summaryrefslogtreecommitdiff
path: root/arch/powerpc/mm/pgtable-hash64.c
blob: 9699a1ccedb50ac9509e6f0dfd8f64a7ef8dd572 (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
/*
 * Copyright 2005, Paul Mackerras, IBM Corporation.
 * Copyright 2009, Benjamin Herrenschmidt, IBM Corporation.
 * 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 <asm/pgalloc.h>
#include <asm/tlb.h>

#include "mmu_decl.h"

#define CREATE_TRACE_POINTS
#include <trace/events/thp.h>

#ifdef CONFIG_SPARSEMEM_VMEMMAP
/*
 * On hash-based CPUs, the vmemmap is bolted in the hash table.
 *
 */
int __meminit hash__vmemmap_create_mapping(unsigned long start,
				       unsigned long page_size,
				       unsigned long phys)
{
	int rc = htab_bolt_mapping(start, start + page_size, phys,
				   pgprot_val(PAGE_KERNEL),
				   mmu_vmemmap_psize, mmu_kernel_ssize);
	if (rc < 0) {
		int rc2 = htab_remove_mapping(start, start + page_size,
					      mmu_vmemmap_psize,
					      mmu_kernel_ssize);
		BUG_ON(rc2 && (rc2 != -ENOENT));
	}
	return rc;
}

#ifdef CONFIG_MEMORY_HOTPLUG
void hash__vmemmap_remove_mapping(unsigned long start,
			      unsigned long page_size)
{
	int rc = htab_remove_mapping(start, start + page_size,
				     mmu_vmemmap_psize,
				     mmu_kernel_ssize);
	BUG_ON((rc < 0) && (rc != -ENOENT));
	WARN_ON(rc == -ENOENT);
}
#endif
#endif /* CONFIG_SPARSEMEM_VMEMMAP */

/*
 * map_kernel_page currently only called by __ioremap
 * map_kernel_page adds an entry to the ioremap page table
 * and adds an entry to the HPT, possibly bolting it
 */
int hash__map_kernel_page(unsigned long ea, unsigned long pa, unsigned long flags)
{
	pgd_t *pgdp;
	pud_t *pudp;
	pmd_t *pmdp;
	pte_t *ptep;

	BUILD_BUG_ON(TASK_SIZE_USER64 > H_PGTABLE_RANGE);
	if (slab_is_available()) {
		pgdp = pgd_offset_k(ea);
		pudp = pud_alloc(&init_mm, pgdp, ea);
		if (!pudp)
			return -ENOMEM;
		pmdp = pmd_alloc(&init_mm, pudp, ea);
		if (!pmdp)
			return -ENOMEM;
		ptep = pte_alloc_kernel(pmdp, ea);
		if (!ptep)
			return -ENOMEM;
		set_pte_at(&init_mm, ea, ptep, pfn_pte(pa >> PAGE_SHIFT,
							  __pgprot(flags)));
	} else {
		/*
		 * If the mm subsystem is not fully up, we cannot create a
		 * linux page table entry for this mapping.  Simply bolt an
		 * entry in the hardware page table.
		 *
		 */
		if (htab_bolt_mapping(ea, ea + PAGE_SIZE, pa, flags,
				      mmu_io_psize, mmu_kernel_ssize)) {
			printk(KERN_ERR "Failed to do bolted mapping IO "
			       "memory at %016lx !\n", pa);
			return -ENOMEM;
		}
	}

	smp_wmb();
	return 0;
}

#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));
	assert_spin_locked(&vma->vm_mm->page_table_lock);
#endif
	changed = !pmd_same(*(pmdp), entry);
	if (changed) {
		__ptep_set_access_flags(pmdp_ptep(pmdp), pmd_pte(entry));
		/*
		 * Since we are not supporting SW TLB systems, we don't
		 * have any thing similar to flush_tlb_page_nohash()
		 */
	}
	return changed;
}

unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr,
				  pmd_t *pmdp, unsigned long clr,
				  unsigned long set)
{
	__be64 old_be, tmp;
	unsigned long old;

#ifdef CONFIG_DEBUG_VM
	WARN_ON(!pmd_trans_huge(*pmdp));
	assert_spin_locked(&mm->page_table_lock);
#endif

	__asm__ __volatile__(
	"1:	ldarx	%0,0,%3\n\
		and.	%1,%0,%6\n\
		bne-	1b \n\
		andc	%1,%0,%4 \n\
		or	%1,%1,%7\n\
		stdcx.	%1,0,%3 \n\
		bne-	1b"
	: "=&r" (old_be), "=&r" (tmp), "=m" (*pmdp)
	: "r" (pmdp), "r" (cpu_to_be64(clr)), "m" (*pmdp),
	  "r" (cpu_to_be64(H_PAGE_BUSY)), "r" (cpu_to_be64(set))
	: "cc" );

	old = be64_to_cpu(old_be);

	trace_hugepage_update(addr, old, clr, set);
	if (old & H_PAGE_HASHPTE)
		hpte_do_hugepage_flush(mm, addr, pmdp, old);
	return old;
}

pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address,
			  pmd_t *pmdp)
{
	pmd_t pmd;

	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
	VM_BUG_ON(pmd_trans_huge(*pmdp));

	pmd = *pmdp;
	pmd_clear(pmdp);
	/*
	 * Wait for all pending hash_page to finish. This is needed
	 * in case of subpage collapse. When we collapse normal pages
	 * to hugepage, we first clear the pmd, then invalidate all
	 * the PTE entries. The assumption here is that any low level
	 * page fault will see a none pmd and take the slow path that
	 * will wait on mmap_sem. But we could very well be in a
	 * hash_page with local ptep pointer value. Such a hash page
	 * can result in adding new HPTE entries for normal subpages.
	 * That means we could be modifying the page content as we
	 * copy them to a huge page. So wait for parallel hash_page
	 * to finish before invalidating HPTE entries. We can do this
	 * by sending an IPI to all the cpus and executing a dummy
	 * function there.
	 */
	kick_all_cpus_sync();
	/*
	 * Now invalidate the hpte entries in the range
	 * covered by pmd. This make sure we take a
	 * fault and will find the pmd as none, which will
	 * result in a major fault which takes mmap_sem and
	 * hence wait for collapse to complete. Without this
	 * the __collapse_huge_page_copy can result in copying
	 * the old content.
	 */
	flush_tlb_pmd_range(vma->vm_mm, &pmd, address);
	return pmd;
}

/*
 * We currently remove entries from the hashtable regardless of whether
 * the entry was young or dirty.
 *
 * We should be more intelligent about this but for the moment we override
 * these functions and force a tlb flush unconditionally
 */
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);
}

/*
 * We want to put the pgtable in pmd and use pgtable for tracking
 * the base page size hptes
 */
void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
				pgtable_t pgtable)
{
	pgtable_t *pgtable_slot;
	assert_spin_locked(&mm->page_table_lock);
	/*
	 * we store the pgtable in the second half of PMD
	 */
	pgtable_slot = (pgtable_t *)pmdp + PTRS_PER_PMD;
	*pgtable_slot = pgtable;
	/*
	 * expose the deposited pgtable to other cpus.
	 * before we set the hugepage PTE at pmd level
	 * hash fault code looks at the deposted pgtable
	 * to store hash index values.
	 */
	smp_wmb();
}

pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
{
	pgtable_t pgtable;
	pgtable_t *pgtable_slot;

	assert_spin_locked(&mm->page_table_lock);
	pgtable_slot = (pgtable_t *)pmdp + PTRS_PER_PMD;
	pgtable = *pgtable_slot;
	/*
	 * Once we withdraw, mark the entry NULL.
	 */
	*pgtable_slot = NULL;
	/*
	 * We store HPTE information in the deposited PTE fragment.
	 * zero out the content on withdraw.
	 */
	memset(pgtable, 0, PTE_FRAG_SIZE);
	return pgtable;
}

void pmdp_huge_split_prepare(struct vm_area_struct *vma,
			     unsigned long address, pmd_t *pmdp)
{
	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
	VM_BUG_ON(REGION_ID(address) != USER_REGION_ID);

	/*
	 * We can't mark the pmd none here, because that will cause a race
	 * against exit_mmap. We need to continue mark pmd TRANS HUGE, while
	 * we spilt, but at the same time we wan't rest of the ppc64 code
	 * not to insert hash pte on this, because we will be modifying
	 * the deposited pgtable in the caller of this function. Hence
	 * clear the _PAGE_USER so that we move the fault handling to
	 * higher level function and that will serialize against ptl.
	 * We need to flush existing hash pte entries here even though,
	 * the translation is still valid, because we will withdraw
	 * pgtable_t after this.
	 */
	pmd_hugepage_update(vma->vm_mm, address, pmdp, 0, _PAGE_PRIVILEGED);
}


/*
 * 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(&mm->page_table_lock);
	WARN_ON(!pmd_trans_huge(pmd));
#endif
	trace_hugepage_set_pmd(addr, pmd_val(pmd));
	return set_pte_at(mm, addr, pmdp_ptep(pmdp), pmd_pte(pmd));
}

/*
 * We use this to invalidate a pmdp entry before switching from a
 * hugepte to regular pmd entry.
 */
void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
		     pmd_t *pmdp)
{
	pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, 0);

	/*
	 * This ensures that generic code that rely on IRQ disabling
	 * to prevent a parallel THP split work as expected.
	 */
	kick_all_cpus_sync();
}

/*
 * A linux hugepage PMD was changed and the corresponding hash table entries
 * neesd to be flushed.
 */
void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
			    pmd_t *pmdp, unsigned long old_pmd)
{
	int ssize;
	unsigned int psize;
	unsigned long vsid;
	unsigned long flags = 0;
	const struct cpumask *tmp;

	/* get the base page size,vsid and segment size */
#ifdef CONFIG_DEBUG_VM
	psize = get_slice_psize(mm, addr);
	BUG_ON(psize == MMU_PAGE_16M);
#endif
	if (old_pmd & H_PAGE_COMBO)
		psize = MMU_PAGE_4K;
	else
		psize = MMU_PAGE_64K;

	if (!is_kernel_addr(addr)) {
		ssize = user_segment_size(addr);
		vsid = get_vsid(mm->context.id, addr, ssize);
		WARN_ON(vsid == 0);
	} else {
		vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
		ssize = mmu_kernel_ssize;
	}

	tmp = cpumask_of(smp_processor_id());
	if (cpumask_equal(mm_cpumask(mm), tmp))
		flags |= HPTE_LOCAL_UPDATE;

	return flush_hash_hugepage(vsid, addr, pmdp, psize, ssize, flags);
}

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)
{
	return;
}

pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
			      unsigned long addr, pmd_t *pmdp)
{
	pmd_t old_pmd;
	pgtable_t pgtable;
	unsigned long old;
	pgtable_t *pgtable_slot;

	old = pmd_hugepage_update(mm, addr, pmdp, ~0UL, 0);
	old_pmd = __pmd(old);
	/*
	 * We have pmd == none and we are holding page_table_lock.
	 * So we can safely go and clear the pgtable hash
	 * index info.
	 */
	pgtable_slot = (pgtable_t *)pmdp + PTRS_PER_PMD;
	pgtable = *pgtable_slot;
	/*
	 * Let's zero out old valid and hash index details
	 * hash fault look at them.
	 */
	memset(pgtable, 0, PTE_FRAG_SIZE);
	/*
	 * Serialize against find_linux_pte_or_hugepte 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_linux_pte_or_hugepage to finish.
	 */
	kick_all_cpus_sync();
	return old_pmd;
}

int has_transparent_hugepage(void)
{

	if (!mmu_has_feature(MMU_FTR_16M_PAGE))
		return 0;
	/*
	 * We support THP only if PMD_SIZE is 16MB.
	 */
	if (mmu_psize_defs[MMU_PAGE_16M].shift != PMD_SHIFT)
		return 0;
	/*
	 * We need to make sure that we support 16MB hugepage in a segement
	 * with base page size 64K or 4K. We only enable THP with a PAGE_SIZE
	 * of 64K.
	 */
	/*
	 * If we have 64K HPTE, we will be using that by default
	 */
	if (mmu_psize_defs[MMU_PAGE_64K].shift &&
	    (mmu_psize_defs[MMU_PAGE_64K].penc[MMU_PAGE_16M] == -1))
		return 0;
	/*
	 * Ok we only have 4K HPTE
	 */
	if (mmu_psize_defs[MMU_PAGE_4K].penc[MMU_PAGE_16M] == -1)
		return 0;

	return 1;
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */