KVM: Improve TSC offset matching

There are a few improvements that can be made to the TSC offset
matching code.  First, we don't need to call the 128-bit multiply
(especially on a constant number), the code works much nicer to
do computation in nanosecond units.

Second, the way everything is setup with software TSC rate scaling,
we currently have per-cpu rates.  Obviously this isn't too desirable
to use in practice, but if for some reason we do change the rate of
all VCPUs at runtime, then reset the TSCs, we will only want to
match offsets for VCPUs running at the same rate.

Finally, for the case where we have an unstable host TSC, but
rate scaling is being done in hardware, we should call the platform
code to compute the TSC offset, so the math is reorganized to recompute
the base instead, then transform the base into an offset using the
existing API.

[avi: fix 64-bit division on i386]

Signed-off-by: Zachary Amsden <zamsden@gmail.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

KVM: Fix 64-bit division in kvm_write_tsc()

Breaks i386 build.

Signed-off-by: Avi Kivity <avi@redhat.com>

2 files changed, 30 insertions, 15 deletions

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index ddebbe01fff9..8a34fca6c572 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -513,6 +513,7 @@ struct kvm_arch {
         u64 last_tsc_nsec;
         u64 last_tsc_offset;
         u64 last_tsc_write;
+        u32 last_tsc_khz;
 
         struct kvm_xen_hvm_config xen_hvm_config;
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 41bb90acb238..4390f42b371f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1025,33 +1025,46 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data)
         struct kvm *kvm = vcpu->kvm;
         u64 offset, ns, elapsed;
         unsigned long flags;
-        s64 sdiff;
+        s64 nsdiff;
 
         raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
         offset = kvm_x86_ops->compute_tsc_offset(vcpu, data);
         ns = get_kernel_ns();
         elapsed = ns - kvm->arch.last_tsc_nsec;
-        sdiff = data - kvm->arch.last_tsc_write;
-        if (sdiff < 0)
-                sdiff = -sdiff;
+
+        /* n.b - signed multiplication and division required */
+        nsdiff = data - kvm->arch.last_tsc_write;
+#ifdef CONFIG_X86_64
+        nsdiff = (nsdiff * 1000) / vcpu->arch.virtual_tsc_khz;
+#else
+        /* do_div() only does unsigned */
+        asm("idivl %2; xor %%edx, %%edx"
+            : "=A"(nsdiff)
+            : "A"(nsdiff * 1000), "rm"(vcpu->arch.virtual_tsc_khz));
+#endif
+        nsdiff -= elapsed;
+        if (nsdiff < 0)
+                nsdiff = -nsdiff;
 
         /*
-         * Special case: close write to TSC within 5 seconds of
-         * another CPU is interpreted as an attempt to synchronize
-         * The 5 seconds is to accommodate host load / swapping as
-         * well as any reset of TSC during the boot process.
-         *
-         * In that case, for a reliable TSC, we can match TSC offsets,
-         * or make a best guest using elapsed value.
-         */
-        if (sdiff < nsec_to_cycles(vcpu, 5ULL * NSEC_PER_SEC) &&
-            elapsed < 5ULL * NSEC_PER_SEC) {
+         * Special case: TSC write with a small delta (1 second) of virtual
+         * cycle time against real time is interpreted as an attempt to
+         * synchronize the CPU.
+         *
+         * For a reliable TSC, we can match TSC offsets, and for an unstable
+         * TSC, we add elapsed time in this computation.  We could let the
+         * compensation code attempt to catch up if we fall behind, but
+         * it's better to try to match offsets from the beginning.
+         */
+        if (nsdiff < NSEC_PER_SEC &&
+            vcpu->arch.virtual_tsc_khz == kvm->arch.last_tsc_khz) {
                 if (!check_tsc_unstable()) {
                         offset = kvm->arch.last_tsc_offset;
                         pr_debug("kvm: matched tsc offset for %llu\n", data);
                 } else {
                         u64 delta = nsec_to_cycles(vcpu, elapsed);
-                        offset += delta;
+                        data += delta;
+                        offset = kvm_x86_ops->compute_tsc_offset(vcpu, data);
                         pr_debug("kvm: adjusted tsc offset by %llu\n", delta);
                 }
                 ns = kvm->arch.last_tsc_nsec;
@@ -1059,6 +1072,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data)
         kvm->arch.last_tsc_nsec = ns;
         kvm->arch.last_tsc_write = data;
         kvm->arch.last_tsc_offset = offset;
+        kvm->arch.last_tsc_khz = vcpu->arch.virtual_tsc_khz;
         kvm_x86_ops->write_tsc_offset(vcpu, offset);
         raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);