arm64/mm: Refactor __set_ptes() and __ptep_get_and_clear()

Refactor __set_ptes(), set_pmd_at() and set_pud_at() so that they are
all a thin wrapper around a new common __set_ptes_anysz(), which takes
pgsize parameter. Additionally, refactor __ptep_get_and_clear() and
pmdp_huge_get_and_clear() to use a new common
__ptep_get_and_clear_anysz() which also takes a pgsize parameter.

These changes will permit the huge_pte API to efficiently batch-set
pgtable entries and take advantage of the future barrier optimizations.
Additionally since the new *_anysz() helpers call the correct
page_table_check_*_set() API based on pgsize, this means that huge_ptes
will be able to get proper coverage. Currently the huge_pte API always
uses the pte API which assumes an entry only covers a single page.

Reviewed-by: Catalin Marinas <[email protected]>
Signed-off-by: Ryan Roberts <[email protected]>
Reviewed-by: Anshuman Khandual <[email protected]>
Tested-by: Luiz Capitulino <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Will Deacon <[email protected]>

Author: Ryan Roberts

arch/arm64/include/asm/pgtable.h

@@ -423,23 +423,6 @@ static inline pte_t pte_advance_pfn(pte_t pte, unsigned long nr)
 	return pfn_pte(pte_pfn(pte) + nr, pte_pgprot(pte));
 }
 
-static inline void __set_ptes(struct mm_struct *mm,
-			      unsigned long __always_unused addr,
-			      pte_t *ptep, pte_t pte, unsigned int nr)
-{
-	page_table_check_ptes_set(mm, ptep, pte, nr);
-	__sync_cache_and_tags(pte, nr);
-
-	for (;;) {
-		__check_safe_pte_update(mm, ptep, pte);
-		__set_pte(ptep, pte);
-		if (--nr == 0)
-			break;
-		ptep++;
-		pte = pte_advance_pfn(pte, 1);
-	}
-}
-
 /*
  * Hugetlb definitions.
  */
@@ -649,30 +632,62 @@ static inline pgprot_t pud_pgprot(pud_t pud)
 	return __pgprot(pud_val(pfn_pud(pfn, __pgprot(0))) ^ pud_val(pud));
 }
 
-static inline void __set_pte_at(struct mm_struct *mm,
-				unsigned long __always_unused addr,
-				pte_t *ptep, pte_t pte, unsigned int nr)
+static inline void __set_ptes_anysz(struct mm_struct *mm, pte_t *ptep,
+				    pte_t pte, unsigned int nr,
+				    unsigned long pgsize)
 {
-	__sync_cache_and_tags(pte, nr);
-	__check_safe_pte_update(mm, ptep, pte);
-	__set_pte(ptep, pte);
+	unsigned long stride = pgsize >> PAGE_SHIFT;
+
+	switch (pgsize) {
+	case PAGE_SIZE:
+		page_table_check_ptes_set(mm, ptep, pte, nr);
+		break;
+	case PMD_SIZE:
+		page_table_check_pmds_set(mm, (pmd_t *)ptep, pte_pmd(pte), nr);
+		break;
+#ifndef __PAGETABLE_PMD_FOLDED
+	case PUD_SIZE:
+		page_table_check_puds_set(mm, (pud_t *)ptep, pte_pud(pte), nr);
+		break;
+#endif
+	default:
+		VM_WARN_ON(1);
+	}
+
+	__sync_cache_and_tags(pte, nr * stride);
+
+	for (;;) {
+		__check_safe_pte_update(mm, ptep, pte);
+		__set_pte(ptep, pte);
+		if (--nr == 0)
+			break;
+		ptep++;
+		pte = pte_advance_pfn(pte, stride);
+	}
+}
+
+static inline void __set_ptes(struct mm_struct *mm,
+			      unsigned long __always_unused addr,
+			      pte_t *ptep, pte_t pte, unsigned int nr)
+{
+	__set_ptes_anysz(mm, ptep, pte, nr, PAGE_SIZE);
 }
 
-static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
-			      pmd_t *pmdp, pmd_t pmd)
+static inline void __set_pmds(struct mm_struct *mm,
+			      unsigned long __always_unused addr,
+			      pmd_t *pmdp, pmd_t pmd, unsigned int nr)
 {
-	page_table_check_pmd_set(mm, pmdp, pmd);
-	return __set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd),
-						PMD_SIZE >> PAGE_SHIFT);
+	__set_ptes_anysz(mm, (pte_t *)pmdp, pmd_pte(pmd), nr, PMD_SIZE);
 }
+#define set_pmd_at(mm, addr, pmdp, pmd) __set_pmds(mm, addr, pmdp, pmd, 1)
 
-static inline void set_pud_at(struct mm_struct *mm, unsigned long addr,
-			      pud_t *pudp, pud_t pud)
+static inline void __set_puds(struct mm_struct *mm,
+			      unsigned long __always_unused addr,
+			      pud_t *pudp, pud_t pud, unsigned int nr)
 {
-	page_table_check_pud_set(mm, pudp, pud);
-	return __set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud),
-						PUD_SIZE >> PAGE_SHIFT);
+	__set_ptes_anysz(mm, (pte_t *)pudp, pud_pte(pud), nr, PUD_SIZE);
 }
+#define set_pud_at(mm, addr, pudp, pud) __set_puds(mm, addr, pudp, pud, 1)
 
 #define __p4d_to_phys(p4d)	__pte_to_phys(p4d_pte(p4d))
 #define __phys_to_p4d_val(phys)	__phys_to_pte_val(phys)
@@ -1301,16 +1316,37 @@ static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG */
 
-static inline pte_t __ptep_get_and_clear(struct mm_struct *mm,
-				       unsigned long address, pte_t *ptep)
+static inline pte_t __ptep_get_and_clear_anysz(struct mm_struct *mm,
+					       pte_t *ptep,
+					       unsigned long pgsize)
 {
 	pte_t pte = __pte(xchg_relaxed(&pte_val(*ptep), 0));
 
-	page_table_check_pte_clear(mm, pte);
+	switch (pgsize) {
+	case PAGE_SIZE:
+		page_table_check_pte_clear(mm, pte);
+		break;
+	case PMD_SIZE:
+		page_table_check_pmd_clear(mm, pte_pmd(pte));
+		break;
+#ifndef __PAGETABLE_PMD_FOLDED
+	case PUD_SIZE:
+		page_table_check_pud_clear(mm, pte_pud(pte));
+		break;
+#endif
+	default:
+		VM_WARN_ON(1);
+	}
 
 	return pte;
 }
 
+static inline pte_t __ptep_get_and_clear(struct mm_struct *mm,
+				       unsigned long address, pte_t *ptep)
+{
+	return __ptep_get_and_clear_anysz(mm, ptep, PAGE_SIZE);
+}
+
 static inline void __clear_full_ptes(struct mm_struct *mm, unsigned long addr,
 				pte_t *ptep, unsigned int nr, int full)
 {
@@ -1347,11 +1383,7 @@ static inline pte_t __get_and_clear_full_ptes(struct mm_struct *mm,
 static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
 					    unsigned long address, pmd_t *pmdp)
 {
-	pmd_t pmd = __pmd(xchg_relaxed(&pmd_val(*pmdp), 0));
-
-	page_table_check_pmd_clear(mm, pmd);
-
-	return pmd;
+	return pte_pmd(__ptep_get_and_clear_anysz(mm, (pte_t *)pmdp, PMD_SIZE));
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */