[patch 1/5] KVM: x86: report stolen time

[Marcelo Tosatti <mtosatti@redhat.com>]

[-- Attachment #1: kvm-stolen-time-host --]
[-- Type: text/plain, Size: 4967 bytes --]

Report stolen time (run_delay field from schedstat) to guests via
pvclock.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

Index: kvm/arch/x86/include/asm/kvm_para.h
===================================================================
--- kvm.orig/arch/x86/include/asm/kvm_para.h
+++ kvm/arch/x86/include/asm/kvm_para.h
@@ -15,9 +15,11 @@
 #define KVM_FEATURE_CLOCKSOURCE		0
 #define KVM_FEATURE_NOP_IO_DELAY	1
 #define KVM_FEATURE_MMU_OP		2
+#define KVM_FEATURE_RUNTIME_INFO	3
 
 #define MSR_KVM_WALL_CLOCK  0x11
 #define MSR_KVM_SYSTEM_TIME 0x12
+#define MSR_KVM_RUN_TIME    0x13
 
 #define KVM_MAX_MMU_OP_BATCH           32
 
@@ -50,6 +52,11 @@ struct kvm_mmu_op_release_pt {
 #ifdef __KERNEL__
 #include <asm/processor.h>
 
+struct kvm_vcpu_runtime_info {
+	u64 stolen_time;		/* time spent starving */
+	u64 reserved[3];		/* for future use */
+};
+
 extern void kvmclock_init(void);
 
 
Index: kvm/arch/x86/include/asm/kvm_host.h
===================================================================
--- kvm.orig/arch/x86/include/asm/kvm_host.h
+++ kvm/arch/x86/include/asm/kvm_host.h
@@ -354,6 +354,10 @@ struct kvm_vcpu_arch {
 	unsigned int time_offset;
 	struct page *time_page;
 
+	bool stolen_time_enable;
+	struct kvm_vcpu_runtime_info stolen_time;
+	unsigned int stolen_time_offset;
+
 	bool singlestep; /* guest is single stepped by KVM */
 	bool nmi_pending;
 	bool nmi_injected;
Index: kvm/arch/x86/kvm/x86.c
===================================================================
--- kvm.orig/arch/x86/kvm/x86.c
+++ kvm/arch/x86/kvm/x86.c
@@ -507,9 +507,9 @@ static inline u32 bit(int bitno)
  * kvm-specific. Those are put in the beginning of the list.
  */
 
-#define KVM_SAVE_MSRS_BEGIN	2
+#define KVM_SAVE_MSRS_BEGIN	3
 static u32 msrs_to_save[] = {
-	MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
+	MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, MSR_KVM_RUN_TIME,
 	MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
 	MSR_K6_STAR,
 #ifdef CONFIG_X86_64
@@ -679,6 +679,7 @@ static void kvm_write_guest_time(struct 
 	struct kvm_vcpu_arch *vcpu = &v->arch;
 	void *shared_kaddr;
 	unsigned long this_tsc_khz;
+	struct task_struct *task = current;
 
 	if ((!vcpu->time_page))
 		return;
@@ -700,6 +701,9 @@ static void kvm_write_guest_time(struct 
 
 	vcpu->hv_clock.system_time = ts.tv_nsec +
 				     (NSEC_PER_SEC * (u64)ts.tv_sec);
+
+	vcpu->stolen_time.stolen_time = task->sched_info.run_delay;
+
 	/*
 	 * The interface expects us to write an even number signaling that the
 	 * update is finished. Since the guest won't see the intermediate
@@ -712,6 +716,10 @@ static void kvm_write_guest_time(struct 
 	memcpy(shared_kaddr + vcpu->time_offset, &vcpu->hv_clock,
 	       sizeof(vcpu->hv_clock));
 
+	if (vcpu->stolen_time_enable)
+		memcpy(shared_kaddr + vcpu->stolen_time_offset,
+		       &vcpu->stolen_time, sizeof(vcpu->stolen_time));
+
 	kunmap_atomic(shared_kaddr, KM_USER0);
 
 	mark_page_dirty(v->kvm, vcpu->time >> PAGE_SHIFT);
@@ -937,6 +945,35 @@ int kvm_set_msr_common(struct kvm_vcpu *
 		kvm_request_guest_time_update(vcpu);
 		break;
 	}
+	case MSR_KVM_RUN_TIME: {
+		struct page *page;
+		unsigned int stolen_time_offset;
+
+		if (!vcpu->arch.time_page)
+			return 1;
+
+		/* we verify if the enable bit is set... */
+		if (!(data & 1))
+			break;
+
+		/* ...but clean it before doing the actual write */
+		stolen_time_offset = data & ~(PAGE_MASK | 1);
+
+		/* that it matches the hvclock page */
+		page = gfn_to_page(vcpu->kvm, data >> PAGE_SHIFT);
+		if (is_error_page(page)) {
+			kvm_release_page_clean(page);
+			return 1;
+		}
+		if (page != vcpu->arch.time_page) {
+			kvm_release_page_clean(page);
+			return 1;
+		}
+		kvm_release_page_clean(page);
+		vcpu->arch.stolen_time_offset = stolen_time_offset;
+		vcpu->arch.stolen_time_enable = 1;
+		break;
+	}
 	case MSR_IA32_MCG_CTL:
 	case MSR_IA32_MCG_STATUS:
 	case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1:
@@ -1246,6 +1283,7 @@ int kvm_dev_ioctl_check_extension(long e
 	case KVM_CAP_PIT2:
 	case KVM_CAP_PIT_STATE2:
 	case KVM_CAP_SET_IDENTITY_MAP_ADDR:
+	case KVM_CAP_PVCLOCK_RUNTIME:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:
Index: kvm/arch/x86/kvm/Kconfig
===================================================================
--- kvm.orig/arch/x86/kvm/Kconfig
+++ kvm/arch/x86/kvm/Kconfig
@@ -28,6 +28,7 @@ config KVM
 	select HAVE_KVM_IRQCHIP
 	select HAVE_KVM_EVENTFD
 	select KVM_APIC_ARCHITECTURE
+	select SCHEDSTATS
 	---help---
 	  Support hosting fully virtualized guest machines using hardware
 	  virtualization extensions.  You will need a fairly recent
Index: kvm/include/linux/kvm.h
===================================================================
--- kvm.orig/include/linux/kvm.h
+++ kvm/include/linux/kvm.h
@@ -436,6 +436,7 @@ struct kvm_ioeventfd {
 #endif
 #define KVM_CAP_IOEVENTFD 36
 #define KVM_CAP_SET_IDENTITY_MAP_ADDR 37
+#define KVM_CAP_PVCLOCK_RUNTIME 38
 
 #ifdef KVM_CAP_IRQ_ROUTING