[PATCH] watchdog/softlockup: Fix softlockup_stop_all() hungtask bug

[Jinhui Guo]

If NR_CPUS equal to 1, it would trigger hungtask, it can be
triggered by follow command:
	echo 0 > /proc/sys/kernel/watchdog
	echo 1 > /proc/sys/kernel/watchdog
The hungtask stack:
	__schedule
	schedule
	schedule_timeout
	__wait_for_common
	softlockup_stop_fn
	lockup_detector_reconfigure
	proc_watchdog_common
	proc_watchdog
	proc_sys_call_handler
	vfs_write
	ksys_write
The watchdog_allowed_mask is completely cleared when the
watchdog is disabled. But the macro for_each_cpu() assume
all masks are "1" when macro NR_CPUS equal to 1. It makes
watchdog_allowed_mask not work at all.

Fixes: be45bf5395e0 ("watchdog/softlockup: Fix cpu_stop_queue_work() double-queue bug")

Cc: Petr Mladek <pmladek@xxxxxxxx>
Reported-by: kernel test robot <lkp@xxxxxxxxx>
Signed-off-by: Jinhui Guo <guojinhui@xxxxxxxxxx>
---
 arch/x86/include/asm/smp.h | 5 +++++
 include/linux/cpumask.h    | 5 +++--
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 630ff08532be..f5d3ca5696b3 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -21,7 +21,12 @@ DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number);
 
 static inline struct cpumask *cpu_llc_shared_mask(int cpu)
 {
+#ifdef CONFIG_SMP
 	return per_cpu(cpu_llc_shared_map, cpu);
+#else
+	/* cpu_llc_shared_map is not defined while !CONFIG_SMP */
+	return cpu_all_mask;
+#endif
 }
 
 DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid);
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 5d4d07a9e1ed..1a35dbcc397d 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -175,10 +175,11 @@ static inline int cpumask_any_distribute(const struct cpumask *srcp)
 	return cpumask_first(srcp);
 }
 
+/* It should check cpumask in some special case, such as watchdog */
 #define for_each_cpu(cpu, mask)			\
-	for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask)
+	for ((cpu) = 0; (cpu) < 1 && test_bit(0, cpumask_bits(mask)); (cpu)++)
 #define for_each_cpu_not(cpu, mask)		\
-	for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask)
+	for ((cpu) = 0; (cpu) < 1 && !test_bit(0, cpumask_bits(mask)); (cpu)++)
 #define for_each_cpu_wrap(cpu, mask, start)	\
 	for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask, (void)(start))
 #define for_each_cpu_and(cpu, mask1, mask2)	\
-- 
2.12.3