1 files changed, 230 insertions, 84 deletions

diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 656e0ece2289..6cb0fa92a651 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -41,6 +41,16 @@ int pud_huge(pud_t pud)
 #endif
 }
 
+/*
+ * Select all bits except the pfn
+ */
+static inline pgprot_t pte_pgprot(pte_t pte)
+{
+	unsigned long pfn = pte_pfn(pte);
+
+	return __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ pte_val(pte));
+}
+
 static int find_num_contig(struct mm_struct *mm, unsigned long addr,
 			   pte_t *ptep, size_t *pgsize)
 {
@@ -58,15 +68,107 @@ static int find_num_contig(struct mm_struct *mm, unsigned long addr,
 	return CONT_PTES;
 }
 
+static inline int num_contig_ptes(unsigned long size, size_t *pgsize)
+{
+	int contig_ptes = 0;
+
+	*pgsize = size;
+
+	switch (size) {
+#ifdef CONFIG_ARM64_4K_PAGES
+	case PUD_SIZE:
+#endif
+	case PMD_SIZE:
+		contig_ptes = 1;
+		break;
+	case CONT_PMD_SIZE:
+		*pgsize = PMD_SIZE;
+		contig_ptes = CONT_PMDS;
+		break;
+	case CONT_PTE_SIZE:
+		*pgsize = PAGE_SIZE;
+		contig_ptes = CONT_PTES;
+		break;
+	}
+
+	return contig_ptes;
+}
+
+/*
+ * Changing some bits of contiguous entries requires us to follow a
+ * Break-Before-Make approach, breaking the whole contiguous set
+ * before we can change any entries. See ARM DDI 0487A.k_iss10775,
+ * "Misprogramming of the Contiguous bit", page D4-1762.
+ *
+ * This helper performs the break step.
+ */
+static pte_t get_clear_flush(struct mm_struct *mm,
+			     unsigned long addr,
+			     pte_t *ptep,
+			     unsigned long pgsize,
+			     unsigned long ncontig)
+{
+	struct vm_area_struct vma = { .vm_mm = mm };
+	pte_t orig_pte = huge_ptep_get(ptep);
+	bool valid = pte_valid(orig_pte);
+	unsigned long i, saddr = addr;
+
+	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 bit for any page in the set, so check
+		 * them all.  All hugetlb entries are already young.
+		 */
+		if (pte_dirty(pte))
+			orig_pte = pte_mkdirty(orig_pte);
+	}
+
+	if (valid)
+		flush_tlb_range(&vma, saddr, addr);
+	return orig_pte;
+}
+
+/*
+ * Changing some bits of contiguous entries requires us to follow a
+ * Break-Before-Make approach, breaking the whole contiguous set
+ * before we can change any entries. See ARM DDI 0487A.k_iss10775,
+ * "Misprogramming of the Contiguous bit", page D4-1762.
+ *
+ * This helper performs the break step for use cases where the
+ * original pte is not needed.
+ */
+static void clear_flush(struct mm_struct *mm,
+			     unsigned long addr,
+			     pte_t *ptep,
+			     unsigned long pgsize,
+			     unsigned long ncontig)
+{
+	struct vm_area_struct vma = { .vm_mm = mm };
+	unsigned long i, saddr = addr;
+
+	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
+		pte_clear(mm, addr, ptep);
+
+	flush_tlb_range(&vma, saddr, addr);
+}
+
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 			    pte_t *ptep, pte_t pte)
 {
 	size_t pgsize;
 	int i;
 	int ncontig;
-	unsigned long pfn;
+	unsigned long pfn, dpfn;
 	pgprot_t hugeprot;
 
+	/*
+	 * Code needs to be expanded to handle huge swap and migration
+	 * entries. Needed for HUGETLB and MEMORY_FAILURE.
+	 */
+	WARN_ON(!pte_present(pte));
+
 	if (!pte_cont(pte)) {
 		set_pte_at(mm, addr, ptep, pte);
 		return;
@@ -74,17 +176,30 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 
 	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
 	pfn = pte_pfn(pte);
-	hugeprot = __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ pte_val(pte));
-	for (i = 0; i < ncontig; i++) {
+	dpfn = pgsize >> PAGE_SHIFT;
+	hugeprot = pte_pgprot(pte);
+
+	clear_flush(mm, addr, ptep, pgsize, ncontig);
+
+	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) {
 		pr_debug("%s: set pte %p to 0x%llx\n", __func__, ptep,
 			 pte_val(pfn_pte(pfn, hugeprot)));
 		set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
-		ptep++;
-		pfn += pgsize >> PAGE_SHIFT;
-		addr += pgsize;
 	}
 }
 
+void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
+			  pte_t *ptep, pte_t pte, unsigned long sz)
+{
+	int i, ncontig;
+	size_t pgsize;
+
+	ncontig = num_contig_ptes(sz, &pgsize);
+
+	for (i = 0; i < ncontig; i++, ptep++)
+		set_pte(ptep, pte);
+}
+
 pte_t *huge_pte_alloc(struct mm_struct *mm,
 		      unsigned long addr, unsigned long sz)
 {
@@ -144,19 +259,28 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 		return NULL;
 
 	pud = pud_offset(pgd, addr);
-	if (pud_none(*pud))
+	if (sz != PUD_SIZE && pud_none(*pud))
 		return NULL;
-	/* swap or huge page */
-	if (!pud_present(*pud) || pud_huge(*pud))
+	/* hugepage or swap? */
+	if (pud_huge(*pud) || !pud_present(*pud))
 		return (pte_t *)pud;
 	/* table; check the next level */
 
+	if (sz == CONT_PMD_SIZE)
+		addr &= CONT_PMD_MASK;
+
 	pmd = pmd_offset(pud, addr);
-	if (pmd_none(*pmd))
+	if (!(sz == PMD_SIZE || sz == CONT_PMD_SIZE) &&
+	    pmd_none(*pmd))
 		return NULL;
-	if (!pmd_present(*pmd) || pmd_huge(*pmd))
+	if (pmd_huge(*pmd) || !pmd_present(*pmd))
 		return (pte_t *)pmd;
 
+	if (sz == CONT_PTE_SIZE) {
+		pte_t *pte = pte_offset_kernel(pmd, (addr & CONT_PTE_MASK));
+		return pte;
+	}
+
 	return NULL;
 }
 
@@ -176,111 +300,133 @@ pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
 	return entry;
 }
 
+void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
+		    pte_t *ptep, unsigned long sz)
+{
+	int i, ncontig;
+	size_t pgsize;
+
+	ncontig = num_contig_ptes(sz, &pgsize);
+
+	for (i = 0; i < ncontig; i++, addr += pgsize, 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 pte;
+	int ncontig;
+	size_t pgsize;
+	pte_t orig_pte = huge_ptep_get(ptep);
 
-	if (pte_cont(*ptep)) {
-		int ncontig, i;
-		size_t pgsize;
-		bool is_dirty = false;
-
-		ncontig = find_num_contig(mm, addr, ptep, &pgsize);
-		/* save the 1st pte to return */
-		pte = ptep_get_and_clear(mm, addr, ptep);
-		for (i = 1, addr += pgsize; i < ncontig; ++i, addr += pgsize) {
-			/*
-			 * If HW_AFDBM is enabled, then the HW could
-			 * turn on the dirty bit for any of the page
-			 * in the set, so check them all.
-			 */
-			++ptep;
-			if (pte_dirty(ptep_get_and_clear(mm, addr, ptep)))
-				is_dirty = true;
-		}
-		if (is_dirty)
-			return pte_mkdirty(pte);
-		else
-			return pte;
-	} else {
+	if (!pte_cont(orig_pte))
 		return ptep_get_and_clear(mm, addr, ptep);
-	}
+
+	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
+
+	return get_clear_flush(mm, addr, ptep, pgsize, ncontig);
 }
 
 int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 			       unsigned long addr, pte_t *ptep,
 			       pte_t pte, int dirty)
 {
-	if (pte_cont(pte)) {
-		int ncontig, i, changed = 0;
-		size_t pgsize = 0;
-		unsigned long pfn = pte_pfn(pte);
-		/* Select all bits except the pfn */
-		pgprot_t hugeprot =
-			__pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^
-				 pte_val(pte));
-
-		pfn = pte_pfn(pte);
-		ncontig = find_num_contig(vma->vm_mm, addr, ptep,
-					  &pgsize);
-		for (i = 0; i < ncontig; ++i, ++ptep, addr += pgsize) {
-			changed |= ptep_set_access_flags(vma, addr, ptep,
-							pfn_pte(pfn,
-								hugeprot),
-							dirty);
-			pfn += pgsize >> PAGE_SHIFT;
-		}
-		return changed;
-	} else {
+	int ncontig, i, changed = 0;
+	size_t pgsize = 0;
+	unsigned long pfn = pte_pfn(pte), dpfn;
+	pgprot_t hugeprot;
+	pte_t orig_pte;
+
+	if (!pte_cont(pte))
 		return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
-	}
+
+	ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize);
+	dpfn = pgsize >> PAGE_SHIFT;
+
+	orig_pte = get_clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig);
+	if (!pte_same(orig_pte, pte))
+		changed = 1;
+
+	/* Make sure we don't lose the dirty state */
+	if (pte_dirty(orig_pte))
+		pte = pte_mkdirty(pte);
+
+	hugeprot = pte_pgprot(pte);
+	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
+		set_pte_at(vma->vm_mm, addr, ptep, pfn_pte(pfn, hugeprot));
+
+	return changed;
 }
 
 void huge_ptep_set_wrprotect(struct mm_struct *mm,
 			     unsigned long addr, pte_t *ptep)
 {
-	if (pte_cont(*ptep)) {
-		int ncontig, i;
-		size_t pgsize = 0;
-
-		ncontig = find_num_contig(mm, addr, ptep, &pgsize);
-		for (i = 0; i < ncontig; ++i, ++ptep, addr += pgsize)
-			ptep_set_wrprotect(mm, addr, ptep);
-	} else {
+	unsigned long pfn, dpfn;
+	pgprot_t hugeprot;
+	int ncontig, i;
+	size_t pgsize;
+	pte_t pte;
+
+	if (!pte_cont(*ptep)) {
 		ptep_set_wrprotect(mm, addr, ptep);
+		return;
 	}
+
+	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
+	dpfn = pgsize >> PAGE_SHIFT;
+
+	pte = get_clear_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_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
 }
 
 void huge_ptep_clear_flush(struct vm_area_struct *vma,
 			   unsigned long addr, pte_t *ptep)
 {
-	if (pte_cont(*ptep)) {
-		int ncontig, i;
-		size_t pgsize = 0;
-
-		ncontig = find_num_contig(vma->vm_mm, addr, ptep,
-					  &pgsize);
-		for (i = 0; i < ncontig; ++i, ++ptep, addr += pgsize)
-			ptep_clear_flush(vma, addr, ptep);
-	} else {
+	size_t pgsize;
+	int ncontig;
+
+	if (!pte_cont(*ptep)) {
 		ptep_clear_flush(vma, addr, ptep);
+		return;
 	}
+
+	ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize);
+	clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig);
 }
 
 static __init int setup_hugepagesz(char *opt)
 {
 	unsigned long ps = memparse(opt, &opt);
 
-	if (ps == PMD_SIZE) {
-		hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT);
-	} else if (ps == PUD_SIZE) {
-		hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
-	} else {
-		hugetlb_bad_size();
-		pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10);
-		return 0;
+	switch (ps) {
+#ifdef CONFIG_ARM64_4K_PAGES
+	case PUD_SIZE:
+#endif
+	case PMD_SIZE * CONT_PMDS:
+	case PMD_SIZE:
+	case PAGE_SIZE * CONT_PTES:
+		hugetlb_add_hstate(ilog2(ps) - PAGE_SHIFT);
+		return 1;
 	}
-	return 1;
+
+	hugetlb_bad_size();
+	pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10);
+	return 0;
 }
 __setup("hugepagesz=", setup_hugepagesz);
+
+#ifdef CONFIG_ARM64_64K_PAGES
+static __init int add_default_hugepagesz(void)
+{
+	if (size_to_hstate(CONT_PTES * PAGE_SIZE) == NULL)
+		hugetlb_add_hstate(CONT_PTE_SHIFT);
+	return 0;
+}
+arch_initcall(add_default_hugepagesz);
+#endif