[PATCH 1/1] mm: implement page refcount locking via dedicated bit

[Gladyshev Ilya]

The current atomic-based page refcount implementation treats zero
counter as dead and requires a compare-and-swap loop in folio_try_get()
to prevent incrementing a dead refcount. This CAS loop acts as a
serialization point and can become a significant bottleneck during
high-frequency file read operations.

This patch introduces FOLIO_LOCKED_BIT to distinguish between a
(temporary) zero refcount and a locked (dead/frozen) state. Because now
incrementing counter doesn't affect it's locked/unlocked state, it is
possible to use an optimistic atomic_add_return() in
page_ref_add_unless_zero() that operates independently of the locked bit.
The locked state is handled after the increment attempt, eliminating the
need for the CAS loop.

If locked state is detected after atomic_add(), pageref counter will be
reset using CAS loop, eliminating theoretical possibility of overflow.

Co-developed-by: Gorbunov Ivan <gorbunov.ivan@xxxxxxxxxxxxxx>
Signed-off-by: Gorbunov Ivan <gorbunov.ivan@xxxxxxxxxxxxxx>
Signed-off-by: Gladyshev Ilya <gladyshev.ilya1@xxxxxxxxxxxxxx>
---
 include/linux/page-flags.h |  5 ++++-
 include/linux/page_ref.h   | 28 ++++++++++++++++++++++++----
 2 files changed, 28 insertions(+), 5 deletions(-)

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 7c2195baf4c1..f2a9302104eb 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -196,6 +196,9 @@ enum pageflags {
 
 #define PAGEFLAGS_MASK		((1UL << NR_PAGEFLAGS) - 1)
 
+/* Most significant bit in page refcount */
+#define PAGEREF_LOCKED_BIT	(1 << 31)
+
 #ifndef __GENERATING_BOUNDS_H
 
 #ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
@@ -257,7 +260,7 @@ static __always_inline bool page_count_writable(const struct page *page)
 	 * The refcount check also prevents modification attempts to other (r/o)
 	 * tail pages that are not fake heads.
 	 */
-	if (!atomic_read_acquire(&page->_refcount))
+	if (atomic_read_acquire(&page->_refcount) & PAGEREF_LOCKED_BIT)
 		return false;
 
 	return page_fixed_fake_head(page) == page;
diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h
index b0e3f4a4b4b8..f2f2775af4bb 100644
--- a/include/linux/page_ref.h
+++ b/include/linux/page_ref.h
@@ -64,7 +64,12 @@ static inline void __page_ref_unfreeze(struct page *page, int v)
 
 static inline int page_ref_count(const struct page *page)
 {
-	return atomic_read(&page->_refcount);
+	int val = atomic_read(&page->_refcount);
+
+	if (unlikely(val & PAGEREF_LOCKED_BIT))
+		return 0;
+
+	return val;
 }
 
 /**
@@ -176,6 +181,9 @@ static inline int page_ref_sub_and_test(struct page *page, int nr)
 {
 	int ret = atomic_sub_and_test(nr, &page->_refcount);
 
+	if (ret)
+		ret = !atomic_cmpxchg_relaxed(&page->_refcount, 0, PAGEREF_LOCKED_BIT);
+
 	if (page_ref_tracepoint_active(page_ref_mod_and_test))
 		__page_ref_mod_and_test(page, -nr, ret);
 	return ret;
@@ -204,6 +212,9 @@ static inline int page_ref_dec_and_test(struct page *page)
 {
 	int ret = atomic_dec_and_test(&page->_refcount);
 
+	if (ret)
+		ret = !atomic_cmpxchg_relaxed(&page->_refcount, 0, PAGEREF_LOCKED_BIT);
+
 	if (page_ref_tracepoint_active(page_ref_mod_and_test))
 		__page_ref_mod_and_test(page, -1, ret);
 	return ret;
@@ -228,14 +239,23 @@ static inline int folio_ref_dec_return(struct folio *folio)
 	return page_ref_dec_return(&folio->page);
 }
 
+#define _PAGEREF_LOCKED_LIMIT	((1 << 30) | PAGEREF_LOCKED_BIT)
+
 static inline bool page_ref_add_unless_zero(struct page *page, int nr)
 {
 	bool ret = false;
+	int val;
 
 	rcu_read_lock();
 	/* avoid writing to the vmemmap area being remapped */
-	if (page_count_writable(page))
-		ret = atomic_add_unless(&page->_refcount, nr, 0);
+	if (page_count_writable(page)) {
+		val = atomic_add_return(nr, &page->_refcount);
+		ret = !(val & PAGEREF_LOCKED_BIT);
+
+		/* Undo atomic_add() if counter is locked and scary big */
+		while (unlikely((unsigned int)val >= _PAGEREF_LOCKED_LIMIT))
+			val = atomic_cmpxchg_relaxed(&page->_refcount, val, PAGEREF_LOCKED_BIT);
+	}
 	rcu_read_unlock();
 
 	if (page_ref_tracepoint_active(page_ref_mod_unless))
@@ -271,7 +291,7 @@ static inline bool folio_ref_try_add(struct folio *folio, int count)
 
 static inline int page_ref_freeze(struct page *page, int count)
 {
-	int ret = likely(atomic_cmpxchg(&page->_refcount, count, 0) == count);
+	int ret = likely(atomic_cmpxchg(&page->_refcount, count, PAGEREF_LOCKED_BIT) == count);
 
 	if (page_ref_tracepoint_active(page_ref_freeze))
 		__page_ref_freeze(page, count, ret);
-- 
2.43.0