s390/time: fix sched_clock() overflow

Converting a 64 Bit TOD format value to nanoseconds means that the value
must be divided by 4.096. In order to achieve that we multiply with 125
and divide by 512.
When used within sched_clock() this triggers an overflow after appr.
417 days. Resulting in a sched_clock() return value that is much smaller
than previously and therefore may cause all sort of weird things in
subsystems that rely on a monotonic sched_clock() behaviour.

To fix this implement a tod_to_ns() helper function which converts TOD
values without overflow and call this function from both places that
open coded the conversion: sched_clock() and kvm_s390_handle_wait().

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

diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h
index fba4d66788a247c94adfba5c13ae750e19929496..4c060bb5b8eafbfc5b816411dc91f9dea1201daf 100644 (file)
--- a/arch/s390/include/asm/timex.h
+++ b/arch/s390/include/asm/timex.h
@@ -128,4 +128,32 @@ static inline unsigned long long get_clock_monotonic(void)
        return get_clock_xt() - sched_clock_base_cc;
 }
 
+/**
+ * tod_to_ns - convert a TOD format value to nanoseconds
+ * @todval: to be converted TOD format value
+ * Returns: number of nanoseconds that correspond to the TOD format value
+ *
+ * Converting a 64 Bit TOD format value to nanoseconds means that the value
+ * must be divided by 4.096. In order to achieve that we multiply with 125
+ * and divide by 512:
+ *
+ *    ns = (todval * 125) >> 9;
+ *
+ * In order to avoid an overflow with the multiplication we can rewrite this.
+ * With a split todval == 2^32 * th + tl (th upper 32 bits, tl lower 32 bits)
+ * we end up with
+ *
+ *    ns = ((2^32 * th + tl) * 125 ) >> 9;
+ * -> ns = (2^23 * th * 125) + ((tl * 125) >> 9);
+ *
+ */
+static inline unsigned long long tod_to_ns(unsigned long long todval)
+{
+       unsigned long long ns;
+
+       ns = ((todval >> 32) << 23) * 125;
+       ns += ((todval & 0xffffffff) * 125) >> 9;
+       return ns;
+}
+
 #endif

diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index aff0e350d776cbc65d68ec11e5aa6418fe4d0651..a5f4f5a1d24b951ac8e7e10cc9af81e153208c63 100644 (file)
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -63,7 +63,7 @@ static DEFINE_PER_CPU(struct clock_event_device, comparators);
  */
 unsigned long long notrace __kprobes sched_clock(void)
 {
-       return (get_clock_monotonic() * 125) >> 9;
+       return tod_to_ns(get_clock_monotonic());
 }
 
 /*

diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index c30615e605ac6716a1f93ee8dc377f9691ee99e0..82c481ddef76286c9be88ce0e45e4df31780eb5d 100644 (file)
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -408,7 +408,7 @@ int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
                return 0;
        }
 
-       sltime = ((vcpu->arch.sie_block->ckc - now)*125)>>9;
+       sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
 
        hrtimer_start(&vcpu->arch.ckc_timer, ktime_set (0, sltime) , HRTIMER_MODE_REL);
        VCPU_EVENT(vcpu, 5, "enabled wait via clock comparator: %llx ns", sltime);