1 files changed, 82 insertions, 87 deletions

diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 5f1e2103888b..0c8737f4f2ce 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;
@@ -136,7 +129,7 @@ pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 	if (!pte_present(orig_pte) || !pte_cont(orig_pte))
 		return orig_pte;
 
-	ncontig = num_contig_ptes(page_size(pte_page(orig_pte)), &pgsize);
+	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
 	for (i = 0; i < ncontig; i++, ptep++) {
 		pte_t pte = __ptep_get(ptep);
 
@@ -163,24 +156,22 @@ 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_anysz(mm, ptep, pgsize);
+	present = pte_present(pte);
+	while (--ncontig) {
+		ptep++;
+		tmp_pte = __ptep_get_and_clear_anysz(mm, ptep, pgsize);
+		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,
@@ -191,8 +182,9 @@ static pte_t get_clear_contig_flush(struct mm_struct *mm,
 {
 	pte_t orig_pte = get_clear_contig(mm, addr, ptep, pgsize, ncontig);
 	struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0);
+	unsigned long end = addr + (pgsize * ncontig);
 
-	flush_tlb_range(&vma, addr, addr + (pgsize * ncontig));
+	__flush_hugetlb_tlb_range(&vma, addr, end, pgsize, true);
 	return orig_pte;
 }
 
@@ -215,9 +207,12 @@ static void clear_flush(struct mm_struct *mm,
 	unsigned long i, saddr = addr;
 
 	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
-		__ptep_get_and_clear(mm, addr, ptep);
+		__ptep_get_and_clear_anysz(mm, ptep, pgsize);
 
-	flush_tlb_range(&vma, saddr, addr);
+	if (mm == &init_mm)
+		flush_tlb_kernel_range(saddr, addr);
+	else
+		__flush_hugetlb_tlb_range(&vma, saddr, addr, pgsize, true);
 }
 
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
@@ -226,30 +221,20 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 	size_t pgsize;
 	int i;
 	int ncontig;
-	unsigned long pfn, dpfn;
-	pgprot_t hugeprot;
 
 	ncontig = num_contig_ptes(sz, &pgsize);
 
 	if (!pte_present(pte)) {
 		for (i = 0; i < ncontig; i++, ptep++, addr += pgsize)
-			__set_ptes(mm, addr, ptep, pte, 1);
+			__set_ptes_anysz(mm, ptep, pte, 1, pgsize);
 		return;
 	}
 
-	if (!pte_cont(pte)) {
-		__set_ptes(mm, addr, ptep, pte, 1);
-		return;
-	}
-
-	pfn = pte_pfn(pte);
-	dpfn = pgsize >> PAGE_SHIFT;
-	hugeprot = pte_pgprot(pte);
+	/* Only need to "break" if transitioning valid -> valid. */
+	if (pte_cont(pte) && pte_valid(__ptep_get(ptep)))
+		clear_flush(mm, addr, ptep, pgsize, ncontig);
 
-	clear_flush(mm, addr, ptep, pgsize, ncontig);
-
-	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
-		__set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1);
+	__set_ptes_anysz(mm, ptep, pte, ncontig, pgsize);
 }
 
 pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
@@ -342,7 +327,9 @@ unsigned long hugetlb_mask_last_page(struct hstate *h)
 	switch (hp_size) {
 #ifndef __PAGETABLE_PMD_FOLDED
 	case PUD_SIZE:
-		return PGDIR_SIZE - PUD_SIZE;
+		if (pud_sect_supported())
+			return PGDIR_SIZE - PUD_SIZE;
+		break;
 #endif
 	case CONT_PMD_SIZE:
 		return PUD_SIZE - CONT_PMD_SIZE;
@@ -361,15 +348,24 @@ 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) {
-		entry = pmd_pte(pmd_mkcont(pte_pmd(entry)));
-	} else if (pagesize != PUD_SIZE && pagesize != PMD_SIZE) {
-		pr_warn("%s: unrecognized huge page size 0x%lx\n",
-			__func__, pagesize);
+	switch (pagesize) {
+#ifndef __PAGETABLE_PMD_FOLDED
+	case PUD_SIZE:
+		if (pud_sect_supported())
+			return pud_pte(pud_mkhuge(pte_pud(entry)));
+		break;
+#endif
+	case CONT_PMD_SIZE:
+		return pmd_pte(pmd_mkhuge(pmd_mkcont(pte_pmd(entry))));
+	case PMD_SIZE:
+		return pmd_pte(pmd_mkhuge(pte_pmd(entry)));
+	case CONT_PTE_SIZE:
+		return pte_mkcont(entry);
+	default:
+		break;
 	}
+	pr_warn("%s: unrecognized huge page size 0x%lx\n",
+		__func__, pagesize);
 	return entry;
 }
 
@@ -385,18 +381,13 @@ 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);
 }
 
@@ -433,23 +424,23 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 			       unsigned long addr, pte_t *ptep,
 			       pte_t pte, int dirty)
 {
-	int ncontig, i;
+	int ncontig;
 	size_t pgsize = 0;
-	unsigned long pfn = pte_pfn(pte), dpfn;
 	struct mm_struct *mm = vma->vm_mm;
-	pgprot_t hugeprot;
 	pte_t orig_pte;
 
+	VM_WARN_ON(!pte_present(pte));
+
 	if (!pte_cont(pte))
 		return __ptep_set_access_flags(vma, addr, ptep, pte, dirty);
 
-	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
-	dpfn = pgsize >> PAGE_SHIFT;
+	ncontig = num_contig_ptes(huge_page_size(hstate_vma(vma)), &pgsize);
 
 	if (!__cont_access_flags_changed(ptep, pte, ncontig))
 		return 0;
 
 	orig_pte = get_clear_contig_flush(mm, addr, ptep, pgsize, ncontig);
+	VM_WARN_ON(!pte_present(orig_pte));
 
 	/* Make sure we don't lose the dirty or young state */
 	if (pte_dirty(orig_pte))
@@ -458,38 +449,31 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 	if (pte_young(orig_pte))
 		pte = pte_mkyoung(pte);
 
-	hugeprot = pte_pgprot(pte);
-	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
-		__set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1);
-
+	__set_ptes_anysz(mm, ptep, pte, ncontig, pgsize);
 	return 1;
 }
 
 void huge_ptep_set_wrprotect(struct mm_struct *mm,
 			     unsigned long addr, pte_t *ptep)
 {
-	unsigned long pfn, dpfn;
-	pgprot_t hugeprot;
-	int ncontig, i;
+	int ncontig;
 	size_t pgsize;
 	pte_t pte;
 
-	if (!pte_cont(__ptep_get(ptep))) {
+	pte = __ptep_get(ptep);
+	VM_WARN_ON(!pte_present(pte));
+
+	if (!pte_cont(pte)) {
 		__ptep_set_wrprotect(mm, addr, ptep);
 		return;
 	}
 
 	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
-	dpfn = pgsize >> PAGE_SHIFT;
 
 	pte = get_clear_contig_flush(mm, addr, ptep, pgsize, ncontig);
 	pte = pte_wrprotect(pte);
 
-	hugeprot = pte_pgprot(pte);
-	pfn = pte_pfn(pte);
-
-	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
-		__set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1);
+	__set_ptes_anysz(mm, ptep, pte, ncontig, pgsize);
 }
 
 pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
@@ -499,15 +483,24 @@ pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 	size_t pgsize;
 	int ncontig;
 
-	if (!pte_cont(__ptep_get(ptep)))
-		return ptep_clear_flush(vma, addr, ptep);
-
-	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
+	ncontig = num_contig_ptes(huge_page_size(hstate_vma(vma)), &pgsize);
 	return get_clear_contig_flush(mm, addr, ptep, pgsize, ncontig);
 }
 
 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);
 
@@ -526,6 +519,8 @@ 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
@@ -535,7 +530,7 @@ 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,