[PATCH mm-hotfixes 1/2] mm/huge_memory: separate out CONFIG_PERSISTENT_HUGE_ZERO_FOLIO logic

["Lorenzo Stoakes (ARM)" <ljs@kernel.org>]

Rather than mixing the refcounted and non-refcounted
CONFIG_PERSISTENT_HUGE_ZERO_FOLIO logic, separate the two out cleanly
so it is clear what happens when this configuration option is set and what
happens when it is not.

Introduce HUGE_ZERO_UNSET_PFN to abstract the ~0UL assignment, only
introduce the refcount and shrinker if !CONFIG_PERSISTENT_HUGE_ZERO_FOLIO,
abstract initialisation and teardown, abstract the huge zero folio
allocation from refcounting.

Also change a BUG_ON() to WARN_ON_ONCE() while we're at it.

Without this change, the subsequent fix for a subtle race is harder to
understand thus this is a dependency of it.

Cc: stable@vger.kernel.org # 6.18.x: dependency of subsequent fix
Signed-off-by: Lorenzo Stoakes (ARM) <ljs@kernel.org>
---
 mm/huge_memory.c | 159 ++++++++++++++++++++++++++++++++-----------------------
 1 file changed, 94 insertions(+), 65 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 032702a4637b..0f60bc82e87a 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -77,9 +77,14 @@ static unsigned long deferred_split_scan(struct shrinker *shrink,
 					 struct shrink_control *sc);
 static bool split_underused_thp = true;
 
-static atomic_t huge_zero_refcount;
+#define HUGE_ZERO_UNSET_PFN (~0UL)
 struct folio *huge_zero_folio __read_mostly;
-unsigned long huge_zero_pfn __read_mostly = ~0UL;
+unsigned long huge_zero_pfn __read_mostly = HUGE_ZERO_UNSET_PFN;
+#ifndef CONFIG_PERSISTENT_HUGE_ZERO_FOLIO
+static atomic_t huge_zero_refcount;
+static struct shrinker *huge_zero_folio_shrinker;
+#endif
+
 unsigned long huge_anon_orders_always __read_mostly;
 unsigned long huge_anon_orders_madvise __read_mostly;
 unsigned long huge_anon_orders_inherit __read_mostly;
@@ -221,22 +226,58 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma,
 	return orders;
 }
 
-static bool get_huge_zero_folio(void)
+static struct folio *alloc_huge_zero_folio(void)
 {
 	struct folio *zero_folio;
-retry:
-	if (likely(atomic_inc_not_zero(&huge_zero_refcount)))
-		return true;
 
 	zero_folio = folio_alloc((GFP_TRANSHUGE | __GFP_ZERO | __GFP_ZEROTAGS) &
 				 ~__GFP_MOVABLE,
 			HPAGE_PMD_ORDER);
 	if (!zero_folio) {
 		count_vm_event(THP_ZERO_PAGE_ALLOC_FAILED);
-		return false;
+		return NULL;
+	}
+	folio_clear_large_rmappable(zero_folio); /* Explicitly not rmappable. */
+	return zero_folio;
+}
+
+#ifdef CONFIG_PERSISTENT_HUGE_ZERO_FOLIO
+static int __init huge_zero_init(void)
+{
+	huge_zero_folio = alloc_huge_zero_folio();
+	if (!huge_zero_folio) {
+		pr_warn("Allocating persistent huge zero folio failed\n");
+	} else {
+		huge_zero_pfn = folio_pfn(huge_zero_folio);
+		count_vm_event(THP_ZERO_PAGE_ALLOC);
 	}
-	/* Ensure zero folio won't have large_rmappable flag set. */
-	folio_clear_large_rmappable(zero_folio);
+	return 0;
+}
+
+static void __init huge_zero_shrinker_exit(void)
+{
+}
+
+struct folio *mm_get_huge_zero_folio(struct mm_struct *mm)
+{
+	return huge_zero_folio;
+}
+
+void mm_put_huge_zero_folio(struct mm_struct *mm)
+{
+}
+#else
+static bool get_huge_zero_folio(void)
+{
+	struct folio *zero_folio;
+retry:
+	if (likely(atomic_inc_not_zero(&huge_zero_refcount)))
+		return true;
+
+	zero_folio = alloc_huge_zero_folio();
+	if (unlikely(!zero_folio))
+		return false;
+
 	preempt_disable();
 	if (cmpxchg(&huge_zero_folio, NULL, zero_folio)) {
 		preempt_enable();
@@ -258,33 +299,7 @@ static void put_huge_zero_folio(void)
 	 * Counter should never go to zero here. Only shrinker can put
 	 * last reference.
 	 */
-	BUG_ON(atomic_dec_and_test(&huge_zero_refcount));
-}
-
-struct folio *mm_get_huge_zero_folio(struct mm_struct *mm)
-{
-	if (IS_ENABLED(CONFIG_PERSISTENT_HUGE_ZERO_FOLIO))
-		return huge_zero_folio;
-
-	if (mm_flags_test(MMF_HUGE_ZERO_FOLIO, mm))
-		return READ_ONCE(huge_zero_folio);
-
-	if (!get_huge_zero_folio())
-		return NULL;
-
-	if (mm_flags_test_and_set(MMF_HUGE_ZERO_FOLIO, mm))
-		put_huge_zero_folio();
-
-	return READ_ONCE(huge_zero_folio);
-}
-
-void mm_put_huge_zero_folio(struct mm_struct *mm)
-{
-	if (IS_ENABLED(CONFIG_PERSISTENT_HUGE_ZERO_FOLIO))
-		return;
-
-	if (mm_flags_test(MMF_HUGE_ZERO_FOLIO, mm))
-		put_huge_zero_folio();
+	WARN_ON_ONCE(atomic_dec_and_test(&huge_zero_refcount));
 }
 
 static unsigned long shrink_huge_zero_folio_count(struct shrinker *shrink,
@@ -300,7 +315,7 @@ static unsigned long shrink_huge_zero_folio_scan(struct shrinker *shrink,
 	if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) {
 		struct folio *zero_folio = xchg(&huge_zero_folio, NULL);
 		BUG_ON(zero_folio == NULL);
-		WRITE_ONCE(huge_zero_pfn, ~0UL);
+		WRITE_ONCE(huge_zero_pfn, HUGE_ZERO_UNSET_PFN);
 		folio_put(zero_folio);
 		return HPAGE_PMD_NR;
 	}
@@ -308,7 +323,46 @@ static unsigned long shrink_huge_zero_folio_scan(struct shrinker *shrink,
 	return 0;
 }
 
-static struct shrinker *huge_zero_folio_shrinker;
+static int __init huge_zero_init(void)
+{
+	huge_zero_folio_shrinker = shrinker_alloc(0, "thp-zero");
+	if (!huge_zero_folio_shrinker) {
+		shrinker_free(deferred_split_shrinker);
+		list_lru_destroy(&deferred_split_lru);
+		return -ENOMEM;
+	}
+
+	huge_zero_folio_shrinker->count_objects = shrink_huge_zero_folio_count;
+	huge_zero_folio_shrinker->scan_objects = shrink_huge_zero_folio_scan;
+	shrinker_register(huge_zero_folio_shrinker);
+	return 0;
+}
+
+static void __init huge_zero_shrinker_exit(void)
+{
+	shrinker_free(huge_zero_folio_shrinker);
+}
+
+struct folio *mm_get_huge_zero_folio(struct mm_struct *mm)
+{
+	if (mm_flags_test(MMF_HUGE_ZERO_FOLIO, mm))
+		return READ_ONCE(huge_zero_folio);
+
+	if (!get_huge_zero_folio())
+		return NULL;
+
+	if (mm_flags_test_and_set(MMF_HUGE_ZERO_FOLIO, mm))
+		put_huge_zero_folio();
+
+	return READ_ONCE(huge_zero_folio);
+}
+
+void mm_put_huge_zero_folio(struct mm_struct *mm)
+{
+	if (mm_flags_test(MMF_HUGE_ZERO_FOLIO, mm))
+		put_huge_zero_folio();
+}
+#endif /* CONFIG_PERSISTENT_HUGE_ZERO_FOLIO */
 
 #ifdef CONFIG_SYSFS
 static ssize_t enabled_show(struct kobject *kobj,
@@ -972,39 +1026,14 @@ static int __init thp_shrinker_init(void)
 	deferred_split_shrinker->scan_objects = deferred_split_scan;
 	shrinker_register(deferred_split_shrinker);
 
-	if (IS_ENABLED(CONFIG_PERSISTENT_HUGE_ZERO_FOLIO)) {
-		/*
-		 * Bump the reference of the huge_zero_folio and do not
-		 * initialize the shrinker.
-		 *
-		 * huge_zero_folio will always be NULL on failure. We assume
-		 * that get_huge_zero_folio() will most likely not fail as
-		 * thp_shrinker_init() is invoked early on during boot.
-		 */
-		if (!get_huge_zero_folio())
-			pr_warn("Allocating persistent huge zero folio failed\n");
-		return 0;
-	}
-
-	huge_zero_folio_shrinker = shrinker_alloc(0, "thp-zero");
-	if (!huge_zero_folio_shrinker) {
-		shrinker_free(deferred_split_shrinker);
-		list_lru_destroy(&deferred_split_lru);
-		return -ENOMEM;
-	}
-
-	huge_zero_folio_shrinker->count_objects = shrink_huge_zero_folio_count;
-	huge_zero_folio_shrinker->scan_objects = shrink_huge_zero_folio_scan;
-	shrinker_register(huge_zero_folio_shrinker);
-
-	return 0;
+	return huge_zero_init();
 }
 
 static void __init thp_shrinker_exit(void)
 {
-	shrinker_free(huge_zero_folio_shrinker);
 	shrinker_free(deferred_split_shrinker);
 	list_lru_destroy(&deferred_split_lru);
+	huge_zero_shrinker_exit();
 }
 
 static int __init hugepage_init(void)

-- 
2.55.0