3 files changed, 62 insertions, 10 deletions

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 7748489fde1b..bd547857c6c1 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -495,6 +495,17 @@ static inline bool is_huge_zero_pmd(pmd_t pmd)
 struct folio *mm_get_huge_zero_folio(struct mm_struct *mm);
 void mm_put_huge_zero_folio(struct mm_struct *mm);
 
+static inline struct folio *get_persistent_huge_zero_folio(void)
+{
+	if (!IS_ENABLED(CONFIG_PERSISTENT_HUGE_ZERO_FOLIO))
+		return NULL;
+
+	if (unlikely(!huge_zero_folio))
+		return NULL;
+
+	return huge_zero_folio;
+}
+
 static inline bool thp_migration_supported(void)
 {
 	return IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION);
@@ -685,6 +696,11 @@ static inline int change_huge_pud(struct mmu_gather *tlb,
 {
 	return 0;
 }
+
+static inline struct folio *get_persistent_huge_zero_folio(void)
+{
+	return NULL;
+}
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 static inline int split_folio_to_list_to_order(struct folio *folio,
diff --git a/mm/Kconfig b/mm/Kconfig
index 59a04d0b2e27..4108bcd96784 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -823,6 +823,22 @@ config ARCH_WANT_GENERAL_HUGETLB
 config ARCH_WANTS_THP_SWAP
 	def_bool n
 
+config PERSISTENT_HUGE_ZERO_FOLIO
+	bool "Allocate a PMD sized folio for zeroing"
+	depends on TRANSPARENT_HUGEPAGE
+	help
+	  Enable this option to reduce the runtime refcounting overhead
+	  of the huge zero folio and expand the places in the kernel
+	  that can use huge zero folios. For instance, block I/O benefits
+	  from access to large folios for zeroing memory.
+
+	  With this option enabled, the huge zero folio is allocated
+	  once and never freed. One full huge page's worth of memory shall
+	  be used.
+
+	  Say Y if your system has lots of memory. Say N if you are
+	  memory constrained.
+
 config MM_ID
 	def_bool n
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 2801ce9bbde9..b8bb078a1a34 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -248,6 +248,9 @@ static void put_huge_zero_folio(void)
 
 struct folio *mm_get_huge_zero_folio(struct mm_struct *mm)
 {
+	if (IS_ENABLED(CONFIG_PERSISTENT_HUGE_ZERO_FOLIO))
+		return huge_zero_folio;
+
 	if (test_bit(MMF_HUGE_ZERO_FOLIO, &mm->flags))
 		return READ_ONCE(huge_zero_folio);
 
@@ -262,6 +265,9 @@ struct folio *mm_get_huge_zero_folio(struct mm_struct *mm)
 
 void mm_put_huge_zero_folio(struct mm_struct *mm)
 {
+	if (IS_ENABLED(CONFIG_PERSISTENT_HUGE_ZERO_FOLIO))
+		return;
+
 	if (test_bit(MMF_HUGE_ZERO_FOLIO, &mm->flags))
 		put_huge_zero_folio();
 }
@@ -849,16 +855,34 @@ static inline void hugepage_exit_sysfs(struct kobject *hugepage_kobj)
 
 static int __init thp_shrinker_init(void)
 {
-	huge_zero_folio_shrinker = shrinker_alloc(0, "thp-zero");
-	if (!huge_zero_folio_shrinker)
-		return -ENOMEM;
-
 	deferred_split_shrinker = shrinker_alloc(SHRINKER_NUMA_AWARE |
 						 SHRINKER_MEMCG_AWARE |
 						 SHRINKER_NONSLAB,
 						 "thp-deferred_split");
-	if (!deferred_split_shrinker) {
-		shrinker_free(huge_zero_folio_shrinker);
+	if (!deferred_split_shrinker)
+		return -ENOMEM;
+
+	deferred_split_shrinker->count_objects = deferred_split_count;
+	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);
 		return -ENOMEM;
 	}
 
@@ -866,10 +890,6 @@ static int __init thp_shrinker_init(void)
 	huge_zero_folio_shrinker->scan_objects = shrink_huge_zero_folio_scan;
 	shrinker_register(huge_zero_folio_shrinker);
 
-	deferred_split_shrinker->count_objects = deferred_split_count;
-	deferred_split_shrinker->scan_objects = deferred_split_scan;
-	shrinker_register(deferred_split_shrinker);
-
 	return 0;
 }