1 files changed, 1661 insertions, 499 deletions

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 336983da9e7..7a12edbb61e 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -30,6 +30,8 @@
 #include <linux/cpumask.h>
 #include <linux/spinlock.h>
 #include <linux/page-flags.h>
+#include <linux/srcu.h>
+#include <linux/miscdevice.h>
 
 #include <asm/reg.h>
 #include <asm/cputable.h>
@@ -45,48 +47,177 @@
 #include <asm/cputhreads.h>
 #include <asm/page.h>
 #include <asm/hvcall.h>
+#include <asm/switch_to.h>
+#include <asm/smp.h>
 #include <linux/gfp.h>
-#include <linux/sched.h>
 #include <linux/vmalloc.h>
 #include <linux/highmem.h>
+#include <linux/hugetlb.h>
+#include <linux/module.h>
 
-/*
- * For now, limit memory to 64GB and require it to be large pages.
- * This value is chosen because it makes the ram_pginfo array be
- * 64kB in size, which is about as large as we want to be trying
- * to allocate with kmalloc.
- */
-#define MAX_MEM_ORDER		36
-
-#define LARGE_PAGE_ORDER	24	/* 16MB pages */
+#include "book3s.h"
 
 /* #define EXIT_DEBUG */
 /* #define EXIT_DEBUG_SIMPLE */
 /* #define EXIT_DEBUG_INT */
 
+/* Used to indicate that a guest page fault needs to be handled */
+#define RESUME_PAGE_FAULT	(RESUME_GUEST | RESUME_FLAG_ARCH1)
+
+/* Used as a "null" value for timebase values */
+#define TB_NIL	(~(u64)0)
+
 static void kvmppc_end_cede(struct kvm_vcpu *vcpu);
+static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu);
+
+static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
+{
+	int me;
+	int cpu = vcpu->cpu;
+	wait_queue_head_t *wqp;
+
+	wqp = kvm_arch_vcpu_wq(vcpu);
+	if (waitqueue_active(wqp)) {
+		wake_up_interruptible(wqp);
+		++vcpu->stat.halt_wakeup;
+	}
+
+	me = get_cpu();
+
+	/* CPU points to the first thread of the core */
+	if (cpu != me && cpu >= 0 && cpu < nr_cpu_ids) {
+#ifdef CONFIG_PPC_ICP_NATIVE
+		int real_cpu = cpu + vcpu->arch.ptid;
+		if (paca[real_cpu].kvm_hstate.xics_phys)
+			xics_wake_cpu(real_cpu);
+		else
+#endif
+		if (cpu_online(cpu))
+			smp_send_reschedule(cpu);
+	}
+	put_cpu();
+}
+
+/*
+ * We use the vcpu_load/put functions to measure stolen time.
+ * Stolen time is counted as time when either the vcpu is able to
+ * run as part of a virtual core, but the task running the vcore
+ * is preempted or sleeping, or when the vcpu needs something done
+ * in the kernel by the task running the vcpu, but that task is
+ * preempted or sleeping.  Those two things have to be counted
+ * separately, since one of the vcpu tasks will take on the job
+ * of running the core, and the other vcpu tasks in the vcore will
+ * sleep waiting for it to do that, but that sleep shouldn't count
+ * as stolen time.
+ *
+ * Hence we accumulate stolen time when the vcpu can run as part of
+ * a vcore using vc->stolen_tb, and the stolen time when the vcpu
+ * needs its task to do other things in the kernel (for example,
+ * service a page fault) in busy_stolen.  We don't accumulate
+ * stolen time for a vcore when it is inactive, or for a vcpu
+ * when it is in state RUNNING or NOTREADY.  NOTREADY is a bit of
+ * a misnomer; it means that the vcpu task is not executing in
+ * the KVM_VCPU_RUN ioctl, i.e. it is in userspace or elsewhere in
+ * the kernel.  We don't have any way of dividing up that time
+ * between time that the vcpu is genuinely stopped, time that
+ * the task is actively working on behalf of the vcpu, and time
+ * that the task is preempted, so we don't count any of it as
+ * stolen.
+ *
+ * Updates to busy_stolen are protected by arch.tbacct_lock;
+ * updates to vc->stolen_tb are protected by the arch.tbacct_lock
+ * of the vcpu that has taken responsibility for running the vcore
+ * (i.e. vc->runner).  The stolen times are measured in units of
+ * timebase ticks.  (Note that the != TB_NIL checks below are
+ * purely defensive; they should never fail.)
+ */
 
-void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+static void kvmppc_core_vcpu_load_hv(struct kvm_vcpu *vcpu, int cpu)
 {
-	local_paca->kvm_hstate.kvm_vcpu = vcpu;
-	local_paca->kvm_hstate.kvm_vcore = vcpu->arch.vcore;
+	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+	unsigned long flags;
+
+	spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags);
+	if (vc->runner == vcpu && vc->vcore_state != VCORE_INACTIVE &&
+	    vc->preempt_tb != TB_NIL) {
+		vc->stolen_tb += mftb() - vc->preempt_tb;
+		vc->preempt_tb = TB_NIL;
+	}
+	if (vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST &&
+	    vcpu->arch.busy_preempt != TB_NIL) {
+		vcpu->arch.busy_stolen += mftb() - vcpu->arch.busy_preempt;
+		vcpu->arch.busy_preempt = TB_NIL;
+	}
+	spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags);
 }
 
-void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
+static void kvmppc_core_vcpu_put_hv(struct kvm_vcpu *vcpu)
 {
+	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+	unsigned long flags;
+
+	spin_lock_irqsave(&vcpu->arch.tbacct_lock, flags);
+	if (vc->runner == vcpu && vc->vcore_state != VCORE_INACTIVE)
+		vc->preempt_tb = mftb();
+	if (vcpu->arch.state == KVMPPC_VCPU_BUSY_IN_HOST)
+		vcpu->arch.busy_preempt = mftb();
+	spin_unlock_irqrestore(&vcpu->arch.tbacct_lock, flags);
 }
 
-void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
+static void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr)
 {
 	vcpu->arch.shregs.msr = msr;
 	kvmppc_end_cede(vcpu);
 }
 
-void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr)
+void kvmppc_set_pvr_hv(struct kvm_vcpu *vcpu, u32 pvr)
 {
 	vcpu->arch.pvr = pvr;
 }
 
+int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat)
+{
+	unsigned long pcr = 0;
+	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+
+	if (arch_compat) {
+		if (!cpu_has_feature(CPU_FTR_ARCH_206))
+			return -EINVAL;	/* 970 has no compat mode support */
+
+		switch (arch_compat) {
+		case PVR_ARCH_205:
+			/*
+			 * If an arch bit is set in PCR, all the defined
+			 * higher-order arch bits also have to be set.
+			 */
+			pcr = PCR_ARCH_206 | PCR_ARCH_205;
+			break;
+		case PVR_ARCH_206:
+		case PVR_ARCH_206p:
+			pcr = PCR_ARCH_206;
+			break;
+		case PVR_ARCH_207:
+			break;
+		default:
+			return -EINVAL;
+		}
+
+		if (!cpu_has_feature(CPU_FTR_ARCH_207S)) {
+			/* POWER7 can't emulate POWER8 */
+			if (!(pcr & PCR_ARCH_206))
+				return -EINVAL;
+			pcr &= ~PCR_ARCH_206;
+		}
+	}
+
+	spin_lock(&vc->lock);
+	vc->arch_compat = arch_compat;
+	vc->pcr = pcr;
+	spin_unlock(&vc->lock);
+
+	return 0;
+}
+
 void kvmppc_dump_regs(struct kvm_vcpu *vcpu)
 {
 	int r;
@@ -116,7 +247,7 @@ void kvmppc_dump_regs(struct kvm_vcpu *vcpu)
 		pr_err("  ESID = %.16llx VSID = %.16llx\n",
 		       vcpu->arch.slb[r].orige, vcpu->arch.slb[r].origv);
 	pr_err("lpcr = %.16lx sdr1 = %.16lx last_inst = %.8x\n",
-	       vcpu->kvm->arch.lpcr, vcpu->kvm->arch.sdr1,
+	       vcpu->arch.vcore->lpcr, vcpu->kvm->arch.sdr1,
 	       vcpu->arch.last_inst);
 }
 
@@ -138,89 +269,290 @@ struct kvm_vcpu *kvmppc_find_vcpu(struct kvm *kvm, int id)
 
 static void init_vpa(struct kvm_vcpu *vcpu, struct lppaca *vpa)
 {
-	vpa->shared_proc = 1;
+	vpa->__old_status |= LPPACA_OLD_SHARED_PROC;
 	vpa->yield_count = 1;
 }
 
+static int set_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *v,
+		   unsigned long addr, unsigned long len)
+{
+	/* check address is cacheline aligned */
+	if (addr & (L1_CACHE_BYTES - 1))
+		return -EINVAL;
+	spin_lock(&vcpu->arch.vpa_update_lock);
+	if (v->next_gpa != addr || v->len != len) {
+		v->next_gpa = addr;
+		v->len = addr ? len : 0;
+		v->update_pending = 1;
+	}
+	spin_unlock(&vcpu->arch.vpa_update_lock);
+	return 0;
+}
+
+/* Length for a per-processor buffer is passed in at offset 4 in the buffer */
+struct reg_vpa {
+	u32 dummy;
+	union {
+		u16 hword;
+		u32 word;
+	} length;
+};
+
+static int vpa_is_registered(struct kvmppc_vpa *vpap)
+{
+	if (vpap->update_pending)
+		return vpap->next_gpa != 0;
+	return vpap->pinned_addr != NULL;
+}
+
 static unsigned long do_h_register_vpa(struct kvm_vcpu *vcpu,
 				       unsigned long flags,
 				       unsigned long vcpuid, unsigned long vpa)
 {
 	struct kvm *kvm = vcpu->kvm;
-	unsigned long pg_index, ra, len;
-	unsigned long pg_offset;
+	unsigned long len, nb;
 	void *va;
 	struct kvm_vcpu *tvcpu;
+	int err;
+	int subfunc;
+	struct kvmppc_vpa *vpap;
 
 	tvcpu = kvmppc_find_vcpu(kvm, vcpuid);
 	if (!tvcpu)
 		return H_PARAMETER;
 
-	flags >>= 63 - 18;
-	flags &= 7;
-	if (flags == 0 || flags == 4)
-		return H_PARAMETER;
-	if (flags < 4) {
-		if (vpa & 0x7f)
+	subfunc = (flags >> H_VPA_FUNC_SHIFT) & H_VPA_FUNC_MASK;
+	if (subfunc == H_VPA_REG_VPA || subfunc == H_VPA_REG_DTL ||
+	    subfunc == H_VPA_REG_SLB) {
+		/* Registering new area - address must be cache-line aligned */
+		if ((vpa & (L1_CACHE_BYTES - 1)) || !vpa)
 			return H_PARAMETER;
-		/* registering new area; convert logical addr to real */
-		pg_index = vpa >> kvm->arch.ram_porder;
-		pg_offset = vpa & (kvm->arch.ram_psize - 1);
-		if (pg_index >= kvm->arch.ram_npages)
-			return H_PARAMETER;
-		if (kvm->arch.ram_pginfo[pg_index].pfn == 0)
+
+		/* convert logical addr to kernel addr and read length */
+		va = kvmppc_pin_guest_page(kvm, vpa, &nb);
+		if (va == NULL)
 			return H_PARAMETER;
-		ra = kvm->arch.ram_pginfo[pg_index].pfn << PAGE_SHIFT;
-		ra |= pg_offset;
-		va = __va(ra);
-		if (flags <= 1)
-			len = *(unsigned short *)(va + 4);
+		if (subfunc == H_VPA_REG_VPA)
+			len = ((struct reg_vpa *)va)->length.hword;
 		else
-			len = *(unsigned int *)(va + 4);
-		if (pg_offset + len > kvm->arch.ram_psize)
+			len = ((struct reg_vpa *)va)->length.word;
+		kvmppc_unpin_guest_page(kvm, va, vpa, false);
+
+		/* Check length */
+		if (len > nb || len < sizeof(struct reg_vpa))
 			return H_PARAMETER;
-		switch (flags) {
-		case 1:		/* register VPA */
-			if (len < 640)
-				return H_PARAMETER;
-			tvcpu->arch.vpa = va;
-			init_vpa(vcpu, va);
+	} else {
+		vpa = 0;
+		len = 0;
+	}
+
+	err = H_PARAMETER;
+	vpap = NULL;
+	spin_lock(&tvcpu->arch.vpa_update_lock);
+
+	switch (subfunc) {
+	case H_VPA_REG_VPA:		/* register VPA */
+		if (len < sizeof(struct lppaca))
 			break;
-		case 2:		/* register DTL */
-			if (len < 48)
-				return H_PARAMETER;
-			if (!tvcpu->arch.vpa)
-				return H_RESOURCE;
-			len -= len % 48;
-			tvcpu->arch.dtl = va;
-			tvcpu->arch.dtl_end = va + len;
+		vpap = &tvcpu->arch.vpa;
+		err = 0;
+		break;
+
+	case H_VPA_REG_DTL:		/* register DTL */
+		if (len < sizeof(struct dtl_entry))
 			break;
-		case 3:		/* register SLB shadow buffer */
-			if (len < 8)
-				return H_PARAMETER;
-			if (!tvcpu->arch.vpa)
-				return H_RESOURCE;
-			tvcpu->arch.slb_shadow = va;
-			len = (len - 16) / 16;
-			tvcpu->arch.slb_shadow = va;
+		len -= len % sizeof(struct dtl_entry);
+
+		/* Check that they have previously registered a VPA */
+		err = H_RESOURCE;
+		if (!vpa_is_registered(&tvcpu->arch.vpa))
 			break;
-		}
-	} else {
-		switch (flags) {
-		case 5:		/* unregister VPA */
-			if (tvcpu->arch.slb_shadow || tvcpu->arch.dtl)
-				return H_RESOURCE;
-			tvcpu->arch.vpa = NULL;
+
+		vpap = &tvcpu->arch.dtl;
+		err = 0;
+		break;
+
+	case H_VPA_REG_SLB:		/* register SLB shadow buffer */
+		/* Check that they have previously registered a VPA */
+		err = H_RESOURCE;
+		if (!vpa_is_registered(&tvcpu->arch.vpa))
 			break;
-		case 6:		/* unregister DTL */
-			tvcpu->arch.dtl = NULL;
+
+		vpap = &tvcpu->arch.slb_shadow;
+		err = 0;
+		break;
+
+	case H_VPA_DEREG_VPA:		/* deregister VPA */
+		/* Check they don't still have a DTL or SLB buf registered */
+		err = H_RESOURCE;
+		if (vpa_is_registered(&tvcpu->arch.dtl) ||
+		    vpa_is_registered(&tvcpu->arch.slb_shadow))
 			break;
-		case 7:		/* unregister SLB shadow buffer */
-			tvcpu->arch.slb_shadow = NULL;
+
+		vpap = &tvcpu->arch.vpa;
+		err = 0;
+		break;
+
+	case H_VPA_DEREG_DTL:		/* deregister DTL */
+		vpap = &tvcpu->arch.dtl;
+		err = 0;
+		break;
+
+	case H_VPA_DEREG_SLB:		/* deregister SLB shadow buffer */
+		vpap = &tvcpu->arch.slb_shadow;
+		err = 0;
+		break;
+	}
+
+	if (vpap) {
+		vpap->next_gpa = vpa;
+		vpap->len = len;
+		vpap->update_pending = 1;
+	}
+
+	spin_unlock(&tvcpu->arch.vpa_update_lock);
+
+	return err;
+}
+
+static void kvmppc_update_vpa(struct kvm_vcpu *vcpu, struct kvmppc_vpa *vpap)
+{
+	struct kvm *kvm = vcpu->kvm;
+	void *va;
+	unsigned long nb;
+	unsigned long gpa;
+
+	/*
+	 * We need to pin the page pointed to by vpap->next_gpa,
+	 * but we can't call kvmppc_pin_guest_page under the lock
+	 * as it does get_user_pages() and down_read().  So we
+	 * have to drop the lock, pin the page, then get the lock
+	 * again and check that a new area didn't get registered
+	 * in the meantime.
+	 */
+	for (;;) {
+		gpa = vpap->next_gpa;
+		spin_unlock(&vcpu->arch.vpa_update_lock);
+		va = NULL;
+		nb = 0;
+		if (gpa)
+			va = kvmppc_pin_guest_page(kvm, gpa, &nb);
+		spin_lock(&vcpu->arch.vpa_update_lock);
+		if (gpa == vpap->next_gpa)
 			break;
-		}
+		/* sigh... unpin that one and try again */
+		if (va)
+			kvmppc_unpin_guest_page(kvm, va, gpa, false);
+	}
+
+	vpap->update_pending = 0;
+	if (va && nb < vpap->len) {
+		/*
+		 * If it's now too short, it must be that userspace
+		 * has changed the mappings underlying guest memory,
+		 * so unregister the region.
+		 */
+		kvmppc_unpin_guest_page(kvm, va, gpa, false);
+		va = NULL;
+	}
+	if (vpap->pinned_addr)
+		kvmppc_unpin_guest_page(kvm, vpap->pinned_addr, vpap->gpa,
+					vpap->dirty);
+	vpap->gpa = gpa;
+	vpap->pinned_addr = va;
+	vpap->dirty = false;
+	if (va)
+		vpap->pinned_end = va + vpap->len;
+}
+
+static void kvmppc_update_vpas(struct kvm_vcpu *vcpu)
+{
+	if (!(vcpu->arch.vpa.update_pending ||
+	      vcpu->arch.slb_shadow.update_pending ||
+	      vcpu->arch.dtl.update_pending))
+		return;
+
+	spin_lock(&vcpu->arch.vpa_update_lock);
+	if (vcpu->arch.vpa.update_pending) {
+		kvmppc_update_vpa(vcpu, &vcpu->arch.vpa);
+		if (vcpu->arch.vpa.pinned_addr)
+			init_vpa(vcpu, vcpu->arch.vpa.pinned_addr);
+	}
+	if (vcpu->arch.dtl.update_pending) {
+		kvmppc_update_vpa(vcpu, &vcpu->arch.dtl);
+		vcpu->arch.dtl_ptr = vcpu->arch.dtl.pinned_addr;
+		vcpu->arch.dtl_index = 0;
+	}
+	if (vcpu->arch.slb_shadow.update_pending)
+		kvmppc_update_vpa(vcpu, &vcpu->arch.slb_shadow);
+	spin_unlock(&vcpu->arch.vpa_update_lock);
+}
+
+/*
+ * Return the accumulated stolen time for the vcore up until `now'.
+ * The caller should hold the vcore lock.
+ */
+static u64 vcore_stolen_time(struct kvmppc_vcore *vc, u64 now)
+{
+	u64 p;
+
+	/*
+	 * If we are the task running the vcore, then since we hold
+	 * the vcore lock, we can't be preempted, so stolen_tb/preempt_tb
+	 * can't be updated, so we don't need the tbacct_lock.
+	 * If the vcore is inactive, it can't become active (since we
+	 * hold the vcore lock), so the vcpu load/put functions won't
+	 * update stolen_tb/preempt_tb, and we don't need tbacct_lock.
+	 */
+	if (vc->vcore_state != VCORE_INACTIVE &&
+	    vc->runner->arch.run_task != current) {
+		spin_lock_irq(&vc->runner->arch.tbacct_lock);
+		p = vc->stolen_tb;
+		if (vc->preempt_tb != TB_NIL)
+			p += now - vc->preempt_tb;
+		spin_unlock_irq(&vc->runner->arch.tbacct_lock);
+	} else {
+		p = vc->stolen_tb;
 	}
-	return H_SUCCESS;
+	return p;
+}
+
+static void kvmppc_create_dtl_entry(struct kvm_vcpu *vcpu,
+				    struct kvmppc_vcore *vc)
+{
+	struct dtl_entry *dt;
+	struct lppaca *vpa;
+	unsigned long stolen;
+	unsigned long core_stolen;
+	u64 now;
+
+	dt = vcpu->arch.dtl_ptr;
+	vpa = vcpu->arch.vpa.pinned_addr;
+	now = mftb();
+	core_stolen = vcore_stolen_time(vc, now);
+	stolen = core_stolen - vcpu->arch.stolen_logged;
+	vcpu->arch.stolen_logged = core_stolen;
+	spin_lock_irq(&vcpu->arch.tbacct_lock);
+	stolen += vcpu->arch.busy_stolen;
+	vcpu->arch.busy_stolen = 0;
+	spin_unlock_irq(&vcpu->arch.tbacct_lock);
+	if (!dt || !vpa)
+		return;
+	memset(dt, 0, sizeof(struct dtl_entry));
+	dt->dispatch_reason = 7;
+	dt->processor_id = vc->pcpu + vcpu->arch.ptid;
+	dt->timebase = now + vc->tb_offset;
+	dt->enqueue_to_dispatch_time = stolen;
+	dt->srr0 = kvmppc_get_pc(vcpu);
+	dt->srr1 = vcpu->arch.shregs.msr;
+	++dt;
+	if (dt == vcpu->arch.dtl.pinned_end)
+		dt = vcpu->arch.dtl.pinned_addr;
+	vcpu->arch.dtl_ptr = dt;
+	/* order writing *dt vs. writing vpa->dtl_idx */
+	smp_wmb();
+	vpa->dtl_idx = ++vcpu->arch.dtl_index;
+	vcpu->arch.dtl.dirty = true;
 }
 
 int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
@@ -228,8 +560,17 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 	unsigned long req = kvmppc_get_gpr(vcpu, 3);
 	unsigned long target, ret = H_SUCCESS;
 	struct kvm_vcpu *tvcpu;
+	int idx, rc;
 
 	switch (req) {
+	case H_ENTER:
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
+		ret = kvmppc_virtmode_h_enter(vcpu, kvmppc_get_gpr(vcpu, 4),
+					      kvmppc_get_gpr(vcpu, 5),
+					      kvmppc_get_gpr(vcpu, 6),
+					      kvmppc_get_gpr(vcpu, 7));
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
+		break;
 	case H_CEDE:
 		break;
 	case H_PROD:
@@ -249,12 +590,47 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 		}
 		break;
 	case H_CONFER:
+		target = kvmppc_get_gpr(vcpu, 4);
+		if (target == -1)
+			break;
+		tvcpu = kvmppc_find_vcpu(vcpu->kvm, target);
+		if (!tvcpu) {
+			ret = H_PARAMETER;
+			break;
+		}
+		kvm_vcpu_yield_to(tvcpu);
 		break;
 	case H_REGISTER_VPA:
 		ret = do_h_register_vpa(vcpu, kvmppc_get_gpr(vcpu, 4),
 					kvmppc_get_gpr(vcpu, 5),
 					kvmppc_get_gpr(vcpu, 6));
 		break;
+	case H_RTAS:
+		if (list_empty(&vcpu->kvm->arch.rtas_tokens))
+			return RESUME_HOST;
+
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
+		rc = kvmppc_rtas_hcall(vcpu);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
+
+		if (rc == -ENOENT)
+			return RESUME_HOST;
+		else if (rc == 0)
+			break;
+
+		/* Send the error out to userspace via KVM_RUN */
+		return rc;
+
+	case H_XIRR:
+	case H_CPPR:
+	case H_EOI:
+	case H_IPI:
+	case H_IPOLL:
+	case H_XIRR_X:
+		if (kvmppc_xics_enabled(vcpu)) {
+			ret = kvmppc_xics_hcall(vcpu, req);
+			break;
+		} /* fallthrough */
 	default:
 		return RESUME_HOST;
 	}
@@ -263,8 +639,8 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 	return RESUME_GUEST;
 }
 
-static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
-			      struct task_struct *tsk)
+static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
+				 struct task_struct *tsk)
 {
 	int r = RESUME_HOST;
 
@@ -279,12 +655,24 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		r = RESUME_GUEST;
 		break;
 	case BOOK3S_INTERRUPT_EXTERNAL:
+	case BOOK3S_INTERRUPT_H_DOORBELL:
 		vcpu->stat.ext_intr_exits++;
 		r = RESUME_GUEST;
 		break;
 	case BOOK3S_INTERRUPT_PERFMON:
 		r = RESUME_GUEST;
 		break;
+	case BOOK3S_INTERRUPT_MACHINE_CHECK:
+		/*
+		 * Deliver a machine check interrupt to the guest.
+		 * We have to do this, even if the host has handled the
+		 * machine check, because machine checks use SRR0/1 and
+		 * the interrupt might have trashed guest state in them.
+		 */
+		kvmppc_book3s_queue_irqprio(vcpu,
+					    BOOK3S_INTERRUPT_MACHINE_CHECK);
+		r = RESUME_GUEST;
+		break;
 	case BOOK3S_INTERRUPT_PROGRAM:
 	{
 		ulong flags;
@@ -304,12 +692,10 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		/* hcall - punt to userspace */
 		int i;
 
-		if (vcpu->arch.shregs.msr & MSR_PR) {
-			/* sc 1 from userspace - reflect to guest syscall */
-			kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_SYSCALL);
-			r = RESUME_GUEST;
-			break;
-		}
+		/* hypercall with MSR_PR has already been handled in rmode,
+		 * and never reaches here.
+		 */
+
 		run->papr_hcall.nr = kvmppc_get_gpr(vcpu, 3);
 		for (i = 0; i < 9; ++i)
 			run->papr_hcall.args[i] = kvmppc_get_gpr(vcpu, 4 + i);
@@ -319,20 +705,19 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		break;
 	}
 	/*
-	 * We get these next two if the guest does a bad real-mode access,
-	 * as we have enabled VRMA (virtualized real mode area) mode in the
-	 * LPCR.  We just generate an appropriate DSI/ISI to the guest.
+	 * We get these next two if the guest accesses a page which it thinks
+	 * it has mapped but which is not actually present, either because
+	 * it is for an emulated I/O device or because the corresonding
+	 * host page has been paged out.  Any other HDSI/HISI interrupts
+	 * have been handled already.
 	 */
 	case BOOK3S_INTERRUPT_H_DATA_STORAGE:
-		vcpu->arch.shregs.dsisr = vcpu->arch.fault_dsisr;
-		vcpu->arch.shregs.dar = vcpu->arch.fault_dar;
-		kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_DATA_STORAGE, 0);
-		r = RESUME_GUEST;
+		r = RESUME_PAGE_FAULT;
 		break;
 	case BOOK3S_INTERRUPT_H_INST_STORAGE:
-		kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_INST_STORAGE,
-					0x08000000);
-		r = RESUME_GUEST;
+		vcpu->arch.fault_dar = kvmppc_get_pc(vcpu);
+		vcpu->arch.fault_dsisr = 0;
+		r = RESUME_PAGE_FAULT;
 		break;
 	/*
 	 * This occurs if the guest executes an illegal instruction.
@@ -340,7 +725,16 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	 * we don't emulate any guest instructions at this stage.
 	 */
 	case BOOK3S_INTERRUPT_H_EMUL_ASSIST:
-		kvmppc_core_queue_program(vcpu, 0x80000);
+		kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
+		r = RESUME_GUEST;
+		break;
+	/*
+	 * This occurs if the guest (kernel or userspace), does something that
+	 * is prohibited by HFSCR.  We just generate a program interrupt to
+	 * the guest.
+	 */
+	case BOOK3S_INTERRUPT_H_FAC_UNAVAIL:
+		kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
 		r = RESUME_GUEST;
 		break;
 	default:
@@ -348,22 +742,21 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		printk(KERN_EMERG "trap=0x%x | pc=0x%lx | msr=0x%llx\n",
 			vcpu->arch.trap, kvmppc_get_pc(vcpu),
 			vcpu->arch.shregs.msr);
+		run->hw.hardware_exit_reason = vcpu->arch.trap;
 		r = RESUME_HOST;
-		BUG();
 		break;
 	}
 
 	return r;
 }
 
-int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
-                                  struct kvm_sregs *sregs)
+static int kvm_arch_vcpu_ioctl_get_sregs_hv(struct kvm_vcpu *vcpu,
+					    struct kvm_sregs *sregs)
 {
 	int i;
 
-	sregs->pvr = vcpu->arch.pvr;
-
 	memset(sregs, 0, sizeof(struct kvm_sregs));
+	sregs->pvr = vcpu->arch.pvr;
 	for (i = 0; i < vcpu->arch.slb_max; i++) {
 		sregs->u.s.ppc64.slb[i].slbe = vcpu->arch.slb[i].orige;
 		sregs->u.s.ppc64.slb[i].slbv = vcpu->arch.slb[i].origv;
@@ -372,12 +765,12 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
-                                  struct kvm_sregs *sregs)
+static int kvm_arch_vcpu_ioctl_set_sregs_hv(struct kvm_vcpu *vcpu,
+					    struct kvm_sregs *sregs)
 {
 	int i, j;
 
-	kvmppc_set_pvr(vcpu, sregs->pvr);
+	kvmppc_set_pvr_hv(vcpu, sregs->pvr);
 
 	j = 0;
 	for (i = 0; i < vcpu->arch.slb_nr; i++) {
@@ -392,26 +785,463 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-int kvmppc_core_check_processor_compat(void)
+static void kvmppc_set_lpcr(struct kvm_vcpu *vcpu, u64 new_lpcr)
 {
-	if (cpu_has_feature(CPU_FTR_HVMODE))
-		return 0;
-	return -EIO;
+	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+	u64 mask;
+
+	spin_lock(&vc->lock);
+	/*
+	 * If ILE (interrupt little-endian) has changed, update the
+	 * MSR_LE bit in the intr_msr for each vcpu in this vcore.
+	 */
+	if ((new_lpcr & LPCR_ILE) != (vc->lpcr & LPCR_ILE)) {
+		struct kvm *kvm = vcpu->kvm;
+		struct kvm_vcpu *vcpu;
+		int i;
+
+		mutex_lock(&kvm->lock);
+		kvm_for_each_vcpu(i, vcpu, kvm) {
+			if (vcpu->arch.vcore != vc)
+				continue;
+			if (new_lpcr & LPCR_ILE)
+				vcpu->arch.intr_msr |= MSR_LE;
+			else
+				vcpu->arch.intr_msr &= ~MSR_LE;
+		}
+		mutex_unlock(&kvm->lock);
+	}
+
+	/*
+	 * Userspace can only modify DPFD (default prefetch depth),
+	 * ILE (interrupt little-endian) and TC (translation control).
+	 * On POWER8 userspace can also modify AIL (alt. interrupt loc.)
+	 */
+	mask = LPCR_DPFD | LPCR_ILE | LPCR_TC;
+	if (cpu_has_feature(CPU_FTR_ARCH_207S))
+		mask |= LPCR_AIL;
+	vc->lpcr = (vc->lpcr & ~mask) | (new_lpcr & mask);
+	spin_unlock(&vc->lock);
+}
+
+static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
+				 union kvmppc_one_reg *val)
+{
+	int r = 0;
+	long int i;
+
+	switch (id) {
+	case KVM_REG_PPC_HIOR:
+		*val = get_reg_val(id, 0);
+		break;
+	case KVM_REG_PPC_DABR:
+		*val = get_reg_val(id, vcpu->arch.dabr);
+		break;
+	case KVM_REG_PPC_DABRX:
+		*val = get_reg_val(id, vcpu->arch.dabrx);
+		break;
+	case KVM_REG_PPC_DSCR:
+		*val = get_reg_val(id, vcpu->arch.dscr);
+		break;
+	case KVM_REG_PPC_PURR:
+		*val = get_reg_val(id, vcpu->arch.purr);
+		break;
+	case KVM_REG_PPC_SPURR:
+		*val = get_reg_val(id, vcpu->arch.spurr);
+		break;
+	case KVM_REG_PPC_AMR:
+		*val = get_reg_val(id, vcpu->arch.amr);
+		break;
+	case KVM_REG_PPC_UAMOR:
+		*val = get_reg_val(id, vcpu->arch.uamor);
+		break;
+	case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCRS:
+		i = id - KVM_REG_PPC_MMCR0;
+		*val = get_reg_val(id, vcpu->arch.mmcr[i]);
+		break;
+	case KVM_REG_PPC_PMC1 ... KVM_REG_PPC_PMC8:
+		i = id - KVM_REG_PPC_PMC1;
+		*val = get_reg_val(id, vcpu->arch.pmc[i]);
+		break;
+	case KVM_REG_PPC_SPMC1 ... KVM_REG_PPC_SPMC2:
+		i = id - KVM_REG_PPC_SPMC1;
+		*val = get_reg_val(id, vcpu->arch.spmc[i]);
+		break;
+	case KVM_REG_PPC_SIAR:
+		*val = get_reg_val(id, vcpu->arch.siar);
+		break;
+	case KVM_REG_PPC_SDAR:
+		*val = get_reg_val(id, vcpu->arch.sdar);
+		break;
+	case KVM_REG_PPC_SIER:
+		*val = get_reg_val(id, vcpu->arch.sier);
+		break;
+	case KVM_REG_PPC_IAMR:
+		*val = get_reg_val(id, vcpu->arch.iamr);
+		break;
+	case KVM_REG_PPC_PSPB:
+		*val = get_reg_val(id, vcpu->arch.pspb);
+		break;
+	case KVM_REG_PPC_DPDES:
+		*val = get_reg_val(id, vcpu->arch.vcore->dpdes);
+		break;
+	case KVM_REG_PPC_DAWR:
+		*val = get_reg_val(id, vcpu->arch.dawr);
+		break;
+	case KVM_REG_PPC_DAWRX:
+		*val = get_reg_val(id, vcpu->arch.dawrx);
+		break;
+	case KVM_REG_PPC_CIABR:
+		*val = get_reg_val(id, vcpu->arch.ciabr);
+		break;
+	case KVM_REG_PPC_IC:
+		*val = get_reg_val(id, vcpu->arch.ic);
+		break;
+	case KVM_REG_PPC_VTB:
+		*val = get_reg_val(id, vcpu->arch.vtb);
+		break;
+	case KVM_REG_PPC_CSIGR:
+		*val = get_reg_val(id, vcpu->arch.csigr);
+		break;
+	case KVM_REG_PPC_TACR:
+		*val = get_reg_val(id, vcpu->arch.tacr);
+		break;
+	case KVM_REG_PPC_TCSCR:
+		*val = get_reg_val(id, vcpu->arch.tcscr);
+		break;
+	case KVM_REG_PPC_PID:
+		*val = get_reg_val(id, vcpu->arch.pid);
+		break;
+	case KVM_REG_PPC_ACOP:
+		*val = get_reg_val(id, vcpu->arch.acop);
+		break;
+	case KVM_REG_PPC_WORT:
+		*val = get_reg_val(id, vcpu->arch.wort);
+		break;
+	case KVM_REG_PPC_VPA_ADDR:
+		spin_lock(&vcpu->arch.vpa_update_lock);
+		*val = get_reg_val(id, vcpu->arch.vpa.next_gpa);
+		spin_unlock(&vcpu->arch.vpa_update_lock);
+		break;
+	case KVM_REG_PPC_VPA_SLB:
+		spin_lock(&vcpu->arch.vpa_update_lock);
+		val->vpaval.addr = vcpu->arch.slb_shadow.next_gpa;
+		val->vpaval.length = vcpu->arch.slb_shadow.len;
+		spin_unlock(&vcpu->arch.vpa_update_lock);
+		break;
+	case KVM_REG_PPC_VPA_DTL:
+		spin_lock(&vcpu->arch.vpa_update_lock);
+		val->vpaval.addr = vcpu->arch.dtl.next_gpa;
+		val->vpaval.length = vcpu->arch.dtl.len;
+		spin_unlock(&vcpu->arch.vpa_update_lock);
+		break;
+	case KVM_REG_PPC_TB_OFFSET:
+		*val = get_reg_val(id, vcpu->arch.vcore->tb_offset);
+		break;
+	case KVM_REG_PPC_LPCR:
+		*val = get_reg_val(id, vcpu->arch.vcore->lpcr);
+		break;
+	case KVM_REG_PPC_PPR:
+		*val = get_reg_val(id, vcpu->arch.ppr);
+		break;
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	case KVM_REG_PPC_TFHAR:
+		*val = get_reg_val(id, vcpu->arch.tfhar);
+		break;
+	case KVM_REG_PPC_TFIAR:
+		*val = get_reg_val(id, vcpu->arch.tfiar);
+		break;
+	case KVM_REG_PPC_TEXASR:
+		*val = get_reg_val(id, vcpu->arch.texasr);
+		break;
+	case KVM_REG_PPC_TM_GPR0 ... KVM_REG_PPC_TM_GPR31:
+		i = id - KVM_REG_PPC_TM_GPR0;
+		*val = get_reg_val(id, vcpu->arch.gpr_tm[i]);
+		break;
+	case KVM_REG_PPC_TM_VSR0 ... KVM_REG_PPC_TM_VSR63:
+	{
+		int j;
+		i = id - KVM_REG_PPC_TM_VSR0;
+		if (i < 32)
+			for (j = 0; j < TS_FPRWIDTH; j++)
+				val->vsxval[j] = vcpu->arch.fp_tm.fpr[i][j];
+		else {
+			if (cpu_has_feature(CPU_FTR_ALTIVEC))
+				val->vval = vcpu->arch.vr_tm.vr[i-32];
+			else
+				r = -ENXIO;
+		}
+		break;
+	}
+	case KVM_REG_PPC_TM_CR:
+		*val = get_reg_val(id, vcpu->arch.cr_tm);
+		break;
+	case KVM_REG_PPC_TM_LR:
+		*val = get_reg_val(id, vcpu->arch.lr_tm);
+		break;
+	case KVM_REG_PPC_TM_CTR:
+		*val = get_reg_val(id, vcpu->arch.ctr_tm);
+		break;
+	case KVM_REG_PPC_TM_FPSCR:
+		*val = get_reg_val(id, vcpu->arch.fp_tm.fpscr);
+		break;
+	case KVM_REG_PPC_TM_AMR:
+		*val = get_reg_val(id, vcpu->arch.amr_tm);
+		break;
+	case KVM_REG_PPC_TM_PPR:
+		*val = get_reg_val(id, vcpu->arch.ppr_tm);
+		break;
+	case KVM_REG_PPC_TM_VRSAVE:
+		*val = get_reg_val(id, vcpu->arch.vrsave_tm);
+		break;
+	case KVM_REG_PPC_TM_VSCR:
+		if (cpu_has_feature(CPU_FTR_ALTIVEC))
+			*val = get_reg_val(id, vcpu->arch.vr_tm.vscr.u[3]);
+		else
+			r = -ENXIO;
+		break;
+	case KVM_REG_PPC_TM_DSCR:
+		*val = get_reg_val(id, vcpu->arch.dscr_tm);
+		break;
+	case KVM_REG_PPC_TM_TAR:
+		*val = get_reg_val(id, vcpu->arch.tar_tm);
+		break;
+#endif
+	case KVM_REG_PPC_ARCH_COMPAT:
+		*val = get_reg_val(id, vcpu->arch.vcore->arch_compat);
+		break;
+	default:
+		r = -EINVAL;
+		break;
+	}
+
+	return r;
 }
 
-struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
+static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
+				 union kvmppc_one_reg *val)
+{
+	int r = 0;
+	long int i;
+	unsigned long addr, len;
+
+	switch (id) {
+	case KVM_REG_PPC_HIOR:
+		/* Only allow this to be set to zero */
+		if (set_reg_val(id, *val))
+			r = -EINVAL;
+		break;
+	case KVM_REG_PPC_DABR:
+		vcpu->arch.dabr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_DABRX:
+		vcpu->arch.dabrx = set_reg_val(id, *val) & ~DABRX_HYP;
+		break;
+	case KVM_REG_PPC_DSCR:
+		vcpu->arch.dscr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_PURR:
+		vcpu->arch.purr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_SPURR:
+		vcpu->arch.spurr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_AMR:
+		vcpu->arch.amr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_UAMOR:
+		vcpu->arch.uamor = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_MMCR0 ... KVM_REG_PPC_MMCRS:
+		i = id - KVM_REG_PPC_MMCR0;
+		vcpu->arch.mmcr[i] = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_PMC1 ... KVM_REG_PPC_PMC8:
+		i = id - KVM_REG_PPC_PMC1;
+		vcpu->arch.pmc[i] = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_SPMC1 ... KVM_REG_PPC_SPMC2:
+		i = id - KVM_REG_PPC_SPMC1;
+		vcpu->arch.spmc[i] = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_SIAR:
+		vcpu->arch.siar = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_SDAR:
+		vcpu->arch.sdar = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_SIER:
+		vcpu->arch.sier = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_IAMR:
+		vcpu->arch.iamr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_PSPB:
+		vcpu->arch.pspb = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_DPDES:
+		vcpu->arch.vcore->dpdes = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_DAWR:
+		vcpu->arch.dawr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_DAWRX:
+		vcpu->arch.dawrx = set_reg_val(id, *val) & ~DAWRX_HYP;
+		break;
+	case KVM_REG_PPC_CIABR:
+		vcpu->arch.ciabr = set_reg_val(id, *val);
+		/* Don't allow setting breakpoints in hypervisor code */
+		if ((vcpu->arch.ciabr & CIABR_PRIV) == CIABR_PRIV_HYPER)
+			vcpu->arch.ciabr &= ~CIABR_PRIV;	/* disable */
+		break;
+	case KVM_REG_PPC_IC:
+		vcpu->arch.ic = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_VTB:
+		vcpu->arch.vtb = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_CSIGR:
+		vcpu->arch.csigr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TACR:
+		vcpu->arch.tacr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TCSCR:
+		vcpu->arch.tcscr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_PID:
+		vcpu->arch.pid = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_ACOP:
+		vcpu->arch.acop = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_WORT:
+		vcpu->arch.wort = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_VPA_ADDR:
+		addr = set_reg_val(id, *val);
+		r = -EINVAL;
+		if (!addr && (vcpu->arch.slb_shadow.next_gpa ||
+			      vcpu->arch.dtl.next_gpa))
+			break;
+		r = set_vpa(vcpu, &vcpu->arch.vpa, addr, sizeof(struct lppaca));
+		break;
+	case KVM_REG_PPC_VPA_SLB:
+		addr = val->vpaval.addr;
+		len = val->vpaval.length;
+		r = -EINVAL;
+		if (addr && !vcpu->arch.vpa.next_gpa)
+			break;
+		r = set_vpa(vcpu, &vcpu->arch.slb_shadow, addr, len);
+		break;
+	case KVM_REG_PPC_VPA_DTL:
+		addr = val->vpaval.addr;
+		len = val->vpaval.length;
+		r = -EINVAL;
+		if (addr && (len < sizeof(struct dtl_entry) ||
+			     !vcpu->arch.vpa.next_gpa))
+			break;
+		len -= len % sizeof(struct dtl_entry);
+		r = set_vpa(vcpu, &vcpu->arch.dtl, addr, len);
+		break;
+	case KVM_REG_PPC_TB_OFFSET:
+		/* round up to multiple of 2^24 */
+		vcpu->arch.vcore->tb_offset =
+			ALIGN(set_reg_val(id, *val), 1UL << 24);
+		break;
+	case KVM_REG_PPC_LPCR:
+		kvmppc_set_lpcr(vcpu, set_reg_val(id, *val));
+		break;
+	case KVM_REG_PPC_PPR:
+		vcpu->arch.ppr = set_reg_val(id, *val);
+		break;
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	case KVM_REG_PPC_TFHAR:
+		vcpu->arch.tfhar = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TFIAR:
+		vcpu->arch.tfiar = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TEXASR:
+		vcpu->arch.texasr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TM_GPR0 ... KVM_REG_PPC_TM_GPR31:
+		i = id - KVM_REG_PPC_TM_GPR0;
+		vcpu->arch.gpr_tm[i] = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TM_VSR0 ... KVM_REG_PPC_TM_VSR63:
+	{
+		int j;
+		i = id - KVM_REG_PPC_TM_VSR0;
+		if (i < 32)
+			for (j = 0; j < TS_FPRWIDTH; j++)
+				vcpu->arch.fp_tm.fpr[i][j] = val->vsxval[j];
+		else
+			if (cpu_has_feature(CPU_FTR_ALTIVEC))
+				vcpu->arch.vr_tm.vr[i-32] = val->vval;
+			else
+				r = -ENXIO;
+		break;
+	}
+	case KVM_REG_PPC_TM_CR:
+		vcpu->arch.cr_tm = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TM_LR:
+		vcpu->arch.lr_tm = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TM_CTR:
+		vcpu->arch.ctr_tm = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TM_FPSCR:
+		vcpu->arch.fp_tm.fpscr = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TM_AMR:
+		vcpu->arch.amr_tm = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TM_PPR:
+		vcpu->arch.ppr_tm = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TM_VRSAVE:
+		vcpu->arch.vrsave_tm = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TM_VSCR:
+		if (cpu_has_feature(CPU_FTR_ALTIVEC))
+			vcpu->arch.vr.vscr.u[3] = set_reg_val(id, *val);
+		else
+			r = - ENXIO;
+		break;
+	case KVM_REG_PPC_TM_DSCR:
+		vcpu->arch.dscr_tm = set_reg_val(id, *val);
+		break;
+	case KVM_REG_PPC_TM_TAR:
+		vcpu->arch.tar_tm = set_reg_val(id, *val);
+		break;
+#endif
+	case KVM_REG_PPC_ARCH_COMPAT:
+		r = kvmppc_set_arch_compat(vcpu, set_reg_val(id, *val));
+		break;
+	default:
+		r = -EINVAL;
+		break;
+	}
+
+	return r;
+}
+
+static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
+						   unsigned int id)
 {
 	struct kvm_vcpu *vcpu;
 	int err = -EINVAL;
 	int core;
 	struct kvmppc_vcore *vcore;
 
-	core = id / threads_per_core;
+	core = id / threads_per_subcore;
 	if (core >= KVM_MAX_VCORES)
 		goto out;
 
 	err = -ENOMEM;
-	vcpu = kzalloc(sizeof(struct kvm_vcpu), GFP_KERNEL);
+	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
 	if (!vcpu)
 		goto out;
 
@@ -420,19 +1250,29 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 		goto free_vcpu;
 
 	vcpu->arch.shared = &vcpu->arch.shregs;
-	vcpu->arch.last_cpu = -1;
+#ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
+	/*
+	 * The shared struct is never shared on HV,
+	 * so we can always use host endianness
+	 */
+#ifdef __BIG_ENDIAN__
+	vcpu->arch.shared_big_endian = true;
+#else
+	vcpu->arch.shared_big_endian = false;
+#endif
+#endif
 	vcpu->arch.mmcr[0] = MMCR0_FC;
 	vcpu->arch.ctrl = CTRL_RUNLATCH;
 	/* default to host PVR, since we can't spoof it */
-	vcpu->arch.pvr = mfspr(SPRN_PVR);
-	kvmppc_set_pvr(vcpu, vcpu->arch.pvr);
+	kvmppc_set_pvr_hv(vcpu, mfspr(SPRN_PVR));
+	spin_lock_init(&vcpu->arch.vpa_update_lock);
+	spin_lock_init(&vcpu->arch.tbacct_lock);
+	vcpu->arch.busy_preempt = TB_NIL;
+	vcpu->arch.intr_msr = MSR_SF | MSR_ME;
 
 	kvmppc_mmu_book3s_hv_init(vcpu);
 
-	/*
-	 * We consider the vcpu stopped until we see the first run ioctl for it.
-	 */
-	vcpu->arch.state = KVMPPC_VCPU_STOPPED;
+	vcpu->arch.state = KVMPPC_VCPU_NOTREADY;
 
 	init_waitqueue_head(&vcpu->arch.cpu_run);
 
@@ -444,8 +1284,13 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 			INIT_LIST_HEAD(&vcore->runnable_threads);
 			spin_lock_init(&vcore->lock);
 			init_waitqueue_head(&vcore->wq);
+			vcore->preempt_tb = TB_NIL;
+			vcore->lpcr = kvm->arch.lpcr;
+			vcore->first_vcpuid = core * threads_per_subcore;
+			vcore->kvm = kvm;
 		}
 		kvm->arch.vcores[core] = vcore;
+		kvm->arch.online_vcores++;
 	}
 	mutex_unlock(&kvm->lock);
 
@@ -456,6 +1301,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 	++vcore->num_threads;
 	spin_unlock(&vcore->lock);
 	vcpu->arch.vcore = vcore;
+	vcpu->arch.ptid = vcpu->vcpu_id - vcore->first_vcpuid;
 
 	vcpu->arch.cpu_type = KVM_CPU_3S_64;
 	kvmppc_sanity_check(vcpu);
@@ -463,15 +1309,33 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 	return vcpu;
 
 free_vcpu:
-	kfree(vcpu);
+	kmem_cache_free(kvm_vcpu_cache, vcpu);
 out:
 	return ERR_PTR(err);
 }
 
-void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
+static void unpin_vpa(struct kvm *kvm, struct kvmppc_vpa *vpa)
 {
+	if (vpa->pinned_addr)
+		kvmppc_unpin_guest_page(kvm, vpa->pinned_addr, vpa->gpa,
+					vpa->dirty);
+}
+
+static void kvmppc_core_vcpu_free_hv(struct kvm_vcpu *vcpu)
+{
+	spin_lock(&vcpu->arch.vpa_update_lock);
+	unpin_vpa(vcpu->kvm, &vcpu->arch.dtl);
+	unpin_vpa(vcpu->kvm, &vcpu->arch.slb_shadow);
+	unpin_vpa(vcpu->kvm, &vcpu->arch.vpa);
+	spin_unlock(&vcpu->arch.vpa_update_lock);
 	kvm_vcpu_uninit(vcpu);
-	kfree(vcpu);
+	kmem_cache_free(kvm_vcpu_cache, vcpu);
+}
+
+static int kvmppc_core_check_requests_hv(struct kvm_vcpu *vcpu)
+{
+	/* Indicate we want to get back into the guest */
+	return 1;
 }
 
 static void kvmppc_set_timer(struct kvm_vcpu *vcpu)
@@ -482,7 +1346,7 @@ static void kvmppc_set_timer(struct kvm_vcpu *vcpu)
 	if (now > vcpu->arch.dec_expires) {
 		/* decrementer has already gone negative */
 		kvmppc_core_queue_dec(vcpu);
-		kvmppc_core_deliver_interrupts(vcpu);
+		kvmppc_core_prepare_to_enter(vcpu);
 		return;
 	}
 	dec_nsec = (vcpu->arch.dec_expires - now) * NSEC_PER_SEC
@@ -501,26 +1365,66 @@ static void kvmppc_end_cede(struct kvm_vcpu *vcpu)
 	}
 }
 
-extern int __kvmppc_vcore_entry(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu);
-extern void xics_wake_cpu(int cpu);
+extern void __kvmppc_vcore_entry(void);
 
 static void kvmppc_remove_runnable(struct kvmppc_vcore *vc,
 				   struct kvm_vcpu *vcpu)
 {
-	struct kvm_vcpu *v;
+	u64 now;
 
 	if (vcpu->arch.state != KVMPPC_VCPU_RUNNABLE)
 		return;
+	spin_lock_irq(&vcpu->arch.tbacct_lock);
+	now = mftb();
+	vcpu->arch.busy_stolen += vcore_stolen_time(vc, now) -
+		vcpu->arch.stolen_logged;
+	vcpu->arch.busy_preempt = now;
 	vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
+	spin_unlock_irq(&vcpu->arch.tbacct_lock);
 	--vc->n_runnable;
-	++vc->n_busy;
-	/* decrement the physical thread id of each following vcpu */
-	v = vcpu;
-	list_for_each_entry_continue(v, &vc->runnable_threads, arch.run_list)
-		--v->arch.ptid;
 	list_del(&vcpu->arch.run_list);
 }
 
+static int kvmppc_grab_hwthread(int cpu)
+{
+	struct paca_struct *tpaca;
+	long timeout = 1000;
+
+	tpaca = &paca[cpu];
+
+	/* Ensure the thread won't go into the kernel if it wakes */
+	tpaca->kvm_hstate.hwthread_req = 1;
+	tpaca->kvm_hstate.kvm_vcpu = NULL;
+
+	/*
+	 * If the thread is already executing in the kernel (e.g. handling
+	 * a stray interrupt), wait for it to get back to nap mode.
+	 * The smp_mb() is to ensure that our setting of hwthread_req
+	 * is visible before we look at hwthread_state, so if this
+	 * races with the code at system_reset_pSeries and the thread
+	 * misses our setting of hwthread_req, we are sure to see its
+	 * setting of hwthread_state, and vice versa.
+	 */
+	smp_mb();
+	while (tpaca->kvm_hstate.hwthread_state == KVM_HWTHREAD_IN_KERNEL) {
+		if (--timeout <= 0) {
+			pr_err("KVM: couldn't grab cpu %d\n", cpu);
+			return -EBUSY;
+		}
+		udelay(1);
+	}
+	return 0;
+}
+
+static void kvmppc_release_hwthread(int cpu)
+{
+	struct paca_struct *tpaca;
+
+	tpaca = &paca[cpu];
+	tpaca->kvm_hstate.hwthread_req = 0;
+	tpaca->kvm_hstate.kvm_vcpu = NULL;
+}
+
 static void kvmppc_start_thread(struct kvm_vcpu *vcpu)
 {
 	int cpu;
@@ -535,15 +1439,14 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu)
 	tpaca = &paca[cpu];
 	tpaca->kvm_hstate.kvm_vcpu = vcpu;
 	tpaca->kvm_hstate.kvm_vcore = vc;
-	tpaca->kvm_hstate.napping = 0;
+	tpaca->kvm_hstate.ptid = vcpu->arch.ptid;
 	vcpu->cpu = vc->pcpu;
 	smp_wmb();
 #if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP)
-	if (vcpu->arch.ptid) {
-		tpaca->cpu_start = 0x80;
-		wmb();
+	if (cpu != smp_processor_id()) {
 		xics_wake_cpu(cpu);
-		++vc->n_woken;
+		if (vcpu->arch.ptid)
+			++vc->n_woken;
 	}
 #endif
 }
@@ -567,18 +1470,33 @@ static void kvmppc_wait_for_nap(struct kvmppc_vcore *vc)
 
 /*
  * Check that we are on thread 0 and that any other threads in
- * this core are off-line.
+ * this core are off-line.  Then grab the threads so they can't
+ * enter the kernel.
  */
 static int on_primary_thread(void)
 {
 	int cpu = smp_processor_id();
-	int thr = cpu_thread_in_core(cpu);
+	int thr;
 
-	if (thr)
+	/* Are we on a primary subcore? */
+	if (cpu_thread_in_subcore(cpu))
 		return 0;
-	while (++thr < threads_per_core)
+
+	thr = 0;
+	while (++thr < threads_per_subcore)
 		if (cpu_online(cpu + thr))
 			return 0;
+
+	/* Grab all hw threads so they can't go into the kernel */
+	for (thr = 1; thr < threads_per_subcore; ++thr) {
+		if (kvmppc_grab_hwthread(cpu + thr)) {
+			/* Couldn't grab one; let the others go */
+			do {
+				kvmppc_release_hwthread(cpu + thr);
+			} while (--thr > 0);
+			return 0;
+		}
+	}
 	return 1;
 }
 
@@ -586,64 +1504,80 @@ static int on_primary_thread(void)
  * Run a set of guest threads on a physical core.
  * Called with vc->lock held.
  */
-static int kvmppc_run_core(struct kvmppc_vcore *vc)
+static void kvmppc_run_core(struct kvmppc_vcore *vc)
 {
-	struct kvm_vcpu *vcpu, *vcpu0, *vnext;
+	struct kvm_vcpu *vcpu, *vnext;
 	long ret;
 	u64 now;
-	int ptid;
+	int i, need_vpa_update;
+	int srcu_idx;
+	struct kvm_vcpu *vcpus_to_update[threads_per_core];
 
 	/* don't start if any threads have a signal pending */
-	list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
+	need_vpa_update = 0;
+	list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
 		if (signal_pending(vcpu->arch.run_task))
-			return 0;
+			return;
+		if (vcpu->arch.vpa.update_pending ||
+		    vcpu->arch.slb_shadow.update_pending ||
+		    vcpu->arch.dtl.update_pending)
+			vcpus_to_update[need_vpa_update++] = vcpu;
+	}
 
 	/*
-	 * Make sure we are running on thread 0, and that
-	 * secondary threads are offline.
-	 * XXX we should also block attempts to bring any
-	 * secondary threads online.
+	 * Initialize *vc, in particular vc->vcore_state, so we can
+	 * drop the vcore lock if necessary.
 	 */
-	if (threads_per_core > 1 && !on_primary_thread()) {
-		list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
-			vcpu->arch.ret = -EBUSY;
-		goto out;
+	vc->n_woken = 0;
+	vc->nap_count = 0;
+	vc->entry_exit_count = 0;
+	vc->vcore_state = VCORE_STARTING;
+	vc->in_guest = 0;
+	vc->napping_threads = 0;
+
+	/*
+	 * Updating any of the vpas requires calling kvmppc_pin_guest_page,
+	 * which can't be called with any spinlocks held.
+	 */
+	if (need_vpa_update) {
+		spin_unlock(&vc->lock);
+		for (i = 0; i < need_vpa_update; ++i)
+			kvmppc_update_vpas(vcpus_to_update[i]);
+		spin_lock(&vc->lock);
 	}
 
 	/*
-	 * Assign physical thread IDs, first to non-ceded vcpus
-	 * and then to ceded ones.
+	 * Make sure we are running on primary threads, and that secondary
+	 * threads are offline.  Also check if the number of threads in this
+	 * guest are greater than the current system threads per guest.
 	 */
-	ptid = 0;
-	vcpu0 = NULL;
-	list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
-		if (!vcpu->arch.ceded) {
-			if (!ptid)
-				vcpu0 = vcpu;
-			vcpu->arch.ptid = ptid++;
-		}
+	if ((threads_per_core > 1) &&
+	    ((vc->num_threads > threads_per_subcore) || !on_primary_thread())) {
+		list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
+			vcpu->arch.ret = -EBUSY;
+		goto out;
 	}
-	if (!vcpu0)
-		return 0;		/* nothing to run */
-	list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
-		if (vcpu->arch.ceded)
-			vcpu->arch.ptid = ptid++;
 
-	vc->n_woken = 0;
-	vc->nap_count = 0;
-	vc->entry_exit_count = 0;
-	vc->vcore_state = VCORE_RUNNING;
-	vc->in_guest = 0;
+
 	vc->pcpu = smp_processor_id();
-	vc->napping_threads = 0;
-	list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list)
+	list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
 		kvmppc_start_thread(vcpu);
+		kvmppc_create_dtl_entry(vcpu, vc);
+	}
+
+	/* Set this explicitly in case thread 0 doesn't have a vcpu */
+	get_paca()->kvm_hstate.kvm_vcore = vc;
+	get_paca()->kvm_hstate.ptid = 0;
 
+	vc->vcore_state = VCORE_RUNNING;
 	preempt_disable();
 	spin_unlock(&vc->lock);
 
 	kvm_guest_enter();
-	__kvmppc_vcore_entry(NULL, vcpu0);
+
+	srcu_idx = srcu_read_lock(&vc->kvm->srcu);
+
+	__kvmppc_vcore_entry();
 
 	spin_lock(&vc->lock);
 	/* disable sending of IPIs on virtual external irqs */
@@ -652,17 +1586,22 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc)
 	/* wait for secondary threads to finish writing their state to memory */
 	if (vc->nap_count < vc->n_woken)
 		kvmppc_wait_for_nap(vc);
+	for (i = 0; i < threads_per_subcore; ++i)
+		kvmppc_release_hwthread(vc->pcpu + i);
 	/* prevent other vcpu threads from doing kvmppc_start_thread() now */
 	vc->vcore_state = VCORE_EXITING;
 	spin_unlock(&vc->lock);
 
+	srcu_read_unlock(&vc->kvm->srcu, srcu_idx);
+
 	/* make sure updates to secondary vcpu structs are visible now */
 	smp_mb();
 	kvm_guest_exit();
 
 	preempt_enable();
-	kvm_resched(vcpu);
+	cond_resched();
 
+	spin_lock(&vc->lock);
 	now = get_tb();
 	list_for_each_entry(vcpu, &vc->runnable_threads, arch.run_list) {
 		/* cancel pending dec exception if dec is positive */
@@ -672,32 +1611,29 @@ static int kvmppc_run_core(struct kvmppc_vcore *vc)
 
 		ret = RESUME_GUEST;
 		if (vcpu->arch.trap)
-			ret = kvmppc_handle_exit(vcpu->arch.kvm_run, vcpu,
-						 vcpu->arch.run_task);
+			ret = kvmppc_handle_exit_hv(vcpu->arch.kvm_run, vcpu,
+						    vcpu->arch.run_task);
 
 		vcpu->arch.ret = ret;
 		vcpu->arch.trap = 0;
 
 		if (vcpu->arch.ceded) {
-			if (ret != RESUME_GUEST)
+			if (!is_kvmppc_resume_guest(ret))
 				kvmppc_end_cede(vcpu);
 			else
 				kvmppc_set_timer(vcpu);
 		}
 	}
 
-	spin_lock(&vc->lock);
  out:
 	vc->vcore_state = VCORE_INACTIVE;
 	list_for_each_entry_safe(vcpu, vnext, &vc->runnable_threads,
 				 arch.run_list) {
-		if (vcpu->arch.ret != RESUME_GUEST) {
+		if (!is_kvmppc_resume_guest(vcpu->arch.ret)) {
 			kvmppc_remove_runnable(vc, vcpu);
 			wake_up(&vcpu->arch.cpu_run);
 		}
 	}
-
-	return 1;
 }
 
 /*
@@ -721,20 +1657,11 @@ static void kvmppc_wait_for_exec(struct kvm_vcpu *vcpu, int wait_state)
 static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 {
 	DEFINE_WAIT(wait);
-	struct kvm_vcpu *v;
-	int all_idle = 1;
 
 	prepare_to_wait(&vc->wq, &wait, TASK_INTERRUPTIBLE);
 	vc->vcore_state = VCORE_SLEEPING;
 	spin_unlock(&vc->lock);
-	list_for_each_entry(v, &vc->runnable_threads, arch.run_list) {
-		if (!v->arch.ceded || v->arch.pending_exceptions) {
-			all_idle = 0;
-			break;
-		}
-	}
-	if (all_idle)
-		schedule();
+	schedule();
 	finish_wait(&vc->wq, &wait);
 	spin_lock(&vc->lock);
 	vc->vcore_state = VCORE_INACTIVE;
@@ -743,13 +1670,13 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 {
 	int n_ceded;
-	int prev_state;
 	struct kvmppc_vcore *vc;
 	struct kvm_vcpu *v, *vn;
 
 	kvm_run->exit_reason = 0;
 	vcpu->arch.ret = RESUME_GUEST;
 	vcpu->arch.trap = 0;
+	kvmppc_update_vpas(vcpu);
 
 	/*
 	 * Synchronize with other threads in this virtual core
@@ -759,8 +1686,9 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	vcpu->arch.ceded = 0;
 	vcpu->arch.run_task = current;
 	vcpu->arch.kvm_run = kvm_run;
-	prev_state = vcpu->arch.state;
+	vcpu->arch.stolen_logged = vcore_stolen_time(vc, mftb());
 	vcpu->arch.state = KVMPPC_VCPU_RUNNABLE;
+	vcpu->arch.busy_preempt = TB_NIL;
 	list_add_tail(&vcpu->arch.run_list, &vc->runnable_threads);
 	++vc->n_runnable;
 
@@ -769,35 +1697,28 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	 * If the vcore is already running, we may be able to start
 	 * this thread straight away and have it join in.
 	 */
-	if (prev_state == KVMPPC_VCPU_STOPPED) {
+	if (!signal_pending(current)) {
 		if (vc->vcore_state == VCORE_RUNNING &&
 		    VCORE_EXIT_COUNT(vc) == 0) {
-			vcpu->arch.ptid = vc->n_runnable - 1;
+			kvmppc_create_dtl_entry(vcpu, vc);
 			kvmppc_start_thread(vcpu);
+		} else if (vc->vcore_state == VCORE_SLEEPING) {
+			wake_up(&vc->wq);
 		}
 
-	} else if (prev_state == KVMPPC_VCPU_BUSY_IN_HOST)
-		--vc->n_busy;
+	}
 
 	while (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE &&
 	       !signal_pending(current)) {
-		if (vc->n_busy || vc->vcore_state != VCORE_INACTIVE) {
+		if (vc->vcore_state != VCORE_INACTIVE) {
 			spin_unlock(&vc->lock);
 			kvmppc_wait_for_exec(vcpu, TASK_INTERRUPTIBLE);
 			spin_lock(&vc->lock);
 			continue;
 		}
-		n_ceded = 0;
-		list_for_each_entry(v, &vc->runnable_threads, arch.run_list)
-			n_ceded += v->arch.ceded;
-		if (n_ceded == vc->n_runnable)
-			kvmppc_vcore_blocked(vc);
-		else
-			kvmppc_run_core(vc);
-
 		list_for_each_entry_safe(v, vn, &vc->runnable_threads,
 					 arch.run_list) {
-			kvmppc_core_deliver_interrupts(v);
+			kvmppc_core_prepare_to_enter(v);
 			if (signal_pending(v->arch.run_task)) {
 				kvmppc_remove_runnable(vc, v);
 				v->stat.signal_exits++;
@@ -806,50 +1727,84 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 				wake_up(&v->arch.cpu_run);
 			}
 		}
+		if (!vc->n_runnable || vcpu->arch.state != KVMPPC_VCPU_RUNNABLE)
+			break;
+		vc->runner = vcpu;
+		n_ceded = 0;
+		list_for_each_entry(v, &vc->runnable_threads, arch.run_list) {
+			if (!v->arch.pending_exceptions)
+				n_ceded += v->arch.ceded;
+			else
+				v->arch.ceded = 0;
+		}
+		if (n_ceded == vc->n_runnable)
+			kvmppc_vcore_blocked(vc);
+		else
+			kvmppc_run_core(vc);
+		vc->runner = NULL;
 	}
 
-	if (signal_pending(current)) {
-		if (vc->vcore_state == VCORE_RUNNING ||
-		    vc->vcore_state == VCORE_EXITING) {
-			spin_unlock(&vc->lock);
-			kvmppc_wait_for_exec(vcpu, TASK_UNINTERRUPTIBLE);
-			spin_lock(&vc->lock);
-		}
-		if (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE) {
-			kvmppc_remove_runnable(vc, vcpu);
-			vcpu->stat.signal_exits++;
-			kvm_run->exit_reason = KVM_EXIT_INTR;
-			vcpu->arch.ret = -EINTR;
-		}
+	while (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE &&
+	       (vc->vcore_state == VCORE_RUNNING ||
+		vc->vcore_state == VCORE_EXITING)) {
+		spin_unlock(&vc->lock);
+		kvmppc_wait_for_exec(vcpu, TASK_UNINTERRUPTIBLE);
+		spin_lock(&vc->lock);
+	}
+
+	if (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE) {
+		kvmppc_remove_runnable(vc, vcpu);
+		vcpu->stat.signal_exits++;
+		kvm_run->exit_reason = KVM_EXIT_INTR;
+		vcpu->arch.ret = -EINTR;
+	}
+
+	if (vc->n_runnable && vc->vcore_state == VCORE_INACTIVE) {
+		/* Wake up some vcpu to run the core */
+		v = list_first_entry(&vc->runnable_threads,
+				     struct kvm_vcpu, arch.run_list);
+		wake_up(&v->arch.cpu_run);
 	}
 
 	spin_unlock(&vc->lock);
 	return vcpu->arch.ret;
 }
 
-int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu)
+static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
 {
 	int r;
+	int srcu_idx;
 
 	if (!vcpu->arch.sane) {
 		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		return -EINVAL;
 	}
 
+	kvmppc_core_prepare_to_enter(vcpu);
+
 	/* No need to go into the guest when all we'll do is come back out */
 	if (signal_pending(current)) {
 		run->exit_reason = KVM_EXIT_INTR;
 		return -EINTR;
 	}
 
-	/* On PPC970, check that we have an RMA region */
-	if (!vcpu->kvm->arch.rma && cpu_has_feature(CPU_FTR_ARCH_201))
-		return -EPERM;
+	atomic_inc(&vcpu->kvm->arch.vcpus_running);
+	/* Order vcpus_running vs. rma_setup_done, see kvmppc_alloc_reset_hpt */
+	smp_mb();
+
+	/* On the first time here, set up HTAB and VRMA or RMA */
+	if (!vcpu->kvm->arch.rma_setup_done) {
+		r = kvmppc_hv_setup_htab_rma(vcpu);
+		if (r)
+			goto out;
+	}
 
 	flush_fp_to_thread(current);
 	flush_altivec_to_thread(current);
 	flush_vsx_to_thread(current);
 	vcpu->arch.wqp = &vcpu->arch.vcore->wq;
+	vcpu->arch.pgdir = current->mm->pgd;
+	vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
 
 	do {
 		r = kvmppc_run_vcpu(run, vcpu);
@@ -857,121 +1812,21 @@ int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		if (run->exit_reason == KVM_EXIT_PAPR_HCALL &&
 		    !(vcpu->arch.shregs.msr & MSR_PR)) {
 			r = kvmppc_pseries_do_hcall(vcpu);
-			kvmppc_core_deliver_interrupts(vcpu);
+			kvmppc_core_prepare_to_enter(vcpu);
+		} else if (r == RESUME_PAGE_FAULT) {
+			srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+			r = kvmppc_book3s_hv_page_fault(run, vcpu,
+				vcpu->arch.fault_dar, vcpu->arch.fault_dsisr);
+			srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
 		}
-	} while (r == RESUME_GUEST);
-	return r;
-}
-
-static long kvmppc_stt_npages(unsigned long window_size)
-{
-	return ALIGN((window_size >> SPAPR_TCE_SHIFT)
-		     * sizeof(u64), PAGE_SIZE) / PAGE_SIZE;
-}
-
-static void release_spapr_tce_table(struct kvmppc_spapr_tce_table *stt)
-{
-	struct kvm *kvm = stt->kvm;
-	int i;
-
-	mutex_lock(&kvm->lock);
-	list_del(&stt->list);
-	for (i = 0; i < kvmppc_stt_npages(stt->window_size); i++)
-		__free_page(stt->pages[i]);
-	kfree(stt);
-	mutex_unlock(&kvm->lock);
-
-	kvm_put_kvm(kvm);
-}
-
-static int kvm_spapr_tce_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	struct kvmppc_spapr_tce_table *stt = vma->vm_file->private_data;
-	struct page *page;
-
-	if (vmf->pgoff >= kvmppc_stt_npages(stt->window_size))
-		return VM_FAULT_SIGBUS;
-
-	page = stt->pages[vmf->pgoff];
-	get_page(page);
-	vmf->page = page;
-	return 0;
-}
-
-static const struct vm_operations_struct kvm_spapr_tce_vm_ops = {
-	.fault = kvm_spapr_tce_fault,
-};
+	} while (is_kvmppc_resume_guest(r));
 
-static int kvm_spapr_tce_mmap(struct file *file, struct vm_area_struct *vma)
-{
-	vma->vm_ops = &kvm_spapr_tce_vm_ops;
-	return 0;
-}
-
-static int kvm_spapr_tce_release(struct inode *inode, struct file *filp)
-{
-	struct kvmppc_spapr_tce_table *stt = filp->private_data;
-
-	release_spapr_tce_table(stt);
-	return 0;
+ out:
+	vcpu->arch.state = KVMPPC_VCPU_NOTREADY;
+	atomic_dec(&vcpu->kvm->arch.vcpus_running);
+	return r;
 }
 
-static struct file_operations kvm_spapr_tce_fops = {
-	.mmap           = kvm_spapr_tce_mmap,
-	.release	= kvm_spapr_tce_release,
-};
-
-long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
-				   struct kvm_create_spapr_tce *args)
-{
-	struct kvmppc_spapr_tce_table *stt = NULL;
-	long npages;
-	int ret = -ENOMEM;
-	int i;
-
-	/* Check this LIOBN hasn't been previously allocated */
-	list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) {
-		if (stt->liobn == args->liobn)
-			return -EBUSY;
-	}
-
-	npages = kvmppc_stt_npages(args->window_size);
-
-	stt = kzalloc(sizeof(*stt) + npages* sizeof(struct page *),
-		      GFP_KERNEL);
-	if (!stt)
-		goto fail;
-
-	stt->liobn = args->liobn;
-	stt->window_size = args->window_size;
-	stt->kvm = kvm;
-
-	for (i = 0; i < npages; i++) {
-		stt->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO);
-		if (!stt->pages[i])
-			goto fail;
-	}
-
-	kvm_get_kvm(kvm);
-
-	mutex_lock(&kvm->lock);
-	list_add(&stt->list, &kvm->arch.spapr_tce_tables);
-
-	mutex_unlock(&kvm->lock);
-
-	return anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops,
-				stt, O_RDWR);
-
-fail:
-	if (stt) {
-		for (i = 0; i < npages; i++)
-			if (stt->pages[i])
-				__free_page(stt->pages[i]);
-
-		kfree(stt);
-	}
-	return ret;
-}
 
 /* Work out RMLS (real mode limit selector) field value for a given RMA size.
    Assumes POWER7 or PPC970. */
@@ -1001,10 +1856,10 @@ static inline int lpcr_rmls(unsigned long rma_size)
 
 static int kvm_rma_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-	struct kvmppc_rma_info *ri = vma->vm_file->private_data;
 	struct page *page;
+	struct kvm_rma_info *ri = vma->vm_file->private_data;
 
-	if (vmf->pgoff >= ri->npages)
+	if (vmf->pgoff >= kvm_rma_pages)
 		return VM_FAULT_SIGBUS;
 
 	page = pfn_to_page(ri->base_pfn + vmf->pgoff);
@@ -1019,218 +1874,419 @@ static const struct vm_operations_struct kvm_rma_vm_ops = {
 
 static int kvm_rma_mmap(struct file *file, struct vm_area_struct *vma)
 {
-	vma->vm_flags |= VM_RESERVED;
+	vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;
 	vma->vm_ops = &kvm_rma_vm_ops;
 	return 0;
 }
 
 static int kvm_rma_release(struct inode *inode, struct file *filp)
 {
-	struct kvmppc_rma_info *ri = filp->private_data;
+	struct kvm_rma_info *ri = filp->private_data;
 
 	kvm_release_rma(ri);
 	return 0;
 }
 
-static struct file_operations kvm_rma_fops = {
+static const struct file_operations kvm_rma_fops = {
 	.mmap           = kvm_rma_mmap,
 	.release	= kvm_rma_release,
 };
 
-long kvm_vm_ioctl_allocate_rma(struct kvm *kvm, struct kvm_allocate_rma *ret)
+static long kvm_vm_ioctl_allocate_rma(struct kvm *kvm,
+				      struct kvm_allocate_rma *ret)
 {
-	struct kvmppc_rma_info *ri;
 	long fd;
+	struct kvm_rma_info *ri;
+	/*
+	 * Only do this on PPC970 in HV mode
+	 */
+	if (!cpu_has_feature(CPU_FTR_HVMODE) ||
+	    !cpu_has_feature(CPU_FTR_ARCH_201))
+		return -EINVAL;
+
+	if (!kvm_rma_pages)
+		return -EINVAL;
 
 	ri = kvm_alloc_rma();
 	if (!ri)
 		return -ENOMEM;
 
-	fd = anon_inode_getfd("kvm-rma", &kvm_rma_fops, ri, O_RDWR);
+	fd = anon_inode_getfd("kvm-rma", &kvm_rma_fops, ri, O_RDWR | O_CLOEXEC);
 	if (fd < 0)
 		kvm_release_rma(ri);
 
-	ret->rma_size = ri->npages << PAGE_SHIFT;
+	ret->rma_size = kvm_rma_pages << PAGE_SHIFT;
 	return fd;
 }
 
-static struct page *hva_to_page(unsigned long addr)
+static void kvmppc_add_seg_page_size(struct kvm_ppc_one_seg_page_size **sps,
+				     int linux_psize)
+{
+	struct mmu_psize_def *def = &mmu_psize_defs[linux_psize];
+
+	if (!def->shift)
+		return;
+	(*sps)->page_shift = def->shift;
+	(*sps)->slb_enc = def->sllp;
+	(*sps)->enc[0].page_shift = def->shift;
+	/*
+	 * Only return base page encoding. We don't want to return
+	 * all the supporting pte_enc, because our H_ENTER doesn't
+	 * support MPSS yet. Once they do, we can start passing all
+	 * support pte_enc here
+	 */
+	(*sps)->enc[0].pte_enc = def->penc[linux_psize];
+	/*
+	 * Add 16MB MPSS support if host supports it
+	 */
+	if (linux_psize != MMU_PAGE_16M && def->penc[MMU_PAGE_16M] != -1) {
+		(*sps)->enc[1].page_shift = 24;
+		(*sps)->enc[1].pte_enc = def->penc[MMU_PAGE_16M];
+	}
+	(*sps)++;
+}
+
+static int kvm_vm_ioctl_get_smmu_info_hv(struct kvm *kvm,
+					 struct kvm_ppc_smmu_info *info)
 {
-	struct page *page[1];
-	int npages;
+	struct kvm_ppc_one_seg_page_size *sps;
 
-	might_sleep();
+	info->flags = KVM_PPC_PAGE_SIZES_REAL;
+	if (mmu_has_feature(MMU_FTR_1T_SEGMENT))
+		info->flags |= KVM_PPC_1T_SEGMENTS;
+	info->slb_size = mmu_slb_size;
 
-	npages = get_user_pages_fast(addr, 1, 1, page);
+	/* We only support these sizes for now, and no muti-size segments */
+	sps = &info->sps[0];
+	kvmppc_add_seg_page_size(&sps, MMU_PAGE_4K);
+	kvmppc_add_seg_page_size(&sps, MMU_PAGE_64K);
+	kvmppc_add_seg_page_size(&sps, MMU_PAGE_16M);
 
-	if (unlikely(npages != 1))
-		return 0;
+	return 0;
+}
+
+/*
+ * Get (and clear) the dirty memory log for a memory slot.
+ */
+static int kvm_vm_ioctl_get_dirty_log_hv(struct kvm *kvm,
+					 struct kvm_dirty_log *log)
+{
+	struct kvm_memory_slot *memslot;
+	int r;
+	unsigned long n;
+
+	mutex_lock(&kvm->slots_lock);
+
+	r = -EINVAL;
+	if (log->slot >= KVM_USER_MEM_SLOTS)
+		goto out;
+
+	memslot = id_to_memslot(kvm->memslots, log->slot);
+	r = -ENOENT;
+	if (!memslot->dirty_bitmap)
+		goto out;
+
+	n = kvm_dirty_bitmap_bytes(memslot);
+	memset(memslot->dirty_bitmap, 0, n);
+
+	r = kvmppc_hv_get_dirty_log(kvm, memslot, memslot->dirty_bitmap);
+	if (r)
+		goto out;
 
-	return page[0];
+	r = -EFAULT;
+	if (copy_to_user(log->dirty_bitmap, memslot->dirty_bitmap, n))
+		goto out;
+
+	r = 0;
+out:
+	mutex_unlock(&kvm->slots_lock);
+	return r;
 }
 
-int kvmppc_core_prepare_memory_region(struct kvm *kvm,
-				struct kvm_userspace_memory_region *mem)
+static void unpin_slot(struct kvm_memory_slot *memslot)
 {
-	unsigned long psize, porder;
-	unsigned long i, npages, totalpages;
-	unsigned long pg_ix;
-	struct kvmppc_pginfo *pginfo;
-	unsigned long hva;
-	struct kvmppc_rma_info *ri = NULL;
+	unsigned long *physp;
+	unsigned long j, npages, pfn;
 	struct page *page;
 
-	/* For now, only allow 16MB pages */
-	porder = LARGE_PAGE_ORDER;
-	psize = 1ul << porder;
-	if ((mem->memory_size & (psize - 1)) ||
-	    (mem->guest_phys_addr & (psize - 1))) {
-		pr_err("bad memory_size=%llx @ %llx\n",
-		       mem->memory_size, mem->guest_phys_addr);
-		return -EINVAL;
+	physp = memslot->arch.slot_phys;
+	npages = memslot->npages;
+	if (!physp)
+		return;
+	for (j = 0; j < npages; j++) {
+		if (!(physp[j] & KVMPPC_GOT_PAGE))
+			continue;
+		pfn = physp[j] >> PAGE_SHIFT;
+		page = pfn_to_page(pfn);
+		SetPageDirty(page);
+		put_page(page);
 	}
+}
 
-	npages = mem->memory_size >> porder;
-	totalpages = (mem->guest_phys_addr + mem->memory_size) >> porder;
+static void kvmppc_core_free_memslot_hv(struct kvm_memory_slot *free,
+					struct kvm_memory_slot *dont)
+{
+	if (!dont || free->arch.rmap != dont->arch.rmap) {
+		vfree(free->arch.rmap);
+		free->arch.rmap = NULL;
+	}
+	if (!dont || free->arch.slot_phys != dont->arch.slot_phys) {
+		unpin_slot(free);
+		vfree(free->arch.slot_phys);
+		free->arch.slot_phys = NULL;
+	}
+}
 
-	/* More memory than we have space to track? */
-	if (totalpages > (1ul << (MAX_MEM_ORDER - LARGE_PAGE_ORDER)))
-		return -EINVAL;
+static int kvmppc_core_create_memslot_hv(struct kvm_memory_slot *slot,
+					 unsigned long npages)
+{
+	slot->arch.rmap = vzalloc(npages * sizeof(*slot->arch.rmap));
+	if (!slot->arch.rmap)
+		return -ENOMEM;
+	slot->arch.slot_phys = NULL;
 
-	/* Do we already have an RMA registered? */
-	if (mem->guest_phys_addr == 0 && kvm->arch.rma)
-		return -EINVAL;
+	return 0;
+}
 
-	if (totalpages > kvm->arch.ram_npages)
-		kvm->arch.ram_npages = totalpages;
+static int kvmppc_core_prepare_memory_region_hv(struct kvm *kvm,
+					struct kvm_memory_slot *memslot,
+					struct kvm_userspace_memory_region *mem)
+{
+	unsigned long *phys;
+
+	/* Allocate a slot_phys array if needed */
+	phys = memslot->arch.slot_phys;
+	if (!kvm->arch.using_mmu_notifiers && !phys && memslot->npages) {
+		phys = vzalloc(memslot->npages * sizeof(unsigned long));
+		if (!phys)
+			return -ENOMEM;
+		memslot->arch.slot_phys = phys;
+	}
 
-	/* Is this one of our preallocated RMAs? */
-	if (mem->guest_phys_addr == 0) {
-		struct vm_area_struct *vma;
-
-		down_read(&current->mm->mmap_sem);
-		vma = find_vma(current->mm, mem->userspace_addr);
-		if (vma && vma->vm_file &&
-		    vma->vm_file->f_op == &kvm_rma_fops &&
-		    mem->userspace_addr == vma->vm_start)
-			ri = vma->vm_file->private_data;
-		up_read(&current->mm->mmap_sem);
-		if (!ri && cpu_has_feature(CPU_FTR_ARCH_201)) {
-			pr_err("CPU requires an RMO\n");
-			return -EINVAL;
+	return 0;
+}
+
+static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm,
+				struct kvm_userspace_memory_region *mem,
+				const struct kvm_memory_slot *old)
+{
+	unsigned long npages = mem->memory_size >> PAGE_SHIFT;
+	struct kvm_memory_slot *memslot;
+
+	if (npages && old->npages) {
+		/*
+		 * If modifying a memslot, reset all the rmap dirty bits.
+		 * If this is a new memslot, we don't need to do anything
+		 * since the rmap array starts out as all zeroes,
+		 * i.e. no pages are dirty.
+		 */
+		memslot = id_to_memslot(kvm->memslots, mem->slot);
+		kvmppc_hv_get_dirty_log(kvm, memslot, NULL);
+	}
+}
+
+/*
+ * Update LPCR values in kvm->arch and in vcores.
+ * Caller must hold kvm->lock.
+ */
+void kvmppc_update_lpcr(struct kvm *kvm, unsigned long lpcr, unsigned long mask)
+{
+	long int i;
+	u32 cores_done = 0;
+
+	if ((kvm->arch.lpcr & mask) == lpcr)
+		return;
+
+	kvm->arch.lpcr = (kvm->arch.lpcr & ~mask) | lpcr;
+
+	for (i = 0; i < KVM_MAX_VCORES; ++i) {
+		struct kvmppc_vcore *vc = kvm->arch.vcores[i];
+		if (!vc)
+			continue;
+		spin_lock(&vc->lock);
+		vc->lpcr = (vc->lpcr & ~mask) | lpcr;
+		spin_unlock(&vc->lock);
+		if (++cores_done >= kvm->arch.online_vcores)
+			break;
+	}
+}
+
+static void kvmppc_mmu_destroy_hv(struct kvm_vcpu *vcpu)
+{
+	return;
+}
+
+static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
+{
+	int err = 0;
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_rma_info *ri = NULL;
+	unsigned long hva;
+	struct kvm_memory_slot *memslot;
+	struct vm_area_struct *vma;
+	unsigned long lpcr = 0, senc;
+	unsigned long lpcr_mask = 0;
+	unsigned long psize, porder;
+	unsigned long rma_size;
+	unsigned long rmls;
+	unsigned long *physp;
+	unsigned long i, npages;
+	int srcu_idx;
+
+	mutex_lock(&kvm->lock);
+	if (kvm->arch.rma_setup_done)
+		goto out;	/* another vcpu beat us to it */
+
+	/* Allocate hashed page table (if not done already) and reset it */
+	if (!kvm->arch.hpt_virt) {
+		err = kvmppc_alloc_hpt(kvm, NULL);
+		if (err) {
+			pr_err("KVM: Couldn't alloc HPT\n");
+			goto out;
 		}
 	}
 
-	if (ri) {
-		unsigned long rma_size;
-		unsigned long lpcr;
-		long rmls;
+	/* Look up the memslot for guest physical address 0 */
+	srcu_idx = srcu_read_lock(&kvm->srcu);
+	memslot = gfn_to_memslot(kvm, 0);
 
-		rma_size = ri->npages << PAGE_SHIFT;
-		if (rma_size > mem->memory_size)
-			rma_size = mem->memory_size;
+	/* We must have some memory at 0 by now */
+	err = -EINVAL;
+	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
+		goto out_srcu;
+
+	/* Look up the VMA for the start of this memory slot */
+	hva = memslot->userspace_addr;
+	down_read(&current->mm->mmap_sem);
+	vma = find_vma(current->mm, hva);
+	if (!vma || vma->vm_start > hva || (vma->vm_flags & VM_IO))
+		goto up_out;
+
+	psize = vma_kernel_pagesize(vma);
+	porder = __ilog2(psize);
+
+	/* Is this one of our preallocated RMAs? */
+	if (vma->vm_file && vma->vm_file->f_op == &kvm_rma_fops &&
+	    hva == vma->vm_start)
+		ri = vma->vm_file->private_data;
+
+	up_read(&current->mm->mmap_sem);
+
+	if (!ri) {
+		/* On POWER7, use VRMA; on PPC970, give up */
+		err = -EPERM;
+		if (cpu_has_feature(CPU_FTR_ARCH_201)) {
+			pr_err("KVM: CPU requires an RMO\n");
+			goto out_srcu;
+		}
+
+		/* We can handle 4k, 64k or 16M pages in the VRMA */
+		err = -EINVAL;
+		if (!(psize == 0x1000 || psize == 0x10000 ||
+		      psize == 0x1000000))
+			goto out_srcu;
+
+		/* Update VRMASD field in the LPCR */
+		senc = slb_pgsize_encoding(psize);
+		kvm->arch.vrma_slb_v = senc | SLB_VSID_B_1T |
+			(VRMA_VSID << SLB_VSID_SHIFT_1T);
+		lpcr_mask = LPCR_VRMASD;
+		/* the -4 is to account for senc values starting at 0x10 */
+		lpcr = senc << (LPCR_VRMASD_SH - 4);
+
+		/* Create HPTEs in the hash page table for the VRMA */
+		kvmppc_map_vrma(vcpu, memslot, porder);
+
+	} else {
+		/* Set up to use an RMO region */
+		rma_size = kvm_rma_pages;
+		if (rma_size > memslot->npages)
+			rma_size = memslot->npages;
+		rma_size <<= PAGE_SHIFT;
 		rmls = lpcr_rmls(rma_size);
-		if (rmls < 0) {
-			pr_err("Can't use RMA of 0x%lx bytes\n", rma_size);
-			return -EINVAL;
+		err = -EINVAL;
+		if ((long)rmls < 0) {
+			pr_err("KVM: Can't use RMA of 0x%lx bytes\n", rma_size);
+			goto out_srcu;
 		}
 		atomic_inc(&ri->use_count);
 		kvm->arch.rma = ri;
-		kvm->arch.n_rma_pages = rma_size >> porder;
 
 		/* Update LPCR and RMOR */
-		lpcr = kvm->arch.lpcr;
 		if (cpu_has_feature(CPU_FTR_ARCH_201)) {
 			/* PPC970; insert RMLS value (split field) in HID4 */
-			lpcr &= ~((1ul << HID4_RMLS0_SH) |
-				  (3ul << HID4_RMLS2_SH));
-			lpcr |= ((rmls >> 2) << HID4_RMLS0_SH) |
+			lpcr_mask = (1ul << HID4_RMLS0_SH) |
+				(3ul << HID4_RMLS2_SH) | HID4_RMOR;
+			lpcr = ((rmls >> 2) << HID4_RMLS0_SH) |
 				((rmls & 3) << HID4_RMLS2_SH);
 			/* RMOR is also in HID4 */
 			lpcr |= ((ri->base_pfn >> (26 - PAGE_SHIFT)) & 0xffff)
 				<< HID4_RMOR_SH;
 		} else {
 			/* POWER7 */
-			lpcr &= ~(LPCR_VPM0 | LPCR_VRMA_L);
-			lpcr |= rmls << LPCR_RMLS_SH;
-			kvm->arch.rmor = kvm->arch.rma->base_pfn << PAGE_SHIFT;
+			lpcr_mask = LPCR_VPM0 | LPCR_VRMA_L | LPCR_RMLS;
+			lpcr = rmls << LPCR_RMLS_SH;
+			kvm->arch.rmor = ri->base_pfn << PAGE_SHIFT;
 		}
-		kvm->arch.lpcr = lpcr;
-		pr_info("Using RMO at %lx size %lx (LPCR = %lx)\n",
+		pr_info("KVM: Using RMO at %lx size %lx (LPCR = %lx)\n",
 			ri->base_pfn << PAGE_SHIFT, rma_size, lpcr);
-	}
 
-	pg_ix = mem->guest_phys_addr >> porder;
-	pginfo = kvm->arch.ram_pginfo + pg_ix;
-	for (i = 0; i < npages; ++i, ++pg_ix) {
-		if (ri && pg_ix < kvm->arch.n_rma_pages) {
-			pginfo[i].pfn = ri->base_pfn +
-				(pg_ix << (porder - PAGE_SHIFT));
-			continue;
-		}
-		hva = mem->userspace_addr + (i << porder);
-		page = hva_to_page(hva);
-		if (!page) {
-			pr_err("oops, no pfn for hva %lx\n", hva);
-			goto err;
-		}
-		/* Check it's a 16MB page */
-		if (!PageHead(page) ||
-		    compound_order(page) != (LARGE_PAGE_ORDER - PAGE_SHIFT)) {
-			pr_err("page at %lx isn't 16MB (o=%d)\n",
-			       hva, compound_order(page));
-			goto err;
+		/* Initialize phys addrs of pages in RMO */
+		npages = kvm_rma_pages;
+		porder = __ilog2(npages);
+		physp = memslot->arch.slot_phys;
+		if (physp) {
+			if (npages > memslot->npages)
+				npages = memslot->npages;
+			spin_lock(&kvm->arch.slot_phys_lock);
+			for (i = 0; i < npages; ++i)
+				physp[i] = ((ri->base_pfn + i) << PAGE_SHIFT) +
+					porder;
+			spin_unlock(&kvm->arch.slot_phys_lock);
 		}
-		pginfo[i].pfn = page_to_pfn(page);
 	}
 
-	return 0;
+	kvmppc_update_lpcr(kvm, lpcr, lpcr_mask);
 
- err:
-	return -EINVAL;
-}
+	/* Order updates to kvm->arch.lpcr etc. vs. rma_setup_done */
+	smp_wmb();
+	kvm->arch.rma_setup_done = 1;
+	err = 0;
+ out_srcu:
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+ out:
+	mutex_unlock(&kvm->lock);
+	return err;
 
-void kvmppc_core_commit_memory_region(struct kvm *kvm,
-				struct kvm_userspace_memory_region *mem)
-{
-	if (mem->guest_phys_addr == 0 && mem->memory_size != 0 &&
-	    !kvm->arch.rma)
-		kvmppc_map_vrma(kvm, mem);
+ up_out:
+	up_read(&current->mm->mmap_sem);
+	goto out_srcu;
 }
 
-int kvmppc_core_init_vm(struct kvm *kvm)
+static int kvmppc_core_init_vm_hv(struct kvm *kvm)
 {
-	long r;
-	unsigned long npages = 1ul << (MAX_MEM_ORDER - LARGE_PAGE_ORDER);
-	long err = -ENOMEM;
-	unsigned long lpcr;
+	unsigned long lpcr, lpid;
 
-	/* Allocate hashed page table */
-	r = kvmppc_alloc_hpt(kvm);
-	if (r)
-		return r;
+	/* Allocate the guest's logical partition ID */
 
-	INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables);
+	lpid = kvmppc_alloc_lpid();
+	if ((long)lpid < 0)
+		return -ENOMEM;
+	kvm->arch.lpid = lpid;
 
-	kvm->arch.ram_pginfo = kzalloc(npages * sizeof(struct kvmppc_pginfo),
-				       GFP_KERNEL);
-	if (!kvm->arch.ram_pginfo) {
-		pr_err("kvmppc_core_init_vm: couldn't alloc %lu bytes\n",
-		       npages * sizeof(struct kvmppc_pginfo));
-		goto out_free;
-	}
+	/*
+	 * Since we don't flush the TLB when tearing down a VM,
+	 * and this lpid might have previously been used,
+	 * make sure we flush on each core before running the new VM.
+	 */
+	cpumask_setall(&kvm->arch.need_tlb_flush);
 
-	kvm->arch.ram_npages = 0;
-	kvm->arch.ram_psize = 1ul << LARGE_PAGE_ORDER;
-	kvm->arch.ram_porder = LARGE_PAGE_ORDER;
 	kvm->arch.rma = NULL;
-	kvm->arch.n_rma_pages = 0;
 
 	kvm->arch.host_sdr1 = mfspr(SPRN_SDR1);
 
 	if (cpu_has_feature(CPU_FTR_ARCH_201)) {
 		/* PPC970; HID4 is effectively the LPCR */
-		unsigned long lpid = kvm->arch.lpid;
 		kvm->arch.host_lpid = 0;
 		kvm->arch.host_lpcr = lpcr = mfspr(SPRN_HID4);
 		lpcr &= ~((3 << HID4_LPID1_SH) | (0xful << HID4_LPID5_SH));
@@ -1242,79 +2298,185 @@ int kvmppc_core_init_vm(struct kvm *kvm)
 		kvm->arch.host_lpcr = lpcr = mfspr(SPRN_LPCR);
 		lpcr &= LPCR_PECE | LPCR_LPES;
 		lpcr |= (4UL << LPCR_DPFD_SH) | LPCR_HDICE |
-			LPCR_VPM0 | LPCR_VRMA_L;
+			LPCR_VPM0 | LPCR_VPM1;
+		kvm->arch.vrma_slb_v = SLB_VSID_B_1T |
+			(VRMA_VSID << SLB_VSID_SHIFT_1T);
+		/* On POWER8 turn on online bit to enable PURR/SPURR */
+		if (cpu_has_feature(CPU_FTR_ARCH_207S))
+			lpcr |= LPCR_ONL;
 	}
 	kvm->arch.lpcr = lpcr;
 
+	kvm->arch.using_mmu_notifiers = !!cpu_has_feature(CPU_FTR_ARCH_206);
+	spin_lock_init(&kvm->arch.slot_phys_lock);
+
+	/*
+	 * Track that we now have a HV mode VM active. This blocks secondary
+	 * CPU threads from coming online.
+	 */
+	kvm_hv_vm_activated();
+
 	return 0;
+}
 
- out_free:
-	kvmppc_free_hpt(kvm);
-	return err;
+static void kvmppc_free_vcores(struct kvm *kvm)
+{
+	long int i;
+
+	for (i = 0; i < KVM_MAX_VCORES; ++i)
+		kfree(kvm->arch.vcores[i]);
+	kvm->arch.online_vcores = 0;
 }
 
-void kvmppc_core_destroy_vm(struct kvm *kvm)
+static void kvmppc_core_destroy_vm_hv(struct kvm *kvm)
 {
-	struct kvmppc_pginfo *pginfo;
-	unsigned long i;
+	kvm_hv_vm_deactivated();
 
-	if (kvm->arch.ram_pginfo) {
-		pginfo = kvm->arch.ram_pginfo;
-		kvm->arch.ram_pginfo = NULL;
-		for (i = kvm->arch.n_rma_pages; i < kvm->arch.ram_npages; ++i)
-			if (pginfo[i].pfn)
-				put_page(pfn_to_page(pginfo[i].pfn));
-		kfree(pginfo);
-	}
+	kvmppc_free_vcores(kvm);
 	if (kvm->arch.rma) {
 		kvm_release_rma(kvm->arch.rma);
 		kvm->arch.rma = NULL;
 	}
 
 	kvmppc_free_hpt(kvm);
-	WARN_ON(!list_empty(&kvm->arch.spapr_tce_tables));
 }
 
-/* These are stubs for now */
-void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, ulong pa_start, ulong pa_end)
+/* We don't need to emulate any privileged instructions or dcbz */
+static int kvmppc_core_emulate_op_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
+				     unsigned int inst, int *advance)
 {
+	return EMULATE_FAIL;
 }
 
-/* We don't need to emulate any privileged instructions or dcbz */
-int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
-                           unsigned int inst, int *advance)
+static int kvmppc_core_emulate_mtspr_hv(struct kvm_vcpu *vcpu, int sprn,
+					ulong spr_val)
 {
 	return EMULATE_FAIL;
 }
 
-int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
+static int kvmppc_core_emulate_mfspr_hv(struct kvm_vcpu *vcpu, int sprn,
+					ulong *spr_val)
 {
 	return EMULATE_FAIL;
 }
 
-int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
+static int kvmppc_core_check_processor_compat_hv(void)
 {
-	return EMULATE_FAIL;
+	if (!cpu_has_feature(CPU_FTR_HVMODE))
+		return -EIO;
+	return 0;
 }
 
-static int kvmppc_book3s_hv_init(void)
+static long kvm_arch_vm_ioctl_hv(struct file *filp,
+				 unsigned int ioctl, unsigned long arg)
 {
-	int r;
+	struct kvm *kvm __maybe_unused = filp->private_data;
+	void __user *argp = (void __user *)arg;
+	long r;
 
-	r = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
+	switch (ioctl) {
 
-	if (r)
-		return r;
+	case KVM_ALLOCATE_RMA: {
+		struct kvm_allocate_rma rma;
+		struct kvm *kvm = filp->private_data;
 
-	r = kvmppc_mmu_hv_init();
+		r = kvm_vm_ioctl_allocate_rma(kvm, &rma);
+		if (r >= 0 && copy_to_user(argp, &rma, sizeof(rma)))
+			r = -EFAULT;
+		break;
+	}
+
+	case KVM_PPC_ALLOCATE_HTAB: {
+		u32 htab_order;
+
+		r = -EFAULT;
+		if (get_user(htab_order, (u32 __user *)argp))
+			break;
+		r = kvmppc_alloc_reset_hpt(kvm, &htab_order);
+		if (r)
+			break;
+		r = -EFAULT;
+		if (put_user(htab_order, (u32 __user *)argp))
+			break;
+		r = 0;
+		break;
+	}
+
+	case KVM_PPC_GET_HTAB_FD: {
+		struct kvm_get_htab_fd ghf;
 
+		r = -EFAULT;
+		if (copy_from_user(&ghf, argp, sizeof(ghf)))
+			break;
+		r = kvm_vm_ioctl_get_htab_fd(kvm, &ghf);
+		break;
+	}
+
+	default:
+		r = -ENOTTY;
+	}
+
+	return r;
+}
+
+static struct kvmppc_ops kvm_ops_hv = {
+	.get_sregs = kvm_arch_vcpu_ioctl_get_sregs_hv,
+	.set_sregs = kvm_arch_vcpu_ioctl_set_sregs_hv,
+	.get_one_reg = kvmppc_get_one_reg_hv,
+	.set_one_reg = kvmppc_set_one_reg_hv,
+	.vcpu_load   = kvmppc_core_vcpu_load_hv,
+	.vcpu_put    = kvmppc_core_vcpu_put_hv,
+	.set_msr     = kvmppc_set_msr_hv,
+	.vcpu_run    = kvmppc_vcpu_run_hv,
+	.vcpu_create = kvmppc_core_vcpu_create_hv,
+	.vcpu_free   = kvmppc_core_vcpu_free_hv,
+	.check_requests = kvmppc_core_check_requests_hv,
+	.get_dirty_log  = kvm_vm_ioctl_get_dirty_log_hv,
+	.flush_memslot  = kvmppc_core_flush_memslot_hv,
+	.prepare_memory_region = kvmppc_core_prepare_memory_region_hv,
+	.commit_memory_region  = kvmppc_core_commit_memory_region_hv,
+	.unmap_hva = kvm_unmap_hva_hv,
+	.unmap_hva_range = kvm_unmap_hva_range_hv,
+	.age_hva  = kvm_age_hva_hv,
+	.test_age_hva = kvm_test_age_hva_hv,
+	.set_spte_hva = kvm_set_spte_hva_hv,
+	.mmu_destroy  = kvmppc_mmu_destroy_hv,
+	.free_memslot = kvmppc_core_free_memslot_hv,
+	.create_memslot = kvmppc_core_create_memslot_hv,
+	.init_vm =  kvmppc_core_init_vm_hv,
+	.destroy_vm = kvmppc_core_destroy_vm_hv,
+	.get_smmu_info = kvm_vm_ioctl_get_smmu_info_hv,
+	.emulate_op = kvmppc_core_emulate_op_hv,
+	.emulate_mtspr = kvmppc_core_emulate_mtspr_hv,
+	.emulate_mfspr = kvmppc_core_emulate_mfspr_hv,
+	.fast_vcpu_kick = kvmppc_fast_vcpu_kick_hv,
+	.arch_vm_ioctl  = kvm_arch_vm_ioctl_hv,
+};
+
+static int kvmppc_book3s_init_hv(void)
+{
+	int r;
+	/*
+	 * FIXME!! Do we need to check on all cpus ?
+	 */
+	r = kvmppc_core_check_processor_compat_hv();
+	if (r < 0)
+		return -ENODEV;
+
+	kvm_ops_hv.owner = THIS_MODULE;
+	kvmppc_hv_ops = &kvm_ops_hv;
+
+	r = kvmppc_mmu_hv_init();
 	return r;
 }
 
-static void kvmppc_book3s_hv_exit(void)
+static void kvmppc_book3s_exit_hv(void)
 {
-	kvm_exit();
+	kvmppc_hv_ops = NULL;
 }
 
-module_init(kvmppc_book3s_hv_init);
-module_exit(kvmppc_book3s_hv_exit);
+module_init(kvmppc_book3s_init_hv);
+module_exit(kvmppc_book3s_exit_hv);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_MISCDEV(KVM_MINOR);
+MODULE_ALIAS("devname:kvm");