The huge_zero_folio was initially placed in huge_memory.c as most of the
users were in that file. But it does not depend on THP, so it could very
well be a part of memory.c file.
As huge_zero_folio is going to be exposed to more users outside of mm,
let's move it to memory.c file.
This is a prep patch to add CONFIG_STATIC_PMD_ZERO_PAGE. No functional
changes.
Suggested-by: David Hildenbrand <david@xxxxxxxxxx>
Signed-off-by: Pankaj Raghav <p.raghav@xxxxxxxxxxx>
---
include/linux/huge_mm.h | 16 ------
include/linux/mm.h | 16 ++++++
mm/huge_memory.c | 105 +---------------------------------------
mm/memory.c | 99 +++++++++++++++++++++++++++++++++++++
4 files changed, 117 insertions(+), 119 deletions(-)
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 2f190c90192d..d48973a6bd0f 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -478,22 +478,6 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf);
-extern struct folio *huge_zero_folio;
-extern unsigned long huge_zero_pfn;
-
-static inline bool is_huge_zero_folio(const struct folio *folio)
-{
- return READ_ONCE(huge_zero_folio) == folio;
-}
-
-static inline bool is_huge_zero_pmd(pmd_t pmd)
-{
- return pmd_present(pmd) && READ_ONCE(huge_zero_pfn) == pmd_pfn(pmd);
-}
-
-struct folio *mm_get_huge_zero_folio(struct mm_struct *mm);
-void mm_put_huge_zero_folio(struct mm_struct *mm);
-
static inline bool thp_migration_supported(void)
{
return IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index cd2e513189d6..58d150dfc2da 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -69,6 +69,22 @@ static inline void totalram_pages_add(long count)
extern void * high_memory;
+extern struct folio *huge_zero_folio;
+extern unsigned long huge_zero_pfn;
+
+static inline bool is_huge_zero_folio(const struct folio *folio)
+{
+ return READ_ONCE(huge_zero_folio) == folio;
+}
+
+static inline bool is_huge_zero_pmd(pmd_t pmd)
+{
+ return pmd_present(pmd) && READ_ONCE(huge_zero_pfn) == pmd_pfn(pmd);
+}
+
+struct folio *mm_get_huge_zero_folio(struct mm_struct *mm);
+void mm_put_huge_zero_folio(struct mm_struct *mm);
+
#ifdef CONFIG_SYSCTL
extern int sysctl_legacy_va_layout;
#else
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index d3e66136e41a..c6e203abb2de 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -75,9 +75,6 @@ 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;
-struct folio *huge_zero_folio __read_mostly;
-unsigned long huge_zero_pfn __read_mostly = ~0UL;
unsigned long huge_anon_orders_always __read_mostly;
unsigned long huge_anon_orders_madvise __read_mostly;
unsigned long huge_anon_orders_inherit __read_mostly;
@@ -208,88 +205,6 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma,
return orders;
}
-static bool get_huge_zero_page(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_MOVABLE,
- HPAGE_PMD_ORDER);
- if (!zero_folio) {
- count_vm_event(THP_ZERO_PAGE_ALLOC_FAILED);
- return false;
- }
- /* Ensure zero folio won't have large_rmappable flag set. */
- folio_clear_large_rmappable(zero_folio);
- preempt_disable();
- if (cmpxchg(&huge_zero_folio, NULL, zero_folio)) {
- preempt_enable();
- folio_put(zero_folio);
- goto retry;
- }
- WRITE_ONCE(huge_zero_pfn, folio_pfn(zero_folio));
-
- /* We take additional reference here. It will be put back by shrinker */
- atomic_set(&huge_zero_refcount, 2);
- preempt_enable();
- count_vm_event(THP_ZERO_PAGE_ALLOC);
- return true;
-}
-
-static void put_huge_zero_page(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 (test_bit(MMF_HUGE_ZERO_PAGE, &mm->flags))
- return READ_ONCE(huge_zero_folio);
-
- if (!get_huge_zero_page())
- return NULL;
-
- if (test_and_set_bit(MMF_HUGE_ZERO_PAGE, &mm->flags))
- put_huge_zero_page();
-
- return READ_ONCE(huge_zero_folio);
-}
-
-void mm_put_huge_zero_folio(struct mm_struct *mm)
-{
- if (test_bit(MMF_HUGE_ZERO_PAGE, &mm->flags))
- put_huge_zero_page();
-}
-
-static unsigned long shrink_huge_zero_page_count(struct shrinker *shrink,
- struct shrink_control *sc)
-{
- /* we can free zero page only if last reference remains */
- return atomic_read(&huge_zero_refcount) == 1 ? HPAGE_PMD_NR : 0;
-}
-
-static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink,
- struct shrink_control *sc)
-{
- 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);
- folio_put(zero_folio);
- return HPAGE_PMD_NR;
- }
-
- return 0;
-}
-
-static struct shrinker *huge_zero_page_shrinker;
-
#ifdef CONFIG_SYSFS
static ssize_t enabled_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
@@ -850,22 +765,12 @@ static inline void hugepage_exit_sysfs(struct kobject *hugepage_kobj)
static int __init thp_shrinker_init(void)
{
- huge_zero_page_shrinker = shrinker_alloc(0, "thp-zero");
- if (!huge_zero_page_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_page_shrinker);
+ if (!deferred_split_shrinker)
return -ENOMEM;
- }
-
- huge_zero_page_shrinker->count_objects = shrink_huge_zero_page_count;
- huge_zero_page_shrinker->scan_objects = shrink_huge_zero_page_scan;
- shrinker_register(huge_zero_page_shrinker);
deferred_split_shrinker->count_objects = deferred_split_count;
deferred_split_shrinker->scan_objects = deferred_split_scan;
@@ -874,12 +779,6 @@ static int __init thp_shrinker_init(void)
return 0;
}
-static void __init thp_shrinker_exit(void)
-{
- shrinker_free(huge_zero_page_shrinker);
- shrinker_free(deferred_split_shrinker);
-}
-
static int __init hugepage_init(void)
{
int err;
@@ -923,7 +822,7 @@ static int __init hugepage_init(void)
return 0;
err_khugepaged:
- thp_shrinker_exit();
+ shrinker_free(deferred_split_shrinker);
err_shrinker:
khugepaged_destroy();
err_slab:
diff --git a/mm/memory.c b/mm/memory.c
index 5cb48f262ab0..11edc4d66e74 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -159,6 +159,105 @@ static int __init init_zero_pfn(void)
}
early_initcall(init_zero_pfn);
+static atomic_t huge_zero_refcount;
+struct folio *huge_zero_folio __read_mostly;
+unsigned long huge_zero_pfn __read_mostly = ~0UL;
+static struct shrinker *huge_zero_page_shrinker;
+
+static bool get_huge_zero_page(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_MOVABLE,
+ HPAGE_PMD_ORDER);
+ if (!zero_folio) {
+ count_vm_event(THP_ZERO_PAGE_ALLOC_FAILED);
+ return false;
+ }
+ /* Ensure zero folio won't have large_rmappable flag set. */
+ folio_clear_large_rmappable(zero_folio);
+ preempt_disable();
+ if (cmpxchg(&huge_zero_folio, NULL, zero_folio)) {
+ preempt_enable();
+ folio_put(zero_folio);
+ goto retry;
+ }
+ WRITE_ONCE(huge_zero_pfn, folio_pfn(zero_folio));
+
+ /* We take additional reference here. It will be put back by shrinker */
+ atomic_set(&huge_zero_refcount, 2);
+ preempt_enable();
+ count_vm_event(THP_ZERO_PAGE_ALLOC);
+ return true;
+}
+
+static void put_huge_zero_page(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 (test_bit(MMF_HUGE_ZERO_PAGE, &mm->flags))
+ return READ_ONCE(huge_zero_folio);
+
+ if (!get_huge_zero_page())
+ return NULL;
+
+ if (test_and_set_bit(MMF_HUGE_ZERO_PAGE, &mm->flags))
+ put_huge_zero_page();
+
+ return READ_ONCE(huge_zero_folio);
+}
+
+void mm_put_huge_zero_folio(struct mm_struct *mm)
+{
+ if (test_bit(MMF_HUGE_ZERO_PAGE, &mm->flags))
+ put_huge_zero_page();
+}
+
+static unsigned long shrink_huge_zero_page_count(struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ /* we can free zero page only if last reference remains */
+ return atomic_read(&huge_zero_refcount) == 1 ? HPAGE_PMD_NR : 0;
+}
+
+static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink,
+ struct shrink_control *sc)
+{
+ 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);
+ folio_put(zero_folio);
+ return HPAGE_PMD_NR;
+ }
+
+ return 0;
+}
+
+static int __init init_huge_zero_page(void)
+{
+ huge_zero_page_shrinker = shrinker_alloc(0, "thp-zero");
+ if (!huge_zero_page_shrinker)
+ return -ENOMEM;
+
+ huge_zero_page_shrinker->count_objects = shrink_huge_zero_page_count;
+ huge_zero_page_shrinker->scan_objects = shrink_huge_zero_page_scan;
+ shrinker_register(huge_zero_page_shrinker);
+
+ return 0;
+}
+early_initcall(init_huge_zero_page);
+
void mm_trace_rss_stat(struct mm_struct *mm, int member)
{
trace_rss_stat(mm, member);
--
2.47.2
