3 files changed, 33 insertions, 42 deletions

diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 98a2a0e64e25..b3a7fafe8892 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -100,20 +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;
@@ -122,6 +113,8 @@ 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;
@@ -163,24 +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,
@@ -396,18 +388,13 @@ void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 		__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);
 }
 
@@ -549,6 +536,8 @@ 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
@@ -558,7 +547,7 @@ pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr
 		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,
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 9c0b8d9558fc..ccdef53872a0 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -279,12 +279,7 @@ void __init arm64_memblock_init(void)
 
 	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
 		extern u16 memstart_offset_seed;
-
-		/*
-		 * Use the sanitised version of id_aa64mmfr0_el1 so that linear
-		 * map randomization can be enabled by shrinking the IPA space.
-		 */
-		u64 mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
+		u64 mmfr0 = read_cpuid(ID_AA64MMFR0_EL1);
 		int parange = cpuid_feature_extract_unsigned_field(
 					mmfr0, ID_AA64MMFR0_EL1_PARANGE_SHIFT);
 		s64 range = linear_region_size -
diff --git a/arch/arm64/mm/trans_pgd.c b/arch/arm64/mm/trans_pgd.c
index 19c67ed1a21f..18543b603c77 100644
--- a/arch/arm64/mm/trans_pgd.c
+++ b/arch/arm64/mm/trans_pgd.c
@@ -162,6 +162,13 @@ static int copy_p4d(struct trans_pgd_info *info, pgd_t *dst_pgdp,
 	unsigned long next;
 	unsigned long addr = start;
 
+	if (pgd_none(READ_ONCE(*dst_pgdp))) {
+		dst_p4dp = trans_alloc(info);
+		if (!dst_p4dp)
+			return -ENOMEM;
+		pgd_populate(NULL, dst_pgdp, dst_p4dp);
+	}
+
 	dst_p4dp = p4d_offset(dst_pgdp, start);
 	src_p4dp = p4d_offset(src_pgdp, start);
 	do {