summaryrefslogtreecommitdiff
path: root/arch/powerpc/mm/book3s64/pgtable.c
blob: 9e16c7b1a6c5680fe1f9dcd0daab01592a0556c4 (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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Copyright 2015-2016, Aneesh Kumar K.V, IBM Corporation.
 */

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

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

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

#include "internal.h"

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

#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
	/*
	 * Make sure hardware valid bit is not set. We don't do
	 * tlb flush for this update.
	 */

	WARN_ON(pte_hw_valid(pmd_pte(*pmdp)) && !pte_protnone(pmd_pte(*pmdp)));
	assert_spin_locked(pmd_lockptr(mm, pmdp));
	WARN_ON(!(pmd_large(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_serialize(void *arg)
{
	/* We've taken the IPI, so try to trim the mask while here */
	if (radix_enabled()) {
		struct mm_struct *mm = arg;
		exit_lazy_flush_tlb(mm, false);
	}
}

/*
 * 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_serialize, mm, 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, _PAGE_INVALID);
	flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
	return __pmd(old_pmd);
}

pmd_t pmdp_huge_get_and_clear_full(struct vm_area_struct *vma,
				   unsigned long addr, pmd_t *pmdp, int full)
{
	pmd_t pmd;
	VM_BUG_ON(addr & ~HPAGE_PMD_MASK);
	VM_BUG_ON((pmd_present(*pmdp) && !pmd_trans_huge(*pmdp) &&
		   !pmd_devmap(*pmdp)) || !pmd_present(*pmdp));
	pmd = pmdp_huge_get_and_clear(vma->vm_mm, addr, pmdp);
	/*
	 * if it not a fullmm flush, then we can possibly end up converting
	 * this PMD pte entry to a regular level 0 PTE by a parallel page fault.
	 * Make sure we flush the tlb in this case.
	 */
	if (!full)
		flush_pmd_tlb_range(vma, addr, addr + HPAGE_PMD_SIZE);
	return pmd;
}

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

/*
 * At some point we should be able to get rid of
 * pmd_mkhuge() and mk_huge_pmd() when we update all the
 * other archs to mark the pmd huge in pfn_pmd()
 */
pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot)
{
	unsigned long pmdv;

	pmdv = (pfn << PAGE_SHIFT) & PTE_RPN_MASK;

	return __pmd_mkhuge(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);
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */

/* For use by kexec, called with MMU off */
notrace 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();

	reset_sprs();
}

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

	return hash__create_section_mapping(start, end, nid, prot);
}

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.");
	/* Initialize the Partition Table with no entries */
	partition_tb = memblock_alloc(patb_size, patb_size);
	if (!partition_tb)
		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
		      __func__, patb_size, patb_size);

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

static void flush_partition(unsigned int lpid, bool radix)
{
	if (radix) {
		radix__flush_all_lpid(lpid);
		radix__flush_all_lpid_guest(lpid);
	} else {
		asm volatile("ptesync" : : : "memory");
		asm volatile(PPC_TLBIE_5(%0,%1,2,0,0) : :
			     "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid));
		/* do we need fixup here ?*/
		asm volatile("eieio; tlbsync; ptesync" : : : "memory");
		trace_tlbie(lpid, 0, TLBIEL_INVAL_SET_LPID, lpid, 2, 0, 0);
	}
}

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

	/*
	 * When ultravisor is enabled, the partition table is stored in secure
	 * memory and can only be accessed doing an ultravisor call. However, we
	 * maintain a copy of the partition table in normal memory to allow Nest
	 * MMU translations to occur (for normal VMs).
	 *
	 * Therefore, here we always update partition_tb, regardless of whether
	 * we are running under an ultravisor or not.
	 */
	partition_tb[lpid].patb0 = cpu_to_be64(dw0);
	partition_tb[lpid].patb1 = cpu_to_be64(dw1);

	/*
	 * If ultravisor is enabled, we do an ultravisor call to register the
	 * partition table entry (PATE), which also do a global flush of TLBs
	 * and partition table caches for the lpid. Otherwise, just do the
	 * flush. The type of flush (hash or radix) depends on what the previous
	 * use of the partition ID was, not the new use.
	 */
	if (firmware_has_feature(FW_FEATURE_ULTRAVISOR)) {
		uv_register_pate(lpid, dw0, dw1);
		pr_info("PATE registered by ultravisor: dw0 = 0x%lx, dw1 = 0x%lx\n",
			dw0, dw1);
	} else if (flush) {
		/*
		 * Boot does not need to flush, because MMU is off and each
		 * CPU does a tlbiel_all() before switching them on, which
		 * flushes everything.
		 */
		flush_partition(lpid, (old & PATB_HR));
	}
}
EXPORT_SYMBOL_GPL(mmu_partition_table_set_entry);

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

	if (PMD_FRAG_NR == 1)
		return NULL;

	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;
	}

	atomic_set(&page->pt_frag_refcount, 1);

	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)) {
		atomic_set(&page->pt_frag_refcount, 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 (PageReserved(page))
		return free_reserved_page(page);

	BUG_ON(atomic_read(&page->pt_frag_refcount) <= 0);
	if (atomic_dec_and_test(&page->pt_frag_refcount)) {
		pgtable_pmd_page_dtor(page);
		__free_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:
		__pud_free(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();
	}
}

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);
}

#ifdef CONFIG_PROC_FS
atomic_long_t direct_pages_count[MMU_PAGE_COUNT];

void arch_report_meminfo(struct seq_file *m)
{
	/*
	 * Hash maps the memory with one size mmu_linear_psize.
	 * So don't bother to print these on hash
	 */
	if (!radix_enabled())
		return;
	seq_printf(m, "DirectMap4k:    %8lu kB\n",
		   atomic_long_read(&direct_pages_count[MMU_PAGE_4K]) << 2);
	seq_printf(m, "DirectMap64k:    %8lu kB\n",
		   atomic_long_read(&direct_pages_count[MMU_PAGE_64K]) << 6);
	seq_printf(m, "DirectMap2M:    %8lu kB\n",
		   atomic_long_read(&direct_pages_count[MMU_PAGE_2M]) << 11);
	seq_printf(m, "DirectMap1G:    %8lu kB\n",
		   atomic_long_read(&direct_pages_count[MMU_PAGE_1G]) << 20);
}
#endif /* CONFIG_PROC_FS */

pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr,
			     pte_t *ptep)
{
	unsigned long pte_val;

	/*
	 * Clear the _PAGE_PRESENT so that no hardware parallel update is
	 * possible. Also keep the pte_present true so that we don't take
	 * wrong fault.
	 */
	pte_val = pte_update(vma->vm_mm, addr, ptep, _PAGE_PRESENT, _PAGE_INVALID, 0);

	return __pte(pte_val);

}

void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
			     pte_t *ptep, pte_t old_pte, pte_t pte)
{
	if (radix_enabled())
		return radix__ptep_modify_prot_commit(vma, addr,
						      ptep, old_pte, pte);
	set_pte_at(vma->vm_mm, addr, ptep, pte);
}

/*
 * For hash translation mode, we use the deposited table to store hash slot
 * information and they are stored at PTRS_PER_PMD offset from related pmd
 * location. Hence a pmd move requires deposit and withdraw.
 *
 * For radix translation with split pmd ptl, we store the deposited table in the
 * pmd page. Hence if we have different pmd page we need to withdraw during pmd
 * move.
 *
 * With hash we use deposited table always irrespective of anon or not.
 * With radix we use deposited table only for anonymous mapping.
 */
int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl,
			   struct spinlock *old_pmd_ptl,
			   struct vm_area_struct *vma)
{
	if (radix_enabled())
		return (new_pmd_ptl != old_pmd_ptl) && vma_is_anonymous(vma);

	return true;
}

/*
 * Does the CPU support tlbie?
 */
bool tlbie_capable __read_mostly = true;
EXPORT_SYMBOL(tlbie_capable);

/*
 * Should tlbie be used for management of CPU TLBs, for kernel and process
 * address spaces? tlbie may still be used for nMMU accelerators, and for KVM
 * guest address spaces.
 */
bool tlbie_enabled __read_mostly = true;

static int __init setup_disable_tlbie(char *str)
{
	if (!radix_enabled()) {
		pr_err("disable_tlbie: Unable to disable TLBIE with Hash MMU.\n");
		return 1;
	}

	tlbie_capable = false;
	tlbie_enabled = false;

        return 1;
}
__setup("disable_tlbie", setup_disable_tlbie);

static int __init pgtable_debugfs_setup(void)
{
	if (!tlbie_capable)
		return 0;

	/*
	 * There is no locking vs tlb flushing when changing this value.
	 * The tlb flushers will see one value or another, and use either
	 * tlbie or tlbiel with IPIs. In both cases the TLBs will be
	 * invalidated as expected.
	 */
	debugfs_create_bool("tlbie_enabled", 0600,
			arch_debugfs_dir,
			&tlbie_enabled);

	return 0;
}
arch_initcall(pgtable_debugfs_setup);