1 files changed, 99 insertions, 37 deletions

diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index c4ba047a82d2..edf6625ce965 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -33,6 +33,7 @@
 #include <linux/mmdebug.h>
 #include <linux/mm_types.h>
 #include <linux/sched.h>
+#include <linux/page_table_check.h>
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
@@ -44,6 +45,12 @@
 	__flush_tlb_range(vma, addr, end, PUD_SIZE, false, 1)
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
+static inline bool arch_thp_swp_supported(void)
+{
+	return !system_supports_mte();
+}
+#define arch_thp_swp_supported arch_thp_swp_supported
+
 /*
  * Outside of a few very special situations (e.g. hibernation), we always
  * use broadcast TLB invalidation instructions, therefore a spurious page
@@ -96,6 +103,7 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys)
 #define pte_young(pte)		(!!(pte_val(pte) & PTE_AF))
 #define pte_special(pte)	(!!(pte_val(pte) & PTE_SPECIAL))
 #define pte_write(pte)		(!!(pte_val(pte) & PTE_WRITE))
+#define pte_user(pte)		(!!(pte_val(pte) & PTE_USER))
 #define pte_user_exec(pte)	(!(pte_val(pte) & PTE_UXN))
 #define pte_cont(pte)		(!!(pte_val(pte) & PTE_CONT))
 #define pte_devmap(pte)		(!!(pte_val(pte) & PTE_DEVMAP))
@@ -312,8 +320,8 @@ static inline void __check_racy_pte_update(struct mm_struct *mm, pte_t *ptep,
 		     __func__, pte_val(old_pte), pte_val(pte));
 }
 
-static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep, pte_t pte)
+static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
+				pte_t *ptep, pte_t pte)
 {
 	if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte))
 		__sync_icache_dcache(pte);
@@ -343,6 +351,13 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 	set_pte(ptep, pte);
 }
 
+static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, pte_t pte)
+{
+	page_table_check_pte_set(mm, addr, ptep, pte);
+	return __set_pte_at(mm, addr, ptep, pte);
+}
+
 /*
  * Huge pte definitions.
  */
@@ -402,6 +417,32 @@ static inline pgprot_t mk_pmd_sect_prot(pgprot_t prot)
 	return __pgprot((pgprot_val(prot) & ~PMD_TABLE_BIT) | PMD_TYPE_SECT);
 }
 
+#define __HAVE_ARCH_PTE_SWP_EXCLUSIVE
+static inline pte_t pte_swp_mkexclusive(pte_t pte)
+{
+	return set_pte_bit(pte, __pgprot(PTE_SWP_EXCLUSIVE));
+}
+
+static inline int pte_swp_exclusive(pte_t pte)
+{
+	return pte_val(pte) & PTE_SWP_EXCLUSIVE;
+}
+
+static inline pte_t pte_swp_clear_exclusive(pte_t pte)
+{
+	return clear_pte_bit(pte, __pgprot(PTE_SWP_EXCLUSIVE));
+}
+
+/*
+ * 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));
+}
+
 #ifdef CONFIG_NUMA_BALANCING
 /*
  * See the comment in include/linux/pgtable.h
@@ -438,6 +479,8 @@ static inline int pmd_trans_huge(pmd_t pmd)
 #define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
 #define pmd_young(pmd)		pte_young(pmd_pte(pmd))
 #define pmd_valid(pmd)		pte_valid(pmd_pte(pmd))
+#define pmd_user(pmd)		pte_user(pmd_pte(pmd))
+#define pmd_user_exec(pmd)	pte_user_exec(pmd_pte(pmd))
 #define pmd_cont(pmd)		pte_cont(pmd_pte(pmd))
 #define pmd_wrprotect(pmd)	pte_pmd(pte_wrprotect(pmd_pte(pmd)))
 #define pmd_mkold(pmd)		pte_pmd(pte_mkold(pmd_pte(pmd)))
@@ -485,8 +528,19 @@ static inline pmd_t pmd_mkdevmap(pmd_t pmd)
 #define pud_pfn(pud)		((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT)
 #define pfn_pud(pfn,prot)	__pud(__phys_to_pud_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))
 
-#define set_pmd_at(mm, addr, pmdp, pmd)	set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd))
-#define set_pud_at(mm, addr, pudp, pud)	set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud))
+static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr,
+			      pmd_t *pmdp, pmd_t pmd)
+{
+	page_table_check_pmd_set(mm, addr, pmdp, pmd);
+	return __set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd));
+}
+
+static inline void set_pud_at(struct mm_struct *mm, unsigned long addr,
+			      pud_t *pudp, pud_t pud)
+{
+	page_table_check_pud_set(mm, addr, pudp, pud);
+	return __set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud));
+}
 
 #define __p4d_to_phys(p4d)	__pte_to_phys(p4d_pte(p4d))
 #define __phys_to_p4d_val(phys)	__phys_to_pte_val(phys)
@@ -535,7 +589,7 @@ extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 				 PMD_TYPE_TABLE)
 #define pmd_sect(pmd)		((pmd_val(pmd) & PMD_TYPE_MASK) == \
 				 PMD_TYPE_SECT)
-#define pmd_leaf(pmd)		pmd_sect(pmd)
+#define pmd_leaf(pmd)		(pmd_present(pmd) && !pmd_table(pmd))
 #define pmd_bad(pmd)		(!pmd_table(pmd))
 
 #define pmd_leaf_size(pmd)	(pmd_cont(pmd) ? CONT_PMD_SIZE : PMD_SIZE)
@@ -625,8 +679,10 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
 #define pud_none(pud)		(!pud_val(pud))
 #define pud_bad(pud)		(!pud_table(pud))
 #define pud_present(pud)	pte_present(pud_pte(pud))
-#define pud_leaf(pud)		pud_sect(pud)
+#define pud_leaf(pud)		(pud_present(pud) && !pud_table(pud))
 #define pud_valid(pud)		pte_valid(pud_pte(pud))
+#define pud_user(pud)		pte_user(pud_pte(pud))
+
 
 static inline void set_pud(pud_t *pudp, pud_t pud)
 {
@@ -799,6 +855,23 @@ static inline int pgd_devmap(pgd_t pgd)
 }
 #endif
 
+#ifdef CONFIG_PAGE_TABLE_CHECK
+static inline bool pte_user_accessible_page(pte_t pte)
+{
+	return pte_present(pte) && (pte_user(pte) || pte_user_exec(pte));
+}
+
+static inline bool pmd_user_accessible_page(pmd_t pmd)
+{
+	return pmd_leaf(pmd) && (pmd_user(pmd) || pmd_user_exec(pmd));
+}
+
+static inline bool pud_user_accessible_page(pud_t pud)
+{
+	return pud_leaf(pud) && pud_user(pud);
+}
+#endif
+
 /*
  * Atomic pte/pmd modifications.
  */
@@ -860,7 +933,11 @@ static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 				       unsigned long address, pte_t *ptep)
 {
-	return __pte(xchg_relaxed(&pte_val(*ptep), 0));
+	pte_t pte = __pte(xchg_relaxed(&pte_val(*ptep), 0));
+
+	page_table_check_pte_clear(mm, address, pte);
+
+	return pte;
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -868,7 +945,11 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
 					    unsigned long address, pmd_t *pmdp)
 {
-	return pte_pmd(ptep_get_and_clear(mm, address, (pte_t *)pmdp));
+	pmd_t pmd = __pmd(xchg_relaxed(&pmd_val(*pmdp), 0));
+
+	page_table_check_pmd_clear(mm, address, pmd);
+
+	return pmd;
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
@@ -902,6 +983,7 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
 static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
 		unsigned long address, pmd_t *pmdp, pmd_t pmd)
 {
+	page_table_check_pmd_set(vma->vm_mm, address, pmdp, pmd);
 	return __pmd(xchg_relaxed(&pmd_val(*pmdp), pmd_val(pmd)));
 }
 #endif
@@ -909,12 +991,13 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
 /*
  * Encode and decode a swap entry:
  *	bits 0-1:	present (must be zero)
- *	bits 2-7:	swap type
+ *	bits 2:		remember PG_anon_exclusive
+ *	bits 3-7:	swap type
  *	bits 8-57:	swap offset
  *	bit  58:	PTE_PROT_NONE (must be zero)
  */
-#define __SWP_TYPE_SHIFT	2
-#define __SWP_TYPE_BITS		6
+#define __SWP_TYPE_SHIFT	3
+#define __SWP_TYPE_BITS		5
 #define __SWP_OFFSET_BITS	50
 #define __SWP_TYPE_MASK		((1 << __SWP_TYPE_BITS) - 1)
 #define __SWP_OFFSET_SHIFT	(__SWP_TYPE_BITS + __SWP_TYPE_SHIFT)
@@ -964,10 +1047,10 @@ static inline void arch_swap_invalidate_area(int type)
 }
 
 #define __HAVE_ARCH_SWAP_RESTORE
-static inline void arch_swap_restore(swp_entry_t entry, struct page *page)
+static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio)
 {
-	if (system_supports_mte() && mte_restore_tags(entry, page))
-		set_bit(PG_mte_tagged, &page->flags);
+	if (system_supports_mte() && mte_restore_tags(entry, &folio->page))
+		set_bit(PG_mte_tagged, &folio->flags);
 }
 
 #endif /* CONFIG_ARM64_MTE */
@@ -999,34 +1082,13 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
  * page after fork() + CoW for pfn mappings. We don't always have a
  * hardware-managed access flag on arm64.
  */
-static inline bool arch_faults_on_old_pte(void)
-{
-	WARN_ON(preemptible());
-
-	return !cpu_has_hw_af();
-}
-#define arch_faults_on_old_pte		arch_faults_on_old_pte
+#define arch_has_hw_pte_young		cpu_has_hw_af
 
 /*
  * Experimentally, it's cheap to set the access flag in hardware and we
  * benefit from prefaulting mappings as 'old' to start with.
  */
-static inline bool arch_wants_old_prefaulted_pte(void)
-{
-	return !arch_faults_on_old_pte();
-}
-#define arch_wants_old_prefaulted_pte	arch_wants_old_prefaulted_pte
-
-static inline pgprot_t arch_filter_pgprot(pgprot_t prot)
-{
-	if (cpus_have_const_cap(ARM64_HAS_EPAN))
-		return prot;
-
-	if (pgprot_val(prot) != pgprot_val(PAGE_EXECONLY))
-		return prot;
-
-	return PAGE_READONLY_EXEC;
-}
+#define arch_wants_old_prefaulted_pte	cpu_has_hw_af
 
 static inline bool pud_sect_supported(void)
 {