xref: /kernel/linux/linux-6.6/arch/x86/mm/pgtable.c (revision 62306a36)
1// SPDX-License-Identifier: GPL-2.0
2#include <linux/mm.h>
3#include <linux/gfp.h>
4#include <linux/hugetlb.h>
5#include <asm/pgalloc.h>
6#include <asm/tlb.h>
7#include <asm/fixmap.h>
8#include <asm/mtrr.h>
9
10#ifdef CONFIG_DYNAMIC_PHYSICAL_MASK
11phys_addr_t physical_mask __ro_after_init = (1ULL << __PHYSICAL_MASK_SHIFT) - 1;
12EXPORT_SYMBOL(physical_mask);
13#endif
14
15#ifdef CONFIG_HIGHPTE
16#define PGTABLE_HIGHMEM __GFP_HIGHMEM
17#else
18#define PGTABLE_HIGHMEM 0
19#endif
20
21#ifndef CONFIG_PARAVIRT
22static inline
23void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table)
24{
25	tlb_remove_page(tlb, table);
26}
27#endif
28
29gfp_t __userpte_alloc_gfp = GFP_PGTABLE_USER | PGTABLE_HIGHMEM;
30
31pgtable_t pte_alloc_one(struct mm_struct *mm)
32{
33	return __pte_alloc_one(mm, __userpte_alloc_gfp);
34}
35
36static int __init setup_userpte(char *arg)
37{
38	if (!arg)
39		return -EINVAL;
40
41	/*
42	 * "userpte=nohigh" disables allocation of user pagetables in
43	 * high memory.
44	 */
45	if (strcmp(arg, "nohigh") == 0)
46		__userpte_alloc_gfp &= ~__GFP_HIGHMEM;
47	else
48		return -EINVAL;
49	return 0;
50}
51early_param("userpte", setup_userpte);
52
53void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte)
54{
55	pagetable_pte_dtor(page_ptdesc(pte));
56	paravirt_release_pte(page_to_pfn(pte));
57	paravirt_tlb_remove_table(tlb, pte);
58}
59
60#if CONFIG_PGTABLE_LEVELS > 2
61void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd)
62{
63	struct ptdesc *ptdesc = virt_to_ptdesc(pmd);
64	paravirt_release_pmd(__pa(pmd) >> PAGE_SHIFT);
65	/*
66	 * NOTE! For PAE, any changes to the top page-directory-pointer-table
67	 * entries need a full cr3 reload to flush.
68	 */
69#ifdef CONFIG_X86_PAE
70	tlb->need_flush_all = 1;
71#endif
72	pagetable_pmd_dtor(ptdesc);
73	paravirt_tlb_remove_table(tlb, ptdesc_page(ptdesc));
74}
75
76#if CONFIG_PGTABLE_LEVELS > 3
77void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud)
78{
79	paravirt_release_pud(__pa(pud) >> PAGE_SHIFT);
80	paravirt_tlb_remove_table(tlb, virt_to_page(pud));
81}
82
83#if CONFIG_PGTABLE_LEVELS > 4
84void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d)
85{
86	paravirt_release_p4d(__pa(p4d) >> PAGE_SHIFT);
87	paravirt_tlb_remove_table(tlb, virt_to_page(p4d));
88}
89#endif	/* CONFIG_PGTABLE_LEVELS > 4 */
90#endif	/* CONFIG_PGTABLE_LEVELS > 3 */
91#endif	/* CONFIG_PGTABLE_LEVELS > 2 */
92
93static inline void pgd_list_add(pgd_t *pgd)
94{
95	struct ptdesc *ptdesc = virt_to_ptdesc(pgd);
96
97	list_add(&ptdesc->pt_list, &pgd_list);
98}
99
100static inline void pgd_list_del(pgd_t *pgd)
101{
102	struct ptdesc *ptdesc = virt_to_ptdesc(pgd);
103
104	list_del(&ptdesc->pt_list);
105}
106
107#define UNSHARED_PTRS_PER_PGD				\
108	(SHARED_KERNEL_PMD ? KERNEL_PGD_BOUNDARY : PTRS_PER_PGD)
109#define MAX_UNSHARED_PTRS_PER_PGD			\
110	max_t(size_t, KERNEL_PGD_BOUNDARY, PTRS_PER_PGD)
111
112
113static void pgd_set_mm(pgd_t *pgd, struct mm_struct *mm)
114{
115	virt_to_ptdesc(pgd)->pt_mm = mm;
116}
117
118struct mm_struct *pgd_page_get_mm(struct page *page)
119{
120	return page_ptdesc(page)->pt_mm;
121}
122
123static void pgd_ctor(struct mm_struct *mm, pgd_t *pgd)
124{
125	/* If the pgd points to a shared pagetable level (either the
126	   ptes in non-PAE, or shared PMD in PAE), then just copy the
127	   references from swapper_pg_dir. */
128	if (CONFIG_PGTABLE_LEVELS == 2 ||
129	    (CONFIG_PGTABLE_LEVELS == 3 && SHARED_KERNEL_PMD) ||
130	    CONFIG_PGTABLE_LEVELS >= 4) {
131		clone_pgd_range(pgd + KERNEL_PGD_BOUNDARY,
132				swapper_pg_dir + KERNEL_PGD_BOUNDARY,
133				KERNEL_PGD_PTRS);
134	}
135
136	/* list required to sync kernel mapping updates */
137	if (!SHARED_KERNEL_PMD) {
138		pgd_set_mm(pgd, mm);
139		pgd_list_add(pgd);
140	}
141}
142
143static void pgd_dtor(pgd_t *pgd)
144{
145	if (SHARED_KERNEL_PMD)
146		return;
147
148	spin_lock(&pgd_lock);
149	pgd_list_del(pgd);
150	spin_unlock(&pgd_lock);
151}
152
153/*
154 * List of all pgd's needed for non-PAE so it can invalidate entries
155 * in both cached and uncached pgd's; not needed for PAE since the
156 * kernel pmd is shared. If PAE were not to share the pmd a similar
157 * tactic would be needed. This is essentially codepath-based locking
158 * against pageattr.c; it is the unique case in which a valid change
159 * of kernel pagetables can't be lazily synchronized by vmalloc faults.
160 * vmalloc faults work because attached pagetables are never freed.
161 * -- nyc
162 */
163
164#ifdef CONFIG_X86_PAE
165/*
166 * In PAE mode, we need to do a cr3 reload (=tlb flush) when
167 * updating the top-level pagetable entries to guarantee the
168 * processor notices the update.  Since this is expensive, and
169 * all 4 top-level entries are used almost immediately in a
170 * new process's life, we just pre-populate them here.
171 *
172 * Also, if we're in a paravirt environment where the kernel pmd is
173 * not shared between pagetables (!SHARED_KERNEL_PMDS), we allocate
174 * and initialize the kernel pmds here.
175 */
176#define PREALLOCATED_PMDS	UNSHARED_PTRS_PER_PGD
177#define MAX_PREALLOCATED_PMDS	MAX_UNSHARED_PTRS_PER_PGD
178
179/*
180 * We allocate separate PMDs for the kernel part of the user page-table
181 * when PTI is enabled. We need them to map the per-process LDT into the
182 * user-space page-table.
183 */
184#define PREALLOCATED_USER_PMDS	 (boot_cpu_has(X86_FEATURE_PTI) ? \
185					KERNEL_PGD_PTRS : 0)
186#define MAX_PREALLOCATED_USER_PMDS KERNEL_PGD_PTRS
187
188void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd)
189{
190	paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT);
191
192	/* Note: almost everything apart from _PAGE_PRESENT is
193	   reserved at the pmd (PDPT) level. */
194	set_pud(pudp, __pud(__pa(pmd) | _PAGE_PRESENT));
195
196	/*
197	 * According to Intel App note "TLBs, Paging-Structure Caches,
198	 * and Their Invalidation", April 2007, document 317080-001,
199	 * section 8.1: in PAE mode we explicitly have to flush the
200	 * TLB via cr3 if the top-level pgd is changed...
201	 */
202	flush_tlb_mm(mm);
203}
204#else  /* !CONFIG_X86_PAE */
205
206/* No need to prepopulate any pagetable entries in non-PAE modes. */
207#define PREALLOCATED_PMDS	0
208#define MAX_PREALLOCATED_PMDS	0
209#define PREALLOCATED_USER_PMDS	 0
210#define MAX_PREALLOCATED_USER_PMDS 0
211#endif	/* CONFIG_X86_PAE */
212
213static void free_pmds(struct mm_struct *mm, pmd_t *pmds[], int count)
214{
215	int i;
216	struct ptdesc *ptdesc;
217
218	for (i = 0; i < count; i++)
219		if (pmds[i]) {
220			ptdesc = virt_to_ptdesc(pmds[i]);
221
222			pagetable_pmd_dtor(ptdesc);
223			pagetable_free(ptdesc);
224			mm_dec_nr_pmds(mm);
225		}
226}
227
228static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[], int count)
229{
230	int i;
231	bool failed = false;
232	gfp_t gfp = GFP_PGTABLE_USER;
233
234	if (mm == &init_mm)
235		gfp &= ~__GFP_ACCOUNT;
236	gfp &= ~__GFP_HIGHMEM;
237
238	for (i = 0; i < count; i++) {
239		pmd_t *pmd = NULL;
240		struct ptdesc *ptdesc = pagetable_alloc(gfp, 0);
241
242		if (!ptdesc)
243			failed = true;
244		if (ptdesc && !pagetable_pmd_ctor(ptdesc)) {
245			pagetable_free(ptdesc);
246			ptdesc = NULL;
247			failed = true;
248		}
249		if (ptdesc) {
250			mm_inc_nr_pmds(mm);
251			pmd = ptdesc_address(ptdesc);
252		}
253
254		pmds[i] = pmd;
255	}
256
257	if (failed) {
258		free_pmds(mm, pmds, count);
259		return -ENOMEM;
260	}
261
262	return 0;
263}
264
265/*
266 * Mop up any pmd pages which may still be attached to the pgd.
267 * Normally they will be freed by munmap/exit_mmap, but any pmd we
268 * preallocate which never got a corresponding vma will need to be
269 * freed manually.
270 */
271static void mop_up_one_pmd(struct mm_struct *mm, pgd_t *pgdp)
272{
273	pgd_t pgd = *pgdp;
274
275	if (pgd_val(pgd) != 0) {
276		pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd);
277
278		pgd_clear(pgdp);
279
280		paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT);
281		pmd_free(mm, pmd);
282		mm_dec_nr_pmds(mm);
283	}
284}
285
286static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp)
287{
288	int i;
289
290	for (i = 0; i < PREALLOCATED_PMDS; i++)
291		mop_up_one_pmd(mm, &pgdp[i]);
292
293#ifdef CONFIG_PAGE_TABLE_ISOLATION
294
295	if (!boot_cpu_has(X86_FEATURE_PTI))
296		return;
297
298	pgdp = kernel_to_user_pgdp(pgdp);
299
300	for (i = 0; i < PREALLOCATED_USER_PMDS; i++)
301		mop_up_one_pmd(mm, &pgdp[i + KERNEL_PGD_BOUNDARY]);
302#endif
303}
304
305static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[])
306{
307	p4d_t *p4d;
308	pud_t *pud;
309	int i;
310
311	p4d = p4d_offset(pgd, 0);
312	pud = pud_offset(p4d, 0);
313
314	for (i = 0; i < PREALLOCATED_PMDS; i++, pud++) {
315		pmd_t *pmd = pmds[i];
316
317		if (i >= KERNEL_PGD_BOUNDARY)
318			memcpy(pmd, (pmd_t *)pgd_page_vaddr(swapper_pg_dir[i]),
319			       sizeof(pmd_t) * PTRS_PER_PMD);
320
321		pud_populate(mm, pud, pmd);
322	}
323}
324
325#ifdef CONFIG_PAGE_TABLE_ISOLATION
326static void pgd_prepopulate_user_pmd(struct mm_struct *mm,
327				     pgd_t *k_pgd, pmd_t *pmds[])
328{
329	pgd_t *s_pgd = kernel_to_user_pgdp(swapper_pg_dir);
330	pgd_t *u_pgd = kernel_to_user_pgdp(k_pgd);
331	p4d_t *u_p4d;
332	pud_t *u_pud;
333	int i;
334
335	u_p4d = p4d_offset(u_pgd, 0);
336	u_pud = pud_offset(u_p4d, 0);
337
338	s_pgd += KERNEL_PGD_BOUNDARY;
339	u_pud += KERNEL_PGD_BOUNDARY;
340
341	for (i = 0; i < PREALLOCATED_USER_PMDS; i++, u_pud++, s_pgd++) {
342		pmd_t *pmd = pmds[i];
343
344		memcpy(pmd, (pmd_t *)pgd_page_vaddr(*s_pgd),
345		       sizeof(pmd_t) * PTRS_PER_PMD);
346
347		pud_populate(mm, u_pud, pmd);
348	}
349
350}
351#else
352static void pgd_prepopulate_user_pmd(struct mm_struct *mm,
353				     pgd_t *k_pgd, pmd_t *pmds[])
354{
355}
356#endif
357/*
358 * Xen paravirt assumes pgd table should be in one page. 64 bit kernel also
359 * assumes that pgd should be in one page.
360 *
361 * But kernel with PAE paging that is not running as a Xen domain
362 * only needs to allocate 32 bytes for pgd instead of one page.
363 */
364#ifdef CONFIG_X86_PAE
365
366#include <linux/slab.h>
367
368#define PGD_SIZE	(PTRS_PER_PGD * sizeof(pgd_t))
369#define PGD_ALIGN	32
370
371static struct kmem_cache *pgd_cache;
372
373void __init pgtable_cache_init(void)
374{
375	/*
376	 * When PAE kernel is running as a Xen domain, it does not use
377	 * shared kernel pmd. And this requires a whole page for pgd.
378	 */
379	if (!SHARED_KERNEL_PMD)
380		return;
381
382	/*
383	 * when PAE kernel is not running as a Xen domain, it uses
384	 * shared kernel pmd. Shared kernel pmd does not require a whole
385	 * page for pgd. We are able to just allocate a 32-byte for pgd.
386	 * During boot time, we create a 32-byte slab for pgd table allocation.
387	 */
388	pgd_cache = kmem_cache_create("pgd_cache", PGD_SIZE, PGD_ALIGN,
389				      SLAB_PANIC, NULL);
390}
391
392static inline pgd_t *_pgd_alloc(void)
393{
394	/*
395	 * If no SHARED_KERNEL_PMD, PAE kernel is running as a Xen domain.
396	 * We allocate one page for pgd.
397	 */
398	if (!SHARED_KERNEL_PMD)
399		return (pgd_t *)__get_free_pages(GFP_PGTABLE_USER,
400						 PGD_ALLOCATION_ORDER);
401
402	/*
403	 * Now PAE kernel is not running as a Xen domain. We can allocate
404	 * a 32-byte slab for pgd to save memory space.
405	 */
406	return kmem_cache_alloc(pgd_cache, GFP_PGTABLE_USER);
407}
408
409static inline void _pgd_free(pgd_t *pgd)
410{
411	if (!SHARED_KERNEL_PMD)
412		free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER);
413	else
414		kmem_cache_free(pgd_cache, pgd);
415}
416#else
417
418static inline pgd_t *_pgd_alloc(void)
419{
420	return (pgd_t *)__get_free_pages(GFP_PGTABLE_USER,
421					 PGD_ALLOCATION_ORDER);
422}
423
424static inline void _pgd_free(pgd_t *pgd)
425{
426	free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER);
427}
428#endif /* CONFIG_X86_PAE */
429
430pgd_t *pgd_alloc(struct mm_struct *mm)
431{
432	pgd_t *pgd;
433	pmd_t *u_pmds[MAX_PREALLOCATED_USER_PMDS];
434	pmd_t *pmds[MAX_PREALLOCATED_PMDS];
435
436	pgd = _pgd_alloc();
437
438	if (pgd == NULL)
439		goto out;
440
441	mm->pgd = pgd;
442
443	if (sizeof(pmds) != 0 &&
444			preallocate_pmds(mm, pmds, PREALLOCATED_PMDS) != 0)
445		goto out_free_pgd;
446
447	if (sizeof(u_pmds) != 0 &&
448			preallocate_pmds(mm, u_pmds, PREALLOCATED_USER_PMDS) != 0)
449		goto out_free_pmds;
450
451	if (paravirt_pgd_alloc(mm) != 0)
452		goto out_free_user_pmds;
453
454	/*
455	 * Make sure that pre-populating the pmds is atomic with
456	 * respect to anything walking the pgd_list, so that they
457	 * never see a partially populated pgd.
458	 */
459	spin_lock(&pgd_lock);
460
461	pgd_ctor(mm, pgd);
462	if (sizeof(pmds) != 0)
463		pgd_prepopulate_pmd(mm, pgd, pmds);
464
465	if (sizeof(u_pmds) != 0)
466		pgd_prepopulate_user_pmd(mm, pgd, u_pmds);
467
468	spin_unlock(&pgd_lock);
469
470	return pgd;
471
472out_free_user_pmds:
473	if (sizeof(u_pmds) != 0)
474		free_pmds(mm, u_pmds, PREALLOCATED_USER_PMDS);
475out_free_pmds:
476	if (sizeof(pmds) != 0)
477		free_pmds(mm, pmds, PREALLOCATED_PMDS);
478out_free_pgd:
479	_pgd_free(pgd);
480out:
481	return NULL;
482}
483
484void pgd_free(struct mm_struct *mm, pgd_t *pgd)
485{
486	pgd_mop_up_pmds(mm, pgd);
487	pgd_dtor(pgd);
488	paravirt_pgd_free(mm, pgd);
489	_pgd_free(pgd);
490}
491
492/*
493 * Used to set accessed or dirty bits in the page table entries
494 * on other architectures. On x86, the accessed and dirty bits
495 * are tracked by hardware. However, do_wp_page calls this function
496 * to also make the pte writeable at the same time the dirty bit is
497 * set. In that case we do actually need to write the PTE.
498 */
499int ptep_set_access_flags(struct vm_area_struct *vma,
500			  unsigned long address, pte_t *ptep,
501			  pte_t entry, int dirty)
502{
503	int changed = !pte_same(*ptep, entry);
504
505	if (changed && dirty)
506		set_pte(ptep, entry);
507
508	return changed;
509}
510
511#ifdef CONFIG_TRANSPARENT_HUGEPAGE
512int pmdp_set_access_flags(struct vm_area_struct *vma,
513			  unsigned long address, pmd_t *pmdp,
514			  pmd_t entry, int dirty)
515{
516	int changed = !pmd_same(*pmdp, entry);
517
518	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
519
520	if (changed && dirty) {
521		set_pmd(pmdp, entry);
522		/*
523		 * We had a write-protection fault here and changed the pmd
524		 * to to more permissive. No need to flush the TLB for that,
525		 * #PF is architecturally guaranteed to do that and in the
526		 * worst-case we'll generate a spurious fault.
527		 */
528	}
529
530	return changed;
531}
532
533int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address,
534			  pud_t *pudp, pud_t entry, int dirty)
535{
536	int changed = !pud_same(*pudp, entry);
537
538	VM_BUG_ON(address & ~HPAGE_PUD_MASK);
539
540	if (changed && dirty) {
541		set_pud(pudp, entry);
542		/*
543		 * We had a write-protection fault here and changed the pud
544		 * to to more permissive. No need to flush the TLB for that,
545		 * #PF is architecturally guaranteed to do that and in the
546		 * worst-case we'll generate a spurious fault.
547		 */
548	}
549
550	return changed;
551}
552#endif
553
554int ptep_test_and_clear_young(struct vm_area_struct *vma,
555			      unsigned long addr, pte_t *ptep)
556{
557	int ret = 0;
558
559	if (pte_young(*ptep))
560		ret = test_and_clear_bit(_PAGE_BIT_ACCESSED,
561					 (unsigned long *) &ptep->pte);
562
563	return ret;
564}
565
566#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG)
567int pmdp_test_and_clear_young(struct vm_area_struct *vma,
568			      unsigned long addr, pmd_t *pmdp)
569{
570	int ret = 0;
571
572	if (pmd_young(*pmdp))
573		ret = test_and_clear_bit(_PAGE_BIT_ACCESSED,
574					 (unsigned long *)pmdp);
575
576	return ret;
577}
578#endif
579
580#ifdef CONFIG_TRANSPARENT_HUGEPAGE
581int pudp_test_and_clear_young(struct vm_area_struct *vma,
582			      unsigned long addr, pud_t *pudp)
583{
584	int ret = 0;
585
586	if (pud_young(*pudp))
587		ret = test_and_clear_bit(_PAGE_BIT_ACCESSED,
588					 (unsigned long *)pudp);
589
590	return ret;
591}
592#endif
593
594int ptep_clear_flush_young(struct vm_area_struct *vma,
595			   unsigned long address, pte_t *ptep)
596{
597	/*
598	 * On x86 CPUs, clearing the accessed bit without a TLB flush
599	 * doesn't cause data corruption. [ It could cause incorrect
600	 * page aging and the (mistaken) reclaim of hot pages, but the
601	 * chance of that should be relatively low. ]
602	 *
603	 * So as a performance optimization don't flush the TLB when
604	 * clearing the accessed bit, it will eventually be flushed by
605	 * a context switch or a VM operation anyway. [ In the rare
606	 * event of it not getting flushed for a long time the delay
607	 * shouldn't really matter because there's no real memory
608	 * pressure for swapout to react to. ]
609	 */
610	return ptep_test_and_clear_young(vma, address, ptep);
611}
612
613#ifdef CONFIG_TRANSPARENT_HUGEPAGE
614int pmdp_clear_flush_young(struct vm_area_struct *vma,
615			   unsigned long address, pmd_t *pmdp)
616{
617	int young;
618
619	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
620
621	young = pmdp_test_and_clear_young(vma, address, pmdp);
622	if (young)
623		flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
624
625	return young;
626}
627
628pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address,
629			 pmd_t *pmdp)
630{
631	/*
632	 * No flush is necessary. Once an invalid PTE is established, the PTE's
633	 * access and dirty bits cannot be updated.
634	 */
635	return pmdp_establish(vma, address, pmdp, pmd_mkinvalid(*pmdp));
636}
637#endif
638
639/**
640 * reserve_top_address - reserves a hole in the top of kernel address space
641 * @reserve - size of hole to reserve
642 *
643 * Can be used to relocate the fixmap area and poke a hole in the top
644 * of kernel address space to make room for a hypervisor.
645 */
646void __init reserve_top_address(unsigned long reserve)
647{
648#ifdef CONFIG_X86_32
649	BUG_ON(fixmaps_set > 0);
650	__FIXADDR_TOP = round_down(-reserve, 1 << PMD_SHIFT) - PAGE_SIZE;
651	printk(KERN_INFO "Reserving virtual address space above 0x%08lx (rounded to 0x%08lx)\n",
652	       -reserve, __FIXADDR_TOP + PAGE_SIZE);
653#endif
654}
655
656int fixmaps_set;
657
658void __native_set_fixmap(enum fixed_addresses idx, pte_t pte)
659{
660	unsigned long address = __fix_to_virt(idx);
661
662#ifdef CONFIG_X86_64
663       /*
664	* Ensure that the static initial page tables are covering the
665	* fixmap completely.
666	*/
667	BUILD_BUG_ON(__end_of_permanent_fixed_addresses >
668		     (FIXMAP_PMD_NUM * PTRS_PER_PTE));
669#endif
670
671	if (idx >= __end_of_fixed_addresses) {
672		BUG();
673		return;
674	}
675	set_pte_vaddr(address, pte);
676	fixmaps_set++;
677}
678
679void native_set_fixmap(unsigned /* enum fixed_addresses */ idx,
680		       phys_addr_t phys, pgprot_t flags)
681{
682	/* Sanitize 'prot' against any unsupported bits: */
683	pgprot_val(flags) &= __default_kernel_pte_mask;
684
685	__native_set_fixmap(idx, pfn_pte(phys >> PAGE_SHIFT, flags));
686}
687
688#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
689#ifdef CONFIG_X86_5LEVEL
690/**
691 * p4d_set_huge - setup kernel P4D mapping
692 *
693 * No 512GB pages yet -- always return 0
694 */
695int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
696{
697	return 0;
698}
699
700/**
701 * p4d_clear_huge - clear kernel P4D mapping when it is set
702 *
703 * No 512GB pages yet -- always return 0
704 */
705void p4d_clear_huge(p4d_t *p4d)
706{
707}
708#endif
709
710/**
711 * pud_set_huge - setup kernel PUD mapping
712 *
713 * MTRRs can override PAT memory types with 4KiB granularity. Therefore, this
714 * function sets up a huge page only if the complete range has the same MTRR
715 * caching mode.
716 *
717 * Callers should try to decrease page size (1GB -> 2MB -> 4K) if the bigger
718 * page mapping attempt fails.
719 *
720 * Returns 1 on success and 0 on failure.
721 */
722int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
723{
724	u8 uniform;
725
726	mtrr_type_lookup(addr, addr + PUD_SIZE, &uniform);
727	if (!uniform)
728		return 0;
729
730	/* Bail out if we are we on a populated non-leaf entry: */
731	if (pud_present(*pud) && !pud_huge(*pud))
732		return 0;
733
734	set_pte((pte_t *)pud, pfn_pte(
735		(u64)addr >> PAGE_SHIFT,
736		__pgprot(protval_4k_2_large(pgprot_val(prot)) | _PAGE_PSE)));
737
738	return 1;
739}
740
741/**
742 * pmd_set_huge - setup kernel PMD mapping
743 *
744 * See text over pud_set_huge() above.
745 *
746 * Returns 1 on success and 0 on failure.
747 */
748int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
749{
750	u8 uniform;
751
752	mtrr_type_lookup(addr, addr + PMD_SIZE, &uniform);
753	if (!uniform) {
754		pr_warn_once("%s: Cannot satisfy [mem %#010llx-%#010llx] with a huge-page mapping due to MTRR override.\n",
755			     __func__, addr, addr + PMD_SIZE);
756		return 0;
757	}
758
759	/* Bail out if we are we on a populated non-leaf entry: */
760	if (pmd_present(*pmd) && !pmd_huge(*pmd))
761		return 0;
762
763	set_pte((pte_t *)pmd, pfn_pte(
764		(u64)addr >> PAGE_SHIFT,
765		__pgprot(protval_4k_2_large(pgprot_val(prot)) | _PAGE_PSE)));
766
767	return 1;
768}
769
770/**
771 * pud_clear_huge - clear kernel PUD mapping when it is set
772 *
773 * Returns 1 on success and 0 on failure (no PUD map is found).
774 */
775int pud_clear_huge(pud_t *pud)
776{
777	if (pud_large(*pud)) {
778		pud_clear(pud);
779		return 1;
780	}
781
782	return 0;
783}
784
785/**
786 * pmd_clear_huge - clear kernel PMD mapping when it is set
787 *
788 * Returns 1 on success and 0 on failure (no PMD map is found).
789 */
790int pmd_clear_huge(pmd_t *pmd)
791{
792	if (pmd_large(*pmd)) {
793		pmd_clear(pmd);
794		return 1;
795	}
796
797	return 0;
798}
799
800#ifdef CONFIG_X86_64
801/**
802 * pud_free_pmd_page - Clear pud entry and free pmd page.
803 * @pud: Pointer to a PUD.
804 * @addr: Virtual address associated with pud.
805 *
806 * Context: The pud range has been unmapped and TLB purged.
807 * Return: 1 if clearing the entry succeeded. 0 otherwise.
808 *
809 * NOTE: Callers must allow a single page allocation.
810 */
811int pud_free_pmd_page(pud_t *pud, unsigned long addr)
812{
813	pmd_t *pmd, *pmd_sv;
814	pte_t *pte;
815	int i;
816
817	pmd = pud_pgtable(*pud);
818	pmd_sv = (pmd_t *)__get_free_page(GFP_KERNEL);
819	if (!pmd_sv)
820		return 0;
821
822	for (i = 0; i < PTRS_PER_PMD; i++) {
823		pmd_sv[i] = pmd[i];
824		if (!pmd_none(pmd[i]))
825			pmd_clear(&pmd[i]);
826	}
827
828	pud_clear(pud);
829
830	/* INVLPG to clear all paging-structure caches */
831	flush_tlb_kernel_range(addr, addr + PAGE_SIZE-1);
832
833	for (i = 0; i < PTRS_PER_PMD; i++) {
834		if (!pmd_none(pmd_sv[i])) {
835			pte = (pte_t *)pmd_page_vaddr(pmd_sv[i]);
836			free_page((unsigned long)pte);
837		}
838	}
839
840	free_page((unsigned long)pmd_sv);
841
842	pagetable_pmd_dtor(virt_to_ptdesc(pmd));
843	free_page((unsigned long)pmd);
844
845	return 1;
846}
847
848/**
849 * pmd_free_pte_page - Clear pmd entry and free pte page.
850 * @pmd: Pointer to a PMD.
851 * @addr: Virtual address associated with pmd.
852 *
853 * Context: The pmd range has been unmapped and TLB purged.
854 * Return: 1 if clearing the entry succeeded. 0 otherwise.
855 */
856int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
857{
858	pte_t *pte;
859
860	pte = (pte_t *)pmd_page_vaddr(*pmd);
861	pmd_clear(pmd);
862
863	/* INVLPG to clear all paging-structure caches */
864	flush_tlb_kernel_range(addr, addr + PAGE_SIZE-1);
865
866	free_page((unsigned long)pte);
867
868	return 1;
869}
870
871#else /* !CONFIG_X86_64 */
872
873/*
874 * Disable free page handling on x86-PAE. This assures that ioremap()
875 * does not update sync'd pmd entries. See vmalloc_sync_one().
876 */
877int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
878{
879	return pmd_none(*pmd);
880}
881
882#endif /* CONFIG_X86_64 */
883#endif	/* CONFIG_HAVE_ARCH_HUGE_VMAP */
884
885pte_t pte_mkwrite(pte_t pte, struct vm_area_struct *vma)
886{
887	if (vma->vm_flags & VM_SHADOW_STACK)
888		return pte_mkwrite_shstk(pte);
889
890	pte = pte_mkwrite_novma(pte);
891
892	return pte_clear_saveddirty(pte);
893}
894
895pmd_t pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
896{
897	if (vma->vm_flags & VM_SHADOW_STACK)
898		return pmd_mkwrite_shstk(pmd);
899
900	pmd = pmd_mkwrite_novma(pmd);
901
902	return pmd_clear_saveddirty(pmd);
903}
904
905void arch_check_zapped_pte(struct vm_area_struct *vma, pte_t pte)
906{
907	/*
908	 * Hardware before shadow stack can (rarely) set Dirty=1
909	 * on a Write=0 PTE. So the below condition
910	 * only indicates a software bug when shadow stack is
911	 * supported by the HW. This checking is covered in
912	 * pte_shstk().
913	 */
914	VM_WARN_ON_ONCE(!(vma->vm_flags & VM_SHADOW_STACK) &&
915			pte_shstk(pte));
916}
917
918void arch_check_zapped_pmd(struct vm_area_struct *vma, pmd_t pmd)
919{
920	/* See note in arch_check_zapped_pte() */
921	VM_WARN_ON_ONCE(!(vma->vm_flags & VM_SHADOW_STACK) &&
922			pmd_shstk(pmd));
923}
924