mm: introduce arch_has_hw_nonleaf_pmd_young()

When running as a Xen PV guests commit eed9a32 ("mm: x86: add
CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG") can cause a protection violation in
pmdp_test_and_clear_young():

 BUG: unable to handle page fault for address: ffff8880083374d0
 #PF: supervisor write access in kernel mode
 #PF: error_code(0x0003) - permissions violation
 PGD 3026067 P4D 3026067 PUD 3027067 PMD 7fee5067 PTE 8010000008337065
 Oops: 0003 [#1] PREEMPT SMP NOPTI
 CPU: 7 PID: 158 Comm: kswapd0 Not tainted 6.1.0-rc5-20221118-doflr+ #1
 RIP: e030:pmdp_test_and_clear_young+0x25/0x40

This happens because the Xen hypervisor can't emulate direct writes to
page table entries other than PTEs.

This can easily be fixed by introducing arch_has_hw_nonleaf_pmd_young()
similar to arch_has_hw_pte_young() and test that instead of
CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG.

Link: https://lkml.kernel.org/r/[email protected]
Fixes: eed9a32 ("mm: x86: add CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG")
Signed-off-by: Juergen Gross <[email protected]>
Reported-by: Sander Eikelenboom <[email protected]>
Acked-by: Yu Zhao <[email protected]>
Tested-by: Sander Eikelenboom <[email protected]>
Acked-by: David Hildenbrand <[email protected]>	[core changes]
Signed-off-by: Andrew Morton <[email protected]>

Author: jgross1

arch/x86/include/asm/pgtable.h

@@ -1439,6 +1439,14 @@ static inline bool arch_has_hw_pte_young(void)
 	return true;
 }
 
+#ifdef CONFIG_XEN_PV
+#define arch_has_hw_nonleaf_pmd_young arch_has_hw_nonleaf_pmd_young
+static inline bool arch_has_hw_nonleaf_pmd_young(void)
+{
+	return !cpu_feature_enabled(X86_FEATURE_XENPV);
+}
+#endif
+
 #ifdef CONFIG_PAGE_TABLE_CHECK
 static inline bool pte_user_accessible_page(pte_t pte)
 {

include/linux/pgtable.h

@@ -267,6 +267,17 @@ static inline int pmdp_clear_flush_young(struct vm_area_struct *vma,
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif
 
+#ifndef arch_has_hw_nonleaf_pmd_young
+/*
+ * Return whether the accessed bit in non-leaf PMD entries is supported on the
+ * local CPU.
+ */
+static inline bool arch_has_hw_nonleaf_pmd_young(void)
+{
+	return IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG);
+}
+#endif
+
 #ifndef arch_has_hw_pte_young
 /*
  * Return whether the accessed bit is supported on the local CPU.

mm/vmscan.c

@@ -3987,7 +3987,7 @@ static void walk_pmd_range_locked(pud_t *pud, unsigned long next, struct vm_area
 			goto next;
 
 		if (!pmd_trans_huge(pmd[i])) {
-			if (IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) &&
+			if (arch_has_hw_nonleaf_pmd_young() &&
 			    get_cap(LRU_GEN_NONLEAF_YOUNG))
 				pmdp_test_and_clear_young(vma, addr, pmd + i);
 			goto next;
@@ -4085,14 +4085,14 @@ static void walk_pmd_range(pud_t *pud, unsigned long start, unsigned long end,
 #endif
 		walk->mm_stats[MM_NONLEAF_TOTAL]++;
 
-#ifdef CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG
-		if (get_cap(LRU_GEN_NONLEAF_YOUNG)) {
+		if (arch_has_hw_nonleaf_pmd_young() &&
+		    get_cap(LRU_GEN_NONLEAF_YOUNG)) {
 			if (!pmd_young(val))
 				continue;
 
 			walk_pmd_range_locked(pud, addr, vma, args, bitmap, &pos);
 		}
-#endif
+
 		if (!walk->force_scan && !test_bloom_filter(walk->lruvec, walk->max_seq, pmd + i))
 			continue;
 
@@ -5392,7 +5392,7 @@ static ssize_t show_enabled(struct kobject *kobj, struct kobj_attribute *attr, c
 	if (arch_has_hw_pte_young() && get_cap(LRU_GEN_MM_WALK))
 		caps |= BIT(LRU_GEN_MM_WALK);
 
-	if (IS_ENABLED(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) && get_cap(LRU_GEN_NONLEAF_YOUNG))
+	if (arch_has_hw_nonleaf_pmd_young() && get_cap(LRU_GEN_NONLEAF_YOUNG))
 		caps |= BIT(LRU_GEN_NONLEAF_YOUNG);
 
 	return snprintf(buf, PAGE_SIZE, "0x%04x\n", caps);