1 files changed, 76 insertions, 82 deletions

diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 8116ac599f80..b3a7fafe8892 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -45,13 +45,6 @@ void __init arm64_hugetlb_cma_reserve(void)
 	else
 		order = CONT_PMD_SHIFT - PAGE_SHIFT;
 
-	/*
-	 * HugeTLB CMA reservation is required for gigantic
-	 * huge pages which could not be allocated via the
-	 * page allocator. Just warn if there is any change
-	 * breaking this assumption.
-	 */
-	WARN_ON(order <= MAX_PAGE_ORDER);
 	hugetlb_cma_reserve(order);
 }
 #endif /* CONFIG_CMA */
@@ -86,20 +79,6 @@ bool arch_hugetlb_migration_supported(struct hstate *h)
 }
 #endif
 
-int pmd_huge(pmd_t pmd)
-{
-	return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT);
-}
-
-int pud_huge(pud_t pud)
-{
-#ifndef __PAGETABLE_PMD_FOLDED
-	return pud_val(pud) && !(pud_val(pud) & PUD_TABLE_BIT);
-#else
-	return 0;
-#endif
-}
-
 static int find_num_contig(struct mm_struct *mm, unsigned long addr,
 			   pte_t *ptep, size_t *pgsize)
 {
@@ -121,20 +100,11 @@ static int find_num_contig(struct mm_struct *mm, unsigned long addr,
 
 static inline int num_contig_ptes(unsigned long size, size_t *pgsize)
 {
-	int contig_ptes = 0;
+	int contig_ptes = 1;
 
 	*pgsize = size;
 
 	switch (size) {
-#ifndef __PAGETABLE_PMD_FOLDED
-	case PUD_SIZE:
-		if (pud_sect_supported())
-			contig_ptes = 1;
-		break;
-#endif
-	case PMD_SIZE:
-		contig_ptes = 1;
-		break;
 	case CONT_PMD_SIZE:
 		*pgsize = PMD_SIZE;
 		contig_ptes = CONT_PMDS;
@@ -143,23 +113,25 @@ static inline int num_contig_ptes(unsigned long size, size_t *pgsize)
 		*pgsize = PAGE_SIZE;
 		contig_ptes = CONT_PTES;
 		break;
+	default:
+		WARN_ON(!__hugetlb_valid_size(size));
 	}
 
 	return contig_ptes;
 }
 
-pte_t huge_ptep_get(pte_t *ptep)
+pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
 	int ncontig, i;
 	size_t pgsize;
-	pte_t orig_pte = ptep_get(ptep);
+	pte_t orig_pte = __ptep_get(ptep);
 
 	if (!pte_present(orig_pte) || !pte_cont(orig_pte))
 		return orig_pte;
 
 	ncontig = num_contig_ptes(page_size(pte_page(orig_pte)), &pgsize);
 	for (i = 0; i < ncontig; i++, ptep++) {
-		pte_t pte = ptep_get(ptep);
+		pte_t pte = __ptep_get(ptep);
 
 		if (pte_dirty(pte))
 			orig_pte = pte_mkdirty(orig_pte);
@@ -184,24 +156,23 @@ static pte_t get_clear_contig(struct mm_struct *mm,
 			     unsigned long pgsize,
 			     unsigned long ncontig)
 {
-	pte_t orig_pte = ptep_get(ptep);
-	unsigned long i;
-
-	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) {
-		pte_t pte = ptep_get_and_clear(mm, addr, ptep);
-
-		/*
-		 * If HW_AFDBM is enabled, then the HW could turn on
-		 * the dirty or accessed bit for any page in the set,
-		 * so check them all.
-		 */
-		if (pte_dirty(pte))
-			orig_pte = pte_mkdirty(orig_pte);
-
-		if (pte_young(pte))
-			orig_pte = pte_mkyoung(orig_pte);
+	pte_t pte, tmp_pte;
+	bool present;
+
+	pte = __ptep_get_and_clear(mm, addr, ptep);
+	present = pte_present(pte);
+	while (--ncontig) {
+		ptep++;
+		addr += pgsize;
+		tmp_pte = __ptep_get_and_clear(mm, addr, ptep);
+		if (present) {
+			if (pte_dirty(tmp_pte))
+				pte = pte_mkdirty(pte);
+			if (pte_young(tmp_pte))
+				pte = pte_mkyoung(pte);
+		}
 	}
-	return orig_pte;
+	return pte;
 }
 
 static pte_t get_clear_contig_flush(struct mm_struct *mm,
@@ -236,7 +207,7 @@ static void clear_flush(struct mm_struct *mm,
 	unsigned long i, saddr = addr;
 
 	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
-		ptep_clear(mm, addr, ptep);
+		__ptep_get_and_clear(mm, addr, ptep);
 
 	flush_tlb_range(&vma, saddr, addr);
 }
@@ -254,12 +225,12 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 
 	if (!pte_present(pte)) {
 		for (i = 0; i < ncontig; i++, ptep++, addr += pgsize)
-			set_pte_at(mm, addr, ptep, pte);
+			__set_ptes(mm, addr, ptep, pte, 1);
 		return;
 	}
 
 	if (!pte_cont(pte)) {
-		set_pte_at(mm, addr, ptep, pte);
+		__set_ptes(mm, addr, ptep, pte, 1);
 		return;
 	}
 
@@ -270,7 +241,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 	clear_flush(mm, addr, ptep, pgsize, ncontig);
 
 	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
-		set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
+		__set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1);
 }
 
 pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
@@ -283,7 +254,10 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 	pte_t *ptep = NULL;
 
 	pgdp = pgd_offset(mm, addr);
-	p4dp = p4d_offset(pgdp, addr);
+	p4dp = p4d_alloc(mm, pgdp, addr);
+	if (!p4dp)
+		return NULL;
+
 	pudp = pud_alloc(mm, p4dp, addr);
 	if (!pudp)
 		return NULL;
@@ -332,7 +306,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 	if (sz != PUD_SIZE && pud_none(pud))
 		return NULL;
 	/* hugepage or swap? */
-	if (pud_huge(pud) || !pud_present(pud))
+	if (pud_leaf(pud) || !pud_present(pud))
 		return (pte_t *)pudp;
 	/* table; check the next level */
 
@@ -344,7 +318,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 	if (!(sz == PMD_SIZE || sz == CONT_PMD_SIZE) &&
 	    pmd_none(pmd))
 		return NULL;
-	if (pmd_huge(pmd) || !pmd_present(pmd))
+	if (pmd_leaf(pmd) || !pmd_present(pmd))
 		return (pte_t *)pmdp;
 
 	if (sz == CONT_PTE_SIZE)
@@ -379,14 +353,25 @@ pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags)
 {
 	size_t pagesize = 1UL << shift;
 
-	entry = pte_mkhuge(entry);
-	if (pagesize == CONT_PTE_SIZE) {
-		entry = pte_mkcont(entry);
-	} else if (pagesize == CONT_PMD_SIZE) {
+	switch (pagesize) {
+#ifndef __PAGETABLE_PMD_FOLDED
+	case PUD_SIZE:
+		entry = pud_pte(pud_mkhuge(pte_pud(entry)));
+		break;
+#endif
+	case CONT_PMD_SIZE:
 		entry = pmd_pte(pmd_mkcont(pte_pmd(entry)));
-	} else if (pagesize != PUD_SIZE && pagesize != PMD_SIZE) {
+		fallthrough;
+	case PMD_SIZE:
+		entry = pmd_pte(pmd_mkhuge(pte_pmd(entry)));
+		break;
+	case CONT_PTE_SIZE:
+		entry = pte_mkcont(entry);
+		break;
+	default:
 		pr_warn("%s: unrecognized huge page size 0x%lx\n",
 			__func__, pagesize);
+		break;
 	}
 	return entry;
 }
@@ -400,21 +385,16 @@ void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 	ncontig = num_contig_ptes(sz, &pgsize);
 
 	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
-		pte_clear(mm, addr, ptep);
+		__pte_clear(mm, addr, ptep);
 }
 
-pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-			      unsigned long addr, pte_t *ptep)
+pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, unsigned long sz)
 {
 	int ncontig;
 	size_t pgsize;
-	pte_t orig_pte = ptep_get(ptep);
-
-	if (!pte_cont(orig_pte))
-		return ptep_get_and_clear(mm, addr, ptep);
-
-	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
 
+	ncontig = num_contig_ptes(sz, &pgsize);
 	return get_clear_contig(mm, addr, ptep, pgsize, ncontig);
 }
 
@@ -431,11 +411,11 @@ static int __cont_access_flags_changed(pte_t *ptep, pte_t pte, int ncontig)
 {
 	int i;
 
-	if (pte_write(pte) != pte_write(ptep_get(ptep)))
+	if (pte_write(pte) != pte_write(__ptep_get(ptep)))
 		return 1;
 
 	for (i = 0; i < ncontig; i++) {
-		pte_t orig_pte = ptep_get(ptep + i);
+		pte_t orig_pte = __ptep_get(ptep + i);
 
 		if (pte_dirty(pte) != pte_dirty(orig_pte))
 			return 1;
@@ -459,7 +439,7 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 	pte_t orig_pte;
 
 	if (!pte_cont(pte))
-		return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
+		return __ptep_set_access_flags(vma, addr, ptep, pte, dirty);
 
 	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
 	dpfn = pgsize >> PAGE_SHIFT;
@@ -478,7 +458,7 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 
 	hugeprot = pte_pgprot(pte);
 	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
-		set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
+		__set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1);
 
 	return 1;
 }
@@ -492,8 +472,8 @@ void huge_ptep_set_wrprotect(struct mm_struct *mm,
 	size_t pgsize;
 	pte_t pte;
 
-	if (!pte_cont(READ_ONCE(*ptep))) {
-		ptep_set_wrprotect(mm, addr, ptep);
+	if (!pte_cont(__ptep_get(ptep))) {
+		__ptep_set_wrprotect(mm, addr, ptep);
 		return;
 	}
 
@@ -507,7 +487,7 @@ void huge_ptep_set_wrprotect(struct mm_struct *mm,
 	pfn = pte_pfn(pte);
 
 	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
-		set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
+		__set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1);
 }
 
 pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
@@ -517,7 +497,7 @@ pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 	size_t pgsize;
 	int ncontig;
 
-	if (!pte_cont(READ_ONCE(*ptep)))
+	if (!pte_cont(__ptep_get(ptep)))
 		return ptep_clear_flush(vma, addr, ptep);
 
 	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
@@ -526,6 +506,18 @@ pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 
 static int __init hugetlbpage_init(void)
 {
+	/*
+	 * HugeTLB pages are supported on maximum four page table
+	 * levels (PUD, CONT PMD, PMD, CONT PTE) for a given base
+	 * page size, corresponding to hugetlb_add_hstate() calls
+	 * here.
+	 *
+	 * HUGE_MAX_HSTATE should at least match maximum supported
+	 * HugeTLB page sizes on the platform. Any new addition to
+	 * supported HugeTLB page sizes will also require changing
+	 * HUGE_MAX_HSTATE as well.
+	 */
+	BUILD_BUG_ON(HUGE_MAX_HSTATE < 4);
 	if (pud_sect_supported())
 		hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
 
@@ -544,16 +536,18 @@ bool __init arch_hugetlb_valid_size(unsigned long size)
 
 pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
 {
+	unsigned long psize = huge_page_size(hstate_vma(vma));
+
 	if (alternative_has_cap_unlikely(ARM64_WORKAROUND_2645198)) {
 		/*
 		 * Break-before-make (BBM) is required for all user space mappings
 		 * when the permission changes from executable to non-executable
 		 * in cases where cpu is affected with errata #2645198.
 		 */
-		if (pte_user_exec(READ_ONCE(*ptep)))
+		if (pte_user_exec(__ptep_get(ptep)))
 			return huge_ptep_clear_flush(vma, addr, ptep);
 	}
-	return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, psize);
 }
 
 void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep,