From: Munehisa Kamata <[email protected]>
Currently, steal time accounting code in scheduler expects steal clock
callback to provide monotonically increasing value. If the accounting
code receives a smaller value than previous one, it uses a negative
value to calculate steal time and results in incorrectly updated idle
and steal time accounting. This breaks userspace tools which read
/proc/stat.
top - 08:05:35 up 2:12, 3 users, load average: 0.00, 0.07, 0.23
Tasks: 80 total, 1 running, 79 sleeping, 0 stopped, 0 zombie
Cpu(s): 0.0%us, 0.0%sy, 0.0%ni,30100.0%id, 0.0%wa, 0.0%hi, 0.0%si,
-1253874204672.0%st
This can actually happen when a Xen PVHVM guest gets restored from
hibernation, because such a restored guest is just a fresh domain from
Xen perspective and the time information in runstate info starts over
from scratch.
Introduce xen_save_steal_clock() which saves current steal clock values
of all present CPUs in runstate info into per-cpu variables during system
core ops suspend callbacks. Its couterpart, xen_restore_steal_clock(),
restores a boot CPU's steal clock in the system core resume callback. It
sets offset if it found the current values in runstate info are smaller
than previous ones. xen_steal_clock() is also modified to use the offset
to ensure that scheduler only sees monotonically increasing number.
For non-boot CPUs, restore after they're brought up, because runstate
info for non-boot CPUs are not active until then.
[Anchal Changelog: Merged patch xen/time: introduce xen_{save,restore}_steal_clock
with this one for better code readability]
Signed-off-by: Anchal Agarwal <[email protected]>
Signed-off-by: Munehisa Kamata <[email protected]>
---
arch/x86/xen/suspend.c | 13 ++++++++++++-
arch/x86/xen/time.c | 3 +++
drivers/xen/time.c | 28 +++++++++++++++++++++++++++-
include/xen/xen-ops.h | 2 ++
4 files changed, 44 insertions(+), 2 deletions(-)
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index 784c4484100b..dae0f74f5390 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -91,12 +91,20 @@ void xen_arch_suspend(void)
static int xen_syscore_suspend(void)
{
struct xen_remove_from_physmap xrfp;
- int ret;
+ int cpu, ret;
/* Xen suspend does similar stuffs in its own logic */
if (xen_suspend_mode_is_xen_suspend())
return 0;
+ for_each_present_cpu(cpu) {
+ /*
+ * Nonboot CPUs are already offline, but the last copy of
+ * runstate info is still accessible.
+ */
+ xen_save_steal_clock(cpu);
+ }
+
xrfp.domid = DOMID_SELF;
xrfp.gpfn = __pa(HYPERVISOR_shared_info) >> PAGE_SHIFT;
@@ -118,6 +126,9 @@ static void xen_syscore_resume(void)
pvclock_resume();
+ /* Nonboot CPUs will be resumed when they're brought up */
+ xen_restore_steal_clock(smp_processor_id());
+
gnttab_resume();
}
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index befbdd8b17f0..8cf632dda605 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -537,6 +537,9 @@ static void xen_hvm_setup_cpu_clockevents(void)
{
int cpu = smp_processor_id();
xen_setup_runstate_info(cpu);
+ if (cpu)
+ xen_restore_steal_clock(cpu);
+
/*
* xen_setup_timer(cpu) - snprintf is bad in atomic context. Hence
* doing it xen_hvm_cpu_notify (which gets called by smp_init during
diff --git a/drivers/xen/time.c b/drivers/xen/time.c
index 0968859c29d0..3713d716070c 100644
--- a/drivers/xen/time.c
+++ b/drivers/xen/time.c
@@ -20,6 +20,8 @@
/* runstate info updated by Xen */
static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate);
+static DEFINE_PER_CPU(u64, xen_prev_steal_clock);
+static DEFINE_PER_CPU(u64, xen_steal_clock_offset);
static DEFINE_PER_CPU(u64[4], old_runstate_time);
@@ -149,7 +151,7 @@ bool xen_vcpu_stolen(int vcpu)
return per_cpu(xen_runstate, vcpu).state == RUNSTATE_runnable;
}
-u64 xen_steal_clock(int cpu)
+static u64 __xen_steal_clock(int cpu)
{
struct vcpu_runstate_info state;
@@ -157,6 +159,30 @@ u64 xen_steal_clock(int cpu)
return state.time[RUNSTATE_runnable] + state.time[RUNSTATE_offline];
}
+u64 xen_steal_clock(int cpu)
+{
+ return __xen_steal_clock(cpu) + per_cpu(xen_steal_clock_offset, cpu);
+}
+
+void xen_save_steal_clock(int cpu)
+{
+ per_cpu(xen_prev_steal_clock, cpu) = xen_steal_clock(cpu);
+}
+
+void xen_restore_steal_clock(int cpu)
+{
+ u64 steal_clock = __xen_steal_clock(cpu);
+
+ if (per_cpu(xen_prev_steal_clock, cpu) > steal_clock) {
+ /* Need to update the offset */
+ per_cpu(xen_steal_clock_offset, cpu) =
+ per_cpu(xen_prev_steal_clock, cpu) - steal_clock;
+ } else {
+ /* Avoid unnecessary steal clock warp */
+ per_cpu(xen_steal_clock_offset, cpu) = 0;
+ }
+}
+
void xen_setup_runstate_info(int cpu)
{
struct vcpu_register_runstate_memory_area area;
diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h
index 3b3992b5b0c2..12b3f4474a05 100644
--- a/include/xen/xen-ops.h
+++ b/include/xen/xen-ops.h
@@ -37,6 +37,8 @@ void xen_time_setup_guest(void);
void xen_manage_runstate_time(int action);
void xen_get_runstate_snapshot(struct vcpu_runstate_info *res);
u64 xen_steal_clock(int cpu);
+void xen_save_steal_clock(int cpu);
+void xen_restore_steal_clock(int cpu);
int xen_setup_shutdown_event(void);
--
2.15.3.AMZN