Merge branch 'kvm-updates/3.1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

* 'kvm-updates/3.1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (143 commits)
  KVM: IOMMU: Disable device assignment without interrupt remapping
  KVM: MMU: trace mmio page fault
  KVM: MMU: mmio page fault support
  KVM: MMU: reorganize struct kvm_shadow_walk_iterator
  KVM: MMU: lockless walking shadow page table
  KVM: MMU: do not need atomicly to set/clear spte
  KVM: MMU: introduce the rules to modify shadow page table
  KVM: MMU: abstract some functions to handle fault pfn
  KVM: MMU: filter out the mmio pfn from the fault pfn
  KVM: MMU: remove bypass_guest_pf
  KVM: MMU: split kvm_mmu_free_page
  KVM: MMU: count used shadow pages on prepareing path
  KVM: MMU: rename 'pt_write' to 'emulate'
  KVM: MMU: cleanup for FNAME(fetch)
  KVM: MMU: optimize to handle dirty bit
  KVM: MMU: cache mmio info on page fault path
  KVM: x86: introduce vcpu_mmio_gva_to_gpa to cleanup the code
  KVM: MMU: do not update slot bitmap if spte is nonpresent
  KVM: MMU: fix walking shadow page table
  KVM guest: KVM Steal time registration
  ...

3 files changed, 83 insertions, 0 deletions

diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 33c07b0..a9c2116 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -51,6 +51,15 @@ static int parse_no_kvmapf(char *arg)
 
 early_param("no-kvmapf", parse_no_kvmapf);
 
+static int steal_acc = 1;
+static int parse_no_stealacc(char *arg)
+{
+        steal_acc = 0;
+        return 0;
+}
+
+early_param("no-steal-acc", parse_no_stealacc);
+
 struct kvm_para_state {
 	u8 mmu_queue[MMU_QUEUE_SIZE];
 	int mmu_queue_len;
@@ -58,6 +67,8 @@ struct kvm_para_state {
 
 static DEFINE_PER_CPU(struct kvm_para_state, para_state);
 static DEFINE_PER_CPU(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64);
+static DEFINE_PER_CPU(struct kvm_steal_time, steal_time) __aligned(64);
+static int has_steal_clock = 0;
 
 static struct kvm_para_state *kvm_para_state(void)
 {
@@ -441,6 +452,21 @@ static void __init paravirt_ops_setup(void)
 #endif
 }
 
+static void kvm_register_steal_time(void)
+{
+	int cpu = smp_processor_id();
+	struct kvm_steal_time *st = &per_cpu(steal_time, cpu);
+
+	if (!has_steal_clock)
+		return;
+
+	memset(st, 0, sizeof(*st));
+
+	wrmsrl(MSR_KVM_STEAL_TIME, (__pa(st) | KVM_MSR_ENABLED));
+	printk(KERN_INFO "kvm-stealtime: cpu %d, msr %lx\n",
+		cpu, __pa(st));
+}
+
 void __cpuinit kvm_guest_cpu_init(void)
 {
 	if (!kvm_para_available())
@@ -457,6 +483,9 @@ void __cpuinit kvm_guest_cpu_init(void)
 		printk(KERN_INFO"KVM setup async PF for cpu %d\n",
 		       smp_processor_id());
 	}
+
+	if (has_steal_clock)
+		kvm_register_steal_time();
 }
 
 static void kvm_pv_disable_apf(void *unused)
@@ -483,6 +512,31 @@ static struct notifier_block kvm_pv_reboot_nb = {
 	.notifier_call = kvm_pv_reboot_notify,
 };
 
+static u64 kvm_steal_clock(int cpu)
+{
+	u64 steal;
+	struct kvm_steal_time *src;
+	int version;
+
+	src = &per_cpu(steal_time, cpu);
+	do {
+		version = src->version;
+		rmb();
+		steal = src->steal;
+		rmb();
+	} while ((version & 1) || (version != src->version));
+
+	return steal;
+}
+
+void kvm_disable_steal_time(void)
+{
+	if (!has_steal_clock)
+		return;
+
+	wrmsr(MSR_KVM_STEAL_TIME, 0, 0);
+}
+
 #ifdef CONFIG_SMP
 static void __init kvm_smp_prepare_boot_cpu(void)
 {
@@ -500,6 +554,7 @@ static void __cpuinit kvm_guest_cpu_online(void *dummy)
 
 static void kvm_guest_cpu_offline(void *dummy)
 {
+	kvm_disable_steal_time();
 	kvm_pv_disable_apf(NULL);
 	apf_task_wake_all();
 }
@@ -548,6 +603,11 @@ void __init kvm_guest_init(void)
 	if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF))
 		x86_init.irqs.trap_init = kvm_apf_trap_init;
 
+	if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
+		has_steal_clock = 1;
+		pv_time_ops.steal_clock = kvm_steal_clock;
+	}
+
 #ifdef CONFIG_SMP
 	smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
 	register_cpu_notifier(&kvm_cpu_notifier);
@@ -555,3 +615,15 @@ void __init kvm_guest_init(void)
 	kvm_guest_cpu_init();
 #endif
 }
+
+static __init int activate_jump_labels(void)
+{
+	if (has_steal_clock) {
+		jump_label_inc(&paravirt_steal_enabled);
+		if (steal_acc)
+			jump_label_inc(&paravirt_steal_rq_enabled);
+	}
+
+	return 0;
+}
+arch_initcall(activate_jump_labels);
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 6389a6b..c1a0188 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -160,6 +160,7 @@ static void __cpuinit kvm_setup_secondary_clock(void)
 static void kvm_crash_shutdown(struct pt_regs *regs)
 {
 	native_write_msr(msr_kvm_system_time, 0, 0);
+	kvm_disable_steal_time();
 	native_machine_crash_shutdown(regs);
 }
 #endif
@@ -167,6 +168,7 @@ static void kvm_crash_shutdown(struct pt_regs *regs)
 static void kvm_shutdown(void)
 {
 	native_write_msr(msr_kvm_system_time, 0, 0);
+	kvm_disable_steal_time();
 	native_machine_shutdown();
 }
 
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 869e1ae..613a793 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -202,6 +202,14 @@ static void native_flush_tlb_single(unsigned long addr)
 	__native_flush_tlb_single(addr);
 }
 
+struct jump_label_key paravirt_steal_enabled;
+struct jump_label_key paravirt_steal_rq_enabled;
+
+static u64 native_steal_clock(int cpu)
+{
+	return 0;
+}
+
 /* These are in entry.S */
 extern void native_iret(void);
 extern void native_irq_enable_sysexit(void);
@@ -307,6 +315,7 @@ struct pv_init_ops pv_init_ops = {
 
 struct pv_time_ops pv_time_ops = {
 	.sched_clock = native_sched_clock,
+	.steal_clock = native_steal_clock,
 };
 
 struct pv_irq_ops pv_irq_ops = {