[PATCH v2 0/12] Hypervisor-mode KVM on POWER7

[PATCH v2 0/12] Hypervisor-mode KVM on POWER7

[Paul Mackerras]

The following series of patches enable KVM to exploit the hardware
hypervisor mode on 64-bit Power ISA Book3S machines.  At present only
POWER7 is supported, but it would be easy to add other processors.

Running the KVM host in hypervisor mode means that the guest can use
both supervisor mode and user mode.  That means that the guest can
execute supervisor-privilege instructions and access supervisor-
privilege registers.  In addition the hardware directs most exceptions
to the guest.  Thus we don't need to emulate any instructions in the
host.  Generally, the only times we need to exit the guest are when it
does a hypercall or when an external interrupt or host timer
(decrementer) interrupt occurs.

The focus of this KVM implementation is to run guests that use the
PAPR (Power Architecture Platform Requirements) paravirtualization
interface, which is the interface supplied by PowerVM on IBM pSeries
machines.  Currently the "pseries" machine type in qemu is only
supported by book3s_hv KVM, and book3s_hv KVM only supports the
"pseries" machine type.  That will hopefully change in future.

These patches are against Linus' v3.0-rc1 tree.

Paul.

[PATCH v2 01/12] kvm/powerpc: Move fields between struct kvm_vcpu_arch and kvmppc_vcpu_book3s

[Paul Mackerras]

This moves the slb field, which represents the state of the emulated
SLB, from the kvmppc_vcpu_book3s struct to the kvm_vcpu_arch, and the
hpte_hash_[v]pte[_long] fields from kvm_vcpu_arch to kvmppc_vcpu_book3s.
This is in accord with the principle that the kvm_vcpu_arch struct
represents the state of the emulated CPU, and the kvmppc_vcpu_book3s
struct holds the auxiliary data structures used in the emulation.

Signed-off-by: Paul Mackerras <paulus@samba.org>
---
 arch/powerpc/include/asm/kvm_book3s.h |   35 +++++++++-------
 arch/powerpc/include/asm/kvm_host.h   |   34 +++++++---------
 arch/powerpc/kvm/book3s.c             |    9 ++--
 arch/powerpc/kvm/book3s_64_mmu.c      |   54 +++++++++++-------------
 arch/powerpc/kvm/book3s_mmu_hpte.c    |   71 +++++++++++++++++++-------------
 arch/powerpc/kvm/trace.h              |    2 +-
 6 files changed, 107 insertions(+), 98 deletions(-)

diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index d62e703..e1e8d43 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -24,20 +24,6 @@
 #include <linux/kvm_host.h>
 #include <asm/kvm_book3s_asm.h>
 
-struct kvmppc_slb {
-	u64 esid;
-	u64 vsid;
-	u64 orige;
-	u64 origv;
-	bool valid	: 1;
-	bool Ks		: 1;
-	bool Kp		: 1;
-	bool nx		: 1;
-	bool large	: 1;	/* PTEs are 16MB */
-	bool tb		: 1;	/* 1TB segment */
-	bool class	: 1;
-};
-
 struct kvmppc_bat {
 	u64 raw;
 	u32 bepi;
@@ -67,11 +53,22 @@ struct kvmppc_sid_map {
 #define VSID_POOL_SIZE	(SID_CONTEXTS * 16)
 #endif
 
+struct hpte_cache {
+	struct hlist_node list_pte;
+	struct hlist_node list_pte_long;
+	struct hlist_node list_vpte;
+	struct hlist_node list_vpte_long;
+	struct rcu_head rcu_head;
+	u64 host_va;
+	u64 pfn;
+	ulong slot;
+	struct kvmppc_pte pte;
+};
+
 struct kvmppc_vcpu_book3s {
 	struct kvm_vcpu vcpu;
 	struct kvmppc_book3s_shadow_vcpu *shadow_vcpu;
 	struct kvmppc_sid_map sid_map[SID_MAP_NUM];
-	struct kvmppc_slb slb[64];
 	struct {
 		u64 esid;
 		u64 vsid;
@@ -81,7 +78,6 @@ struct kvmppc_vcpu_book3s {
 	struct kvmppc_bat dbat[8];
 	u64 hid[6];
 	u64 gqr[8];
-	int slb_nr;
 	u64 sdr1;
 	u64 hior;
 	u64 msr_mask;
@@ -94,6 +90,13 @@ struct kvmppc_vcpu_book3s {
 #endif
 	int context_id[SID_CONTEXTS];
 	ulong prog_flags; /* flags to inject when giving a 700 trap */
+
+	struct hlist_head hpte_hash_pte[HPTEG_HASH_NUM_PTE];
+	struct hlist_head hpte_hash_pte_long[HPTEG_HASH_NUM_PTE_LONG];
+	struct hlist_head hpte_hash_vpte[HPTEG_HASH_NUM_VPTE];
+	struct hlist_head hpte_hash_vpte_long[HPTEG_HASH_NUM_VPTE_LONG];
+	int hpte_cache_count;
+	spinlock_t mmu_lock;
 };
 
 #define CONTEXT_HOST		0
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 186f150..8bb47e0 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -163,16 +163,18 @@ struct kvmppc_mmu {
 	bool (*is_dcbz32)(struct kvm_vcpu *vcpu);
 };
 
-struct hpte_cache {
-	struct hlist_node list_pte;
-	struct hlist_node list_pte_long;
-	struct hlist_node list_vpte;
-	struct hlist_node list_vpte_long;
-	struct rcu_head rcu_head;
-	u64 host_va;
-	u64 pfn;
-	ulong slot;
-	struct kvmppc_pte pte;
+struct kvmppc_slb {
+	u64 esid;
+	u64 vsid;
+	u64 orige;
+	u64 origv;
+	bool valid	: 1;
+	bool Ks		: 1;
+	bool Kp		: 1;
+	bool nx		: 1;
+	bool large	: 1;	/* PTEs are 16MB */
+	bool tb		: 1;	/* 1TB segment */
+	bool class	: 1;
 };
 
 struct kvm_vcpu_arch {
@@ -187,6 +189,9 @@ struct kvm_vcpu_arch {
 	ulong highmem_handler;
 	ulong rmcall;
 	ulong host_paca_phys;
+	struct kvmppc_slb slb[64];
+	int slb_max;		/* # valid entries in slb[] */
+	int slb_nr;		/* total number of entries in SLB */
 	struct kvmppc_mmu mmu;
 #endif
 
@@ -298,15 +303,6 @@ struct kvm_vcpu_arch {
 	struct kvm_vcpu_arch_shared *shared;
 	unsigned long magic_page_pa; /* phys addr to map the magic page to */
 	unsigned long magic_page_ea; /* effect. addr to map the magic page to */
-
-#ifdef CONFIG_PPC_BOOK3S
-	struct hlist_head hpte_hash_pte[HPTEG_HASH_NUM_PTE];
-	struct hlist_head hpte_hash_pte_long[HPTEG_HASH_NUM_PTE_LONG];
-	struct hlist_head hpte_hash_vpte[HPTEG_HASH_NUM_VPTE];
-	struct hlist_head hpte_hash_vpte_long[HPTEG_HASH_NUM_VPTE_LONG];
-	int hpte_cache_count;
-	spinlock_t mmu_lock;
-#endif
 };
 
 #endif /* __POWERPC_KVM_HOST_H__ */
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 0f95b5c..0c3820e 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -17,7 +17,6 @@
 #include <linux/kvm_host.h>
 #include <linux/err.h>
 #include <linux/slab.h>
-#include "trace.h"
 
 #include <asm/reg.h>
 #include <asm/cputable.h>
@@ -33,6 +32,8 @@
 #include <linux/vmalloc.h>
 #include <linux/highmem.h>
 
+#include "trace.h"
+
 #define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
 
 /* #define EXIT_DEBUG */
@@ -1190,8 +1191,8 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 	sregs->u.s.sdr1 = to_book3s(vcpu)->sdr1;
 	if (vcpu->arch.hflags & BOOK3S_HFLAG_SLB) {
 		for (i = 0; i < 64; i++) {
-			sregs->u.s.ppc64.slb[i].slbe = vcpu3s->slb[i].orige | i;
-			sregs->u.s.ppc64.slb[i].slbv = vcpu3s->slb[i].origv;
+			sregs->u.s.ppc64.slb[i].slbe = vcpu->arch.slb[i].orige | i;
+			sregs->u.s.ppc64.slb[i].slbv = vcpu->arch.slb[i].origv;
 		}
 	} else {
 		for (i = 0; i < 16; i++)
@@ -1339,7 +1340,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 	vcpu->arch.pvr = 0x84202;
 #endif
 	kvmppc_set_pvr(vcpu, vcpu->arch.pvr);
-	vcpu_book3s->slb_nr = 64;
+	vcpu->arch.slb_nr = 64;
 
 	/* remember where some real-mode handlers are */
 	vcpu->arch.trampoline_lowmem = kvmppc_trampoline_lowmem;
diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c
index d7889ef..c6d3e19 100644
--- a/arch/powerpc/kvm/book3s_64_mmu.c
+++ b/arch/powerpc/kvm/book3s_64_mmu.c
@@ -41,36 +41,36 @@ static void kvmppc_mmu_book3s_64_reset_msr(struct kvm_vcpu *vcpu)
 }
 
 static struct kvmppc_slb *kvmppc_mmu_book3s_64_find_slbe(
-				struct kvmppc_vcpu_book3s *vcpu_book3s,
+				struct kvm_vcpu *vcpu,
 				gva_t eaddr)
 {
 	int i;
 	u64 esid = GET_ESID(eaddr);
 	u64 esid_1t = GET_ESID_1T(eaddr);
 
-	for (i = 0; i < vcpu_book3s->slb_nr; i++) {
+	for (i = 0; i < vcpu->arch.slb_nr; i++) {
 		u64 cmp_esid = esid;
 
-		if (!vcpu_book3s->slb[i].valid)
+		if (!vcpu->arch.slb[i].valid)
 			continue;
 
-		if (vcpu_book3s->slb[i].tb)
+		if (vcpu->arch.slb[i].tb)
 			cmp_esid = esid_1t;
 
-		if (vcpu_book3s->slb[i].esid == cmp_esid)
-			return &vcpu_book3s->slb[i];
+		if (vcpu->arch.slb[i].esid == cmp_esid)
+			return &vcpu->arch.slb[i];
 	}
 
 	dprintk("KVM: No SLB entry found for 0x%lx [%llx | %llx]\n",
 		eaddr, esid, esid_1t);
-	for (i = 0; i < vcpu_book3s->slb_nr; i++) {
-	    if (vcpu_book3s->slb[i].vsid)
+	for (i = 0; i < vcpu->arch.slb_nr; i++) {
+	    if (vcpu->arch.slb[i].vsid)
 		dprintk("  %d: %c%c%c %llx %llx\n", i,
-			vcpu_book3s->slb[i].valid ? 'v' : ' ',
-			vcpu_book3s->slb[i].large ? 'l' : ' ',
-			vcpu_book3s->slb[i].tb    ? 't' : ' ',
-			vcpu_book3s->slb[i].esid,
-			vcpu_book3s->slb[i].vsid);
+			vcpu->arch.slb[i].valid ? 'v' : ' ',
+			vcpu->arch.slb[i].large ? 'l' : ' ',
+			vcpu->arch.slb[i].tb    ? 't' : ' ',
+			vcpu->arch.slb[i].esid,
+			vcpu->arch.slb[i].vsid);
 	}
 
 	return NULL;
@@ -81,7 +81,7 @@ static u64 kvmppc_mmu_book3s_64_ea_to_vp(struct kvm_vcpu *vcpu, gva_t eaddr,
 {
 	struct kvmppc_slb *slb;
 
-	slb = kvmppc_mmu_book3s_64_find_slbe(to_book3s(vcpu), eaddr);
+	slb = kvmppc_mmu_book3s_64_find_slbe(vcpu, eaddr);
 	if (!slb)
 		return 0;
 
@@ -180,7 +180,7 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 		return 0;
 	}
 
-	slbe = kvmppc_mmu_book3s_64_find_slbe(vcpu_book3s, eaddr);
+	slbe = kvmppc_mmu_book3s_64_find_slbe(vcpu, eaddr);
 	if (!slbe)
 		goto no_seg_found;
 
@@ -320,10 +320,10 @@ static void kvmppc_mmu_book3s_64_slbmte(struct kvm_vcpu *vcpu, u64 rs, u64 rb)
 	esid_1t = GET_ESID_1T(rb);
 	slb_nr = rb & 0xfff;
 
-	if (slb_nr > vcpu_book3s->slb_nr)
+	if (slb_nr > vcpu->arch.slb_nr)
 		return;
 
-	slbe = &vcpu_book3s->slb[slb_nr];
+	slbe = &vcpu->arch.slb[slb_nr];
 
 	slbe->large = (rs & SLB_VSID_L) ? 1 : 0;
 	slbe->tb    = (rs & SLB_VSID_B_1T) ? 1 : 0;
@@ -344,38 +344,35 @@ static void kvmppc_mmu_book3s_64_slbmte(struct kvm_vcpu *vcpu, u64 rs, u64 rb)
 
 static u64 kvmppc_mmu_book3s_64_slbmfee(struct kvm_vcpu *vcpu, u64 slb_nr)
 {
-	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
 	struct kvmppc_slb *slbe;
 
-	if (slb_nr > vcpu_book3s->slb_nr)
+	if (slb_nr > vcpu->arch.slb_nr)
 		return 0;
 
-	slbe = &vcpu_book3s->slb[slb_nr];
+	slbe = &vcpu->arch.slb[slb_nr];
 
 	return slbe->orige;
 }
 
 static u64 kvmppc_mmu_book3s_64_slbmfev(struct kvm_vcpu *vcpu, u64 slb_nr)
 {
-	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
 	struct kvmppc_slb *slbe;
 
-	if (slb_nr > vcpu_book3s->slb_nr)
+	if (slb_nr > vcpu->arch.slb_nr)
 		return 0;
 
-	slbe = &vcpu_book3s->slb[slb_nr];
+	slbe = &vcpu->arch.slb[slb_nr];
 
 	return slbe->origv;
 }
 
 static void kvmppc_mmu_book3s_64_slbie(struct kvm_vcpu *vcpu, u64 ea)
 {
-	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
 	struct kvmppc_slb *slbe;
 
 	dprintk("KVM MMU: slbie(0x%llx)\n", ea);
 
-	slbe = kvmppc_mmu_book3s_64_find_slbe(vcpu_book3s, ea);
+	slbe = kvmppc_mmu_book3s_64_find_slbe(vcpu, ea);
 
 	if (!slbe)
 		return;
@@ -389,13 +386,12 @@ static void kvmppc_mmu_book3s_64_slbie(struct kvm_vcpu *vcpu, u64 ea)
 
 static void kvmppc_mmu_book3s_64_slbia(struct kvm_vcpu *vcpu)
 {
-	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
 	int i;
 
 	dprintk("KVM MMU: slbia()\n");
 
-	for (i = 1; i < vcpu_book3s->slb_nr; i++)
-		vcpu_book3s->slb[i].valid = false;
+	for (i = 1; i < vcpu->arch.slb_nr; i++)
+		vcpu->arch.slb[i].valid = false;
 
 	if (vcpu->arch.shared->msr & MSR_IR) {
 		kvmppc_mmu_flush_segments(vcpu);
@@ -464,7 +460,7 @@ static int kvmppc_mmu_book3s_64_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
 	ulong mp_ea = vcpu->arch.magic_page_ea;
 
 	if (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {
-		slb = kvmppc_mmu_book3s_64_find_slbe(to_book3s(vcpu), ea);
+		slb = kvmppc_mmu_book3s_64_find_slbe(vcpu, ea);
 		if (slb)
 			gvsid = slb->vsid;
 	}
diff --git a/arch/powerpc/kvm/book3s_mmu_hpte.c b/arch/powerpc/kvm/book3s_mmu_hpte.c
index 79751d8..41cb001 100644
--- a/arch/powerpc/kvm/book3s_mmu_hpte.c
+++ b/arch/powerpc/kvm/book3s_mmu_hpte.c
@@ -21,7 +21,6 @@
 #include <linux/kvm_host.h>
 #include <linux/hash.h>
 #include <linux/slab.h>
-#include "trace.h"
 
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
@@ -29,6 +28,8 @@
 #include <asm/mmu_context.h>
 #include <asm/hw_irq.h>
 
+#include "trace.h"
+
 #define PTE_SIZE	12
 
 static struct kmem_cache *hpte_cache;
@@ -58,30 +59,31 @@ static inline u64 kvmppc_mmu_hash_vpte_long(u64 vpage)
 void kvmppc_mmu_hpte_cache_map(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 {
 	u64 index;
+	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
 
 	trace_kvm_book3s_mmu_map(pte);
 
-	spin_lock(&vcpu->arch.mmu_lock);
+	spin_lock(&vcpu3s->mmu_lock);
 
 	/* Add to ePTE list */
 	index = kvmppc_mmu_hash_pte(pte->pte.eaddr);
-	hlist_add_head_rcu(&pte->list_pte, &vcpu->arch.hpte_hash_pte[index]);
+	hlist_add_head_rcu(&pte->list_pte, &vcpu3s->hpte_hash_pte[index]);
 
 	/* Add to ePTE_long list */
 	index = kvmppc_mmu_hash_pte_long(pte->pte.eaddr);
 	hlist_add_head_rcu(&pte->list_pte_long,
-			   &vcpu->arch.hpte_hash_pte_long[index]);
+			   &vcpu3s->hpte_hash_pte_long[index]);
 
 	/* Add to vPTE list */
 	index = kvmppc_mmu_hash_vpte(pte->pte.vpage);
-	hlist_add_head_rcu(&pte->list_vpte, &vcpu->arch.hpte_hash_vpte[index]);
+	hlist_add_head_rcu(&pte->list_vpte, &vcpu3s->hpte_hash_vpte[index]);
 
 	/* Add to vPTE_long list */
 	index = kvmppc_mmu_hash_vpte_long(pte->pte.vpage);
 	hlist_add_head_rcu(&pte->list_vpte_long,
-			   &vcpu->arch.hpte_hash_vpte_long[index]);
+			   &vcpu3s->hpte_hash_vpte_long[index]);
 
-	spin_unlock(&vcpu->arch.mmu_lock);
+	spin_unlock(&vcpu3s->mmu_lock);
 }
 
 static void free_pte_rcu(struct rcu_head *head)
@@ -92,16 +94,18 @@ static void free_pte_rcu(struct rcu_head *head)
 
 static void invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 {
+	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
+
 	trace_kvm_book3s_mmu_invalidate(pte);
 
 	/* Different for 32 and 64 bit */
 	kvmppc_mmu_invalidate_pte(vcpu, pte);
 
-	spin_lock(&vcpu->arch.mmu_lock);
+	spin_lock(&vcpu3s->mmu_lock);
 
 	/* pte already invalidated in between? */
 	if (hlist_unhashed(&pte->list_pte)) {
-		spin_unlock(&vcpu->arch.mmu_lock);
+		spin_unlock(&vcpu3s->mmu_lock);
 		return;
 	}
 
@@ -115,14 +119,15 @@ static void invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 	else
 		kvm_release_pfn_clean(pte->pfn);
 
-	spin_unlock(&vcpu->arch.mmu_lock);
+	spin_unlock(&vcpu3s->mmu_lock);
 
-	vcpu->arch.hpte_cache_count--;
+	vcpu3s->hpte_cache_count--;
 	call_rcu(&pte->rcu_head, free_pte_rcu);
 }
 
 static void kvmppc_mmu_pte_flush_all(struct kvm_vcpu *vcpu)
 {
+	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
 	struct hpte_cache *pte;
 	struct hlist_node *node;
 	int i;
@@ -130,7 +135,7 @@ static void kvmppc_mmu_pte_flush_all(struct kvm_vcpu *vcpu)
 	rcu_read_lock();
 
 	for (i = 0; i < HPTEG_HASH_NUM_VPTE_LONG; i++) {
-		struct hlist_head *list = &vcpu->arch.hpte_hash_vpte_long[i];
+		struct hlist_head *list = &vcpu3s->hpte_hash_vpte_long[i];
 
 		hlist_for_each_entry_rcu(pte, node, list, list_vpte_long)
 			invalidate_pte(vcpu, pte);
@@ -141,12 +146,13 @@ static void kvmppc_mmu_pte_flush_all(struct kvm_vcpu *vcpu)
 
 static void kvmppc_mmu_pte_flush_page(struct kvm_vcpu *vcpu, ulong guest_ea)
 {
+	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
 	struct hlist_head *list;
 	struct hlist_node *node;
 	struct hpte_cache *pte;
 
 	/* Find the list of entries in the map */
-	list = &vcpu->arch.hpte_hash_pte[kvmppc_mmu_hash_pte(guest_ea)];
+	list = &vcpu3s->hpte_hash_pte[kvmppc_mmu_hash_pte(guest_ea)];
 
 	rcu_read_lock();
 
@@ -160,12 +166,13 @@ static void kvmppc_mmu_pte_flush_page(struct kvm_vcpu *vcpu, ulong guest_ea)
 
 static void kvmppc_mmu_pte_flush_long(struct kvm_vcpu *vcpu, ulong guest_ea)
 {
+	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
 	struct hlist_head *list;
 	struct hlist_node *node;
 	struct hpte_cache *pte;
 
 	/* Find the list of entries in the map */
-	list = &vcpu->arch.hpte_hash_pte_long[
+	list = &vcpu3s->hpte_hash_pte_long[
 			kvmppc_mmu_hash_pte_long(guest_ea)];
 
 	rcu_read_lock();
@@ -203,12 +210,13 @@ void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, ulong guest_ea, ulong ea_mask)
 /* Flush with mask 0xfffffffff */
 static void kvmppc_mmu_pte_vflush_short(struct kvm_vcpu *vcpu, u64 guest_vp)
 {
+	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
 	struct hlist_head *list;
 	struct hlist_node *node;
 	struct hpte_cache *pte;
 	u64 vp_mask = 0xfffffffffULL;
 
-	list = &vcpu->arch.hpte_hash_vpte[kvmppc_mmu_hash_vpte(guest_vp)];
+	list = &vcpu3s->hpte_hash_vpte[kvmppc_mmu_hash_vpte(guest_vp)];
 
 	rcu_read_lock();
 
@@ -223,12 +231,13 @@ static void kvmppc_mmu_pte_vflush_short(struct kvm_vcpu *vcpu, u64 guest_vp)
 /* Flush with mask 0xffffff000 */
 static void kvmppc_mmu_pte_vflush_long(struct kvm_vcpu *vcpu, u64 guest_vp)
 {
+	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
 	struct hlist_head *list;
 	struct hlist_node *node;
 	struct hpte_cache *pte;
 	u64 vp_mask = 0xffffff000ULL;
 
-	list = &vcpu->arch.hpte_hash_vpte_long[
+	list = &vcpu3s->hpte_hash_vpte_long[
 		kvmppc_mmu_hash_vpte_long(guest_vp)];
 
 	rcu_read_lock();
@@ -261,6 +270,7 @@ void kvmppc_mmu_pte_vflush(struct kvm_vcpu *vcpu, u64 guest_vp, u64 vp_mask)
 
 void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, ulong pa_start, ulong pa_end)
 {
+	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
 	struct hlist_node *node;
 	struct hpte_cache *pte;
 	int i;
@@ -270,7 +280,7 @@ void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, ulong pa_start, ulong pa_end)
 	rcu_read_lock();
 
 	for (i = 0; i < HPTEG_HASH_NUM_VPTE_LONG; i++) {
-		struct hlist_head *list = &vcpu->arch.hpte_hash_vpte_long[i];
+		struct hlist_head *list = &vcpu3s->hpte_hash_vpte_long[i];
 
 		hlist_for_each_entry_rcu(pte, node, list, list_vpte_long)
 			if ((pte->pte.raddr >= pa_start) &&
@@ -283,12 +293,13 @@ void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, ulong pa_start, ulong pa_end)
 
 struct hpte_cache *kvmppc_mmu_hpte_cache_next(struct kvm_vcpu *vcpu)
 {
+	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
 	struct hpte_cache *pte;
 
 	pte = kmem_cache_zalloc(hpte_cache, GFP_KERNEL);
-	vcpu->arch.hpte_cache_count++;
+	vcpu3s->hpte_cache_count++;
 
-	if (vcpu->arch.hpte_cache_count == HPTEG_CACHE_NUM)
+	if (vcpu3s->hpte_cache_count == HPTEG_CACHE_NUM)
 		kvmppc_mmu_pte_flush_all(vcpu);
 
 	return pte;
@@ -309,17 +320,19 @@ static void kvmppc_mmu_hpte_init_hash(struct hlist_head *hash_list, int len)
 
 int kvmppc_mmu_hpte_init(struct kvm_vcpu *vcpu)
 {
+	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
+
 	/* init hpte lookup hashes */
-	kvmppc_mmu_hpte_init_hash(vcpu->arch.hpte_hash_pte,
-				  ARRAY_SIZE(vcpu->arch.hpte_hash_pte));
-	kvmppc_mmu_hpte_init_hash(vcpu->arch.hpte_hash_pte_long,
-				  ARRAY_SIZE(vcpu->arch.hpte_hash_pte_long));
-	kvmppc_mmu_hpte_init_hash(vcpu->arch.hpte_hash_vpte,
-				  ARRAY_SIZE(vcpu->arch.hpte_hash_vpte));
-	kvmppc_mmu_hpte_init_hash(vcpu->arch.hpte_hash_vpte_long,
-				  ARRAY_SIZE(vcpu->arch.hpte_hash_vpte_long));
-
-	spin_lock_init(&vcpu->arch.mmu_lock);
+	kvmppc_mmu_hpte_init_hash(vcpu3s->hpte_hash_pte,
+				  ARRAY_SIZE(vcpu3s->hpte_hash_pte));
+	kvmppc_mmu_hpte_init_hash(vcpu3s->hpte_hash_pte_long,
+				  ARRAY_SIZE(vcpu3s->hpte_hash_pte_long));
+	kvmppc_mmu_hpte_init_hash(vcpu3s->hpte_hash_vpte,
+				  ARRAY_SIZE(vcpu3s->hpte_hash_vpte));
+	kvmppc_mmu_hpte_init_hash(vcpu3s->hpte_hash_vpte_long,
+				  ARRAY_SIZE(vcpu3s->hpte_hash_vpte_long));
+
+	spin_lock_init(&vcpu3s->mmu_lock);
 
 	return 0;
 }
diff --git a/arch/powerpc/kvm/trace.h b/arch/powerpc/kvm/trace.h
index 3aca1b0..d62a14b 100644
--- a/arch/powerpc/kvm/trace.h
+++ b/arch/powerpc/kvm/trace.h
@@ -252,7 +252,7 @@ TRACE_EVENT(kvm_book3s_mmu_flush,
 	),
 
 	TP_fast_assign(
-		__entry->count		= vcpu->arch.hpte_cache_count;
+		__entry->count		= to_book3s(vcpu)->hpte_cache_count;
 		__entry->p1		= p1;
 		__entry->p2		= p2;
 		__entry->type		= type;
-- 
1.7.5.3

[PATCH v2 02/12] kvm/powerpc: Split out code from book3s.c into book3s_pr.c

[Paul Mackerras]

In preparation for adding code to enable KVM to use hypervisor mode
on 64-bit Book 3S processors, this splits book3s.c into two files,
book3s.c and book3s_pr.c, where book3s_pr.c contains the code that is
specific to running the guest in problem state (user mode) and book3s.c
contains code which should apply to all Book 3S processors.

In doing this, we abstract some details, namely the interrupt offset,
updating the interrupt pending flag, and detecting if the guest is
in a critical section.  These are all things that will be different
when we use hypervisor mode.

Signed-off-by: Paul Mackerras <paulus@samba.org>
---
 arch/powerpc/include/asm/kvm_book3s.h |   35 ++
 arch/powerpc/kvm/Makefile             |    2 +
 arch/powerpc/kvm/book3s.c             |  995 +--------------------------------
 arch/powerpc/kvm/book3s_pr.c          | 1009 +++++++++++++++++++++++++++++++++
 4 files changed, 1053 insertions(+), 988 deletions(-)
 create mode 100644 arch/powerpc/kvm/book3s_pr.c

diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index e1e8d43..fe20c74 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -113,6 +113,7 @@ extern void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, ulong ea, ulong ea_mask)
 extern void kvmppc_mmu_pte_vflush(struct kvm_vcpu *vcpu, u64 vp, u64 vp_mask);
 extern void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, ulong pa_start, ulong pa_end);
 extern void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 new_msr);
+extern void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr);
 extern void kvmppc_mmu_book3s_64_init(struct kvm_vcpu *vcpu);
 extern void kvmppc_mmu_book3s_32_init(struct kvm_vcpu *vcpu);
 extern int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte);
@@ -150,6 +151,20 @@ static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu)
 	return container_of(vcpu, struct kvmppc_vcpu_book3s, vcpu);
 }
 
+static inline unsigned long kvmppc_interrupt_offset(struct kvm_vcpu *vcpu)
+{
+	return to_book3s(vcpu)->hior;
+}
+
+static inline void kvmppc_update_int_pending(struct kvm_vcpu *vcpu,
+			unsigned long pending_now, unsigned long old_pending)
+{
+	if (pending_now)
+		vcpu->arch.shared->int_pending = 1;
+	else if (old_pending)
+		vcpu->arch.shared->int_pending = 0;
+}
+
 static inline ulong dsisr(void)
 {
 	ulong r;
@@ -247,6 +262,26 @@ static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu)
 	return to_svcpu(vcpu)->fault_dar;
 }
 
+static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu)
+{
+	ulong crit_raw = vcpu->arch.shared->critical;
+	ulong crit_r1 = kvmppc_get_gpr(vcpu, 1);
+	bool crit;
+
+	/* Truncate crit indicators in 32 bit mode */
+	if (!(vcpu->arch.shared->msr & MSR_SF)) {
+		crit_raw &= 0xffffffff;
+		crit_r1 &= 0xffffffff;
+	}
+
+	/* Critical section when crit == r1 */
+	crit = (crit_raw == crit_r1);
+	/* ... and we're in supervisor mode */
+	crit = crit && !(vcpu->arch.shared->msr & MSR_PR);
+
+	return crit;
+}
+
 /* Magic register values loaded into r3 and r4 before the 'sc' assembly
  * instruction for the OSI hypercalls */
 #define OSI_SC_MAGIC_R3			0x113724FA
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index 4d68638..bf9854f 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -43,6 +43,7 @@ kvm-book3s_64-objs := \
 	fpu.o \
 	book3s_paired_singles.o \
 	book3s.o \
+	book3s_pr.o \
 	book3s_emulate.o \
 	book3s_interrupts.o \
 	book3s_mmu_hpte.o \
@@ -56,6 +57,7 @@ kvm-book3s_32-objs := \
 	fpu.o \
 	book3s_paired_singles.o \
 	book3s.o \
+	book3s_pr.o \
 	book3s_emulate.o \
 	book3s_interrupts.o \
 	book3s_mmu_hpte.o \
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 0c3820e..af63de3 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -37,17 +37,6 @@
 #define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
 
 /* #define EXIT_DEBUG */
-/* #define DEBUG_EXT */
-
-static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
-			     ulong msr);
-
-/* Some compatibility defines */
-#ifdef CONFIG_PPC_BOOK3S_32
-#define MSR_USER32 MSR_USER
-#define MSR_USER64 MSR_USER
-#define HW_PAGE_SIZE PAGE_SIZE
-#endif
 
 struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "exits",       VCPU_STAT(sum_exits) },
@@ -78,100 +67,11 @@ void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu)
 {
 }
 
-void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
-{
-#ifdef CONFIG_PPC_BOOK3S_64
-	memcpy(to_svcpu(vcpu)->slb, to_book3s(vcpu)->slb_shadow, sizeof(to_svcpu(vcpu)->slb));
-	memcpy(&get_paca()->shadow_vcpu, to_book3s(vcpu)->shadow_vcpu,
-	       sizeof(get_paca()->shadow_vcpu));
-	to_svcpu(vcpu)->slb_max = to_book3s(vcpu)->slb_shadow_max;
-#endif
-
-#ifdef CONFIG_PPC_BOOK3S_32
-	current->thread.kvm_shadow_vcpu = to_book3s(vcpu)->shadow_vcpu;
-#endif
-}
-
-void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
-{
-#ifdef CONFIG_PPC_BOOK3S_64
-	memcpy(to_book3s(vcpu)->slb_shadow, to_svcpu(vcpu)->slb, sizeof(to_svcpu(vcpu)->slb));
-	memcpy(to_book3s(vcpu)->shadow_vcpu, &get_paca()->shadow_vcpu,
-	       sizeof(get_paca()->shadow_vcpu));
-	to_book3s(vcpu)->slb_shadow_max = to_svcpu(vcpu)->slb_max;
-#endif
-
-	kvmppc_giveup_ext(vcpu, MSR_FP);
-	kvmppc_giveup_ext(vcpu, MSR_VEC);
-	kvmppc_giveup_ext(vcpu, MSR_VSX);
-}
-
-static void kvmppc_recalc_shadow_msr(struct kvm_vcpu *vcpu)
-{
-	ulong smsr = vcpu->arch.shared->msr;
-
-	/* Guest MSR values */
-	smsr &= MSR_FE0 | MSR_FE1 | MSR_SF | MSR_SE | MSR_BE | MSR_DE;
-	/* Process MSR values */
-	smsr |= MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_PR | MSR_EE;
-	/* External providers the guest reserved */
-	smsr |= (vcpu->arch.shared->msr & vcpu->arch.guest_owned_ext);
-	/* 64-bit Process MSR values */
-#ifdef CONFIG_PPC_BOOK3S_64
-	smsr |= MSR_ISF | MSR_HV;
-#endif
-	vcpu->arch.shadow_msr = smsr;
-}
-
-void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
-{
-	ulong old_msr = vcpu->arch.shared->msr;
-
-#ifdef EXIT_DEBUG
-	printk(KERN_INFO "KVM: Set MSR to 0x%llx\n", msr);
-#endif
-
-	msr &= to_book3s(vcpu)->msr_mask;
-	vcpu->arch.shared->msr = msr;
-	kvmppc_recalc_shadow_msr(vcpu);
-
-	if (msr & MSR_POW) {
-		if (!vcpu->arch.pending_exceptions) {
-			kvm_vcpu_block(vcpu);
-			vcpu->stat.halt_wakeup++;
-
-			/* Unset POW bit after we woke up */
-			msr &= ~MSR_POW;
-			vcpu->arch.shared->msr = msr;
-		}
-	}
-
-	if ((vcpu->arch.shared->msr & (MSR_PR|MSR_IR|MSR_DR)) !=
-		   (old_msr & (MSR_PR|MSR_IR|MSR_DR))) {
-		kvmppc_mmu_flush_segments(vcpu);
-		kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu));
-
-		/* Preload magic page segment when in kernel mode */
-		if (!(msr & MSR_PR) && vcpu->arch.magic_page_pa) {
-			struct kvm_vcpu_arch *a = &vcpu->arch;
-
-			if (msr & MSR_DR)
-				kvmppc_mmu_map_segment(vcpu, a->magic_page_ea);
-			else
-				kvmppc_mmu_map_segment(vcpu, a->magic_page_pa);
-		}
-	}
-
-	/* Preload FPU if it's enabled */
-	if (vcpu->arch.shared->msr & MSR_FP)
-		kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP);
-}
-
 void kvmppc_inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 flags)
 {
 	vcpu->arch.shared->srr0 = kvmppc_get_pc(vcpu);
 	vcpu->arch.shared->srr1 = vcpu->arch.shared->msr | flags;
-	kvmppc_set_pc(vcpu, to_book3s(vcpu)->hior + vec);
+	kvmppc_set_pc(vcpu, kvmppc_interrupt_offset(vcpu) + vec);
 	vcpu->arch.mmu.reset_msr(vcpu);
 }
 
@@ -205,11 +105,13 @@ static int kvmppc_book3s_vec2irqprio(unsigned int vec)
 static void kvmppc_book3s_dequeue_irqprio(struct kvm_vcpu *vcpu,
 					  unsigned int vec)
 {
+	unsigned long old_pending = vcpu->arch.pending_exceptions;
+
 	clear_bit(kvmppc_book3s_vec2irqprio(vec),
 		  &vcpu->arch.pending_exceptions);
 
-	if (!vcpu->arch.pending_exceptions)
-		vcpu->arch.shared->int_pending = 0;
+	kvmppc_update_int_pending(vcpu, vcpu->arch.pending_exceptions,
+				  old_pending);
 }
 
 void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec)
@@ -268,20 +170,7 @@ int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu, unsigned int priority)
 	int deliver = 1;
 	int vec = 0;
 	ulong flags = 0ULL;
-	ulong crit_raw = vcpu->arch.shared->critical;
-	ulong crit_r1 = kvmppc_get_gpr(vcpu, 1);
-	bool crit;
-
-	/* Truncate crit indicators in 32 bit mode */
-	if (!(vcpu->arch.shared->msr & MSR_SF)) {
-		crit_raw &= 0xffffffff;
-		crit_r1 &= 0xffffffff;
-	}
-
-	/* Critical section when crit == r1 */
-	crit = (crit_raw == crit_r1);
-	/* ... and we're in supervisor mode */
-	crit = crit && !(vcpu->arch.shared->msr & MSR_PR);
+	bool crit = kvmppc_critical_section(vcpu);
 
 	switch (priority) {
 	case BOOK3S_IRQPRIO_DECREMENTER:
@@ -393,64 +282,7 @@ void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu)
 	}
 
 	/* Tell the guest about our interrupt status */
-	if (*pending)
-		vcpu->arch.shared->int_pending = 1;
-	else if (old_pending)
-		vcpu->arch.shared->int_pending = 0;
-}
-
-void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr)
-{
-	u32 host_pvr;
-
-	vcpu->arch.hflags &= ~BOOK3S_HFLAG_SLB;
-	vcpu->arch.pvr = pvr;
-#ifdef CONFIG_PPC_BOOK3S_64
-	if ((pvr >= 0x330000) && (pvr < 0x70330000)) {
-		kvmppc_mmu_book3s_64_init(vcpu);
-		to_book3s(vcpu)->hior = 0xfff00000;
-		to_book3s(vcpu)->msr_mask = 0xffffffffffffffffULL;
-	} else
-#endif
-	{
-		kvmppc_mmu_book3s_32_init(vcpu);
-		to_book3s(vcpu)->hior = 0;
-		to_book3s(vcpu)->msr_mask = 0xffffffffULL;
-	}
-
-	/* If we are in hypervisor level on 970, we can tell the CPU to
-	 * treat DCBZ as 32 bytes store */
-	vcpu->arch.hflags &= ~BOOK3S_HFLAG_DCBZ32;
-	if (vcpu->arch.mmu.is_dcbz32(vcpu) && (mfmsr() & MSR_HV) &&
-	    !strcmp(cur_cpu_spec->platform, "ppc970"))
-		vcpu->arch.hflags |= BOOK3S_HFLAG_DCBZ32;
-
-	/* Cell performs badly if MSR_FEx are set. So let's hope nobody
-	   really needs them in a VM on Cell and force disable them. */
-	if (!strcmp(cur_cpu_spec->platform, "ppc-cell-be"))
-		to_book3s(vcpu)->msr_mask &= ~(MSR_FE0 | MSR_FE1);
-
-#ifdef CONFIG_PPC_BOOK3S_32
-	/* 32 bit Book3S always has 32 byte dcbz */
-	vcpu->arch.hflags |= BOOK3S_HFLAG_DCBZ32;
-#endif
-
-	/* On some CPUs we can execute paired single operations natively */
-	asm ( "mfpvr %0" : "=r"(host_pvr));
-	switch (host_pvr) {
-	case 0x00080200:	/* lonestar 2.0 */
-	case 0x00088202:	/* lonestar 2.2 */
-	case 0x70000100:	/* gekko 1.0 */
-	case 0x00080100:	/* gekko 2.0 */
-	case 0x00083203:	/* gekko 2.3a */
-	case 0x00083213:	/* gekko 2.3b */
-	case 0x00083204:	/* gekko 2.4 */
-	case 0x00083214:	/* gekko 2.4e (8SE) - retail HW2 */
-	case 0x00087200:	/* broadway */
-		vcpu->arch.hflags |= BOOK3S_HFLAG_NATIVE_PS;
-		/* Enable HID2.PSE - in case we need it later */
-		mtspr(SPRN_HID2_GEKKO, mfspr(SPRN_HID2_GEKKO) | (1 << 29));
-	}
+	kvmppc_update_int_pending(vcpu, *pending, old_pending);
 }
 
 pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn)
@@ -472,44 +304,6 @@ pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn)
 	return gfn_to_pfn(vcpu->kvm, gfn);
 }
 
-/* Book3s_32 CPUs always have 32 bytes cache line size, which Linux assumes. To
- * make Book3s_32 Linux work on Book3s_64, we have to make sure we trap dcbz to
- * emulate 32 bytes dcbz length.
- *
- * The Book3s_64 inventors also realized this case and implemented a special bit
- * in the HID5 register, which is a hypervisor ressource. Thus we can't use it.
- *
- * My approach here is to patch the dcbz instruction on executing pages.
- */
-static void kvmppc_patch_dcbz(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte)
-{
-	struct page *hpage;
-	u64 hpage_offset;
-	u32 *page;
-	int i;
-
-	hpage = gfn_to_page(vcpu->kvm, pte->raddr >> PAGE_SHIFT);
-	if (is_error_page(hpage)) {
-		kvm_release_page_clean(hpage);
-		return;
-	}
-
-	hpage_offset = pte->raddr & ~PAGE_MASK;
-	hpage_offset &= ~0xFFFULL;
-	hpage_offset /= 4;
-
-	get_page(hpage);
-	page = kmap_atomic(hpage, KM_USER0);
-
-	/* patch dcbz into reserved instruction, so we trap */
-	for (i=hpage_offset; i < hpage_offset + (HW_PAGE_SIZE / 4); i++)
-		if ((page[i] & 0xff0007ff) == INS_DCBZ)
-			page[i] &= 0xfffffff7;
-
-	kunmap_atomic(page, KM_USER0);
-	put_page(hpage);
-}
-
 static int kvmppc_xlate(struct kvm_vcpu *vcpu, ulong eaddr, bool data,
 			 struct kvmppc_pte *pte)
 {
@@ -607,519 +401,6 @@ mmio:
 	return EMULATE_DO_MMIO;
 }
 
-static int kvmppc_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn)
-{
-	ulong mp_pa = vcpu->arch.magic_page_pa;
-
-	if (unlikely(mp_pa) &&
-	    unlikely((mp_pa & KVM_PAM) >> PAGE_SHIFT == gfn)) {
-		return 1;
-	}
-
-	return kvm_is_visible_gfn(vcpu->kvm, gfn);
-}
-
-int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
-			    ulong eaddr, int vec)
-{
-	bool data = (vec == BOOK3S_INTERRUPT_DATA_STORAGE);
-	int r = RESUME_GUEST;
-	int relocated;
-	int page_found = 0;
-	struct kvmppc_pte pte;
-	bool is_mmio = false;
-	bool dr = (vcpu->arch.shared->msr & MSR_DR) ? true : false;
-	bool ir = (vcpu->arch.shared->msr & MSR_IR) ? true : false;
-	u64 vsid;
-
-	relocated = data ? dr : ir;
-
-	/* Resolve real address if translation turned on */
-	if (relocated) {
-		page_found = vcpu->arch.mmu.xlate(vcpu, eaddr, &pte, data);
-	} else {
-		pte.may_execute = true;
-		pte.may_read = true;
-		pte.may_write = true;
-		pte.raddr = eaddr & KVM_PAM;
-		pte.eaddr = eaddr;
-		pte.vpage = eaddr >> 12;
-	}
-
-	switch (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {
-	case 0:
-		pte.vpage |= ((u64)VSID_REAL << (SID_SHIFT - 12));
-		break;
-	case MSR_DR:
-	case MSR_IR:
-		vcpu->arch.mmu.esid_to_vsid(vcpu, eaddr >> SID_SHIFT, &vsid);
-
-		if ((vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) == MSR_DR)
-			pte.vpage |= ((u64)VSID_REAL_DR << (SID_SHIFT - 12));
-		else
-			pte.vpage |= ((u64)VSID_REAL_IR << (SID_SHIFT - 12));
-		pte.vpage |= vsid;
-
-		if (vsid == -1)
-			page_found = -EINVAL;
-		break;
-	}
-
-	if (vcpu->arch.mmu.is_dcbz32(vcpu) &&
-	   (!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32))) {
-		/*
-		 * If we do the dcbz hack, we have to NX on every execution,
-		 * so we can patch the executing code. This renders our guest
-		 * NX-less.
-		 */
-		pte.may_execute = !data;
-	}
-
-	if (page_found == -ENOENT) {
-		/* Page not found in guest PTE entries */
-		vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
-		vcpu->arch.shared->dsisr = to_svcpu(vcpu)->fault_dsisr;
-		vcpu->arch.shared->msr |=
-			(to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL);
-		kvmppc_book3s_queue_irqprio(vcpu, vec);
-	} else if (page_found == -EPERM) {
-		/* Storage protection */
-		vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
-		vcpu->arch.shared->dsisr =
-			to_svcpu(vcpu)->fault_dsisr & ~DSISR_NOHPTE;
-		vcpu->arch.shared->dsisr |= DSISR_PROTFAULT;
-		vcpu->arch.shared->msr |=
-			(to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL);
-		kvmppc_book3s_queue_irqprio(vcpu, vec);
-	} else if (page_found == -EINVAL) {
-		/* Page not found in guest SLB */
-		vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
-		kvmppc_book3s_queue_irqprio(vcpu, vec + 0x80);
-	} else if (!is_mmio &&
-		   kvmppc_visible_gfn(vcpu, pte.raddr >> PAGE_SHIFT)) {
-		/* The guest's PTE is not mapped yet. Map on the host */
-		kvmppc_mmu_map_page(vcpu, &pte);
-		if (data)
-			vcpu->stat.sp_storage++;
-		else if (vcpu->arch.mmu.is_dcbz32(vcpu) &&
-			(!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32)))
-			kvmppc_patch_dcbz(vcpu, &pte);
-	} else {
-		/* MMIO */
-		vcpu->stat.mmio_exits++;
-		vcpu->arch.paddr_accessed = pte.raddr;
-		r = kvmppc_emulate_mmio(run, vcpu);
-		if ( r == RESUME_HOST_NV )
-			r = RESUME_HOST;
-	}
-
-	return r;
-}
-
-static inline int get_fpr_index(int i)
-{
-#ifdef CONFIG_VSX
-	i *= 2;
-#endif
-	return i;
-}
-
-/* Give up external provider (FPU, Altivec, VSX) */
-void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr)
-{
-	struct thread_struct *t = &current->thread;
-	u64 *vcpu_fpr = vcpu->arch.fpr;
-#ifdef CONFIG_VSX
-	u64 *vcpu_vsx = vcpu->arch.vsr;
-#endif
-	u64 *thread_fpr = (u64*)t->fpr;
-	int i;
-
-	if (!(vcpu->arch.guest_owned_ext & msr))
-		return;
-
-#ifdef DEBUG_EXT
-	printk(KERN_INFO "Giving up ext 0x%lx\n", msr);
-#endif
-
-	switch (msr) {
-	case MSR_FP:
-		giveup_fpu(current);
-		for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++)
-			vcpu_fpr[i] = thread_fpr[get_fpr_index(i)];
-
-		vcpu->arch.fpscr = t->fpscr.val;
-		break;
-	case MSR_VEC:
-#ifdef CONFIG_ALTIVEC
-		giveup_altivec(current);
-		memcpy(vcpu->arch.vr, t->vr, sizeof(vcpu->arch.vr));
-		vcpu->arch.vscr = t->vscr;
-#endif
-		break;
-	case MSR_VSX:
-#ifdef CONFIG_VSX
-		__giveup_vsx(current);
-		for (i = 0; i < ARRAY_SIZE(vcpu->arch.vsr); i++)
-			vcpu_vsx[i] = thread_fpr[get_fpr_index(i) + 1];
-#endif
-		break;
-	default:
-		BUG();
-	}
-
-	vcpu->arch.guest_owned_ext &= ~msr;
-	current->thread.regs->msr &= ~msr;
-	kvmppc_recalc_shadow_msr(vcpu);
-}
-
-static int kvmppc_read_inst(struct kvm_vcpu *vcpu)
-{
-	ulong srr0 = kvmppc_get_pc(vcpu);
-	u32 last_inst = kvmppc_get_last_inst(vcpu);
-	int ret;
-
-	ret = kvmppc_ld(vcpu, &srr0, sizeof(u32), &last_inst, false);
-	if (ret == -ENOENT) {
-		ulong msr = vcpu->arch.shared->msr;
-
-		msr = kvmppc_set_field(msr, 33, 33, 1);
-		msr = kvmppc_set_field(msr, 34, 36, 0);
-		vcpu->arch.shared->msr = kvmppc_set_field(msr, 42, 47, 0);
-		kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_INST_STORAGE);
-		return EMULATE_AGAIN;
-	}
-
-	return EMULATE_DONE;
-}
-
-static int kvmppc_check_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr)
-{
-
-	/* Need to do paired single emulation? */
-	if (!(vcpu->arch.hflags & BOOK3S_HFLAG_PAIRED_SINGLE))
-		return EMULATE_DONE;
-
-	/* Read out the instruction */
-	if (kvmppc_read_inst(vcpu) == EMULATE_DONE)
-		/* Need to emulate */
-		return EMULATE_FAIL;
-
-	return EMULATE_AGAIN;
-}
-
-/* Handle external providers (FPU, Altivec, VSX) */
-static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
-			     ulong msr)
-{
-	struct thread_struct *t = &current->thread;
-	u64 *vcpu_fpr = vcpu->arch.fpr;
-#ifdef CONFIG_VSX
-	u64 *vcpu_vsx = vcpu->arch.vsr;
-#endif
-	u64 *thread_fpr = (u64*)t->fpr;
-	int i;
-
-	/* When we have paired singles, we emulate in software */
-	if (vcpu->arch.hflags & BOOK3S_HFLAG_PAIRED_SINGLE)
-		return RESUME_GUEST;
-
-	if (!(vcpu->arch.shared->msr & msr)) {
-		kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
-		return RESUME_GUEST;
-	}
-
-	/* We already own the ext */
-	if (vcpu->arch.guest_owned_ext & msr) {
-		return RESUME_GUEST;
-	}
-
-#ifdef DEBUG_EXT
-	printk(KERN_INFO "Loading up ext 0x%lx\n", msr);
-#endif
-
-	current->thread.regs->msr |= msr;
-
-	switch (msr) {
-	case MSR_FP:
-		for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++)
-			thread_fpr[get_fpr_index(i)] = vcpu_fpr[i];
-
-		t->fpscr.val = vcpu->arch.fpscr;
-		t->fpexc_mode = 0;
-		kvmppc_load_up_fpu();
-		break;
-	case MSR_VEC:
-#ifdef CONFIG_ALTIVEC
-		memcpy(t->vr, vcpu->arch.vr, sizeof(vcpu->arch.vr));
-		t->vscr = vcpu->arch.vscr;
-		t->vrsave = -1;
-		kvmppc_load_up_altivec();
-#endif
-		break;
-	case MSR_VSX:
-#ifdef CONFIG_VSX
-		for (i = 0; i < ARRAY_SIZE(vcpu->arch.vsr); i++)
-			thread_fpr[get_fpr_index(i) + 1] = vcpu_vsx[i];
-		kvmppc_load_up_vsx();
-#endif
-		break;
-	default:
-		BUG();
-	}
-
-	vcpu->arch.guest_owned_ext |= msr;
-
-	kvmppc_recalc_shadow_msr(vcpu);
-
-	return RESUME_GUEST;
-}
-
-int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
-                       unsigned int exit_nr)
-{
-	int r = RESUME_HOST;
-
-	vcpu->stat.sum_exits++;
-
-	run->exit_reason = KVM_EXIT_UNKNOWN;
-	run->ready_for_interrupt_injection = 1;
-
-	trace_kvm_book3s_exit(exit_nr, vcpu);
-	kvm_resched(vcpu);
-	switch (exit_nr) {
-	case BOOK3S_INTERRUPT_INST_STORAGE:
-		vcpu->stat.pf_instruc++;
-
-#ifdef CONFIG_PPC_BOOK3S_32
-		/* We set segments as unused segments when invalidating them. So
-		 * treat the respective fault as segment fault. */
-		if (to_svcpu(vcpu)->sr[kvmppc_get_pc(vcpu) >> SID_SHIFT]
-		    == SR_INVALID) {
-			kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu));
-			r = RESUME_GUEST;
-			break;
-		}
-#endif
-
-		/* only care about PTEG not found errors, but leave NX alone */
-		if (to_svcpu(vcpu)->shadow_srr1 & 0x40000000) {
-			r = kvmppc_handle_pagefault(run, vcpu, kvmppc_get_pc(vcpu), exit_nr);
-			vcpu->stat.sp_instruc++;
-		} else if (vcpu->arch.mmu.is_dcbz32(vcpu) &&
-			  (!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32))) {
-			/*
-			 * XXX If we do the dcbz hack we use the NX bit to flush&patch the page,
-			 *     so we can't use the NX bit inside the guest. Let's cross our fingers,
-			 *     that no guest that needs the dcbz hack does NX.
-			 */
-			kvmppc_mmu_pte_flush(vcpu, kvmppc_get_pc(vcpu), ~0xFFFUL);
-			r = RESUME_GUEST;
-		} else {
-			vcpu->arch.shared->msr |=
-				to_svcpu(vcpu)->shadow_srr1 & 0x58000000;
-			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
-			r = RESUME_GUEST;
-		}
-		break;
-	case BOOK3S_INTERRUPT_DATA_STORAGE:
-	{
-		ulong dar = kvmppc_get_fault_dar(vcpu);
-		vcpu->stat.pf_storage++;
-
-#ifdef CONFIG_PPC_BOOK3S_32
-		/* We set segments as unused segments when invalidating them. So
-		 * treat the respective fault as segment fault. */
-		if ((to_svcpu(vcpu)->sr[dar >> SID_SHIFT]) == SR_INVALID) {
-			kvmppc_mmu_map_segment(vcpu, dar);
-			r = RESUME_GUEST;
-			break;
-		}
-#endif
-
-		/* The only case we need to handle is missing shadow PTEs */
-		if (to_svcpu(vcpu)->fault_dsisr & DSISR_NOHPTE) {
-			r = kvmppc_handle_pagefault(run, vcpu, dar, exit_nr);
-		} else {
-			vcpu->arch.shared->dar = dar;
-			vcpu->arch.shared->dsisr = to_svcpu(vcpu)->fault_dsisr;
-			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
-			r = RESUME_GUEST;
-		}
-		break;
-	}
-	case BOOK3S_INTERRUPT_DATA_SEGMENT:
-		if (kvmppc_mmu_map_segment(vcpu, kvmppc_get_fault_dar(vcpu)) < 0) {
-			vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
-			kvmppc_book3s_queue_irqprio(vcpu,
-				BOOK3S_INTERRUPT_DATA_SEGMENT);
-		}
-		r = RESUME_GUEST;
-		break;
-	case BOOK3S_INTERRUPT_INST_SEGMENT:
-		if (kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu)) < 0) {
-			kvmppc_book3s_queue_irqprio(vcpu,
-				BOOK3S_INTERRUPT_INST_SEGMENT);
-		}
-		r = RESUME_GUEST;
-		break;
-	/* We're good on these - the host merely wanted to get our attention */
-	case BOOK3S_INTERRUPT_DECREMENTER:
-		vcpu->stat.dec_exits++;
-		r = RESUME_GUEST;
-		break;
-	case BOOK3S_INTERRUPT_EXTERNAL:
-		vcpu->stat.ext_intr_exits++;
-		r = RESUME_GUEST;
-		break;
-	case BOOK3S_INTERRUPT_PERFMON:
-		r = RESUME_GUEST;
-		break;
-	case BOOK3S_INTERRUPT_PROGRAM:
-	{
-		enum emulation_result er;
-		ulong flags;
-
-program_interrupt:
-		flags = to_svcpu(vcpu)->shadow_srr1 & 0x1f0000ull;
-
-		if (vcpu->arch.shared->msr & MSR_PR) {
-#ifdef EXIT_DEBUG
-			printk(KERN_INFO "Userspace triggered 0x700 exception at 0x%lx (0x%x)\n", kvmppc_get_pc(vcpu), kvmppc_get_last_inst(vcpu));
-#endif
-			if ((kvmppc_get_last_inst(vcpu) & 0xff0007ff) !=
-			    (INS_DCBZ & 0xfffffff7)) {
-				kvmppc_core_queue_program(vcpu, flags);
-				r = RESUME_GUEST;
-				break;
-			}
-		}
-
-		vcpu->stat.emulated_inst_exits++;
-		er = kvmppc_emulate_instruction(run, vcpu);
-		switch (er) {
-		case EMULATE_DONE:
-			r = RESUME_GUEST_NV;
-			break;
-		case EMULATE_AGAIN:
-			r = RESUME_GUEST;
-			break;
-		case EMULATE_FAIL:
-			printk(KERN_CRIT "%s: emulation at %lx failed (%08x)\n",
-			       __func__, kvmppc_get_pc(vcpu), kvmppc_get_last_inst(vcpu));
-			kvmppc_core_queue_program(vcpu, flags);
-			r = RESUME_GUEST;
-			break;
-		case EMULATE_DO_MMIO:
-			run->exit_reason = KVM_EXIT_MMIO;
-			r = RESUME_HOST_NV;
-			break;
-		default:
-			BUG();
-		}
-		break;
-	}
-	case BOOK3S_INTERRUPT_SYSCALL:
-		if (vcpu->arch.osi_enabled &&
-		    (((u32)kvmppc_get_gpr(vcpu, 3)) == OSI_SC_MAGIC_R3) &&
-		    (((u32)kvmppc_get_gpr(vcpu, 4)) == OSI_SC_MAGIC_R4)) {
-			/* MOL hypercalls */
-			u64 *gprs = run->osi.gprs;
-			int i;
-
-			run->exit_reason = KVM_EXIT_OSI;
-			for (i = 0; i < 32; i++)
-				gprs[i] = kvmppc_get_gpr(vcpu, i);
-			vcpu->arch.osi_needed = 1;
-			r = RESUME_HOST_NV;
-		} else if (!(vcpu->arch.shared->msr & MSR_PR) &&
-		    (((u32)kvmppc_get_gpr(vcpu, 0)) == KVM_SC_MAGIC_R0)) {
-			/* KVM PV hypercalls */
-			kvmppc_set_gpr(vcpu, 3, kvmppc_kvm_pv(vcpu));
-			r = RESUME_GUEST;
-		} else {
-			/* Guest syscalls */
-			vcpu->stat.syscall_exits++;
-			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
-			r = RESUME_GUEST;
-		}
-		break;
-	case BOOK3S_INTERRUPT_FP_UNAVAIL:
-	case BOOK3S_INTERRUPT_ALTIVEC:
-	case BOOK3S_INTERRUPT_VSX:
-	{
-		int ext_msr = 0;
-
-		switch (exit_nr) {
-		case BOOK3S_INTERRUPT_FP_UNAVAIL: ext_msr = MSR_FP;  break;
-		case BOOK3S_INTERRUPT_ALTIVEC:    ext_msr = MSR_VEC; break;
-		case BOOK3S_INTERRUPT_VSX:        ext_msr = MSR_VSX; break;
-		}
-
-		switch (kvmppc_check_ext(vcpu, exit_nr)) {
-		case EMULATE_DONE:
-			/* everything ok - let's enable the ext */
-			r = kvmppc_handle_ext(vcpu, exit_nr, ext_msr);
-			break;
-		case EMULATE_FAIL:
-			/* we need to emulate this instruction */
-			goto program_interrupt;
-			break;
-		default:
-			/* nothing to worry about - go again */
-			break;
-		}
-		break;
-	}
-	case BOOK3S_INTERRUPT_ALIGNMENT:
-		if (kvmppc_read_inst(vcpu) == EMULATE_DONE) {
-			vcpu->arch.shared->dsisr = kvmppc_alignment_dsisr(vcpu,
-				kvmppc_get_last_inst(vcpu));
-			vcpu->arch.shared->dar = kvmppc_alignment_dar(vcpu,
-				kvmppc_get_last_inst(vcpu));
-			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
-		}
-		r = RESUME_GUEST;
-		break;
-	case BOOK3S_INTERRUPT_MACHINE_CHECK:
-	case BOOK3S_INTERRUPT_TRACE:
-		kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
-		r = RESUME_GUEST;
-		break;
-	default:
-		/* Ugh - bork here! What did we get? */
-		printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | msr=0x%lx\n",
-			exit_nr, kvmppc_get_pc(vcpu), to_svcpu(vcpu)->shadow_srr1);
-		r = RESUME_HOST;
-		BUG();
-		break;
-	}
-
-
-	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)) {
-#ifdef EXIT_DEBUG
-			printk(KERN_EMERG "KVM: Going back to host\n");
-#endif
-			vcpu->stat.signal_exits++;
-			run->exit_reason = KVM_EXIT_INTR;
-			r = -EINTR;
-		} else {
-			/* In case an interrupt came in that was triggered
-			 * from userspace (like DEC), we need to check what
-			 * to inject now! */
-			kvmppc_core_deliver_interrupts(vcpu);
-		}
-	}
-
-	trace_kvm_book3s_reenter(r, vcpu);
-
-	return r;
-}
-
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
 	return 0;
@@ -1180,69 +461,6 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	return 0;
 }
 
-int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
-                                  struct kvm_sregs *sregs)
-{
-	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
-	int i;
-
-	sregs->pvr = vcpu->arch.pvr;
-
-	sregs->u.s.sdr1 = to_book3s(vcpu)->sdr1;
-	if (vcpu->arch.hflags & BOOK3S_HFLAG_SLB) {
-		for (i = 0; i < 64; i++) {
-			sregs->u.s.ppc64.slb[i].slbe = vcpu->arch.slb[i].orige | i;
-			sregs->u.s.ppc64.slb[i].slbv = vcpu->arch.slb[i].origv;
-		}
-	} else {
-		for (i = 0; i < 16; i++)
-			sregs->u.s.ppc32.sr[i] = vcpu->arch.shared->sr[i];
-
-		for (i = 0; i < 8; i++) {
-			sregs->u.s.ppc32.ibat[i] = vcpu3s->ibat[i].raw;
-			sregs->u.s.ppc32.dbat[i] = vcpu3s->dbat[i].raw;
-		}
-	}
-
-	return 0;
-}
-
-int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
-                                  struct kvm_sregs *sregs)
-{
-	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
-	int i;
-
-	kvmppc_set_pvr(vcpu, sregs->pvr);
-
-	vcpu3s->sdr1 = sregs->u.s.sdr1;
-	if (vcpu->arch.hflags & BOOK3S_HFLAG_SLB) {
-		for (i = 0; i < 64; i++) {
-			vcpu->arch.mmu.slbmte(vcpu, sregs->u.s.ppc64.slb[i].slbv,
-						    sregs->u.s.ppc64.slb[i].slbe);
-		}
-	} else {
-		for (i = 0; i < 16; i++) {
-			vcpu->arch.mmu.mtsrin(vcpu, i, sregs->u.s.ppc32.sr[i]);
-		}
-		for (i = 0; i < 8; i++) {
-			kvmppc_set_bat(vcpu, &(vcpu3s->ibat[i]), false,
-				       (u32)sregs->u.s.ppc32.ibat[i]);
-			kvmppc_set_bat(vcpu, &(vcpu3s->ibat[i]), true,
-				       (u32)(sregs->u.s.ppc32.ibat[i] >> 32));
-			kvmppc_set_bat(vcpu, &(vcpu3s->dbat[i]), false,
-				       (u32)sregs->u.s.ppc32.dbat[i]);
-			kvmppc_set_bat(vcpu, &(vcpu3s->dbat[i]), true,
-				       (u32)(sregs->u.s.ppc32.dbat[i] >> 32));
-		}
-	}
-
-	/* Flush the MMU after messing with the segments */
-	kvmppc_mmu_pte_flush(vcpu, 0, 0);
-
-	return 0;
-}
-
 int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
 {
 	return -ENOTSUPP;
@@ -1297,202 +515,3 @@ out:
 	mutex_unlock(&kvm->slots_lock);
 	return r;
 }
-
-int kvmppc_core_check_processor_compat(void)
-{
-	return 0;
-}
-
-struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
-{
-	struct kvmppc_vcpu_book3s *vcpu_book3s;
-	struct kvm_vcpu *vcpu;
-	int err = -ENOMEM;
-	unsigned long p;
-
-	vcpu_book3s = vzalloc(sizeof(struct kvmppc_vcpu_book3s));
-	if (!vcpu_book3s)
-		goto out;
-
-	vcpu_book3s->shadow_vcpu = (struct kvmppc_book3s_shadow_vcpu *)
-		kzalloc(sizeof(*vcpu_book3s->shadow_vcpu), GFP_KERNEL);
-	if (!vcpu_book3s->shadow_vcpu)
-		goto free_vcpu;
-
-	vcpu = &vcpu_book3s->vcpu;
-	err = kvm_vcpu_init(vcpu, kvm, id);
-	if (err)
-		goto free_shadow_vcpu;
-
-	p = __get_free_page(GFP_KERNEL|__GFP_ZERO);
-	/* the real shared page fills the last 4k of our page */
-	vcpu->arch.shared = (void*)(p + PAGE_SIZE - 4096);
-	if (!p)
-		goto uninit_vcpu;
-
-	vcpu->arch.host_retip = kvm_return_point;
-	vcpu->arch.host_msr = mfmsr();
-#ifdef CONFIG_PPC_BOOK3S_64
-	/* default to book3s_64 (970fx) */
-	vcpu->arch.pvr = 0x3C0301;
-#else
-	/* default to book3s_32 (750) */
-	vcpu->arch.pvr = 0x84202;
-#endif
-	kvmppc_set_pvr(vcpu, vcpu->arch.pvr);
-	vcpu->arch.slb_nr = 64;
-
-	/* remember where some real-mode handlers are */
-	vcpu->arch.trampoline_lowmem = kvmppc_trampoline_lowmem;
-	vcpu->arch.trampoline_enter = kvmppc_trampoline_enter;
-	vcpu->arch.highmem_handler = (ulong)kvmppc_handler_highmem;
-#ifdef CONFIG_PPC_BOOK3S_64
-	vcpu->arch.rmcall = *(ulong*)kvmppc_rmcall;
-#else
-	vcpu->arch.rmcall = (ulong)kvmppc_rmcall;
-#endif
-
-	vcpu->arch.shadow_msr = MSR_USER64;
-
-	err = kvmppc_mmu_init(vcpu);
-	if (err < 0)
-		goto uninit_vcpu;
-
-	return vcpu;
-
-uninit_vcpu:
-	kvm_vcpu_uninit(vcpu);
-free_shadow_vcpu:
-	kfree(vcpu_book3s->shadow_vcpu);
-free_vcpu:
-	vfree(vcpu_book3s);
-out:
-	return ERR_PTR(err);
-}
-
-void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
-{
-	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
-
-	free_page((unsigned long)vcpu->arch.shared & PAGE_MASK);
-	kvm_vcpu_uninit(vcpu);
-	kfree(vcpu_book3s->shadow_vcpu);
-	vfree(vcpu_book3s);
-}
-
-extern int __kvmppc_vcpu_entry(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu);
-int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
-{
-	int ret;
-	double fpr[32][TS_FPRWIDTH];
-	unsigned int fpscr;
-	int fpexc_mode;
-#ifdef CONFIG_ALTIVEC
-	vector128 vr[32];
-	vector128 vscr;
-	unsigned long uninitialized_var(vrsave);
-	int used_vr;
-#endif
-#ifdef CONFIG_VSX
-	int used_vsr;
-#endif
-	ulong ext_msr;
-
-	/* No need to go into the guest when all we do is going out */
-	if (signal_pending(current)) {
-		kvm_run->exit_reason = KVM_EXIT_INTR;
-		return -EINTR;
-	}
-
-	/* Save FPU state in stack */
-	if (current->thread.regs->msr & MSR_FP)
-		giveup_fpu(current);
-	memcpy(fpr, current->thread.fpr, sizeof(current->thread.fpr));
-	fpscr = current->thread.fpscr.val;
-	fpexc_mode = current->thread.fpexc_mode;
-
-#ifdef CONFIG_ALTIVEC
-	/* Save Altivec state in stack */
-	used_vr = current->thread.used_vr;
-	if (used_vr) {
-		if (current->thread.regs->msr & MSR_VEC)
-			giveup_altivec(current);
-		memcpy(vr, current->thread.vr, sizeof(current->thread.vr));
-		vscr = current->thread.vscr;
-		vrsave = current->thread.vrsave;
-	}
-#endif
-
-#ifdef CONFIG_VSX
-	/* Save VSX state in stack */
-	used_vsr = current->thread.used_vsr;
-	if (used_vsr && (current->thread.regs->msr & MSR_VSX))
-			__giveup_vsx(current);
-#endif
-
-	/* Remember the MSR with disabled extensions */
-	ext_msr = current->thread.regs->msr;
-
-	/* XXX we get called with irq disabled - change that! */
-	local_irq_enable();
-
-	/* Preload FPU if it's enabled */
-	if (vcpu->arch.shared->msr & MSR_FP)
-		kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP);
-
-	ret = __kvmppc_vcpu_entry(kvm_run, vcpu);
-
-	local_irq_disable();
-
-	current->thread.regs->msr = ext_msr;
-
-	/* Make sure we save the guest FPU/Altivec/VSX state */
-	kvmppc_giveup_ext(vcpu, MSR_FP);
-	kvmppc_giveup_ext(vcpu, MSR_VEC);
-	kvmppc_giveup_ext(vcpu, MSR_VSX);
-
-	/* Restore FPU state from stack */
-	memcpy(current->thread.fpr, fpr, sizeof(current->thread.fpr));
-	current->thread.fpscr.val = fpscr;
-	current->thread.fpexc_mode = fpexc_mode;
-
-#ifdef CONFIG_ALTIVEC
-	/* Restore Altivec state from stack */
-	if (used_vr && current->thread.used_vr) {
-		memcpy(current->thread.vr, vr, sizeof(current->thread.vr));
-		current->thread.vscr = vscr;
-		current->thread.vrsave = vrsave;
-	}
-	current->thread.used_vr = used_vr;
-#endif
-
-#ifdef CONFIG_VSX
-	current->thread.used_vsr = used_vsr;
-#endif
-
-	return ret;
-}
-
-static int kvmppc_book3s_init(void)
-{
-	int r;
-
-	r = kvm_init(NULL, sizeof(struct kvmppc_vcpu_book3s), 0,
-		     THIS_MODULE);
-
-	if (r)
-		return r;
-
-	r = kvmppc_mmu_hpte_sysinit();
-
-	return r;
-}
-
-static void kvmppc_book3s_exit(void)
-{
-	kvmppc_mmu_hpte_sysexit();
-	kvm_exit();
-}
-
-module_init(kvmppc_book3s_init);
-module_exit(kvmppc_book3s_exit);
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
new file mode 100644
index 0000000..82df775
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -0,0 +1,1009 @@
+/*
+ * Copyright (C) 2009. SUSE Linux Products GmbH. All rights reserved.
+ *
+ * Authors:
+ *    Alexander Graf <agraf@suse.de>
+ *    Kevin Wolf <mail@kevin-wolf.de>
+ *    Paul Mackerras <paulus@samba.org>
+ *
+ * Description:
+ * Functions relating to running KVM on Book 3S processors where
+ * we don't have access to hypervisor mode, and we run the guest
+ * in problem state (user mode).
+ *
+ * This file is derived from arch/powerpc/kvm/44x.c,
+ * by Hollis Blanchard <hollisb@us.ibm.com>.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+
+#include <asm/reg.h>
+#include <asm/cputable.h>
+#include <asm/cacheflush.h>
+#include <asm/tlbflush.h>
+#include <asm/uaccess.h>
+#include <asm/io.h>
+#include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s.h>
+#include <asm/mmu_context.h>
+#include <linux/gfp.h>
+#include <linux/sched.h>
+#include <linux/vmalloc.h>
+#include <linux/highmem.h>
+
+#include "trace.h"
+
+/* #define EXIT_DEBUG */
+/* #define DEBUG_EXT */
+
+static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
+			     ulong msr);
+
+/* Some compatibility defines */
+#ifdef CONFIG_PPC_BOOK3S_32
+#define MSR_USER32 MSR_USER
+#define MSR_USER64 MSR_USER
+#define HW_PAGE_SIZE PAGE_SIZE
+#endif
+
+void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+#ifdef CONFIG_PPC_BOOK3S_64
+	memcpy(to_svcpu(vcpu)->slb, to_book3s(vcpu)->slb_shadow, sizeof(to_svcpu(vcpu)->slb));
+	memcpy(&get_paca()->shadow_vcpu, to_book3s(vcpu)->shadow_vcpu,
+	       sizeof(get_paca()->shadow_vcpu));
+	to_svcpu(vcpu)->slb_max = to_book3s(vcpu)->slb_shadow_max;
+#endif
+
+#ifdef CONFIG_PPC_BOOK3S_32
+	current->thread.kvm_shadow_vcpu = to_book3s(vcpu)->shadow_vcpu;
+#endif
+}
+
+void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_PPC_BOOK3S_64
+	memcpy(to_book3s(vcpu)->slb_shadow, to_svcpu(vcpu)->slb, sizeof(to_svcpu(vcpu)->slb));
+	memcpy(to_book3s(vcpu)->shadow_vcpu, &get_paca()->shadow_vcpu,
+	       sizeof(get_paca()->shadow_vcpu));
+	to_book3s(vcpu)->slb_shadow_max = to_svcpu(vcpu)->slb_max;
+#endif
+
+	kvmppc_giveup_ext(vcpu, MSR_FP);
+	kvmppc_giveup_ext(vcpu, MSR_VEC);
+	kvmppc_giveup_ext(vcpu, MSR_VSX);
+}
+
+static void kvmppc_recalc_shadow_msr(struct kvm_vcpu *vcpu)
+{
+	ulong smsr = vcpu->arch.shared->msr;
+
+	/* Guest MSR values */
+	smsr &= MSR_FE0 | MSR_FE1 | MSR_SF | MSR_SE | MSR_BE | MSR_DE;
+	/* Process MSR values */
+	smsr |= MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_PR | MSR_EE;
+	/* External providers the guest reserved */
+	smsr |= (vcpu->arch.shared->msr & vcpu->arch.guest_owned_ext);
+	/* 64-bit Process MSR values */
+#ifdef CONFIG_PPC_BOOK3S_64
+	smsr |= MSR_ISF | MSR_HV;
+#endif
+	vcpu->arch.shadow_msr = smsr;
+}
+
+void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
+{
+	ulong old_msr = vcpu->arch.shared->msr;
+
+#ifdef EXIT_DEBUG
+	printk(KERN_INFO "KVM: Set MSR to 0x%llx\n", msr);
+#endif
+
+	msr &= to_book3s(vcpu)->msr_mask;
+	vcpu->arch.shared->msr = msr;
+	kvmppc_recalc_shadow_msr(vcpu);
+
+	if (msr & MSR_POW) {
+		if (!vcpu->arch.pending_exceptions) {
+			kvm_vcpu_block(vcpu);
+			vcpu->stat.halt_wakeup++;
+
+			/* Unset POW bit after we woke up */
+			msr &= ~MSR_POW;
+			vcpu->arch.shared->msr = msr;
+		}
+	}
+
+	if ((vcpu->arch.shared->msr & (MSR_PR|MSR_IR|MSR_DR)) !=
+		   (old_msr & (MSR_PR|MSR_IR|MSR_DR))) {
+		kvmppc_mmu_flush_segments(vcpu);
+		kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu));
+
+		/* Preload magic page segment when in kernel mode */
+		if (!(msr & MSR_PR) && vcpu->arch.magic_page_pa) {
+			struct kvm_vcpu_arch *a = &vcpu->arch;
+
+			if (msr & MSR_DR)
+				kvmppc_mmu_map_segment(vcpu, a->magic_page_ea);
+			else
+				kvmppc_mmu_map_segment(vcpu, a->magic_page_pa);
+		}
+	}
+
+	/* Preload FPU if it's enabled */
+	if (vcpu->arch.shared->msr & MSR_FP)
+		kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP);
+}
+
+void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr)
+{
+	u32 host_pvr;
+
+	vcpu->arch.hflags &= ~BOOK3S_HFLAG_SLB;
+	vcpu->arch.pvr = pvr;
+#ifdef CONFIG_PPC_BOOK3S_64
+	if ((pvr >= 0x330000) && (pvr < 0x70330000)) {
+		kvmppc_mmu_book3s_64_init(vcpu);
+		to_book3s(vcpu)->hior = 0xfff00000;
+		to_book3s(vcpu)->msr_mask = 0xffffffffffffffffULL;
+	} else
+#endif
+	{
+		kvmppc_mmu_book3s_32_init(vcpu);
+		to_book3s(vcpu)->hior = 0;
+		to_book3s(vcpu)->msr_mask = 0xffffffffULL;
+	}
+
+	/* If we are in hypervisor level on 970, we can tell the CPU to
+	 * treat DCBZ as 32 bytes store */
+	vcpu->arch.hflags &= ~BOOK3S_HFLAG_DCBZ32;
+	if (vcpu->arch.mmu.is_dcbz32(vcpu) && (mfmsr() & MSR_HV) &&
+	    !strcmp(cur_cpu_spec->platform, "ppc970"))
+		vcpu->arch.hflags |= BOOK3S_HFLAG_DCBZ32;
+
+	/* Cell performs badly if MSR_FEx are set. So let's hope nobody
+	   really needs them in a VM on Cell and force disable them. */
+	if (!strcmp(cur_cpu_spec->platform, "ppc-cell-be"))
+		to_book3s(vcpu)->msr_mask &= ~(MSR_FE0 | MSR_FE1);
+
+#ifdef CONFIG_PPC_BOOK3S_32
+	/* 32 bit Book3S always has 32 byte dcbz */
+	vcpu->arch.hflags |= BOOK3S_HFLAG_DCBZ32;
+#endif
+
+	/* On some CPUs we can execute paired single operations natively */
+	asm ( "mfpvr %0" : "=r"(host_pvr));
+	switch (host_pvr) {
+	case 0x00080200:	/* lonestar 2.0 */
+	case 0x00088202:	/* lonestar 2.2 */
+	case 0x70000100:	/* gekko 1.0 */
+	case 0x00080100:	/* gekko 2.0 */
+	case 0x00083203:	/* gekko 2.3a */
+	case 0x00083213:	/* gekko 2.3b */
+	case 0x00083204:	/* gekko 2.4 */
+	case 0x00083214:	/* gekko 2.4e (8SE) - retail HW2 */
+	case 0x00087200:	/* broadway */
+		vcpu->arch.hflags |= BOOK3S_HFLAG_NATIVE_PS;
+		/* Enable HID2.PSE - in case we need it later */
+		mtspr(SPRN_HID2_GEKKO, mfspr(SPRN_HID2_GEKKO) | (1 << 29));
+	}
+}
+
+/* Book3s_32 CPUs always have 32 bytes cache line size, which Linux assumes. To
+ * make Book3s_32 Linux work on Book3s_64, we have to make sure we trap dcbz to
+ * emulate 32 bytes dcbz length.
+ *
+ * The Book3s_64 inventors also realized this case and implemented a special bit
+ * in the HID5 register, which is a hypervisor ressource. Thus we can't use it.
+ *
+ * My approach here is to patch the dcbz instruction on executing pages.
+ */
+static void kvmppc_patch_dcbz(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte)
+{
+	struct page *hpage;
+	u64 hpage_offset;
+	u32 *page;
+	int i;
+
+	hpage = gfn_to_page(vcpu->kvm, pte->raddr >> PAGE_SHIFT);
+	if (is_error_page(hpage)) {
+		kvm_release_page_clean(hpage);
+		return;
+	}
+
+	hpage_offset = pte->raddr & ~PAGE_MASK;
+	hpage_offset &= ~0xFFFULL;
+	hpage_offset /= 4;
+
+	get_page(hpage);
+	page = kmap_atomic(hpage, KM_USER0);
+
+	/* patch dcbz into reserved instruction, so we trap */
+	for (i=hpage_offset; i < hpage_offset + (HW_PAGE_SIZE / 4); i++)
+		if ((page[i] & 0xff0007ff) == INS_DCBZ)
+			page[i] &= 0xfffffff7;
+
+	kunmap_atomic(page, KM_USER0);
+	put_page(hpage);
+}
+
+static int kvmppc_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+	ulong mp_pa = vcpu->arch.magic_page_pa;
+
+	if (unlikely(mp_pa) &&
+	    unlikely((mp_pa & KVM_PAM) >> PAGE_SHIFT == gfn)) {
+		return 1;
+	}
+
+	return kvm_is_visible_gfn(vcpu->kvm, gfn);
+}
+
+int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
+			    ulong eaddr, int vec)
+{
+	bool data = (vec == BOOK3S_INTERRUPT_DATA_STORAGE);
+	int r = RESUME_GUEST;
+	int relocated;
+	int page_found = 0;
+	struct kvmppc_pte pte;
+	bool is_mmio = false;
+	bool dr = (vcpu->arch.shared->msr & MSR_DR) ? true : false;
+	bool ir = (vcpu->arch.shared->msr & MSR_IR) ? true : false;
+	u64 vsid;
+
+	relocated = data ? dr : ir;
+
+	/* Resolve real address if translation turned on */
+	if (relocated) {
+		page_found = vcpu->arch.mmu.xlate(vcpu, eaddr, &pte, data);
+	} else {
+		pte.may_execute = true;
+		pte.may_read = true;
+		pte.may_write = true;
+		pte.raddr = eaddr & KVM_PAM;
+		pte.eaddr = eaddr;
+		pte.vpage = eaddr >> 12;
+	}
+
+	switch (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {
+	case 0:
+		pte.vpage |= ((u64)VSID_REAL << (SID_SHIFT - 12));
+		break;
+	case MSR_DR:
+	case MSR_IR:
+		vcpu->arch.mmu.esid_to_vsid(vcpu, eaddr >> SID_SHIFT, &vsid);
+
+		if ((vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) == MSR_DR)
+			pte.vpage |= ((u64)VSID_REAL_DR << (SID_SHIFT - 12));
+		else
+			pte.vpage |= ((u64)VSID_REAL_IR << (SID_SHIFT - 12));
+		pte.vpage |= vsid;
+
+		if (vsid == -1)
+			page_found = -EINVAL;
+		break;
+	}
+
+	if (vcpu->arch.mmu.is_dcbz32(vcpu) &&
+	   (!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32))) {
+		/*
+		 * If we do the dcbz hack, we have to NX on every execution,
+		 * so we can patch the executing code. This renders our guest
+		 * NX-less.
+		 */
+		pte.may_execute = !data;
+	}
+
+	if (page_found == -ENOENT) {
+		/* Page not found in guest PTE entries */
+		vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
+		vcpu->arch.shared->dsisr = to_svcpu(vcpu)->fault_dsisr;
+		vcpu->arch.shared->msr |=
+			(to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL);
+		kvmppc_book3s_queue_irqprio(vcpu, vec);
+	} else if (page_found == -EPERM) {
+		/* Storage protection */
+		vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
+		vcpu->arch.shared->dsisr =
+			to_svcpu(vcpu)->fault_dsisr & ~DSISR_NOHPTE;
+		vcpu->arch.shared->dsisr |= DSISR_PROTFAULT;
+		vcpu->arch.shared->msr |=
+			(to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL);
+		kvmppc_book3s_queue_irqprio(vcpu, vec);
+	} else if (page_found == -EINVAL) {
+		/* Page not found in guest SLB */
+		vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
+		kvmppc_book3s_queue_irqprio(vcpu, vec + 0x80);
+	} else if (!is_mmio &&
+		   kvmppc_visible_gfn(vcpu, pte.raddr >> PAGE_SHIFT)) {
+		/* The guest's PTE is not mapped yet. Map on the host */
+		kvmppc_mmu_map_page(vcpu, &pte);
+		if (data)
+			vcpu->stat.sp_storage++;
+		else if (vcpu->arch.mmu.is_dcbz32(vcpu) &&
+			(!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32)))
+			kvmppc_patch_dcbz(vcpu, &pte);
+	} else {
+		/* MMIO */
+		vcpu->stat.mmio_exits++;
+		vcpu->arch.paddr_accessed = pte.raddr;
+		r = kvmppc_emulate_mmio(run, vcpu);
+		if ( r == RESUME_HOST_NV )
+			r = RESUME_HOST;
+	}
+
+	return r;
+}
+
+static inline int get_fpr_index(int i)
+{
+#ifdef CONFIG_VSX
+	i *= 2;
+#endif
+	return i;
+}
+
+/* Give up external provider (FPU, Altivec, VSX) */
+void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr)
+{
+	struct thread_struct *t = &current->thread;
+	u64 *vcpu_fpr = vcpu->arch.fpr;
+#ifdef CONFIG_VSX
+	u64 *vcpu_vsx = vcpu->arch.vsr;
+#endif
+	u64 *thread_fpr = (u64*)t->fpr;
+	int i;
+
+	if (!(vcpu->arch.guest_owned_ext & msr))
+		return;
+
+#ifdef DEBUG_EXT
+	printk(KERN_INFO "Giving up ext 0x%lx\n", msr);
+#endif
+
+	switch (msr) {
+	case MSR_FP:
+		giveup_fpu(current);
+		for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++)
+			vcpu_fpr[i] = thread_fpr[get_fpr_index(i)];
+
+		vcpu->arch.fpscr = t->fpscr.val;
+		break;
+	case MSR_VEC:
+#ifdef CONFIG_ALTIVEC
+		giveup_altivec(current);
+		memcpy(vcpu->arch.vr, t->vr, sizeof(vcpu->arch.vr));
+		vcpu->arch.vscr = t->vscr;
+#endif
+		break;
+	case MSR_VSX:
+#ifdef CONFIG_VSX
+		__giveup_vsx(current);
+		for (i = 0; i < ARRAY_SIZE(vcpu->arch.vsr); i++)
+			vcpu_vsx[i] = thread_fpr[get_fpr_index(i) + 1];
+#endif
+		break;
+	default:
+		BUG();
+	}
+
+	vcpu->arch.guest_owned_ext &= ~msr;
+	current->thread.regs->msr &= ~msr;
+	kvmppc_recalc_shadow_msr(vcpu);
+}
+
+static int kvmppc_read_inst(struct kvm_vcpu *vcpu)
+{
+	ulong srr0 = kvmppc_get_pc(vcpu);
+	u32 last_inst = kvmppc_get_last_inst(vcpu);
+	int ret;
+
+	ret = kvmppc_ld(vcpu, &srr0, sizeof(u32), &last_inst, false);
+	if (ret == -ENOENT) {
+		ulong msr = vcpu->arch.shared->msr;
+
+		msr = kvmppc_set_field(msr, 33, 33, 1);
+		msr = kvmppc_set_field(msr, 34, 36, 0);
+		vcpu->arch.shared->msr = kvmppc_set_field(msr, 42, 47, 0);
+		kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_INST_STORAGE);
+		return EMULATE_AGAIN;
+	}
+
+	return EMULATE_DONE;
+}
+
+static int kvmppc_check_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr)
+{
+
+	/* Need to do paired single emulation? */
+	if (!(vcpu->arch.hflags & BOOK3S_HFLAG_PAIRED_SINGLE))
+		return EMULATE_DONE;
+
+	/* Read out the instruction */
+	if (kvmppc_read_inst(vcpu) == EMULATE_DONE)
+		/* Need to emulate */
+		return EMULATE_FAIL;
+
+	return EMULATE_AGAIN;
+}
+
+/* Handle external providers (FPU, Altivec, VSX) */
+static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
+			     ulong msr)
+{
+	struct thread_struct *t = &current->thread;
+	u64 *vcpu_fpr = vcpu->arch.fpr;
+#ifdef CONFIG_VSX
+	u64 *vcpu_vsx = vcpu->arch.vsr;
+#endif
+	u64 *thread_fpr = (u64*)t->fpr;
+	int i;
+
+	/* When we have paired singles, we emulate in software */
+	if (vcpu->arch.hflags & BOOK3S_HFLAG_PAIRED_SINGLE)
+		return RESUME_GUEST;
+
+	if (!(vcpu->arch.shared->msr & msr)) {
+		kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
+		return RESUME_GUEST;
+	}
+
+	/* We already own the ext */
+	if (vcpu->arch.guest_owned_ext & msr) {
+		return RESUME_GUEST;
+	}
+
+#ifdef DEBUG_EXT
+	printk(KERN_INFO "Loading up ext 0x%lx\n", msr);
+#endif
+
+	current->thread.regs->msr |= msr;
+
+	switch (msr) {
+	case MSR_FP:
+		for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++)
+			thread_fpr[get_fpr_index(i)] = vcpu_fpr[i];
+
+		t->fpscr.val = vcpu->arch.fpscr;
+		t->fpexc_mode = 0;
+		kvmppc_load_up_fpu();
+		break;
+	case MSR_VEC:
+#ifdef CONFIG_ALTIVEC
+		memcpy(t->vr, vcpu->arch.vr, sizeof(vcpu->arch.vr));
+		t->vscr = vcpu->arch.vscr;
+		t->vrsave = -1;
+		kvmppc_load_up_altivec();
+#endif
+		break;
+	case MSR_VSX:
+#ifdef CONFIG_VSX
+		for (i = 0; i < ARRAY_SIZE(vcpu->arch.vsr); i++)
+			thread_fpr[get_fpr_index(i) + 1] = vcpu_vsx[i];
+		kvmppc_load_up_vsx();
+#endif
+		break;
+	default:
+		BUG();
+	}
+
+	vcpu->arch.guest_owned_ext |= msr;
+
+	kvmppc_recalc_shadow_msr(vcpu);
+
+	return RESUME_GUEST;
+}
+
+int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
+                       unsigned int exit_nr)
+{
+	int r = RESUME_HOST;
+
+	vcpu->stat.sum_exits++;
+
+	run->exit_reason = KVM_EXIT_UNKNOWN;
+	run->ready_for_interrupt_injection = 1;
+
+	trace_kvm_book3s_exit(exit_nr, vcpu);
+	kvm_resched(vcpu);
+	switch (exit_nr) {
+	case BOOK3S_INTERRUPT_INST_STORAGE:
+		vcpu->stat.pf_instruc++;
+
+#ifdef CONFIG_PPC_BOOK3S_32
+		/* We set segments as unused segments when invalidating them. So
+		 * treat the respective fault as segment fault. */
+		if (to_svcpu(vcpu)->sr[kvmppc_get_pc(vcpu) >> SID_SHIFT]
+		    == SR_INVALID) {
+			kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu));
+			r = RESUME_GUEST;
+			break;
+		}
+#endif
+
+		/* only care about PTEG not found errors, but leave NX alone */
+		if (to_svcpu(vcpu)->shadow_srr1 & 0x40000000) {
+			r = kvmppc_handle_pagefault(run, vcpu, kvmppc_get_pc(vcpu), exit_nr);
+			vcpu->stat.sp_instruc++;
+		} else if (vcpu->arch.mmu.is_dcbz32(vcpu) &&
+			  (!(vcpu->arch.hflags & BOOK3S_HFLAG_DCBZ32))) {
+			/*
+			 * XXX If we do the dcbz hack we use the NX bit to flush&patch the page,
+			 *     so we can't use the NX bit inside the guest. Let's cross our fingers,
+			 *     that no guest that needs the dcbz hack does NX.
+			 */
+			kvmppc_mmu_pte_flush(vcpu, kvmppc_get_pc(vcpu), ~0xFFFUL);
+			r = RESUME_GUEST;
+		} else {
+			vcpu->arch.shared->msr |=
+				to_svcpu(vcpu)->shadow_srr1 & 0x58000000;
+			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
+			r = RESUME_GUEST;
+		}
+		break;
+	case BOOK3S_INTERRUPT_DATA_STORAGE:
+	{
+		ulong dar = kvmppc_get_fault_dar(vcpu);
+		vcpu->stat.pf_storage++;
+
+#ifdef CONFIG_PPC_BOOK3S_32
+		/* We set segments as unused segments when invalidating them. So
+		 * treat the respective fault as segment fault. */
+		if ((to_svcpu(vcpu)->sr[dar >> SID_SHIFT]) == SR_INVALID) {
+			kvmppc_mmu_map_segment(vcpu, dar);
+			r = RESUME_GUEST;
+			break;
+		}
+#endif
+
+		/* The only case we need to handle is missing shadow PTEs */
+		if (to_svcpu(vcpu)->fault_dsisr & DSISR_NOHPTE) {
+			r = kvmppc_handle_pagefault(run, vcpu, dar, exit_nr);
+		} else {
+			vcpu->arch.shared->dar = dar;
+			vcpu->arch.shared->dsisr = to_svcpu(vcpu)->fault_dsisr;
+			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
+			r = RESUME_GUEST;
+		}
+		break;
+	}
+	case BOOK3S_INTERRUPT_DATA_SEGMENT:
+		if (kvmppc_mmu_map_segment(vcpu, kvmppc_get_fault_dar(vcpu)) < 0) {
+			vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
+			kvmppc_book3s_queue_irqprio(vcpu,
+				BOOK3S_INTERRUPT_DATA_SEGMENT);
+		}
+		r = RESUME_GUEST;
+		break;
+	case BOOK3S_INTERRUPT_INST_SEGMENT:
+		if (kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu)) < 0) {
+			kvmppc_book3s_queue_irqprio(vcpu,
+				BOOK3S_INTERRUPT_INST_SEGMENT);
+		}
+		r = RESUME_GUEST;
+		break;
+	/* We're good on these - the host merely wanted to get our attention */
+	case BOOK3S_INTERRUPT_DECREMENTER:
+		vcpu->stat.dec_exits++;
+		r = RESUME_GUEST;
+		break;
+	case BOOK3S_INTERRUPT_EXTERNAL:
+		vcpu->stat.ext_intr_exits++;
+		r = RESUME_GUEST;
+		break;
+	case BOOK3S_INTERRUPT_PERFMON:
+		r = RESUME_GUEST;
+		break;
+	case BOOK3S_INTERRUPT_PROGRAM:
+	{
+		enum emulation_result er;
+		ulong flags;
+
+program_interrupt:
+		flags = to_svcpu(vcpu)->shadow_srr1 & 0x1f0000ull;
+
+		if (vcpu->arch.shared->msr & MSR_PR) {
+#ifdef EXIT_DEBUG
+			printk(KERN_INFO "Userspace triggered 0x700 exception at 0x%lx (0x%x)\n", kvmppc_get_pc(vcpu), kvmppc_get_last_inst(vcpu));
+#endif
+			if ((kvmppc_get_last_inst(vcpu) & 0xff0007ff) !=
+			    (INS_DCBZ & 0xfffffff7)) {
+				kvmppc_core_queue_program(vcpu, flags);
+				r = RESUME_GUEST;
+				break;
+			}
+		}
+
+		vcpu->stat.emulated_inst_exits++;
+		er = kvmppc_emulate_instruction(run, vcpu);
+		switch (er) {
+		case EMULATE_DONE:
+			r = RESUME_GUEST_NV;
+			break;
+		case EMULATE_AGAIN:
+			r = RESUME_GUEST;
+			break;
+		case EMULATE_FAIL:
+			printk(KERN_CRIT "%s: emulation at %lx failed (%08x)\n",
+			       __func__, kvmppc_get_pc(vcpu), kvmppc_get_last_inst(vcpu));
+			kvmppc_core_queue_program(vcpu, flags);
+			r = RESUME_GUEST;
+			break;
+		case EMULATE_DO_MMIO:
+			run->exit_reason = KVM_EXIT_MMIO;
+			r = RESUME_HOST_NV;
+			break;
+		default:
+			BUG();
+		}
+		break;
+	}
+	case BOOK3S_INTERRUPT_SYSCALL:
+		if (vcpu->arch.osi_enabled &&
+		    (((u32)kvmppc_get_gpr(vcpu, 3)) == OSI_SC_MAGIC_R3) &&
+		    (((u32)kvmppc_get_gpr(vcpu, 4)) == OSI_SC_MAGIC_R4)) {
+			/* MOL hypercalls */
+			u64 *gprs = run->osi.gprs;
+			int i;
+
+			run->exit_reason = KVM_EXIT_OSI;
+			for (i = 0; i < 32; i++)
+				gprs[i] = kvmppc_get_gpr(vcpu, i);
+			vcpu->arch.osi_needed = 1;
+			r = RESUME_HOST_NV;
+		} else if (!(vcpu->arch.shared->msr & MSR_PR) &&
+		    (((u32)kvmppc_get_gpr(vcpu, 0)) == KVM_SC_MAGIC_R0)) {
+			/* KVM PV hypercalls */
+			kvmppc_set_gpr(vcpu, 3, kvmppc_kvm_pv(vcpu));
+			r = RESUME_GUEST;
+		} else {
+			/* Guest syscalls */
+			vcpu->stat.syscall_exits++;
+			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
+			r = RESUME_GUEST;
+		}
+		break;
+	case BOOK3S_INTERRUPT_FP_UNAVAIL:
+	case BOOK3S_INTERRUPT_ALTIVEC:
+	case BOOK3S_INTERRUPT_VSX:
+	{
+		int ext_msr = 0;
+
+		switch (exit_nr) {
+		case BOOK3S_INTERRUPT_FP_UNAVAIL: ext_msr = MSR_FP;  break;
+		case BOOK3S_INTERRUPT_ALTIVEC:    ext_msr = MSR_VEC; break;
+		case BOOK3S_INTERRUPT_VSX:        ext_msr = MSR_VSX; break;
+		}
+
+		switch (kvmppc_check_ext(vcpu, exit_nr)) {
+		case EMULATE_DONE:
+			/* everything ok - let's enable the ext */
+			r = kvmppc_handle_ext(vcpu, exit_nr, ext_msr);
+			break;
+		case EMULATE_FAIL:
+			/* we need to emulate this instruction */
+			goto program_interrupt;
+			break;
+		default:
+			/* nothing to worry about - go again */
+			break;
+		}
+		break;
+	}
+	case BOOK3S_INTERRUPT_ALIGNMENT:
+		if (kvmppc_read_inst(vcpu) == EMULATE_DONE) {
+			vcpu->arch.shared->dsisr = kvmppc_alignment_dsisr(vcpu,
+				kvmppc_get_last_inst(vcpu));
+			vcpu->arch.shared->dar = kvmppc_alignment_dar(vcpu,
+				kvmppc_get_last_inst(vcpu));
+			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
+		}
+		r = RESUME_GUEST;
+		break;
+	case BOOK3S_INTERRUPT_MACHINE_CHECK:
+	case BOOK3S_INTERRUPT_TRACE:
+		kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
+		r = RESUME_GUEST;
+		break;
+	default:
+		/* Ugh - bork here! What did we get? */
+		printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | msr=0x%lx\n",
+			exit_nr, kvmppc_get_pc(vcpu), to_svcpu(vcpu)->shadow_srr1);
+		r = RESUME_HOST;
+		BUG();
+		break;
+	}
+
+
+	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)) {
+#ifdef EXIT_DEBUG
+			printk(KERN_EMERG "KVM: Going back to host\n");
+#endif
+			vcpu->stat.signal_exits++;
+			run->exit_reason = KVM_EXIT_INTR;
+			r = -EINTR;
+		} else {
+			/* In case an interrupt came in that was triggered
+			 * from userspace (like DEC), we need to check what
+			 * to inject now! */
+			kvmppc_core_deliver_interrupts(vcpu);
+		}
+	}
+
+	trace_kvm_book3s_reenter(r, vcpu);
+
+	return r;
+}
+
+int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
+                                  struct kvm_sregs *sregs)
+{
+	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
+	int i;
+
+	sregs->pvr = vcpu->arch.pvr;
+
+	sregs->u.s.sdr1 = to_book3s(vcpu)->sdr1;
+	if (vcpu->arch.hflags & BOOK3S_HFLAG_SLB) {
+		for (i = 0; i < 64; i++) {
+			sregs->u.s.ppc64.slb[i].slbe = vcpu->arch.slb[i].orige | i;
+			sregs->u.s.ppc64.slb[i].slbv = vcpu->arch.slb[i].origv;
+		}
+	} else {
+		for (i = 0; i < 16; i++)
+			sregs->u.s.ppc32.sr[i] = vcpu->arch.shared->sr[i];
+
+		for (i = 0; i < 8; i++) {
+			sregs->u.s.ppc32.ibat[i] = vcpu3s->ibat[i].raw;
+			sregs->u.s.ppc32.dbat[i] = vcpu3s->dbat[i].raw;
+		}
+	}
+
+	return 0;
+}
+
+int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
+                                  struct kvm_sregs *sregs)
+{
+	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
+	int i;
+
+	kvmppc_set_pvr(vcpu, sregs->pvr);
+
+	vcpu3s->sdr1 = sregs->u.s.sdr1;
+	if (vcpu->arch.hflags & BOOK3S_HFLAG_SLB) {
+		for (i = 0; i < 64; i++) {
+			vcpu->arch.mmu.slbmte(vcpu, sregs->u.s.ppc64.slb[i].slbv,
+						    sregs->u.s.ppc64.slb[i].slbe);
+		}
+	} else {
+		for (i = 0; i < 16; i++) {
+			vcpu->arch.mmu.mtsrin(vcpu, i, sregs->u.s.ppc32.sr[i]);
+		}
+		for (i = 0; i < 8; i++) {
+			kvmppc_set_bat(vcpu, &(vcpu3s->ibat[i]), false,
+				       (u32)sregs->u.s.ppc32.ibat[i]);
+			kvmppc_set_bat(vcpu, &(vcpu3s->ibat[i]), true,
+				       (u32)(sregs->u.s.ppc32.ibat[i] >> 32));
+			kvmppc_set_bat(vcpu, &(vcpu3s->dbat[i]), false,
+				       (u32)sregs->u.s.ppc32.dbat[i]);
+			kvmppc_set_bat(vcpu, &(vcpu3s->dbat[i]), true,
+				       (u32)(sregs->u.s.ppc32.dbat[i] >> 32));
+		}
+	}
+
+	/* Flush the MMU after messing with the segments */
+	kvmppc_mmu_pte_flush(vcpu, 0, 0);
+
+	return 0;
+}
+
+int kvmppc_core_check_processor_compat(void)
+{
+	return 0;
+}
+
+struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
+{
+	struct kvmppc_vcpu_book3s *vcpu_book3s;
+	struct kvm_vcpu *vcpu;
+	int err = -ENOMEM;
+	unsigned long p;
+
+	vcpu_book3s = vzalloc(sizeof(struct kvmppc_vcpu_book3s));
+	if (!vcpu_book3s)
+		goto out;
+
+	vcpu_book3s->shadow_vcpu = (struct kvmppc_book3s_shadow_vcpu *)
+		kzalloc(sizeof(*vcpu_book3s->shadow_vcpu), GFP_KERNEL);
+	if (!vcpu_book3s->shadow_vcpu)
+		goto free_vcpu;
+
+	vcpu = &vcpu_book3s->vcpu;
+	err = kvm_vcpu_init(vcpu, kvm, id);
+	if (err)
+		goto free_shadow_vcpu;
+
+	p = __get_free_page(GFP_KERNEL|__GFP_ZERO);
+	/* the real shared page fills the last 4k of our page */
+	vcpu->arch.shared = (void*)(p + PAGE_SIZE - 4096);
+	if (!p)
+		goto uninit_vcpu;
+
+	vcpu->arch.host_retip = kvm_return_point;
+	vcpu->arch.host_msr = mfmsr();
+#ifdef CONFIG_PPC_BOOK3S_64
+	/* default to book3s_64 (970fx) */
+	vcpu->arch.pvr = 0x3C0301;
+#else
+	/* default to book3s_32 (750) */
+	vcpu->arch.pvr = 0x84202;
+#endif
+	kvmppc_set_pvr(vcpu, vcpu->arch.pvr);
+	vcpu->arch.slb_nr = 64;
+
+	/* remember where some real-mode handlers are */
+	vcpu->arch.trampoline_lowmem = kvmppc_trampoline_lowmem;
+	vcpu->arch.trampoline_enter = kvmppc_trampoline_enter;
+	vcpu->arch.highmem_handler = (ulong)kvmppc_handler_highmem;
+#ifdef CONFIG_PPC_BOOK3S_64
+	vcpu->arch.rmcall = *(ulong*)kvmppc_rmcall;
+#else
+	vcpu->arch.rmcall = (ulong)kvmppc_rmcall;
+#endif
+
+	vcpu->arch.shadow_msr = MSR_USER64;
+
+	err = kvmppc_mmu_init(vcpu);
+	if (err < 0)
+		goto uninit_vcpu;
+
+	return vcpu;
+
+uninit_vcpu:
+	kvm_vcpu_uninit(vcpu);
+free_shadow_vcpu:
+	kfree(vcpu_book3s->shadow_vcpu);
+free_vcpu:
+	vfree(vcpu_book3s);
+out:
+	return ERR_PTR(err);
+}
+
+void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
+
+	free_page((unsigned long)vcpu->arch.shared & PAGE_MASK);
+	kvm_vcpu_uninit(vcpu);
+	kfree(vcpu_book3s->shadow_vcpu);
+	vfree(vcpu_book3s);
+}
+
+extern int __kvmppc_vcpu_entry(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu);
+int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
+{
+	int ret;
+	double fpr[32][TS_FPRWIDTH];
+	unsigned int fpscr;
+	int fpexc_mode;
+#ifdef CONFIG_ALTIVEC
+	vector128 vr[32];
+	vector128 vscr;
+	unsigned long uninitialized_var(vrsave);
+	int used_vr;
+#endif
+#ifdef CONFIG_VSX
+	int used_vsr;
+#endif
+	ulong ext_msr;
+
+	/* No need to go into the guest when all we do is going out */
+	if (signal_pending(current)) {
+		kvm_run->exit_reason = KVM_EXIT_INTR;
+		return -EINTR;
+	}
+
+	/* Save FPU state in stack */
+	if (current->thread.regs->msr & MSR_FP)
+		giveup_fpu(current);
+	memcpy(fpr, current->thread.fpr, sizeof(current->thread.fpr));
+	fpscr = current->thread.fpscr.val;
+	fpexc_mode = current->thread.fpexc_mode;
+
+#ifdef CONFIG_ALTIVEC
+	/* Save Altivec state in stack */
+	used_vr = current->thread.used_vr;
+	if (used_vr) {
+		if (current->thread.regs->msr & MSR_VEC)
+			giveup_altivec(current);
+		memcpy(vr, current->thread.vr, sizeof(current->thread.vr));
+		vscr = current->thread.vscr;
+		vrsave = current->thread.vrsave;
+	}
+#endif
+
+#ifdef CONFIG_VSX
+	/* Save VSX state in stack */
+	used_vsr = current->thread.used_vsr;
+	if (used_vsr && (current->thread.regs->msr & MSR_VSX))
+			__giveup_vsx(current);
+#endif
+
+	/* Remember the MSR with disabled extensions */
+	ext_msr = current->thread.regs->msr;
+
+	/* XXX we get called with irq disabled - change that! */
+	local_irq_enable();
+
+	/* Preload FPU if it's enabled */
+	if (vcpu->arch.shared->msr & MSR_FP)
+		kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP);
+
+	ret = __kvmppc_vcpu_entry(kvm_run, vcpu);
+
+	local_irq_disable();
+
+	current->thread.regs->msr = ext_msr;
+
+	/* Make sure we save the guest FPU/Altivec/VSX state */
+	kvmppc_giveup_ext(vcpu, MSR_FP);
+	kvmppc_giveup_ext(vcpu, MSR_VEC);
+	kvmppc_giveup_ext(vcpu, MSR_VSX);
+
+	/* Restore FPU state from stack */
+	memcpy(current->thread.fpr, fpr, sizeof(current->thread.fpr));
+	current->thread.fpscr.val = fpscr;
+	current->thread.fpexc_mode = fpexc_mode;
+
+#ifdef CONFIG_ALTIVEC
+	/* Restore Altivec state from stack */
+	if (used_vr && current->thread.used_vr) {
+		memcpy(current->thread.vr, vr, sizeof(current->thread.vr));
+		current->thread.vscr = vscr;
+		current->thread.vrsave = vrsave;
+	}
+	current->thread.used_vr = used_vr;
+#endif
+
+#ifdef CONFIG_VSX
+	current->thread.used_vsr = used_vsr;
+#endif
+
+	return ret;
+}
+
+static int kvmppc_book3s_init(void)
+{
+	int r;
+
+	r = kvm_init(NULL, sizeof(struct kvmppc_vcpu_book3s), 0,
+		     THIS_MODULE);
+
+	if (r)
+		return r;
+
+	r = kvmppc_mmu_hpte_sysinit();
+
+	return r;
+}
+
+static void kvmppc_book3s_exit(void)
+{
+	kvmppc_mmu_hpte_sysexit();
+	kvm_exit();
+}
+
+module_init(kvmppc_book3s_init);
+module_exit(kvmppc_book3s_exit);
-- 
1.7.5.3

[PATCH v2 03/12] powerpc, kvm: Rework KVM checks in first-level interrupt handlers

[Paul Mackerras]

Instead of branching out-of-line with the DO_KVM macro to check if we
are in a KVM guest at the time of an interrupt, this moves the KVM
check inline in the first-level interrupt handlers.  This speeds up
the non-KVM case and makes sure that none of the interrupt handlers
are missing the check.

Because the first-level interrupt handlers are now larger, some things
had to be move out of line in exceptions-64s.S.

This all necessitated some minor changes to the interrupt entry code
in KVM.  This also streamlines the book3s_32 KVM test.

Signed-off-by: Paul Mackerras <paulus@samba.org>
---
 arch/powerpc/include/asm/exception-64s.h   |  121 ++++++++++++------
 arch/powerpc/kernel/exceptions-64s.S       |  189 +++++++++++++++++-----------
 arch/powerpc/kvm/book3s_rmhandlers.S       |   78 ++++++------
 arch/powerpc/kvm/book3s_segment.S          |    7 +
 arch/powerpc/platforms/iseries/exception.S |    2 +-
 arch/powerpc/platforms/iseries/exception.h |    4 +-
 6 files changed, 247 insertions(+), 154 deletions(-)

diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index f5dfe34..b6a3a44 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -61,19 +61,22 @@
 #define EXC_HV	H
 #define EXC_STD
 
-#define EXCEPTION_PROLOG_1(area)					\
+#define __EXCEPTION_PROLOG_1(area, extra, vec)				\
 	GET_PACA(r13);							\
 	std	r9,area+EX_R9(r13);	/* save r9 - r12 */		\
 	std	r10,area+EX_R10(r13);					\
-	std	r11,area+EX_R11(r13);					\
-	std	r12,area+EX_R12(r13);					\
 	BEGIN_FTR_SECTION_NESTED(66);					\
 	mfspr	r10,SPRN_CFAR;						\
 	std	r10,area+EX_CFAR(r13);					\
 	END_FTR_SECTION_NESTED(CPU_FTR_CFAR, CPU_FTR_CFAR, 66);		\
-	GET_SCRATCH0(r9);						\
-	std	r9,area+EX_R13(r13);					\
-	mfcr	r9
+	mfcr	r9;							\
+	extra(vec);							\
+	std	r11,area+EX_R11(r13);					\
+	std	r12,area+EX_R12(r13);					\
+	GET_SCRATCH0(r10);						\
+	std	r10,area+EX_R13(r13)
+#define EXCEPTION_PROLOG_1(area, extra, vec)				\
+	__EXCEPTION_PROLOG_1(area, extra, vec)
 
 #define __EXCEPTION_PROLOG_PSERIES_1(label, h)				\
 	ld	r12,PACAKBASE(r13);	/* get high part of &label */	\
@@ -85,13 +88,54 @@
 	mtspr	SPRN_##h##SRR1,r10;					\
 	h##rfid;							\
 	b	.	/* prevent speculative execution */
-#define EXCEPTION_PROLOG_PSERIES_1(label, h) \
+#define EXCEPTION_PROLOG_PSERIES_1(label, h)				\
 	__EXCEPTION_PROLOG_PSERIES_1(label, h)
 
-#define EXCEPTION_PROLOG_PSERIES(area, label, h)			\
-	EXCEPTION_PROLOG_1(area);					\
+#define EXCEPTION_PROLOG_PSERIES(area, label, h, extra, vec)		\
+	EXCEPTION_PROLOG_1(area, extra, vec);				\
 	EXCEPTION_PROLOG_PSERIES_1(label, h);
 
+#define __KVMTEST(n)							\
+	lbz	r10,PACA_KVM_SVCPU+SVCPU_IN_GUEST(r13);			\
+	cmpwi	r10,0;							\
+	bne	do_kvm_##n
+
+#define __KVM_HANDLER(area, h, n)					\
+do_kvm_##n:								\
+	ld	r10,area+EX_R10(r13);					\
+	stw	r9,PACA_KVM_SVCPU+SVCPU_SCRATCH1(r13);			\
+	ld	r9,area+EX_R9(r13);					\
+	std	r12,PACA_KVM_SVCPU+SVCPU_SCRATCH0(r13);			\
+	li	r12,n;							\
+	b	kvmppc_interrupt
+
+#define __KVM_HANDLER_SKIP(area, h, n)					\
+do_kvm_##n:								\
+	cmpwi	r10,KVM_GUEST_MODE_SKIP;				\
+	ld	r10,area+EX_R10(r13);					\
+	beq	89f;							\
+	stw	r9,PACA_KVM_SVCPU+SVCPU_SCRATCH1(r13);			\
+	ld	r9,area+EX_R9(r13);					\
+	std	r12,PACA_KVM_SVCPU+SVCPU_SCRATCH0(r13);			\
+	li	r12,n;							\
+	b	kvmppc_interrupt;					\
+89:	mtocrf	0x80,r9;						\
+	ld	r9,area+EX_R9(r13);					\
+	b	kvmppc_skip_##h##interrupt
+
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+#define KVMTEST(n)			__KVMTEST(n)
+#define KVM_HANDLER(area, h, n)		__KVM_HANDLER(area, h, n)
+#define KVM_HANDLER_SKIP(area, h, n)	__KVM_HANDLER_SKIP(area, h, n)
+
+#else
+#define KVMTEST(n)
+#define KVM_HANDLER(area, h, n)
+#define KVM_HANDLER_SKIP(area, h, n)
+#endif
+
+#define NOTEST(n)
+
 /*
  * The common exception prolog is used for all except a few exceptions
  * such as a segment miss on a kernel address.  We have to be prepared
@@ -164,57 +208,54 @@
 	.globl label##_pSeries;				\
 label##_pSeries:					\
 	HMT_MEDIUM;					\
-	DO_KVM	vec;					\
 	SET_SCRATCH0(r13);		/* save r13 */		\
-	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common, EXC_STD)
+	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common,	\
+				 EXC_STD, KVMTEST, vec)
 
 #define STD_EXCEPTION_HV(loc, vec, label)		\
 	. = loc;					\
 	.globl label##_hv;				\
 label##_hv:						\
 	HMT_MEDIUM;					\
-	DO_KVM	vec;					\
-	SET_SCRATCH0(r13);	/* save r13 */		\
-	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common, EXC_HV)
+	SET_SCRATCH0(r13);	/* save r13 */			\
+	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common,	\
+				 EXC_HV, KVMTEST, vec)
 
-#define __MASKABLE_EXCEPTION_PSERIES(vec, label, h)			\
-	HMT_MEDIUM;							\
-	DO_KVM	vec;							\
-	SET_SCRATCH0(r13);    /* save r13 */				\
-	GET_PACA(r13);							\
-	std	r9,PACA_EXGEN+EX_R9(r13);	/* save r9, r10 */	\
-	std	r10,PACA_EXGEN+EX_R10(r13);				\
+#define __SOFTEN_TEST(h)						\
 	lbz	r10,PACASOFTIRQEN(r13);					\
-	mfcr	r9;							\
 	cmpwi	r10,0;							\
-	beq	masked_##h##interrupt;					\
-	GET_SCRATCH0(r10);						\
-	std	r10,PACA_EXGEN+EX_R13(r13);				\
-	std	r11,PACA_EXGEN+EX_R11(r13);				\
-	std	r12,PACA_EXGEN+EX_R12(r13);				\
-	ld	r12,PACAKBASE(r13);	/* get high part of &label */	\
-	ld	r10,PACAKMSR(r13);	/* get MSR value for kernel */	\
-	mfspr	r11,SPRN_##h##SRR0;	/* save SRR0 */			\
-	LOAD_HANDLER(r12,label##_common)				\
-	mtspr	SPRN_##h##SRR0,r12;					\
-	mfspr	r12,SPRN_##h##SRR1;	/* and SRR1 */			\
-	mtspr	SPRN_##h##SRR1,r10;					\
-	h##rfid;							\
-	b	.	/* prevent speculative execution */
-#define _MASKABLE_EXCEPTION_PSERIES(vec, label, h)			\
-	__MASKABLE_EXCEPTION_PSERIES(vec, label, h)
+	beq	masked_##h##interrupt
+#define _SOFTEN_TEST(h)	__SOFTEN_TEST(h)
+
+#define SOFTEN_TEST(vec)						\
+	KVMTEST(vec);							\
+	_SOFTEN_TEST(EXC_STD)
+
+#define SOFTEN_TEST_HV(vec)						\
+	KVMTEST(vec);							\
+	_SOFTEN_TEST(EXC_HV)
+
+#define __MASKABLE_EXCEPTION_PSERIES(vec, label, h, extra)		\
+	HMT_MEDIUM;							\
+	SET_SCRATCH0(r13);    /* save r13 */				\
+	__EXCEPTION_PROLOG_1(PACA_EXGEN, extra, vec);		\
+	EXCEPTION_PROLOG_PSERIES_1(label##_common, h);
+#define _MASKABLE_EXCEPTION_PSERIES(vec, label, h, extra)		\
+	__MASKABLE_EXCEPTION_PSERIES(vec, label, h, extra)
 
 #define MASKABLE_EXCEPTION_PSERIES(loc, vec, label)			\
 	. = loc;							\
 	.globl label##_pSeries;						\
 label##_pSeries:							\
-	_MASKABLE_EXCEPTION_PSERIES(vec, label, EXC_STD)
+	_MASKABLE_EXCEPTION_PSERIES(vec, label,				\
+				    EXC_STD, SOFTEN_TEST)
 
 #define MASKABLE_EXCEPTION_HV(loc, vec, label)				\
 	. = loc;							\
 	.globl label##_hv;						\
 label##_hv:								\
-	_MASKABLE_EXCEPTION_PSERIES(vec, label, EXC_HV)
+	_MASKABLE_EXCEPTION_PSERIES(vec, label,				\
+				    EXC_HV, SOFTEN_TEST_HV)
 
 #ifdef CONFIG_PPC_ISERIES
 #define DISABLE_INTS				\
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index a85f487..e0b7987 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -40,7 +40,6 @@ __start_interrupts:
 	.globl system_reset_pSeries;
 system_reset_pSeries:
 	HMT_MEDIUM;
-	DO_KVM	0x100;
 	SET_SCRATCH0(r13)
 #ifdef CONFIG_PPC_P7_NAP
 BEGIN_FTR_SECTION
@@ -65,67 +64,45 @@ BEGIN_FTR_SECTION
 	beq	.
 END_FTR_SECTION_IFSET(CPU_FTR_HVMODE_206)
 #endif /* CONFIG_PPC_P7_NAP */
-	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD)
+	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD,
+				 NOTEST, 0x100)
 
 	. = 0x200
-_machine_check_pSeries:
-	HMT_MEDIUM
-	DO_KVM	0x200
-	SET_SCRATCH0(r13)
-	EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common, EXC_STD)
+machine_check_pSeries_1:
+	/* This is moved out of line as it can be patched by FW, but
+	 * some code path might still want to branch into the original
+	 * vector
+	 */
+	b	machine_check_pSeries
 
 	. = 0x300
 	.globl data_access_pSeries
 data_access_pSeries:
 	HMT_MEDIUM
-	DO_KVM	0x300
 	SET_SCRATCH0(r13)
+#ifndef CONFIG_POWER4_ONLY
 BEGIN_FTR_SECTION
-	GET_PACA(r13)
-	std	r9,PACA_EXSLB+EX_R9(r13)
-	std	r10,PACA_EXSLB+EX_R10(r13)
-	mfspr	r10,SPRN_DAR
-	mfspr	r9,SPRN_DSISR
-	srdi	r10,r10,60
-	rlwimi	r10,r9,16,0x20
-	mfcr	r9
-	cmpwi	r10,0x2c
-	beq	do_stab_bolted_pSeries
-	ld	r10,PACA_EXSLB+EX_R10(r13)
-	std	r11,PACA_EXGEN+EX_R11(r13)
-	ld	r11,PACA_EXSLB+EX_R9(r13)
-	std	r12,PACA_EXGEN+EX_R12(r13)
-	GET_SCRATCH0(r12)
-	std	r10,PACA_EXGEN+EX_R10(r13)
-	std	r11,PACA_EXGEN+EX_R9(r13)
-	std	r12,PACA_EXGEN+EX_R13(r13)
-	EXCEPTION_PROLOG_PSERIES_1(data_access_common, EXC_STD)
-FTR_SECTION_ELSE
-	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common, EXC_STD)
-ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_SLB)
+	b	data_access_check_stab
+data_access_not_stab:
+END_MMU_FTR_SECTION_IFCLR(MMU_FTR_SLB)
+#endif
+	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common, EXC_STD,
+				 KVMTEST, 0x300)
 
 	. = 0x380
 	.globl data_access_slb_pSeries
 data_access_slb_pSeries:
 	HMT_MEDIUM
-	DO_KVM	0x380
 	SET_SCRATCH0(r13)
-	GET_PACA(r13)
+	EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST, 0x380)
 	std	r3,PACA_EXSLB+EX_R3(r13)
 	mfspr	r3,SPRN_DAR
-	std	r9,PACA_EXSLB+EX_R9(r13)	/* save r9 - r12 */
-	mfcr	r9
 #ifdef __DISABLED__
 	/* Keep that around for when we re-implement dynamic VSIDs */
 	cmpdi	r3,0
 	bge	slb_miss_user_pseries
 #endif /* __DISABLED__ */
-	std	r10,PACA_EXSLB+EX_R10(r13)
-	std	r11,PACA_EXSLB+EX_R11(r13)
-	std	r12,PACA_EXSLB+EX_R12(r13)
-	GET_SCRATCH0(r10)
-	std	r10,PACA_EXSLB+EX_R13(r13)
-	mfspr	r12,SPRN_SRR1		/* and SRR1 */
+	mfspr	r12,SPRN_SRR1
 #ifndef CONFIG_RELOCATABLE
 	b	.slb_miss_realmode
 #else
@@ -147,24 +124,16 @@ data_access_slb_pSeries:
 	.globl instruction_access_slb_pSeries
 instruction_access_slb_pSeries:
 	HMT_MEDIUM
-	DO_KVM	0x480
 	SET_SCRATCH0(r13)
-	GET_PACA(r13)
+	EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST, 0x480)
 	std	r3,PACA_EXSLB+EX_R3(r13)
 	mfspr	r3,SPRN_SRR0		/* SRR0 is faulting address */
-	std	r9,PACA_EXSLB+EX_R9(r13)	/* save r9 - r12 */
-	mfcr	r9
 #ifdef __DISABLED__
 	/* Keep that around for when we re-implement dynamic VSIDs */
 	cmpdi	r3,0
 	bge	slb_miss_user_pseries
 #endif /* __DISABLED__ */
-	std	r10,PACA_EXSLB+EX_R10(r13)
-	std	r11,PACA_EXSLB+EX_R11(r13)
-	std	r12,PACA_EXSLB+EX_R12(r13)
-	GET_SCRATCH0(r10)
-	std	r10,PACA_EXSLB+EX_R13(r13)
-	mfspr	r12,SPRN_SRR1		/* and SRR1 */
+	mfspr	r12,SPRN_SRR1
 #ifndef CONFIG_RELOCATABLE
 	b	.slb_miss_realmode
 #else
@@ -184,26 +153,46 @@ instruction_access_slb_pSeries:
 hardware_interrupt_pSeries:
 hardware_interrupt_hv:
 	BEGIN_FTR_SECTION
-		_MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt, EXC_STD)
+		_MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt,
+					    EXC_STD, SOFTEN_TEST)
+		KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x500)
 	FTR_SECTION_ELSE
-		_MASKABLE_EXCEPTION_PSERIES(0x502, hardware_interrupt, EXC_HV)
+		_MASKABLE_EXCEPTION_PSERIES(0x502, hardware_interrupt,
+					    EXC_HV, SOFTEN_TEST_HV)
+		KVM_HANDLER(PACA_EXGEN, EXC_HV, 0x502)
 	ALT_FTR_SECTION_END_IFCLR(CPU_FTR_HVMODE_206)
 
 	STD_EXCEPTION_PSERIES(0x600, 0x600, alignment)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x600)
+
 	STD_EXCEPTION_PSERIES(0x700, 0x700, program_check)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x700)
+
 	STD_EXCEPTION_PSERIES(0x800, 0x800, fp_unavailable)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x800)
 
 	MASKABLE_EXCEPTION_PSERIES(0x900, 0x900, decrementer)
-	MASKABLE_EXCEPTION_HV(0x980, 0x980, decrementer)
+	MASKABLE_EXCEPTION_HV(0x980, 0x982, decrementer)
 
 	STD_EXCEPTION_PSERIES(0xa00, 0xa00, trap_0a)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xa00)
+
 	STD_EXCEPTION_PSERIES(0xb00, 0xb00, trap_0b)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xb00)
 
 	. = 0xc00
 	.globl	system_call_pSeries
 system_call_pSeries:
 	HMT_MEDIUM
-	DO_KVM	0xc00
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+	SET_SCRATCH0(r13)
+	GET_PACA(r13)
+	std	r9,PACA_EXGEN+EX_R9(r13)
+	std	r10,PACA_EXGEN+EX_R10(r13)
+	mfcr	r9
+	KVMTEST(0xc00)
+	GET_SCRATCH0(r13)
+#endif
 BEGIN_FTR_SECTION
 	cmpdi	r0,0x1ebe
 	beq-	1f
@@ -220,6 +209,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)
 	rfid
 	b	.	/* prevent speculative execution */
 
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xc00)
+
 /* Fast LE/BE switch system call */
 1:	mfspr	r12,SPRN_SRR1
 	xori	r12,r12,MSR_LE
@@ -228,6 +219,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)
 	b	.
 
 	STD_EXCEPTION_PSERIES(0xd00, 0xd00, single_step)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xd00)
 
 	/* At 0xe??? we have a bunch of hypervisor exceptions, we branch
 	 * out of line to handle them
@@ -262,30 +254,93 @@ vsx_unavailable_pSeries_1:
 
 #ifdef CONFIG_CBE_RAS
 	STD_EXCEPTION_HV(0x1200, 0x1202, cbe_system_error)
+	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1202)
 #endif /* CONFIG_CBE_RAS */
+
 	STD_EXCEPTION_PSERIES(0x1300, 0x1300, instruction_breakpoint)
+	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x1300)
+
 #ifdef CONFIG_CBE_RAS
 	STD_EXCEPTION_HV(0x1600, 0x1602, cbe_maintenance)
+	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1602)
 #endif /* CONFIG_CBE_RAS */
+
 	STD_EXCEPTION_PSERIES(0x1700, 0x1700, altivec_assist)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x1700)
+
 #ifdef CONFIG_CBE_RAS
 	STD_EXCEPTION_HV(0x1800, 0x1802, cbe_thermal)
+	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1802)
 #endif /* CONFIG_CBE_RAS */
 
 	. = 0x3000
 
 /*** Out of line interrupts support ***/
 
+	/* moved from 0x200 */
+machine_check_pSeries:
+	.globl machine_check_fwnmi
+machine_check_fwnmi:
+	HMT_MEDIUM
+	SET_SCRATCH0(r13)		/* save r13 */
+	EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common,
+				 EXC_STD, KVMTEST, 0x200)
+	KVM_HANDLER_SKIP(PACA_EXMC, EXC_STD, 0x200)
+
+#ifndef CONFIG_POWER4_ONLY
+	/* moved from 0x300 */
+data_access_check_stab:
+	GET_PACA(r13)
+	std	r9,PACA_EXSLB+EX_R9(r13)
+	std	r10,PACA_EXSLB+EX_R10(r13)
+	mfspr	r10,SPRN_DAR
+	mfspr	r9,SPRN_DSISR
+	srdi	r10,r10,60
+	rlwimi	r10,r9,16,0x20
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+	lbz	r9,PACA_KVM_SVCPU+SVCPU_IN_GUEST(r13)
+	rlwimi	r10,r9,8,0x300
+#endif
+	mfcr	r9
+	cmpwi	r10,0x2c
+	beq	do_stab_bolted_pSeries
+	mtcrf	0x80,r9
+	ld	r9,PACA_EXSLB+EX_R9(r13)
+	ld	r10,PACA_EXSLB+EX_R10(r13)
+	b	data_access_not_stab
+do_stab_bolted_pSeries:
+	std	r11,PACA_EXSLB+EX_R11(r13)
+	std	r12,PACA_EXSLB+EX_R12(r13)
+	GET_SCRATCH0(r10)
+	std	r10,PACA_EXSLB+EX_R13(r13)
+	EXCEPTION_PROLOG_PSERIES_1(.do_stab_bolted, EXC_STD)
+#endif /* CONFIG_POWER4_ONLY */
+
+	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x300)
+	KVM_HANDLER_SKIP(PACA_EXSLB, EXC_STD, 0x380)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x400)
+	KVM_HANDLER(PACA_EXSLB, EXC_STD, 0x480)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x900)
+	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0x982)
+
+	.align	7
 	/* moved from 0xe00 */
-	STD_EXCEPTION_HV(., 0xe00, h_data_storage)
-	STD_EXCEPTION_HV(., 0xe20, h_instr_storage)
-	STD_EXCEPTION_HV(., 0xe40, emulation_assist)
-	STD_EXCEPTION_HV(., 0xe60, hmi_exception) /* need to flush cache ? */
+	STD_EXCEPTION_HV(., 0xe02, h_data_storage)
+	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0xe02)
+	STD_EXCEPTION_HV(., 0xe22, h_instr_storage)
+	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe22)
+	STD_EXCEPTION_HV(., 0xe42, emulation_assist)
+	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe42)
+	STD_EXCEPTION_HV(., 0xe62, hmi_exception) /* need to flush cache ? */
+	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe62)
 
 	/* moved from 0xf00 */
 	STD_EXCEPTION_PSERIES(., 0xf00, performance_monitor)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf00)
 	STD_EXCEPTION_PSERIES(., 0xf20, altivec_unavailable)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf20)
 	STD_EXCEPTION_PSERIES(., 0xf40, vsx_unavailable)
+	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf40)
 
 /*
  * An interrupt came in while soft-disabled; clear EE in SRR1,
@@ -317,14 +372,6 @@ masked_Hinterrupt:
 	hrfid
 	b	.
 
-	.align	7
-do_stab_bolted_pSeries:
-	std	r11,PACA_EXSLB+EX_R11(r13)
-	std	r12,PACA_EXSLB+EX_R12(r13)
-	GET_SCRATCH0(r10)
-	std	r10,PACA_EXSLB+EX_R13(r13)
-	EXCEPTION_PROLOG_PSERIES_1(.do_stab_bolted, EXC_STD)
-
 #ifdef CONFIG_PPC_PSERIES
 /*
  * Vectors for the FWNMI option.  Share common code.
@@ -334,14 +381,8 @@ do_stab_bolted_pSeries:
 system_reset_fwnmi:
 	HMT_MEDIUM
 	SET_SCRATCH0(r13)		/* save r13 */
-	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD)
-
-	.globl machine_check_fwnmi
-      .align 7
-machine_check_fwnmi:
-	HMT_MEDIUM
-	SET_SCRATCH0(r13)		/* save r13 */
-	EXCEPTION_PROLOG_PSERIES(PACA_EXMC, machine_check_common, EXC_STD)
+	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD,
+				 NOTEST, 0x100)
 
 #endif /* CONFIG_PPC_PSERIES */
 
diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S
index 1a1b344..6c14efa 100644
--- a/arch/powerpc/kvm/book3s_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_rmhandlers.S
@@ -40,37 +40,42 @@
 #define MSR_NOIRQ		MSR_KERNEL & ~(MSR_IR | MSR_DR)
 #define FUNC(name) 		GLUE(.,name)
 
-#elif defined(CONFIG_PPC_BOOK3S_32)
+kvmppc_skip_interrupt:
+	/*
+	 * Here all GPRs are unchanged from when the interrupt happened
+	 * except for r13, which is saved in SPRG_SCRATCH0.
+	 */
+	mfspr	r13, SPRN_SRR0
+	addi	r13, r13, 4
+	mtspr	SPRN_SRR0, r13
+	GET_SCRATCH0(r13)
+	rfid
+	b	.
+
+kvmppc_skip_Hinterrupt:
+	/*
+	 * Here all GPRs are unchanged from when the interrupt happened
+	 * except for r13, which is saved in SPRG_SCRATCH0.
+	 */
+	mfspr	r13, SPRN_HSRR0
+	addi	r13, r13, 4
+	mtspr	SPRN_HSRR0, r13
+	GET_SCRATCH0(r13)
+	hrfid
+	b	.
 
-#define LOAD_SHADOW_VCPU(reg)						\
-	mfspr	reg, SPRN_SPRG_THREAD;					\
-	lwz	reg, THREAD_KVM_SVCPU(reg);				\
-	/* PPC32 can have a NULL pointer - let's check for that */	\
-	mtspr   SPRN_SPRG_SCRATCH1, r12;	/* Save r12 */		\
-	mfcr	r12;							\
-	cmpwi	reg, 0;							\
-	bne	1f;							\
-	mfspr	reg, SPRN_SPRG_SCRATCH0;				\
-	mtcr	r12;							\
-	mfspr	r12, SPRN_SPRG_SCRATCH1;				\
-	b	kvmppc_resume_\intno;					\
-1:;									\
-	mtcr	r12;							\
-	mfspr	r12, SPRN_SPRG_SCRATCH1;				\
-	tophys(reg, reg)
+#elif defined(CONFIG_PPC_BOOK3S_32)
 
 #define SHADOW_VCPU_OFF		0
 #define MSR_NOIRQ		MSR_KERNEL
 #define FUNC(name)		name
 
-#endif
-
 .macro INTERRUPT_TRAMPOLINE intno
 
 .global kvmppc_trampoline_\intno
 kvmppc_trampoline_\intno:
 
-	SET_SCRATCH0(r13)		/* Save r13 */
+	mtspr	SPRN_SPRG_SCRATCH0, r13		/* Save r13 */
 
 	/*
 	 * First thing to do is to find out if we're coming
@@ -78,19 +83,28 @@ kvmppc_trampoline_\intno:
 	 *
 	 * To distinguish, we check a magic byte in the PACA/current
 	 */
-	LOAD_SHADOW_VCPU(r13)
-	PPC_STL	r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH0)(r13)
+	mfspr	r13, SPRN_SPRG_THREAD
+	lwz	r13, THREAD_KVM_SVCPU(r13)
+	/* PPC32 can have a NULL pointer - let's check for that */
+	mtspr   SPRN_SPRG_SCRATCH1, r12		/* Save r12 */
 	mfcr	r12
+	cmpwi	r13, 0
+	bne	1f
+2:	mtcr	r12
+	mfspr	r12, SPRN_SPRG_SCRATCH1
+	mfspr	r13, SPRN_SPRG_SCRATCH0		/* r13 = original r13 */
+	b	kvmppc_resume_\intno		/* Get back original handler */
+
+1:	tophys(r13, r13)
 	stw	r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH1)(r13)
+	mfspr	r12, SPRN_SPRG_SCRATCH1
+	stw	r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH0)(r13)
 	lbz	r12, (SHADOW_VCPU_OFF + SVCPU_IN_GUEST)(r13)
 	cmpwi	r12, KVM_GUEST_MODE_NONE
 	bne	..kvmppc_handler_hasmagic_\intno
 	/* No KVM guest? Then jump back to the Linux handler! */
 	lwz	r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH1)(r13)
-	mtcr	r12
-	PPC_LL	r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH0)(r13)
-	GET_SCRATCH0(r13)			/* r13 = original r13 */
-	b	kvmppc_resume_\intno		/* Get back original handler */
+	b	2b
 
 	/* Now we know we're handling a KVM guest */
 ..kvmppc_handler_hasmagic_\intno:
@@ -112,9 +126,6 @@ INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_MACHINE_CHECK
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_DATA_STORAGE
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_INST_STORAGE
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_EXTERNAL
-#ifdef CONFIG_PPC_BOOK3S_64
-INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_EXTERNAL_HV
-#endif
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_ALIGNMENT
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_PROGRAM
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_FP_UNAVAIL
@@ -124,14 +135,6 @@ INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_TRACE
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_PERFMON
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_ALTIVEC
 
-/* Those are only available on 64 bit machines */
-
-#ifdef CONFIG_PPC_BOOK3S_64
-INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_DATA_SEGMENT
-INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_INST_SEGMENT
-INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_VSX
-#endif
-
 /*
  * Bring us back to the faulting code, but skip the
  * faulting instruction.
@@ -163,6 +166,7 @@ kvmppc_handler_skip_ins:
 
 	/* And get back into the code */
 	RFI
+#endif
 
 /*
  * This trampoline brings us back to a real mode handler
diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S
index 4512642..4a623eb 100644
--- a/arch/powerpc/kvm/book3s_segment.S
+++ b/arch/powerpc/kvm/book3s_segment.S
@@ -125,6 +125,9 @@ kvmppc_handler_trampoline_enter_end:
 .global kvmppc_handler_trampoline_exit
 kvmppc_handler_trampoline_exit:
 
+.global kvmppc_interrupt
+kvmppc_interrupt:
+
 	/* Register usage at this point:
 	 *
 	 * SPRG_SCRATCH0  = guest R13
@@ -155,12 +158,16 @@ kvmppc_handler_trampoline_exit:
 	PPC_LL	r2, (SHADOW_VCPU_OFF + SVCPU_HOST_R2)(r13)
 
 	/* Save guest PC and MSR */
+#ifdef CONFIG_PPC64
+BEGIN_FTR_SECTION
 	andi.	r0,r12,0x2
 	beq	1f
 	mfspr	r3,SPRN_HSRR0
 	mfspr	r4,SPRN_HSRR1
 	andi.	r12,r12,0x3ffd
 	b	2f
+END_FTR_SECTION_IFSET(CPU_FTR_HVMODE_206)
+#endif
 1:	mfsrr0	r3
 	mfsrr1	r4
 2:
diff --git a/arch/powerpc/platforms/iseries/exception.S b/arch/powerpc/platforms/iseries/exception.S
index 29c02f3..f519ee1 100644
--- a/arch/powerpc/platforms/iseries/exception.S
+++ b/arch/powerpc/platforms/iseries/exception.S
@@ -167,7 +167,7 @@ BEGIN_FTR_SECTION
 	std	r12,PACA_EXGEN+EX_R13(r13)
 	EXCEPTION_PROLOG_ISERIES_1
 FTR_SECTION_ELSE
-	EXCEPTION_PROLOG_1(PACA_EXGEN)
+	EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, 0)
 	EXCEPTION_PROLOG_ISERIES_1
 ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_SLB)
 	b	data_access_common
diff --git a/arch/powerpc/platforms/iseries/exception.h b/arch/powerpc/platforms/iseries/exception.h
index bae3fba..50271b5 100644
--- a/arch/powerpc/platforms/iseries/exception.h
+++ b/arch/powerpc/platforms/iseries/exception.h
@@ -39,7 +39,7 @@
 label##_iSeries:							\
 	HMT_MEDIUM;							\
 	mtspr	SPRN_SPRG_SCRATCH0,r13;	/* save r13 */			\
-	EXCEPTION_PROLOG_1(area);					\
+	EXCEPTION_PROLOG_1(area, NOTEST, 0);				\
 	EXCEPTION_PROLOG_ISERIES_1;					\
 	b	label##_common
 
@@ -48,7 +48,7 @@ label##_iSeries:							\
 label##_iSeries:							\
 	HMT_MEDIUM;							\
 	mtspr	SPRN_SPRG_SCRATCH0,r13;	/* save r13 */			\
-	EXCEPTION_PROLOG_1(PACA_EXGEN);					\
+	EXCEPTION_PROLOG_1(PACA_EXGEN, NOTEST, 0);			\
 	lbz	r10,PACASOFTIRQEN(r13);					\
 	cmpwi	0,r10,0;						\
 	beq-	label##_iSeries_masked;					\
-- 
1.7.5.3

[PATCH v2 04/12] kvm/powerpc: Deliver program interrupts right away instead of queueing them

[Paul Mackerras]

Doing so means that we don't have to save the flags anywhere and gets
rid of the last reference to to_book3s(vcpu) in arch/powerpc/kvm/book3s.c.

Doing so is OK because a program interrupt won't be generated at the
same time as any other synchronous interrupt.  If a program interrupt
and an asynchronous interrupt (external or decrementer) are generated
at the same time, the program interrupt will be delivered, which is
correct because it has a higher priority, and then the asynchronous
interrupt will be masked.

We don't ever generate system reset or machine check interrupts to the
guest, but if we did, then we would need to make sure they got delivered
rather than the program interrupt.  The current code would be wrong in
this situation anyway since it would deliver the program interrupt as
well as the reset/machine check interrupt.

Signed-off-by: Paul Mackerras <paulus@samba.org>
---
 arch/powerpc/kvm/book3s.c |    8 +++-----
 1 files changed, 3 insertions(+), 5 deletions(-)

diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index af63de3..096c711 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -128,8 +128,8 @@ void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec)
 
 void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags)
 {
-	to_book3s(vcpu)->prog_flags = flags;
-	kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_PROGRAM);
+	/* might as well deliver this straight away */
+	kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_PROGRAM, flags);
 }
 
 void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu)
@@ -169,7 +169,6 @@ int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu, unsigned int priority)
 {
 	int deliver = 1;
 	int vec = 0;
-	ulong flags = 0ULL;
 	bool crit = kvmppc_critical_section(vcpu);
 
 	switch (priority) {
@@ -205,7 +204,6 @@ int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu, unsigned int priority)
 		break;
 	case BOOK3S_IRQPRIO_PROGRAM:
 		vec = BOOK3S_INTERRUPT_PROGRAM;
-		flags = to_book3s(vcpu)->prog_flags;
 		break;
 	case BOOK3S_IRQPRIO_VSX:
 		vec = BOOK3S_INTERRUPT_VSX;
@@ -236,7 +234,7 @@ int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu, unsigned int priority)
 #endif
 
 	if (deliver)
-		kvmppc_inject_interrupt(vcpu, vec, flags);
+		kvmppc_inject_interrupt(vcpu, vec, 0);
 
 	return deliver;
 }
-- 
1.7.5.3

[PATCH v2 05/12] kvm/powerpc: Pass init/destroy vm and prepare/commit memory region ops down

[Paul Mackerras]

This arranges for the top-level arch/powerpc/kvm/powerpc.c file to
pass down some of the calls it gets to the lower-level subarchitecture
specific code.  The lower-level implementations (in booke.c and book3s.c)
are no-ops.  The coming book3s_hv.c will need this.

Signed-off-by: Paul Mackerras <paulus@samba.org>
---
 arch/powerpc/include/asm/kvm_ppc.h |    7 +++++++
 arch/powerpc/kvm/book3s_pr.c       |   20 ++++++++++++++++++++
 arch/powerpc/kvm/booke.c           |   20 ++++++++++++++++++++
 arch/powerpc/kvm/powerpc.c         |    9 ++++++---
 4 files changed, 53 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 9345238..3a925fa 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -110,6 +110,13 @@ extern void kvmppc_booke_exit(void);
 extern void kvmppc_core_destroy_mmu(struct kvm_vcpu *vcpu);
 extern int kvmppc_kvm_pv(struct kvm_vcpu *vcpu);
 
+extern int kvmppc_core_init_vm(struct kvm *kvm);
+extern void kvmppc_core_destroy_vm(struct kvm *kvm);
+extern int kvmppc_core_prepare_memory_region(struct kvm *kvm,
+				struct kvm_userspace_memory_region *mem);
+extern void kvmppc_core_commit_memory_region(struct kvm *kvm,
+				struct kvm_userspace_memory_region *mem);
+
 /*
  * Cuts out inst bits with ordering according to spec.
  * That means the leftmost bit is zero. All given bits are included.
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 82df775..82aaf65 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -984,6 +984,26 @@ int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	return ret;
 }
 
+int kvmppc_core_prepare_memory_region(struct kvm *kvm,
+				      struct kvm_userspace_memory_region *mem)
+{
+	return 0;
+}
+
+void kvmppc_core_commit_memory_region(struct kvm *kvm,
+				struct kvm_userspace_memory_region *mem)
+{
+}
+
+int kvmppc_core_init_vm(struct kvm *kvm)
+{
+	return 0;
+}
+
+void kvmppc_core_destroy_vm(struct kvm *kvm)
+{
+}
+
 static int kvmppc_book3s_init(void)
 {
 	int r;
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 8462b3a..7a0bc11 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -770,6 +770,26 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
 	return -ENOTSUPP;
 }
 
+int kvmppc_core_prepare_memory_region(struct kvm *kvm,
+				      struct kvm_userspace_memory_region *mem)
+{
+	return 0;
+}
+
+void kvmppc_core_commit_memory_region(struct kvm *kvm,
+				struct kvm_userspace_memory_region *mem)
+{
+}
+
+int kvmppc_core_init_vm(struct kvm *kvm)
+{
+	return 0;
+}
+
+void kvmppc_core_destroy_vm(struct kvm *kvm)
+{
+}
+
 int __init kvmppc_booke_init(void)
 {
 	unsigned long ivor[16];
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 616dd51..216905b 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -147,7 +147,7 @@ void kvm_arch_check_processor_compat(void *rtn)
 
 int kvm_arch_init_vm(struct kvm *kvm)
 {
-	return 0;
+	return kvmppc_core_init_vm(kvm);
 }
 
 void kvm_arch_destroy_vm(struct kvm *kvm)
@@ -163,6 +163,9 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 		kvm->vcpus[i] = NULL;
 
 	atomic_set(&kvm->online_vcpus, 0);
+
+	kvmppc_core_destroy_vm(kvm);
+
 	mutex_unlock(&kvm->lock);
 }
 
@@ -211,7 +214,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
                                    struct kvm_userspace_memory_region *mem,
                                    int user_alloc)
 {
-	return 0;
+	return kvmppc_core_prepare_memory_region(kvm, mem);
 }
 
 void kvm_arch_commit_memory_region(struct kvm *kvm,
@@ -219,7 +222,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
                struct kvm_memory_slot old,
                int user_alloc)
 {
-       return;
+	kvmppc_core_commit_memory_region(kvm, mem);
 }
 
 
-- 
1.7.5.3

[PATCH v2 06/12] kvm/powerpc: Move guest enter/exit down into subarch-specific code

[Paul Mackerras]

Instead of doing the kvm_guest_enter/exit() and local_irq_dis/enable()
calls in powerpc.c, this moves them down into the subarch-specific
book3s_pr.c and booke.c.  This eliminates an extra local_irq_enable()
call in book3s_pr.c, and will be needed for when we do SMT4 guest
support in the book3s hypervisor mode code.

Signed-off-by: Paul Mackerras <paulus@samba.org>
---
 arch/powerpc/include/asm/kvm_ppc.h   |    1 +
 arch/powerpc/kvm/book3s_interrupts.S |    2 +-
 arch/powerpc/kvm/book3s_pr.c         |   12 ++++++------
 arch/powerpc/kvm/booke.c             |   13 +++++++++++++
 arch/powerpc/kvm/powerpc.c           |    6 +-----
 5 files changed, 22 insertions(+), 12 deletions(-)

diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 3a925fa..c3dde27 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -42,6 +42,7 @@ enum emulation_result {
 	EMULATE_AGAIN,        /* something went wrong. go again */
 };
 
+extern int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu);
 extern int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu);
 extern char kvmppc_handlers_start[];
 extern unsigned long kvmppc_handler_len;
diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S
index 2f0bc92..8c5e0e1 100644
--- a/arch/powerpc/kvm/book3s_interrupts.S
+++ b/arch/powerpc/kvm/book3s_interrupts.S
@@ -85,7 +85,7 @@
  *  r3: kvm_run pointer
  *  r4: vcpu pointer
  */
-_GLOBAL(__kvmppc_vcpu_entry)
+_GLOBAL(__kvmppc_vcpu_run)
 
 kvm_start_entry:
 	/* Write correct stack frame */
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 82aaf65..f0de167 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -891,8 +891,7 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 	vfree(vcpu_book3s);
 }
 
-extern int __kvmppc_vcpu_entry(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu);
-int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
+int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 {
 	int ret;
 	double fpr[32][TS_FPRWIDTH];
@@ -944,14 +943,15 @@ int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	/* Remember the MSR with disabled extensions */
 	ext_msr = current->thread.regs->msr;
 
-	/* XXX we get called with irq disabled - change that! */
-	local_irq_enable();
-
 	/* Preload FPU if it's enabled */
 	if (vcpu->arch.shared->msr & MSR_FP)
 		kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP);
 
-	ret = __kvmppc_vcpu_entry(kvm_run, vcpu);
+	kvm_guest_enter();
+
+	ret = __kvmppc_vcpu_run(kvm_run, vcpu);
+
+	kvm_guest_exit();
 
 	local_irq_disable();
 
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 7a0bc11..39c34c6 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -257,6 +257,19 @@ void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu)
 		vcpu->arch.shared->int_pending = 0;
 }
 
+int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
+{
+	int ret;
+
+	local_irq_disable();
+	kvm_guest_enter();
+	ret = __kvmppc_vcpu_run(kvm_run, vcpu);
+	kvm_guest_exit();
+	local_irq_enable();
+
+	return ret;
+}
+
 /**
  * kvmppc_handle_exit
  *
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 216905b..74179b9 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -499,11 +499,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 	kvmppc_core_deliver_interrupts(vcpu);
 
-	local_irq_disable();
-	kvm_guest_enter();
-	r = __kvmppc_vcpu_run(run, vcpu);
-	kvm_guest_exit();
-	local_irq_enable();
+	r = kvmppc_vcpu_run(run, vcpu);
 
 	if (vcpu->sigset_active)
 		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
-- 
1.7.5.3

[PATCH v2 07/12] powerpc: Set up LPCR for running guest partitions

[Paul Mackerras]

In hypervisor mode, the LPCR controls several aspects of guest
partitions, including virtual partition memory mode, and also controls
whether the hypervisor decrementer interrupts are enabled.  This sets
up LPCR at boot time so that guest partitions will use a virtual real
memory area (VRMA) composed of 16MB large pages, and hypervisor
decrementer interrupts are disabled.

Signed-off-by: Paul Mackerras <paulus@samba.org>
---
 arch/powerpc/include/asm/reg.h         |    4 ++++
 arch/powerpc/kernel/cpu_setup_power7.S |   18 +++++++++++-------
 2 files changed, 15 insertions(+), 7 deletions(-)

diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index c5cae0d..d879a6b 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -232,10 +232,12 @@
 #define   LPCR_VPM0	(1ul << (63-0))
 #define   LPCR_VPM1	(1ul << (63-1))
 #define   LPCR_ISL	(1ul << (63-2))
+#define   LPCR_VC_SH	(63-2)
 #define   LPCR_DPFD_SH	(63-11)
 #define   LPCR_VRMA_L	(1ul << (63-12))
 #define   LPCR_VRMA_LP0	(1ul << (63-15))
 #define   LPCR_VRMA_LP1	(1ul << (63-16))
+#define   LPCR_VRMASD_SH (63-16)
 #define   LPCR_RMLS    0x1C000000      /* impl dependent rmo limit sel */
 #define   LPCR_ILE     0x02000000      /* !HV irqs set MSR:LE */
 #define   LPCR_PECE	0x00007000	/* powersave exit cause enable */
@@ -243,8 +245,10 @@
 #define     LPCR_PECE1	0x00002000	/* decrementer can cause exit */
 #define     LPCR_PECE2	0x00001000	/* machine check etc can cause exit */
 #define   LPCR_MER	0x00000800	/* Mediated External Exception */
+#define   LPCR_LPES    0x0000000c
 #define   LPCR_LPES0   0x00000008      /* LPAR Env selector 0 */
 #define   LPCR_LPES1   0x00000004      /* LPAR Env selector 1 */
+#define   LPCR_LPES_SH	2
 #define   LPCR_RMI     0x00000002      /* real mode is cache inhibit */
 #define   LPCR_HDICE   0x00000001      /* Hyp Decr enable (HV,PR,EE) */
 #define SPRN_LPID	0x13F	/* Logical Partition Identifier */
diff --git a/arch/powerpc/kernel/cpu_setup_power7.S b/arch/powerpc/kernel/cpu_setup_power7.S
index 4f9a93f..2ef6749 100644
--- a/arch/powerpc/kernel/cpu_setup_power7.S
+++ b/arch/powerpc/kernel/cpu_setup_power7.S
@@ -61,19 +61,23 @@ __init_LPCR:
 	 *   LPES = 0b01 (HSRR0/1 used for 0x500)
 	 *   PECE = 0b111
 	 *   DPFD = 4
+	 *   HDICE = 0
+	 *   VC = 0b100 (VPM0=1, VPM1=0, ISL=0)
+	 *   VRMASD = 0b10000 (L=1, LP=00)
 	 *
 	 * Other bits untouched for now
 	 */
 	mfspr	r3,SPRN_LPCR
-	ori	r3,r3,(LPCR_LPES0|LPCR_LPES1)
-	xori	r3,r3, LPCR_LPES0
+	li	r5,1
+	rldimi	r3,r5, LPCR_LPES_SH, 64-LPCR_LPES_SH-2
 	ori	r3,r3,(LPCR_PECE0|LPCR_PECE1|LPCR_PECE2)
-	li	r5,7
-	sldi	r5,r5,LPCR_DPFD_SH
-	andc	r3,r3,r5
 	li	r5,4
-	sldi	r5,r5,LPCR_DPFD_SH
-	or	r3,r3,r5
+	rldimi	r3,r5, LPCR_DPFD_SH, 64-LPCR_DPFD_SH-3
+	clrrdi	r3,r3,1		/* clear HDICE */
+	li	r5,4
+	rldimi	r3,r5, LPCR_VC_SH, 0
+	li	r5,0x10
+	rldimi	r3,r5, LPCR_VRMASD_SH, 64-LPCR_VRMASD_SH-5
 	mtspr	SPRN_LPCR,r3
 	isync
 	blr
-- 
1.7.5.3

[PATCH v2 08/12] kvm/powerpc: Split host-state fields out of kvmppc_book3s_shadow_vcpu

[Paul Mackerras]

There are several fields in struct kvmppc_book3s_shadow_vcpu that
temporarily store bits of host state while a guest is running,
rather than anything relating to the particular guest or vcpu.
This splits them out into a new kvmppc_host_state structure and
modifies the definitions in asm-offsets.c to suit.

On 32-bit, we have a kvmppc_host_state structure inside the
kvmppc_book3s_shadow_vcpu since the assembly code needs to be able
to get to them both with one pointer.  On 64-bit they are separate
fields in the PACA.  This means that on 64-bit we don't need to
copy the kvmppc_host_state in and out on vcpu load/unload, and
in future will mean that the book3s_hv code doesn't need a
shadow_vcpu struct in the PACA at all.

Signed-off-by: Paul Mackerras <paulus@samba.org>
---
 arch/powerpc/include/asm/exception-64s.h  |   10 ++--
 arch/powerpc/include/asm/kvm_book3s_asm.h |   27 ++++++---
 arch/powerpc/include/asm/paca.h           |    1 +
 arch/powerpc/kernel/asm-offsets.c         |   94 ++++++++++++++--------------
 arch/powerpc/kvm/book3s_interrupts.S      |   17 +++---
 arch/powerpc/kvm/book3s_rmhandlers.S      |   18 +++---
 arch/powerpc/kvm/book3s_segment.S         |   72 +++++++++++-----------
 7 files changed, 124 insertions(+), 115 deletions(-)

diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index b6a3a44..296c9b6 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -96,16 +96,16 @@
 	EXCEPTION_PROLOG_PSERIES_1(label, h);
 
 #define __KVMTEST(n)							\
-	lbz	r10,PACA_KVM_SVCPU+SVCPU_IN_GUEST(r13);			\
+	lbz	r10,HSTATE_IN_GUEST(r13);			\
 	cmpwi	r10,0;							\
 	bne	do_kvm_##n
 
 #define __KVM_HANDLER(area, h, n)					\
 do_kvm_##n:								\
 	ld	r10,area+EX_R10(r13);					\
-	stw	r9,PACA_KVM_SVCPU+SVCPU_SCRATCH1(r13);			\
+	stw	r9,HSTATE_SCRATCH1(r13);			\
 	ld	r9,area+EX_R9(r13);					\
-	std	r12,PACA_KVM_SVCPU+SVCPU_SCRATCH0(r13);			\
+	std	r12,HSTATE_SCRATCH0(r13);			\
 	li	r12,n;							\
 	b	kvmppc_interrupt
 
@@ -114,9 +114,9 @@ do_kvm_##n:								\
 	cmpwi	r10,KVM_GUEST_MODE_SKIP;				\
 	ld	r10,area+EX_R10(r13);					\
 	beq	89f;							\
-	stw	r9,PACA_KVM_SVCPU+SVCPU_SCRATCH1(r13);			\
+	stw	r9,HSTATE_SCRATCH1(r13);			\
 	ld	r9,area+EX_R9(r13);					\
-	std	r12,PACA_KVM_SVCPU+SVCPU_SCRATCH0(r13);			\
+	std	r12,HSTATE_SCRATCH0(r13);			\
 	li	r12,n;							\
 	b	kvmppc_interrupt;					\
 89:	mtocrf	0x80,r9;						\
diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h
index d5a8a38..3126175 100644
--- a/arch/powerpc/include/asm/kvm_book3s_asm.h
+++ b/arch/powerpc/include/asm/kvm_book3s_asm.h
@@ -60,6 +60,22 @@ kvmppc_resume_\intno:
 
 #else  /*__ASSEMBLY__ */
 
+/*
+ * This struct goes in the PACA on 64-bit processors.  It is used
+ * to store host state that needs to be saved when we enter a guest
+ * and restored when we exit, but isn't specific to any particular
+ * guest or vcpu.  It also has some scratch fields used by the guest
+ * exit code.
+ */
+struct kvmppc_host_state {
+	ulong host_r1;
+	ulong host_r2;
+	ulong vmhandler;
+	ulong scratch0;
+	ulong scratch1;
+	u8 in_guest;
+};
+
 struct kvmppc_book3s_shadow_vcpu {
 	ulong gpr[14];
 	u32 cr;
@@ -73,17 +89,12 @@ struct kvmppc_book3s_shadow_vcpu {
 	ulong shadow_srr1;
 	ulong fault_dar;
 
-	ulong host_r1;
-	ulong host_r2;
-	ulong handler;
-	ulong scratch0;
-	ulong scratch1;
-	ulong vmhandler;
-	u8 in_guest;
-
 #ifdef CONFIG_PPC_BOOK3S_32
 	u32     sr[16];			/* Guest SRs */
+
+	struct kvmppc_host_state hstate;
 #endif
+
 #ifdef CONFIG_PPC_BOOK3S_64
 	u8 slb_max;			/* highest used guest slb entry */
 	struct  {
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 7412676..58f4a18 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -149,6 +149,7 @@ struct paca_struct {
 #ifdef CONFIG_KVM_BOOK3S_HANDLER
 	/* We use this to store guest state in */
 	struct kvmppc_book3s_shadow_vcpu shadow_vcpu;
+	struct kvmppc_host_state kvm_hstate;
 #endif
 };
 
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 36e1c8a..61064207 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -198,11 +198,6 @@ int main(void)
 	DEFINE(PACA_USER_TIME, offsetof(struct paca_struct, user_time));
 	DEFINE(PACA_SYSTEM_TIME, offsetof(struct paca_struct, system_time));
 	DEFINE(PACA_TRAP_SAVE, offsetof(struct paca_struct, trap_save));
-#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
-	DEFINE(PACA_KVM_SVCPU, offsetof(struct paca_struct, shadow_vcpu));
-	DEFINE(SVCPU_SLB, offsetof(struct kvmppc_book3s_shadow_vcpu, slb));
-	DEFINE(SVCPU_SLB_MAX, offsetof(struct kvmppc_book3s_shadow_vcpu, slb_max));
-#endif
 #endif /* CONFIG_PPC64 */
 
 	/* RTAS */
@@ -415,49 +410,54 @@ int main(void)
 	DEFINE(VCPU_HIGHMEM_HANDLER, offsetof(struct kvm_vcpu, arch.highmem_handler));
 	DEFINE(VCPU_RMCALL, offsetof(struct kvm_vcpu, arch.rmcall));
 	DEFINE(VCPU_HFLAGS, offsetof(struct kvm_vcpu, arch.hflags));
-	DEFINE(VCPU_SVCPU, offsetof(struct kvmppc_vcpu_book3s, shadow_vcpu) -
-			   offsetof(struct kvmppc_vcpu_book3s, vcpu));
-	DEFINE(SVCPU_CR, offsetof(struct kvmppc_book3s_shadow_vcpu, cr));
-	DEFINE(SVCPU_XER, offsetof(struct kvmppc_book3s_shadow_vcpu, xer));
-	DEFINE(SVCPU_CTR, offsetof(struct kvmppc_book3s_shadow_vcpu, ctr));
-	DEFINE(SVCPU_LR, offsetof(struct kvmppc_book3s_shadow_vcpu, lr));
-	DEFINE(SVCPU_PC, offsetof(struct kvmppc_book3s_shadow_vcpu, pc));
-	DEFINE(SVCPU_R0, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[0]));
-	DEFINE(SVCPU_R1, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[1]));
-	DEFINE(SVCPU_R2, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[2]));
-	DEFINE(SVCPU_R3, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[3]));
-	DEFINE(SVCPU_R4, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[4]));
-	DEFINE(SVCPU_R5, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[5]));
-	DEFINE(SVCPU_R6, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[6]));
-	DEFINE(SVCPU_R7, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[7]));
-	DEFINE(SVCPU_R8, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[8]));
-	DEFINE(SVCPU_R9, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[9]));
-	DEFINE(SVCPU_R10, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[10]));
-	DEFINE(SVCPU_R11, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[11]));
-	DEFINE(SVCPU_R12, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[12]));
-	DEFINE(SVCPU_R13, offsetof(struct kvmppc_book3s_shadow_vcpu, gpr[13]));
-	DEFINE(SVCPU_HOST_R1, offsetof(struct kvmppc_book3s_shadow_vcpu, host_r1));
-	DEFINE(SVCPU_HOST_R2, offsetof(struct kvmppc_book3s_shadow_vcpu, host_r2));
-	DEFINE(SVCPU_VMHANDLER, offsetof(struct kvmppc_book3s_shadow_vcpu,
-					 vmhandler));
-	DEFINE(SVCPU_SCRATCH0, offsetof(struct kvmppc_book3s_shadow_vcpu,
-					scratch0));
-	DEFINE(SVCPU_SCRATCH1, offsetof(struct kvmppc_book3s_shadow_vcpu,
-					scratch1));
-	DEFINE(SVCPU_IN_GUEST, offsetof(struct kvmppc_book3s_shadow_vcpu,
-					in_guest));
-	DEFINE(SVCPU_FAULT_DSISR, offsetof(struct kvmppc_book3s_shadow_vcpu,
-					   fault_dsisr));
-	DEFINE(SVCPU_FAULT_DAR, offsetof(struct kvmppc_book3s_shadow_vcpu,
-					 fault_dar));
-	DEFINE(SVCPU_LAST_INST, offsetof(struct kvmppc_book3s_shadow_vcpu,
-					 last_inst));
-	DEFINE(SVCPU_SHADOW_SRR1, offsetof(struct kvmppc_book3s_shadow_vcpu,
-					   shadow_srr1));
+
+#ifdef CONFIG_PPC_BOOK3S_64
+# define SVCPU_FIELD(x, f)	DEFINE(x, offsetof(struct paca_struct, shadow_vcpu.f))
+# define HSTATE_FIELD(x, f)	DEFINE(x, offsetof(struct paca_struct, kvm_hstate.f))
+#else	/* 32-bit */
+# define SVCPU_FIELD(x, f)	DEFINE(x, offsetof(struct kvmppc_book3s_shadow_vcpu, f))
+# define HSTATE_FIELD(x, f)	DEFINE(x, offsetof(struct kvmppc_book3s_shadow_vcpu, hstate.f))
+#endif
+
+	SVCPU_FIELD(SVCPU_CR, cr);
+	SVCPU_FIELD(SVCPU_XER, xer);
+	SVCPU_FIELD(SVCPU_CTR, ctr);
+	SVCPU_FIELD(SVCPU_LR, lr);
+	SVCPU_FIELD(SVCPU_PC, pc);
+	SVCPU_FIELD(SVCPU_R0, gpr[0]);
+	SVCPU_FIELD(SVCPU_R1, gpr[1]);
+	SVCPU_FIELD(SVCPU_R2, gpr[2]);
+	SVCPU_FIELD(SVCPU_R3, gpr[3]);
+	SVCPU_FIELD(SVCPU_R4, gpr[4]);
+	SVCPU_FIELD(SVCPU_R5, gpr[5]);
+	SVCPU_FIELD(SVCPU_R6, gpr[6]);
+	SVCPU_FIELD(SVCPU_R7, gpr[7]);
+	SVCPU_FIELD(SVCPU_R8, gpr[8]);
+	SVCPU_FIELD(SVCPU_R9, gpr[9]);
+	SVCPU_FIELD(SVCPU_R10, gpr[10]);
+	SVCPU_FIELD(SVCPU_R11, gpr[11]);
+	SVCPU_FIELD(SVCPU_R12, gpr[12]);
+	SVCPU_FIELD(SVCPU_R13, gpr[13]);
+	SVCPU_FIELD(SVCPU_FAULT_DSISR, fault_dsisr);
+	SVCPU_FIELD(SVCPU_FAULT_DAR, fault_dar);
+	SVCPU_FIELD(SVCPU_LAST_INST, last_inst);
+	SVCPU_FIELD(SVCPU_SHADOW_SRR1, shadow_srr1);
 #ifdef CONFIG_PPC_BOOK3S_32
-	DEFINE(SVCPU_SR, offsetof(struct kvmppc_book3s_shadow_vcpu, sr));
+	SVCPU_FIELD(SVCPU_SR, sr);
 #endif
-#else
+#ifdef CONFIG_PPC64
+	SVCPU_FIELD(SVCPU_SLB, slb);
+	SVCPU_FIELD(SVCPU_SLB_MAX, slb_max);
+#endif
+
+	HSTATE_FIELD(HSTATE_HOST_R1, host_r1);
+	HSTATE_FIELD(HSTATE_HOST_R2, host_r2);
+	HSTATE_FIELD(HSTATE_VMHANDLER, vmhandler);
+	HSTATE_FIELD(HSTATE_SCRATCH0, scratch0);
+	HSTATE_FIELD(HSTATE_SCRATCH1, scratch1);
+	HSTATE_FIELD(HSTATE_IN_GUEST, in_guest);
+
+#else /* CONFIG_PPC_BOOK3S */
 	DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr));
 	DEFINE(VCPU_XER, offsetof(struct kvm_vcpu, arch.xer));
 	DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr));
@@ -467,7 +467,7 @@ int main(void)
 	DEFINE(VCPU_FAULT_DEAR, offsetof(struct kvm_vcpu, arch.fault_dear));
 	DEFINE(VCPU_FAULT_ESR, offsetof(struct kvm_vcpu, arch.fault_esr));
 #endif /* CONFIG_PPC_BOOK3S */
-#endif
+#endif /* CONFIG_KVM */
 
 #ifdef CONFIG_KVM_GUEST
 	DEFINE(KVM_MAGIC_SCRATCH1, offsetof(struct kvm_vcpu_arch_shared,
diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S
index 8c5e0e1..91c6de6 100644
--- a/arch/powerpc/kvm/book3s_interrupts.S
+++ b/arch/powerpc/kvm/book3s_interrupts.S
@@ -29,8 +29,7 @@
 #define ULONG_SIZE 		8
 #define FUNC(name) 		GLUE(.,name)
 
-#define GET_SHADOW_VCPU(reg)    \
-        addi    reg, r13, PACA_KVM_SVCPU
+#define GET_SHADOW_VCPU_R13
 
 #define DISABLE_INTERRUPTS	\
 	mfmsr   r0;		\
@@ -43,8 +42,8 @@
 #define ULONG_SIZE              4
 #define FUNC(name)		name
 
-#define GET_SHADOW_VCPU(reg)    \
-        lwz     reg, (THREAD + THREAD_KVM_SVCPU)(r2)
+#define GET_SHADOW_VCPU_R13	\
+	lwz	r13, (THREAD + THREAD_KVM_SVCPU)(r2)
 
 #define DISABLE_INTERRUPTS	\
 	mfmsr   r0;		\
@@ -107,15 +106,15 @@ kvm_start_entry:
 	/* Load non-volatile guest state from the vcpu */
 	VCPU_LOAD_NVGPRS(r4)
 
-	GET_SHADOW_VCPU(r5)
+	GET_SHADOW_VCPU_R13
 
-	/* Save R1/R2 in the PACA */
-	PPC_STL	r1, SVCPU_HOST_R1(r5)
-	PPC_STL	r2, SVCPU_HOST_R2(r5)
+	/* Save R1/R2 in the PACA (64-bit) or shadow_vcpu (32-bit) */
+	PPC_STL	r1, HSTATE_HOST_R1(r13)
+	PPC_STL	r2, HSTATE_HOST_R2(r13)
 
 	/* XXX swap in/out on load? */
 	PPC_LL	r3, VCPU_HIGHMEM_HANDLER(r4)
-	PPC_STL	r3, SVCPU_VMHANDLER(r5)
+	PPC_STL	r3, HSTATE_VMHANDLER(r13)
 
 kvm_start_lightweight:
 
diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S
index 6c14efa..789f050 100644
--- a/arch/powerpc/kvm/book3s_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_rmhandlers.S
@@ -36,7 +36,6 @@
 #if defined(CONFIG_PPC_BOOK3S_64)
 
 #define LOAD_SHADOW_VCPU(reg)	GET_PACA(reg)					
-#define SHADOW_VCPU_OFF		PACA_KVM_SVCPU
 #define MSR_NOIRQ		MSR_KERNEL & ~(MSR_IR | MSR_DR)
 #define FUNC(name) 		GLUE(.,name)
 
@@ -66,7 +65,6 @@ kvmppc_skip_Hinterrupt:
 
 #elif defined(CONFIG_PPC_BOOK3S_32)
 
-#define SHADOW_VCPU_OFF		0
 #define MSR_NOIRQ		MSR_KERNEL
 #define FUNC(name)		name
 
@@ -96,14 +94,14 @@ kvmppc_trampoline_\intno:
 	b	kvmppc_resume_\intno		/* Get back original handler */
 
 1:	tophys(r13, r13)
-	stw	r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH1)(r13)
+	stw	r12, HSTATE_SCRATCH1(r13)
 	mfspr	r12, SPRN_SPRG_SCRATCH1
-	stw	r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH0)(r13)
-	lbz	r12, (SHADOW_VCPU_OFF + SVCPU_IN_GUEST)(r13)
+	stw	r12, HSTATE_SCRATCH0(r13)
+	lbz	r12, HSTATE_IN_GUEST(r13)
 	cmpwi	r12, KVM_GUEST_MODE_NONE
 	bne	..kvmppc_handler_hasmagic_\intno
 	/* No KVM guest? Then jump back to the Linux handler! */
-	lwz	r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH1)(r13)
+	lwz	r12, HSTATE_SCRATCH1(r13)
 	b	2b
 
 	/* Now we know we're handling a KVM guest */
@@ -146,8 +144,8 @@ INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_ALTIVEC
  *
  * R12            = free
  * R13            = Shadow VCPU (PACA)
- * SVCPU.SCRATCH0 = guest R12
- * SVCPU.SCRATCH1 = guest CR
+ * HSTATE.SCRATCH0 = guest R12
+ * HSTATE.SCRATCH1 = guest CR
  * SPRG_SCRATCH0  = guest R13
  *
  */
@@ -159,9 +157,9 @@ kvmppc_handler_skip_ins:
 	mtsrr0	r12
 
 	/* Clean up all state */
-	lwz	r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH1)(r13)
+	lwz	r12, HSTATE_SCRATCH1(r13)
 	mtcr	r12
-	PPC_LL	r12, (SHADOW_VCPU_OFF + SVCPU_SCRATCH0)(r13)
+	PPC_LL	r12, HSTATE_SCRATCH0(r13)
 	GET_SCRATCH0(r13)
 
 	/* And get back into the code */
diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S
index 4a623eb..b0ae527 100644
--- a/arch/powerpc/kvm/book3s_segment.S
+++ b/arch/powerpc/kvm/book3s_segment.S
@@ -22,7 +22,7 @@
 #if defined(CONFIG_PPC_BOOK3S_64)
 
 #define GET_SHADOW_VCPU(reg)    \
-	addi    reg, r13, PACA_KVM_SVCPU
+	mr	reg, r13
 
 #elif defined(CONFIG_PPC_BOOK3S_32)
 
@@ -78,7 +78,7 @@ kvmppc_handler_trampoline_enter:
 
 	/* Activate guest mode, so faults get handled by KVM */
 	li	r11, KVM_GUEST_MODE_GUEST
-	stb	r11, SVCPU_IN_GUEST(r3)
+	stb	r11, HSTATE_IN_GUEST(r3)
 
 	/* Switch to guest segment. This is subarch specific. */
 	LOAD_GUEST_SEGMENTS
@@ -132,30 +132,30 @@ kvmppc_interrupt:
 	 *
 	 * SPRG_SCRATCH0  = guest R13
 	 * R12            = exit handler id
-	 * R13            = shadow vcpu - SHADOW_VCPU_OFF [=PACA on PPC64]
-	 * SVCPU.SCRATCH0 = guest R12
-	 * SVCPU.SCRATCH1 = guest CR
+	 * R13            = shadow vcpu (32-bit) or PACA (64-bit)
+	 * HSTATE.SCRATCH0 = guest R12
+	 * HSTATE.SCRATCH1 = guest CR
 	 *
 	 */
 
 	/* Save registers */
 
-	PPC_STL	r0, (SHADOW_VCPU_OFF + SVCPU_R0)(r13)
-	PPC_STL	r1, (SHADOW_VCPU_OFF + SVCPU_R1)(r13)
-	PPC_STL	r2, (SHADOW_VCPU_OFF + SVCPU_R2)(r13)
-	PPC_STL	r3, (SHADOW_VCPU_OFF + SVCPU_R3)(r13)
-	PPC_STL	r4, (SHADOW_VCPU_OFF + SVCPU_R4)(r13)
-	PPC_STL	r5, (SHADOW_VCPU_OFF + SVCPU_R5)(r13)
-	PPC_STL	r6, (SHADOW_VCPU_OFF + SVCPU_R6)(r13)
-	PPC_STL	r7, (SHADOW_VCPU_OFF + SVCPU_R7)(r13)
-	PPC_STL	r8, (SHADOW_VCPU_OFF + SVCPU_R8)(r13)
-	PPC_STL	r9, (SHADOW_VCPU_OFF + SVCPU_R9)(r13)
-	PPC_STL	r10, (SHADOW_VCPU_OFF + SVCPU_R10)(r13)
-	PPC_STL	r11, (SHADOW_VCPU_OFF + SVCPU_R11)(r13)
+	PPC_STL	r0, SVCPU_R0(r13)
+	PPC_STL	r1, SVCPU_R1(r13)
+	PPC_STL	r2, SVCPU_R2(r13)
+	PPC_STL	r3, SVCPU_R3(r13)
+	PPC_STL	r4, SVCPU_R4(r13)
+	PPC_STL	r5, SVCPU_R5(r13)
+	PPC_STL	r6, SVCPU_R6(r13)
+	PPC_STL	r7, SVCPU_R7(r13)
+	PPC_STL	r8, SVCPU_R8(r13)
+	PPC_STL	r9, SVCPU_R9(r13)
+	PPC_STL	r10, SVCPU_R10(r13)
+	PPC_STL	r11, SVCPU_R11(r13)
 
 	/* Restore R1/R2 so we can handle faults */
-	PPC_LL	r1, (SHADOW_VCPU_OFF + SVCPU_HOST_R1)(r13)
-	PPC_LL	r2, (SHADOW_VCPU_OFF + SVCPU_HOST_R2)(r13)
+	PPC_LL	r1, HSTATE_HOST_R1(r13)
+	PPC_LL	r2, HSTATE_HOST_R2(r13)
 
 	/* Save guest PC and MSR */
 #ifdef CONFIG_PPC64
@@ -171,17 +171,17 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE_206)
 1:	mfsrr0	r3
 	mfsrr1	r4
 2:
-	PPC_STL	r3, (SHADOW_VCPU_OFF + SVCPU_PC)(r13)
-	PPC_STL	r4, (SHADOW_VCPU_OFF + SVCPU_SHADOW_SRR1)(r13)
+	PPC_STL	r3, SVCPU_PC(r13)
+	PPC_STL	r4, SVCPU_SHADOW_SRR1(r13)
 
 	/* Get scratch'ed off registers */
 	GET_SCRATCH0(r9)
-	PPC_LL	r8, (SHADOW_VCPU_OFF + SVCPU_SCRATCH0)(r13)
-	lwz	r7, (SHADOW_VCPU_OFF + SVCPU_SCRATCH1)(r13)
+	PPC_LL	r8, HSTATE_SCRATCH0(r13)
+	lwz	r7, HSTATE_SCRATCH1(r13)
 
-	PPC_STL	r9, (SHADOW_VCPU_OFF + SVCPU_R13)(r13)
-	PPC_STL	r8, (SHADOW_VCPU_OFF + SVCPU_R12)(r13)
-	stw	r7, (SHADOW_VCPU_OFF + SVCPU_CR)(r13)
+	PPC_STL	r9, SVCPU_R13(r13)
+	PPC_STL	r8, SVCPU_R12(r13)
+	stw	r7, SVCPU_CR(r13)
 
 	/* Save more register state  */
 
@@ -191,11 +191,11 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE_206)
 	mfctr	r8
 	mflr	r9
 
-	stw	r5, (SHADOW_VCPU_OFF + SVCPU_XER)(r13)
-	PPC_STL	r6, (SHADOW_VCPU_OFF + SVCPU_FAULT_DAR)(r13)
-	stw	r7, (SHADOW_VCPU_OFF + SVCPU_FAULT_DSISR)(r13)
-	PPC_STL	r8, (SHADOW_VCPU_OFF + SVCPU_CTR)(r13)
-	PPC_STL	r9, (SHADOW_VCPU_OFF + SVCPU_LR)(r13)
+	stw	r5, SVCPU_XER(r13)
+	PPC_STL	r6, SVCPU_FAULT_DAR(r13)
+	stw	r7, SVCPU_FAULT_DSISR(r13)
+	PPC_STL	r8, SVCPU_CTR(r13)
+	PPC_STL	r9, SVCPU_LR(r13)
 
 	/*
 	 * In order for us to easily get the last instruction,
@@ -225,7 +225,7 @@ ld_last_inst:
 	/* Set guest mode to 'jump over instruction' so if lwz faults
 	 * we'll just continue at the next IP. */
 	li	r9, KVM_GUEST_MODE_SKIP
-	stb	r9, (SHADOW_VCPU_OFF + SVCPU_IN_GUEST)(r13)
+	stb	r9, HSTATE_IN_GUEST(r13)
 
 	/*    1) enable paging for data */
 	mfmsr	r9
@@ -239,13 +239,13 @@ ld_last_inst:
 	sync
 
 #endif
-	stw	r0, (SHADOW_VCPU_OFF + SVCPU_LAST_INST)(r13)
+	stw	r0, SVCPU_LAST_INST(r13)
 
 no_ld_last_inst:
 
 	/* Unset guest mode */
 	li	r9, KVM_GUEST_MODE_NONE
-	stb	r9, (SHADOW_VCPU_OFF + SVCPU_IN_GUEST)(r13)
+	stb	r9, HSTATE_IN_GUEST(r13)
 
 	/* Switch back to host MMU */
 	LOAD_HOST_SEGMENTS
@@ -255,7 +255,7 @@ no_ld_last_inst:
 	 * R1       = host R1
 	 * R2       = host R2
 	 * R12      = exit handler id
-	 * R13      = shadow vcpu - SHADOW_VCPU_OFF [=PACA on PPC64]
+	 * R13      = shadow vcpu (32-bit) or PACA (64-bit)
 	 * SVCPU.*  = guest *
 	 *
 	 */
@@ -265,7 +265,7 @@ no_ld_last_inst:
 	ori	r7, r7, MSR_IR|MSR_DR|MSR_RI|MSR_ME	/* Enable paging */
 	mtsrr1	r7
 	/* Load highmem handler address */
-	PPC_LL	r8, (SHADOW_VCPU_OFF + SVCPU_VMHANDLER)(r13)
+	PPC_LL	r8, HSTATE_VMHANDLER(r13)
 	mtsrr0	r8
 
 	RFI
-- 
1.7.5.3

[PATCH v2 09/12] kvm/powerpc: Add support for Book3S processors in hypervisor mode

[Paul Mackerras]

This adds support for KVM running on 64-bit Book 3S processors,
specifically POWER7, in hypervisor mode.  Using hypervisor mode means
that the guest can use the processor's supervisor mode.  That means
that the guest can execute privileged instructions and access privileged
registers itself without trapping to the host.  This gives excellent
performance, but does mean that KVM cannot emulate a processor
architecture other than the one that the hardware implements.

This code assumes that the guest is running paravirtualized using the
PAPR (Power Architecture Platform Requirements) interface, which is the
interface that IBM's PowerVM hypervisor uses.  That means that existing
Linux distributions that run on IBM pSeries machines will also run
under KVM without modification.  In order to communicate the PAPR
hypercalls to qemu, this adds a new KVM_EXIT_PAPR_HCALL exit code
to include/linux/kvm.h.

Currently the choice between book3s_hv support and book3s_pr support
(i.e. the existing code, which runs the guest in user mode) has to be
made at kernel configuration time, so a given kernel binary can only
do one or the other.

This new book3s_hv code doesn't support MMIO emulation at present.
Since we are running paravirtualized guests, this isn't a serious
restriction.

With the guest running in supervisor mode, most exceptions go straight
to the guest.  We will never get data or instruction storage or segment
interrupts, alignment interrupts, decrementer interrupts, program
interrupts, single-step interrupts, etc., coming to the hypervisor from
the guest.  Therefore this introduces a new KVMTEST_NONHV macro for the
exception entry path so that we don't have to do the KVM test on entry
to those exception handlers.

We do however get hypervisor decrementer, hypervisor data storage,
hypervisor instruction storage, and hypervisor emulation assist
interrupts, so we have to handle those.

In hypervisor mode, real-mode accesses can access all of RAM, not just
a limited amount.  Therefore we put all the guest state in the vcpu.arch
and use the shadow_vcpu in the PACA only for temporary scratch space.
We allocate the vcpu with kzalloc rather than vzalloc, and we don't use
anything in the kvmppc_vcpu_book3s struct, so we don't allocate it.
We don't have a shared page with the guest, but we still need a
kvm_vcpu_arch_shared struct to store the values of various registers,
so we include one in the vcpu_arch struct.

The POWER7 processor has a restriction that all threads in a core have
to be in the same partition.  MMU-on kernel code counts as a partition
(partition 0), so we have to do a partition switch on every entry to and
exit from the guest.  At present we require the host and guest to run
in single-thread mode because of this hardware restriction.

This code allocates a hashed page table for the guest and initializes
it with HPTEs for the guest's Virtual Real Memory Area (VRMA).  We
require that the guest memory is allocated using 16MB huge pages, in
order to simplify the low-level memory management.  This also means that
we can get away without tracking paging activity in the host for now,
since huge pages can't be paged or swapped.

Signed-off-by: Paul Mackerras <paulus@samba.org>
---
 Documentation/virtual/kvm/api.txt         |   17 +
 arch/powerpc/include/asm/exception-64s.h  |   19 +-
 arch/powerpc/include/asm/kvm_asm.h        |    4 +
 arch/powerpc/include/asm/kvm_book3s.h     |  136 +++++-
 arch/powerpc/include/asm/kvm_book3s_64.h  |    2 +
 arch/powerpc/include/asm/kvm_book3s_asm.h |   11 +
 arch/powerpc/include/asm/kvm_booke.h      |    4 +
 arch/powerpc/include/asm/kvm_host.h       |   53 ++-
 arch/powerpc/include/asm/kvm_ppc.h        |    6 +
 arch/powerpc/include/asm/mmu-hash64.h     |   10 +-
 arch/powerpc/include/asm/paca.h           |    2 +
 arch/powerpc/include/asm/reg.h            |    4 +
 arch/powerpc/kernel/asm-offsets.c         |   78 ++++
 arch/powerpc/kernel/exceptions-64s.S      |   60 ++--
 arch/powerpc/kvm/Kconfig                  |   41 ++-
 arch/powerpc/kvm/Makefile                 |   16 +-
 arch/powerpc/kvm/book3s_64_mmu_hv.c       |  258 +++++++++++
 arch/powerpc/kvm/book3s_hv.c              |  430 +++++++++++++++++++
 arch/powerpc/kvm/book3s_hv_interrupts.S   |  325 ++++++++++++++
 arch/powerpc/kvm/book3s_hv_rmhandlers.S   |  667 +++++++++++++++++++++++++++++
 arch/powerpc/kvm/book3s_segment.S         |   34 +-
 arch/powerpc/kvm/powerpc.c                |   22 +-
 arch/powerpc/kvm/trace.h                  |    2 +-
 include/linux/kvm.h                       |    6 +
 24 files changed, 2125 insertions(+), 82 deletions(-)
 create mode 100644 arch/powerpc/kvm/book3s_64_mmu_hv.c
 create mode 100644 arch/powerpc/kvm/book3s_hv.c
 create mode 100644 arch/powerpc/kvm/book3s_hv_interrupts.S
 create mode 100644 arch/powerpc/kvm/book3s_hv_rmhandlers.S

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 42542eb..f61e986 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1473,6 +1473,23 @@ Userspace can now handle the hypercall and when it's done modify the gprs as
 necessary. Upon guest entry all guest GPRs will then be replaced by the values
 in this struct.
 
+		/* KVM_EXIT_PAPR_HCALL */
+		struct {
+			__u64 nr;
+			__u64 ret;
+			__u64 args[9];
+		} papr_hcall;
+
+This is used on 64-bit PowerPC when emulating a pSeries partition,
+e.g. with the 'pseries' machine type in qemu.  It occurs when the
+guest does a hypercall using the 'sc 1' instruction.  The 'nr' field
+contains the hypercall number (from the guest R3), and 'args' contains
+the arguments (from the guest R4 - R12).  Userspace should put the
+return code in 'ret' and any extra returned values in args[].
+The possible hypercalls are defined in the Power Architecture Platform
+Requirements (PAPR) document available from www.power.org (free
+developer registration required to access it).
+
 		/* Fix the size of the union. */
 		char padding[256];
 	};
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 296c9b6..69435da 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -134,6 +134,17 @@ do_kvm_##n:								\
 #define KVM_HANDLER_SKIP(area, h, n)
 #endif
 
+#ifdef CONFIG_KVM_BOOK3S_PR
+#define KVMTEST_PR(n)			__KVMTEST(n)
+#define KVM_HANDLER_PR(area, h, n)	__KVM_HANDLER(area, h, n)
+#define KVM_HANDLER_PR_SKIP(area, h, n)	__KVM_HANDLER_SKIP(area, h, n)
+
+#else
+#define KVMTEST_PR(n)
+#define KVM_HANDLER_PR(area, h, n)
+#define KVM_HANDLER_PR_SKIP(area, h, n)
+#endif
+
 #define NOTEST(n)
 
 /*
@@ -210,7 +221,7 @@ label##_pSeries:					\
 	HMT_MEDIUM;					\
 	SET_SCRATCH0(r13);		/* save r13 */		\
 	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, label##_common,	\
-				 EXC_STD, KVMTEST, vec)
+				 EXC_STD, KVMTEST_PR, vec)
 
 #define STD_EXCEPTION_HV(loc, vec, label)		\
 	. = loc;					\
@@ -227,8 +238,8 @@ label##_hv:						\
 	beq	masked_##h##interrupt
 #define _SOFTEN_TEST(h)	__SOFTEN_TEST(h)
 
-#define SOFTEN_TEST(vec)						\
-	KVMTEST(vec);							\
+#define SOFTEN_TEST_PR(vec)						\
+	KVMTEST_PR(vec);						\
 	_SOFTEN_TEST(EXC_STD)
 
 #define SOFTEN_TEST_HV(vec)						\
@@ -248,7 +259,7 @@ label##_hv:						\
 	.globl label##_pSeries;						\
 label##_pSeries:							\
 	_MASKABLE_EXCEPTION_PSERIES(vec, label,				\
-				    EXC_STD, SOFTEN_TEST)
+				    EXC_STD, SOFTEN_TEST_PR)
 
 #define MASKABLE_EXCEPTION_HV(loc, vec, label)				\
 	. = loc;							\
diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h
index 0951b17..7b1f0e0 100644
--- a/arch/powerpc/include/asm/kvm_asm.h
+++ b/arch/powerpc/include/asm/kvm_asm.h
@@ -64,8 +64,12 @@
 #define BOOK3S_INTERRUPT_PROGRAM	0x700
 #define BOOK3S_INTERRUPT_FP_UNAVAIL	0x800
 #define BOOK3S_INTERRUPT_DECREMENTER	0x900
+#define BOOK3S_INTERRUPT_HV_DECREMENTER	0x980
 #define BOOK3S_INTERRUPT_SYSCALL	0xc00
 #define BOOK3S_INTERRUPT_TRACE		0xd00
+#define BOOK3S_INTERRUPT_H_DATA_STORAGE	0xe00
+#define BOOK3S_INTERRUPT_H_INST_STORAGE	0xe20
+#define BOOK3S_INTERRUPT_H_EMUL_ASSIST	0xe40
 #define BOOK3S_INTERRUPT_PERFMON	0xf00
 #define BOOK3S_INTERRUPT_ALTIVEC	0xf20
 #define BOOK3S_INTERRUPT_VSX		0xf40
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index fe20c74..b91aa22 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -116,6 +116,7 @@ extern void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 new_msr);
 extern void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr);
 extern void kvmppc_mmu_book3s_64_init(struct kvm_vcpu *vcpu);
 extern void kvmppc_mmu_book3s_32_init(struct kvm_vcpu *vcpu);
+extern void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu);
 extern int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte);
 extern int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr);
 extern void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu);
@@ -127,10 +128,12 @@ extern int kvmppc_mmu_hpte_init(struct kvm_vcpu *vcpu);
 extern void kvmppc_mmu_invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte);
 extern int kvmppc_mmu_hpte_sysinit(void);
 extern void kvmppc_mmu_hpte_sysexit(void);
+extern int kvmppc_mmu_hv_init(void);
 
 extern int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, bool data);
 extern int kvmppc_st(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, bool data);
 extern void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec);
+extern void kvmppc_inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 flags);
 extern void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat,
 			   bool upper, u32 val);
 extern void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr);
@@ -151,6 +154,19 @@ static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu)
 	return container_of(vcpu, struct kvmppc_vcpu_book3s, vcpu);
 }
 
+extern void kvm_return_point(void);
+
+/* Also add subarch specific defines */
+
+#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
+#include <asm/kvm_book3s_32.h>
+#endif
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+#include <asm/kvm_book3s_64.h>
+#endif
+
+#ifdef CONFIG_KVM_BOOK3S_PR
+
 static inline unsigned long kvmppc_interrupt_offset(struct kvm_vcpu *vcpu)
 {
 	return to_book3s(vcpu)->hior;
@@ -165,16 +181,6 @@ static inline void kvmppc_update_int_pending(struct kvm_vcpu *vcpu,
 		vcpu->arch.shared->int_pending = 0;
 }
 
-static inline ulong dsisr(void)
-{
-	ulong r;
-	asm ( "mfdsisr %0 " : "=r" (r) );
-	return r;
-}
-
-extern void kvm_return_point(void);
-static inline struct kvmppc_book3s_shadow_vcpu *to_svcpu(struct kvm_vcpu *vcpu);
-
 static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val)
 {
 	if ( num < 14 ) {
@@ -281,6 +287,108 @@ static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu)
 
 	return crit;
 }
+#else /* CONFIG_KVM_BOOK3S_PR */
+
+static inline unsigned long kvmppc_interrupt_offset(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+
+static inline void kvmppc_update_int_pending(struct kvm_vcpu *vcpu,
+			unsigned long pending_now, unsigned long old_pending)
+{
+	/* Recalculate LPCR:MER based on the presence of
+	 * a pending external interrupt
+	 */
+	if (test_bit(BOOK3S_IRQPRIO_EXTERNAL, &pending_now) ||
+	    test_bit(BOOK3S_IRQPRIO_EXTERNAL_LEVEL, &pending_now))
+		vcpu->arch.lpcr |= LPCR_MER;
+	else
+		vcpu->arch.lpcr &= ~((u64)LPCR_MER);
+}
+
+static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val)
+{
+	vcpu->arch.gpr[num] = val;
+}
+
+static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num)
+{
+	return vcpu->arch.gpr[num];
+}
+
+static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val)
+{
+	vcpu->arch.cr = val;
+}
+
+static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.cr;
+}
+
+static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, u32 val)
+{
+	vcpu->arch.xer = val;
+}
+
+static inline u32 kvmppc_get_xer(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.xer;
+}
+
+static inline void kvmppc_set_ctr(struct kvm_vcpu *vcpu, ulong val)
+{
+	vcpu->arch.ctr = val;
+}
+
+static inline ulong kvmppc_get_ctr(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.ctr;
+}
+
+static inline void kvmppc_set_lr(struct kvm_vcpu *vcpu, ulong val)
+{
+	vcpu->arch.lr = val;
+}
+
+static inline ulong kvmppc_get_lr(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.lr;
+}
+
+static inline void kvmppc_set_pc(struct kvm_vcpu *vcpu, ulong val)
+{
+	vcpu->arch.pc = val;
+}
+
+static inline ulong kvmppc_get_pc(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.pc;
+}
+
+static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu)
+{
+	ulong pc = kvmppc_get_pc(vcpu);
+
+	/* Load the instruction manually if it failed to do so in the
+	 * exit path */
+	if (vcpu->arch.last_inst == KVM_INST_FETCH_FAILED)
+		kvmppc_ld(vcpu, &pc, sizeof(u32), &vcpu->arch.last_inst, false);
+
+	return vcpu->arch.last_inst;
+}
+
+static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.fault_dar;
+}
+
+static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+#endif
 
 /* Magic register values loaded into r3 and r4 before the 'sc' assembly
  * instruction for the OSI hypercalls */
@@ -289,12 +397,4 @@ static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu)
 
 #define INS_DCBZ			0x7c0007ec
 
-/* Also add subarch specific defines */
-
-#ifdef CONFIG_PPC_BOOK3S_32
-#include <asm/kvm_book3s_32.h>
-#else
-#include <asm/kvm_book3s_64.h>
-#endif
-
 #endif /* __ASM_KVM_BOOK3S_H__ */
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 4cadd61..5f73388 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -20,9 +20,11 @@
 #ifndef __ASM_KVM_BOOK3S_64_H__
 #define __ASM_KVM_BOOK3S_64_H__
 
+#ifdef CONFIG_KVM_BOOK3S_PR
 static inline struct kvmppc_book3s_shadow_vcpu *to_svcpu(struct kvm_vcpu *vcpu)
 {
 	return &get_paca()->shadow_vcpu;
 }
+#endif
 
 #endif /* __ASM_KVM_BOOK3S_64_H__ */
diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h
index 3126175..550cf07 100644
--- a/arch/powerpc/include/asm/kvm_book3s_asm.h
+++ b/arch/powerpc/include/asm/kvm_book3s_asm.h
@@ -74,6 +74,17 @@ struct kvmppc_host_state {
 	ulong scratch0;
 	ulong scratch1;
 	u8 in_guest;
+
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+	struct kvm_vcpu *kvm_vcpu;
+	u64 dabr;
+	u64 host_mmcr[3];
+	u32 host_pmc[6];
+	u64 host_purr;
+	u64 host_spurr;
+	u64 host_dscr;
+	u64 dec_expires;
+#endif
 };
 
 struct kvmppc_book3s_shadow_vcpu {
diff --git a/arch/powerpc/include/asm/kvm_booke.h b/arch/powerpc/include/asm/kvm_booke.h
index 9c9ba3d..a90e091 100644
--- a/arch/powerpc/include/asm/kvm_booke.h
+++ b/arch/powerpc/include/asm/kvm_booke.h
@@ -93,4 +93,8 @@ static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu)
 	return vcpu->arch.fault_dear;
 }
 
+static inline ulong kvmppc_get_msr(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.shared->msr;
+}
 #endif /* __ASM_KVM_BOOKE_H__ */
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 8bb47e0..5645532 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -33,7 +33,9 @@
 /* memory slots that does not exposed to userspace */
 #define KVM_PRIVATE_MEM_SLOTS 4
 
+#ifdef CONFIG_KVM_MMIO
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
+#endif
 
 /* We don't currently support large pages. */
 #define KVM_HPAGE_GFN_SHIFT(x)	0
@@ -133,7 +135,26 @@ struct kvmppc_exit_timing {
 	};
 };
 
+struct kvmppc_pginfo {
+	unsigned long pfn;
+	atomic_t refcnt;
+};
+
 struct kvm_arch {
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+	unsigned long hpt_virt;
+	unsigned long ram_npages;
+	unsigned long ram_psize;
+	unsigned long ram_porder;
+	struct kvmppc_pginfo *ram_pginfo;
+	unsigned int lpid;
+	unsigned int host_lpid;
+	unsigned long host_lpcr;
+	unsigned long sdr1;
+	unsigned long host_sdr1;
+	int tlbie_lock;
+	unsigned short last_vcpu[NR_CPUS];
+#endif /* CONFIG_KVM_BOOK3S_64_HV */
 };
 
 struct kvmppc_pte {
@@ -190,7 +211,7 @@ struct kvm_vcpu_arch {
 	ulong rmcall;
 	ulong host_paca_phys;
 	struct kvmppc_slb slb[64];
-	int slb_max;		/* # valid entries in slb[] */
+	int slb_max;		/* 1 + index of last valid entry in slb[] */
 	int slb_nr;		/* total number of entries in SLB */
 	struct kvmppc_mmu mmu;
 #endif
@@ -206,7 +227,7 @@ struct kvm_vcpu_arch {
 #endif
 
 #ifdef CONFIG_VSX
-	u64 vsr[32];
+	u64 vsr[64];
 #endif
 
 #ifdef CONFIG_PPC_BOOK3S
@@ -214,19 +235,25 @@ struct kvm_vcpu_arch {
 	u32 qpr[32];
 #endif
 
-#ifdef CONFIG_BOOKE
 	ulong pc;
 	ulong ctr;
 	ulong lr;
 
 	ulong xer;
 	u32 cr;
-#endif
 
 #ifdef CONFIG_PPC_BOOK3S
 	ulong shadow_msr;
 	ulong hflags;
 	ulong guest_owned_ext;
+	ulong purr;
+	ulong spurr;
+	ulong lpcr;
+	ulong dscr;
+	ulong amr;
+	ulong uamor;
+	u32 ctrl;
+	ulong dabr;
 #endif
 	u32 vrsave; /* also USPRG0 */
 	u32 mmucr;
@@ -263,6 +290,9 @@ struct kvm_vcpu_arch {
 	u32 dbcr1;
 	u32 dbsr;
 
+	u64 mmcr[3];
+	u32 pmc[6];
+
 #ifdef CONFIG_KVM_EXIT_TIMING
 	struct mutex exit_timing_lock;
 	struct kvmppc_exit_timing timing_exit;
@@ -277,8 +307,12 @@ struct kvm_vcpu_arch {
 	struct dentry *debugfs_exit_timing;
 #endif
 
+#ifdef CONFIG_PPC_BOOK3S
+	ulong fault_dar;
+	u32 fault_dsisr;
+#endif
+
 #ifdef CONFIG_BOOKE
-	u32 last_inst;
 	ulong fault_dear;
 	ulong fault_esr;
 	ulong queued_dear;
@@ -293,16 +327,25 @@ struct kvm_vcpu_arch {
 	u8 dcr_is_write;
 	u8 osi_needed;
 	u8 osi_enabled;
+	u8 hcall_needed;
 
 	u32 cpr0_cfgaddr; /* holds the last set cpr0_cfgaddr */
 
 	struct hrtimer dec_timer;
 	struct tasklet_struct tasklet;
 	u64 dec_jiffies;
+	u64 dec_expires;
 	unsigned long pending_exceptions;
+	u16 last_cpu;
+	u32 last_inst;
+	int trap;
 	struct kvm_vcpu_arch_shared *shared;
 	unsigned long magic_page_pa; /* phys addr to map the magic page to */
 	unsigned long magic_page_ea; /* effect. addr to map the magic page to */
+
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+	struct kvm_vcpu_arch_shared shregs;
+#endif
 };
 
 #endif /* __POWERPC_KVM_HOST_H__ */
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index c3dde27..2a10e82 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -111,6 +111,12 @@ extern void kvmppc_booke_exit(void);
 extern void kvmppc_core_destroy_mmu(struct kvm_vcpu *vcpu);
 extern int kvmppc_kvm_pv(struct kvm_vcpu *vcpu);
 
+extern long kvmppc_alloc_hpt(struct kvm *kvm);
+extern void kvmppc_free_hpt(struct kvm *kvm);
+extern long kvmppc_prepare_vrma(struct kvm *kvm,
+				struct kvm_userspace_memory_region *mem);
+extern void kvmppc_map_vrma(struct kvm *kvm,
+			    struct kvm_userspace_memory_region *mem);
 extern int kvmppc_core_init_vm(struct kvm *kvm);
 extern void kvmppc_core_destroy_vm(struct kvm *kvm);
 extern int kvmppc_core_prepare_memory_region(struct kvm *kvm,
diff --git a/arch/powerpc/include/asm/mmu-hash64.h b/arch/powerpc/include/asm/mmu-hash64.h
index d865bd9..b445e0a 100644
--- a/arch/powerpc/include/asm/mmu-hash64.h
+++ b/arch/powerpc/include/asm/mmu-hash64.h
@@ -90,13 +90,19 @@ extern char initial_stab[];
 
 #define HPTE_R_PP0		ASM_CONST(0x8000000000000000)
 #define HPTE_R_TS		ASM_CONST(0x4000000000000000)
+#define HPTE_R_KEY_HI		ASM_CONST(0x3000000000000000)
 #define HPTE_R_RPN_SHIFT	12
-#define HPTE_R_RPN		ASM_CONST(0x3ffffffffffff000)
-#define HPTE_R_FLAGS		ASM_CONST(0x00000000000003ff)
+#define HPTE_R_RPN		ASM_CONST(0x0ffffffffffff000)
 #define HPTE_R_PP		ASM_CONST(0x0000000000000003)
 #define HPTE_R_N		ASM_CONST(0x0000000000000004)
+#define HPTE_R_G		ASM_CONST(0x0000000000000008)
+#define HPTE_R_M		ASM_CONST(0x0000000000000010)
+#define HPTE_R_I		ASM_CONST(0x0000000000000020)
+#define HPTE_R_W		ASM_CONST(0x0000000000000040)
+#define HPTE_R_WIMG		ASM_CONST(0x0000000000000078)
 #define HPTE_R_C		ASM_CONST(0x0000000000000080)
 #define HPTE_R_R		ASM_CONST(0x0000000000000100)
+#define HPTE_R_KEY_LO		ASM_CONST(0x0000000000000e00)
 
 #define HPTE_V_1TB_SEG		ASM_CONST(0x4000000000000000)
 #define HPTE_V_VRMA_MASK	ASM_CONST(0x4001ffffff000000)
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 58f4a18..a6da128 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -147,8 +147,10 @@ struct paca_struct {
 	struct dtl_entry *dtl_curr;	/* pointer corresponding to dtl_ridx */
 
 #ifdef CONFIG_KVM_BOOK3S_HANDLER
+#ifdef CONFIG_KVM_BOOK3S_PR
 	/* We use this to store guest state in */
 	struct kvmppc_book3s_shadow_vcpu shadow_vcpu;
+#endif
 	struct kvmppc_host_state kvm_hstate;
 #endif
 };
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index d879a6b..36a611b 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -189,6 +189,9 @@
 #define SPRN_CTR	0x009	/* Count Register */
 #define SPRN_DSCR	0x11
 #define SPRN_CFAR	0x1c	/* Come From Address Register */
+#define SPRN_AMR	0x1d	/* Authority Mask Register */
+#define SPRN_UAMOR	0x9d	/* User Authority Mask Override Register */
+#define SPRN_AMOR	0x15d	/* Authority Mask Override Register */
 #define SPRN_ACOP	0x1F	/* Available Coprocessor Register */
 #define SPRN_CTRLF	0x088
 #define SPRN_CTRLT	0x098
@@ -252,6 +255,7 @@
 #define   LPCR_RMI     0x00000002      /* real mode is cache inhibit */
 #define   LPCR_HDICE   0x00000001      /* Hyp Decr enable (HV,PR,EE) */
 #define SPRN_LPID	0x13F	/* Logical Partition Identifier */
+#define   LPID_RSVD	0x3ff		/* Reserved LPID for partn switching */
 #define	SPRN_HMER	0x150	/* Hardware m? error recovery */
 #define	SPRN_HMEER	0x151	/* Hardware m? enable error recovery */
 #define	SPRN_HEIR	0x153	/* Hypervisor Emulated Instruction Register */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 61064207..a2f540b 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -187,6 +187,7 @@ int main(void)
 	DEFINE(LPPACASRR1, offsetof(struct lppaca, saved_srr1));
 	DEFINE(LPPACAANYINT, offsetof(struct lppaca, int_dword.any_int));
 	DEFINE(LPPACADECRINT, offsetof(struct lppaca, int_dword.fields.decr_int));
+	DEFINE(LPPACA_PMCINUSE, offsetof(struct lppaca, pmcregs_in_use));
 	DEFINE(LPPACA_DTLIDX, offsetof(struct lppaca, dtl_idx));
 	DEFINE(PACA_DTL_RIDX, offsetof(struct paca_struct, dtl_ridx));
 #endif /* CONFIG_PPC_STD_MMU_64 */
@@ -392,6 +393,29 @@ int main(void)
 	DEFINE(VCPU_HOST_PID, offsetof(struct kvm_vcpu, arch.host_pid));
 	DEFINE(VCPU_GPRS, offsetof(struct kvm_vcpu, arch.gpr));
 	DEFINE(VCPU_VRSAVE, offsetof(struct kvm_vcpu, arch.vrsave));
+	DEFINE(VCPU_FPRS, offsetof(struct kvm_vcpu, arch.fpr));
+	DEFINE(VCPU_FPSCR, offsetof(struct kvm_vcpu, arch.fpscr));
+#ifdef CONFIG_ALTIVEC
+	DEFINE(VCPU_VRS, offsetof(struct kvm_vcpu, arch.vr));
+	DEFINE(VCPU_VSCR, offsetof(struct kvm_vcpu, arch.vscr));
+#endif
+#ifdef CONFIG_VSX
+	DEFINE(VCPU_VSRS, offsetof(struct kvm_vcpu, arch.vsr));
+#endif
+	DEFINE(VCPU_XER, offsetof(struct kvm_vcpu, arch.xer));
+	DEFINE(VCPU_CTR, offsetof(struct kvm_vcpu, arch.ctr));
+	DEFINE(VCPU_LR, offsetof(struct kvm_vcpu, arch.lr));
+	DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr));
+	DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.pc));
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+	DEFINE(VCPU_MSR, offsetof(struct kvm_vcpu, arch.shregs.msr));
+	DEFINE(VCPU_SRR0, offsetof(struct kvm_vcpu, arch.shregs.srr0));
+	DEFINE(VCPU_SRR1, offsetof(struct kvm_vcpu, arch.shregs.srr1));
+	DEFINE(VCPU_SPRG0, offsetof(struct kvm_vcpu, arch.shregs.sprg0));
+	DEFINE(VCPU_SPRG1, offsetof(struct kvm_vcpu, arch.shregs.sprg1));
+	DEFINE(VCPU_SPRG2, offsetof(struct kvm_vcpu, arch.shregs.sprg2));
+	DEFINE(VCPU_SPRG3, offsetof(struct kvm_vcpu, arch.shregs.sprg3));
+#endif
 	DEFINE(VCPU_SPRG4, offsetof(struct kvm_vcpu, arch.sprg4));
 	DEFINE(VCPU_SPRG5, offsetof(struct kvm_vcpu, arch.sprg5));
 	DEFINE(VCPU_SPRG6, offsetof(struct kvm_vcpu, arch.sprg6));
@@ -401,18 +425,61 @@ int main(void)
 	DEFINE(VCPU_SHARED_MSR, offsetof(struct kvm_vcpu_arch_shared, msr));
 
 	/* book3s */
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+	DEFINE(KVM_LPID, offsetof(struct kvm, arch.lpid));
+	DEFINE(KVM_SDR1, offsetof(struct kvm, arch.sdr1));
+	DEFINE(KVM_HOST_LPID, offsetof(struct kvm, arch.host_lpid));
+	DEFINE(KVM_HOST_LPCR, offsetof(struct kvm, arch.host_lpcr));
+	DEFINE(KVM_HOST_SDR1, offsetof(struct kvm, arch.host_sdr1));
+	DEFINE(KVM_TLBIE_LOCK, offsetof(struct kvm, arch.tlbie_lock));
+	DEFINE(KVM_ONLINE_CPUS, offsetof(struct kvm, online_vcpus.counter));
+	DEFINE(KVM_LAST_VCPU, offsetof(struct kvm, arch.last_vcpu));
+	DEFINE(VCPU_DSISR, offsetof(struct kvm_vcpu, arch.shregs.dsisr));
+	DEFINE(VCPU_DAR, offsetof(struct kvm_vcpu, arch.shregs.dar));
+#endif
 #ifdef CONFIG_PPC_BOOK3S
+	DEFINE(VCPU_KVM, offsetof(struct kvm_vcpu, kvm));
+	DEFINE(VCPU_VCPUID, offsetof(struct kvm_vcpu, vcpu_id));
 	DEFINE(VCPU_HOST_RETIP, offsetof(struct kvm_vcpu, arch.host_retip));
 	DEFINE(VCPU_HOST_MSR, offsetof(struct kvm_vcpu, arch.host_msr));
 	DEFINE(VCPU_SHADOW_MSR, offsetof(struct kvm_vcpu, arch.shadow_msr));
+	DEFINE(VCPU_PURR, offsetof(struct kvm_vcpu, arch.purr));
+	DEFINE(VCPU_SPURR, offsetof(struct kvm_vcpu, arch.spurr));
+	DEFINE(VCPU_DSCR, offsetof(struct kvm_vcpu, arch.dscr));
+	DEFINE(VCPU_AMR, offsetof(struct kvm_vcpu, arch.amr));
+	DEFINE(VCPU_UAMOR, offsetof(struct kvm_vcpu, arch.uamor));
+	DEFINE(VCPU_CTRL, offsetof(struct kvm_vcpu, arch.ctrl));
+	DEFINE(VCPU_DABR, offsetof(struct kvm_vcpu, arch.dabr));
 	DEFINE(VCPU_TRAMPOLINE_LOWMEM, offsetof(struct kvm_vcpu, arch.trampoline_lowmem));
 	DEFINE(VCPU_TRAMPOLINE_ENTER, offsetof(struct kvm_vcpu, arch.trampoline_enter));
 	DEFINE(VCPU_HIGHMEM_HANDLER, offsetof(struct kvm_vcpu, arch.highmem_handler));
 	DEFINE(VCPU_RMCALL, offsetof(struct kvm_vcpu, arch.rmcall));
 	DEFINE(VCPU_HFLAGS, offsetof(struct kvm_vcpu, arch.hflags));
+	DEFINE(VCPU_DEC, offsetof(struct kvm_vcpu, arch.dec));
+	DEFINE(VCPU_DEC_EXPIRES, offsetof(struct kvm_vcpu, arch.dec_expires));
+	DEFINE(VCPU_LPCR, offsetof(struct kvm_vcpu, arch.lpcr));
+	DEFINE(VCPU_MMCR, offsetof(struct kvm_vcpu, arch.mmcr));
+	DEFINE(VCPU_PMC, offsetof(struct kvm_vcpu, arch.pmc));
+	DEFINE(VCPU_SLB, offsetof(struct kvm_vcpu, arch.slb));
+	DEFINE(VCPU_SLB_MAX, offsetof(struct kvm_vcpu, arch.slb_max));
+	DEFINE(VCPU_SLB_NR, offsetof(struct kvm_vcpu, arch.slb_nr));
+	DEFINE(VCPU_LAST_CPU, offsetof(struct kvm_vcpu, arch.last_cpu));
+	DEFINE(VCPU_FAULT_DSISR, offsetof(struct kvm_vcpu, arch.fault_dsisr));
+	DEFINE(VCPU_FAULT_DAR, offsetof(struct kvm_vcpu, arch.fault_dar));
+	DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst));
+	DEFINE(VCPU_TRAP, offsetof(struct kvm_vcpu, arch.trap));
+	DEFINE(VCPU_SVCPU, offsetof(struct kvmppc_vcpu_book3s, shadow_vcpu) -
+			   offsetof(struct kvmppc_vcpu_book3s, vcpu));
+	DEFINE(VCPU_SLB_E, offsetof(struct kvmppc_slb, orige));
+	DEFINE(VCPU_SLB_V, offsetof(struct kvmppc_slb, origv));
+	DEFINE(VCPU_SLB_SIZE, sizeof(struct kvmppc_slb));
 
 #ifdef CONFIG_PPC_BOOK3S_64
+#ifdef CONFIG_KVM_BOOK3S_PR
 # define SVCPU_FIELD(x, f)	DEFINE(x, offsetof(struct paca_struct, shadow_vcpu.f))
+#else
+# define SVCPU_FIELD(x, f)
+#endif
 # define HSTATE_FIELD(x, f)	DEFINE(x, offsetof(struct paca_struct, kvm_hstate.f))
 #else	/* 32-bit */
 # define SVCPU_FIELD(x, f)	DEFINE(x, offsetof(struct kvmppc_book3s_shadow_vcpu, f))
@@ -457,6 +524,17 @@ int main(void)
 	HSTATE_FIELD(HSTATE_SCRATCH1, scratch1);
 	HSTATE_FIELD(HSTATE_IN_GUEST, in_guest);
 
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+	HSTATE_FIELD(HSTATE_KVM_VCPU, kvm_vcpu);
+	HSTATE_FIELD(HSTATE_MMCR, host_mmcr);
+	HSTATE_FIELD(HSTATE_PMC, host_pmc);
+	HSTATE_FIELD(HSTATE_PURR, host_purr);
+	HSTATE_FIELD(HSTATE_SPURR, host_spurr);
+	HSTATE_FIELD(HSTATE_DSCR, host_dscr);
+	HSTATE_FIELD(HSTATE_DABR, dabr);
+	HSTATE_FIELD(HSTATE_DECEXP, dec_expires);
+#endif /* CONFIG_KVM_BOOK3S_64_HV */
+
 #else /* CONFIG_PPC_BOOK3S */
 	DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr));
 	DEFINE(VCPU_XER, offsetof(struct kvm_vcpu, arch.xer));
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index e0b7987..b20d04c 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -87,14 +87,14 @@ data_access_not_stab:
 END_MMU_FTR_SECTION_IFCLR(MMU_FTR_SLB)
 #endif
 	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common, EXC_STD,
-				 KVMTEST, 0x300)
+				 KVMTEST_PR, 0x300)
 
 	. = 0x380
 	.globl data_access_slb_pSeries
 data_access_slb_pSeries:
 	HMT_MEDIUM
 	SET_SCRATCH0(r13)
-	EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST, 0x380)
+	EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x380)
 	std	r3,PACA_EXSLB+EX_R3(r13)
 	mfspr	r3,SPRN_DAR
 #ifdef __DISABLED__
@@ -125,7 +125,7 @@ data_access_slb_pSeries:
 instruction_access_slb_pSeries:
 	HMT_MEDIUM
 	SET_SCRATCH0(r13)
-	EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST, 0x480)
+	EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x480)
 	std	r3,PACA_EXSLB+EX_R3(r13)
 	mfspr	r3,SPRN_SRR0		/* SRR0 is faulting address */
 #ifdef __DISABLED__
@@ -153,32 +153,32 @@ instruction_access_slb_pSeries:
 hardware_interrupt_pSeries:
 hardware_interrupt_hv:
 	BEGIN_FTR_SECTION
-		_MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt,
-					    EXC_STD, SOFTEN_TEST)
-		KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x500)
-	FTR_SECTION_ELSE
 		_MASKABLE_EXCEPTION_PSERIES(0x502, hardware_interrupt,
 					    EXC_HV, SOFTEN_TEST_HV)
 		KVM_HANDLER(PACA_EXGEN, EXC_HV, 0x502)
-	ALT_FTR_SECTION_END_IFCLR(CPU_FTR_HVMODE_206)
+	FTR_SECTION_ELSE
+		_MASKABLE_EXCEPTION_PSERIES(0x500, hardware_interrupt,
+					    EXC_STD, SOFTEN_TEST_PR)
+		KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x500)
+	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE_206)
 
 	STD_EXCEPTION_PSERIES(0x600, 0x600, alignment)
-	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x600)
+	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x600)
 
 	STD_EXCEPTION_PSERIES(0x700, 0x700, program_check)
-	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x700)
+	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x700)
 
 	STD_EXCEPTION_PSERIES(0x800, 0x800, fp_unavailable)
-	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x800)
+	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x800)
 
 	MASKABLE_EXCEPTION_PSERIES(0x900, 0x900, decrementer)
 	MASKABLE_EXCEPTION_HV(0x980, 0x982, decrementer)
 
 	STD_EXCEPTION_PSERIES(0xa00, 0xa00, trap_0a)
-	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xa00)
+	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xa00)
 
 	STD_EXCEPTION_PSERIES(0xb00, 0xb00, trap_0b)
-	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xb00)
+	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xb00)
 
 	. = 0xc00
 	.globl	system_call_pSeries
@@ -219,7 +219,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_REAL_LE)
 	b	.
 
 	STD_EXCEPTION_PSERIES(0xd00, 0xd00, single_step)
-	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xd00)
+	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xd00)
 
 	/* At 0xe??? we have a bunch of hypervisor exceptions, we branch
 	 * out of line to handle them
@@ -254,23 +254,23 @@ vsx_unavailable_pSeries_1:
 
 #ifdef CONFIG_CBE_RAS
 	STD_EXCEPTION_HV(0x1200, 0x1202, cbe_system_error)
-	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1202)
+	KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_HV, 0x1202)
 #endif /* CONFIG_CBE_RAS */
 
 	STD_EXCEPTION_PSERIES(0x1300, 0x1300, instruction_breakpoint)
-	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x1300)
+	KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_STD, 0x1300)
 
 #ifdef CONFIG_CBE_RAS
 	STD_EXCEPTION_HV(0x1600, 0x1602, cbe_maintenance)
-	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1602)
+	KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_HV, 0x1602)
 #endif /* CONFIG_CBE_RAS */
 
 	STD_EXCEPTION_PSERIES(0x1700, 0x1700, altivec_assist)
-	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x1700)
+	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x1700)
 
 #ifdef CONFIG_CBE_RAS
 	STD_EXCEPTION_HV(0x1800, 0x1802, cbe_thermal)
-	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0x1802)
+	KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_HV, 0x1802)
 #endif /* CONFIG_CBE_RAS */
 
 	. = 0x3000
@@ -297,7 +297,7 @@ data_access_check_stab:
 	mfspr	r9,SPRN_DSISR
 	srdi	r10,r10,60
 	rlwimi	r10,r9,16,0x20
-#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+#ifdef CONFIG_KVM_BOOK3S_PR
 	lbz	r9,PACA_KVM_SVCPU+SVCPU_IN_GUEST(r13)
 	rlwimi	r10,r9,8,0x300
 #endif
@@ -316,11 +316,11 @@ do_stab_bolted_pSeries:
 	EXCEPTION_PROLOG_PSERIES_1(.do_stab_bolted, EXC_STD)
 #endif /* CONFIG_POWER4_ONLY */
 
-	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_STD, 0x300)
-	KVM_HANDLER_SKIP(PACA_EXSLB, EXC_STD, 0x380)
-	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x400)
-	KVM_HANDLER(PACA_EXSLB, EXC_STD, 0x480)
-	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0x900)
+	KVM_HANDLER_PR_SKIP(PACA_EXGEN, EXC_STD, 0x300)
+	KVM_HANDLER_PR_SKIP(PACA_EXSLB, EXC_STD, 0x380)
+	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x400)
+	KVM_HANDLER_PR(PACA_EXSLB, EXC_STD, 0x480)
+	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x900)
 	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0x982)
 
 	.align	7
@@ -336,11 +336,11 @@ do_stab_bolted_pSeries:
 
 	/* moved from 0xf00 */
 	STD_EXCEPTION_PSERIES(., 0xf00, performance_monitor)
-	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf00)
+	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf00)
 	STD_EXCEPTION_PSERIES(., 0xf20, altivec_unavailable)
-	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf20)
+	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf20)
 	STD_EXCEPTION_PSERIES(., 0xf40, vsx_unavailable)
-	KVM_HANDLER(PACA_EXGEN, EXC_STD, 0xf40)
+	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf40)
 
 /*
  * An interrupt came in while soft-disabled; clear EE in SRR1,
@@ -417,7 +417,11 @@ slb_miss_user_pseries:
 /* KVM's trampoline code needs to be close to the interrupt handlers */
 
 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+#ifdef CONFIG_KVM_BOOK3S_PR
 #include "../kvm/book3s_rmhandlers.S"
+#else
+#include "../kvm/book3s_hv_rmhandlers.S"
+#endif
 #endif
 
 	.align	7
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index b7baff7..3662ecc 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -20,7 +20,6 @@ config KVM
 	bool
 	select PREEMPT_NOTIFIERS
 	select ANON_INODES
-	select KVM_MMIO
 
 config KVM_BOOK3S_HANDLER
 	bool
@@ -28,16 +27,22 @@ config KVM_BOOK3S_HANDLER
 config KVM_BOOK3S_32_HANDLER
 	bool
 	select KVM_BOOK3S_HANDLER
+	select KVM_MMIO
 
 config KVM_BOOK3S_64_HANDLER
 	bool
 	select KVM_BOOK3S_HANDLER
 
+config KVM_BOOK3S_PR
+	bool
+	select KVM_MMIO
+
 config KVM_BOOK3S_32
 	tristate "KVM support for PowerPC book3s_32 processors"
 	depends on EXPERIMENTAL && PPC_BOOK3S_32 && !SMP && !PTE_64BIT
 	select KVM
 	select KVM_BOOK3S_32_HANDLER
+	select KVM_BOOK3S_PR
 	---help---
 	  Support running unmodified book3s_32 guest kernels
 	  in virtual machines on book3s_32 host processors.
@@ -48,10 +53,38 @@ config KVM_BOOK3S_32
 	  If unsure, say N.
 
 config KVM_BOOK3S_64
-	tristate "KVM support for PowerPC book3s_64 processors"
+	bool
+	select KVM_BOOK3S_64_HANDLER
+
+config KVM_BOOK3S_64_HV
+	bool "KVM support for POWER7 using hypervisor mode in host"
 	depends on EXPERIMENTAL && PPC_BOOK3S_64
 	select KVM
-	select KVM_BOOK3S_64_HANDLER
+	select KVM_BOOK3S_64
+	---help---
+	  Support running unmodified book3s_64 guest kernels in
+	  virtual machines on POWER7 processors that have hypervisor
+	  mode available to the host.
+
+	  If you say Y here, KVM will use the hardware virtualization
+	  facilities of POWER7 (and later) processors, meaning that
+	  guest operating systems will run at full hardware speed
+	  using supervisor and user modes.  However, this also means
+	  that KVM is not usable under PowerVM (pHyp), is only usable
+	  on POWER7 (or later) processors, and can only emulate
+	  POWER5+, POWER6 and POWER7 processors.
+
+	  This module provides access to the hardware capabilities through
+	  a character device node named /dev/kvm.
+
+	  If unsure, say N.
+
+config KVM_BOOK3S_64_PR
+	tristate "KVM support for PowerPC book3s_64 processors"
+	depends on EXPERIMENTAL && PPC_BOOK3S_64 && !KVM_BOOK3S_64_HV
+	select KVM
+	select KVM_BOOK3S_64
+	select KVM_BOOK3S_PR
 	---help---
 	  Support running unmodified book3s_64 and book3s_32 guest kernels
 	  in virtual machines on book3s_64 host processors.
@@ -65,6 +98,7 @@ config KVM_440
 	bool "KVM support for PowerPC 440 processors"
 	depends on EXPERIMENTAL && 44x
 	select KVM
+	select KVM_MMIO
 	---help---
 	  Support running unmodified 440 guest kernels in virtual machines on
 	  440 host processors.
@@ -89,6 +123,7 @@ config KVM_E500
 	bool "KVM support for PowerPC E500 processors"
 	depends on EXPERIMENTAL && E500
 	select KVM
+	select KVM_MMIO
 	---help---
 	  Support running unmodified E500 guest kernels in virtual machines on
 	  E500 host processors.
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index bf9854f..ca7ed27 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -14,7 +14,7 @@ CFLAGS_emulate.o  := -I.
 
 common-objs-y += powerpc.o emulate.o
 obj-$(CONFIG_KVM_EXIT_TIMING) += timing.o
-obj-$(CONFIG_KVM_BOOK3S_HANDLER) += book3s_exports.o
+obj-$(CONFIG_KVM_BOOK3S_PR) += book3s_exports.o
 
 AFLAGS_booke_interrupts.o := -I$(obj)
 
@@ -38,7 +38,7 @@ kvm-e500-objs := \
 	e500_emulate.o
 kvm-objs-$(CONFIG_KVM_E500) := $(kvm-e500-objs)
 
-kvm-book3s_64-objs := \
+kvm-book3s_64_pr-objs := \
 	$(common-objs-y) \
 	fpu.o \
 	book3s_paired_singles.o \
@@ -50,7 +50,17 @@ kvm-book3s_64-objs := \
 	book3s_64_mmu_host.o \
 	book3s_64_mmu.o \
 	book3s_32_mmu.o
-kvm-objs-$(CONFIG_KVM_BOOK3S_64) := $(kvm-book3s_64-objs)
+kvm-objs-$(CONFIG_KVM_BOOK3S_64_PR) := $(kvm-book3s_64_pr-objs)
+
+kvm-book3s_64_hv-objs := \
+	../../../virt/kvm/kvm_main.o \
+	powerpc.o \
+	emulate.o \
+	book3s.o \
+	book3s_hv.o \
+	book3s_hv_interrupts.o \
+	book3s_64_mmu_hv.o
+kvm-objs-$(CONFIG_KVM_BOOK3S_64_HV) := $(kvm-book3s_64_hv-objs)
 
 kvm-book3s_32-objs := \
 	$(common-objs-y) \
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
new file mode 100644
index 0000000..4a4fbec
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -0,0 +1,258 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright 2010 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
+ */
+
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/highmem.h>
+#include <linux/gfp.h>
+#include <linux/slab.h>
+#include <linux/hugetlb.h>
+
+#include <asm/tlbflush.h>
+#include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s.h>
+#include <asm/mmu-hash64.h>
+#include <asm/hvcall.h>
+#include <asm/synch.h>
+#include <asm/ppc-opcode.h>
+#include <asm/cputable.h>
+
+/* For now use fixed-size 16MB page table */
+#define HPT_ORDER	24
+#define HPT_NPTEG	(1ul << (HPT_ORDER - 7))	/* 128B per pteg */
+#define HPT_HASH_MASK	(HPT_NPTEG - 1)
+
+/* Pages in the VRMA are 16MB pages */
+#define VRMA_PAGE_ORDER	24
+#define VRMA_VSID	0x1ffffffUL	/* 1TB VSID reserved for VRMA */
+
+#define NR_LPIDS	(LPID_RSVD + 1)
+unsigned long lpid_inuse[BITS_TO_LONGS(NR_LPIDS)];
+
+long kvmppc_alloc_hpt(struct kvm *kvm)
+{
+	unsigned long hpt;
+	unsigned long lpid;
+
+	hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT|__GFP_NOWARN,
+			       HPT_ORDER - PAGE_SHIFT);
+	if (!hpt) {
+		pr_err("kvm_alloc_hpt: Couldn't alloc HPT\n");
+		return -ENOMEM;
+	}
+	kvm->arch.hpt_virt = hpt;
+
+	do {
+		lpid = find_first_zero_bit(lpid_inuse, NR_LPIDS);
+		if (lpid >= NR_LPIDS) {
+			pr_err("kvm_alloc_hpt: No LPIDs free\n");
+			free_pages(hpt, HPT_ORDER - PAGE_SHIFT);
+			return -ENOMEM;
+		}
+	} while (test_and_set_bit(lpid, lpid_inuse));
+
+	kvm->arch.sdr1 = __pa(hpt) | (HPT_ORDER - 18);
+	kvm->arch.lpid = lpid;
+	kvm->arch.host_sdr1 = mfspr(SPRN_SDR1);
+	kvm->arch.host_lpid = mfspr(SPRN_LPID);
+	kvm->arch.host_lpcr = mfspr(SPRN_LPCR);
+
+	pr_info("KVM guest htab at %lx, LPID %lx\n", hpt, lpid);
+	return 0;
+}
+
+void kvmppc_free_hpt(struct kvm *kvm)
+{
+	unsigned long i;
+	struct kvmppc_pginfo *pginfo;
+
+	clear_bit(kvm->arch.lpid, lpid_inuse);
+	free_pages(kvm->arch.hpt_virt, HPT_ORDER - PAGE_SHIFT);
+
+	if (kvm->arch.ram_pginfo) {
+		pginfo = kvm->arch.ram_pginfo;
+		kvm->arch.ram_pginfo = NULL;
+		for (i = 0; i < kvm->arch.ram_npages; ++i)
+			put_page(pfn_to_page(pginfo[i].pfn));
+		kfree(pginfo);
+	}
+}
+
+static unsigned long user_page_size(unsigned long addr)
+{
+	struct vm_area_struct *vma;
+	unsigned long size = PAGE_SIZE;
+
+	down_read(&current->mm->mmap_sem);
+	vma = find_vma(current->mm, addr);
+	if (vma)
+		size = vma_kernel_pagesize(vma);
+	up_read(&current->mm->mmap_sem);
+	return size;
+}
+
+static pfn_t hva_to_pfn(unsigned long addr)
+{
+	struct page *page[1];
+	int npages;
+
+	might_sleep();
+
+	npages = get_user_pages_fast(addr, 1, 1, page);
+
+	if (unlikely(npages != 1))
+		return 0;
+
+	return page_to_pfn(page[0]);
+}
+
+long kvmppc_prepare_vrma(struct kvm *kvm,
+			 struct kvm_userspace_memory_region *mem)
+{
+	unsigned long psize, porder;
+	unsigned long i, npages;
+	struct kvmppc_pginfo *pginfo;
+	pfn_t pfn;
+	unsigned long hva;
+
+	/* First see what page size we have */
+	psize = user_page_size(mem->userspace_addr);
+	/* For now, only allow 16MB pages */
+	if (psize != 1ul << VRMA_PAGE_ORDER || (mem->memory_size & (psize - 1))) {
+		pr_err("bad psize=%lx memory_size=%llx @ %llx\n",
+		       psize, mem->memory_size, mem->userspace_addr);
+		return -EINVAL;
+	}
+	porder = __ilog2(psize);
+
+	npages = mem->memory_size >> porder;
+	pginfo = kzalloc(npages * sizeof(struct kvmppc_pginfo), GFP_KERNEL);
+	if (!pginfo) {
+		pr_err("kvmppc_prepare_vrma: couldn't alloc %lu bytes\n",
+		       npages * sizeof(struct kvmppc_pginfo));
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < npages; ++i) {
+		hva = mem->userspace_addr + (i << porder);
+		if (user_page_size(hva) != psize)
+			goto err;
+		pfn = hva_to_pfn(hva);
+		if (pfn == 0) {
+			pr_err("oops, no pfn for hva %lx\n", hva);
+			goto err;
+		}
+		if (pfn & ((1ul << (porder - PAGE_SHIFT)) - 1)) {
+			pr_err("oops, unaligned pfn %llx\n", pfn);
+			put_page(pfn_to_page(pfn));
+			goto err;
+		}
+		pginfo[i].pfn = pfn;
+	}
+
+	kvm->arch.ram_npages = npages;
+	kvm->arch.ram_psize = psize;
+	kvm->arch.ram_porder = porder;
+	kvm->arch.ram_pginfo = pginfo;
+
+	return 0;
+
+ err:
+	kfree(pginfo);
+	return -EINVAL;
+}
+
+void kvmppc_map_vrma(struct kvm *kvm, struct kvm_userspace_memory_region *mem)
+{
+	unsigned long i;
+	unsigned long npages = kvm->arch.ram_npages;
+	unsigned long pfn;
+	unsigned long *hpte;
+	unsigned long hash;
+	struct kvmppc_pginfo *pginfo = kvm->arch.ram_pginfo;
+
+	if (!pginfo)
+		return;
+
+	/* VRMA can't be > 1TB */
+	if (npages > 1ul << (40 - kvm->arch.ram_porder))
+		npages = 1ul << (40 - kvm->arch.ram_porder);
+	/* Can't use more than 1 HPTE per HPTEG */
+	if (npages > HPT_NPTEG)
+		npages = HPT_NPTEG;
+
+	for (i = 0; i < npages; ++i) {
+		pfn = pginfo[i].pfn;
+		/* can't use hpt_hash since va > 64 bits */
+		hash = (i ^ (VRMA_VSID ^ (VRMA_VSID << 25))) & HPT_HASH_MASK;
+		/*
+		 * We assume that the hash table is empty and no
+		 * vcpus are using it at this stage.  Since we create
+		 * at most one HPTE per HPTEG, we just assume entry 7
+		 * is available and use it.
+		 */
+		hpte = (unsigned long *) (kvm->arch.hpt_virt + (hash << 7));
+		hpte += 7 * 2;
+		/* HPTE low word - RPN, protection, etc. */
+		hpte[1] = (pfn << PAGE_SHIFT) | HPTE_R_R | HPTE_R_C |
+			HPTE_R_M | PP_RWXX;
+		wmb();
+		hpte[0] = HPTE_V_1TB_SEG | (VRMA_VSID << (40 - 16)) |
+			(i << (VRMA_PAGE_ORDER - 16)) | HPTE_V_BOLTED |
+			HPTE_V_LARGE | HPTE_V_VALID;
+	}
+}
+
+int kvmppc_mmu_hv_init(void)
+{
+	if (!cpu_has_feature(CPU_FTR_HVMODE_206))
+		return -EINVAL;
+	memset(lpid_inuse, 0, sizeof(lpid_inuse));
+	set_bit(mfspr(SPRN_LPID), lpid_inuse);
+	set_bit(LPID_RSVD, lpid_inuse);
+
+	return 0;
+}
+
+void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
+{
+}
+
+static void kvmppc_mmu_book3s_64_hv_reset_msr(struct kvm_vcpu *vcpu)
+{
+	kvmppc_set_msr(vcpu, MSR_SF | MSR_ME);
+}
+
+static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
+				struct kvmppc_pte *gpte, bool data)
+{
+	return -ENOENT;
+}
+
+void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_mmu *mmu = &vcpu->arch.mmu;
+
+	vcpu->arch.slb_nr = 32;		/* Assume POWER7 for now */
+
+	mmu->xlate = kvmppc_mmu_book3s_64_hv_xlate;
+	mmu->reset_msr = kvmppc_mmu_book3s_64_hv_reset_msr;
+
+	vcpu->arch.hflags |= BOOK3S_HFLAG_SLB;
+}
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
new file mode 100644
index 0000000..0d812c5
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -0,0 +1,430 @@
+/*
+ * Copyright 2011 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
+ * Copyright (C) 2009. SUSE Linux Products GmbH. All rights reserved.
+ *
+ * Authors:
+ *    Paul Mackerras <paulus@au1.ibm.com>
+ *    Alexander Graf <agraf@suse.de>
+ *    Kevin Wolf <mail@kevin-wolf.de>
+ *
+ * Description: KVM functions specific to running on Book 3S
+ * processors in hypervisor mode (specifically POWER7 and later).
+ *
+ * This file is derived from arch/powerpc/kvm/book3s.c,
+ * by Alexander Graf <agraf@suse.de>.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/preempt.h>
+#include <linux/sched.h>
+#include <linux/delay.h>
+#include <linux/fs.h>
+#include <linux/anon_inodes.h>
+
+#include <asm/reg.h>
+#include <asm/cputable.h>
+#include <asm/cacheflush.h>
+#include <asm/tlbflush.h>
+#include <asm/uaccess.h>
+#include <asm/io.h>
+#include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s.h>
+#include <asm/mmu_context.h>
+#include <asm/lppaca.h>
+#include <asm/processor.h>
+#include <linux/gfp.h>
+#include <linux/sched.h>
+#include <linux/vmalloc.h>
+#include <linux/highmem.h>
+
+/* #define EXIT_DEBUG */
+/* #define EXIT_DEBUG_SIMPLE */
+/* #define EXIT_DEBUG_INT */
+
+void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+	local_paca->kvm_hstate.kvm_vcpu = vcpu;
+}
+
+void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
+{
+}
+
+void kvmppc_vcpu_block(struct kvm_vcpu *vcpu)
+{
+	u64 now;
+	unsigned long dec_nsec;
+
+	now = get_tb();
+	if (now >= vcpu->arch.dec_expires && !kvmppc_core_pending_dec(vcpu))
+		kvmppc_core_queue_dec(vcpu);
+	if (vcpu->arch.pending_exceptions)
+		return;
+	if (vcpu->arch.dec_expires != ~(u64)0) {
+		dec_nsec = (vcpu->arch.dec_expires - now) * NSEC_PER_SEC /
+			tb_ticks_per_sec;
+		hrtimer_start(&vcpu->arch.dec_timer, ktime_set(0, dec_nsec),
+			      HRTIMER_MODE_REL);
+	}
+
+	kvm_vcpu_block(vcpu);
+	vcpu->stat.halt_wakeup++;
+
+	if (vcpu->arch.dec_expires != ~(u64)0)
+		hrtimer_try_to_cancel(&vcpu->arch.dec_timer);
+}
+
+void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
+{
+	vcpu->arch.shregs.msr = msr;
+}
+
+void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr)
+{
+	vcpu->arch.pvr = pvr;
+}
+
+void kvmppc_dump_regs(struct kvm_vcpu *vcpu)
+{
+	int r;
+
+	pr_err("vcpu %p (%d):\n", vcpu, vcpu->vcpu_id);
+	pr_err("pc  = %.16lx  msr = %.16llx  trap = %x\n",
+	       vcpu->arch.pc, vcpu->arch.shregs.msr, vcpu->arch.trap);
+	for (r = 0; r < 16; ++r)
+		pr_err("r%2d = %.16lx  r%d = %.16lx\n",
+		       r, kvmppc_get_gpr(vcpu, r),
+		       r+16, kvmppc_get_gpr(vcpu, r+16));
+	pr_err("ctr = %.16lx  lr  = %.16lx\n",
+	       vcpu->arch.ctr, vcpu->arch.lr);
+	pr_err("srr0 = %.16llx srr1 = %.16llx\n",
+	       vcpu->arch.shregs.srr0, vcpu->arch.shregs.srr1);
+	pr_err("sprg0 = %.16llx sprg1 = %.16llx\n",
+	       vcpu->arch.shregs.sprg0, vcpu->arch.shregs.sprg1);
+	pr_err("sprg2 = %.16llx sprg3 = %.16llx\n",
+	       vcpu->arch.shregs.sprg2, vcpu->arch.shregs.sprg3);
+	pr_err("cr = %.8x  xer = %.16lx  dsisr = %.8x\n",
+	       vcpu->arch.cr, vcpu->arch.xer, vcpu->arch.shregs.dsisr);
+	pr_err("dar = %.16llx\n", vcpu->arch.shregs.dar);
+	pr_err("fault dar = %.16lx dsisr = %.8x\n",
+	       vcpu->arch.fault_dar, vcpu->arch.fault_dsisr);
+	pr_err("SLB (%d entries):\n", vcpu->arch.slb_max);
+	for (r = 0; r < vcpu->arch.slb_max; ++r)
+		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->arch.lpcr, vcpu->kvm->arch.sdr1,
+	       vcpu->arch.last_inst);
+}
+
+static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
+			      struct task_struct *tsk)
+{
+	int r = RESUME_HOST;
+
+	vcpu->stat.sum_exits++;
+
+	run->exit_reason = KVM_EXIT_UNKNOWN;
+	run->ready_for_interrupt_injection = 1;
+	switch (vcpu->arch.trap) {
+	/* We're good on these - the host merely wanted to get our attention */
+	case BOOK3S_INTERRUPT_HV_DECREMENTER:
+		vcpu->stat.dec_exits++;
+		r = RESUME_GUEST;
+		break;
+	case BOOK3S_INTERRUPT_EXTERNAL:
+		vcpu->stat.ext_intr_exits++;
+		r = RESUME_GUEST;
+		break;
+	case BOOK3S_INTERRUPT_PERFMON:
+		r = RESUME_GUEST;
+		break;
+	case BOOK3S_INTERRUPT_PROGRAM:
+	{
+		ulong flags;
+		/*
+		 * Normally program interrupts are delivered directly
+		 * to the guest by the hardware, but we can get here
+		 * as a result of a hypervisor emulation interrupt
+		 * (e40) getting turned into a 700 by BML RTAS.
+		 */
+		flags = vcpu->arch.shregs.msr & 0x1f0000ull;
+		kvmppc_core_queue_program(vcpu, flags);
+		r = RESUME_GUEST;
+		break;
+	}
+	case BOOK3S_INTERRUPT_SYSCALL:
+	{
+		/* 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;
+		}
+		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);
+		run->exit_reason = KVM_EXIT_PAPR_HCALL;
+		vcpu->arch.hcall_needed = 1;
+		r = RESUME_HOST;
+		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.
+	 */
+	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;
+		break;
+	case BOOK3S_INTERRUPT_H_INST_STORAGE:
+		kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_INST_STORAGE,
+					0x08000000);
+		r = RESUME_GUEST;
+		break;
+	/*
+	 * This occurs if the guest executes an illegal instruction.
+	 * We just generate a program interrupt to the guest, since
+	 * we don't emulate any guest instructions at this stage.
+	 */
+	case BOOK3S_INTERRUPT_H_EMUL_ASSIST:
+		kvmppc_core_queue_program(vcpu, 0x80000);
+		r = RESUME_GUEST;
+		break;
+	default:
+		kvmppc_dump_regs(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);
+		r = RESUME_HOST;
+		BUG();
+		break;
+	}
+
+
+	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(tsk)) {
+			vcpu->stat.signal_exits++;
+			run->exit_reason = KVM_EXIT_INTR;
+			r = -EINTR;
+		} else {
+			kvmppc_core_deliver_interrupts(vcpu);
+		}
+	}
+
+	return r;
+}
+
+int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
+                                  struct kvm_sregs *sregs)
+{
+	int i;
+
+	sregs->pvr = vcpu->arch.pvr;
+
+	memset(sregs, 0, sizeof(struct kvm_sregs));
+	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;
+	}
+
+	return 0;
+}
+
+int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
+                                  struct kvm_sregs *sregs)
+{
+	int i, j;
+
+	kvmppc_set_pvr(vcpu, sregs->pvr);
+
+	j = 0;
+	for (i = 0; i < vcpu->arch.slb_nr; i++) {
+		if (sregs->u.s.ppc64.slb[i].slbe & SLB_ESID_V) {
+			vcpu->arch.slb[j].orige = sregs->u.s.ppc64.slb[i].slbe;
+			vcpu->arch.slb[j].origv = sregs->u.s.ppc64.slb[i].slbv;
+			++j;
+		}
+	}
+	vcpu->arch.slb_max = j;
+
+	return 0;
+}
+
+int kvmppc_core_check_processor_compat(void)
+{
+	if (cpu_has_feature(CPU_FTR_HVMODE_206))
+		return 0;
+	return -EIO;
+}
+
+struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
+{
+	struct kvm_vcpu *vcpu;
+	int err = -ENOMEM;
+	unsigned long lpcr;
+
+	vcpu = kzalloc(sizeof(struct kvm_vcpu), GFP_KERNEL);
+	if (!vcpu)
+		goto out;
+
+	err = kvm_vcpu_init(vcpu, kvm, id);
+	if (err)
+		goto free_vcpu;
+
+	vcpu->arch.shared = &vcpu->arch.shregs;
+	vcpu->arch.last_cpu = -1;
+	vcpu->arch.host_msr = mfmsr();
+	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);
+
+	/* remember where some real-mode handlers are */
+	vcpu->arch.trampoline_lowmem = kvmppc_trampoline_lowmem;
+	vcpu->arch.trampoline_enter = kvmppc_trampoline_enter;
+	vcpu->arch.highmem_handler = (ulong)kvmppc_handler_highmem;
+	vcpu->arch.rmcall = *(ulong*)kvmppc_rmcall;
+
+	lpcr = kvm->arch.host_lpcr & (LPCR_PECE | LPCR_LPES);
+	lpcr |= LPCR_VPM0 | LPCR_VRMA_L | (4UL << LPCR_DPFD_SH) | LPCR_HDICE;
+	vcpu->arch.lpcr = lpcr;
+
+	kvmppc_mmu_book3s_hv_init(vcpu);
+
+	return vcpu;
+
+free_vcpu:
+	kfree(vcpu);
+out:
+	return ERR_PTR(err);
+}
+
+void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
+{
+	kvm_vcpu_uninit(vcpu);
+	kfree(vcpu);
+}
+
+extern int __kvmppc_vcore_entry(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu);
+
+int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu)
+{
+	u64 now;
+
+	if (signal_pending(current)) {
+		run->exit_reason = KVM_EXIT_INTR;
+		return -EINTR;
+	}
+
+	flush_fp_to_thread(current);
+	flush_altivec_to_thread(current);
+	flush_vsx_to_thread(current);
+	preempt_disable();
+
+	kvm_guest_enter();
+
+	__kvmppc_vcore_entry(NULL, vcpu);
+
+	kvm_guest_exit();
+
+	preempt_enable();
+	kvm_resched(vcpu);
+
+	now = get_tb();
+	/* cancel pending dec exception if dec is positive */
+	if (now < vcpu->arch.dec_expires && kvmppc_core_pending_dec(vcpu))
+		kvmppc_core_dequeue_dec(vcpu);
+
+	return kvmppc_handle_exit(run, vcpu, current);
+}
+
+int kvmppc_core_prepare_memory_region(struct kvm *kvm,
+				struct kvm_userspace_memory_region *mem)
+{
+	if (mem->guest_phys_addr == 0 && mem->memory_size != 0)
+		return kvmppc_prepare_vrma(kvm, mem);
+	return 0;
+}
+
+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)
+		kvmppc_map_vrma(kvm, mem);
+}
+
+int kvmppc_core_init_vm(struct kvm *kvm)
+{
+	long r;
+
+	/* Allocate hashed page table */
+	r = kvmppc_alloc_hpt(kvm);
+
+	return r;
+}
+
+void kvmppc_core_destroy_vm(struct kvm *kvm)
+{
+	kvmppc_free_hpt(kvm);
+}
+
+/* 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 */
+int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
+                           unsigned int inst, int *advance)
+{
+	return EMULATE_FAIL;
+}
+
+int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
+{
+	return EMULATE_FAIL;
+}
+
+int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
+{
+	return EMULATE_FAIL;
+}
+
+static int kvmppc_book3s_hv_init(void)
+{
+	int r;
+
+	r = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
+
+	if (r)
+		return r;
+
+	r = kvmppc_mmu_hv_init();
+
+	return r;
+}
+
+static void kvmppc_book3s_hv_exit(void)
+{
+	kvm_exit();
+}
+
+module_init(kvmppc_book3s_hv_init);
+module_exit(kvmppc_book3s_hv_exit);
diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S
new file mode 100644
index 0000000..5c6a387
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_hv_interrupts.S
@@ -0,0 +1,325 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright 2011 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
+ *
+ * Derived from book3s_interrupts.S, which is:
+ * Copyright SUSE Linux Products GmbH 2009
+ *
+ * Authors: Alexander Graf <agraf@suse.de>
+ */
+
+#include <asm/ppc_asm.h>
+#include <asm/kvm_asm.h>
+#include <asm/reg.h>
+#include <asm/page.h>
+#include <asm/asm-offsets.h>
+#include <asm/exception-64s.h>
+#include <asm/ppc-opcode.h>
+
+#define DISABLE_INTERRUPTS	\
+	mfmsr   r0;		\
+	rldicl  r0,r0,48,1;	\
+	rotldi  r0,r0,16;	\
+	mtmsrd  r0,1;		\
+
+/*****************************************************************************
+ *                                                                           *
+ *     Guest entry / exit code that is in kernel module memory (vmalloc)     *
+ *                                                                           *
+ ****************************************************************************/
+
+/* Registers:
+ *  r4: vcpu pointer
+ */
+_GLOBAL(__kvmppc_vcore_entry)
+
+	/* Write correct stack frame */
+	mflr	r0
+	std	r0,PPC_LR_STKOFF(r1)
+
+	/* Save host state to the stack */
+	stdu	r1, -SWITCH_FRAME_SIZE(r1)
+
+	/* Save non-volatile registers (r14 - r31) */
+	SAVE_NVGPRS(r1)
+
+	/* Save host PMU registers and load guest PMU registers */
+	/* R4 is live here (vcpu pointer) but not r3 or r5 */
+	li	r3, 1
+	sldi	r3, r3, 31		/* MMCR0_FC (freeze counters) bit */
+	mfspr	r7, SPRN_MMCR0		/* save MMCR0 */
+	mtspr	SPRN_MMCR0, r3		/* freeze all counters, disable interrupts */
+	isync
+	ld	r3, PACALPPACAPTR(r13)	/* is the host using the PMU? */
+	lbz	r5, LPPACA_PMCINUSE(r3)
+	cmpwi	r5, 0
+	beq	31f			/* skip if not */
+	mfspr	r5, SPRN_MMCR1
+	mfspr	r6, SPRN_MMCRA
+	std	r7, HSTATE_MMCR(r13)
+	std	r5, HSTATE_MMCR + 8(r13)
+	std	r6, HSTATE_MMCR + 16(r13)
+	mfspr	r3, SPRN_PMC1
+	mfspr	r5, SPRN_PMC2
+	mfspr	r6, SPRN_PMC3
+	mfspr	r7, SPRN_PMC4
+	mfspr	r8, SPRN_PMC5
+	mfspr	r9, SPRN_PMC6
+	stw	r3, HSTATE_PMC(r13)
+	stw	r5, HSTATE_PMC + 4(r13)
+	stw	r6, HSTATE_PMC + 8(r13)
+	stw	r7, HSTATE_PMC + 12(r13)
+	stw	r8, HSTATE_PMC + 16(r13)
+	stw	r9, HSTATE_PMC + 20(r13)
+31:
+
+	/* Save host DSCR */
+	mfspr	r3, SPRN_DSCR
+	std	r3, HSTATE_DSCR(r13)
+
+	/* Save host DABR */
+	mfspr	r3, SPRN_DABR
+	std	r3, HSTATE_DABR(r13)
+
+	DISABLE_INTERRUPTS
+
+	/*
+	 * Put whatever is in the decrementer into the
+	 * hypervisor decrementer.
+	 */
+	mfspr	r8,SPRN_DEC
+	mftb	r7
+	mtspr	SPRN_HDEC,r8
+	extsw	r8,r8
+	add	r8,r8,r7
+	std	r8,HSTATE_DECEXP(r13)
+
+	ld	r5, VCPU_TRAMPOLINE_ENTER(r4)
+	LOAD_REG_IMMEDIATE(r6, MSR_KERNEL & ~(MSR_IR | MSR_DR))
+
+	/* Jump to segment patching handler and into our guest */
+	b	kvmppc_rmcall
+
+/*
+ * This is the handler in module memory. It gets jumped at from the
+ * lowmem trampoline code, so it's basically the guest exit code.
+ *
+ */
+
+.global kvmppc_handler_highmem
+kvmppc_handler_highmem:
+
+	/*
+	 * Register usage at this point:
+	 *
+	 * R1       = host R1
+	 * R2       = host R2
+	 * R12      = exit handler id
+	 * R13      = PACA
+	 *
+	 */
+
+	/* R7 = vcpu */
+	ld	r7, HSTATE_KVM_VCPU(r13)
+
+	/*
+	 * Reload DEC.  HDEC interrupts were disabled when
+	 * we reloaded the host's LPCR value.
+	 */
+	ld	r3, HSTATE_DECEXP(r13)
+	mftb	r4
+	subf	r4, r4, r3
+	mtspr	SPRN_DEC, r4
+
+	ld	r3, PACALPPACAPTR(r13)	/* is the host using the PMU? */
+	lbz	r4, LPPACA_PMCINUSE(r3)
+	cmpwi	r4, 0
+	beq	23f			/* skip if not */
+	lwz	r3, HSTATE_PMC(r13)
+	lwz	r4, HSTATE_PMC + 4(r13)
+	lwz	r5, HSTATE_PMC + 8(r13)
+	lwz	r6, HSTATE_PMC + 12(r13)
+	lwz	r8, HSTATE_PMC + 16(r13)
+	lwz	r9, HSTATE_PMC + 20(r13)
+	mtspr	SPRN_PMC1, r3
+	mtspr	SPRN_PMC2, r4
+	mtspr	SPRN_PMC3, r5
+	mtspr	SPRN_PMC4, r6
+	mtspr	SPRN_PMC5, r8
+	mtspr	SPRN_PMC6, r9
+	ld	r3, HSTATE_MMCR(r13)
+	ld	r4, HSTATE_MMCR + 8(r13)
+	ld	r5, HSTATE_MMCR + 16(r13)
+	mtspr	SPRN_MMCR1, r4
+	mtspr	SPRN_MMCRA, r5
+	mtspr	SPRN_MMCR0, r3
+	isync
+23:
+
+	/* Restore host msr -> SRR1 */
+	ld	r4, VCPU_HOST_MSR(r7)
+
+	/*
+	 * For some interrupts, we need to call the real Linux
+	 * handler, so it can do work for us. This has to happen
+	 * as if the interrupt arrived from the kernel though,
+	 * so let's fake it here where most state is restored.
+	 *
+	 * Call Linux for hardware interrupts/decrementer
+	 * r3 = address of interrupt handler (exit reason)
+	 */
+	/* Note: preemption is disabled at this point */
+
+	cmpwi	r12, BOOK3S_INTERRUPT_MACHINE_CHECK
+	beq	1f
+	cmpwi	r12, BOOK3S_INTERRUPT_EXTERNAL
+	beq	1f
+
+	/* Back to EE=1 */
+	mtmsr	r4
+	sync
+	b	kvm_return_point
+
+1:	bl	call_linux_handler
+
+.global kvm_return_point
+kvm_return_point:
+	/* Restore non-volatile host registers (r14 - r31) */
+	REST_NVGPRS(r1)
+
+	addi    r1, r1, SWITCH_FRAME_SIZE
+	ld	r0, PPC_LR_STKOFF(r1)
+	mtlr	r0
+	blr
+
+call_linux_handler:
+	/* Restore host IP -> SRR0 */
+	mflr	r3
+	mtlr	r12
+
+	ld	r5, VCPU_TRAMPOLINE_LOWMEM(r7)
+	LOAD_REG_IMMEDIATE(r6, MSR_KERNEL & ~(MSR_IR | MSR_DR))
+	b	kvmppc_rmcall
+
+/*
+ * Save away FP, VMX and VSX registers.
+ * r3 = vcpu pointer
+*/
+_GLOBAL(kvmppc_save_fp)
+	mfmsr	r9
+	ori	r8,r9,MSR_FP
+#ifdef CONFIG_ALTIVEC
+#ifdef CONFIG_VSX
+	oris	r8,r8,(MSR_VEC|MSR_VSX)@h
+#else
+	oris	r8,r8,MSR_VEC@h
+#endif
+#endif
+	mtmsrd	r8
+	isync
+#ifdef CONFIG_VSX
+BEGIN_FTR_SECTION
+	reg = 0
+	.rept	32
+	li	r6,reg*16+VCPU_VSRS
+	stxvd2x	reg,r6,r3
+	reg = reg + 1
+	.endr
+FTR_SECTION_ELSE
+#endif
+	reg = 0
+	.rept	32
+	stfd	reg,reg*8+VCPU_FPRS(r3)
+	reg = reg + 1
+	.endr
+#ifdef CONFIG_VSX
+ALT_FTR_SECTION_END_IFSET(CPU_FTR_VSX)
+#endif
+	mffs	fr0
+	stfd	fr0,VCPU_FPSCR(r3)
+
+#ifdef CONFIG_ALTIVEC
+BEGIN_FTR_SECTION
+	reg = 0
+	.rept	32
+	li	r6,reg*16+VCPU_VRS
+	stvx	reg,r6,r3
+	reg = reg + 1
+	.endr
+	mfvscr	vr0
+	li	r6,VCPU_VSCR
+	stvx	vr0,r6,r3
+END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+#endif
+	mfspr	r6,SPRN_VRSAVE
+	stw	r6,VCPU_VRSAVE(r3)
+	mtmsrd	r9
+	isync
+	blr
+
+/*
+ * Load up FP, VMX and VSX registers
+ * r4 = vcpu pointer
+ */
+	.globl	kvmppc_load_fp
+kvmppc_load_fp:
+	mfmsr	r9
+	ori	r8,r9,MSR_FP
+#ifdef CONFIG_ALTIVEC
+#ifdef CONFIG_VSX
+	oris	r8,r8,(MSR_VEC|MSR_VSX)@h
+#else
+	oris	r8,r8,MSR_VEC@h
+#endif
+#endif
+	mtmsrd	r8
+	isync
+	lfd	fr0,VCPU_FPSCR(r4)
+	MTFSF_L(fr0)
+#ifdef CONFIG_VSX
+BEGIN_FTR_SECTION
+	reg = 0
+	.rept	32
+	li	r7,reg*16+VCPU_VSRS
+	lxvd2x	reg,r7,r4
+	reg = reg + 1
+	.endr
+FTR_SECTION_ELSE
+#endif
+	reg = 0
+	.rept	32
+	lfd	reg,reg*8+VCPU_FPRS(r4)
+	reg = reg + 1
+	.endr
+#ifdef CONFIG_VSX
+ALT_FTR_SECTION_END_IFSET(CPU_FTR_VSX)
+#endif
+
+#ifdef CONFIG_ALTIVEC
+	li	r7,VCPU_VSCR
+	lvx	vr0,r7,r4
+	mtvscr	vr0
+BEGIN_FTR_SECTION
+	reg = 0
+	.rept	32
+	li	r7,reg*16+VCPU_VRS
+	lvx	reg,r7,r4
+	reg = reg + 1
+	.endr
+END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+#endif
+	lwz	r7,VCPU_VRSAVE(r4)
+	mtspr	SPRN_VRSAVE,r7
+	blr
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
new file mode 100644
index 0000000..f0dc0ff
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -0,0 +1,667 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Copyright 2011 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
+ *
+ * Derived from book3s_rmhandlers.S and other files, which are:
+ *
+ * Copyright SUSE Linux Products GmbH 2009
+ *
+ * Authors: Alexander Graf <agraf@suse.de>
+ */
+
+#include <asm/ppc_asm.h>
+#include <asm/kvm_asm.h>
+#include <asm/reg.h>
+#include <asm/page.h>
+#include <asm/asm-offsets.h>
+#include <asm/exception-64s.h>
+
+/*****************************************************************************
+ *                                                                           *
+ *        Real Mode handlers that need to be in the linear mapping           *
+ *                                                                           *
+ ****************************************************************************/
+
+#define SHADOW_VCPU_OFF		PACA_KVM_SVCPU
+
+	.globl	kvmppc_skip_interrupt
+kvmppc_skip_interrupt:
+	mfspr	r13,SPRN_SRR0
+	addi	r13,r13,4
+	mtspr	SPRN_SRR0,r13
+	GET_SCRATCH0(r13)
+	rfid
+	b	.
+
+	.globl	kvmppc_skip_Hinterrupt
+kvmppc_skip_Hinterrupt:
+	mfspr	r13,SPRN_HSRR0
+	addi	r13,r13,4
+	mtspr	SPRN_HSRR0,r13
+	GET_SCRATCH0(r13)
+	hrfid
+	b	.
+
+/*
+ * This trampoline brings us back to a real mode handler
+ *
+ * Input Registers:
+ *
+ * R5 = SRR0
+ * R6 = SRR1
+ * R12 = real-mode IP
+ * LR = real-mode IP
+ *
+ * We have external interrupts set to come to the hypervisor using
+ * HSRR0/1, so if we're handling an external interrupt, we have to
+ * set HSRR0/1 rather than SRR0/1.
+ */
+.global kvmppc_handler_lowmem_trampoline
+kvmppc_handler_lowmem_trampoline:
+	cmpwi	r12,BOOK3S_INTERRUPT_EXTERNAL
+	beq	1f
+	mtsrr0	r3
+	mtsrr1	r4
+	blr
+1:	mtspr	SPRN_HSRR0,r3
+	mtspr	SPRN_HSRR1,r4
+	blr
+
+/*
+ * Call a function in real mode.
+ * Must be called with interrupts hard-disabled.
+ *
+ * Input Registers:
+ *
+ * R5 = function
+ * R6 = MSR
+ * R7 = scratch register
+ *
+ */
+_GLOBAL(kvmppc_rmcall)
+	mfmsr	r7
+	li	r0,MSR_RI		/* clear RI in MSR */
+	andc	r7,r7,r0
+	mtmsrd	r7,1
+	mtsrr0	r5
+	mtsrr1	r6
+	RFI
+
+.global kvmppc_trampoline_lowmem
+kvmppc_trampoline_lowmem:
+	PPC_LONG kvmppc_handler_lowmem_trampoline - _stext
+
+.global kvmppc_trampoline_enter
+kvmppc_trampoline_enter:
+	PPC_LONG kvmppc_handler_trampoline_enter - _stext
+
+#define ULONG_SIZE 		8
+#define VCPU_GPR(n)		(VCPU_GPRS + (n * ULONG_SIZE))
+
+/******************************************************************************
+ *                                                                            *
+ *                               Entry code                                   *
+ *                                                                            *
+ *****************************************************************************/
+
+.global kvmppc_handler_trampoline_enter
+kvmppc_handler_trampoline_enter:
+
+	/* Required state:
+	 *
+	 * R4 = vcpu pointer
+	 * MSR = ~IR|DR
+	 * R13 = PACA
+	 * R1 = host R1
+	 * all other volatile GPRS = free
+	 */
+	ld	r14, VCPU_GPR(r14)(r4)
+	ld	r15, VCPU_GPR(r15)(r4)
+	ld	r16, VCPU_GPR(r16)(r4)
+	ld	r17, VCPU_GPR(r17)(r4)
+	ld	r18, VCPU_GPR(r18)(r4)
+	ld	r19, VCPU_GPR(r19)(r4)
+	ld	r20, VCPU_GPR(r20)(r4)
+	ld	r21, VCPU_GPR(r21)(r4)
+	ld	r22, VCPU_GPR(r22)(r4)
+	ld	r23, VCPU_GPR(r23)(r4)
+	ld	r24, VCPU_GPR(r24)(r4)
+	ld	r25, VCPU_GPR(r25)(r4)
+	ld	r26, VCPU_GPR(r26)(r4)
+	ld	r27, VCPU_GPR(r27)(r4)
+	ld	r28, VCPU_GPR(r28)(r4)
+	ld	r29, VCPU_GPR(r29)(r4)
+	ld	r30, VCPU_GPR(r30)(r4)
+	ld	r31, VCPU_GPR(r31)(r4)
+
+	/* Load guest PMU registers */
+	/* R4 is live here (vcpu pointer) */
+	li	r3, 1
+	sldi	r3, r3, 31		/* MMCR0_FC (freeze counters) bit */
+	mtspr	SPRN_MMCR0, r3		/* freeze all counters, disable ints */
+	isync
+	lwz	r3, VCPU_PMC(r4)	/* always load up guest PMU registers */
+	lwz	r5, VCPU_PMC + 4(r4)	/* to prevent information leak */
+	lwz	r6, VCPU_PMC + 8(r4)
+	lwz	r7, VCPU_PMC + 12(r4)
+	lwz	r8, VCPU_PMC + 16(r4)
+	lwz	r9, VCPU_PMC + 20(r4)
+	mtspr	SPRN_PMC1, r3
+	mtspr	SPRN_PMC2, r5
+	mtspr	SPRN_PMC3, r6
+	mtspr	SPRN_PMC4, r7
+	mtspr	SPRN_PMC5, r8
+	mtspr	SPRN_PMC6, r9
+	ld	r3, VCPU_MMCR(r4)
+	ld	r5, VCPU_MMCR + 8(r4)
+	ld	r6, VCPU_MMCR + 16(r4)
+	mtspr	SPRN_MMCR1, r5
+	mtspr	SPRN_MMCRA, r6
+	mtspr	SPRN_MMCR0, r3
+	isync
+
+	/* Load up FP, VMX and VSX registers */
+	bl	kvmppc_load_fp
+
+	/* Switch DSCR to guest value */
+	ld	r5, VCPU_DSCR(r4)
+	mtspr	SPRN_DSCR, r5
+
+	/*
+	 * Set the decrementer to the guest decrementer.
+	 */
+	ld	r8,VCPU_DEC_EXPIRES(r4)
+	mftb	r7
+	subf	r3,r7,r8
+	mtspr	SPRN_DEC,r3
+	stw	r3,VCPU_DEC(r4)
+
+	ld	r5, VCPU_SPRG0(r4)
+	ld	r6, VCPU_SPRG1(r4)
+	ld	r7, VCPU_SPRG2(r4)
+	ld	r8, VCPU_SPRG3(r4)
+	mtspr	SPRN_SPRG0, r5
+	mtspr	SPRN_SPRG1, r6
+	mtspr	SPRN_SPRG2, r7
+	mtspr	SPRN_SPRG3, r8
+
+	/* Save R1 in the PACA */
+	std	r1, HSTATE_HOST_R1(r13)
+
+	/* Load up DAR and DSISR */
+	ld	r5, VCPU_DAR(r4)
+	lwz	r6, VCPU_DSISR(r4)
+	mtspr	SPRN_DAR, r5
+	mtspr	SPRN_DSISR, r6
+
+	/* Set partition DABR */
+	li	r5,3
+	ld	r6,VCPU_DABR(r4)
+	mtspr	SPRN_DABRX,r5
+	mtspr	SPRN_DABR,r6
+
+	/* Restore AMR and UAMOR, set AMOR to all 1s */
+	ld	r5,VCPU_AMR(r4)
+	ld	r6,VCPU_UAMOR(r4)
+	li	r7,-1
+	mtspr	SPRN_AMR,r5
+	mtspr	SPRN_UAMOR,r6
+	mtspr	SPRN_AMOR,r7
+
+	/* Clear out SLB */
+	li	r6,0
+	slbmte	r6,r6
+	slbia
+	ptesync
+
+	/* Switch to guest partition. */
+	ld	r9,VCPU_KVM(r4)		/* pointer to struct kvm */
+	ld	r6,KVM_SDR1(r9)
+	lwz	r7,KVM_LPID(r9)
+	li	r0,LPID_RSVD		/* switch to reserved LPID */
+	mtspr	SPRN_LPID,r0
+	ptesync
+	mtspr	SPRN_SDR1,r6		/* switch to partition page table */
+	mtspr	SPRN_LPID,r7
+	isync
+	ld	r8,VCPU_LPCR(r4)
+	mtspr	SPRN_LPCR,r8
+	isync
+
+	/* Check if HDEC expires soon */
+	mfspr	r3,SPRN_HDEC
+	cmpwi	r3,10
+	li	r12,BOOK3S_INTERRUPT_HV_DECREMENTER
+	mr	r9,r4
+	blt	hdec_soon
+
+	/*
+	 * Invalidate the TLB if we could possibly have stale TLB
+	 * entries for this partition on this core due to the use
+	 * of tlbiel.
+	 */
+	ld	r9,VCPU_KVM(r4)		/* pointer to struct kvm */
+	lwz	r5,VCPU_VCPUID(r4)
+	lhz	r6,PACAPACAINDEX(r13)
+	lhz	r8,VCPU_LAST_CPU(r4)
+	sldi	r7,r6,1			/* see if this is the same vcpu */
+	add	r7,r7,r9		/* as last ran on this pcpu */
+	lhz	r0,KVM_LAST_VCPU(r7)
+	cmpw	r6,r8			/* on the same cpu core as last time? */
+	bne	3f
+	cmpw	r0,r5			/* same vcpu as this core last ran? */
+	beq	1f
+3:	sth	r6,VCPU_LAST_CPU(r4)	/* if not, invalidate partition TLB */
+	sth	r5,KVM_LAST_VCPU(r7)
+	li	r6,128
+	mtctr	r6
+	li	r7,0x800		/* IS field = 0b10 */
+	ptesync
+2:	tlbiel	r7
+	addi	r7,r7,0x1000
+	bdnz	2b
+	ptesync
+1:
+
+	/* Save purr/spurr */
+	mfspr	r5,SPRN_PURR
+	mfspr	r6,SPRN_SPURR
+	std	r5,HSTATE_PURR(r13)
+	std	r6,HSTATE_SPURR(r13)
+	ld	r7,VCPU_PURR(r4)
+	ld	r8,VCPU_SPURR(r4)
+	mtspr	SPRN_PURR,r7
+	mtspr	SPRN_SPURR,r8
+
+	/* Load up guest SLB entries */
+	lwz	r5,VCPU_SLB_MAX(r4)
+	cmpwi	r5,0
+	beq	9f
+	mtctr	r5
+	addi	r6,r4,VCPU_SLB
+1:	ld	r8,VCPU_SLB_E(r6)
+	ld	r9,VCPU_SLB_V(r6)
+	slbmte	r9,r8
+	addi	r6,r6,VCPU_SLB_SIZE
+	bdnz	1b
+9:
+
+	/* Restore state of CTRL run bit; assume 1 on entry */
+	lwz	r5,VCPU_CTRL(r4)
+	andi.	r5,r5,1
+	bne	4f
+	mfspr	r6,SPRN_CTRLF
+	clrrdi	r6,r6,1
+	mtspr	SPRN_CTRLT,r6
+4:
+	ld	r6, VCPU_CTR(r4)
+	lwz	r7, VCPU_XER(r4)
+
+	mtctr	r6
+	mtxer	r7
+
+	/* Move SRR0 and SRR1 into the respective regs */
+	ld	r6, VCPU_SRR0(r4)
+	ld	r7, VCPU_SRR1(r4)
+	mtspr	SPRN_SRR0, r6
+	mtspr	SPRN_SRR1, r7
+
+	ld	r10, VCPU_PC(r4)
+
+	ld	r11, VCPU_MSR(r4)	/* r10 = vcpu->arch.msr & ~MSR_HV */
+	rldicl	r11, r11, 63 - MSR_HV_LG, 1
+	rotldi	r11, r11, 1 + MSR_HV_LG
+	ori	r11, r11, MSR_ME
+
+fast_guest_return:
+	mtspr	SPRN_HSRR0,r10
+	mtspr	SPRN_HSRR1,r11
+
+	/* Activate guest mode, so faults get handled by KVM */
+	li	r9, KVM_GUEST_MODE_GUEST
+	stb	r9, HSTATE_IN_GUEST(r13)
+
+	/* Enter guest */
+
+	ld	r5, VCPU_LR(r4)
+	lwz	r6, VCPU_CR(r4)
+	mtlr	r5
+	mtcr	r6
+
+	ld	r0, VCPU_GPR(r0)(r4)
+	ld	r1, VCPU_GPR(r1)(r4)
+	ld	r2, VCPU_GPR(r2)(r4)
+	ld	r3, VCPU_GPR(r3)(r4)
+	ld	r5, VCPU_GPR(r5)(r4)
+	ld	r6, VCPU_GPR(r6)(r4)
+	ld	r7, VCPU_GPR(r7)(r4)
+	ld	r8, VCPU_GPR(r8)(r4)
+	ld	r9, VCPU_GPR(r9)(r4)
+	ld	r10, VCPU_GPR(r10)(r4)
+	ld	r11, VCPU_GPR(r11)(r4)
+	ld	r12, VCPU_GPR(r12)(r4)
+	ld	r13, VCPU_GPR(r13)(r4)
+
+	ld	r4, VCPU_GPR(r4)(r4)
+
+	hrfid
+	b	.
+kvmppc_handler_trampoline_enter_end:
+
+
+/******************************************************************************
+ *                                                                            *
+ *                               Exit code                                    *
+ *                                                                            *
+ *****************************************************************************/
+
+/*
+ * We come here from the first-level interrupt handlers.
+ */
+	.globl	kvmppc_interrupt
+kvmppc_interrupt:
+	/*
+	 * Register contents:
+	 * R12		= interrupt vector
+	 * R13		= PACA
+	 * guest CR, R12 saved in shadow VCPU SCRATCH1/0
+	 * guest R13 saved in SPRN_SCRATCH0
+	 */
+	/* abuse host_r2 as third scratch area; we get r2 from PACATOC(r13) */
+	std	r9, HSTATE_HOST_R2(r13)
+	ld	r9, HSTATE_KVM_VCPU(r13)
+
+	/* Save registers */
+
+	std	r0, VCPU_GPR(r0)(r9)
+	std	r1, VCPU_GPR(r1)(r9)
+	std	r2, VCPU_GPR(r2)(r9)
+	std	r3, VCPU_GPR(r3)(r9)
+	std	r4, VCPU_GPR(r4)(r9)
+	std	r5, VCPU_GPR(r5)(r9)
+	std	r6, VCPU_GPR(r6)(r9)
+	std	r7, VCPU_GPR(r7)(r9)
+	std	r8, VCPU_GPR(r8)(r9)
+	ld	r0, HSTATE_HOST_R2(r13)
+	std	r0, VCPU_GPR(r9)(r9)
+	std	r10, VCPU_GPR(r10)(r9)
+	std	r11, VCPU_GPR(r11)(r9)
+	ld	r3, HSTATE_SCRATCH0(r13)
+	lwz	r4, HSTATE_SCRATCH1(r13)
+	std	r3, VCPU_GPR(r12)(r9)
+	stw	r4, VCPU_CR(r9)
+
+	/* Restore R1/R2 so we can handle faults */
+	ld	r1, HSTATE_HOST_R1(r13)
+	ld	r2, PACATOC(r13)
+
+	mfspr	r10, SPRN_SRR0
+	mfspr	r11, SPRN_SRR1
+	std	r10, VCPU_SRR0(r9)
+	std	r11, VCPU_SRR1(r9)
+	andi.	r0, r12, 2		/* need to read HSRR0/1? */
+	beq	1f
+	mfspr	r10, SPRN_HSRR0
+	mfspr	r11, SPRN_HSRR1
+	clrrdi	r12, r12, 2
+1:	std	r10, VCPU_PC(r9)
+	std	r11, VCPU_MSR(r9)
+
+	GET_SCRATCH0(r3)
+	mflr	r4
+	std	r3, VCPU_GPR(r13)(r9)
+	std	r4, VCPU_LR(r9)
+
+	/* Unset guest mode */
+	li	r0, KVM_GUEST_MODE_NONE
+	stb	r0, HSTATE_IN_GUEST(r13)
+
+	stw	r12,VCPU_TRAP(r9)
+
+	/* See if this is a leftover HDEC interrupt */
+	cmpwi	r12,BOOK3S_INTERRUPT_HV_DECREMENTER
+	bne	2f
+	mfspr	r3,SPRN_HDEC
+	cmpwi	r3,0
+	bge	ignore_hdec
+2:
+
+	/* Check for mediated interrupts (could be done earlier really ...) */
+	cmpwi	r12,BOOK3S_INTERRUPT_EXTERNAL
+	bne+	1f
+	ld	r5,VCPU_LPCR(r9)
+	andi.	r0,r11,MSR_EE
+	beq	1f
+	andi.	r0,r5,LPCR_MER
+	bne	bounce_ext_interrupt
+1:
+
+	/* Save DEC */
+	mfspr	r5,SPRN_DEC
+	mftb	r6
+	extsw	r5,r5
+	add	r5,r5,r6
+	std	r5,VCPU_DEC_EXPIRES(r9)
+
+	/* Save HEIR (HV emulation assist reg) in last_inst
+	   if this is an HEI (HV emulation interrupt, e40) */
+	li	r3,-1
+	cmpwi	r12,BOOK3S_INTERRUPT_H_EMUL_ASSIST
+	bne	11f
+	mfspr	r3,SPRN_HEIR
+11:	stw	r3,VCPU_LAST_INST(r9)
+
+	/* Save more register state  */
+	mfxer	r5
+	mfdar	r6
+	mfdsisr	r7
+	mfctr	r8
+
+	stw	r5, VCPU_XER(r9)
+	std	r6, VCPU_DAR(r9)
+	stw	r7, VCPU_DSISR(r9)
+	std	r8, VCPU_CTR(r9)
+	/* grab HDAR & HDSISR if HV data storage interrupt (HDSI) */
+	cmpwi	r12,BOOK3S_INTERRUPT_H_DATA_STORAGE
+	beq	6f
+7:	std	r6, VCPU_FAULT_DAR(r9)
+	stw	r7, VCPU_FAULT_DSISR(r9)
+
+	/* Save guest CTRL register, set runlatch to 1 */
+	mfspr	r6,SPRN_CTRLF
+	stw	r6,VCPU_CTRL(r9)
+	andi.	r0,r6,1
+	bne	4f
+	ori	r6,r6,1
+	mtspr	SPRN_CTRLT,r6
+4:
+	/* Read the guest SLB and save it away */
+	lwz	r0,VCPU_SLB_NR(r9)	/* number of entries in SLB */
+	mtctr	r0
+	li	r6,0
+	addi	r7,r9,VCPU_SLB
+	li	r5,0
+1:	slbmfee	r8,r6
+	andis.	r0,r8,SLB_ESID_V@h
+	beq	2f
+	add	r8,r8,r6		/* put index in */
+	slbmfev	r3,r6
+	std	r8,VCPU_SLB_E(r7)
+	std	r3,VCPU_SLB_V(r7)
+	addi	r7,r7,VCPU_SLB_SIZE
+	addi	r5,r5,1
+2:	addi	r6,r6,1
+	bdnz	1b
+	stw	r5,VCPU_SLB_MAX(r9)
+
+	/*
+	 * Save the guest PURR/SPURR
+	 */
+	mfspr	r5,SPRN_PURR
+	mfspr	r6,SPRN_SPURR
+	ld	r7,VCPU_PURR(r9)
+	ld	r8,VCPU_SPURR(r9)
+	std	r5,VCPU_PURR(r9)
+	std	r6,VCPU_SPURR(r9)
+	subf	r5,r7,r5
+	subf	r6,r8,r6
+
+	/*
+	 * Restore host PURR/SPURR and add guest times
+	 * so that the time in the guest gets accounted.
+	 */
+	ld	r3,HSTATE_PURR(r13)
+	ld	r4,HSTATE_SPURR(r13)
+	add	r3,r3,r5
+	add	r4,r4,r6
+	mtspr	SPRN_PURR,r3
+	mtspr	SPRN_SPURR,r4
+
+	/* Clear out SLB */
+	li	r5,0
+	slbmte	r5,r5
+	slbia
+	ptesync
+
+hdec_soon:
+	/* Switch back to host partition */
+	ld	r4,VCPU_KVM(r9)		/* pointer to struct kvm */
+	ld	r6,KVM_HOST_SDR1(r4)
+	lwz	r7,KVM_HOST_LPID(r4)
+	li	r8,LPID_RSVD		/* switch to reserved LPID */
+	mtspr	SPRN_LPID,r8
+	ptesync
+	mtspr	SPRN_SDR1,r6		/* switch to partition page table */
+	mtspr	SPRN_LPID,r7
+	isync
+	lis	r8,0x7fff		/* MAX_INT@h */
+	mtspr	SPRN_HDEC,r8
+
+	ld	r8,KVM_HOST_LPCR(r4)
+	mtspr	SPRN_LPCR,r8
+	isync
+
+	/* load host SLB entries */
+	ld	r8,PACA_SLBSHADOWPTR(r13)
+
+	.rept	SLB_NUM_BOLTED
+	ld	r5,SLBSHADOW_SAVEAREA(r8)
+	ld	r6,SLBSHADOW_SAVEAREA+8(r8)
+	andis.	r7,r5,SLB_ESID_V@h
+	beq	1f
+	slbmte	r6,r5
+1:	addi	r8,r8,16
+	.endr
+
+	/* Save and reset AMR and UAMOR before turning on the MMU */
+	mfspr	r5,SPRN_AMR
+	mfspr	r6,SPRN_UAMOR
+	std	r5,VCPU_AMR(r9)
+	std	r6,VCPU_UAMOR(r9)
+	li	r6,0
+	mtspr	SPRN_AMR,r6
+
+	/* Restore host DABR and DABRX */
+	ld	r5,HSTATE_DABR(r13)
+	li	r6,7
+	mtspr	SPRN_DABR,r5
+	mtspr	SPRN_DABRX,r6
+
+	/* Switch DSCR back to host value */
+	mfspr	r8, SPRN_DSCR
+	ld	r7, HSTATE_DSCR(r13)
+	std	r8, VCPU_DSCR(r7)
+	mtspr	SPRN_DSCR, r7
+
+	/* Save non-volatile GPRs */
+	std	r14, VCPU_GPR(r14)(r9)
+	std	r15, VCPU_GPR(r15)(r9)
+	std	r16, VCPU_GPR(r16)(r9)
+	std	r17, VCPU_GPR(r17)(r9)
+	std	r18, VCPU_GPR(r18)(r9)
+	std	r19, VCPU_GPR(r19)(r9)
+	std	r20, VCPU_GPR(r20)(r9)
+	std	r21, VCPU_GPR(r21)(r9)
+	std	r22, VCPU_GPR(r22)(r9)
+	std	r23, VCPU_GPR(r23)(r9)
+	std	r24, VCPU_GPR(r24)(r9)
+	std	r25, VCPU_GPR(r25)(r9)
+	std	r26, VCPU_GPR(r26)(r9)
+	std	r27, VCPU_GPR(r27)(r9)
+	std	r28, VCPU_GPR(r28)(r9)
+	std	r29, VCPU_GPR(r29)(r9)
+	std	r30, VCPU_GPR(r30)(r9)
+	std	r31, VCPU_GPR(r31)(r9)
+
+	/* Save SPRGs */
+	mfspr	r3, SPRN_SPRG0
+	mfspr	r4, SPRN_SPRG1
+	mfspr	r5, SPRN_SPRG2
+	mfspr	r6, SPRN_SPRG3
+	std	r3, VCPU_SPRG0(r9)
+	std	r4, VCPU_SPRG1(r9)
+	std	r5, VCPU_SPRG2(r9)
+	std	r6, VCPU_SPRG3(r9)
+
+	/* Save PMU registers */
+	li	r3, 1
+	sldi	r3, r3, 31		/* MMCR0_FC (freeze counters) bit */
+	mfspr	r4, SPRN_MMCR0		/* save MMCR0 */
+	mtspr	SPRN_MMCR0, r3		/* freeze all counters, disable ints */
+	isync
+	mfspr	r5, SPRN_MMCR1
+	mfspr	r6, SPRN_MMCRA
+	std	r4, VCPU_MMCR(r9)
+	std	r5, VCPU_MMCR + 8(r9)
+	std	r6, VCPU_MMCR + 16(r9)
+	mfspr	r3, SPRN_PMC1
+	mfspr	r4, SPRN_PMC2
+	mfspr	r5, SPRN_PMC3
+	mfspr	r6, SPRN_PMC4
+	mfspr	r7, SPRN_PMC5
+	mfspr	r8, SPRN_PMC6
+	stw	r3, VCPU_PMC(r9)
+	stw	r4, VCPU_PMC + 4(r9)
+	stw	r5, VCPU_PMC + 8(r9)
+	stw	r6, VCPU_PMC + 12(r9)
+	stw	r7, VCPU_PMC + 16(r9)
+	stw	r8, VCPU_PMC + 20(r9)
+22:
+	/* save FP state */
+	mr	r3, r9
+	bl	.kvmppc_save_fp
+
+	/* RFI into the highmem handler */
+	mfmsr	r7
+	ori	r7, r7, MSR_IR|MSR_DR|MSR_RI|MSR_ME	/* Enable paging */
+	mtsrr1	r7
+	/* Load highmem handler address */
+	ld	r8, VCPU_HIGHMEM_HANDLER(r3)
+	mtsrr0	r8
+
+	RFI
+kvmppc_handler_trampoline_exit_end:
+
+6:	mfspr	r6,SPRN_HDAR
+	mfspr	r7,SPRN_HDSISR
+	b	7b
+
+ignore_hdec:
+	mr	r4,r9
+	b	fast_guest_return
+
+bounce_ext_interrupt:
+	mr	r4,r9
+	mtspr	SPRN_SRR0,r10
+	mtspr	SPRN_SRR1,r11
+	li	r10,BOOK3S_INTERRUPT_EXTERNAL
+	LOAD_REG_IMMEDIATE(r11,MSR_SF | MSR_ME);
+	b	fast_guest_return
diff --git a/arch/powerpc/kvm/book3s_segment.S b/arch/powerpc/kvm/book3s_segment.S
index b0ae527..174d59c 100644
--- a/arch/powerpc/kvm/book3s_segment.S
+++ b/arch/powerpc/kvm/book3s_segment.S
@@ -85,29 +85,29 @@ kvmppc_handler_trampoline_enter:
 
 	/* Enter guest */
 
-	PPC_LL	r4, (SVCPU_CTR)(r3)
-	PPC_LL	r5, (SVCPU_LR)(r3)
-	lwz	r6, (SVCPU_CR)(r3)
-	lwz	r7, (SVCPU_XER)(r3)
+	PPC_LL	r4, SVCPU_CTR(r3)
+	PPC_LL	r5, SVCPU_LR(r3)
+	lwz	r6, SVCPU_CR(r3)
+	lwz	r7, SVCPU_XER(r3)
 
 	mtctr	r4
 	mtlr	r5
 	mtcr	r6
 	mtxer	r7
 
-	PPC_LL	r0, (SVCPU_R0)(r3)
-	PPC_LL	r1, (SVCPU_R1)(r3)
-	PPC_LL	r2, (SVCPU_R2)(r3)
-	PPC_LL	r4, (SVCPU_R4)(r3)
-	PPC_LL	r5, (SVCPU_R5)(r3)
-	PPC_LL	r6, (SVCPU_R6)(r3)
-	PPC_LL	r7, (SVCPU_R7)(r3)
-	PPC_LL	r8, (SVCPU_R8)(r3)
-	PPC_LL	r9, (SVCPU_R9)(r3)
-	PPC_LL	r10, (SVCPU_R10)(r3)
-	PPC_LL	r11, (SVCPU_R11)(r3)
-	PPC_LL	r12, (SVCPU_R12)(r3)
-	PPC_LL	r13, (SVCPU_R13)(r3)
+	PPC_LL	r0, SVCPU_R0(r3)
+	PPC_LL	r1, SVCPU_R1(r3)
+	PPC_LL	r2, SVCPU_R2(r3)
+	PPC_LL	r4, SVCPU_R4(r3)
+	PPC_LL	r5, SVCPU_R5(r3)
+	PPC_LL	r6, SVCPU_R6(r3)
+	PPC_LL	r7, SVCPU_R7(r3)
+	PPC_LL	r8, SVCPU_R8(r3)
+	PPC_LL	r9, SVCPU_R9(r3)
+	PPC_LL	r10, SVCPU_R10(r3)
+	PPC_LL	r11, SVCPU_R11(r3)
+	PPC_LL	r12, SVCPU_R12(r3)
+	PPC_LL	r13, SVCPU_R13(r3)
 
 	PPC_LL	r3, (SVCPU_R3)(r3)
 
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 74179b9..a5635c9 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -38,8 +38,12 @@
 
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
 {
+#ifndef CONFIG_KVM_BOOK3S_64_HV
 	return !(v->arch.shared->msr & MSR_WE) ||
 	       !!(v->arch.pending_exceptions);
+#else
+	return 1;
+#endif
 }
 
 int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
@@ -183,10 +187,13 @@ int kvm_dev_ioctl_check_extension(long ext)
 #else
 	case KVM_CAP_PPC_SEGSTATE:
 #endif
-	case KVM_CAP_PPC_PAIRED_SINGLES:
 	case KVM_CAP_PPC_UNSET_IRQ:
 	case KVM_CAP_PPC_IRQ_LEVEL:
 	case KVM_CAP_ENABLE_CAP:
+		r = 1;
+		break;
+#ifndef CONFIG_KVM_BOOK3S_64_HV
+	case KVM_CAP_PPC_PAIRED_SINGLES:
 	case KVM_CAP_PPC_OSI:
 	case KVM_CAP_PPC_GET_PVINFO:
 		r = 1;
@@ -194,6 +201,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_COALESCED_MMIO:
 		r = KVM_COALESCED_MMIO_PAGE_OFFSET;
 		break;
+#endif
 	default:
 		r = 0;
 		break;
@@ -290,6 +298,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	hrtimer_init(&vcpu->arch.dec_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
 	tasklet_init(&vcpu->arch.tasklet, kvmppc_decrementer_func, (ulong)vcpu);
 	vcpu->arch.dec_timer.function = kvmppc_decrementer_wakeup;
+	vcpu->arch.dec_expires = ~(u64)0;
 
 #ifdef CONFIG_KVM_EXIT_TIMING
 	mutex_init(&vcpu->arch.exit_timing_lock);
@@ -316,6 +325,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	mtspr(SPRN_VRSAVE, vcpu->arch.vrsave);
 #endif
 	kvmppc_core_vcpu_load(vcpu, cpu);
+	vcpu->cpu = smp_processor_id();
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
@@ -324,6 +334,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 #ifdef CONFIG_BOOKE
 	vcpu->arch.vrsave = mfspr(SPRN_VRSAVE);
 #endif
+	vcpu->cpu = -1;
 }
 
 int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
@@ -495,6 +506,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		for (i = 0; i < 32; i++)
 			kvmppc_set_gpr(vcpu, i, gprs[i]);
 		vcpu->arch.osi_needed = 0;
+	} else if (vcpu->arch.hcall_needed) {
+		int i;
+
+		kvmppc_set_gpr(vcpu, 3, run->papr_hcall.ret);
+		for (i = 0; i < 9; ++i)
+			kvmppc_set_gpr(vcpu, 4 + i, run->papr_hcall.args[i]);
+		vcpu->arch.hcall_needed = 0;
 	}
 
 	kvmppc_core_deliver_interrupts(vcpu);
@@ -517,6 +535,8 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq)
 	if (waitqueue_active(&vcpu->wq)) {
 		wake_up_interruptible(&vcpu->wq);
 		vcpu->stat.halt_wakeup++;
+	} else if (vcpu->cpu != -1) {
+		smp_send_reschedule(vcpu->cpu);
 	}
 
 	return 0;
diff --git a/arch/powerpc/kvm/trace.h b/arch/powerpc/kvm/trace.h
index d62a14b..b135d3d 100644
--- a/arch/powerpc/kvm/trace.h
+++ b/arch/powerpc/kvm/trace.h
@@ -103,7 +103,7 @@ TRACE_EVENT(kvm_gtlb_write,
  *                         Book3S trace points                           *
  *************************************************************************/
 
-#ifdef CONFIG_PPC_BOOK3S
+#ifdef CONFIG_KVM_BOOK3S_PR
 
 TRACE_EVENT(kvm_book3s_exit,
 	TP_PROTO(unsigned int exit_nr, struct kvm_vcpu *vcpu),
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 55ef181..bea0116 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -161,6 +161,7 @@ struct kvm_pit_config {
 #define KVM_EXIT_NMI              16
 #define KVM_EXIT_INTERNAL_ERROR   17
 #define KVM_EXIT_OSI              18
+#define KVM_EXIT_PAPR_HCALL	  19
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 #define KVM_INTERNAL_ERROR_EMULATION 1
@@ -264,6 +265,11 @@ struct kvm_run {
 		struct {
 			__u64 gprs[32];
 		} osi;
+		struct {
+			__u64 nr;
+			__u64 ret;
+			__u64 args[9];
+		} papr_hcall;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
-- 
1.7.5.3

[PATCH v2 10/12] kvm/powerpc: Handle some PAPR hcalls in the kernel

[Paul Mackerras]

This adds the infrastructure for handling PAPR hcalls in the kernel,
either early in the guest exit path while we are still in real mode,
or later once the MMU has been turned back on and we are in the full
kernel context.  The advantage of handling hcalls in real mode if
possible is that we avoid two partition switches -- and this will
become more important when we support SMT4 guests, since a partition
switch means we have to pull all of the threads in the core out of
the guest.  The disadvantage is that we can only access the kernel
linear mapping, not anything vmalloced or ioremapped, since the MMU
is off.

This also adds code to handle the following hcalls in real mode:

H_ENTER       Add an HPTE to the hashed page table
H_REMOVE      Remove an HPTE from the hashed page table
H_READ        Read HPTEs from the hashed page table
H_PROTECT     Change the protection bits in an HPTE
H_BULK_REMOVE Remove up to 4 HPTEs from the hashed page table
H_SET_DABR    Set the data address breakpoint register

Plus code to handle the following hcalls in the kernel:

H_CEDE        Idle the vcpu until an interrupt or H_PROD hcall arrives
H_PROD        Wake up a ceded vcpu
H_REGISTER_VPA Register a virtual processor area (VPA)

Signed-off-by: Paul Mackerras <paulus@samba.org>
---
 arch/powerpc/include/asm/hvcall.h       |    5 +
 arch/powerpc/include/asm/kvm_host.h     |   11 +
 arch/powerpc/include/asm/kvm_ppc.h      |    1 +
 arch/powerpc/kernel/asm-offsets.c       |    2 +
 arch/powerpc/kvm/book3s_64_mmu_hv.c     |  342 +++++++++++++++++++++++++++++++
 arch/powerpc/kvm/book3s_hv.c            |  170 +++++++++++++++-
 arch/powerpc/kvm/book3s_hv_rmhandlers.S |  156 ++++++++++++++-
 arch/powerpc/kvm/powerpc.c              |    2 +-
 8 files changed, 685 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index fd8201d..1c324ff 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -29,6 +29,10 @@
 #define H_LONG_BUSY_ORDER_100_SEC	9905  /* Long busy, hint that 100sec \
 						 is a good time to retry */
 #define H_LONG_BUSY_END_RANGE		9905  /* End of long busy range */
+
+/* Internal value used in book3s_hv kvm support; not returned to guests */
+#define H_TOO_HARD	9999
+
 #define H_HARDWARE	-1	/* Hardware error */
 #define H_FUNCTION	-2	/* Function not supported */
 #define H_PRIVILEGE	-3	/* Caller not privileged */
@@ -100,6 +104,7 @@
 #define H_PAGE_SET_ACTIVE	H_PAGE_STATE_CHANGE
 #define H_AVPN			(1UL<<(63-32))	/* An avpn is provided as a sanity test */
 #define H_ANDCOND		(1UL<<(63-33))
+#define H_LOCAL			(1UL<<(63-35))
 #define H_ICACHE_INVALIDATE	(1UL<<(63-40))	/* icbi, etc.  (ignored for IO pages) */
 #define H_ICACHE_SYNCHRONIZE	(1UL<<(63-41))	/* dcbst, icbi, etc (ignored for IO pages */
 #define H_COALESCE_CAND	(1UL<<(63-42))	/* page is a good candidate for coalescing */
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 5645532..359db37 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -59,6 +59,10 @@ struct kvm;
 struct kvm_run;
 struct kvm_vcpu;
 
+struct lppaca;
+struct slb_shadow;
+struct dtl;
+
 struct kvm_vm_stat {
 	u32 remote_tlb_flush;
 };
@@ -337,7 +341,14 @@ struct kvm_vcpu_arch {
 	u64 dec_expires;
 	unsigned long pending_exceptions;
 	u16 last_cpu;
+	u8 ceded;
+	u8 prodded;
 	u32 last_inst;
+
+	struct lppaca *vpa;
+	struct slb_shadow *slb_shadow;
+	struct dtl *dtl;
+	struct dtl *dtl_end;
 	int trap;
 	struct kvm_vcpu_arch_shared *shared;
 	unsigned long magic_page_pa; /* phys addr to map the magic page to */
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 2a10e82..d809e58 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -117,6 +117,7 @@ extern long kvmppc_prepare_vrma(struct kvm *kvm,
 				struct kvm_userspace_memory_region *mem);
 extern void kvmppc_map_vrma(struct kvm *kvm,
 			    struct kvm_userspace_memory_region *mem);
+extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu);
 extern int kvmppc_core_init_vm(struct kvm *kvm);
 extern void kvmppc_core_destroy_vm(struct kvm *kvm);
 extern int kvmppc_core_prepare_memory_region(struct kvm *kvm,
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index a2f540b..d29f19a 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -189,6 +189,7 @@ int main(void)
 	DEFINE(LPPACADECRINT, offsetof(struct lppaca, int_dword.fields.decr_int));
 	DEFINE(LPPACA_PMCINUSE, offsetof(struct lppaca, pmcregs_in_use));
 	DEFINE(LPPACA_DTLIDX, offsetof(struct lppaca, dtl_idx));
+	DEFINE(LPPACA_YIELDCOUNT, offsetof(struct lppaca, yield_count));
 	DEFINE(PACA_DTL_RIDX, offsetof(struct paca_struct, dtl_ridx));
 #endif /* CONFIG_PPC_STD_MMU_64 */
 	DEFINE(PACAEMERGSP, offsetof(struct paca_struct, emergency_sp));
@@ -458,6 +459,7 @@ int main(void)
 	DEFINE(VCPU_DEC, offsetof(struct kvm_vcpu, arch.dec));
 	DEFINE(VCPU_DEC_EXPIRES, offsetof(struct kvm_vcpu, arch.dec_expires));
 	DEFINE(VCPU_LPCR, offsetof(struct kvm_vcpu, arch.lpcr));
+	DEFINE(VCPU_VPA, offsetof(struct kvm_vcpu, arch.vpa));
 	DEFINE(VCPU_MMCR, offsetof(struct kvm_vcpu, arch.mmcr));
 	DEFINE(VCPU_PMC, offsetof(struct kvm_vcpu, arch.pmc));
 	DEFINE(VCPU_SLB, offsetof(struct kvm_vcpu, arch.slb));
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 4a4fbec..f6fc4e5 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -219,6 +219,348 @@ void kvmppc_map_vrma(struct kvm *kvm, struct kvm_userspace_memory_region *mem)
 	}
 }
 
+#define HPTE_V_HVLOCK	0x40UL
+
+static inline long lock_hpte(unsigned long *hpte, unsigned long bits)
+{
+	unsigned long tmp, old;
+
+	asm volatile("	ldarx	%0,0,%2\n"
+		     "	and.	%1,%0,%3\n"
+		     "	bne	2f\n"
+		     "	ori	%0,%0,%4\n"
+		     "  stdcx.	%0,0,%2\n"
+		     "	beq+	2f\n"
+		     "	li	%1,%3\n"
+		     "2:	isync"
+		     : "=&r" (tmp), "=&r" (old)
+		     : "r" (hpte), "r" (bits), "i" (HPTE_V_HVLOCK)
+		     : "cc", "memory");
+	return old == 0;
+}
+
+long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
+		    long pte_index, unsigned long pteh, unsigned long ptel)
+{
+	unsigned long porder;
+	struct kvm *kvm = vcpu->kvm;
+	unsigned long i, lpn, pa;
+	unsigned long *hpte;
+
+	/* only handle 4k, 64k and 16M pages for now */
+	porder = 12;
+	if (pteh & HPTE_V_LARGE) {
+		if ((ptel & 0xf000) == 0x1000) {
+			/* 64k page */
+			porder = 16;
+		} else if ((ptel & 0xff000) == 0) {
+			/* 16M page */
+			porder = 24;
+			/* lowest AVA bit must be 0 for 16M pages */
+			if (pteh & 0x80)
+				return H_PARAMETER;
+		} else
+			return H_PARAMETER;
+	}
+	lpn = (ptel & HPTE_R_RPN) >> kvm->arch.ram_porder;
+	if (lpn >= kvm->arch.ram_npages || porder > kvm->arch.ram_porder)
+		return H_PARAMETER;
+	pa = kvm->arch.ram_pginfo[lpn].pfn << PAGE_SHIFT;
+	if (!pa)
+		return H_PARAMETER;
+	/* Check WIMG */
+	if ((ptel & HPTE_R_WIMG) != HPTE_R_M &&
+	    (ptel & HPTE_R_WIMG) != (HPTE_R_W | HPTE_R_I | HPTE_R_M))
+		return H_PARAMETER;
+	pteh &= ~0x60UL;
+	ptel &= ~(HPTE_R_PP0 - kvm->arch.ram_psize);
+	ptel |= pa;
+	if (pte_index >= (HPT_NPTEG << 3))
+		return H_PARAMETER;
+	if (likely((flags & H_EXACT) == 0)) {
+		pte_index &= ~7UL;
+		hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
+		for (i = 0; ; ++i) {
+			if (i == 8)
+				return H_PTEG_FULL;
+			if ((*hpte & HPTE_V_VALID) == 0 &&
+			    lock_hpte(hpte, HPTE_V_HVLOCK | HPTE_V_VALID))
+				break;
+			hpte += 2;
+		}
+	} else {
+		i = 0;
+		hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
+		if (!lock_hpte(hpte, HPTE_V_HVLOCK | HPTE_V_VALID))
+			return H_PTEG_FULL;
+	}
+	hpte[1] = ptel;
+	eieio();
+	hpte[0] = pteh;
+	asm volatile("ptesync" : : : "memory");
+	atomic_inc(&kvm->arch.ram_pginfo[lpn].refcnt);
+	vcpu->arch.gpr[4] = pte_index + i;
+	return H_SUCCESS;
+}
+
+static unsigned long compute_tlbie_rb(unsigned long v, unsigned long r,
+				      unsigned long pte_index)
+{
+	unsigned long rb, va_low;
+
+	rb = (v & ~0x7fUL) << 16;		/* AVA field */
+	va_low = pte_index >> 3;
+	if (v & HPTE_V_SECONDARY)
+		va_low = ~va_low;
+	/* xor vsid from AVA */
+	if (!(v & HPTE_V_1TB_SEG))
+		va_low ^= v >> 12;
+	else
+		va_low ^= v >> 24;
+	va_low &= 0x7ff;
+	if (v & HPTE_V_LARGE) {
+		rb |= 1;			/* L field */
+		if (r & 0xff000) {
+			/* non-16MB large page, must be 64k */
+			/* (masks depend on page size) */
+			rb |= 0x1000;		/* page encoding in LP field */
+			rb |= (va_low & 0x7f) << 16; /* 7b of VA in AVA/LP field */
+			rb |= (va_low & 0xfe);	/* AVAL field (P7 doesn't seem to care) */
+		}
+	} else {
+		/* 4kB page */
+		rb |= (va_low & 0x7ff) << 12;	/* remaining 11b of VA */
+	}
+	rb |= (v >> 54) & 0x300;		/* B field */
+	return rb;
+}
+
+#define LOCK_TOKEN	(*(u32 *)(&get_paca()->lock_token))
+
+static inline int try_lock_tlbie(unsigned int *lock)
+{
+	unsigned int tmp, old;
+	unsigned int token = LOCK_TOKEN;
+
+	asm volatile("1:lwarx	%1,0,%2\n"
+		     "	cmpwi	cr0,%1,0\n"
+		     "	bne	2f\n"
+		     "  stwcx.	%3,0,%2\n"
+		     "	bne-	1b\n"
+		     "  isync\n"
+		     "2:"
+		     : "=&r" (tmp), "=&r" (old)
+		     : "r" (lock), "r" (token)
+		     : "cc", "memory");
+	return old == 0;
+}
+
+long kvmppc_h_remove(struct kvm_vcpu *vcpu, unsigned long flags,
+		     unsigned long pte_index, unsigned long avpn,
+		     unsigned long va)
+{
+	struct kvm *kvm = vcpu->kvm;
+	unsigned long *hpte;
+	unsigned long v, r, rb;
+
+	if (pte_index >= (HPT_NPTEG << 3))
+		return H_PARAMETER;
+	hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
+	while (!lock_hpte(hpte, HPTE_V_HVLOCK))
+		cpu_relax();
+	if ((hpte[0] & HPTE_V_VALID) == 0 ||
+	    ((flags & H_AVPN) && (hpte[0] & ~0x7fUL) != avpn) ||
+	    ((flags & H_ANDCOND) && (hpte[0] & avpn) != 0)) {
+		hpte[0] &= ~HPTE_V_HVLOCK;
+		return H_NOT_FOUND;
+	}
+	if (atomic_read(&kvm->online_vcpus) == 1)
+		flags |= H_LOCAL;
+	vcpu->arch.gpr[4] = v = hpte[0] & ~HPTE_V_HVLOCK;
+	vcpu->arch.gpr[5] = r = hpte[1];
+	rb = compute_tlbie_rb(v, r, pte_index);
+	hpte[0] = 0;
+	if (!(flags & H_LOCAL)) {
+		while(!try_lock_tlbie(&kvm->arch.tlbie_lock))
+			cpu_relax();
+		asm volatile("ptesync" : : : "memory");
+		asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync"
+			     : : "r" (rb), "r" (kvm->arch.lpid));
+		asm volatile("ptesync" : : : "memory");
+		kvm->arch.tlbie_lock = 0;
+	} else {
+		asm volatile("ptesync" : : : "memory");
+		asm volatile("tlbiel %0" : : "r" (rb));
+		asm volatile("ptesync" : : : "memory");
+	}
+	return H_SUCCESS;
+}
+
+long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	unsigned long *args = &vcpu->arch.gpr[4];
+	unsigned long *hp, tlbrb[4];
+	long int i, found;
+	long int n_inval = 0;
+	unsigned long flags, req, pte_index;
+	long int local = 0;
+	long int ret = H_SUCCESS;
+
+	if (atomic_read(&kvm->online_vcpus) == 1)
+		local = 1;
+	for (i = 0; i < 4; ++i) {
+		pte_index = args[i * 2];
+		flags = pte_index >> 56;
+		pte_index &= ((1ul << 56) - 1);
+		req = flags >> 6;
+		flags &= 3;
+		if (req == 3)
+			break;
+		if (req != 1 || flags == 3 ||
+		    pte_index >= (HPT_NPTEG << 3)) {
+			/* parameter error */
+			args[i * 2] = ((0xa0 | flags) << 56) + pte_index;
+			ret = H_PARAMETER;
+			break;
+		}
+		hp = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
+		while (!lock_hpte(hp, HPTE_V_HVLOCK))
+			cpu_relax();
+		found = 0;
+		if (hp[0] & HPTE_V_VALID) {
+			switch (flags & 3) {
+			case 0:		/* absolute */
+				found = 1;
+				break;
+			case 1:		/* andcond */
+				if (!(hp[0] & args[i * 2 + 1]))
+					found = 1;
+				break;
+			case 2:		/* AVPN */
+				if ((hp[0] & ~0x7fUL) == args[i * 2 + 1])
+					found = 1;
+				break;
+			}
+		}
+		if (!found) {
+			hp[0] &= ~HPTE_V_HVLOCK;
+			args[i * 2] = ((0x90 | flags) << 56) + pte_index;
+			continue;
+		}
+		/* insert R and C bits from PTE */
+		flags |= (hp[1] >> 5) & 0x0c;
+		args[i * 2] = ((0x80 | flags) << 56) + pte_index;
+		tlbrb[n_inval++] = compute_tlbie_rb(hp[0], hp[1], pte_index);
+		hp[0] = 0;
+	}
+	if (n_inval == 0)
+		return ret;
+
+	if (!local) {
+		while(!try_lock_tlbie(&kvm->arch.tlbie_lock))
+			cpu_relax();
+		asm volatile("ptesync" : : : "memory");
+		for (i = 0; i < n_inval; ++i)
+			asm volatile(PPC_TLBIE(%1,%0)
+				     : : "r" (tlbrb[i]), "r" (kvm->arch.lpid));
+		asm volatile("eieio; tlbsync; ptesync" : : : "memory");
+		kvm->arch.tlbie_lock = 0;
+	} else {
+		asm volatile("ptesync" : : : "memory");
+		for (i = 0; i < n_inval; ++i)
+			asm volatile("tlbiel %0" : : "r" (tlbrb[i]));
+		asm volatile("ptesync" : : : "memory");
+	}
+	return ret;
+}
+
+long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
+		      unsigned long pte_index, unsigned long avpn,
+		      unsigned long va)
+{
+	struct kvm *kvm = vcpu->kvm;
+	unsigned long *hpte;
+	unsigned long v, r, rb;
+
+	if (pte_index >= (HPT_NPTEG << 3))
+		return H_PARAMETER;
+	hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
+	while (!lock_hpte(hpte, HPTE_V_HVLOCK))
+		cpu_relax();
+	if ((hpte[0] & HPTE_V_VALID) == 0 ||
+	    ((flags & H_AVPN) && (hpte[0] & ~0x7fUL) != avpn)) {
+		hpte[0] &= ~HPTE_V_HVLOCK;
+		return H_NOT_FOUND;
+	}
+	if (atomic_read(&kvm->online_vcpus) == 1)
+		flags |= H_LOCAL;
+	v = hpte[0];
+	r = hpte[1] & ~(HPTE_R_PP0 | HPTE_R_PP | HPTE_R_N |
+			HPTE_R_KEY_HI | HPTE_R_KEY_LO);
+	r |= (flags << 55) & HPTE_R_PP0;
+	r |= (flags << 48) & HPTE_R_KEY_HI;
+	r |= flags & (HPTE_R_PP | HPTE_R_N | HPTE_R_KEY_LO);
+	rb = compute_tlbie_rb(v, r, pte_index);
+	hpte[0] = v & ~HPTE_V_VALID;
+	if (!(flags & H_LOCAL)) {
+		while(!try_lock_tlbie(&kvm->arch.tlbie_lock))
+			cpu_relax();
+		asm volatile("ptesync" : : : "memory");
+		asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync"
+			     : : "r" (rb), "r" (kvm->arch.lpid));
+		asm volatile("ptesync" : : : "memory");
+		kvm->arch.tlbie_lock = 0;
+	} else {
+		asm volatile("ptesync" : : : "memory");
+		asm volatile("tlbiel %0" : : "r" (rb));
+		asm volatile("ptesync" : : : "memory");
+	}
+	hpte[1] = r;
+	eieio();
+	hpte[0] = v & ~HPTE_V_HVLOCK;
+	asm volatile("ptesync" : : : "memory");
+	return H_SUCCESS;
+}
+
+static unsigned long reverse_xlate(struct kvm *kvm, unsigned long realaddr)
+{
+	long int i;
+	unsigned long offset, rpn;
+
+	offset = realaddr & (kvm->arch.ram_psize - 1);
+	rpn = (realaddr - offset) >> PAGE_SHIFT;
+	for (i = 0; i < kvm->arch.ram_npages; ++i)
+		if (rpn == kvm->arch.ram_pginfo[i].pfn)
+			return (i << PAGE_SHIFT) + offset;
+	return HPTE_R_RPN;	/* all 1s in the RPN field */
+}
+
+long kvmppc_h_read(struct kvm_vcpu *vcpu, unsigned long flags,
+		   unsigned long pte_index)
+{
+	struct kvm *kvm = vcpu->kvm;
+	unsigned long *hpte, r;
+	int i, n = 1;
+
+	if (pte_index >= (HPT_NPTEG << 3))
+		return H_PARAMETER;
+	if (flags & H_READ_4) {
+		pte_index &= ~3;
+		n = 4;
+	}
+	for (i = 0; i < n; ++i, ++pte_index) {
+		hpte = (unsigned long *)(kvm->arch.hpt_virt + (pte_index << 4));
+		r = hpte[1];
+		if ((flags & H_R_XLATE) && (hpte[0] & HPTE_V_VALID))
+			r = reverse_xlate(kvm, r & HPTE_R_RPN) |
+				(r & ~HPTE_R_RPN);
+		vcpu->arch.gpr[4 + i * 2] = hpte[0];
+		vcpu->arch.gpr[5 + i * 2] = r;
+	}
+	return H_SUCCESS;
+}
+
 int kvmppc_mmu_hv_init(void)
 {
 	if (!cpu_has_feature(CPU_FTR_HVMODE_206))
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 0d812c5..d565a9f 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -123,6 +123,158 @@ void kvmppc_dump_regs(struct kvm_vcpu *vcpu)
 	       vcpu->arch.last_inst);
 }
 
+struct kvm_vcpu *kvmppc_find_vcpu(struct kvm *kvm, int id)
+{
+	int r;
+	struct kvm_vcpu *v, *ret = NULL;
+
+	mutex_lock(&kvm->lock);
+	kvm_for_each_vcpu(r, v, kvm) {
+		if (v->vcpu_id == id) {
+			ret = v;
+			break;
+		}
+	}
+	mutex_unlock(&kvm->lock);
+	return ret;
+}
+
+static void init_vpa(struct kvm_vcpu *vcpu, struct lppaca *vpa)
+{
+	vpa->shared_proc = 1;
+	vpa->yield_count = 1;
+}
+
+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;
+	void *va;
+	struct kvm_vcpu *tvcpu;
+
+	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)
+			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)
+			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);
+		else
+			len = *(unsigned int *)(va + 4);
+		if (pg_offset + len > kvm->arch.ram_psize)
+			return H_PARAMETER;
+		switch (flags) {
+		case 1:		/* register VPA */
+			if (len < 640)
+				return H_PARAMETER;
+			tvcpu->arch.vpa = va;
+			init_vpa(vcpu, va);
+			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;
+			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;
+			break;
+		}
+	} else {
+		switch (flags) {
+		case 5:		/* unregister VPA */
+			if (tvcpu->arch.slb_shadow || tvcpu->arch.dtl)
+				return H_RESOURCE;
+			tvcpu->arch.vpa = NULL;
+			break;
+		case 6:		/* unregister DTL */
+			tvcpu->arch.dtl = NULL;
+			break;
+		case 7:		/* unregister SLB shadow buffer */
+			tvcpu->arch.slb_shadow = NULL;
+			break;
+		}
+	}
+	return H_SUCCESS;
+}
+
+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;
+
+	switch (req) {
+	case H_CEDE:
+		vcpu->arch.shregs.msr |= MSR_EE;
+		vcpu->arch.ceded = 1;
+		smp_mb();
+		if (!vcpu->arch.prodded)
+			kvmppc_vcpu_block(vcpu);
+		else
+			vcpu->arch.prodded = 0;
+		smp_mb();
+		vcpu->arch.ceded = 0;
+		break;
+	case H_PROD:
+		target = kvmppc_get_gpr(vcpu, 4);
+		tvcpu = kvmppc_find_vcpu(vcpu->kvm, target);
+		if (!tvcpu) {
+			ret = H_PARAMETER;
+			break;
+		}
+		tvcpu->arch.prodded = 1;
+		smp_mb();
+		if (vcpu->arch.ceded) {
+			if (waitqueue_active(&vcpu->wq)) {
+				wake_up_interruptible(&vcpu->wq);
+				vcpu->stat.halt_wakeup++;
+			}
+		}
+		break;
+	case H_CONFER:
+		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;
+	default:
+		return RESUME_HOST;
+	}
+	kvmppc_set_gpr(vcpu, 3, ret);
+	vcpu->arch.hcall_needed = 0;
+	return RESUME_GUEST;
+}
+
 static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			      struct task_struct *tsk)
 {
@@ -324,7 +476,7 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 
 extern int __kvmppc_vcore_entry(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu);
 
-int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu)
+static int kvmppc_run_vcpu(struct kvm_run *run, struct kvm_vcpu *vcpu)
 {
 	u64 now;
 
@@ -355,6 +507,22 @@ int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	return kvmppc_handle_exit(run, vcpu, current);
 }
 
+int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu)
+{
+	int r;
+
+	do {
+		r = kvmppc_run_vcpu(run, 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);
+		}
+	} while (r == RESUME_GUEST);
+	return r;
+}
+
 int kvmppc_core_prepare_memory_region(struct kvm *kvm,
 				struct kvm_userspace_memory_region *mem)
 {
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index f0dc0ff..e0643b3 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -196,6 +196,14 @@ kvmppc_handler_trampoline_enter:
 	/* Save R1 in the PACA */
 	std	r1, HSTATE_HOST_R1(r13)
 
+	/* Increment yield count if they have a VPA */
+	ld	r3, VCPU_VPA(r4)
+	cmpdi	r3, 0
+	beq	25f
+	lwz	r5, LPPACA_YIELDCOUNT(r3)
+	addi	r5, r5, 1
+	stw	r5, LPPACA_YIELDCOUNT(r3)
+25:
 	/* Load up DAR and DSISR */
 	ld	r5, VCPU_DAR(r4)
 	lwz	r6, VCPU_DSISR(r4)
@@ -433,6 +441,10 @@ kvmppc_interrupt:
 	cmpwi	r3,0
 	bge	ignore_hdec
 2:
+	/* See if this is something we can handle in real mode */
+	cmpwi	r12,BOOK3S_INTERRUPT_SYSCALL
+	beq	hcall_try_real_mode
+hcall_real_cont:
 
 	/* Check for mediated interrupts (could be done earlier really ...) */
 	cmpwi	r12,BOOK3S_INTERRUPT_EXTERNAL
@@ -611,13 +623,28 @@ hdec_soon:
 	std	r5, VCPU_SPRG2(r9)
 	std	r6, VCPU_SPRG3(r9)
 
-	/* Save PMU registers */
+	/* Increment yield count if they have a VPA */
+	ld	r8, VCPU_VPA(r9)	/* do they have a VPA? */
+	cmpdi	r8, 0
+	beq	25f
+	lwz	r3, LPPACA_YIELDCOUNT(r8)
+	addi	r3, r3, 1
+	stw	r3, LPPACA_YIELDCOUNT(r8)
+25:
+	/* Save PMU registers if requested */
+	/* r8 and cr0.eq are live here */
 	li	r3, 1
 	sldi	r3, r3, 31		/* MMCR0_FC (freeze counters) bit */
 	mfspr	r4, SPRN_MMCR0		/* save MMCR0 */
 	mtspr	SPRN_MMCR0, r3		/* freeze all counters, disable ints */
 	isync
-	mfspr	r5, SPRN_MMCR1
+	beq	21f			/* if no VPA, save PMU stuff anyway */
+	lbz	r7, LPPACA_PMCINUSE(r8)
+	cmpwi	r7, 0			/* did they ask for PMU stuff to be saved? */
+	bne	21f
+	std	r3, VCPU_MMCR(r9)	/* if not, set saved MMCR0 to FC */
+	b	22f
+21:	mfspr	r5, SPRN_MMCR1
 	mfspr	r6, SPRN_MMCRA
 	std	r4, VCPU_MMCR(r9)
 	std	r5, VCPU_MMCR + 8(r9)
@@ -654,6 +681,125 @@ kvmppc_handler_trampoline_exit_end:
 	mfspr	r7,SPRN_HDSISR
 	b	7b
 
+/*
+ * Try to handle an hcall in real mode.
+ * Returns to the guest if we handle it, or continues on up to
+ * the kernel if we can't (i.e. if we don't have a handler for
+ * it, or if the handler returns H_TOO_HARD).
+ */
+	.globl	hcall_try_real_mode
+hcall_try_real_mode:
+	ld	r3,VCPU_GPR(r3)(r9)
+	andi.	r0,r11,MSR_PR
+	bne	hcall_real_cont
+	clrrdi	r3,r3,2
+	cmpldi	r3,hcall_real_table_end - hcall_real_table
+	bge	hcall_real_cont
+	LOAD_REG_ADDR(r4, hcall_real_table)
+	lwzx	r3,r3,r4
+	cmpwi	r3,0
+	beq	hcall_real_cont
+	add	r3,r3,r4
+	mtctr	r3
+	mr	r3,r9		/* get vcpu pointer */
+	ld	r4,VCPU_GPR(r4)(r9)
+	bctrl
+	cmpdi	r3,H_TOO_HARD
+	beq	hcall_real_fallback
+	ld	r4,HSTATE_KVM_VCPU(r13)
+	std	r3,VCPU_GPR(r3)(r4)
+	ld	r10,VCPU_PC(r4)
+	ld	r11,VCPU_MSR(r4)
+	b	fast_guest_return
+
+	/* We've attempted a real mode hcall, but it's punted it back
+	 * to userspace.  We need to restore some clobbered volatiles
+	 * before resuming the pass-it-to-qemu path */
+hcall_real_fallback:
+	li	r12,BOOK3S_INTERRUPT_SYSCALL
+	ld	r9, HSTATE_KVM_VCPU(r13)
+	ld	r11, VCPU_MSR(r9)
+
+	b	hcall_real_cont
+
+	.globl	hcall_real_table
+hcall_real_table:
+	.long	0		/* 0 - unused */
+	.long	.kvmppc_h_remove - hcall_real_table
+	.long	.kvmppc_h_enter - hcall_real_table
+	.long	.kvmppc_h_read - hcall_real_table
+	.long	0		/* 0x10 - H_CLEAR_MOD */
+	.long	0		/* 0x14 - H_CLEAR_REF */
+	.long	.kvmppc_h_protect - hcall_real_table
+	.long	0		/* 0x1c - H_GET_TCE */
+	.long	0		/* 0x20 - H_SET_TCE */
+	.long	0		/* 0x24 - H_SET_SPRG0 */
+	.long	.kvmppc_h_set_dabr - hcall_real_table
+	.long	0		/* 0x2c */
+	.long	0		/* 0x30 */
+	.long	0		/* 0x34 */
+	.long	0		/* 0x38 */
+	.long	0		/* 0x3c */
+	.long	0		/* 0x40 */
+	.long	0		/* 0x44 */
+	.long	0		/* 0x48 */
+	.long	0		/* 0x4c */
+	.long	0		/* 0x50 */
+	.long	0		/* 0x54 */
+	.long	0		/* 0x58 */
+	.long	0		/* 0x5c */
+	.long	0		/* 0x60 */
+	.long	0		/* 0x64 */
+	.long	0		/* 0x68 */
+	.long	0		/* 0x6c */
+	.long	0		/* 0x70 */
+	.long	0		/* 0x74 */
+	.long	0		/* 0x78 */
+	.long	0		/* 0x7c */
+	.long	0		/* 0x80 */
+	.long	0		/* 0x84 */
+	.long	0		/* 0x88 */
+	.long	0		/* 0x8c */
+	.long	0		/* 0x90 */
+	.long	0		/* 0x94 */
+	.long	0		/* 0x98 */
+	.long	0		/* 0x9c */
+	.long	0		/* 0xa0 */
+	.long	0		/* 0xa4 */
+	.long	0		/* 0xa8 */
+	.long	0		/* 0xac */
+	.long	0		/* 0xb0 */
+	.long	0		/* 0xb4 */
+	.long	0		/* 0xb8 */
+	.long	0		/* 0xbc */
+	.long	0		/* 0xc0 */
+	.long	0		/* 0xc4 */
+	.long	0		/* 0xc8 */
+	.long	0		/* 0xcc */
+	.long	0		/* 0xd0 */
+	.long	0		/* 0xd4 */
+	.long	0		/* 0xd8 */
+	.long	0		/* 0xdc */
+	.long	0		/* 0xe0 */
+	.long	0		/* 0xe4 */
+	.long	0		/* 0xe8 */
+	.long	0		/* 0xec */
+	.long	0		/* 0xf0 */
+	.long	0		/* 0xf4 */
+	.long	0		/* 0xf8 */
+	.long	0		/* 0xfc */
+	.long	0		/* 0x100 */
+	.long	0		/* 0x104 */
+	.long	0		/* 0x108 */
+	.long	0		/* 0x10c */
+	.long	0		/* 0x110 */
+	.long	0		/* 0x114 */
+	.long	0		/* 0x118 */
+	.long	0		/* 0x11c */
+	.long	0		/* 0x120 */
+	.long	.kvmppc_h_bulk_remove - hcall_real_table
+hcall_real_table_end:
+
 ignore_hdec:
 	mr	r4,r9
 	b	fast_guest_return
@@ -665,3 +811,9 @@ bounce_ext_interrupt:
 	li	r10,BOOK3S_INTERRUPT_EXTERNAL
 	LOAD_REG_IMMEDIATE(r11,MSR_SF | MSR_ME);
 	b	fast_guest_return
+
+_GLOBAL(kvmppc_h_set_dabr)
+	std	r4,VCPU_DABR(r3)
+	mtspr	SPRN_DABR,r4
+	li	r3,0
+	blr
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index a5635c9..985ee72 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -42,7 +42,7 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
 	return !(v->arch.shared->msr & MSR_WE) ||
 	       !!(v->arch.pending_exceptions);
 #else
-	return 1;
+	return !(v->arch.ceded) || !!(v->arch.pending_exceptions);
 #endif
 }
 
-- 
1.7.5.3

[PATCH v2 11/12] kvm/powerpc: Accelerate H_PUT_TCE by implementing it in real mode

[Paul Mackerras]

From: David Gibson <dwg@au1.ibm.com>

This improves I/O performance for guests using the PAPR
paravirtualization interface by making the H_PUT_TCE hcall faster, by
implementing it in real mode.  H_PUT_TCE is used for updating virtual
IOMMU tables, and is used both for virtual I/O and for real I/O in the
PAPR interface.

Since this moves the IOMMU tables into the kernel, we define a new
KVM_CREATE_SPAPR_TCE ioctl to allow qemu to create the tables.  The
ioctl returns a file descriptor which can be used to mmap the newly
created table.  The qemu driver models use them in the same way as
userspace managed tables, but they can be updated directly by the
guest with a real-mode H_PUT_TCE implementation, reducing the number
of host/guest context switches during guest IO.

There are certain circumstances where it is useful for userland qemu
to write to the TCE table even if the kernel H_PUT_TCE path is used
most of the time.  Specifically, allowing this will avoid awkwardness
when we need to reset the table.  More importantly, we will in the
future need to write the table in order to restore its state after a
checkpoint resume or migration.

Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
---
 Documentation/virtual/kvm/api.txt        |   35 +++++++++
 arch/powerpc/include/asm/kvm.h           |    9 +++
 arch/powerpc/include/asm/kvm_book3s_64.h |    2 +
 arch/powerpc/include/asm/kvm_host.h      |    9 +++
 arch/powerpc/include/asm/kvm_ppc.h       |    2 +
 arch/powerpc/kvm/Makefile                |    3 +-
 arch/powerpc/kvm/book3s_64_vio_hv.c      |   73 +++++++++++++++++++
 arch/powerpc/kvm/book3s_hv.c             |  116 +++++++++++++++++++++++++++++-
 arch/powerpc/kvm/book3s_hv_rmhandlers.S  |    2 +-
 arch/powerpc/kvm/powerpc.c               |   18 +++++
 include/linux/kvm.h                      |    3 +
 11 files changed, 269 insertions(+), 3 deletions(-)
 create mode 100644 arch/powerpc/kvm/book3s_64_vio_hv.c

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index f61e986..acf0fcd 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1291,6 +1291,41 @@ Returns the tsc frequency of the guest. The unit of the return value is
 KHz. If the host has unstable tsc this ioctl returns -EIO instead as an
 error.
 
+4.56 KVM_CREATE_SPAPR_TCE
+
+Capability: KVM_CAP_SPAPR_TCE
+Architectures: powerpc
+Type: vm ioctl
+Parameters: struct kvm_create_spapr_tce (in)
+Returns: file descriptor for manipulating the created TCE table
+
+This creates a virtual TCE (translation control entry) table, which
+is an IOMMU for PAPR-style virtual I/O.  It is used to translate
+logical addresses used in virtual I/O into guest physical addresses,
+and provides a scatter/gather capability for PAPR virtual I/O.
+
+/* for KVM_CAP_SPAPR_TCE */
+struct kvm_create_spapr_tce {
+	__u64 liobn;
+	__u32 window_size;
+};
+
+The liobn field gives the logical IO bus number for which to create a
+TCE table.  The window_size field specifies the size of the DMA window
+which this TCE table will translate - the table will contain one 64
+bit TCE entry for every 4kiB of the DMA window.
+
+When the guest issues an H_PUT_TCE hcall on a liobn for which a TCE
+table has been created using this ioctl(), the kernel will handle it
+in real mode, updating the TCE table.  H_PUT_TCE calls for other
+liobns will cause a vm exit and must be handled by userspace.
+
+The return value is a file descriptor which can be passed to mmap(2)
+to map the created TCE table into userspace.  This lets userspace read
+the entries written by kernel-handled H_PUT_TCE calls, and also lets
+userspace update the TCE table directly which is useful in some
+circumstances.
+
 5. The kvm_run structure
 
 Application code obtains a pointer to the kvm_run structure by
diff --git a/arch/powerpc/include/asm/kvm.h b/arch/powerpc/include/asm/kvm.h
index d2ca5ed..c3ec990 100644
--- a/arch/powerpc/include/asm/kvm.h
+++ b/arch/powerpc/include/asm/kvm.h
@@ -22,6 +22,9 @@
 
 #include <linux/types.h>
 
+/* Select powerpc specific features in <linux/kvm.h> */
+#define __KVM_HAVE_SPAPR_TCE
+
 struct kvm_regs {
 	__u64 pc;
 	__u64 cr;
@@ -272,4 +275,10 @@ struct kvm_guest_debug_arch {
 #define KVM_INTERRUPT_UNSET	-2U
 #define KVM_INTERRUPT_SET_LEVEL	-3U
 
+/* for KVM_CAP_SPAPR_TCE */
+struct kvm_create_spapr_tce {
+	__u64 liobn;
+	__u32 window_size;
+};
+
 #endif /* __LINUX_KVM_POWERPC_H */
diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 5f73388..e43fe42 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -27,4 +27,6 @@ static inline struct kvmppc_book3s_shadow_vcpu *to_svcpu(struct kvm_vcpu *vcpu)
 }
 #endif
 
+#define SPAPR_TCE_SHIFT		12
+
 #endif /* __ASM_KVM_BOOK3S_64_H__ */
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 359db37..2225718 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -144,6 +144,14 @@ struct kvmppc_pginfo {
 	atomic_t refcnt;
 };
 
+struct kvmppc_spapr_tce_table {
+	struct list_head list;
+	struct kvm *kvm;
+	u64 liobn;
+	u32 window_size;
+	struct page *pages[0];
+};
+
 struct kvm_arch {
 #ifdef CONFIG_KVM_BOOK3S_64_HV
 	unsigned long hpt_virt;
@@ -157,6 +165,7 @@ struct kvm_arch {
 	unsigned long sdr1;
 	unsigned long host_sdr1;
 	int tlbie_lock;
+	struct list_head spapr_tce_tables;
 	unsigned short last_vcpu[NR_CPUS];
 #endif /* CONFIG_KVM_BOOK3S_64_HV */
 };
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index d809e58..7655703 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -118,6 +118,8 @@ extern long kvmppc_prepare_vrma(struct kvm *kvm,
 extern void kvmppc_map_vrma(struct kvm *kvm,
 			    struct kvm_userspace_memory_region *mem);
 extern int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu);
+extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
+				struct kvm_create_spapr_tce *args);
 extern int kvmppc_core_init_vm(struct kvm *kvm);
 extern void kvmppc_core_destroy_vm(struct kvm *kvm);
 extern int kvmppc_core_prepare_memory_region(struct kvm *kvm,
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index ca7ed27..ef37969 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -59,7 +59,8 @@ kvm-book3s_64_hv-objs := \
 	book3s.o \
 	book3s_hv.o \
 	book3s_hv_interrupts.o \
-	book3s_64_mmu_hv.o
+	book3s_64_mmu_hv.o \
+	book3s_64_vio_hv.o
 kvm-objs-$(CONFIG_KVM_BOOK3S_64_HV) := $(kvm-book3s_64_hv-objs)
 
 kvm-book3s_32-objs := \
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
new file mode 100644
index 0000000..ea0f8c5
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -0,0 +1,73 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright 2010 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
+ * Copyright 2011 David Gibson, IBM Corporation <dwg@au1.ibm.com>
+ */
+
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <linux/highmem.h>
+#include <linux/gfp.h>
+#include <linux/slab.h>
+#include <linux/hugetlb.h>
+#include <linux/list.h>
+
+#include <asm/tlbflush.h>
+#include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s.h>
+#include <asm/mmu-hash64.h>
+#include <asm/hvcall.h>
+#include <asm/synch.h>
+#include <asm/ppc-opcode.h>
+#include <asm/kvm_host.h>
+#include <asm/udbg.h>
+
+#define TCES_PER_PAGE	(PAGE_SIZE / sizeof(u64))
+
+long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
+		      unsigned long ioba, unsigned long tce)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvmppc_spapr_tce_table *stt;
+
+	/* udbg_printf("H_PUT_TCE(): liobn=0x%lx ioba=0x%lx, tce=0x%lx\n", */
+	/* 	    liobn, ioba, tce); */
+
+	list_for_each_entry(stt, &kvm->arch.spapr_tce_tables, list) {
+		if (stt->liobn == liobn) {
+			unsigned long idx = ioba >> SPAPR_TCE_SHIFT;
+			struct page *page;
+			u64 *tbl;
+
+			/* udbg_printf("H_PUT_TCE: liobn 0x%lx => stt=%p  window_size=0x%x\n", */
+			/* 	    liobn, stt, stt->window_size); */
+			if (ioba >= stt->window_size)
+				return H_PARAMETER;
+
+			page = stt->pages[idx / TCES_PER_PAGE];
+			tbl = (u64 *)page_address(page);
+
+			/* FIXME: Need to validate the TCE itself */
+			/* udbg_printf("tce @ %p\n", &tbl[idx % TCES_PER_PAGE]); */
+			tbl[idx % TCES_PER_PAGE] = tce;
+			return H_SUCCESS;
+		}
+	}
+
+	/* Didn't find the liobn, punt it to userspace */
+	return H_TOO_HARD;
+}
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index d565a9f..aee457c 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -523,6 +523,116 @@ int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	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,
+};
+
+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;
+}
+
+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;
+}
+
 int kvmppc_core_prepare_memory_region(struct kvm *kvm,
 				struct kvm_userspace_memory_region *mem)
 {
@@ -544,13 +654,17 @@ int kvmppc_core_init_vm(struct kvm *kvm)
 
 	/* Allocate hashed page table */
 	r = kvmppc_alloc_hpt(kvm);
+	if (r)
+		return r;
 
-	return r;
+	INIT_LIST_HEAD(&kvm->arch.spapr_tce_tables);
+	return 0;
 }
 
 void kvmppc_core_destroy_vm(struct kvm *kvm)
 {
 	kvmppc_free_hpt(kvm);
+	WARN_ON(!list_empty(&kvm->arch.spapr_tce_tables));
 }
 
 /* These are stubs for now */
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index e0643b3..f63a884 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -732,7 +732,7 @@ hcall_real_table:
 	.long	0		/* 0x14 - H_CLEAR_REF */
 	.long	.kvmppc_h_protect - hcall_real_table
 	.long	0		/* 0x1c - H_GET_TCE */
-	.long	0		/* 0x20 - H_SET_TCE */
+	.long	.kvmppc_h_put_tce - hcall_real_table
 	.long	0		/* 0x24 - H_SET_SPRG0 */
 	.long	.kvmppc_h_set_dabr - hcall_real_table
 	.long	0		/* 0x2c */
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 985ee72..7343051 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -202,6 +202,11 @@ int kvm_dev_ioctl_check_extension(long ext)
 		r = KVM_COALESCED_MMIO_PAGE_OFFSET;
 		break;
 #endif
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+	case KVM_CAP_SPAPR_TCE:
+		r = 1;
+		break;
+#endif
 	default:
 		r = 0;
 		break;
@@ -652,6 +657,19 @@ long kvm_arch_vm_ioctl(struct file *filp,
 
 		break;
 	}
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+	case KVM_CREATE_SPAPR_TCE: {
+		struct kvm_create_spapr_tce create_tce;
+		struct kvm *kvm = filp->private_data;
+
+		r = -EFAULT;
+		if (copy_from_user(&create_tce, argp, sizeof(create_tce)))
+			goto out;
+		r = kvm_vm_ioctl_create_spapr_tce(kvm, &create_tce);
+		goto out;
+	}
+#endif /* CONFIG_KVM_BOOK3S_64_HV */
+
 	default:
 		r = -ENOTTY;
 	}
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index bea0116..0836366 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -550,6 +550,7 @@ struct kvm_ppc_pvinfo {
 #define KVM_CAP_TSC_CONTROL 60
 #define KVM_CAP_GET_TSC_KHZ 61
 #define KVM_CAP_PPC_BOOKE_SREGS 62
+#define KVM_CAP_SPAPR_TCE 63
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -752,6 +753,8 @@ struct kvm_clock_data {
 /* Available with KVM_CAP_XCRS */
 #define KVM_GET_XCRS		  _IOR(KVMIO,  0xa6, struct kvm_xcrs)
 #define KVM_SET_XCRS		  _IOW(KVMIO,  0xa7, struct kvm_xcrs)
+/* Available with KVM_CAP_SPAPR_TCE */
+#define KVM_CREATE_SPAPR_TCE	  _IOW(KVMIO,  0xa8, struct kvm_create_spapr_tce)
 
 #define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)
 
-- 
1.7.5.3

[PATCH v2 12/12] kvm/powerpc: Allow book3s_hv guests to use SMT processor modes

[Paul Mackerras]

This lifts the restriction that book3s_hv guests can only run one
hardware thread per core, and allows them to use up to 4 threads
per core on POWER7.  The host still has to run single-threaded.

This capability is advertised to qemu through a new KVM_CAP_PPC_SMT
capability.  The return value of the ioctl querying this capability
is the number of vcpus per virtual CPU core (vcore), currently 4.

To use this, the host kernel should be booted with all threads
active, and then all the secondary threads should be offlined.
This will put the secondary threads into nap mode.  KVM will then
wake them from nap mode and use them for running guest code (while
they are still offline).  To wake the secondary threads, we send
them an IPI using a new xics_wake_cpu() function, implemented in
arch/powerpc/sysdev/xics/icp-native.c.  In other words, at this stage
we assume that the platform has a XICS interrupt controller and
we are using icp-native.c to drive it.  Since the woken thread will
need to acknowledge and clear the IPI, we also export the base
physical address of the XICS registers using kvmppc_set_xics_phys()
for use in the low-level KVM book3s code.

When a vcpu is created, it is assigned to a virtual CPU core.
The vcore number is obtained by dividing the vcpu number by 4,
since we assume at most 4 threads per core.  Thus, if qemu wishes
to run the guest in single-threaded mode, it should make all vcpu
numbers be multiples of 4.

We distinguish three states of a vcpu: runnable (i.e., ready to execute
the guest), blocked (that is, idle), and busy in host.  We currently
implement a policy that the vcore can run only when all its threads
are runnable or blocked.  This way, if a vcpu needs to execute elsewhere
in the kernel or in qemu, it can do so without being starved of CPU
by the other vcpus.

When a vcore starts to run, it executes in the context of one of the
vcpu threads.  The other vcpu threads all go to sleep and stay asleep
until something happens requiring the vcpu thread to return to qemu,
or to wake up to run the vcore (this can happen when another vcpu
thread goes from busy in host state to blocked).

It can happen that a vcpu goes from blocked to runnable state (e.g.
because of an interrupt), and the vcore it belongs to is already
running.  In that case it can start to run immediately as long as
the none of the vcpus in the vcore have started to exit the guest.
We send the next free thread in the vcore an IPI to get it to start
to execute the guest.  It synchronizes with the other threads via
the vcore->entry_exit_count field to make sure that it doesn't go
into the guest if the other vcpus are exiting by the time that it
is ready to actually enter the guest.

Note that there is no fixed relationship between the hardware thread
number and the vcpu number.  Hardware threads are assigned to vcpus
as they become runnable, so we will always use the lower-numbered
hardware threads in preference to higher-numbered threads if not all
the vcpus in the vcore are runnable, regardless of which vcpus are
runnable.

Signed-off-by: Paul Mackerras <paulus@samba.org>
---
 Documentation/virtual/kvm/api.txt         |   13 ++
 arch/powerpc/include/asm/kvm.h            |    1 +
 arch/powerpc/include/asm/kvm_book3s_asm.h |    2 +
 arch/powerpc/include/asm/kvm_host.h       |   45 +++++-
 arch/powerpc/include/asm/kvm_ppc.h        |   13 ++
 arch/powerpc/kernel/asm-offsets.c         |    6 +
 arch/powerpc/kernel/exceptions-64s.S      |   31 +++-
 arch/powerpc/kernel/idle_power7.S         |    2 -
 arch/powerpc/kvm/Kconfig                  |    2 +-
 arch/powerpc/kvm/book3s_hv.c              |  265 +++++++++++++++++++++++++++--
 arch/powerpc/kvm/book3s_hv_rmhandlers.S   |  168 ++++++++++++++++++-
 arch/powerpc/kvm/powerpc.c                |    3 +
 arch/powerpc/sysdev/xics/icp-native.c     |    7 +
 include/linux/kvm.h                       |    1 +
 14 files changed, 529 insertions(+), 30 deletions(-)

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index acf0fcd..e25f3da 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -180,6 +180,19 @@ KVM_CHECK_EXTENSION ioctl() to determine the value for max_vcpus at run-time.
 If the KVM_CAP_NR_VCPUS does not exist, you should assume that max_vcpus is 4
 cpus max.
 
+On powerpc using book3s_hv mode, the vcpus are mapped onto virtual
+threads in one or more virtual CPU cores.  (This is because the
+hardware requires all the hardware threads in a CPU core to be in the
+same partition.)  The KVM_CAP_PPC_SMT capability indicates the number
+of vcpus per virtual core (vcore).  The vcore id is obtained by
+dividing the vcpu id by the number of vcpus per vcore.  The vcpus in a
+given vcore will always be in the same physical core as each other
+(though that might be a different physical core from time to time).
+Userspace can control the threading (SMT) mode of the guest by its
+allocation of vcpu ids.  For example, if userspace wants
+single-threaded guest vcpus, it should make all vcpu ids be a multiple
+of the number of vcpus per vcore.
+
 4.8 KVM_GET_DIRTY_LOG (vm ioctl)
 
 Capability: basic
diff --git a/arch/powerpc/include/asm/kvm.h b/arch/powerpc/include/asm/kvm.h
index c3ec990..471bb3d 100644
--- a/arch/powerpc/include/asm/kvm.h
+++ b/arch/powerpc/include/asm/kvm.h
@@ -24,6 +24,7 @@
 
 /* Select powerpc specific features in <linux/kvm.h> */
 #define __KVM_HAVE_SPAPR_TCE
+#define __KVM_HAVE_PPC_SMT
 
 struct kvm_regs {
 	__u64 pc;
diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h
index 550cf07..3ac82f1 100644
--- a/arch/powerpc/include/asm/kvm_book3s_asm.h
+++ b/arch/powerpc/include/asm/kvm_book3s_asm.h
@@ -77,6 +77,8 @@ struct kvmppc_host_state {
 
 #ifdef CONFIG_KVM_BOOK3S_64_HV
 	struct kvm_vcpu *kvm_vcpu;
+	struct kvmppc_vcore *kvm_vcore;
+	unsigned long xics_phys;
 	u64 dabr;
 	u64 host_mmcr[3];
 	u32 host_pmc[6];
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 2225718..1608b53 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -25,10 +25,15 @@
 #include <linux/interrupt.h>
 #include <linux/types.h>
 #include <linux/kvm_types.h>
+#include <linux/threads.h>
+#include <linux/spinlock.h>
 #include <linux/kvm_para.h>
 #include <asm/kvm_asm.h>
+#include <asm/processor.h>
 
-#define KVM_MAX_VCPUS 1
+#define KVM_MAX_VCPUS		NR_CPUS
+#define KVM_THREADS_PER_CORE	4
+#define KVM_MAX_VCORES		(KVM_MAX_VCPUS / KVM_THREADS_PER_CORE)
 #define KVM_MEMORY_SLOTS 32
 /* memory slots that does not exposed to userspace */
 #define KVM_PRIVATE_MEM_SLOTS 4
@@ -167,9 +172,36 @@ struct kvm_arch {
 	int tlbie_lock;
 	struct list_head spapr_tce_tables;
 	unsigned short last_vcpu[NR_CPUS];
+	struct kvmppc_vcore *vcores[KVM_MAX_VCORES];
 #endif /* CONFIG_KVM_BOOK3S_64_HV */
 };
 
+/*
+ * Struct for a virtual core.
+ * Note: entry_exit_count combines an entry count in the bottom 8 bits
+ * and an exit count in the next 8 bits.  This is so that we can
+ * atomically increment the entry count iff the exit count is 0
+ * without taking the lock.
+ */
+struct kvmppc_vcore {
+	int n_runnable;
+	int n_blocked;
+	int num_threads;
+	int entry_exit_count;
+	int n_woken;
+	int nap_count;
+	u16 pcpu;
+	u8 vcore_running;
+	u8 in_guest;
+	struct kvm_vcpu *runnable_threads[KVM_THREADS_PER_CORE];
+	struct task_struct *run_task[KVM_THREADS_PER_CORE];
+	struct kvm_run *kvm_run[KVM_THREADS_PER_CORE];
+	spinlock_t lock;
+};
+
+#define VCORE_ENTRY_COUNT(vc)	((vc)->entry_exit_count & 0xff)
+#define VCORE_EXIT_COUNT(vc)	((vc)->entry_exit_count >> 8)
+
 struct kvmppc_pte {
 	ulong eaddr;
 	u64 vpage;
@@ -358,7 +390,14 @@ struct kvm_vcpu_arch {
 	struct slb_shadow *slb_shadow;
 	struct dtl *dtl;
 	struct dtl *dtl_end;
+
+	struct kvmppc_vcore *vcore;
+	int ret;
 	int trap;
+	int state;
+	int ptid;
+	wait_queue_head_t cpu_run;
+
 	struct kvm_vcpu_arch_shared *shared;
 	unsigned long magic_page_pa; /* phys addr to map the magic page to */
 	unsigned long magic_page_ea; /* effect. addr to map the magic page to */
@@ -368,4 +407,8 @@ struct kvm_vcpu_arch {
 #endif
 };
 
+#define KVMPPC_VCPU_BUSY_IN_HOST	0
+#define KVMPPC_VCPU_BLOCKED		1
+#define KVMPPC_VCPU_RUNNABLE		2
+
 #endif /* __POWERPC_KVM_HOST_H__ */
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 7655703..cb685c5 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -33,6 +33,9 @@
 #else
 #include <asm/kvm_booke.h>
 #endif
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+#include <asm/paca.h>
+#endif
 
 enum emulation_result {
 	EMULATE_DONE,         /* no further processing */
@@ -168,4 +171,14 @@ int kvmppc_set_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
 
 void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid);
 
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr)
+{
+	paca[cpu].kvm_hstate.xics_phys = addr;
+}
+#else
+static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr)
+{}
+#endif
+
 #endif /* __POWERPC_KVM_PPC_H__ */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index d29f19a..a1242f3 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -470,6 +470,10 @@ int main(void)
 	DEFINE(VCPU_FAULT_DAR, offsetof(struct kvm_vcpu, arch.fault_dar));
 	DEFINE(VCPU_LAST_INST, offsetof(struct kvm_vcpu, arch.last_inst));
 	DEFINE(VCPU_TRAP, offsetof(struct kvm_vcpu, arch.trap));
+	DEFINE(VCPU_PTID, offsetof(struct kvm_vcpu, arch.ptid));
+	DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_count));
+	DEFINE(VCORE_NAP_COUNT, offsetof(struct kvmppc_vcore, nap_count));
+	DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest));
 	DEFINE(VCPU_SVCPU, offsetof(struct kvmppc_vcpu_book3s, shadow_vcpu) -
 			   offsetof(struct kvmppc_vcpu_book3s, vcpu));
 	DEFINE(VCPU_SLB_E, offsetof(struct kvmppc_slb, orige));
@@ -528,6 +532,8 @@ int main(void)
 
 #ifdef CONFIG_KVM_BOOK3S_64_HV
 	HSTATE_FIELD(HSTATE_KVM_VCPU, kvm_vcpu);
+	HSTATE_FIELD(HSTATE_KVM_VCORE, kvm_vcore);
+	HSTATE_FIELD(HSTATE_XICS_PHYS, xics_phys);
 	HSTATE_FIELD(HSTATE_MMCR, host_mmcr);
 	HSTATE_FIELD(HSTATE_PMC, host_pmc);
 	HSTATE_FIELD(HSTATE_PURR, host_purr);
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index b20d04c..7f07bcb 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -49,19 +49,32 @@ BEGIN_FTR_SECTION
 	 * state loss at this time.
 	 */
 	mfspr	r13,SPRN_SRR1
-	rlwinm	r13,r13,47-31,30,31
-	cmpwi	cr0,r13,1
-	bne	1f
-	b	.power7_wakeup_noloss
-1:	cmpwi	cr0,r13,2
-	bne	1f
-	b	.power7_wakeup_loss
+	rlwinm.	r13,r13,47-31,30,31
+	beq	9f
+
+	/* waking up from powersave (nap) state */
+	cmpwi	cr1,r13,2
 	/* Total loss of HV state is fatal, we could try to use the
 	 * PIR to locate a PACA, then use an emergency stack etc...
 	 * but for now, let's just stay stuck here
 	 */
-1:	cmpwi	cr0,r13,3
-	beq	.
+	bgt	cr1,.
+	GET_PACA(r13)
+
+#ifdef CONFIG_KVM_BOOK3S_64_HV
+	lbz	r0,PACAPROCSTART(r13)
+	cmpwi	r0,0x80
+	bne	1f
+	li	r0,0
+	stb	r0,PACAPROCSTART(r13)
+	b	kvm_start_guest
+1:
+#endif
+
+	beq	cr1,2f
+	b	.power7_wakeup_noloss
+2:	b	.power7_wakeup_loss
+9:
 END_FTR_SECTION_IFSET(CPU_FTR_HVMODE_206)
 #endif /* CONFIG_PPC_P7_NAP */
 	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, system_reset_common, EXC_STD,
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index f8f0bc7..3a70845 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -73,7 +73,6 @@ _GLOBAL(power7_idle)
 	b	.
 
 _GLOBAL(power7_wakeup_loss)
-	GET_PACA(r13)
 	ld	r1,PACAR1(r13)
 	REST_NVGPRS(r1)
 	REST_GPR(2, r1)
@@ -87,7 +86,6 @@ _GLOBAL(power7_wakeup_loss)
 	rfid
 
 _GLOBAL(power7_wakeup_noloss)
-	GET_PACA(r13)
 	ld	r1,PACAR1(r13)
 	ld	r4,_MSR(r1)
 	ld	r5,_NIP(r1)
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 3662ecc..738b365 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -58,7 +58,7 @@ config KVM_BOOK3S_64
 
 config KVM_BOOK3S_64_HV
 	bool "KVM support for POWER7 using hypervisor mode in host"
-	depends on EXPERIMENTAL && PPC_BOOK3S_64
+	depends on EXPERIMENTAL && PPC_BOOK3S_64 && (PPC_PSERIES || PPC_POWERNV)
 	select KVM
 	select KVM_BOOK3S_64
 	---help---
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index aee457c..cb5a20e 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -50,12 +50,16 @@
 void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	local_paca->kvm_hstate.kvm_vcpu = vcpu;
+	local_paca->kvm_hstate.kvm_vcore = vcpu->arch.vcore;
 }
 
 void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
 {
 }
 
+static void kvmppc_vcpu_blocked(struct kvm_vcpu *vcpu);
+static void kvmppc_vcpu_unblocked(struct kvm_vcpu *vcpu);
+
 void kvmppc_vcpu_block(struct kvm_vcpu *vcpu)
 {
 	u64 now;
@@ -73,11 +77,15 @@ void kvmppc_vcpu_block(struct kvm_vcpu *vcpu)
 			      HRTIMER_MODE_REL);
 	}
 
+	kvmppc_vcpu_blocked(vcpu);
+
 	kvm_vcpu_block(vcpu);
 	vcpu->stat.halt_wakeup++;
 
 	if (vcpu->arch.dec_expires != ~(u64)0)
 		hrtimer_try_to_cancel(&vcpu->arch.dec_timer);
+
+	kvmppc_vcpu_unblocked(vcpu);
 }
 
 void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
@@ -429,6 +437,8 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 {
 	struct kvm_vcpu *vcpu;
 	int err = -ENOMEM;
+	int core;
+	struct kvmppc_vcore *vcore;
 	unsigned long lpcr;
 
 	vcpu = kzalloc(sizeof(struct kvm_vcpu), GFP_KERNEL);
@@ -460,6 +470,37 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 
 	kvmppc_mmu_book3s_hv_init(vcpu);
 
+	/*
+	 * Some vcpus may start out in stopped state.  If we initialize
+	 * them to busy-in-host state they will stop other vcpus in the
+	 * vcore from running.  Instead we initialize them to blocked
+	 * state, effectively considering them to be stopped until we
+	 * see the first run ioctl for them.
+	 */
+	vcpu->arch.state = KVMPPC_VCPU_BLOCKED;
+
+	init_waitqueue_head(&vcpu->arch.cpu_run);
+	core = id / KVM_THREADS_PER_CORE;
+
+	mutex_lock(&kvm->lock);
+	vcore = kvm->arch.vcores[core];
+	if (!vcore) {
+		vcore = kzalloc(sizeof(struct kvmppc_vcore), GFP_KERNEL);
+		if (vcore)
+			spin_lock_init(&vcore->lock);
+		kvm->arch.vcores[core] = vcore;
+	}
+	mutex_unlock(&kvm->lock);
+
+	if (!vcore)
+		goto free_vcpu;
+
+	spin_lock(&vcore->lock);
+	++vcore->num_threads;
+	++vcore->n_blocked;
+	spin_unlock(&vcore->lock);
+	vcpu->arch.vcore = vcore;
+
 	return vcpu;
 
 free_vcpu:
@@ -474,37 +515,239 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 	kfree(vcpu);
 }
 
+static void kvmppc_vcpu_blocked(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+
+	spin_lock(&vc->lock);
+	vcpu->arch.state = KVMPPC_VCPU_BLOCKED;
+	++vc->n_blocked;
+	if (vc->n_runnable > 0 &&
+	    vc->n_runnable + vc->n_blocked == vc->num_threads)
+		wake_up(&vc->runnable_threads[0]->arch.cpu_run);
+	spin_unlock(&vc->lock);
+}
+
+static void kvmppc_vcpu_unblocked(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+
+	spin_lock(&vc->lock);
+	vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
+	--vc->n_blocked;
+	spin_unlock(&vc->lock);
+}
+
 extern int __kvmppc_vcore_entry(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu);
+extern void xics_wake_cpu(int cpu);
+
+static void kvmppc_remove_runnable(struct kvmppc_vcore *vc, int ptid)
+{
+	int i;
+	struct kvm_vcpu *vcpu;
+
+	vcpu = vc->runnable_threads[ptid];
+	if (vcpu->arch.state != KVMPPC_VCPU_RUNNABLE)
+		return;
+	vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
+	--vc->n_runnable;
+	for (i = ptid; i < vc->n_runnable; ++i) {
+		vcpu = vc->runnable_threads[i+1];
+		vc->runnable_threads[i] = vcpu;
+		vcpu->arch.ptid = i;
+		vc->run_task[i] = vc->run_task[i+1];
+		vc->kvm_run[i] = vc->kvm_run[i+1];
+	}
+}
+
+static void kvmppc_start_thread(struct kvm_vcpu *vcpu)
+{
+	int cpu;
+	struct paca_struct *tpaca;
+	struct kvmppc_vcore *vc = vcpu->arch.vcore;
+
+	cpu = vc->pcpu + vcpu->arch.ptid;
+	tpaca = &paca[cpu];
+	tpaca->kvm_hstate.kvm_vcpu = vcpu;
+	tpaca->kvm_hstate.kvm_vcore = vc;
+	smp_wmb();
+	if (vcpu->arch.ptid) {
+		tpaca->cpu_start = 0x80;
+		tpaca->kvm_hstate.in_guest = KVM_GUEST_MODE_GUEST;
+		wmb();
+		xics_wake_cpu(cpu);
+		++vc->n_woken;
+	}
+}
+
+static void kvmppc_wait_for_nap(struct kvmppc_vcore *vc)
+{
+	int i;
+
+	HMT_low();
+	i = 0;
+	while (vc->nap_count < vc->n_woken) {
+		if (++i >= 1000000) {
+			pr_err("kvmppc_wait_for_nap timeout %d %d\n",
+			       vc->nap_count, vc->n_woken);
+			break;
+		}
+		cpu_relax();
+	}
+	HMT_medium();
+}
 
-static int kvmppc_run_vcpu(struct kvm_run *run, struct kvm_vcpu *vcpu)
+static int kvmppc_run_core(struct kvmppc_vcore *vc)
 {
+	struct kvm_vcpu *vcpu;
+	long i, ret;
 	u64 now;
 
-	if (signal_pending(current)) {
-		run->exit_reason = KVM_EXIT_INTR;
-		return -EINTR;
+	/* don't start if any threads have a signal pending */
+	for (i = 0; i < vc->n_runnable; ++i) {
+		if (signal_pending(vc->run_task[i]))
+			return 0;
 	}
 
-	flush_fp_to_thread(current);
-	flush_altivec_to_thread(current);
-	flush_vsx_to_thread(current);
-	preempt_disable();
+	vc->n_woken = 0;
+	vc->nap_count = 0;
+	vc->entry_exit_count = 0;
+	vc->vcore_running = 1;
+	vc->in_guest = 0;
+	vc->pcpu = smp_processor_id();
+	for (i = 0; i < vc->n_runnable; ++i)
+		kvmppc_start_thread(vc->runnable_threads[i]);
+	vcpu = vc->runnable_threads[0];
 
-	kvm_guest_enter();
+	spin_unlock(&vc->lock);
 
+	kvm_guest_enter();
 	__kvmppc_vcore_entry(NULL, vcpu);
 
+	/* wait for secondary threads to finish writing their state to memory */
+	spin_lock(&vc->lock);
+	if (vc->nap_count < vc->n_woken)
+		kvmppc_wait_for_nap(vc);
+	/* prevent other vcpu threads from doing kvmppc_start_thread() now */
+	vc->vcore_running = 2;
+	spin_unlock(&vc->lock);
+
+	/* make sure updates to secondary vcpu structs are visible now */
+	smp_mb();
 	kvm_guest_exit();
 
 	preempt_enable();
 	kvm_resched(vcpu);
 
 	now = get_tb();
+	for (i = 0; i < vc->n_runnable; ++i) {
+		vcpu = vc->runnable_threads[i];
 	/* cancel pending dec exception if dec is positive */
-	if (now < vcpu->arch.dec_expires && kvmppc_core_pending_dec(vcpu))
+		if (now < vcpu->arch.dec_expires &&
+		    kvmppc_core_pending_dec(vcpu))
 		kvmppc_core_dequeue_dec(vcpu);
+		if (!vcpu->arch.trap) {
+			if (signal_pending(vc->run_task[i])) {
+				vc->kvm_run[i]->exit_reason = KVM_EXIT_INTR;
+				vcpu->arch.ret = -EINTR;
+			}
+			continue;		/* didn't get to run */
+		}
+		ret = kvmppc_handle_exit(vc->kvm_run[i], vcpu, vc->run_task[i]);
+		vcpu->arch.ret = ret;
+		vcpu->arch.trap = 0;
+	}
+
+	preempt_disable();
+	spin_lock(&vc->lock);
+
+	vc->vcore_running = 0;
+	for (i = 0; i < vc->n_runnable; ) {
+		vcpu = vc->runnable_threads[i];
+		if (vcpu->arch.ret != RESUME_GUEST) {
+			kvmppc_remove_runnable(vc, i);
+			wake_up(&vcpu->arch.cpu_run);
+		} else
+			++i;
+	}
+
+	return 1;
+}
+
+static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
+{
+	int ptid;
+	int wait_state;
+	struct kvmppc_vcore *vc;
+	DEFINE_WAIT(wait);
+
+	/* No need to go into the guest when all we do is going out */
+	if (signal_pending(current)) {
+		kvm_run->exit_reason = KVM_EXIT_INTR;
+		return -EINTR;
+	}
+
+	kvm_run->exit_reason = 0;
+	vcpu->arch.ret = RESUME_GUEST;
+	vcpu->arch.trap = 0;
+
+	flush_fp_to_thread(current);
+	flush_altivec_to_thread(current);
+	flush_vsx_to_thread(current);
+	preempt_disable();
+
+	/*
+	 * Synchronize with other threads in this virtual core
+	 */
+	vc = vcpu->arch.vcore;
+	spin_lock(&vc->lock);
+	/* This happens the first time this is called for a vcpu */
+	if (vcpu->arch.state == KVMPPC_VCPU_BLOCKED)
+		--vc->n_blocked;
+	vcpu->arch.state = KVMPPC_VCPU_RUNNABLE;
+	ptid = vc->n_runnable;
+	vc->runnable_threads[ptid] = vcpu;
+	vc->run_task[ptid] = current;
+	vc->kvm_run[ptid] = kvm_run;
+	vcpu->arch.ptid = ptid;
+	++vc->n_runnable;
+
+	wait_state = TASK_INTERRUPTIBLE;
+	while (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE) {
+		if (signal_pending(current)) {
+			if (!vc->vcore_running) {
+				kvm_run->exit_reason = KVM_EXIT_INTR;
+				vcpu->arch.ret = -EINTR;
+				break;
+			}
+			/* have to wait for vcore to stop executing guest */
+			wait_state = TASK_UNINTERRUPTIBLE;
+			smp_send_reschedule(vc->pcpu);
+		}
+
+		if (!vc->vcore_running &&
+		    vc->n_runnable + vc->n_blocked == vc->num_threads) {
+			/* we can run now */
+			if (kvmppc_run_core(vc))
+				continue;
+		}
+
+		if (vc->vcore_running == 1 && VCORE_EXIT_COUNT(vc) == 0)
+			kvmppc_start_thread(vcpu);
+
+		/* wait for other threads to come in, or wait for vcore */
+		prepare_to_wait(&vcpu->arch.cpu_run, &wait, wait_state);
+		spin_unlock(&vc->lock);
+		schedule();
+		finish_wait(&vcpu->arch.cpu_run, &wait);
+		spin_lock(&vc->lock);
+	}
+
+	if (vcpu->arch.state == KVMPPC_VCPU_RUNNABLE)
+		kvmppc_remove_runnable(vc, vcpu->arch.ptid);
+	spin_unlock(&vc->lock);
 
-	return kvmppc_handle_exit(run, vcpu, current);
+	return vcpu->arch.ret;
 }
 
 int kvmppc_vcpu_run(struct kvm_run *run, struct kvm_vcpu *vcpu)
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index f63a884..e5d286f 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -30,8 +30,6 @@
  *                                                                           *
  ****************************************************************************/
 
-#define SHADOW_VCPU_OFF		PACA_KVM_SVCPU
-
 	.globl	kvmppc_skip_interrupt
 kvmppc_skip_interrupt:
 	mfspr	r13,SPRN_SRR0
@@ -112,6 +110,32 @@ kvmppc_trampoline_enter:
  *                                                                            *
  *****************************************************************************/
 
+#define XICS_XIRR		4
+#define XICS_QIRR		0xc
+
+/*
+ * We come in here when wakened from nap mode on a secondary hw thread.
+ * Relocation is off and most register values are lost.
+ * r13 points to the PACA.
+ */
+	.globl	kvm_start_guest
+kvm_start_guest:
+	ld	r1,PACAEMERGSP(r13)
+	subi	r1,r1,STACK_FRAME_OVERHEAD
+
+	/* get vcpu pointer */
+	ld	r4, HSTATE_KVM_VCPU(r13)
+
+	/* We got here with an IPI; clear it */
+	ld	r5, HSTATE_XICS_PHYS(r13)
+	li	r0, 0xff
+	li	r6, XICS_QIRR
+	li	r7, XICS_XIRR
+	lwzcix	r8, r5, r7		/* ack the interrupt */
+	sync
+	stbcix	r0, r5, r6		/* clear it */
+	stwcix	r8, r5, r7		/* EOI it */
+
 .global kvmppc_handler_trampoline_enter
 kvmppc_handler_trampoline_enter:
 
@@ -230,7 +254,20 @@ kvmppc_handler_trampoline_enter:
 	slbia
 	ptesync
 
-	/* Switch to guest partition. */
+	/* Increment entry count iff exit count is zero. */
+	ld	r5,HSTATE_KVM_VCORE(r13)
+	addi	r9,r5,VCORE_ENTRY_EXIT
+21:	lwarx	r3,0,r9
+	cmpwi	r3,0x100		/* any threads starting to exit? */
+	bge	secondary_too_late	/* if so we're too late to the party */
+	addi	r3,r3,1
+	stwcx.	r3,0,r9
+	bne	21b
+
+	/* Primary thread switches to guest partition. */
+	lwz	r6,VCPU_PTID(r4)
+	cmpwi	r6,0
+	bne	20f
 	ld	r9,VCPU_KVM(r4)		/* pointer to struct kvm */
 	ld	r6,KVM_SDR1(r9)
 	lwz	r7,KVM_LPID(r9)
@@ -240,7 +277,15 @@ kvmppc_handler_trampoline_enter:
 	mtspr	SPRN_SDR1,r6		/* switch to partition page table */
 	mtspr	SPRN_LPID,r7
 	isync
-	ld	r8,VCPU_LPCR(r4)
+	li	r0,1
+	stb	r0,VCORE_IN_GUEST(r5)	/* signal secondaries to continue */
+	b	10f
+
+	/* Secondary threads wait for primary to have done partition switch */
+20:	lbz	r0,VCORE_IN_GUEST(r5)
+	cmpwi	r0,0
+	beq	20b
+10:	ld	r8,VCPU_LPCR(r4)
 	mtspr	SPRN_LPCR,r8
 	isync
 
@@ -255,10 +300,12 @@ kvmppc_handler_trampoline_enter:
 	 * Invalidate the TLB if we could possibly have stale TLB
 	 * entries for this partition on this core due to the use
 	 * of tlbiel.
+	 * XXX maybe only need this on primary thread?
 	 */
 	ld	r9,VCPU_KVM(r4)		/* pointer to struct kvm */
 	lwz	r5,VCPU_VCPUID(r4)
 	lhz	r6,PACAPACAINDEX(r13)
+	rldimi	r6,r5,0,62		/* XXX map as if threads 1:1 p:v */
 	lhz	r8,VCPU_LAST_CPU(r4)
 	sldi	r7,r6,1			/* see if this is the same vcpu */
 	add	r7,r7,r9		/* as last ran on this pcpu */
@@ -544,8 +591,60 @@ hcall_real_cont:
 	ptesync
 
 hdec_soon:
-	/* Switch back to host partition */
+	/* Increment the threads-exiting-guest count in the 0xff00
+	   bits of vcore->entry_exit_count */
+	lwsync
+	ld	r5,HSTATE_KVM_VCORE(r13)
+	addi	r6,r5,VCORE_ENTRY_EXIT
+41:	lwarx	r3,0,r6
+	addi	r0,r3,0x100
+	stwcx.	r0,0,r6
+	bne	41b
+
+	/*
+	 * At this point we have an interrupt that we have to pass
+	 * up to the kernel or qemu; we can't handle it in real mode.
+	 * Thus we have to do a partition switch, so we have to
+	 * collect the other threads, if we are the first thread
+	 * to take an interrupt.  To do this, we set the HDEC to 0,
+	 * which causes an HDEC interrupt in all threads within 2ns
+	 * because the HDEC register is shared between all 4 threads.
+	 * However, we don't need to bother if this is an HDEC
+	 * interrupt, since the other threads will already be on their
+	 * way here in that case.
+	 */
+	cmpwi	r12,BOOK3S_INTERRUPT_HV_DECREMENTER
+	beq	40f
+	cmpwi	r3,0x100	/* Are we the first here? */
+	bge	40f
+	cmpwi	r3,1
+	ble	40f
+	li	r0,0
+	mtspr	SPRN_HDEC,r0
+40:
+
+	/* Secondary threads wait for primary to do partition switch */
 	ld	r4,VCPU_KVM(r9)		/* pointer to struct kvm */
+	ld	r5,HSTATE_KVM_VCORE(r13)
+	lwz	r3,VCPU_PTID(r9)
+	cmpwi	r3,0
+	beq	15f
+	HMT_LOW
+13:	lbz	r3,VCORE_IN_GUEST(r5)
+	cmpwi	r3,0
+	bne	13b
+	HMT_MEDIUM
+	b	16f
+
+	/* Primary thread waits for all the secondaries to exit guest */
+15:	lwz	r3,VCORE_ENTRY_EXIT(r5)
+	srwi	r0,r3,8
+	clrldi	r3,r3,56
+	cmpw	r3,r0
+	bne	15b
+	isync
+
+	/* Primary thread switches back to host partition */
 	ld	r6,KVM_HOST_SDR1(r4)
 	lwz	r7,KVM_HOST_LPID(r4)
 	li	r8,LPID_RSVD		/* switch to reserved LPID */
@@ -554,10 +653,12 @@ hdec_soon:
 	mtspr	SPRN_SDR1,r6		/* switch to partition page table */
 	mtspr	SPRN_LPID,r7
 	isync
+	li	r0,0
+	stb	r0,VCORE_IN_GUEST(r5)
 	lis	r8,0x7fff		/* MAX_INT@h */
 	mtspr	SPRN_HDEC,r8
 
-	ld	r8,KVM_HOST_LPCR(r4)
+16:	ld	r8,KVM_HOST_LPCR(r4)
 	mtspr	SPRN_LPCR,r8
 	isync
 
@@ -666,6 +767,11 @@ hdec_soon:
 	mr	r3, r9
 	bl	.kvmppc_save_fp
 
+	/* Secondary threads go off to take a nap */
+	lwz	r0,VCPU_PTID(r3)
+	cmpwi	r0,0
+	bne	secondary_nap
+
 	/* RFI into the highmem handler */
 	mfmsr	r7
 	ori	r7, r7, MSR_IR|MSR_DR|MSR_RI|MSR_ME	/* Enable paging */
@@ -817,3 +923,53 @@ _GLOBAL(kvmppc_h_set_dabr)
 	mtspr	SPRN_DABR,r4
 	li	r3,0
 	blr
+
+secondary_too_late:
+	ld	r5,HSTATE_KVM_VCORE(r13)
+	HMT_LOW
+13:	lbz	r3,VCORE_IN_GUEST(r5)
+	cmpwi	r3,0
+	bne	13b
+	HMT_MEDIUM
+	ld	r11,PACA_SLBSHADOWPTR(r13)
+
+	.rept	SLB_NUM_BOLTED
+	ld	r5,SLBSHADOW_SAVEAREA(r11)
+	ld	r6,SLBSHADOW_SAVEAREA+8(r11)
+	andis.	r7,r5,SLB_ESID_V@h
+	beq	1f
+	slbmte	r6,r5
+1:	addi	r11,r11,16
+	.endr
+	b	50f
+
+secondary_nap:
+	/* Clear any pending IPI */
+50:	ld	r5, HSTATE_XICS_PHYS(r13)
+	li	r0, 0xff
+	li	r6, XICS_QIRR
+	stbcix	r0, r5, r6
+
+	/* increment the nap count and then go to nap mode */
+	ld	r4, HSTATE_KVM_VCORE(r13)
+	addi	r4, r4, VCORE_NAP_COUNT
+	lwsync				/* make previous updates visible */
+51:	lwarx	r3, 0, r4
+	addi	r3, r3, 1
+	stwcx.	r3, 0, r4
+	bne	51b
+	isync
+
+	mfspr	r4, SPRN_LPCR
+	li	r0, LPCR_PECE
+	andc	r4, r4, r0
+	ori	r4, r4, LPCR_PECE0	/* exit nap on interrupt */
+	mtspr	SPRN_LPCR, r4
+	li	r0, 0
+	std	r0, HSTATE_SCRATCH0(r13)
+	ptesync
+	ld	r0, HSTATE_SCRATCH0(r13)
+1:	cmpd	r0, r0
+	bne	1b
+	nap
+	b	.
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 7343051..a01a9a1 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -206,6 +206,9 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_SPAPR_TCE:
 		r = 1;
 		break;
+	case KVM_CAP_PPC_SMT:
+		r = KVM_THREADS_PER_CORE;
+		break;
 #endif
 	default:
 		r = 0;
diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c
index 1f15ad4..96b0c5b 100644
--- a/arch/powerpc/sysdev/xics/icp-native.c
+++ b/arch/powerpc/sysdev/xics/icp-native.c
@@ -24,6 +24,7 @@
 #include <asm/irq.h>
 #include <asm/errno.h>
 #include <asm/xics.h>
+#include <asm/kvm_ppc.h>
 
 struct icp_ipl {
 	union {
@@ -139,6 +140,11 @@ static void icp_native_cause_ipi(int cpu, unsigned long data)
 	icp_native_set_qirr(cpu, IPI_PRIORITY);
 }
 
+void xics_wake_cpu(int cpu)
+{
+	icp_native_set_qirr(cpu, IPI_PRIORITY);
+}
+
 static irqreturn_t icp_native_ipi_action(int irq, void *dev_id)
 {
 	int cpu = smp_processor_id();
@@ -185,6 +191,7 @@ static int __init icp_native_map_one_cpu(int hw_id, unsigned long addr,
 	}
 
 	icp_native_regs[cpu] = ioremap(addr, size);
+	kvmppc_set_xics_phys(cpu, addr);
 	if (!icp_native_regs[cpu]) {
 		pr_warning("icp_native: Failed ioremap for CPU %d, "
 			   "interrupt server #0x%x, addr %#lx\n",
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 0836366..b7e37e3 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -551,6 +551,7 @@ struct kvm_ppc_pvinfo {
 #define KVM_CAP_GET_TSC_KHZ 61
 #define KVM_CAP_PPC_BOOKE_SREGS 62
 #define KVM_CAP_SPAPR_TCE 63
+#define KVM_CAP_PPC_SMT 64
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
-- 
1.7.5.3

Re: [PATCH v2 0/12] Hypervisor-mode KVM on POWER7

[Alexander Graf]

On 31.05.2011, at 08:40, Paul Mackerras wrote:

> The following series of patches enable KVM to exploit the hardware
> hypervisor mode on 64-bit Power ISA Book3S machines.  At present only
> POWER7 is supported, but it would be easy to add other processors.
>=20
> Running the KVM host in hypervisor mode means that the guest can use
> both supervisor mode and user mode.  That means that the guest can
> execute supervisor-privilege instructions and access supervisor-
> privilege registers.  In addition the hardware directs most exceptions
> to the guest.  Thus we don't need to emulate any instructions in the
> host.  Generally, the only times we need to exit the guest are when it
> does a hypercall or when an external interrupt or host timer
> (decrementer) interrupt occurs.
>=20
> The focus of this KVM implementation is to run guests that use the
> PAPR (Power Architecture Platform Requirements) paravirtualization
> interface, which is the interface supplied by PowerVM on IBM pSeries
> machines.  Currently the "pseries" machine type in qemu is only
> supported by book3s_hv KVM, and book3s_hv KVM only supports the
> "pseries" machine type.  That will hopefully change in future.
>=20
> These patches are against Linus' v3.0-rc1 tree.

Thinking about the testability of this a bit more ... how much effort =
would it be to get this code running on a 970MP with SLOF? There should =
only be a few POWER7 specific pieces, right?


Alex

Re: [PATCH v2 0/12] Hypervisor-mode KVM on POWER7

[Paul Mackerras]

On Tue, May 31, 2011 at 12:40:31PM +0200, Alexander Graf wrote:

> Thinking about the testability of this a bit more ... how much
> effort would it be to get this code running on a 970MP with SLOF?
> There should only be a few POWER7 specific pieces, right?

Do you have a 970MP that has a usable hypervisor mode, i.e. not an
Apple machine?  The 970s in Apple machines have the HV hard-wired to
1, which means they do have a hypervisor mode but it isn't any use.

If you do have such a machine, then we would have to look at some
details like the instruction sequence for the partition switch, and
make sure we don't try to use SMT4 mode.  Also, I believe we will have
to flush the TLB on partition switches, since Power processors prior
to POWER7 didn't tag the TLB entries with the partition ID.

So it should be quite feasible if you have a non-Apple machine.
I will check whether the 970MP machines that Terrasoft were
distributing would be suitable.  We have one of them in the lab.

Regards,
Paul.

Re: [PATCH v2 0/12] Hypervisor-mode KVM on POWER7

[Alexander Graf]

On 31.05.2011, at 14:35, Paul Mackerras wrote:

> On Tue, May 31, 2011 at 12:40:31PM +0200, Alexander Graf wrote:
>=20
>> Thinking about the testability of this a bit more ... how much
>> effort would it be to get this code running on a 970MP with SLOF?
>> There should only be a few POWER7 specific pieces, right?
>=20
> Do you have a 970MP that has a usable hypervisor mode, i.e. not an
> Apple machine?  The 970s in Apple machines have the HV hard-wired to
> 1, which means they do have a hypervisor mode but it isn't any use.
>=20
> If you do have such a machine, then we would have to look at some
> details like the instruction sequence for the partition switch, and
> make sure we don't try to use SMT4 mode.  Also, I believe we will have
> to flush the TLB on partition switches, since Power processors prior
> to POWER7 didn't tag the TLB entries with the partition ID.
>=20
> So it should be quite feasible if you have a non-Apple machine.
> I will check whether the 970MP machines that Terrasoft were
> distributing would be suitable.  We have one of them in the lab.

That's the one I was thinking of and yes, I have one available. That way =
I could test 99% of your code, you don't have to release hardware, and =
everyone's happy :).


Alex

Re: [PATCH v2 0/12] Hypervisor-mode KVM on POWER7

[Jimi Xenidis]

On May 31, 2011, at 8:50 AM, Alexander Graf wrote:

>=20
> On 31.05.2011, at 14:35, Paul Mackerras wrote:
>=20
>> On Tue, May 31, 2011 at 12:40:31PM +0200, Alexander Graf wrote:
>>=20
>>> Thinking about the testability of this a bit more ... how much
>>> effort would it be to get this code running on a 970MP with SLOF?
>>> There should only be a few POWER7 specific pieces, right?
>>=20
>> Do you have a 970MP that has a usable hypervisor mode, i.e. not an
>> Apple machine?  The 970s in Apple machines have the HV hard-wired to
>> 1, which means they do have a hypervisor mode but it isn't any use.
>>=20
>> If you do have such a machine, then we would have to look at some
>> details like the instruction sequence for the partition switch, and
>> make sure we don't try to use SMT4 mode.  Also, I believe we will =
have
>> to flush the TLB on partition switches, since Power processors prior
>> to POWER7 didn't tag the TLB entries with the partition ID.
>>=20
>> So it should be quite feasible if you have a non-Apple machine.
>> I will check whether the 970MP machines that Terrasoft were
>> distributing would be suitable.  We have one of them in the lab.
>=20
> That's the one I was thinking of and yes, I have one available. That =
way I could test 99% of your code, you don't have to release hardware, =
and everyone's happy :).
>=20

Be aware that on 970s (off the top of my head):
 - did not have the LPCR architected so you'll have to access individual =
HID registers.
 - old style RMOR is supported, not VRMA
 - no MEDiated interrupt
=20
-jx

>=20
> Alex
>=20
> --
> To unsubscribe from this list: send the line "unsubscribe kvm-ppc" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH v2 0/12] Hypervisor-mode KVM on POWER7

[Paul Mackerras]

On Tue, May 31, 2011 at 02:50:20PM +0200, Alexander Graf wrote:
> 
> On 31.05.2011, at 14:35, Paul Mackerras wrote:
> 
> > On Tue, May 31, 2011 at 12:40:31PM +0200, Alexander Graf wrote:
> > 
> >> Thinking about the testability of this a bit more ... how much
> >> effort would it be to get this code running on a 970MP with SLOF?
> >> There should only be a few POWER7 specific pieces, right?
> > 
> > Do you have a 970MP that has a usable hypervisor mode, i.e. not an
> > Apple machine?  The 970s in Apple machines have the HV hard-wired to
> > 1, which means they do have a hypervisor mode but it isn't any use.
> > 
> > If you do have such a machine, then we would have to look at some
> > details like the instruction sequence for the partition switch, and
> > make sure we don't try to use SMT4 mode.  Also, I believe we will have
> > to flush the TLB on partition switches, since Power processors prior
> > to POWER7 didn't tag the TLB entries with the partition ID.
> > 
> > So it should be quite feasible if you have a non-Apple machine.
> > I will check whether the 970MP machines that Terrasoft were
> > distributing would be suitable.  We have one of them in the lab.
> 
> That's the one I was thinking of and yes, I have one available. That
> way I could test 99% of your code, you don't have to release
> hardware, and everyone's happy :).

I checked our YDL PowerStation and it does appear to have a usable
hypervisor mode. :)

As Jimi X pointed out, there are a few things that POWER7 has that 970
doesn't.  In particular the lack of VRMA mode means that we will have
to find 64MB of physically contiguous memory, aligned on a 64MB
address boundary, for the real mode area (RMO) for the guest.  64MB is
the smallest RMO size that the 970 supports; it also supports 128MB,
256MB, 1GB, 16GB and 256GB.  I think we'll have to reserve some memory
at boot.  We may get away with bumping up CONFIG_FORCE_MAX_ZONEORDER,
but relying on allocating a physically contiguous 64MB at runtime
seems somewhat fragile.  Also, we'll need some qemu changes since it
won't be able to allocate the RMO itself.

The other thing is that we have to flush the TLB on every partitions
switch, plus make sure that we're not switching the partition ID while
any other cpu in the same partition is doing a tlbie or tlbsync.
Still, it should all be doable.

Paul.

Re: [PATCH v2 0/12] Hypervisor-mode KVM on POWER7

[Olof Johansson]

On Tue, May 31, 2011 at 5:35 AM, Paul Mackerras <paulus@samba.org> wrote:
> On Tue, May 31, 2011 at 12:40:31PM +0200, Alexander Graf wrote:
>
>> Thinking about the testability of this a bit more ... how much
>> effort would it be to get this code running on a 970MP with SLOF?
>> There should only be a few POWER7 specific pieces, right?
>
> Do you have a 970MP that has a usable hypervisor mode, i.e. not an
> Apple machine? =A0The 970s in Apple machines have the HV hard-wired to
> 1, which means they do have a hypervisor mode but it isn't any use.
>
> If you do have such a machine, then we would have to look at some
> details like the instruction sequence for the partition switch, and
> make sure we don't try to use SMT4 mode. =A0Also, I believe we will have
> to flush the TLB on partition switches, since Power processors prior
> to POWER7 didn't tag the TLB entries with the partition ID.
>
> So it should be quite feasible if you have a non-Apple machine.
> I will check whether the 970MP machines that Terrasoft were
> distributing would be suitable. =A0We have one of them in the lab.

PA6T is closer to power7 than 970 when it comes to hypervisor features
(i.e. VRMA, LPCR, mediated interrupts are all available there). I can
try to find some old hardware if there's any interest from anyone to
use it.

Of course, there isn't much of a roadmap. But 970 isn't really going
anywhere either. :)


-Olof