Merge branch 'next' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM changes from Avi Kivity:
 "Changes include additional instruction emulation, page-crossing MMIO,
  faster dirty logging, preventing the watchdog from killing a stopped
  guest, module autoload, a new MSI ABI, and some minor optimizations
  and fixes.  Outside x86 we have a small s390 and a very large ppc
  update.

  Regarding the new (for kvm) rebaseless workflow, some of the patches
  that were merged before we switch trees had to be rebased, while
  others are true pulls.  In either case the signoffs should be correct
  now."

Fix up trivial conflicts in Documentation/feature-removal-schedule.txt
arch/powerpc/kvm/book3s_segment.S and arch/x86/include/asm/kvm_para.h.

I suspect the kvm_para.h resolution ends up doing the "do I have cpuid"
check effectively twice (it was done differently in two different
commits), but better safe than sorry ;)

* 'next' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (125 commits)
  KVM: make asm-generic/kvm_para.h have an ifdef __KERNEL__ block
  KVM: s390: onereg for timer related registers
  KVM: s390: epoch difference and TOD programmable field
  KVM: s390: KVM_GET/SET_ONEREG for s390
  KVM: s390: add capability indicating COW support
  KVM: Fix mmu_reload() clash with nested vmx event injection
  KVM: MMU: Don't use RCU for lockless shadow walking
  KVM: VMX: Optimize %ds, %es reload
  KVM: VMX: Fix %ds/%es clobber
  KVM: x86 emulator: convert bsf/bsr instructions to emulate_2op_SrcV_nobyte()
  KVM: VMX: unlike vmcs on fail path
  KVM: PPC: Emulator: clean up SPR reads and writes
  KVM: PPC: Emulator: clean up instruction parsing
  kvm/powerpc: Add new ioctl to retreive server MMU infos
  kvm/book3s: Make kernel emulated H_PUT_TCE available for "PR" KVM
  KVM: PPC: bookehv: Fix r8/r13 storing in level exception handler
  KVM: PPC: Book3S: Enable IRQs during exit handling
  KVM: PPC: Fix PR KVM on POWER7 bare metal
  KVM: PPC: Fix stbux emulation
  KVM: PPC: bookehv: Use lwz/stw instead of PPC_LL/PPC_STL for 32-bit fields
  ...

1 files changed, 392 insertions, 79 deletions

diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index ee9e1ee..72f13f4 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -17,6 +17,8 @@
  *
  * Authors: Hollis Blanchard <hollisb@us.ibm.com>
  *          Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
+ *          Scott Wood <scottwood@freescale.com>
+ *          Varun Sethi <varun.sethi@freescale.com>
  */
 
 #include <linux/errno.h>
@@ -30,9 +32,12 @@
 #include <asm/cputable.h>
 #include <asm/uaccess.h>
 #include <asm/kvm_ppc.h>
-#include "timing.h"
 #include <asm/cacheflush.h>
+#include <asm/dbell.h>
+#include <asm/hw_irq.h>
+#include <asm/irq.h>
 
+#include "timing.h"
 #include "booke.h"
 
 unsigned long kvmppc_booke_handlers;
@@ -55,6 +60,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "dec",        VCPU_STAT(dec_exits) },
 	{ "ext_intr",   VCPU_STAT(ext_intr_exits) },
 	{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
+	{ "doorbell", VCPU_STAT(dbell_exits) },
+	{ "guest doorbell", VCPU_STAT(gdbell_exits) },
 	{ NULL }
 };
 
@@ -121,6 +128,10 @@ void kvmppc_set_msr(struct kvm_vcpu *vcpu, u32 new_msr)
 {
 	u32 old_msr = vcpu->arch.shared->msr;
 
+#ifdef CONFIG_KVM_BOOKE_HV
+	new_msr |= MSR_GS;
+#endif
+
 	vcpu->arch.shared->msr = new_msr;
 
 	kvmppc_mmu_msr_notify(vcpu, old_msr);
@@ -195,17 +206,87 @@ void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu,
 	clear_bit(BOOKE_IRQPRIO_EXTERNAL_LEVEL, &vcpu->arch.pending_exceptions);
 }
 
+static void set_guest_srr(struct kvm_vcpu *vcpu, unsigned long srr0, u32 srr1)
+{
+#ifdef CONFIG_KVM_BOOKE_HV
+	mtspr(SPRN_GSRR0, srr0);
+	mtspr(SPRN_GSRR1, srr1);
+#else
+	vcpu->arch.shared->srr0 = srr0;
+	vcpu->arch.shared->srr1 = srr1;
+#endif
+}
+
+static void set_guest_csrr(struct kvm_vcpu *vcpu, unsigned long srr0, u32 srr1)
+{
+	vcpu->arch.csrr0 = srr0;
+	vcpu->arch.csrr1 = srr1;
+}
+
+static void set_guest_dsrr(struct kvm_vcpu *vcpu, unsigned long srr0, u32 srr1)
+{
+	if (cpu_has_feature(CPU_FTR_DEBUG_LVL_EXC)) {
+		vcpu->arch.dsrr0 = srr0;
+		vcpu->arch.dsrr1 = srr1;
+	} else {
+		set_guest_csrr(vcpu, srr0, srr1);
+	}
+}
+
+static void set_guest_mcsrr(struct kvm_vcpu *vcpu, unsigned long srr0, u32 srr1)
+{
+	vcpu->arch.mcsrr0 = srr0;
+	vcpu->arch.mcsrr1 = srr1;
+}
+
+static unsigned long get_guest_dear(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_KVM_BOOKE_HV
+	return mfspr(SPRN_GDEAR);
+#else
+	return vcpu->arch.shared->dar;
+#endif
+}
+
+static void set_guest_dear(struct kvm_vcpu *vcpu, unsigned long dear)
+{
+#ifdef CONFIG_KVM_BOOKE_HV
+	mtspr(SPRN_GDEAR, dear);
+#else
+	vcpu->arch.shared->dar = dear;
+#endif
+}
+
+static unsigned long get_guest_esr(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_KVM_BOOKE_HV
+	return mfspr(SPRN_GESR);
+#else
+	return vcpu->arch.shared->esr;
+#endif
+}
+
+static void set_guest_esr(struct kvm_vcpu *vcpu, u32 esr)
+{
+#ifdef CONFIG_KVM_BOOKE_HV
+	mtspr(SPRN_GESR, esr);
+#else
+	vcpu->arch.shared->esr = esr;
+#endif
+}
+
 /* Deliver the interrupt of the corresponding priority, if possible. */
 static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
                                         unsigned int priority)
 {
 	int allowed = 0;
-	ulong uninitialized_var(msr_mask);
+	ulong msr_mask = 0;
 	bool update_esr = false, update_dear = false;
 	ulong crit_raw = vcpu->arch.shared->critical;
 	ulong crit_r1 = kvmppc_get_gpr(vcpu, 1);
 	bool crit;
 	bool keep_irq = false;
+	enum int_class int_class;
 
 	/* Truncate crit indicators in 32 bit mode */
 	if (!(vcpu->arch.shared->msr & MSR_SF)) {
@@ -241,46 +322,85 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 	case BOOKE_IRQPRIO_AP_UNAVAIL:
 	case BOOKE_IRQPRIO_ALIGNMENT:
 		allowed = 1;
-		msr_mask = MSR_CE|MSR_ME|MSR_DE;
+		msr_mask = MSR_CE | MSR_ME | MSR_DE;
+		int_class = INT_CLASS_NONCRIT;
 		break;
 	case BOOKE_IRQPRIO_CRITICAL:
-	case BOOKE_IRQPRIO_WATCHDOG:
+	case BOOKE_IRQPRIO_DBELL_CRIT:
 		allowed = vcpu->arch.shared->msr & MSR_CE;
+		allowed = allowed && !crit;
 		msr_mask = MSR_ME;
+		int_class = INT_CLASS_CRIT;
 		break;
 	case BOOKE_IRQPRIO_MACHINE_CHECK:
 		allowed = vcpu->arch.shared->msr & MSR_ME;
-		msr_mask = 0;
+		allowed = allowed && !crit;
+		int_class = INT_CLASS_MC;
 		break;
 	case BOOKE_IRQPRIO_DECREMENTER:
 	case BOOKE_IRQPRIO_FIT:
 		keep_irq = true;
 		/* fall through */
 	case BOOKE_IRQPRIO_EXTERNAL:
+	case BOOKE_IRQPRIO_DBELL:
 		allowed = vcpu->arch.shared->msr & MSR_EE;
 		allowed = allowed && !crit;
-		msr_mask = MSR_CE|MSR_ME|MSR_DE;
+		msr_mask = MSR_CE | MSR_ME | MSR_DE;
+		int_class = INT_CLASS_NONCRIT;
 		break;
 	case BOOKE_IRQPRIO_DEBUG:
 		allowed = vcpu->arch.shared->msr & MSR_DE;
+		allowed = allowed && !crit;
 		msr_mask = MSR_ME;
+		int_class = INT_CLASS_CRIT;
 		break;
 	}
 
 	if (allowed) {
-		vcpu->arch.shared->srr0 = vcpu->arch.pc;
-		vcpu->arch.shared->srr1 = vcpu->arch.shared->msr;
+		switch (int_class) {
+		case INT_CLASS_NONCRIT:
+			set_guest_srr(vcpu, vcpu->arch.pc,
+				      vcpu->arch.shared->msr);
+			break;
+		case INT_CLASS_CRIT:
+			set_guest_csrr(vcpu, vcpu->arch.pc,
+				       vcpu->arch.shared->msr);
+			break;
+		case INT_CLASS_DBG:
+			set_guest_dsrr(vcpu, vcpu->arch.pc,
+				       vcpu->arch.shared->msr);
+			break;
+		case INT_CLASS_MC:
+			set_guest_mcsrr(vcpu, vcpu->arch.pc,
+					vcpu->arch.shared->msr);
+			break;
+		}
+
 		vcpu->arch.pc = vcpu->arch.ivpr | vcpu->arch.ivor[priority];
 		if (update_esr == true)
-			vcpu->arch.shared->esr = vcpu->arch.queued_esr;
+			set_guest_esr(vcpu, vcpu->arch.queued_esr);
 		if (update_dear == true)
-			vcpu->arch.shared->dar = vcpu->arch.queued_dear;
+			set_guest_dear(vcpu, vcpu->arch.queued_dear);
 		kvmppc_set_msr(vcpu, vcpu->arch.shared->msr & msr_mask);
 
 		if (!keep_irq)
 			clear_bit(priority, &vcpu->arch.pending_exceptions);
 	}
 
+#ifdef CONFIG_KVM_BOOKE_HV
+	/*
+	 * If an interrupt is pending but masked, raise a guest doorbell
+	 * so that we are notified when the guest enables the relevant
+	 * MSR bit.
+	 */
+	if (vcpu->arch.pending_exceptions & BOOKE_IRQMASK_EE)
+		kvmppc_set_pending_interrupt(vcpu, INT_CLASS_NONCRIT);
+	if (vcpu->arch.pending_exceptions & BOOKE_IRQMASK_CE)
+		kvmppc_set_pending_interrupt(vcpu, INT_CLASS_CRIT);
+	if (vcpu->arch.pending_exceptions & BOOKE_IRQPRIO_MACHINE_CHECK)
+		kvmppc_set_pending_interrupt(vcpu, INT_CLASS_MC);
+#endif
+
 	return allowed;
 }
 
@@ -305,7 +425,7 @@ static void kvmppc_core_check_exceptions(struct kvm_vcpu *vcpu)
 	}
 
 	priority = __ffs(*pending);
-	while (priority <= BOOKE_IRQPRIO_MAX) {
+	while (priority < BOOKE_IRQPRIO_MAX) {
 		if (kvmppc_booke_irqprio_deliver(vcpu, priority))
 			break;
 
@@ -319,8 +439,9 @@ static void kvmppc_core_check_exceptions(struct kvm_vcpu *vcpu)
 }
 
 /* Check pending exceptions and deliver one, if possible. */
-void kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu)
+int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu)
 {
+	int r = 0;
 	WARN_ON_ONCE(!irqs_disabled());
 
 	kvmppc_core_check_exceptions(vcpu);
@@ -328,16 +449,60 @@ void kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.shared->msr & MSR_WE) {
 		local_irq_enable();
 		kvm_vcpu_block(vcpu);
+		clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
 		local_irq_disable();
 
 		kvmppc_set_exit_type(vcpu, EMULATED_MTMSRWE_EXITS);
-		kvmppc_core_check_exceptions(vcpu);
+		r = 1;
 	};
+
+	return r;
+}
+
+/*
+ * Common checks before entering the guest world.  Call with interrupts
+ * disabled.
+ *
+ * returns !0 if a signal is pending and check_signal is true
+ */
+static int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu)
+{
+	int r = 0;
+
+	WARN_ON_ONCE(!irqs_disabled());
+	while (true) {
+		if (need_resched()) {
+			local_irq_enable();
+			cond_resched();
+			local_irq_disable();
+			continue;
+		}
+
+		if (signal_pending(current)) {
+			r = 1;
+			break;
+		}
+
+		if (kvmppc_core_prepare_to_enter(vcpu)) {
+			/* interrupts got enabled in between, so we
+			   are back at square 1 */
+			continue;
+		}
+
+		break;
+	}
+
+	return r;
 }
 
 int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 {
 	int ret;
+#ifdef CONFIG_PPC_FPU
+	unsigned int fpscr;
+	int fpexc_mode;
+	u64 fpr[32];
+#endif
 
 	if (!vcpu->arch.sane) {
 		kvm_run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
@@ -345,17 +510,53 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	}
 
 	local_irq_disable();
-
-	kvmppc_core_prepare_to_enter(vcpu);
-
-	if (signal_pending(current)) {
+	if (kvmppc_prepare_to_enter(vcpu)) {
 		kvm_run->exit_reason = KVM_EXIT_INTR;
 		ret = -EINTR;
 		goto out;
 	}
 
 	kvm_guest_enter();
+
+#ifdef CONFIG_PPC_FPU
+	/* Save userspace FPU state in stack */
+	enable_kernel_fp();
+	memcpy(fpr, current->thread.fpr, sizeof(current->thread.fpr));
+	fpscr = current->thread.fpscr.val;
+	fpexc_mode = current->thread.fpexc_mode;
+
+	/* Restore guest FPU state to thread */
+	memcpy(current->thread.fpr, vcpu->arch.fpr, sizeof(vcpu->arch.fpr));
+	current->thread.fpscr.val = vcpu->arch.fpscr;
+
+	/*
+	 * 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.
+	 */
+	vcpu->fpu_active = 1;
+
+	kvmppc_load_guest_fp(vcpu);
+#endif
+
 	ret = __kvmppc_vcpu_run(kvm_run, vcpu);
+
+#ifdef CONFIG_PPC_FPU
+	kvmppc_save_guest_fp(vcpu);
+
+	vcpu->fpu_active = 0;
+
+	/* Save guest FPU state from thread */
+	memcpy(vcpu->arch.fpr, current->thread.fpr, sizeof(vcpu->arch.fpr));
+	vcpu->arch.fpscr = current->thread.fpscr.val;
+
+	/* Restore userspace FPU state from stack */
+	memcpy(current->thread.fpr, fpr, sizeof(current->thread.fpr));
+	current->thread.fpscr.val = fpscr;
+	current->thread.fpexc_mode = fpexc_mode;
+#endif
+
 	kvm_guest_exit();
 
 out:
@@ -363,6 +564,84 @@ out:
 	return ret;
 }
 
+static int emulation_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
+{
+	enum emulation_result er;
+
+	er = kvmppc_emulate_instruction(run, vcpu);
+	switch (er) {
+	case EMULATE_DONE:
+		/* don't overwrite subtypes, just account kvm_stats */
+		kvmppc_account_exit_stat(vcpu, EMULATED_INST_EXITS);
+		/* Future optimization: only reload non-volatiles if
+		 * they were actually modified by emulation. */
+		return RESUME_GUEST_NV;
+
+	case EMULATE_DO_DCR:
+		run->exit_reason = KVM_EXIT_DCR;
+		return RESUME_HOST;
+
+	case EMULATE_FAIL:
+		printk(KERN_CRIT "%s: emulation at %lx failed (%08x)\n",
+		       __func__, vcpu->arch.pc, vcpu->arch.last_inst);
+		/* For debugging, encode the failing instruction and
+		 * report it to userspace. */
+		run->hw.hardware_exit_reason = ~0ULL << 32;
+		run->hw.hardware_exit_reason |= vcpu->arch.last_inst;
+		kvmppc_core_queue_program(vcpu, ESR_PIL);
+		return RESUME_HOST;
+
+	default:
+		BUG();
+	}
+}
+
+static void kvmppc_fill_pt_regs(struct pt_regs *regs)
+{
+	ulong r1, ip, msr, lr;
+
+	asm("mr %0, 1" : "=r"(r1));
+	asm("mflr %0" : "=r"(lr));
+	asm("mfmsr %0" : "=r"(msr));
+	asm("bl 1f; 1: mflr %0" : "=r"(ip));
+
+	memset(regs, 0, sizeof(*regs));
+	regs->gpr[1] = r1;
+	regs->nip = ip;
+	regs->msr = msr;
+	regs->link = lr;
+}
+
+static void kvmppc_restart_interrupt(struct kvm_vcpu *vcpu,
+				     unsigned int exit_nr)
+{
+	struct pt_regs regs;
+
+	switch (exit_nr) {
+	case BOOKE_INTERRUPT_EXTERNAL:
+		kvmppc_fill_pt_regs(&regs);
+		do_IRQ(&regs);
+		break;
+	case BOOKE_INTERRUPT_DECREMENTER:
+		kvmppc_fill_pt_regs(&regs);
+		timer_interrupt(&regs);
+		break;
+#if defined(CONFIG_PPC_FSL_BOOK3E) || defined(CONFIG_PPC_BOOK3E_64)
+	case BOOKE_INTERRUPT_DOORBELL:
+		kvmppc_fill_pt_regs(&regs);
+		doorbell_exception(&regs);
+		break;
+#endif
+	case BOOKE_INTERRUPT_MACHINE_CHECK:
+		/* FIXME */
+		break;
+	case BOOKE_INTERRUPT_PERFORMANCE_MONITOR:
+		kvmppc_fill_pt_regs(&regs);
+		performance_monitor_exception(&regs);
+		break;
+	}
+}
+
 /**
  * kvmppc_handle_exit
  *
@@ -371,12 +650,14 @@ out:
 int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
                        unsigned int exit_nr)
 {
-	enum emulation_result er;
 	int r = RESUME_HOST;
 
 	/* update before a new last_exit_type is rewritten */
 	kvmppc_update_timing_stats(vcpu);
 
+	/* restart interrupts if they were meant for the host */
+	kvmppc_restart_interrupt(vcpu, exit_nr);
+
 	local_irq_enable();
 
 	run->exit_reason = KVM_EXIT_UNKNOWN;
@@ -386,62 +667,74 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	case BOOKE_INTERRUPT_MACHINE_CHECK:
 		printk("MACHINE CHECK: %lx\n", mfspr(SPRN_MCSR));
 		kvmppc_dump_vcpu(vcpu);
+		/* For debugging, send invalid exit reason to user space */
+		run->hw.hardware_exit_reason = ~1ULL << 32;
+		run->hw.hardware_exit_reason |= mfspr(SPRN_MCSR);
 		r = RESUME_HOST;
 		break;
 
 	case BOOKE_INTERRUPT_EXTERNAL:
 		kvmppc_account_exit(vcpu, EXT_INTR_EXITS);
-		if (need_resched())
-			cond_resched();
 		r = RESUME_GUEST;
 		break;
 
 	case BOOKE_INTERRUPT_DECREMENTER:
-		/* Since we switched IVPR back to the host's value, the host
-		 * handled this interrupt the moment we enabled interrupts.
-		 * Now we just offer it a chance to reschedule the guest. */
 		kvmppc_account_exit(vcpu, DEC_EXITS);
-		if (need_resched())
-			cond_resched();
 		r = RESUME_GUEST;
 		break;
 
+	case BOOKE_INTERRUPT_DOORBELL:
+		kvmppc_account_exit(vcpu, DBELL_EXITS);
+		r = RESUME_GUEST;
+		break;
+
+	case BOOKE_INTERRUPT_GUEST_DBELL_CRIT:
+		kvmppc_account_exit(vcpu, GDBELL_EXITS);
+
+		/*
+		 * We are here because there is a pending guest interrupt
+		 * which could not be delivered as MSR_CE or MSR_ME was not
+		 * set.  Once we break from here we will retry delivery.
+		 */
+		r = RESUME_GUEST;
+		break;
+
+	case BOOKE_INTERRUPT_GUEST_DBELL:
+		kvmppc_account_exit(vcpu, GDBELL_EXITS);
+
+		/*
+		 * We are here because there is a pending guest interrupt
+		 * which could not be delivered as MSR_EE was not set.  Once
+		 * we break from here we will retry delivery.
+		 */
+		r = RESUME_GUEST;
+		break;
+
+	case BOOKE_INTERRUPT_PERFORMANCE_MONITOR:
+		r = RESUME_GUEST;
+		break;
+
+	case BOOKE_INTERRUPT_HV_PRIV:
+		r = emulation_exit(run, vcpu);
+		break;
+
 	case BOOKE_INTERRUPT_PROGRAM:
-		if (vcpu->arch.shared->msr & MSR_PR) {
-			/* Program traps generated by user-level software must be handled
-			 * by the guest kernel. */
+		if (vcpu->arch.shared->msr & (MSR_PR | MSR_GS)) {
+			/*
+			 * Program traps generated by user-level software must
+			 * be handled by the guest kernel.
+			 *
+			 * In GS mode, hypervisor privileged instructions trap
+			 * on BOOKE_INTERRUPT_HV_PRIV, not here, so these are
+			 * actual program interrupts, handled by the guest.
+			 */
 			kvmppc_core_queue_program(vcpu, vcpu->arch.fault_esr);
 			r = RESUME_GUEST;
 			kvmppc_account_exit(vcpu, USR_PR_INST);
 			break;
 		}
 
-		er = kvmppc_emulate_instruction(run, vcpu);
-		switch (er) {
-		case EMULATE_DONE:
-			/* don't overwrite subtypes, just account kvm_stats */
-			kvmppc_account_exit_stat(vcpu, EMULATED_INST_EXITS);
-			/* Future optimization: only reload non-volatiles if
-			 * they were actually modified by emulation. */
-			r = RESUME_GUEST_NV;
-			break;
-		case EMULATE_DO_DCR:
-			run->exit_reason = KVM_EXIT_DCR;
-			r = RESUME_HOST;
-			break;
-		case EMULATE_FAIL:
-			/* XXX Deliver Program interrupt to guest. */
-			printk(KERN_CRIT "%s: emulation at %lx failed (%08x)\n",
-			       __func__, vcpu->arch.pc, vcpu->arch.last_inst);
-			/* For debugging, encode the failing instruction and
-			 * report it to userspace. */
-			run->hw.hardware_exit_reason = ~0ULL << 32;
-			run->hw.hardware_exit_reason |= vcpu->arch.last_inst;
-			r = RESUME_HOST;
-			break;
-		default:
-			BUG();
-		}
+		r = emulation_exit(run, vcpu);
 		break;
 
 	case BOOKE_INTERRUPT_FP_UNAVAIL:
@@ -506,6 +799,21 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		r = RESUME_GUEST;
 		break;
 
+#ifdef CONFIG_KVM_BOOKE_HV
+	case BOOKE_INTERRUPT_HV_SYSCALL:
+		if (!(vcpu->arch.shared->msr & MSR_PR)) {
+			kvmppc_set_gpr(vcpu, 3, kvmppc_kvm_pv(vcpu));
+		} else {
+			/*
+			 * hcall from guest userspace -- send privileged
+			 * instruction program check.
+			 */
+			kvmppc_core_queue_program(vcpu, ESR_PPR);
+		}
+
+		r = RESUME_GUEST;
+		break;
+#else
 	case BOOKE_INTERRUPT_SYSCALL:
 		if (!(vcpu->arch.shared->msr & MSR_PR) &&
 		    (((u32)kvmppc_get_gpr(vcpu, 0)) == KVM_SC_MAGIC_R0)) {
@@ -519,6 +827,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		kvmppc_account_exit(vcpu, SYSCALL_EXITS);
 		r = RESUME_GUEST;
 		break;
+#endif
 
 	case BOOKE_INTERRUPT_DTLB_MISS: {
 		unsigned long eaddr = vcpu->arch.fault_dear;
@@ -526,7 +835,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		gpa_t gpaddr;
 		gfn_t gfn;
 
-#ifdef CONFIG_KVM_E500
+#ifdef CONFIG_KVM_E500V2
 		if (!(vcpu->arch.shared->msr & MSR_PR) &&
 		    (eaddr & PAGE_MASK) == vcpu->arch.magic_page_ea) {
 			kvmppc_map_magic(vcpu);
@@ -567,6 +876,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			/* Guest has mapped and accessed a page which is not
 			 * actually RAM. */
 			vcpu->arch.paddr_accessed = gpaddr;
+			vcpu->arch.vaddr_accessed = eaddr;
 			r = kvmppc_emulate_mmio(run, vcpu);
 			kvmppc_account_exit(vcpu, MMIO_EXITS);
 		}
@@ -634,15 +944,13 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		BUG();
 	}
 
-	local_irq_disable();
-
-	kvmppc_core_prepare_to_enter(vcpu);
-
+	/*
+	 * To avoid clobbering exit_reason, only check for signals if we
+	 * aren't already exiting to userspace for some other reason.
+	 */
 	if (!(r & RESUME_HOST)) {
-		/* To avoid clobbering exit_reason, only check for signals if
-		 * we aren't already exiting to userspace for some other
-		 * reason. */
-		if (signal_pending(current)) {
+		local_irq_disable();
+		if (kvmppc_prepare_to_enter(vcpu)) {
 			run->exit_reason = KVM_EXIT_INTR;
 			r = (-EINTR << 2) | RESUME_HOST | (r & RESUME_FLAG_NV);
 			kvmppc_account_exit(vcpu, SIGNAL_EXITS);
@@ -659,12 +967,15 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	int r;
 
 	vcpu->arch.pc = 0;
-	vcpu->arch.shared->msr = 0;
-	vcpu->arch.shadow_msr = MSR_USER | MSR_DE | MSR_IS | MSR_DS;
 	vcpu->arch.shared->pir = vcpu->vcpu_id;
 	kvmppc_set_gpr(vcpu, 1, (16<<20) - 8); /* -8 for the callee-save LR slot */
+	kvmppc_set_msr(vcpu, 0);
 
+#ifndef CONFIG_KVM_BOOKE_HV
+	vcpu->arch.shadow_msr = MSR_USER | MSR_DE | MSR_IS | MSR_DS;
 	vcpu->arch.shadow_pid = 1;
+	vcpu->arch.shared->msr = 0;
+#endif
 
 	/* Eye-catching numbers so we know if the guest takes an interrupt
 	 * before it's programmed its own IVPR/IVORs. */
@@ -745,8 +1056,8 @@ static void get_sregs_base(struct kvm_vcpu *vcpu,
 	sregs->u.e.csrr0 = vcpu->arch.csrr0;
 	sregs->u.e.csrr1 = vcpu->arch.csrr1;
 	sregs->u.e.mcsr = vcpu->arch.mcsr;
-	sregs->u.e.esr = vcpu->arch.shared->esr;
-	sregs->u.e.dear = vcpu->arch.shared->dar;
+	sregs->u.e.esr = get_guest_esr(vcpu);
+	sregs->u.e.dear = get_guest_dear(vcpu);
 	sregs->u.e.tsr = vcpu->arch.tsr;
 	sregs->u.e.tcr = vcpu->arch.tcr;
 	sregs->u.e.dec = kvmppc_get_dec(vcpu, tb);
@@ -763,8 +1074,8 @@ static int set_sregs_base(struct kvm_vcpu *vcpu,
 	vcpu->arch.csrr0 = sregs->u.e.csrr0;
 	vcpu->arch.csrr1 = sregs->u.e.csrr1;
 	vcpu->arch.mcsr = sregs->u.e.mcsr;
-	vcpu->arch.shared->esr = sregs->u.e.esr;
-	vcpu->arch.shared->dar = sregs->u.e.dear;
+	set_guest_esr(vcpu, sregs->u.e.esr);
+	set_guest_dear(vcpu, sregs->u.e.dear);
 	vcpu->arch.vrsave = sregs->u.e.vrsave;
 	kvmppc_set_tcr(vcpu, sregs->u.e.tcr);
 
@@ -932,15 +1243,6 @@ void kvmppc_core_commit_memory_region(struct kvm *kvm,
 {
 }
 
-int kvmppc_core_init_vm(struct kvm *kvm)
-{
-	return 0;
-}
-
-void kvmppc_core_destroy_vm(struct kvm *kvm)
-{
-}
-
 void kvmppc_set_tcr(struct kvm_vcpu *vcpu, u32 new_tcr)
 {
 	vcpu->arch.tcr = new_tcr;
@@ -968,8 +1270,19 @@ void kvmppc_decrementer_func(unsigned long data)
 	kvmppc_set_tsr_bits(vcpu, TSR_DIS);
 }
 
+void kvmppc_booke_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+	current->thread.kvm_vcpu = vcpu;
+}
+
+void kvmppc_booke_vcpu_put(struct kvm_vcpu *vcpu)
+{
+	current->thread.kvm_vcpu = NULL;
+}
+
 int __init kvmppc_booke_init(void)
 {
+#ifndef CONFIG_KVM_BOOKE_HV
 	unsigned long ivor[16];
 	unsigned long max_ivor = 0;
 	int i;
@@ -1012,7 +1325,7 @@ int __init kvmppc_booke_init(void)
 	}
 	flush_icache_range(kvmppc_booke_handlers,
 	                   kvmppc_booke_handlers + max_ivor + kvmppc_handler_len);
-
+#endif /* !BOOKE_HV */
 	return 0;
 }