summaryrefslogtreecommitdiffstats
path: root/arch/s390/mm/pgtable.c
blob: 4324b87f93982f08552ecb86bb9c893431507427 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
/*
 *    Copyright IBM Corp. 2007, 2011
 *    Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
 */

#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/gfp.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/smp.h>
#include <linux/spinlock.h>
#include <linux/rcupdate.h>
#include <linux/slab.h>
#include <linux/swapops.h>
#include <linux/sysctl.h>
#include <linux/ksm.h>
#include <linux/mman.h>

#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>

static inline pte_t ptep_flush_direct(struct mm_struct *mm,
				      unsigned long addr, pte_t *ptep)
{
	int active, count;
	pte_t old;

	old = *ptep;
	if (unlikely(pte_val(old) & _PAGE_INVALID))
		return old;
	active = (mm == current->active_mm) ? 1 : 0;
	count = atomic_add_return(0x10000, &mm->context.attach_count);
	if (MACHINE_HAS_TLB_LC && (count & 0xffff) <= active &&
	    cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id())))
		__ptep_ipte_local(addr, ptep);
	else
		__ptep_ipte(addr, ptep);
	atomic_sub(0x10000, &mm->context.attach_count);
	return old;
}

static inline pte_t ptep_flush_lazy(struct mm_struct *mm,
				    unsigned long addr, pte_t *ptep)
{
	int active, count;
	pte_t old;

	old = *ptep;
	if (unlikely(pte_val(old) & _PAGE_INVALID))
		return old;
	active = (mm == current->active_mm) ? 1 : 0;
	count = atomic_add_return(0x10000, &mm->context.attach_count);
	if ((count & 0xffff) <= active) {
		pte_val(*ptep) |= _PAGE_INVALID;
		mm->context.flush_mm = 1;
	} else
		__ptep_ipte(addr, ptep);
	atomic_sub(0x10000, &mm->context.attach_count);
	return old;
}

static inline pgste_t pgste_get_lock(pte_t *ptep)
{
	unsigned long new = 0;
#ifdef CONFIG_PGSTE
	unsigned long old;

	preempt_disable();
	asm(
		"	lg	%0,%2\n"
		"0:	lgr	%1,%0\n"
		"	nihh	%0,0xff7f\n"	/* clear PCL bit in old */
		"	oihh	%1,0x0080\n"	/* set PCL bit in new */
		"	csg	%0,%1,%2\n"
		"	jl	0b\n"
		: "=&d" (old), "=&d" (new), "=Q" (ptep[PTRS_PER_PTE])
		: "Q" (ptep[PTRS_PER_PTE]) : "cc", "memory");
#endif
	return __pgste(new);
}

static inline void pgste_set_unlock(pte_t *ptep, pgste_t pgste)
{
#ifdef CONFIG_PGSTE
	asm(
		"	nihh	%1,0xff7f\n"	/* clear PCL bit */
		"	stg	%1,%0\n"
		: "=Q" (ptep[PTRS_PER_PTE])
		: "d" (pgste_val(pgste)), "Q" (ptep[PTRS_PER_PTE])
		: "cc", "memory");
	preempt_enable();
#endif
}

static inline pgste_t pgste_get(pte_t *ptep)
{
	unsigned long pgste = 0;
#ifdef CONFIG_PGSTE
	pgste = *(unsigned long *)(ptep + PTRS_PER_PTE);
#endif
	return __pgste(pgste);
}

static inline void pgste_set(pte_t *ptep, pgste_t pgste)
{
#ifdef CONFIG_PGSTE
	*(pgste_t *)(ptep + PTRS_PER_PTE) = pgste;
#endif
}

static inline pgste_t pgste_update_all(pte_t pte, pgste_t pgste,
				       struct mm_struct *mm)
{
#ifdef CONFIG_PGSTE
	unsigned long address, bits, skey;

	if (!mm_use_skey(mm) || pte_val(pte) & _PAGE_INVALID)
		return pgste;
	address = pte_val(pte) & PAGE_MASK;
	skey = (unsigned long) page_get_storage_key(address);
	bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED);
	/* Transfer page changed & referenced bit to guest bits in pgste */
	pgste_val(pgste) |= bits << 48;		/* GR bit & GC bit */
	/* Copy page access key and fetch protection bit to pgste */
	pgste_val(pgste) &= ~(PGSTE_ACC_BITS | PGSTE_FP_BIT);
	pgste_val(pgste) |= (skey & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56;
#endif
	return pgste;

}

static inline void pgste_set_key(pte_t *ptep, pgste_t pgste, pte_t entry,
				 struct mm_struct *mm)
{
#ifdef CONFIG_PGSTE
	unsigned long address;
	unsigned long nkey;

	if (!mm_use_skey(mm) || pte_val(entry) & _PAGE_INVALID)
		return;
	VM_BUG_ON(!(pte_val(*ptep) & _PAGE_INVALID));
	address = pte_val(entry) & PAGE_MASK;
	/*
	 * Set page access key and fetch protection bit from pgste.
	 * The guest C/R information is still in the PGSTE, set real
	 * key C/R to 0.
	 */
	nkey = (pgste_val(pgste) & (PGSTE_ACC_BITS | PGSTE_FP_BIT)) >> 56;
	nkey |= (pgste_val(pgste) & (PGSTE_GR_BIT | PGSTE_GC_BIT)) >> 48;
	page_set_storage_key(address, nkey, 0);
#endif
}

static inline pgste_t pgste_set_pte(pte_t *ptep, pgste_t pgste, pte_t entry)
{
#ifdef CONFIG_PGSTE
	if ((pte_val(entry) & _PAGE_PRESENT) &&
	    (pte_val(entry) & _PAGE_WRITE) &&
	    !(pte_val(entry) & _PAGE_INVALID)) {
		if (!MACHINE_HAS_ESOP) {
			/*
			 * Without enhanced suppression-on-protection force
			 * the dirty bit on for all writable ptes.
			 */
			pte_val(entry) |= _PAGE_DIRTY;
			pte_val(entry) &= ~_PAGE_PROTECT;
		}
		if (!(pte_val(entry) & _PAGE_PROTECT))
			/* This pte allows write access, set user-dirty */
			pgste_val(pgste) |= PGSTE_UC_BIT;
	}
#endif
	*ptep = entry;
	return pgste;
}

static inline pgste_t pgste_ipte_notify(struct mm_struct *mm,
					unsigned long addr,
					pte_t *ptep, pgste_t pgste)
{
#ifdef CONFIG_PGSTE
	if (pgste_val(pgste) & PGSTE_IN_BIT) {
		pgste_val(pgste) &= ~PGSTE_IN_BIT;
		ptep_notify(mm, addr, ptep);
	}
#endif
	return pgste;
}

static inline pgste_t ptep_xchg_start(struct mm_struct *mm,
				      unsigned long addr, pte_t *ptep)
{
	pgste_t pgste = __pgste(0);

	if (mm_has_pgste(mm)) {
		pgste = pgste_get_lock(ptep);
		pgste = pgste_ipte_notify(mm, addr, ptep, pgste);
	}
	return pgste;
}

static inline void ptep_xchg_commit(struct mm_struct *mm,
				    unsigned long addr, pte_t *ptep,
				    pgste_t pgste, pte_t old, pte_t new)
{
	if (mm_has_pgste(mm)) {
		if (pte_val(old) & _PAGE_INVALID)
			pgste_set_key(ptep, pgste, new, mm);
		if (pte_val(new) & _PAGE_INVALID) {
			pgste = pgste_update_all(old, pgste, mm);
			if ((pgste_val(pgste) & _PGSTE_GPS_USAGE_MASK) ==
			    _PGSTE_GPS_USAGE_UNUSED)
				pte_val(old) |= _PAGE_UNUSED;
		}
		pgste = pgste_set_pte(ptep, pgste, new);
		pgste_set_unlock(ptep, pgste);
	} else {
		*ptep = new;
	}
}

pte_t ptep_xchg_direct(struct mm_struct *mm, unsigned long addr,
		       pte_t *ptep, pte_t new)
{
	pgste_t pgste;
	pte_t old;

	pgste = ptep_xchg_start(mm, addr, ptep);
	old = ptep_flush_direct(mm, addr, ptep);
	ptep_xchg_commit(mm, addr, ptep, pgste, old, new);
	return old;
}
EXPORT_SYMBOL(ptep_xchg_direct);

pte_t ptep_xchg_lazy(struct mm_struct *mm, unsigned long addr,
		     pte_t *ptep, pte_t new)
{
	pgste_t pgste;
	pte_t old;

	pgste = ptep_xchg_start(mm, addr, ptep);
	old = ptep_flush_lazy(mm, addr, ptep);
	ptep_xchg_commit(mm, addr, ptep, pgste, old, new);
	return old;
}
EXPORT_SYMBOL(ptep_xchg_lazy);

pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr,
			     pte_t *ptep)
{
	pgste_t pgste;
	pte_t old;

	pgste = ptep_xchg_start(mm, addr, ptep);
	old = ptep_flush_lazy(mm, addr, ptep);
	if (mm_has_pgste(mm)) {
		pgste = pgste_update_all(old, pgste, mm);
		pgste_set(ptep, pgste);
	}
	return old;
}
EXPORT_SYMBOL(ptep_modify_prot_start);

void ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
			     pte_t *ptep, pte_t pte)
{
	pgste_t pgste;

	if (mm_has_pgste(mm)) {
		pgste = pgste_get(ptep);
		pgste_set_key(ptep, pgste, pte, mm);
		pgste = pgste_set_pte(ptep, pgste, pte);
		pgste_set_unlock(ptep, pgste);
	} else {
		*ptep = pte;
	}
}
EXPORT_SYMBOL(ptep_modify_prot_commit);

static inline pmd_t pmdp_flush_direct(struct mm_struct *mm,
				      unsigned long addr, pmd_t *pmdp)
{
	int active, count;
	pmd_t old;

	old = *pmdp;
	if (pmd_val(old) & _SEGMENT_ENTRY_INVALID)
		return old;
	if (!MACHINE_HAS_IDTE) {
		__pmdp_csp(pmdp);
		return old;
	}
	active = (mm == current->active_mm) ? 1 : 0;
	count = atomic_add_return(0x10000, &mm->context.attach_count);
	if (MACHINE_HAS_TLB_LC && (count & 0xffff) <= active &&
	    cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id())))
		__pmdp_idte_local(addr, pmdp);
	else
		__pmdp_idte(addr, pmdp);
	atomic_sub(0x10000, &mm->context.attach_count);
	return old;
}

static inline pmd_t pmdp_flush_lazy(struct mm_struct *mm,
				    unsigned long addr, pmd_t *pmdp)
{
	int active, count;
	pmd_t old;

	old = *pmdp;
	if (pmd_val(old) & _SEGMENT_ENTRY_INVALID)
		return old;
	active = (mm == current->active_mm) ? 1 : 0;
	count = atomic_add_return(0x10000, &mm->context.attach_count);
	if ((count & 0xffff) <= active) {
		pmd_val(*pmdp) |= _SEGMENT_ENTRY_INVALID;
		mm->context.flush_mm = 1;
	} else if (MACHINE_HAS_IDTE)
		__pmdp_idte(addr, pmdp);
	else
		__pmdp_csp(pmdp);
	atomic_sub(0x10000, &mm->context.attach_count);
	return old;
}

pmd_t pmdp_xchg_direct(struct mm_struct *mm, unsigned long addr,
		       pmd_t *pmdp, pmd_t new)
{
	pmd_t old;

	old = pmdp_flush_direct(mm, addr, pmdp);
	*pmdp = new;
	return old;
}
EXPORT_SYMBOL(pmdp_xchg_direct);

pmd_t pmdp_xchg_lazy(struct mm_struct *mm, unsigned long addr,
		     pmd_t *pmdp, pmd_t new)
{
	pmd_t old;

	old = pmdp_flush_lazy(mm, addr, pmdp);
	*pmdp = new;
	return old;
}
EXPORT_SYMBOL(pmdp_xchg_lazy);

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
				pgtable_t pgtable)
{
	struct list_head *lh = (struct list_head *) pgtable;

	assert_spin_locked(pmd_lockptr(mm, pmdp));

	/* FIFO */
	if (!pmd_huge_pte(mm, pmdp))
		INIT_LIST_HEAD(lh);
	else
		list_add(lh, (struct list_head *) pmd_huge_pte(mm, pmdp));
	pmd_huge_pte(mm, pmdp) = pgtable;
}

pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
{
	struct list_head *lh;
	pgtable_t pgtable;
	pte_t *ptep;

	assert_spin_locked(pmd_lockptr(mm, pmdp));

	/* FIFO */
	pgtable = pmd_huge_pte(mm, pmdp);
	lh = (struct list_head *) pgtable;
	if (list_empty(lh))
		pmd_huge_pte(mm, pmdp) = NULL;
	else {
		pmd_huge_pte(mm, pmdp) = (pgtable_t) lh->next;
		list_del(lh);
	}
	ptep = (pte_t *) pgtable;
	pte_val(*ptep) = _PAGE_INVALID;
	ptep++;
	pte_val(*ptep) = _PAGE_INVALID;
	return pgtable;
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */

#ifdef CONFIG_PGSTE
void ptep_set_pte_at(struct mm_struct *mm, unsigned long addr,
		     pte_t *ptep, pte_t entry)
{
	pgste_t pgste;

	/* the mm_has_pgste() check is done in set_pte_at() */
	pgste = pgste_get_lock(ptep);
	pgste_val(pgste) &= ~_PGSTE_GPS_ZERO;
	pgste_set_key(ptep, pgste, entry, mm);
	pgste = pgste_set_pte(ptep, pgste, entry);
	pgste_set_unlock(ptep, pgste);
}

void ptep_set_notify(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
{
	pgste_t pgste;

	pgste = pgste_get_lock(ptep);
	pgste_val(pgste) |= PGSTE_IN_BIT;
	pgste_set_unlock(ptep, pgste);
}

static void ptep_zap_swap_entry(struct mm_struct *mm, swp_entry_t entry)
{
	if (!non_swap_entry(entry))
		dec_mm_counter(mm, MM_SWAPENTS);
	else if (is_migration_entry(entry)) {
		struct page *page = migration_entry_to_page(entry);

		dec_mm_counter(mm, mm_counter(page));
	}
	free_swap_and_cache(entry);
}

void ptep_zap_unused(struct mm_struct *mm, unsigned long addr,
		     pte_t *ptep, int reset)
{
	unsigned long pgstev;
	pgste_t pgste;
	pte_t pte;

	/* Zap unused and logically-zero pages */
	pgste = pgste_get_lock(ptep);
	pgstev = pgste_val(pgste);
	pte = *ptep;
	if (pte_swap(pte) &&
	    ((pgstev & _PGSTE_GPS_USAGE_MASK) == _PGSTE_GPS_USAGE_UNUSED ||
	     (pgstev & _PGSTE_GPS_ZERO))) {
		ptep_zap_swap_entry(mm, pte_to_swp_entry(pte));
		pte_clear(mm, addr, ptep);
	}
	if (reset)
		pgste_val(pgste) &= ~_PGSTE_GPS_USAGE_MASK;
	pgste_set_unlock(ptep, pgste);
}

void ptep_zap_key(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
{
	unsigned long ptev;
	pgste_t pgste;

	/* Clear storage key */
	pgste = pgste_get_lock(ptep);
	pgste_val(pgste) &= ~(PGSTE_ACC_BITS | PGSTE_FP_BIT |
			      PGSTE_GR_BIT | PGSTE_GC_BIT);
	ptev = pte_val(*ptep);
	if (!(ptev & _PAGE_INVALID) && (ptev & _PAGE_WRITE))
		page_set_storage_key(ptev & PAGE_MASK, PAGE_DEFAULT_KEY, 1);
	pgste_set_unlock(ptep, pgste);
}

/*
 * Test and reset if a guest page is dirty
 */
bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long addr)
{
	spinlock_t *ptl;
	pgste_t pgste;
	pte_t *ptep;
	pte_t pte;
	bool dirty;

	ptep = get_locked_pte(mm, addr, &ptl);
	if (unlikely(!ptep))
		return false;

	pgste = pgste_get_lock(ptep);
	dirty = !!(pgste_val(pgste) & PGSTE_UC_BIT);
	pgste_val(pgste) &= ~PGSTE_UC_BIT;
	pte = *ptep;
	if (dirty && (pte_val(pte) & _PAGE_PRESENT)) {
		pgste = pgste_ipte_notify(mm, addr, ptep, pgste);
		__ptep_ipte(addr, ptep);
		if (MACHINE_HAS_ESOP || !(pte_val(pte) & _PAGE_WRITE))
			pte_val(pte) |= _PAGE_PROTECT;
		else
			pte_val(pte) |= _PAGE_INVALID;
		*ptep = pte;
	}
	pgste_set_unlock(ptep, pgste);

	spin_unlock(ptl);
	return dirty;
}
EXPORT_SYMBOL_GPL(test_and_clear_guest_dirty);

int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
			  unsigned char key, bool nq)
{
	unsigned long keyul;
	spinlock_t *ptl;
	pgste_t old, new;
	pte_t *ptep;

	down_read(&mm->mmap_sem);
	ptep = get_locked_pte(mm, addr, &ptl);
	if (unlikely(!ptep)) {
		up_read(&mm->mmap_sem);
		return -EFAULT;
	}

	new = old = pgste_get_lock(ptep);
	pgste_val(new) &= ~(PGSTE_GR_BIT | PGSTE_GC_BIT |
			    PGSTE_ACC_BITS | PGSTE_FP_BIT);
	keyul = (unsigned long) key;
	pgste_val(new) |= (keyul & (_PAGE_CHANGED | _PAGE_REFERENCED)) << 48;
	pgste_val(new) |= (keyul & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56;
	if (!(pte_val(*ptep) & _PAGE_INVALID)) {
		unsigned long address, bits, skey;

		address = pte_val(*ptep) & PAGE_MASK;
		skey = (unsigned long) page_get_storage_key(address);
		bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED);
		skey = key & (_PAGE_ACC_BITS | _PAGE_FP_BIT);
		/* Set storage key ACC and FP */
		page_set_storage_key(address, skey, !nq);
		/* Merge host changed & referenced into pgste  */
		pgste_val(new) |= bits << 52;
	}
	/* changing the guest storage key is considered a change of the page */
	if ((pgste_val(new) ^ pgste_val(old)) &
	    (PGSTE_ACC_BITS | PGSTE_FP_BIT | PGSTE_GR_BIT | PGSTE_GC_BIT))
		pgste_val(new) |= PGSTE_UC_BIT;

	pgste_set_unlock(ptep, new);
	pte_unmap_unlock(ptep, ptl);
	up_read(&mm->mmap_sem);
	return 0;
}
EXPORT_SYMBOL(set_guest_storage_key);

unsigned char get_guest_storage_key(struct mm_struct *mm, unsigned long addr)
{
	unsigned char key;
	spinlock_t *ptl;
	pgste_t pgste;
	pte_t *ptep;

	down_read(&mm->mmap_sem);
	ptep = get_locked_pte(mm, addr, &ptl);
	if (unlikely(!ptep)) {
		up_read(&mm->mmap_sem);
		return -EFAULT;
	}
	pgste = pgste_get_lock(ptep);

	if (pte_val(*ptep) & _PAGE_INVALID) {
		key  = (pgste_val(pgste) & PGSTE_ACC_BITS) >> 56;
		key |= (pgste_val(pgste) & PGSTE_FP_BIT) >> 56;
		key |= (pgste_val(pgste) & PGSTE_GR_BIT) >> 48;
		key |= (pgste_val(pgste) & PGSTE_GC_BIT) >> 48;
	} else {
		key = page_get_storage_key(pte_val(*ptep) & PAGE_MASK);

		/* Reflect guest's logical view, not physical */
		if (pgste_val(pgste) & PGSTE_GR_BIT)
			key |= _PAGE_REFERENCED;
		if (pgste_val(pgste) & PGSTE_GC_BIT)
			key |= _PAGE_CHANGED;
	}

	pgste_set_unlock(ptep, pgste);
	pte_unmap_unlock(ptep, ptl);
	up_read(&mm->mmap_sem);
	return key;
}
EXPORT_SYMBOL(get_guest_storage_key);
#endif