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

Pull KVM updates from Paolo Bonzini:
 "Fixes and features for 3.18.

  Apart from the usual cleanups, here is the summary of new features:

   - s390 moves closer towards host large page support

   - PowerPC has improved support for debugging (both inside the guest
     and via gdbstub) and support for e6500 processors

   - ARM/ARM64 support read-only memory (which is necessary to put
     firmware in emulated NOR flash)

   - x86 has the usual emulator fixes and nested virtualization
     improvements (including improved Windows support on Intel and
     Jailhouse hypervisor support on AMD), adaptive PLE which helps
     overcommitting of huge guests.  Also included are some patches that
     make KVM more friendly to memory hot-unplug, and fixes for rare
     caching bugs.

  Two patches have trivial mm/ parts that were acked by Rik and Andrew.

  Note: I will soon switch to a subkey for signing purposes"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (157 commits)
  kvm: do not handle APIC access page if in-kernel irqchip is not in use
  KVM: s390: count vcpu wakeups in stat.halt_wakeup
  KVM: s390/facilities: allow TOD-CLOCK steering facility bit
  KVM: PPC: BOOK3S: HV: CMA: Reserve cma region only in hypervisor mode
  arm/arm64: KVM: Report correct FSC for unsupported fault types
  arm/arm64: KVM: Fix VTTBR_BADDR_MASK and pgd alloc
  kvm: Fix kvm_get_page_retry_io __gup retval check
  arm/arm64: KVM: Fix set_clear_sgi_pend_reg offset
  kvm: x86: Unpin and remove kvm_arch->apic_access_page
  kvm: vmx: Implement set_apic_access_page_addr
  kvm: x86: Add request bit to reload APIC access page address
  kvm: Add arch specific mmu notifier for page invalidation
  kvm: Rename make_all_cpus_request() to kvm_make_all_cpus_request() and make it non-static
  kvm: Fix page ageing bugs
  kvm/x86/mmu: Pass gfn and level to rmapp callback.
  x86: kvm: use alternatives for VMCALL vs. VMMCALL if kernel text is read-only
  kvm: x86: use macros to compute bank MSRs
  KVM: x86: Remove debug assertion of non-PAE reserved bits
  kvm: don't take vcpu mutex for obviously invalid vcpu ioctls
  kvm: Faults which trigger IO release the mmap_sem
  ...

18 files changed, 704 insertions, 303 deletions

diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index dd03f6b299ba..b32db4b95361 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -535,174 +535,111 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 	return -ENOTSUPP;
 }
 
-int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
+int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id,
+			union kvmppc_one_reg *val)
 {
-	int r;
-	union kvmppc_one_reg val;
-	int size;
+	int r = 0;
 	long int i;
 
-	size = one_reg_size(reg->id);
-	if (size > sizeof(val))
-		return -EINVAL;
-
-	r = vcpu->kvm->arch.kvm_ops->get_one_reg(vcpu, reg->id, &val);
+	r = vcpu->kvm->arch.kvm_ops->get_one_reg(vcpu, id, val);
 	if (r == -EINVAL) {
 		r = 0;
-		switch (reg->id) {
+		switch (id) {
 		case KVM_REG_PPC_DAR:
-			val = get_reg_val(reg->id, kvmppc_get_dar(vcpu));
+			*val = get_reg_val(id, kvmppc_get_dar(vcpu));
 			break;
 		case KVM_REG_PPC_DSISR:
-			val = get_reg_val(reg->id, kvmppc_get_dsisr(vcpu));
+			*val = get_reg_val(id, kvmppc_get_dsisr(vcpu));
 			break;
 		case KVM_REG_PPC_FPR0 ... KVM_REG_PPC_FPR31:
-			i = reg->id - KVM_REG_PPC_FPR0;
-			val = get_reg_val(reg->id, VCPU_FPR(vcpu, i));
+			i = id - KVM_REG_PPC_FPR0;
+			*val = get_reg_val(id, VCPU_FPR(vcpu, i));
 			break;
 		case KVM_REG_PPC_FPSCR:
-			val = get_reg_val(reg->id, vcpu->arch.fp.fpscr);
-			break;
-#ifdef CONFIG_ALTIVEC
-		case KVM_REG_PPC_VR0 ... KVM_REG_PPC_VR31:
-			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
-				r = -ENXIO;
-				break;
-			}
-			val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0];
-			break;
-		case KVM_REG_PPC_VSCR:
-			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
-				r = -ENXIO;
-				break;
-			}
-			val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]);
+			*val = get_reg_val(id, vcpu->arch.fp.fpscr);
 			break;
-		case KVM_REG_PPC_VRSAVE:
-			val = get_reg_val(reg->id, vcpu->arch.vrsave);
-			break;
-#endif /* CONFIG_ALTIVEC */
 #ifdef CONFIG_VSX
 		case KVM_REG_PPC_VSR0 ... KVM_REG_PPC_VSR31:
 			if (cpu_has_feature(CPU_FTR_VSX)) {
-				long int i = reg->id - KVM_REG_PPC_VSR0;
-				val.vsxval[0] = vcpu->arch.fp.fpr[i][0];
-				val.vsxval[1] = vcpu->arch.fp.fpr[i][1];
+				i = id - KVM_REG_PPC_VSR0;
+				val->vsxval[0] = vcpu->arch.fp.fpr[i][0];
+				val->vsxval[1] = vcpu->arch.fp.fpr[i][1];
 			} else {
 				r = -ENXIO;
 			}
 			break;
 #endif /* CONFIG_VSX */
-		case KVM_REG_PPC_DEBUG_INST: {
-			u32 opcode = INS_TW;
-			r = copy_to_user((u32 __user *)(long)reg->addr,
-					 &opcode, sizeof(u32));
+		case KVM_REG_PPC_DEBUG_INST:
+			*val = get_reg_val(id, INS_TW);
 			break;
-		}
 #ifdef CONFIG_KVM_XICS
 		case KVM_REG_PPC_ICP_STATE:
 			if (!vcpu->arch.icp) {
 				r = -ENXIO;
 				break;
 			}
-			val = get_reg_val(reg->id, kvmppc_xics_get_icp(vcpu));
+			*val = get_reg_val(id, kvmppc_xics_get_icp(vcpu));
 			break;
 #endif /* CONFIG_KVM_XICS */
 		case KVM_REG_PPC_FSCR:
-			val = get_reg_val(reg->id, vcpu->arch.fscr);
+			*val = get_reg_val(id, vcpu->arch.fscr);
 			break;
 		case KVM_REG_PPC_TAR:
-			val = get_reg_val(reg->id, vcpu->arch.tar);
+			*val = get_reg_val(id, vcpu->arch.tar);
 			break;
 		case KVM_REG_PPC_EBBHR:
-			val = get_reg_val(reg->id, vcpu->arch.ebbhr);
+			*val = get_reg_val(id, vcpu->arch.ebbhr);
 			break;
 		case KVM_REG_PPC_EBBRR:
-			val = get_reg_val(reg->id, vcpu->arch.ebbrr);
+			*val = get_reg_val(id, vcpu->arch.ebbrr);
 			break;
 		case KVM_REG_PPC_BESCR:
-			val = get_reg_val(reg->id, vcpu->arch.bescr);
+			*val = get_reg_val(id, vcpu->arch.bescr);
 			break;
 		case KVM_REG_PPC_VTB:
-			val = get_reg_val(reg->id, vcpu->arch.vtb);
+			*val = get_reg_val(id, vcpu->arch.vtb);
 			break;
 		case KVM_REG_PPC_IC:
-			val = get_reg_val(reg->id, vcpu->arch.ic);
+			*val = get_reg_val(id, vcpu->arch.ic);
 			break;
 		default:
 			r = -EINVAL;
 			break;
 		}
 	}
-	if (r)
-		return r;
-
-	if (copy_to_user((char __user *)(unsigned long)reg->addr, &val, size))
-		r = -EFAULT;
 
 	return r;
 }
 
-int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
+int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id,
+			union kvmppc_one_reg *val)
 {
-	int r;
-	union kvmppc_one_reg val;
-	int size;
+	int r = 0;
 	long int i;
 
-	size = one_reg_size(reg->id);
-	if (size > sizeof(val))
-		return -EINVAL;
-
-	if (copy_from_user(&val, (char __user *)(unsigned long)reg->addr, size))
-		return -EFAULT;
-
-	r = vcpu->kvm->arch.kvm_ops->set_one_reg(vcpu, reg->id, &val);
+	r = vcpu->kvm->arch.kvm_ops->set_one_reg(vcpu, id, val);
 	if (r == -EINVAL) {
 		r = 0;
-		switch (reg->id) {
+		switch (id) {
 		case KVM_REG_PPC_DAR:
-			kvmppc_set_dar(vcpu, set_reg_val(reg->id, val));
+			kvmppc_set_dar(vcpu, set_reg_val(id, *val));
 			break;
 		case KVM_REG_PPC_DSISR:
-			kvmppc_set_dsisr(vcpu, set_reg_val(reg->id, val));
+			kvmppc_set_dsisr(vcpu, set_reg_val(id, *val));
 			break;
 		case KVM_REG_PPC_FPR0 ... KVM_REG_PPC_FPR31:
-			i = reg->id - KVM_REG_PPC_FPR0;
-			VCPU_FPR(vcpu, i) = set_reg_val(reg->id, val);
+			i = id - KVM_REG_PPC_FPR0;
+			VCPU_FPR(vcpu, i) = set_reg_val(id, *val);
 			break;
 		case KVM_REG_PPC_FPSCR:
-			vcpu->arch.fp.fpscr = set_reg_val(reg->id, val);
-			break;
-#ifdef CONFIG_ALTIVEC
-		case KVM_REG_PPC_VR0 ... KVM_REG_PPC_VR31:
-			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
-				r = -ENXIO;
-				break;
-			}
-			vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval;
-			break;
-		case KVM_REG_PPC_VSCR:
-			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
-				r = -ENXIO;
-				break;
-			}
-			vcpu->arch.vr.vscr.u[3] = set_reg_val(reg->id, val);
-			break;
-		case KVM_REG_PPC_VRSAVE:
-			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
-				r = -ENXIO;
-				break;
-			}
-			vcpu->arch.vrsave = set_reg_val(reg->id, val);
+			vcpu->arch.fp.fpscr = set_reg_val(id, *val);
 			break;
-#endif /* CONFIG_ALTIVEC */
 #ifdef CONFIG_VSX
 		case KVM_REG_PPC_VSR0 ... KVM_REG_PPC_VSR31:
 			if (cpu_has_feature(CPU_FTR_VSX)) {
-				long int i = reg->id - KVM_REG_PPC_VSR0;
-				vcpu->arch.fp.fpr[i][0] = val.vsxval[0];
-				vcpu->arch.fp.fpr[i][1] = val.vsxval[1];
+				i = id - KVM_REG_PPC_VSR0;
+				vcpu->arch.fp.fpr[i][0] = val->vsxval[0];
+				vcpu->arch.fp.fpr[i][1] = val->vsxval[1];
 			} else {
 				r = -ENXIO;
 			}
@@ -715,29 +652,29 @@ int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
 				break;
 			}
 			r = kvmppc_xics_set_icp(vcpu,
-						set_reg_val(reg->id, val));
+						set_reg_val(id, *val));
 			break;
 #endif /* CONFIG_KVM_XICS */
 		case KVM_REG_PPC_FSCR:
-			vcpu->arch.fscr = set_reg_val(reg->id, val);
+			vcpu->arch.fscr = set_reg_val(id, *val);
 			break;
 		case KVM_REG_PPC_TAR:
-			vcpu->arch.tar = set_reg_val(reg->id, val);
+			vcpu->arch.tar = set_reg_val(id, *val);
 			break;
 		case KVM_REG_PPC_EBBHR:
-			vcpu->arch.ebbhr = set_reg_val(reg->id, val);
+			vcpu->arch.ebbhr = set_reg_val(id, *val);
 			break;
 		case KVM_REG_PPC_EBBRR:
-			vcpu->arch.ebbrr = set_reg_val(reg->id, val);
+			vcpu->arch.ebbrr = set_reg_val(id, *val);
 			break;
 		case KVM_REG_PPC_BESCR:
-			vcpu->arch.bescr = set_reg_val(reg->id, val);
+			vcpu->arch.bescr = set_reg_val(id, *val);
 			break;
 		case KVM_REG_PPC_VTB:
-			vcpu->arch.vtb = set_reg_val(reg->id, val);
+			vcpu->arch.vtb = set_reg_val(id, *val);
 			break;
 		case KVM_REG_PPC_IC:
-			vcpu->arch.ic = set_reg_val(reg->id, val);
+			vcpu->arch.ic = set_reg_val(id, *val);
 			break;
 		default:
 			r = -EINVAL;
@@ -778,13 +715,12 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
 int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 					struct kvm_guest_debug *dbg)
 {
-	return -EINVAL;
+	vcpu->guest_debug = dbg->control;
+	return 0;
 }
 
-void kvmppc_decrementer_func(unsigned long data)
+void kvmppc_decrementer_func(struct kvm_vcpu *vcpu)
 {
-	struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data;
-
 	kvmppc_core_queue_dec(vcpu);
 	kvm_vcpu_kick(vcpu);
 }
@@ -851,9 +787,9 @@ int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
 	return kvm->arch.kvm_ops->unmap_hva_range(kvm, start, end);
 }
 
-int kvm_age_hva(struct kvm *kvm, unsigned long hva)
+int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
 {
-	return kvm->arch.kvm_ops->age_hva(kvm, hva);
+	return kvm->arch.kvm_ops->age_hva(kvm, start, end);
 }
 
 int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
diff --git a/arch/powerpc/kvm/book3s.h b/arch/powerpc/kvm/book3s.h
index 4bf956cf94d6..d2b3ec088b8c 100644
--- a/arch/powerpc/kvm/book3s.h
+++ b/arch/powerpc/kvm/book3s.h
@@ -17,7 +17,8 @@ extern void kvmppc_core_flush_memslot_hv(struct kvm *kvm,
 extern int kvm_unmap_hva_hv(struct kvm *kvm, unsigned long hva);
 extern int kvm_unmap_hva_range_hv(struct kvm *kvm, unsigned long start,
 				  unsigned long end);
-extern int kvm_age_hva_hv(struct kvm *kvm, unsigned long hva);
+extern int kvm_age_hva_hv(struct kvm *kvm, unsigned long start,
+			  unsigned long end);
 extern int kvm_test_age_hva_hv(struct kvm *kvm, unsigned long hva);
 extern void kvm_set_spte_hva_hv(struct kvm *kvm, unsigned long hva, pte_t pte);
 
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 79294c4c5015..d40770248b6a 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -1002,11 +1002,11 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
 	return ret;
 }
 
-int kvm_age_hva_hv(struct kvm *kvm, unsigned long hva)
+int kvm_age_hva_hv(struct kvm *kvm, unsigned long start, unsigned long end)
 {
 	if (!kvm->arch.using_mmu_notifiers)
 		return 0;
-	return kvm_handle_hva(kvm, hva, kvm_age_rmapp);
+	return kvm_handle_hva_range(kvm, start, end, kvm_age_rmapp);
 }
 
 static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 27cced9c7249..e63587d30b70 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -725,6 +725,30 @@ static int kvmppc_hcall_impl_hv(unsigned long cmd)
 	return kvmppc_hcall_impl_hv_realmode(cmd);
 }
 
+static int kvmppc_emulate_debug_inst(struct kvm_run *run,
+					struct kvm_vcpu *vcpu)
+{
+	u32 last_inst;
+
+	if (kvmppc_get_last_inst(vcpu, INST_GENERIC, &last_inst) !=
+					EMULATE_DONE) {
+		/*
+		 * Fetch failed, so return to guest and
+		 * try executing it again.
+		 */
+		return RESUME_GUEST;
+	}
+
+	if (last_inst == KVMPPC_INST_SW_BREAKPOINT) {
+		run->exit_reason = KVM_EXIT_DEBUG;
+		run->debug.arch.address = kvmppc_get_pc(vcpu);
+		return RESUME_HOST;
+	} else {
+		kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
+		return RESUME_GUEST;
+	}
+}
+
 static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
 				 struct task_struct *tsk)
 {
@@ -807,12 +831,18 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		break;
 	/*
 	 * This occurs if the guest executes an illegal instruction.
-	 * We just generate a program interrupt to the guest, since
-	 * we don't emulate any guest instructions at this stage.
+	 * If the guest debug is disabled, generate a program interrupt
+	 * to the guest. If guest debug is enabled, we need to check
+	 * whether the instruction is a software breakpoint instruction.
+	 * Accordingly return to Guest or Host.
 	 */
 	case BOOK3S_INTERRUPT_H_EMUL_ASSIST:
-		kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
-		r = RESUME_GUEST;
+		if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) {
+			r = kvmppc_emulate_debug_inst(run, vcpu);
+		} else {
+			kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
+			r = RESUME_GUEST;
+		}
 		break;
 	/*
 	 * This occurs if the guest (kernel or userspace), does something that
@@ -856,7 +886,9 @@ static int kvm_arch_vcpu_ioctl_set_sregs_hv(struct kvm_vcpu *vcpu,
 {
 	int i, j;
 
-	kvmppc_set_pvr_hv(vcpu, sregs->pvr);
+	/* Only accept the same PVR as the host's, since we can't spoof it */
+	if (sregs->pvr != vcpu->arch.pvr)
+		return -EINVAL;
 
 	j = 0;
 	for (i = 0; i < vcpu->arch.slb_nr; i++) {
@@ -922,6 +954,9 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 	long int i;
 
 	switch (id) {
+	case KVM_REG_PPC_DEBUG_INST:
+		*val = get_reg_val(id, KVMPPC_INST_SW_BREAKPOINT);
+		break;
 	case KVM_REG_PPC_HIOR:
 		*val = get_reg_val(id, 0);
 		break;
@@ -1489,7 +1524,7 @@ static void kvmppc_remove_runnable(struct kvmppc_vcore *vc,
 static int kvmppc_grab_hwthread(int cpu)
 {
 	struct paca_struct *tpaca;
-	long timeout = 1000;
+	long timeout = 10000;
 
 	tpaca = &paca[cpu];
 
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index b9615ba5b083..4fdc27c80f4c 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -163,6 +163,12 @@ void __init kvm_cma_reserve(void)
 	unsigned long align_size;
 	struct memblock_region *reg;
 	phys_addr_t selected_size = 0;
+
+	/*
+	 * We need CMA reservation only when we are in HV mode
+	 */
+	if (!cpu_has_feature(CPU_FTR_HVMODE))
+		return;
 	/*
 	 * We cannot use memblock_phys_mem_size() here, because
 	 * memblock_analyze() has not been called yet.
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index f0c4db7704c3..edb2ccdbb2ba 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -355,6 +355,7 @@ kvmppc_hv_entry:
 	 * MSR = ~IR|DR
 	 * R13 = PACA
 	 * R1 = host R1
+	 * R2 = TOC
 	 * all other volatile GPRS = free
 	 */
 	mflr	r0
@@ -503,7 +504,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 toc_tlbie_lock:
 	.tc	native_tlbie_lock[TC],native_tlbie_lock
 	.previous
-	ld	r3,toc_tlbie_lock@toc(2)
+	ld	r3,toc_tlbie_lock@toc(r2)
 #ifdef __BIG_ENDIAN__
 	lwz	r8,PACA_LOCK_TOKEN(r13)
 #else
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index faffb27badd9..cf2eb16846d1 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -295,7 +295,8 @@ static int kvm_unmap_hva_range_pr(struct kvm *kvm, unsigned long start,
 	return 0;
 }
 
-static int kvm_age_hva_pr(struct kvm *kvm, unsigned long hva)
+static int kvm_age_hva_pr(struct kvm *kvm, unsigned long start,
+			  unsigned long end)
 {
 	/* XXX could be more clever ;) */
 	return 0;
@@ -1319,6 +1320,9 @@ static int kvmppc_get_one_reg_pr(struct kvm_vcpu *vcpu, u64 id,
 	int r = 0;
 
 	switch (id) {
+	case KVM_REG_PPC_DEBUG_INST:
+		*val = get_reg_val(id, KVMPPC_INST_SW_BREAKPOINT);
+		break;
 	case KVM_REG_PPC_HIOR:
 		*val = get_reg_val(id, to_book3s(vcpu)->hior);
 		break;
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index b4c89fa6f109..9b55dec2d6cc 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -124,6 +124,40 @@ static void kvmppc_vcpu_sync_spe(struct kvm_vcpu *vcpu)
 }
 #endif
 
+/*
+ * Load up guest vcpu FP state if it's needed.
+ * It also set the MSR_FP in thread so that host know
+ * we're holding FPU, and then host can help to save
+ * guest vcpu FP state if other threads require to use FPU.
+ * This simulates an FP unavailable fault.
+ *
+ * It requires to be called with preemption disabled.
+ */
+static inline void kvmppc_load_guest_fp(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_PPC_FPU
+	if (!(current->thread.regs->msr & MSR_FP)) {
+		enable_kernel_fp();
+		load_fp_state(&vcpu->arch.fp);
+		current->thread.fp_save_area = &vcpu->arch.fp;
+		current->thread.regs->msr |= MSR_FP;
+	}
+#endif
+}
+
+/*
+ * Save guest vcpu FP state into thread.
+ * It requires to be called with preemption disabled.
+ */
+static inline void kvmppc_save_guest_fp(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_PPC_FPU
+	if (current->thread.regs->msr & MSR_FP)
+		giveup_fpu(current);
+	current->thread.fp_save_area = NULL;
+#endif
+}
+
 static void kvmppc_vcpu_sync_fpu(struct kvm_vcpu *vcpu)
 {
 #if defined(CONFIG_PPC_FPU) && !defined(CONFIG_KVM_BOOKE_HV)
@@ -134,6 +168,40 @@ static void kvmppc_vcpu_sync_fpu(struct kvm_vcpu *vcpu)
 #endif
 }
 
+/*
+ * Simulate AltiVec unavailable fault to load guest state
+ * from thread to AltiVec unit.
+ * It requires to be called with preemption disabled.
+ */
+static inline void kvmppc_load_guest_altivec(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_ALTIVEC
+	if (cpu_has_feature(CPU_FTR_ALTIVEC)) {
+		if (!(current->thread.regs->msr & MSR_VEC)) {
+			enable_kernel_altivec();
+			load_vr_state(&vcpu->arch.vr);
+			current->thread.vr_save_area = &vcpu->arch.vr;
+			current->thread.regs->msr |= MSR_VEC;
+		}
+	}
+#endif
+}
+
+/*
+ * Save guest vcpu AltiVec state into thread.
+ * It requires to be called with preemption disabled.
+ */
+static inline void kvmppc_save_guest_altivec(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_ALTIVEC
+	if (cpu_has_feature(CPU_FTR_ALTIVEC)) {
+		if (current->thread.regs->msr & MSR_VEC)
+			giveup_altivec(current);
+		current->thread.vr_save_area = NULL;
+	}
+#endif
+}
+
 static void kvmppc_vcpu_sync_debug(struct kvm_vcpu *vcpu)
 {
 	/* Synchronize guest's desire to get debug interrupts into shadow MSR */
@@ -267,6 +335,16 @@ static void kvmppc_core_dequeue_watchdog(struct kvm_vcpu *vcpu)
 	clear_bit(BOOKE_IRQPRIO_WATCHDOG, &vcpu->arch.pending_exceptions);
 }
 
+void kvmppc_core_queue_debug(struct kvm_vcpu *vcpu)
+{
+	kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_DEBUG);
+}
+
+void kvmppc_core_dequeue_debug(struct kvm_vcpu *vcpu)
+{
+	clear_bit(BOOKE_IRQPRIO_DEBUG, &vcpu->arch.pending_exceptions);
+}
+
 static void set_guest_srr(struct kvm_vcpu *vcpu, unsigned long srr0, u32 srr1)
 {
 	kvmppc_set_srr0(vcpu, srr0);
@@ -341,9 +419,15 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 	case BOOKE_IRQPRIO_ITLB_MISS:
 	case BOOKE_IRQPRIO_SYSCALL:
 	case BOOKE_IRQPRIO_FP_UNAVAIL:
+#ifdef CONFIG_SPE_POSSIBLE
 	case BOOKE_IRQPRIO_SPE_UNAVAIL:
 	case BOOKE_IRQPRIO_SPE_FP_DATA:
 	case BOOKE_IRQPRIO_SPE_FP_ROUND:
+#endif
+#ifdef CONFIG_ALTIVEC
+	case BOOKE_IRQPRIO_ALTIVEC_UNAVAIL:
+	case BOOKE_IRQPRIO_ALTIVEC_ASSIST:
+#endif
 	case BOOKE_IRQPRIO_AP_UNAVAIL:
 		allowed = 1;
 		msr_mask = MSR_CE | MSR_ME | MSR_DE;
@@ -377,7 +461,11 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 		allowed = vcpu->arch.shared->msr & MSR_DE;
 		allowed = allowed && !crit;
 		msr_mask = MSR_ME;
-		int_class = INT_CLASS_CRIT;
+		if (cpu_has_feature(CPU_FTR_DEBUG_LVL_EXC))
+			int_class = INT_CLASS_DBG;
+		else
+			int_class = INT_CLASS_CRIT;
+
 		break;
 	}
 
@@ -654,20 +742,27 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 
 	/*
 	 * Since we can't trap on MSR_FP in GS-mode, we consider the guest
-	 * as always using the FPU.  Kernel usage of FP (via
-	 * enable_kernel_fp()) in this thread must not occur while
-	 * vcpu->fpu_active is set.
+	 * as always using the FPU.
 	 */
-	vcpu->fpu_active = 1;
-
 	kvmppc_load_guest_fp(vcpu);
 #endif
 
+#ifdef CONFIG_ALTIVEC
+	/* Save userspace AltiVec state in stack */
+	if (cpu_has_feature(CPU_FTR_ALTIVEC))
+		enable_kernel_altivec();
+	/*
+	 * Since we can't trap on MSR_VEC in GS-mode, we consider the guest
+	 * as always using the AltiVec.
+	 */
+	kvmppc_load_guest_altivec(vcpu);
+#endif
+
 	/* Switch to guest debug context */
-	debug = vcpu->arch.shadow_dbg_reg;
+	debug = vcpu->arch.dbg_reg;
 	switch_booke_debug_regs(&debug);
 	debug = current->thread.debug;
-	current->thread.debug = vcpu->arch.shadow_dbg_reg;
+	current->thread.debug = vcpu->arch.dbg_reg;
 
 	vcpu->arch.pgdir = current->mm->pgd;
 	kvmppc_fix_ee_before_entry();
@@ -683,8 +778,10 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 
 #ifdef CONFIG_PPC_FPU
 	kvmppc_save_guest_fp(vcpu);
+#endif
 
-	vcpu->fpu_active = 0;
+#ifdef CONFIG_ALTIVEC
+	kvmppc_save_guest_altivec(vcpu);
 #endif
 
 out:
@@ -728,9 +825,36 @@ static int emulation_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
 
 static int kvmppc_handle_debug(struct kvm_run *run, struct kvm_vcpu *vcpu)
 {
-	struct debug_reg *dbg_reg = &(vcpu->arch.shadow_dbg_reg);
+	struct debug_reg *dbg_reg = &(vcpu->arch.dbg_reg);
 	u32 dbsr = vcpu->arch.dbsr;
 
+	if (vcpu->guest_debug == 0) {
+		/*
+		 * Debug resources belong to Guest.
+		 * Imprecise debug event is not injected
+		 */
+		if (dbsr & DBSR_IDE) {
+			dbsr &= ~DBSR_IDE;
+			if (!dbsr)
+				return RESUME_GUEST;
+		}
+
+		if (dbsr && (vcpu->arch.shared->msr & MSR_DE) &&
+			    (vcpu->arch.dbg_reg.dbcr0 & DBCR0_IDM))
+			kvmppc_core_queue_debug(vcpu);
+
+		/* Inject a program interrupt if trap debug is not allowed */
+		if ((dbsr & DBSR_TIE) && !(vcpu->arch.shared->msr & MSR_DE))
+			kvmppc_core_queue_program(vcpu, ESR_PTR);
+
+		return RESUME_GUEST;
+	}
+
+	/*
+	 * Debug resource owned by userspace.
+	 * Clear guest dbsr (vcpu->arch.dbsr)
+	 */
+	vcpu->arch.dbsr = 0;
 	run->debug.arch.status = 0;
 	run->debug.arch.address = vcpu->arch.pc;
 
@@ -868,7 +992,12 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	case BOOKE_INTERRUPT_DATA_STORAGE:
 	case BOOKE_INTERRUPT_DTLB_MISS:
 	case BOOKE_INTERRUPT_HV_PRIV:
-		emulated = kvmppc_get_last_inst(vcpu, false, &last_inst);
+		emulated = kvmppc_get_last_inst(vcpu, INST_GENERIC, &last_inst);
+		break;
+	case BOOKE_INTERRUPT_PROGRAM:
+		/* SW breakpoints arrive as illegal instructions on HV */
+		if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
+			emulated = kvmppc_get_last_inst(vcpu, INST_GENERIC, &last_inst);
 		break;
 	default:
 		break;
@@ -947,6 +1076,18 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		break;
 
 	case BOOKE_INTERRUPT_PROGRAM:
+		if ((vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) &&
+			(last_inst == KVMPPC_INST_SW_BREAKPOINT)) {
+			/*
+			 * We are here because of an SW breakpoint instr,
+			 * so lets return to host to handle.
+			 */
+			r = kvmppc_handle_debug(run, vcpu);
+			run->exit_reason = KVM_EXIT_DEBUG;
+			kvmppc_account_exit(vcpu, DEBUG_EXITS);
+			break;
+		}
+
 		if (vcpu->arch.shared->msr & (MSR_PR | MSR_GS)) {
 			/*
 			 * Program traps generated by user-level software must
@@ -991,7 +1132,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_SPE_FP_ROUND);
 		r = RESUME_GUEST;
 		break;
-#else
+#elif defined(CONFIG_SPE_POSSIBLE)
 	case BOOKE_INTERRUPT_SPE_UNAVAIL:
 		/*
 		 * Guest wants SPE, but host kernel doesn't support it.  Send
@@ -1012,6 +1153,22 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		run->hw.hardware_exit_reason = exit_nr;
 		r = RESUME_HOST;
 		break;
+#endif /* CONFIG_SPE_POSSIBLE */
+
+/*
+ * On cores with Vector category, KVM is loaded only if CONFIG_ALTIVEC,
+ * see kvmppc_core_check_processor_compat().
+ */
+#ifdef CONFIG_ALTIVEC
+	case BOOKE_INTERRUPT_ALTIVEC_UNAVAIL:
+		kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_ALTIVEC_UNAVAIL);
+		r = RESUME_GUEST;
+		break;
+
+	case BOOKE_INTERRUPT_ALTIVEC_ASSIST:
+		kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_ALTIVEC_ASSIST);
+		r = RESUME_GUEST;
+		break;
 #endif
 
 	case BOOKE_INTERRUPT_DATA_STORAGE:
@@ -1188,6 +1345,8 @@ out:
 		else {
 			/* interrupts now hard-disabled */
 			kvmppc_fix_ee_before_entry();
+			kvmppc_load_guest_fp(vcpu);
+			kvmppc_load_guest_altivec(vcpu);
 		}
 	}
 
@@ -1243,6 +1402,11 @@ int kvmppc_subarch_vcpu_init(struct kvm_vcpu *vcpu)
 	setup_timer(&vcpu->arch.wdt_timer, kvmppc_watchdog_func,
 		    (unsigned long)vcpu);
 
+	/*
+	 * Clear DBSR.MRR to avoid guest debug interrupt as
+	 * this is of host interest
+	 */
+	mtspr(SPRN_DBSR, DBSR_MRR);
 	return 0;
 }
 
@@ -1457,144 +1621,125 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	return vcpu->kvm->arch.kvm_ops->set_sregs(vcpu, sregs);
 }
 
-int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
+int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id,
+			union kvmppc_one_reg *val)
 {
 	int r = 0;
-	union kvmppc_one_reg val;
-	int size;
-
-	size = one_reg_size(reg->id);
-	if (size > sizeof(val))
-		return -EINVAL;
 
-	switch (reg->id) {
+	switch (id) {
 	case KVM_REG_PPC_IAC1:
-		val = get_reg_val(reg->id, vcpu->arch.dbg_reg.iac1);
+		*val = get_reg_val(id, vcpu->arch.dbg_reg.iac1);
 		break;
 	case KVM_REG_PPC_IAC2:
-		val = get_reg_val(reg->id, vcpu->arch.dbg_reg.iac2);
+		*val = get_reg_val(id, vcpu->arch.dbg_reg.iac2);
 		break;
 #if CONFIG_PPC_ADV_DEBUG_IACS > 2
 	case KVM_REG_PPC_IAC3:
-		val = get_reg_val(reg->id, vcpu->arch.dbg_reg.iac3);
+		*val = get_reg_val(id, vcpu->arch.dbg_reg.iac3);
 		break;
 	case KVM_REG_PPC_IAC4:
-		val = get_reg_val(reg->id, vcpu->arch.dbg_reg.iac4);
+		*val = get_reg_val(id, vcpu->arch.dbg_reg.iac4);
 		break;
 #endif
 	case KVM_REG_PPC_DAC1:
-		val = get_reg_val(reg->id, vcpu->arch.dbg_reg.dac1);
+		*val = get_reg_val(id, vcpu->arch.dbg_reg.dac1);
 		break;
 	case KVM_REG_PPC_DAC2:
-		val = get_reg_val(reg->id, vcpu->arch.dbg_reg.dac2);
+		*val = get_reg_val(id, vcpu->arch.dbg_reg.dac2);
 		break;
 	case KVM_REG_PPC_EPR: {
 		u32 epr = kvmppc_get_epr(vcpu);
-		val = get_reg_val(reg->id, epr);
+		*val = get_reg_val(id, epr);
 		break;
 	}
 #if defined(CONFIG_64BIT)
 	case KVM_REG_PPC_EPCR:
-		val = get_reg_val(reg->id, vcpu->arch.epcr);
+		*val = get_reg_val(id, vcpu->arch.epcr);
 		break;
 #endif
 	case KVM_REG_PPC_TCR:
-		val = get_reg_val(reg->id, vcpu->arch.tcr);
+		*val = get_reg_val(id, vcpu->arch.tcr);
 		break;
 	case KVM_REG_PPC_TSR:
-		val = get_reg_val(reg->id, vcpu->arch.tsr);
+		*val = get_reg_val(id, vcpu->arch.tsr);
 		break;
 	case KVM_REG_PPC_DEBUG_INST:
-		val = get_reg_val(reg->id, KVMPPC_INST_EHPRIV_DEBUG);
+		*val = get_reg_val(id, KVMPPC_INST_SW_BREAKPOINT);
 		break;
 	case KVM_REG_PPC_VRSAVE:
-		val = get_reg_val(reg->id, vcpu->arch.vrsave);
+		*val = get_reg_val(id, vcpu->arch.vrsave);
 		break;
 	default:
-		r = vcpu->kvm->arch.kvm_ops->get_one_reg(vcpu, reg->id, &val);
+		r = vcpu->kvm->arch.kvm_ops->get_one_reg(vcpu, id, val);
 		break;
 	}
 
-	if (r)
-		return r;
-
-	if (copy_to_user((char __user *)(unsigned long)reg->addr, &val, size))
-		r = -EFAULT;
-
 	return r;
 }
 
-int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
+int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id,
+			union kvmppc_one_reg *val)
 {
 	int r = 0;
-	union kvmppc_one_reg val;
-	int size;
 
-	size = one_reg_size(reg->id);
-	if (size > sizeof(val))
-		return -EINVAL;
-
-	if (copy_from_user(&val, (char __user *)(unsigned long)reg->addr, size))
-		return -EFAULT;
-
-	switch (reg->id) {
+	switch (id) {
 	case KVM_REG_PPC_IAC1:
-		vcpu->arch.dbg_reg.iac1 = set_reg_val(reg->id, val);
+		vcpu->arch.dbg_reg.iac1 = set_reg_val(id, *val);
 		break;
 	case KVM_REG_PPC_IAC2:
-		vcpu->arch.dbg_reg.iac2 = set_reg_val(reg->id, val);
+		vcpu->arch.dbg_reg.iac2 = set_reg_val(id, *val);
 		break;
 #if CONFIG_PPC_ADV_DEBUG_IACS > 2
 	case KVM_REG_PPC_IAC3:
-		vcpu->arch.dbg_reg.iac3 = set_reg_val(reg->id, val);
+		vcpu->arch.dbg_reg.iac3 = set_reg_val(id, *val);
 		break;
 	case KVM_REG_PPC_IAC4:
-		vcpu->arch.dbg_reg.iac4 = set_reg_val(reg->id, val);
+		vcpu->arch.dbg_reg.iac4 = set_reg_val(id, *val);
 		break;
 #endif
 	case KVM_REG_PPC_DAC1:
-		vcpu->arch.dbg_reg.dac1 = set_reg_val(reg->id, val);
+		vcpu->arch.dbg_reg.dac1 = set_reg_val(id, *val);
 		break;
 	case KVM_REG_PPC_DAC2:
-		vcpu->arch.dbg_reg.dac2 = set_reg_val(reg->id, val);
+		vcpu->arch.dbg_reg.dac2 = set_reg_val(id, *val);
 		break;
 	case KVM_REG_PPC_EPR: {
-		u32 new_epr = set_reg_val(reg->id, val);
+		u32 new_epr = set_reg_val(id, *val);
 		kvmppc_set_epr(vcpu, new_epr);
 		break;
 	}
 #if defined(CONFIG_64BIT)
 	case KVM_REG_PPC_EPCR: {
-		u32 new_epcr = set_reg_val(reg->id, val);
+		u32 new_epcr = set_reg_val(id, *val);
 		kvmppc_set_epcr(vcpu, new_epcr);
 		break;
 	}
 #endif
 	case KVM_REG_PPC_OR_TSR: {
-		u32 tsr_bits = set_reg_val(reg->id, val);
+		u32 tsr_bits = set_reg_val(id, *val);
 		kvmppc_set_tsr_bits(vcpu, tsr_bits);
 		break;
 	}
 	case KVM_REG_PPC_CLEAR_TSR: {
-		u32 tsr_bits = set_reg_val(reg->id, val);
+		u32 tsr_bits = set_reg_val(id, *val);
 		kvmppc_clr_tsr_bits(vcpu, tsr_bits);
 		break;
 	}
 	case KVM_REG_PPC_TSR: {
-		u32 tsr = set_reg_val(reg->id, val);
+		u32 tsr = set_reg_val(id, *val);
 		kvmppc_set_tsr(vcpu, tsr);
 		break;
 	}
 	case KVM_REG_PPC_TCR: {
-		u32 tcr = set_reg_val(reg->id, val);
+		u32 tcr = set_reg_val(id, *val);
 		kvmppc_set_tcr(vcpu, tcr);
 		break;
 	}
 	case KVM_REG_PPC_VRSAVE:
-		vcpu->arch.vrsave = set_reg_val(reg->id, val);
+		vcpu->arch.vrsave = set_reg_val(id, *val);
 		break;
 	default:
-		r = vcpu->kvm->arch.kvm_ops->set_one_reg(vcpu, reg->id, &val);
+		r = vcpu->kvm->arch.kvm_ops->set_one_reg(vcpu, id, val);
 		break;
 	}
 
@@ -1694,10 +1839,8 @@ void kvmppc_clr_tsr_bits(struct kvm_vcpu *vcpu, u32 tsr_bits)
 	update_timer_ints(vcpu);
 }
 
-void kvmppc_decrementer_func(unsigned long data)
+void kvmppc_decrementer_func(struct kvm_vcpu *vcpu)
 {
-	struct kvm_vcpu *vcpu = (struct kvm_vcpu *)data;
-
 	if (vcpu->arch.tcr & TCR_ARE) {
 		vcpu->arch.dec = vcpu->arch.decar;
 		kvmppc_emulate_dec(vcpu);
@@ -1842,7 +1985,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 	int n, b = 0, w = 0;
 
 	if (!(dbg->control & KVM_GUESTDBG_ENABLE)) {
-		vcpu->arch.shadow_dbg_reg.dbcr0 = 0;
+		vcpu->arch.dbg_reg.dbcr0 = 0;
 		vcpu->guest_debug = 0;
 		kvm_guest_protect_msr(vcpu, MSR_DE, false);
 		return 0;
@@ -1850,15 +1993,13 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 
 	kvm_guest_protect_msr(vcpu, MSR_DE, true);
 	vcpu->guest_debug = dbg->control;
-	vcpu->arch.shadow_dbg_reg.dbcr0 = 0;
-	/* Set DBCR0_EDM in guest visible DBCR0 register. */
-	vcpu->arch.dbg_reg.dbcr0 = DBCR0_EDM;
+	vcpu->arch.dbg_reg.dbcr0 = 0;
 
 	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
-		vcpu->arch.shadow_dbg_reg.dbcr0 |= DBCR0_IDM | DBCR0_IC;
+		vcpu->arch.dbg_reg.dbcr0 |= DBCR0_IDM | DBCR0_IC;
 
 	/* Code below handles only HW breakpoints */
-	dbg_reg = &(vcpu->arch.shadow_dbg_reg);
+	dbg_reg = &(vcpu->arch.dbg_reg);
 
 #ifdef CONFIG_KVM_BOOKE_HV
 	/*
diff --git a/arch/powerpc/kvm/booke.h b/arch/powerpc/kvm/booke.h
index f753543c56fa..22ba08ea68e9 100644
--- a/arch/powerpc/kvm/booke.h
+++ b/arch/powerpc/kvm/booke.h
@@ -32,9 +32,15 @@
 #define BOOKE_IRQPRIO_ALIGNMENT 2
 #define BOOKE_IRQPRIO_PROGRAM 3
 #define BOOKE_IRQPRIO_FP_UNAVAIL 4
+#ifdef CONFIG_SPE_POSSIBLE
 #define BOOKE_IRQPRIO_SPE_UNAVAIL 5
 #define BOOKE_IRQPRIO_SPE_FP_DATA 6
 #define BOOKE_IRQPRIO_SPE_FP_ROUND 7
+#endif
+#ifdef CONFIG_PPC_E500MC
+#define BOOKE_IRQPRIO_ALTIVEC_UNAVAIL 5
+#define BOOKE_IRQPRIO_ALTIVEC_ASSIST 6
+#endif
 #define BOOKE_IRQPRIO_SYSCALL 8
 #define BOOKE_IRQPRIO_AP_UNAVAIL 9
 #define BOOKE_IRQPRIO_DTLB_MISS 10
@@ -116,40 +122,6 @@ extern int kvmppc_core_emulate_mtspr_e500(struct kvm_vcpu *vcpu, int sprn,
 extern int kvmppc_core_emulate_mfspr_e500(struct kvm_vcpu *vcpu, int sprn,
 					  ulong *spr_val);
 
-/*
- * Load up guest vcpu FP state if it's needed.
- * It also set the MSR_FP in thread so that host know
- * we're holding FPU, and then host can help to save
- * guest vcpu FP state if other threads require to use FPU.
- * This simulates an FP unavailable fault.
- *
- * It requires to be called with preemption disabled.
- */
-static inline void kvmppc_load_guest_fp(struct kvm_vcpu *vcpu)
-{
-#ifdef CONFIG_PPC_FPU
-	if (vcpu->fpu_active && !(current->thread.regs->msr & MSR_FP)) {
-		enable_kernel_fp();
-		load_fp_state(&vcpu->arch.fp);
-		current->thread.fp_save_area = &vcpu->arch.fp;
-		current->thread.regs->msr |= MSR_FP;
-	}
-#endif
-}
-
-/*
- * Save guest vcpu FP state into thread.
- * It requires to be called with preemption disabled.
- */
-static inline void kvmppc_save_guest_fp(struct kvm_vcpu *vcpu)
-{
-#ifdef CONFIG_PPC_FPU
-	if (vcpu->fpu_active && (current->thread.regs->msr & MSR_FP))
-		giveup_fpu(current);
-	current->thread.fp_save_area = NULL;
-#endif
-}
-
 static inline void kvmppc_clear_dbsr(void)
 {
 	mtspr(SPRN_DBSR, mfspr(SPRN_DBSR));
diff --git a/arch/powerpc/kvm/booke_emulate.c b/arch/powerpc/kvm/booke_emulate.c
index 28c158881d23..a82f64502de1 100644
--- a/arch/powerpc/kvm/booke_emulate.c
+++ b/arch/powerpc/kvm/booke_emulate.c
@@ -25,6 +25,7 @@
 
 #define OP_19_XOP_RFI     50
 #define OP_19_XOP_RFCI    51
+#define OP_19_XOP_RFDI    39
 
 #define OP_31_XOP_MFMSR   83
 #define OP_31_XOP_WRTEE   131
@@ -37,6 +38,12 @@ static void kvmppc_emul_rfi(struct kvm_vcpu *vcpu)
 	kvmppc_set_msr(vcpu, vcpu->arch.shared->srr1);
 }
 
+static void kvmppc_emul_rfdi(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.pc = vcpu->arch.dsrr0;
+	kvmppc_set_msr(vcpu, vcpu->arch.dsrr1);
+}
+
 static void kvmppc_emul_rfci(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.pc = vcpu->arch.csrr0;
@@ -65,6 +72,12 @@ int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			*advance = 0;
 			break;
 
+		case OP_19_XOP_RFDI:
+			kvmppc_emul_rfdi(vcpu);
+			kvmppc_set_exit_type(vcpu, EMULATED_RFDI_EXITS);
+			*advance = 0;
+			break;
+
 		default:
 			emulated = EMULATE_FAIL;
 			break;
@@ -118,6 +131,7 @@ int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 {
 	int emulated = EMULATE_DONE;
+	bool debug_inst = false;
 
 	switch (sprn) {
 	case SPRN_DEAR:
@@ -132,14 +146,128 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 	case SPRN_CSRR1:
 		vcpu->arch.csrr1 = spr_val;
 		break;
+	case SPRN_DSRR0:
+		vcpu->arch.dsrr0 = spr_val;
+		break;
+	case SPRN_DSRR1:
+		vcpu->arch.dsrr1 = spr_val;
+		break;
+	case SPRN_IAC1:
+		/*
+		 * If userspace is debugging guest then guest
+		 * can not access debug registers.
+		 */
+		if (vcpu->guest_debug)
+			break;
+
+		debug_inst = true;
+		vcpu->arch.dbg_reg.iac1 = spr_val;
+		break;
+	case SPRN_IAC2:
+		/*
+		 * If userspace is debugging guest then guest
+		 * can not access debug registers.
+		 */
+		if (vcpu->guest_debug)
+			break;
+
+		debug_inst = true;
+		vcpu->arch.dbg_reg.iac2 = spr_val;
+		break;
+#if CONFIG_PPC_ADV_DEBUG_IACS > 2
+	case SPRN_IAC3:
+		/*
+		 * If userspace is debugging guest then guest
+		 * can not access debug registers.
+		 */
+		if (vcpu->guest_debug)
+			break;
+
+		debug_inst = true;
+		vcpu->arch.dbg_reg.iac3 = spr_val;
+		break;
+	case SPRN_IAC4:
+		/*
+		 * If userspace is debugging guest then guest
+		 * can not access debug registers.
+		 */
+		if (vcpu->guest_debug)
+			break;
+
+		debug_inst = true;
+		vcpu->arch.dbg_reg.iac4 = spr_val;
+		break;
+#endif
+	case SPRN_DAC1:
+		/*
+		 * If userspace is debugging guest then guest
+		 * can not access debug registers.
+		 */
+		if (vcpu->guest_debug)
+			break;
+
+		debug_inst = true;
+		vcpu->arch.dbg_reg.dac1 = spr_val;
+		break;
+	case SPRN_DAC2:
+		/*
+		 * If userspace is debugging guest then guest
+		 * can not access debug registers.
+		 */
+		if (vcpu->guest_debug)
+			break;
+
+		debug_inst = true;
+		vcpu->arch.dbg_reg.dac2 = spr_val;
+		break;
 	case SPRN_DBCR0:
+		/*
+		 * If userspace is debugging guest then guest
+		 * can not access debug registers.
+		 */
+		if (vcpu->guest_debug)
+			break;
+
+		debug_inst = true;
+		spr_val &= (DBCR0_IDM | DBCR0_IC | DBCR0_BT | DBCR0_TIE |
+			DBCR0_IAC1 | DBCR0_IAC2 | DBCR0_IAC3 | DBCR0_IAC4  |
+			DBCR0_DAC1R | DBCR0_DAC1W | DBCR0_DAC2R | DBCR0_DAC2W);
+
 		vcpu->arch.dbg_reg.dbcr0 = spr_val;
 		break;
 	case SPRN_DBCR1:
+		/*
+		 * If userspace is debugging guest then guest
+		 * can not access debug registers.
+		 */
+		if (vcpu->guest_debug)
+			break;
+
+		debug_inst = true;
 		vcpu->arch.dbg_reg.dbcr1 = spr_val;
 		break;
+	case SPRN_DBCR2:
+		/*
+		 * If userspace is debugging guest then guest
+		 * can not access debug registers.
+		 */
+		if (vcpu->guest_debug)
+			break;
+
+		debug_inst = true;
+		vcpu->arch.dbg_reg.dbcr2 = spr_val;
+		break;
 	case SPRN_DBSR:
+		/*
+		 * If userspace is debugging guest then guest
+		 * can not access debug registers.
+		 */
+		if (vcpu->guest_debug)
+			break;
+
 		vcpu->arch.dbsr &= ~spr_val;
+		if (!(vcpu->arch.dbsr & ~DBSR_IDE))
+			kvmppc_core_dequeue_debug(vcpu);
 		break;
 	case SPRN_TSR:
 		kvmppc_clr_tsr_bits(vcpu, spr_val);
@@ -252,6 +380,10 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 		emulated = EMULATE_FAIL;
 	}
 
+	if (debug_inst) {
+		current->thread.debug = vcpu->arch.dbg_reg;
+		switch_booke_debug_regs(&vcpu->arch.dbg_reg);
+	}
 	return emulated;
 }
 
@@ -278,12 +410,43 @@ int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
 	case SPRN_CSRR1:
 		*spr_val = vcpu->arch.csrr1;
 		break;
+	case SPRN_DSRR0:
+		*spr_val = vcpu->arch.dsrr0;
+		break;
+	case SPRN_DSRR1:
+		*spr_val = vcpu->arch.dsrr1;
+		break;
+	case SPRN_IAC1:
+		*spr_val = vcpu->arch.dbg_reg.iac1;
+		break;
+	case SPRN_IAC2:
+		*spr_val = vcpu->arch.dbg_reg.iac2;
+		break;
+#if CONFIG_PPC_ADV_DEBUG_IACS > 2
+	case SPRN_IAC3:
+		*spr_val = vcpu->arch.dbg_reg.iac3;
+		break;
+	case SPRN_IAC4:
+		*spr_val = vcpu->arch.dbg_reg.iac4;
+		break;
+#endif
+	case SPRN_DAC1:
+		*spr_val = vcpu->arch.dbg_reg.dac1;
+		break;
+	case SPRN_DAC2:
+		*spr_val = vcpu->arch.dbg_reg.dac2;
+		break;
 	case SPRN_DBCR0:
 		*spr_val = vcpu->arch.dbg_reg.dbcr0;
+		if (vcpu->guest_debug)
+			*spr_val = *spr_val | DBCR0_EDM;
 		break;
 	case SPRN_DBCR1:
 		*spr_val = vcpu->arch.dbg_reg.dbcr1;
 		break;
+	case SPRN_DBCR2:
+		*spr_val = vcpu->arch.dbg_reg.dbcr2;
+		break;
 	case SPRN_DBSR:
 		*spr_val = vcpu->arch.dbsr;
 		break;
diff --git a/arch/powerpc/kvm/bookehv_interrupts.S b/arch/powerpc/kvm/bookehv_interrupts.S
index e9fa56a911fd..81bd8a07aa51 100644
--- a/arch/powerpc/kvm/bookehv_interrupts.S
+++ b/arch/powerpc/kvm/bookehv_interrupts.S
@@ -238,7 +238,7 @@ kvm_handler BOOKE_INTERRUPT_EXTERNAL, EX_PARAMS(GEN), \
 kvm_handler BOOKE_INTERRUPT_ALIGNMENT, EX_PARAMS(GEN), \
 	SPRN_SRR0, SPRN_SRR1,(NEED_DEAR | NEED_ESR)
 kvm_handler BOOKE_INTERRUPT_PROGRAM, EX_PARAMS(GEN), \
-	SPRN_SRR0, SPRN_SRR1,NEED_ESR
+	SPRN_SRR0, SPRN_SRR1, (NEED_ESR | NEED_EMU)
 kvm_handler BOOKE_INTERRUPT_FP_UNAVAIL, EX_PARAMS(GEN), \
 	SPRN_SRR0, SPRN_SRR1, 0
 kvm_handler BOOKE_INTERRUPT_AP_UNAVAIL, EX_PARAMS(GEN), \
@@ -256,11 +256,9 @@ kvm_handler BOOKE_INTERRUPT_DTLB_MISS, EX_PARAMS_TLB, \
 	SPRN_SRR0, SPRN_SRR1, (NEED_EMU | NEED_DEAR | NEED_ESR)
 kvm_handler BOOKE_INTERRUPT_ITLB_MISS, EX_PARAMS_TLB, \
 	SPRN_SRR0, SPRN_SRR1, 0
-kvm_handler BOOKE_INTERRUPT_SPE_UNAVAIL, EX_PARAMS(GEN), \
+kvm_handler BOOKE_INTERRUPT_ALTIVEC_UNAVAIL, EX_PARAMS(GEN), \
 	SPRN_SRR0, SPRN_SRR1, 0
-kvm_handler BOOKE_INTERRUPT_SPE_FP_DATA, EX_PARAMS(GEN), \
-	SPRN_SRR0, SPRN_SRR1, 0
-kvm_handler BOOKE_INTERRUPT_SPE_FP_ROUND, EX_PARAMS(GEN), \
+kvm_handler BOOKE_INTERRUPT_ALTIVEC_ASSIST, EX_PARAMS(GEN), \
 	SPRN_SRR0, SPRN_SRR1, 0
 kvm_handler BOOKE_INTERRUPT_PERFORMANCE_MONITOR, EX_PARAMS(GEN), \
 	SPRN_SRR0, SPRN_SRR1, 0
@@ -350,7 +348,7 @@ kvm_handler BOOKE_INTERRUPT_INST_STORAGE, SPRN_SRR0, SPRN_SRR1, NEED_ESR
 kvm_handler BOOKE_INTERRUPT_EXTERNAL, SPRN_SRR0, SPRN_SRR1, 0
 kvm_handler BOOKE_INTERRUPT_ALIGNMENT, \
 	SPRN_SRR0, SPRN_SRR1, (NEED_DEAR | NEED_ESR)
-kvm_handler BOOKE_INTERRUPT_PROGRAM, SPRN_SRR0, SPRN_SRR1, NEED_ESR
+kvm_handler BOOKE_INTERRUPT_PROGRAM, SPRN_SRR0, SPRN_SRR1, (NEED_ESR | NEED_EMU)
 kvm_handler BOOKE_INTERRUPT_FP_UNAVAIL, SPRN_SRR0, SPRN_SRR1, 0
 kvm_handler BOOKE_INTERRUPT_SYSCALL, SPRN_SRR0, SPRN_SRR1, 0
 kvm_handler BOOKE_INTERRUPT_AP_UNAVAIL, SPRN_SRR0, SPRN_SRR1, 0
@@ -361,9 +359,6 @@ kvm_lvl_handler BOOKE_INTERRUPT_WATCHDOG, \
 kvm_handler BOOKE_INTERRUPT_DTLB_MISS, \
 	SPRN_SRR0, SPRN_SRR1, (NEED_EMU | NEED_DEAR | NEED_ESR)
 kvm_handler BOOKE_INTERRUPT_ITLB_MISS, SPRN_SRR0, SPRN_SRR1, 0
-kvm_handler BOOKE_INTERRUPT_SPE_UNAVAIL, SPRN_SRR0, SPRN_SRR1, 0
-kvm_handler BOOKE_INTERRUPT_SPE_FP_DATA, SPRN_SRR0, SPRN_SRR1, 0
-kvm_handler BOOKE_INTERRUPT_SPE_FP_ROUND, SPRN_SRR0, SPRN_SRR1, 0
 kvm_handler BOOKE_INTERRUPT_PERFORMANCE_MONITOR, SPRN_SRR0, SPRN_SRR1, 0
 kvm_handler BOOKE_INTERRUPT_DOORBELL, SPRN_SRR0, SPRN_SRR1, 0
 kvm_lvl_handler BOOKE_INTERRUPT_DOORBELL_CRITICAL, \
diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h
index a326178bdea5..72920bed3ac6 100644
--- a/arch/powerpc/kvm/e500.h
+++ b/arch/powerpc/kvm/e500.h
@@ -22,6 +22,7 @@
 #include <linux/kvm_host.h>
 #include <asm/mmu-book3e.h>
 #include <asm/tlb.h>
+#include <asm/cputhreads.h>
 
 enum vcpu_ftr {
 	VCPU_FTR_MMU_V2
@@ -289,6 +290,25 @@ void kvmppc_e500_tlbil_all(struct kvmppc_vcpu_e500 *vcpu_e500);
 #define kvmppc_e500_get_tlb_stid(vcpu, gtlbe)       get_tlb_tid(gtlbe)
 #define get_tlbmiss_tid(vcpu)           get_cur_pid(vcpu)
 #define get_tlb_sts(gtlbe)              (gtlbe->mas1 & MAS1_TS)
+
+/*
+ * These functions should be called with preemption disabled
+ * and the returned value is valid only in that context
+ */
+static inline int get_thread_specific_lpid(int vm_lpid)
+{
+	int vcpu_lpid = vm_lpid;
+
+	if (threads_per_core == 2)
+		vcpu_lpid |= smp_processor_id() & 1;
+
+	return vcpu_lpid;
+}
+
+static inline int get_lpid(struct kvm_vcpu *vcpu)
+{
+	return get_thread_specific_lpid(vcpu->kvm->arch.lpid);
+}
 #else
 unsigned int kvmppc_e500_get_tlb_stid(struct kvm_vcpu *vcpu,
 				      struct kvm_book3e_206_tlb_entry *gtlbe);
diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c
index c99c40e9182a..ce7291c79f6c 100644
--- a/arch/powerpc/kvm/e500_emulate.c
+++ b/arch/powerpc/kvm/e500_emulate.c
@@ -259,6 +259,7 @@ int kvmppc_core_emulate_mtspr_e500(struct kvm_vcpu *vcpu, int sprn, ulong spr_va
 		break;
 
 	/* extra exceptions */
+#ifdef CONFIG_SPE_POSSIBLE
 	case SPRN_IVOR32:
 		vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL] = spr_val;
 		break;
@@ -268,6 +269,15 @@ int kvmppc_core_emulate_mtspr_e500(struct kvm_vcpu *vcpu, int sprn, ulong spr_va
 	case SPRN_IVOR34:
 		vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND] = spr_val;
 		break;
+#endif
+#ifdef CONFIG_ALTIVEC
+	case SPRN_IVOR32:
+		vcpu->arch.ivor[BOOKE_IRQPRIO_ALTIVEC_UNAVAIL] = spr_val;
+		break;
+	case SPRN_IVOR33:
+		vcpu->arch.ivor[BOOKE_IRQPRIO_ALTIVEC_ASSIST] = spr_val;
+		break;
+#endif
 	case SPRN_IVOR35:
 		vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR] = spr_val;
 		break;
@@ -381,6 +391,7 @@ int kvmppc_core_emulate_mfspr_e500(struct kvm_vcpu *vcpu, int sprn, ulong *spr_v
 		break;
 
 	/* extra exceptions */
+#ifdef CONFIG_SPE_POSSIBLE
 	case SPRN_IVOR32:
 		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL];
 		break;
@@ -390,6 +401,15 @@ int kvmppc_core_emulate_mfspr_e500(struct kvm_vcpu *vcpu, int sprn, ulong *spr_v
 	case SPRN_IVOR34:
 		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND];
 		break;
+#endif
+#ifdef CONFIG_ALTIVEC
+	case SPRN_IVOR32:
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_ALTIVEC_UNAVAIL];
+		break;
+	case SPRN_IVOR33:
+		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_ALTIVEC_ASSIST];
+		break;
+#endif
 	case SPRN_IVOR35:
 		*spr_val = vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR];
 		break;
diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c
index 08f14bb57897..769778f855b0 100644
--- a/arch/powerpc/kvm/e500_mmu_host.c
+++ b/arch/powerpc/kvm/e500_mmu_host.c
@@ -69,7 +69,8 @@ static inline u32 e500_shadow_mas3_attrib(u32 mas3, int usermode)
  * writing shadow tlb entry to host TLB
  */
 static inline void __write_host_tlbe(struct kvm_book3e_206_tlb_entry *stlbe,
-				     uint32_t mas0)
+				     uint32_t mas0,
+				     uint32_t lpid)
 {
 	unsigned long flags;
 
@@ -80,7 +81,7 @@ static inline void __write_host_tlbe(struct kvm_book3e_206_tlb_entry *stlbe,
 	mtspr(SPRN_MAS3, (u32)stlbe->mas7_3);
 	mtspr(SPRN_MAS7, (u32)(stlbe->mas7_3 >> 32));
 #ifdef CONFIG_KVM_BOOKE_HV
-	mtspr(SPRN_MAS8, stlbe->mas8);
+	mtspr(SPRN_MAS8, MAS8_TGS | get_thread_specific_lpid(lpid));
 #endif
 	asm volatile("isync; tlbwe" : : : "memory");
 
@@ -129,11 +130,12 @@ static inline void write_host_tlbe(struct kvmppc_vcpu_e500 *vcpu_e500,
 
 	if (tlbsel == 0) {
 		mas0 = get_host_mas0(stlbe->mas2);
-		__write_host_tlbe(stlbe, mas0);
+		__write_host_tlbe(stlbe, mas0, vcpu_e500->vcpu.kvm->arch.lpid);
 	} else {
 		__write_host_tlbe(stlbe,
 				  MAS0_TLBSEL(1) |
-				  MAS0_ESEL(to_htlb1_esel(sesel)));
+				  MAS0_ESEL(to_htlb1_esel(sesel)),
+				  vcpu_e500->vcpu.kvm->arch.lpid);
 	}
 }
 
@@ -176,7 +178,7 @@ void kvmppc_map_magic(struct kvm_vcpu *vcpu)
 		       MAS3_SW | MAS3_SR | MAS3_UW | MAS3_UR;
 	magic.mas8 = 0;
 
-	__write_host_tlbe(&magic, MAS0_TLBSEL(1) | MAS0_ESEL(tlbcam_index));
+	__write_host_tlbe(&magic, MAS0_TLBSEL(1) | MAS0_ESEL(tlbcam_index), 0);
 	preempt_enable();
 }
 #endif
@@ -317,10 +319,6 @@ static void kvmppc_e500_setup_stlbe(
 	stlbe->mas2 = (gvaddr & MAS2_EPN) | (ref->flags & E500_TLB_MAS2_ATTR);
 	stlbe->mas7_3 = ((u64)pfn << PAGE_SHIFT) |
 			e500_shadow_mas3_attrib(gtlbe->mas7_3, pr);
-
-#ifdef CONFIG_KVM_BOOKE_HV
-	stlbe->mas8 = MAS8_TGS | vcpu->kvm->arch.lpid;
-#endif
 }
 
 static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
@@ -633,7 +631,7 @@ int kvmppc_load_last_inst(struct kvm_vcpu *vcpu, enum instruction_type type,
 
 	local_irq_save(flags);
 	mtspr(SPRN_MAS6, (vcpu->arch.pid << MAS6_SPID_SHIFT) | addr_space);
-	mtspr(SPRN_MAS5, MAS5_SGS | vcpu->kvm->arch.lpid);
+	mtspr(SPRN_MAS5, MAS5_SGS | get_lpid(vcpu));
 	asm volatile("tlbsx 0, %[geaddr]\n" : :
 		     [geaddr] "r" (geaddr));
 	mtspr(SPRN_MAS5, 0);
@@ -732,7 +730,7 @@ int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
 	return 0;
 }
 
-int kvm_age_hva(struct kvm *kvm, unsigned long hva)
+int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
 {
 	/* XXX could be more clever ;) */
 	return 0;
diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c
index 164bad2a19bf..2fdc8722e324 100644
--- a/arch/powerpc/kvm/e500mc.c
+++ b/arch/powerpc/kvm/e500mc.c
@@ -48,10 +48,11 @@ void kvmppc_set_pending_interrupt(struct kvm_vcpu *vcpu, enum int_class type)
 		return;
 	}
 
-
-	tag = PPC_DBELL_LPID(vcpu->kvm->arch.lpid) | vcpu->vcpu_id;
+	preempt_disable();
+	tag = PPC_DBELL_LPID(get_lpid(vcpu)) | vcpu->vcpu_id;
 	mb();
 	ppc_msgsnd(dbell_type, 0, tag);
+	preempt_enable();
 }
 
 /* gtlbe must not be mapped by more than one host tlb entry */
@@ -60,12 +61,11 @@ void kvmppc_e500_tlbil_one(struct kvmppc_vcpu_e500 *vcpu_e500,
 {
 	unsigned int tid, ts;
 	gva_t eaddr;
-	u32 val, lpid;
+	u32 val;
 	unsigned long flags;
 
 	ts = get_tlb_ts(gtlbe);
 	tid = get_tlb_tid(gtlbe);
-	lpid = vcpu_e500->vcpu.kvm->arch.lpid;
 
 	/* We search the host TLB to invalidate its shadow TLB entry */
 	val = (tid << 16) | ts;
@@ -74,7 +74,7 @@ void kvmppc_e500_tlbil_one(struct kvmppc_vcpu_e500 *vcpu_e500,
 	local_irq_save(flags);
 
 	mtspr(SPRN_MAS6, val);
-	mtspr(SPRN_MAS5, MAS5_SGS | lpid);
+	mtspr(SPRN_MAS5, MAS5_SGS | get_lpid(&vcpu_e500->vcpu));
 
 	asm volatile("tlbsx 0, %[eaddr]\n" : : [eaddr] "r" (eaddr));
 	val = mfspr(SPRN_MAS1);
@@ -95,7 +95,7 @@ void kvmppc_e500_tlbil_all(struct kvmppc_vcpu_e500 *vcpu_e500)
 	unsigned long flags;
 
 	local_irq_save(flags);
-	mtspr(SPRN_MAS5, MAS5_SGS | vcpu_e500->vcpu.kvm->arch.lpid);
+	mtspr(SPRN_MAS5, MAS5_SGS | get_lpid(&vcpu_e500->vcpu));
 	asm volatile("tlbilxlpid");
 	mtspr(SPRN_MAS5, 0);
 	local_irq_restore(flags);
@@ -110,6 +110,7 @@ void kvmppc_mmu_msr_notify(struct kvm_vcpu *vcpu, u32 old_msr)
 {
 }
 
+/* We use two lpids per VM */
 static DEFINE_PER_CPU(struct kvm_vcpu *[KVMPPC_NR_LPIDS], last_vcpu_of_lpid);
 
 static void kvmppc_core_vcpu_load_e500mc(struct kvm_vcpu *vcpu, int cpu)
@@ -118,10 +119,12 @@ static void kvmppc_core_vcpu_load_e500mc(struct kvm_vcpu *vcpu, int cpu)
 
 	kvmppc_booke_vcpu_load(vcpu, cpu);
 
-	mtspr(SPRN_LPID, vcpu->kvm->arch.lpid);
+	mtspr(SPRN_LPID, get_lpid(vcpu));
 	mtspr(SPRN_EPCR, vcpu->arch.shadow_epcr);
 	mtspr(SPRN_GPIR, vcpu->vcpu_id);
 	mtspr(SPRN_MSRP, vcpu->arch.shadow_msrp);
+	vcpu->arch.eplc = EPC_EGS | (get_lpid(vcpu) << EPC_ELPID_SHIFT);
+	vcpu->arch.epsc = vcpu->arch.eplc;
 	mtspr(SPRN_EPLC, vcpu->arch.eplc);
 	mtspr(SPRN_EPSC, vcpu->arch.epsc);
 
@@ -141,12 +144,10 @@ static void kvmppc_core_vcpu_load_e500mc(struct kvm_vcpu *vcpu, int cpu)
 	mtspr(SPRN_GESR, vcpu->arch.shared->esr);
 
 	if (vcpu->arch.oldpir != mfspr(SPRN_PIR) ||
-	    __get_cpu_var(last_vcpu_of_lpid)[vcpu->kvm->arch.lpid] != vcpu) {
+	    __get_cpu_var(last_vcpu_of_lpid)[get_lpid(vcpu)] != vcpu) {
 		kvmppc_e500_tlbil_all(vcpu_e500);
-		__get_cpu_var(last_vcpu_of_lpid)[vcpu->kvm->arch.lpid] = vcpu;
+		__get_cpu_var(last_vcpu_of_lpid)[get_lpid(vcpu)] = vcpu;
 	}
-
-	kvmppc_load_guest_fp(vcpu);
 }
 
 static void kvmppc_core_vcpu_put_e500mc(struct kvm_vcpu *vcpu)
@@ -179,6 +180,16 @@ int kvmppc_core_check_processor_compat(void)
 		r = 0;
 	else if (strcmp(cur_cpu_spec->cpu_name, "e5500") == 0)
 		r = 0;
+#ifdef CONFIG_ALTIVEC
+	/*
+	 * Since guests have the priviledge to enable AltiVec, we need AltiVec
+	 * support in the host to save/restore their context.
+	 * Don't use CPU_FTR_ALTIVEC to identify cores with AltiVec unit
+	 * because it's cleared in the absence of CONFIG_ALTIVEC!
+	 */
+	else if (strcmp(cur_cpu_spec->cpu_name, "e6500") == 0)
+		r = 0;
+#endif
 	else
 		r = -ENOTSUPP;
 
@@ -194,9 +205,7 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
 #ifdef CONFIG_64BIT
 	vcpu->arch.shadow_epcr |= SPRN_EPCR_ICM;
 #endif
-	vcpu->arch.shadow_msrp = MSRP_UCLEP | MSRP_DEP | MSRP_PMMP;
-	vcpu->arch.eplc = EPC_EGS | (vcpu->kvm->arch.lpid << EPC_ELPID_SHIFT);
-	vcpu->arch.epsc = vcpu->arch.eplc;
+	vcpu->arch.shadow_msrp = MSRP_UCLEP | MSRP_PMMP;
 
 	vcpu->arch.pvr = mfspr(SPRN_PVR);
 	vcpu_e500->svr = mfspr(SPRN_SVR);
@@ -356,13 +365,26 @@ static int kvmppc_core_init_vm_e500mc(struct kvm *kvm)
 	if (lpid < 0)
 		return lpid;
 
+	/*
+	 * Use two lpids per VM on cores with two threads like e6500. Use
+	 * even numbers to speedup vcpu lpid computation with consecutive lpids
+	 * per VM. vm1 will use lpids 2 and 3, vm2 lpids 4 and 5, and so on.
+	 */
+	if (threads_per_core == 2)
+		lpid <<= 1;
+
 	kvm->arch.lpid = lpid;
 	return 0;
 }
 
 static void kvmppc_core_destroy_vm_e500mc(struct kvm *kvm)
 {
-	kvmppc_free_lpid(kvm->arch.lpid);
+	int lpid = kvm->arch.lpid;
+
+	if (threads_per_core == 2)
+		lpid >>= 1;
+
+	kvmppc_free_lpid(lpid);
 }
 
 static struct kvmppc_ops kvm_ops_e500mc = {
@@ -390,7 +412,13 @@ static int __init kvmppc_e500mc_init(void)
 	if (r)
 		goto err_out;
 
-	kvmppc_init_lpid(64);
+	/*
+	 * Use two lpids per VM on dual threaded processors like e6500
+	 * to workarround the lack of tlb write conditional instruction.
+	 * Expose half the number of available hardware lpids to the lpid
+	 * allocator.
+	 */
+	kvmppc_init_lpid(KVMPPC_NR_LPIDS/threads_per_core);
 	kvmppc_claim_lpid(0); /* host */
 
 	r = kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE);
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index e96b50d0bdab..5cc2e7af3a7b 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -219,7 +219,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	/* this default type might be overwritten by subcategories */
 	kvmppc_set_exit_type(vcpu, EMULATED_INST_EXITS);
 
-	emulated = kvmppc_get_last_inst(vcpu, false, &inst);
+	emulated = kvmppc_get_last_inst(vcpu, INST_GENERIC, &inst);
 	if (emulated != EMULATE_DONE)
 		return emulated;
 
@@ -274,6 +274,21 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		}
 		break;
 
+	case 0:
+		/*
+		 * Instruction with primary opcode 0. Based on PowerISA
+		 * these are illegal instructions.
+		 */
+		if (inst == KVMPPC_INST_SW_BREAKPOINT) {
+			run->exit_reason = KVM_EXIT_DEBUG;
+			run->debug.arch.address = kvmppc_get_pc(vcpu);
+			emulated = EMULATE_EXIT_USER;
+			advance = 0;
+		} else
+			emulated = EMULATE_FAIL;
+
+		break;
+
 	default:
 		emulated = EMULATE_FAIL;
 	}
diff --git a/arch/powerpc/kvm/emulate_loadstore.c b/arch/powerpc/kvm/emulate_loadstore.c
index 0de4ffa175a9..6d3c0ee1d744 100644
--- a/arch/powerpc/kvm/emulate_loadstore.c
+++ b/arch/powerpc/kvm/emulate_loadstore.c
@@ -58,7 +58,7 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 	/* this default type might be overwritten by subcategories */
 	kvmppc_set_exit_type(vcpu, EMULATED_INST_EXITS);
 
-	emulated = kvmppc_get_last_inst(vcpu, false, &inst);
+	emulated = kvmppc_get_last_inst(vcpu, INST_GENERIC, &inst);
 	if (emulated != EMULATE_DONE)
 		return emulated;
 
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 4c79284b58be..c1f8f53cd312 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -294,7 +294,7 @@ int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	{
 		u32 last_inst;
 
-		kvmppc_get_last_inst(vcpu, false, &last_inst);
+		kvmppc_get_last_inst(vcpu, INST_GENERIC, &last_inst);
 		/* XXX Deliver Program interrupt to guest. */
 		pr_emerg("%s: emulation failed (%08x)\n", __func__, last_inst);
 		r = RESUME_HOST;
@@ -384,24 +384,16 @@ int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr,
 }
 EXPORT_SYMBOL_GPL(kvmppc_ld);
 
-int kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void)
 {
 	return 0;
 }
 
-void kvm_arch_hardware_disable(void *garbage)
-{
-}
-
 int kvm_arch_hardware_setup(void)
 {
 	return 0;
 }
 
-void kvm_arch_hardware_unsetup(void)
-{
-}
-
 void kvm_arch_check_processor_compat(void *rtn)
 {
 	*(int *)rtn = kvmppc_core_check_processor_compat();
@@ -462,10 +454,6 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	module_put(kvm->arch.kvm_ops->owner);
 }
 
-void kvm_arch_sync_events(struct kvm *kvm)
-{
-}
-
 int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 {
 	int r;
@@ -608,10 +596,6 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
 	return kvmppc_core_create_memslot(kvm, slot, npages);
 }
 
-void kvm_arch_memslots_updated(struct kvm *kvm)
-{
-}
-
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				   struct kvm_memory_slot *memslot,
 				   struct kvm_userspace_memory_region *mem,
@@ -628,10 +612,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 	kvmppc_core_commit_memory_region(kvm, mem, old);
 }
 
-void kvm_arch_flush_shadow_all(struct kvm *kvm)
-{
-}
-
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 				   struct kvm_memory_slot *slot)
 {
@@ -658,7 +638,6 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 {
 	/* Make sure we're not using the vcpu anymore */
 	hrtimer_cancel(&vcpu->arch.dec_timer);
-	tasklet_kill(&vcpu->arch.tasklet);
 
 	kvmppc_remove_vcpu_debugfs(vcpu);
 
@@ -684,16 +663,12 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 	return kvmppc_core_pending_dec(vcpu);
 }
 
-/*
- * low level hrtimer wake routine. Because this runs in hardirq context
- * we schedule a tasklet to do the real work.
- */
 enum hrtimer_restart kvmppc_decrementer_wakeup(struct hrtimer *timer)
 {
 	struct kvm_vcpu *vcpu;
 
 	vcpu = container_of(timer, struct kvm_vcpu, arch.dec_timer);
-	tasklet_schedule(&vcpu->arch.tasklet);
+	kvmppc_decrementer_func(vcpu);
 
 	return HRTIMER_NORESTART;
 }
@@ -703,7 +678,6 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	int ret;
 
 	hrtimer_init(&vcpu->arch.dec_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
-	tasklet_init(&vcpu->arch.tasklet, kvmppc_decrementer_func, (ulong)vcpu);
 	vcpu->arch.dec_timer.function = kvmppc_decrementer_wakeup;
 	vcpu->arch.dec_expires = ~(u64)0;
 
@@ -927,6 +901,103 @@ int kvmppc_handle_store(struct kvm_run *run, struct kvm_vcpu *vcpu,
 }
 EXPORT_SYMBOL_GPL(kvmppc_handle_store);
 
+int kvm_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
+{
+	int r = 0;
+	union kvmppc_one_reg val;
+	int size;
+
+	size = one_reg_size(reg->id);
+	if (size > sizeof(val))
+		return -EINVAL;
+
+	r = kvmppc_get_one_reg(vcpu, reg->id, &val);
+	if (r == -EINVAL) {
+		r = 0;
+		switch (reg->id) {
+#ifdef CONFIG_ALTIVEC
+		case KVM_REG_PPC_VR0 ... KVM_REG_PPC_VR31:
+			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
+				r = -ENXIO;
+				break;
+			}
+			vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0] = val.vval;
+			break;
+		case KVM_REG_PPC_VSCR:
+			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
+				r = -ENXIO;
+				break;
+			}
+			vcpu->arch.vr.vscr.u[3] = set_reg_val(reg->id, val);
+			break;
+		case KVM_REG_PPC_VRSAVE:
+			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
+				r = -ENXIO;
+				break;
+			}
+			vcpu->arch.vrsave = set_reg_val(reg->id, val);
+			break;
+#endif /* CONFIG_ALTIVEC */
+		default:
+			r = -EINVAL;
+			break;
+		}
+	}
+
+	if (r)
+		return r;
+
+	if (copy_to_user((char __user *)(unsigned long)reg->addr, &val, size))
+		r = -EFAULT;
+
+	return r;
+}
+
+int kvm_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu, struct kvm_one_reg *reg)
+{
+	int r;
+	union kvmppc_one_reg val;
+	int size;
+
+	size = one_reg_size(reg->id);
+	if (size > sizeof(val))
+		return -EINVAL;
+
+	if (copy_from_user(&val, (char __user *)(unsigned long)reg->addr, size))
+		return -EFAULT;
+
+	r = kvmppc_set_one_reg(vcpu, reg->id, &val);
+	if (r == -EINVAL) {
+		r = 0;
+		switch (reg->id) {
+#ifdef CONFIG_ALTIVEC
+		case KVM_REG_PPC_VR0 ... KVM_REG_PPC_VR31:
+			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
+				r = -ENXIO;
+				break;
+			}
+			val.vval = vcpu->arch.vr.vr[reg->id - KVM_REG_PPC_VR0];
+			break;
+		case KVM_REG_PPC_VSCR:
+			if (!cpu_has_feature(CPU_FTR_ALTIVEC)) {
+				r = -ENXIO;
+				break;
+			}
+			val = get_reg_val(reg->id, vcpu->arch.vr.vscr.u[3]);
+			break;
+		case KVM_REG_PPC_VRSAVE:
+			val = get_reg_val(reg->id, vcpu->arch.vrsave);
+			break;
+#endif /* CONFIG_ALTIVEC */
+		default:
+			r = -EINVAL;
+			break;
+		}
+	}
+
+	return r;
+}
+
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
 	int r;
@@ -1343,9 +1414,4 @@ int kvm_arch_init(void *opaque)
 	return 0;
 }
 
-void kvm_arch_exit(void)
-{
-
-}
-
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_ppc_instr);