_mask(&potential_mask, &potential_mask, compat_maskp);
		newaddr = slice_find_area(mm, len, &potential_mask,
					  psize, topdown, high_limit);
	}
#endif

	if (newaddr == -ENOMEM)
		return -ENOMEM;

	slice_range_to_mask(newaddr, len, &potential_mask);
	slice_dbg(" found potential area at 0x%lx\n", newaddr);
	slice_print_mask(" mask", &potential_mask);

 convert:
	/*
	 * Try to allocate the context before we do slice convert
	 * so that we handle the context allocation failure gracefully.
	 */
	if (need_extra_context(mm, newaddr)) {
		if (alloc_extended_context(mm, newaddr) < 0)
			return -ENOMEM;
	}

	slice_andnot_mask(&potential_mask, &potential_mask, &good_mask);
	if (compat_maskp && !fixed)
		slice_andnot_mask(&potential_mask, &potential_mask, compat_maskp);
	if (potential_mask.low_slices ||
		(SLICE_NUM_HIGH &&
		 !bitmap_empty(potential_mask.high_slices, SLICE_NUM_HIGH))) {
		slice_convert(mm, &potential_mask, psize);
		if (psize > MMU_PAGE_BASE)
			on_each_cpu(slice_flush_segments, mm, 1);
	}
	return newaddr;

return_addr:
	if (need_extra_context(mm, newaddr)) {
		if (alloc_extended_context(mm, newaddr) < 0)
			return -ENOMEM;
	}
	return newaddr;
}
EXPORT_SYMBOL_GPL(slice_get_unmapped_area);

unsigned long arch_get_unmapped_area(struct file *filp,
				     unsigned long addr,
				     unsigned long len,
				     unsigned long pgoff,
				     unsigned long flags)
{
	return slice_get_unmapped_area(addr, len, flags,
				       current->mm->context.user_psize, 0);
}

unsigned long arch_get_unmapped_area_topdown(struct file *filp,
					     const unsigned long addr0,
					     const unsigned long len,
					     const unsigned long pgoff,
					     const unsigned long flags)
{
	return slice_get_unmapped_area(addr0, len, flags,
				       current->mm->context.user_psize, 1);
}

unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr)
{
	unsigned char *psizes;
	int index, mask_index;

	VM_BUG_ON(radix_enabled());

	if (addr < SLICE_LOW_TOP) {
		psizes = mm->context.low_slices_psize;
		index = GET_LOW_SLICE_INDEX(addr);
	} else {
		psizes = mm->context.high_slices_psize;
		index = GET_HIGH_SLICE_INDEX(addr);
	}
	mask_index = index & 0x1;
	return (psizes[index >> 1] >> (mask_index * 4)) & 0xf;
}
EXPORT_SYMBOL_GPL(get_slice_psize);

void slice_init_new_context_exec(struct mm_struct *mm)
{
	unsigned char *hpsizes, *lpsizes;
	struct slice_mask *mask;
	unsigned int psize = mmu_virtual_psize;

	slice_dbg("slice_init_new_context_exec(mm=%p)\n", mm);

	/*
	 * In the case of exec, use the default limit. In the
	 * case of fork it is just inherited from the mm being
	 * duplicated.
	 */
#ifdef CONFIG_PPC64
	mm->context.slb_addr_limit = DEFAULT_MAP_WINDOW_USER64;
#else
	mm->context.slb_addr_limit = DEFAULT_MAP_WINDOW;
#endif

	mm->context.user_psize = psize;

	/*
	 * Set all slice psizes to the default.
	 */
	lpsizes = mm->context.low_slices_psize;
	memset(lpsizes, (psize << 4) | psize, SLICE_NUM_LOW >> 1);

	hpsizes = mm->context.high_slices_psize;
	memset(hpsizes, (psize << 4) | psize, SLICE_NUM_HIGH >> 1);

	/*
	 * Slice mask cache starts zeroed, fill the default size cache.
	 */
	mask = slice_mask_for_size(mm, psize);
	mask->low_slices = ~0UL;
	if (SLICE_NUM_HIGH)
		bitmap_fill(mask->high_slices, SLICE_NUM_HIGH);
}

void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
			   unsigned long len, unsigned int psize)
{
	struct slice_mask mask;

	VM_BUG_ON(radix_enabled());

	slice_range_to_mask(start, len, &mask);
	slice_convert(mm, &mask, psize);
}

#ifdef CONFIG_HUGETLB_PAGE
/*
 * is_hugepage_only_range() is used by generic code to verify whether
 * a normal mmap mapping (non hugetlbfs) is valid on a given area.
 *
 * until the generic code provides a more generic hook and/or starts
 * calling arch get_unmapped_area for MAP_FIXED (which our implementation
 * here knows how to deal with), we hijack it to keep standard mappings
 * away from us.
 *
 * because of that generic code limitation, MAP_FIXED mapping cannot
 * "convert" back a slice with no VMAs to the standard page size, only
 * get_unmapped_area() can. It would be possible to fix it here but I
 * prefer working on fixing the generic code instead.
 *
 * WARNING: This will not work if hugetlbfs isn't enabled since the
 * generic code will redefine that function as 0 in that. This is ok
 * for now as we only use slices with hugetlbfs enabled. This should
 * be fixed as the generic code gets fixed.
 */
int slice_is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
			   unsigned long len)
{
	const struct slice_mask *maskp;
	unsigned int psize = mm->context.user_psize;

	VM_BUG_ON(radix_enabled());

	maskp = slice_mask_for_size(mm, psize);
#ifdef CONFIG_PPC_64K_PAGES
	/* We need to account for 4k slices too */
	if (psize == MMU_PAGE_64K) {
		const struct slice_mask *compat_maskp;
		struct slice_mask available;

		compat_maskp = slice_mask_for_size(mm, MMU_PAGE_4K);
		slice_or_mask(&available, maskp, compat_maskp);
		return !slice_check_range_fits(mm, &available, addr, len);
	}
#endif

	return !slice_check_range_fits(mm, maskp, addr, len);
}
#endif