debugobjects: Reduce number of pool_lock acquisitions in fill_pool()

In fill_pool(), the pool_lock is acquired and then released once per debug
object. If many objects are to be filled, the constant lock and unlock
operations are extra overhead.

To reduce the overhead, batch them up and do an allocation of 4 objects per
lock/unlock sequence.

Signed-off-by: Waiman Long <[email protected]>
Signed-off-by: Thomas Gleixner <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Yang Shi <[email protected]>
Cc: "Joel Fernandes (Google)" <[email protected]>
Cc: Qian Cai <[email protected]>
Cc: Zhong Jiang <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]

lib/debugobjects.c

@@ -120,7 +120,7 @@ static const char *obj_states[ODEBUG_STATE_MAX] = {
 static void fill_pool(void)
 {
 	gfp_t gfp = GFP_ATOMIC | __GFP_NORETRY | __GFP_NOWARN;
-	struct debug_obj *new, *obj;
+	struct debug_obj *obj;
 	unsigned long flags;
 
 	if (likely(obj_pool_free >= debug_objects_pool_min_level))
@@ -136,7 +136,7 @@ static void fill_pool(void)
 		 * Recheck with the lock held as the worker thread might have
 		 * won the race and freed the global free list already.
 		 */
-		if (obj_nr_tofree) {
+		while (obj_nr_tofree && (obj_pool_free < obj_pool_min_free)) {
 			obj = hlist_entry(obj_to_free.first, typeof(*obj), node);
 			hlist_del(&obj->node);
 			obj_nr_tofree--;
@@ -150,15 +150,23 @@ static void fill_pool(void)
 		return;
 
 	while (obj_pool_free < debug_objects_pool_min_level) {
+		struct debug_obj *new[ODEBUG_BATCH_SIZE];
+		int cnt;
 
-		new = kmem_cache_zalloc(obj_cache, gfp);
-		if (!new)
+		for (cnt = 0; cnt < ODEBUG_BATCH_SIZE; cnt++) {
+			new[cnt] = kmem_cache_zalloc(obj_cache, gfp);
+			if (!new[cnt])
+				break;
+		}
+		if (!cnt)
 			return;
 
 		raw_spin_lock_irqsave(&pool_lock, flags);
-		hlist_add_head(&new->node, &obj_pool);
-		debug_objects_allocated++;
-		obj_pool_free++;
+		while (cnt) {
+			hlist_add_head(&new[--cnt]->node, &obj_pool);
+			debug_objects_allocated++;
+			obj_pool_free++;
+		}
 		raw_spin_unlock_irqrestore(&pool_lock, flags);
 	}
 }
@@ -280,7 +288,7 @@ static void free_obj_work(struct work_struct *work)
 	/*
 	 * The objs on the pool list might be allocated before the work is
 	 * run, so recheck if pool list it full or not, if not fill pool
-	 * list from the global free list
+	 * list from the global free list.
 	 */
 	while (obj_nr_tofree && obj_pool_free < debug_objects_pool_size) {
 		obj = hlist_entry(obj_to_free.first, typeof(*obj), node);