From 50eb2a3cd0f50d912b26d0b79b7f443344608390 Mon Sep 17 00:00:00 2001
From: Avi Kivity <avi@redhat.com>
Date: Sun, 20 Dec 2009 15:00:10 +0200
Subject: KVM: Add KVM_MMIO kconfig item

s390 doesn't have mmio, this will simplify ifdefing it out.

Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kvm/Kconfig | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 6fb6e8aa389..be28968c794 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -20,6 +20,7 @@ config KVM
 	bool
 	select PREEMPT_NOTIFIERS
 	select ANON_INODES
+	select KVM_MMIO
 
 config KVM_BOOK3S_64_HANDLER
 	bool
-- 
cgit v1.2.3


From 583617b7866cfcc0b3830a4b7ab20f218d180f67 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Mon, 21 Dec 2009 20:21:23 +0100
Subject: KVM: powerpc: Move vector to irqprio resolving to separate function

We're using a switch table to find the irqprio that belongs to a specific
interrupt vector. This table is part of the interrupt inject logic.

Since we'll add a new function to stop interrupts, let's move this table
out of the injection logic into a separate function.

Signed-off-by: Alexander Graf <agraf@suse.de>
Acked-by: Acked-by: Hollis Blanchard <hollis@penguinppc.org>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kvm/book3s.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 3e294bd9b8c..241795bdf34 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -125,11 +125,10 @@ void kvmppc_inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 flags)
 	vcpu->arch.mmu.reset_msr(vcpu);
 }
 
-void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec)
+static int kvmppc_book3s_vec2irqprio(unsigned int vec)
 {
 	unsigned int prio;
 
-	vcpu->stat.queue_intr++;
 	switch (vec) {
 	case 0x100: prio = BOOK3S_IRQPRIO_SYSTEM_RESET;		break;
 	case 0x200: prio = BOOK3S_IRQPRIO_MACHINE_CHECK;	break;
@@ -149,7 +148,15 @@ void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec)
 	default:    prio = BOOK3S_IRQPRIO_MAX;			break;
 	}
 
-	set_bit(prio, &vcpu->arch.pending_exceptions);
+	return prio;
+}
+
+void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec)
+{
+	vcpu->stat.queue_intr++;
+
+	set_bit(kvmppc_book3s_vec2irqprio(vec),
+		&vcpu->arch.pending_exceptions);
 #ifdef EXIT_DEBUG
 	printk(KERN_INFO "Queueing interrupt %x\n", vec);
 #endif
-- 
cgit v1.2.3


From 7706664d39a8eb8555408a24b1f17bd2086189c6 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Mon, 21 Dec 2009 20:21:24 +0100
Subject: KVM: powerpc: Improve DEC handling

We treated the DEC interrupt like an edge based one. This is not true for
Book3s. The DEC keeps firing until mtdec is issued again and thus clears
the interrupt line.

So let's implement this logic in KVM too. This patch moves the line clearing
from the firing of the interrupt to the mtdec emulation.

This makes PPC64 guests work without AGGRESSIVE_DEC defined.

Signed-off-by: Alexander Graf <agraf@suse.de>
Acked-by: Acked-by: Hollis Blanchard <hollis@penguinppc.org>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_ppc.h |  1 +
 arch/powerpc/kvm/book3s.c          | 16 +++++++++++++++-
 arch/powerpc/kvm/booke.c           |  5 +++++
 arch/powerpc/kvm/emulate.c         |  3 +++
 4 files changed, 24 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 269ee46ab02..abfd0c4d567 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -82,6 +82,7 @@ extern void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu);
 extern int kvmppc_core_pending_dec(struct kvm_vcpu *vcpu);
 extern void kvmppc_core_queue_program(struct kvm_vcpu *vcpu);
 extern void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu);
+extern void kvmppc_core_dequeue_dec(struct kvm_vcpu *vcpu);
 extern void kvmppc_core_queue_external(struct kvm_vcpu *vcpu,
                                        struct kvm_interrupt *irq);
 
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 241795bdf34..fd3ad6c7f35 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -151,6 +151,13 @@ static int kvmppc_book3s_vec2irqprio(unsigned int vec)
 	return prio;
 }
 
+static void kvmppc_book3s_dequeue_irqprio(struct kvm_vcpu *vcpu,
+					  unsigned int vec)
+{
+	clear_bit(kvmppc_book3s_vec2irqprio(vec),
+		  &vcpu->arch.pending_exceptions);
+}
+
 void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec)
 {
 	vcpu->stat.queue_intr++;
@@ -178,6 +185,11 @@ int kvmppc_core_pending_dec(struct kvm_vcpu *vcpu)
 	return test_bit(BOOK3S_INTERRUPT_DECREMENTER >> 7, &vcpu->arch.pending_exceptions);
 }
 
+void kvmppc_core_dequeue_dec(struct kvm_vcpu *vcpu)
+{
+	kvmppc_book3s_dequeue_irqprio(vcpu, BOOK3S_INTERRUPT_DECREMENTER);
+}
+
 void kvmppc_core_queue_external(struct kvm_vcpu *vcpu,
                                 struct kvm_interrupt *irq)
 {
@@ -275,7 +287,9 @@ void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu)
 #endif
 	priority = __ffs(*pending);
 	while (priority <= (sizeof(unsigned int) * 8)) {
-		if (kvmppc_book3s_irqprio_deliver(vcpu, priority)) {
+		if (kvmppc_book3s_irqprio_deliver(vcpu, priority) &&
+		    (priority != BOOK3S_IRQPRIO_DECREMENTER)) {
+			/* DEC interrupts get cleared by mtdec */
 			clear_bit(priority, &vcpu->arch.pending_exceptions);
 			break;
 		}
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 06f5a9ecc42..d8b63420acf 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -97,6 +97,11 @@ int kvmppc_core_pending_dec(struct kvm_vcpu *vcpu)
 	return test_bit(BOOKE_IRQPRIO_DECREMENTER, &vcpu->arch.pending_exceptions);
 }
 
+void kvmppc_core_dequeue_dec(struct kvm_vcpu *vcpu)
+{
+	clear_bit(BOOKE_IRQPRIO_DECREMENTER, &vcpu->arch.pending_exceptions);
+}
+
 void kvmppc_core_queue_external(struct kvm_vcpu *vcpu,
                                 struct kvm_interrupt *irq)
 {
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index 4a9ac6640fa..303457b2f52 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -83,6 +83,9 @@ void kvmppc_emulate_dec(struct kvm_vcpu *vcpu)
 
 	pr_debug("mtDEC: %x\n", vcpu->arch.dec);
 #ifdef CONFIG_PPC64
+	/* mtdec lowers the interrupt line when positive. */
+	kvmppc_core_dequeue_dec(vcpu);
+
 	/* POWER4+ triggers a dec interrupt if the value is < 0 */
 	if (vcpu->arch.dec & 0x80000000) {
 		hrtimer_try_to_cancel(&vcpu->arch.dec_timer);
-- 
cgit v1.2.3


From 0bb1fb7178c55f3e295b2ffe0433c330f960458e Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Mon, 21 Dec 2009 20:21:25 +0100
Subject: KVM: powerpc: Remove AGGRESSIVE_DEC

Because we now emulate the DEC interrupt according to real life behavior,
there's no need to keep the AGGRESSIVE_DEC hack around.

Let's just remove it.

Signed-off-by: Alexander Graf <agraf@suse.de>
Acked-by: Acked-by: Hollis Blanchard <hollis@penguinppc.org>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kvm/book3s.c | 16 +---------------
 1 file changed, 1 insertion(+), 15 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index fd3ad6c7f35..803505d3e45 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -34,12 +34,6 @@
 /* #define EXIT_DEBUG */
 /* #define EXIT_DEBUG_SIMPLE */
 
-/* Without AGGRESSIVE_DEC we only fire off a DEC interrupt when DEC turns 0.
- * When set, we retrigger a DEC interrupt after that if DEC <= 0.
- * PPC32 Linux runs faster without AGGRESSIVE_DEC, PPC64 Linux requires it. */
-
-/* #define AGGRESSIVE_DEC */
-
 struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "exits",       VCPU_STAT(sum_exits) },
 	{ "mmio",        VCPU_STAT(mmio_exits) },
@@ -81,7 +75,7 @@ void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
 	to_book3s(vcpu)->slb_shadow_max = get_paca()->kvm_slb_max;
 }
 
-#if defined(AGGRESSIVE_DEC) || defined(EXIT_DEBUG)
+#if defined(EXIT_DEBUG)
 static u32 kvmppc_get_dec(struct kvm_vcpu *vcpu)
 {
 	u64 jd = mftb() - vcpu->arch.dec_jiffies;
@@ -273,14 +267,6 @@ void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu)
 	unsigned long *pending = &vcpu->arch.pending_exceptions;
 	unsigned int priority;
 
-	/* XXX be more clever here - no need to mftb() on every entry */
-	/* Issue DEC again if it's still active */
-#ifdef AGGRESSIVE_DEC
-	if (vcpu->arch.msr & MSR_EE)
-		if (kvmppc_get_dec(vcpu) & 0x80000000)
-			kvmppc_core_queue_dec(vcpu);
-#endif
-
 #ifdef EXIT_DEBUG
 	if (vcpu->arch.pending_exceptions)
 		printk(KERN_EMERG "KVM: Check pending: %lx\n", vcpu->arch.pending_exceptions);
-- 
cgit v1.2.3


From 46a26bf55714c1e2f17e34683292a389acb8e601 Mon Sep 17 00:00:00 2001
From: Marcelo Tosatti <mtosatti@redhat.com>
Date: Wed, 23 Dec 2009 14:35:16 -0200
Subject: KVM: modify memslots layout in struct kvm

Have a pointer to an allocated region inside struct kvm.

[alex: fix ppc book 3s]

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/ia64/kvm/kvm-ia64.c  | 10 ++++++----
 arch/powerpc/kvm/book3s.c |  2 +-
 arch/x86/kvm/mmu.c        | 11 ++++++-----
 arch/x86/kvm/vmx.c        |  4 ++--
 arch/x86/kvm/x86.c        |  4 ++--
 include/linux/kvm_host.h  | 12 ++++++++----
 virt/kvm/iommu.c          | 18 ++++++++++++------
 virt/kvm/kvm_main.c       | 36 +++++++++++++++++++++++-------------
 8 files changed, 60 insertions(+), 37 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index 5fdeec5fddc..1ca1dbf4811 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -1377,12 +1377,14 @@ static void free_kvm(struct kvm *kvm)
 
 static void kvm_release_vm_pages(struct kvm *kvm)
 {
+	struct kvm_memslots *slots;
 	struct kvm_memory_slot *memslot;
 	int i, j;
 	unsigned long base_gfn;
 
-	for (i = 0; i < kvm->nmemslots; i++) {
-		memslot = &kvm->memslots[i];
+	slots = kvm->memslots;
+	for (i = 0; i < slots->nmemslots; i++) {
+		memslot = &slots->memslots[i];
 		base_gfn = memslot->base_gfn;
 
 		for (j = 0; j < memslot->npages; j++) {
@@ -1802,7 +1804,7 @@ static int kvm_ia64_sync_dirty_log(struct kvm *kvm,
 	if (log->slot >= KVM_MEMORY_SLOTS)
 		goto out;
 
-	memslot = &kvm->memslots[log->slot];
+	memslot = &kvm->memslots->memslots[log->slot];
 	r = -ENOENT;
 	if (!memslot->dirty_bitmap)
 		goto out;
@@ -1840,7 +1842,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 	/* If nothing is dirty, don't bother messing with page tables. */
 	if (is_dirty) {
 		kvm_flush_remote_tlbs(kvm);
-		memslot = &kvm->memslots[log->slot];
+		memslot = &kvm->memslots->memslots[log->slot];
 		n = ALIGN(memslot->npages, BITS_PER_LONG) / 8;
 		memset(memslot->dirty_bitmap, 0, n);
 	}
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 803505d3e45..bb8873dcb20 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -865,7 +865,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 
 	/* If nothing is dirty, don't bother messing with page tables. */
 	if (is_dirty) {
-		memslot = &kvm->memslots[log->slot];
+		memslot = &kvm->memslots->memslots[log->slot];
 
 		ga = memslot->base_gfn << PAGE_SHIFT;
 		ga_end = ga + (memslot->npages << PAGE_SHIFT);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 4f499d7f710..81f84d326a8 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -807,13 +807,14 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
 {
 	int i, j;
 	int retval = 0;
+	struct kvm_memslots *slots = kvm->memslots;
 
 	/*
 	 * If mmap_sem isn't taken, we can look the memslots with only
 	 * the mmu_lock by skipping over the slots with userspace_addr == 0.
 	 */
-	for (i = 0; i < kvm->nmemslots; i++) {
-		struct kvm_memory_slot *memslot = &kvm->memslots[i];
+	for (i = 0; i < slots->nmemslots; i++) {
+		struct kvm_memory_slot *memslot = &slots->memslots[i];
 		unsigned long start = memslot->userspace_addr;
 		unsigned long end;
 
@@ -3021,8 +3022,8 @@ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm)
 	unsigned int nr_mmu_pages;
 	unsigned int  nr_pages = 0;
 
-	for (i = 0; i < kvm->nmemslots; i++)
-		nr_pages += kvm->memslots[i].npages;
+	for (i = 0; i < kvm->memslots->nmemslots; i++)
+		nr_pages += kvm->memslots->memslots[i].npages;
 
 	nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000;
 	nr_mmu_pages = max(nr_mmu_pages,
@@ -3295,7 +3296,7 @@ static int count_rmaps(struct kvm_vcpu *vcpu)
 	int i, j, k;
 
 	for (i = 0; i < KVM_MEMORY_SLOTS; ++i) {
-		struct kvm_memory_slot *m = &vcpu->kvm->memslots[i];
+		struct kvm_memory_slot *m = &vcpu->kvm->memslots->memslots[i];
 		struct kvm_rmap_desc *d;
 
 		for (j = 0; j < m->npages; ++j) {
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 74a66f0c00b..18698799e36 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1503,8 +1503,8 @@ static void enter_pmode(struct kvm_vcpu *vcpu)
 static gva_t rmode_tss_base(struct kvm *kvm)
 {
 	if (!kvm->arch.tss_addr) {
-		gfn_t base_gfn = kvm->memslots[0].base_gfn +
-				 kvm->memslots[0].npages - 3;
+		gfn_t base_gfn = kvm->memslots->memslots[0].base_gfn +
+				 kvm->memslots->memslots[0].npages - 3;
 		return base_gfn << PAGE_SHIFT;
 	}
 	return kvm->arch.tss_addr;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 8798504ace1..3b81cb9da8b 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2427,7 +2427,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 		spin_lock(&kvm->mmu_lock);
 		kvm_mmu_slot_remove_write_access(kvm, log->slot);
 		spin_unlock(&kvm->mmu_lock);
-		memslot = &kvm->memslots[log->slot];
+		memslot = &kvm->memslots->memslots[log->slot];
 		n = ALIGN(memslot->npages, BITS_PER_LONG) / 8;
 		memset(memslot->dirty_bitmap, 0, n);
 	}
@@ -5223,7 +5223,7 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 				int user_alloc)
 {
 	int npages = mem->memory_size >> PAGE_SHIFT;
-	struct kvm_memory_slot *memslot = &kvm->memslots[mem->slot];
+	struct kvm_memory_slot *memslot = &kvm->memslots->memslots[mem->slot];
 
 	/*To keep backward compatibility with older userspace,
 	 *x86 needs to hanlde !user_alloc case.
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index bd5a616d937..782bfb185f8 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -150,14 +150,18 @@ struct kvm_irq_routing_table {};
 
 #endif
 
+struct kvm_memslots {
+	int nmemslots;
+	struct kvm_memory_slot memslots[KVM_MEMORY_SLOTS +
+					KVM_PRIVATE_MEM_SLOTS];
+};
+
 struct kvm {
 	spinlock_t mmu_lock;
 	spinlock_t requests_lock;
 	struct rw_semaphore slots_lock;
 	struct mm_struct *mm; /* userspace tied to this vm */
-	int nmemslots;
-	struct kvm_memory_slot memslots[KVM_MEMORY_SLOTS +
-					KVM_PRIVATE_MEM_SLOTS];
+	struct kvm_memslots *memslots;
 #ifdef CONFIG_KVM_APIC_ARCHITECTURE
 	u32 bsp_vcpu_id;
 	struct kvm_vcpu *bsp_vcpu;
@@ -482,7 +486,7 @@ static inline void kvm_guest_exit(void)
 
 static inline int memslot_id(struct kvm *kvm, struct kvm_memory_slot *slot)
 {
-	return slot - kvm->memslots;
+	return slot - kvm->memslots->memslots;
 }
 
 static inline gpa_t gfn_to_gpa(gfn_t gfn)
diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c
index 15147583abd..bc697a66a88 100644
--- a/virt/kvm/iommu.c
+++ b/virt/kvm/iommu.c
@@ -76,10 +76,13 @@ unmap_pages:
 static int kvm_iommu_map_memslots(struct kvm *kvm)
 {
 	int i, r = 0;
+	struct kvm_memslots *slots;
 
-	for (i = 0; i < kvm->nmemslots; i++) {
-		r = kvm_iommu_map_pages(kvm, kvm->memslots[i].base_gfn,
-					kvm->memslots[i].npages);
+	slots = kvm->memslots;
+
+	for (i = 0; i < slots->nmemslots; i++) {
+		r = kvm_iommu_map_pages(kvm, slots->memslots[i].base_gfn,
+					slots->memslots[i].npages);
 		if (r)
 			break;
 	}
@@ -210,10 +213,13 @@ static void kvm_iommu_put_pages(struct kvm *kvm,
 static int kvm_iommu_unmap_memslots(struct kvm *kvm)
 {
 	int i;
+	struct kvm_memslots *slots;
+
+	slots = kvm->memslots;
 
-	for (i = 0; i < kvm->nmemslots; i++) {
-		kvm_iommu_put_pages(kvm, kvm->memslots[i].base_gfn,
-				    kvm->memslots[i].npages);
+	for (i = 0; i < slots->nmemslots; i++) {
+		kvm_iommu_put_pages(kvm, slots->memslots[i].base_gfn,
+				    slots->memslots[i].npages);
 	}
 
 	return 0;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index bc23b8e0609..86dd8f3d29c 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -375,12 +375,16 @@ static struct kvm *kvm_create_vm(void)
 	INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list);
 #endif
 
+	r = -ENOMEM;
+	kvm->memslots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
+	if (!kvm->memslots)
+		goto out_err;
+
 #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
 	page = alloc_page(GFP_KERNEL | __GFP_ZERO);
-	if (!page) {
-		r = -ENOMEM;
+	if (!page)
 		goto out_err;
-	}
+
 	kvm->coalesced_mmio_ring =
 			(struct kvm_coalesced_mmio_ring *)page_address(page);
 #endif
@@ -416,6 +420,7 @@ out:
 out_err:
 	hardware_disable_all();
 out_err_nodisable:
+	kfree(kvm->memslots);
 	kfree(kvm);
 	return ERR_PTR(r);
 }
@@ -450,9 +455,12 @@ static void kvm_free_physmem_slot(struct kvm_memory_slot *free,
 void kvm_free_physmem(struct kvm *kvm)
 {
 	int i;
+	struct kvm_memslots *slots = kvm->memslots;
+
+	for (i = 0; i < slots->nmemslots; ++i)
+		kvm_free_physmem_slot(&slots->memslots[i], NULL);
 
-	for (i = 0; i < kvm->nmemslots; ++i)
-		kvm_free_physmem_slot(&kvm->memslots[i], NULL);
+	kfree(kvm->memslots);
 }
 
 static void kvm_destroy_vm(struct kvm *kvm)
@@ -533,7 +541,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr)
 		goto out;
 
-	memslot = &kvm->memslots[mem->slot];
+	memslot = &kvm->memslots->memslots[mem->slot];
 	base_gfn = mem->guest_phys_addr >> PAGE_SHIFT;
 	npages = mem->memory_size >> PAGE_SHIFT;
 
@@ -554,7 +562,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	/* Check for overlaps */
 	r = -EEXIST;
 	for (i = 0; i < KVM_MEMORY_SLOTS; ++i) {
-		struct kvm_memory_slot *s = &kvm->memslots[i];
+		struct kvm_memory_slot *s = &kvm->memslots->memslots[i];
 
 		if (s == memslot || !s->npages)
 			continue;
@@ -656,8 +664,8 @@ skip_lpage:
 		kvm_arch_flush_shadow(kvm);
 
 	spin_lock(&kvm->mmu_lock);
-	if (mem->slot >= kvm->nmemslots)
-		kvm->nmemslots = mem->slot + 1;
+	if (mem->slot >= kvm->memslots->nmemslots)
+		kvm->memslots->nmemslots = mem->slot + 1;
 
 	*memslot = new;
 	spin_unlock(&kvm->mmu_lock);
@@ -727,7 +735,7 @@ int kvm_get_dirty_log(struct kvm *kvm,
 	if (log->slot >= KVM_MEMORY_SLOTS)
 		goto out;
 
-	memslot = &kvm->memslots[log->slot];
+	memslot = &kvm->memslots->memslots[log->slot];
 	r = -ENOENT;
 	if (!memslot->dirty_bitmap)
 		goto out;
@@ -781,9 +789,10 @@ EXPORT_SYMBOL_GPL(kvm_is_error_hva);
 struct kvm_memory_slot *gfn_to_memslot_unaliased(struct kvm *kvm, gfn_t gfn)
 {
 	int i;
+	struct kvm_memslots *slots = kvm->memslots;
 
-	for (i = 0; i < kvm->nmemslots; ++i) {
-		struct kvm_memory_slot *memslot = &kvm->memslots[i];
+	for (i = 0; i < slots->nmemslots; ++i) {
+		struct kvm_memory_slot *memslot = &slots->memslots[i];
 
 		if (gfn >= memslot->base_gfn
 		    && gfn < memslot->base_gfn + memslot->npages)
@@ -802,10 +811,11 @@ struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
 int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn)
 {
 	int i;
+	struct kvm_memslots *slots = kvm->memslots;
 
 	gfn = unalias_gfn(kvm, gfn);
 	for (i = 0; i < KVM_MEMORY_SLOTS; ++i) {
-		struct kvm_memory_slot *memslot = &kvm->memslots[i];
+		struct kvm_memory_slot *memslot = &slots->memslots[i];
 
 		if (gfn >= memslot->base_gfn
 		    && gfn < memslot->base_gfn + memslot->npages)
-- 
cgit v1.2.3


From f7784b8ec9b6a041fa828cfbe9012fe51933f5ac Mon Sep 17 00:00:00 2001
From: Marcelo Tosatti <mtosatti@redhat.com>
Date: Wed, 23 Dec 2009 14:35:18 -0200
Subject: KVM: split kvm_arch_set_memory_region into prepare and commit

Required for SRCU convertion later.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/ia64/kvm/kvm-ia64.c   | 16 +++++++++++----
 arch/powerpc/kvm/powerpc.c | 18 ++++++++++++----
 arch/s390/kvm/kvm-s390.c   | 25 +++++++++++++++--------
 arch/x86/kvm/x86.c         | 51 ++++++++++++++++++++++++++--------------------
 include/linux/kvm_host.h   |  7 ++++++-
 virt/kvm/kvm_main.c        | 12 +++++------
 6 files changed, 82 insertions(+), 47 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index 1ca1dbf4811..0757c702798 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -1578,15 +1578,15 @@ out:
 	return r;
 }
 
-int kvm_arch_set_memory_region(struct kvm *kvm,
-		struct kvm_userspace_memory_region *mem,
+int kvm_arch_prepare_memory_region(struct kvm *kvm,
+		struct kvm_memory_slot *memslot,
 		struct kvm_memory_slot old,
+		struct kvm_userspace_memory_region *mem,
 		int user_alloc)
 {
 	unsigned long i;
 	unsigned long pfn;
-	int npages = mem->memory_size >> PAGE_SHIFT;
-	struct kvm_memory_slot *memslot = &kvm->memslots[mem->slot];
+	int npages = memslot->npages;
 	unsigned long base_gfn = memslot->base_gfn;
 
 	if (base_gfn + npages > (KVM_MAX_MEM_SIZE >> PAGE_SHIFT))
@@ -1610,6 +1610,14 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 	return 0;
 }
 
+void kvm_arch_commit_memory_region(struct kvm *kvm,
+		struct kvm_userspace_memory_region *mem,
+		struct kvm_memory_slot old,
+		int user_alloc)
+{
+	return;
+}
+
 void kvm_arch_flush_shadow(struct kvm *kvm)
 {
 	kvm_flush_remote_tlbs(kvm);
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index f06cf93b178..4633e7850dd 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -165,14 +165,24 @@ long kvm_arch_dev_ioctl(struct file *filp,
 	return -EINVAL;
 }
 
-int kvm_arch_set_memory_region(struct kvm *kvm,
-                               struct kvm_userspace_memory_region *mem,
-                               struct kvm_memory_slot old,
-                               int user_alloc)
+int kvm_arch_prepare_memory_region(struct kvm *kvm,
+                                   struct kvm_memory_slot *memslot,
+                                   struct kvm_memory_slot old,
+                                   struct kvm_userspace_memory_region *mem,
+                                   int user_alloc)
 {
 	return 0;
 }
 
+void kvm_arch_commit_memory_region(struct kvm *kvm,
+               struct kvm_userspace_memory_region *mem,
+               struct kvm_memory_slot old,
+               int user_alloc)
+{
+       return;
+}
+
+
 void kvm_arch_flush_shadow(struct kvm *kvm)
 {
 }
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 3fa0a10e466..c8002193d9d 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -690,14 +690,12 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 }
 
 /* Section: memory related */
-int kvm_arch_set_memory_region(struct kvm *kvm,
-				struct kvm_userspace_memory_region *mem,
-				struct kvm_memory_slot old,
-				int user_alloc)
+int kvm_arch_prepare_memory_region(struct kvm *kvm,
+				   struct kvm_memory_slot *memslot,
+				   struct kvm_memory_slot old,
+				   struct kvm_userspace_memory_region *mem,
+				   int user_alloc)
 {
-	int i;
-	struct kvm_vcpu *vcpu;
-
 	/* A few sanity checks. We can have exactly one memory slot which has
 	   to start at guest virtual zero and which has to be located at a
 	   page boundary in userland and which has to end at a page boundary.
@@ -720,14 +718,23 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 	if (!user_alloc)
 		return -EINVAL;
 
+	return 0;
+}
+
+void kvm_arch_commit_memory_region(struct kvm *kvm,
+				struct kvm_userspace_memory_region *mem,
+				struct kvm_memory_slot old,
+				int user_alloc)
+{
+	int i;
+	struct kvm_vcpu *vcpu;
+
 	/* request update of sie control block for all available vcpus */
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		if (test_and_set_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests))
 			continue;
 		kvm_s390_inject_sigp_stop(vcpu, ACTION_RELOADVCPU_ON_STOP);
 	}
-
-	return 0;
 }
 
 void kvm_arch_flush_shadow(struct kvm *kvm)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1ce83319143..43da65feed4 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5228,13 +5228,13 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	kfree(kvm);
 }
 
-int kvm_arch_set_memory_region(struct kvm *kvm,
-				struct kvm_userspace_memory_region *mem,
+int kvm_arch_prepare_memory_region(struct kvm *kvm,
+				struct kvm_memory_slot *memslot,
 				struct kvm_memory_slot old,
+				struct kvm_userspace_memory_region *mem,
 				int user_alloc)
 {
-	int npages = mem->memory_size >> PAGE_SHIFT;
-	struct kvm_memory_slot *memslot = &kvm->memslots->memslots[mem->slot];
+	int npages = memslot->npages;
 
 	/*To keep backward compatibility with older userspace,
 	 *x86 needs to hanlde !user_alloc case.
@@ -5254,26 +5254,35 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 			if (IS_ERR((void *)userspace_addr))
 				return PTR_ERR((void *)userspace_addr);
 
-			/* set userspace_addr atomically for kvm_hva_to_rmapp */
-			spin_lock(&kvm->mmu_lock);
 			memslot->userspace_addr = userspace_addr;
-			spin_unlock(&kvm->mmu_lock);
-		} else {
-			if (!old.user_alloc && old.rmap) {
-				int ret;
-
-				down_write(&current->mm->mmap_sem);
-				ret = do_munmap(current->mm, old.userspace_addr,
-						old.npages * PAGE_SIZE);
-				up_write(&current->mm->mmap_sem);
-				if (ret < 0)
-					printk(KERN_WARNING
-				       "kvm_vm_ioctl_set_memory_region: "
-				       "failed to munmap memory\n");
-			}
 		}
 	}
 
+
+	return 0;
+}
+
+void kvm_arch_commit_memory_region(struct kvm *kvm,
+				struct kvm_userspace_memory_region *mem,
+				struct kvm_memory_slot old,
+				int user_alloc)
+{
+
+	int npages = mem->memory_size >> PAGE_SHIFT;
+
+	if (!user_alloc && !old.user_alloc && old.rmap && !npages) {
+		int ret;
+
+		down_write(&current->mm->mmap_sem);
+		ret = do_munmap(current->mm, old.userspace_addr,
+				old.npages * PAGE_SIZE);
+		up_write(&current->mm->mmap_sem);
+		if (ret < 0)
+			printk(KERN_WARNING
+			       "kvm_vm_ioctl_set_memory_region: "
+			       "failed to munmap memory\n");
+	}
+
 	spin_lock(&kvm->mmu_lock);
 	if (!kvm->arch.n_requested_mmu_pages) {
 		unsigned int nr_mmu_pages = kvm_mmu_calculate_mmu_pages(kvm);
@@ -5282,8 +5291,6 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 
 	kvm_mmu_slot_remove_write_access(kvm, mem->slot);
 	spin_unlock(&kvm->mmu_lock);
-
-	return 0;
 }
 
 void kvm_arch_flush_shadow(struct kvm *kvm)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 782bfb185f8..3c44687b342 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -253,7 +253,12 @@ int kvm_set_memory_region(struct kvm *kvm,
 int __kvm_set_memory_region(struct kvm *kvm,
 			    struct kvm_userspace_memory_region *mem,
 			    int user_alloc);
-int kvm_arch_set_memory_region(struct kvm *kvm,
+int kvm_arch_prepare_memory_region(struct kvm *kvm,
+				struct kvm_memory_slot *memslot,
+				struct kvm_memory_slot old,
+				struct kvm_userspace_memory_region *mem,
+				int user_alloc);
+void kvm_arch_commit_memory_region(struct kvm *kvm,
 				struct kvm_userspace_memory_region *mem,
 				struct kvm_memory_slot old,
 				int user_alloc);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 86dd8f3d29c..c9f6cfe8312 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -663,6 +663,10 @@ skip_lpage:
 	if (!npages)
 		kvm_arch_flush_shadow(kvm);
 
+	r = kvm_arch_prepare_memory_region(kvm, &new, old, mem, user_alloc);
+	if (r)
+		goto out_free;
+
 	spin_lock(&kvm->mmu_lock);
 	if (mem->slot >= kvm->memslots->nmemslots)
 		kvm->memslots->nmemslots = mem->slot + 1;
@@ -670,13 +674,7 @@ skip_lpage:
 	*memslot = new;
 	spin_unlock(&kvm->mmu_lock);
 
-	r = kvm_arch_set_memory_region(kvm, mem, old, user_alloc);
-	if (r) {
-		spin_lock(&kvm->mmu_lock);
-		*memslot = old;
-		spin_unlock(&kvm->mmu_lock);
-		goto out_free;
-	}
+	kvm_arch_commit_memory_region(kvm, mem, old, user_alloc);
 
 	kvm_free_physmem_slot(&old, npages ? &new : NULL);
 	/* Slot deletion case: we have to update the current slot */
-- 
cgit v1.2.3


From 79fac95ecfa3969aab8119d37ccd7226165f933a Mon Sep 17 00:00:00 2001
From: Marcelo Tosatti <mtosatti@redhat.com>
Date: Wed, 23 Dec 2009 14:35:26 -0200
Subject: KVM: convert slots_lock to a mutex

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/ia64/kvm/kvm-ia64.c  |  4 ++--
 arch/powerpc/kvm/book3s.c |  4 ++--
 arch/x86/kvm/i8254.c      |  2 +-
 arch/x86/kvm/i8259.c      |  4 ++--
 arch/x86/kvm/vmx.c        |  8 ++++----
 arch/x86/kvm/x86.c        | 16 ++++++++--------
 include/linux/kvm_host.h  |  2 +-
 virt/kvm/coalesced_mmio.c | 14 +++++++-------
 virt/kvm/eventfd.c        | 10 +++++-----
 virt/kvm/ioapic.c         |  4 ++--
 virt/kvm/kvm_main.c       | 10 +++++-----
 11 files changed, 39 insertions(+), 39 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index d5e38464127..e6ac549f8d5 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -1834,7 +1834,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 	struct kvm_memory_slot *memslot;
 	int is_dirty = 0;
 
-	down_write(&kvm->slots_lock);
+	mutex_lock(&kvm->slots_lock);
 	spin_lock(&kvm->arch.dirty_log_lock);
 
 	r = kvm_ia64_sync_dirty_log(kvm, log);
@@ -1854,7 +1854,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 	}
 	r = 0;
 out:
-	up_write(&kvm->slots_lock);
+	mutex_unlock(&kvm->slots_lock);
 	spin_unlock(&kvm->arch.dirty_log_lock);
 	return r;
 }
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index bb8873dcb20..492dcc198dd 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -857,7 +857,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 	int is_dirty = 0;
 	int r, n;
 
-	down_write(&kvm->slots_lock);
+	mutex_lock(&kvm->slots_lock);
 
 	r = kvm_get_dirty_log(kvm, log, &is_dirty);
 	if (r)
@@ -879,7 +879,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 
 	r = 0;
 out:
-	up_write(&kvm->slots_lock);
+	mutex_unlock(&kvm->slots_lock);
 	return r;
 }
 
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 4b433de02e5..6a74246f80c 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -605,7 +605,7 @@ static const struct kvm_io_device_ops speaker_dev_ops = {
 	.write    = speaker_ioport_write,
 };
 
-/* Caller must have writers lock on slots_lock */
+/* Caller must hold slots_lock */
 struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
 {
 	struct kvm_pit *pit;
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index b7d145b2095..d5753a75d58 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -533,9 +533,9 @@ struct kvm_pic *kvm_create_pic(struct kvm *kvm)
 	 * Initialize PIO device
 	 */
 	kvm_iodevice_init(&s->dev, &picdev_ops);
-	down_write(&kvm->slots_lock);
+	mutex_lock(&kvm->slots_lock);
 	ret = kvm_io_bus_register_dev(kvm, KVM_PIO_BUS, &s->dev);
-	up_write(&kvm->slots_lock);
+	mutex_unlock(&kvm->slots_lock);
 	if (ret < 0) {
 		kfree(s);
 		return NULL;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 22ab7137d1d..f04e2ff2138 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2223,7 +2223,7 @@ static int alloc_apic_access_page(struct kvm *kvm)
 	struct kvm_userspace_memory_region kvm_userspace_mem;
 	int r = 0;
 
-	down_write(&kvm->slots_lock);
+	mutex_lock(&kvm->slots_lock);
 	if (kvm->arch.apic_access_page)
 		goto out;
 	kvm_userspace_mem.slot = APIC_ACCESS_PAGE_PRIVATE_MEMSLOT;
@@ -2236,7 +2236,7 @@ static int alloc_apic_access_page(struct kvm *kvm)
 
 	kvm->arch.apic_access_page = gfn_to_page(kvm, 0xfee00);
 out:
-	up_write(&kvm->slots_lock);
+	mutex_unlock(&kvm->slots_lock);
 	return r;
 }
 
@@ -2245,7 +2245,7 @@ static int alloc_identity_pagetable(struct kvm *kvm)
 	struct kvm_userspace_memory_region kvm_userspace_mem;
 	int r = 0;
 
-	down_write(&kvm->slots_lock);
+	mutex_lock(&kvm->slots_lock);
 	if (kvm->arch.ept_identity_pagetable)
 		goto out;
 	kvm_userspace_mem.slot = IDENTITY_PAGETABLE_PRIVATE_MEMSLOT;
@@ -2260,7 +2260,7 @@ static int alloc_identity_pagetable(struct kvm *kvm)
 	kvm->arch.ept_identity_pagetable = gfn_to_page(kvm,
 			kvm->arch.ept_identity_map_addr >> PAGE_SHIFT);
 out:
-	up_write(&kvm->slots_lock);
+	mutex_unlock(&kvm->slots_lock);
 	return r;
 }
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 53bc06a6810..aff3479867a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2208,14 +2208,14 @@ static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm,
 	if (kvm_nr_mmu_pages < KVM_MIN_ALLOC_MMU_PAGES)
 		return -EINVAL;
 
-	down_write(&kvm->slots_lock);
+	mutex_lock(&kvm->slots_lock);
 	spin_lock(&kvm->mmu_lock);
 
 	kvm_mmu_change_mmu_pages(kvm, kvm_nr_mmu_pages);
 	kvm->arch.n_requested_mmu_pages = kvm_nr_mmu_pages;
 
 	spin_unlock(&kvm->mmu_lock);
-	up_write(&kvm->slots_lock);
+	mutex_unlock(&kvm->slots_lock);
 	return 0;
 }
 
@@ -2292,7 +2292,7 @@ static int kvm_vm_ioctl_set_memory_alias(struct kvm *kvm,
 	if (!aliases)
 		goto out;
 
-	down_write(&kvm->slots_lock);
+	mutex_lock(&kvm->slots_lock);
 
 	/* invalidate any gfn reference in case of deletion/shrinking */
 	memcpy(aliases, kvm->arch.aliases, sizeof(struct kvm_mem_aliases));
@@ -2328,7 +2328,7 @@ static int kvm_vm_ioctl_set_memory_alias(struct kvm *kvm,
 	r = 0;
 
 out_unlock:
-	up_write(&kvm->slots_lock);
+	mutex_unlock(&kvm->slots_lock);
 out:
 	return r;
 }
@@ -2462,7 +2462,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 	unsigned long is_dirty = 0;
 	unsigned long *dirty_bitmap = NULL;
 
-	down_write(&kvm->slots_lock);
+	mutex_lock(&kvm->slots_lock);
 
 	r = -EINVAL;
 	if (log->slot >= KVM_MEMORY_SLOTS)
@@ -2512,7 +2512,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 out_free:
 	vfree(dirty_bitmap);
 out:
-	up_write(&kvm->slots_lock);
+	mutex_unlock(&kvm->slots_lock);
 	return r;
 }
 
@@ -2625,7 +2625,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 				   sizeof(struct kvm_pit_config)))
 			goto out;
 	create_pit:
-		down_write(&kvm->slots_lock);
+		mutex_lock(&kvm->slots_lock);
 		r = -EEXIST;
 		if (kvm->arch.vpit)
 			goto create_pit_unlock;
@@ -2634,7 +2634,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		if (kvm->arch.vpit)
 			r = 0;
 	create_pit_unlock:
-		up_write(&kvm->slots_lock);
+		mutex_unlock(&kvm->slots_lock);
 		break;
 	case KVM_IRQ_LINE_STATUS:
 	case KVM_IRQ_LINE: {
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 0bb9aa295e6..bb0314ea926 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -161,7 +161,7 @@ struct kvm_memslots {
 struct kvm {
 	spinlock_t mmu_lock;
 	spinlock_t requests_lock;
-	struct rw_semaphore slots_lock;
+	struct mutex slots_lock;
 	struct mm_struct *mm; /* userspace tied to this vm */
 	struct kvm_memslots *memslots;
 	struct srcu_struct srcu;
diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c
index a736a93ca7b..5de6594260c 100644
--- a/virt/kvm/coalesced_mmio.c
+++ b/virt/kvm/coalesced_mmio.c
@@ -110,9 +110,9 @@ int kvm_coalesced_mmio_init(struct kvm *kvm)
 	dev->kvm = kvm;
 	kvm->coalesced_mmio_dev = dev;
 
-	down_write(&kvm->slots_lock);
+	mutex_lock(&kvm->slots_lock);
 	ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, &dev->dev);
-	up_write(&kvm->slots_lock);
+	mutex_unlock(&kvm->slots_lock);
 	if (ret < 0)
 		goto out_free_dev;
 
@@ -140,16 +140,16 @@ int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm,
 	if (dev == NULL)
 		return -EINVAL;
 
-	down_write(&kvm->slots_lock);
+	mutex_lock(&kvm->slots_lock);
 	if (dev->nb_zones >= KVM_COALESCED_MMIO_ZONE_MAX) {
-		up_write(&kvm->slots_lock);
+		mutex_unlock(&kvm->slots_lock);
 		return -ENOBUFS;
 	}
 
 	dev->zone[dev->nb_zones] = *zone;
 	dev->nb_zones++;
 
-	up_write(&kvm->slots_lock);
+	mutex_unlock(&kvm->slots_lock);
 	return 0;
 }
 
@@ -163,7 +163,7 @@ int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm,
 	if (dev == NULL)
 		return -EINVAL;
 
-	down_write(&kvm->slots_lock);
+	mutex_lock(&kvm->slots_lock);
 
 	i = dev->nb_zones;
 	while(i) {
@@ -181,7 +181,7 @@ int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm,
 		i--;
 	}
 
-	up_write(&kvm->slots_lock);
+	mutex_unlock(&kvm->slots_lock);
 
 	return 0;
 }
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 315a586ec4d..486c604365d 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -508,7 +508,7 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 	else
 		p->wildcard = true;
 
-	down_write(&kvm->slots_lock);
+	mutex_lock(&kvm->slots_lock);
 
 	/* Verify that there isnt a match already */
 	if (ioeventfd_check_collision(kvm, p)) {
@@ -524,12 +524,12 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 
 	list_add_tail(&p->list, &kvm->ioeventfds);
 
-	up_write(&kvm->slots_lock);
+	mutex_unlock(&kvm->slots_lock);
 
 	return 0;
 
 unlock_fail:
-	up_write(&kvm->slots_lock);
+	mutex_unlock(&kvm->slots_lock);
 
 fail:
 	kfree(p);
@@ -551,7 +551,7 @@ kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 	if (IS_ERR(eventfd))
 		return PTR_ERR(eventfd);
 
-	down_write(&kvm->slots_lock);
+	mutex_lock(&kvm->slots_lock);
 
 	list_for_each_entry_safe(p, tmp, &kvm->ioeventfds, list) {
 		bool wildcard = !(args->flags & KVM_IOEVENTFD_FLAG_DATAMATCH);
@@ -571,7 +571,7 @@ kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 		break;
 	}
 
-	up_write(&kvm->slots_lock);
+	mutex_unlock(&kvm->slots_lock);
 
 	eventfd_ctx_put(eventfd);
 
diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index f326a6f301c..f01392f51e8 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -372,9 +372,9 @@ int kvm_ioapic_init(struct kvm *kvm)
 	kvm_ioapic_reset(ioapic);
 	kvm_iodevice_init(&ioapic->dev, &ioapic_mmio_ops);
 	ioapic->kvm = kvm;
-	down_write(&kvm->slots_lock);
+	mutex_lock(&kvm->slots_lock);
 	ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, &ioapic->dev);
-	up_write(&kvm->slots_lock);
+	mutex_unlock(&kvm->slots_lock);
 	if (ret < 0)
 		kfree(ioapic);
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 659bc12ad16..2b7cd6c0d9c 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -429,7 +429,7 @@ static struct kvm *kvm_create_vm(void)
 	kvm_eventfd_init(kvm);
 	mutex_init(&kvm->lock);
 	mutex_init(&kvm->irq_lock);
-	init_rwsem(&kvm->slots_lock);
+	mutex_init(&kvm->slots_lock);
 	atomic_set(&kvm->users_count, 1);
 	spin_lock(&kvm_lock);
 	list_add(&kvm->vm_list, &vm_list);
@@ -763,9 +763,9 @@ int kvm_set_memory_region(struct kvm *kvm,
 {
 	int r;
 
-	down_write(&kvm->slots_lock);
+	mutex_lock(&kvm->slots_lock);
 	r = __kvm_set_memory_region(kvm, mem, user_alloc);
-	up_write(&kvm->slots_lock);
+	mutex_unlock(&kvm->slots_lock);
 	return r;
 }
 EXPORT_SYMBOL_GPL(kvm_set_memory_region);
@@ -1997,7 +1997,7 @@ int kvm_io_bus_read(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 	return -EOPNOTSUPP;
 }
 
-/* Caller must have write lock on slots_lock. */
+/* Caller must hold slots_lock. */
 int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 			    struct kvm_io_device *dev)
 {
@@ -2019,7 +2019,7 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 	return 0;
 }
 
-/* Caller must have write lock on slots_lock. */
+/* Caller must hold slots_lock. */
 int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 			      struct kvm_io_device *dev)
 {
-- 
cgit v1.2.3


From b480f780f071a068810ccd0e49c1daa210bfbeab Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Mon, 4 Jan 2010 22:19:22 +0100
Subject: KVM: PPC: Fix typo in rebolting code

When we're loading bolted entries into the SLB again, we're checking if an
entry is in use and only slbmte it when it is.

Unfortunately, the check always goes to the skip label of the first entry,
resulting in an endless loop when it actually gets triggered.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/powerpc/kvm/book3s_64_slb.S | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/book3s_64_slb.S b/arch/powerpc/kvm/book3s_64_slb.S
index ecd237a03fd..8e447886666 100644
--- a/arch/powerpc/kvm/book3s_64_slb.S
+++ b/arch/powerpc/kvm/book3s_64_slb.S
@@ -31,7 +31,7 @@
 #define REBOLT_SLB_ENTRY(num) \
 	ld	r10, SHADOW_SLB_ESID(num)(r11); \
 	cmpdi	r10, 0; \
-	beq	slb_exit_skip_1; \
+	beq	slb_exit_skip_ ## num; \
 	oris	r10, r10, SLB_ESID_V@h; \
 	ld	r9, SHADOW_SLB_VSID(num)(r11); \
 	slbmte	r9, r10; \
-- 
cgit v1.2.3


From 97c4cfbe890a4ad82dde8660008d42b7b05dc488 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Mon, 4 Jan 2010 22:19:25 +0100
Subject: KVM: PPC: Enable lightweight exits again

The PowerPC C ABI defines that registers r14-r31 need to be preserved across
function calls. Since our exit handler is written in C, we can make use of that
and don't need to reload r14-r31 on every entry/exit cycle.

This technique is also used in the BookE code and is called "lightweight exits"
there. To follow the tradition, it's called the same in Book3S.

So far this optimization was disabled though, as the code didn't do what it was
expected to do, but failed to work.

This patch fixes and enables lightweight exits again.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/powerpc/kvm/book3s.c               |   4 +-
 arch/powerpc/kvm/book3s_64_interrupts.S | 106 +++++++++++++++++---------------
 2 files changed, 57 insertions(+), 53 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 492dcc198dd..fd2a4d53158 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -539,8 +539,6 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		r = kvmppc_emulate_mmio(run, vcpu);
 		if ( r == RESUME_HOST_NV )
 			r = RESUME_HOST;
-		if ( r == RESUME_GUEST_NV )
-			r = RESUME_GUEST;
 	}
 
 	return r;
@@ -645,7 +643,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		er = kvmppc_emulate_instruction(run, vcpu);
 		switch (er) {
 		case EMULATE_DONE:
-			r = RESUME_GUEST;
+			r = RESUME_GUEST_NV;
 			break;
 		case EMULATE_FAIL:
 			printk(KERN_CRIT "%s: emulation at %lx failed (%08x)\n",
diff --git a/arch/powerpc/kvm/book3s_64_interrupts.S b/arch/powerpc/kvm/book3s_64_interrupts.S
index 7b55d8094c8..d95d0d967d5 100644
--- a/arch/powerpc/kvm/book3s_64_interrupts.S
+++ b/arch/powerpc/kvm/book3s_64_interrupts.S
@@ -40,6 +40,26 @@
        mtmsrd  r0,1
 .endm
 
+#define VCPU_LOAD_NVGPRS(vcpu) \
+	ld	r14, VCPU_GPR(r14)(vcpu); \
+	ld	r15, VCPU_GPR(r15)(vcpu); \
+	ld	r16, VCPU_GPR(r16)(vcpu); \
+	ld	r17, VCPU_GPR(r17)(vcpu); \
+	ld	r18, VCPU_GPR(r18)(vcpu); \
+	ld	r19, VCPU_GPR(r19)(vcpu); \
+	ld	r20, VCPU_GPR(r20)(vcpu); \
+	ld	r21, VCPU_GPR(r21)(vcpu); \
+	ld	r22, VCPU_GPR(r22)(vcpu); \
+	ld	r23, VCPU_GPR(r23)(vcpu); \
+	ld	r24, VCPU_GPR(r24)(vcpu); \
+	ld	r25, VCPU_GPR(r25)(vcpu); \
+	ld	r26, VCPU_GPR(r26)(vcpu); \
+	ld	r27, VCPU_GPR(r27)(vcpu); \
+	ld	r28, VCPU_GPR(r28)(vcpu); \
+	ld	r29, VCPU_GPR(r29)(vcpu); \
+	ld	r30, VCPU_GPR(r30)(vcpu); \
+	ld	r31, VCPU_GPR(r31)(vcpu); \
+
 /*****************************************************************************
  *                                                                           *
  *     Guest entry / exit code that is in kernel module memory (highmem)     *
@@ -67,12 +87,16 @@ kvm_start_entry:
 	SAVE_NVGPRS(r1)
 
 	/* Save LR */
-	mflr	r14
-	std	r14, _LINK(r1)
+	std	r0, _LINK(r1)
+
+	/* Load non-volatile guest state from the vcpu */
+	VCPU_LOAD_NVGPRS(r4)
 
-/* XXX optimize non-volatile loading away */
 kvm_start_lightweight:
 
+	ld	r9, VCPU_PC(r4)			/* r9 = vcpu->arch.pc */
+	ld	r10, VCPU_SHADOW_MSR(r4)	/* r10 = vcpu->arch.shadow_msr */
+
 	DISABLE_INTERRUPTS
 
 	/* Save R1/R2 in the PACA */
@@ -81,29 +105,6 @@ kvm_start_lightweight:
 	ld	r3, VCPU_HIGHMEM_HANDLER(r4)
 	std	r3, PACASAVEDMSR(r13)
 
-	/* Load non-volatile guest state from the vcpu */
-	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)
-
-	ld	r9, VCPU_PC(r4)			/* r9 = vcpu->arch.pc */
-	ld	r10, VCPU_SHADOW_MSR(r4)	/* r10 = vcpu->arch.shadow_msr */
-
 	ld	r3, VCPU_TRAMPOLINE_ENTER(r4)
 	mtsrr0	r3
 
@@ -247,7 +248,6 @@ kvmppc_handler_highmem:
 
 no_dcbz32_off:
 
-	/* XXX maybe skip on lightweight? */
 	std	r14, VCPU_GPR(r14)(r12)
 	std	r15, VCPU_GPR(r15)(r12)
 	std	r16, VCPU_GPR(r16)(r12)
@@ -267,9 +267,6 @@ no_dcbz32_off:
 	std	r30, VCPU_GPR(r30)(r12)
 	std	r31, VCPU_GPR(r31)(r12)
 
-	/* Restore non-volatile host registers (r14 - r31) */
-	REST_NVGPRS(r1)
-
 	/* Save guest PC (R10) */
 	std	r10, VCPU_PC(r12)
 
@@ -351,42 +348,51 @@ kvm_return_point:
 
 	/* Jump back to lightweight entry if we're supposed to */
 	/* go back into the guest */
+
+	/* Pass the exit number as 3rd argument to kvmppc_handle_exit */
 	mr	r5, r3
+
 	/* Restore r3 (kvm_run) and r4 (vcpu) */
 	REST_2GPRS(3, r1)
 	bl	KVMPPC_HANDLE_EXIT
 
-#if 0 /* XXX get lightweight exits back */
+	/* If RESUME_GUEST, get back in the loop */
 	cmpwi	r3, RESUME_GUEST
-	bne	kvm_exit_heavyweight
+	beq	kvm_loop_lightweight
 
-	/* put VCPU and KVM_RUN back into place and roll again! */
-	REST_2GPRS(3, r1)
-	b	kvm_start_lightweight
+	cmpwi	r3, RESUME_GUEST_NV
+	beq	kvm_loop_heavyweight
 
-kvm_exit_heavyweight:
-	/* Restore non-volatile host registers */
-	ld	r14, _LINK(r1)
-	mtlr	r14
-	REST_NVGPRS(r1)
+kvm_exit_loop:
 
-	addi    r1, r1, SWITCH_FRAME_SIZE
-#else
 	ld	r4, _LINK(r1)
 	mtlr	r4
 
-	cmpwi	r3, RESUME_GUEST
-	bne	kvm_exit_heavyweight
+	/* Restore non-volatile host registers (r14 - r31) */
+	REST_NVGPRS(r1)
+
+	addi    r1, r1, SWITCH_FRAME_SIZE
+	blr
+
+kvm_loop_heavyweight:
 
+	ld	r4, _LINK(r1)
+	std     r4, (16 + SWITCH_FRAME_SIZE)(r1)
+
+	/* Load vcpu and cpu_run */
 	REST_2GPRS(3, r1)
 
-	addi    r1, r1, SWITCH_FRAME_SIZE
+	/* Load non-volatile guest state from the vcpu */
+	VCPU_LOAD_NVGPRS(r4)
 
-	b	kvm_start_entry
+	/* Jump back into the beginning of this function */
+	b	kvm_start_lightweight
 
-kvm_exit_heavyweight:
+kvm_loop_lightweight:
 
-	addi    r1, r1, SWITCH_FRAME_SIZE
-#endif
+	/* We'll need the vcpu pointer */
+	REST_GPR(4, r1)
+
+	/* Jump back into the beginning of this function */
+	b	kvm_start_lightweight
 
-	blr
-- 
cgit v1.2.3


From 8e5b26b55a8b6aee2c789b1d20ec715f9e4bea5c Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 8 Jan 2010 02:58:01 +0100
Subject: KVM: PPC: Use accessor functions for GPR access

All code in PPC KVM currently accesses gprs in the vcpu struct directly.

While there's nothing wrong with that wrt the current way gprs are stored
and loaded, it doesn't suffice for the PACA acceleration that will follow
in this patchset.

So let's just create little wrapper inline functions that we call whenever
a GPR needs to be read from or written to. The compiled code shouldn't really
change at all for now.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_ppc.h   |  26 +++++++++
 arch/powerpc/kvm/44x_emulate.c       |  25 ++++----
 arch/powerpc/kvm/44x_tlb.c           |  14 ++---
 arch/powerpc/kvm/book3s.c            |   8 +--
 arch/powerpc/kvm/book3s_64_emulate.c |  77 +++++++++++++------------
 arch/powerpc/kvm/booke.c             |  16 +++---
 arch/powerpc/kvm/booke_emulate.c     | 107 ++++++++++++++++++-----------------
 arch/powerpc/kvm/e500_emulate.c      |  95 +++++++++++++++++--------------
 arch/powerpc/kvm/e500_tlb.c          |   4 +-
 arch/powerpc/kvm/emulate.c           | 106 ++++++++++++++++++----------------
 arch/powerpc/kvm/powerpc.c           |  21 +++----
 11 files changed, 274 insertions(+), 225 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index abfd0c4d567..ba01b9c1d38 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -96,4 +96,30 @@ extern void kvmppc_booke_exit(void);
 
 extern void kvmppc_core_destroy_mmu(struct kvm_vcpu *vcpu);
 
+#ifdef CONFIG_PPC_BOOK3S
+
+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];
+}
+
+#else
+
+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];
+}
+
+#endif
+
 #endif /* __POWERPC_KVM_PPC_H__ */
diff --git a/arch/powerpc/kvm/44x_emulate.c b/arch/powerpc/kvm/44x_emulate.c
index 61af58fcece..65ea083a5b2 100644
--- a/arch/powerpc/kvm/44x_emulate.c
+++ b/arch/powerpc/kvm/44x_emulate.c
@@ -65,13 +65,14 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			 */
 			switch (dcrn) {
 			case DCRN_CPR0_CONFIG_ADDR:
-				vcpu->arch.gpr[rt] = vcpu->arch.cpr0_cfgaddr;
+				kvmppc_set_gpr(vcpu, rt, vcpu->arch.cpr0_cfgaddr);
 				break;
 			case DCRN_CPR0_CONFIG_DATA:
 				local_irq_disable();
 				mtdcr(DCRN_CPR0_CONFIG_ADDR,
 					  vcpu->arch.cpr0_cfgaddr);
-				vcpu->arch.gpr[rt] = mfdcr(DCRN_CPR0_CONFIG_DATA);
+				kvmppc_set_gpr(vcpu, rt,
+					       mfdcr(DCRN_CPR0_CONFIG_DATA));
 				local_irq_enable();
 				break;
 			default:
@@ -93,11 +94,11 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			/* emulate some access in kernel */
 			switch (dcrn) {
 			case DCRN_CPR0_CONFIG_ADDR:
-				vcpu->arch.cpr0_cfgaddr = vcpu->arch.gpr[rs];
+				vcpu->arch.cpr0_cfgaddr = kvmppc_get_gpr(vcpu, rs);
 				break;
 			default:
 				run->dcr.dcrn = dcrn;
-				run->dcr.data = vcpu->arch.gpr[rs];
+				run->dcr.data = kvmppc_get_gpr(vcpu, rs);
 				run->dcr.is_write = 1;
 				vcpu->arch.dcr_needed = 1;
 				kvmppc_account_exit(vcpu, DCR_EXITS);
@@ -146,13 +147,13 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 
 	switch (sprn) {
 	case SPRN_PID:
-		kvmppc_set_pid(vcpu, vcpu->arch.gpr[rs]); break;
+		kvmppc_set_pid(vcpu, kvmppc_get_gpr(vcpu, rs)); break;
 	case SPRN_MMUCR:
-		vcpu->arch.mmucr = vcpu->arch.gpr[rs]; break;
+		vcpu->arch.mmucr = kvmppc_get_gpr(vcpu, rs); break;
 	case SPRN_CCR0:
-		vcpu->arch.ccr0 = vcpu->arch.gpr[rs]; break;
+		vcpu->arch.ccr0 = kvmppc_get_gpr(vcpu, rs); break;
 	case SPRN_CCR1:
-		vcpu->arch.ccr1 = vcpu->arch.gpr[rs]; break;
+		vcpu->arch.ccr1 = kvmppc_get_gpr(vcpu, rs); break;
 	default:
 		emulated = kvmppc_booke_emulate_mtspr(vcpu, sprn, rs);
 	}
@@ -167,13 +168,13 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 
 	switch (sprn) {
 	case SPRN_PID:
-		vcpu->arch.gpr[rt] = vcpu->arch.pid; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.pid); break;
 	case SPRN_MMUCR:
-		vcpu->arch.gpr[rt] = vcpu->arch.mmucr; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.mmucr); break;
 	case SPRN_CCR0:
-		vcpu->arch.gpr[rt] = vcpu->arch.ccr0; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ccr0); break;
 	case SPRN_CCR1:
-		vcpu->arch.gpr[rt] = vcpu->arch.ccr1; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ccr1); break;
 	default:
 		emulated = kvmppc_booke_emulate_mfspr(vcpu, sprn, rt);
 	}
diff --git a/arch/powerpc/kvm/44x_tlb.c b/arch/powerpc/kvm/44x_tlb.c
index ff3cb63b811..8b3773669c9 100644
--- a/arch/powerpc/kvm/44x_tlb.c
+++ b/arch/powerpc/kvm/44x_tlb.c
@@ -439,7 +439,7 @@ int kvmppc_44x_emul_tlbwe(struct kvm_vcpu *vcpu, u8 ra, u8 rs, u8 ws)
 	struct kvmppc_44x_tlbe *tlbe;
 	unsigned int gtlb_index;
 
-	gtlb_index = vcpu->arch.gpr[ra];
+	gtlb_index = kvmppc_get_gpr(vcpu, ra);
 	if (gtlb_index > KVM44x_GUEST_TLB_SIZE) {
 		printk("%s: index %d\n", __func__, gtlb_index);
 		kvmppc_dump_vcpu(vcpu);
@@ -455,15 +455,15 @@ int kvmppc_44x_emul_tlbwe(struct kvm_vcpu *vcpu, u8 ra, u8 rs, u8 ws)
 	switch (ws) {
 	case PPC44x_TLB_PAGEID:
 		tlbe->tid = get_mmucr_stid(vcpu);
-		tlbe->word0 = vcpu->arch.gpr[rs];
+		tlbe->word0 = kvmppc_get_gpr(vcpu, rs);
 		break;
 
 	case PPC44x_TLB_XLAT:
-		tlbe->word1 = vcpu->arch.gpr[rs];
+		tlbe->word1 = kvmppc_get_gpr(vcpu, rs);
 		break;
 
 	case PPC44x_TLB_ATTRIB:
-		tlbe->word2 = vcpu->arch.gpr[rs];
+		tlbe->word2 = kvmppc_get_gpr(vcpu, rs);
 		break;
 
 	default:
@@ -500,9 +500,9 @@ int kvmppc_44x_emul_tlbsx(struct kvm_vcpu *vcpu, u8 rt, u8 ra, u8 rb, u8 rc)
 	unsigned int as = get_mmucr_sts(vcpu);
 	unsigned int pid = get_mmucr_stid(vcpu);
 
-	ea = vcpu->arch.gpr[rb];
+	ea = kvmppc_get_gpr(vcpu, rb);
 	if (ra)
-		ea += vcpu->arch.gpr[ra];
+		ea += kvmppc_get_gpr(vcpu, ra);
 
 	gtlb_index = kvmppc_44x_tlb_index(vcpu, ea, pid, as);
 	if (rc) {
@@ -511,7 +511,7 @@ int kvmppc_44x_emul_tlbsx(struct kvm_vcpu *vcpu, u8 rt, u8 ra, u8 rb, u8 rc)
 		else
 			vcpu->arch.cr |= 0x20000000;
 	}
-	vcpu->arch.gpr[rt] = gtlb_index;
+	kvmppc_set_gpr(vcpu, rt, gtlb_index);
 
 	kvmppc_set_exit_type(vcpu, EMULATED_TLBSX_EXITS);
 	return EMULATE_DONE;
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index fd2a4d53158..574b24fb6e0 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -658,7 +658,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	}
 	case BOOK3S_INTERRUPT_SYSCALL:
 #ifdef EXIT_DEBUG
-		printk(KERN_INFO "Syscall Nr %d\n", (int)vcpu->arch.gpr[0]);
+		printk(KERN_INFO "Syscall Nr %d\n", (int)kvmppc_get_gpr(vcpu, 0));
 #endif
 		vcpu->stat.syscall_exits++;
 		kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
@@ -734,7 +734,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	regs->sprg7 = vcpu->arch.sprg6;
 
 	for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
-		regs->gpr[i] = vcpu->arch.gpr[i];
+		regs->gpr[i] = kvmppc_get_gpr(vcpu, i);
 
 	return 0;
 }
@@ -759,8 +759,8 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	vcpu->arch.sprg6 = regs->sprg5;
 	vcpu->arch.sprg7 = regs->sprg6;
 
-	for (i = 0; i < ARRAY_SIZE(vcpu->arch.gpr); i++)
-		vcpu->arch.gpr[i] = regs->gpr[i];
+	for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
+		kvmppc_set_gpr(vcpu, i, regs->gpr[i]);
 
 	return 0;
 }
diff --git a/arch/powerpc/kvm/book3s_64_emulate.c b/arch/powerpc/kvm/book3s_64_emulate.c
index 1027eac6d47..2b0ee7e040c 100644
--- a/arch/powerpc/kvm/book3s_64_emulate.c
+++ b/arch/powerpc/kvm/book3s_64_emulate.c
@@ -65,11 +65,11 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	case 31:
 		switch (get_xop(inst)) {
 		case OP_31_XOP_MFMSR:
-			vcpu->arch.gpr[get_rt(inst)] = vcpu->arch.msr;
+			kvmppc_set_gpr(vcpu, get_rt(inst), vcpu->arch.msr);
 			break;
 		case OP_31_XOP_MTMSRD:
 		{
-			ulong rs = vcpu->arch.gpr[get_rs(inst)];
+			ulong rs = kvmppc_get_gpr(vcpu, get_rs(inst));
 			if (inst & 0x10000) {
 				vcpu->arch.msr &= ~(MSR_RI | MSR_EE);
 				vcpu->arch.msr |= rs & (MSR_RI | MSR_EE);
@@ -78,30 +78,30 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			break;
 		}
 		case OP_31_XOP_MTMSR:
-			kvmppc_set_msr(vcpu, vcpu->arch.gpr[get_rs(inst)]);
+			kvmppc_set_msr(vcpu, kvmppc_get_gpr(vcpu, get_rs(inst)));
 			break;
 		case OP_31_XOP_MFSRIN:
 		{
 			int srnum;
 
-			srnum = (vcpu->arch.gpr[get_rb(inst)] >> 28) & 0xf;
+			srnum = (kvmppc_get_gpr(vcpu, get_rb(inst)) >> 28) & 0xf;
 			if (vcpu->arch.mmu.mfsrin) {
 				u32 sr;
 				sr = vcpu->arch.mmu.mfsrin(vcpu, srnum);
-				vcpu->arch.gpr[get_rt(inst)] = sr;
+				kvmppc_set_gpr(vcpu, get_rt(inst), sr);
 			}
 			break;
 		}
 		case OP_31_XOP_MTSRIN:
 			vcpu->arch.mmu.mtsrin(vcpu,
-				(vcpu->arch.gpr[get_rb(inst)] >> 28) & 0xf,
-				vcpu->arch.gpr[get_rs(inst)]);
+				(kvmppc_get_gpr(vcpu, get_rb(inst)) >> 28) & 0xf,
+				kvmppc_get_gpr(vcpu, get_rs(inst)));
 			break;
 		case OP_31_XOP_TLBIE:
 		case OP_31_XOP_TLBIEL:
 		{
 			bool large = (inst & 0x00200000) ? true : false;
-			ulong addr = vcpu->arch.gpr[get_rb(inst)];
+			ulong addr = kvmppc_get_gpr(vcpu, get_rb(inst));
 			vcpu->arch.mmu.tlbie(vcpu, addr, large);
 			break;
 		}
@@ -111,14 +111,16 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			if (!vcpu->arch.mmu.slbmte)
 				return EMULATE_FAIL;
 
-			vcpu->arch.mmu.slbmte(vcpu, vcpu->arch.gpr[get_rs(inst)],
-						vcpu->arch.gpr[get_rb(inst)]);
+			vcpu->arch.mmu.slbmte(vcpu,
+					kvmppc_get_gpr(vcpu, get_rs(inst)),
+					kvmppc_get_gpr(vcpu, get_rb(inst)));
 			break;
 		case OP_31_XOP_SLBIE:
 			if (!vcpu->arch.mmu.slbie)
 				return EMULATE_FAIL;
 
-			vcpu->arch.mmu.slbie(vcpu, vcpu->arch.gpr[get_rb(inst)]);
+			vcpu->arch.mmu.slbie(vcpu,
+					kvmppc_get_gpr(vcpu, get_rb(inst)));
 			break;
 		case OP_31_XOP_SLBIA:
 			if (!vcpu->arch.mmu.slbia)
@@ -132,9 +134,9 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			} else {
 				ulong t, rb;
 
-				rb = vcpu->arch.gpr[get_rb(inst)];
+				rb = kvmppc_get_gpr(vcpu, get_rb(inst));
 				t = vcpu->arch.mmu.slbmfee(vcpu, rb);
-				vcpu->arch.gpr[get_rt(inst)] = t;
+				kvmppc_set_gpr(vcpu, get_rt(inst), t);
 			}
 			break;
 		case OP_31_XOP_SLBMFEV:
@@ -143,20 +145,20 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			} else {
 				ulong t, rb;
 
-				rb = vcpu->arch.gpr[get_rb(inst)];
+				rb = kvmppc_get_gpr(vcpu, get_rb(inst));
 				t = vcpu->arch.mmu.slbmfev(vcpu, rb);
-				vcpu->arch.gpr[get_rt(inst)] = t;
+				kvmppc_set_gpr(vcpu, get_rt(inst), t);
 			}
 			break;
 		case OP_31_XOP_DCBZ:
 		{
-			ulong rb =  vcpu->arch.gpr[get_rb(inst)];
+			ulong rb = kvmppc_get_gpr(vcpu, get_rb(inst));
 			ulong ra = 0;
 			ulong addr;
 			u32 zeros[8] = { 0, 0, 0, 0, 0, 0, 0, 0 };
 
 			if (get_ra(inst))
-				ra = vcpu->arch.gpr[get_ra(inst)];
+				ra = kvmppc_get_gpr(vcpu, get_ra(inst));
 
 			addr = (ra + rb) & ~31ULL;
 			if (!(vcpu->arch.msr & MSR_SF))
@@ -233,43 +235,44 @@ static void kvmppc_write_bat(struct kvm_vcpu *vcpu, int sprn, u32 val)
 int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 {
 	int emulated = EMULATE_DONE;
+	ulong spr_val = kvmppc_get_gpr(vcpu, rs);
 
 	switch (sprn) {
 	case SPRN_SDR1:
-		to_book3s(vcpu)->sdr1 = vcpu->arch.gpr[rs];
+		to_book3s(vcpu)->sdr1 = spr_val;
 		break;
 	case SPRN_DSISR:
-		to_book3s(vcpu)->dsisr = vcpu->arch.gpr[rs];
+		to_book3s(vcpu)->dsisr = spr_val;
 		break;
 	case SPRN_DAR:
-		vcpu->arch.dear = vcpu->arch.gpr[rs];
+		vcpu->arch.dear = spr_val;
 		break;
 	case SPRN_HIOR:
-		to_book3s(vcpu)->hior = vcpu->arch.gpr[rs];
+		to_book3s(vcpu)->hior = spr_val;
 		break;
 	case SPRN_IBAT0U ... SPRN_IBAT3L:
 	case SPRN_IBAT4U ... SPRN_IBAT7L:
 	case SPRN_DBAT0U ... SPRN_DBAT3L:
 	case SPRN_DBAT4U ... SPRN_DBAT7L:
-		kvmppc_write_bat(vcpu, sprn, (u32)vcpu->arch.gpr[rs]);
+		kvmppc_write_bat(vcpu, sprn, (u32)spr_val);
 		/* BAT writes happen so rarely that we're ok to flush
 		 * everything here */
 		kvmppc_mmu_pte_flush(vcpu, 0, 0);
 		break;
 	case SPRN_HID0:
-		to_book3s(vcpu)->hid[0] = vcpu->arch.gpr[rs];
+		to_book3s(vcpu)->hid[0] = spr_val;
 		break;
 	case SPRN_HID1:
-		to_book3s(vcpu)->hid[1] = vcpu->arch.gpr[rs];
+		to_book3s(vcpu)->hid[1] = spr_val;
 		break;
 	case SPRN_HID2:
-		to_book3s(vcpu)->hid[2] = vcpu->arch.gpr[rs];
+		to_book3s(vcpu)->hid[2] = spr_val;
 		break;
 	case SPRN_HID4:
-		to_book3s(vcpu)->hid[4] = vcpu->arch.gpr[rs];
+		to_book3s(vcpu)->hid[4] = spr_val;
 		break;
 	case SPRN_HID5:
-		to_book3s(vcpu)->hid[5] = vcpu->arch.gpr[rs];
+		to_book3s(vcpu)->hid[5] = spr_val;
 		/* guest HID5 set can change is_dcbz32 */
 		if (vcpu->arch.mmu.is_dcbz32(vcpu) &&
 		    (mfmsr() & MSR_HV))
@@ -299,38 +302,38 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 
 	switch (sprn) {
 	case SPRN_SDR1:
-		vcpu->arch.gpr[rt] = to_book3s(vcpu)->sdr1;
+		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->sdr1);
 		break;
 	case SPRN_DSISR:
-		vcpu->arch.gpr[rt] = to_book3s(vcpu)->dsisr;
+		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->dsisr);
 		break;
 	case SPRN_DAR:
-		vcpu->arch.gpr[rt] = vcpu->arch.dear;
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.dear);
 		break;
 	case SPRN_HIOR:
-		vcpu->arch.gpr[rt] = to_book3s(vcpu)->hior;
+		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hior);
 		break;
 	case SPRN_HID0:
-		vcpu->arch.gpr[rt] = to_book3s(vcpu)->hid[0];
+		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[0]);
 		break;
 	case SPRN_HID1:
-		vcpu->arch.gpr[rt] = to_book3s(vcpu)->hid[1];
+		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[1]);
 		break;
 	case SPRN_HID2:
-		vcpu->arch.gpr[rt] = to_book3s(vcpu)->hid[2];
+		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[2]);
 		break;
 	case SPRN_HID4:
-		vcpu->arch.gpr[rt] = to_book3s(vcpu)->hid[4];
+		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[4]);
 		break;
 	case SPRN_HID5:
-		vcpu->arch.gpr[rt] = to_book3s(vcpu)->hid[5];
+		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hid[5]);
 		break;
 	case SPRN_THRM1:
 	case SPRN_THRM2:
 	case SPRN_THRM3:
 	case SPRN_CTRLF:
 	case SPRN_CTRLT:
-		vcpu->arch.gpr[rt] = 0;
+		kvmppc_set_gpr(vcpu, rt, 0);
 		break;
 	default:
 		printk(KERN_INFO "KVM: invalid SPR read: %d\n", sprn);
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index d8b63420acf..49af80e4a6e 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -69,10 +69,10 @@ void kvmppc_dump_vcpu(struct kvm_vcpu *vcpu)
 
 	for (i = 0; i < 32; i += 4) {
 		printk("gpr%02d: %08lx %08lx %08lx %08lx\n", i,
-		       vcpu->arch.gpr[i],
-		       vcpu->arch.gpr[i+1],
-		       vcpu->arch.gpr[i+2],
-		       vcpu->arch.gpr[i+3]);
+		       kvmppc_get_gpr(vcpu, i),
+		       kvmppc_get_gpr(vcpu, i+1),
+		       kvmppc_get_gpr(vcpu, i+2),
+		       kvmppc_get_gpr(vcpu, i+3));
 	}
 }
 
@@ -431,7 +431,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.pc = 0;
 	vcpu->arch.msr = 0;
-	vcpu->arch.gpr[1] = (16<<20) - 8; /* -8 for the callee-save LR slot */
+	kvmppc_set_gpr(vcpu, 1, (16<<20) - 8); /* -8 for the callee-save LR slot */
 
 	vcpu->arch.shadow_pid = 1;
 
@@ -466,7 +466,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	regs->sprg7 = vcpu->arch.sprg6;
 
 	for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
-		regs->gpr[i] = vcpu->arch.gpr[i];
+		regs->gpr[i] = kvmppc_get_gpr(vcpu, i);
 
 	return 0;
 }
@@ -491,8 +491,8 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	vcpu->arch.sprg6 = regs->sprg5;
 	vcpu->arch.sprg7 = regs->sprg6;
 
-	for (i = 0; i < ARRAY_SIZE(vcpu->arch.gpr); i++)
-		vcpu->arch.gpr[i] = regs->gpr[i];
+	for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
+		kvmppc_set_gpr(vcpu, i, regs->gpr[i]);
 
 	return 0;
 }
diff --git a/arch/powerpc/kvm/booke_emulate.c b/arch/powerpc/kvm/booke_emulate.c
index aebc65e93f4..cbc790ee192 100644
--- a/arch/powerpc/kvm/booke_emulate.c
+++ b/arch/powerpc/kvm/booke_emulate.c
@@ -62,20 +62,20 @@ int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 		case OP_31_XOP_MFMSR:
 			rt = get_rt(inst);
-			vcpu->arch.gpr[rt] = vcpu->arch.msr;
+			kvmppc_set_gpr(vcpu, rt, vcpu->arch.msr);
 			kvmppc_set_exit_type(vcpu, EMULATED_MFMSR_EXITS);
 			break;
 
 		case OP_31_XOP_MTMSR:
 			rs = get_rs(inst);
 			kvmppc_set_exit_type(vcpu, EMULATED_MTMSR_EXITS);
-			kvmppc_set_msr(vcpu, vcpu->arch.gpr[rs]);
+			kvmppc_set_msr(vcpu, kvmppc_get_gpr(vcpu, rs));
 			break;
 
 		case OP_31_XOP_WRTEE:
 			rs = get_rs(inst);
 			vcpu->arch.msr = (vcpu->arch.msr & ~MSR_EE)
-							 | (vcpu->arch.gpr[rs] & MSR_EE);
+					| (kvmppc_get_gpr(vcpu, rs) & MSR_EE);
 			kvmppc_set_exit_type(vcpu, EMULATED_WRTEE_EXITS);
 			break;
 
@@ -101,22 +101,23 @@ int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 {
 	int emulated = EMULATE_DONE;
+	ulong spr_val = kvmppc_get_gpr(vcpu, rs);
 
 	switch (sprn) {
 	case SPRN_DEAR:
-		vcpu->arch.dear = vcpu->arch.gpr[rs]; break;
+		vcpu->arch.dear = spr_val; break;
 	case SPRN_ESR:
-		vcpu->arch.esr = vcpu->arch.gpr[rs]; break;
+		vcpu->arch.esr = spr_val; break;
 	case SPRN_DBCR0:
-		vcpu->arch.dbcr0 = vcpu->arch.gpr[rs]; break;
+		vcpu->arch.dbcr0 = spr_val; break;
 	case SPRN_DBCR1:
-		vcpu->arch.dbcr1 = vcpu->arch.gpr[rs]; break;
+		vcpu->arch.dbcr1 = spr_val; break;
 	case SPRN_DBSR:
-		vcpu->arch.dbsr &= ~vcpu->arch.gpr[rs]; break;
+		vcpu->arch.dbsr &= ~spr_val; break;
 	case SPRN_TSR:
-		vcpu->arch.tsr &= ~vcpu->arch.gpr[rs]; break;
+		vcpu->arch.tsr &= ~spr_val; break;
 	case SPRN_TCR:
-		vcpu->arch.tcr = vcpu->arch.gpr[rs];
+		vcpu->arch.tcr = spr_val;
 		kvmppc_emulate_dec(vcpu);
 		break;
 
@@ -124,64 +125,64 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 	 * loaded into the real SPRGs when resuming the
 	 * guest. */
 	case SPRN_SPRG4:
-		vcpu->arch.sprg4 = vcpu->arch.gpr[rs]; break;
+		vcpu->arch.sprg4 = spr_val; break;
 	case SPRN_SPRG5:
-		vcpu->arch.sprg5 = vcpu->arch.gpr[rs]; break;
+		vcpu->arch.sprg5 = spr_val; break;
 	case SPRN_SPRG6:
-		vcpu->arch.sprg6 = vcpu->arch.gpr[rs]; break;
+		vcpu->arch.sprg6 = spr_val; break;
 	case SPRN_SPRG7:
-		vcpu->arch.sprg7 = vcpu->arch.gpr[rs]; break;
+		vcpu->arch.sprg7 = spr_val; break;
 
 	case SPRN_IVPR:
-		vcpu->arch.ivpr = vcpu->arch.gpr[rs];
+		vcpu->arch.ivpr = spr_val;
 		break;
 	case SPRN_IVOR0:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_CRITICAL] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_CRITICAL] = spr_val;
 		break;
 	case SPRN_IVOR1:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_MACHINE_CHECK] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_MACHINE_CHECK] = spr_val;
 		break;
 	case SPRN_IVOR2:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_DATA_STORAGE] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_DATA_STORAGE] = spr_val;
 		break;
 	case SPRN_IVOR3:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_INST_STORAGE] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_INST_STORAGE] = spr_val;
 		break;
 	case SPRN_IVOR4:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_EXTERNAL] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_EXTERNAL] = spr_val;
 		break;
 	case SPRN_IVOR5:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_ALIGNMENT] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_ALIGNMENT] = spr_val;
 		break;
 	case SPRN_IVOR6:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_PROGRAM] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_PROGRAM] = spr_val;
 		break;
 	case SPRN_IVOR7:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_FP_UNAVAIL] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_FP_UNAVAIL] = spr_val;
 		break;
 	case SPRN_IVOR8:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_SYSCALL] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_SYSCALL] = spr_val;
 		break;
 	case SPRN_IVOR9:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_AP_UNAVAIL] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_AP_UNAVAIL] = spr_val;
 		break;
 	case SPRN_IVOR10:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_DECREMENTER] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_DECREMENTER] = spr_val;
 		break;
 	case SPRN_IVOR11:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_FIT] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_FIT] = spr_val;
 		break;
 	case SPRN_IVOR12:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_WATCHDOG] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_WATCHDOG] = spr_val;
 		break;
 	case SPRN_IVOR13:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_DTLB_MISS] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_DTLB_MISS] = spr_val;
 		break;
 	case SPRN_IVOR14:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_ITLB_MISS] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_ITLB_MISS] = spr_val;
 		break;
 	case SPRN_IVOR15:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_DEBUG] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_DEBUG] = spr_val;
 		break;
 
 	default:
@@ -197,65 +198,65 @@ int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 
 	switch (sprn) {
 	case SPRN_IVPR:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivpr; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivpr); break;
 	case SPRN_DEAR:
-		vcpu->arch.gpr[rt] = vcpu->arch.dear; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.dear); break;
 	case SPRN_ESR:
-		vcpu->arch.gpr[rt] = vcpu->arch.esr; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.esr); break;
 	case SPRN_DBCR0:
-		vcpu->arch.gpr[rt] = vcpu->arch.dbcr0; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.dbcr0); break;
 	case SPRN_DBCR1:
-		vcpu->arch.gpr[rt] = vcpu->arch.dbcr1; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.dbcr1); break;
 	case SPRN_DBSR:
-		vcpu->arch.gpr[rt] = vcpu->arch.dbsr; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.dbsr); break;
 
 	case SPRN_IVOR0:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_CRITICAL];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_CRITICAL]);
 		break;
 	case SPRN_IVOR1:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_MACHINE_CHECK];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_MACHINE_CHECK]);
 		break;
 	case SPRN_IVOR2:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_DATA_STORAGE];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_DATA_STORAGE]);
 		break;
 	case SPRN_IVOR3:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_INST_STORAGE];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_INST_STORAGE]);
 		break;
 	case SPRN_IVOR4:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_EXTERNAL];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_EXTERNAL]);
 		break;
 	case SPRN_IVOR5:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_ALIGNMENT];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_ALIGNMENT]);
 		break;
 	case SPRN_IVOR6:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_PROGRAM];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_PROGRAM]);
 		break;
 	case SPRN_IVOR7:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_FP_UNAVAIL];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_FP_UNAVAIL]);
 		break;
 	case SPRN_IVOR8:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_SYSCALL];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_SYSCALL]);
 		break;
 	case SPRN_IVOR9:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_AP_UNAVAIL];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_AP_UNAVAIL]);
 		break;
 	case SPRN_IVOR10:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_DECREMENTER];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_DECREMENTER]);
 		break;
 	case SPRN_IVOR11:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_FIT];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_FIT]);
 		break;
 	case SPRN_IVOR12:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_WATCHDOG];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_WATCHDOG]);
 		break;
 	case SPRN_IVOR13:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_DTLB_MISS];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_DTLB_MISS]);
 		break;
 	case SPRN_IVOR14:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_ITLB_MISS];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_ITLB_MISS]);
 		break;
 	case SPRN_IVOR15:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_DEBUG];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_DEBUG]);
 		break;
 
 	default:
diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c
index be95b8d8e3b..7644f7a9bac 100644
--- a/arch/powerpc/kvm/e500_emulate.c
+++ b/arch/powerpc/kvm/e500_emulate.c
@@ -74,54 +74,55 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 	int emulated = EMULATE_DONE;
+	ulong spr_val = kvmppc_get_gpr(vcpu, rs);
 
 	switch (sprn) {
 	case SPRN_PID:
 		vcpu_e500->pid[0] = vcpu->arch.shadow_pid =
-			vcpu->arch.pid = vcpu->arch.gpr[rs];
+			vcpu->arch.pid = spr_val;
 		break;
 	case SPRN_PID1:
-		vcpu_e500->pid[1] = vcpu->arch.gpr[rs]; break;
+		vcpu_e500->pid[1] = spr_val; break;
 	case SPRN_PID2:
-		vcpu_e500->pid[2] = vcpu->arch.gpr[rs]; break;
+		vcpu_e500->pid[2] = spr_val; break;
 	case SPRN_MAS0:
-		vcpu_e500->mas0 = vcpu->arch.gpr[rs]; break;
+		vcpu_e500->mas0 = spr_val; break;
 	case SPRN_MAS1:
-		vcpu_e500->mas1 = vcpu->arch.gpr[rs]; break;
+		vcpu_e500->mas1 = spr_val; break;
 	case SPRN_MAS2:
-		vcpu_e500->mas2 = vcpu->arch.gpr[rs]; break;
+		vcpu_e500->mas2 = spr_val; break;
 	case SPRN_MAS3:
-		vcpu_e500->mas3 = vcpu->arch.gpr[rs]; break;
+		vcpu_e500->mas3 = spr_val; break;
 	case SPRN_MAS4:
-		vcpu_e500->mas4 = vcpu->arch.gpr[rs]; break;
+		vcpu_e500->mas4 = spr_val; break;
 	case SPRN_MAS6:
-		vcpu_e500->mas6 = vcpu->arch.gpr[rs]; break;
+		vcpu_e500->mas6 = spr_val; break;
 	case SPRN_MAS7:
-		vcpu_e500->mas7 = vcpu->arch.gpr[rs]; break;
+		vcpu_e500->mas7 = spr_val; break;
 	case SPRN_L1CSR1:
-		vcpu_e500->l1csr1 = vcpu->arch.gpr[rs]; break;
+		vcpu_e500->l1csr1 = spr_val; break;
 	case SPRN_HID0:
-		vcpu_e500->hid0 = vcpu->arch.gpr[rs]; break;
+		vcpu_e500->hid0 = spr_val; break;
 	case SPRN_HID1:
-		vcpu_e500->hid1 = vcpu->arch.gpr[rs]; break;
+		vcpu_e500->hid1 = spr_val; break;
 
 	case SPRN_MMUCSR0:
 		emulated = kvmppc_e500_emul_mt_mmucsr0(vcpu_e500,
-				vcpu->arch.gpr[rs]);
+				spr_val);
 		break;
 
 	/* extra exceptions */
 	case SPRN_IVOR32:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL] = spr_val;
 		break;
 	case SPRN_IVOR33:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_DATA] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_DATA] = spr_val;
 		break;
 	case SPRN_IVOR34:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND] = spr_val;
 		break;
 	case SPRN_IVOR35:
-		vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR] = vcpu->arch.gpr[rs];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR] = spr_val;
 		break;
 
 	default:
@@ -138,63 +139,71 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 
 	switch (sprn) {
 	case SPRN_PID:
-		vcpu->arch.gpr[rt] = vcpu_e500->pid[0]; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->pid[0]); break;
 	case SPRN_PID1:
-		vcpu->arch.gpr[rt] = vcpu_e500->pid[1]; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->pid[1]); break;
 	case SPRN_PID2:
-		vcpu->arch.gpr[rt] = vcpu_e500->pid[2]; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->pid[2]); break;
 	case SPRN_MAS0:
-		vcpu->arch.gpr[rt] = vcpu_e500->mas0; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas0); break;
 	case SPRN_MAS1:
-		vcpu->arch.gpr[rt] = vcpu_e500->mas1; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas1); break;
 	case SPRN_MAS2:
-		vcpu->arch.gpr[rt] = vcpu_e500->mas2; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas2); break;
 	case SPRN_MAS3:
-		vcpu->arch.gpr[rt] = vcpu_e500->mas3; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas3); break;
 	case SPRN_MAS4:
-		vcpu->arch.gpr[rt] = vcpu_e500->mas4; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas4); break;
 	case SPRN_MAS6:
-		vcpu->arch.gpr[rt] = vcpu_e500->mas6; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas6); break;
 	case SPRN_MAS7:
-		vcpu->arch.gpr[rt] = vcpu_e500->mas7; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas7); break;
 
 	case SPRN_TLB0CFG:
-		vcpu->arch.gpr[rt] = mfspr(SPRN_TLB0CFG);
-		vcpu->arch.gpr[rt] &= ~0xfffUL;
-		vcpu->arch.gpr[rt] |= vcpu_e500->guest_tlb_size[0];
+	{
+		ulong tmp = SPRN_TLB0CFG;
+
+		tmp &= ~0xfffUL;
+		tmp |= vcpu_e500->guest_tlb_size[0];
+		kvmppc_set_gpr(vcpu, rt, tmp);
 		break;
+	}
 
 	case SPRN_TLB1CFG:
-		vcpu->arch.gpr[rt] = mfspr(SPRN_TLB1CFG);
-		vcpu->arch.gpr[rt] &= ~0xfffUL;
-		vcpu->arch.gpr[rt] |= vcpu_e500->guest_tlb_size[1];
+	{
+		ulong tmp = SPRN_TLB1CFG;
+
+		tmp &= ~0xfffUL;
+		tmp |= vcpu_e500->guest_tlb_size[1];
+		kvmppc_set_gpr(vcpu, rt, tmp);
 		break;
+	}
 
 	case SPRN_L1CSR1:
-		vcpu->arch.gpr[rt] = vcpu_e500->l1csr1; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->l1csr1); break;
 	case SPRN_HID0:
-		vcpu->arch.gpr[rt] = vcpu_e500->hid0; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->hid0); break;
 	case SPRN_HID1:
-		vcpu->arch.gpr[rt] = vcpu_e500->hid1; break;
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->hid1); break;
 
 	case SPRN_MMUCSR0:
-		vcpu->arch.gpr[rt] = 0; break;
+		kvmppc_set_gpr(vcpu, rt, 0); break;
 
 	case SPRN_MMUCFG:
-		vcpu->arch.gpr[rt] = mfspr(SPRN_MMUCFG); break;
+		kvmppc_set_gpr(vcpu, rt, mfspr(SPRN_MMUCFG)); break;
 
 	/* extra exceptions */
 	case SPRN_IVOR32:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL]);
 		break;
 	case SPRN_IVOR33:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_DATA];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_DATA]);
 		break;
 	case SPRN_IVOR34:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND]);
 		break;
 	case SPRN_IVOR35:
-		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR];
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR]);
 		break;
 	default:
 		emulated = kvmppc_booke_emulate_mfspr(vcpu, sprn, rt);
diff --git a/arch/powerpc/kvm/e500_tlb.c b/arch/powerpc/kvm/e500_tlb.c
index fb1e1dc11ba..6a7fc012b93 100644
--- a/arch/powerpc/kvm/e500_tlb.c
+++ b/arch/powerpc/kvm/e500_tlb.c
@@ -417,7 +417,7 @@ int kvmppc_e500_emul_tlbivax(struct kvm_vcpu *vcpu, int ra, int rb)
 	int esel, tlbsel;
 	gva_t ea;
 
-	ea = ((ra) ? vcpu->arch.gpr[ra] : 0) + vcpu->arch.gpr[rb];
+	ea = ((ra) ? kvmppc_get_gpr(vcpu, ra) : 0) + kvmppc_get_gpr(vcpu, rb);
 
 	ia = (ea >> 2) & 0x1;
 
@@ -470,7 +470,7 @@ int kvmppc_e500_emul_tlbsx(struct kvm_vcpu *vcpu, int rb)
 	struct tlbe *gtlbe = NULL;
 	gva_t ea;
 
-	ea = vcpu->arch.gpr[rb];
+	ea = kvmppc_get_gpr(vcpu, rb);
 
 	for (tlbsel = 0; tlbsel < 2; tlbsel++) {
 		esel = kvmppc_e500_tlb_index(vcpu_e500, ea, tlbsel, pid, as);
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index 303457b2f52..38219af0cd0 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -170,14 +170,14 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		case OP_31_XOP_STWX:
 			rs = get_rs(inst);
 			emulated = kvmppc_handle_store(run, vcpu,
-			                               vcpu->arch.gpr[rs],
+						       kvmppc_get_gpr(vcpu, rs),
 			                               4, 1);
 			break;
 
 		case OP_31_XOP_STBX:
 			rs = get_rs(inst);
 			emulated = kvmppc_handle_store(run, vcpu,
-			                               vcpu->arch.gpr[rs],
+						       kvmppc_get_gpr(vcpu, rs),
 			                               1, 1);
 			break;
 
@@ -186,14 +186,14 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			ra = get_ra(inst);
 			rb = get_rb(inst);
 
-			ea = vcpu->arch.gpr[rb];
+			ea = kvmppc_get_gpr(vcpu, rb);
 			if (ra)
-				ea += vcpu->arch.gpr[ra];
+				ea += kvmppc_get_gpr(vcpu, ra);
 
 			emulated = kvmppc_handle_store(run, vcpu,
-			                               vcpu->arch.gpr[rs],
+						       kvmppc_get_gpr(vcpu, rs),
 			                               1, 1);
-			vcpu->arch.gpr[rs] = ea;
+			kvmppc_set_gpr(vcpu, rs, ea);
 			break;
 
 		case OP_31_XOP_LHZX:
@@ -206,12 +206,12 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			ra = get_ra(inst);
 			rb = get_rb(inst);
 
-			ea = vcpu->arch.gpr[rb];
+			ea = kvmppc_get_gpr(vcpu, rb);
 			if (ra)
-				ea += vcpu->arch.gpr[ra];
+				ea += kvmppc_get_gpr(vcpu, ra);
 
 			emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1);
-			vcpu->arch.gpr[ra] = ea;
+			kvmppc_set_gpr(vcpu, ra, ea);
 			break;
 
 		case OP_31_XOP_MFSPR:
@@ -220,47 +220,49 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 
 			switch (sprn) {
 			case SPRN_SRR0:
-				vcpu->arch.gpr[rt] = vcpu->arch.srr0; break;
+				kvmppc_set_gpr(vcpu, rt, vcpu->arch.srr0); break;
 			case SPRN_SRR1:
-				vcpu->arch.gpr[rt] = vcpu->arch.srr1; break;
+				kvmppc_set_gpr(vcpu, rt, vcpu->arch.srr1); break;
 			case SPRN_PVR:
-				vcpu->arch.gpr[rt] = vcpu->arch.pvr; break;
+				kvmppc_set_gpr(vcpu, rt, vcpu->arch.pvr); break;
 			case SPRN_PIR:
-				vcpu->arch.gpr[rt] = vcpu->vcpu_id; break;
+				kvmppc_set_gpr(vcpu, rt, vcpu->vcpu_id); break;
 			case SPRN_MSSSR0:
-				vcpu->arch.gpr[rt] = 0; break;
+				kvmppc_set_gpr(vcpu, rt, 0); break;
 
 			/* Note: mftb and TBRL/TBWL are user-accessible, so
 			 * the guest can always access the real TB anyways.
 			 * In fact, we probably will never see these traps. */
 			case SPRN_TBWL:
-				vcpu->arch.gpr[rt] = get_tb() >> 32; break;
+				kvmppc_set_gpr(vcpu, rt, get_tb() >> 32); break;
 			case SPRN_TBWU:
-				vcpu->arch.gpr[rt] = get_tb(); break;
+				kvmppc_set_gpr(vcpu, rt, get_tb()); break;
 
 			case SPRN_SPRG0:
-				vcpu->arch.gpr[rt] = vcpu->arch.sprg0; break;
+				kvmppc_set_gpr(vcpu, rt, vcpu->arch.sprg0); break;
 			case SPRN_SPRG1:
-				vcpu->arch.gpr[rt] = vcpu->arch.sprg1; break;
+				kvmppc_set_gpr(vcpu, rt, vcpu->arch.sprg1); break;
 			case SPRN_SPRG2:
-				vcpu->arch.gpr[rt] = vcpu->arch.sprg2; break;
+				kvmppc_set_gpr(vcpu, rt, vcpu->arch.sprg2); break;
 			case SPRN_SPRG3:
-				vcpu->arch.gpr[rt] = vcpu->arch.sprg3; break;
+				kvmppc_set_gpr(vcpu, rt, vcpu->arch.sprg3); break;
 			/* Note: SPRG4-7 are user-readable, so we don't get
 			 * a trap. */
 
 			case SPRN_DEC:
 			{
 				u64 jd = get_tb() - vcpu->arch.dec_jiffies;
-				vcpu->arch.gpr[rt] = vcpu->arch.dec - jd;
-				pr_debug(KERN_INFO "mfDEC: %x - %llx = %lx\n", vcpu->arch.dec, jd, vcpu->arch.gpr[rt]);
+				kvmppc_set_gpr(vcpu, rt, vcpu->arch.dec - jd);
+				pr_debug(KERN_INFO "mfDEC: %x - %llx = %lx\n",
+					 vcpu->arch.dec, jd,
+					 kvmppc_get_gpr(vcpu, rt));
 				break;
 			}
 			default:
 				emulated = kvmppc_core_emulate_mfspr(vcpu, sprn, rt);
 				if (emulated == EMULATE_FAIL) {
 					printk("mfspr: unknown spr %x\n", sprn);
-					vcpu->arch.gpr[rt] = 0;
+					kvmppc_set_gpr(vcpu, rt, 0);
 				}
 				break;
 			}
@@ -272,7 +274,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			rb = get_rb(inst);
 
 			emulated = kvmppc_handle_store(run, vcpu,
-			                               vcpu->arch.gpr[rs],
+						       kvmppc_get_gpr(vcpu, rs),
 			                               2, 1);
 			break;
 
@@ -281,14 +283,14 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			ra = get_ra(inst);
 			rb = get_rb(inst);
 
-			ea = vcpu->arch.gpr[rb];
+			ea = kvmppc_get_gpr(vcpu, rb);
 			if (ra)
-				ea += vcpu->arch.gpr[ra];
+				ea += kvmppc_get_gpr(vcpu, ra);
 
 			emulated = kvmppc_handle_store(run, vcpu,
-			                               vcpu->arch.gpr[rs],
+						       kvmppc_get_gpr(vcpu, rs),
 			                               2, 1);
-			vcpu->arch.gpr[ra] = ea;
+			kvmppc_set_gpr(vcpu, ra, ea);
 			break;
 
 		case OP_31_XOP_MTSPR:
@@ -296,9 +298,9 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			rs = get_rs(inst);
 			switch (sprn) {
 			case SPRN_SRR0:
-				vcpu->arch.srr0 = vcpu->arch.gpr[rs]; break;
+				vcpu->arch.srr0 = kvmppc_get_gpr(vcpu, rs); break;
 			case SPRN_SRR1:
-				vcpu->arch.srr1 = vcpu->arch.gpr[rs]; break;
+				vcpu->arch.srr1 = kvmppc_get_gpr(vcpu, rs); break;
 
 			/* XXX We need to context-switch the timebase for
 			 * watchdog and FIT. */
@@ -308,18 +310,18 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			case SPRN_MSSSR0: break;
 
 			case SPRN_DEC:
-				vcpu->arch.dec = vcpu->arch.gpr[rs];
+				vcpu->arch.dec = kvmppc_get_gpr(vcpu, rs);
 				kvmppc_emulate_dec(vcpu);
 				break;
 
 			case SPRN_SPRG0:
-				vcpu->arch.sprg0 = vcpu->arch.gpr[rs]; break;
+				vcpu->arch.sprg0 = kvmppc_get_gpr(vcpu, rs); break;
 			case SPRN_SPRG1:
-				vcpu->arch.sprg1 = vcpu->arch.gpr[rs]; break;
+				vcpu->arch.sprg1 = kvmppc_get_gpr(vcpu, rs); break;
 			case SPRN_SPRG2:
-				vcpu->arch.sprg2 = vcpu->arch.gpr[rs]; break;
+				vcpu->arch.sprg2 = kvmppc_get_gpr(vcpu, rs); break;
 			case SPRN_SPRG3:
-				vcpu->arch.sprg3 = vcpu->arch.gpr[rs]; break;
+				vcpu->arch.sprg3 = kvmppc_get_gpr(vcpu, rs); break;
 
 			default:
 				emulated = kvmppc_core_emulate_mtspr(vcpu, sprn, rs);
@@ -351,7 +353,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			rb = get_rb(inst);
 
 			emulated = kvmppc_handle_store(run, vcpu,
-			                               vcpu->arch.gpr[rs],
+						       kvmppc_get_gpr(vcpu, rs),
 			                               4, 0);
 			break;
 
@@ -366,7 +368,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			rb = get_rb(inst);
 
 			emulated = kvmppc_handle_store(run, vcpu,
-			                               vcpu->arch.gpr[rs],
+						       kvmppc_get_gpr(vcpu, rs),
 			                               2, 0);
 			break;
 
@@ -385,7 +387,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		ra = get_ra(inst);
 		rt = get_rt(inst);
 		emulated = kvmppc_handle_load(run, vcpu, rt, 4, 1);
-		vcpu->arch.gpr[ra] = vcpu->arch.paddr_accessed;
+		kvmppc_set_gpr(vcpu, ra, vcpu->arch.paddr_accessed);
 		break;
 
 	case OP_LBZ:
@@ -397,35 +399,39 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		ra = get_ra(inst);
 		rt = get_rt(inst);
 		emulated = kvmppc_handle_load(run, vcpu, rt, 1, 1);
-		vcpu->arch.gpr[ra] = vcpu->arch.paddr_accessed;
+		kvmppc_set_gpr(vcpu, ra, vcpu->arch.paddr_accessed);
 		break;
 
 	case OP_STW:
 		rs = get_rs(inst);
-		emulated = kvmppc_handle_store(run, vcpu, vcpu->arch.gpr[rs],
+		emulated = kvmppc_handle_store(run, vcpu,
+					       kvmppc_get_gpr(vcpu, rs),
 		                               4, 1);
 		break;
 
 	case OP_STWU:
 		ra = get_ra(inst);
 		rs = get_rs(inst);
-		emulated = kvmppc_handle_store(run, vcpu, vcpu->arch.gpr[rs],
+		emulated = kvmppc_handle_store(run, vcpu,
+					       kvmppc_get_gpr(vcpu, rs),
 		                               4, 1);
-		vcpu->arch.gpr[ra] = vcpu->arch.paddr_accessed;
+		kvmppc_set_gpr(vcpu, ra, vcpu->arch.paddr_accessed);
 		break;
 
 	case OP_STB:
 		rs = get_rs(inst);
-		emulated = kvmppc_handle_store(run, vcpu, vcpu->arch.gpr[rs],
+		emulated = kvmppc_handle_store(run, vcpu,
+					       kvmppc_get_gpr(vcpu, rs),
 		                               1, 1);
 		break;
 
 	case OP_STBU:
 		ra = get_ra(inst);
 		rs = get_rs(inst);
-		emulated = kvmppc_handle_store(run, vcpu, vcpu->arch.gpr[rs],
+		emulated = kvmppc_handle_store(run, vcpu,
+					       kvmppc_get_gpr(vcpu, rs),
 		                               1, 1);
-		vcpu->arch.gpr[ra] = vcpu->arch.paddr_accessed;
+		kvmppc_set_gpr(vcpu, ra, vcpu->arch.paddr_accessed);
 		break;
 
 	case OP_LHZ:
@@ -437,21 +443,23 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		ra = get_ra(inst);
 		rt = get_rt(inst);
 		emulated = kvmppc_handle_load(run, vcpu, rt, 2, 1);
-		vcpu->arch.gpr[ra] = vcpu->arch.paddr_accessed;
+		kvmppc_set_gpr(vcpu, ra, vcpu->arch.paddr_accessed);
 		break;
 
 	case OP_STH:
 		rs = get_rs(inst);
-		emulated = kvmppc_handle_store(run, vcpu, vcpu->arch.gpr[rs],
+		emulated = kvmppc_handle_store(run, vcpu,
+					       kvmppc_get_gpr(vcpu, rs),
 		                               2, 1);
 		break;
 
 	case OP_STHU:
 		ra = get_ra(inst);
 		rs = get_rs(inst);
-		emulated = kvmppc_handle_store(run, vcpu, vcpu->arch.gpr[rs],
+		emulated = kvmppc_handle_store(run, vcpu,
+					       kvmppc_get_gpr(vcpu, rs),
 		                               2, 1);
-		vcpu->arch.gpr[ra] = vcpu->arch.paddr_accessed;
+		kvmppc_set_gpr(vcpu, ra, vcpu->arch.paddr_accessed);
 		break;
 
 	default:
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 4633e7850dd..2c291161df8 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -270,34 +270,35 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 static void kvmppc_complete_dcr_load(struct kvm_vcpu *vcpu,
                                      struct kvm_run *run)
 {
-	ulong *gpr = &vcpu->arch.gpr[vcpu->arch.io_gpr];
-	*gpr = run->dcr.data;
+	kvmppc_set_gpr(vcpu, vcpu->arch.io_gpr, run->dcr.data);
 }
 
 static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu,
                                       struct kvm_run *run)
 {
-	ulong *gpr = &vcpu->arch.gpr[vcpu->arch.io_gpr];
+	ulong gpr;
 
-	if (run->mmio.len > sizeof(*gpr)) {
+	if (run->mmio.len > sizeof(gpr)) {
 		printk(KERN_ERR "bad MMIO length: %d\n", run->mmio.len);
 		return;
 	}
 
 	if (vcpu->arch.mmio_is_bigendian) {
 		switch (run->mmio.len) {
-		case 4: *gpr = *(u32 *)run->mmio.data; break;
-		case 2: *gpr = *(u16 *)run->mmio.data; break;
-		case 1: *gpr = *(u8 *)run->mmio.data; break;
+		case 4: gpr = *(u32 *)run->mmio.data; break;
+		case 2: gpr = *(u16 *)run->mmio.data; break;
+		case 1: gpr = *(u8 *)run->mmio.data; break;
 		}
 	} else {
 		/* Convert BE data from userland back to LE. */
 		switch (run->mmio.len) {
-		case 4: *gpr = ld_le32((u32 *)run->mmio.data); break;
-		case 2: *gpr = ld_le16((u16 *)run->mmio.data); break;
-		case 1: *gpr = *(u8 *)run->mmio.data; break;
+		case 4: gpr = ld_le32((u32 *)run->mmio.data); break;
+		case 2: gpr = ld_le16((u16 *)run->mmio.data); break;
+		case 1: gpr = *(u8 *)run->mmio.data; break;
 		}
 	}
+
+	kvmppc_set_gpr(vcpu, vcpu->arch.io_gpr, gpr);
 }
 
 int kvmppc_handle_load(struct kvm_run *run, struct kvm_vcpu *vcpu,
-- 
cgit v1.2.3


From 992b5b29b5ae254c416c62faf98d59a6cf970027 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 8 Jan 2010 02:58:02 +0100
Subject: KVM: PPC: Add helpers for CR, XER

We now have helpers for the GPRs, so let's also add some for CR and XER.

Having them in the PACA simplifies code a lot, as we don't need to care
about where to store CC or not to overflow any integers.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_ppc.h | 40 ++++++++++++++++++++++++++++++++++++++
 arch/powerpc/kvm/44x_tlb.c         |  6 ++++--
 arch/powerpc/kvm/book3s.c          |  8 ++++----
 arch/powerpc/kvm/booke.c           |  8 ++++----
 4 files changed, 52 insertions(+), 10 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index ba01b9c1d38..d60b2f0cdcf 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -108,6 +108,26 @@ 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;
+}
+
 #else
 
 static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val)
@@ -120,6 +140,26 @@ 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;
+}
+
 #endif
 
 #endif /* __POWERPC_KVM_PPC_H__ */
diff --git a/arch/powerpc/kvm/44x_tlb.c b/arch/powerpc/kvm/44x_tlb.c
index 8b3773669c9..2570fcc7665 100644
--- a/arch/powerpc/kvm/44x_tlb.c
+++ b/arch/powerpc/kvm/44x_tlb.c
@@ -506,10 +506,12 @@ int kvmppc_44x_emul_tlbsx(struct kvm_vcpu *vcpu, u8 rt, u8 ra, u8 rb, u8 rc)
 
 	gtlb_index = kvmppc_44x_tlb_index(vcpu, ea, pid, as);
 	if (rc) {
+		u32 cr = kvmppc_get_cr(vcpu);
+
 		if (gtlb_index < 0)
-			vcpu->arch.cr &= ~0x20000000;
+			kvmppc_set_cr(vcpu, cr & ~0x20000000);
 		else
-			vcpu->arch.cr |= 0x20000000;
+			kvmppc_set_cr(vcpu, cr | 0x20000000);
 	}
 	kvmppc_set_gpr(vcpu, rt, gtlb_index);
 
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 574b24fb6e0..09ba8dbaaba 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -717,10 +717,10 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	int i;
 
 	regs->pc = vcpu->arch.pc;
-	regs->cr = vcpu->arch.cr;
+	regs->cr = kvmppc_get_cr(vcpu);
 	regs->ctr = vcpu->arch.ctr;
 	regs->lr = vcpu->arch.lr;
-	regs->xer = vcpu->arch.xer;
+	regs->xer = kvmppc_get_xer(vcpu);
 	regs->msr = vcpu->arch.msr;
 	regs->srr0 = vcpu->arch.srr0;
 	regs->srr1 = vcpu->arch.srr1;
@@ -744,10 +744,10 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	int i;
 
 	vcpu->arch.pc = regs->pc;
-	vcpu->arch.cr = regs->cr;
+	kvmppc_set_cr(vcpu, regs->cr);
 	vcpu->arch.ctr = regs->ctr;
 	vcpu->arch.lr = regs->lr;
-	vcpu->arch.xer = regs->xer;
+	kvmppc_set_xer(vcpu, regs->xer);
 	kvmppc_set_msr(vcpu, regs->msr);
 	vcpu->arch.srr0 = regs->srr0;
 	vcpu->arch.srr1 = regs->srr1;
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 49af80e4a6e..338baf9f6b2 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -449,10 +449,10 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	int i;
 
 	regs->pc = vcpu->arch.pc;
-	regs->cr = vcpu->arch.cr;
+	regs->cr = kvmppc_get_cr(vcpu);
 	regs->ctr = vcpu->arch.ctr;
 	regs->lr = vcpu->arch.lr;
-	regs->xer = vcpu->arch.xer;
+	regs->xer = kvmppc_get_xer(vcpu);
 	regs->msr = vcpu->arch.msr;
 	regs->srr0 = vcpu->arch.srr0;
 	regs->srr1 = vcpu->arch.srr1;
@@ -476,10 +476,10 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	int i;
 
 	vcpu->arch.pc = regs->pc;
-	vcpu->arch.cr = regs->cr;
+	kvmppc_set_cr(vcpu, regs->cr);
 	vcpu->arch.ctr = regs->ctr;
 	vcpu->arch.lr = regs->lr;
-	vcpu->arch.xer = regs->xer;
+	kvmppc_set_xer(vcpu, regs->xer);
 	kvmppc_set_msr(vcpu, regs->msr);
 	vcpu->arch.srr0 = regs->srr0;
 	vcpu->arch.srr1 = regs->srr1;
-- 
cgit v1.2.3


From 7e57cba06074da84d7c24d8c3f44040d2d8c88ac Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 8 Jan 2010 02:58:03 +0100
Subject: KVM: PPC: Use PACA backed shadow vcpu

We're being horribly racy right now. All the entry and exit code hijacks
random fields from the PACA that could easily be used by different code in
case we get interrupted, for example by a #MC or even page fault.

After discussing this with Ben, we figured it's best to reserve some more
space in the PACA and just shove off some vcpu state to there.

That way we can drastically improve the readability of the code, make it
less racy and less complex.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_book3s.h        |   2 +
 arch/powerpc/include/asm/kvm_book3s_64_asm.h |  19 +++
 arch/powerpc/include/asm/kvm_host.h          |   5 +-
 arch/powerpc/include/asm/kvm_ppc.h           |  20 ++-
 arch/powerpc/include/asm/paca.h              |   5 +
 arch/powerpc/kernel/asm-offsets.c            |  33 +++-
 arch/powerpc/kvm/book3s.c                    |   4 +
 arch/powerpc/kvm/book3s_64_interrupts.S      | 216 +++++++++------------------
 arch/powerpc/kvm/book3s_64_rmhandlers.S      |  32 +---
 arch/powerpc/kvm/book3s_64_slb.S             | 150 +++++++++++--------
 10 files changed, 249 insertions(+), 237 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 74b7369770d..f192017d799 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -23,6 +23,7 @@
 #include <linux/types.h>
 #include <linux/kvm_host.h>
 #include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s_64_asm.h>
 
 struct kvmppc_slb {
 	u64 esid;
@@ -69,6 +70,7 @@ struct kvmppc_sid_map {
 
 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 {
diff --git a/arch/powerpc/include/asm/kvm_book3s_64_asm.h b/arch/powerpc/include/asm/kvm_book3s_64_asm.h
index 2e06ee8184e..fca9404c1a7 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64_asm.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64_asm.h
@@ -20,6 +20,8 @@
 #ifndef __ASM_KVM_BOOK3S_ASM_H__
 #define __ASM_KVM_BOOK3S_ASM_H__
 
+#ifdef __ASSEMBLY__
+
 #ifdef CONFIG_KVM_BOOK3S_64_HANDLER
 
 #include <asm/kvm_asm.h>
@@ -55,4 +57,21 @@ kvmppc_resume_\intno:
 
 #endif /* CONFIG_KVM_BOOK3S_64_HANDLER */
 
+#else  /*__ASSEMBLY__ */
+
+struct kvmppc_book3s_shadow_vcpu {
+	ulong gpr[14];
+	u32 cr;
+	u32 xer;
+	ulong host_r1;
+	ulong host_r2;
+	ulong handler;
+	ulong scratch0;
+	ulong scratch1;
+	ulong vmhandler;
+	ulong rmhandler;
+};
+
+#endif /*__ASSEMBLY__ */
+
 #endif /* __ASM_KVM_BOOK3S_ASM_H__ */
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 1201f62d0d7..d615fa8a141 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -175,10 +175,13 @@ struct kvm_vcpu_arch {
 	ulong gpr[32];
 
 	ulong pc;
-	u32 cr;
 	ulong ctr;
 	ulong lr;
+
+#ifdef CONFIG_BOOKE
 	ulong xer;
+	u32 cr;
+#endif
 
 	ulong msr;
 #ifdef CONFIG_PPC64
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index d60b2f0cdcf..89c5d79c347 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -98,34 +98,42 @@ extern void kvmppc_core_destroy_mmu(struct kvm_vcpu *vcpu);
 
 #ifdef CONFIG_PPC_BOOK3S
 
+/* We assume we're always acting on the current vcpu */
+
 static inline void kvmppc_set_gpr(struct kvm_vcpu *vcpu, int num, ulong val)
 {
-	vcpu->arch.gpr[num] = val;
+	if ( num < 14 )
+		get_paca()->shadow_vcpu.gpr[num] = val;
+	else
+		vcpu->arch.gpr[num] = val;
 }
 
 static inline ulong kvmppc_get_gpr(struct kvm_vcpu *vcpu, int num)
 {
-	return vcpu->arch.gpr[num];
+	if ( num < 14 )
+		return get_paca()->shadow_vcpu.gpr[num];
+	else
+		return vcpu->arch.gpr[num];
 }
 
 static inline void kvmppc_set_cr(struct kvm_vcpu *vcpu, u32 val)
 {
-	vcpu->arch.cr = val;
+	get_paca()->shadow_vcpu.cr = val;
 }
 
 static inline u32 kvmppc_get_cr(struct kvm_vcpu *vcpu)
 {
-	return vcpu->arch.cr;
+	return get_paca()->shadow_vcpu.cr;
 }
 
 static inline void kvmppc_set_xer(struct kvm_vcpu *vcpu, u32 val)
 {
-	vcpu->arch.xer = val;
+	get_paca()->shadow_vcpu.xer = val;
 }
 
 static inline u32 kvmppc_get_xer(struct kvm_vcpu *vcpu)
 {
-	return vcpu->arch.xer;
+	return get_paca()->shadow_vcpu.xer;
 }
 
 #else
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 5e9b4ef7141..d8a693109c8 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -19,6 +19,9 @@
 #include <asm/mmu.h>
 #include <asm/page.h>
 #include <asm/exception-64e.h>
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+#include <asm/kvm_book3s_64_asm.h>
+#endif
 
 register struct paca_struct *local_paca asm("r13");
 
@@ -135,6 +138,8 @@ struct paca_struct {
 		u64     esid;
 		u64     vsid;
 	} kvm_slb[64];			/* guest SLB */
+	/* We use this to store guest state in */
+	struct kvmppc_book3s_shadow_vcpu shadow_vcpu;
 	u8 kvm_slb_max;			/* highest used guest slb entry */
 	u8 kvm_in_guest;		/* are we inside the guest? */
 #endif
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index a6c2b63227b..1501e77c980 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -194,6 +194,32 @@ int main(void)
 	DEFINE(PACA_KVM_IN_GUEST, offsetof(struct paca_struct, kvm_in_guest));
 	DEFINE(PACA_KVM_SLB, offsetof(struct paca_struct, kvm_slb));
 	DEFINE(PACA_KVM_SLB_MAX, offsetof(struct paca_struct, kvm_slb_max));
+	DEFINE(PACA_KVM_CR, offsetof(struct paca_struct, shadow_vcpu.cr));
+	DEFINE(PACA_KVM_XER, offsetof(struct paca_struct, shadow_vcpu.xer));
+	DEFINE(PACA_KVM_R0, offsetof(struct paca_struct, shadow_vcpu.gpr[0]));
+	DEFINE(PACA_KVM_R1, offsetof(struct paca_struct, shadow_vcpu.gpr[1]));
+	DEFINE(PACA_KVM_R2, offsetof(struct paca_struct, shadow_vcpu.gpr[2]));
+	DEFINE(PACA_KVM_R3, offsetof(struct paca_struct, shadow_vcpu.gpr[3]));
+	DEFINE(PACA_KVM_R4, offsetof(struct paca_struct, shadow_vcpu.gpr[4]));
+	DEFINE(PACA_KVM_R5, offsetof(struct paca_struct, shadow_vcpu.gpr[5]));
+	DEFINE(PACA_KVM_R6, offsetof(struct paca_struct, shadow_vcpu.gpr[6]));
+	DEFINE(PACA_KVM_R7, offsetof(struct paca_struct, shadow_vcpu.gpr[7]));
+	DEFINE(PACA_KVM_R8, offsetof(struct paca_struct, shadow_vcpu.gpr[8]));
+	DEFINE(PACA_KVM_R9, offsetof(struct paca_struct, shadow_vcpu.gpr[9]));
+	DEFINE(PACA_KVM_R10, offsetof(struct paca_struct, shadow_vcpu.gpr[10]));
+	DEFINE(PACA_KVM_R11, offsetof(struct paca_struct, shadow_vcpu.gpr[11]));
+	DEFINE(PACA_KVM_R12, offsetof(struct paca_struct, shadow_vcpu.gpr[12]));
+	DEFINE(PACA_KVM_R13, offsetof(struct paca_struct, shadow_vcpu.gpr[13]));
+	DEFINE(PACA_KVM_HOST_R1, offsetof(struct paca_struct, shadow_vcpu.host_r1));
+	DEFINE(PACA_KVM_HOST_R2, offsetof(struct paca_struct, shadow_vcpu.host_r2));
+	DEFINE(PACA_KVM_VMHANDLER, offsetof(struct paca_struct,
+					    shadow_vcpu.vmhandler));
+	DEFINE(PACA_KVM_RMHANDLER, offsetof(struct paca_struct,
+					    shadow_vcpu.rmhandler));
+	DEFINE(PACA_KVM_SCRATCH0, offsetof(struct paca_struct,
+					   shadow_vcpu.scratch0));
+	DEFINE(PACA_KVM_SCRATCH1, offsetof(struct paca_struct,
+					   shadow_vcpu.scratch1));
 #endif
 #endif /* CONFIG_PPC64 */
 
@@ -389,8 +415,6 @@ 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_LR, offsetof(struct kvm_vcpu, arch.lr));
-	DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr));
-	DEFINE(VCPU_XER, offsetof(struct kvm_vcpu, arch.xer));
 	DEFINE(VCPU_CTR, offsetof(struct kvm_vcpu, arch.ctr));
 	DEFINE(VCPU_PC, offsetof(struct kvm_vcpu, arch.pc));
 	DEFINE(VCPU_MSR, offsetof(struct kvm_vcpu, arch.msr));
@@ -415,7 +439,10 @@ int main(void)
 	DEFINE(VCPU_TRAMPOLINE_ENTER, offsetof(struct kvm_vcpu, arch.trampoline_enter));
 	DEFINE(VCPU_HIGHMEM_HANDLER, offsetof(struct kvm_vcpu, arch.highmem_handler));
 	DEFINE(VCPU_HFLAGS, offsetof(struct kvm_vcpu, arch.hflags));
-#endif
+#else
+	DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr));
+	DEFINE(VCPU_XER, offsetof(struct kvm_vcpu, arch.xer));
+#endif /* CONFIG_PPC64 */
 #endif
 #ifdef CONFIG_44x
 	DEFINE(PGD_T_LOG2, PGD_T_LOG2);
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 09ba8dbaaba..3e06eae3f2c 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -66,12 +66,16 @@ void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu)
 void kvmppc_core_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	memcpy(get_paca()->kvm_slb, to_book3s(vcpu)->slb_shadow, sizeof(get_paca()->kvm_slb));
+	memcpy(&get_paca()->shadow_vcpu, &to_book3s(vcpu)->shadow_vcpu,
+	       sizeof(get_paca()->shadow_vcpu));
 	get_paca()->kvm_slb_max = to_book3s(vcpu)->slb_shadow_max;
 }
 
 void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	memcpy(to_book3s(vcpu)->slb_shadow, get_paca()->kvm_slb, sizeof(get_paca()->kvm_slb));
+	memcpy(&to_book3s(vcpu)->shadow_vcpu, &get_paca()->shadow_vcpu,
+	       sizeof(get_paca()->shadow_vcpu));
 	to_book3s(vcpu)->slb_shadow_max = get_paca()->kvm_slb_max;
 }
 
diff --git a/arch/powerpc/kvm/book3s_64_interrupts.S b/arch/powerpc/kvm/book3s_64_interrupts.S
index d95d0d967d5..66e3b1179b3 100644
--- a/arch/powerpc/kvm/book3s_64_interrupts.S
+++ b/arch/powerpc/kvm/book3s_64_interrupts.S
@@ -28,11 +28,6 @@
 #define ULONG_SIZE 8
 #define VCPU_GPR(n)     (VCPU_GPRS + (n * ULONG_SIZE))
 
-.macro mfpaca tmp_reg, src_reg, offset, vcpu_reg
-	ld	\tmp_reg, (PACA_EXMC+\offset)(r13)
-	std	\tmp_reg, VCPU_GPR(\src_reg)(\vcpu_reg)
-.endm
-
 .macro DISABLE_INTERRUPTS
        mfmsr   r0
        rldicl  r0,r0,48,1
@@ -92,37 +87,30 @@ kvm_start_entry:
 	/* Load non-volatile guest state from the vcpu */
 	VCPU_LOAD_NVGPRS(r4)
 
-kvm_start_lightweight:
-
-	ld	r9, VCPU_PC(r4)			/* r9 = vcpu->arch.pc */
-	ld	r10, VCPU_SHADOW_MSR(r4)	/* r10 = vcpu->arch.shadow_msr */
-
-	DISABLE_INTERRUPTS
-
 	/* Save R1/R2 in the PACA */
-	std	r1, PACAR1(r13)
-	std	r2, (PACA_EXMC+EX_SRR0)(r13)
+	std	r1, PACA_KVM_HOST_R1(r13)
+	std	r2, PACA_KVM_HOST_R2(r13)
+
+	/* XXX swap in/out on load? */
 	ld	r3, VCPU_HIGHMEM_HANDLER(r4)
-	std	r3, PACASAVEDMSR(r13)
+	std	r3, PACA_KVM_VMHANDLER(r13)
 
 	ld	r3, VCPU_TRAMPOLINE_ENTER(r4)
-	mtsrr0	r3
+	std	r3, PACA_KVM_RMHANDLER(r13)
 
-	LOAD_REG_IMMEDIATE(r3, MSR_KERNEL & ~(MSR_IR | MSR_DR))
-	mtsrr1	r3
+kvm_start_lightweight:
 
-	/* Load guest state in the respective registers */
-	lwz	r3, VCPU_CR(r4)		/* r3 = vcpu->arch.cr */
-	stw	r3, (PACA_EXMC + EX_CCR)(r13)
+	ld	r9, VCPU_PC(r4)			/* r9 = vcpu->arch.pc */
+	ld	r10, VCPU_SHADOW_MSR(r4)	/* r10 = vcpu->arch.shadow_msr */
 
+	/* Load some guest state in the respective registers */
 	ld	r3, VCPU_CTR(r4)	/* r3 = vcpu->arch.ctr */
 	mtctr	r3			/* CTR = r3 */
 
 	ld	r3, VCPU_LR(r4)		/* r3 = vcpu->arch.lr */
 	mtlr	r3			/* LR = r3 */
 
-	ld	r3, VCPU_XER(r4)	/* r3 = vcpu->arch.xer */
-	std	r3, (PACA_EXMC + EX_R3)(r13)
+	DISABLE_INTERRUPTS
 
 	/* Some guests may need to have dcbz set to 32 byte length.
 	 *
@@ -142,34 +130,21 @@ kvm_start_lightweight:
 	mtspr   SPRN_HID5,r3
 
 no_dcbz32_on:
-	/*	Load guest GPRs */
-
-	ld	r3, VCPU_GPR(r9)(r4)
-	std	r3, (PACA_EXMC + EX_R9)(r13)
-	ld	r3, VCPU_GPR(r10)(r4)
-	std	r3, (PACA_EXMC + EX_R10)(r13)
-	ld	r3, VCPU_GPR(r11)(r4)
-	std	r3, (PACA_EXMC + EX_R11)(r13)
-	ld	r3, VCPU_GPR(r12)(r4)
-	std	r3, (PACA_EXMC + EX_R12)(r13)
-	ld	r3, VCPU_GPR(r13)(r4)
-	std	r3, (PACA_EXMC + EX_R13)(r13)
-
-	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	r4, VCPU_GPR(r4)(r4)
 
 	/* This sets the Magic value for the trampoline */
 
+	/* XXX this needs to move into a safe function, so we can
+	   be sure we don't get any interrupts */
+
 	li	r11, 1
 	stb	r11, PACA_KVM_IN_GUEST(r13)
 
+	ld	r3, PACA_KVM_RMHANDLER(r13)
+	mtsrr0	r3
+
+	LOAD_REG_IMMEDIATE(r3, MSR_KERNEL & ~(MSR_IR | MSR_DR))
+	mtsrr1	r3
+
 	/* Jump to SLB patching handlder and into our guest */
 	RFI
 
@@ -185,60 +160,31 @@ kvmppc_handler_highmem:
 	/*
 	 * Register usage at this point:
 	 *
-	 * R00   = guest R13
-	 * R01   = host R1
-	 * R02   = host R2
-	 * R10   = guest PC
-	 * R11   = guest MSR
-	 * R12   = exit handler id
-	 * R13   = PACA
-	 * PACA.exmc.R9    = guest R1
-	 * PACA.exmc.R10   = guest R10
-	 * PACA.exmc.R11   = guest R11
-	 * PACA.exmc.R12   = guest R12
-	 * PACA.exmc.R13   = guest R2
-	 * PACA.exmc.DAR   = guest DAR
-	 * PACA.exmc.DSISR = guest DSISR
-	 * PACA.exmc.LR    = guest instruction
-	 * PACA.exmc.CCR   = guest CR
-	 * PACA.exmc.SRR0  = guest R0
+	 * R0         = guest last inst
+	 * R1         = host R1
+	 * R2         = host R2
+	 * R3         = guest PC
+	 * R4         = guest MSR
+	 * R5         = guest DAR
+	 * R6         = guest DSISR
+	 * R13        = PACA
+	 * PACA.KVM.* = guest *
 	 *
 	 */
 
-	std	r3, (PACA_EXMC+EX_R3)(r13)
+	/* R7 = vcpu */
+	ld	r7, GPR4(r1)
 
-	/* save the exit id in R3 */
-	mr	r3, r12
+	/* Now save the guest state */
 
-	/* R12 = vcpu */
-	ld	r12, GPR4(r1)
+	stw	r0, VCPU_LAST_INST(r7)
 
-	/* Now save the guest state */
+	std	r3, VCPU_PC(r7)
+	std	r4, VCPU_SHADOW_MSR(r7)
+	std	r5, VCPU_FAULT_DEAR(r7)
+	std	r6, VCPU_FAULT_DSISR(r7)
 
-	std	r0, VCPU_GPR(r13)(r12)
-	std	r4, VCPU_GPR(r4)(r12)
-	std	r5, VCPU_GPR(r5)(r12)
-	std	r6, VCPU_GPR(r6)(r12)
-	std	r7, VCPU_GPR(r7)(r12)
-	std	r8, VCPU_GPR(r8)(r12)
-	std	r9, VCPU_GPR(r9)(r12)
-
-	/* get registers from PACA */
-	mfpaca	r5, r0, EX_SRR0, r12
-	mfpaca	r5, r3, EX_R3, r12
-	mfpaca	r5, r1, EX_R9, r12
-	mfpaca	r5, r10, EX_R10, r12
-	mfpaca	r5, r11, EX_R11, r12
-	mfpaca	r5, r12, EX_R12, r12
-	mfpaca	r5, r2, EX_R13, r12
-
-	lwz	r5, (PACA_EXMC+EX_LR)(r13)
-	stw	r5, VCPU_LAST_INST(r12)
-
-	lwz	r5, (PACA_EXMC+EX_CCR)(r13)
-	stw	r5, VCPU_CR(r12)
-
-	ld	r5, VCPU_HFLAGS(r12)
+	ld	r5, VCPU_HFLAGS(r7)
 	rldicl.	r5, r5, 0, 63		/* CR = ((r5 & 1) == 0) */
 	beq	no_dcbz32_off
 
@@ -248,58 +194,42 @@ kvmppc_handler_highmem:
 
 no_dcbz32_off:
 
-	std	r14, VCPU_GPR(r14)(r12)
-	std	r15, VCPU_GPR(r15)(r12)
-	std	r16, VCPU_GPR(r16)(r12)
-	std	r17, VCPU_GPR(r17)(r12)
-	std	r18, VCPU_GPR(r18)(r12)
-	std	r19, VCPU_GPR(r19)(r12)
-	std	r20, VCPU_GPR(r20)(r12)
-	std	r21, VCPU_GPR(r21)(r12)
-	std	r22, VCPU_GPR(r22)(r12)
-	std	r23, VCPU_GPR(r23)(r12)
-	std	r24, VCPU_GPR(r24)(r12)
-	std	r25, VCPU_GPR(r25)(r12)
-	std	r26, VCPU_GPR(r26)(r12)
-	std	r27, VCPU_GPR(r27)(r12)
-	std	r28, VCPU_GPR(r28)(r12)
-	std	r29, VCPU_GPR(r29)(r12)
-	std	r30, VCPU_GPR(r30)(r12)
-	std	r31, VCPU_GPR(r31)(r12)
-
-	/* Save guest PC (R10) */
-	std	r10, VCPU_PC(r12)
-
-	/* Save guest msr (R11) */
-	std	r11, VCPU_SHADOW_MSR(r12)
-
-	/* Save guest CTR (in R12) */
+	std	r14, VCPU_GPR(r14)(r7)
+	std	r15, VCPU_GPR(r15)(r7)
+	std	r16, VCPU_GPR(r16)(r7)
+	std	r17, VCPU_GPR(r17)(r7)
+	std	r18, VCPU_GPR(r18)(r7)
+	std	r19, VCPU_GPR(r19)(r7)
+	std	r20, VCPU_GPR(r20)(r7)
+	std	r21, VCPU_GPR(r21)(r7)
+	std	r22, VCPU_GPR(r22)(r7)
+	std	r23, VCPU_GPR(r23)(r7)
+	std	r24, VCPU_GPR(r24)(r7)
+	std	r25, VCPU_GPR(r25)(r7)
+	std	r26, VCPU_GPR(r26)(r7)
+	std	r27, VCPU_GPR(r27)(r7)
+	std	r28, VCPU_GPR(r28)(r7)
+	std	r29, VCPU_GPR(r29)(r7)
+	std	r30, VCPU_GPR(r30)(r7)
+	std	r31, VCPU_GPR(r31)(r7)
+
+	/* Save guest CTR */
 	mfctr	r5
-	std	r5, VCPU_CTR(r12)
+	std	r5, VCPU_CTR(r7)
 
 	/* Save guest LR */
 	mflr	r5
-	std	r5, VCPU_LR(r12)
-
-	/* Save guest XER */
-	mfxer	r5
-	std	r5, VCPU_XER(r12)
+	std	r5, VCPU_LR(r7)
 
-	/* Save guest DAR */
-	ld	r5, (PACA_EXMC+EX_DAR)(r13)
-	std	r5, VCPU_FAULT_DEAR(r12)
-
-	/* Save guest DSISR */
-	lwz	r5, (PACA_EXMC+EX_DSISR)(r13)
-	std	r5, VCPU_FAULT_DSISR(r12)
+	/* XXX convert to safe function call */
 
 	/* Restore host msr -> SRR1 */
-	ld	r7, VCPU_HOST_MSR(r12)
-	mtsrr1	r7
+	ld	r6, VCPU_HOST_MSR(r7)
+	mtsrr1	r6
 
 	/* Restore host IP -> SRR0 */
-	ld	r6, VCPU_HOST_RETIP(r12)
-	mtsrr0	r6
+	ld	r5, VCPU_HOST_RETIP(r7)
+	mtsrr0	r5
 
 	/*
 	 * For some interrupts, we need to call the real Linux
@@ -311,9 +241,9 @@ no_dcbz32_off:
 	 * r3 = address of interrupt handler (exit reason)
 	 */
 
-	cmpwi	r3, BOOK3S_INTERRUPT_EXTERNAL
+	cmpwi	r12, BOOK3S_INTERRUPT_EXTERNAL
 	beq	call_linux_handler
-	cmpwi	r3, BOOK3S_INTERRUPT_DECREMENTER
+	cmpwi	r12, BOOK3S_INTERRUPT_DECREMENTER
 	beq	call_linux_handler
 
 	/* Back to Interruptable Mode! (goto kvm_return_point) */
@@ -334,12 +264,12 @@ call_linux_handler:
 	 * R7 VCPU_HOST_MSR
 	 */
 
-	mtlr	r3
+	mtlr	r12
 
-	ld	r5, VCPU_TRAMPOLINE_LOWMEM(r12)
-	mtsrr0	r5
-	LOAD_REG_IMMEDIATE(r5, MSR_KERNEL & ~(MSR_IR | MSR_DR))
-	mtsrr1	r5
+	ld	r4, VCPU_TRAMPOLINE_LOWMEM(r7)
+	mtsrr0	r4
+	LOAD_REG_IMMEDIATE(r3, MSR_KERNEL & ~(MSR_IR | MSR_DR))
+	mtsrr1	r3
 
 	RFI
 
@@ -350,7 +280,7 @@ kvm_return_point:
 	/* go back into the guest */
 
 	/* Pass the exit number as 3rd argument to kvmppc_handle_exit */
-	mr	r5, r3
+	mr	r5, r12
 
 	/* Restore r3 (kvm_run) and r4 (vcpu) */
 	REST_2GPRS(3, r1)
diff --git a/arch/powerpc/kvm/book3s_64_rmhandlers.S b/arch/powerpc/kvm/book3s_64_rmhandlers.S
index fb7dd2e9ac8..cd9f0b609e4 100644
--- a/arch/powerpc/kvm/book3s_64_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_64_rmhandlers.S
@@ -45,37 +45,21 @@ kvmppc_trampoline_\intno:
 	 * To distinguish, we check a magic byte in the PACA
 	 */
 	mfspr	r13, SPRN_SPRG_PACA		/* r13 = PACA */
-	std	r12, (PACA_EXMC + EX_R12)(r13)
+	std	r12, PACA_KVM_SCRATCH0(r13)
 	mfcr	r12
-	stw	r12, (PACA_EXMC + EX_CCR)(r13)
+	stw	r12, PACA_KVM_SCRATCH1(r13)
 	lbz	r12, PACA_KVM_IN_GUEST(r13)
 	cmpwi	r12, 0
 	bne	..kvmppc_handler_hasmagic_\intno
 	/* No KVM guest? Then jump back to the Linux handler! */
-	lwz	r12, (PACA_EXMC + EX_CCR)(r13)
+	lwz	r12, PACA_KVM_SCRATCH1(r13)
 	mtcr	r12
-	ld	r12, (PACA_EXMC + EX_R12)(r13)
+	ld	r12, PACA_KVM_SCRATCH0(r13)
 	mfspr	r13, SPRN_SPRG_SCRATCH0		/* r13 = original r13 */
 	b	kvmppc_resume_\intno		/* Get back original handler */
 
 	/* Now we know we're handling a KVM guest */
 ..kvmppc_handler_hasmagic_\intno:
-	/* Unset guest state */
-	li	r12, 0
-	stb	r12, PACA_KVM_IN_GUEST(r13)
-
-	std	r1, (PACA_EXMC+EX_R9)(r13)
-	std	r10, (PACA_EXMC+EX_R10)(r13)
-	std	r11, (PACA_EXMC+EX_R11)(r13)
-	std	r2, (PACA_EXMC+EX_R13)(r13)
-
-	mfsrr0	r10
-	mfsrr1	r11
-
-	/* Restore R1/R2 so we can handle faults */
-	ld	r1, PACAR1(r13)
-	ld	r2, (PACA_EXMC+EX_SRR0)(r13)
-
 	/* Let's store which interrupt we're handling */
 	li	r12, \intno
 
@@ -106,16 +90,16 @@ INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_VSX
  *
  * Input Registers:
  *
- * R6 = SRR0
- * R7 = SRR1
+ * R5 = SRR0
+ * R6 = SRR1
  * LR = real-mode IP
  *
  */
 .global kvmppc_handler_lowmem_trampoline
 kvmppc_handler_lowmem_trampoline:
 
-	mtsrr0	r6
-	mtsrr1	r7
+	mtsrr0	r5
+	mtsrr1	r6
 	blr
 kvmppc_handler_lowmem_trampoline_end:
 
diff --git a/arch/powerpc/kvm/book3s_64_slb.S b/arch/powerpc/kvm/book3s_64_slb.S
index 8e447886666..7188c11ed7d 100644
--- a/arch/powerpc/kvm/book3s_64_slb.S
+++ b/arch/powerpc/kvm/book3s_64_slb.S
@@ -51,24 +51,18 @@ kvmppc_handler_trampoline_enter:
 	 *
 	 * MSR = ~IR|DR
 	 * R13 = PACA
+	 * R1 = host R1
+	 * R2 = host R2
 	 * R9 = guest IP
 	 * R10 = guest MSR
-	 * R11 = free
-	 * R12 = free
-	 * PACA[PACA_EXMC + EX_R9] = guest R9
-	 * PACA[PACA_EXMC + EX_R10] = guest R10
-	 * PACA[PACA_EXMC + EX_R11] = guest R11
-	 * PACA[PACA_EXMC + EX_R12] = guest R12
-	 * PACA[PACA_EXMC + EX_R13] = guest R13
-	 * PACA[PACA_EXMC + EX_CCR] = guest CR
-	 * PACA[PACA_EXMC + EX_R3] = guest XER
+	 * all other GPRS = free
+	 * PACA[KVM_CR] = guest CR
+	 * PACA[KVM_XER] = guest XER
 	 */
 
 	mtsrr0	r9
 	mtsrr1	r10
 
-	mtspr	SPRN_SPRG_SCRATCH0, r0
-
 	/* Remove LPAR shadow entries */
 
 #if SLB_NUM_BOLTED == 3
@@ -131,20 +125,27 @@ slb_do_enter:
 
 	/* Enter guest */
 
-	mfspr	r0, SPRN_SPRG_SCRATCH0
-
-	ld	r9, (PACA_EXMC+EX_R9)(r13)
-	ld	r10, (PACA_EXMC+EX_R10)(r13)
-	ld	r12, (PACA_EXMC+EX_R12)(r13)
-
-	lwz	r11, (PACA_EXMC+EX_CCR)(r13)
+	ld	r0, (PACA_KVM_R0)(r13)
+	ld	r1, (PACA_KVM_R1)(r13)
+	ld	r2, (PACA_KVM_R2)(r13)
+	ld	r3, (PACA_KVM_R3)(r13)
+	ld	r4, (PACA_KVM_R4)(r13)
+	ld	r5, (PACA_KVM_R5)(r13)
+	ld	r6, (PACA_KVM_R6)(r13)
+	ld	r7, (PACA_KVM_R7)(r13)
+	ld	r8, (PACA_KVM_R8)(r13)
+	ld	r9, (PACA_KVM_R9)(r13)
+	ld	r10, (PACA_KVM_R10)(r13)
+	ld	r12, (PACA_KVM_R12)(r13)
+
+	lwz	r11, (PACA_KVM_CR)(r13)
 	mtcr	r11
 
-	ld	r11, (PACA_EXMC+EX_R3)(r13)
+	ld	r11, (PACA_KVM_XER)(r13)
 	mtxer	r11
 
-	ld	r11, (PACA_EXMC+EX_R11)(r13)
-	ld	r13, (PACA_EXMC+EX_R13)(r13)
+	ld	r11, (PACA_KVM_R11)(r13)
+	ld	r13, (PACA_KVM_R13)(r13)
 
 	RFI
 kvmppc_handler_trampoline_enter_end:
@@ -162,28 +163,58 @@ kvmppc_handler_trampoline_exit:
 
 	/* Register usage at this point:
 	 *
-	 * SPRG_SCRATCH0 = guest R13
-	 * R01           = host R1
-	 * R02           = host R2
-	 * R10           = guest PC
-	 * R11           = guest MSR
-	 * R12           = exit handler id
-	 * R13           = PACA
-	 * PACA.exmc.CCR  = guest CR
-	 * PACA.exmc.R9  = guest R1
-	 * PACA.exmc.R10 = guest R10
-	 * PACA.exmc.R11 = guest R11
-	 * PACA.exmc.R12 = guest R12
-	 * PACA.exmc.R13 = guest R2
+	 * SPRG_SCRATCH0     = guest R13
+	 * R12               = exit handler id
+	 * R13               = PACA
+	 * PACA.KVM.SCRATCH0 = guest R12
+	 * PACA.KVM.SCRATCH1 = guest CR
 	 *
 	 */
 
 	/* Save registers */
 
-	std	r0, (PACA_EXMC+EX_SRR0)(r13)
-	std	r9, (PACA_EXMC+EX_R3)(r13)
-	std	r10, (PACA_EXMC+EX_LR)(r13)
-	std	r11, (PACA_EXMC+EX_DAR)(r13)
+	std	r0, PACA_KVM_R0(r13)
+	std	r1, PACA_KVM_R1(r13)
+	std	r2, PACA_KVM_R2(r13)
+	std	r3, PACA_KVM_R3(r13)
+	std	r4, PACA_KVM_R4(r13)
+	std	r5, PACA_KVM_R5(r13)
+	std	r6, PACA_KVM_R6(r13)
+	std	r7, PACA_KVM_R7(r13)
+	std	r8, PACA_KVM_R8(r13)
+	std	r9, PACA_KVM_R9(r13)
+	std	r10, PACA_KVM_R10(r13)
+	std	r11, PACA_KVM_R11(r13)
+
+	/* Restore R1/R2 so we can handle faults */
+	ld	r1, PACA_KVM_HOST_R1(r13)
+	ld	r2, PACA_KVM_HOST_R2(r13)
+
+	/* Save guest PC and MSR in GPRs */
+	mfsrr0	r3
+	mfsrr1	r4
+
+	/* Get scratch'ed off registers */
+	mfspr	r9, SPRN_SPRG_SCRATCH0
+	std	r9, PACA_KVM_R13(r13)
+
+	ld	r8, PACA_KVM_SCRATCH0(r13)
+	std	r8, PACA_KVM_R12(r13)
+
+	lwz	r7, PACA_KVM_SCRATCH1(r13)
+	stw	r7, PACA_KVM_CR(r13)
+
+	/* Save more register state  */
+
+	mfxer	r6
+	stw	r6, PACA_KVM_XER(r13)
+
+	mfdar	r5
+	mfdsisr	r6
+
+	/* Unset guest state */
+	li	r9, 0
+	stb	r9, PACA_KVM_IN_GUEST(r13)
 
 	/*
 	 * In order for us to easily get the last instruction,
@@ -207,7 +238,8 @@ ld_last_inst:
 	ori	r11, r9, MSR_DR			/* Enable paging for data */
 	mtmsr	r11
 	/*    2) fetch the instruction */
-	lwz	r0, 0(r10)
+	/* XXX implement PACA_KVM_IN_GUEST=2 path to safely jump over this */
+	lwz	r0, 0(r3)
 	/*    3) disable paging again */
 	mtmsr	r9
 
@@ -233,29 +265,27 @@ no_ld_last_inst:
 
 slb_do_exit:
 
-	/* Restore registers */
-
-	ld	r11, (PACA_EXMC+EX_DAR)(r13)
-	ld	r10, (PACA_EXMC+EX_LR)(r13)
-	ld	r9, (PACA_EXMC+EX_R3)(r13)
-
-	/* Save last inst */
-	stw	r0, (PACA_EXMC+EX_LR)(r13)
-
-	/* Save DAR and DSISR before going to paged mode */
-	mfdar	r0
-	std	r0, (PACA_EXMC+EX_DAR)(r13)
-	mfdsisr	r0
-	stw	r0, (PACA_EXMC+EX_DSISR)(r13)
+	/* Register usage at this point:
+	 *
+	 * R0         = guest last inst
+	 * R1         = host R1
+	 * R2         = host R2
+	 * R3         = guest PC
+	 * R4         = guest MSR
+	 * R5         = guest DAR
+	 * R6         = guest DSISR
+	 * R12        = exit handler id
+	 * R13        = PACA
+	 * PACA.KVM.* = guest *
+	 *
+	 */
 
 	/* RFI into the highmem handler */
-	mfmsr	r0
-	ori	r0, r0, MSR_IR|MSR_DR|MSR_RI	/* Enable paging */
-	mtsrr1	r0
-	ld	r0, PACASAVEDMSR(r13)		/* Highmem handler address */
-	mtsrr0	r0
-
-	mfspr	r0, SPRN_SPRG_SCRATCH0
+	mfmsr	r7
+	ori	r7, r7, MSR_IR|MSR_DR|MSR_RI	/* Enable paging */
+	mtsrr1	r7
+	ld	r8, PACA_KVM_VMHANDLER(r13)	/* Highmem handler address */
+	mtsrr0	r8
 
 	RFI
 kvmppc_handler_trampoline_exit_end:
-- 
cgit v1.2.3


From b4433a7cceed59714b0778e1ace624befdd15ded Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 8 Jan 2010 02:58:04 +0100
Subject: KVM: PPC: Implement 'skip instruction' mode

To fetch the last instruction we were interrupted on, we enable DR in early
exit code, where we are still in a very transitional phase between guest
and host state.

Most of the time this seemed to work, but another CPU can easily flush our
TLB and HTAB which makes us go in the Linux page fault handler which totally
breaks because we still use the guest's SLB entries.

To work around that, let's introduce a second KVM guest mode that defines
that whenever we get a trap, we don't call the Linux handler or go into
the KVM exit code, but just jump over the faulting instruction.

That way a potentially bad lwz doesn't trigger any faults and we can later
on interpret the invalid instruction we fetched as "fetch didn't work".

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_asm.h      |  6 +++++
 arch/powerpc/kvm/book3s_64_rmhandlers.S | 39 ++++++++++++++++++++++++++++++++-
 arch/powerpc/kvm/book3s_64_slb.S        | 16 +++++++++-----
 arch/powerpc/kvm/emulate.c              |  4 ++++
 4 files changed, 59 insertions(+), 6 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h
index af2abe74f54..aadf2dd6f84 100644
--- a/arch/powerpc/include/asm/kvm_asm.h
+++ b/arch/powerpc/include/asm/kvm_asm.h
@@ -97,4 +97,10 @@
 #define RESUME_HOST             RESUME_FLAG_HOST
 #define RESUME_HOST_NV          (RESUME_FLAG_HOST|RESUME_FLAG_NV)
 
+#define KVM_GUEST_MODE_NONE	0
+#define KVM_GUEST_MODE_GUEST	1
+#define KVM_GUEST_MODE_SKIP	2
+
+#define KVM_INST_FETCH_FAILED	-1
+
 #endif /* __POWERPC_KVM_ASM_H__ */
diff --git a/arch/powerpc/kvm/book3s_64_rmhandlers.S b/arch/powerpc/kvm/book3s_64_rmhandlers.S
index cd9f0b609e4..9ad1c2645d6 100644
--- a/arch/powerpc/kvm/book3s_64_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_64_rmhandlers.S
@@ -49,7 +49,7 @@ kvmppc_trampoline_\intno:
 	mfcr	r12
 	stw	r12, PACA_KVM_SCRATCH1(r13)
 	lbz	r12, PACA_KVM_IN_GUEST(r13)
-	cmpwi	r12, 0
+	cmpwi	r12, KVM_GUEST_MODE_NONE
 	bne	..kvmppc_handler_hasmagic_\intno
 	/* No KVM guest? Then jump back to the Linux handler! */
 	lwz	r12, PACA_KVM_SCRATCH1(r13)
@@ -60,6 +60,11 @@ kvmppc_trampoline_\intno:
 
 	/* Now we know we're handling a KVM guest */
 ..kvmppc_handler_hasmagic_\intno:
+
+	/* Should we just skip the faulting instruction? */
+	cmpwi	r12, KVM_GUEST_MODE_SKIP
+	beq	kvmppc_handler_skip_ins
+
 	/* Let's store which interrupt we're handling */
 	li	r12, \intno
 
@@ -85,6 +90,38 @@ INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_PERFMON
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_ALTIVEC
 INTERRUPT_TRAMPOLINE	BOOK3S_INTERRUPT_VSX
 
+/*
+ * Bring us back to the faulting code, but skip the
+ * faulting instruction.
+ *
+ * This is a generic exit path from the interrupt
+ * trampolines above.
+ *
+ * Input Registers:
+ *
+ * R12               = free
+ * R13               = PACA
+ * PACA.KVM.SCRATCH0 = guest R12
+ * PACA.KVM.SCRATCH1 = guest CR
+ * SPRG_SCRATCH0     = guest R13
+ *
+ */
+kvmppc_handler_skip_ins:
+
+	/* Patch the IP to the next instruction */
+	mfsrr0	r12
+	addi	r12, r12, 4
+	mtsrr0	r12
+
+	/* Clean up all state */
+	lwz	r12, PACA_KVM_SCRATCH1(r13)
+	mtcr	r12
+	ld	r12, PACA_KVM_SCRATCH0(r13)
+	mfspr	r13, SPRN_SPRG_SCRATCH0
+
+	/* And get back into the code */
+	RFI
+
 /*
  * This trampoline brings us back to a real mode handler
  *
diff --git a/arch/powerpc/kvm/book3s_64_slb.S b/arch/powerpc/kvm/book3s_64_slb.S
index 7188c11ed7d..d07b88617b2 100644
--- a/arch/powerpc/kvm/book3s_64_slb.S
+++ b/arch/powerpc/kvm/book3s_64_slb.S
@@ -212,10 +212,6 @@ kvmppc_handler_trampoline_exit:
 	mfdar	r5
 	mfdsisr	r6
 
-	/* Unset guest state */
-	li	r9, 0
-	stb	r9, PACA_KVM_IN_GUEST(r13)
-
 	/*
 	 * In order for us to easily get the last instruction,
 	 * we got the #vmexit at, we exploit the fact that the
@@ -233,18 +229,28 @@ kvmppc_handler_trampoline_exit:
 
 ld_last_inst:
 	/* Save off the guest instruction we're at */
+
+	/* 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, PACA_KVM_IN_GUEST(r13)
+
 	/*    1) enable paging for data */
 	mfmsr	r9
 	ori	r11, r9, MSR_DR			/* Enable paging for data */
 	mtmsr	r11
 	/*    2) fetch the instruction */
-	/* XXX implement PACA_KVM_IN_GUEST=2 path to safely jump over this */
+	li	r0, KVM_INST_FETCH_FAILED	/* In case lwz faults */
 	lwz	r0, 0(r3)
 	/*    3) disable paging again */
 	mtmsr	r9
 
 no_ld_last_inst:
 
+	/* Unset guest mode */
+	li	r9, KVM_GUEST_MODE_NONE
+	stb	r9, PACA_KVM_IN_GUEST(r13)
+
 	/* Restore bolted entries from the shadow and fix it along the way */
 
 	/* We don't store anything in entry 0, so we don't need to take care of it */
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index 38219af0cd0..04e317c1bbe 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -143,6 +143,10 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 
 	pr_debug(KERN_INFO "Emulating opcode %d / %d\n", get_op(inst), get_xop(inst));
 
+	/* Try again next time */
+	if (inst == KVM_INST_FETCH_FAILED)
+		return EMULATE_DONE;
+
 	switch (get_op(inst)) {
 	case OP_TRAP:
 #ifdef CONFIG_PPC64
-- 
cgit v1.2.3


From bc90923e27908ef65aa8aaad2f234e18b5273c78 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 8 Jan 2010 02:58:05 +0100
Subject: KVM: PPC: Get rid of unnecessary RFI

Using an RFI in IR=1 is dangerous. We need to set two SRRs and then do an RFI
without getting interrupted at all, because every interrupt could potentially
overwrite the SRR values.

Fortunately, we don't need to RFI in at least this particular case of the code,
so we can just replace it with an mtmsr and b.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kvm/book3s_64_interrupts.S | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/book3s_64_interrupts.S b/arch/powerpc/kvm/book3s_64_interrupts.S
index 66e3b1179b3..3c0ba551307 100644
--- a/arch/powerpc/kvm/book3s_64_interrupts.S
+++ b/arch/powerpc/kvm/book3s_64_interrupts.S
@@ -221,15 +221,8 @@ no_dcbz32_off:
 	mflr	r5
 	std	r5, VCPU_LR(r7)
 
-	/* XXX convert to safe function call */
-
 	/* Restore host msr -> SRR1 */
 	ld	r6, VCPU_HOST_MSR(r7)
-	mtsrr1	r6
-
-	/* Restore host IP -> SRR0 */
-	ld	r5, VCPU_HOST_RETIP(r7)
-	mtsrr0	r5
 
 	/*
 	 * For some interrupts, we need to call the real Linux
@@ -246,8 +239,9 @@ no_dcbz32_off:
 	cmpwi	r12, BOOK3S_INTERRUPT_DECREMENTER
 	beq	call_linux_handler
 
-	/* Back to Interruptable Mode! (goto kvm_return_point) */
-	RFI
+	/* Back to EE=1 */
+	mtmsr	r6
+	b	kvm_return_point
 
 call_linux_handler:
 
@@ -260,10 +254,16 @@ call_linux_handler:
 	 * interrupt handler!
 	 *
 	 * R3 still contains the exit code,
-	 * R6 VCPU_HOST_RETIP and
-	 * R7 VCPU_HOST_MSR
+	 * R5 VCPU_HOST_RETIP and
+	 * R6 VCPU_HOST_MSR
 	 */
 
+	/* Restore host IP -> SRR0 */
+	ld	r5, VCPU_HOST_RETIP(r7)
+
+	/* XXX Better move to a safe function?
+	 *     What if we get an HTAB flush in between mtsrr0 and mtsrr1? */
+
 	mtlr	r12
 
 	ld	r4, VCPU_TRAMPOLINE_LOWMEM(r7)
-- 
cgit v1.2.3


From 021ec9c69f8b7b20f46296cc76cc4cb341b25191 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 8 Jan 2010 02:58:06 +0100
Subject: KVM: PPC: Call SLB patching code in interrupt safe manner

Currently we're racy when doing the transition from IR=1 to IR=0, from
the module memory entry code to the real mode SLB switching code.

To work around that I took a look at the RTAS entry code which is faced
with a similar problem and did the same thing:

  A small helper in linear mapped memory that does mtmsr with IR=0 and
  then RFIs info the actual handler.

Thanks to that trick we can safely take page faults in the entry code
and only need to be really wary of what to do as of the SLB switching
part.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_book3s.h        |  1 +
 arch/powerpc/include/asm/kvm_book3s_64_asm.h |  1 -
 arch/powerpc/include/asm/kvm_host.h          |  1 +
 arch/powerpc/kernel/asm-offsets.c            |  3 +--
 arch/powerpc/kvm/book3s.c                    |  1 +
 arch/powerpc/kvm/book3s_64_exports.c         |  1 +
 arch/powerpc/kvm/book3s_64_interrupts.S      | 25 +++++++------------------
 arch/powerpc/kvm/book3s_64_rmhandlers.S      | 18 ++++++++++++++++++
 arch/powerpc/kvm/book3s_64_slb.S             |  4 ++++
 9 files changed, 34 insertions(+), 21 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index f192017d799..c91be0ff023 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -121,6 +121,7 @@ extern void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat,
 
 extern u32 kvmppc_trampoline_lowmem;
 extern u32 kvmppc_trampoline_enter;
+extern void kvmppc_rmcall(ulong srr0, ulong srr1);
 
 static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu)
 {
diff --git a/arch/powerpc/include/asm/kvm_book3s_64_asm.h b/arch/powerpc/include/asm/kvm_book3s_64_asm.h
index fca9404c1a7..183461b4840 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64_asm.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64_asm.h
@@ -69,7 +69,6 @@ struct kvmppc_book3s_shadow_vcpu {
 	ulong scratch0;
 	ulong scratch1;
 	ulong vmhandler;
-	ulong rmhandler;
 };
 
 #endif /*__ASSEMBLY__ */
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index d615fa8a141..f7215e622df 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -167,6 +167,7 @@ struct kvm_vcpu_arch {
 	ulong trampoline_lowmem;
 	ulong trampoline_enter;
 	ulong highmem_handler;
+	ulong rmcall;
 	ulong host_paca_phys;
 	struct kvmppc_mmu mmu;
 #endif
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 1501e77c980..ee9935442f0 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -214,8 +214,6 @@ int main(void)
 	DEFINE(PACA_KVM_HOST_R2, offsetof(struct paca_struct, shadow_vcpu.host_r2));
 	DEFINE(PACA_KVM_VMHANDLER, offsetof(struct paca_struct,
 					    shadow_vcpu.vmhandler));
-	DEFINE(PACA_KVM_RMHANDLER, offsetof(struct paca_struct,
-					    shadow_vcpu.rmhandler));
 	DEFINE(PACA_KVM_SCRATCH0, offsetof(struct paca_struct,
 					   shadow_vcpu.scratch0));
 	DEFINE(PACA_KVM_SCRATCH1, offsetof(struct paca_struct,
@@ -438,6 +436,7 @@ int main(void)
 	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));
 #else
 	DEFINE(VCPU_CR, offsetof(struct kvm_vcpu, arch.cr));
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 3e06eae3f2c..13173922b67 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -919,6 +919,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 	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;
 
 	vcpu->arch.shadow_msr = MSR_USER64;
 
diff --git a/arch/powerpc/kvm/book3s_64_exports.c b/arch/powerpc/kvm/book3s_64_exports.c
index 5b2db38ed86..99b07125c52 100644
--- a/arch/powerpc/kvm/book3s_64_exports.c
+++ b/arch/powerpc/kvm/book3s_64_exports.c
@@ -22,3 +22,4 @@
 
 EXPORT_SYMBOL_GPL(kvmppc_trampoline_enter);
 EXPORT_SYMBOL_GPL(kvmppc_trampoline_lowmem);
+EXPORT_SYMBOL_GPL(kvmppc_rmcall);
diff --git a/arch/powerpc/kvm/book3s_64_interrupts.S b/arch/powerpc/kvm/book3s_64_interrupts.S
index 3c0ba551307..33aef5345f6 100644
--- a/arch/powerpc/kvm/book3s_64_interrupts.S
+++ b/arch/powerpc/kvm/book3s_64_interrupts.S
@@ -95,17 +95,14 @@ kvm_start_entry:
 	ld	r3, VCPU_HIGHMEM_HANDLER(r4)
 	std	r3, PACA_KVM_VMHANDLER(r13)
 
-	ld	r3, VCPU_TRAMPOLINE_ENTER(r4)
-	std	r3, PACA_KVM_RMHANDLER(r13)
-
 kvm_start_lightweight:
 
 	ld	r9, VCPU_PC(r4)			/* r9 = vcpu->arch.pc */
 	ld	r10, VCPU_SHADOW_MSR(r4)	/* r10 = vcpu->arch.shadow_msr */
 
 	/* Load some guest state in the respective registers */
-	ld	r3, VCPU_CTR(r4)	/* r3 = vcpu->arch.ctr */
-	mtctr	r3			/* CTR = r3 */
+	ld	r5, VCPU_CTR(r4)	/* r5 = vcpu->arch.ctr */
+					/* will be swapped in by rmcall */
 
 	ld	r3, VCPU_LR(r4)		/* r3 = vcpu->arch.lr */
 	mtlr	r3			/* LR = r3 */
@@ -131,22 +128,14 @@ kvm_start_lightweight:
 
 no_dcbz32_on:
 
-	/* This sets the Magic value for the trampoline */
-
-	/* XXX this needs to move into a safe function, so we can
-	   be sure we don't get any interrupts */
-
-	li	r11, 1
-	stb	r11, PACA_KVM_IN_GUEST(r13)
-
-	ld	r3, PACA_KVM_RMHANDLER(r13)
-	mtsrr0	r3
+	ld	r6, VCPU_RMCALL(r4)
+	mtctr	r6
 
-	LOAD_REG_IMMEDIATE(r3, MSR_KERNEL & ~(MSR_IR | MSR_DR))
-	mtsrr1	r3
+	ld	r3, VCPU_TRAMPOLINE_ENTER(r4)
+	LOAD_REG_IMMEDIATE(r4, MSR_KERNEL & ~(MSR_IR | MSR_DR))
 
 	/* Jump to SLB patching handlder and into our guest */
-	RFI
+	bctr
 
 /*
  * This is the handler in module memory. It gets jumped at from the
diff --git a/arch/powerpc/kvm/book3s_64_rmhandlers.S b/arch/powerpc/kvm/book3s_64_rmhandlers.S
index 9ad1c2645d6..e7091c9459a 100644
--- a/arch/powerpc/kvm/book3s_64_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_64_rmhandlers.S
@@ -140,6 +140,24 @@ kvmppc_handler_lowmem_trampoline:
 	blr
 kvmppc_handler_lowmem_trampoline_end:
 
+/*
+ * Call a function in real mode
+ *
+ * Input Registers:
+ *
+ * R3 = function
+ * R4 = MSR
+ * R5 = CTR
+ *
+ */
+_GLOBAL(kvmppc_rmcall)
+	mtmsr	r4		/* Disable relocation, so mtsrr
+				   doesn't get interrupted */
+	mtctr	r5
+	mtsrr0	r3
+	mtsrr1	r4
+	RFI
+
 .global kvmppc_trampoline_lowmem
 kvmppc_trampoline_lowmem:
 	.long kvmppc_handler_lowmem_trampoline - _stext
diff --git a/arch/powerpc/kvm/book3s_64_slb.S b/arch/powerpc/kvm/book3s_64_slb.S
index d07b88617b2..35b76272218 100644
--- a/arch/powerpc/kvm/book3s_64_slb.S
+++ b/arch/powerpc/kvm/book3s_64_slb.S
@@ -63,6 +63,10 @@ kvmppc_handler_trampoline_enter:
 	mtsrr0	r9
 	mtsrr1	r10
 
+	/* Activate guest mode, so faults get handled by KVM */
+	li	r11, KVM_GUEST_MODE_GUEST
+	stb	r11, PACA_KVM_IN_GUEST(r13)
+
 	/* Remove LPAR shadow entries */
 
 #if SLB_NUM_BOLTED == 3
-- 
cgit v1.2.3


From 25a8a02d26a71c28e26417a3520c653c2d40af6b Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 8 Jan 2010 02:58:07 +0100
Subject: KVM: PPC: Emulate trap SRR1 flags properly

Book3S needs some flags in SRR1 to get to know details about an interrupt.

One such example is the trap instruction. It tells the guest kernel that
a program interrupt is due to a trap using a bit in SRR1.

This patch implements above behavior, making WARN_ON behave like WARN_ON.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_book3s.h | 1 +
 arch/powerpc/include/asm/kvm_ppc.h    | 2 +-
 arch/powerpc/include/asm/reg.h        | 4 ++++
 arch/powerpc/kvm/book3s.c             | 7 +++++--
 arch/powerpc/kvm/booke.c              | 3 ++-
 arch/powerpc/kvm/emulate.c            | 2 +-
 6 files changed, 14 insertions(+), 5 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index c91be0ff023..79ab8faf18e 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -91,6 +91,7 @@ struct kvmppc_vcpu_book3s {
 	u64 vsid_next;
 	u64 vsid_max;
 	int context_id;
+	ulong prog_flags; /* flags to inject when giving a 700 trap */
 };
 
 #define CONTEXT_HOST		0
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 89c5d79c347..09816da9e95 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -80,7 +80,7 @@ extern void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu);
 
 extern void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu);
 extern int kvmppc_core_pending_dec(struct kvm_vcpu *vcpu);
-extern void kvmppc_core_queue_program(struct kvm_vcpu *vcpu);
+extern void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags);
 extern void kvmppc_core_queue_dec(struct kvm_vcpu *vcpu);
 extern void kvmppc_core_dequeue_dec(struct kvm_vcpu *vcpu);
 extern void kvmppc_core_queue_external(struct kvm_vcpu *vcpu,
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index bc8dd53f718..5572e86223f 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -426,6 +426,10 @@
 #define   SRR1_WAKEMT		0x00280000 /* mtctrl */
 #define   SRR1_WAKEDEC		0x00180000 /* Decrementer interrupt */
 #define   SRR1_WAKETHERM	0x00100000 /* Thermal management interrupt */
+#define   SRR1_PROGFPE		0x00100000 /* Floating Point Enabled */
+#define   SRR1_PROGPRIV		0x00040000 /* Privileged instruction */
+#define   SRR1_PROGTRAP		0x00020000 /* Trap */
+#define   SRR1_PROGADDR		0x00010000 /* SRR0 contains subsequent addr */
 #define SPRN_HSRR0	0x13A	/* Save/Restore Register 0 */
 #define SPRN_HSRR1	0x13B	/* Save/Restore Register 1 */
 
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 13173922b67..66b5924e174 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -168,8 +168,9 @@ void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec)
 }
 
 
-void kvmppc_core_queue_program(struct kvm_vcpu *vcpu)
+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);
 }
 
@@ -198,6 +199,7 @@ int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu, unsigned int priority)
 {
 	int deliver = 1;
 	int vec = 0;
+	ulong flags = 0ULL;
 
 	switch (priority) {
 	case BOOK3S_IRQPRIO_DECREMENTER:
@@ -231,6 +233,7 @@ 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;
@@ -261,7 +264,7 @@ int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu, unsigned int priority)
 #endif
 
 	if (deliver)
-		kvmppc_inject_interrupt(vcpu, vec, 0ULL);
+		kvmppc_inject_interrupt(vcpu, vec, flags);
 
 	return deliver;
 }
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 338baf9f6b2..e283e44e9f1 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -82,8 +82,9 @@ static void kvmppc_booke_queue_irqprio(struct kvm_vcpu *vcpu,
 	set_bit(priority, &vcpu->arch.pending_exceptions);
 }
 
-void kvmppc_core_queue_program(struct kvm_vcpu *vcpu)
+void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags)
 {
+	/* BookE does flags in ESR, so ignore those we get here */
 	kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_PROGRAM);
 }
 
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index 04e317c1bbe..8b0ba0b69c2 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -154,7 +154,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 #else
 		vcpu->arch.esr |= ESR_PTR;
 #endif
-		kvmppc_core_queue_program(vcpu);
+		kvmppc_core_queue_program(vcpu, SRR1_PROGTRAP);
 		advance = 0;
 		break;
 
-- 
cgit v1.2.3


From d35feb26ef7e9fbef7643051be5f0773662b1f91 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 8 Jan 2010 02:58:08 +0100
Subject: KVM: PPC: Fix HID5 setting code

The code to unset HID5.dcbz32 is broken.
This patch makes it do the right rotate magic.

Signed-off-by: Alexander Graf <agraf@suse.de>
Reported-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kvm/book3s_64_interrupts.S | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/book3s_64_interrupts.S b/arch/powerpc/kvm/book3s_64_interrupts.S
index 33aef5345f6..2ff0b2137e6 100644
--- a/arch/powerpc/kvm/book3s_64_interrupts.S
+++ b/arch/powerpc/kvm/book3s_64_interrupts.S
@@ -177,8 +177,9 @@ kvmppc_handler_highmem:
 	rldicl.	r5, r5, 0, 63		/* CR = ((r5 & 1) == 0) */
 	beq	no_dcbz32_off
 
+	li	r4, 0
 	mfspr   r5,SPRN_HID5
-	rldimi  r5,r5,6,56
+	rldimi  r5,r4,6,56
 	mtspr   SPRN_HID5,r5
 
 no_dcbz32_off:
-- 
cgit v1.2.3


From ff1ca3f983c4180018dbf5e02f2af06f86ef6d03 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 8 Jan 2010 02:58:09 +0100
Subject: KVM: PPC: Pass program interrupt flags to the guest

When we need to reinject a program interrupt into the guest, we also need to
reinject the corresponding flags into the guest.

Signed-off-by: Alexander Graf <agraf@suse.de>
Reported-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kvm/book3s.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 66b5924e174..02861fda73d 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -633,6 +633,9 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	case BOOK3S_INTERRUPT_PROGRAM:
 	{
 		enum emulation_result er;
+		ulong flags;
+
+		flags = (vcpu->arch.shadow_msr & 0x1f0000ull);
 
 		if (vcpu->arch.msr & MSR_PR) {
 #ifdef EXIT_DEBUG
@@ -640,7 +643,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 #endif
 			if ((vcpu->arch.last_inst & 0xff0007ff) !=
 			    (INS_DCBZ & 0xfffffff7)) {
-				kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
+				kvmppc_core_queue_program(vcpu, flags);
 				r = RESUME_GUEST;
 				break;
 			}
@@ -655,7 +658,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		case EMULATE_FAIL:
 			printk(KERN_CRIT "%s: emulation at %lx failed (%08x)\n",
 			       __func__, vcpu->arch.pc, vcpu->arch.last_inst);
-			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
+			kvmppc_core_queue_program(vcpu, flags);
 			r = RESUME_GUEST;
 			break;
 		default:
-- 
cgit v1.2.3


From 5f2b105a1d6a137c8cfb2792b79128db965880a8 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Sun, 10 Jan 2010 03:27:32 +0100
Subject: KVM: PPC: Pass through program interrupts

When we get a program interrupt in guest kernel mode, we try to emulate the
instruction.

If that doesn't fail, we report to the user and try again - at the exact same
instruction pointer. So if the guest kernel really does trigger an invalid
instruction, we loop forever.

So let's better go and forward program exceptions to the guest when we don't
know the instruction we're supposed to emulate.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kvm/emulate.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index 8b0ba0b69c2..b905623735b 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -476,6 +476,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			advance = 0;
 			printk(KERN_ERR "Couldn't emulate instruction 0x%08x "
 			       "(op %d xop %d)\n", inst, get_op(inst), get_xop(inst));
+			kvmppc_core_queue_program(vcpu, 0);
 		}
 	}
 
-- 
cgit v1.2.3


From 4b5c9b7f9bdd76a3c860731db08bfc6758e96e29 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Sun, 10 Jan 2010 03:27:47 +0100
Subject: KVM: PPC: Make large pages work

An SLB entry contains two pieces of information related to size:

  1) PTE size
  2) SLB size

The L bit defines the PTE be "large" (usually means 16MB),
SLB_VSID_B_1T defines that the SLB should span 1 GB instead of the
default 256MB.

Apparently I messed things up and just put those two in one box,
shaked it heavily and came up with the current code which handles
large pages incorrectly, because it also treats large page SLB entries
as "1TB" segment entries.

This patch splits those two features apart, making Linux guests boot
even when they have > 256MB.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_book3s.h |  3 ++-
 arch/powerpc/kvm/book3s_64_mmu.c      | 10 ++++++----
 2 files changed, 8 insertions(+), 5 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 79ab8faf18e..c7db69f1e77 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -34,7 +34,8 @@ struct kvmppc_slb {
 	bool Ks;
 	bool Kp;
 	bool nx;
-	bool large;
+	bool large;	/* PTEs are 16MB */
+	bool tb;	/* 1TB segment */
 	bool class;
 };
 
diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c
index e4beeb371a7..512dcff7755 100644
--- a/arch/powerpc/kvm/book3s_64_mmu.c
+++ b/arch/powerpc/kvm/book3s_64_mmu.c
@@ -54,7 +54,7 @@ static struct kvmppc_slb *kvmppc_mmu_book3s_64_find_slbe(
 		if (!vcpu_book3s->slb[i].valid)
 			continue;
 
-		if (vcpu_book3s->slb[i].large)
+		if (vcpu_book3s->slb[i].tb)
 			cmp_esid = esid_1t;
 
 		if (vcpu_book3s->slb[i].esid == cmp_esid)
@@ -65,9 +65,10 @@ static struct kvmppc_slb *kvmppc_mmu_book3s_64_find_slbe(
 		eaddr, esid, esid_1t);
 	for (i = 0; i < vcpu_book3s->slb_nr; i++) {
 	    if (vcpu_book3s->slb[i].vsid)
-		dprintk("  %d: %c%c %llx %llx\n", i,
+		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);
 	}
@@ -84,7 +85,7 @@ static u64 kvmppc_mmu_book3s_64_ea_to_vp(struct kvm_vcpu *vcpu, gva_t eaddr,
 	if (!slb)
 		return 0;
 
-	if (slb->large)
+	if (slb->tb)
 		return (((u64)eaddr >> 12) & 0xfffffff) |
 		       (((u64)slb->vsid) << 28);
 
@@ -309,7 +310,8 @@ static void kvmppc_mmu_book3s_64_slbmte(struct kvm_vcpu *vcpu, u64 rs, u64 rb)
 	slbe = &vcpu_book3s->slb[slb_nr];
 
 	slbe->large = (rs & SLB_VSID_L) ? 1 : 0;
-	slbe->esid  = slbe->large ? esid_1t : esid;
+	slbe->tb    = (rs & SLB_VSID_B_1T) ? 1 : 0;
+	slbe->esid  = slbe->tb ? esid_1t : esid;
 	slbe->vsid  = rs >> 12;
 	slbe->valid = (rb & SLB_ESID_V) ? 1 : 0;
 	slbe->Ks    = (rs & SLB_VSID_KS) ? 1 : 0;
-- 
cgit v1.2.3


From d5e528136cda31a32ff7d1eaa8d06220eb443781 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 15 Jan 2010 14:49:10 +0100
Subject: KVM: PPC: Add helper functions to call real mode loaders

Linux contains quite some bits of code to load FPU, Altivec and VSX lazily for
a task. It calls those bits in real mode, coming from an interrupt handler.

For KVM we better reuse those, so let's wrap a bit of trampoline magic around
them and then we can call them from normal module code.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_book3s.h   |  3 +++
 arch/powerpc/kvm/book3s_64_exports.c    |  7 +++++++
 arch/powerpc/kvm/book3s_64_rmhandlers.S | 34 +++++++++++++++++++++++++++++++++
 3 files changed, 44 insertions(+)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index c7db69f1e77..e1b441cce41 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -124,6 +124,9 @@ extern void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat,
 extern u32 kvmppc_trampoline_lowmem;
 extern u32 kvmppc_trampoline_enter;
 extern void kvmppc_rmcall(ulong srr0, ulong srr1);
+extern void kvmppc_load_up_fpu(void);
+extern void kvmppc_load_up_altivec(void);
+extern void kvmppc_load_up_vsx(void);
 
 static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu)
 {
diff --git a/arch/powerpc/kvm/book3s_64_exports.c b/arch/powerpc/kvm/book3s_64_exports.c
index 99b07125c52..1dd5a1ddfd0 100644
--- a/arch/powerpc/kvm/book3s_64_exports.c
+++ b/arch/powerpc/kvm/book3s_64_exports.c
@@ -23,3 +23,10 @@
 EXPORT_SYMBOL_GPL(kvmppc_trampoline_enter);
 EXPORT_SYMBOL_GPL(kvmppc_trampoline_lowmem);
 EXPORT_SYMBOL_GPL(kvmppc_rmcall);
+EXPORT_SYMBOL_GPL(kvmppc_load_up_fpu);
+#ifdef CONFIG_ALTIVEC
+EXPORT_SYMBOL_GPL(kvmppc_load_up_altivec);
+#endif
+#ifdef CONFIG_VSX
+EXPORT_SYMBOL_GPL(kvmppc_load_up_vsx);
+#endif
diff --git a/arch/powerpc/kvm/book3s_64_rmhandlers.S b/arch/powerpc/kvm/book3s_64_rmhandlers.S
index e7091c9459a..c83c60ad96c 100644
--- a/arch/powerpc/kvm/book3s_64_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_64_rmhandlers.S
@@ -158,6 +158,40 @@ _GLOBAL(kvmppc_rmcall)
 	mtsrr1	r4
 	RFI
 
+/*
+ * Activate current's external feature (FPU/Altivec/VSX)
+ */
+#define define_load_up(what) 				\
+							\
+_GLOBAL(kvmppc_load_up_ ## what);			\
+	subi	r1, r1, INT_FRAME_SIZE;			\
+	mflr	r3;					\
+	std	r3, _LINK(r1);				\
+	mfmsr	r4;					\
+	std	r31, GPR3(r1);				\
+	mr	r31, r4;				\
+	li	r5, MSR_DR;				\
+	oris	r5, r5, MSR_EE@h;			\
+	andc	r4, r4, r5;				\
+	mtmsr	r4;					\
+							\
+	bl	.load_up_ ## what;			\
+							\
+	mtmsr	r31;					\
+	ld	r3, _LINK(r1);				\
+	ld	r31, GPR3(r1);				\
+	addi	r1, r1, INT_FRAME_SIZE;			\
+	mtlr	r3;					\
+	blr
+
+define_load_up(fpu)
+#ifdef CONFIG_ALTIVEC
+define_load_up(altivec)
+#endif
+#ifdef CONFIG_VSX
+define_load_up(vsx)
+#endif
+
 .global kvmppc_trampoline_lowmem
 kvmppc_trampoline_lowmem:
 	.long kvmppc_handler_lowmem_trampoline - _stext
-- 
cgit v1.2.3


From 180a34d2d3fda0151154f9cead4aab9dddd3d0c1 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 15 Jan 2010 14:49:11 +0100
Subject: KVM: PPC: Add support for FPU/Altivec/VSX

When our guest starts using either the FPU, Altivec or VSX we need to make
sure Linux knows about it and sneak into its process switching code
accordingly.

This patch makes accesses to the above parts of the system work inside the
VM.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_host.h |  14 ++-
 arch/powerpc/kvm/book3s.c           | 193 +++++++++++++++++++++++++++++++++++-
 2 files changed, 201 insertions(+), 6 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index f7215e622df..c30a70c6b93 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -172,9 +172,20 @@ struct kvm_vcpu_arch {
 	struct kvmppc_mmu mmu;
 #endif
 
-	u64 fpr[32];
 	ulong gpr[32];
 
+	u64 fpr[32];
+	u32 fpscr;
+
+#ifdef CONFIG_ALTIVEC
+	vector128 vr[32];
+	vector128 vscr;
+#endif
+
+#ifdef CONFIG_VSX
+	u64 vsr[32];
+#endif
+
 	ulong pc;
 	ulong ctr;
 	ulong lr;
@@ -188,6 +199,7 @@ struct kvm_vcpu_arch {
 #ifdef CONFIG_PPC64
 	ulong shadow_msr;
 	ulong hflags;
+	ulong guest_owned_ext;
 #endif
 	u32 mmucr;
 	ulong sprg0;
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 02861fda73d..2cb181396f8 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -33,6 +33,9 @@
 
 /* #define EXIT_DEBUG */
 /* #define EXIT_DEBUG_SIMPLE */
+/* #define DEBUG_EXT */
+
+static void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr);
 
 struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "exits",       VCPU_STAT(sum_exits) },
@@ -77,6 +80,10 @@ void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
 	memcpy(&to_book3s(vcpu)->shadow_vcpu, &get_paca()->shadow_vcpu,
 	       sizeof(get_paca()->shadow_vcpu));
 	to_book3s(vcpu)->slb_shadow_max = get_paca()->kvm_slb_max;
+
+	kvmppc_giveup_ext(vcpu, MSR_FP);
+	kvmppc_giveup_ext(vcpu, MSR_VEC);
+	kvmppc_giveup_ext(vcpu, MSR_VSX);
 }
 
 #if defined(EXIT_DEBUG)
@@ -97,9 +104,9 @@ void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
 	msr &= to_book3s(vcpu)->msr_mask;
 	vcpu->arch.msr = msr;
 	vcpu->arch.shadow_msr = msr | MSR_USER32;
-	vcpu->arch.shadow_msr &= ( MSR_VEC | MSR_VSX | MSR_FP | MSR_FE0 |
-				   MSR_USER64 | MSR_SE | MSR_BE | MSR_DE |
-				   MSR_FE1);
+	vcpu->arch.shadow_msr &= (MSR_FE0 | MSR_USER64 | MSR_SE | MSR_BE |
+				  MSR_DE | MSR_FE1);
+	vcpu->arch.shadow_msr |= (msr & vcpu->arch.guest_owned_ext);
 
 	if (msr & (MSR_WE|MSR_POW)) {
 		if (!vcpu->arch.pending_exceptions) {
@@ -551,6 +558,117 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	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) */
+static void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr)
+{
+	struct thread_struct *t = &current->thread;
+	u64 *vcpu_fpr = vcpu->arch.fpr;
+	u64 *vcpu_vsx = vcpu->arch.vsr;
+	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_set_msr(vcpu, vcpu->arch.msr);
+}
+
+/* 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;
+	u64 *vcpu_vsx = vcpu->arch.vsr;
+	u64 *thread_fpr = (u64*)t->fpr;
+	int i;
+
+	if (!(vcpu->arch.msr & msr)) {
+		kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
+		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_set_msr(vcpu, vcpu->arch.msr);
+
+	return RESUME_GUEST;
+}
+
 int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
                        unsigned int exit_nr)
 {
@@ -674,11 +792,17 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
 		r = RESUME_GUEST;
 		break;
-	case BOOK3S_INTERRUPT_MACHINE_CHECK:
 	case BOOK3S_INTERRUPT_FP_UNAVAIL:
-	case BOOK3S_INTERRUPT_TRACE:
+		r = kvmppc_handle_ext(vcpu, exit_nr, MSR_FP);
+		break;
 	case BOOK3S_INTERRUPT_ALTIVEC:
+		r = kvmppc_handle_ext(vcpu, exit_nr, MSR_VEC);
+		break;
 	case BOOK3S_INTERRUPT_VSX:
+		r = kvmppc_handle_ext(vcpu, exit_nr, MSR_VSX);
+		break;
+	case BOOK3S_INTERRUPT_MACHINE_CHECK:
+	case BOOK3S_INTERRUPT_TRACE:
 		kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
 		r = RESUME_GUEST;
 		break;
@@ -959,6 +1083,10 @@ 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;
+	struct thread_struct ext_bkp;
+	bool save_vec = current->thread.used_vr;
+	bool save_vsx = current->thread.used_vsr;
+	ulong ext_msr;
 
 	/* No need to go into the guest when all we do is going out */
 	if (signal_pending(current)) {
@@ -966,6 +1094,35 @@ int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 		return -EINTR;
 	}
 
+	/* Save FPU state in stack */
+	if (current->thread.regs->msr & MSR_FP)
+		giveup_fpu(current);
+	memcpy(ext_bkp.fpr, current->thread.fpr, sizeof(current->thread.fpr));
+	ext_bkp.fpscr = current->thread.fpscr;
+	ext_bkp.fpexc_mode = current->thread.fpexc_mode;
+
+#ifdef CONFIG_ALTIVEC
+	/* Save Altivec state in stack */
+	if (save_vec) {
+		if (current->thread.regs->msr & MSR_VEC)
+			giveup_altivec(current);
+		memcpy(ext_bkp.vr, current->thread.vr, sizeof(ext_bkp.vr));
+		ext_bkp.vscr = current->thread.vscr;
+		ext_bkp.vrsave = current->thread.vrsave;
+	}
+	ext_bkp.used_vr = current->thread.used_vr;
+#endif
+
+#ifdef CONFIG_VSX
+	/* Save VSX state in stack */
+	if (save_vsx && (current->thread.regs->msr & MSR_VSX))
+			__giveup_vsx(current);
+	ext_bkp.used_vsr = current->thread.used_vsr;
+#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();
 
@@ -973,6 +1130,32 @@ int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *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, ext_bkp.fpr, sizeof(ext_bkp.fpr));
+	current->thread.fpscr = ext_bkp.fpscr;
+	current->thread.fpexc_mode = ext_bkp.fpexc_mode;
+
+#ifdef CONFIG_ALTIVEC
+	/* Restore Altivec state from stack */
+	if (save_vec && current->thread.used_vr) {
+		memcpy(current->thread.vr, ext_bkp.vr, sizeof(ext_bkp.vr));
+		current->thread.vscr = ext_bkp.vscr;
+		current->thread.vrsave= ext_bkp.vrsave;
+	}
+	current->thread.used_vr = ext_bkp.used_vr;
+#endif
+
+#ifdef CONFIG_VSX
+	current->thread.used_vsr = ext_bkp.used_vsr;
+#endif
+
 	return ret;
 }
 
-- 
cgit v1.2.3


From f7adbba1e5d464b0d449adac1eb2519be6be9728 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 15 Jan 2010 14:49:13 +0100
Subject: KVM: PPC: Keep SRR1 flags around in shadow_msr

SRR1 stores more information that just the MSR value. It also stores
valuable information about the type of interrupt we received, for
example whether the storage interrupt we just got was because of a
missing htab entry or not.

We use that information to speed up the exit path.

Now if we get preempted before we can interpret the shadow_msr values,
we get into vcpu_put which then calls the MSR handler, which then sets
all the SRR1 information bits in shadow_msr to 0. Great.

So let's preserve the SRR1 specific bits in shadow_msr whenever we set
the MSR. They don't hurt.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_host.h     |  1 +
 arch/powerpc/kernel/asm-offsets.c       |  1 +
 arch/powerpc/kvm/book3s.c               | 13 +++++++------
 arch/powerpc/kvm/book3s_64_interrupts.S |  2 +-
 4 files changed, 10 insertions(+), 7 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index c30a70c6b93..715aa6baf6f 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -198,6 +198,7 @@ struct kvm_vcpu_arch {
 	ulong msr;
 #ifdef CONFIG_PPC64
 	ulong shadow_msr;
+	ulong shadow_srr1;
 	ulong hflags;
 	ulong guest_owned_ext;
 #endif
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index ee9935442f0..957ceb7059c 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -433,6 +433,7 @@ int main(void)
 	DEFINE(VCPU_HOST_R2, offsetof(struct kvm_vcpu, arch.host_r2));
 	DEFINE(VCPU_HOST_MSR, offsetof(struct kvm_vcpu, arch.host_msr));
 	DEFINE(VCPU_SHADOW_MSR, offsetof(struct kvm_vcpu, arch.shadow_msr));
+	DEFINE(VCPU_SHADOW_SRR1, offsetof(struct kvm_vcpu, arch.shadow_srr1));
 	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));
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 2cb181396f8..58f5200fc09 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -524,14 +524,14 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		/* Page not found in guest PTE entries */
 		vcpu->arch.dear = vcpu->arch.fault_dear;
 		to_book3s(vcpu)->dsisr = vcpu->arch.fault_dsisr;
-		vcpu->arch.msr |= (vcpu->arch.shadow_msr & 0x00000000f8000000ULL);
+		vcpu->arch.msr |= (vcpu->arch.shadow_srr1 & 0x00000000f8000000ULL);
 		kvmppc_book3s_queue_irqprio(vcpu, vec);
 	} else if (page_found == -EPERM) {
 		/* Storage protection */
 		vcpu->arch.dear = vcpu->arch.fault_dear;
 		to_book3s(vcpu)->dsisr = vcpu->arch.fault_dsisr & ~DSISR_NOHPTE;
 		to_book3s(vcpu)->dsisr |= DSISR_PROTFAULT;
-		vcpu->arch.msr |= (vcpu->arch.shadow_msr & 0x00000000f8000000ULL);
+		vcpu->arch.msr |= (vcpu->arch.shadow_srr1 & 0x00000000f8000000ULL);
 		kvmppc_book3s_queue_irqprio(vcpu, vec);
 	} else if (page_found == -EINVAL) {
 		/* Page not found in guest SLB */
@@ -693,7 +693,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	case BOOK3S_INTERRUPT_INST_STORAGE:
 		vcpu->stat.pf_instruc++;
 		/* only care about PTEG not found errors, but leave NX alone */
-		if (vcpu->arch.shadow_msr & 0x40000000) {
+		if (vcpu->arch.shadow_srr1 & 0x40000000) {
 			r = kvmppc_handle_pagefault(run, vcpu, vcpu->arch.pc, exit_nr);
 			vcpu->stat.sp_instruc++;
 		} else if (vcpu->arch.mmu.is_dcbz32(vcpu) &&
@@ -705,7 +705,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			 */
 			kvmppc_mmu_pte_flush(vcpu, vcpu->arch.pc, ~0xFFFULL);
 		} else {
-			vcpu->arch.msr |= (vcpu->arch.shadow_msr & 0x58000000);
+			vcpu->arch.msr |= vcpu->arch.shadow_srr1 & 0x58000000;
 			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
 			kvmppc_mmu_pte_flush(vcpu, vcpu->arch.pc, ~0xFFFULL);
 			r = RESUME_GUEST;
@@ -753,7 +753,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		enum emulation_result er;
 		ulong flags;
 
-		flags = (vcpu->arch.shadow_msr & 0x1f0000ull);
+		flags = vcpu->arch.shadow_srr1 & 0x1f0000ull;
 
 		if (vcpu->arch.msr & MSR_PR) {
 #ifdef EXIT_DEBUG
@@ -808,7 +808,8 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		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, vcpu->arch.pc, vcpu->arch.shadow_msr);
+		printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | msr=0x%lx\n",
+			exit_nr, vcpu->arch.pc, vcpu->arch.shadow_srr1);
 		r = RESUME_HOST;
 		BUG();
 		break;
diff --git a/arch/powerpc/kvm/book3s_64_interrupts.S b/arch/powerpc/kvm/book3s_64_interrupts.S
index 2ff0b2137e6..c1584d0cbce 100644
--- a/arch/powerpc/kvm/book3s_64_interrupts.S
+++ b/arch/powerpc/kvm/book3s_64_interrupts.S
@@ -169,7 +169,7 @@ kvmppc_handler_highmem:
 	stw	r0, VCPU_LAST_INST(r7)
 
 	std	r3, VCPU_PC(r7)
-	std	r4, VCPU_SHADOW_MSR(r7)
+	std	r4, VCPU_SHADOW_SRR1(r7)
 	std	r5, VCPU_FAULT_DEAR(r7)
 	std	r6, VCPU_FAULT_DSISR(r7)
 
-- 
cgit v1.2.3


From a76f8497fd475028869f4b45087d80df14d74a50 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 15 Jan 2010 14:49:14 +0100
Subject: KVM: PPC: Move Shadow MSR calculation to function

We keep a copy of the MSR around that we use when we go into the guest context.

That copy is basically the normal process MSR flags OR some allowed guest
specified MSR flags. We also AND the external providers into this, so we get
traps on FPU usage when we haven't activated it on the host yet.

Currently this calculation is part of the set_msr function that we use whenever
we set the guest MSR value. With the external providers, we also have the case
that we don't modify the guest's MSR, but only want to update the shadow MSR.

So let's move the shadow MSR parts to a separate function that we then use
whenever we only need to update it. That way we don't accidently kvm_vcpu_block
within a preempt notifier context.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kvm/book3s.c | 27 +++++++++++++++++++++------
 1 file changed, 21 insertions(+), 6 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 58f5200fc09..9a271f0929c 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -94,6 +94,23 @@ static u32 kvmppc_get_dec(struct kvm_vcpu *vcpu)
 }
 #endif
 
+static void kvmppc_recalc_shadow_msr(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.shadow_msr = vcpu->arch.msr;
+	/* Guest MSR values */
+	vcpu->arch.shadow_msr &= MSR_FE0 | MSR_FE1 | MSR_SF | MSR_SE |
+				 MSR_BE | MSR_DE;
+	/* Process MSR values */
+	vcpu->arch.shadow_msr |= MSR_ME | MSR_RI | MSR_IR | MSR_DR | MSR_PR |
+				 MSR_EE;
+	/* External providers the guest reserved */
+	vcpu->arch.shadow_msr |= (vcpu->arch.msr & vcpu->arch.guest_owned_ext);
+	/* 64-bit Process MSR values */
+#ifdef CONFIG_PPC_BOOK3S_64
+	vcpu->arch.shadow_msr |= MSR_ISF | MSR_HV;
+#endif
+}
+
 void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
 {
 	ulong old_msr = vcpu->arch.msr;
@@ -101,12 +118,10 @@ void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
 #ifdef EXIT_DEBUG
 	printk(KERN_INFO "KVM: Set MSR to 0x%llx\n", msr);
 #endif
+
 	msr &= to_book3s(vcpu)->msr_mask;
 	vcpu->arch.msr = msr;
-	vcpu->arch.shadow_msr = msr | MSR_USER32;
-	vcpu->arch.shadow_msr &= (MSR_FE0 | MSR_USER64 | MSR_SE | MSR_BE |
-				  MSR_DE | MSR_FE1);
-	vcpu->arch.shadow_msr |= (msr & vcpu->arch.guest_owned_ext);
+	kvmppc_recalc_shadow_msr(vcpu);
 
 	if (msr & (MSR_WE|MSR_POW)) {
 		if (!vcpu->arch.pending_exceptions) {
@@ -610,7 +625,7 @@ static void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr)
 
 	vcpu->arch.guest_owned_ext &= ~msr;
 	current->thread.regs->msr &= ~msr;
-	kvmppc_set_msr(vcpu, vcpu->arch.msr);
+	kvmppc_recalc_shadow_msr(vcpu);
 }
 
 /* Handle external providers (FPU, Altivec, VSX) */
@@ -664,7 +679,7 @@ static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
 
 	vcpu->arch.guest_owned_ext |= msr;
 
-	kvmppc_set_msr(vcpu, vcpu->arch.msr);
+	kvmppc_recalc_shadow_msr(vcpu);
 
 	return RESUME_GUEST;
 }
-- 
cgit v1.2.3


From 647492047763c3ee8fe51ecf9a04f39040aa495b Mon Sep 17 00:00:00 2001
From: Marcelo Tosatti <mtosatti@redhat.com>
Date: Tue, 19 Jan 2010 12:45:23 -0200
Subject: KVM: fix cleanup_srcu_struct on vm destruction

cleanup_srcu_struct on VM destruction remains broken:

BUG: unable to handle kernel paging request at ffffffffffffffff
IP: [<ffffffff802533d2>] srcu_read_lock+0x16/0x21
RIP: 0010:[<ffffffff802533d2>]  [<ffffffff802533d2>] srcu_read_lock+0x16/0x21
Call Trace:
 [<ffffffffa05354c4>] kvm_arch_vcpu_uninit+0x1b/0x48 [kvm]
 [<ffffffffa05339c6>] kvm_vcpu_uninit+0x9/0x15 [kvm]
 [<ffffffffa0569f7d>] vmx_free_vcpu+0x7f/0x8f [kvm_intel]
 [<ffffffffa05357b5>] kvm_arch_destroy_vm+0x78/0x111 [kvm]
 [<ffffffffa053315b>] kvm_put_kvm+0xd4/0xfe [kvm]

Move it to kvm_arch_destroy_vm.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Reported-by: Jan Kiszka <jan.kiszka@siemens.com>
---
 arch/ia64/kvm/kvm-ia64.c   | 1 +
 arch/powerpc/kvm/powerpc.c | 1 +
 arch/s390/kvm/kvm-s390.c   | 1 +
 arch/x86/kvm/x86.c         | 1 +
 virt/kvm/kvm_main.c        | 1 -
 5 files changed, 4 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index e6ac549f8d5..06188988ed2 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -1404,6 +1404,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	kfree(kvm->arch.vioapic);
 	kvm_release_vm_pages(kvm);
 	kvm_free_physmem(kvm);
+	cleanup_srcu_struct(&kvm->srcu);
 	free_kvm(kvm);
 }
 
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 2c291161df8..51aedd7f16b 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -137,6 +137,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 {
 	kvmppc_free_vcpus(kvm);
 	kvm_free_physmem(kvm);
+	cleanup_srcu_struct(&kvm->srcu);
 	kfree(kvm);
 }
 
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index c8002193d9d..49292869a5c 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -242,6 +242,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	kvm_free_physmem(kvm);
 	free_page((unsigned long)(kvm->arch.sca));
 	debug_unregister(kvm->arch.dbf);
+	cleanup_srcu_struct(&kvm->srcu);
 	kfree(kvm);
 }
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9b0758b4d55..322c2c5f9bc 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5547,6 +5547,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 		put_page(kvm->arch.apic_access_page);
 	if (kvm->arch.ept_identity_pagetable)
 		put_page(kvm->arch.ept_identity_pagetable);
+	cleanup_srcu_struct(&kvm->srcu);
 	kfree(kvm->arch.aliases);
 	kfree(kvm);
 }
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 2b7cd6c0d9c..7c5c873812f 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -506,7 +506,6 @@ static void kvm_destroy_vm(struct kvm *kvm)
 #else
 	kvm_arch_flush_shadow(kvm);
 #endif
-	cleanup_srcu_struct(&kvm->srcu);
 	kvm_arch_destroy_vm(kvm);
 	hardware_disable_all();
 	mmdrop(mm);
-- 
cgit v1.2.3


From d86be077a4d62e5615e97674dab8d894ce582b09 Mon Sep 17 00:00:00 2001
From: Liu Yu <yu.liu@freescale.com>
Date: Fri, 22 Jan 2010 18:50:29 +0800
Subject: KVM: PPC E500: Add register l1csr0 emulation

Latest kernel start to access l1csr0 to contron L1.
We just tell guest no operation is on going.

Signed-off-by: Liu Yu <yu.liu@freescale.com>
Acked-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/powerpc/include/asm/kvm_e500.h | 1 +
 arch/powerpc/kvm/e500_emulate.c     | 6 ++++++
 2 files changed, 7 insertions(+)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_e500.h b/arch/powerpc/include/asm/kvm_e500.h
index 9d497ce4972..569dfd31ee7 100644
--- a/arch/powerpc/include/asm/kvm_e500.h
+++ b/arch/powerpc/include/asm/kvm_e500.h
@@ -52,6 +52,7 @@ struct kvmppc_vcpu_e500 {
 	u32 mas5;
 	u32 mas6;
 	u32 mas7;
+	u32 l1csr0;
 	u32 l1csr1;
 	u32 hid0;
 	u32 hid1;
diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c
index 7644f7a9bac..95f8ec8fdc7 100644
--- a/arch/powerpc/kvm/e500_emulate.c
+++ b/arch/powerpc/kvm/e500_emulate.c
@@ -99,6 +99,10 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 		vcpu_e500->mas6 = spr_val; break;
 	case SPRN_MAS7:
 		vcpu_e500->mas7 = spr_val; break;
+	case SPRN_L1CSR0:
+		vcpu_e500->l1csr0 = spr_val;
+		vcpu_e500->l1csr0 &= ~(L1CSR0_DCFI | L1CSR0_CLFC);
+		break;
 	case SPRN_L1CSR1:
 		vcpu_e500->l1csr1 = spr_val; break;
 	case SPRN_HID0:
@@ -179,6 +183,8 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 		break;
 	}
 
+	case SPRN_L1CSR0:
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->l1csr0); break;
 	case SPRN_L1CSR1:
 		kvmppc_set_gpr(vcpu, rt, vcpu_e500->l1csr1); break;
 	case SPRN_HID0:
-- 
cgit v1.2.3


From a9040f274285c3c962a08b177ac5764b4a93df07 Mon Sep 17 00:00:00 2001
From: Liu Yu <yu.liu@freescale.com>
Date: Fri, 22 Jan 2010 18:50:30 +0800
Subject: KVM: PPC: Add PVR/PIR init for E500

commit 513579e3a391a3874c478a8493080822069976e8 change the way
we emulate PVR/PIR,
which left PVR/PIR uninitialized on E500, and make guest puzzled.

Signed-off-by: Liu Yu <yu.liu@freescale.com>
Acked-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/powerpc/kvm/e500.c | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c
index 64949eef43f..efa1198940a 100644
--- a/arch/powerpc/kvm/e500.c
+++ b/arch/powerpc/kvm/e500.c
@@ -60,6 +60,12 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
 
 	kvmppc_e500_tlb_setup(vcpu_e500);
 
+	/* Registers init */
+	vcpu->arch.pvr = mfspr(SPRN_PVR);
+
+	/* Since booke kvm only support one core, update all vcpus' PIR to 0 */
+	vcpu->vcpu_id = 0;
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From da15bf436bc9586603b47b39244157431fa38b56 Mon Sep 17 00:00:00 2001
From: Liu Yu <yu.liu@freescale.com>
Date: Fri, 22 Jan 2010 19:36:53 +0800
Subject: KVM: PPC E500: fix tlbcfg emulation

commit 55fb1027c1cf9797dbdeab48180da530e81b1c39 doesn't update tlbcfg correctly.
Fix it.

And since guest OS likes 'fixed' hardware,
initialize tlbcfg everytime when guest access is useless.
So move this part to init code.

Signed-off-by: Liu Yu <yu.liu@freescale.com>
Acked-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
---
 arch/powerpc/include/asm/kvm_e500.h |  2 ++
 arch/powerpc/kvm/e500_emulate.c     | 20 ++------------------
 arch/powerpc/kvm/e500_tlb.c         |  6 ++++++
 3 files changed, 10 insertions(+), 18 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_e500.h b/arch/powerpc/include/asm/kvm_e500.h
index 569dfd31ee7..7fea26fffb2 100644
--- a/arch/powerpc/include/asm/kvm_e500.h
+++ b/arch/powerpc/include/asm/kvm_e500.h
@@ -56,6 +56,8 @@ struct kvmppc_vcpu_e500 {
 	u32 l1csr1;
 	u32 hid0;
 	u32 hid1;
+	u32 tlb0cfg;
+	u32 tlb1cfg;
 
 	struct kvm_vcpu vcpu;
 };
diff --git a/arch/powerpc/kvm/e500_emulate.c b/arch/powerpc/kvm/e500_emulate.c
index 95f8ec8fdc7..8e3edfbc963 100644
--- a/arch/powerpc/kvm/e500_emulate.c
+++ b/arch/powerpc/kvm/e500_emulate.c
@@ -164,25 +164,9 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 		kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas7); break;
 
 	case SPRN_TLB0CFG:
-	{
-		ulong tmp = SPRN_TLB0CFG;
-
-		tmp &= ~0xfffUL;
-		tmp |= vcpu_e500->guest_tlb_size[0];
-		kvmppc_set_gpr(vcpu, rt, tmp);
-		break;
-	}
-
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->tlb0cfg); break;
 	case SPRN_TLB1CFG:
-	{
-		ulong tmp = SPRN_TLB1CFG;
-
-		tmp &= ~0xfffUL;
-		tmp |= vcpu_e500->guest_tlb_size[1];
-		kvmppc_set_gpr(vcpu, rt, tmp);
-		break;
-	}
-
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->tlb1cfg); break;
 	case SPRN_L1CSR0:
 		kvmppc_set_gpr(vcpu, rt, vcpu_e500->l1csr0); break;
 	case SPRN_L1CSR1:
diff --git a/arch/powerpc/kvm/e500_tlb.c b/arch/powerpc/kvm/e500_tlb.c
index 6a7fc012b93..0d772e6b631 100644
--- a/arch/powerpc/kvm/e500_tlb.c
+++ b/arch/powerpc/kvm/e500_tlb.c
@@ -728,6 +728,12 @@ int kvmppc_e500_tlb_init(struct kvmppc_vcpu_e500 *vcpu_e500)
 	if (vcpu_e500->shadow_pages[1] == NULL)
 		goto err_out_page0;
 
+	/* Init TLB configuration register */
+	vcpu_e500->tlb0cfg = mfspr(SPRN_TLB0CFG) & ~0xfffUL;
+	vcpu_e500->tlb0cfg |= vcpu_e500->guest_tlb_size[0];
+	vcpu_e500->tlb1cfg = mfspr(SPRN_TLB1CFG) & ~0xfffUL;
+	vcpu_e500->tlb1cfg |= vcpu_e500->guest_tlb_size[1];
+
 	return 0;
 
 err_out_page0:
-- 
cgit v1.2.3


From daf5e27109c8c16c987e955cc6abbbc0af050edd Mon Sep 17 00:00:00 2001
From: Liu Yu <yu.liu@freescale.com>
Date: Tue, 2 Feb 2010 19:44:35 +0800
Subject: KVM: ppc/booke: Set ESR and DEAR when inject interrupt to guest

Old method prematurely sets ESR and DEAR.
Move this part after we decide to inject interrupt,
which is more like hardware behave.

Signed-off-by: Liu Yu <yu.liu@freescale.com>
Acked-by: Hollis Blanchard <hollis@penguinppc.org>
Acked-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_host.h |  2 ++
 arch/powerpc/kvm/booke.c            | 59 +++++++++++++++++++++++++++----------
 arch/powerpc/kvm/emulate.c          |  4 +--
 3 files changed, 48 insertions(+), 17 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 715aa6baf6f..5e5bae7e152 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -259,6 +259,8 @@ struct kvm_vcpu_arch {
 #endif
 	ulong fault_dear;
 	ulong fault_esr;
+	ulong queued_dear;
+	ulong queued_esr;
 	gpa_t paddr_accessed;
 
 	u8 io_gpr; /* GPR used as IO source/target */
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index e283e44e9f1..4d686cc6b26 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -82,9 +82,32 @@ static void kvmppc_booke_queue_irqprio(struct kvm_vcpu *vcpu,
 	set_bit(priority, &vcpu->arch.pending_exceptions);
 }
 
-void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags)
+static void kvmppc_core_queue_dtlb_miss(struct kvm_vcpu *vcpu,
+                                        ulong dear_flags, ulong esr_flags)
 {
-	/* BookE does flags in ESR, so ignore those we get here */
+	vcpu->arch.queued_dear = dear_flags;
+	vcpu->arch.queued_esr = esr_flags;
+	kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_DTLB_MISS);
+}
+
+static void kvmppc_core_queue_data_storage(struct kvm_vcpu *vcpu,
+                                           ulong dear_flags, ulong esr_flags)
+{
+	vcpu->arch.queued_dear = dear_flags;
+	vcpu->arch.queued_esr = esr_flags;
+	kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_DATA_STORAGE);
+}
+
+static void kvmppc_core_queue_inst_storage(struct kvm_vcpu *vcpu,
+                                           ulong esr_flags)
+{
+	vcpu->arch.queued_esr = esr_flags;
+	kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_INST_STORAGE);
+}
+
+void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong esr_flags)
+{
+	vcpu->arch.queued_esr = esr_flags;
 	kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_PROGRAM);
 }
 
@@ -115,14 +138,19 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 {
 	int allowed = 0;
 	ulong msr_mask;
+	bool update_esr = false, update_dear = false;
 
 	switch (priority) {
-	case BOOKE_IRQPRIO_PROGRAM:
 	case BOOKE_IRQPRIO_DTLB_MISS:
-	case BOOKE_IRQPRIO_ITLB_MISS:
-	case BOOKE_IRQPRIO_SYSCALL:
 	case BOOKE_IRQPRIO_DATA_STORAGE:
+		update_dear = true;
+		/* fall through */
 	case BOOKE_IRQPRIO_INST_STORAGE:
+	case BOOKE_IRQPRIO_PROGRAM:
+		update_esr = true;
+		/* fall through */
+	case BOOKE_IRQPRIO_ITLB_MISS:
+	case BOOKE_IRQPRIO_SYSCALL:
 	case BOOKE_IRQPRIO_FP_UNAVAIL:
 	case BOOKE_IRQPRIO_SPE_UNAVAIL:
 	case BOOKE_IRQPRIO_SPE_FP_DATA:
@@ -157,6 +185,10 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 		vcpu->arch.srr0 = vcpu->arch.pc;
 		vcpu->arch.srr1 = vcpu->arch.msr;
 		vcpu->arch.pc = vcpu->arch.ivpr | vcpu->arch.ivor[priority];
+		if (update_esr == true)
+			vcpu->arch.esr = vcpu->arch.queued_esr;
+		if (update_dear == true)
+			vcpu->arch.dear = vcpu->arch.queued_dear;
 		kvmppc_set_msr(vcpu, vcpu->arch.msr & msr_mask);
 
 		clear_bit(priority, &vcpu->arch.pending_exceptions);
@@ -229,8 +261,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		if (vcpu->arch.msr & MSR_PR) {
 			/* Program traps generated by user-level software must be handled
 			 * by the guest kernel. */
-			vcpu->arch.esr = vcpu->arch.fault_esr;
-			kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_PROGRAM);
+			kvmppc_core_queue_program(vcpu, vcpu->arch.fault_esr);
 			r = RESUME_GUEST;
 			kvmppc_account_exit(vcpu, USR_PR_INST);
 			break;
@@ -286,16 +317,14 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		break;
 
 	case BOOKE_INTERRUPT_DATA_STORAGE:
-		vcpu->arch.dear = vcpu->arch.fault_dear;
-		vcpu->arch.esr = vcpu->arch.fault_esr;
-		kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_DATA_STORAGE);
+		kvmppc_core_queue_data_storage(vcpu, vcpu->arch.fault_dear,
+		                               vcpu->arch.fault_esr);
 		kvmppc_account_exit(vcpu, DSI_EXITS);
 		r = RESUME_GUEST;
 		break;
 
 	case BOOKE_INTERRUPT_INST_STORAGE:
-		vcpu->arch.esr = vcpu->arch.fault_esr;
-		kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_INST_STORAGE);
+		kvmppc_core_queue_inst_storage(vcpu, vcpu->arch.fault_esr);
 		kvmppc_account_exit(vcpu, ISI_EXITS);
 		r = RESUME_GUEST;
 		break;
@@ -316,9 +345,9 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		gtlb_index = kvmppc_mmu_dtlb_index(vcpu, eaddr);
 		if (gtlb_index < 0) {
 			/* The guest didn't have a mapping for it. */
-			kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_DTLB_MISS);
-			vcpu->arch.dear = vcpu->arch.fault_dear;
-			vcpu->arch.esr = vcpu->arch.fault_esr;
+			kvmppc_core_queue_dtlb_miss(vcpu,
+			                            vcpu->arch.fault_dear,
+			                            vcpu->arch.fault_esr);
 			kvmppc_mmu_dtlb_miss(vcpu);
 			kvmppc_account_exit(vcpu, DTLB_REAL_MISS_EXITS);
 			r = RESUME_GUEST;
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index b905623735b..cb72a65f4ec 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -151,10 +151,10 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	case OP_TRAP:
 #ifdef CONFIG_PPC64
 	case OP_TRAP_64:
+		kvmppc_core_queue_program(vcpu, SRR1_PROGTRAP);
 #else
-		vcpu->arch.esr |= ESR_PTR;
+		kvmppc_core_queue_program(vcpu, vcpu->arch.esr | ESR_PTR);
 #endif
-		kvmppc_core_queue_program(vcpu, SRR1_PROGTRAP);
 		advance = 0;
 		break;
 
-- 
cgit v1.2.3