x86/rtc: Don't recursively acquire rtc_lock

A deadlock was introduced on x86 in commit ef68c8f87ed1 ("x86:
Serialize EFI time accesses on rtc_lock") because efi_get_time()
and friends can be called with rtc_lock already held by
read_persistent_time(), e.g.:

 timekeeping_init()
    read_persistent_clock()     <-- acquire rtc_lock
        efi_get_time()
            phys_efi_get_time() <-- acquire rtc_lock <DEADLOCK>

To fix this let's push the locking down into the get_wallclock()
and set_wallclock() implementations.  Only the clock
implementations that access the x86 RTC directly need to acquire
rtc_lock, so it makes sense to push the locking down into the
rtc, vrtc and efi code.

The virtualization implementations don't require rtc_lock to be
held because they provide their own serialization.

Signed-off-by: Matt Fleming <matt.fleming@intel.com>
Acked-by: Jan Beulich <jbeulich@novell.com>
Acked-by: Avi Kivity <avi@redhat.com> [for the virtualization aspect]
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Zhang Rui <rui.zhang@intel.com>
Cc: Josh Boyer <jwboyer@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 12 insertions, 11 deletions

diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 3f2ad2640d85..ccdbc16b8941 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -42,8 +42,11 @@ int mach_set_rtc_mmss(unsigned long nowtime)
 {
 	int real_seconds, real_minutes, cmos_minutes;
 	unsigned char save_control, save_freq_select;
+	unsigned long flags;
 	int retval = 0;
 
+	spin_lock_irqsave(&rtc_lock, flags);
+
 	 /* tell the clock it's being set */
 	save_control = CMOS_READ(RTC_CONTROL);
 	CMOS_WRITE((save_control|RTC_SET), RTC_CONTROL);
@@ -93,12 +96,17 @@ int mach_set_rtc_mmss(unsigned long nowtime)
 	CMOS_WRITE(save_control, RTC_CONTROL);
 	CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT);
 
+	spin_unlock_irqrestore(&rtc_lock, flags);
+
 	return retval;
 }
 
 unsigned long mach_get_cmos_time(void)
 {
 	unsigned int status, year, mon, day, hour, min, sec, century = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&rtc_lock, flags);
 
 	/*
 	 * If UIP is clear, then we have >= 244 microseconds before
@@ -125,6 +133,8 @@ unsigned long mach_get_cmos_time(void)
 	status = CMOS_READ(RTC_CONTROL);
 	WARN_ON_ONCE(RTC_ALWAYS_BCD && (status & RTC_DM_BINARY));
 
+	spin_unlock_irqrestore(&rtc_lock, flags);
+
 	if (RTC_ALWAYS_BCD || !(status & RTC_DM_BINARY)) {
 		sec = bcd2bin(sec);
 		min = bcd2bin(min);
@@ -169,24 +179,15 @@ EXPORT_SYMBOL(rtc_cmos_write);
 
 int update_persistent_clock(struct timespec now)
 {
-	unsigned long flags;
-	int retval;
-
-	spin_lock_irqsave(&rtc_lock, flags);
-	retval = x86_platform.set_wallclock(now.tv_sec);
-	spin_unlock_irqrestore(&rtc_lock, flags);
-
-	return retval;
+	return x86_platform.set_wallclock(now.tv_sec);
 }
 
 /* not static: needed by APM */
 void read_persistent_clock(struct timespec *ts)
 {
-	unsigned long retval, flags;
+	unsigned long retval;
 
-	spin_lock_irqsave(&rtc_lock, flags);
 	retval = x86_platform.get_wallclock();
-	spin_unlock_irqrestore(&rtc_lock, flags);
 
 	ts->tv_sec = retval;
 	ts->tv_nsec = 0;