Subject: mm: slab: Fix potential deadlock
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 26 Sep 2012 16:20:00 +0200

 =============================================
[ INFO: possible recursive locking detected ]
 3.6.0-rt1+ #49 Not tainted
 ---------------------------------------------
 swapper/0/1 is trying to acquire lock:
 lock_slab_on+0x72/0x77
 
 but task is already holding lock:
 __local_lock_irq+0x24/0x77
 
 other info that might help us debug this:
  Possible unsafe locking scenario:
 
        CPU0
        ----
   lock(&per_cpu(slab_lock, __cpu).lock);
   lock(&per_cpu(slab_lock, __cpu).lock);
 
  *** DEADLOCK ***
 
  May be due to missing lock nesting notation
 
 2 locks held by swapper/0/1:
 kmem_cache_create+0x33/0x89
 __local_lock_irq+0x24/0x77
 
 stack backtrace:
 Pid: 1, comm: swapper/0 Not tainted 3.6.0-rt1+ #49
 Call Trace:
 __lock_acquire+0x9a4/0xdc4
 ? __local_lock_irq+0x24/0x77
 ? lock_slab_on+0x72/0x77
 lock_acquire+0xc4/0x108
 ? lock_slab_on+0x72/0x77
 ? unlock_slab_on+0x5b/0x5b
 rt_spin_lock+0x36/0x3d
 ? lock_slab_on+0x72/0x77
 ? migrate_disable+0x85/0x93
 lock_slab_on+0x72/0x77
 do_ccupdate_local+0x19/0x44
 slab_on_each_cpu+0x36/0x5a
 do_tune_cpucache+0xc1/0x305
 enable_cpucache+0x8c/0xb5
 setup_cpu_cache+0x28/0x182
 __kmem_cache_create+0x34b/0x380
 ? shmem_mount+0x1a/0x1a
 kmem_cache_create+0x4a/0x89
 ? shmem_mount+0x1a/0x1a
 shmem_init+0x3e/0xd4
 kernel_init+0x11c/0x214
 kernel_thread_helper+0x4/0x10
 ? retint_restore_args+0x13/0x13
 ? start_kernel+0x3bc/0x3bc
 ? gs_change+0x13/0x13

It's not a missing annotation. It's simply wrong code and needs to be
fixed. Instead of nesting the local and the remote cpu lock simply
acquire only the remote cpu lock, which is sufficient protection for
this procedure.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable-rt@vger.kernel.org
---
 include/linux/locallock.h |    8 ++++++++
 mm/slab.c                 |   10 ++--------
 2 files changed, 10 insertions(+), 8 deletions(-)

Index: linux-stable/include/linux/locallock.h
===================================================================
--- linux-stable.orig/include/linux/locallock.h
+++ linux-stable/include/linux/locallock.h
@@ -96,6 +96,9 @@ static inline void __local_lock_irq(stru
 #define local_lock_irq(lvar)						\
 	do { __local_lock_irq(&get_local_var(lvar)); } while (0)
 
+#define local_lock_irq_on(lvar, cpu)					\
+	do { __local_lock_irq(&per_cpu(lvar, cpu)); } while (0)
+
 static inline void __local_unlock_irq(struct local_irq_lock *lv)
 {
 	LL_WARN(!lv->nestcnt);
@@ -111,6 +114,11 @@ static inline void __local_unlock_irq(st
 		put_local_var(lvar);					\
 	} while (0)
 
+#define local_unlock_irq_on(lvar, cpu)					\
+	do {								\
+		__local_unlock_irq(&per_cpu(lvar, cpu));		\
+	} while (0)
+
 static inline int __local_lock_irqsave(struct local_irq_lock *lv)
 {
 	if (lv->owner != current) {
Index: linux-stable/mm/slab.c
===================================================================
--- linux-stable.orig/mm/slab.c
+++ linux-stable/mm/slab.c
@@ -728,18 +728,12 @@ slab_on_each_cpu(void (*func)(void *arg,
 
 static void lock_slab_on(unsigned int cpu)
 {
-	if (cpu == smp_processor_id())
-		local_lock_irq(slab_lock);
-	else
-		local_spin_lock_irq(slab_lock, &per_cpu(slab_lock, cpu).lock);
+	local_lock_irq_on(slab_lock, cpu);
 }
 
 static void unlock_slab_on(unsigned int cpu)
 {
-	if (cpu == smp_processor_id())
-		local_unlock_irq(slab_lock);
-	else
-		local_spin_unlock_irq(slab_lock, &per_cpu(slab_lock, cpu).lock);
+	local_unlock_irq_on(slab_lock, cpu);
 }
 #endif