[PATCH -rt 4/5] workqueue: hotplug fix

[Yong Zhang]

BUG: sleeping function called from invalid context at kernel/rtmutex.c:645
in_atomic(): 1, irqs_disabled(): 0, pid: 1739, name: bash
Pid: 1739, comm: bash Not tainted 3.0.6-rt17-00284-gb76d419 #3
Call Trace:
 [<c06e3b5d>] ? printk+0x1d/0x20
 [<c01390b6>] __might_sleep+0xe6/0x110
 [<c06e633c>] rt_spin_lock+0x1c/0x30
 [<c01655a6>] flush_gcwq+0x236/0x320
 [<c021c651>] ? kfree+0xe1/0x1a0
 [<c05b7178>] ? __cpufreq_remove_dev+0xf8/0x260
 [<c0183fad>] ? rt_down_write+0xd/0x10
 [<c06cd91e>] workqueue_cpu_down_callback+0x26/0x2d
 [<c06e9d65>] notifier_call_chain+0x45/0x60
 [<c0171cfe>] __raw_notifier_call_chain+0x1e/0x30
 [<c014c9b4>] __cpu_notify+0x24/0x40
 [<c06cbc6f>] _cpu_down+0xdf/0x330
 [<c06cbef0>] cpu_down+0x30/0x50
 [<c06cd6b0>] store_online+0x50/0xa7
 [<c06cd660>] ? acpi_os_map_memory+0xec/0xec
 [<c04f2faa>] sysdev_store+0x2a/0x40
 [<c02887a4>] sysfs_write_file+0xa4/0x100
 [<c0229ab2>] vfs_write+0xa2/0x170
 [<c0288700>] ? sysfs_poll+0x90/0x90
 [<c0229d92>] sys_write+0x42/0x70
 [<c06ecedf>] sysenter_do_call+0x12/0x2d
CPU 1 is now offline
SMP alternatives: switching to UP code
SMP alternatives: switching to SMP code
Booting Node 0 Processor 1 APIC 0x1
smpboot cpu 1: start_ip = 9b000
Initializing CPU#1
BUG: sleeping function called from invalid context at kernel/rtmutex.c:645
in_atomic(): 1, irqs_disabled(): 1, pid: 0, name: kworker/0:0
Pid: 0, comm: kworker/0:0 Not tainted 3.0.6-rt17-00284-gb76d419 #3
Call Trace:
 [<c06e3b5d>] ? printk+0x1d/0x20
 [<c01390b6>] __might_sleep+0xe6/0x110
 [<c06e633c>] rt_spin_lock+0x1c/0x30
 [<c06cd85b>] workqueue_cpu_up_callback+0x56/0xf3
 [<c06e9d65>] notifier_call_chain+0x45/0x60
 [<c0171cfe>] __raw_notifier_call_chain+0x1e/0x30
 [<c014c9b4>] __cpu_notify+0x24/0x40
 [<c014c9ec>] cpu_notify+0x1c/0x20
 [<c06e1d43>] notify_cpu_starting+0x1e/0x20
 [<c06e0aad>] smp_callin+0xfb/0x10e
 [<c06e0ad9>] start_secondary+0x19/0xd7
NMI watchdog enabled, takes one hw-pmu counter.
Switched to NOHz mode on CPU #1

Signed-off-by: Yong Zhang <yong.zhang0@xxxxxxxxx>
---
 kernel/workqueue.c |   12 ++++++++----
 1 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index e262f6b..ddbf89c 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3195,30 +3195,34 @@ static int __devinit workqueue_cpu_up_callback(struct notifier_block *nfb,
 	}
 
 	/* some are called w/ irq disabled, don't disturb irq status */
-	spin_lock_irqsave(&gcwq->lock, flags);
 
 	switch (action) {
 	case CPU_UP_PREPARE:
+		spin_lock_irqsave(&gcwq->lock, flags);
 		BUG_ON(gcwq->first_idle);
 		gcwq->first_idle = new_worker;
+		spin_unlock_irqrestore(&gcwq->lock, flags);
 		break;
 
 	case CPU_UP_CANCELED:
+		spin_lock_irqsave(&gcwq->lock, flags);
 		destroy_worker(gcwq->first_idle);
 		gcwq->first_idle = NULL;
+		spin_unlock_irqrestore(&gcwq->lock, flags);
 		break;
 
 	case CPU_ONLINE:
+		spin_lock_irqsave(&gcwq->lock, flags);
 		spin_unlock_irq(&gcwq->lock);
 		kthread_bind(gcwq->first_idle->task, cpu);
 		spin_lock_irq(&gcwq->lock);
 		gcwq->flags |= GCWQ_MANAGE_WORKERS;
 		start_worker(gcwq->first_idle);
 		gcwq->first_idle = NULL;
+		spin_unlock_irqrestore(&gcwq->lock, flags);
 		break;
 	}
 
-	spin_unlock_irqrestore(&gcwq->lock, flags);
 
 	return notifier_from_errno(0);
 }
@@ -3274,14 +3278,14 @@ static void flush_gcwq(struct global_cwq *gcwq)
 
 	spin_unlock_irq(&gcwq->lock);
 
-	gcwq = get_gcwq(get_cpu());
+	gcwq = get_gcwq(get_cpu_light());
 	spin_lock_irq(&gcwq->lock);
 	list_for_each_entry_safe(work, nw, &non_affine_works, entry) {
 		list_del_init(&work->entry);
 		___queue_work(get_work_cwq(work)->wq, gcwq, work);
 	}
 	spin_unlock_irq(&gcwq->lock);
-	put_cpu();
+	put_cpu_light();
 }
 
 static int __devinit workqueue_cpu_down_callback(struct notifier_block *nfb,
-- 
1.7.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/