nmi: fix clock comparator revalidation

commit e8129c642155616d9e2160a75f103e127c8c3708 upstream.

On each machine check all registers are revalidated. The save area for
the clock comparator however only contains the upper most seven bytes
of the former contents, if valid.
Therefore the machine check handler uses a store clock instruction to
get the current time and writes that to the clock comparator register
which in turn will generate an immediate timer interrupt.
However within the lowcore the expected time of the next timer
interrupt is stored. If the interrupt happens before that time the
handler won't be called. In turn the clock comparator won't be
reprogrammed and therefore the interrupt condition stays pending which
causes an interrupt loop until the expected time is reached.

On NOHZ machines this can result in unresponsive machines since the
time of the next expected interrupted can be a couple of days in the
future.

To fix this just revalidate the clock comparator register with the
expected value.
In addition the special handling for udelay must be changed as well.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Signed-off-by: Andi Kleen <ak@linux.intel.com>

2 files changed, 13 insertions, 11 deletions

diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index ac151399ef34..1995c1712fc8 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -95,7 +95,6 @@ EXPORT_SYMBOL_GPL(s390_handle_mcck);
 static int notrace s390_revalidate_registers(struct mci *mci)
 {
 	int kill_task;
-	u64 tmpclock;
 	u64 zero;
 	void *fpt_save_area, *fpt_creg_save_area;
 
@@ -214,11 +213,10 @@ static int notrace s390_revalidate_registers(struct mci *mci)
 			: "0", "cc");
 #endif
 	/* Revalidate clock comparator register */
-	asm volatile(
-		"	stck	0(%1)\n"
-		"	sckc	0(%1)"
-		: "=m" (tmpclock) : "a" (&(tmpclock)) : "cc", "memory");
-
+	if (S390_lowcore.clock_comparator == -1)
+		set_clock_comparator(S390_lowcore.mcck_clock);
+	else
+		set_clock_comparator(S390_lowcore.clock_comparator);
 	/* Check if old PSW is valid */
 	if (!mci->wp)
 		/*
diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c
index 752b362bf651..7c37ec359ec2 100644
--- a/arch/s390/lib/delay.c
+++ b/arch/s390/lib/delay.c
@@ -29,17 +29,21 @@ static void __udelay_disabled(unsigned long long usecs)
 {
 	unsigned long mask, cr0, cr0_saved;
 	u64 clock_saved;
+	u64 end;
 
+	mask = psw_kernel_bits | PSW_MASK_WAIT | PSW_MASK_EXT;
+	end = get_clock() + (usecs << 12);
 	clock_saved = local_tick_disable();
-	set_clock_comparator(get_clock() + (usecs << 12));
 	__ctl_store(cr0_saved, 0, 0);
 	cr0 = (cr0_saved & 0xffff00e0) | 0x00000800;
 	__ctl_load(cr0 , 0, 0);
-	mask = psw_kernel_bits | PSW_MASK_WAIT | PSW_MASK_EXT;
 	lockdep_off();
-	trace_hardirqs_on();
-	__load_psw_mask(mask);
-	local_irq_disable();
+	do {
+		set_clock_comparator(end);
+		trace_hardirqs_on();
+		__load_psw_mask(mask);
+		local_irq_disable();
+	} while (get_clock() < end);
 	lockdep_on();
 	__ctl_load(cr0_saved, 0, 0);
 	local_tick_enable(clock_saved);