KVM: x86: Fix a possible backwards warp of kvmclock

(backported from commit 1d5f066e0b63271b67eac6d3752f8aa96adcbddb)

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>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
BugLink: http://bugs.launchpad.net/bugs/714335
Signed-off-by: Serge E. Hallyn <serge.hallyn@canonical.com>
Reviewed-by: Stefan Bader <stefan.bader@canonical.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 600807b3d3650420c1aac56b10b69cc9abd15deb..08bc2ff8dcc8e436b85e0981cd0ee0d51f098af7 100644 (file)
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -357,6 +357,9 @@ struct kvm_vcpu_arch {
        struct page *time_page;
 
        bool singlestep; /* guest is single stepped by KVM */
+       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 b2c02a2b00381ca22e47df3180d03980fcf810c7..8a10f27233af46d03f814449b703de3f2929c7ed 100644 (file)
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -47,6 +47,7 @@
 #include <asm/desc.h>
 #include <asm/mtrr.h>
 #include <asm/mce.h>
+#include <asm/pvclock.h>
 
 #define MAX_IO_MSRS 256
 #define CR0_RESERVED_BITS                                              \
@@ -633,6 +634,8 @@ static void 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, max_kernel_ns;
+       u64 tsc_timestamp;
 
        if ((!vcpu->time_page))
                return;
@@ -646,15 +649,51 @@ static void kvm_write_guest_time(struct kvm_vcpu *v)
 
        /* 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);
        ktime_get_ts(&ts);
        monotonic_to_bootbased(&ts);
+       kernel_ns = timespec_to_ns(&ts);
        local_irq_restore(flags);
 
+       /*
+        * 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 (max_kernel_ns > kernel_ns)
+               kernel_ns = max_kernel_ns;
+
        /* With all the info we got, fill in the values */
 
-       vcpu->hv_clock.system_time = ts.tv_nsec +
-                                    (NSEC_PER_SEC * (u64)ts.tv_sec) + v->kvm->arch.kvmclock_offset;
+       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;
 
        /*
         * The interface expects us to write an even number signaling that the
@@ -3695,6 +3734,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
        kvm_x86_ops->prepare_guest_switch(vcpu);
        kvm_load_guest_fpu(vcpu);
 
+       kvm_get_msr(vcpu, MSR_IA32_TSC, &vcpu->arch.last_guest_tsc);
+
        local_irq_disable();
 
        clear_bit(KVM_REQ_KICK, &vcpu->requests);