lkml.org 
[lkml]   [2010]   [Jul]   [12]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH 14/18] Fix a possible backwards warp of kvmclock
Date
Kernel time, which advances in discrete steps may progress much slower
than TSC. As a result, when kvmclock is adjusted to a new base, the
apparent time to the guest, which runs at a much higher, nsec scaled
rate based on the current TSC, may have already been observed to have
a larger value (kernel_ns + scaled tsc) than the value to which we are
setting it (kernel_ns + 0).

We must instead compute the clock as potentially observed by the guest
for kernel_ns to make sure it does not go backwards.

Signed-off-by: Zachary Amsden <zamsden@redhat.com>
---
arch/x86/include/asm/kvm_host.h | 2 +
arch/x86/kvm/x86.c | 43 +++++++++++++++++++++++++++++++++++++-
2 files changed, 43 insertions(+), 2 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index d9e0aa0..94dd16b 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -340,6 +340,8 @@ struct kvm_vcpu_arch {
struct page *time_page;
u64 last_host_tsc;
u64 last_host_ns;
+ u64 last_guest_tsc;
+ u64 last_kernel_ns;

bool nmi_pending;
bool nmi_injected;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 574cb69..7b9fdf3 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -973,14 +973,15 @@ static int kvm_write_guest_time(struct kvm_vcpu *v)
struct kvm_vcpu_arch *vcpu = &v->arch;
void *shared_kaddr;
unsigned long this_tsc_khz;
- s64 kernel_ns;
+ s64 kernel_ns, max_kernel_ns;
+ u64 tsc_timestamp;

if ((!vcpu->time_page))
return 0;

/* Keep irq disabled to prevent changes to the clock */
local_irq_save(flags);
- kvm_get_msr(v, MSR_IA32_TSC, &vcpu->hv_clock.tsc_timestamp);
+ kvm_get_msr(v, MSR_IA32_TSC, &tsc_timestamp);
kernel_ns = get_kernel_ns();
this_tsc_khz = __get_cpu_var(cpu_tsc_khz);
local_irq_restore(flags);
@@ -990,13 +991,49 @@ static int kvm_write_guest_time(struct kvm_vcpu *v)
return 1;
}

+ /*
+ * Time as measured by the TSC may go backwards when resetting the base
+ * tsc_timestamp. The reason for this is that the TSC resolution is
+ * higher than the resolution of the other clock scales. Thus, many
+ * possible measurments of the TSC correspond to one measurement of any
+ * other clock, and so a spread of values is possible. This is not a
+ * problem for the computation of the nanosecond clock; with TSC rates
+ * around 1GHZ, there can only be a few cycles which correspond to one
+ * nanosecond value, and any path through this code will inevitably
+ * take longer than that. However, with the kernel_ns value itself,
+ * the precision may be much lower, down to HZ granularity. If the
+ * first sampling of TSC against kernel_ns ends in the low part of the
+ * range, and the second in the high end of the range, we can get:
+ *
+ * (TSC - offset_low) * S + kns_old > (TSC - offset_high) * S + kns_new
+ *
+ * As the sampling errors potentially range in the thousands of cycles,
+ * it is possible such a time value has already been observed by the
+ * guest. To protect against this, we must compute the system time as
+ * observed by the guest and ensure the new system time is greater.
+ */
+ max_kernel_ns = 0;
+ if (vcpu->hv_clock.tsc_timestamp && vcpu->last_guest_tsc) {
+ max_kernel_ns = vcpu->last_guest_tsc -
+ vcpu->hv_clock.tsc_timestamp;
+ max_kernel_ns = pvclock_scale_delta(max_kernel_ns,
+ vcpu->hv_clock.tsc_to_system_mul,
+ vcpu->hv_clock.tsc_shift);
+ max_kernel_ns += vcpu->last_kernel_ns;
+ }
+
if (unlikely(vcpu->hw_tsc_khz != this_tsc_khz)) {
kvm_set_time_scale(this_tsc_khz, &vcpu->hv_clock);
vcpu->hw_tsc_khz = this_tsc_khz;
}

+ if (max_kernel_ns > kernel_ns)
+ kernel_ns = max_kernel_ns;
+
/* With all the info we got, fill in the values */
+ vcpu->hv_clock.tsc_timestamp = tsc_timestamp;
vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset;
+ vcpu->last_kernel_ns = kernel_ns;
vcpu->hv_clock.flags = 0;

/*
@@ -4917,6 +4954,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
if (hw_breakpoint_active())
hw_breakpoint_restore();

+ kvm_get_msr(vcpu, MSR_IA32_TSC, &vcpu->arch.last_guest_tsc);
+
atomic_set(&vcpu->guest_mode, 0);
smp_wmb();
local_irq_enable();
--
1.7.1


\
 
 \ /
  Last update: 2010-07-13 04:35    [from the cache]
©2003-2011 Jasper Spaans