[PATCH v6 3/4] mm/zsmalloc: drop class lock before freeing zspage

[Wenchao Hao]

From: Xueyuan Chen <xueyuan.chen21@xxxxxxxxx>

Currently in zs_free(), the class->lock is held until the zspage is
completely freed and the counters are updated. However, freeing pages
back to the buddy allocator requires acquiring the zone lock.

Under heavy memory pressure, zone lock contention can be severe. When
this happens, the CPU holding the class->lock will stall waiting for
the zone lock, thereby blocking all other CPUs attempting to acquire
the same class->lock.

This patch shrinks the critical section of the class->lock to reduce
lock contention. By moving the actual page freeing process outside the
class->lock, we can improve the concurrency performance of zs_free().

Testing on the RADXA O6 platform shows that with 12 CPUs concurrently
performing zs_free() operations, the execution time is reduced by 20%.

Signed-off-by: Xueyuan Chen <xueyuan.chen21@xxxxxxxxx>
Reviewed-by: Nhat Pham <nphamcs@xxxxxxxxx>
Reviewed-by: Joshua Hahn <joshua.hahnjy@xxxxxxxxx>
Reviewed-by: Barry Song <baohua@xxxxxxxxxx>
Signed-off-by: Wenchao Hao <haowenchao@xxxxxxxxxx>
---
 mm/zsmalloc.c | 29 +++++++++++++++++++++++------
 1 file changed, 23 insertions(+), 6 deletions(-)

diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 210a777081b7..f3045345e3a8 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -884,13 +884,10 @@ static int trylock_zspage(struct zspage *zspage)
 	return 0;
 }
 
-static void __free_zspage(struct zs_pool *pool, struct size_class *class,
-				struct zspage *zspage)
+static inline void __free_zspage_lockless(struct zspage *zspage)
 {
 	struct zpdesc *zpdesc, *next;
 
-	assert_spin_locked(&class->lock);
-
 	VM_BUG_ON(get_zspage_inuse(zspage));
 	VM_BUG_ON(zspage->fullness != ZS_INUSE_RATIO_0);
 
@@ -906,7 +903,13 @@ static void __free_zspage(struct zs_pool *pool, struct size_class *class,
 	} while (zpdesc != NULL);
 
 	cache_free_zspage(zspage);
+}
 
+static void __free_zspage(struct zs_pool *pool, struct size_class *class,
+			  struct zspage *zspage)
+{
+	assert_spin_locked(&class->lock);
+	__free_zspage_lockless(zspage);
 	class_stat_sub(class, ZS_OBJS_ALLOCATED, class->objs_per_zspage);
 	atomic_long_sub(class->pages_per_zspage, &pool->pages_allocated);
 }
@@ -1519,6 +1522,7 @@ void zs_free(struct zs_pool *pool, unsigned long handle)
 	unsigned long obj;
 	struct size_class *class;
 	int fullness;
+	struct zspage *zspage_to_free = NULL;
 
 	if (IS_ERR_OR_NULL((void *)handle))
 		return;
@@ -1529,10 +1533,23 @@ void zs_free(struct zs_pool *pool, unsigned long handle)
 	obj_free(class->size, obj);
 
 	fullness = fix_fullness_group(class, zspage);
-	if (fullness == ZS_INUSE_RATIO_0)
-		free_zspage(pool, class, zspage);
+	if (fullness == ZS_INUSE_RATIO_0) {
+		if (trylock_zspage(zspage)) {
+			remove_zspage(class, zspage);
+			class_stat_sub(class, ZS_OBJS_ALLOCATED,
+				       class->objs_per_zspage);
+			zspage_to_free = zspage;
+		} else {
+			kick_deferred_free(pool);
+		}
+	}
 
 	spin_unlock(&class->lock);
+
+	if (zspage_to_free) {
+		__free_zspage_lockless(zspage_to_free);
+		atomic_long_sub(class->pages_per_zspage, &pool->pages_allocated);
+	}
 	cache_free_handle(handle);
 }
 EXPORT_SYMBOL_GPL(zs_free);
-- 
2.34.1