From 1842d91b7b4c6be23064b6601127293173aa750c Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Wed, 8 Feb 2017 10:44:15 +1100 Subject: debugobjects: reduce contention on the global pool_lock On a large SMP system with many CPUs, the global pool_lock may become a performance bottleneck as all the CPUs that need to allocate or free debug objects have to take the lock. That can sometimes cause soft lockups like: NMI watchdog: BUG: soft lockup - CPU#35 stuck for 22s! [rcuos/1:21] ... RIP: 0010:[] [] _raw_spin_unlock_irqrestore+0x3b/0x60 ... Call Trace: [] free_object+0x81/0xb0 [] debug_check_no_obj_freed+0x193/0x220 [] ? trace_hardirqs_on_caller+0xf9/0x1c0 [] ? file_free_rcu+0x36/0x60 [] kmem_cache_free+0xd2/0x380 [] ? fput+0x90/0x90 [] file_free_rcu+0x36/0x60 [] rcu_nocb_kthread+0x1b3/0x550 [] ? rcu_nocb_kthread+0x101/0x550 [] ? sync_exp_work_done.constprop.63+0x50/0x50 [] kthread+0x101/0x120 [] ? trace_hardirqs_on_caller+0xf9/0x1c0 [] ret_from_fork+0x22/0x50 To reduce the amount of contention on the pool_lock, the actual kmem_cache_free() of the debug objects will be delayed if the pool_lock is busy. This will temporarily increase the amount of free objects available at the free pool when the system is busy. As a result, the number of kmem_cache allocation and freeing should be reduced. This patch also groups the freeing of debug objects in a batch of 4 to reduce the total number of lock/unlock cycles. Link: http://lkml.kernel.org/r/1483647425-4135-4-git-send-email-longman@redhat.com Signed-off-by: Waiman Long Cc: Thomas Gleixner Cc: "Du Changbin" Cc: Christian Borntraeger Cc: Jan Stancek Signed-off-by: Andrew Morton --- lib/debugobjects.c | 31 ++++++++++++++++++++++--------- 1 file changed, 22 insertions(+), 9 deletions(-) diff --git a/lib/debugobjects.c b/lib/debugobjects.c index dc78217b2199..5476bbe318e4 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -172,25 +172,38 @@ alloc_object(void *addr, struct debug_bucket *b, struct debug_obj_descr *descr) /* * workqueue function to free objects. + * + * To reduce contention on the global pool_lock, the actual freeing of + * debug objects will be delayed if the pool_lock is busy. We also free + * the objects in a batch of 4 for each lock/unlock cycle. */ +#define ODEBUG_FREE_BATCH 4 static void free_obj_work(struct work_struct *work) { - struct debug_obj *obj; + struct debug_obj *objs[ODEBUG_FREE_BATCH]; unsigned long flags; + int i; - raw_spin_lock_irqsave(&pool_lock, flags); - while (obj_pool_free > debug_objects_pool_size) { - obj = hlist_entry(obj_pool.first, typeof(*obj), node); - hlist_del(&obj->node); - obj_pool_free--; - debug_objects_freed++; + if (!raw_spin_trylock_irqsave(&pool_lock, flags)) + return; + while (obj_pool_free >= debug_objects_pool_size + ODEBUG_FREE_BATCH) { + for (i = 0; i < ODEBUG_FREE_BATCH; i++) { + objs[i] = hlist_entry(obj_pool.first, + typeof(*objs[0]), node); + hlist_del(&objs[i]->node); + } + + obj_pool_free -= ODEBUG_FREE_BATCH; + debug_objects_freed += ODEBUG_FREE_BATCH; /* * We release pool_lock across kmem_cache_free() to * avoid contention on pool_lock. */ raw_spin_unlock_irqrestore(&pool_lock, flags); - kmem_cache_free(obj_cache, obj); - raw_spin_lock_irqsave(&pool_lock, flags); + for (i = 0; i < ODEBUG_FREE_BATCH; i++) + kmem_cache_free(obj_cache, objs[i]); + if (!raw_spin_trylock_irqsave(&pool_lock, flags)) + return; } raw_spin_unlock_irqrestore(&pool_lock, flags); } -- cgit v1.2.3