[PATCH 2/3] [PATCH] kvmclock - the host part.

[Glauber de Oliveira Costa <gcosta-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>]

This is the host part of kvm clocksource implementation. As it does
not include clockevents, it is a fairly simple implementation. We
only have to register a per-vcpu area, and start writting to it periodically.

The area is binary compatible with xen, as we use the same shadow_info structure.

Signed-off-by: Glauber de Oliveira Costa <gcosta-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
---
 arch/x86/kvm/x86.c         |   64 +++++++++++++++++++++++++++++++++++++++++++-
 include/asm-x86/kvm_host.h |    5 +++
 include/asm-x86/kvm_para.h |    5 +++
 include/linux/kvm.h        |    1 +
 4 files changed, 74 insertions(+), 1 deletions(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 8a90403..d3fd920 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -19,6 +19,7 @@
 #include "irq.h"
 #include "mmu.h"
 
+#include <linux/clocksource.h>
 #include <linux/kvm.h>
 #include <linux/fs.h>
 #include <linux/vmalloc.h>
@@ -412,7 +413,7 @@ static u32 msrs_to_save[] = {
 #ifdef CONFIG_X86_64
 	MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR,
 #endif
-	MSR_IA32_TIME_STAMP_COUNTER,
+	MSR_IA32_TIME_STAMP_COUNTER, MSR_PARAVIRT_CLOCK,
 };
 
 static unsigned num_msrs_to_save;
@@ -467,6 +468,50 @@ static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
 	return kvm_set_msr(vcpu, index, *data);
 }
 
+#define WC_OFFSET offsetof(struct shared_info, wc_version)
+
+static void kvm_write_guest_time(struct kvm_vcpu *v)
+{
+	struct timespec ts, wc_ts;
+	int wc_args[3]; /* version, wc_sec, wc_nsec */
+	unsigned long flags;
+	struct kvm_vcpu_arch *vcpu = &v->arch;
+
+	if (!vcpu->shared_info)
+		return;
+
+	/* Make the update of both version numbers visible to guest */
+	wc_args[0] = ++vcpu->wc_version;
+	kvm_write_guest(v->kvm, vcpu->shared_info + WC_OFFSET, wc_args,
+			sizeof(wc_args));
+	vcpu->hv_clock.version++;
+	kvm_write_guest(v->kvm, vcpu->clock_addr, &vcpu->hv_clock,
+			sizeof(vcpu->hv_clock));
+
+	/* Keep irq disabled to prevent changes to the clock */
+	local_irq_save(flags);
+	kvm_get_msr(v, MSR_IA32_TIME_STAMP_COUNTER,
+			  &vcpu->hv_clock.tsc_timestamp);
+	wc_ts = current_kernel_time();
+	ktime_get_ts(&ts);
+	local_irq_restore(flags);
+
+	/* With all the info we got, fill in the values */
+	wc_args[1] = wc_ts.tv_sec;
+	wc_args[2] = wc_ts.tv_nsec;
+	wc_args[0] = ++vcpu->wc_version;
+
+	vcpu->hv_clock.system_time = ts.tv_nsec +
+				     (NSEC_PER_SEC * (u64)ts.tv_sec);
+	vcpu->hv_clock.version++;
+
+	/* And finally, let the guest see them */
+	kvm_write_guest(v->kvm, vcpu->shared_info + WC_OFFSET, wc_args,
+			sizeof(wc_args));
+	kvm_write_guest(v->kvm, vcpu->clock_addr, &vcpu->hv_clock,
+			sizeof(vcpu->hv_clock));
+}
+
 
 int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 {
@@ -494,6 +539,18 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 	case MSR_IA32_MISC_ENABLE:
 		vcpu->arch.ia32_misc_enable_msr = data;
 		break;
+	case MSR_PARAVIRT_CLOCK: {
+		vcpu->arch.shared_info = data;
+
+		vcpu->arch.clock_addr = data + offsetof(struct vcpu_info, time)
+				 + sizeof(struct vcpu_info) * vcpu->vcpu_id;
+
+		vcpu->arch.hv_clock.tsc_to_system_mul =
+				clocksource_khz2mult(tsc_khz, 22);
+		vcpu->arch.hv_clock.tsc_shift = 22;
+		kvm_write_guest_time(vcpu);
+		break;
+	}
 	default:
 		pr_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n", msr, data);
 		return 1;
@@ -553,6 +610,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 		data = vcpu->arch.shadow_efer;
 		break;
 #endif
+	case MSR_PARAVIRT_CLOCK:
+		data = vcpu->arch.shared_info;
+		break;
 	default:
 		pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr);
 		return 1;
@@ -680,6 +740,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_USER_MEMORY:
 	case KVM_CAP_SET_TSS_ADDR:
 	case KVM_CAP_EXT_CPUID:
+	case KVM_CAP_CLOCKSOURCE:
 		r = 1;
 		break;
 	case KVM_CAP_VAPIC:
@@ -737,6 +798,7 @@ out:
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	kvm_x86_ops->vcpu_load(vcpu, cpu);
+	kvm_write_guest_time(vcpu);
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
diff --git a/include/asm-x86/kvm_host.h b/include/asm-x86/kvm_host.h
index d6db0de..bbc4b51 100644
--- a/include/asm-x86/kvm_host.h
+++ b/include/asm-x86/kvm_host.h
@@ -261,6 +261,11 @@ struct kvm_vcpu_arch {
 	/* emulate context */
 
 	struct x86_emulate_ctxt emulate_ctxt;
+
+	struct vcpu_time_info hv_clock;
+	gpa_t shared_info;
+	gpa_t clock_addr; /* so we avoid computing it every time */
+	int wc_version;
 };
 
 struct kvm_mem_alias {
diff --git a/include/asm-x86/kvm_para.h b/include/asm-x86/kvm_para.h
index c6f3fd8..abe412a 100644
--- a/include/asm-x86/kvm_para.h
+++ b/include/asm-x86/kvm_para.h
@@ -1,5 +1,6 @@
 #ifndef __X86_KVM_PARA_H
 #define __X86_KVM_PARA_H
+#include <xen/interface/xen.h>
 
 /* This CPUID returns the signature 'KVMKVMKVM' in ebx, ecx, and edx.  It
  * should be used to determine that a VM is running under KVM.
@@ -10,9 +11,13 @@
  * paravirtualization, the appropriate feature bit should be checked.
  */
 #define KVM_CPUID_FEATURES	0x40000001
+#define KVM_FEATURE_CLOCKSOURCE 0
 
+#define MSR_PARAVIRT_CLOCK	0x11
 #ifdef __KERNEL__
 #include <asm/processor.h>
+extern void kvmclock_init(void);
+
 
 /* This instruction is vmcall.  On non-VT architectures, it will generate a
  * trap that we will then rewrite to the appropriate instruction.
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 4de4fd2..78ce53f 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -232,6 +232,7 @@ struct kvm_vapic_addr {
 #define KVM_CAP_SET_TSS_ADDR 4
 #define KVM_CAP_EXT_CPUID 5
 #define KVM_CAP_VAPIC 6
+#define KVM_CAP_CLOCKSOURCE 7
 
 /*
  * ioctls for VM fds
-- 
1.5.0.6


-------------------------------------------------------------------------
Check out the new SourceForge.net Marketplace.
It's the best place to buy or sell services for
just about anything Open Source.
http://ad.doubleclick.net/clk;164216239;13503038;w?http://sf.net/marketplace