diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index d7a5407..6cf3cd6 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -91,8 +91,9 @@ __XCHG_GEN(_mb)
 #define __xchg_wrapper(sfx, ptr, x)					\
 ({									\
 	__typeof__(*(ptr)) __ret;					\
-	__ret = (__typeof__(*(ptr)))					\
-		__arch_xchg##sfx((unsigned long)(x), (ptr), sizeof(*(ptr))); \
+	__ret = (__force __typeof__(*(ptr)))				\
+		__arch_xchg##sfx((__force unsigned long)(x), (ptr),	\
+				  sizeof(*(ptr)));			\
 	__ret;								\
 })
 
@@ -175,9 +176,10 @@ __CMPXCHG_GEN(_mb)
 #define __cmpxchg_wrapper(sfx, ptr, o, n)				\
 ({									\
 	__typeof__(*(ptr)) __ret;					\
-	__ret = (__typeof__(*(ptr)))					\
-		__cmpxchg##sfx((ptr), (unsigned long)(o),		\
-				(unsigned long)(n), sizeof(*(ptr)));	\
+	__ret = (__force __typeof__(*(ptr)))				\
+		__cmpxchg##sfx((ptr), (__force unsigned long)(o),	\
+				(__force unsigned long)(n),		\
+				sizeof(*(ptr)));			\
 	__ret;								\
 })
 
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 2b32639..f560e64 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -50,11 +50,11 @@
 
 #define _PAGE_DEFAULT		(_PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL))
 
-#define _PAGE_KERNEL		(PROT_NORMAL)
-#define _PAGE_KERNEL_RO		((PROT_NORMAL & ~PTE_WRITE) | PTE_RDONLY)
-#define _PAGE_KERNEL_ROX	((PROT_NORMAL & ~(PTE_WRITE | PTE_PXN)) | PTE_RDONLY)
-#define _PAGE_KERNEL_EXEC	(PROT_NORMAL & ~PTE_PXN)
-#define _PAGE_KERNEL_EXEC_CONT	((PROT_NORMAL & ~PTE_PXN) | PTE_CONT)
+#define _PAGE_KERNEL		(PROT_NORMAL | PTE_DIRTY)
+#define _PAGE_KERNEL_RO		((PROT_NORMAL & ~PTE_WRITE) | PTE_RDONLY | PTE_DIRTY)
+#define _PAGE_KERNEL_ROX	((PROT_NORMAL & ~(PTE_WRITE | PTE_PXN)) | PTE_RDONLY | PTE_DIRTY)
+#define _PAGE_KERNEL_EXEC	((PROT_NORMAL & ~PTE_PXN) | PTE_DIRTY)
+#define _PAGE_KERNEL_EXEC_CONT	((PROT_NORMAL & ~PTE_PXN) | PTE_CONT | PTE_DIRTY)
 
 #define _PAGE_SHARED		(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)
 #define _PAGE_SHARED_EXEC	(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_WRITE)
diff --git a/arch/arm64/include/asm/runtime-const.h b/arch/arm64/include/asm/runtime-const.h
index be59156..c3dbd3a 100644
--- a/arch/arm64/include/asm/runtime-const.h
+++ b/arch/arm64/include/asm/runtime-const.h
@@ -2,6 +2,10 @@
 #ifndef _ASM_RUNTIME_CONST_H
 #define _ASM_RUNTIME_CONST_H
 
+#ifdef MODULE
+  #error "Cannot use runtime-const infrastructure from modules"
+#endif
+
 #include <asm/cacheflush.h>
 
 /* Sigh. You can still run arm64 in BE mode */
diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c
index b929a45..1519d09 100644
--- a/arch/arm64/mm/contpte.c
+++ b/arch/arm64/mm/contpte.c
@@ -599,6 +599,27 @@ void contpte_clear_young_dirty_ptes(struct vm_area_struct *vma,
 }
 EXPORT_SYMBOL_GPL(contpte_clear_young_dirty_ptes);
 
+static bool contpte_all_subptes_match_access_flags(pte_t *ptep, pte_t entry)
+{
+	pte_t *cont_ptep = contpte_align_down(ptep);
+	/*
+	 * PFNs differ per sub-PTE. Match only bits consumed by
+	 * __ptep_set_access_flags(): AF, DIRTY and write permission.
+	 */
+	const pteval_t cmp_mask = PTE_RDONLY | PTE_AF | PTE_WRITE | PTE_DIRTY;
+	pteval_t entry_cmp = pte_val(entry) & cmp_mask;
+	int i;
+
+	for (i = 0; i < CONT_PTES; i++) {
+		pteval_t pte_cmp = pte_val(__ptep_get(cont_ptep + i)) & cmp_mask;
+
+		if (pte_cmp != entry_cmp)
+			return false;
+	}
+
+	return true;
+}
+
 int contpte_ptep_set_access_flags(struct vm_area_struct *vma,
 					unsigned long addr, pte_t *ptep,
 					pte_t entry, int dirty)
@@ -608,14 +629,38 @@ int contpte_ptep_set_access_flags(struct vm_area_struct *vma,
 	int i;
 
 	/*
-	 * Gather the access/dirty bits for the contiguous range. If nothing has
-	 * changed, its a noop.
+	 * Check whether all sub-PTEs in the CONT block already match the
+	 * requested access flags/write permission, using raw per-PTE values
+	 * rather than the gathered ptep_get() view.
+	 *
+	 * __ptep_set_access_flags() can update AF, dirty and write
+	 * permission, but only to make the mapping more permissive.
+	 *
+	 * ptep_get() gathers AF/dirty state across the whole CONT block,
+	 * which is correct for a CPU with FEAT_HAFDBS. But page-table
+	 * walkers that evaluate each descriptor individually (e.g. a CPU
+	 * without DBM support, or an SMMU without HTTU, or with HA/HD
+	 * disabled in CD.TCR) can keep faulting on the target sub-PTE if
+	 * only a sibling has been updated. Gathering can therefore cause
+	 * false no-ops when only a sibling has been updated:
+	 *  - write faults: target still has PTE_RDONLY (needs PTE_RDONLY cleared)
+	 *  - read faults:  target still lacks PTE_AF
+	 *
+	 * Per Arm ARM (DDI 0487) D8.7.1, any sub-PTE in a CONT range may
+	 * become the effective cached translation, so all entries must have
+	 * consistent attributes. Check the full CONT block before returning
+	 * no-op, and when any sub-PTE mismatches, proceed to update the whole
+	 * range.
 	 */
-	orig_pte = pte_mknoncont(ptep_get(ptep));
-	if (pte_val(orig_pte) == pte_val(entry))
+	if (contpte_all_subptes_match_access_flags(ptep, entry))
 		return 0;
 
 	/*
+	 * Use raw target pte (not gathered) for write-bit unfold decision.
+	 */
+	orig_pte = pte_mknoncont(__ptep_get(ptep));
+
+	/*
 	 * We can fix up access/dirty bits without having to unfold the contig
 	 * range. But if the write bit is changing, we must unfold.
 	 */
diff --git a/tools/testing/selftests/arm64/abi/hwcap.c b/tools/testing/selftests/arm64/abi/hwcap.c
index 9d2df1f..c2661a3 100644
--- a/tools/testing/selftests/arm64/abi/hwcap.c
+++ b/tools/testing/selftests/arm64/abi/hwcap.c
@@ -475,8 +475,8 @@ static void sve2_sigill(void)
 
 static void sve2p1_sigill(void)
 {
-	/* BFADD Z0.H, Z0.H, Z0.H */
-	asm volatile(".inst 0x65000000" : : : "z0");
+	/* LD1Q {Z0.Q}, P0/Z, [Z0.D, X0] */
+	asm volatile(".inst 0xC400A000" : : : "z0");
 }
 
 static void sve2p2_sigill(void)