summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--arch/x86/kernel/tsc_32.c15
-rw-r--r--arch/x86/kernel/tsc_64.c23
-rw-r--r--kernel/time/timekeeping.c2
3 files changed, 36 insertions, 4 deletions
diff --git a/arch/x86/kernel/tsc_32.c b/arch/x86/kernel/tsc_32.c
index 06af8cf8251f..e4790728b224 100644
--- a/arch/x86/kernel/tsc_32.c
+++ b/arch/x86/kernel/tsc_32.c
@@ -284,14 +284,27 @@ core_initcall(cpufreq_tsc);
/* clock source code */
static unsigned long current_tsc_khz;
+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 ceeba01e7f47..fcc16e58609e 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;
@@ -287,18 +288,34 @@ 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 = {
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index a3fa587c350c..2d6087c7cf98 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -178,6 +178,7 @@ static void change_clocksource(void)
if (clock == new)
return;
+ new->cycle_last = 0;
now = clocksource_read(new);
nsec = __get_nsec_offset();
timespec_add_ns(&xtime, nsec);
@@ -295,6 +296,7 @@ static int timekeeping_resume(struct sys_device *dev)
timespec_add_ns(&xtime, timekeeping_suspend_nsecs);
update_xtime_cache(0);
/* re-base the last cycle value */
+ clock->cycle_last = 0;
clock->cycle_last = clocksource_read(clock);
clock->error = 0;
timekeeping_suspended = 0;