Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull more KVM updates from Paolo Bonzini:
 "Second batch of KVM updates.  Some minor x86 fixes, two s390 guest
  features that need some handling in the host, and all the PPC changes.

  The PPC changes include support for little-endian guests and
  enablement for new POWER8 features"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (45 commits)
  x86, kvm: correctly access the KVM_CPUID_FEATURES leaf at 0x40000101
  x86, kvm: cache the base of the KVM cpuid leaves
  kvm: x86: move KVM_CAP_HYPERV_TIME outside #ifdef
  KVM: PPC: Book3S PR: Cope with doorbell interrupts
  KVM: PPC: Book3S HV: Add software abort codes for transactional memory
  KVM: PPC: Book3S HV: Add new state for transactional memory
  powerpc/Kconfig: Make TM select VSX and VMX
  KVM: PPC: Book3S HV: Basic little-endian guest support
  KVM: PPC: Book3S HV: Add support for DABRX register on POWER7
  KVM: PPC: Book3S HV: Prepare for host using hypervisor doorbells
  KVM: PPC: Book3S HV: Handle new LPCR bits on POWER8
  KVM: PPC: Book3S HV: Handle guest using doorbells for IPIs
  KVM: PPC: Book3S HV: Consolidate code that checks reason for wake from nap
  KVM: PPC: Book3S HV: Implement architecture compatibility modes for POWER8
  KVM: PPC: Book3S HV: Add handler for HV facility unavailable
  KVM: PPC: Book3S HV: Flush the correct number of TLB sets on POWER8
  KVM: PPC: Book3S HV: Context-switch new POWER8 SPRs
  KVM: PPC: Book3S HV: Align physical and virtual CPU thread numbers
  KVM: PPC: Book3S HV: Don't set DABR on POWER8
  kvm/ppc: IRQ disabling cleanup
  ...

6 files changed, 89 insertions, 36 deletions

diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 1df115909758..c7678e43465b 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -85,28 +85,9 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1,
 	return ret;
 }
 
-static inline uint32_t kvm_cpuid_base(void)
-{
-	if (boot_cpu_data.cpuid_level < 0)
-		return 0;	/* So we don't blow up on old processors */
-
-	if (cpu_has_hypervisor)
-		return hypervisor_cpuid_base("KVMKVMKVM\0\0\0", 0);
-
-	return 0;
-}
-
-static inline bool kvm_para_available(void)
-{
-	return kvm_cpuid_base() != 0;
-}
-
-static inline unsigned int kvm_arch_para_features(void)
-{
-	return cpuid_eax(KVM_CPUID_FEATURES);
-}
-
 #ifdef CONFIG_KVM_GUEST
+bool kvm_para_available(void);
+unsigned int kvm_arch_para_features(void);
 void __init kvm_guest_init(void);
 void kvm_async_pf_task_wait(u32 token);
 void kvm_async_pf_task_wake(u32 token);
@@ -126,6 +107,16 @@ static inline void kvm_spinlock_init(void)
 #define kvm_async_pf_task_wait(T) do {} while(0)
 #define kvm_async_pf_task_wake(T) do {} while(0)
 
+static inline bool kvm_para_available(void)
+{
+	return 0;
+}
+
+static inline unsigned int kvm_arch_para_features(void)
+{
+	return 0;
+}
+
 static inline u32 kvm_read_and_reset_pf_reason(void)
 {
 	return 0;
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index cd1b362e4a23..713f1b3bad52 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -500,6 +500,38 @@ void __init kvm_guest_init(void)
 #endif
 }
 
+static noinline uint32_t __kvm_cpuid_base(void)
+{
+	if (boot_cpu_data.cpuid_level < 0)
+		return 0;	/* So we don't blow up on old processors */
+
+	if (cpu_has_hypervisor)
+		return hypervisor_cpuid_base("KVMKVMKVM\0\0\0", 0);
+
+	return 0;
+}
+
+static inline uint32_t kvm_cpuid_base(void)
+{
+	static int kvm_cpuid_base = -1;
+
+	if (kvm_cpuid_base == -1)
+		kvm_cpuid_base = __kvm_cpuid_base();
+
+	return kvm_cpuid_base;
+}
+
+bool kvm_para_available(void)
+{
+	return kvm_cpuid_base() != 0;
+}
+EXPORT_SYMBOL_GPL(kvm_para_available);
+
+unsigned int kvm_arch_para_features(void)
+{
+	return cpuid_eax(kvm_cpuid_base() | KVM_CPUID_FEATURES);
+}
+
 static uint32_t __init kvm_detect(void)
 {
 	return kvm_cpuid_base();
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index f1e4895174b2..a2a1bb7ed8c1 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -72,4 +72,12 @@ static inline bool guest_cpuid_has_pcid(struct kvm_vcpu *vcpu)
 	return best && (best->ecx & bit(X86_FEATURE_PCID));
 }
 
+static inline bool guest_cpuid_has_x2apic(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 1, 0);
+	return best && (best->ecx & bit(X86_FEATURE_X2APIC));
+}
+
 #endif
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index c8b0d0d2da5c..6a11845fd8b9 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -65,7 +65,7 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
 		struct kvm_lapic_irq *irq, int *r, unsigned long *dest_map);
 
 u64 kvm_get_apic_base(struct kvm_vcpu *vcpu);
-void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data);
+int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
 void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu,
 		struct kvm_lapic_state *s);
 int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 5c8879127cfa..a06f101ef64b 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -4392,7 +4392,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 static void vmx_vcpu_reset(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	u64 msr;
+	struct msr_data apic_base_msr;
 
 	vmx->rmode.vm86_active = 0;
 
@@ -4400,10 +4400,11 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu)
 
 	vmx->vcpu.arch.regs[VCPU_REGS_RDX] = get_rdx_init_val();
 	kvm_set_cr8(&vmx->vcpu, 0);
-	msr = 0xfee00000 | MSR_IA32_APICBASE_ENABLE;
+	apic_base_msr.data = 0xfee00000 | MSR_IA32_APICBASE_ENABLE;
 	if (kvm_vcpu_is_bsp(&vmx->vcpu))
-		msr |= MSR_IA32_APICBASE_BSP;
-	kvm_set_apic_base(&vmx->vcpu, msr);
+		apic_base_msr.data |= MSR_IA32_APICBASE_BSP;
+	apic_base_msr.host_initiated = true;
+	kvm_set_apic_base(&vmx->vcpu, &apic_base_msr);
 
 	vmx_segment_cache_clear(vmx);
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0c76f7cfdb32..39c28f09dfd5 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -257,10 +257,26 @@ u64 kvm_get_apic_base(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_get_apic_base);
 
-void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data)
-{
-	/* TODO: reserve bits check */
-	kvm_lapic_set_base(vcpu, data);
+int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
+{
+	u64 old_state = vcpu->arch.apic_base &
+		(MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE);
+	u64 new_state = msr_info->data &
+		(MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE);
+	u64 reserved_bits = ((~0ULL) << cpuid_maxphyaddr(vcpu)) |
+		0x2ff | (guest_cpuid_has_x2apic(vcpu) ? 0 : X2APIC_ENABLE);
+
+	if (!msr_info->host_initiated &&
+	    ((msr_info->data & reserved_bits) != 0 ||
+	     new_state == X2APIC_ENABLE ||
+	     (new_state == MSR_IA32_APICBASE_ENABLE &&
+	      old_state == (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE)) ||
+	     (new_state == (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE) &&
+	      old_state == 0)))
+		return 1;
+
+	kvm_lapic_set_base(vcpu, msr_info->data);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(kvm_set_apic_base);
 
@@ -1840,6 +1856,7 @@ static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		if (__copy_to_user((void __user *)addr, instructions, 4))
 			return 1;
 		kvm->arch.hv_hypercall = data;
+		mark_page_dirty(kvm, gfn);
 		break;
 	}
 	case HV_X64_MSR_REFERENCE_TSC: {
@@ -1868,19 +1885,21 @@ static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 {
 	switch (msr) {
 	case HV_X64_MSR_APIC_ASSIST_PAGE: {
+		u64 gfn;
 		unsigned long addr;
 
 		if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) {
 			vcpu->arch.hv_vapic = data;
 			break;
 		}
-		addr = gfn_to_hva(vcpu->kvm, data >>
-				  HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT);
+		gfn = data >> HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT;
+		addr = gfn_to_hva(vcpu->kvm, gfn);
 		if (kvm_is_error_hva(addr))
 			return 1;
 		if (__clear_user((void __user *)addr, PAGE_SIZE))
 			return 1;
 		vcpu->arch.hv_vapic = data;
+		mark_page_dirty(vcpu->kvm, gfn);
 		break;
 	}
 	case HV_X64_MSR_EOI:
@@ -2006,8 +2025,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case 0x200 ... 0x2ff:
 		return set_msr_mtrr(vcpu, msr, data);
 	case MSR_IA32_APICBASE:
-		kvm_set_apic_base(vcpu, data);
-		break;
+		return kvm_set_apic_base(vcpu, msr_info);
 	case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff:
 		return kvm_x2apic_msr_write(vcpu, msr, data);
 	case MSR_IA32_TSCDEADLINE:
@@ -2598,10 +2616,10 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_GET_TSC_KHZ:
 	case KVM_CAP_KVMCLOCK_CTRL:
 	case KVM_CAP_READONLY_MEM:
+	case KVM_CAP_HYPERV_TIME:
 #ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
 	case KVM_CAP_ASSIGN_DEV_IRQ:
 	case KVM_CAP_PCI_2_3:
-	case KVM_CAP_HYPERV_TIME:
 #endif
 		r = 1;
 		break;
@@ -6409,6 +6427,7 @@ EXPORT_SYMBOL_GPL(kvm_task_switch);
 int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 				  struct kvm_sregs *sregs)
 {
+	struct msr_data apic_base_msr;
 	int mmu_reset_needed = 0;
 	int pending_vec, max_bits, idx;
 	struct desc_ptr dt;
@@ -6432,7 +6451,9 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 
 	mmu_reset_needed |= vcpu->arch.efer != sregs->efer;
 	kvm_x86_ops->set_efer(vcpu, sregs->efer);
-	kvm_set_apic_base(vcpu, sregs->apic_base);
+	apic_base_msr.data = sregs->apic_base;
+	apic_base_msr.host_initiated = true;
+	kvm_set_apic_base(vcpu, &apic_base_msr);
 
 	mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0;
 	kvm_x86_ops->set_cr0(vcpu, sregs->cr0);