s390/udelay: make udelay have busy loop semantics

When using systemtap it was observed that our udelay implementation is
rather suboptimal if being called from a kprobe handler installed by
systemtap.

The problem observed when a kprobe was installed on lock_acquired().
When the probe was hit the kprobe handler did call udelay, which set
up an (internal) timer and reenabled interrupts (only the clock comparator
interrupt) and waited for the interrupt.
This is an optimization to avoid that the cpu is busy looping while waiting
that enough time passes. The problem is that the interrupt handler still
does call irq_enter()/irq_exit() which then again can lead to a deadlock,
since some accounting functions may take locks as well.

If one of these locks is the same, which caused lock_acquired() to be
called, we have a nice deadlock.

This patch reworks the udelay code for the interrupts disabled case to
immediately leave the low level interrupt handler when the clock
comparator interrupt happens. That way no C code is being called and the
deadlock cannot happen anymore.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Reviewed-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

1 files changed, 14 insertions, 16 deletions

diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c
index 246a7eb..501dcd4 100644
--- a/arch/s390/lib/delay.c
+++ b/arch/s390/lib/delay.c
@@ -12,8 +12,10 @@
 #include <linux/module.h>
 #include <linux/irqflags.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <asm/vtimer.h>
 #include <asm/div64.h>
+#include <asm/idle.h>
 
 void __delay(unsigned long loops)
 {
@@ -30,26 +32,22 @@ EXPORT_SYMBOL(__delay);
 
 static void __udelay_disabled(unsigned long long usecs)
 {
-	unsigned long cr0, cr6, new;
-	u64 clock_saved, end;
+	unsigned long cr0, cr0_new, psw_mask;
+	struct s390_idle_data idle;
+	u64 end;
 
 	end = get_tod_clock() + (usecs << 12);
-	clock_saved = local_tick_disable();
 	__ctl_store(cr0, 0, 0);
-	__ctl_store(cr6, 6, 6);
-	new = (cr0 &  0xffff00e0) | 0x00000800;
-	__ctl_load(new , 0, 0);
-	new = 0;
-	__ctl_load(new, 6, 6);
-	lockdep_off();
-	do {
-		set_clock_comparator(end);
-		enabled_wait();
-	} while (get_tod_clock_fast() < end);
-	lockdep_on();
+	cr0_new = cr0 & ~CR0_IRQ_SUBCLASS_MASK;
+	cr0_new |= (1UL << (63 - 52)); /* enable clock comparator irq */
+	__ctl_load(cr0_new, 0, 0);
+	psw_mask = __extract_psw() | PSW_MASK_EXT | PSW_MASK_WAIT;
+	set_clock_comparator(end);
+	set_cpu_flag(CIF_IGNORE_IRQ);
+	psw_idle(&idle, psw_mask);
+	clear_cpu_flag(CIF_IGNORE_IRQ);
+	set_clock_comparator(S390_lowcore.clock_comparator);
 	__ctl_load(cr0, 0, 0);
-	__ctl_load(cr6, 6, 6);
-	local_tick_enable(clock_saved);
 }
 
 static void __udelay_enabled(unsigned long long usecs)