[PATCH 2/3] 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         |   79 +++++++++++++++++++++++++++++++++++++++++++-
 include/asm-x86/kvm_host.h |    4 ++
 include/asm-x86/kvm_para.h |   37 ++++++++++++++++++++
 include/linux/kvm.h        |    1 +
 4 files changed, 120 insertions(+), 1 deletions(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 8a90403..53b5692 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_KVM_PARAVIRT_CLOCK,
 };
 
 static unsigned num_msrs_to_save;
@@ -467,6 +468,60 @@ 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 xen_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;
+	struct xen_shared_info *shared_kaddr;
+
+	if ((!vcpu->shared_page))
+		return;
+
+	/* 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;
+
+	vcpu->hv_clock.system_time = ts.tv_nsec +
+				     (NSEC_PER_SEC * (u64)ts.tv_sec);
+	/*
+	 * The interface expects us to write an even number signaling that the
+	 * update is finished. Since the guest won't see the intermediate states,
+	 * we just write "2" at the end
+	 */
+	wc_args[0] = 2;
+	vcpu->hv_clock.version = 2;
+
+	preempt_disable();
+
+	shared_kaddr = kmap_atomic(vcpu->shared_page, KM_USER0);
+
+	/*
+	 * We could write everything at once, but it can break future
+	 * implementations. We're just a tiny and lonely clock, so let's
+	 * write only what matters here
+	 */
+	memcpy(&shared_kaddr->wc_version, wc_args, sizeof(wc_args));
+	memcpy(&shared_kaddr->vcpu_info[v->vcpu_id].time, &vcpu->hv_clock,
+		sizeof(vcpu->hv_clock));
+
+	kunmap_atomic(shared_kaddr, KM_USER0);
+	preempt_enable();
+
+	mark_page_dirty(v->kvm, vcpu->shared_info >> PAGE_SHIFT);
+}
+
 
 int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 {
@@ -494,6 +549,20 @@ 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_KVM_PARAVIRT_CLOCK: {
+		vcpu->arch.shared_info = data;
+
+		vcpu->arch.hv_clock.tsc_to_system_mul =
+					clocksource_khz2mult(tsc_khz, 22);
+		vcpu->arch.hv_clock.tsc_shift = 22;
+
+		down_write(&current->mm->mmap_sem);
+		vcpu->arch.shared_page = gfn_to_page(vcpu->kvm, data >> PAGE_SHIFT);
+		up_write(&current->mm->mmap_sem);
+		if (is_error_page(vcpu->arch.shared_page))
+			vcpu->arch.shared_page = NULL;
+		break;
+	}
 	default:
 		pr_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n", msr, data);
 		return 1;
@@ -553,6 +622,10 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 		data = vcpu->arch.shadow_efer;
 		break;
 #endif
+	case MSR_KVM_PARAVIRT_CLOCK:
+		data = vcpu->arch.shared_info;
+		break;
+
 	default:
 		pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr);
 		return 1;
@@ -680,6 +753,7 @@ 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 +811,7 @@ 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)
@@ -3190,6 +3265,8 @@ static void kvm_free_vcpus(struct kvm *kvm)
 			kvm_unload_vcpu_mmu(kvm->vcpus[i]);
 	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
 		if (kvm->vcpus[i]) {
+			if (kvm->vcpus[i]->arch.shared_page)
+				kvm_release_page_dirty(kvm->vcpus[i]->arch.shared_page);
 			kvm_arch_vcpu_free(kvm->vcpus[i]);
 			kvm->vcpus[i] = NULL;
 		}
diff --git a/include/asm-x86/kvm_host.h b/include/asm-x86/kvm_host.h
index d6db0de..9a66b90 100644
--- a/include/asm-x86/kvm_host.h
+++ b/include/asm-x86/kvm_host.h
@@ -261,6 +261,10 @@ struct kvm_vcpu_arch {
 	/* emulate context */
 
 	struct x86_emulate_ctxt emulate_ctxt;
+
+	struct xen_vcpu_time_info hv_clock;
+	gpa_t shared_info;
+	struct page *shared_page;
 };
 
 struct kvm_mem_alias {
diff --git a/include/asm-x86/kvm_para.h b/include/asm-x86/kvm_para.h
index c6f3fd8..145107d 100644
--- a/include/asm-x86/kvm_para.h
+++ b/include/asm-x86/kvm_para.h
@@ -10,10 +10,47 @@
  * paravirtualization, the appropriate feature bit should be checked.
  */
 #define KVM_CPUID_FEATURES	0x40000001
+#define KVM_FEATURE_CLOCKSOURCE 0
+
+#define MSR_KVM_PARAVIRT_CLOCK  0x11
 
 #ifdef __KERNEL__
 #include <asm/processor.h>
 
+/* xen binary-compatible interfaces. See xen headers for details */
+struct xen_vcpu_time_info {
+	uint32_t version;
+	uint32_t pad0;
+	uint64_t tsc_timestamp;
+	uint64_t system_time;
+	uint32_t tsc_to_system_mul;
+	int8_t   tsc_shift;
+	int8_t   pad1[3];
+};
+
+struct xen_vcpu_info {
+	uint8_t  pad[32];
+	struct xen_vcpu_time_info time;
+};
+
+#define XEN_MAX_VIRT_CPUS	32
+
+struct xen_shared_info {
+	struct xen_vcpu_info vcpu_info[XEN_MAX_VIRT_CPUS];
+
+	unsigned long evt[2];
+
+	uint32_t wc_version;      /* Version counter: see vcpu_time_info_t. */
+	uint32_t wc_sec;          /* Secs  00:00:00 UTC, Jan 1, 1970.  */
+	uint32_t wc_nsec;         /* Nsecs 00:00:00 UTC, Jan 1, 1970.  */
+
+	unsigned long pad[12];
+};
+
+
+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


-------------------------------------------------------------------------
This SF.net email is sponsored by: Microsoft
Defy all challenges. Microsoft(R) Visual Studio 2008.
http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/