arm64/mm: Add uffd write-protect support

Let's use the newly-free PTE SW bit (58) to add support for uffd-wp.

The standard handlers are implemented for set/test/clear for both pte
and pmd. Additionally we must also track the uffd-wp state as a pte swp
bit, so use a free swap pte bit (3).

Acked-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Link: https://lore.kernel.org/r/20240503144604.151095-5-ryan.roberts@arm.com
Signed-off-by: Will Deacon <will@kernel.org>

Author: ryanhrob

arch/arm64/Kconfig

@@ -255,6 +255,7 @@ config ARM64
 	select SYSCTL_EXCEPTION_TRACE
 	select THREAD_INFO_IN_TASK
 	select HAVE_ARCH_USERFAULTFD_MINOR if USERFAULTFD
+	select HAVE_ARCH_USERFAULTFD_WP if USERFAULTFD
 	select TRACE_IRQFLAGS_SUPPORT
 	select TRACE_IRQFLAGS_NMI_SUPPORT
 	select HAVE_SOFTIRQ_ON_OWN_STACK

arch/arm64/include/asm/pgtable-prot.h

@@ -26,6 +26,14 @@
  */
 #define PTE_PRESENT_INVALID	(PTE_NG)		 /* only when !PTE_VALID */
 
+#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
+#define PTE_UFFD_WP		(_AT(pteval_t, 1) << 58) /* uffd-wp tracking */
+#define PTE_SWP_UFFD_WP		(_AT(pteval_t, 1) << 3)	 /* only for swp ptes */
+#else
+#define PTE_UFFD_WP		(_AT(pteval_t, 0))
+#define PTE_SWP_UFFD_WP		(_AT(pteval_t, 0))
+#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */
+
 #define _PROT_DEFAULT		(PTE_TYPE_PAGE | PTE_AF | PTE_SHARED)
 #define _PROT_SECT_DEFAULT	(PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S)
 

arch/arm64/include/asm/pgtable.h

@@ -280,6 +280,23 @@ static inline pte_t pte_mkdevmap(pte_t pte)
 	return set_pte_bit(pte, __pgprot(PTE_DEVMAP | PTE_SPECIAL));
 }
 
+#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
+static inline int pte_uffd_wp(pte_t pte)
+{
+	return !!(pte_val(pte) & PTE_UFFD_WP);
+}
+
+static inline pte_t pte_mkuffd_wp(pte_t pte)
+{
+	return pte_wrprotect(set_pte_bit(pte, __pgprot(PTE_UFFD_WP)));
+}
+
+static inline pte_t pte_clear_uffd_wp(pte_t pte)
+{
+	return clear_pte_bit(pte, __pgprot(PTE_UFFD_WP));
+}
+#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */
+
 static inline void __set_pte_nosync(pte_t *ptep, pte_t pte)
 {
 	WRITE_ONCE(*ptep, pte);
@@ -477,6 +494,23 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte)
 	return clear_pte_bit(pte, __pgprot(PTE_SWP_EXCLUSIVE));
 }
 
+#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
+static inline pte_t pte_swp_mkuffd_wp(pte_t pte)
+{
+	return set_pte_bit(pte, __pgprot(PTE_SWP_UFFD_WP));
+}
+
+static inline int pte_swp_uffd_wp(pte_t pte)
+{
+	return !!(pte_val(pte) & PTE_SWP_UFFD_WP);
+}
+
+static inline pte_t pte_swp_clear_uffd_wp(pte_t pte)
+{
+	return clear_pte_bit(pte, __pgprot(PTE_SWP_UFFD_WP));
+}
+#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */
+
 #ifdef CONFIG_NUMA_BALANCING
 /*
  * See the comment in include/linux/pgtable.h
@@ -527,6 +561,15 @@ static inline int pmd_trans_huge(pmd_t pmd)
 #define pmd_mkdirty(pmd)	pte_pmd(pte_mkdirty(pmd_pte(pmd)))
 #define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
 #define pmd_mkinvalid(pmd)	pte_pmd(pte_mkinvalid(pmd_pte(pmd)))
+#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
+#define pmd_uffd_wp(pmd)	pte_uffd_wp(pmd_pte(pmd))
+#define pmd_mkuffd_wp(pmd)	pte_pmd(pte_mkuffd_wp(pmd_pte(pmd)))
+#define pmd_clear_uffd_wp(pmd)	pte_pmd(pte_clear_uffd_wp(pmd_pte(pmd)))
+#define pmd_swp_uffd_wp(pmd)	pte_swp_uffd_wp(pmd_pte(pmd))
+#define pmd_swp_mkuffd_wp(pmd)	pte_pmd(pte_swp_mkuffd_wp(pmd_pte(pmd)))
+#define pmd_swp_clear_uffd_wp(pmd) \
+				pte_pmd(pte_swp_clear_uffd_wp(pmd_pte(pmd)))
+#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */
 
 #define pmd_thp_or_huge(pmd)	(pmd_huge(pmd) || pmd_trans_huge(pmd))
 
@@ -1261,6 +1304,7 @@ 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:		remember PG_anon_exclusive
+ *	bit  3:		remember uffd-wp state
  *	bits 6-10:	swap type
  *	bit  11:	PTE_PRESENT_INVALID (must be zero)
  *	bits 12-61:	swap offset