summaryrefslogtreecommitdiff
path: root/arch/powerpc/mm/pgtable-book3s64.c
blob: 4afbfbb64bfd0a21254a177f4fa3df3c37bff6ea (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
/*
 * Copyright 2015-2016, Aneesh Kumar K.V, 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.
 */

#include <linux/sched.h>
#include <linux/mm_types.h>
#include <linux/memblock.h>
#include <misc/cxl-base.h>

#include <asm/pgalloc.h>
#include <asm/tlb.h>
#include <asm/trace.h>
#include <asm/powernv.h>

#include "mmu_decl.h"
#include <trace/events/thp.h>

unsigned long __pmd_frag_nr;
EXPORT_SYMBOL(__pmd_frag_nr);
unsigned long __pmd_frag_size_shift;
EXPORT_SYMBOL(__pmd_frag_size_shift);

int (*register_process_table)(unsigned long base, unsigned long page_size,
			      unsigned long tbl_size);

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/*
 * This is called when relaxing access to a hugepage. It's also called in the page
 * fault path when we don't hit any of the major fault cases, ie, a minor
 * update of _PAGE_ACCESSED, _PAGE_DIRTY, etc... The generic code will have
 * handled those two for us, we additionally deal with missing execute
 * permission here on some processors
 */
int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address,
			  pmd_t *pmdp, pmd_t entry, int dirty)
{
	int changed;
#ifdef CONFIG_DEBUG_VM
	WARN_ON(!pmd_trans_huge(*pmdp) && !pmd_devmap(*pmdp));
	assert_spin_locked(pmd_lockptr(vma->vm_mm, pmdp));
#endif
	changed = !pmd_same(*(pmdp), entry);
	if (changed) {
		/*
		 * We can use MMU_PAGE_2M here, because only radix
		 * path look at the psize.
		 */
		__ptep_set_access_flags(vma, pmdp_ptep(pmdp),
					pmd_pte(entry), address, MMU_PAGE_2M);
	}
	return changed;
}

int pmdp_test_and_clear_young(struct vm_area_struct *vma,
			      unsigned long address, pmd_t *pmdp)
{
	return __pmdp_test_and_clear_young(vma->vm_mm, address, pmdp);
}
/*
 * set a new huge pmd. We should not be called for updating
 * an existing pmd entry. That should go via pmd_hugepage_update.
 */
void set_pmd_at(struct mm_struct *mm, unsigned long addr,
		pmd_t *pmdp, pmd_t pmd)
{
#ifdef CONFIG_DEBUG_VM
	WARN_ON(pte_present(pmd_pte(*pmdp)) && !pte_protnone(pmd_pte(*pmdp)));
	assert_spin_locked(pmd_lockptr(mm, pmdp));
	WARN_ON(!(pmd_trans_huge(pmd) || pmd_devmap(pmd)));
#endif
	trace_hugepage_set_pmd(addr, pmd_val(pmd));
	return set_pte_at(mm, addr, pmdp_ptep(pmdp), pmd_pte(pmd));
}

static void do_nothing(void *unused)
{

}
/*
 * Serialize against find_current_mm_pte which does lock-less
 * lookup in page tables with local interrupts disabled. For huge pages
 * it casts pmd_t to pte_t. Since format of pte_t is different from
 * pmd_t we want to prevent transit from pmd pointing to page table
 * to pmd pointing to huge page (and back) while interrupts are disabled.
 * We clear pmd to possibly replace it with page table pointer in
 * different code paths. So make sure we wait for the parallel
 * find_current_mm_pte to finish.
 */
void serialize_against_pte_lookup(struct mm_struct *mm)
{
	smp_mb();
	smp_call_function_many(mm_cpumask(mm), do_nothing, NULL, 1);
}

/*
 * We use this to invalidate a pmdp entry before switching from a
 * hugepte to regular pmd entry.
 */
pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
		     pmd_t *pmdp)
{
	unsigned long old_pmd;

	old_pmd = pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, 0);
	flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
	/*
	 * This ensures that generic code that rely on IRQ disabling
	 * to prevent a parallel THP split work as expected.
	 */
	serialize_against_pte_lookup(vma->vm_mm);
	return __pmd(old_pmd);
}

static pmd_t pmd_set_protbits(pmd_t pmd, pgprot_t pgprot)
{
	return __pmd(pmd_val(pmd) | pgprot_val(pgprot));
}

pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot)
{
	unsigned long pmdv;

	pmdv = (pfn << PAGE_SHIFT) & PTE_RPN_MASK;
	return pmd_set_protbits(__pmd(pmdv), pgprot);
}

pmd_t mk_pmd(struct page *page, pgprot_t pgprot)
{
	return pfn_pmd(page_to_pfn(page), pgprot);
}

pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
{
	unsigned long pmdv;

	pmdv = pmd_val(pmd);
	pmdv &= _HPAGE_CHG_MASK;
	return pmd_set_protbits(__pmd(pmdv), newprot);
}

/*
 * This is called at the end of handling a user page fault, when the
 * fault has been handled by updating a HUGE PMD entry in the linux page tables.
 * We use it to preload an HPTE into the hash table corresponding to
 * the updated linux HUGE PMD entry.
 */
void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
			  pmd_t *pmd)
{
	if (radix_enabled())
		prefetch((void *)addr);
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */

/* For use by kexec */
void mmu_cleanup_all(void)
{
	if (radix_enabled())
		radix__mmu_cleanup_all();
	else if (mmu_hash_ops.hpte_clear_all)
		mmu_hash_ops.hpte_clear_all();
}

#ifdef CONFIG_MEMORY_HOTPLUG
int __meminit create_section_mapping(unsigned long start, unsigned long end, int nid)
{
	if (radix_enabled())
		return radix__create_section_mapping(start, end, nid);

	return hash__create_section_mapping(start, end, nid);
}

int __meminit remove_section_mapping(unsigned long start, unsigned long end)
{
	if (radix_enabled())
		return radix__remove_section_mapping(start, end);

	return hash__remove_section_mapping(start, end);
}
#endif /* CONFIG_MEMORY_HOTPLUG */

void __init mmu_partition_table_init(void)
{
	unsigned long patb_size = 1UL << PATB_SIZE_SHIFT;
	unsigned long ptcr;

	BUILD_BUG_ON_MSG((PATB_SIZE_SHIFT > 36), "Partition table size too large.");
	partition_tb = __va(memblock_alloc_base(patb_size, patb_size,
						MEMBLOCK_ALLOC_ANYWHERE));

	/* Initialize the Partition Table with no entries */
	memset((void *)partition_tb, 0, patb_size);

	/*
	 * update partition table control register,
	 * 64 K size.
	 */
	ptcr = __pa(partition_tb) | (PATB_SIZE_SHIFT - 12);
	mtspr(SPRN_PTCR, ptcr);
	powernv_set_nmmu_ptcr(ptcr);
}

void mmu_partition_table_set_entry(unsigned int lpid, unsigned long dw0,
				   unsigned long dw1)
{
	unsigned long old = be64_to_cpu(partition_tb[lpid].patb0);

	partition_tb[lpid].patb0 = cpu_to_be64(dw0);
	partition_tb[lpid].patb1 = cpu_to_be64(dw1);

	/*
	 * Global flush of TLBs and partition table caches for this lpid.
	 * The type of flush (hash or radix) depends on what the previous
	 * use of this partition ID was, not the new use.
	 */
	asm volatile("ptesync" : : : "memory");
	if (old & PATB_HR) {
		asm volatile(PPC_TLBIE_5(%0,%1,2,0,1) : :
			     "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid));
		asm volatile(PPC_TLBIE_5(%0,%1,2,1,1) : :
			     "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid));
		trace_tlbie(lpid, 0, TLBIEL_INVAL_SET_LPID, lpid, 2, 0, 1);
	} else {
		asm volatile(PPC_TLBIE_5(%0,%1,2,0,0) : :
			     "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid));
		trace_tlbie(lpid, 0, TLBIEL_INVAL_SET_LPID, lpid, 2, 0, 0);
	}
	/* do we need fixup here ?*/
	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
}
EXPORT_SYMBOL_GPL(mmu_partition_table_set_entry);

static pmd_t *get_pmd_from_cache(struct mm_struct *mm)
{
	void *pmd_frag, *ret;

	spin_lock(&mm->page_table_lock);
	ret = mm->context.pmd_frag;
	if (ret) {
		pmd_frag = ret + PMD_FRAG_SIZE;
		/*
		 * If we have taken up all the fragments mark PTE page NULL
		 */
		if (((unsigned long)pmd_frag & ~PAGE_MASK) == 0)
			pmd_frag = NULL;
		mm->context.pmd_frag = pmd_frag;
	}
	spin_unlock(&mm->page_table_lock);
	return (pmd_t *)ret;
}

static pmd_t *__alloc_for_pmdcache(struct mm_struct *mm)
{
	void *ret = NULL;
	struct page *page;
	gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO;

	if (mm == &init_mm)
		gfp &= ~__GFP_ACCOUNT;
	page = alloc_page(gfp);
	if (!page)
		return NULL;
	if (!pgtable_pmd_page_ctor(page)) {
		__free_pages(page, 0);
		return NULL;
	}

	ret = page_address(page);
	/*
	 * if we support only one fragment just return the
	 * allocated page.
	 */
	if (PMD_FRAG_NR == 1)
		return ret;

	spin_lock(&mm->page_table_lock);
	/*
	 * If we find pgtable_page set, we return
	 * the allocated page with single fragement
	 * count.
	 */
	if (likely(!mm->context.pmd_frag)) {
		set_page_count(page, PMD_FRAG_NR);
		mm->context.pmd_frag = ret + PMD_FRAG_SIZE;
	}
	spin_unlock(&mm->page_table_lock);

	return (pmd_t *)ret;
}

pmd_t *pmd_fragment_alloc(struct mm_struct *mm, unsigned long vmaddr)
{
	pmd_t *pmd;

	pmd = get_pmd_from_cache(mm);
	if (pmd)
		return pmd;

	return __alloc_for_pmdcache(mm);
}

void pmd_fragment_free(unsigned long *pmd)
{
	struct page *page = virt_to_page(pmd);

	if (put_page_testzero(page)) {
		pgtable_pmd_page_dtor(page);
		free_unref_page(page);
	}
}

static pte_t *get_pte_from_cache(struct mm_struct *mm)
{
	void *pte_frag, *ret;

	spin_lock(&mm->page_table_lock);
	ret = mm->context.pte_frag;
	if (ret) {
		pte_frag = ret + PTE_FRAG_SIZE;
		/*
		 * If we have taken up all the fragments mark PTE page NULL
		 */
		if (((unsigned long)pte_frag & ~PAGE_MASK) == 0)
			pte_frag = NULL;
		mm->context.pte_frag = pte_frag;
	}
	spin_unlock(&mm->page_table_lock);
	return (pte_t *)ret;
}

static pte_t *__alloc_for_ptecache(struct mm_struct *mm, int kernel)
{
	void *ret = NULL;
	struct page *page;

	if (!kernel) {
		page = alloc_page(PGALLOC_GFP | __GFP_ACCOUNT);
		if (!page)
			return NULL;
		if (!pgtable_page_ctor(page)) {
			__free_page(page);
			return NULL;
		}
	} else {
		page = alloc_page(PGALLOC_GFP);
		if (!page)
			return NULL;
	}


	ret = page_address(page);
	/*
	 * if we support only one fragment just return the
	 * allocated page.
	 */
	if (PTE_FRAG_NR == 1)
		return ret;
	spin_lock(&mm->page_table_lock);
	/*
	 * If we find pgtable_page set, we return
	 * the allocated page with single fragement
	 * count.
	 */
	if (likely(!mm->context.pte_frag)) {
		set_page_count(page, PTE_FRAG_NR);
		mm->context.pte_frag = ret + PTE_FRAG_SIZE;
	}
	spin_unlock(&mm->page_table_lock);

	return (pte_t *)ret;
}

pte_t *pte_fragment_alloc(struct mm_struct *mm, unsigned long vmaddr, int kernel)
{
	pte_t *pte;

	pte = get_pte_from_cache(mm);
	if (pte)
		return pte;

	return __alloc_for_ptecache(mm, kernel);
}

void pte_fragment_free(unsigned long *table, int kernel)
{
	struct page *page = virt_to_page(table);

	if (put_page_testzero(page)) {
		if (!kernel)
			pgtable_page_dtor(page);
		free_unref_page(page);
	}
}

static inline void pgtable_free(void *table, int index)
{
	switch (index) {
	case PTE_INDEX:
		pte_fragment_free(table, 0);
		break;
	case PMD_INDEX:
		pmd_fragment_free(table);
		break;
	case PUD_INDEX:
		kmem_cache_free(PGT_CACHE(PUD_CACHE_INDEX), table);
		break;
#if defined(CONFIG_PPC_4K_PAGES) && defined(CONFIG_HUGETLB_PAGE)
		/* 16M hugepd directory at pud level */
	case HTLB_16M_INDEX:
		BUILD_BUG_ON(H_16M_CACHE_INDEX <= 0);
		kmem_cache_free(PGT_CACHE(H_16M_CACHE_INDEX), table);
		break;
		/* 16G hugepd directory at the pgd level */
	case HTLB_16G_INDEX:
		BUILD_BUG_ON(H_16G_CACHE_INDEX <= 0);
		kmem_cache_free(PGT_CACHE(H_16G_CACHE_INDEX), table);
		break;
#endif
		/* We don't free pgd table via RCU callback */
	default:
		BUG();
	}
}

#ifdef CONFIG_SMP
void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int index)
{
	unsigned long pgf = (unsigned long)table;

	BUG_ON(index > MAX_PGTABLE_INDEX_SIZE);
	pgf |= index;
	tlb_remove_table(tlb, (void *)pgf);
}

void __tlb_remove_table(void *_table)
{
	void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE);
	unsigned int index = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE;

	return pgtable_free(table, index);
}
#else
void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int index)
{
	return pgtable_free(table, index);
}
#endif