2 files changed, 34 insertions, 4 deletions

diff --git a/arch/x86/kernel/tsc_32.c b/arch/x86/kernel/tsc_32.c
index f14cfd9d1f94..d7498b34c8e9 100644
--- a/arch/x86/kernel/tsc_32.c
+++ b/arch/x86/kernel/tsc_32.c
@@ -287,14 +287,27 @@ core_initcall(cpufreq_tsc);
 /* clock source code */
 
 static unsigned long current_tsc_khz = 0;
+static struct clocksource clocksource_tsc;
 
+/*
+ * We compare the TSC to the cycle_last value in the clocksource
+ * structure to avoid a nasty time-warp issue. This can be observed in
+ * a very small window right after one CPU updated cycle_last under
+ * xtime lock and the other CPU reads a TSC value which is smaller
+ * than the cycle_last reference value due to a TSC which is slighty
+ * behind. This delta is nowhere else observable, but in that case it
+ * results in a forward time jump in the range of hours due to the
+ * unsigned delta calculation of the time keeping core code, which is
+ * necessary to support wrapping clocksources like pm timer.
+ */
 static cycle_t read_tsc(void)
 {
 	cycle_t ret;
 
 	rdtscll(ret);
 
-	return ret;
+	return ret >= clocksource_tsc.cycle_last ?
+		ret : clocksource_tsc.cycle_last;
 }
 
 static struct clocksource clocksource_tsc = {
diff --git a/arch/x86/kernel/tsc_64.c b/arch/x86/kernel/tsc_64.c
index 947554ddabb6..01fc9f0c39e2 100644
--- a/arch/x86/kernel/tsc_64.c
+++ b/arch/x86/kernel/tsc_64.c
@@ -11,6 +11,7 @@
 #include <asm/hpet.h>
 #include <asm/timex.h>
 #include <asm/timer.h>
+#include <asm/vgtod.h>
 
 static int notsc __initdata = 0;
 
@@ -290,18 +291,34 @@ int __init notsc_setup(char *s)
 
 __setup("notsc", notsc_setup);
 
+static struct clocksource clocksource_tsc;
 
-/* clock source code: */
+/*
+ * We compare the TSC to the cycle_last value in the clocksource
+ * structure to avoid a nasty time-warp. This can be observed in a
+ * very small window right after one CPU updated cycle_last under
+ * xtime/vsyscall_gtod lock and the other CPU reads a TSC value which
+ * is smaller than the cycle_last reference value due to a TSC which
+ * is slighty behind. This delta is nowhere else observable, but in
+ * that case it results in a forward time jump in the range of hours
+ * due to the unsigned delta calculation of the time keeping core
+ * code, which is necessary to support wrapping clocksources like pm
+ * timer.
+ */
 static cycle_t read_tsc(void)
 {
 	cycle_t ret = (cycle_t)get_cycles();
-	return ret;
+
+	return ret >= clocksource_tsc.cycle_last ?
+		ret : clocksource_tsc.cycle_last;
 }
 
 static cycle_t __vsyscall_fn vread_tsc(void)
 {
 	cycle_t ret = (cycle_t)vget_cycles();
-	return ret;
+
+	return ret >= __vsyscall_gtod_data.clock.cycle_last ?
+		ret : __vsyscall_gtod_data.clock.cycle_last;
 }
 
 static struct clocksource clocksource_tsc = {