Subject: printk: Don't call printk_tick in printk_needs_cpu() on RT

printk_tick() can't be called in atomic context when RT is enabled,
otherwise below warning will show:

[  117.597095] BUG: sleeping function called from invalid context at kernel/rtmutex.c:645
[  117.597102] in_atomic(): 1, irqs_disabled(): 1, pid: 0, name: kworker/0:0
[  117.597111] Pid: 0, comm: kworker/0:0 Not tainted 3.0.6-rt17-00284-gb76d419-dirty raspberrypi#7
[  117.597116] Call Trace:
[  117.597131]  [<c06e3b61>] ? printk+0x1d/0x24
[  117.597142]  [<c01390b6>] __might_sleep+0xe6/0x110
[  117.597151]  [<c06e634c>] rt_spin_lock+0x1c/0x30
[  117.597158]  [<c0142f26>] __wake_up+0x26/0x60
[  117.597166]  [<c014c78e>] printk_tick+0x3e/0x40
[  117.597173]  [<c014c7b4>] printk_needs_cpu+0x24/0x30
[  117.597181]  [<c017ecc8>] tick_nohz_stop_sched_tick+0x2e8/0x410
[  117.597191]  [<c017305a>] ? sched_clock_idle_wakeup_event+0x1a/0x20
[  117.597201]  [<c010182a>] cpu_idle+0x4a/0xb0
[  117.597209]  [<c06e0b97>] start_secondary+0xd3/0xd7

Now this is a really rare case and it's very unlikely that we starve
an logbuf waiter that way.

Signed-off-by: Yong Zhang <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Thomas Gleixner <[email protected]>

Author: yongzhang0

kernel/printk.c

@@ -2027,8 +2027,8 @@ void printk_tick(void)
 
 int printk_needs_cpu(int cpu)
 {
-	if (cpu_is_offline(cpu))
-		printk_tick();
+	if (unlikely(cpu_is_offline(cpu)))
+		__this_cpu_write(printk_pending, 0);
 	return __this_cpu_read(printk_pending);
 }